1 files changed, 1 insertions, 4 deletions
diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c
index 67ebff829cf2..3068802824b7 100644
--- a/arch/arm/mach-omap2/clockdomains7xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains7xx_data.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * DRA7xx Clock domains framework
  *
@@ -14,10 +15,6 @@
  * with the public linux-omap@vger.kernel.org mailing list and the
  * authors above to ensure that the autogeneration scripts are kept
  * up-to-date with the file contents.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore
new file mode 100644
index 000000000000..cca6d870f7a5
--- /dev/null
+++ b/.get_maintainer.ignore
@@ -0,0 +1 @@
+Christoph Hellwig <hch@lst.de>
diff --git a/.gitignore b/.gitignore
index 4ad4a98b884b..17fa24dd7e46 100644
--- a/.gitignore
+++ b/.gitignore
@@ -97,6 +97,7 @@ GTAGS
 # Leavings from module signing
 #
 extra_certificates
+signing_key.pem
 signing_key.priv
 signing_key.x509
 x509.genkey
diff --git a/.mailmap b/.mailmap
index 977f958eedbe..4b31af54ccd5 100644
--- a/.mailmap
+++ b/.mailmap
@@ -17,6 +17,7 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
 Andreas Herrmann <aherrman@de.ibm.com>
+Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andy Adamson <andros@citi.umich.edu>
@@ -116,6 +117,7 @@ Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
+Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
 Sumit Semwal <sumit.semwal@ti.com>
 Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
@@ -125,7 +127,9 @@ Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
 Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
-Viresh Kumar <viresh.linux@gmail.com> <viresh.kumar@st.com>
+Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
+Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
+Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
diff --git a/CREDITS b/CREDITS
index 1d616640bbf6..bcb8efaa9459 100644
--- a/CREDITS
+++ b/CREDITS
@@ -20,6 +20,10 @@ D: One of assisting postmasters for vger.kernel.org's lists
 S: (ask for current address)
 S: Finland
 
+N: Thomas Abraham
+E: thomas.ab@samsung.com
+D: Samsung pin controller driver
+
 N: Dragos Acostachioaie
 E: dragos@iname.com
 W: http://www.arbornet.org/~dragos
@@ -3219,6 +3223,11 @@ S: 69 rue Dunois
 S: 75013 Paris
 S: France
 
+N: Aleksa Sarai
+E: cyphar@cyphar.com
+W: https://www.cyphar.com/
+D: `pids` cgroup subsystem
+
 N: Dipankar Sarma
 E: dipankar@in.ibm.com
 D: RCU
diff --git a/Documentation/ABI/stable/sysfs-bus-vmbus b/Documentation/ABI/stable/sysfs-bus-vmbus
new file mode 100644
index 000000000000..636e938d5e33
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-bus-vmbus
@@ -0,0 +1,29 @@
+What:		/sys/bus/vmbus/devices/vmbus_*/id
+Date:		Jul 2009
+KernelVersion:	2.6.31
+Contact:	K. Y. Srinivasan <kys@microsoft.com>
+Description:	The VMBus child_relid of the device's primary channel
+Users:		tools/hv/lsvmbus
+
+What:		/sys/bus/vmbus/devices/vmbus_*/class_id
+Date:		Jul 2009
+KernelVersion:	2.6.31
+Contact:	K. Y. Srinivasan <kys@microsoft.com>
+Description:	The VMBus interface type GUID of the device
+Users:		tools/hv/lsvmbus
+
+What:		/sys/bus/vmbus/devices/vmbus_*/device_id
+Date:		Jul 2009
+KernelVersion:	2.6.31
+Contact:	K. Y. Srinivasan <kys@microsoft.com>
+Description:	The VMBus interface instance GUID of the device
+Users:		tools/hv/lsvmbus
+
+What:		/sys/bus/vmbus/devices/vmbus_*/channel_vp_mapping
+Date:		Jul 2015
+KernelVersion:	4.2.0
+Contact:	K. Y. Srinivasan <kys@microsoft.com>
+Description:	The mapping of which primary/sub channels are bound to which
+		Virtual Processors.
+		Format: <channel's child_relid:the bound cpu's number>
+Users:		tools/hv/lsvmbus
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-loopback b/Documentation/ABI/testing/configfs-usb-gadget-loopback
index 9aae5bfb9908..06beefbcf061 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-loopback
+++ b/Documentation/ABI/testing/configfs-usb-gadget-loopback
@@ -5,4 +5,4 @@ Description:
 		The attributes:
 
 		qlen		- depth of loopback queue
-		bulk_buflen	- buffer length
+		buflen		- buffer length
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
index 29477c319f61..bc7ff731aa0c 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
+++ b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
@@ -9,4 +9,4 @@ Description:
 		isoc_maxpacket	- 0 - 1023 (fs), 0 - 1024 (hs/ss)
 		isoc_mult	- 0..2 (hs/ss only)
 		isoc_maxburst	- 0..15 (ss only)
-		qlen		- buffer length
+		buflen		- buffer length
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x
index b4d0b99afffb..d72ca1736ba4 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x
@@ -112,7 +112,7 @@ KernelVersion:	3.19
 Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
 Description: 	(RW) Mask to apply to all the context ID comparator.
 
-What:		/sys/bus/coresight/devices/<memory_map>.[etm|ptm]/ctxid_val
+What:		/sys/bus/coresight/devices/<memory_map>.[etm|ptm]/ctxid_pid
 Date:		November 2014
 KernelVersion:	3.19
 Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
index 2fe2e3dae487..2355ed8ae31f 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
@@ -249,7 +249,7 @@ KernelVersion:	4.01
 Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
 Description:	(RW) Select which context ID comparator to work with.
 
-What:		/sys/bus/coresight/devices/<memory_map>.etm/ctxid_val
+What:		/sys/bus/coresight/devices/<memory_map>.etm/ctxid_pid
 Date:		April 2015
 KernelVersion:	4.01
 Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index bbed111c31b4..42d360fe66a5 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -413,6 +413,11 @@ Description:
 		to compute the calories burnt by the user.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_scale_available
+What:		/sys/.../iio:deviceX/in_anglvel_scale_available
+What:		/sys/.../iio:deviceX/in_magn_scale_available
+What:		/sys/.../iio:deviceX/in_illuminance_scale_available
+What:		/sys/.../iio:deviceX/in_intensity_scale_available
+What:		/sys/.../iio:deviceX/in_proximity_scale_available
 What:		/sys/.../iio:deviceX/in_voltageX_scale_available
 What:		/sys/.../iio:deviceX/in_voltage-voltage_scale_available
 What:		/sys/.../iio:deviceX/out_voltageX_scale_available
@@ -488,7 +493,7 @@ Contact:	linux-iio@vger.kernel.org
 Description:
 		Specifies the output powerdown mode.
 		DAC output stage is disconnected from the amplifier and
-		1kohm_to_gnd: connected	to ground via an 1kOhm resistor,
+		1kohm_to_gnd: connected to ground via an 1kOhm resistor,
 		6kohm_to_gnd: connected to ground via a 6kOhm resistor,
 		20kohm_to_gnd: connected to ground via a 20kOhm resistor,
 		100kohm_to_gnd: connected to ground via an 100kOhm resistor,
@@ -498,9 +503,9 @@ Description:
 		outX_powerdown_mode_available. If Y is not present the
 		mode is shared across all outputs.
 
-What:		/sys/.../iio:deviceX/out_votlageY_powerdown_mode_available
+What:		/sys/.../iio:deviceX/out_voltageY_powerdown_mode_available
 What:		/sys/.../iio:deviceX/out_voltage_powerdown_mode_available
-What:		/sys/.../iio:deviceX/out_altvotlageY_powerdown_mode_available
+What:		/sys/.../iio:deviceX/out_altvoltageY_powerdown_mode_available
 What:		/sys/.../iio:deviceX/out_altvoltage_powerdown_mode_available
 KernelVersion:	2.6.38
 Contact:	linux-iio@vger.kernel.org
@@ -1035,13 +1040,6 @@ Contact:	linux-iio@vger.kernel.org
 Description:
 		Number of scans contained by the buffer.
 
-What:		/sys/bus/iio/devices/iio:deviceX/buffer/bytes_per_datum
-KernelVersion:	2.6.37
-Contact:	linux-iio@vger.kernel.org
-Description:
-		Bytes per scan.  Due to alignment fun, the scan may be larger
-		than implied directly by the scan_element parameters.
-
 What:		/sys/bus/iio/devices/iio:deviceX/buffer/enable
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
@@ -1234,10 +1232,8 @@ Description:
 		object is near the sensor, usually be observing
 		reflectivity of infrared or ultrasound emitted.
 		Often these sensors are unit less and as such conversion
-		to SI units is not possible.  Where it is, the units should
-		be meters.  If such a conversion is not possible, the reported
-		values should behave in the same way as a distance, i.e. lower
-		values indicate something is closer to the sensor.
+		to SI units is not possible. Higher proximity measurements
+		indicate closer objects, and vice versa.
 
 What:		/sys/.../iio:deviceX/in_illuminance_input
 What:		/sys/.../iio:deviceX/in_illuminance_raw
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-trigger-sysfs b/Documentation/ABI/testing/sysfs-bus-iio-trigger-sysfs
index 5235e6c749ab..bbb039237a25 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-trigger-sysfs
+++ b/Documentation/ABI/testing/sysfs-bus-iio-trigger-sysfs
@@ -9,3 +9,12 @@ Description:
 		automated testing or in situations, where other trigger methods
 		are not applicable. For example no RTC or spare GPIOs.
 		X is the IIO index of the trigger.
+
+What:		/sys/bus/iio/devices/triggerX/name
+KernelVersion:	2.6.39
+Contact:	linux-iio@vger.kernel.org
+Description:
+		The name attribute holds a description string for the current
+		trigger. In order to associate the trigger with an IIO device
+		one should write this name string to
+		/sys/bus/iio/devices/iio:deviceY/trigger/current_trigger.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index e5cc7633d013..864637f25bee 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -114,6 +114,20 @@ Description:
 		enabled for the device. Developer can write y/Y/1 or n/N/0 to
 		the file to enable/disable the feature.
 
+What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm
+Date:		June 2015
+Contact:	Kevin Strasser <kevin.strasser@linux.intel.com>
+Description:
+		If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged
+		in to a xHCI host which supports link PM, it will check if U1
+		and U2 exit latencies have been set in the BOS descriptor; if
+		the check is is passed and the host supports USB3 hardware LPM,
+		USB3 hardware LPM will be enabled for the device and the USB
+		device directory will contain a file named
+		power/usb3_hardware_lpm. The file holds a string value (enable
+		or disable) indicating whether or not USB3 hardware LPM is
+		enabled for the device.
+
 What:		/sys/bus/usb/devices/.../removable
 Date:		February 2012
 Contact:	Matthew Garrett <mjg@redhat.com>
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index acfe9df83139..b07e86d4597f 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -223,3 +223,13 @@ Description:    write only
                 Writing 1 will issue a PERST to card which may cause the card
                 to reload the FPGA depending on load_image_on_perst.
 Users:		https://github.com/ibm-capi/libcxl
+
+What:		/sys/class/cxl/<card>/perst_reloads_same_image
+Date:		July 2015
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read/write
+		Trust that when an image is reloaded via PERST, it will not
+		have changed.
+		0 = don't trust, the image may be different (default)
+		1 = trust that the image will not change.
+Users:		https://github.com/ibm-capi/libcxl
diff --git a/Documentation/ABI/testing/sysfs-class-power-twl4030 b/Documentation/ABI/testing/sysfs-class-power-twl4030
new file mode 100644
index 000000000000..be26af0f1895
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-power-twl4030
@@ -0,0 +1,45 @@
+What: /sys/class/power_supply/twl4030_ac/max_current
+      /sys/class/power_supply/twl4030_usb/max_current
+Description:
+	Read/Write limit on current which may
+	be drawn from the ac (Accessory Charger) or
+	USB port.
+
+	Value is in micro-Amps.
+
+	Value is set automatically to an appropriate
+	value when a cable is plugged or unplugged.
+
+	Value can the set by writing to the attribute.
+	The change will only persist until the next
+	plug event.  These event are reported via udev.
+
+
+What: /sys/class/power_supply/twl4030_usb/mode
+Description:
+	Changing mode for USB port.
+	Writing to this can disable charging.
+
+	Possible values are:
+		"auto" - draw power as appropriate for detected
+			 power source and battery status.
+		"off"  - do not draw any power.
+		"continuous"
+		       - activate mode described as "linear" in
+		         TWL data sheets.  This uses whatever
+			 current is available and doesn't switch off
+			 when voltage drops.
+
+			 This is useful for unstable power sources
+			 such as bicycle dynamo, but care should
+			 be taken that battery is not over-charged.
+
+What: /sys/class/power_supply/twl4030_ac/mode
+Description:
+	Changing mode for 'ac' port.
+	Writing to this can disable charging.
+
+	Possible values are:
+		"auto" - draw power as appropriate for detected
+			 power source and battery status.
+		"off"  - do not draw any power.
diff --git a/Documentation/ABI/testing/sysfs-driver-sunxi-sid b/Documentation/ABI/testing/sysfs-driver-sunxi-sid
deleted file mode 100644
index ffb9536f6ecc..000000000000
--- a/Documentation/ABI/testing/sysfs-driver-sunxi-sid
+++ /dev/null
@@ -1,22 +0,0 @@
-What:		/sys/devices/*/<our-device>/eeprom
-Date:		August 2013
-Contact:	Oliver Schinagl <oliver@schinagl.nl>
-Description:	read-only access to the SID (Security-ID) on current
-		A-series SoC's from Allwinner. Currently supports A10, A10s, A13
-		and A20 CPU's. The earlier A1x series of SoCs exports 16 bytes,
-		whereas the newer A20 SoC exposes 512 bytes split into sections.
-		Besides the 16 bytes of SID, there's also an SJTAG area,
-		HDMI-HDCP key and some custom keys. Below a quick overview, for
-		details see the user manual:
-		0x000  128 bit root-key (sun[457]i)
-		0x010  128 bit boot-key (sun7i)
-		0x020   64 bit security-jtag-key (sun7i)
-		0x028   16 bit key configuration (sun7i)
-		0x02b   16 bit custom-vendor-key (sun7i)
-		0x02c  320 bit low general key (sun7i)
-		0x040   32 bit read-control access (sun7i)
-		0x064  224 bit low general key (sun7i)
-		0x080 2304 bit HDCP-key (sun7i)
-		0x1a0  768 bit high general key (sun7i)
-Users:		any user space application which wants to read the SID on
-		Allwinner's A-series of CPU's.
diff --git a/Documentation/ABI/testing/sysfs-driver-wacom b/Documentation/ABI/testing/sysfs-driver-wacom
index c4f0fed64a6e..dca429340772 100644
--- a/Documentation/ABI/testing/sysfs-driver-wacom
+++ b/Documentation/ABI/testing/sysfs-driver-wacom
@@ -77,3 +77,22 @@ Description:
 		The format is also scrambled, like in the USB mode, and it can
 		be summarized by converting 76543210 into GECA6420.
 					    HGFEDCBA      HFDB7531
+
+What:		/sys/bus/hid/devices/<bus>:<vid>:<pid>.<n>/wacom_remote/unpair_remote
+Date:		July 2015
+Contact:	linux-input@vger.kernel.org
+Description:
+		Writing the character sequence '*' followed by a newline to
+		this file will delete all of the current pairings on the
+		device. Other character sequences are reserved. This file is
+		write only.
+
+What:		/sys/bus/hid/devices/<bus>:<vid>:<pid>.<n>/wacom_remote/<serial_number>/remote_mode
+Date:		July 2015
+Contact:	linux-input@vger.kernel.org
+Description:
+		Reading from this file reports the mode status of the
+		remote as indicated by the LED lights on the device. If no
+		reports have been received from the paired device, reading
+		from this file will report '-1'. The mode is read-only
+		and cannot be set through the driver.
diff --git a/Documentation/ABI/testing/sysfs-gpio b/Documentation/ABI/testing/sysfs-gpio
index 80f4c94c7bef..55ffa2df1c10 100644
--- a/Documentation/ABI/testing/sysfs-gpio
+++ b/Documentation/ABI/testing/sysfs-gpio
@@ -16,7 +16,8 @@ Description:
     /sys/class/gpio
 	/export ... asks the kernel to export a GPIO to userspace
 	/unexport ... to return a GPIO to the kernel
-	/gpioN ... for each exported GPIO #N
+	/gpioN ... for each exported GPIO #N OR
+	/<LINE-NAME> ... for a properly named GPIO line
 	    /value ... always readable, writes fail for input GPIOs
 	    /direction ... r/w as: in, out (default low); write: high, low
 	    /edge ... r/w as: none, falling, rising, both
diff --git a/Documentation/ABI/testing/sysfs-hypervisor-pmu b/Documentation/ABI/testing/sysfs-hypervisor-pmu
new file mode 100644
index 000000000000..224faa105e18
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-hypervisor-pmu
@@ -0,0 +1,23 @@
+What:		/sys/hypervisor/pmu/pmu_mode
+Date:		August 2015
+KernelVersion:	4.3
+Contact:	Boris Ostrovsky <boris.ostrovsky@oracle.com>
+Description:
+		Describes mode that Xen's performance-monitoring unit (PMU)
+		uses. Accepted values are
+			"off"  -- PMU is disabled
+			"self" -- The guest can profile itself
+			"hv"   -- The guest can profile itself and, if it is
+				  privileged (e.g. dom0), the hypervisor
+			"all" --  The guest can profile itself, the hypervisor
+				  and all other guests. Only available to
+				  privileged guests.
+
+What:           /sys/hypervisor/pmu/pmu_features
+Date:           August 2015
+KernelVersion:  4.3
+Contact:        Boris Ostrovsky <boris.ostrovsky@oracle.com>
+Description:
+		Describes Xen PMU features (as an integer). A set bit indicates
+		that the corresponding feature is enabled. See
+		include/xen/interface/xenpmu.h for available features
diff --git a/Documentation/Changes b/Documentation/Changes
index 646cdaa6e9d1..6d8863004858 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -43,6 +43,7 @@ o  udev                   081                     # udevd --version
 o  grub                   0.93                    # grub --version || grub-install --version
 o  mcelog                 0.6                     # mcelog --version
 o  iptables               1.4.2                   # iptables -V
+o  openssl & libcrypto    1.0.1k                  # openssl version
 
 
 Kernel compilation
@@ -79,6 +80,17 @@ BC
 You will need bc to build kernels 3.10 and higher
 
 
+OpenSSL
+-------
+
+Module signing and external certificate handling use the OpenSSL program and
+crypto library to do key creation and signature generation.
+
+You will need openssl to build kernels 3.7 and higher if module signing is
+enabled.  You will also need openssl development packages to build kernels 4.3
+and higher.
+
+
 System utilities
 ================
 
@@ -295,6 +307,10 @@ Binutils
 --------
 o  <ftp://ftp.kernel.org/pub/linux/devel/binutils/>
 
+OpenSSL
+-------
+o  <https://www.openssl.org/>
+
 System utilities
 ****************
 
@@ -392,4 +408,3 @@ o  <http://oprofile.sf.net/download/>
 NFS-Utils
 ---------
 o  <http://nfs.sourceforge.net/>
-
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index b713c35f8543..c06f817b3091 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -929,13 +929,11 @@ The C Programming Language, Second Edition
 by Brian W. Kernighan and Dennis M. Ritchie.
 Prentice Hall, Inc., 1988.
 ISBN 0-13-110362-8 (paperback), 0-13-110370-9 (hardback).
-URL: http://cm.bell-labs.com/cm/cs/cbook/
 
 The Practice of Programming
 by Brian W. Kernighan and Rob Pike.
 Addison-Wesley, Inc., 1999.
 ISBN 0-201-61586-X.
-URL: http://cm.bell-labs.com/cm/cs/tpop/
 
 GNU manuals - where in compliance with K&R and this text - for cpp, gcc,
 gcc internals and indent, all available from http://www.gnu.org/manual/
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index b6a6a2e0dd3b..93eff64387cd 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -15,7 +15,7 @@ DOCBOOKS := z8530book.xml device-drivers.xml \
 	    80211.xml debugobjects.xml sh.xml regulator.xml \
 	    alsa-driver-api.xml writing-an-alsa-driver.xml \
 	    tracepoint.xml drm.xml media_api.xml w1.xml \
-	    writing_musb_glue_layer.xml crypto-API.xml
+	    writing_musb_glue_layer.xml crypto-API.xml iio.xml
 
 include Documentation/DocBook/media/Makefile
 
@@ -56,16 +56,19 @@ htmldocs: $(HTML)
 
 MAN := $(patsubst %.xml, %.9, $(BOOKS))
 mandocs: $(MAN)
-	find $(obj)/man -name '*.9' | xargs gzip -f
+	find $(obj)/man -name '*.9' | xargs gzip -nf
 
 installmandocs: mandocs
 	mkdir -p /usr/local/man/man9/
-	install $(obj)/man/*.9.gz /usr/local/man/man9/
+	find $(obj)/man -name '*.9.gz' -printf '%h %f\n' | \
+		sort -k 2 -k 1 | uniq -f 1 | sed -e 's: :/:' | \
+		xargs install -m 644 -t /usr/local/man/man9/
 
 ###
 #External programs used
-KERNELDOC = $(srctree)/scripts/kernel-doc
-DOCPROC   = $(objtree)/scripts/docproc
+KERNELDOCXMLREF = $(srctree)/scripts/kernel-doc-xml-ref
+KERNELDOC       = $(srctree)/scripts/kernel-doc
+DOCPROC         = $(objtree)/scripts/docproc
 
 XMLTOFLAGS = -m $(srctree)/$(src)/stylesheet.xsl
 XMLTOFLAGS += --skip-validation
@@ -89,7 +92,7 @@ define rule_docproc
         ) > $(dir $@).$(notdir $@).cmd
 endef
 
-%.xml: %.tmpl $(KERNELDOC) $(DOCPROC) FORCE
+%.xml: %.tmpl $(KERNELDOC) $(DOCPROC) $(KERNELDOCXMLREF) FORCE
 	$(call if_changed_rule,docproc)
 
 # Tell kbuild to always build the programs
@@ -140,7 +143,20 @@ quiet_cmd_db2html = HTML    $@
 		echo '<a HREF="$(patsubst %.html,%,$(notdir $@))/index.html"> \
 		$(patsubst %.html,%,$(notdir $@))</a><p>' > $@
 
-%.html:	%.xml
+###
+# Rules to create an aux XML and .db, and use them to re-process the DocBook XML
+# to fill internal hyperlinks
+       gen_aux_xml = :
+ quiet_gen_aux_xml = echo '  XMLREF  $@'
+silent_gen_aux_xml = :
+%.aux.xml: %.xml
+	@$($(quiet)gen_aux_xml)
+	@rm -rf $@
+	@(cat $< | egrep "^<refentry id" | egrep -o "\".*\"" | cut -f 2 -d \" > $<.db)
+	@$(KERNELDOCXMLREF) -db $<.db $< > $@
+.PRECIOUS: %.aux.xml
+
+%.html:	%.aux.xml
 	@(which xmlto > /dev/null 2>&1) || \
 	 (echo "*** You need to install xmlto ***"; \
 	  exit 1)
@@ -150,12 +166,12 @@ quiet_cmd_db2html = HTML    $@
             cp $(PNG-$(basename $(notdir $@))) $(patsubst %.html,%,$@); fi
 
 quiet_cmd_db2man = MAN     $@
-      cmd_db2man = if grep -q refentry $<; then xmlto man $(XMLTOFLAGS) -o $(obj)/man $< ; fi
+      cmd_db2man = if grep -q refentry $<; then xmlto man $(XMLTOFLAGS) -o $(obj)/man/$(*F) $< ; fi
 %.9 : %.xml
 	@(which xmlto > /dev/null 2>&1) || \
 	 (echo "*** You need to install xmlto ***"; \
 	  exit 1)
-	$(Q)mkdir -p $(obj)/man
+	$(Q)mkdir -p $(obj)/man/$(*F)
 	$(call cmd,db2man)
 	@touch $@
 
@@ -209,15 +225,18 @@ dochelp:
 ###
 # Temporary files left by various tools
 clean-files := $(DOCBOOKS) \
-	$(patsubst %.xml, %.dvi,  $(DOCBOOKS)) \
-	$(patsubst %.xml, %.aux,  $(DOCBOOKS)) \
-	$(patsubst %.xml, %.tex,  $(DOCBOOKS)) \
-	$(patsubst %.xml, %.log,  $(DOCBOOKS)) \
-	$(patsubst %.xml, %.out,  $(DOCBOOKS)) \
-	$(patsubst %.xml, %.ps,   $(DOCBOOKS)) \
-	$(patsubst %.xml, %.pdf,  $(DOCBOOKS)) \
-	$(patsubst %.xml, %.html, $(DOCBOOKS)) \
-	$(patsubst %.xml, %.9,    $(DOCBOOKS)) \
+	$(patsubst %.xml, %.dvi,     $(DOCBOOKS)) \
+	$(patsubst %.xml, %.aux,     $(DOCBOOKS)) \
+	$(patsubst %.xml, %.tex,     $(DOCBOOKS)) \
+	$(patsubst %.xml, %.log,     $(DOCBOOKS)) \
+	$(patsubst %.xml, %.out,     $(DOCBOOKS)) \
+	$(patsubst %.xml, %.ps,      $(DOCBOOKS)) \
+	$(patsubst %.xml, %.pdf,     $(DOCBOOKS)) \
+	$(patsubst %.xml, %.html,    $(DOCBOOKS)) \
+	$(patsubst %.xml, %.9,       $(DOCBOOKS)) \
+	$(patsubst %.xml, %.aux.xml, $(DOCBOOKS)) \
+	$(patsubst %.xml, %.xml.db,  $(DOCBOOKS)) \
+	$(patsubst %.xml, %.xml,     $(DOCBOOKS)) \
 	$(index)
 
 clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man
diff --git a/Documentation/DocBook/alsa-driver-api.tmpl b/Documentation/DocBook/alsa-driver-api.tmpl
index 71f9246127ec..e94a10bb4a9e 100644
--- a/Documentation/DocBook/alsa-driver-api.tmpl
+++ b/Documentation/DocBook/alsa-driver-api.tmpl
@@ -108,7 +108,7 @@
      <sect1><title>ASoC Core API</title>
 !Iinclude/sound/soc.h
 !Esound/soc/soc-core.c
-!Esound/soc/soc-cache.c
+<!-- !Esound/soc/soc-cache.c no docbook comments here -->
 !Esound/soc/soc-devres.c
 !Esound/soc/soc-io.c
 !Esound/soc/soc-pcm.c
diff --git a/Documentation/DocBook/crypto-API.tmpl b/Documentation/DocBook/crypto-API.tmpl
index 0992531ffefb..07df23ea06e4 100644
--- a/Documentation/DocBook/crypto-API.tmpl
+++ b/Documentation/DocBook/crypto-API.tmpl
@@ -585,7 +585,7 @@ kernel crypto API                                |   IPSEC Layer
 +-----------+                                    |
 |           |            (1)
 |   aead    | <-----------------------------------  esp_output
-| (seqniv)  | ---+
+|  (seqiv)  | ---+
 +-----------+    |
                  | (2)
 +-----------+    |
@@ -1101,7 +1101,7 @@ kernel crypto API            |       Caller
     </para>
 
     <para>
-     [1] http://www.chronox.de/libkcapi.html
+     [1] <ulink url="http://www.chronox.de/libkcapi.html">http://www.chronox.de/libkcapi.html</ulink>
     </para>
 
    </sect1>
@@ -1661,7 +1661,7 @@ read(opfd, out, outlen);
     </para>
 
     <para>
-     [1] http://www.chronox.de/libkcapi.html
+     [1] <ulink url="http://www.chronox.de/libkcapi.html">http://www.chronox.de/libkcapi.html</ulink>
     </para>
 
    </sect1>
@@ -1687,7 +1687,7 @@ read(opfd, out, outlen);
 !Pinclude/linux/crypto.h Block Cipher Algorithm Definitions
 !Finclude/linux/crypto.h crypto_alg
 !Finclude/linux/crypto.h ablkcipher_alg
-!Finclude/linux/crypto.h aead_alg
+!Finclude/crypto/aead.h aead_alg
 !Finclude/linux/crypto.h blkcipher_alg
 !Finclude/linux/crypto.h cipher_alg
 !Finclude/crypto/rng.h rng_alg
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index faf09d4a0ea8..abba93f9d64a 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -66,6 +66,7 @@
 !Ekernel/time/hrtimer.c
      </sect1>
      <sect1><title>Workqueues and Kevents</title>
+!Iinclude/linux/workqueue.h
 !Ekernel/workqueue.c
      </sect1>
      <sect1><title>Internal Functions</title>
@@ -216,6 +217,40 @@ X!Isound/sound_firmware.c
 -->
   </chapter>
 
+  <chapter id="mediadev">
+     <title>Media Devices</title>
+
+     <sect1><title>Video2Linux devices</title>
+!Iinclude/media/v4l2-async.h
+!Iinclude/media/v4l2-ctrls.h
+!Iinclude/media/v4l2-dv-timings.h
+!Iinclude/media/v4l2-event.h
+!Iinclude/media/v4l2-flash-led-class.h
+!Iinclude/media/v4l2-mediabus.h
+!Iinclude/media/v4l2-mem2mem.h
+!Iinclude/media/v4l2-of.h
+!Iinclude/media/v4l2-subdev.h
+!Iinclude/media/videobuf2-core.h
+!Iinclude/media/videobuf2-memops.h
+     </sect1>
+     <sect1><title>Digital TV (DVB) devices</title>
+!Idrivers/media/dvb-core/dvb_ca_en50221.h
+!Idrivers/media/dvb-core/dvb_frontend.h
+!Idrivers/media/dvb-core/dvb_math.h
+!Idrivers/media/dvb-core/dvb_ringbuffer.h
+!Idrivers/media/dvb-core/dvbdev.h
+     </sect1>
+     <sect1><title>Remote Controller devices</title>
+!Iinclude/media/rc-core.h
+     </sect1>
+     <sect1><title>Media Controller devices</title>
+!Iinclude/media/media-device.h
+!Iinclude/media/media-devnode.h
+!Iinclude/media/media-entity.h
+     </sect1>
+
+  </chapter>
+
   <chapter id="uart16x50">
      <title>16x50 UART Driver</title>
 !Edrivers/tty/serial/serial_core.c
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index c0312cbd023d..9ddf8c6cb887 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -3383,7 +3383,7 @@ void intel_crt_init(struct drm_device *dev)
 	<td valign="top" >TBD</td>
 	</tr>
 	<tr>
-	<td rowspan="2" valign="top" >omap</td>
+	<td valign="top" >omap</td>
 	<td valign="top" >Generic</td>
 	<td valign="top" >“zorder”</td>
 	<td valign="top" >RANGE</td>
@@ -3982,7 +3982,6 @@ int num_ioctls;</synopsis>
         <title>Interrupt Handling</title>
 !Pdrivers/gpu/drm/i915/i915_irq.c interrupt handling
 !Fdrivers/gpu/drm/i915/i915_irq.c intel_irq_init intel_irq_init_hw intel_hpd_init
-!Fdrivers/gpu/drm/i915/i915_irq.c intel_irq_fini
 !Fdrivers/gpu/drm/i915/i915_irq.c intel_runtime_pm_disable_interrupts
 !Fdrivers/gpu/drm/i915/i915_irq.c intel_runtime_pm_enable_interrupts
       </sect2>
@@ -4012,7 +4011,6 @@ int num_ioctls;</synopsis>
         <title>Frontbuffer Tracking</title>
 !Pdrivers/gpu/drm/i915/intel_frontbuffer.c frontbuffer tracking
 !Idrivers/gpu/drm/i915/intel_frontbuffer.c
-!Fdrivers/gpu/drm/i915/intel_drv.h intel_frontbuffer_flip
 !Fdrivers/gpu/drm/i915/i915_gem.c i915_gem_track_fb
       </sect2>
       <sect2>
@@ -4045,6 +4043,11 @@ int num_ioctls;</synopsis>
         </para>
       </sect2>
       <sect2>
+        <title>Hotplug</title>
+!Pdrivers/gpu/drm/i915/intel_hotplug.c Hotplug
+!Idrivers/gpu/drm/i915/intel_hotplug.c
+      </sect2>
+      <sect2>
 	<title>High Definition Audio</title>
 !Pdrivers/gpu/drm/i915/intel_audio.c High Definition Audio over HDMI and Display Port
 !Idrivers/gpu/drm/i915/intel_audio.c
@@ -4195,6 +4198,23 @@ int num_ioctls;</synopsis>
 !Idrivers/gpu/drm/i915/i915_gem_gtt.c
       </sect2>
       <sect2>
+        <title>GTT Fences and Swizzling</title>
+!Idrivers/gpu/drm/i915/i915_gem_fence.c
+        <sect3>
+          <title>Global GTT Fence Handling</title>
+!Pdrivers/gpu/drm/i915/i915_gem_fence.c fence register handling
+        </sect3>
+        <sect3>
+          <title>Hardware Tiling and Swizzling Details</title>
+!Pdrivers/gpu/drm/i915/i915_gem_fence.c tiling swizzling details
+        </sect3>
+      </sect2>
+      <sect2>
+        <title>Object Tiling IOCTLs</title>
+!Idrivers/gpu/drm/i915/i915_gem_tiling.c
+!Pdrivers/gpu/drm/i915/i915_gem_tiling.c buffer object tiling
+      </sect2>
+      <sect2>
         <title>Buffer Object Eviction</title>
 	<para>
 	  This section documents the interface functions for evicting buffer
diff --git a/Documentation/DocBook/filesystems.tmpl b/Documentation/DocBook/filesystems.tmpl
index bcdfdb9a9277..6006b6358c86 100644
--- a/Documentation/DocBook/filesystems.tmpl
+++ b/Documentation/DocBook/filesystems.tmpl
@@ -146,36 +146,30 @@
 The journalling layer is  easy to use. You need to
 first of all create a journal_t data structure. There are
 two calls to do this dependent on how you decide to allocate the physical
-media on which the journal resides. The journal_init_inode() call
-is for journals stored in filesystem inodes, or the journal_init_dev()
-call can be use for journal stored on a raw device (in a continuous range
+media on which the journal resides. The jbd2_journal_init_inode() call
+is for journals stored in filesystem inodes, or the jbd2_journal_init_dev()
+call can be used for journal stored on a raw device (in a continuous range
 of blocks). A journal_t is a typedef for a struct pointer, so when
-you are finally finished make sure you call journal_destroy() on it
+you are finally finished make sure you call jbd2_journal_destroy() on it
 to free up any used kernel memory.
 </para>
 
 <para>
 Once you have got your journal_t object you need to 'mount' or load the journal
-file, unless of course you haven't initialised it yet - in which case you
-need to call journal_create().
+file. The journalling layer expects the space for the journal was already
+allocated and initialized properly by the userspace tools.  When loading the
+journal you must call jbd2_journal_load() to process journal contents.  If the
+client file system detects the journal contents does not need to be processed
+(or even need not have valid contents), it may call jbd2_journal_wipe() to
+clear the journal contents before calling jbd2_journal_load().
 </para>
 
 <para>
-Most of the time however your journal file will already have been created, but
-before you load it you must call journal_wipe() to empty the journal file.
-Hang on, you say , what if the filesystem wasn't cleanly umount()'d . Well, it is the
-job of the client file system to detect this and skip the call to journal_wipe().
-</para>
-
-<para>
-In either case the next call should be to journal_load() which prepares the
-journal file for use. Note that journal_wipe(..,0) calls journal_skip_recovery()
-for you if it detects any outstanding transactions in the journal and similarly
-journal_load() will call journal_recover() if necessary.
-I would advise reading fs/ext3/super.c for examples on this stage.
-[RGG: Why is the journal_wipe() call necessary - doesn't this needlessly
-complicate the API. Or isn't a good idea for the journal layer to hide
-dirty mounts from the client fs]
+Note that jbd2_journal_wipe(..,0) calls jbd2_journal_skip_recovery() for you if
+it detects any outstanding transactions in the journal and similarly
+jbd2_journal_load() will call jbd2_journal_recover() if necessary.  I would
+advise reading ext4_load_journal() in fs/ext4/super.c for examples on this
+stage.
 </para>
 
 <para>
@@ -189,41 +183,41 @@ You still need to actually journal your filesystem changes, this
 is done by wrapping them into transactions. Additionally you
 also need to wrap the modification of each of the buffers
 with calls to the journal layer, so it knows what the modifications
-you are actually making are. To do this use  journal_start() which
+you are actually making are. To do this use jbd2_journal_start() which
 returns a transaction handle.
 </para>
 
 <para>
-journal_start()
-and its counterpart journal_stop(), which indicates the end of a transaction
-are nestable calls, so you can reenter a transaction if necessary,
-but remember you must call journal_stop() the same number of times as
-journal_start() before the transaction is completed (or more accurately
-leaves the update phase). Ext3/VFS makes use of this feature to simplify
-quota support.
+jbd2_journal_start()
+and its counterpart jbd2_journal_stop(), which indicates the end of a
+transaction are nestable calls, so you can reenter a transaction if necessary,
+but remember you must call jbd2_journal_stop() the same number of times as
+jbd2_journal_start() before the transaction is completed (or more accurately
+leaves the update phase). Ext4/VFS makes use of this feature to simplify
+handling of inode dirtying, quota support, etc.
 </para>
 
 <para>
 Inside each transaction you need to wrap the modifications to the
 individual buffers (blocks). Before you start to modify a buffer you
-need to call journal_get_{create,write,undo}_access() as appropriate,
+need to call jbd2_journal_get_{create,write,undo}_access() as appropriate,
 this allows the journalling layer to copy the unmodified data if it
 needs to. After all the buffer may be part of a previously uncommitted
 transaction.
 At this point you are at last ready to modify a buffer, and once
-you are have done so you need to call journal_dirty_{meta,}data().
+you are have done so you need to call jbd2_journal_dirty_{meta,}data().
 Or if you've asked for access to a buffer you now know is now longer
-required to be pushed back on the device you can call journal_forget()
+required to be pushed back on the device you can call jbd2_journal_forget()
 in much the same way as you might have used bforget() in the past.
 </para>
 
 <para>
-A journal_flush() may be called at any time to commit and checkpoint
+A jbd2_journal_flush() may be called at any time to commit and checkpoint
 all your transactions.
 </para>
 
 <para>
-Then at umount time , in your put_super() you can then call journal_destroy()
+Then at umount time , in your put_super() you can then call jbd2_journal_destroy()
 to clean up your in-core journal object.
 </para>
 
@@ -231,53 +225,68 @@ to clean up your in-core journal object.
 Unfortunately there a couple of ways the journal layer can cause a deadlock.
 The first thing to note is that each task can only have
 a single outstanding transaction at any one time, remember nothing
-commits until the outermost journal_stop(). This means
+commits until the outermost jbd2_journal_stop(). This means
 you must complete the transaction at the end of each file/inode/address
 etc. operation you perform, so that the journalling system isn't re-entered
 on another journal. Since transactions can't be nested/batched
 across differing journals, and another filesystem other than
-yours (say ext3) may be modified in a later syscall.
+yours (say ext4) may be modified in a later syscall.
 </para>
 
 <para>
-The second case to bear in mind is that journal_start() can
+The second case to bear in mind is that jbd2_journal_start() can
 block if there isn't enough space in the journal for your transaction
 (based on the passed nblocks param) - when it blocks it merely(!) needs to
 wait for transactions to complete and be committed from other tasks,
-so essentially we are waiting for journal_stop(). So to avoid
-deadlocks you must treat journal_start/stop() as if they
+so essentially we are waiting for jbd2_journal_stop(). So to avoid
+deadlocks you must treat jbd2_journal_start/stop() as if they
 were semaphores and include them in your semaphore ordering rules to prevent
-deadlocks. Note that journal_extend() has similar blocking behaviour to
-journal_start() so you can deadlock here just as easily as on journal_start().
+deadlocks. Note that jbd2_journal_extend() has similar blocking behaviour to
+jbd2_journal_start() so you can deadlock here just as easily as on
+jbd2_journal_start().
 </para>
 
 <para>
 Try to reserve the right number of blocks the first time. ;-). This will
 be the maximum number of blocks you are going to touch in this transaction.
-I advise having a look at at least ext3_jbd.h to see the basis on which
-ext3 uses to make these decisions.
+I advise having a look at at least ext4_jbd.h to see the basis on which
+ext4 uses to make these decisions.
 </para>
 
 <para>
 Another wriggle to watch out for is your on-disk block allocation strategy.
-why? Because, if you undo a delete, you need to ensure you haven't reused any
-of the freed blocks in a later transaction. One simple way of doing this
-is make sure any blocks you allocate only have checkpointed transactions
-listed against them. Ext3 does this in ext3_test_allocatable().
+Why? Because, if you do a delete, you need to ensure you haven't reused any
+of the freed blocks until the transaction freeing these blocks commits. If you
+reused these blocks and crash happens, there is no way to restore the contents
+of the reallocated blocks at the end of the last fully committed transaction.
+
+One simple way of doing this is to mark blocks as free in internal in-memory
+block allocation structures only after the transaction freeing them commits.
+Ext4 uses journal commit callback for this purpose.
+</para>
+
+<para>
+With journal commit callbacks you can ask the journalling layer to call a
+callback function when the transaction is finally committed to disk, so that
+you can do some of your own management. You ask the journalling layer for
+calling the callback by simply setting journal->j_commit_callback function
+pointer and that function is called after each transaction commit. You can also
+use transaction->t_private_list for attaching entries to a transaction that
+need processing when the transaction commits.
 </para>
 
 <para>
-Lock is also providing through journal_{un,}lock_updates(),
-ext3 uses this when it wants a window with a clean and stable fs for a moment.
-eg.
+JBD2 also provides a way to block all transaction updates via
+jbd2_journal_{un,}lock_updates(). Ext4 uses this when it wants a window with a
+clean and stable fs for a moment.  E.g.
 </para>
 
 <programlisting>
 
-	journal_lock_updates() //stop new stuff happening..
-	journal_flush()        // checkpoint everything.
+	jbd2_journal_lock_updates() //stop new stuff happening..
+	jbd2_journal_flush()        // checkpoint everything.
 	..do stuff on stable fs
-	journal_unlock_updates() // carry on with filesystem use.
+	jbd2_journal_unlock_updates() // carry on with filesystem use.
 </programlisting>
 
 <para>
@@ -286,29 +295,6 @@ if you allow unprivileged userspace to trigger codepaths containing these
 calls.
 </para>
 
-<para>
-A new feature of jbd since 2.5.25 is commit callbacks with the new
-journal_callback_set() function you can now ask the journalling layer
-to call you back when the transaction is finally committed to disk, so that
-you can do some of your own management. The key to this is the journal_callback
-struct, this maintains the internal callback information but you can
-extend it like this:-
-</para>
-<programlisting>
-	struct  myfs_callback_s {
-		//Data structure element required by jbd..
-		struct journal_callback for_jbd;
-		// Stuff for myfs allocated together.
-		myfs_inode*    i_commited;
-
-	}
-</programlisting>
-
-<para>
-this would be useful if you needed to know when data was committed to a
-particular inode.
-</para>
-
     </sect2>
 
     <sect2 id="jbd_summary">
@@ -319,36 +305,6 @@ being each mount, each modification (transaction) and each changed buffer
 to tell the journalling layer about them.
 </para>
 
-<para>
-Here is a some pseudo code to give you an idea of how it works, as
-an example.
-</para>
-
-<programlisting>
-  journal_t* my_jnrl = journal_create();
-  journal_init_{dev,inode}(jnrl,...)
-  if (clean) journal_wipe();
-  journal_load();
-
-   foreach(transaction) { /*transactions must be
-                            completed before
-                            a syscall returns to
-                            userspace*/
-
-          handle_t * xct=journal_start(my_jnrl);
-          foreach(bh) {
-                journal_get_{create,write,undo}_access(xact,bh);
-                if ( myfs_modify(bh) ) { /* returns true
-                                        if makes changes */
-                           journal_dirty_{meta,}data(xact,bh);
-                } else {
-                           journal_forget(bh);
-                }
-          }
-          journal_stop(xct);
-   }
-   journal_destroy(my_jrnl);
-</programlisting>
     </sect2>
 
     </sect1>
@@ -357,13 +313,13 @@ an example.
      <title>Data Types</title>
      <para>
 	The journalling layer uses typedefs to 'hide' the concrete definitions
-	of the structures used. As a client of the JBD layer you can
+	of the structures used. As a client of the JBD2 layer you can
 	just rely on the using the pointer as a magic cookie  of some sort.
 
 	Obviously the hiding is not enforced as this is 'C'.
      </para>
 	<sect2 id="structures"><title>Structures</title>
-!Iinclude/linux/jbd.h
+!Iinclude/linux/jbd2.h
 	</sect2>
     </sect1>
 
@@ -375,11 +331,11 @@ an example.
 	manage transactions
      </para>
 	<sect2 id="journal_level"><title>Journal Level</title>
-!Efs/jbd/journal.c
-!Ifs/jbd/recovery.c
+!Efs/jbd2/journal.c
+!Ifs/jbd2/recovery.c
 	</sect2>
 	<sect2 id="transaction_level"><title>Transasction Level</title>
-!Efs/jbd/transaction.c
+!Efs/jbd2/transaction.c
 	</sect2>
     </sect1>
     <sect1 id="see_also">
diff --git a/Documentation/DocBook/iio.tmpl b/Documentation/DocBook/iio.tmpl
new file mode 100644
index 000000000000..06bb53de5a47
--- /dev/null
+++ b/Documentation/DocBook/iio.tmpl
@@ -0,0 +1,697 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+
+<book id="iioid">
+  <bookinfo>
+    <title>Industrial I/O driver developer's guide </title>
+
+    <authorgroup>
+      <author>
+        <firstname>Daniel</firstname>
+        <surname>Baluta</surname>
+        <affiliation>
+          <address>
+            <email>daniel.baluta@intel.com</email>
+          </address>
+        </affiliation>
+      </author>
+    </authorgroup>
+
+    <copyright>
+      <year>2015</year>
+      <holder>Intel Corporation</holder>
+    </copyright>
+
+    <legalnotice>
+      <para>
+        This documentation is free software; you can redistribute
+        it and/or modify it under the terms of the GNU General Public
+        License version 2.
+      </para>
+    </legalnotice>
+  </bookinfo>
+
+  <toc></toc>
+
+  <chapter id="intro">
+    <title>Introduction</title>
+    <para>
+      The main purpose of the Industrial I/O subsystem (IIO) is to provide
+      support for devices that in some sense perform either analog-to-digital
+      conversion (ADC) or digital-to-analog conversion (DAC) or both. The aim
+      is to fill the gap between the somewhat similar hwmon and input
+      subsystems.
+      Hwmon is directed at low sample rate sensors used to monitor and
+      control the system itself, like fan speed control or temperature
+      measurement. Input is, as its name suggests, focused on human interaction
+      input devices (keyboard, mouse, touchscreen). In some cases there is
+      considerable overlap between these and IIO.
+  </para>
+  <para>
+    Devices that fall into this category include:
+    <itemizedlist>
+      <listitem>
+        analog to digital converters (ADCs)
+      </listitem>
+      <listitem>
+        accelerometers
+      </listitem>
+      <listitem>
+        capacitance to digital converters (CDCs)
+      </listitem>
+      <listitem>
+        digital to analog converters (DACs)
+      </listitem>
+      <listitem>
+        gyroscopes
+      </listitem>
+      <listitem>
+        inertial measurement units (IMUs)
+      </listitem>
+      <listitem>
+        color and light sensors
+      </listitem>
+      <listitem>
+        magnetometers
+      </listitem>
+      <listitem>
+        pressure sensors
+      </listitem>
+      <listitem>
+        proximity sensors
+      </listitem>
+      <listitem>
+        temperature sensors
+      </listitem>
+    </itemizedlist>
+    Usually these sensors are connected via SPI or I2C. A common use case of the
+    sensors devices is to have combined functionality (e.g. light plus proximity
+    sensor).
+  </para>
+  </chapter>
+  <chapter id='iiosubsys'>
+    <title>Industrial I/O core</title>
+    <para>
+      The Industrial I/O core offers:
+      <itemizedlist>
+        <listitem>
+         a unified framework for writing drivers for many different types of
+         embedded sensors.
+        </listitem>
+        <listitem>
+         a standard interface to user space applications manipulating sensors.
+        </listitem>
+      </itemizedlist>
+      The implementation can be found under <filename>
+      drivers/iio/industrialio-*</filename>
+  </para>
+  <sect1 id="iiodevice">
+    <title> Industrial I/O devices </title>
+
+!Finclude/linux/iio/iio.h iio_dev
+!Fdrivers/iio/industrialio-core.c iio_device_alloc
+!Fdrivers/iio/industrialio-core.c iio_device_free
+!Fdrivers/iio/industrialio-core.c iio_device_register
+!Fdrivers/iio/industrialio-core.c iio_device_unregister
+
+    <para>
+      An IIO device usually corresponds to a single hardware sensor and it
+      provides all the information needed by a driver handling a device.
+      Let's first have a look at the functionality embedded in an IIO
+      device then we will show how a device driver makes use of an IIO
+      device.
+    </para>
+    <para>
+        There are two ways for a user space application to interact
+        with an IIO driver.
+      <itemizedlist>
+        <listitem>
+          <filename>/sys/bus/iio/iio:deviceX/</filename>, this
+          represents a hardware sensor and groups together the data
+          channels of the same chip.
+        </listitem>
+        <listitem>
+          <filename>/dev/iio:deviceX</filename>, character device node
+          interface used for buffered data transfer and for events information
+          retrieval.
+        </listitem>
+      </itemizedlist>
+    </para>
+    A typical IIO driver will register itself as an I2C or SPI driver and will
+    create two routines, <function> probe </function> and <function> remove
+    </function>. At <function>probe</function>:
+    <itemizedlist>
+    <listitem>call <function>iio_device_alloc</function>, which allocates memory
+      for an IIO device.
+    </listitem>
+    <listitem> initialize IIO device fields with driver specific information
+              (e.g. device name, device channels).
+    </listitem>
+    <listitem>call <function> iio_device_register</function>, this registers the
+      device with the IIO core. After this call the device is ready to accept
+      requests from user space applications.
+    </listitem>
+    </itemizedlist>
+      At <function>remove</function>, we free the resources allocated in
+      <function>probe</function> in reverse order:
+    <itemizedlist>
+    <listitem><function>iio_device_unregister</function>, unregister the device
+      from the IIO core.
+    </listitem>
+    <listitem><function>iio_device_free</function>, free the memory allocated
+      for the IIO device.
+    </listitem>
+    </itemizedlist>
+
+    <sect2 id="iioattr"> <title> IIO device sysfs interface </title>
+      <para>
+        Attributes are sysfs files used to expose chip info and also allowing
+        applications to set various configuration parameters. For device
+        with index X, attributes can be found under
+        <filename>/sys/bus/iio/iio:deviceX/ </filename> directory.
+        Common attributes are:
+        <itemizedlist>
+          <listitem><filename>name</filename>, description of the physical
+            chip.
+          </listitem>
+          <listitem><filename>dev</filename>, shows the major:minor pair
+            associated with <filename>/dev/iio:deviceX</filename> node.
+          </listitem>
+          <listitem><filename>sampling_frequency_available</filename>,
+            available discrete set of sampling frequency values for
+            device.
+          </listitem>
+      </itemizedlist>
+      Available standard attributes for IIO devices are described in the
+      <filename>Documentation/ABI/testing/sysfs-bus-iio </filename> file
+      in the Linux kernel sources.
+      </para>
+    </sect2>
+    <sect2 id="iiochannel"> <title> IIO device channels </title>
+!Finclude/linux/iio/iio.h iio_chan_spec structure.
+      <para>
+        An IIO device channel is a representation of a data channel. An
+        IIO device can have one or multiple channels. For example:
+        <itemizedlist>
+          <listitem>
+          a thermometer sensor has one channel representing the
+          temperature measurement.
+          </listitem>
+          <listitem>
+          a light sensor with two channels indicating the measurements in
+          the visible and infrared spectrum.
+          </listitem>
+          <listitem>
+          an accelerometer can have up to 3 channels representing
+          acceleration on X, Y and Z axes.
+          </listitem>
+        </itemizedlist>
+      An IIO channel is described by the <type> struct iio_chan_spec
+      </type>. A thermometer driver for the temperature sensor in the
+      example above would have to describe its channel as follows:
+      <programlisting>
+      static const struct iio_chan_spec temp_channel[] = {
+          {
+              .type = IIO_TEMP,
+              .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+          },
+      };
+
+      </programlisting>
+      Channel sysfs attributes exposed to userspace are specified in
+      the form of <emphasis>bitmasks</emphasis>. Depending on their
+      shared info, attributes can be set in one of the following masks:
+      <itemizedlist>
+      <listitem><emphasis>info_mask_separate</emphasis>, attributes will
+        be specific to this channel</listitem>
+      <listitem><emphasis>info_mask_shared_by_type</emphasis>,
+        attributes are shared by all channels of the same type</listitem>
+      <listitem><emphasis>info_mask_shared_by_dir</emphasis>, attributes
+        are shared by all channels of the same direction </listitem>
+      <listitem><emphasis>info_mask_shared_by_all</emphasis>,
+        attributes are shared by all channels</listitem>
+      </itemizedlist>
+      When there are multiple data channels per channel type we have two
+      ways to distinguish between them:
+      <itemizedlist>
+      <listitem> set <emphasis> .modified</emphasis> field of <type>
+        iio_chan_spec</type> to 1. Modifiers are specified using
+        <emphasis>.channel2</emphasis> field of the same
+        <type>iio_chan_spec</type> structure and are used to indicate a
+        physically unique characteristic of the channel such as its direction
+        or spectral response. For example, a light sensor can have two channels,
+        one for infrared light and one for both infrared and visible light.
+      </listitem>
+      <listitem> set <emphasis>.indexed </emphasis> field of
+        <type>iio_chan_spec</type> to 1. In this case the channel is
+        simply another instance with an index specified by the
+        <emphasis>.channel</emphasis> field.
+      </listitem>
+      </itemizedlist>
+      Here is how we can make use of the channel's modifiers:
+      <programlisting>
+      static const struct iio_chan_spec light_channels[] = {
+          {
+              .type = IIO_INTENSITY,
+              .modified = 1,
+              .channel2 = IIO_MOD_LIGHT_IR,
+              .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+              .info_mask_shared = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+          },
+          {
+              .type = IIO_INTENSITY,
+              .modified = 1,
+              .channel2 = IIO_MOD_LIGHT_BOTH,
+              .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+              .info_mask_shared = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+          },
+          {
+              .type = IIO_LIGHT,
+              .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+              .info_mask_shared = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+          },
+
+      }
+      </programlisting>
+      This channel's definition will generate two separate sysfs files
+      for raw data retrieval:
+      <itemizedlist>
+      <listitem>
+      <filename>/sys/bus/iio/iio:deviceX/in_intensity_ir_raw</filename>
+      </listitem>
+      <listitem>
+      <filename>/sys/bus/iio/iio:deviceX/in_intensity_both_raw</filename>
+      </listitem>
+      </itemizedlist>
+      one file for processed data:
+      <itemizedlist>
+      <listitem>
+      <filename>/sys/bus/iio/iio:deviceX/in_illuminance_input
+      </filename>
+      </listitem>
+      </itemizedlist>
+      and one shared sysfs file for sampling frequency:
+      <itemizedlist>
+      <listitem>
+      <filename>/sys/bus/iio/iio:deviceX/sampling_frequency.
+      </filename>
+      </listitem>
+      </itemizedlist>
+      </para>
+      <para>
+      Here is how we can make use of the channel's indexing:
+      <programlisting>
+      static const struct iio_chan_spec light_channels[] = {
+          {
+              .type = IIO_VOLTAGE,
+              .indexed = 1,
+              .channel = 0,
+              .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+          },
+          {
+              .type = IIO_VOLTAGE,
+              .indexed = 1,
+              .channel = 1,
+              .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+          },
+      }
+      </programlisting>
+      This will generate two separate attributes files for raw data
+      retrieval:
+      <itemizedlist>
+      <listitem>
+        <filename>/sys/bus/iio/devices/iio:deviceX/in_voltage0_raw</filename>,
+          representing voltage measurement for channel 0.
+      </listitem>
+      <listitem>
+        <filename>/sys/bus/iio/devices/iio:deviceX/in_voltage1_raw</filename>,
+          representing voltage measurement for channel 1.
+      </listitem>
+      </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
+
+  <sect1 id="iiobuffer"> <title> Industrial I/O buffers </title>
+!Finclude/linux/iio/buffer.h iio_buffer
+!Edrivers/iio/industrialio-buffer.c
+
+    <para>
+    The Industrial I/O core offers a way for continuous data capture
+    based on a trigger source. Multiple data channels can be read at once
+    from <filename>/dev/iio:deviceX</filename> character device node,
+    thus reducing the CPU load.
+    </para>
+
+    <sect2 id="iiobuffersysfs">
+    <title>IIO buffer sysfs interface </title>
+    <para>
+      An IIO buffer has an associated attributes directory under <filename>
+      /sys/bus/iio/iio:deviceX/buffer/</filename>. Here are the existing
+      attributes:
+      <itemizedlist>
+      <listitem>
+      <emphasis>length</emphasis>, the total number of data samples
+      (capacity) that can be stored by the buffer.
+      </listitem>
+      <listitem>
+        <emphasis>enable</emphasis>, activate buffer capture.
+      </listitem>
+      </itemizedlist>
+
+    </para>
+    </sect2>
+    <sect2 id="iiobuffersetup"> <title> IIO buffer setup </title>
+      <para>The meta information associated with a channel reading
+        placed in a buffer is called a <emphasis> scan element </emphasis>.
+        The important bits configuring scan elements are exposed to
+        userspace applications via the <filename>
+        /sys/bus/iio/iio:deviceX/scan_elements/</filename> directory. This
+        file contains attributes of the following form:
+      <itemizedlist>
+      <listitem><emphasis>enable</emphasis>, used for enabling a channel.
+        If and only if its attribute is non zero, then a triggered capture
+        will contain data samples for this channel.
+      </listitem>
+      <listitem><emphasis>type</emphasis>, description of the scan element
+        data storage within the buffer and hence the form in which it is
+        read from user space. Format is <emphasis>
+        [be|le]:[s|u]bits/storagebitsXrepeat[>>shift] </emphasis>.
+        <itemizedlist>
+        <listitem> <emphasis>be</emphasis> or <emphasis>le</emphasis>, specifies
+          big or little endian.
+        </listitem>
+        <listitem>
+        <emphasis>s </emphasis>or <emphasis>u</emphasis>, specifies if
+          signed (2's complement) or unsigned.
+        </listitem>
+        <listitem><emphasis>bits</emphasis>, is the number of valid data
+          bits.
+        </listitem>
+        <listitem><emphasis>storagebits</emphasis>, is the number of bits
+          (after padding) that it occupies in the buffer.
+        </listitem>
+        <listitem>
+        <emphasis>shift</emphasis>, if specified, is the shift that needs
+          to be applied prior to masking out unused bits.
+        </listitem>
+        <listitem>
+        <emphasis>repeat</emphasis>, specifies the number of bits/storagebits
+        repetitions. When the repeat element is 0 or 1, then the repeat
+        value is omitted.
+        </listitem>
+        </itemizedlist>
+      </listitem>
+      </itemizedlist>
+      For example, a driver for a 3-axis accelerometer with 12 bit
+      resolution where data is stored in two 8-bits registers as
+      follows:
+      <programlisting>
+        7   6   5   4   3   2   1   0
+      +---+---+---+---+---+---+---+---+
+      |D3 |D2 |D1 |D0 | X | X | X | X | (LOW byte, address 0x06)
+      +---+---+---+---+---+---+---+---+
+
+        7   6   5   4   3   2   1   0
+      +---+---+---+---+---+---+---+---+
+      |D11|D10|D9 |D8 |D7 |D6 |D5 |D4 | (HIGH byte, address 0x07)
+      +---+---+---+---+---+---+---+---+
+      </programlisting>
+
+      will have the following scan element type for each axis:
+      <programlisting>
+      $ cat /sys/bus/iio/devices/iio:device0/scan_elements/in_accel_y_type
+      le:s12/16>>4
+      </programlisting>
+      A user space application will interpret data samples read from the
+      buffer as two byte little endian signed data, that needs a 4 bits
+      right shift before masking out the 12 valid bits of data.
+    </para>
+    <para>
+      For implementing buffer support a driver should initialize the following
+      fields in <type>iio_chan_spec</type> definition:
+      <programlisting>
+          struct iio_chan_spec {
+              /* other members */
+              int scan_index
+              struct {
+                  char sign;
+                  u8 realbits;
+                  u8 storagebits;
+                  u8 shift;
+                  u8 repeat;
+                  enum iio_endian endianness;
+              } scan_type;
+          };
+      </programlisting>
+      The driver implementing the accelerometer described above will
+      have the following channel definition:
+      <programlisting>
+      struct struct iio_chan_spec accel_channels[] = {
+          {
+            .type = IIO_ACCEL,
+            .modified = 1,
+            .channel2 = IIO_MOD_X,
+            /* other stuff here */
+            .scan_index = 0,
+            .scan_type = {
+              .sign = 's',
+              .realbits = 12,
+              .storgebits = 16,
+              .shift = 4,
+              .endianness = IIO_LE,
+            },
+        }
+        /* similar for Y (with channel2 = IIO_MOD_Y, scan_index = 1)
+         * and Z (with channel2 = IIO_MOD_Z, scan_index = 2) axis
+         */
+    }
+    </programlisting>
+    </para>
+    <para>
+    Here <emphasis> scan_index </emphasis> defines the order in which
+    the enabled channels are placed inside the buffer. Channels with a lower
+    scan_index will be placed before channels with a higher index. Each
+    channel needs to have a unique scan_index.
+    </para>
+    <para>
+    Setting scan_index to -1 can be used to indicate that the specific
+    channel does not support buffered capture. In this case no entries will
+    be created for the channel in the scan_elements directory.
+    </para>
+    </sect2>
+  </sect1>
+
+  <sect1 id="iiotrigger"> <title> Industrial I/O triggers  </title>
+!Finclude/linux/iio/trigger.h iio_trigger
+!Edrivers/iio/industrialio-trigger.c
+    <para>
+      In many situations it is useful for a driver to be able to
+      capture data based on some external event (trigger) as opposed
+      to periodically polling for data. An IIO trigger can be provided
+      by a device driver that also has an IIO device based on hardware
+      generated events (e.g. data ready or threshold exceeded) or
+      provided by a separate driver from an independent interrupt
+      source (e.g. GPIO line connected to some external system, timer
+      interrupt or user space writing a specific file in sysfs). A
+      trigger may initiate data capture for a number of sensors and
+      also it may be completely unrelated to the sensor itself.
+    </para>
+
+    <sect2 id="iiotrigsysfs"> <title> IIO trigger sysfs interface </title>
+      There are two locations in sysfs related to triggers:
+      <itemizedlist>
+        <listitem><filename>/sys/bus/iio/devices/triggerY</filename>,
+          this file is created once an IIO trigger is registered with
+          the IIO core and corresponds to trigger with index Y. Because
+          triggers can be very different depending on type there are few
+          standard attributes that we can describe here:
+          <itemizedlist>
+            <listitem>
+              <emphasis>name</emphasis>, trigger name that can be later
+                used for association with a device.
+            </listitem>
+            <listitem>
+            <emphasis>sampling_frequency</emphasis>, some timer based
+              triggers use this attribute to specify the frequency for
+              trigger calls.
+            </listitem>
+          </itemizedlist>
+        </listitem>
+        <listitem>
+          <filename>/sys/bus/iio/devices/iio:deviceX/trigger/</filename>, this
+          directory is created once the device supports a triggered
+          buffer. We can associate a trigger with our device by writing
+          the trigger's name in the <filename>current_trigger</filename> file.
+        </listitem>
+      </itemizedlist>
+    </sect2>
+
+    <sect2 id="iiotrigattr"> <title> IIO trigger setup</title>
+
+    <para>
+      Let's see a simple example of how to setup a trigger to be used
+      by a driver.
+
+      <programlisting>
+      struct iio_trigger_ops trigger_ops = {
+          .set_trigger_state = sample_trigger_state,
+          .validate_device = sample_validate_device,
+      }
+
+      struct iio_trigger *trig;
+
+      /* first, allocate memory for our trigger */
+      trig = iio_trigger_alloc(dev, "trig-%s-%d", name, idx);
+
+      /* setup trigger operations field */
+      trig->ops = &amp;trigger_ops;
+
+      /* now register the trigger with the IIO core */
+      iio_trigger_register(trig);
+      </programlisting>
+    </para>
+    </sect2>
+
+    <sect2 id="iiotrigsetup"> <title> IIO trigger ops</title>
+!Finclude/linux/iio/trigger.h iio_trigger_ops
+     <para>
+        Notice that a trigger has a set of operations attached:
+        <itemizedlist>
+        <listitem>
+          <function>set_trigger_state</function>, switch the trigger on/off
+          on demand.
+        </listitem>
+        <listitem>
+          <function>validate_device</function>, function to validate the
+          device when the current trigger gets changed.
+        </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
+  <sect1 id="iiotriggered_buffer">
+    <title> Industrial I/O triggered buffers </title>
+    <para>
+    Now that we know what buffers and triggers are let's see how they
+    work together.
+    </para>
+    <sect2 id="iiotrigbufsetup"> <title> IIO triggered buffer setup</title>
+!Edrivers/iio/industrialio-triggered-buffer.c
+!Finclude/linux/iio/iio.h iio_buffer_setup_ops
+
+
+    <para>
+    A typical triggered buffer setup looks like this:
+    <programlisting>
+    const struct iio_buffer_setup_ops sensor_buffer_setup_ops = {
+      .preenable    = sensor_buffer_preenable,
+      .postenable   = sensor_buffer_postenable,
+      .postdisable  = sensor_buffer_postdisable,
+      .predisable   = sensor_buffer_predisable,
+    };
+
+    irqreturn_t sensor_iio_pollfunc(int irq, void *p)
+    {
+        pf->timestamp = iio_get_time_ns();
+        return IRQ_WAKE_THREAD;
+    }
+
+    irqreturn_t sensor_trigger_handler(int irq, void *p)
+    {
+        u16 buf[8];
+        int i = 0;
+
+        /* read data for each active channel */
+        for_each_set_bit(bit, active_scan_mask, masklength)
+            buf[i++] = sensor_get_data(bit)
+
+        iio_push_to_buffers_with_timestamp(indio_dev, buf, timestamp);
+
+        iio_trigger_notify_done(trigger);
+        return IRQ_HANDLED;
+    }
+
+    /* setup triggered buffer, usually in probe function */
+    iio_triggered_buffer_setup(indio_dev, sensor_iio_polfunc,
+                               sensor_trigger_handler,
+                               sensor_buffer_setup_ops);
+    </programlisting>
+    </para>
+    The important things to notice here are:
+    <itemizedlist>
+    <listitem><function> iio_buffer_setup_ops</function>, the buffer setup
+    functions to be called at predefined points in the buffer configuration
+    sequence (e.g. before enable, after disable). If not specified, the
+    IIO core uses the default <type>iio_triggered_buffer_setup_ops</type>.
+    </listitem>
+    <listitem><function>sensor_iio_pollfunc</function>, the function that
+    will be used as top half of poll function. It should do as little
+    processing as possible, because it runs in interrupt context. The most
+    common operation is recording of the current timestamp and for this reason
+    one can use the IIO core defined <function>iio_pollfunc_store_time
+    </function> function.
+    </listitem>
+    <listitem><function>sensor_trigger_handler</function>, the function that
+    will be used as bottom half of the poll function. This runs in the
+    context of a kernel thread and all the processing takes place here.
+    It usually reads data from the device and stores it in the internal
+    buffer together with the timestamp recorded in the top half.
+    </listitem>
+    </itemizedlist>
+    </sect2>
+  </sect1>
+  </chapter>
+  <chapter id='iioresources'>
+    <title> Resources </title>
+      IIO core may change during time so the best documentation to read is the
+      source code. There are several locations where you should look:
+      <itemizedlist>
+        <listitem>
+          <filename>drivers/iio/</filename>, contains the IIO core plus
+          and directories for each sensor type (e.g. accel, magnetometer,
+          etc.)
+        </listitem>
+        <listitem>
+          <filename>include/linux/iio/</filename>, contains the header
+          files, nice to read for the internal kernel interfaces.
+        </listitem>
+        <listitem>
+        <filename>include/uapi/linux/iio/</filename>, contains files to be
+          used by user space applications.
+        </listitem>
+        <listitem>
+         <filename>tools/iio/</filename>, contains tools for rapidly
+          testing buffers, events and device creation.
+        </listitem>
+        <listitem>
+          <filename>drivers/staging/iio/</filename>, contains code for some
+          drivers or experimental features that are not yet mature enough
+          to be moved out.
+        </listitem>
+      </itemizedlist>
+    <para>
+    Besides the code, there are some good online documentation sources:
+    <itemizedlist>
+    <listitem>
+      <ulink url="http://marc.info/?l=linux-iio"> Industrial I/O mailing
+      list </ulink>
+    </listitem>
+    <listitem>
+      <ulink url="http://wiki.analog.com/software/linux/docs/iio/iio">
+      Analog Device IIO wiki page </ulink>
+    </listitem>
+    <listitem>
+      <ulink url="https://fosdem.org/2015/schedule/event/iiosdr/">
+      Using the Linux IIO framework for SDR, Lars-Peter Clausen's
+      presentation at FOSDEM </ulink>
+    </listitem>
+    </itemizedlist>
+    </para>
+  </chapter>
+</book>
+
+<!--
+vim: softtabstop=2:shiftwidth=2:expandtab:textwidth=72
+-->
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index 23996f88cd58..08527e7ea4d0 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -199,7 +199,8 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)-mkdir $(MEDIA_OBJ_DIR)/media_api; \
+	cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/DocBook/media/dvb/intro.xml b/Documentation/DocBook/media/dvb/intro.xml
index bcc72c216402..51db15648099 100644
--- a/Documentation/DocBook/media/dvb/intro.xml
+++ b/Documentation/DocBook/media/dvb/intro.xml
@@ -163,9 +163,8 @@ are called:</para>
 <para>where N enumerates the DVB PCI cards in a system starting
 from&#x00A0;0, and M enumerates the devices of each type within each
 adapter, starting from&#x00A0;0, too. We will omit the &#8220;
-<constant>/dev/dvb/adapterN/</constant>&#8221; in the further dicussion
-of these devices. The naming scheme for the devices is the same wheter
-devfs is used or not.</para>
+<constant>/dev/dvb/adapterN/</constant>&#8221; in the further discussion
+of these devices.</para>
 
 <para>More details about the data structures and function calls of all
 the devices are described in the following chapters.</para>
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index 6e1667b5f3eb..33aece541880 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -3414,7 +3414,7 @@ giving priority to the center of the metered area.</entry>
 		<row>
 		  <entry><constant>V4L2_EXPOSURE_METERING_MATRIX</constant>&nbsp;</entry>
 		  <entry>A multi-zone metering. The light intensity is measured
-in several points of the frame and the the results are combined. The
+in several points of the frame and the results are combined. The
 algorithm of the zones selection and their significance in calculating the
 final value is device dependent.</entry>
 		</row>
diff --git a/Documentation/DocBook/media/v4l/media-ioc-device-info.xml b/Documentation/DocBook/media/v4l/media-ioc-device-info.xml
index 2ce521419e67..b0a21ac300b8 100644
--- a/Documentation/DocBook/media/v4l/media-ioc-device-info.xml
+++ b/Documentation/DocBook/media/v4l/media-ioc-device-info.xml
@@ -102,7 +102,7 @@
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
-	    <entry><structfield>media_version</structfield></entry>
+	    <entry><structfield>driver_version</structfield></entry>
 	    <entry>Media device driver version, formatted with the
 	    <constant>KERNEL_VERSION()</constant> macro. Together with the
 	    <structfield>driver</structfield> field this identifies a particular
diff --git a/Documentation/DocBook/media/v4l/vidioc-expbuf.xml b/Documentation/DocBook/media/v4l/vidioc-expbuf.xml
index a78c9207422f..0ae0b6a915d0 100644
--- a/Documentation/DocBook/media/v4l/vidioc-expbuf.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-expbuf.xml
@@ -62,28 +62,28 @@ buffer as a DMABUF file at any time after buffers have been allocated with the
 &VIDIOC-REQBUFS; ioctl.</para>
 
 <para> To export a buffer, applications fill &v4l2-exportbuffer;.  The
-<structfield> type </structfield> field is set to the same buffer type as was
-previously used with  &v4l2-requestbuffers;<structfield> type </structfield>.
-Applications must also set the <structfield> index </structfield> field. Valid
+<structfield>type</structfield> field is set to the same buffer type as was
+previously used with &v4l2-requestbuffers; <structfield>type</structfield>.
+Applications must also set the <structfield>index</structfield> field. Valid
 index numbers range from zero to the number of buffers allocated with
-&VIDIOC-REQBUFS; (&v4l2-requestbuffers;<structfield> count </structfield>)
-minus one.  For the multi-planar API, applications set the <structfield> plane
-</structfield> field to the index of the plane to be exported. Valid planes
+&VIDIOC-REQBUFS; (&v4l2-requestbuffers; <structfield>count</structfield>)
+minus one.  For the multi-planar API, applications set the <structfield>plane</structfield>
+field to the index of the plane to be exported. Valid planes
 range from zero to the maximal number of valid planes for the currently active
-format. For the single-planar API, applications must set <structfield> plane
-</structfield> to zero.  Additional flags may be posted in the <structfield>
-flags </structfield> field.  Refer to a manual for open() for details.
+format. For the single-planar API, applications must set <structfield>plane</structfield>
+to zero.  Additional flags may be posted in the <structfield>flags</structfield>
+field.  Refer to a manual for open() for details.
 Currently only O_CLOEXEC, O_RDONLY, O_WRONLY, and O_RDWR are supported.  All
 other fields must be set to zero.
 In the case of multi-planar API, every plane is exported separately using
-multiple <constant> VIDIOC_EXPBUF </constant> calls. </para>
+multiple <constant>VIDIOC_EXPBUF</constant> calls.</para>
 
-<para> After calling <constant>VIDIOC_EXPBUF</constant> the <structfield> fd
-</structfield> field will be set by a driver.  This is a DMABUF file
+<para>After calling <constant>VIDIOC_EXPBUF</constant> the <structfield>fd</structfield>
+field will be set by a driver.  This is a DMABUF file
 descriptor. The application may pass it to other DMABUF-aware devices. Refer to
 <link linkend="dmabuf">DMABUF importing</link> for details about importing
 DMABUF files into V4L2 nodes. It is recommended to close a DMABUF file when it
-is no longer used to allow the associated memory to be reclaimed. </para>
+is no longer used to allow the associated memory to be reclaimed.</para>
   </refsect1>
 
   <refsect1>
@@ -170,9 +170,9 @@ multi-planar API. Otherwise this value must be set to zero. </entry>
 	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>flags</structfield></entry>
-	    <entry>Flags for the newly created file, currently only <constant>
-O_CLOEXEC </constant>, <constant>O_RDONLY</constant>, <constant>O_WRONLY
-</constant>, and <constant>O_RDWR</constant> are supported, refer to the manual
+	    <entry>Flags for the newly created file, currently only
+<constant>O_CLOEXEC</constant>, <constant>O_RDONLY</constant>, <constant>O_WRONLY</constant>,
+and <constant>O_RDWR</constant> are supported, refer to the manual
 of open() for more details.</entry>
 	  </row>
 	  <row>
@@ -200,9 +200,9 @@ set the array to zero.</entry>
 	<term><errorcode>EINVAL</errorcode></term>
 	<listitem>
 	  <para>A queue is not in MMAP mode or DMABUF exporting is not
-supported or <structfield> flags </structfield> or <structfield> type
-</structfield> or <structfield> index </structfield> or <structfield> plane
-</structfield> fields are invalid.</para>
+supported or <structfield>flags</structfield> or <structfield>type</structfield>
+or <structfield>index</structfield> or <structfield>plane</structfield> fields
+are invalid.</para>
 	</listitem>
       </varlistentry>
     </variablelist>
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-parm.xml b/Documentation/DocBook/media/v4l/vidioc-g-parm.xml
index f4e28e7d4751..721728745407 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-parm.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-parm.xml
@@ -267,7 +267,7 @@ is intended for still imaging applications. The idea is to get the
 best possible image quality that the hardware can deliver. It is not
 defined how the driver writer may achieve that; it will depend on the
 hardware and the ingenuity of the driver writer. High quality mode is
-a different mode from the the regular motion video capture modes. In
+a different mode from the regular motion video capture modes. In
 high quality mode:<itemizedlist>
 		  <listitem>
 		    <para>The driver may be able to capture higher
diff --git a/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml b/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml
index dc83ad70f8dc..6ec39c698baf 100644
--- a/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-queryctrl.xml
@@ -616,7 +616,7 @@ pointer to memory containing the payload of the control.</entry>
 	    <entry><constant>V4L2_CTRL_FLAG_EXECUTE_ON_WRITE</constant></entry>
 	    <entry>0x0200</entry>
 	    <entry>The value provided to the control will be propagated to the driver
-even if remains constant. This is required when the control represents an action
+even if it remains constant. This is required when the control represents an action
 on the hardware. For example: clearing an error flag or triggering the flash. All the
 controls of the type <constant>V4L2_CTRL_TYPE_BUTTON</constant> have this flag set.</entry>
 	  </row>
diff --git a/Documentation/DocBook/stylesheet.xsl b/Documentation/DocBook/stylesheet.xsl
index 85b25275196f..3bf4ecf3d760 100644
--- a/Documentation/DocBook/stylesheet.xsl
+++ b/Documentation/DocBook/stylesheet.xsl
@@ -5,6 +5,7 @@
 <param name="funcsynopsis.tabular.threshold">80</param>
 <param name="callout.graphics">0</param>
 <!-- <param name="paper.type">A4</param> -->
+<param name="generate.consistent.ids">1</param>
 <param name="generate.section.toc.level">2</param>
 <param name="use.id.as.filename">1</param>
 </stylesheet>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 93aa8604630e..21152d397b88 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -218,16 +218,16 @@ The development process
 Linux kernel development process currently consists of a few different
 main kernel "branches" and lots of different subsystem-specific kernel
 branches.  These different branches are:
-  - main 3.x kernel tree
-  - 3.x.y -stable kernel tree
-  - 3.x -git kernel patches
+  - main 4.x kernel tree
+  - 4.x.y -stable kernel tree
+  - 4.x -git kernel patches
   - subsystem specific kernel trees and patches
-  - the 3.x -next kernel tree for integration tests
+  - the 4.x -next kernel tree for integration tests
 
-3.x kernel tree
+4.x kernel tree
 -----------------
-3.x kernels are maintained by Linus Torvalds, and can be found on
-kernel.org in the pub/linux/kernel/v3.x/ directory.  Its development
+4.x kernels are maintained by Linus Torvalds, and can be found on
+kernel.org in the pub/linux/kernel/v4.x/ directory.  Its development
 process is as follows:
   - As soon as a new kernel is released a two weeks window is open,
     during this period of time maintainers can submit big diffs to
@@ -262,20 +262,20 @@ mailing list about kernel releases:
 	released according to perceived bug status, not according to a
 	preconceived timeline."
 
-3.x.y -stable kernel tree
+4.x.y -stable kernel tree
 ---------------------------
 Kernels with 3-part versions are -stable kernels. They contain
 relatively small and critical fixes for security problems or significant
-regressions discovered in a given 3.x kernel.
+regressions discovered in a given 4.x kernel.
 
 This is the recommended branch for users who want the most recent stable
 kernel and are not interested in helping test development/experimental
 versions.
 
-If no 3.x.y kernel is available, then the highest numbered 3.x
+If no 4.x.y kernel is available, then the highest numbered 4.x
 kernel is the current stable kernel.
 
-3.x.y are maintained by the "stable" team <stable@vger.kernel.org>, and
+4.x.y are maintained by the "stable" team <stable@vger.kernel.org>, and
 are released as needs dictate.  The normal release period is approximately
 two weeks, but it can be longer if there are no pressing problems.  A
 security-related problem, instead, can cause a release to happen almost
@@ -285,7 +285,7 @@ The file Documentation/stable_kernel_rules.txt in the kernel tree
 documents what kinds of changes are acceptable for the -stable tree, and
 how the release process works.
 
-3.x -git patches
+4.x -git patches
 ------------------
 These are daily snapshots of Linus' kernel tree which are managed in a
 git repository (hence the name.) These patches are usually released
@@ -317,9 +317,9 @@ revisions to it, and maintainers can mark patches as under review,
 accepted, or rejected.  Most of these patchwork sites are listed at
 http://patchwork.kernel.org/.
 
-3.x -next kernel tree for integration tests
+4.x -next kernel tree for integration tests
 ---------------------------------------------
-Before updates from subsystem trees are merged into the mainline 3.x
+Before updates from subsystem trees are merged into the mainline 4.x
 tree, they need to be integration-tested.  For this purpose, a special
 testing repository exists into which virtually all subsystem trees are
 pulled on an almost daily basis:
diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt
index cf9431db8731..7b57fc087088 100644
--- a/Documentation/Intel-IOMMU.txt
+++ b/Documentation/Intel-IOMMU.txt
@@ -10,7 +10,7 @@ This guide gives a quick cheat sheet for some basic understanding.
 Some Keywords
 
 DMAR - DMA remapping
-DRHD - DMA Engine Reporting Structure
+DRHD - DMA Remapping Hardware Unit Definition
 RMRR - Reserved memory Region Reporting Structure
 ZLR  - Zero length reads from PCI devices
 IOVA - IO Virtual address.
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index 1e6c0da994f5..c0bf2441a2ba 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -28,7 +28,7 @@ o	You must use one of the rcu_dereference() family of primitives
 o	Avoid cancellation when using the "+" and "-" infix arithmetic
 	operators.  For example, for a given variable "x", avoid
 	"(x-x)".  There are similar arithmetic pitfalls from other
-	arithmetic operatiors, such as "(x*0)", "(x/(x+1))" or "(x%1)".
+	arithmetic operators, such as "(x*0)", "(x/(x+1))" or "(x%1)".
 	The compiler is within its rights to substitute zero for all of
 	these expressions, so that subsequent accesses no longer depend
 	on the rcu_dereference(), again possibly resulting in bugs due
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index b57c0c1cdac6..efb9454875ab 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -26,12 +26,6 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 	Stall-warning messages may be enabled and disabled completely via
 	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
 
-CONFIG_RCU_CPU_STALL_INFO
-
-	This kernel configuration parameter causes the stall warning to
-	print out additional per-CPU diagnostic information, including
-	information on scheduling-clock ticks and RCU's idle-CPU tracking.
-
 RCU_STALL_DELAY_DELTA
 
 	Although the lockdep facility is extremely useful, it does add
@@ -101,15 +95,13 @@ interact.  Please note that it is not possible to entirely eliminate this
 sort of false positive without resorting to things like stop_machine(),
 which is overkill for this sort of problem.
 
-If the CONFIG_RCU_CPU_STALL_INFO kernel configuration parameter is set,
-more information is printed with the stall-warning message, for example:
+Recent kernels will print a long form of the stall-warning message:
 
 	INFO: rcu_preempt detected stall on CPU
 	0: (63959 ticks this GP) idle=241/3fffffffffffffff/0 softirq=82/543
 	   (t=65000 jiffies)
 
-In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is
-printed:
+In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed:
 
 	INFO: rcu_preempt detected stall on CPU
 	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 nonlazy_posted: 25 .D
@@ -171,6 +163,23 @@ message will be about three times the interval between the beginning
 of the stall and the first message.
 
 
+Stall Warnings for Expedited Grace Periods
+
+If an expedited grace period detects a stall, it will place a message
+like the following in dmesg:
+
+	INFO: rcu_sched detected expedited stalls on CPUs: { 1 2 6 } 26009 jiffies s: 1043
+
+This indicates that CPUs 1, 2, and 6 have failed to respond to a
+reschedule IPI, that the expedited grace period has been going on for
+26,009 jiffies, and that the expedited grace-period sequence counter is
+1043.  The fact that this last value is odd indicates that an expedited
+grace period is in flight.
+
+It is entirely possible to see stall warnings from normal and from
+expedited grace periods at about the same time from the same run.
+
+
 What Causes RCU CPU Stall Warnings?
 
 So your kernel printed an RCU CPU stall warning.  The next question is
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 08651da15448..97f17e9decda 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -237,42 +237,26 @@ o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 
 The output of "cat rcu/rcu_preempt/rcuexp" looks as follows:
 
-s=21872 d=21872 w=0 tf=0 wd1=0 wd2=0 n=0 sc=21872 dt=21872 dl=0 dx=21872
+s=21872 wd0=0 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872
 
 These fields are as follows:
 
-o	"s" is the starting sequence number.
+o	"s" is the sequence number, with an odd number indicating that
+	an expedited grace period is in progress.
 
-o	"d" is the ending sequence number.  When the starting and ending
-	numbers differ, there is an expedited grace period in progress.
-
-o	"w" is the number of times that the sequence numbers have been
-	in danger of wrapping.
-
-o	"tf" is the number of times that contention has resulted in a
-	failure to begin an expedited grace period.
-
-o	"wd1" and "wd2" are the number of times that an attempt to
-	start an expedited grace period found that someone else had
-	completed an expedited grace period that satisfies the
+o	"wd0", "wd1", "wd2", and "wd3" are the number of times that an
+	attempt to start an expedited grace period found that someone
+	else had completed an expedited grace period that satisfies the
 	attempted request.  "Our work is done."
 
-o	"n" is number of times that contention was so great that
-	the request was demoted from an expedited grace period to
-	a normal grace period.
+o	"n" is number of times that a concurrent CPU-hotplug operation
+	forced a fallback to a normal grace period.
+
+o	"enq" is the number of quiescent states still outstanding.
 
 o	"sc" is the number of times that the attempt to start a
 	new expedited grace period succeeded.
 
-o	"dt" is the number of times that we attempted to update
-	the "d" counter.
-
-o	"dl" is the number of times that we failed to update the "d"
-	counter.
-
-o	"dx" is the number of times that we succeeded in updating
-	the "d" counter.
-
 
 The output of "cat rcu/rcu_preempt/rcugp" looks as follows:
 
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 5746b0c77f3e..adc2184009c5 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -883,7 +883,7 @@ All:  lockdep-checked RCU-protected pointer access
 
 	rcu_access_pointer
 	rcu_dereference_raw
-	rcu_lockdep_assert
+	RCU_LOCKDEP_WARN
 	rcu_sleep_check
 	RCU_NONIDLE
 
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 27e7e5edeca8..fd89b04d34f0 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -90,11 +90,11 @@ patch.
 
 Make sure your patch does not include any extra files which do not
 belong in a patch submission.  Make sure to review your patch -after-
-generated it with diff(1), to ensure accuracy.
+generating it with diff(1), to ensure accuracy.
 
 If your changes produce a lot of deltas, you need to split them into
 individual patches which modify things in logical stages; see section
-#3.  This will facilitate easier reviewing by other kernel developers,
+#3.  This will facilitate review by other kernel developers,
 very important if you want your patch accepted.
 
 If you're using git, "git rebase -i" can help you with this process.  If
@@ -267,7 +267,7 @@ You should always copy the appropriate subsystem maintainer(s) on any patch
 to code that they maintain; look through the MAINTAINERS file and the
 source code revision history to see who those maintainers are.  The
 script scripts/get_maintainer.pl can be very useful at this step.  If you
-cannot find a maintainer for the subsystem your are working on, Andrew
+cannot find a maintainer for the subsystem you are working on, Andrew
 Morton (akpm@linux-foundation.org) serves as a maintainer of last resort.
 
 You should also normally choose at least one mailing list to receive a copy
@@ -291,7 +291,7 @@ sending him e-mail.
 
 If you have a patch that fixes an exploitable security bug, send that patch
 to security@kernel.org.  For severe bugs, a short embargo may be considered
-to allow distrbutors to get the patch out to users; in such cases,
+to allow distributors to get the patch out to users; in such cases,
 obviously, the patch should not be sent to any public lists.
 
 Patches that fix a severe bug in a released kernel should be directed
@@ -340,7 +340,7 @@ on the changes you are submitting.  It is important for a kernel
 developer to be able to "quote" your changes, using standard e-mail
 tools, so that they may comment on specific portions of your code.
 
-For this reason, all patches should be submitting e-mail "inline".
+For this reason, all patches should be submitted by e-mail "inline".
 WARNING:  Be wary of your editor's word-wrap corrupting your patch,
 if you choose to cut-n-paste your patch.
 
@@ -739,7 +739,7 @@ interest on a single line; it should look something like:
 
       git://jdelvare.pck.nerim.net/jdelvare-2.6 i2c-for-linus
 
-  to get these changes:"
+  to get these changes:
 
 A pull request should also include an overall message saying what will be
 included in the request, a "git shortlog" listing of the patches
@@ -796,7 +796,7 @@ NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!
   <https://lkml.org/lkml/2005/7/11/336>
 
 Kernel Documentation/CodingStyle:
-  <http://users.sosdg.org/~qiyong/lxr/source/Documentation/CodingStyle>
+  <Documentation/CodingStyle>
 
 Linus Torvalds's mail on the canonical patch format:
   <http://lkml.org/lkml/2005/4/7/183>
diff --git a/Documentation/acpi/method-tracing.txt b/Documentation/acpi/method-tracing.txt
index f6efb1ea559a..c2505eefc878 100644
--- a/Documentation/acpi/method-tracing.txt
+++ b/Documentation/acpi/method-tracing.txt
@@ -1,26 +1,192 @@
-/sys/module/acpi/parameters/:
+ACPICA Trace Facility
 
-trace_method_name
-	The AML method name that the user wants to trace
+Copyright (C) 2015, Intel Corporation
+Author: Lv Zheng <lv.zheng@intel.com>
 
-trace_debug_layer
-	The temporary debug_layer used when tracing the method.
-	Using 0xffffffff by default if it is 0.
 
-trace_debug_level
-	The temporary debug_level used when tracing the method.
-	Using 0x00ffffff by default if it is 0.
+Abstract:
 
-trace_state
-	The status of the tracing feature.
+This document describes the functions and the interfaces of the method
+tracing facility.
+
+1. Functionalities and usage examples:
+
+   ACPICA provides method tracing capability. And two functions are
+   currently implemented using this capability.
+
+   A. Log reducer
+   ACPICA subsystem provides debugging outputs when CONFIG_ACPI_DEBUG is
+   enabled. The debugging messages which are deployed via
+   ACPI_DEBUG_PRINT() macro can be reduced at 2 levels - per-component
+   level (known as debug layer, configured via
+   /sys/module/acpi/parameters/debug_layer) and per-type level (known as
+   debug level, configured via /sys/module/acpi/parameters/debug_level).
+
+   But when the particular layer/level is applied to the control method
+   evaluations, the quantity of the debugging outputs may still be too
+   large to be put into the kernel log buffer. The idea thus is worked out
+   to only enable the particular debug layer/level (normally more detailed)
+   logs when the control method evaluation is started, and disable the
+   detailed logging when the control method evaluation is stopped.
+
+   The following command examples illustrate the usage of the "log reducer"
+   functionality:
+   a. Filter out the debug layer/level matched logs when control methods
+      are being evaluated:
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "enable" > trace_state
+   b. Filter out the debug layer/level matched logs when the specified
+      control method is being evaluated:
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method" > /sys/module/acpi/parameters/trace_state
+   c. Filter out the debug layer/level matched logs when the specified
+      control method is being evaluated for the first time:
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method-once" > /sys/module/acpi/parameters/trace_state
+   Where:
+      0xXXXXXXXX/0xYYYYYYYY: Refer to Documentation/acpi/debug.txt for
+			     possible debug layer/level masking values.
+      \PPPP.AAAA.TTTT.HHHH: Full path of a control method that can be found
+			    in the ACPI namespace. It needn't be an entry
+			    of a control method evaluation.
+
+   B. AML tracer
+
+   There are special log entries added by the method tracing facility at
+   the "trace points" the AML interpreter starts/stops to execute a control
+   method, or an AML opcode. Note that the format of the log entries are
+   subject to change:
+     [    0.186427]   exdebug-0398 ex_trace_point        : Method Begin [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
+     [    0.186630]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905c88:If] execution.
+     [    0.186820]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:LEqual] execution.
+     [    0.187010]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905a20:-NamePath-] execution.
+     [    0.187214]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905a20:-NamePath-] execution.
+     [    0.187407]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
+     [    0.187594]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
+     [    0.187789]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:LEqual] execution.
+     [    0.187980]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:Return] execution.
+     [    0.188146]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
+     [    0.188334]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
+     [    0.188524]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:Return] execution.
+     [    0.188712]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905c88:If] execution.
+     [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
 
-	"enabled" means this feature is enabled
-	and the AML method is traced every time it's executed.
+   Developers can utilize these special log entries to track the AML
+   interpretion, thus can aid issue debugging and performance tuning. Note
+   that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
+   macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
+   "AML tracer" logs.
 
-	"1" means this feature is enabled and the AML method
-	will only be traced during the next execution.
+   The following command examples illustrate the usage of the "AML tracer"
+   functionality:
+   a. Filter out the method start/stop "AML tracer" logs when control
+      methods are being evaluated:
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "enable" > trace_state
+   b. Filter out the method start/stop "AML tracer" when the specified
+      control method is being evaluated:
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method" > trace_state
+   c. Filter out the method start/stop "AML tracer" logs when the specified
+      control method is being evaluated for the first time:
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method-once" > trace_state
+   d. Filter out the method/opcode start/stop "AML tracer" when the
+      specified control method is being evaluated:
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "opcode" > trace_state
+   e. Filter out the method/opcode start/stop "AML tracer" when the
+      specified control method is being evaluated for the first time:
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "opcode-opcode" > trace_state
 
-	"disabled" means this feature is disabled.
-	Users can enable/disable this debug tracing feature by
-	"echo string > /sys/module/acpi/parameters/trace_state".
-	"string" should be one of "enable", "disable" and "1".
+  Note that all above method tracing facility related module parameters can
+  be used as the boot parameters, for example:
+      acpi.trace_debug_layer=0x80 acpi.trace_debug_level=0x10 \
+      acpi.trace_method_name=\_SB.LID0._LID acpi.trace_state=opcode-once
+
+2. Interface descriptions:
+
+   All method tracing functions can be configured via ACPI module
+   parameters that are accessible at /sys/module/acpi/parameters/:
+
+   trace_method_name
+	The full path of the AML method that the user wants to trace.
+	Note that the full path shouldn't contain the trailing "_"s in its
+	name segments but may contain "\" to form an absolute path.
+
+   trace_debug_layer
+	The temporary debug_layer used when the tracing feature is enabled.
+	Using ACPI_EXECUTER (0x80) by default, which is the debug_layer
+	used to match all "AML tracer" logs.
+
+   trace_debug_level
+	The temporary debug_level used when the tracing feature is enabled.
+	Using ACPI_LV_TRACE_POINT (0x10) by default, which is the
+	debug_level used to match all "AML tracer" logs.
+
+   trace_state
+	The status of the tracing feature.
+	Users can enable/disable this debug tracing feature by executing
+	the following command:
+	    # echo string > /sys/module/acpi/parameters/trace_state
+	Where "string" should be one of the followings:
+	"disable"
+	    Disable the method tracing feature.
+	"enable"
+	    Enable the method tracing feature.
+	    ACPICA debugging messages matching
+	    "trace_debug_layer/trace_debug_level" during any method
+	    execution will be logged.
+	"method"
+	    Enable the method tracing feature.
+	    ACPICA debugging messages matching
+	    "trace_debug_layer/trace_debug_level" during method execution
+	    of "trace_method_name" will be logged.
+	"method-once"
+	    Enable the method tracing feature.
+	    ACPICA debugging messages matching
+	    "trace_debug_layer/trace_debug_level" during method execution
+	    of "trace_method_name" will be logged only once.
+	"opcode"
+	    Enable the method tracing feature.
+	    ACPICA debugging messages matching
+	    "trace_debug_layer/trace_debug_level" during method/opcode
+	    execution of "trace_method_name" will be logged.
+	"opcode-once"
+	    Enable the method tracing feature.
+	    ACPICA debugging messages matching
+	    "trace_debug_layer/trace_debug_level" during method/opcode
+	    execution of "trace_method_name" will be logged only once.
+	Note that, the difference between the "enable" and other feature
+        enabling options are:
+	1. When "enable" is specified, since
+	   "trace_debug_layer/trace_debug_level" shall apply to all control
+	   method evaluations, after configuring "trace_state" to "enable",
+	   "trace_method_name" will be reset to NULL.
+	2. When "method/opcode" is specified, if
+	   "trace_method_name" is NULL when "trace_state" is configured to
+	   these options, the "trace_debug_layer/trace_debug_level" will
+	   apply to all control method evaluations.
diff --git a/Documentation/adding-syscalls.txt b/Documentation/adding-syscalls.txt
new file mode 100644
index 000000000000..cc2d4ac4f404
--- /dev/null
+++ b/Documentation/adding-syscalls.txt
@@ -0,0 +1,527 @@
+Adding a New System Call
+========================
+
+This document describes what's involved in adding a new system call to the
+Linux kernel, over and above the normal submission advice in
+Documentation/SubmittingPatches.
+
+
+System Call Alternatives
+------------------------
+
+The first thing to consider when adding a new system call is whether one of
+the alternatives might be suitable instead.  Although system calls are the
+most traditional and most obvious interaction points between userspace and the
+kernel, there are other possibilities -- choose what fits best for your
+interface.
+
+ - If the operations involved can be made to look like a filesystem-like
+   object, it may make more sense to create a new filesystem or device.  This
+   also makes it easier to encapsulate the new functionality in a kernel module
+   rather than requiring it to be built into the main kernel.
+     - If the new functionality involves operations where the kernel notifies
+       userspace that something has happened, then returning a new file
+       descriptor for the relevant object allows userspace to use
+       poll/select/epoll to receive that notification.
+     - However, operations that don't map to read(2)/write(2)-like operations
+       have to be implemented as ioctl(2) requests, which can lead to a
+       somewhat opaque API.
+ - If you're just exposing runtime system information, a new node in sysfs
+   (see Documentation/filesystems/sysfs.txt) or the /proc filesystem may be
+   more appropriate.  However, access to these mechanisms requires that the
+   relevant filesystem is mounted, which might not always be the case (e.g.
+   in a namespaced/sandboxed/chrooted environment).  Avoid adding any API to
+   debugfs, as this is not considered a 'production' interface to userspace.
+ - If the operation is specific to a particular file or file descriptor, then
+   an additional fcntl(2) command option may be more appropriate.  However,
+   fcntl(2) is a multiplexing system call that hides a lot of complexity, so
+   this option is best for when the new function is closely analogous to
+   existing fcntl(2) functionality, or the new functionality is very simple
+   (for example, getting/setting a simple flag related to a file descriptor).
+ - If the operation is specific to a particular task or process, then an
+   additional prctl(2) command option may be more appropriate.  As with
+   fcntl(2), this system call is a complicated multiplexor so is best reserved
+   for near-analogs of existing prctl() commands or getting/setting a simple
+   flag related to a process.
+
+
+Designing the API: Planning for Extension
+-----------------------------------------
+
+A new system call forms part of the API of the kernel, and has to be supported
+indefinitely.  As such, it's a very good idea to explicitly discuss the
+interface on the kernel mailing list, and it's important to plan for future
+extensions of the interface.
+
+(The syscall table is littered with historical examples where this wasn't done,
+together with the corresponding follow-up system calls -- eventfd/eventfd2,
+dup2/dup3, inotify_init/inotify_init1,  pipe/pipe2, renameat/renameat2 -- so
+learn from the history of the kernel and plan for extensions from the start.)
+
+For simpler system calls that only take a couple of arguments, the preferred
+way to allow for future extensibility is to include a flags argument to the
+system call.  To make sure that userspace programs can safely use flags
+between kernel versions, check whether the flags value holds any unknown
+flags, and reject the system call (with EINVAL) if it does:
+
+    if (flags & ~(THING_FLAG1 | THING_FLAG2 | THING_FLAG3))
+        return -EINVAL;
+
+(If no flags values are used yet, check that the flags argument is zero.)
+
+For more sophisticated system calls that involve a larger number of arguments,
+it's preferred to encapsulate the majority of the arguments into a structure
+that is passed in by pointer.  Such a structure can cope with future extension
+by including a size argument in the structure:
+
+    struct xyzzy_params {
+        u32 size; /* userspace sets p->size = sizeof(struct xyzzy_params) */
+        u32 param_1;
+        u64 param_2;
+        u64 param_3;
+    };
+
+As long as any subsequently added field, say param_4, is designed so that a
+zero value gives the previous behaviour, then this allows both directions of
+version mismatch:
+
+ - To cope with a later userspace program calling an older kernel, the kernel
+   code should check that any memory beyond the size of the structure that it
+   expects is zero (effectively checking that param_4 == 0).
+ - To cope with an older userspace program calling a newer kernel, the kernel
+   code can zero-extend a smaller instance of the structure (effectively
+   setting param_4 = 0).
+
+See perf_event_open(2) and the perf_copy_attr() function (in
+kernel/events/core.c) for an example of this approach.
+
+
+Designing the API: Other Considerations
+---------------------------------------
+
+If your new system call allows userspace to refer to a kernel object, it
+should use a file descriptor as the handle for that object -- don't invent a
+new type of userspace object handle when the kernel already has mechanisms and
+well-defined semantics for using file descriptors.
+
+If your new xyzzy(2) system call does return a new file descriptor, then the
+flags argument should include a value that is equivalent to setting O_CLOEXEC
+on the new FD.  This makes it possible for userspace to close the timing
+window between xyzzy() and calling fcntl(fd, F_SETFD, FD_CLOEXEC), where an
+unexpected fork() and execve() in another thread could leak a descriptor to
+the exec'ed program. (However, resist the temptation to re-use the actual value
+of the O_CLOEXEC constant, as it is architecture-specific and is part of a
+numbering space of O_* flags that is fairly full.)
+
+If your system call returns a new file descriptor, you should also consider
+what it means to use the poll(2) family of system calls on that file
+descriptor. Making a file descriptor ready for reading or writing is the
+normal way for the kernel to indicate to userspace that an event has
+occurred on the corresponding kernel object.
+
+If your new xyzzy(2) system call involves a filename argument:
+
+    int sys_xyzzy(const char __user *path, ..., unsigned int flags);
+
+you should also consider whether an xyzzyat(2) version is more appropriate:
+
+    int sys_xyzzyat(int dfd, const char __user *path, ..., unsigned int flags);
+
+This allows more flexibility for how userspace specifies the file in question;
+in particular it allows userspace to request the functionality for an
+already-opened file descriptor using the AT_EMPTY_PATH flag, effectively giving
+an fxyzzy(3) operation for free:
+
+ - xyzzyat(AT_FDCWD, path, ..., 0) is equivalent to xyzzy(path,...)
+ - xyzzyat(fd, "", ..., AT_EMPTY_PATH) is equivalent to fxyzzy(fd, ...)
+
+(For more details on the rationale of the *at() calls, see the openat(2) man
+page; for an example of AT_EMPTY_PATH, see the statat(2) man page.)
+
+If your new xyzzy(2) system call involves a parameter describing an offset
+within a file, make its type loff_t so that 64-bit offsets can be supported
+even on 32-bit architectures.
+
+If your new xyzzy(2) system call involves privileged functionality, it needs
+to be governed by the appropriate Linux capability bit (checked with a call to
+capable()), as described in the capabilities(7) man page.  Choose an existing
+capability bit that governs related functionality, but try to avoid combining
+lots of only vaguely related functions together under the same bit, as this
+goes against capabilities' purpose of splitting the power of root.  In
+particular, avoid adding new uses of the already overly-general CAP_SYS_ADMIN
+capability.
+
+If your new xyzzy(2) system call manipulates a process other than the calling
+process, it should be restricted (using a call to ptrace_may_access()) so that
+only a calling process with the same permissions as the target process, or
+with the necessary capabilities, can manipulate the target process.
+
+Finally, be aware that some non-x86 architectures have an easier time if
+system call parameters that are explicitly 64-bit fall on odd-numbered
+arguments (i.e. parameter 1, 3, 5), to allow use of contiguous pairs of 32-bit
+registers.  (This concern does not apply if the arguments are part of a
+structure that's passed in by pointer.)
+
+
+Proposing the API
+-----------------
+
+To make new system calls easy to review, it's best to divide up the patchset
+into separate chunks.  These should include at least the following items as
+distinct commits (each of which is described further below):
+
+ - The core implementation of the system call, together with prototypes,
+   generic numbering, Kconfig changes and fallback stub implementation.
+ - Wiring up of the new system call for one particular architecture, usually
+   x86 (including all of x86_64, x86_32 and x32).
+ - A demonstration of the use of the new system call in userspace via a
+   selftest in tools/testing/selftests/.
+ - A draft man-page for the new system call, either as plain text in the
+   cover letter, or as a patch to the (separate) man-pages repository.
+
+New system call proposals, like any change to the kernel's API, should always
+be cc'ed to linux-api@vger.kernel.org.
+
+
+Generic System Call Implementation
+----------------------------------
+
+The main entry point for your new xyzzy(2) system call will be called
+sys_xyzzy(), but you add this entry point with the appropriate
+SYSCALL_DEFINEn() macro rather than explicitly.  The 'n' indicates the number
+of arguments to the system call, and the macro takes the system call name
+followed by the (type, name) pairs for the parameters as arguments.  Using
+this macro allows metadata about the new system call to be made available for
+other tools.
+
+The new entry point also needs a corresponding function prototype, in
+include/linux/syscalls.h, marked as asmlinkage to match the way that system
+calls are invoked:
+
+    asmlinkage long sys_xyzzy(...);
+
+Some architectures (e.g. x86) have their own architecture-specific syscall
+tables, but several other architectures share a generic syscall table. Add your
+new system call to the generic list by adding an entry to the list in
+include/uapi/asm-generic/unistd.h:
+
+    #define __NR_xyzzy 292
+    __SYSCALL(__NR_xyzzy, sys_xyzzy)
+
+Also update the __NR_syscalls count to reflect the additional system call, and
+note that if multiple new system calls are added in the same merge window,
+your new syscall number may get adjusted to resolve conflicts.
+
+The file kernel/sys_ni.c provides a fallback stub implementation of each system
+call, returning -ENOSYS.  Add your new system call here too:
+
+    cond_syscall(sys_xyzzy);
+
+Your new kernel functionality, and the system call that controls it, should
+normally be optional, so add a CONFIG option (typically to init/Kconfig) for
+it. As usual for new CONFIG options:
+
+ - Include a description of the new functionality and system call controlled
+   by the option.
+ - Make the option depend on EXPERT if it should be hidden from normal users.
+ - Make any new source files implementing the function dependent on the CONFIG
+   option in the Makefile (e.g. "obj-$(CONFIG_XYZZY_SYSCALL) += xyzzy.c").
+ - Double check that the kernel still builds with the new CONFIG option turned
+   off.
+
+To summarize, you need a commit that includes:
+
+ - CONFIG option for the new function, normally in init/Kconfig
+ - SYSCALL_DEFINEn(xyzzy, ...) for the entry point
+ - corresponding prototype in include/linux/syscalls.h
+ - generic table entry in include/uapi/asm-generic/unistd.h
+ - fallback stub in kernel/sys_ni.c
+
+
+x86 System Call Implementation
+------------------------------
+
+To wire up your new system call for x86 platforms, you need to update the
+master syscall tables.  Assuming your new system call isn't special in some
+way (see below), this involves a "common" entry (for x86_64 and x32) in
+arch/x86/entry/syscalls/syscall_64.tbl:
+
+    333   common   xyzzy     sys_xyzzy
+
+and an "i386" entry in arch/x86/entry/syscalls/syscall_32.tbl:
+
+    380   i386     xyzzy     sys_xyzzy
+
+Again, these numbers are liable to be changed if there are conflicts in the
+relevant merge window.
+
+
+Compatibility System Calls (Generic)
+------------------------------------
+
+For most system calls the same 64-bit implementation can be invoked even when
+the userspace program is itself 32-bit; even if the system call's parameters
+include an explicit pointer, this is handled transparently.
+
+However, there are a couple of situations where a compatibility layer is
+needed to cope with size differences between 32-bit and 64-bit.
+
+The first is if the 64-bit kernel also supports 32-bit userspace programs, and
+so needs to parse areas of (__user) memory that could hold either 32-bit or
+64-bit values.  In particular, this is needed whenever a system call argument
+is:
+
+ - a pointer to a pointer
+ - a pointer to a struct containing a pointer (e.g. struct iovec __user *)
+ - a pointer to a varying sized integral type (time_t, off_t, long, ...)
+ - a pointer to a struct containing a varying sized integral type.
+
+The second situation that requires a compatibility layer is if one of the
+system call's arguments has a type that is explicitly 64-bit even on a 32-bit
+architecture, for example loff_t or __u64.  In this case, a value that arrives
+at a 64-bit kernel from a 32-bit application will be split into two 32-bit
+values, which then need to be re-assembled in the compatibility layer.
+
+(Note that a system call argument that's a pointer to an explicit 64-bit type
+does *not* need a compatibility layer; for example, splice(2)'s arguments of
+type loff_t __user * do not trigger the need for a compat_ system call.)
+
+The compatibility version of the system call is called compat_sys_xyzzy(), and
+is added with the COMPAT_SYSCALL_DEFINEn() macro, analogously to
+SYSCALL_DEFINEn.  This version of the implementation runs as part of a 64-bit
+kernel, but expects to receive 32-bit parameter values and does whatever is
+needed to deal with them.  (Typically, the compat_sys_ version converts the
+values to 64-bit versions and either calls on to the sys_ version, or both of
+them call a common inner implementation function.)
+
+The compat entry point also needs a corresponding function prototype, in
+include/linux/compat.h, marked as asmlinkage to match the way that system
+calls are invoked:
+
+    asmlinkage long compat_sys_xyzzy(...);
+
+If the system call involves a structure that is laid out differently on 32-bit
+and 64-bit systems, say struct xyzzy_args, then the include/linux/compat.h
+header file should also include a compat version of the structure (struct
+compat_xyzzy_args) where each variable-size field has the appropriate compat_
+type that corresponds to the type in struct xyzzy_args.  The
+compat_sys_xyzzy() routine can then use this compat_ structure to parse the
+arguments from a 32-bit invocation.
+
+For example, if there are fields:
+
+    struct xyzzy_args {
+        const char __user *ptr;
+        __kernel_long_t varying_val;
+        u64 fixed_val;
+        /* ... */
+    };
+
+in struct xyzzy_args, then struct compat_xyzzy_args would have:
+
+    struct compat_xyzzy_args {
+        compat_uptr_t ptr;
+        compat_long_t varying_val;
+        u64 fixed_val;
+        /* ... */
+    };
+
+The generic system call list also needs adjusting to allow for the compat
+version; the entry in include/uapi/asm-generic/unistd.h should use
+__SC_COMP rather than __SYSCALL:
+
+    #define __NR_xyzzy 292
+    __SC_COMP(__NR_xyzzy, sys_xyzzy, compat_sys_xyzzy)
+
+To summarize, you need:
+
+ - a COMPAT_SYSCALL_DEFINEn(xyzzy, ...) for the compat entry point
+ - corresponding prototype in include/linux/compat.h
+ - (if needed) 32-bit mapping struct in include/linux/compat.h
+ - instance of __SC_COMP not __SYSCALL in include/uapi/asm-generic/unistd.h
+
+
+Compatibility System Calls (x86)
+--------------------------------
+
+To wire up the x86 architecture of a system call with a compatibility version,
+the entries in the syscall tables need to be adjusted.
+
+First, the entry in arch/x86/entry/syscalls/syscall_32.tbl gets an extra
+column to indicate that a 32-bit userspace program running on a 64-bit kernel
+should hit the compat entry point:
+
+    380   i386     xyzzy     sys_xyzzy    compat_sys_xyzzy
+
+Second, you need to figure out what should happen for the x32 ABI version of
+the new system call.  There's a choice here: the layout of the arguments
+should either match the 64-bit version or the 32-bit version.
+
+If there's a pointer-to-a-pointer involved, the decision is easy: x32 is
+ILP32, so the layout should match the 32-bit version, and the entry in
+arch/x86/entry/syscalls/syscall_64.tbl is split so that x32 programs hit the
+compatibility wrapper:
+
+    333   64       xyzzy     sys_xyzzy
+    ...
+    555   x32      xyzzy     compat_sys_xyzzy
+
+If no pointers are involved, then it is preferable to re-use the 64-bit system
+call for the x32 ABI (and consequently the entry in
+arch/x86/entry/syscalls/syscall_64.tbl is unchanged).
+
+In either case, you should check that the types involved in your argument
+layout do indeed map exactly from x32 (-mx32) to either the 32-bit (-m32) or
+64-bit (-m64) equivalents.
+
+
+System Calls Returning Elsewhere
+--------------------------------
+
+For most system calls, once the system call is complete the user program
+continues exactly where it left off -- at the next instruction, with the
+stack the same and most of the registers the same as before the system call,
+and with the same virtual memory space.
+
+However, a few system calls do things differently.  They might return to a
+different location (rt_sigreturn) or change the memory space (fork/vfork/clone)
+or even architecture (execve/execveat) of the program.
+
+To allow for this, the kernel implementation of the system call may need to
+save and restore additional registers to the kernel stack, allowing complete
+control of where and how execution continues after the system call.
+
+This is arch-specific, but typically involves defining assembly entry points
+that save/restore additional registers and invoke the real system call entry
+point.
+
+For x86_64, this is implemented as a stub_xyzzy entry point in
+arch/x86/entry/entry_64.S, and the entry in the syscall table
+(arch/x86/entry/syscalls/syscall_64.tbl) is adjusted to match:
+
+    333   common   xyzzy     stub_xyzzy
+
+The equivalent for 32-bit programs running on a 64-bit kernel is normally
+called stub32_xyzzy and implemented in arch/x86/entry/entry_64_compat.S,
+with the corresponding syscall table adjustment in
+arch/x86/entry/syscalls/syscall_32.tbl:
+
+    380   i386     xyzzy     sys_xyzzy    stub32_xyzzy
+
+If the system call needs a compatibility layer (as in the previous section)
+then the stub32_ version needs to call on to the compat_sys_ version of the
+system call rather than the native 64-bit version.  Also, if the x32 ABI
+implementation is not common with the x86_64 version, then its syscall
+table will also need to invoke a stub that calls on to the compat_sys_
+version.
+
+For completeness, it's also nice to set up a mapping so that user-mode Linux
+still works -- its syscall table will reference stub_xyzzy, but the UML build
+doesn't include arch/x86/entry/entry_64.S implementation (because UML
+simulates registers etc).  Fixing this is as simple as adding a #define to
+arch/x86/um/sys_call_table_64.c:
+
+    #define stub_xyzzy sys_xyzzy
+
+
+Other Details
+-------------
+
+Most of the kernel treats system calls in a generic way, but there is the
+occasional exception that may need updating for your particular system call.
+
+The audit subsystem is one such special case; it includes (arch-specific)
+functions that classify some special types of system call -- specifically
+file open (open/openat), program execution (execve/exeveat) or socket
+multiplexor (socketcall) operations. If your new system call is analogous to
+one of these, then the audit system should be updated.
+
+More generally, if there is an existing system call that is analogous to your
+new system call, it's worth doing a kernel-wide grep for the existing system
+call to check there are no other special cases.
+
+
+Testing
+-------
+
+A new system call should obviously be tested; it is also useful to provide
+reviewers with a demonstration of how user space programs will use the system
+call.  A good way to combine these aims is to include a simple self-test
+program in a new directory under tools/testing/selftests/.
+
+For a new system call, there will obviously be no libc wrapper function and so
+the test will need to invoke it using syscall(); also, if the system call
+involves a new userspace-visible structure, the corresponding header will need
+to be installed to compile the test.
+
+Make sure the selftest runs successfully on all supported architectures.  For
+example, check that it works when compiled as an x86_64 (-m64), x86_32 (-m32)
+and x32 (-mx32) ABI program.
+
+For more extensive and thorough testing of new functionality, you should also
+consider adding tests to the Linux Test Project, or to the xfstests project
+for filesystem-related changes.
+ - https://linux-test-project.github.io/
+ - git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git
+
+
+Man Page
+--------
+
+All new system calls should come with a complete man page, ideally using groff
+markup, but plain text will do.  If groff is used, it's helpful to include a
+pre-rendered ASCII version of the man page in the cover email for the
+patchset, for the convenience of reviewers.
+
+The man page should be cc'ed to linux-man@vger.kernel.org
+For more details, see https://www.kernel.org/doc/man-pages/patches.html
+
+References and Sources
+----------------------
+
+ - LWN article from Michael Kerrisk on use of flags argument in system calls:
+   https://lwn.net/Articles/585415/
+ - LWN article from Michael Kerrisk on how to handle unknown flags in a system
+   call: https://lwn.net/Articles/588444/
+ - LWN article from Jake Edge describing constraints on 64-bit system call
+   arguments: https://lwn.net/Articles/311630/
+ - Pair of LWN articles from David Drysdale that describe the system call
+   implementation paths in detail for v3.14:
+    - https://lwn.net/Articles/604287/
+    - https://lwn.net/Articles/604515/
+ - Architecture-specific requirements for system calls are discussed in the
+   syscall(2) man-page:
+   http://man7.org/linux/man-pages/man2/syscall.2.html#NOTES
+ - Collated emails from Linus Torvalds discussing the problems with ioctl():
+   http://yarchive.net/comp/linux/ioctl.html
+ - "How to not invent kernel interfaces", Arnd Bergmann,
+   http://www.ukuug.org/events/linux2007/2007/papers/Bergmann.pdf
+ - LWN article from Michael Kerrisk on avoiding new uses of CAP_SYS_ADMIN:
+   https://lwn.net/Articles/486306/
+ - Recommendation from Andrew Morton that all related information for a new
+   system call should come in the same email thread:
+   https://lkml.org/lkml/2014/7/24/641
+ - Recommendation from Michael Kerrisk that a new system call should come with
+   a man page: https://lkml.org/lkml/2014/6/13/309
+ - Suggestion from Thomas Gleixner that x86 wire-up should be in a separate
+   commit: https://lkml.org/lkml/2014/11/19/254
+ - Suggestion from Greg Kroah-Hartman that it's good for new system calls to
+   come with a man-page & selftest: https://lkml.org/lkml/2014/3/19/710
+ - Discussion from Michael Kerrisk of new system call vs. prctl(2) extension:
+   https://lkml.org/lkml/2014/6/3/411
+ - Suggestion from Ingo Molnar that system calls that involve multiple
+   arguments should encapsulate those arguments in a struct, which includes a
+   size field for future extensibility: https://lkml.org/lkml/2015/7/30/117
+ - Numbering oddities arising from (re-)use of O_* numbering space flags:
+    - commit 75069f2b5bfb ("vfs: renumber FMODE_NONOTIFY and add to uniqueness
+      check")
+    - commit 12ed2e36c98a ("fanotify: FMODE_NONOTIFY and __O_SYNC in sparc
+      conflict")
+    - commit bb458c644a59 ("Safer ABI for O_TMPFILE")
+ - Discussion from Matthew Wilcox about restrictions on 64-bit arguments:
+   https://lkml.org/lkml/2008/12/12/187
+ - Recommendation from Greg Kroah-Hartman that unknown flags should be
+   policed: https://lkml.org/lkml/2014/7/17/577
+ - Recommendation from Linus Torvalds that x32 system calls should prefer
+   compatibility with 64-bit versions rather than 32-bit versions:
+   https://lkml.org/lkml/2011/8/31/244
diff --git a/Documentation/arm/Atmel/README b/Documentation/arm/Atmel/README
index c53a19b4aab2..0931cf7e2e56 100644
--- a/Documentation/arm/Atmel/README
+++ b/Documentation/arm/Atmel/README
@@ -90,6 +90,11 @@ the Atmel website: http://www.atmel.com.
         + Datasheet
           http://www.atmel.com/Images/Atmel-11238-32-bit-Cortex-A5-Microcontroller-SAMA5D4_Datasheet.pdf
 
+      - sama5d2 family
+        - sama5d27
+        + Datasheet
+          Coming soon
+
 
 Linux kernel information
 ------------------------
diff --git a/Documentation/arm/SPEAr/overview.txt b/Documentation/arm/SPEAr/overview.txt
index 65610bf52ebf..1b049be6c84f 100644
--- a/Documentation/arm/SPEAr/overview.txt
+++ b/Documentation/arm/SPEAr/overview.txt
@@ -60,4 +60,4 @@ Introduction
   Document Author
   ---------------
 
-  Viresh Kumar <viresh.linux@gmail.com>, (c) 2010-2012 ST Microelectronics
+  Viresh Kumar <vireshk@kernel.org>, (c) 2010-2012 ST Microelectronics
diff --git a/Documentation/arm/Samsung/Bootloader-interface.txt b/Documentation/arm/Samsung/Bootloader-interface.txt
index b96ead9a6919..df8d4fb85939 100644
--- a/Documentation/arm/Samsung/Bootloader-interface.txt
+++ b/Documentation/arm/Samsung/Bootloader-interface.txt
@@ -15,6 +15,7 @@ executing kernel.
 
 
 1. Non-Secure mode
+
 Address:      sysram_ns_base_addr
 Offset        Value                                        Purpose
 =============================================================================
@@ -28,6 +29,7 @@ Offset        Value                                        Purpose
 
 
 2. Secure mode
+
 Address:      sysram_base_addr
 Offset        Value                                        Purpose
 =============================================================================
@@ -40,14 +42,25 @@ Offset        Value                                        Purpose
 Address:      pmu_base_addr
 Offset        Value                                        Purpose
 =============================================================================
-0x0800        exynos_cpu_resume                            AFTR
+0x0800        exynos_cpu_resume                            AFTR, suspend
+0x0800        mcpm_entry_point (Exynos542x with MCPM)      AFTR, suspend
+0x0804        0xfcba0d10 (Magic cookie)                    AFTR
+0x0804        0x00000bad (Magic cookie)                    System suspend
 0x0814        exynos4_secondary_startup (Exynos4210 r1.1)  Secondary CPU boot
 0x0818        0xfcba0d10 (Magic cookie, Exynos4210 r1.1)   AFTR
 0x081C        exynos_cpu_resume (Exynos4210 r1.1)          AFTR
 
 
 3. Other (regardless of secure/non-secure mode)
+
 Address:      pmu_base_addr
 Offset        Value                           Purpose
 =============================================================================
 0x0908        Non-zero (only Exynos3250)      Secondary CPU boot up indicator
+
+
+4. Glossary
+
+AFTR - ARM Off Top Running, a low power mode, Cortex cores and many other
+modules are power gated, except the TOP modules
+MCPM - Multi-Cluster Power Management
diff --git a/Documentation/arm/keystone/Overview.txt b/Documentation/arm/keystone/Overview.txt
new file mode 100644
index 000000000000..f17bc4c9dff9
--- /dev/null
+++ b/Documentation/arm/keystone/Overview.txt
@@ -0,0 +1,73 @@
+		TI Keystone Linux Overview
+		--------------------------
+
+Introduction
+------------
+Keystone range of SoCs are based on ARM Cortex-A15 MPCore Processors
+and c66x DSP cores. This document describes essential information required
+for users to run Linux on Keystone based EVMs from Texas Instruments.
+
+Following SoCs  & EVMs are currently supported:-
+
+------------ K2HK SoC and EVM --------------------------------------------------
+
+a.k.a Keystone 2 Hawking/Kepler SoC
+TCI6636K2H & TCI6636K2K: See documentation at
+	http://www.ti.com/product/tci6638k2k
+	http://www.ti.com/product/tci6638k2h
+
+EVM:
+http://www.advantech.com/Support/TI-EVM/EVMK2HX_sd.aspx
+
+------------ K2E SoC and EVM ---------------------------------------------------
+
+a.k.a Keystone 2 Edison SoC
+K2E  -  66AK2E05: See documentation at
+	http://www.ti.com/product/66AK2E05/technicaldocuments
+
+EVM:
+https://www.einfochips.com/index.php/partnerships/texas-instruments/k2e-evm.html
+
+------------ K2L SoC and EVM ---------------------------------------------------
+
+a.k.a Keystone 2 Lamarr SoC
+K2L  -  TCI6630K2L: See documentation at
+	http://www.ti.com/product/TCI6630K2L/technicaldocuments
+EVM:
+https://www.einfochips.com/index.php/partnerships/texas-instruments/k2l-evm.html
+
+Configuration
+-------------
+
+All of the K2 SoCs/EVMs share a common defconfig, keystone_defconfig and same
+image is used to boot on individual EVMs. The platform configuration is
+specified through DTS. Following are the DTS used:-
+	K2HK EVM : k2hk-evm.dts
+	K2E EVM  : k2e-evm.dts
+	K2L EVM  : k2l-evm.dts
+
+The device tree documentation for the keystone machines are located at
+        Documentation/devicetree/bindings/arm/keystone/keystone.txt
+
+Known issues & workaround
+-------------------------
+
+Some of the device drivers used on keystone are re-used from that from
+DaVinci and other TI SoCs. These device drivers may use clock APIs directly.
+Some of the keystone specific drivers such as netcp uses run time power
+management API instead to enable clock. As this API has limitations on
+keystone, following workaround is needed to boot Linux.
+
+   Add 'clk_ignore_unused' to the bootargs env variable in u-boot. Otherwise
+   clock frameworks will try to disable clocks that are unused and disable
+   the hardware. This is because netcp related power domain and clock
+   domains are enabled in u-boot as run time power management API currently
+   doesn't enable clocks for netcp due to a limitation. This workaround is
+   expected to be removed in the future when proper API support becomes
+   available. Until then, this work around is needed.
+
+
+Document Author
+---------------
+Murali Karicheri <m-karicheri2@ti.com>
+Copyright 2015 Texas Instruments
diff --git a/Documentation/arm/sunxi/README b/Documentation/arm/sunxi/README
index 1fe2d7fd4108..5e38e1582f95 100644
--- a/Documentation/arm/sunxi/README
+++ b/Documentation/arm/sunxi/README
@@ -36,7 +36,7 @@ SunXi family
         + User Manual
           http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf
 
-      - Allwinner A23
+      - Allwinner A23 (sun8i)
         + Datasheet
           http://dl.linux-sunxi.org/A23/A23%20Datasheet%20V1.0%2020130830.pdf
         + User Manual
@@ -55,7 +55,23 @@ SunXi family
         + User Manual
           http://dl.linux-sunxi.org/A31/A3x_release_document/A31s/IC/A31s%20User%20Manual%20%20V1.0%2020130322.pdf
 
+      - Allwinner A33 (sun8i)
+        + Datasheet
+          http://dl.linux-sunxi.org/A33/A33%20Datasheet%20release%201.1.pdf
+        + User Manual
+          http://dl.linux-sunxi.org/A33/A33%20user%20manual%20release%201.1.pdf
+
+      - Allwinner H3 (sun8i)
+        + Datasheet
+          http://dl.linux-sunxi.org/H3/Allwinner_H3_Datasheet_V1.0.pdf
+
     * Quad ARM Cortex-A15, Quad ARM Cortex-A7 based SoCs
       - Allwinner A80
         + Datasheet
 	  http://dl.linux-sunxi.org/A80/A80_Datasheet_Revision_1.0_0404.pdf
+
+    * Octa ARM Cortex-A7 based SoCs
+      - Allwinner A83T
+        + Not Supported
+        + Datasheet
+          http://dl.linux-sunxi.org/A83T/A83T_datasheet_Revision_1.1.pdf
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 1690350f16e7..7d9d3c2286b2 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -81,7 +81,7 @@ The decompressed kernel image contains a 64-byte header as follows:
   u64 res3	= 0;		/* reserved */
   u64 res4	= 0;		/* reserved */
   u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
-  u32 res5;      		/* reserved (used for PE COFF offset) */
+  u32 res5;			/* reserved (used for PE COFF offset) */
 
 
 Header notes:
@@ -103,7 +103,7 @@ Header notes:
 
 - The flags field (introduced in v3.17) is a little-endian 64-bit field
   composed as follows:
-  Bit 0: 	Kernel endianness.  1 if BE, 0 if LE.
+  Bit 0:	Kernel endianness.  1 if BE, 0 if LE.
   Bits 1-63:	Reserved.
 
 - When image_size is zero, a bootloader should attempt to keep as much
@@ -115,11 +115,14 @@ The Image must be placed text_offset bytes from a 2MB aligned base
 address near the start of usable system RAM and called there. Memory
 below that base address is currently unusable by Linux, and therefore it
 is strongly recommended that this location is the start of system RAM.
+The region between the 2 MB aligned base address and the start of the
+image has no special significance to the kernel, and may be used for
+other purposes.
 At least image_size bytes from the start of the image must be free for
 use by the kernel.
 
-Any memory described to the kernel (even that below the 2MB aligned base
-address) which is not marked as reserved from the kernel e.g. with a
+Any memory described to the kernel (even that below the start of the
+image) which is not marked as reserved from the kernel (e.g., with a
 memreserve region in the device tree) will be considered as available to
 the kernel.
 
diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt
index dab6da3382d9..b19fc34efdb1 100644
--- a/Documentation/atomic_ops.txt
+++ b/Documentation/atomic_ops.txt
@@ -266,7 +266,9 @@ with the given old and new values. Like all atomic_xxx operations,
 atomic_cmpxchg will only satisfy its atomicity semantics as long as all
 other accesses of *v are performed through atomic_xxx operations.
 
-atomic_cmpxchg must provide explicit memory barriers around the operation.
+atomic_cmpxchg must provide explicit memory barriers around the operation,
+although if the comparison fails then no memory ordering guarantees are
+required.
 
 The semantics for atomic_cmpxchg are the same as those defined for 'cas'
 below.
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index fd12c0d835fd..5be8a7f4cc7f 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -1109,7 +1109,7 @@ it will loop and handle as many sectors (on a bio-segment granularity)
 as specified.
 
 Now bh->b_end_io is replaced by bio->bi_end_io, but most of the time the
-right thing to use is bio_endio(bio, uptodate) instead.
+right thing to use is bio_endio(bio) instead.
 
 If the driver is dropping the io_request_lock from its request_fn strategy,
 then it just needs to replace that with q->queue_lock instead.
diff --git a/Documentation/block/biovecs.txt b/Documentation/block/biovecs.txt
index 74a32ad52f53..25689584e6e0 100644
--- a/Documentation/block/biovecs.txt
+++ b/Documentation/block/biovecs.txt
@@ -24,7 +24,7 @@ particular, presenting the illusion of partially completed biovecs so that
 normal code doesn't have to deal with bi_bvec_done.
 
  * Driver code should no longer refer to biovecs directly; we now have
-   bio_iovec() and bio_iovec_iter() macros that return literal struct biovecs,
+   bio_iovec() and bio_iter_iovec() macros that return literal struct biovecs,
    constructed from the raw biovecs but taking into account bi_bvec_done and
    bi_size.
 
@@ -109,3 +109,11 @@ Other implications:
    over all the biovecs in the new bio - which is silly as it's not needed.
 
    So, don't use bi_vcnt anymore.
+
+ * The current interface allows the block layer to split bios as needed, so we
+   could eliminate a lot of complexity particularly in stacked drivers. Code
+   that creates bios can then create whatever size bios are convenient, and
+   more importantly stacked drivers don't have to deal with both their own bio
+   size limitations and the limitations of the underlying devices. Thus
+   there's no need to define ->merge_bvec_fn() callbacks for individual block
+   drivers.
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index 3a29f8914df9..e5d914845be6 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -20,7 +20,7 @@ This shows the size of internal allocation of the device in bytes, if
 reported by the device. A value of '0' means device does not support
 the discard functionality.
 
-discard_max_bytes (RO)
+discard_max_hw_bytes (RO)
 ----------------------
 Devices that support discard functionality may have internal limits on
 the number of bytes that can be trimmed or unmapped in a single operation.
@@ -29,6 +29,14 @@ number of bytes that can be discarded in a single operation. Discard
 requests issued to the device must not exceed this limit. A discard_max_bytes
 value of 0 means that the device does not support discard functionality.
 
+discard_max_bytes (RW)
+----------------------
+While discard_max_hw_bytes is the hardware limit for the device, this
+setting is the software limit. Some devices exhibit large latencies when
+large discards are issued, setting this value lower will make Linux issue
+smaller discards and potentially help reduce latencies induced by large
+discard operations.
+
 discard_zeroes_data (RO)
 ------------------------
 When read, this file will show if the discarded block are zeroed by the
diff --git a/Documentation/cgroups/00-INDEX b/Documentation/cgroups/00-INDEX
index 96ce071a3633..3f5a40f57d4a 100644
--- a/Documentation/cgroups/00-INDEX
+++ b/Documentation/cgroups/00-INDEX
@@ -22,6 +22,8 @@ net_cls.txt
 	- Network classifier cgroups details and usages.
 net_prio.txt
 	- Network priority cgroups details and usages.
+pids.txt
+	- Process number cgroups details and usages.
 resource_counter.txt
 	- Resource Counter API.
 unified-hierarchy.txt
diff --git a/Documentation/cgroups/pids.txt b/Documentation/cgroups/pids.txt
new file mode 100644
index 000000000000..1a078b5d281a
--- /dev/null
+++ b/Documentation/cgroups/pids.txt
@@ -0,0 +1,85 @@
+						   Process Number Controller
+						   =========================
+
+Abstract
+--------
+
+The process number controller is used to allow a cgroup hierarchy to stop any
+new tasks from being fork()'d or clone()'d after a certain limit is reached.
+
+Since it is trivial to hit the task limit without hitting any kmemcg limits in
+place, PIDs are a fundamental resource. As such, PID exhaustion must be
+preventable in the scope of a cgroup hierarchy by allowing resource limiting of
+the number of tasks in a cgroup.
+
+Usage
+-----
+
+In order to use the `pids` controller, set the maximum number of tasks in
+pids.max (this is not available in the root cgroup for obvious reasons). The
+number of processes currently in the cgroup is given by pids.current.
+
+Organisational operations are not blocked by cgroup policies, so it is possible
+to have pids.current > pids.max. This can be done by either setting the limit to
+be smaller than pids.current, or attaching enough processes to the cgroup such
+that pids.current > pids.max. However, it is not possible to violate a cgroup
+policy through fork() or clone(). fork() and clone() will return -EAGAIN if the
+creation of a new process would cause a cgroup policy to be violated.
+
+To set a cgroup to have no limit, set pids.max to "max". This is the default for
+all new cgroups (N.B. that PID limits are hierarchical, so the most stringent
+limit in the hierarchy is followed).
+
+pids.current tracks all child cgroup hierarchies, so parent/pids.current is a
+superset of parent/child/pids.current.
+
+Example
+-------
+
+First, we mount the pids controller:
+# mkdir -p /sys/fs/cgroup/pids
+# mount -t cgroup -o pids none /sys/fs/cgroup/pids
+
+Then we create a hierarchy, set limits and attach processes to it:
+# mkdir -p /sys/fs/cgroup/pids/parent/child
+# echo 2 > /sys/fs/cgroup/pids/parent/pids.max
+# echo $$ > /sys/fs/cgroup/pids/parent/cgroup.procs
+# cat /sys/fs/cgroup/pids/parent/pids.current
+2
+#
+
+It should be noted that attempts to overcome the set limit (2 in this case) will
+fail:
+
+# cat /sys/fs/cgroup/pids/parent/pids.current
+2
+# ( /bin/echo "Here's some processes for you." | cat )
+sh: fork: Resource temporary unavailable
+#
+
+Even if we migrate to a child cgroup (which doesn't have a set limit), we will
+not be able to overcome the most stringent limit in the hierarchy (in this case,
+parent's):
+
+# echo $$ > /sys/fs/cgroup/pids/parent/child/cgroup.procs
+# cat /sys/fs/cgroup/pids/parent/pids.current
+2
+# cat /sys/fs/cgroup/pids/parent/child/pids.current
+2
+# cat /sys/fs/cgroup/pids/parent/child/pids.max
+max
+# ( /bin/echo "Here's some processes for you." | cat )
+sh: fork: Resource temporary unavailable
+#
+
+We can set a limit that is smaller than pids.current, which will stop any new
+processes from being forked at all (note that the shell itself counts towards
+pids.current):
+
+# echo 1 > /sys/fs/cgroup/pids/parent/pids.max
+# /bin/echo "We can't even spawn a single process now."
+sh: fork: Resource temporary unavailable
+# echo 0 > /sys/fs/cgroup/pids/parent/pids.max
+# /bin/echo "We can't even spawn a single process now."
+sh: fork: Resource temporary unavailable
+#
diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt
index 86847a7647ab..1ee9caf29e57 100644
--- a/Documentation/cgroups/unified-hierarchy.txt
+++ b/Documentation/cgroups/unified-hierarchy.txt
@@ -23,10 +23,13 @@ CONTENTS
 5. Other Changes
   5-1. [Un]populated Notification
   5-2. Other Core Changes
-  5-3. Per-Controller Changes
-    5-3-1. blkio
-    5-3-2. cpuset
-    5-3-3. memory
+  5-3. Controller File Conventions
+    5-3-1. Format
+    5-3-2. Control Knobs
+  5-4. Per-Controller Changes
+    5-4-1. blkio
+    5-4-2. cpuset
+    5-4-3. memory
 6. Planned Changes
   6-1. CAP for resource control
 
@@ -372,14 +375,75 @@ supported and the interface files "release_agent" and
 - The "cgroup.clone_children" file is removed.
 
 
-5-3. Per-Controller Changes
+5-3. Controller File Conventions
 
-5-3-1. blkio
+5-3-1. Format
+
+In general, all controller files should be in one of the following
+formats whenever possible.
+
+- Values only files
+
+  VAL0 VAL1...\n
+
+- Flat keyed files
+
+  KEY0 VAL0\n
+  KEY1 VAL1\n
+  ...
+
+- Nested keyed files
+
+  KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
+  KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
+  ...
+
+For a writeable file, the format for writing should generally match
+reading; however, controllers may allow omitting later fields or
+implement restricted shortcuts for most common use cases.
+
+For both flat and nested keyed files, only the values for a single key
+can be written at a time.  For nested keyed files, the sub key pairs
+may be specified in any order and not all pairs have to be specified.
+
+
+5-3-2. Control Knobs
+
+- Settings for a single feature should generally be implemented in a
+  single file.
+
+- In general, the root cgroup should be exempt from resource control
+  and thus shouldn't have resource control knobs.
+
+- If a controller implements ratio based resource distribution, the
+  control knob should be named "weight" and have the range [1, 10000]
+  and 100 should be the default value.  The values are chosen to allow
+  enough and symmetric bias in both directions while keeping it
+  intuitive (the default is 100%).
+
+- If a controller implements an absolute resource guarantee and/or
+  limit, the control knobs should be named "min" and "max"
+  respectively.  If a controller implements best effort resource
+  gurantee and/or limit, the control knobs should be named "low" and
+  "high" respectively.
+
+  In the above four control files, the special token "max" should be
+  used to represent upward infinity for both reading and writing.
+
+- If a setting has configurable default value and specific overrides,
+  the default settings should be keyed with "default" and appear as
+  the first entry in the file.  Specific entries can use "default" as
+  its value to indicate inheritance of the default value.
+
+
+5-4. Per-Controller Changes
+
+5-4-1. blkio
 
 - blk-throttle becomes properly hierarchical.
 
 
-5-3-2. cpuset
+5-4-2. cpuset
 
 - Tasks are kept in empty cpusets after hotplug and take on the masks
   of the nearest non-empty ancestor, instead of being moved to it.
@@ -388,7 +452,7 @@ supported and the interface files "release_agent" and
   masks of the nearest non-empty ancestor.
 
 
-5-3-3. memory
+5-4-3. memory
 
 - use_hierarchy is on by default and the cgroup file for the flag is
   not created.
diff --git a/Documentation/clk.txt b/Documentation/clk.txt
index f463bdc37f88..5c4bc4d01d0c 100644
--- a/Documentation/clk.txt
+++ b/Documentation/clk.txt
@@ -71,12 +71,8 @@ the operations defined in clk.h:
 		long		(*round_rate)(struct clk_hw *hw,
 						unsigned long rate,
 						unsigned long *parent_rate);
-		long		(*determine_rate)(struct clk_hw *hw,
-						unsigned long rate,
-						unsigned long min_rate,
-						unsigned long max_rate,
-						unsigned long *best_parent_rate,
-						struct clk_hw **best_parent_clk);
+		int		(*determine_rate)(struct clk_hw *hw,
+						  struct clk_rate_request *req);
 		int		(*set_parent)(struct clk_hw *hw, u8 index);
 		u8		(*get_parent)(struct clk_hw *hw);
 		int		(*set_rate)(struct clk_hw *hw,
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt
index 70933eadc308..ba78e7c2a069 100644
--- a/Documentation/cpu-freq/core.txt
+++ b/Documentation/cpu-freq/core.txt
@@ -55,16 +55,13 @@ transition notifiers.
 ----------------------------
 
 These are notified when a new policy is intended to be set. Each
-CPUFreq policy notifier is called three times for a policy transition:
+CPUFreq policy notifier is called twice for a policy transition:
 
 1.) During CPUFREQ_ADJUST all CPUFreq notifiers may change the limit if
     they see a need for this - may it be thermal considerations or
     hardware limitations.
 
-2.) During CPUFREQ_INCOMPATIBLE only changes may be done in order to avoid
-    hardware failure.
-
-3.) And during CPUFREQ_NOTIFY all notifiers are informed of the new policy
+2.) And during CPUFREQ_NOTIFY all notifiers are informed of the new policy
    - if two hardware drivers failed to agree on a new policy before this
    stage, the incompatible hardware shall be shut down, and the user
    informed of this.
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index 82960cffbad3..785eab87aa71 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -258,6 +258,12 @@ cache metadata mode      : ro if read-only, rw if read-write
 	no further I/O will be permitted and the status will just
 	contain the string 'Fail'.  The userspace recovery tools
 	should then be used.
+needs_check		 : 'needs_check' if set, '-' if not set
+	A metadata operation has failed, resulting in the needs_check
+	flag being set in the metadata's superblock.  The metadata
+	device must be deactivated and checked/repaired before the
+	cache can be made fully operational again.  '-' indicates
+	needs_check is not set.
 
 Messages
 --------
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index cb12af3b51c2..df2d636b6088 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -209,6 +209,37 @@ include:
 	"repair" - Initiate a repair of the array.
 	"reshape"- Currently unsupported (-EINVAL).
 
+
+Discard Support
+---------------
+The implementation of discard support among hardware vendors varies.
+When a block is discarded, some storage devices will return zeroes when
+the block is read.  These devices set the 'discard_zeroes_data'
+attribute.  Other devices will return random data.  Confusingly, some
+devices that advertise 'discard_zeroes_data' will not reliably return
+zeroes when discarded blocks are read!  Since RAID 4/5/6 uses blocks
+from a number of devices to calculate parity blocks and (for performance
+reasons) relies on 'discard_zeroes_data' being reliable, it is important
+that the devices be consistent.  Blocks may be discarded in the middle
+of a RAID 4/5/6 stripe and if subsequent read results are not
+consistent, the parity blocks may be calculated differently at any time;
+making the parity blocks useless for redundancy.  It is important to
+understand how your hardware behaves with discards if you are going to
+enable discards with RAID 4/5/6.
+
+Since the behavior of storage devices is unreliable in this respect,
+even when reporting 'discard_zeroes_data', by default RAID 4/5/6
+discard support is disabled -- this ensures data integrity at the
+expense of losing some performance.
+
+Storage devices that properly support 'discard_zeroes_data' are
+increasingly whitelisted in the kernel and can thus be trusted.
+
+For trusted devices, the following dm-raid module parameter can be set
+to safely enable discard support for RAID 4/5/6:
+    'devices_handle_discards_safely'
+
+
 Version History
 ---------------
 1.0.0	Initial version.  Support for RAID 4/5/6
diff --git a/Documentation/device-mapper/statistics.txt b/Documentation/device-mapper/statistics.txt
index 4919b2dfd1b3..6f5ef944ca4c 100644
--- a/Documentation/device-mapper/statistics.txt
+++ b/Documentation/device-mapper/statistics.txt
@@ -121,6 +121,10 @@ Messages
 
 	Output format:
 	  <region_id>: <start_sector>+<length> <step> <program_id> <aux_data>
+	        precise_timestamps histogram:n1,n2,n3,...
+
+	The strings "precise_timestamps" and "histogram" are printed only
+	if they were specified when creating the region.
 
     @stats_print <region_id> [<starting_line> <number_of_lines>]
 
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 4f67578b2954..1699a55b7b70 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -296,7 +296,7 @@ ii) Status
 	underlying device.  When this is enabled when loading the table,
 	it can get disabled if the underlying device doesn't support it.
 
-    ro|rw
+    ro|rw|out_of_data_space
 	If the pool encounters certain types of device failures it will
 	drop into a read-only metadata mode in which no changes to
 	the pool metadata (like allocating new blocks) are permitted.
@@ -314,6 +314,13 @@ ii) Status
 	module parameter can be used to change this timeout -- it
 	defaults to 60 seconds but may be disabled using a value of 0.
 
+    needs_check
+	A metadata operation has failed, resulting in the needs_check
+	flag being set in the metadata's superblock.  The metadata
+	device must be deactivated and checked/repaired before the
+	thin-pool can be made fully operational again.  '-' indicates
+	needs_check is not set.
+
 iii) Messages
 
     create_thin <dev id>
diff --git a/Documentation/devicetree/bindings/arc/archs-pct.txt b/Documentation/devicetree/bindings/arc/archs-pct.txt
new file mode 100644
index 000000000000..1ae98b87c640
--- /dev/null
+++ b/Documentation/devicetree/bindings/arc/archs-pct.txt
@@ -0,0 +1,17 @@
+* ARC HS Performance Counters
+
+The ARC HS can be configured with a pipeline performance monitor for counting
+CPU and cache events like cache misses and hits. Like conventional PCT there
+are 100+ hardware conditions dynamically mapped to upto 32 counters.
+It also supports overflow interrupts.
+
+Required properties:
+
+- compatible : should contain
+	"snps,archs-pct"
+
+Example:
+
+pmu {
+        compatible = "snps,archs-pct";
+};
diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.txt b/Documentation/devicetree/bindings/arm/atmel-at91.txt
index 424ac8cbfa08..7fd64ec9ee1d 100644
--- a/Documentation/devicetree/bindings/arm/atmel-at91.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-at91.txt
@@ -27,6 +27,8 @@ compatible: must be one of:
     o "atmel,at91sam9xe"
  * "atmel,sama5" for SoCs using a Cortex-A5, shall be extended with the specific
    SoC family:
+    o "atmel,sama5d2" shall be extended with the specific SoC compatible:
+       - "atmel,sama5d27"
     o "atmel,sama5d3" shall be extended with the specific SoC compatible:
        - "atmel,sama5d31"
        - "atmel,sama5d33"
@@ -50,6 +52,7 @@ System Timer (ST) required properties:
 - reg: Should contain registers location and length
 - interrupts: Should contain interrupt for the ST which is the IRQ line
   shared across all System Controller members.
+- clocks: phandle to input clock.
 Its subnodes can be:
 - watchdog: compatible should be "atmel,at91rm9200-wdt"
 
@@ -61,7 +64,7 @@ TC/TCLIB Timer required properties:
   Note that you can specify several interrupt cells if the TC
   block has one interrupt per channel.
 - clock-names: tuple listing input clock names.
-	Required elements: "t0_clk"
+	Required elements: "t0_clk", "slow_clk"
 	Optional elements: "t1_clk", "t2_clk"
 - clocks: phandles to input clocks.
 
@@ -87,14 +90,16 @@ One interrupt per TC channel in a TC block:
 
 RSTC Reset Controller required properties:
 - compatible: Should be "atmel,<chip>-rstc".
-  <chip> can be "at91sam9260" or "at91sam9g45"
+  <chip> can be "at91sam9260" or "at91sam9g45" or "sama5d3"
 - reg: Should contain registers location and length
+- clocks: phandle to input clock.
 
 Example:
 
 	rstc@fffffd00 {
 		compatible = "atmel,at91sam9260-rstc";
 		reg = <0xfffffd00 0x10>;
+		clocks = <&clk32k>;
 	};
 
 RAMC SDRAM/DDR Controller required properties:
@@ -117,6 +122,7 @@ required properties:
 - compatible: Should be "atmel,<chip>-shdwc".
   <chip> can be "at91sam9260", "at91sam9rl" or "at91sam9x5".
 - reg: Should contain registers location and length
+- clocks: phandle to input clock.
 
 optional properties:
 - atmel,wakeup-mode: String, operation mode of the wakeup mode.
@@ -135,9 +141,10 @@ optional at91sam9x5 properties:
 
 Example:
 
-	rstc@fffffd00 {
-		compatible = "atmel,at91sam9260-rstc";
-		reg = <0xfffffd00 0x10>;
+	shdwc@fffffd10 {
+		compatible = "atmel,at91sam9260-shdwc";
+		reg = <0xfffffd10 0x10>;
+		clocks = <&clk32k>;
 	};
 
 Special Function Registers (SFR)
diff --git a/Documentation/devicetree/bindings/arm/bcm/ns2.txt b/Documentation/devicetree/bindings/arm/bcm/ns2.txt
new file mode 100644
index 000000000000..35f056f4a1c3
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/bcm/ns2.txt
@@ -0,0 +1,9 @@
+Broadcom North Star 2 (NS2) device tree bindings
+------------------------------------------------
+
+Boards with NS2 shall have the following properties:
+
+Required root node property:
+
+NS2 SVK board
+compatible = "brcm,ns2-svk", "brcm,ns2";
diff --git a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.txt b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.txt
new file mode 100644
index 000000000000..6824b3180ffb
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.txt
@@ -0,0 +1,14 @@
+Raspberry Pi VideoCore firmware driver
+
+Required properties:
+
+- compatible:		Should be "raspberrypi,bcm2835-firmware"
+- mboxes:		Phandle to the firmware device's Mailbox.
+			  (See: ../mailbox/mailbox.txt for more information)
+
+Example:
+
+firmware {
+	compatible = "raspberrypi,bcm2835-firmware";
+	mboxes = <&mailbox>;
+};
diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
index 65a6db2271a2..62938eb9697f 100644
--- a/Documentation/devicetree/bindings/arm/coresight.txt
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -17,6 +17,7 @@ its hardware characteristcs.
 		- "arm,coresight-tmc", "arm,primecell";
 		- "arm,coresight-funnel", "arm,primecell";
 		- "arm,coresight-etm3x", "arm,primecell";
+		- "arm,coresight-etm4x", "arm,primecell";
 		- "qcom,coresight-replicator1x", "arm,primecell";
 
 	* reg: physical base address and length of the register
diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
index d6b794cef0b8..91e6e5c478d0 100644
--- a/Documentation/devicetree/bindings/arm/cpus.txt
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -199,6 +199,7 @@ nodes to be present and contain the properties described below.
 			    "qcom,kpss-acc-v1"
 			    "qcom,kpss-acc-v2"
 			    "rockchip,rk3066-smp"
+			    "ste,dbx500-smp"
 
 	- cpu-release-addr
 		Usage: required for systems that have an "enable-method"
diff --git a/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt b/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
index c431c67524d6..c733e28e18e5 100644
--- a/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+++ b/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
@@ -127,6 +127,24 @@ Example:
 		#clock-cells = <1>;
 	};
 
+
+Hisilicon Hi6220 SRAM controller
+
+Required properties:
+- compatible : "hisilicon,hi6220-sramctrl", "syscon"
+- reg : Register address and size
+
+Hisilicon's SoCs use sram for multiple purpose; on Hi6220 there have several
+SRAM banks for power management, modem, security, etc. Further, use "syscon"
+managing the common sram which can be shared by multiple modules.
+
+Example:
+	/*for Hi6220*/
+	sram: sram@fff80000 {
+		compatible = "hisilicon,hi6220-sramctrl", "syscon";
+		reg = <0x0 0xfff80000 0x0 0x12000>;
+	};
+
 -----------------------------------------------------------------------
 Hisilicon HiP01 system controller
 
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index 2251dccb141e..06c88a4d28ac 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -67,6 +67,12 @@ Optional properties:
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
+- arm,shared-override : The default behavior of the pl310 cache controller with
+  respect to the shareable attribute is to transform "normal memory
+  non-cacheable transactions" into "cacheable no allocate" (for reads) or
+  "write through no write allocate" (for writes).
+  On systems where this may cause DMA buffer corruption, this property must be
+  specified to indicate that such transforms are precluded.
 - prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
   (forcibly enable), property absent (retain settings set by firmware)
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
diff --git a/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt b/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt
index 4f40ff3fee4b..5171ad8f48ff 100644
--- a/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt
+++ b/Documentation/devicetree/bindings/arm/marvell,kirkwood.txt
@@ -20,6 +20,8 @@ And in addition, the compatible shall be extended with the specific
 board. Currently known boards are:
 
 "buffalo,lschlv2"
+"buffalo,lswvl"
+"buffalo,lswxl"
 "buffalo,lsxhl"
 "buffalo,lsxl"
 "dlink,dns-320"
diff --git a/Documentation/devicetree/bindings/arm/mediatek.txt b/Documentation/devicetree/bindings/arm/mediatek.txt
index dd7550a29db6..618a91994a18 100644
--- a/Documentation/devicetree/bindings/arm/mediatek.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek.txt
@@ -1,12 +1,15 @@
-MediaTek mt65xx & mt81xx Platforms Device Tree Bindings
+MediaTek mt65xx, mt67xx & mt81xx Platforms Device Tree Bindings
 
-Boards with a MediaTek mt65xx/mt81xx SoC shall have the following property:
+Boards with a MediaTek mt65xx/mt67xx/mt81xx SoC shall have the
+following property:
 
 Required root node property:
 
 compatible: Must contain one of
+   "mediatek,mt6580"
    "mediatek,mt6589"
    "mediatek,mt6592"
+   "mediatek,mt6795"
    "mediatek,mt8127"
    "mediatek,mt8135"
    "mediatek,mt8173"
@@ -14,12 +17,18 @@ compatible: Must contain one of
 
 Supported boards:
 
+- Evaluation board for MT6580:
+    Required root node properties:
+      - compatible = "mediatek,mt6580-evbp1", "mediatek,mt6580";
 - bq Aquaris5 smart phone:
     Required root node properties:
       - compatible = "mundoreader,bq-aquaris5", "mediatek,mt6589";
 - Evaluation board for MT6592:
     Required root node properties:
       - compatible = "mediatek,mt6592-evb", "mediatek,mt6592";
+- Evaluation board for MT6795(Helio X10):
+    Required root node properties:
+      - compatible = "mediatek,mt6795-evb", "mediatek,mt6795";
 - MTK mt8127 tablet moose EVB:
     Required root node properties:
       - compatible = "mediatek,mt8127-moose", "mediatek,mt8127";
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,sysirq.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,sysirq.txt
index 4f5a5352ccd8..afef6a85ac51 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,sysirq.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,sysirq.txt
@@ -1,4 +1,4 @@
-Mediatek 65xx/81xx sysirq
++Mediatek 65xx/67xx/81xx sysirq
 
 Mediatek SOCs sysirq support controllable irq inverter for each GIC SPI
 interrupt.
@@ -8,9 +8,11 @@ Required properties:
 	"mediatek,mt8173-sysirq"
 	"mediatek,mt8135-sysirq"
 	"mediatek,mt8127-sysirq"
+	"mediatek,mt6795-sysirq"
 	"mediatek,mt6592-sysirq"
 	"mediatek,mt6589-sysirq"
 	"mediatek,mt6582-sysirq"
+	"mediatek,mt6580-sysirq"
 	"mediatek,mt6577-sysirq"
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Use the same format as specified by GIC in
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index 4f6a82cef1d1..9f4e5136e568 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -135,6 +135,9 @@ Boards:
 - AM335X OrionLXm : Substation Automation Platform
   compatible = "novatech,am335x-lxm", "ti,am33xx"
 
+- AM335X phyBOARD-WEGA: Single Board Computer dev kit
+  compatible = "phytec,am335x-wega", "phytec,am335x-phycore-som", "ti,am33xx"
+
 - OMAP5 EVM : Evaluation Module
   compatible = "ti,omap5-evm", "ti,omap5"
 
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 3b5f5d1088c6..435251fa9ce0 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -26,13 +26,19 @@ Required properties:
 
 Optional properties:
 
-- interrupt-affinity : Valid only when using SPIs, specifies a list of phandles
-                       to CPU nodes corresponding directly to the affinity of
+- interrupt-affinity : When using SPIs, specifies a list of phandles to CPU
+                       nodes corresponding directly to the affinity of
 		       the SPIs listed in the interrupts property.
 
-		       This property should be present when there is more than
+                       When using a PPI, specifies a list of phandles to CPU
+		       nodes corresponding to the set of CPUs which have
+		       a PMU of this type signalling the PPI listed in the
+		       interrupts property.
+
+                       This property should be present when there is more than
 		       a single SPI.
 
+
 - qcom,no-pc-write : Indicates that this PMU doesn't support the 0xc and 0xd
                      events.
 
diff --git a/Documentation/devicetree/bindings/arm/rockchip.txt b/Documentation/devicetree/bindings/arm/rockchip.txt
index 60d4a1e0a9b5..af58cd74aeff 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.txt
+++ b/Documentation/devicetree/bindings/arm/rockchip.txt
@@ -26,3 +26,38 @@ Rockchip platforms device tree bindings
 - ChipSPARK PopMetal-RK3288 board:
     Required root node properties:
       - compatible = "chipspark,popmetal-rk3288", "rockchip,rk3288";
+
+- Netxeon R89 board:
+    Required root node properties:
+      - compatible = "netxeon,r89", "rockchip,rk3288";
+
+- Google Jerry (Hisense Chromebook C11 and more):
+    Required root node properties:
+      - compatible = "google,veyron-jerry-rev7", "google,veyron-jerry-rev6",
+		     "google,veyron-jerry-rev5", "google,veyron-jerry-rev4",
+		     "google,veyron-jerry-rev3", "google,veyron-jerry",
+		     "google,veyron", "rockchip,rk3288";
+
+- Google Minnie (Asus Chromebook Flip C100P):
+    Required root node properties:
+      - compatible = "google,veyron-minnie-rev4", "google,veyron-minnie-rev3",
+		     "google,veyron-minnie-rev2", "google,veyron-minnie-rev1",
+		     "google,veyron-minnie-rev0", "google,veyron-minnie",
+		     "google,veyron", "rockchip,rk3288";
+
+- Google Pinky (dev-board):
+    Required root node properties:
+      - compatible = "google,veyron-pinky-rev2", "google,veyron-pinky",
+		     "google,veyron", "rockchip,rk3288";
+
+- Google Speedy (Asus C201 Chromebook):
+    Required root node properties:
+      - compatible = "google,veyron-speedy-rev9", "google,veyron-speedy-rev8",
+		     "google,veyron-speedy-rev7", "google,veyron-speedy-rev6",
+		     "google,veyron-speedy-rev5", "google,veyron-speedy-rev4",
+		     "google,veyron-speedy-rev3", "google,veyron-speedy-rev2",
+		     "google,veyron-speedy", "google,veyron", "rockchip,rk3288";
+
+- Rockchip R88 board:
+    Required root node properties:
+      - compatible = "rockchip,r88", "rockchip,rk3368";
diff --git a/Documentation/devicetree/bindings/arm/sp810.txt b/Documentation/devicetree/bindings/arm/sp810.txt
new file mode 100644
index 000000000000..6808fb5dee40
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/sp810.txt
@@ -0,0 +1,46 @@
+SP810 System Controller
+-----------------------
+
+Required properties:
+
+- compatible:	standard compatible string for a Primecell peripheral,
+		see Documentation/devicetree/bindings/arm/primecell.txt
+		for more details
+		should be: "arm,sp810", "arm,primecell"
+
+- reg:		standard registers property, physical address and size
+		of the control registers
+
+- clock-names:	from the common clock bindings, for more details see
+		Documentation/devicetree/bindings/clock/clock-bindings.txt;
+		should be: "refclk", "timclk", "apb_pclk"
+
+- clocks:	from the common clock bindings, phandle and clock
+		specifier pairs for the entries of clock-names property
+
+- #clock-cells: from the common clock bindings;
+		should be: <1>
+
+- clock-output-names: from the common clock bindings;
+		should be: "timerclken0", "timerclken1", "timerclken2", "timerclken3"
+
+- assigned-clocks: from the common clock binding;
+		should be: clock specifier for each output clock of this
+		provider node
+
+- assigned-clock-parents: from the common clock binding;
+		should be: phandle of input clock listed in clocks
+		property with the highest frequency
+
+Example:
+	v2m_sysctl: sysctl@020000 {
+		compatible = "arm,sp810", "arm,primecell";
+		reg = <0x020000 0x1000>;
+		clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>;
+		clock-names = "refclk", "timclk", "apb_pclk";
+		#clock-cells = <1>;
+		clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+		assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>;
+		assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>;
+
+	};
diff --git a/Documentation/devicetree/bindings/arm/sunxi.txt b/Documentation/devicetree/bindings/arm/sunxi.txt
index 42941fdefb11..67da20539540 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.txt
+++ b/Documentation/devicetree/bindings/arm/sunxi.txt
@@ -9,4 +9,6 @@ using one of the following compatible strings:
   allwinner,sun6i-a31
   allwinner,sun7i-a20
   allwinner,sun8i-a23
+  allwinner,sun8i-a33
+  allwinner,sun8i-h3
   allwinner,sun9i-a80
diff --git a/Documentation/devicetree/bindings/clock/gpio-mux-clock.txt b/Documentation/devicetree/bindings/clock/gpio-mux-clock.txt
new file mode 100644
index 000000000000..2be1e038ca62
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/gpio-mux-clock.txt
@@ -0,0 +1,19 @@
+Binding for simple gpio clock multiplexer.
+
+This binding uses the common clock binding[1].
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible : shall be "gpio-mux-clock".
+- clocks: list of two references to parent clocks.
+- #clock-cells : from common clock binding; shall be set to 0.
+- select-gpios : GPIO reference for selecting the parent clock.
+
+Example:
+	clock {
+		compatible = "gpio-mux-clock";
+		clocks = <&parentclk1>, <&parentclk2>;
+		#clock-cells = <0>;
+		select-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/hi6220-clock.txt b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
index 259e30af9597..e4d5feaebc29 100644
--- a/Documentation/devicetree/bindings/clock/hi6220-clock.txt
+++ b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
@@ -15,19 +15,36 @@ Required Properties:
 	- "hisilicon,hi6220-sysctrl"
 	- "hisilicon,hi6220-mediactrl"
 	- "hisilicon,hi6220-pmctrl"
+	- "hisilicon,hi6220-stub-clk"
 
 - reg: physical base address of the controller and length of memory mapped
   region.
 
 - #clock-cells: should be 1.
 
-For example:
+Optional Properties:
+
+- hisilicon,hi6220-clk-sram: phandle to the syscon managing the SoC internal sram;
+  the driver need use the sram to pass parameters for frequency change.
+
+- mboxes: use the label reference for the mailbox as the first parameter, the
+  second parameter is the channel number.
+
+Example 1:
 	sys_ctrl: sys_ctrl@f7030000 {
 		compatible = "hisilicon,hi6220-sysctrl", "syscon";
 		reg = <0x0 0xf7030000 0x0 0x2000>;
 		#clock-cells = <1>;
 	};
 
+Example 2:
+	stub_clock: stub_clock {
+		compatible = "hisilicon,hi6220-stub-clk";
+		hisilicon,hi6220-clk-sram = <&sram>;
+		#clock-cells = <1>;
+		mboxes = <&mailbox 1>;
+	};
+
 Each clock is assigned an identifier and client nodes use this identifier
 to specify the clock which they consume.
 
diff --git a/Documentation/devicetree/bindings/clock/imx6ul-clock.txt b/Documentation/devicetree/bindings/clock/imx6ul-clock.txt
new file mode 100644
index 000000000000..571d5039f663
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/imx6ul-clock.txt
@@ -0,0 +1,13 @@
+* Clock bindings for Freescale i.MX6 UltraLite
+
+Required properties:
+- compatible: Should be "fsl,imx6ul-ccm"
+- reg: Address and length of the register set
+- #clock-cells: Should be <1>
+- clocks: list of clock specifiers, must contain an entry for each required
+  entry in clock-names
+- clock-names: should include entries "ckil", "osc", "ipp_di0" and "ipp_di1"
+
+The clock consumer should specify the desired clock by having the clock
+ID in its "clocks" phandle cell.  See include/dt-bindings/clock/imx6ul-clock.h
+for the full list of i.MX6 UltraLite clock IDs.
diff --git a/Documentation/devicetree/bindings/clock/mt8173-cpu-dvfs.txt b/Documentation/devicetree/bindings/clock/mt8173-cpu-dvfs.txt
new file mode 100644
index 000000000000..52b457c23eed
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/mt8173-cpu-dvfs.txt
@@ -0,0 +1,83 @@
+Device Tree Clock bindins for CPU DVFS of Mediatek MT8173 SoC
+
+Required properties:
+- clocks: A list of phandle + clock-specifier pairs for the clocks listed in clock names.
+- clock-names: Should contain the following:
+	"cpu"		- The multiplexer for clock input of CPU cluster.
+	"intermediate"	- A parent of "cpu" clock which is used as "intermediate" clock
+			  source (usually MAINPLL) when the original CPU PLL is under
+			  transition and not stable yet.
+	Please refer to Documentation/devicetree/bindings/clk/clock-bindings.txt for
+	generic clock consumer properties.
+- proc-supply: Regulator for Vproc of CPU cluster.
+
+Optional properties:
+- sram-supply: Regulator for Vsram of CPU cluster. When present, the cpufreq driver
+	       needs to do "voltage tracking" to step by step scale up/down Vproc and
+	       Vsram to fit SoC specific needs. When absent, the voltage scaling
+	       flow is handled by hardware, hence no software "voltage tracking" is
+	       needed.
+
+Example:
+--------
+	cpu0: cpu@0 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x000>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_SLEEP_0>;
+		clocks = <&infracfg CLK_INFRA_CA53SEL>,
+			 <&apmixedsys CLK_APMIXED_MAINPLL>;
+		clock-names = "cpu", "intermediate";
+	};
+
+	cpu1: cpu@1 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x001>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_SLEEP_0>;
+		clocks = <&infracfg CLK_INFRA_CA53SEL>,
+			 <&apmixedsys CLK_APMIXED_MAINPLL>;
+		clock-names = "cpu", "intermediate";
+	};
+
+	cpu2: cpu@100 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x100>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_SLEEP_0>;
+		clocks = <&infracfg CLK_INFRA_CA57SEL>,
+			 <&apmixedsys CLK_APMIXED_MAINPLL>;
+		clock-names = "cpu", "intermediate";
+	};
+
+	cpu3: cpu@101 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x101>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_SLEEP_0>;
+		clocks = <&infracfg CLK_INFRA_CA57SEL>,
+			 <&apmixedsys CLK_APMIXED_MAINPLL>;
+		clock-names = "cpu", "intermediate";
+	};
+
+	&cpu0 {
+		proc-supply = <&mt6397_vpca15_reg>;
+	};
+
+	&cpu1 {
+		proc-supply = <&mt6397_vpca15_reg>;
+	};
+
+	&cpu2 {
+		proc-supply = <&da9211_vcpu_reg>;
+		sram-supply = <&mt6397_vsramca7_reg>;
+	};
+
+	&cpu3 {
+		proc-supply = <&da9211_vcpu_reg>;
+		sram-supply = <&mt6397_vsramca7_reg>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/nvidia,tegra124-dfll.txt b/Documentation/devicetree/bindings/clock/nvidia,tegra124-dfll.txt
new file mode 100644
index 000000000000..ee7e5fd4a50b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/nvidia,tegra124-dfll.txt
@@ -0,0 +1,79 @@
+NVIDIA Tegra124 DFLL FCPU clocksource
+
+This binding uses the common clock binding:
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The DFLL IP block on Tegra is a root clocksource designed for clocking
+the fast CPU cluster. It consists of a free-running voltage controlled
+oscillator connected to the CPU voltage rail (VDD_CPU), and a closed loop
+control module that will automatically adjust the VDD_CPU voltage by
+communicating with an off-chip PMIC either via an I2C bus or via PWM signals.
+Currently only the I2C mode is supported by these bindings.
+
+Required properties:
+- compatible : should be "nvidia,tegra124-dfll"
+- reg : Defines the following set of registers, in the order listed:
+        - registers for the DFLL control logic.
+        - registers for the I2C output logic.
+        - registers for the integrated I2C master controller.
+        - look-up table RAM for voltage register values.
+- interrupts: Should contain the DFLL block interrupt.
+- clocks: Must contain an entry for each entry in clock-names.
+  See clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+  - soc: Clock source for the DFLL control logic.
+  - ref: The closed loop reference clock
+  - i2c: Clock source for the integrated I2C master.
+- resets: Must contain an entry for each entry in reset-names.
+  See ../reset/reset.txt for details.
+- reset-names: Must include the following entries:
+  - dvco: Reset control for the DFLL DVCO.
+- #clock-cells: Must be 0.
+- clock-output-names: Name of the clock output.
+- vdd-cpu-supply: Regulator for the CPU voltage rail that the DFLL
+  hardware will start controlling. The regulator will be queried for
+  the I2C register, control values and supported voltages.
+
+Required properties for the control loop parameters:
+- nvidia,sample-rate: Sample rate of the DFLL control loop.
+- nvidia,droop-ctrl: See the register CL_DVFS_DROOP_CTRL in the TRM.
+- nvidia,force-mode: See the field DFLL_PARAMS_FORCE_MODE in the TRM.
+- nvidia,cf: Numeric value, see the field DFLL_PARAMS_CF_PARAM in the TRM.
+- nvidia,ci: Numeric value, see the field DFLL_PARAMS_CI_PARAM in the TRM.
+- nvidia,cg: Numeric value, see the field DFLL_PARAMS_CG_PARAM in the TRM.
+
+Optional properties for the control loop parameters:
+- nvidia,cg-scale: Boolean value, see the field DFLL_PARAMS_CG_SCALE in the TRM.
+
+Required properties for I2C mode:
+- nvidia,i2c-fs-rate: I2C transfer rate, if using full speed mode.
+
+Example:
+
+clock@0,70110000 {
+        compatible = "nvidia,tegra124-dfll";
+        reg = <0 0x70110000 0 0x100>, /* DFLL control */
+              <0 0x70110000 0 0x100>, /* I2C output control */
+              <0 0x70110100 0 0x100>, /* Integrated I2C controller */
+              <0 0x70110200 0 0x100>; /* Look-up table RAM */
+        interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&tegra_car TEGRA124_CLK_DFLL_SOC>,
+                 <&tegra_car TEGRA124_CLK_DFLL_REF>,
+                 <&tegra_car TEGRA124_CLK_I2C5>;
+        clock-names = "soc", "ref", "i2c";
+        resets = <&tegra_car TEGRA124_RST_DFLL_DVCO>;
+        reset-names = "dvco";
+        #clock-cells = <0>;
+        clock-output-names = "dfllCPU_out";
+        vdd-cpu-supply = <&vdd_cpu>;
+        status = "okay";
+
+        nvidia,sample-rate = <12500>;
+        nvidia,droop-ctrl = <0x00000f00>;
+        nvidia,force-mode = <1>;
+        nvidia,cf = <10>;
+        nvidia,ci = <0>;
+        nvidia,cg = <2>;
+
+        nvidia,i2c-fs-rate = <400000>;
+};
diff --git a/Documentation/devicetree/bindings/clock/renesas,r8a7778-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,r8a7778-cpg-clocks.txt
index 2f3747fdcf1c..e4cdaf1cb333 100644
--- a/Documentation/devicetree/bindings/clock/renesas,r8a7778-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,r8a7778-cpg-clocks.txt
@@ -1,7 +1,9 @@
 * Renesas R8A7778 Clock Pulse Generator (CPG)
 
 The CPG generates core clocks for the R8A7778. It includes two PLLs and
-several fixed ratio dividers
+several fixed ratio dividers.
+The CPG also provides a Clock Domain for SoC devices, in combination with the
+CPG Module Stop (MSTP) Clocks.
 
 Required Properties:
 
@@ -10,10 +12,18 @@ Required Properties:
   - #clock-cells: Must be 1
   - clock-output-names: The names of the clocks. Supported clocks are
     "plla", "pllb", "b", "out", "p", "s", and "s1".
+  - #power-domain-cells: Must be 0
 
+SoC devices that are part of the CPG/MSTP Clock Domain and can be power-managed
+through an MSTP clock should refer to the CPG device node in their
+"power-domains" property, as documented by the generic PM domain bindings in
+Documentation/devicetree/bindings/power/power_domain.txt.
 
-Example
--------
+
+Examples
+--------
+
+  - CPG device node:
 
 	cpg_clocks: cpg_clocks@ffc80000 {
 		compatible = "renesas,r8a7778-cpg-clocks";
@@ -22,4 +32,17 @@ Example
 		clocks = <&extal_clk>;
 		clock-output-names = "plla", "pllb", "b",
 				     "out", "p", "s", "s1";
+		#power-domain-cells = <0>;
+	};
+
+
+  - CPG/MSTP Clock Domain member device node:
+
+	sdhi0: sd@ffe4c000 {
+		compatible = "renesas,sdhi-r8a7778";
+		reg = <0xffe4c000 0x100>;
+		interrupts = <0 87 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp3_clks R8A7778_CLK_SDHI0>;
+		power-domains = <&cpg_clocks>;
+		status = "disabled";
 	};
diff --git a/Documentation/devicetree/bindings/clock/renesas,r8a7779-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,r8a7779-cpg-clocks.txt
index ed3c8cb12f4e..8c81547c29f5 100644
--- a/Documentation/devicetree/bindings/clock/renesas,r8a7779-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,r8a7779-cpg-clocks.txt
@@ -1,7 +1,9 @@
 * Renesas R8A7779 Clock Pulse Generator (CPG)
 
 The CPG generates core clocks for the R8A7779. It includes one PLL and
-several fixed ratio dividers
+several fixed ratio dividers.
+The CPG also provides a Clock Domain for SoC devices, in combination with the
+CPG Module Stop (MSTP) Clocks.
 
 Required Properties:
 
@@ -12,16 +14,36 @@ Required Properties:
   - #clock-cells: Must be 1
   - clock-output-names: The names of the clocks. Supported clocks are "plla",
     "z", "zs", "s", "s1", "p", "b", "out".
+  - #power-domain-cells: Must be 0
 
+SoC devices that are part of the CPG/MSTP Clock Domain and can be power-managed
+through an MSTP clock should refer to the CPG device node in their
+"power-domains" property, as documented by the generic PM domain bindings in
+Documentation/devicetree/bindings/power/power_domain.txt.
 
-Example
--------
+
+Examples
+--------
+
+  - CPG device node:
 
 	cpg_clocks: cpg_clocks@ffc80000 {
 		compatible = "renesas,r8a7779-cpg-clocks";
-		reg = <0 0xffc80000 0 0x30>;
+		reg = <0xffc80000 0x30>;
 		clocks = <&extal_clk>;
 		#clock-cells = <1>;
 		clock-output-names = "plla", "z", "zs", "s", "s1", "p",
 		                     "b", "out";
+		#power-domain-cells = <0>;
+	};
+
+
+  - CPG/MSTP Clock Domain member device node:
+
+	sata: sata@fc600000 {
+		compatible = "renesas,sata-r8a7779", "renesas,rcar-sata";
+		reg = <0xfc600000 0x2000>;
+		interrupts = <0 100 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7779_CLK_SATA>;
+		power-domains = <&cpg_clocks>;
 	};
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
index 56f111bd3e45..2a9a8edc8f35 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
@@ -2,6 +2,8 @@
 
 The CPG generates core clocks for the R-Car Gen2 SoCs. It includes three PLLs
 and several fixed ratio dividers.
+The CPG also provides a Clock Domain for SoC devices, in combination with the
+CPG Module Stop (MSTP) Clocks.
 
 Required Properties:
 
@@ -20,10 +22,18 @@ Required Properties:
   - clock-output-names: The names of the clocks. Supported clocks are "main",
     "pll0", "pll1", "pll3", "lb", "qspi", "sdh", "sd0", "sd1", "z", "rcan", and
     "adsp"
+  - #power-domain-cells: Must be 0
 
+SoC devices that are part of the CPG/MSTP Clock Domain and can be power-managed
+through an MSTP clock should refer to the CPG device node in their
+"power-domains" property, as documented by the generic PM domain bindings in
+Documentation/devicetree/bindings/power/power_domain.txt.
 
-Example
--------
+
+Examples
+--------
+
+  - CPG device node:
 
 	cpg_clocks: cpg_clocks@e6150000 {
 		compatible = "renesas,r8a7790-cpg-clocks",
@@ -34,4 +44,16 @@ Example
 		clock-output-names = "main", "pll0, "pll1", "pll3",
 				     "lb", "qspi", "sdh", "sd0", "sd1", "z",
 				     "rcan", "adsp";
+		#power-domain-cells = <0>;
+	};
+
+
+  - CPG/MSTP Clock Domain member device node:
+
+	thermal@e61f0000 {
+		compatible = "renesas,thermal-r8a7790", "renesas,rcar-thermal";
+		reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
+		interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+		power-domains = <&cpg_clocks>;
 	};
diff --git a/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt
index b0f7ddb8cdb1..bb51a33a1fbf 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt
@@ -2,6 +2,8 @@
 
 The CPG generates core clocks for the RZ SoCs. It includes the PLL, variable
 CPU and GPU clocks, and several fixed ratio dividers.
+The CPG also provides a Clock Domain for SoC devices, in combination with the
+CPG Module Stop (MSTP) Clocks.
 
 Required Properties:
 
@@ -14,10 +16,18 @@ Required Properties:
   - #clock-cells: Must be 1
   - clock-output-names: The names of the clocks. Supported clocks are "pll",
     "i", and "g"
+  - #power-domain-cells: Must be 0
 
+SoC devices that are part of the CPG/MSTP Clock Domain and can be power-managed
+through an MSTP clock should refer to the CPG device node in their
+"power-domains" property, as documented by the generic PM domain bindings in
+Documentation/devicetree/bindings/power/power_domain.txt.
 
-Example
--------
+
+Examples
+--------
+
+  - CPG device node:
 
 	cpg_clocks: cpg_clocks@fcfe0000 {
 		#clock-cells = <1>;
@@ -26,4 +36,19 @@ Example
 		reg = <0xfcfe0000 0x18>;
 		clocks = <&extal_clk>, <&usb_x1_clk>;
 		clock-output-names = "pll", "i", "g";
+		#power-domain-cells = <0>;
+	};
+
+
+  - CPG/MSTP Clock Domain member device node:
+
+	mtu2: timer@fcff0000 {
+		compatible = "renesas,mtu2-r7s72100", "renesas,mtu2";
+		reg = <0xfcff0000 0x400>;
+		interrupts = <0 107 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tgi0a";
+		clocks = <&mstp3_clks R7S72100_CLK_MTU2>;
+		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
+		status = "disabled";
 	};
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3368-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3368-cru.txt
new file mode 100644
index 000000000000..7c8bbcfed8d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3368-cru.txt
@@ -0,0 +1,61 @@
+* Rockchip RK3368 Clock and Reset Unit
+
+The RK3368 clock controller generates and supplies clock to various
+controllers within the SoC and also implements a reset controller for SoC
+peripherals.
+
+Required Properties:
+
+- compatible: should be "rockchip,rk3368-cru"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Optional Properties:
+
+- rockchip,grf: phandle to the syscon managing the "general register files"
+  If missing, pll rates are not changeable, due to the missing pll lock status.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/rk3368-cru.h headers and can be
+used in device tree sources. Similar macros exist for the reset sources in
+these files.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "xin24m" - crystal input - required,
+ - "xin32k" - rtc clock - optional,
+ - "ext_i2s" - external I2S clock - optional,
+ - "ext_gmac" - external GMAC clock - optional
+ - "ext_hsadc" - external HSADC clock - optional,
+ - "ext_isp" - external ISP clock - optional,
+ - "ext_jtag" - external JTAG clock - optional
+ - "ext_vip" - external VIP clock - optional,
+ - "usbotg_out" - output clock of the pll in the otg phy
+
+Example: Clock controller node:
+
+	cru: clock-controller@ff760000 {
+		compatible = "rockchip,rk3368-cru";
+		reg = <0x0 0xff760000 0x0 0x1000>;
+		rockchip,grf = <&grf>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart0: serial@10124000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x10124000 0x400>;
+		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <1>;
+		clocks = <&cru SCLK_UART0>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
index efb51cf0c845..d8b168ebd5f1 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
@@ -21,8 +21,8 @@ Required properties:
 	"st,stih416-plls-c32-ddr",	"st,clkgen-plls-c32"
 	"st,stih407-plls-c32-a0",	"st,clkgen-plls-c32"
 	"st,stih407-plls-c32-a9",	"st,clkgen-plls-c32"
-	"st,stih407-plls-c32-c0_0",	"st,clkgen-plls-c32"
-	"st,stih407-plls-c32-c0_1",	"st,clkgen-plls-c32"
+	"sst,plls-c32-cx_0",		"st,clkgen-plls-c32"
+	"sst,plls-c32-cx_1",		"st,clkgen-plls-c32"
 
 	"st,stih415-gpu-pll-c32",	"st,clkgengpu-pll-c32"
 	"st,stih416-gpu-pll-c32",	"st,clkgengpu-pll-c32"
diff --git a/Documentation/devicetree/bindings/clock/ux500.txt b/Documentation/devicetree/bindings/clock/ux500.txt
new file mode 100644
index 000000000000..e52bd4b72348
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/ux500.txt
@@ -0,0 +1,64 @@
+Clock bindings for ST-Ericsson Ux500 clocks
+
+Required properties :
+- compatible : shall contain only one of the following:
+  "stericsson,u8500-clks"
+  "stericsson,u8540-clks"
+  "stericsson,u9540-clks"
+- reg : shall contain base register location and length for
+  CLKRST1, 2, 3, 5, and 6 in an array. Note the absence of
+  CLKRST4, which does not exist.
+
+Required subnodes:
+- prcmu-clock: a subnode with one clock cell for PRCMU (power,
+  reset, control unit) clocks. The cell indicates which PRCMU
+  clock in the prcmu-clock node the consumer wants to use.
+- prcc-periph-clock: a subnode with two clock cells for
+  PRCC (programmable reset- and clock controller) peripheral clocks.
+  The first cell indicates which PRCC block the consumer
+  wants to use, possible values are 1, 2, 3, 5, 6. The second
+  cell indicates which clock inside the PRCC block it wants,
+  possible values are 0 thru 31.
+- prcc-kernel-clock: a subnode with two clock cells for
+  PRCC (programmable reset- and clock controller) kernel clocks
+  The first cell indicates which PRCC block the consumer
+  wants to use, possible values are 1, 2, 3, 5, 6. The second
+  cell indicates which clock inside the PRCC block it wants,
+  possible values are 0 thru 31.
+- rtc32k-clock: a subnode with zero clock cells for the 32kHz
+  RTC clock.
+- smp-twd-clock: a subnode for the ARM SMP Timer Watchdog cluster
+  with zero clock cells.
+
+Example:
+
+clocks {
+	compatible = "stericsson,u8500-clks";
+	/*
+	 * Registers for the CLKRST block on peripheral
+	 * groups 1, 2, 3, 5, 6,
+	 */
+	reg = <0x8012f000 0x1000>, <0x8011f000 0x1000>,
+	    <0x8000f000 0x1000>, <0xa03ff000 0x1000>,
+	    <0xa03cf000 0x1000>;
+
+	prcmu_clk: prcmu-clock {
+		#clock-cells = <1>;
+	};
+
+	prcc_pclk: prcc-periph-clock {
+		#clock-cells = <2>;
+	};
+
+	prcc_kclk: prcc-kernel-clock {
+		#clock-cells = <2>;
+	};
+
+	rtc_clk: rtc32k-clock {
+		#clock-cells = <0>;
+	};
+
+	smp_twd_clk: smp-twd-clock {
+		#clock-cells = <0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/cpufreq/tegra124-cpufreq.txt b/Documentation/devicetree/bindings/cpufreq/tegra124-cpufreq.txt
new file mode 100644
index 000000000000..b1669fbfb740
--- /dev/null
+++ b/Documentation/devicetree/bindings/cpufreq/tegra124-cpufreq.txt
@@ -0,0 +1,44 @@
+Tegra124 CPU frequency scaling driver bindings
+----------------------------------------------
+
+Both required and optional properties listed below must be defined
+under node /cpus/cpu@0.
+
+Required properties:
+- clocks: Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+  - cpu_g: Clock mux for the fast CPU cluster.
+  - cpu_lp: Clock mux for the low-power CPU cluster.
+  - pll_x: Fast PLL clocksource.
+  - pll_p: Auxiliary PLL used during fast PLL rate changes.
+  - dfll: Fast DFLL clocksource that also automatically scales CPU voltage.
+- vdd-cpu-supply: Regulator for CPU voltage
+
+Optional properties:
+- clock-latency: Specify the possible maximum transition latency for clock,
+  in unit of nanoseconds.
+
+Example:
+--------
+cpus {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	cpu@0 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0>;
+
+		clocks = <&tegra_car TEGRA124_CLK_CCLK_G>,
+			 <&tegra_car TEGRA124_CLK_CCLK_LP>,
+			 <&tegra_car TEGRA124_CLK_PLL_X>,
+			 <&tegra_car TEGRA124_CLK_PLL_P>,
+			 <&dfll>;
+		clock-names = "cpu_g", "cpu_lp", "pll_x", "pll_p", "dfll";
+		clock-latency = <300000>;
+		vdd-cpu-supply: <&vdd_cpu>;
+	};
+
+	<...>
+};
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
index e4022776ac6e..6831d025ec24 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
@@ -106,6 +106,18 @@ PROPERTIES
           to the interrupt parent to which the child domain
           is being mapped.
 
+   - clocks
+      Usage: required if SEC 4.0 requires explicit enablement of clocks
+      Value type: <prop_encoded-array>
+      Definition:  A list of phandle and clock specifier pairs describing
+          the clocks required for enabling and disabling SEC 4.0.
+
+   - clock-names
+      Usage: required if SEC 4.0 requires explicit enablement of clocks
+      Value type: <string>
+      Definition: A list of clock name strings in the same order as the
+          clocks property.
+
    Note: All other standard properties (see the ePAPR) are allowed
    but are optional.
 
@@ -120,6 +132,11 @@ EXAMPLE
 		ranges = <0 0x300000 0x10000>;
 		interrupt-parent = <&mpic>;
 		interrupts = <92 2>;
+		clocks = <&clks IMX6QDL_CLK_CAAM_MEM>,
+			 <&clks IMX6QDL_CLK_CAAM_ACLK>,
+			 <&clks IMX6QDL_CLK_CAAM_IPG>,
+			 <&clks IMX6QDL_CLK_EIM_SLOW>;
+		clock-names = "mem", "aclk", "ipg", "emi_slow";
 	};
 
 =====================================================================
@@ -288,12 +305,13 @@ Secure Non-Volatile Storage (SNVS) Node
     Node defines address range and the associated
     interrupt for the SNVS function.  This function
     monitors security state information & reports
-    security violations.
+    security violations. This also included rtc,
+    system power off and ON/OFF key.
 
   - compatible
       Usage: required
       Value type: <string>
-      Definition: Must include "fsl,sec-v4.0-mon".
+      Definition: Must include "fsl,sec-v4.0-mon" and "syscon".
 
   - reg
       Usage: required
@@ -324,7 +342,7 @@ Secure Non-Volatile Storage (SNVS) Node
            the child address, parent address, & length.
 
    - interrupts
-      Usage: required
+      Usage: optional
       Value type: <prop_encoded-array>
       Definition:  Specifies the interrupts generated by this
            device.  The value of the interrupts property
@@ -341,7 +359,7 @@ Secure Non-Volatile Storage (SNVS) Node
 
 EXAMPLE
 	sec_mon@314000 {
-		compatible = "fsl,sec-v4.0-mon";
+		compatible = "fsl,sec-v4.0-mon", "syscon";
 		reg = <0x314000 0x1000>;
 		ranges = <0 0x314000 0x1000>;
 		interrupt-parent = <&mpic>;
@@ -358,16 +376,72 @@ Secure Non-Volatile Storage (SNVS) Low Power (LP) RTC Node
       Value type: <string>
       Definition: Must include "fsl,sec-v4.0-mon-rtc-lp".
 
-  - reg
+  - interrupts
       Usage: required
-      Value type: <prop-encoded-array>
-      Definition: A standard property.  Specifies the physical
-          address and length of the SNVS LP configuration registers.
+      Value type: <prop_encoded-array>
+      Definition: Specifies the interrupts generated by this
+	   device.  The value of the interrupts property
+	   consists of one interrupt specifier. The format
+	   of the specifier is defined by the binding document
+	   describing the node's interrupt parent.
+
+ - regmap
+	Usage: required
+	Value type: <phandle>
+	Definition: this is phandle to the register map node.
+
+ - offset
+	Usage: option
+	value type: <u32>
+	Definition: LP register offset. default it is 0x34.
 
 EXAMPLE
-	sec_mon_rtc_lp@314000 {
+	sec_mon_rtc_lp@1 {
 		compatible = "fsl,sec-v4.0-mon-rtc-lp";
-		reg = <0x34 0x58>;
+		interrupts = <93 2>;
+		regmap = <&snvs>;
+		offset = <0x34>;
+	};
+
+=====================================================================
+System ON/OFF key driver
+
+  The snvs-pwrkey is designed to enable POWER key function which controlled
+  by SNVS ONOFF, the driver can report the status of POWER key and wakeup
+  system if pressed after system suspend.
+
+  - compatible:
+      Usage: required
+      Value type: <string>
+      Definition: Mush include "fsl,sec-v4.0-pwrkey".
+
+  - interrupts:
+      Usage: required
+      Value type: <prop_encoded-array>
+      Definition: The SNVS ON/OFF interrupt number to the CPU(s).
+
+  - linux,keycode:
+      Usage: option
+      Value type: <int>
+      Definition: Keycode to emit, KEY_POWER by default.
+
+  - wakeup-source:
+      Usage: option
+      Value type: <boo>
+      Definition: Button can wake-up the system.
+
+ - regmap:
+      Usage: required:
+      Value type: <phandle>
+      Definition: this is phandle to the register map node.
+
+EXAMPLE:
+	snvs-pwrkey@0x020cc000 {
+		compatible = "fsl,sec-v4.0-pwrkey";
+		regmap = <&snvs>;
+		interrupts = <0 4 0x4>
+	        linux,keycode = <116>; /* KEY_POWER */
+		wakeup;
 	};
 
 =====================================================================
@@ -443,12 +517,20 @@ FULL EXAMPLE
 		compatible = "fsl,sec-v4.0-mon";
 		reg = <0x314000 0x1000>;
 		ranges = <0 0x314000 0x1000>;
-		interrupt-parent = <&mpic>;
-		interrupts = <93 2>;
 
 		sec_mon_rtc_lp@34 {
 			compatible = "fsl,sec-v4.0-mon-rtc-lp";
-			reg = <0x34 0x58>;
+			regmap = <&sec_mon>;
+			offset = <0x34>;
+			interrupts = <93 2>;
+		};
+
+		snvs-pwrkey@0x020cc000 {
+			compatible = "fsl,sec-v4.0-pwrkey";
+			regmap = <&sec_mon>;
+			interrupts = <0 4 0x4>;
+			linux,keycode = <116>; /* KEY_POWER */
+			wakeup;
 		};
 	};
 
diff --git a/Documentation/devicetree/bindings/crypto/sun4i-ss.txt b/Documentation/devicetree/bindings/crypto/sun4i-ss.txt
new file mode 100644
index 000000000000..5d38e9b7033f
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/sun4i-ss.txt
@@ -0,0 +1,23 @@
+* Allwinner Security System found on A20 SoC
+
+Required properties:
+- compatible : Should be "allwinner,sun4i-a10-crypto".
+- reg: Should contain the Security System register location and length.
+- interrupts: Should contain the IRQ line for the Security System.
+- clocks : List of clock specifiers, corresponding to ahb and ss.
+- clock-names : Name of the functional clock, should be
+	* "ahb" : AHB gating clock
+	* "mod" : SS controller clock
+
+Optional properties:
+ - resets : phandle + reset specifier pair
+ - reset-names : must contain "ahb"
+
+Example:
+	crypto: crypto-engine@01c15000 {
+		compatible = "allwinner,sun4i-a10-crypto";
+		reg = <0x01c15000 0x1000>;
+		interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&ahb_gates 5>, <&ss_clk>;
+		clock-names = "ahb", "mod";
+	};
diff --git a/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt b/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt
index b54bf3a2ff57..3e36c1d11386 100644
--- a/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt
+++ b/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt
@@ -11,15 +11,14 @@ to various devfreq devices. The devfreq devices would use the event data when
 derterming the current state of each IP.
 
 Required properties:
-- compatible: Should be "samsung,exynos-ppmu".
+- compatible: Should be "samsung,exynos-ppmu" or "samsung,exynos-ppmu-v2.
 - reg: physical base address of each PPMU and length of memory mapped region.
 
 Optional properties:
 - clock-names : the name of clock used by the PPMU, "ppmu"
 - clocks : phandles for clock specified in "clock-names" property
-- #clock-cells: should be 1.
 
-Example1 : PPMU nodes in exynos3250.dtsi are listed below.
+Example1 : PPMUv1 nodes in exynos3250.dtsi are listed below.
 
 		ppmu_dmc0: ppmu_dmc0@106a0000 {
 			compatible = "samsung,exynos-ppmu";
@@ -108,3 +107,41 @@ Example2 : Events of each PPMU node in exynos3250-rinato.dts are listed below.
 			};
 		};
 	};
+
+Example3 : PPMUv2 nodes in exynos5433.dtsi are listed below.
+
+		ppmu_d0_cpu: ppmu_d0_cpu@10480000 {
+			compatible = "samsung,exynos-ppmu-v2";
+			reg = <0x10480000 0x2000>;
+			status = "disabled";
+		};
+
+		ppmu_d0_general: ppmu_d0_general@10490000 {
+			compatible = "samsung,exynos-ppmu-v2";
+			reg = <0x10490000 0x2000>;
+			status = "disabled";
+		};
+
+		ppmu_d0_rt: ppmu_d0_rt@104a0000 {
+			compatible = "samsung,exynos-ppmu-v2";
+			reg = <0x104a0000 0x2000>;
+			status = "disabled";
+		};
+
+		ppmu_d1_cpu: ppmu_d1_cpu@104b0000 {
+			compatible = "samsung,exynos-ppmu-v2";
+			reg = <0x104b0000 0x2000>;
+			status = "disabled";
+		};
+
+		ppmu_d1_general: ppmu_d1_general@104c0000 {
+			compatible = "samsung,exynos-ppmu-v2";
+			reg = <0x104c0000 0x2000>;
+			status = "disabled";
+		};
+
+		ppmu_d1_rt: ppmu_d1_rt@104d0000 {
+			compatible = "samsung,exynos-ppmu-v2";
+			reg = <0x104d0000 0x2000>;
+			status = "disabled";
+		};
diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
new file mode 100644
index 000000000000..47cb1d14b690
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
@@ -0,0 +1,61 @@
+Analog Device AXI-DMAC DMA controller
+
+Required properties:
+ - compatible: Must be "adi,axi-dmac-1.00.a".
+ - reg: Specification for the controllers memory mapped register map.
+ - interrupts: Specification for the controllers interrupt.
+ - clocks: Phandle and specifier to the controllers AXI interface clock
+ - #dma-cells: Must be 1.
+
+Required sub-nodes:
+ - adi,channels: This sub-node must contain a sub-node for each DMA channel. For
+   the channel sub-nodes the following bindings apply. They must match the
+   configuration options of the peripheral as it was instantiated.
+
+Required properties for adi,channels sub-node:
+ - #size-cells: Must be 0
+ - #address-cells: Must be 1
+
+Required channel sub-node properties:
+ - reg: Which channel this node refers to.
+ - adi,length-width: Width of the DMA transfer length register.
+ - adi,source-bus-width,
+   adi,destination-bus-width: Width of the source or destination bus in bits.
+ - adi,source-bus-type,
+   adi,destination-bus-type: Type of the source or destination bus. Must be one
+   of the following:
+	0 (AXI_DMAC_TYPE_AXI_MM): Memory mapped AXI interface
+	1 (AXI_DMAC_TYPE_AXI_STREAM): Streaming AXI interface
+	2 (AXI_DMAC_TYPE_AXI_FIFO): FIFO interface
+
+Optional channel properties:
+ - adi,cyclic: Must be set if the channel supports hardware cyclic DMA
+   transfers.
+ - adi,2d: Must be set if the channel supports hardware 2D DMA transfers.
+
+DMA clients connected to the AXI-DMAC DMA controller must use the format
+described in the dma.txt file using a one-cell specifier. The value of the
+specifier refers to the DMA channel index.
+
+Example:
+
+dma: dma@7c420000 {
+	compatible = "adi,axi-dmac-1.00.a";
+	reg = <0x7c420000 0x10000>;
+	interrupts = <0 57 0>;
+	clocks = <&clkc 16>;
+	#dma-cells = <1>;
+
+	adi,channels {
+		#size-cells = <0>;
+		#address-cells = <1>;
+
+		dma-channel@0 {
+			reg = <0>;
+			adi,source-bus-width = <32>;
+			adi,source-bus-type = <ADI_AXI_DMAC_TYPE_MM_AXI>;
+			adi,destination-bus-width = <64>;
+			adi,destination-bus-type = <ADI_AXI_DMAC_TYPE_FIFO>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
index d3058768b23d..c53e0b08032f 100644
--- a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
+++ b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
@@ -35,7 +35,7 @@ Example:
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/Documentation/devicetree/bindings/dma/arm-pl08x.txt b/Documentation/devicetree/bindings/dma/arm-pl08x.txt
new file mode 100644
index 000000000000..8a0097a029d3
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/arm-pl08x.txt
@@ -0,0 +1,54 @@
+* ARM PrimeCells PL080 and PL081 and derivatives DMA controller
+
+Required properties:
+- compatible: "arm,pl080", "arm,primecell";
+	      "arm,pl081", "arm,primecell";
+- reg: Address range of the PL08x registers
+- interrupt: The PL08x interrupt number
+- clocks: The clock running the IP core clock
+- clock-names: Must contain "apb_pclk"
+- lli-bus-interface-ahb1: if AHB master 1 is eligible for fetching LLIs
+- lli-bus-interface-ahb2: if AHB master 2 is eligible for fetching LLIs
+- mem-bus-interface-ahb1: if AHB master 1 is eligible for fetching memory contents
+- mem-bus-interface-ahb2: if AHB master 2 is eligible for fetching memory contents
+- #dma-cells: must be <2>. First cell should contain the DMA request,
+              second cell should contain either 1 or 2 depending on
+              which AHB master that is used.
+
+Optional properties:
+- dma-channels: contains the total number of DMA channels supported by the DMAC
+- dma-requests: contains the total number of DMA requests supported by the DMAC
+- memcpy-burst-size: the size of the bursts for memcpy: 1, 4, 8, 16, 32
+  64, 128 or 256 bytes are legal values
+- memcpy-bus-width: the bus width used for memcpy: 8, 16 or 32 are legal
+  values
+
+Clients
+Required properties:
+- dmas: List of DMA controller phandle, request channel and AHB master id
+- dma-names: Names of the aforementioned requested channels
+
+Example:
+
+dmac0: dma-controller@10130000 {
+	compatible = "arm,pl080", "arm,primecell";
+	reg = <0x10130000 0x1000>;
+	interrupt-parent = <&vica>;
+	interrupts = <15>;
+	clocks = <&hclkdma0>;
+	clock-names = "apb_pclk";
+	lli-bus-interface-ahb1;
+	lli-bus-interface-ahb2;
+	mem-bus-interface-ahb2;
+	memcpy-burst-size = <256>;
+	memcpy-bus-width = <32>;
+	#dma-cells = <2>;
+};
+
+device@40008000 {
+	...
+	dmas = <&dmac0 0 2
+		&dmac0 1 2>;
+	dma-names = "tx", "rx";
+	...
+};
diff --git a/Documentation/devicetree/bindings/dma/lpc1850-dmamux.txt b/Documentation/devicetree/bindings/dma/lpc1850-dmamux.txt
new file mode 100644
index 000000000000..87740adb2995
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/lpc1850-dmamux.txt
@@ -0,0 +1,54 @@
+NXP LPC18xx/43xx DMA MUX (DMA request router)
+
+Required properties:
+- compatible:	"nxp,lpc1850-dmamux"
+- reg:		Memory map for accessing module
+- #dma-cells:	Should be set to <3>.
+		* 1st cell contain the master dma request signal
+		* 2nd cell contain the mux value (0-3) for the peripheral
+		* 3rd cell contain either 1 or 2 depending on the AHB
+		  master used.
+- dma-requests:	Number of DMA requests for the mux
+- dma-masters:	phandle pointing to the DMA controller
+
+The DMA controller node need to have the following poroperties:
+- dma-requests:	Number of DMA requests the controller can handle
+
+Example:
+
+dmac: dma@40002000 {
+	compatible = "nxp,lpc1850-gpdma", "arm,pl080", "arm,primecell";
+	arm,primecell-periphid = <0x00041080>;
+	reg = <0x40002000 0x1000>;
+	interrupts = <2>;
+	clocks = <&ccu1 CLK_CPU_DMA>;
+	clock-names = "apb_pclk";
+	#dma-cells = <2>;
+	dma-channels = <8>;
+	dma-requests = <16>;
+	lli-bus-interface-ahb1;
+	lli-bus-interface-ahb2;
+	mem-bus-interface-ahb1;
+	mem-bus-interface-ahb2;
+	memcpy-burst-size = <256>;
+	memcpy-bus-width = <32>;
+};
+
+dmamux: dma-mux {
+	compatible = "nxp,lpc1850-dmamux";
+	#dma-cells = <3>;
+	dma-requests = <64>;
+	dma-masters = <&dmac>;
+};
+
+uart0: serial@40081000 {
+	compatible = "nxp,lpc1850-uart", "ns16550a";
+	reg = <0x40081000 0x1000>;
+	reg-shift = <2>;
+	interrupts = <24>;
+	clocks = <&ccu2 CLK_APB0_UART0>, <&ccu1 CLK_CPU_UART0>;
+	clock-names = "uartclk", "reg";
+	dmas = <&dmamux 1 1 2
+		&dmamux 2 1 2>;
+	dma-names = "tx", "rx";
+};
diff --git a/Documentation/devicetree/bindings/dma/mv-xor.txt b/Documentation/devicetree/bindings/dma/mv-xor.txt
index cc29c35266e2..276ef815ef32 100644
--- a/Documentation/devicetree/bindings/dma/mv-xor.txt
+++ b/Documentation/devicetree/bindings/dma/mv-xor.txt
@@ -12,10 +12,13 @@ XOR engine has. Those sub-nodes have the following required
 properties:
 - interrupts: interrupt of the XOR channel
 
-And the following optional properties:
+The sub-nodes used to contain one or several of the following
+properties, but they are now deprecated:
 - dmacap,memcpy to indicate that the XOR channel is capable of memcpy operations
 - dmacap,memset to indicate that the XOR channel is capable of memset operations
 - dmacap,xor to indicate that the XOR channel is capable of xor operations
+- dmacap,interrupt to indicate that the XOR channel is capable of
+  generating interrupts
 
 Example:
 
@@ -28,13 +31,8 @@ xor@d0060900 {
 
 	xor00 {
 	      interrupts = <51>;
-	      dmacap,memcpy;
-	      dmacap,xor;
 	};
 	xor01 {
 	      interrupts = <52>;
-	      dmacap,memcpy;
-	      dmacap,xor;
-	      dmacap,memset;
 	};
 };
diff --git a/Documentation/devicetree/bindings/dma/sun4i-dma.txt b/Documentation/devicetree/bindings/dma/sun4i-dma.txt
new file mode 100644
index 000000000000..f1634a27a830
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/sun4i-dma.txt
@@ -0,0 +1,46 @@
+Allwinner A10 DMA Controller
+
+This driver follows the generic DMA bindings defined in dma.txt.
+
+Required properties:
+
+- compatible:	Must be "allwinner,sun4i-a10-dma"
+- reg:		Should contain the registers base address and length
+- interrupts:	Should contain a reference to the interrupt used by this device
+- clocks:	Should contain a reference to the parent AHB clock
+- #dma-cells :	Should be 2, first cell denoting normal or dedicated dma,
+		second cell holding the request line number.
+
+Example:
+	dma: dma-controller@01c02000 {
+		compatible = "allwinner,sun4i-a10-dma";
+		reg = <0x01c02000 0x1000>;
+		interrupts = <27>;
+		clocks = <&ahb_gates 6>;
+		#dma-cells = <2>;
+	};
+
+Clients:
+
+DMA clients connected to the Allwinner A10 DMA controller must use the
+format described in the dma.txt file, using a three-cell specifier for
+each channel: a phandle plus two integer cells.
+The three cells in order are:
+
+1. A phandle pointing to the DMA controller.
+2. Whether it is using normal (0) or dedicated (1) channels
+3. The port ID as specified in the datasheet
+
+Example:
+	spi2: spi@01c17000 {
+		compatible = "allwinner,sun4i-a10-spi";
+		reg = <0x01c17000 0x1000>;
+		interrupts = <0 12 4>;
+		clocks = <&ahb_gates 22>, <&spi2_clk>;
+		clock-names = "ahb", "mod";
+		dmas = <&dma 1 29>, <&dma 1 28>;
+		dma-names = "rx", "tx";
+		status = "disabled";
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
diff --git a/Documentation/devicetree/bindings/dma/zxdma.txt b/Documentation/devicetree/bindings/dma/zxdma.txt
new file mode 100644
index 000000000000..3207ceb04d0b
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/zxdma.txt
@@ -0,0 +1,38 @@
+* ZTE ZX296702 DMA controller
+
+Required properties:
+- compatible: Should be "zte,zx296702-dma"
+- reg: Should contain DMA registers location and length.
+- interrupts: Should contain one interrupt shared by all channel
+- #dma-cells: see dma.txt, should be 1, para number
+- dma-channels: physical channels supported
+- dma-requests: virtual channels supported, each virtual channel
+		have specific request line
+- clocks: clock required
+
+Example:
+
+Controller:
+	dma: dma-controller@0x09c00000{
+		compatible = "zte,zx296702-dma";
+		reg = <0x09c00000 0x1000>;
+		clocks = <&topclk ZX296702_DMA_ACLK>;
+		interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>;
+		#dma-cells = <1>;
+		dma-channels = <24>;
+		dma-requests = <24>;
+	};
+
+Client:
+Use specific request line passing from dmax
+For example, spdif0 tx channel request line is 4
+	spdif0: spdif0@0b004000 {
+		#sound-dai-cells = <0>;
+		compatible = "zte,zx296702-spdif";
+		reg = <0x0b004000 0x1000>;
+		clocks = <&lsp0clk ZX296702_SPDIF0_DIV>;
+		clock-names = "tx";
+		interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+		dmas = <&dma 4>;
+		dma-names = "tx";
+	}
diff --git a/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt b/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt
index e75f0e549fff..971c3eedb1c7 100644
--- a/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt
+++ b/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt
@@ -65,8 +65,10 @@ Optional properties:
 - edid: verbatim EDID data block describing attached display.
 - ddc: phandle describing the i2c bus handling the display data
   channel
-- port: A port node with endpoint definitions as defined in
+- port@[0-1]: Port nodes with endpoint definitions as defined in
   Documentation/devicetree/bindings/media/video-interfaces.txt.
+  Port 0 is the input port connected to the IPU display interface,
+  port 1 is the output port connected to a panel.
 
 example:
 
@@ -75,9 +77,29 @@ display@di0 {
 	edid = [edid-data];
 	interface-pix-fmt = "rgb24";
 
-	port {
+	port@0 {
+		reg = <0>;
+
 		display_in: endpoint {
 			remote-endpoint = <&ipu_di0_disp0>;
 		};
 	};
+
+	port@1 {
+		reg = <1>;
+
+		display_out: endpoint {
+			remote-endpoint = <&panel_in>;
+		};
+	};
+};
+
+panel {
+	...
+
+	port {
+		panel_in: endpoint {
+			remote-endpoint = <&display_out>;
+		};
+	};
 };
diff --git a/Documentation/devicetree/bindings/drm/msm/dsi.txt b/Documentation/devicetree/bindings/drm/msm/dsi.txt
index cd8fe6cf536c..d56923cd5590 100644
--- a/Documentation/devicetree/bindings/drm/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/drm/msm/dsi.txt
@@ -30,20 +30,27 @@ Optional properties:
 - panel@0: Node of panel connected to this DSI controller.
   See files in Documentation/devicetree/bindings/panel/ for each supported
   panel.
-- qcom,dual-panel-mode: Boolean value indicating if the DSI controller is
+- qcom,dual-dsi-mode: Boolean value indicating if the DSI controller is
   driving a panel which needs 2 DSI links.
-- qcom,master-panel: Boolean value indicating if the DSI controller is driving
+- qcom,master-dsi: Boolean value indicating if the DSI controller is driving
   the master link of the 2-DSI panel.
-- qcom,sync-dual-panel: Boolean value indicating if the DSI controller is
+- qcom,sync-dual-dsi: Boolean value indicating if the DSI controller is
   driving a 2-DSI panel whose 2 links need receive command simultaneously.
 - interrupt-parent: phandle to the MDP block if the interrupt signal is routed
   through MDP block
+- pinctrl-names: the pin control state names; should contain "default"
+- pinctrl-0: the default pinctrl state (active)
+- pinctrl-n: the "sleep" pinctrl state
+- port: DSI controller output port. This contains one endpoint subnode, with its
+  remote-endpoint set to the phandle of the connected panel's endpoint.
+  See Documentation/devicetree/bindings/graph.txt for device graph info.
 
 DSI PHY:
 Required properties:
 - compatible: Could be the following
   * "qcom,dsi-phy-28nm-hpm"
   * "qcom,dsi-phy-28nm-lp"
+  * "qcom,dsi-phy-20nm"
 - reg: Physical base address and length of the registers of PLL, PHY and PHY
   regulator
 - reg-names: The names of register regions. The following regions are required:
@@ -59,6 +66,10 @@ Required properties:
   * "iface_clk"
 - vddio-supply: phandle to vdd-io regulator device node
 
+Optional properties:
+- qcom,dsi-phy-regulator-ldo-mode: Boolean value indicating if the LDO mode PHY
+  regulator is wanted.
+
 Example:
 	mdss_dsi0: qcom,mdss_dsi@fd922800 {
 		compatible = "qcom,mdss-dsi-ctrl";
@@ -90,9 +101,13 @@ Example:
 
 		qcom,dsi-phy = <&mdss_dsi_phy0>;
 
-		qcom,dual-panel-mode;
-		qcom,master-panel;
-		qcom,sync-dual-panel;
+		qcom,dual-dsi-mode;
+		qcom,master-dsi;
+		qcom,sync-dual-dsi;
+
+		pinctrl-names = "default", "sleep";
+		pinctrl-0 = <&mdss_dsi_active>;
+		pinctrl-1 = <&mdss_dsi_suspend>;
 
 		panel: panel@0 {
 			compatible = "sharp,lq101r1sx01";
@@ -101,6 +116,18 @@ Example:
 
 			power-supply = <...>;
 			backlight = <...>;
+
+			port {
+				panel_in: endpoint {
+					remote-endpoint = <&dsi0_out>;
+				};
+			};
+		};
+
+		port {
+			dsi0_out: endpoint {
+				remote-endpoint = <&panel_in>;
+			};
 		};
 	};
 
@@ -117,4 +144,6 @@ Example:
 		clock-names = "iface_clk";
 		clocks = <&mmcc MDSS_AHB_CLK>;
 		vddio-supply = <&pma8084_l12>;
+
+		qcom,dsi-phy-regulator-ldo-mode;
 	};
diff --git a/Documentation/devicetree/bindings/drm/msm/hdmi.txt b/Documentation/devicetree/bindings/drm/msm/hdmi.txt
index c43aa53debed..e926239e1101 100644
--- a/Documentation/devicetree/bindings/drm/msm/hdmi.txt
+++ b/Documentation/devicetree/bindings/drm/msm/hdmi.txt
@@ -2,8 +2,9 @@ Qualcomm adreno/snapdragon hdmi output
 
 Required properties:
 - compatible: one of the following
+   * "qcom,hdmi-tx-8994"
    * "qcom,hdmi-tx-8084"
-   * "qcom,hdmi-tx-8074"
+   * "qcom,hdmi-tx-8974"
    * "qcom,hdmi-tx-8660"
    * "qcom,hdmi-tx-8960"
 - reg: Physical base address and length of the controller's registers
diff --git a/Documentation/devicetree/bindings/extcon/extcon-palmas.txt b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
index 45414bbcd945..f61d5af44a27 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
@@ -10,8 +10,11 @@ Required Properties:
 
 Optional Properties:
  - ti,wakeup : To enable the wakeup comparator in probe
- - ti,enable-id-detection: Perform ID detection.
+ - ti,enable-id-detection: Perform ID detection. If id-gpio is specified
+		it performs id-detection using GPIO else using OTG core.
  - ti,enable-vbus-detection: Perform VBUS detection.
+ - id-gpio: gpio for GPIO ID detection. See gpio binding.
+ - debounce-delay-ms: debounce delay for GPIO ID pin in milliseconds.
 
 palmas-usb {
        compatible = "ti,twl6035-usb", "ti,palmas-usb";
diff --git a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
index 435f1bcca341..b405b4410bfb 100644
--- a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
@@ -33,6 +33,13 @@ Optional properties:
 - interrupt-parent:
     phandle of the parent interrupt controller
 
+- interrupts-extended:
+    Alternate form of specifying interrupts and parents that allows for
+    multiple parents.  This takes precedence over 'interrupts' and
+    'interrupt-parent'.  Wakeup-capable GPIO controllers often route their
+    wakeup interrupt lines through a different interrupt controller than the
+    primary interrupt line, making this property necessary.
+
 - #interrupt-cells:
     Should be <2>.  The first cell is the GPIO number, the second should specify
     flags.  The following subset of flags is supported:
@@ -47,19 +54,33 @@ Optional properties:
 - interrupt-controller:
     Marks the device node as an interrupt controller
 
-- interrupt-names:
-    The name of the IRQ resource used by this controller
+- wakeup-source:
+    GPIOs for this controller can be used as a wakeup source
 
 Example:
 	upg_gio: gpio@f040a700 {
-		#gpio-cells = <0x2>;
-		#interrupt-cells = <0x2>;
+		#gpio-cells = <2>;
+		#interrupt-cells = <2>;
 		compatible = "brcm,bcm7445-gpio", "brcm,brcmstb-gpio";
 		gpio-controller;
 		interrupt-controller;
 		reg = <0xf040a700 0x80>;
-		interrupt-parent = <0xf>;
+		interrupt-parent = <&irq0_intc>;
+		interrupts = <0x6>;
+		brcm,gpio-bank-widths = <32 32 32 24>;
+	};
+
+	upg_gio_aon: gpio@f04172c0 {
+		#gpio-cells = <2>;
+		#interrupt-cells = <2>;
+		compatible = "brcm,bcm7445-gpio", "brcm,brcmstb-gpio";
+		gpio-controller;
+		interrupt-controller;
+		reg = <0xf04172c0 0x40>;
+		interrupt-parent = <&irq0_aon_intc>;
 		interrupts = <0x6>;
-		interrupt-names = "upg_gio";
-		brcm,gpio-bank-widths = <0x20 0x20 0x20 0x18>;
+		interrupts-extended = <&irq0_aon_intc 0x6>,
+			<&aon_pm_l2_intc 0x5>;
+		wakeup-source;
+		brcm,gpio-bank-widths = <18 4>;
 	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt b/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
index abf4db736c6e..170194af3027 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
@@ -2,8 +2,9 @@ Axis ETRAX FS General I/O controller bindings
 
 Required properties:
 
-- compatible:
+- compatible: one of:
   - "axis,etraxfs-gio"
+  - "axis,artpec3-gio"
 - reg: Physical base address and length of the controller's registers.
 - #gpio-cells: Should be 3
   - The first cell is the gpio offset number.
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
new file mode 100644
index 000000000000..805ddcd79a57
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
@@ -0,0 +1,22 @@
+* Freescale MPC512x/MPC8xxx GPIO controller
+
+Required properties:
+- compatible : Should be "fsl,<soc>-gpio"
+  The following <soc>s are known to be supported:
+    mpc5121, mpc5125, mpc8349, mpc8572, mpc8610, pq3, qoriq
+- reg : Address and length of the register set for the device
+- interrupts : Should be the port interrupt shared by all 32 pins.
+- #gpio-cells : Should be two.  The first cell is the pin number and
+  the second cell is used to specify the gpio polarity:
+      0 = active high
+      1 = active low
+
+Example:
+
+gpio0: gpio@1100 {
+	compatible = "fsl,mpc5125-gpio";
+	#gpio-cells = <2>;
+	reg = <0x1100 0x080>;
+	interrupts = <78 0x8>;
+	status = "okay";
+};
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index 38fb86f28ba2..f60e2f477e93 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -9,6 +9,7 @@ Required Properties:
     - "renesas,gpio-r8a7791": for R8A7791 (R-Car M2-W) compatible GPIO controller.
     - "renesas,gpio-r8a7793": for R8A7793 (R-Car M2-N) compatible GPIO controller.
     - "renesas,gpio-r8a7794": for R8A7794 (R-Car E2) compatible GPIO controller.
+    - "renesas,gpio-r8a7795": for R8A7795 (R-Car H3) compatible GPIO controller.
     - "renesas,gpio-rcar": for generic R-Car GPIO controller.
 
   - reg: Base address and length of each memory resource used by the GPIO
diff --git a/Documentation/devicetree/bindings/gpio/zx296702-gpio.txt b/Documentation/devicetree/bindings/gpio/zx296702-gpio.txt
new file mode 100644
index 000000000000..0dab156fcf41
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/zx296702-gpio.txt
@@ -0,0 +1,24 @@
+ZTE ZX296702 GPIO controller
+
+Required properties:
+- compatible : "zte,zx296702-gpio"
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional parameters:
+  - bit 0 specifies polarity (0 for normal, 1 for inverted)
+- gpio-controller : Marks the device node as a GPIO controller.
+- interrupts : Interrupt mapping for GPIO IRQ.
+- gpio-ranges : Interaction with the PINCTRL subsystem.
+
+gpio1: gpio@b008040 {
+	compatible = "zte,zx296702-gpio";
+	reg = <0xb008040 0x40>;
+	gpio-controller;
+	#gpio-cells = <2>;
+	gpio-ranges = < &pmx0 0 54 2 &pmx0 2 59 14>;
+	interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+	interrupt-parent = <&intc>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+	clock-names = "gpio_pclk";
+	clocks = <&lsp0clk ZX296702_GPIO_CLK>;
+};
diff --git a/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt b/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
index 009f4bfa1590..e685610d38e2 100644
--- a/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
+++ b/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
@@ -197,9 +197,11 @@ of the following host1x client modules:
 - sor: serial output resource
 
   Required properties:
-  - compatible: For Tegra124, must contain "nvidia,tegra124-sor".  Otherwise,
-    must contain '"nvidia,<chip>-sor", "nvidia,tegra124-sor"', where <chip>
-    is tegra132.
+  - compatible: Should be:
+    - "nvidia,tegra124-sor": for Tegra124 and Tegra132
+    - "nvidia,tegra132-sor": for Tegra132
+    - "nvidia,tegra210-sor": for Tegra210
+    - "nvidia,tegra210-sor1": for Tegra210
   - reg: Physical base address and length of the controller's registers.
   - interrupts: The interrupt outputs from the controller.
   - clocks: Must contain an entry for each entry in clock-names.
diff --git a/Documentation/devicetree/bindings/gpu/st,stih4xx.txt b/Documentation/devicetree/bindings/gpu/st,stih4xx.txt
index 6b1d75f1a529..a36dfce0032e 100644
--- a/Documentation/devicetree/bindings/gpu/st,stih4xx.txt
+++ b/Documentation/devicetree/bindings/gpu/st,stih4xx.txt
@@ -52,10 +52,9 @@ STMicroelectronics stih4xx platforms
     See ../reset/reset.txt for details.
   - reset-names: names of the resets listed in resets property in the same
     order.
-  - ranges: to allow probing of subdevices
 
 - sti-hdmi: hdmi output block
-  must be a child of sti-tvout
+  must be a child of sti-display-subsystem
   Required properties:
   - compatible: "st,stih<chip>-hdmi";
   - reg: Physical base address of the IP registers and length of memory mapped region.
@@ -72,7 +71,7 @@ STMicroelectronics stih4xx platforms
 
 sti-hda:
   Required properties:
-  must be a child of sti-tvout
+  must be a child of sti-display-subsystem
   - compatible: "st,stih<chip>-hda"
   - reg: Physical base address of the IP registers and length of memory mapped region.
   - reg-names: names of the mapped memory regions listed in regs property in
@@ -85,7 +84,7 @@ sti-hda:
 
 sti-dvo:
   Required properties:
-  must be a child of sti-tvout
+  must be a child of sti-display-subsystem
   - compatible: "st,stih<chip>-dvo"
   - reg: Physical base address of the IP registers and length of memory mapped region.
   - reg-names: names of the mapped memory regions listed in regs property in
@@ -195,38 +194,37 @@ Example:
 			reg-names	= "tvout-reg", "hda-reg", "syscfg";
 			reset-names     = "tvout";
 			resets          = <&softreset STIH416_HDTVOUT_SOFTRESET>;
-			ranges;
-
-			sti-hdmi@fe85c000 {
-				compatible	= "st,stih416-hdmi";
-				reg		= <0xfe85c000 0x1000>, <0xfe830000 0x10000>;
-				reg-names	= "hdmi-reg", "syscfg";
-				interrupts	= <GIC_SPI 173 IRQ_TYPE_NONE>;
-				interrupt-names	= "irq";
-				clock-names	= "pix", "tmds", "phy", "audio";
-				clocks          = <&clockgen_c_vcc CLK_S_PIX_HDMI>, <&clockgen_c_vcc CLK_S_TMDS_HDMI>, <&clockgen_c_vcc CLK_S_HDMI_REJECT_PLL>, <&clockgen_b1 CLK_S_PCM_0>;
-			};
-
-			sti-hda@fe85a000 {
-				compatible	= "st,stih416-hda";
-				reg		= <0xfe85a000 0x400>, <0xfe83085c 0x4>;
-				reg-names	= "hda-reg", "video-dacs-ctrl";
-				clock-names	= "pix", "hddac";
-				clocks          = <&clockgen_c_vcc CLK_S_PIX_HD>, <&clockgen_c_vcc CLK_S_HDDAC>;
-			};
-
-			sti-dvo@8d00400 {
-				compatible	= "st,stih407-dvo";
-				reg		= <0x8d00400 0x200>;
-				reg-names	= "dvo-reg";
-				clock-names	= "dvo_pix", "dvo",
-						  "main_parent", "aux_parent";
-				clocks		= <&clk_s_d2_flexgen CLK_PIX_DVO>, <&clk_s_d2_flexgen CLK_DVO>,
-						  <&clk_s_d2_quadfs 0>, <&clk_s_d2_quadfs 1>;
-				pinctrl-names	= "default";
-				pinctrl-0	= <&pinctrl_dvo>;
-				sti,panel	= <&panel_dvo>;
-			};
+		};
+
+		sti-hdmi@fe85c000 {
+			compatible	= "st,stih416-hdmi";
+			reg		= <0xfe85c000 0x1000>, <0xfe830000 0x10000>;
+			reg-names	= "hdmi-reg", "syscfg";
+			interrupts	= <GIC_SPI 173 IRQ_TYPE_NONE>;
+			interrupt-names	= "irq";
+			clock-names	= "pix", "tmds", "phy", "audio";
+			clocks          = <&clockgen_c_vcc CLK_S_PIX_HDMI>, <&clockgen_c_vcc CLK_S_TMDS_HDMI>, <&clockgen_c_vcc CLK_S_HDMI_REJECT_PLL>, <&clockgen_b1 CLK_S_PCM_0>;
+		};
+
+		sti-hda@fe85a000 {
+			compatible	= "st,stih416-hda";
+			reg		= <0xfe85a000 0x400>, <0xfe83085c 0x4>;
+			reg-names	= "hda-reg", "video-dacs-ctrl";
+			clock-names	= "pix", "hddac";
+			clocks          = <&clockgen_c_vcc CLK_S_PIX_HD>, <&clockgen_c_vcc CLK_S_HDDAC>;
+		};
+
+		sti-dvo@8d00400 {
+			compatible	= "st,stih407-dvo";
+			reg		= <0x8d00400 0x200>;
+			reg-names	= "dvo-reg";
+			clock-names	= "dvo_pix", "dvo",
+					  "main_parent", "aux_parent";
+			clocks		= <&clk_s_d2_flexgen CLK_PIX_DVO>, <&clk_s_d2_flexgen CLK_DVO>,
+					  <&clk_s_d2_quadfs 0>, <&clk_s_d2_quadfs 1>;
+			pinctrl-names	= "default";
+			pinctrl-0	= <&pinctrl_dvo>;
+			sti,panel	= <&panel_dvo>;
 		};
 
 		sti-hqvdp@9c000000 {
@@ -237,7 +235,7 @@ Example:
 				reset-names     = "hqvdp";
 				resets          = <&softreset STIH407_HDQVDP_SOFTRESET>;
 				st,vtg		= <&vtg_main>;
-			};
+		};
 	};
 	...
 };
diff --git a/Documentation/devicetree/bindings/hwmon/lm70.txt b/Documentation/devicetree/bindings/hwmon/lm70.txt
new file mode 100644
index 000000000000..e7fd921aa4f1
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/lm70.txt
@@ -0,0 +1,21 @@
+* LM70/TMP121/LM71/LM74 thermometer.
+
+Required properties:
+- compatible: one of
+		"ti,lm70"
+		"ti,tmp121"
+		"ti,lm71"
+		"ti,lm74"
+
+See Documentation/devicetree/bindings/spi/spi-bus.txt for more required and
+optional properties.
+
+Example:
+
+spi_master {
+	temperature-sensor@0 {
+		compatible = "ti,lm70";
+		reg = <0>;
+		spi-max-frequency = <1000000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/hwmon/ltc2978.txt b/Documentation/devicetree/bindings/hwmon/ltc2978.txt
index ed2f09dc2483..a7afbf60bb9c 100644
--- a/Documentation/devicetree/bindings/hwmon/ltc2978.txt
+++ b/Documentation/devicetree/bindings/hwmon/ltc2978.txt
@@ -3,10 +3,16 @@ ltc2978
 Required properties:
 - compatible: should contain one of:
   * "lltc,ltc2974"
+  * "lltc,ltc2975"
   * "lltc,ltc2977"
   * "lltc,ltc2978"
+  * "lltc,ltc2980"
   * "lltc,ltc3880"
+  * "lltc,ltc3882"
   * "lltc,ltc3883"
+  * "lltc,ltc3886"
+  * "lltc,ltc3887"
+  * "lltc,ltm2987"
   * "lltc,ltm4676"
 - reg: I2C slave address
 
@@ -17,10 +23,10 @@ Optional properties:
   standard binding for regulators; see regulator.txt.
 
 Valid names of regulators depend on number of supplies supported per device:
-  * ltc2974 : vout0 - vout3
-  * ltc2977 : vout0 - vout7
+  * ltc2974, ltc2975 : vout0 - vout3
+  * ltc2977, ltc2980, ltm2987 : vout0 - vout7
   * ltc2978 : vout0 - vout7
-  * ltc3880 : vout0 - vout1
+  * ltc3880, ltc3882, ltc3886 : vout0 - vout1
   * ltc3883 : vout0
   * ltm4676 : vout0 - vout1
 
diff --git a/Documentation/devicetree/bindings/iio/adc/mcp320x.txt b/Documentation/devicetree/bindings/iio/adc/mcp320x.txt
index b85184391b78..2a1f3af30155 100644
--- a/Documentation/devicetree/bindings/iio/adc/mcp320x.txt
+++ b/Documentation/devicetree/bindings/iio/adc/mcp320x.txt
@@ -18,6 +18,7 @@ Required properties:
 				"mcp3202"
 				"mcp3204"
 				"mcp3208"
+				"mcp3301"
 
 
 Examples:
diff --git a/Documentation/devicetree/bindings/iio/adc/vf610-adc.txt b/Documentation/devicetree/bindings/iio/adc/vf610-adc.txt
index 3eb40e20c143..1aad0514e647 100644
--- a/Documentation/devicetree/bindings/iio/adc/vf610-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/vf610-adc.txt
@@ -17,6 +17,11 @@ Recommended properties:
   - Frequency in normal mode (ADLPC=0, ADHSC=0)
   - Frequency in high-speed mode (ADLPC=0, ADHSC=1)
   - Frequency in low-power mode (ADLPC=1, ADHSC=0)
+- min-sample-time: Minimum sampling time in nanoseconds. This value has
+  to be chosen according to the conversion mode and the connected analog
+  source resistance (R_as) and capacitance (C_as). Refer the datasheet's
+  operating requirements. A safe default across a wide range of R_as and
+  C_as as well as conversion modes is 1000ns.
 
 Example:
 adc0: adc@4003b000 {
diff --git a/Documentation/devicetree/bindings/iio/magnetometer/mmc35240.txt b/Documentation/devicetree/bindings/iio/magnetometer/mmc35240.txt
new file mode 100644
index 000000000000..a01235c7fa15
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/magnetometer/mmc35240.txt
@@ -0,0 +1,13 @@
+* MEMSIC MMC35240 magnetometer sensor
+
+Required properties:
+
+  - compatible : should be "memsic,mmc35240"
+  - reg : the I2C address of the magnetometer
+
+Example:
+
+mmc35240@30 {
+        compatible = "memsic,mmc35240";
+        reg = <0x30>;
+};
diff --git a/Documentation/devicetree/bindings/iio/st-sensors.txt b/Documentation/devicetree/bindings/iio/st-sensors.txt
index 8a6be3bdf267..d3ccdb190c53 100644
--- a/Documentation/devicetree/bindings/iio/st-sensors.txt
+++ b/Documentation/devicetree/bindings/iio/st-sensors.txt
@@ -35,6 +35,7 @@ Accelerometers:
 - st,lsm303dl-accel
 - st,lsm303dlm-accel
 - st,lsm330-accel
+- st,lsm303agr-accel
 
 Gyroscopes:
 - st,l3g4200d-gyro
@@ -46,6 +47,7 @@ Gyroscopes:
 - st,lsm330-gyro
 
 Magnetometers:
+- st,lsm303agr-magn
 - st,lsm303dlh-magn
 - st,lsm303dlhc-magn
 - st,lsm303dlm-magn
diff --git a/Documentation/devicetree/bindings/input/ads7846.txt b/Documentation/devicetree/bindings/input/ads7846.txt
index 5f7619c22743..df8b1279491d 100644
--- a/Documentation/devicetree/bindings/input/ads7846.txt
+++ b/Documentation/devicetree/bindings/input/ads7846.txt
@@ -64,7 +64,7 @@ Optional properties:
 					pendown-gpio (u32).
 	pendown-gpio			GPIO handle describing the pin the !PENIRQ
 					line is connected to.
-	linux,wakeup			use any event on touchscreen as wakeup event.
+	wakeup-source			use any event on touchscreen as wakeup event.
 
 
 Example for a TSC2046 chip connected to an McSPI controller of an OMAP SoC::
diff --git a/Documentation/devicetree/bindings/input/cap11xx.txt b/Documentation/devicetree/bindings/input/cap11xx.txt
index 7d0a3009771b..8c67a0b5058d 100644
--- a/Documentation/devicetree/bindings/input/cap11xx.txt
+++ b/Documentation/devicetree/bindings/input/cap11xx.txt
@@ -55,5 +55,24 @@ i2c_controller {
 				 <105>,		/* KEY_LEFT */
 				 <109>,		/* KEY_PAGEDOWN */
 				 <104>;		/* KEY_PAGEUP */
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		usr@0 {
+			label = "cap11xx:green:usr0";
+			reg = <0>;
+		};
+
+		usr@1 {
+			label = "cap11xx:green:usr1";
+			reg = <1>;
+		};
+
+		alive@2 {
+			label = "cap11xx:green:alive";
+			reg = <2>;
+			linux,default_trigger = "heartbeat";
+		};
 	};
 }
diff --git a/Documentation/devicetree/bindings/input/cypress,cyapa.txt b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
new file mode 100644
index 000000000000..635a3b036630
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
@@ -0,0 +1,44 @@
+Cypress I2C Touchpad
+
+Required properties:
+- compatible: must be "cypress,cyapa".
+- reg: I2C address of the chip.
+- interrupt-parent: a phandle for the interrupt controller (see interrupt
+	binding[0]).
+- interrupts: interrupt to which the chip is connected (see interrupt
+	binding[0]).
+
+Optional properties:
+- wakeup-source: touchpad can be used as a wakeup source.
+- pinctrl-names: should be "default" (see pinctrl binding [1]).
+- pinctrl-0: a phandle pointing to the pin settings for the device (see
+	pinctrl binding [1]).
+- vcc-supply: a phandle for the regulator supplying 3.3V power.
+
+[0]: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+[1]: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+
+Example:
+	&i2c0 {
+		/* ... */
+
+		/* Cypress Gen3 touchpad */
+		touchpad@67 {
+			compatible = "cypress,cyapa";
+			reg = <0x24>;
+			interrupt-parent = <&gpio>;
+			interrupts = <2 IRQ_TYPE_EDGE_FALLING>;	/* GPIO 2 */
+			wakeup-source;
+		};
+
+		/* Cypress Gen5 and later touchpad */
+		touchpad@24 {
+			compatible = "cypress,cyapa";
+			reg = <0x24>;
+			interrupt-parent = <&gpio>;
+			interrupts = <2 IRQ_TYPE_EDGE_FALLING>;	/* GPIO 2 */
+			wakeup-source;
+		};
+
+		/* ... */
+	};
diff --git a/Documentation/devicetree/bindings/input/elants_i2c.txt b/Documentation/devicetree/bindings/input/elants_i2c.txt
index a765232e6446..8a71038f3489 100644
--- a/Documentation/devicetree/bindings/input/elants_i2c.txt
+++ b/Documentation/devicetree/bindings/input/elants_i2c.txt
@@ -13,6 +13,9 @@ Optional properties:
 - pinctrl-names: should be "default" (see pinctrl binding [1]).
 - pinctrl-0: a phandle pointing to the pin settings for the device (see
   pinctrl binding [1]).
+- reset-gpios: reset gpio the chip is connected to.
+- vcc33-supply: a phandle for the regulator supplying 3.3V power.
+- vccio-supply: a phandle for the regulator supplying IO power.
 
 [0]: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 [1]: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
diff --git a/Documentation/devicetree/bindings/input/gpio-keys-polled.txt b/Documentation/devicetree/bindings/input/gpio-keys-polled.txt
index 313abefa37cc..5b91f5a3bd5c 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys-polled.txt
+++ b/Documentation/devicetree/bindings/input/gpio-keys-polled.txt
@@ -20,7 +20,7 @@ Optional subnode-properties:
 	  If not specified defaults to <1> == EV_KEY.
 	- debounce-interval: Debouncing interval time in milliseconds.
 	  If not specified defaults to 5.
-	- gpio-key,wakeup: Boolean, button can wake-up the system.
+	- wakeup-source: Boolean, button can wake-up the system.
 
 Example nodes:
 
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.txt b/Documentation/devicetree/bindings/input/gpio-keys.txt
index 44b705767aca..072bf7573c37 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.txt
+++ b/Documentation/devicetree/bindings/input/gpio-keys.txt
@@ -23,7 +23,7 @@ Optional subnode-properties:
 	  If not specified defaults to <1> == EV_KEY.
 	- debounce-interval: Debouncing interval time in milliseconds.
 	  If not specified defaults to 5.
-	- gpio-key,wakeup: Boolean, button can wake-up the system.
+	- wakeup-source: Boolean, button can wake-up the system.
 	- linux,can-disable: Boolean, indicates that button is connected
 	  to dedicated (not shared) interrupt which can be disabled to
 	  suppress events from the button.
diff --git a/Documentation/devicetree/bindings/input/gpio-matrix-keypad.txt b/Documentation/devicetree/bindings/input/gpio-matrix-keypad.txt
index ead641c65e0a..4d86059c370c 100644
--- a/Documentation/devicetree/bindings/input/gpio-matrix-keypad.txt
+++ b/Documentation/devicetree/bindings/input/gpio-matrix-keypad.txt
@@ -19,7 +19,7 @@ Required Properties:
 
 Optional Properties:
 - linux,no-autorepeat:	do no enable autorepeat feature.
-- linux,wakeup:		use any event on keypad as wakeup event.
+- wakeup-source:	use any event on keypad as wakeup event.
 - debounce-delay-ms:	debounce interval in milliseconds
 - col-scan-delay-us:	delay, measured in microseconds, that is needed
 			before we can scan keypad after activating column gpio
diff --git a/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt b/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
index 7d8cb92831d7..ee6215681182 100644
--- a/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
+++ b/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
@@ -33,7 +33,7 @@ PROPERTIES
 	Value type: <bool>
 	Definition: don't enable autorepeat feature.
 
-- linux,keypad-wakeup:
+- wakeup-source:
 	Usage: optional
 	Value type: <bool>
 	Definition: use any event on keypad as wakeup event.
diff --git a/Documentation/devicetree/bindings/input/samsung-keypad.txt b/Documentation/devicetree/bindings/input/samsung-keypad.txt
index 942d071baaa5..863e77f619dc 100644
--- a/Documentation/devicetree/bindings/input/samsung-keypad.txt
+++ b/Documentation/devicetree/bindings/input/samsung-keypad.txt
@@ -36,9 +36,11 @@ Required Board Specific Properties:
 - pinctrl-0: Should specify pin control groups used for this controller.
 - pinctrl-names: Should contain only one value - "default".
 
+Optional Properties:
+- wakeup-source: use any event on keypad as wakeup event.
+
 Optional Properties specific to linux:
 - linux,keypad-no-autorepeat: do no enable autorepeat feature.
-- linux,keypad-wakeup: use any event on keypad as wakeup event.
 
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/snvs-pwrkey.txt b/Documentation/devicetree/bindings/input/snvs-pwrkey.txt
new file mode 100644
index 000000000000..70c14250323b
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/snvs-pwrkey.txt
@@ -0,0 +1 @@
+See Documentation/devicetree/bindings/crypto/fsl-sec4.txt
diff --git a/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
index 6e551090f465..8eb240a287c8 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
@@ -8,6 +8,9 @@ Required properties:
 - touchscreen-size-x: horizontal resolution of touchscreen (in pixels)
 - touchscreen-size-y: vertical resolution of touchscreen (in pixels)
 
+Optional properties:
+- reset-gpio: GPIO connected to the RESET line of the chip
+
 Example:
 
 	i2c@00000000 {
diff --git a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
index 80c37df940a7..e3c27c4fd9c8 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
@@ -4,12 +4,12 @@ Required properties:
 - compatible: must be "neonode,zforce"
 - reg: I2C address of the chip
 - interrupts: interrupt to which the chip is connected
-- gpios: gpios the chip is connected to
-  first one is the interrupt gpio and second one the reset gpio
+- reset-gpios: reset gpio the chip is connected to
 - x-size: horizontal resolution of touchscreen
 - y-size: vertical resolution of touchscreen
 
 Optional properties:
+- irq-gpios : interrupt gpio the chip is connected to
 - vdd-supply: Regulator controlling the controller supply
 
 Example:
@@ -23,8 +23,8 @@ Example:
 			interrupts = <2 0>;
 			vdd-supply = <&reg_zforce_vdd>;
 
-			gpios = <&gpio5 6 0>, /* INT */
-				<&gpio5 9 0>; /* RST */
+			reset-gpios = <&gpio5 9 0>; /* RST */
+			irq-gpios = <&gpio5 6 0>; /* IRQ, optional */
 
 			x-size = <800>;
 			y-size = <600>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
index 7da578d72123..2d6c8bb4d827 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
@@ -5,9 +5,14 @@ The BCM2835 contains a custom top-level interrupt controller, which supports
 controller, or the HW block containing it, is referred to occasionally
 as "armctrl" in the SoC documentation, hence naming of this binding.
 
+The BCM2836 contains the same interrupt controller with the same
+interrupts, but the per-CPU interrupt controller is the root, and an
+interrupt there indicates that the ARMCTRL has an interrupt to handle.
+
 Required properties:
 
-- compatible : should be "brcm,bcm2835-armctrl-ic"
+- compatible : should be "brcm,bcm2835-armctrl-ic" or
+                 "brcm,bcm2836-armctrl-ic"
 - reg : Specifies base physical address and size of the registers.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
@@ -20,6 +25,12 @@ Required properties:
   The 2nd cell contains the interrupt number within the bank. Valid values
   are 0..7 for bank 0, and 0..31 for bank 1.
 
+Additional required properties for brcm,bcm2836-armctrl-ic:
+- interrupt-parent : Specifies the parent interrupt controller when this
+  controller is the second level.
+- interrupts : Specifies the interrupt on the parent for this interrupt
+  controller to handle.
+
 The interrupt sources are as follows:
 
 Bank 0:
@@ -102,9 +113,21 @@ Bank 2:
 
 Example:
 
+/* BCM2835, first level */
 intc: interrupt-controller {
 	compatible = "brcm,bcm2835-armctrl-ic";
 	reg = <0x7e00b200 0x200>;
 	interrupt-controller;
 	#interrupt-cells = <2>;
 };
+
+/* BCM2836, second level */
+intc: interrupt-controller {
+	compatible = "brcm,bcm2836-armctrl-ic";
+	reg = <0x7e00b200 0x200>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+
+	interrupt-parent = <&local_intc>;
+	interrupts = <8>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt
new file mode 100644
index 000000000000..f320dcd6e69b
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt
@@ -0,0 +1,37 @@
+BCM2836 per-CPU interrupt controller
+
+The BCM2836 has a per-cpu interrupt controller for the timer, PMU
+events, and SMP IPIs.  One of the CPUs may receive interrupts for the
+peripheral (GPU) events, which chain to the BCM2835-style interrupt
+controller.
+
+Required properties:
+
+- compatible:	 	Should be "brcm,bcm2836-l1-intc"
+- reg:			Specifies base physical address and size of the
+			  registers
+- interrupt-controller:	Identifies the node as an interrupt controller
+- #interrupt-cells:	Specifies the number of cells needed to encode an
+			  interrupt source. The value shall be 1
+
+Please refer to interrupts.txt in this directory for details of the common
+Interrupt Controllers bindings used by client devices.
+
+The interrupt sources are as follows:
+
+0: CNTPSIRQ
+1: CNTPNSIRQ
+2: CNTHPIRQ
+3: CNTVIRQ
+8: GPU_FAST
+9: PMU_FAST
+
+Example:
+
+local_intc: local_intc {
+	compatible = "brcm,bcm2836-l1-intc";
+	reg = <0x40000000 0x100>;
+	interrupt-controller;
+	#interrupt-cells = <1>;
+	interrupt-parent = <&local_intc>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/msi.txt b/Documentation/devicetree/bindings/interrupt-controller/msi.txt
new file mode 100644
index 000000000000..c60c034dcf19
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/msi.txt
@@ -0,0 +1,135 @@
+This document describes the generic device tree binding for MSI controllers and
+their master(s).
+
+Message Signaled Interrupts (MSIs) are a class of interrupts generated by a
+write to an MMIO address.
+
+MSIs were originally specified by PCI (and are used with PCIe), but may also be
+used with other busses, and hence a mechanism is required to relate devices on
+those busses to the MSI controllers which they are capable of using,
+potentially including additional information.
+
+MSIs are distinguished by some combination of:
+
+- The doorbell (the MMIO address written to).
+  
+  Devices may be configured by software to write to arbitrary doorbells which
+  they can address. An MSI controller may feature a number of doorbells.
+
+- The payload (the value written to the doorbell).
+  
+  Devices may be configured to write an arbitrary payload chosen by software.
+  MSI controllers may have restrictions on permitted payloads.
+
+- Sideband information accompanying the write.
+  
+  Typically this is neither configurable nor probeable, and depends on the path
+  taken through the memory system (i.e. it is a property of the combination of
+  MSI controller and device rather than a property of either in isolation).
+
+
+MSI controllers:
+================
+
+An MSI controller signals interrupts to a CPU when a write is made to an MMIO
+address by some master. An MSI controller may feature a number of doorbells.
+
+Required properties:
+--------------------
+
+- msi-controller: Identifies the node as an MSI controller.
+
+Optional properties:
+--------------------
+
+- #msi-cells: The number of cells in an msi-specifier, required if not zero.
+
+  Typically this will encode information related to sideband data, and will
+  not encode doorbells or payloads as these can be configured dynamically.
+
+  The meaning of the msi-specifier is defined by the device tree binding of
+  the specific MSI controller. 
+
+
+MSI clients
+===========
+
+MSI clients are devices which generate MSIs. For each MSI they wish to
+generate, the doorbell and payload may be configured, though sideband
+information may not be configurable.
+
+Required properties:
+--------------------
+
+- msi-parent: A list of phandle + msi-specifier pairs, one for each MSI
+  controller which the device is capable of using.
+
+  This property is unordered, and MSIs may be allocated from any combination of
+  MSI controllers listed in the msi-parent property.
+
+  If a device has restrictions on the allocation of MSIs, these restrictions
+  must be described with additional properties.
+
+  When #msi-cells is non-zero, busses with an msi-parent will require
+  additional properties to describe the relationship between devices on the bus
+  and the set of MSIs they can potentially generate.
+
+
+Example
+=======
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	msi_a: msi-controller@a {
+		reg = <0xa 0xf00>;
+		compatible = "vendor-a,some-controller";
+		msi-controller;
+		/* No sideband data, so #msi-cells omitted */
+	};
+
+	msi_b: msi-controller@b {
+		reg = <0xb 0xf00>;
+		compatible = "vendor-b,another-controller";
+		msi-controller;
+		/* Each device has some unique ID */
+		#msi-cells = <1>;
+	};
+
+	msi_c: msi-controller@c {
+		reg = <0xb 0xf00>;
+		compatible = "vendor-b,another-controller";
+		msi-controller;
+		/* Each device has some unique ID */
+		#msi-cells = <1>;
+	};
+
+	dev@0 {
+		reg = <0x0 0xf00>;
+		compatible = "vendor-c,some-device";
+
+		/* Can only generate MSIs to msi_a */
+		msi-parent = <&msi_a>;
+	};
+
+	dev@1 {
+		reg = <0x1 0xf00>;
+		compatible = "vendor-c,some-device";
+
+		/* 
+		 * Can generate MSIs to either A or B.
+		 */
+		msi-parent = <&msi_a>, <&msi_b 0x17>;
+	};
+
+	dev@2 {
+		reg = <0x2 0xf00>;
+		compatible = "vendor-c,some-device";
+		/*
+		 * Has different IDs at each MSI controller.
+		 * Can generate MSIs to all of the MSI controllers.
+		 */
+		msi-parent = <&msi_a>, <&msi_b 0x17>, <&msi_c 0x53>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
index c03eec116872..3443e0f838df 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
@@ -35,3 +35,6 @@ the PCIe specification.
 
                       NOTE: this only applies to the SMMU itself, not
                       masters connected upstream of the SMMU.
+
+- hisilicon,broken-prefetch-cmd
+                    : Avoid sending CMD_PREFETCH_* commands to the SMMU.
diff --git a/Documentation/devicetree/bindings/leds/common.txt b/Documentation/devicetree/bindings/leds/common.txt
index 747c53805eec..68419843e32f 100644
--- a/Documentation/devicetree/bindings/leds/common.txt
+++ b/Documentation/devicetree/bindings/leds/common.txt
@@ -29,14 +29,23 @@ Optional properties for child nodes:
      "ide-disk" - LED indicates disk activity
      "timer" - LED flashes at a fixed, configurable rate
 
-- max-microamp : maximum intensity in microamperes of the LED
-		 (torch LED for flash devices)
-- flash-max-microamp : maximum intensity in microamperes of the
-                       flash LED; it is mandatory if the LED should
-		       support the flash mode
-- flash-timeout-us : timeout in microseconds after which the flash
-                     LED is turned off
+- led-max-microamp : Maximum LED supply current in microamperes. This property
+                     can be made mandatory for the board configurations
+                     introducing a risk of hardware damage in case an excessive
+                     current is set.
+                     For flash LED controllers with configurable current this
+                     property is mandatory for the LEDs in the non-flash modes
+                     (e.g. torch or indicator).
 
+Required properties for flash LED child nodes:
+- flash-max-microamp : Maximum flash LED supply current in microamperes.
+- flash-max-timeout-us : Maximum timeout in microseconds after which the flash
+                         LED is turned off.
+
+For controllers that have no configurable current the flash-max-microamp
+property can be omitted.
+For controllers that have no configurable timeout the flash-max-timeout-us
+property can be omitted.
 
 Examples:
 
@@ -49,7 +58,7 @@ system-status {
 camera-flash {
 	label = "Flash";
 	led-sources = <0>, <1>;
-	max-microamp = <50000>;
+	led-max-microamp = <50000>;
 	flash-max-microamp = <320000>;
-	flash-timeout-us = <500000>;
+	flash-max-timeout-us = <500000>;
 };
diff --git a/Documentation/devicetree/bindings/leds/leds-ns2.txt b/Documentation/devicetree/bindings/leds/leds-ns2.txt
index aef3aca34d2d..9f81258a5b6e 100644
--- a/Documentation/devicetree/bindings/leds/leds-ns2.txt
+++ b/Documentation/devicetree/bindings/leds/leds-ns2.txt
@@ -8,6 +8,9 @@ Each LED is represented as a sub-node of the ns2-leds device.
 Required sub-node properties:
 - cmd-gpio: Command LED GPIO. See OF device-tree GPIO specification.
 - slow-gpio: Slow LED GPIO. See OF device-tree GPIO specification.
+- modes-map: A mapping between LED modes (off, on or SATA activity blinking) and
+  the corresponding cmd-gpio/slow-gpio values. All the GPIO values combinations
+  should be given in order to avoid having an unknown mode at driver probe time.
 
 Optional sub-node properties:
 - label: Name for this LED. If omitted, the label is taken from the node name.
@@ -15,6 +18,8 @@ Optional sub-node properties:
 
 Example:
 
+#include <dt-bindings/leds/leds-ns2.h>
+
 ns2-leds {
 	compatible = "lacie,ns2-leds";
 
@@ -22,5 +27,9 @@ ns2-leds {
 		label = "ns2:blue:sata";
 		slow-gpio = <&gpio0 29 0>;
 		cmd-gpio = <&gpio0 30 0>;
+		modes-map = <NS_V2_LED_OFF  0 1
+			     NS_V2_LED_ON   1 0
+			     NS_V2_LED_ON   0 0
+			     NS_V2_LED_SATA 1 1>;
 	};
 };
diff --git a/Documentation/devicetree/bindings/leds/leds-powernv.txt b/Documentation/devicetree/bindings/leds/leds-powernv.txt
new file mode 100644
index 000000000000..66655690f749
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-powernv.txt
@@ -0,0 +1,26 @@
+Device Tree binding for LEDs on IBM Power Systems
+-------------------------------------------------
+
+Required properties:
+- compatible : Should be "ibm,opal-v3-led".
+- led-mode   : Should be "lightpath" or "guidinglight".
+
+Each location code of FRU/Enclosure must be expressed in the
+form of a sub-node.
+
+Required properties for the sub nodes:
+- led-types : Supported LED types (attention/identify/fault) provided
+              in the form of string array.
+
+Example:
+
+leds {
+	compatible = "ibm,opal-v3-led";
+	led-mode = "lightpath";
+
+	U78C9.001.RST0027-P1-C1 {
+		led-types = "identify", "fault";
+	};
+	...
+	...
+};
diff --git a/Documentation/devicetree/bindings/media/i2c/adv7604.txt b/Documentation/devicetree/bindings/media/i2c/adv7604.txt
index c27cede3bd68..8337f75c75da 100644
--- a/Documentation/devicetree/bindings/media/i2c/adv7604.txt
+++ b/Documentation/devicetree/bindings/media/i2c/adv7604.txt
@@ -1,15 +1,17 @@
-* Analog Devices ADV7604/11 video decoder with HDMI receiver
+* Analog Devices ADV7604/11/12 video decoder with HDMI receiver
 
-The ADV7604 and ADV7611 are multiformat video decoders with an integrated HDMI
-receiver. The ADV7604 has four multiplexed HDMI inputs and one analog input,
-and the ADV7611 has one HDMI input and no analog input.
+The ADV7604 and ADV7611/12 are multiformat video decoders with an integrated
+HDMI receiver. The ADV7604 has four multiplexed HDMI inputs and one analog
+input, and the ADV7611 has one HDMI input and no analog input. The 7612 is
+similar to the 7611 but has 2 HDMI inputs.
 
-These device tree bindings support the ADV7611 only at the moment.
+These device tree bindings support the ADV7611/12 only at the moment.
 
 Required Properties:
 
   - compatible: Must contain one of the following
     - "adi,adv7611" for the ADV7611
+    - "adi,adv7612" for the ADV7612
 
   - reg: I2C slave address
 
@@ -22,10 +24,10 @@ port, in accordance with the video interface bindings defined in
 Documentation/devicetree/bindings/media/video-interfaces.txt. The port nodes
 are numbered as follows.
 
-  Port			ADV7611
+  Port			ADV7611    ADV7612
 ------------------------------------------------------------
-  HDMI			0
-  Digital output	1
+  HDMI			0             0, 1
+  Digital output	1                2
 
 The digital output port node must contain at least one endpoint.
 
@@ -45,6 +47,7 @@ Optional Endpoint Properties:
   If none of hsync-active, vsync-active and pclk-sample is specified the
   endpoint will use embedded BT.656 synchronization.
 
+  - default-input: Select which input is selected after reset.
 
 Example:
 
@@ -58,6 +61,8 @@ Example:
 		#address-cells = <1>;
 		#size-cells = <0>;
 
+		default-input = <0>;
+
 		port@0 {
 			reg = <0>;
 		};
diff --git a/Documentation/devicetree/bindings/media/i2c/tc358743.txt b/Documentation/devicetree/bindings/media/i2c/tc358743.txt
new file mode 100644
index 000000000000..5218921629ed
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/tc358743.txt
@@ -0,0 +1,48 @@
+* Toshiba TC358743 HDMI-RX to MIPI CSI2-TX Bridge
+
+The Toshiba TC358743 HDMI-RX to MIPI CSI2-TX (H2C) is a bridge that converts
+a HDMI stream to MIPI CSI-2 TX. It is programmable through I2C.
+
+Required Properties:
+
+- compatible: value should be "toshiba,tc358743"
+- clocks, clock-names: should contain a phandle link to the reference clock
+		       source, the clock input is named "refclk".
+
+Optional Properties:
+
+- reset-gpios: gpio phandle GPIO connected to the reset pin
+- interrupts, interrupt-parent: GPIO connected to the interrupt pin
+- data-lanes: should be <1 2 3 4> for four-lane operation,
+	      or <1 2> for two-lane operation
+- clock-lanes: should be <0>
+- clock-noncontinuous: Presence of this boolean property decides whether the
+		       MIPI CSI-2 clock is continuous or non-continuous.
+- link-frequencies: List of allowed link frequencies in Hz. Each frequency is
+		    expressed as a 64-bit big-endian integer. The frequency
+		    is half of the bps per lane due to DDR transmission.
+
+For further information on the MIPI CSI-2 endpoint node properties, see
+Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+Example:
+
+	tc358743@0f {
+		compatible = "toshiba,tc358743";
+		reg = <0x0f>;
+		clocks = <&hdmi_osc>;
+		clock-names = "refclk";
+		reset-gpios = <&gpio6 9 GPIO_ACTIVE_LOW>;
+		interrupt-parent = <&gpio2>;
+		interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
+
+		port {
+			tc358743_out: endpoint {
+				remote-endpoint = <&mipi_csi2_in>;
+				data-lanes = <1 2 3 4>;
+				clock-lanes = <0>;
+				clock-noncontinuous;
+				link-frequencies = /bits/ 64 <297000000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/media/renesas,jpu.txt b/Documentation/devicetree/bindings/media/renesas,jpu.txt
new file mode 100644
index 000000000000..0cb94201bf92
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/renesas,jpu.txt
@@ -0,0 +1,24 @@
+* Renesas JPEG Processing Unit
+
+The JPEG processing unit (JPU) incorporates the JPEG codec with an encoding
+and decoding function conforming to the JPEG baseline process, so that the JPU
+can encode image data and decode JPEG data quickly.
+
+Required properties:
+  - compatible: should containg one of the following:
+			- "renesas,jpu-r8a7790" for R-Car H2
+			- "renesas,jpu-r8a7791" for R-Car M2-W
+			- "renesas,jpu-r8a7792" for R-Car V2H
+			- "renesas,jpu-r8a7793" for R-Car M2-N
+
+  - reg: Base address and length of the registers block for the JPU.
+  - interrupts: JPU interrupt specifier.
+  - clocks: A phandle + clock-specifier pair for the JPU functional clock.
+
+Example: R8A7790 (R-Car H2) JPU node
+	jpeg-codec@fe980000 {
+		compatible = "renesas,jpu-r8a7790";
+		reg = <0 0xfe980000 0 0x10300>;
+		interrupts = <0 272 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7790_CLK_JPU>;
+	};
diff --git a/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt b/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
new file mode 100644
index 000000000000..d4def767bdfe
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
@@ -0,0 +1,89 @@
+STMicroelectronics STi c8sectpfe binding
+============================================
+
+This document describes the c8sectpfe device bindings that is used to get transport
+stream data into the SoC on the TS pins, and into DDR for further processing.
+
+It is typically used in conjunction with one or more demodulator and tuner devices
+which converts from the RF to digital domain. Demodulators and tuners are usually
+located on an external DVB frontend card connected to SoC TS input pins.
+
+Currently 7 TS input (tsin) channels are supported on the stih407 family SoC.
+
+Required properties (controller (parent) node):
+- compatible	: Should be "stih407-c8sectpfe"
+
+- reg		: Address and length of register sets for each device in
+		  "reg-names"
+
+- reg-names	: The names of the register addresses corresponding to the
+		  registers filled in "reg":
+			- c8sectpfe: c8sectpfe registers
+			- c8sectpfe-ram: c8sectpfe internal sram
+
+- clocks	: phandle list of c8sectpfe clocks
+- clock-names	: should be "c8sectpfe"
+See: Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+- pinctrl-names	: a pinctrl state named tsin%d-serial or tsin%d-parallel (where %d is tsin-num)
+		   must be defined for each tsin child node.
+- pinctrl-0	: phandle referencing pin configuration for this tsin configuration
+See: Documentation/devicetree/bindings/pinctrl/pinctrl-binding.txt
+
+
+Required properties (tsin (child) node):
+
+- tsin-num	: tsin id of the InputBlock (must be between 0 to 6)
+- i2c-bus	: phandle to the I2C bus DT node which the demodulators & tuners on this tsin channel are connected.
+- rst-gpio	: reset gpio for this tsin channel.
+
+Optional properties (tsin (child) node):
+
+- invert-ts-clk		: Bool property to control sense of ts input clock (data stored on falling edge of clk).
+- serial-not-parallel	: Bool property to configure input bus width (serial on ts_data<7>).
+- async-not-sync	: Bool property to control if data is received in asynchronous mode
+			   (all bits/bytes with ts_valid or ts_packet asserted are valid).
+
+- dvb-card		: Describes the NIM card connected to this tsin channel.
+
+Example:
+
+/* stih410 SoC b2120 + b2004a + stv0367-pll(NIMB) + stv0367-tda18212 (NIMA) DT example) */
+
+	c8sectpfe@08a20000 {
+		compatible = "st,stih407-c8sectpfe";
+		status = "okay";
+		reg = <0x08a20000 0x10000>, <0x08a00000 0x4000>;
+		reg-names = "stfe", "stfe-ram";
+		interrupts = <0 34 0>, <0 35 0>;
+		interrupt-names = "stfe-error-irq", "stfe-idle-irq";
+
+		pinctrl-names	= "tsin0-serial", "tsin0-parallel", "tsin3-serial",
+				"tsin4-serial", "tsin5-serial";
+
+		pinctrl-0	= <&pinctrl_tsin0_serial>;
+		pinctrl-1	= <&pinctrl_tsin0_parallel>;
+		pinctrl-2	= <&pinctrl_tsin3_serial>;
+		pinctrl-3	= <&pinctrl_tsin4_serial_alt3>;
+		pinctrl-4	= <&pinctrl_tsin5_serial_alt1>;
+
+		clocks = <&clk_s_c0_flexgen CLK_PROC_STFE>;
+		clock-names = "stfe";
+
+		/* tsin0 is TSA on NIMA */
+		tsin0: port@0 {
+			tsin-num		= <0>;
+			serial-not-parallel;
+			i2c-bus			= <&ssc2>;
+			rst-gpio		= <&pio15 4 0>;
+			dvb-card		= <STV0367_TDA18212_NIMA_1>;
+		};
+
+		tsin3: port@3 {
+			tsin-num		= <3>;
+			serial-not-parallel;
+			i2c-bus			= <&ssc3>;
+			rst-gpio		= <&pio15 7 0>;
+			dvb-card		= <STV0367_TDA18212_NIMB_1>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/memory-controllers/arm,pl172.txt b/Documentation/devicetree/bindings/memory-controllers/arm,pl172.txt
new file mode 100644
index 000000000000..e6df32f9986d
--- /dev/null
+++ b/Documentation/devicetree/bindings/memory-controllers/arm,pl172.txt
@@ -0,0 +1,125 @@
+* Device tree bindings for ARM PL172 MultiPort Memory Controller
+
+Required properties:
+
+- compatible:		"arm,pl172", "arm,primecell"
+
+- reg:			Must contains offset/length value for controller.
+
+- #address-cells:	Must be 2. The partition number has to be encoded in the
+			first address cell and it may accept values 0..N-1
+			(N - total number of partitions). The second cell is the
+			offset into the partition.
+
+- #size-cells:		Must be set to 1.
+
+- ranges:		Must contain one or more chip select memory regions.
+
+- clocks:		Must contain references to controller clocks.
+
+- clock-names:		Must contain "mpmcclk" and "apb_pclk".
+
+- clock-ranges:		Empty property indicating that child nodes can inherit
+			named clocks. Required only if clock tree data present
+			in device tree.
+			See clock-bindings.txt
+
+Child chip-select (cs) nodes contain the memory devices nodes connected to
+such as NOR (e.g. cfi-flash) and NAND.
+
+Required child cs node properties:
+
+- #address-cells:	Must be 2.
+
+- #size-cells:		Must be 1.
+
+- ranges:		Empty property indicating that child nodes can inherit
+			memory layout.
+
+- clock-ranges:		Empty property indicating that child nodes can inherit
+			named clocks. Required only if clock tree data present
+			in device tree.
+
+- mpmc,cs:		Chip select number. Indicates to the pl0172 driver
+			which chipselect is used for accessing the memory.
+
+- mpmc,memory-width:	Width of the chip select memory. Must be equal to
+			either 8, 16 or 32.
+
+Optional child cs node config properties:
+
+- mpmc,async-page-mode:	Enable asynchronous page mode.
+
+- mpmc,cs-active-high:	Set chip select polarity to active high.
+
+- mpmc,byte-lane-low:	Set byte lane state to low.
+
+- mpmc,extended-wait:	Enable extended wait.
+
+- mpmc,buffer-enable:	Enable write buffer.
+
+- mpmc,write-protect:	Enable write protect.
+
+Optional child cs node timing properties:
+
+- mpmc,write-enable-delay:	Delay from chip select assertion to write
+				enable (WE signal) in nano seconds.
+
+- mpmc,output-enable-delay:	Delay from chip select assertion to output
+				enable (OE signal) in nano seconds.
+
+- mpmc,write-access-delay:	Delay from chip select assertion to write
+				access in nano seconds.
+
+- mpmc,read-access-delay:	Delay from chip select assertion to read
+				access in nano seconds.
+
+- mpmc,page-mode-read-delay:	Delay for asynchronous page mode sequential
+				accesses in nano seconds.
+
+- mpmc,turn-round-delay:	Delay between access to memory banks in nano
+				seconds.
+
+If any of the above timing parameters are absent, current parameter value will
+be taken from the corresponding HW reg.
+
+Example for pl172 with nor flash on chip select 0 shown below.
+
+emc: memory-controller@40005000 {
+	compatible = "arm,pl172", "arm,primecell";
+	reg = <0x40005000 0x1000>;
+	clocks = <&ccu1 CLK_CPU_EMCDIV>, <&ccu1 CLK_CPU_EMC>;
+	clock-names = "mpmcclk", "apb_pclk";
+	#address-cells = <2>;
+	#size-cells = <1>;
+	ranges = <0 0 0x1c000000 0x1000000
+		  1 0 0x1d000000 0x1000000
+		  2 0 0x1e000000 0x1000000
+		  3 0 0x1f000000 0x1000000>;
+
+	cs0 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+
+		mpmc,cs = <0>;
+		mpmc,memory-width = <16>;
+		mpmc,byte-lane-low;
+		mpmc,write-enable-delay = <0>;
+		mpmc,output-enable-delay = <0>;
+		mpmc,read-enable-delay = <70>;
+		mpmc,page-mode-read-delay = <70>;
+
+		flash@0,0 {
+			compatible = "sst,sst39vf320", "cfi-flash";
+			reg = <0 0 0x400000>;
+			bank-width = <2>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "data";
+				reg = <0 0x400000>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt b/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
index d5e370450ac0..89427b018ba7 100644
--- a/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
@@ -18,6 +18,8 @@ Properties:
               interrupt (NAND_EVTER_STAT).  If there is only one,
               that interrupt reports both types of event.
 
+- little-endian : If this property is absent, the big-endian mode will
+                  be in use as default for registers.
 
 - ranges : Each range corresponds to a single chipselect, and covers
            the entire access window as configured.
@@ -34,6 +36,7 @@ Example:
 		#size-cells = <1>;
 		reg = <0x0 0xffe1e000 0 0x2000>;
 		interrupts = <16 2 19 2>;
+		little-endian;
 
 		/* NOR, NAND Flashes and CPLD on board */
 		ranges = <0x0 0x0 0x0 0xee000000 0x02000000
diff --git a/Documentation/devicetree/bindings/memory-controllers/synopsys.txt b/Documentation/devicetree/bindings/memory-controllers/synopsys.txt
index f9c6454146b6..a43d26d41e04 100644
--- a/Documentation/devicetree/bindings/memory-controllers/synopsys.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/synopsys.txt
@@ -1,5 +1,9 @@
 Binding for Synopsys IntelliDDR Multi Protocol Memory Controller
 
+This controller has an optional ECC support in half-bus width (16-bit)
+configuration. The ECC controller corrects one bit error and detects
+two bit errors.
+
 Required properties:
  - compatible: Should be 'xlnx,zynq-ddrc-a05'
  - reg: Base address and size of the controllers memory area
diff --git a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
index 938f8e1ba205..0db60470ebb6 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
@@ -8,6 +8,7 @@ of the EMIF IP and memory parts attached to it.
 Required properties:
 - compatible	: Should be of the form "ti,emif-<ip-rev>" where <ip-rev>
   is the IP revision of the specific EMIF instance.
+		  For am437x should be ti,emif-am4372.
 
 - phy-type	: <u32> indicating the DDR phy type. Following are the
   allowed values
diff --git a/Documentation/devicetree/bindings/mfd/atmel-hlcdc.txt b/Documentation/devicetree/bindings/mfd/atmel-hlcdc.txt
index f64de95a8e8b..ad5d90482a0e 100644
--- a/Documentation/devicetree/bindings/mfd/atmel-hlcdc.txt
+++ b/Documentation/devicetree/bindings/mfd/atmel-hlcdc.txt
@@ -2,7 +2,11 @@ Device-Tree bindings for Atmel's HLCDC (High LCD Controller) MFD driver
 
 Required properties:
  - compatible: value should be one of the following:
+   "atmel,at91sam9n12-hlcdc"
+   "atmel,at91sam9x5-hlcdc"
+   "atmel,sama5d2-hlcdc"
    "atmel,sama5d3-hlcdc"
+   "atmel,sama5d4-hlcdc"
  - reg: base address and size of the HLCDC device registers.
  - clock-names: the name of the 3 clocks requested by the HLCDC device.
    Should contain "periph_clk", "sys_clk" and "slow_clk".
diff --git a/Documentation/devicetree/bindings/mfd/axp20x.txt b/Documentation/devicetree/bindings/mfd/axp20x.txt
index 753f14f46e85..41811223e5be 100644
--- a/Documentation/devicetree/bindings/mfd/axp20x.txt
+++ b/Documentation/devicetree/bindings/mfd/axp20x.txt
@@ -1,12 +1,14 @@
 AXP family PMIC device tree bindings
 
 The axp20x family current members :
+axp152 (X-Powers)
 axp202 (X-Powers)
 axp209 (X-Powers)
 axp221 (X-Powers)
 
 Required properties:
-- compatible: "x-powers,axp202", "x-powers,axp209", "x-powers,axp221"
+- compatible: "x-powers,axp152", "x-powers,axp202", "x-powers,axp209",
+	      "x-powers,axp221"
 - reg: The I2C slave address for the AXP chip
 - interrupt-parent: The parent interrupt controller
 - interrupts: SoC NMI / GPIO interrupt connected to the PMIC's IRQ pin
diff --git a/Documentation/devicetree/bindings/mfd/da9062.txt b/Documentation/devicetree/bindings/mfd/da9062.txt
new file mode 100644
index 000000000000..38802b54d48a
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/da9062.txt
@@ -0,0 +1,88 @@
+* Dialog DA9062 Power Management Integrated Circuit (PMIC)
+
+DA9062 consists of a large and varied group of sub-devices:
+
+Device                   Supply Names    Description
+------                   ------------    -----------
+da9062-regulator        :               : LDOs & BUCKs
+da9062-rtc              :               : Real-Time Clock
+da9062-watchdog         :               : Watchdog Timer
+
+======
+
+Required properties:
+
+- compatible : Should be "dlg,da9062".
+- reg : Specifies the I2C slave address (this defaults to 0x58 but it can be
+  modified to match the chip's OTP settings).
+- interrupt-parent : Specifies the reference to the interrupt controller for
+  the DA9062.
+- interrupts : IRQ line information.
+- interrupt-controller
+
+See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
+further information on IRQ bindings.
+
+Sub-nodes:
+
+- regulators : This node defines the settings for the LDOs and BUCKs. The
+  DA9062 regulators are bound using their names listed below:
+
+    buck1    : BUCK_1
+    buck2    : BUCK_2
+    buck3    : BUCK_3
+    buck4    : BUCK_4
+    ldo1     : LDO_1
+    ldo2     : LDO_2
+    ldo3     : LDO_3
+    ldo4     : LDO_4
+
+  The component follows the standard regulator framework and the bindings
+  details of individual regulator device can be found in:
+  Documentation/devicetree/bindings/regulator/regulator.txt
+
+
+- rtc : This node defines settings required for the Real-Time Clock associated
+  with the DA9062. There are currently no entries in this binding, however
+  compatible = "dlg,da9062-rtc" should be added if a node is created.
+
+- watchdog: This node defines the settings for the watchdog driver associated
+  with the DA9062 PMIC. The compatible = "dlg,da9062-watchdog" should be added
+  if a node is created.
+
+
+Example:
+
+	pmic0: da9062@58 {
+		compatible = "dlg,da9062";
+		reg = <0x58>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+
+		rtc {
+			compatible = "dlg,da9062-rtc";
+		};
+
+		watchdog {
+			compatible = "dlg,da9062-watchdog";
+		};
+
+		regulators {
+			DA9062_BUCK1: buck1 {
+				regulator-name = "BUCK1";
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp = <500000>;
+				regulator-max-microamp = <2000000>;
+				regulator-boot-on;
+			};
+			DA9062_LDO1: ldo1 {
+				regulator-name = "LDO_1";
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <3600000>;
+				regulator-boot-on;
+			};
+		};
+	};
+
diff --git a/Documentation/devicetree/bindings/mfd/max77686.txt b/Documentation/devicetree/bindings/mfd/max77686.txt
index 163bd81a4607..741e76688cf2 100644
--- a/Documentation/devicetree/bindings/mfd/max77686.txt
+++ b/Documentation/devicetree/bindings/mfd/max77686.txt
@@ -7,8 +7,9 @@ different i2c slave address,presently for which we are statically creating i2c
 client while probing.This document describes the binding for mfd device and
 PMIC submodule.
 
-Binding for the built-in 32k clock generator block is defined separately
-in bindings/clk/maxim,max77686.txt file.
+Bindings for the built-in 32k clock generator block and
+regulators are defined in ../clk/maxim,max77686.txt and
+../regulator/max77686.txt respectively.
 
 Required properties:
 - compatible : Must be "maxim,max77686";
@@ -16,67 +17,11 @@ Required properties:
 - interrupts : This i2c device has an IRQ line connected to the main SoC.
 - interrupt-parent : The parent interrupt controller.
 
-Optional node:
-- voltage-regulators : The regulators of max77686 have to be instantiated
-  under subnode named "voltage-regulators" using the following format.
-
-	regulator_name {
-		regulator-compatible = LDOn/BUCKn
-		standard regulator constraints....
-	};
-	refer Documentation/devicetree/bindings/regulator/regulator.txt
-
-  The regulator-compatible property of regulator should initialized with string
-to get matched with their hardware counterparts as follow:
-
-	-LDOn 	:	for LDOs, where n can lie in range 1 to 26.
-		 	example: LDO1, LDO2, LDO26.
-	-BUCKn 	:	for BUCKs, where n can lie in range 1 to 9.
-			example: BUCK1, BUCK5, BUCK9.
-
-  Regulators which can be turned off during system suspend:
-	-LDOn	:	2, 6-8, 10-12, 14-16,
-	-BUCKn	:	1-4.
-  Use standard regulator bindings for it ('regulator-off-in-suspend').
-
-  LDO20, LDO21, LDO22, BUCK8 and BUCK9 can be configured to GPIO enable
-  control. To turn this feature on this property must be added to the regulator
-  sub-node:
-	- maxim,ena-gpios :	one GPIO specifier enable control (the gpio
-				flags are actually ignored and always
-				ACTIVE_HIGH is used)
-
 Example:
 
-	max77686@09 {
+	max77686: pmic@09 {
 		compatible = "maxim,max77686";
 		interrupt-parent = <&wakeup_eint>;
 		interrupts = <26 0>;
 		reg = <0x09>;
-
-		voltage-regulators {
-			ldo11_reg {
-				regulator-compatible = "LDO11";
-				regulator-name = "vdd_ldo11";
-				regulator-min-microvolt = <1900000>;
-				regulator-max-microvolt = <1900000>;
-				regulator-always-on;
-			};
-
-			buck1_reg {
-				regulator-compatible = "BUCK1";
-				regulator-name = "vdd_mif";
-				regulator-min-microvolt = <950000>;
-				regulator-max-microvolt = <1300000>;
-				regulator-always-on;
-				regulator-boot-on;
-			};
-
-			buck9_reg {
-				regulator-compatible = "BUCK9";
-				regulator-name = "CAM_ISP_CORE_1.2V";
-				regulator-min-microvolt = <1000000>;
-				regulator-max-microvolt = <1200000>;
-				maxim,ena-gpios = <&gpm0 3 GPIO_ACTIVE_HIGH>;
-			};
-	}
+	};
diff --git a/Documentation/devicetree/bindings/mfd/max77802.txt b/Documentation/devicetree/bindings/mfd/max77802.txt
new file mode 100644
index 000000000000..51fc1a60caa5
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/max77802.txt
@@ -0,0 +1,26 @@
+Maxim MAX77802 multi-function device
+
+The Maxim MAX77802 is a Power Management IC (PMIC) that contains 10 high
+efficiency Buck regulators, 32 Low-DropOut (LDO) regulators used to power
+up application processors and peripherals, a 2-channel 32kHz clock outputs,
+a Real-Time-Clock (RTC) and a I2C interface to program the individual
+regulators, clocks outputs and the RTC.
+
+Bindings for the built-in 32k clock generator block and
+regulators are defined in ../clk/maxim,max77802.txt and
+../regulator/max77802.txt respectively.
+
+Required properties:
+- compatible		: Must be "maxim,max77802"
+- reg			: Specifies the I2C slave address of PMIC block.
+- interrupts		: I2C device IRQ line connected to the main SoC.
+- interrupt-parent	: The parent interrupt controller.
+
+Example:
+
+	max77802: pmic@09 {
+		compatible = "maxim,max77802";
+		interrupt-parent = <&intc>;
+		interrupts = <26 IRQ_TYPE_NONE>;
+		reg = <0x09>;
+	};
diff --git a/Documentation/devicetree/bindings/mfd/rk808.txt b/Documentation/devicetree/bindings/mfd/rk808.txt
index 9e6e2592e5c8..4ca6aab4273a 100644
--- a/Documentation/devicetree/bindings/mfd/rk808.txt
+++ b/Documentation/devicetree/bindings/mfd/rk808.txt
@@ -24,6 +24,10 @@ Optional properties:
 - vcc10-supply: The input supply for LDO_REG6
 - vcc11-supply: The input supply for LDO_REG8
 - vcc12-supply: The input supply for SWITCH_REG2
+- dvs-gpios:  buck1/2 can be controlled by gpio dvs, this is GPIO specifiers
+  for 2 host gpio's used for dvs. The format of the gpio specifier depends in
+  the gpio controller. If DVS GPIOs aren't present, voltage changes will happen
+  very quickly with no slow ramp time.
 
 Regulators: All the regulators of RK808 to be instantiated shall be
 listed in a child node named 'regulators'. Each regulator is represented
@@ -55,7 +59,9 @@ Example:
 		interrupt-parent = <&gpio0>;
 		interrupts = <4 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
-		pinctrl-0 = <&pmic_int>;
+		pinctrl-0 = <&pmic_int &dvs_1 &dvs_2>;
+		dvs-gpios = <&gpio7 11 GPIO_ACTIVE_HIGH>,
+			    <&gpio7 15 GPIO_ACTIVE_HIGH>;
 		reg = <0x1b>;
 		rockchip,system-power-controller;
 		wakeup-source;
diff --git a/Documentation/devicetree/bindings/mfd/tc3589x.txt b/Documentation/devicetree/bindings/mfd/tc3589x.txt
index 6fcedba46ae9..37bf7f1aa70a 100644
--- a/Documentation/devicetree/bindings/mfd/tc3589x.txt
+++ b/Documentation/devicetree/bindings/mfd/tc3589x.txt
@@ -55,7 +55,7 @@ Optional nodes:
  - linux,keymap: the definition can be found in
    bindings/input/matrix-keymap.txt
  - linux,no-autorepeat: do no enable autorepeat feature.
- - linux,wakeup: use any event on keypad as wakeup event.
+ - wakeup-source: use any event on keypad as wakeup event.
 
 Example:
 
@@ -84,7 +84,6 @@ tc35893@44 {
 		keypad,num-columns = <8>;
 		keypad,num-rows = <8>;
 		linux,no-autorepeat;
-		linux,wakeup;
 		linux,keymap = <0x0301006b
 				0x04010066
 				0x06040072
@@ -103,5 +102,6 @@ tc35893@44 {
 				0x01030039
 				0x07060069
 				0x050500d9>;
+		wakeup-source;
 	};
 };
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index 5d0376b8f202..211e7785f4d2 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -17,7 +17,6 @@ Required properties:
 	       "fsl,imx6sx-usdhc"
 
 Optional properties:
-- fsl,cd-controller : Indicate to use controller internal card detection
 - fsl,wp-controller : Indicate to use controller internal write protection
 - fsl,delay-line : Specify the number of delay cells for override mode.
   This is used to set the clock delay for DLL(Delay Line) on override mode
@@ -35,7 +34,6 @@ esdhc@70004000 {
 	compatible = "fsl,imx51-esdhc";
 	reg = <0x70004000 0x4000>;
 	interrupts = <1>;
-	fsl,cd-controller;
 	fsl,wp-controller;
 };
 
diff --git a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
index 4461dc71cb10..862aa2f8837a 100644
--- a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
+++ b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
@@ -1,7 +1,8 @@
 * Freescale Quad Serial Peripheral Interface(QuadSPI)
 
 Required properties:
-  - compatible : Should be "fsl,vf610-qspi" or "fsl,imx6sx-qspi"
+  - compatible : Should be "fsl,vf610-qspi", "fsl,imx6sx-qspi",
+		 "fsl,imx7d-qspi", "fsl,imx6ul-qspi"
   - reg : the first contains the register location and length,
           the second contains the memory mapping address and length
   - reg-names: Should contain the reg names "QuadSPI" and "QuadSPI-memory"
diff --git a/Documentation/devicetree/bindings/mtd/nxp-spifi.txt b/Documentation/devicetree/bindings/mtd/nxp-spifi.txt
new file mode 100644
index 000000000000..f8b6b250654e
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/nxp-spifi.txt
@@ -0,0 +1,58 @@
+* NXP SPI Flash Interface (SPIFI)
+
+NXP SPIFI is a specialized SPI interface for serial Flash devices.
+It supports one Flash device with 1-, 2- and 4-bits width in SPI
+mode 0 or 3. The controller operates in either command or memory
+mode. In memory mode the Flash is accessible from the CPU as
+normal memory.
+
+Required properties:
+  - compatible : Should be "nxp,lpc1773-spifi"
+  - reg : the first contains the register location and length,
+          the second contains the memory mapping address and length
+  - reg-names: Should contain the reg names "spifi" and "flash"
+  - interrupts : Should contain the interrupt for the device
+  - clocks : The clocks needed by the SPIFI controller
+  - clock-names : Should contain the clock names "spifi" and "reg"
+
+Optional properties:
+ - resets : phandle + reset specifier
+
+The SPI Flash must be a child of the SPIFI node and must have a
+compatible property as specified in bindings/mtd/jedec,spi-nor.txt
+
+Optionally it can also contain the following properties.
+ - spi-cpol : Controller only supports mode 0 and 3 so either
+              both spi-cpol and spi-cpha should be present or
+              none of them
+ - spi-cpha : See above
+ - spi-rx-bus-width : Used to select how many pins that are used
+                      for input on the controller
+
+See bindings/spi/spi-bus.txt for more information.
+
+Example:
+spifi: spifi@40003000 {
+	compatible = "nxp,lpc1773-spifi";
+	reg = <0x40003000 0x1000>, <0x14000000 0x4000000>;
+	reg-names = "spifi", "flash";
+	interrupts = <30>;
+	clocks = <&ccu1 CLK_SPIFI>, <&ccu1 CLK_CPU_SPIFI>;
+	clock-names = "spifi", "reg";
+	resets = <&rgu 53>;
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		spi-cpol;
+		spi-cpha;
+		spi-rx-bus-width = <4>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "data";
+			reg = <0 0x200000>;
+		};
+	};
+};
+
diff --git a/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt b/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt
index 4f833e3c4f51..d9b655f11048 100644
--- a/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt
@@ -11,6 +11,7 @@ Required properties:
 
 Optional properties:
 
+ - dmas:			dma data channel, see dma.txt binding doc
  - marvell,nand-enable-arbiter:	Set to enable the bus arbiter
  - marvell,nand-keep-config:	Set to keep the NAND controller config as set
 				by the bootloader
@@ -32,6 +33,8 @@ Example:
 		compatible = "marvell,pxa3xx-nand";
 		reg = <0x43100000 90>;
 		interrupts = <45>;
+		dmas = <&pdma 97 0>;
+		dma-names = "data";
 		#address-cells = <1>;
 
 		marvell,nand-enable-arbiter;
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 33fe8462edf4..a9df21aaa154 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -2,7 +2,11 @@ TI SoC Ethernet Switch Controller Device Tree Bindings
 ------------------------------------------------------
 
 Required properties:
-- compatible		: Should be "ti,cpsw"
+- compatible		: Should be one of the below:-
+			  "ti,cpsw" for backward compatible
+			  "ti,am335x-cpsw" for AM335x controllers
+			  "ti,am4372-cpsw" for AM437x controllers
+			  "ti,dra7-cpsw" for DRA7x controllers
 - reg			: physical base address and size of the cpsw
 			  registers map
 - interrupts		: property with a value describing the interrupt
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index f0b4cd72411d..04e6bef3ac3f 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -44,9 +44,10 @@ Note that a port labelled "dsa" will imply checking for the uplink phandle
 described below.
 
 Optionnal property:
-- link			: Should be a phandle to another switch's DSA port.
+- link			: Should be a list of phandles to another switch's DSA port.
 			  This property is only used when switches are being
-			  chained/cascaded together.
+			  chained/cascaded together. This port is used as outgoing port
+			  towards the phandle port, which can be more than one hop away.
 
 - phy-handle		: Phandle to a PHY on an external MDIO bus, not the
 			  switch internal one. See
@@ -58,6 +59,10 @@ Optionnal property:
 			  Documentation/devicetree/bindings/net/ethernet.txt
 			  for details.
 
+- mii-bus		: Should be a phandle to a valid MDIO bus device node.
+			  This mii-bus will be used in preference to the
+			  global dsa,mii-bus defined above, for this switch.
+
 Optional subnodes:
 - fixed-link		: Fixed-link subnode describing a link to a non-MDIO
 			  managed entity. See
@@ -96,10 +101,11 @@ Example:
 				label = "cpu";
 			};
 
-			switch0uplink: port@6 {
+			switch0port6: port@6 {
 				reg = <6>;
 				label = "dsa";
-				link = <&switch1uplink>;
+				link = <&switch1port0
+				        &switch2port0>;
 			};
 		};
 
@@ -107,11 +113,31 @@ Example:
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <17 1>;	/* MDIO address 17, switch 1 in tree */
+			mii-bus = <&mii_bus1>;
+
+			switch1port0: port@0 {
+				reg = <0>;
+				label = "dsa";
+				link = <&switch0port6>;
+			};
+			switch1port1: port@1 {
+				reg = <1>;
+				label = "dsa";
+				link = <&switch2port1>;
+			};
+		};
+
+		switch@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <18 2>;	/* MDIO address 18, switch 2 in tree */
+			mii-bus = <&mii_bus1>;
 
-			switch1uplink: port@0 {
+			switch2port0: port@0 {
 				reg = <0>;
 				label = "dsa";
-				link = <&switch0uplink>;
+				link = <&switch1port1
+				        &switch0port6>;
 			};
 		};
 	};
diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
index 41b3f3f864e8..5d88f37480b6 100644
--- a/Documentation/devicetree/bindings/net/ethernet.txt
+++ b/Documentation/devicetree/bindings/net/ethernet.txt
@@ -25,7 +25,11 @@ The following properties are common to the Ethernet controllers:
   flow control thresholds.
 - tx-fifo-depth: the size of the controller's transmit fifo in bytes. This
   is used for components that can have configurable fifo sizes.
+- managed: string, specifies the PHY management type. Supported values are:
+  "auto", "in-band-status". "auto" is the default, it usess MDIO for
+  management if fixed-link is not specified.
 
 Child nodes of the Ethernet controller are typically the individual PHY devices
 connected via the MDIO bus (sometimes the MDIO bus controller is separate).
 They are described in the phy.txt file in this same directory.
+For non-MDIO PHY management see fixed-link.txt.
diff --git a/Documentation/devicetree/bindings/net/fixed-link.txt b/Documentation/devicetree/bindings/net/fixed-link.txt
index 82bf7e0f47b6..ec5d889fe3d8 100644
--- a/Documentation/devicetree/bindings/net/fixed-link.txt
+++ b/Documentation/devicetree/bindings/net/fixed-link.txt
@@ -17,6 +17,8 @@ properties:
   enabled.
 * 'asym-pause' (boolean, optional), to indicate that asym_pause should
   be enabled.
+* 'link-gpios' ('gpio-list', optional), to indicate if a gpio can be read
+  to determine if the link is up.
 
 Old, deprecated 'fixed-link' binding:
 
@@ -30,7 +32,7 @@ Old, deprecated 'fixed-link' binding:
   - e: asymmetric pause configuration: 0 for no asymmetric pause, 1 for
     asymmetric pause
 
-Example:
+Examples:
 
 ethernet@0 {
 	...
@@ -40,3 +42,13 @@ ethernet@0 {
 	};
 	...
 };
+
+ethernet@1 {
+	...
+	fixed-link {
+	      speed = <1000>;
+	      pause;
+	      link-gpios = <&gpio0 12 GPIO_ACTIVE_HIGH>;
+	};
+	...
+};
diff --git a/Documentation/devicetree/bindings/net/keystone-netcp.txt b/Documentation/devicetree/bindings/net/keystone-netcp.txt
index d0e6fa38f335..b30ab6b5cbfa 100644
--- a/Documentation/devicetree/bindings/net/keystone-netcp.txt
+++ b/Documentation/devicetree/bindings/net/keystone-netcp.txt
@@ -130,7 +130,11 @@ Required properties:
 
 Optional properties:
 - efuse-mac:	If this is 1, then the MAC address for the interface is
-		obtained from the device efuse mac address register
+		obtained from the device efuse mac address register.
+		If this is 2, the two DWORDs occupied by the MAC address
+		are swapped.  The netcp driver will swap the two DWORDs
+		back to the proper order when this property is set to 2
+		when it obtains the mac address from efuse.
 - local-mac-address:	the driver is designed to use the of_get_mac_address api
 			only if efuse-mac is 0. When efuse-mac is 0, the MAC
 			address is obtained from local-mac-address. If this
diff --git a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
new file mode 100644
index 000000000000..fb1e75facf1b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
@@ -0,0 +1,27 @@
+* Samsung S3FWRN5 NCI NFC Controller
+
+Required properties:
+- compatible: Should be "samsung,s3fwrn5-i2c".
+- reg: address on the bus
+- interrupt-parent: phandle for the interrupt gpio controller
+- interrupts: GPIO interrupt to which the chip is connected
+- s3fwrn5,en-gpios: Output GPIO pin used for enabling/disabling the chip
+- s3fwrn5,fw-gpios: Output GPIO pin used to enter firmware mode and
+  sleep/wakeup control
+
+Example:
+
+&hsi2c_4 {
+	status = "okay";
+	s3fwrn5@27 {
+		compatible = "samsung,s3fwrn5-i2c";
+
+		reg = <0x27>;
+
+		interrupt-parent = <&gpa1>;
+		interrupts = <3 0 0>;
+
+		s3fwrn5,en-gpios = <&gpf1 4 0>;
+		s3fwrn5,fw-gpios = <&gpj0 2 0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
index d707588ed734..d707588ed734 100644
--- a/Documentation/devicetree/bindings/net/nfc/st-nci.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
new file mode 100644
index 000000000000..525681b6dc39
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
@@ -0,0 +1,31 @@
+* STMicroelectronics SAS. ST NCI NFC Controller
+
+Required properties:
+- compatible: Should be "st,st21nfcb-spi"
+- spi-max-frequency: Maximum SPI frequency (<= 10000000).
+- interrupt-parent: phandle for the interrupt gpio controller
+- interrupts: GPIO interrupt to which the chip is connected
+- reset-gpios: Output GPIO pin used to reset the ST21NFCB
+
+Optional SoC Specific Properties:
+- pinctrl-names: Contains only one value - "default".
+- pintctrl-0: Specifies the pin control groups used for this controller.
+
+Example (for ARM-based BeagleBoard xM with ST21NFCB on SPI4):
+
+&mcspi4 {
+
+	status = "okay";
+
+	st21nfcb: st21nfcb@0 {
+
+		compatible = "st,st21nfcb-spi";
+
+		clock-frequency = <4000000>;
+
+		interrupt-parent = <&gpio5>;
+		interrupts = <2 IRQ_TYPE_EDGE_RISING>;
+
+		reset-gpios = <&gpio5 29 GPIO_ACTIVE_HIGH>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
new file mode 100644
index 000000000000..51f8d2eba8d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
@@ -0,0 +1,75 @@
+* Synopsys DWC Ethernet QoS IP version 4.10 driver (GMAC)
+
+
+Required properties:
+- compatible: Should be "snps,dwc-qos-ethernet-4.10"
+- reg: Address and length of the register set for the device
+- clocks: Phandles to the reference clock and the bus clock
+- clock-names: Should be "phy_ref_clk" for the reference clock and "apb_pclk"
+  for the bus clock.
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the core's combined interrupt signal
+- phy-mode: See ethernet.txt file in the same directory
+
+Optional properties:
+- dma-coherent: Present if dma operations are coherent
+- mac-address: See ethernet.txt in the same directory
+- local-mac-address: See ethernet.txt in the same directory
+- snps,en-lpi: If present it enables use of the AXI low-power interface
+- snps,write-requests: Number of write requests that the AXI port can issue.
+  It depends on the SoC configuration.
+- snps,read-requests: Number of read requests that the AXI port can issue.
+  It depends on the SoC configuration.
+- snps,burst-map: Bitmap of allowed AXI burst lengts, with the LSB
+  representing 4, then 8 etc.
+- snps,txpbl: DMA Programmable burst length for the TX DMA
+- snps,rxpbl: DMA Programmable burst length for the RX DMA
+- snps,en-tx-lpi-clockgating: Enable gating of the MAC TX clock during
+  TX low-power mode.
+- phy-handle: See ethernet.txt file in the same directory
+- mdio device tree subnode: When the GMAC has a phy connected to its local
+    mdio, there must be device tree subnode with the following
+    required properties:
+    - compatible: Must be "snps,dwc-qos-ethernet-mdio".
+    - #address-cells: Must be <1>.
+    - #size-cells: Must be <0>.
+
+    For each phy on the mdio bus, there must be a node with the following
+    fields:
+
+    - reg: phy id used to communicate to phy.
+    - device_type: Must be "ethernet-phy".
+    - fixed-mode device tree subnode: see fixed-link.txt in the same directory
+
+Examples:
+ethernet2@40010000 {
+	clock-names = "phy_ref_clk", "apb_pclk";
+	clocks = <&clkc 17>, <&clkc 15>;
+	compatible = "snps,dwc-qos-ethernet-4.10";
+	interrupt-parent = <&intc>;
+	interrupts = <0x0 0x1e 0x4>;
+	reg = <0x40010000 0x4000>;
+	phy-handle = <&phy2>;
+	phy-mode = "gmii";
+
+	snps,en-tx-lpi-clockgating;
+	snps,en-lpi;
+	snps,write-requests = <2>;
+	snps,read-requests = <16>;
+	snps,burst-map = <0x7>;
+	snps,txpbl = <8>;
+	snps,rxpbl = <2>;
+
+	dma-coherent;
+
+	mdio {
+		#address-cells = <0x1>;
+		#size-cells = <0x0>;
+		phy2: phy@1 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			device_type = "ethernet-phy";
+			reg = <0x1>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/misc/allwinner,sunxi-sid.txt b/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt
index fabdf64a5737..d543ed3f5363 100644
--- a/Documentation/devicetree/bindings/misc/allwinner,sunxi-sid.txt
+++ b/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt
@@ -4,6 +4,10 @@ Required properties:
 - compatible: "allwinner,sun4i-a10-sid" or "allwinner,sun7i-a20-sid"
 - reg: Should contain registers location and length
 
+= Data cells =
+Are child nodes of qfprom, bindings of which as described in
+bindings/nvmem/nvmem.txt
+
 Example for sun4i:
 	sid@01c23800 {
 		compatible = "allwinner,sun4i-a10-sid";
diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.txt b/Documentation/devicetree/bindings/nvmem/nvmem.txt
new file mode 100644
index 000000000000..b52bc11e9597
--- /dev/null
+++ b/Documentation/devicetree/bindings/nvmem/nvmem.txt
@@ -0,0 +1,80 @@
+= NVMEM(Non Volatile Memory) Data Device Tree Bindings =
+
+This binding is intended to represent the location of hardware
+configuration data stored in NVMEMs like eeprom, efuses and so on.
+
+On a significant proportion of boards, the manufacturer has stored
+some data on NVMEM, for the OS to be able to retrieve these information
+and act upon it. Obviously, the OS has to know about where to retrieve
+these data from, and where they are stored on the storage device.
+
+This document is here to document this.
+
+= Data providers =
+Contains bindings specific to provider drivers and data cells as children
+of this node.
+
+Optional properties:
+ read-only: Mark the provider as read only.
+
+= Data cells =
+These are the child nodes of the provider which contain data cell
+information like offset and size in nvmem provider.
+
+Required properties:
+reg:	specifies the offset in byte within the storage device.
+
+Optional properties:
+
+bits:	Is pair of bit location and number of bits, which specifies offset
+	in bit and number of bits within the address range specified by reg property.
+	Offset takes values from 0-7.
+
+For example:
+
+	/* Provider */
+	qfprom: qfprom@00700000 {
+		...
+
+		/* Data cells */
+		tsens_calibration: calib@404 {
+			reg = <0x404 0x10>;
+		};
+
+		tsens_calibration_bckp: calib_bckp@504 {
+			reg = <0x504 0x11>;
+			bits = <6 128>
+		};
+
+		pvs_version: pvs-version@6 {
+			reg = <0x6 0x2>
+			bits = <7 2>
+		};
+
+		speed_bin: speed-bin@c{
+			reg = <0xc 0x1>;
+			bits = <2 3>;
+
+		};
+		...
+	};
+
+= Data consumers =
+Are device nodes which consume nvmem data cells/providers.
+
+Required-properties:
+nvmem-cells: list of phandle to the nvmem data cells.
+nvmem-cell-names: names for the each nvmem-cells specified. Required if
+	nvmem-cells is used.
+
+Optional-properties:
+nvmem	: list of phandles to nvmem providers.
+nvmem-names: names for the each nvmem provider. required if nvmem is used.
+
+For example:
+
+	tsens {
+		...
+		nvmem-cells = <&tsens_calibration>;
+		nvmem-cell-names = "calibration";
+	};
diff --git a/Documentation/devicetree/bindings/nvmem/qfprom.txt b/Documentation/devicetree/bindings/nvmem/qfprom.txt
new file mode 100644
index 000000000000..4ad68b7f5c18
--- /dev/null
+++ b/Documentation/devicetree/bindings/nvmem/qfprom.txt
@@ -0,0 +1,35 @@
+= Qualcomm QFPROM device tree bindings =
+
+This binding is intended to represent QFPROM which is found in most QCOM SOCs.
+
+Required properties:
+- compatible: should be "qcom,qfprom"
+- reg: Should contain registers location and length
+
+= Data cells =
+Are child nodes of qfprom, bindings of which as described in
+bindings/nvmem/nvmem.txt
+
+Example:
+
+	qfprom: qfprom@00700000 {
+		compatible 	= "qcom,qfprom";
+		reg		= <0x00700000 0x8000>;
+		...
+		/* Data cells */
+		tsens_calibration: calib@404 {
+			reg = <0x4404 0x10>;
+		};
+	};
+
+
+= Data consumers =
+Are device nodes which consume nvmem data cells.
+
+For example:
+
+	tsens {
+		...
+		nvmem-cells = <&tsens_calibration>;
+		nvmem-cell-names = "calibration";
+	};
diff --git a/Documentation/devicetree/bindings/power/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt
index 0d5e7c978121..0cb44dc21f97 100644
--- a/Documentation/devicetree/bindings/power/opp.txt
+++ b/Documentation/devicetree/bindings/opp/opp.txt
@@ -88,7 +88,7 @@ This defines voltage-current-frequency combinations along with other related
 properties.
 
 Required properties:
-- opp-hz: Frequency in Hz
+- opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer.
 
 Optional properties:
 - opp-microvolt: voltage in micro Volts.
@@ -158,20 +158,20 @@ Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
 		opp-shared;
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp01 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
 		opp02 {
-			opp-hz = <1200000000>;
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			clock-latency-ns = <290000>;
 			turbo-mode;
@@ -237,20 +237,20 @@ independently.
 		 */
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp01 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
 		opp02 {
-			opp-hz = <1200000000>;
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			opp-microamp = <90000;
 			lock-latency-ns = <290000>;
@@ -313,20 +313,20 @@ DVFS state together.
 		opp-shared;
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp01 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
 		opp02 {
-			opp-hz = <1200000000>;
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			opp-microamp = <90000>;
 			clock-latency-ns = <290000>;
@@ -339,20 +339,20 @@ DVFS state together.
 		opp-shared;
 
 		opp10 {
-			opp-hz = <1300000000>;
+			opp-hz = /bits/ 64 <1300000000>;
 			opp-microvolt = <1045000 1050000 1055000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
 			opp-suspend;
 		};
 		opp11 {
-			opp-hz = <1400000000>;
+			opp-hz = /bits/ 64 <1400000000>;
 			opp-microvolt = <1075000>;
 			opp-microamp = <100000>;
 			clock-latency-ns = <400000>;
 		};
 		opp12 {
-			opp-hz = <1500000000>;
+			opp-hz = /bits/ 64 <1500000000>;
 			opp-microvolt = <1010000 1100000 1110000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
@@ -379,7 +379,7 @@ Example 4: Handling multiple regulators
 		opp-shared;
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000>, /* Supply 0 */
 					<960000>, /* Supply 1 */
 					<960000>; /* Supply 2 */
@@ -392,7 +392,7 @@ Example 4: Handling multiple regulators
 		/* OR */
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
 					<960000 965000 975000>, /* Supply 1 */
 					<960000 965000 975000>; /* Supply 2 */
@@ -405,7 +405,7 @@ Example 4: Handling multiple regulators
 		/* OR */
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
 					<960000 965000 975000>, /* Supply 1 */
 					<960000 965000 975000>; /* Supply 2 */
@@ -437,12 +437,12 @@ Example 5: Multiple OPP tables
 		opp-shared;
 
 		opp00 {
-			opp-hz = <600000000>;
+			opp-hz = /bits/ 64 <600000000>;
 			...
 		};
 
 		opp01 {
-			opp-hz = <800000000>;
+			opp-hz = /bits/ 64 <800000000>;
 			...
 		};
 	};
@@ -453,12 +453,12 @@ Example 5: Multiple OPP tables
 		opp-shared;
 
 		opp10 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			...
 		};
 
 		opp11 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			...
 		};
 	};
diff --git a/Documentation/devicetree/bindings/panel/auo,b080uan01.txt b/Documentation/devicetree/bindings/panel/auo,b080uan01.txt
new file mode 100644
index 000000000000..bae0e2b51467
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/auo,b080uan01.txt
@@ -0,0 +1,7 @@
+AU Optronics Corporation 8.0" WUXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "auo,b101ean01"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/panel/lg,lg4573.txt b/Documentation/devicetree/bindings/panel/lg,lg4573.txt
new file mode 100644
index 000000000000..824441f4e95a
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/lg,lg4573.txt
@@ -0,0 +1,19 @@
+LG LG4573 TFT Liquid Crystal Display with SPI control bus
+
+Required properties:
+  - compatible: "lg,lg4573"
+  - reg: address of the panel on the SPI bus
+
+The panel must obey rules for SPI slave device specified in document [1].
+
+[1]: Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Example:
+
+	lcd_panel: display@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "lg,lg4573";
+		spi-max-frequency = <10000000>;
+		reg = <0>;
+	};
diff --git a/Documentation/devicetree/bindings/panel/nec,nl4827hc19-05b.txt b/Documentation/devicetree/bindings/panel/nec,nl4827hc19-05b.txt
new file mode 100644
index 000000000000..8e1914d1edb8
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/nec,nl4827hc19-05b.txt
@@ -0,0 +1,7 @@
+NEC LCD Technologies,Ltd. WQVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "nec,nl4827hc19-05b"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/panel/okaya,rs800480t-7x0gp.txt b/Documentation/devicetree/bindings/panel/okaya,rs800480t-7x0gp.txt
new file mode 100644
index 000000000000..ddf8e211d382
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/okaya,rs800480t-7x0gp.txt
@@ -0,0 +1,7 @@
+OKAYA Electric America, Inc. RS800480T-7X0GP 7" WVGA LCD panel
+
+Required properties:
+- compatible: should be "okaya,rs800480t-7x0gp"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/pci/ti-pci.txt b/Documentation/devicetree/bindings/pci/ti-pci.txt
index 3d217911b313..60e25161f351 100644
--- a/Documentation/devicetree/bindings/pci/ti-pci.txt
+++ b/Documentation/devicetree/bindings/pci/ti-pci.txt
@@ -23,6 +23,9 @@ PCIe Designware Controller
    interrupt-map-mask,
    interrupt-map : as specified in ../designware-pcie.txt
 
+Optional Property:
+ - gpios : Should be added if a gpio line is required to drive PERST# line
+
 Example:
 axi {
 	compatible = "simple-bus";
diff --git a/Documentation/devicetree/bindings/phy/phy-lpc18xx-usb-otg.txt b/Documentation/devicetree/bindings/phy/phy-lpc18xx-usb-otg.txt
new file mode 100644
index 000000000000..bd61b467e30a
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/phy-lpc18xx-usb-otg.txt
@@ -0,0 +1,26 @@
+NXP LPC18xx/43xx internal USB OTG PHY binding
+---------------------------------------------
+
+This file contains documentation for the internal USB OTG PHY found
+in NXP LPC18xx and LPC43xx SoCs.
+
+Required properties:
+- compatible	: must be "nxp,lpc1850-usb-otg-phy"
+- clocks	: must be exactly one entry
+See: Documentation/devicetree/bindings/clock/clock-bindings.txt
+- #phy-cells	: must be 0 for this phy
+See: Documentation/devicetree/bindings/phy/phy-bindings.txt
+
+The phy node must be a child of the creg syscon node.
+
+Example:
+creg: syscon@40043000 {
+	compatible = "nxp,lpc1850-creg", "syscon", "simple-mfd";
+	reg = <0x40043000 0x1000>;
+
+	usb0_otg_phy: phy@004 {
+		compatible = "nxp,lpc1850-usb-otg-phy";
+		clocks = <&ccu1 CLK_USB0>;
+		#phy-cells = <0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
index 16528b9eb561..0cebf7454517 100644
--- a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
+++ b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
@@ -7,6 +7,8 @@ Required properties:
   * allwinner,sun5i-a13-usb-phy
   * allwinner,sun6i-a31-usb-phy
   * allwinner,sun7i-a20-usb-phy
+  * allwinner,sun8i-a23-usb-phy
+  * allwinner,sun8i-a33-usb-phy
 - reg : a list of offset + length pairs
 - reg-names :
   * "phy_ctrl"
@@ -17,12 +19,21 @@ Required properties:
 - clock-names :
   * "usb_phy" for sun4i, sun5i or sun7i
   * "usb0_phy", "usb1_phy" and "usb2_phy" for sun6i
+  * "usb0_phy", "usb1_phy" for sun8i
 - resets : a list of phandle + reset specifier pairs
 - reset-names :
   * "usb0_reset"
   * "usb1_reset"
   * "usb2_reset" for sun4i, sun6i or sun7i
 
+Optional properties:
+- usb0_id_det-gpios : gpio phandle for reading the otg id pin value
+- usb0_vbus_det-gpios : gpio phandle for detecting the presence of usb0 vbus
+- usb0_vbus_power-supply: power-supply phandle for usb0 vbus presence detect
+- usb0_vbus-supply : regulator phandle for controller usb0 vbus
+- usb1_vbus-supply : regulator phandle for controller usb1 vbus
+- usb2_vbus-supply : regulator phandle for controller usb2 vbus
+
 Example:
 	usbphy: phy@0x01c13400 {
 		#phy-cells = <1>;
@@ -32,6 +43,13 @@ Example:
 		reg-names = "phy_ctrl", "pmu1", "pmu2";
 		clocks = <&usb_clk 8>;
 		clock-names = "usb_phy";
-		resets = <&usb_clk 1>, <&usb_clk 2>;
-		reset-names = "usb1_reset", "usb2_reset";
+		resets = <&usb_clk 0>, <&usb_clk 1>, <&usb_clk 2>;
+		reset-names = "usb0_reset", "usb1_reset", "usb2_reset";
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+		usb0_id_det-gpios = <&pio 7 19 GPIO_ACTIVE_HIGH>; /* PH19 */
+		usb0_vbus_det-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>; /* PH22 */
+		usb0_vbus-supply = <&reg_usb0_vbus>;
+		usb1_vbus-supply = <&reg_usb1_vbus>;
+		usb2_vbus-supply = <&reg_usb2_vbus>;
 	};
diff --git a/Documentation/devicetree/bindings/phy/ti-phy.txt b/Documentation/devicetree/bindings/phy/ti-phy.txt
index 305e3df3d9b1..9cf9446eaf2e 100644
--- a/Documentation/devicetree/bindings/phy/ti-phy.txt
+++ b/Documentation/devicetree/bindings/phy/ti-phy.txt
@@ -82,6 +82,9 @@ Optional properties:
  - id: If there are multiple instance of the same type, in order to
    differentiate between each instance "id" can be used (e.g., multi-lane PCIe
    PHY). If "id" is not provided, it is set to default value of '1'.
+ - syscon-pllreset: Handle to system control region that contains the
+   CTRL_CORE_SMA_SW_0 register and register offset to the CTRL_CORE_SMA_SW_0
+   register that contains the SATA_PLL_SOFT_RESET bit. Only valid for sata_phy.
 
 This is usually a subnode of ocp2scp to which it is connected.
 
@@ -100,3 +103,16 @@ usb3phy@4a084400 {
 			"sysclk",
 			"refclk";
 };
+
+sata_phy: phy@4A096000 {
+	compatible = "ti,phy-pipe3-sata";
+	reg = <0x4A096000 0x80>, /* phy_rx */
+	      <0x4A096400 0x64>, /* phy_tx */
+	      <0x4A096800 0x40>; /* pll_ctrl */
+	reg-names = "phy_rx", "phy_tx", "pll_ctrl";
+	ctrl-module = <&omap_control_sata>;
+	clocks = <&sys_clkin1>, <&sata_ref_clk>;
+	clock-names = "sysclk", "refclk";
+	syscon-pllreset = <&scm_conf 0x3fc>;
+	#phy-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index 9462ab7ddd1f..3c821cda1ad0 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -48,7 +48,7 @@ Optional subnode-properties:
 
 Examples:
 
-pinctrl@01c20800 {
+pio: pinctrl@01c20800 {
 	compatible = "allwinner,sun5i-a13-pinctrl";
 	reg = <0x01c20800 0x400>;
 	#address-cells = <1>;
@@ -68,3 +68,38 @@ pinctrl@01c20800 {
 		allwinner,pull = <0>;
 	};
 };
+
+
+GPIO and interrupt controller
+-----------------------------
+
+This hardware also acts as a GPIO controller and an interrupt
+controller.
+
+Consumers that would want to refer to one or the other (or both)
+should provide through the usual *-gpios and interrupts properties a
+cell with 3 arguments, first the number of the bank, then the pin
+inside that bank, and finally the flags for the GPIO/interrupts.
+
+Example:
+
+xio: gpio@38 {
+	compatible = "nxp,pcf8574a";
+	reg = <0x38>;
+
+	gpio-controller;
+	#gpio-cells = <2>;
+
+	interrupt-parent = <&pio>;
+	interrupts = <6 0 IRQ_TYPE_EDGE_FALLING>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+};
+
+reg_usb1_vbus: usb1-vbus {
+	compatible = "regulator-fixed";
+	regulator-name = "usb1-vbus";
+	regulator-min-microvolt = <5000000>;
+	regulator-max-microvolt = <5000000>;
+	gpio = <&pio 7 6 GPIO_ACTIVE_HIGH>;
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/cnxt,cx92755-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/cnxt,cx92755-pinctrl.txt
new file mode 100644
index 000000000000..23ce8dc26990
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/cnxt,cx92755-pinctrl.txt
@@ -0,0 +1,86 @@
+Conexant Digicolor CX92755 General Purpose Pin Mapping
+
+This document describes the device tree binding of the pin mapping hardware
+modules in the Conexant Digicolor CX92755 SoCs. The CX92755 in one of the
+Digicolor series of SoCs.
+
+=== Pin Controller Node ===
+
+Required Properties:
+
+- compatible: Must be "cnxt,cx92755-pinctrl"
+- reg: Base address of the General Purpose Pin Mapping register block and the
+  size of the block.
+- gpio-controller: Marks the device node as a GPIO controller.
+- #gpio-cells: Must be <2>. The first cell is the pin number and the
+  second cell is used to specify flags. See include/dt-bindings/gpio/gpio.h
+  for possible values.
+
+For example, the following is the bare minimum node:
+
+	pinctrl: pinctrl@f0000e20 {
+		compatible = "cnxt,cx92755-pinctrl";
+		reg = <0xf0000e20 0x100>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+As a pin controller device, in addition to the required properties, this node
+should also contain the pin configuration nodes that client devices reference,
+if any.
+
+For a general description of GPIO bindings, please refer to ../gpio/gpio.txt.
+
+=== Pin Configuration Node ===
+
+Each pin configuration node is a sub-node of the pin controller node and is a
+container of an arbitrary number of subnodes, called pin group nodes in this
+document.
+
+Please refer to the pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the definition of a
+"pin configuration node".
+
+=== Pin Group Node ===
+
+A pin group node specifies the desired pin mux for an arbitrary number of
+pins. The name of the pin group node is optional and not used.
+
+A pin group node only affects the properties specified in the node, and has no
+effect on any properties that are omitted.
+
+The pin group node accepts a subset of the generic pin config properties. For
+details generic pin config properties, please refer to pinctrl-bindings.txt
+and <include/linux/pinctrl/pinconfig-generic.h>.
+
+Required Pin Group Node Properties:
+
+- pins: Multiple strings. Specifies the name(s) of one or more pins to be
+  configured by this node. The format of a pin name string is "GP_xy", where x
+  is an uppercase character from 'A' to 'R', and y is a digit from 0 to 7.
+- function: String. Specifies the pin mux selection. Values must be one of:
+  "gpio", "client_a", "client_b", "client_c"
+
+Example:
+	pinctrl: pinctrl@f0000e20 {
+		compatible = "cnxt,cx92755-pinctrl";
+		reg = <0xf0000e20 0x100>;
+
+		uart0_default: uart0_active {
+			data_signals {
+				pins = "GP_O0", "GP_O1";
+				function = "client_b";
+			};
+		};
+	};
+
+	uart0: uart@f0000740 {
+		compatible = "cnxt,cx92755-usart";
+		...
+		pinctrl-0 = <&uart0_default>;
+		pinctrl-names = "default";
+	};
+
+In the example above, a single pin group configuration node defines the
+"client select" for the Rx and Tx signals of uart0. The uart0 node references
+that pin configuration node using the &uart0_default phandle.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6ul-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6ul-pinctrl.txt
new file mode 100644
index 000000000000..a81bbf37ed66
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx6ul-pinctrl.txt
@@ -0,0 +1,36 @@
+* Freescale i.MX6 UltraLite IOMUX Controller
+
+Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
+and usage.
+
+Required properties:
+- compatible: "fsl,imx6ul-iomuxc"
+- fsl,pins: each entry consists of 6 integers and represents the mux and config
+  setting for one pin.  The first 5 integers <mux_reg conf_reg input_reg mux_val
+  input_val> are specified using a PIN_FUNC_ID macro, which can be found in
+  imx6ul-pinfunc.h under device tree source folder.  The last integer CONFIG is
+  the pad setting value like pull-up on this pin.  Please refer to i.MX6 UltraLite
+  Reference Manual for detailed CONFIG settings.
+
+CONFIG bits definition:
+PAD_CTL_HYS                     (1 << 16)
+PAD_CTL_PUS_100K_DOWN           (0 << 14)
+PAD_CTL_PUS_47K_UP              (1 << 14)
+PAD_CTL_PUS_100K_UP             (2 << 14)
+PAD_CTL_PUS_22K_UP              (3 << 14)
+PAD_CTL_PUE                     (1 << 13)
+PAD_CTL_PKE                     (1 << 12)
+PAD_CTL_ODE                     (1 << 11)
+PAD_CTL_SPEED_LOW               (0 << 6)
+PAD_CTL_SPEED_MED               (1 << 6)
+PAD_CTL_SPEED_HIGH              (3 << 6)
+PAD_CTL_DSE_DISABLE             (0 << 3)
+PAD_CTL_DSE_260ohm              (1 << 3)
+PAD_CTL_DSE_130ohm              (2 << 3)
+PAD_CTL_DSE_87ohm               (3 << 3)
+PAD_CTL_DSE_65ohm               (4 << 3)
+PAD_CTL_DSE_52ohm               (5 << 3)
+PAD_CTL_DSE_43ohm               (6 << 3)
+PAD_CTL_DSE_37ohm               (7 << 3)
+PAD_CTL_SRE_FAST                (1 << 0)
+PAD_CTL_SRE_SLOW                (0 << 0)
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
index ed19991aad35..d7803a2a94e9 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
@@ -7,8 +7,13 @@ of PMIC's from Qualcomm.
 	Usage: required
 	Value type: <string>
 	Definition: Should contain one of:
+		    "qcom,pm8018-mpp",
+		    "qcom,pm8038-mpp",
+		    "qcom,pm8821-mpp",
 		    "qcom,pm8841-mpp",
 		    "qcom,pm8916-mpp",
+		    "qcom,pm8917-mpp",
+		    "qcom,pm8921-mpp",
 		    "qcom,pm8941-mpp",
 		    "qcom,pma8084-mpp",
 
@@ -77,12 +82,9 @@ to specify in a pin configuration subnode:
 	Value type: <string>
 	Definition: Specify the alternative function to be configured for the
 		    specified pins.  Valid values are:
-		    "normal",
-		    "paired",
-		    "dtest1",
-		    "dtest2",
-		    "dtest3",
-		    "dtest4"
+		    "digital",
+		    "analog",
+		    "sink"
 
 - bias-disable:
 	Usage: optional
@@ -127,12 +129,18 @@ to specify in a pin configuration subnode:
 	Definition: Selects the power source for the specified pins. Valid power
 		    sources are defined in <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 
-- qcom,analog-mode:
+- qcom,analog-level:
 	Usage: optional
-	Value type: <none>
-	Definition: Selects Analog mode of operation: combined with input-enable
-		    and/or output-high, output-low MPP could operate as
-		    Bidirectional Logic, Analog Input, Analog Output.
+	Value type: <u32>
+	Definition: Selects the source for analog output. Valued values are
+		    defined in <dt-binding/pinctrl/qcom,pmic-mpp.h>
+		    PMIC_MPP_AOUT_LVL_*
+
+- qcom,dtest:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects which dtest rail to be routed in the various functions.
+		    Valid values are 1-4
 
 - qcom,amux-route:
 	Usage: optional
@@ -140,6 +148,10 @@ to specify in a pin configuration subnode:
 	Definition: Selects the source for analog input. Valid values are
 		    defined in <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 		    PMIC_MPP_AMUX_ROUTE_CH5, PMIC_MPP_AMUX_ROUTE_CH6...
+- qcom,paired:
+	Usage: optional
+	Value type: <none>
+	Definition: Indicates that the pin should be operating in paired mode.
 
 Example:
 
@@ -156,7 +168,7 @@ Example:
 		pm8841_default: default {
 			gpio {
 				pins = "mpp1", "mpp2", "mpp3", "mpp4";
-				function = "normal";
+				function = "digital";
 				input-enable;
 				power-source = <PM8841_MPP_S3>;
 			};
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
index 51cee44fc140..9496934528bd 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
@@ -58,12 +58,12 @@ are parsed through phandles and processed purely based on their content.
 
 Pin Configuration Node Properties:
 
-- renesas,pins : An array of strings, each string containing the name of a pin.
-- renesas,groups : An array of strings, each string containing the name of a pin
+- pins : An array of strings, each string containing the name of a pin.
+- groups : An array of strings, each string containing the name of a pin
   group.
 
-- renesas,function: A string containing the name of the function to mux to the
-  pin group(s) specified by the renesas,groups property
+- function: A string containing the name of the function to mux to the pin
+  group(s) specified by the groups property.
 
   Valid values for pin, group and function names can be found in the group and
   function arrays of the PFC data file corresponding to the SoC
@@ -71,7 +71,9 @@ Pin Configuration Node Properties:
 
 The pin configuration parameters use the generic pinconf bindings defined in
 pinctrl-bindings.txt in this directory. The supported parameters are
-bias-disable, bias-pull-up and bias-pull-down.
+bias-disable, bias-pull-up, bias-pull-down and power-source. For pins that
+have a configurable I/O voltage, the power-source value should be the
+nominal I/O voltage in millivolts.
 
 
 GPIO
@@ -141,19 +143,19 @@ Example 3: KZM-A9-GT (SH-Mobile AG5) default pin state hog and pin control maps
 
 		mmcif_pins: mmcif {
 			mux {
-				renesas,groups = "mmc0_data8_0", "mmc0_ctrl_0";
-				renesas,function = "mmc0";
+				groups = "mmc0_data8_0", "mmc0_ctrl_0";
+				function = "mmc0";
 			};
 			cfg {
-				renesas,groups = "mmc0_data8_0";
-				renesas,pins = "PORT279";
+				groups = "mmc0_data8_0";
+				pins = "PORT279";
 				bias-pull-up;
 			};
 		};
 
 		scifa4_pins: scifa4 {
-			renesas,groups = "scifa4_data", "scifa4_ctrl";
-			renesas,function = "scifa4";
+			groups = "scifa4_data", "scifa4_ctrl";
+			function = "scifa4";
 		};
 	};
 
diff --git a/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt b/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt
index f63fcb3ed352..2213802435e0 100644
--- a/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt
+++ b/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt
@@ -3,7 +3,9 @@ ST Ericsson Nomadik pinmux controller
 Required properties:
 - compatible: "stericsson,db8500-pinctrl", "stericsson,db8540-pinctrl",
               "stericsson,stn8815-pinctrl"
-- reg: Should contain the register physical address and length of the PRCMU.
+- nomadik-gpio-chips: array of phandles to the corresponding GPIO chips
+              (these have the register ranges used by the pin controller).
+- prcm: phandle to the PRCMU managing the back end of this pin controller
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
 common pinctrl bindings used by client devices, including the meaning of the
@@ -74,7 +76,8 @@ Example board file extract:
 
 	pinctrl@80157000 {
 		compatible = "stericsson,db8500-pinctrl";
-		reg = <0x80157000 0x2000>;
+		nomadik-gpio-chips = <&gpio0>, <&gpio1>, <&gpio2>, <&gpio3>;
+		prcm = <&prcmu>;
 
 		pinctrl-names = "default";
 
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 0f8ed3710c66..025b5e7df61c 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -48,7 +48,7 @@ Example 2:
 		#power-domain-cells = <1>;
 	};
 
-	child: power-controller@12340000 {
+	child: power-controller@12341000 {
 		compatible = "foo,power-controller";
 		reg = <0x12341000 0x1000>;
 		power-domains = <&parent 0>;
diff --git a/Documentation/devicetree/bindings/power/qcom,coincell-charger.txt b/Documentation/devicetree/bindings/power/qcom,coincell-charger.txt
new file mode 100644
index 000000000000..0e6d8754e7ec
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/qcom,coincell-charger.txt
@@ -0,0 +1,48 @@
+Qualcomm Coincell Charger:
+
+The hardware block controls charging for a coincell or capacitor that is
+used to provide power backup for certain features of the power management
+IC (PMIC)
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be: "qcom,pm8941-coincell"
+
+- reg:
+	Usage: required
+	Value type: <u32>
+	Definition: base address of the coincell charger registers
+
+- qcom,rset-ohms:
+	Usage: required
+	Value type: <u32>
+	Definition: resistance (in ohms) for current-limiting resistor
+		must be one of: 800, 1200, 1700, 2100
+
+- qcom,vset-millivolts:
+	Usage: required
+	Value type: <u32>
+	Definition: voltage (in millivolts) to apply for charging
+		must be one of: 2500, 3000, 3100, 3200
+
+- qcom,charger-disable:
+	Usage: optional
+	Value type: <boolean>
+	Definition: definining this property disables charging
+
+This charger is a sub-node of one of the 8941 PMIC blocks, and is specified
+as a child node in DTS of that node.  See ../mfd/qcom,spmi-pmic.txt and
+../mfd/qcom-pm8xxx.txt
+
+Example:
+
+	pm8941@0 {
+		coincell@2800 {
+			compatible = "qcom,pm8941-coincell";
+			reg = <0x2800>;
+
+			qcom,rset-ohms = <2100>;
+			qcom,vset-millivolts = <3000>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
index 8b70db103ca7..b8627e763dba 100644
--- a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
+++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
@@ -33,6 +33,8 @@ Required properties:
 - compatible: should be one of:
   - "rockchip,rk3188-io-voltage-domain" for rk3188
   - "rockchip,rk3288-io-voltage-domain" for rk3288
+  - "rockchip,rk3368-io-voltage-domain" for rk3368
+  - "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains
 - rockchip,grf: phandle to the syscon managing the "general register files"
 
 
@@ -64,6 +66,18 @@ Possible supplies for rk3288:
 - sdcard-supply: The supply connected to SDMMC0_VDD.
 - wifi-supply:   The supply connected to APIO3_VDD.  Also known as SDIO0.
 
+Possible supplies for rk3368:
+- audio-supply:  The supply connected to APIO3_VDD.
+- dvp-supply:    The supply connected to DVPIO_VDD.
+- flash0-supply: The supply connected to FLASH0_VDD.  Typically for eMMC
+- gpio30-supply: The supply connected to APIO1_VDD.
+- gpio1830       The supply connected to APIO4_VDD.
+- sdcard-supply: The supply connected to SDMMC0_VDD.
+- wifi-supply:   The supply connected to APIO2_VDD.  Also known as SDIO0.
+
+Possible supplies for rk3368 pmu-domains:
+- pmu-supply:    The supply connected to PMUIO_VDD.
+- vop-supply:    The supply connected to LCDC_VDD.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
index 8832e8798912..647817527c88 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
@@ -6,14 +6,14 @@ PSC in UART mode
 For PSC in UART mode the needed PSC serial devices
 are specified by fsl,mpc5121-psc-uart nodes in the
 fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
-Controller node fsl,mpc5121-psc-fifo is requered there:
+Controller node fsl,mpc5121-psc-fifo is required there:
 
-fsl,mpc5121-psc-uart nodes
+fsl,mpc512x-psc-uart nodes
 --------------------------
 
 Required properties :
- - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
- - cell-index : Index of the PSC in hardware
+ - compatible : Should contain "fsl,<soc>-psc-uart" and "fsl,<soc>-psc"
+   Supported <soc>s: mpc5121, mpc5125
  - reg : Offset and length of the register set for the PSC device
  - interrupts : <a b> where a is the interrupt number of the
    PSC FIFO Controller and b is a field that represents an
@@ -25,12 +25,21 @@ Recommended properties :
  - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
  - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
 
+PSC in SPI mode
+---------------
 
-fsl,mpc5121-psc-fifo node
+Similar to the UART mode a PSC can be operated in SPI mode. The compatible used
+for that is fsl,mpc5121-psc-spi. It requires a fsl,mpc5121-psc-fifo as well.
+The required and recommended properties are identical to the
+fsl,mpc5121-psc-uart nodes, just use spi instead of uart in the compatible
+string.
+
+fsl,mpc512x-psc-fifo node
 -------------------------
 
 Required properties :
- - compatible : Should be "fsl,mpc5121-psc-fifo"
+ - compatible : Should be "fsl,<soc>-psc-fifo"
+   Supported <soc>s: mpc5121, mpc5125
  - reg : Offset and length of the register set for the PSC
          FIFO Controller
  - interrupts : <a b> where a is the interrupt number of the
@@ -39,6 +48,9 @@ Required properties :
  - interrupt-parent : the phandle for the interrupt controller that
    services interrupts for this device.
 
+Recommended properties :
+ - clocks : specifies the clock needed to operate the fifo controller
+ - clock-names : name(s) for the clock(s) listed in clocks
 
 Example for a board using PSC0 and PSC1 devices in serial mode:
 
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/scfg.txt b/Documentation/devicetree/bindings/powerpc/fsl/scfg.txt
new file mode 100644
index 000000000000..0532c46b3372
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/fsl/scfg.txt
@@ -0,0 +1,18 @@
+Freescale Supplement configuration unit (SCFG)
+
+SCFG is the supplemental configuration unit, that provides SoC specific
+configuration and status registers for the chip. Such as getting PEX port
+status.
+
+Required properties:
+
+- compatible: should be "fsl,<chip>-scfg"
+- reg: should contain base address and length of SCFG memory-mapped
+registers
+
+Example:
+
+	scfg: global-utilities@fc000 {
+		compatible = "fsl,t1040-scfg";
+		reg = <0xfc000 0x1000>;
+	};
diff --git a/Documentation/devicetree/bindings/regulator/da9210.txt b/Documentation/devicetree/bindings/regulator/da9210.txt
index 3297c53cb915..7aa9b1fa6b21 100644
--- a/Documentation/devicetree/bindings/regulator/da9210.txt
+++ b/Documentation/devicetree/bindings/regulator/da9210.txt
@@ -5,6 +5,10 @@ Required properties:
 - compatible:	must be "dlg,da9210"
 - reg:		the i2c slave address of the regulator. It should be 0x68.
 
+Optional properties:
+
+- interrupts:	a reference to the DA9210 interrupt, if available.
+
 Any standard regulator properties can be used to configure the single da9210
 DCDC.
 
diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt
index eb618907c7de..c620493e8dbe 100644
--- a/Documentation/devicetree/bindings/regulator/da9211.txt
+++ b/Documentation/devicetree/bindings/regulator/da9211.txt
@@ -1,7 +1,7 @@
-* Dialog Semiconductor DA9211/DA9213 Voltage Regulator
+* Dialog Semiconductor DA9211/DA9213/DA9215 Voltage Regulator
 
 Required properties:
-- compatible: "dlg,da9211" or "dlg,da9213".
+- compatible: "dlg,da9211" or "dlg,da9213" or "dlg,da9215"
 - reg: I2C slave address, usually 0x68.
 - interrupts: the interrupt outputs of the controller
 - regulators: A node that houses a sub-node for each regulator within the
@@ -66,3 +66,31 @@ Example 2) DA9213
 			};
 		};
 	};
+
+
+Example 3) DA9215
+	pmic: da9215@68 {
+		compatible = "dlg,da9215";
+		reg = <0x68>;
+		interrupts = <3 27>;
+
+		regulators {
+			BUCKA {
+				regulator-name = "VBUCKA";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <4000000>;
+				regulator-max-microamp 	= <7000000>;
+				enable-gpios = <&gpio 27 0>;
+			};
+			BUCKB {
+				regulator-name = "VBUCKB";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <4000000>;
+				regulator-max-microamp 	= <7000000>;
+				enable-gpios = <&gpio 17 0>;
+			};
+		};
+	};
+
diff --git a/Documentation/devicetree/bindings/regulator/max77686.txt b/Documentation/devicetree/bindings/regulator/max77686.txt
new file mode 100644
index 000000000000..0dded64d89d3
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/max77686.txt
@@ -0,0 +1,71 @@
+Binding for Maxim MAX77686 regulators
+
+This is a part of the device tree bindings of MAX77686 multi-function device.
+More information can be found in ../mfd/max77686.txt file.
+
+The MAX77686 PMIC has 9 high-efficiency Buck and 26 Low-DropOut (LDO)
+regulators that can be controlled over I2C.
+
+Following properties should be present in main device node of the MFD chip.
+
+Optional node:
+- voltage-regulators : The regulators of max77686 have to be instantiated
+  under subnode named "voltage-regulators" using the following format.
+
+	regulator_name {
+		regulator-compatible = LDOn/BUCKn
+		standard regulator constraints....
+	};
+	refer Documentation/devicetree/bindings/regulator/regulator.txt
+
+  The regulator node's name should be initialized with a string
+to get matched with their hardware counterparts as follow:
+
+	-LDOn 	:	for LDOs, where n can lie in range 1 to 26.
+			example: LDO1, LDO2, LDO26.
+	-BUCKn 	:	for BUCKs, where n can lie in range 1 to 9.
+			example: BUCK1, BUCK5, BUCK9.
+
+  Regulators which can be turned off during system suspend:
+	-LDOn	:	2, 6-8, 10-12, 14-16,
+	-BUCKn	:	1-4.
+  Use standard regulator bindings for it ('regulator-off-in-suspend').
+
+  LDO20, LDO21, LDO22, BUCK8 and BUCK9 can be configured to GPIO enable
+  control. To turn this feature on this property must be added to the regulator
+  sub-node:
+	- maxim,ena-gpios :	one GPIO specifier enable control (the gpio
+				flags are actually ignored and always
+				ACTIVE_HIGH is used)
+
+Example:
+
+	max77686: pmic@09 {
+		compatible = "maxim,max77686";
+		interrupt-parent = <&wakeup_eint>;
+		interrupts = <26 IRQ_TYPE_NONE>;
+		reg = <0x09>;
+
+		voltage-regulators {
+			ldo11_reg: LDO11 {
+				regulator-name = "vdd_ldo11";
+				regulator-min-microvolt = <1900000>;
+				regulator-max-microvolt = <1900000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "vdd_mif";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck9_reg: BUCK9 {
+				regulator-name = "CAM_ISP_CORE_1.2V";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1200000>;
+				maxim,ena-gpios = <&gpm0 3 GPIO_ACTIVE_HIGH>;
+			};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/max8973-regulator.txt b/Documentation/devicetree/bindings/regulator/max8973-regulator.txt
index 55efb24e5683..f80ea2fe27e6 100644
--- a/Documentation/devicetree/bindings/regulator/max8973-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/max8973-regulator.txt
@@ -25,6 +25,12 @@ Optional properties:
 -maxim,enable-frequency-shift: boolean, enable 9% frequency shift.
 -maxim,enable-bias-control: boolean, enable bias control. By enabling this
 		startup delay can be reduce to 20us from 220us.
+-maxim,enable-etr: boolean, enable Enhanced Transient Response.
+-maxim,enable-high-etr-sensitivity: boolean, Enhanced transient response
+		circuit is enabled and set for high sensitivity. If this
+		property is available then etr will be enable default.
+
+Enhanced transient response (ETR) will affect the configuration of CKADV.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/regulator/mt6311-regulator.txt b/Documentation/devicetree/bindings/regulator/mt6311-regulator.txt
new file mode 100644
index 000000000000..02649d8b3f5a
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/mt6311-regulator.txt
@@ -0,0 +1,35 @@
+Mediatek MT6311 Regulator Driver
+
+Required properties:
+- compatible: "mediatek,mt6311-regulator"
+- reg: I2C slave address, usually 0x6b.
+- regulators: List of regulators provided by this controller. It is named
+  to VDVFS and VBIASN.
+  The definition for each of these nodes is defined using the standard binding
+  for regulators at Documentation/devicetree/bindings/regulator/regulator.txt.
+
+The valid names for regulators are:
+BUCK:
+  VDVFS
+LDO:
+  VBIASN
+
+Example:
+	mt6311: pmic@6b {
+		compatible = "mediatek,mt6311-regulator";
+		reg = <0x6b>;
+
+		regulators {
+			mt6311_vcpu_reg: VDVFS {
+				regulator-name = "VDVFS";
+				regulator-min-microvolt = < 600000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-ramp-delay = <10000>;
+			};
+			mt6311_ldo_reg: VBIASN {
+				regulator-name = "VBIASN";
+				regulator-min-microvolt = <200000>;
+				regulator-max-microvolt = <800000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/pwm-regulator.txt b/Documentation/devicetree/bindings/regulator/pwm-regulator.txt
index ce91f61feb12..ed936f0f34f2 100644
--- a/Documentation/devicetree/bindings/regulator/pwm-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/pwm-regulator.txt
@@ -1,27 +1,68 @@
-pwm regulator bindings
+Bindings for the Generic PWM Regulator
+======================================
+
+Currently supports 2 modes of operation:
+
+Voltage Table:		When in this mode, a voltage table (See below) of
+			predefined voltage <=> duty-cycle values must be
+			provided via DT. Limitations are that the regulator can
+			only operate at the voltages supplied in the table.
+			Intermediary duty-cycle values which would normally
+			allow finer grained voltage selection are ignored and
+			rendered useless.  Although more control is given to
+			the user if the assumptions made in continuous-voltage
+			mode do not reign true.
+
+Continuous Voltage:	This mode uses the regulator's maximum and minimum
+			supplied voltages specified in the
+			regulator-{min,max}-microvolt properties to calculate
+			appropriate duty-cycle values.  This allows for a much
+			more fine grained solution when compared with
+			voltage-table mode above.  This solution does make an
+			assumption that a %50 duty-cycle value will cause the
+			regulator voltage to run at half way between the
+			supplied max_uV and min_uV values.
 
 Required properties:
-- compatible: Should be "pwm-regulator"
-- pwms: OF device-tree PWM specification (see PWM binding pwm.txt)
-- voltage-table: voltage and duty table, include 2 members in each set of
-  brackets, first one is voltage(unit: uv), the next is duty(unit: percent)
+--------------------
+- compatible:		Should be "pwm-regulator"
+
+- pwms:			PWM specification (See: ../pwm/pwm.txt)
+
+Only required for Voltage Table Mode:
+- voltage-table: 	Voltage and Duty-Cycle table consisting of 2 cells
+			    First cell is voltage in microvolts (uV)
+			    Second cell is duty-cycle in percent (%)
+
+NB: To be clear, if voltage-table is provided, then the device will be used
+in Voltage Table Mode.  If no voltage-table is provided, then the device will
+be used in Continuous Voltage Mode.
 
-Any property defined as part of the core regulator binding defined in
-regulator.txt can also be used.
+Any property defined as part of the core regulator binding can also be used.
+(See: ../regulator/regulator.txt)
 
-Example:
+Continuous Voltage Example:
 	pwm_regulator {
 		compatible = "pwm-regulator;
 		pwms = <&pwm1 0 8448 0>;
+		regulator-min-microvolt = <1016000>;
+		regulator-max-microvolt = <1114000>;
+		regulator-name = "vdd_logic";
+	};
 
+Voltage Table Example:
+	pwm_regulator {
+		compatible = "pwm-regulator;
+		pwms = <&pwm1 0 8448 0>;
+		regulator-min-microvolt = <1016000>;
+		regulator-max-microvolt = <1114000>;
+		regulator-name = "vdd_logic";
+
+			      /* Voltage Duty-Cycle */
 		voltage-table = <1114000 0>,
 				<1095000 10>,
 				<1076000 20>,
 				<1056000 30>,
 				<1036000 40>,
 				<1016000 50>;
-
-		regulator-min-microvolt = <1016000>;
-		regulator-max-microvolt = <1114000>;
-		regulator-name = "vdd_logic";
 	};
diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
index 75b4604bad07..d00bfd8624a5 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
@@ -91,13 +91,65 @@ see regulator.txt - with additional custom properties described below:
 - regulator-initial-mode:
 	Usage: optional
 	Value type: <u32>
-	Descrption: 1 = Set initial mode to high power mode (HPM), also referred
-		    to as NPM.  HPM consumes more ground current than LPM, but
+	Description: 2 = Set initial mode to auto mode (automatically select
+		    between HPM and LPM); not available on boost type
+		    regulators.
+
+		    1 = Set initial mode to high power mode (HPM), also referred
+		    to as NPM. HPM consumes more ground current than LPM, but
 		    it can source significantly higher load current. HPM is not
 		    available on boost type regulators. For voltage switch type
 		    regulators, HPM implies that over current protection and
-		    soft start are active all the time. 0 = Set initial mode to
-		    low power mode (LPM).
+		    soft start are active all the time.
+
+		    0 = Set initial mode to low power mode (LPM).
+
+- qcom,ocp-max-retries:
+	Usage: optional
+	Value type: <u32>
+	Description: Maximum number of times to try toggling a voltage switch
+		     off and back on as a result of consecutive over current
+		     events.
+
+- qcom,ocp-retry-delay:
+	Usage: optional
+	Value type: <u32>
+	Description: Time to delay in milliseconds between each voltage switch
+		     toggle after an over current event takes place.
+
+- qcom,pin-ctrl-enable:
+	Usage: optional
+	Value type: <u32>
+	Description: Bit mask specifying which hardware pins should be used to
+		     enable the regulator, if any; supported bits are:
+			0 = ignore all hardware enable signals
+			BIT(0) = follow HW0_EN signal
+			BIT(1) = follow HW1_EN signal
+			BIT(2) = follow HW2_EN signal
+			BIT(3) = follow HW3_EN signal
+
+- qcom,pin-ctrl-hpm:
+	Usage: optional
+	Value type: <u32>
+	Description: Bit mask specifying which hardware pins should be used to
+		     force the regulator into high power mode, if any;
+		     supported bits are:
+			0 = ignore all hardware enable signals
+			BIT(0) = follow HW0_EN signal
+			BIT(1) = follow HW1_EN signal
+			BIT(2) = follow HW2_EN signal
+			BIT(3) = follow HW3_EN signal
+			BIT(4) = follow PMIC awake state
+
+- qcom,vs-soft-start-strength:
+	Usage: optional
+	Value type: <u32>
+	Description: This property sets the soft start strength for voltage
+		     switch type regulators; supported values are:
+			0 = 0.05 uA
+			1 = 0.25 uA
+			2 = 0.55 uA
+			3 = 0.75 uA
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt
index db88feb28c03..24bd422cecd5 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/regulator.txt
@@ -42,6 +42,7 @@ Optional properties:
 - regulator-system-load: Load in uA present on regulator that is not captured by
   any consumer request.
 - regulator-pull-down: Enable pull down resistor when the regulator is disabled.
+- regulator-over-current-protection: Enable over current protection.
 
 Deprecated properties:
 - regulator-compatible: If a regulator chip contains multiple
diff --git a/Documentation/devicetree/bindings/reset/ath79-reset.txt b/Documentation/devicetree/bindings/reset/ath79-reset.txt
new file mode 100644
index 000000000000..4c56330bf398
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/ath79-reset.txt
@@ -0,0 +1,20 @@
+Binding for Qualcomm Atheros AR7xxx/AR9XXX reset controller
+
+Please also refer to reset.txt in this directory for common reset
+controller binding usage.
+
+Required Properties:
+- compatible: has to be "qca,<soctype>-reset", "qca,ar7100-reset"
+              as fallback
+- reg: Base address and size of the controllers memory area
+- #reset-cells : Specifies the number of cells needed to encode reset
+                 line, should be 1
+
+Example:
+
+	reset-controller@1806001c {
+		compatible = "qca,ar9132-reset", "qca,ar7100-reset";
+		reg = <0x1806001c 0x4>;
+
+		#reset-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/reset/nxp,lpc1850-rgu.txt b/Documentation/devicetree/bindings/reset/nxp,lpc1850-rgu.txt
new file mode 100644
index 000000000000..b4e96a278445
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/nxp,lpc1850-rgu.txt
@@ -0,0 +1,84 @@
+NXP LPC1850  Reset Generation Unit (RGU)
+========================================
+
+Please also refer to reset.txt in this directory for common reset
+controller binding usage.
+
+Required properties:
+- compatible: Should be "nxp,lpc1850-rgu"
+- reg: register base and length
+- clocks: phandle and clock specifier to RGU clocks
+- clock-names: should contain "delay" and "reg"
+- #reset-cells: should be 1
+
+See table below for valid peripheral reset numbers. Numbers not
+in the table below are either reserved or not applicable for
+normal operation.
+
+Reset	Peripheral
+  9	System control unit (SCU)
+ 12	ARM Cortex-M0 subsystem core (LPC43xx only)
+ 13	CPU core
+ 16	LCD controller
+ 17	USB0
+ 18	USB1
+ 19	DMA
+ 20	SDIO
+ 21	External memory controller (EMC)
+ 22	Ethernet
+ 25	Flash bank A
+ 27	EEPROM
+ 28	GPIO
+ 29	Flash bank B
+ 32	Timer0
+ 33	Timer1
+ 34	Timer2
+ 35	Timer3
+ 36	Repetitive Interrupt timer (RIT)
+ 37	State Configurable Timer (SCT)
+ 38	Motor control PWM (MCPWM)
+ 39	QEI
+ 40	ADC0
+ 41	ADC1
+ 42	DAC
+ 44	USART0
+ 45	UART1
+ 46	USART2
+ 47	USART3
+ 48	I2C0
+ 49	I2C1
+ 50	SSP0
+ 51	SSP1
+ 52	I2S0 and I2S1
+ 53	Serial Flash Interface (SPIFI)
+ 54	C_CAN1
+ 55	C_CAN0
+ 56	ARM Cortex-M0 application core (LPC4370 only)
+ 57	SGPIO (LPC43xx only)
+ 58	SPI (LPC43xx only)
+ 60	ADCHS (12-bit ADC) (LPC4370 only)
+
+Refer to NXP LPC18xx or LPC43xx user manual for more details about
+the reset signals and the connected block/peripheral.
+
+Reset provider example:
+rgu: reset-controller@40053000 {
+	compatible = "nxp,lpc1850-rgu";
+	reg = <0x40053000 0x1000>;
+	clocks = <&cgu BASE_SAFE_CLK>, <&ccu1 CLK_CPU_BUS>;
+	clock-names = "delay", "reg";
+	#reset-cells = <1>;
+};
+
+Reset consumer example:
+mac: ethernet@40010000 {
+	compatible = "nxp,lpc1850-dwmac", "snps,dwmac-3.611", "snps,dwmac";
+	reg = <0x40010000 0x2000>;
+	interrupts = <5>;
+	interrupt-names = "macirq";
+	clocks = <&ccu1 CLK_CPU_ETHERNET>;
+	clock-names = "stmmaceth";
+	resets = <&rgu 22>;
+	reset-names = "stmmaceth";
+	status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/reset/socfpga-reset.txt b/Documentation/devicetree/bindings/reset/socfpga-reset.txt
index 32c1c8bfd5dc..98c9f560e5c5 100644
--- a/Documentation/devicetree/bindings/reset/socfpga-reset.txt
+++ b/Documentation/devicetree/bindings/reset/socfpga-reset.txt
@@ -3,6 +3,7 @@ Altera SOCFPGA Reset Manager
 Required properties:
 - compatible : "altr,rst-mgr"
 - reg : Should contain 1 register ranges(address and length)
+- altr,modrst-offset : Should contain the offset of the first modrst register.
 - #reset-cells: 1
 
 Example:
@@ -10,4 +11,5 @@ Example:
 		#reset-cells = <1>;
 		compatible = "altr,rst-mgr";
 		reg = <0xffd05000 0x1000>;
+		altr,modrst-offset = <0x10>;
 	};
diff --git a/Documentation/devicetree/bindings/reset/st,sti-picophyreset.txt b/Documentation/devicetree/bindings/reset/st,sti-picophyreset.txt
index 54ae9f747e45..9ca27761f811 100644
--- a/Documentation/devicetree/bindings/reset/st,sti-picophyreset.txt
+++ b/Documentation/devicetree/bindings/reset/st,sti-picophyreset.txt
@@ -39,4 +39,4 @@ Example:
 	};
 
 Macro definitions for the supported reset channels can be found in:
-include/dt-bindings/reset-controller/stih407-resets.h
+include/dt-bindings/reset/stih407-resets.h
diff --git a/Documentation/devicetree/bindings/reset/st,sti-powerdown.txt b/Documentation/devicetree/bindings/reset/st,sti-powerdown.txt
index 5ab26b7e9d35..1cfd21d1dfa1 100644
--- a/Documentation/devicetree/bindings/reset/st,sti-powerdown.txt
+++ b/Documentation/devicetree/bindings/reset/st,sti-powerdown.txt
@@ -43,5 +43,5 @@ example:
 
 Macro definitions for the supported reset channels can be found in:
 
-include/dt-bindings/reset-controller/stih415-resets.h
-include/dt-bindings/reset-controller/stih416-resets.h
+include/dt-bindings/reset/stih415-resets.h
+include/dt-bindings/reset/stih416-resets.h
diff --git a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
index a8d3d3c25ca2..891a2fd85ed6 100644
--- a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
+++ b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
@@ -42,5 +42,5 @@ example:
 
 Macro definitions for the supported reset channels can be found in:
 
-include/dt-bindings/reset-controller/stih415-resets.h
-include/dt-bindings/reset-controller/stih416-resets.h
+include/dt-bindings/reset/stih415-resets.h
+include/dt-bindings/reset/stih416-resets.h
diff --git a/Documentation/devicetree/bindings/reset/zynq-reset.txt b/Documentation/devicetree/bindings/reset/zynq-reset.txt
new file mode 100644
index 000000000000..5860120e3064
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/zynq-reset.txt
@@ -0,0 +1,68 @@
+Xilinx Zynq Reset Manager
+
+The Zynq AP-SoC has several different resets.
+
+See Chapter 26 of the Zynq TRM (UG585) for more information about Zynq resets.
+
+Required properties:
+- compatible: "xlnx,zynq-reset"
+- reg: SLCR offset and size taken via syscon <0x200 0x48>
+- syscon: <&slcr>
+  This should be a phandle to the Zynq's SLCR registers.
+- #reset-cells: Must be 1
+
+The Zynq Reset Manager needs to be a childnode of the SLCR.
+
+Example:
+	rstc: rstc@200 {
+		compatible = "xlnx,zynq-reset";
+		reg = <0x200 0x48>;
+		#reset-cells = <1>;
+		syscon = <&slcr>;
+	};
+
+Reset outputs:
+ 0  : soft reset
+ 32 : ddr reset
+ 64 : topsw reset
+ 96 : dmac reset
+ 128: usb0 reset
+ 129: usb1 reset
+ 160: gem0 reset
+ 161: gem1 reset
+ 164: gem0 rx reset
+ 165: gem1 rx reset
+ 166: gem0 ref reset
+ 167: gem1 ref reset
+ 192: sdio0 reset
+ 193: sdio1 reset
+ 196: sdio0 ref reset
+ 197: sdio1 ref reset
+ 224: spi0 reset
+ 225: spi1 reset
+ 226: spi0 ref reset
+ 227: spi1 ref reset
+ 256: can0 reset
+ 257: can1 reset
+ 258: can0 ref reset
+ 259: can1 ref reset
+ 288: i2c0 reset
+ 289: i2c1 reset
+ 320: uart0 reset
+ 321: uart1 reset
+ 322: uart0 ref reset
+ 323: uart1 ref reset
+ 352: gpio reset
+ 384: lqspi reset
+ 385: qspi ref reset
+ 416: smc reset
+ 417: smc ref reset
+ 448: ocm reset
+ 512: fpga0 out reset
+ 513: fpga1 out reset
+ 514: fpga2 out reset
+ 515: fpga3 out reset
+ 544: a9 reset 0
+ 545: a9 reset 1
+ 552: peri reset
+
diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
index 34c1505774bf..5d3791e789c6 100644
--- a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
@@ -5,6 +5,7 @@ Required properties:
 - reg: physical base address of the controller and length of memory mapped
   region.
 - interrupts: rtc alarm/event interrupt
+- clocks: phandle to input clock.
 
 Example:
 
@@ -12,4 +13,5 @@ rtc@fffffe00 {
 	compatible = "atmel,at91rm9200-rtc";
 	reg = <0xfffffe00 0x100>;
 	interrupts = <1 4 7>;
+	clocks = <&clk32k>;
 };
diff --git a/Documentation/devicetree/bindings/rtc/rtc-mxc.txt b/Documentation/devicetree/bindings/rtc/rtc-mxc.txt
new file mode 100644
index 000000000000..5bcd31d995b0
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-mxc.txt
@@ -0,0 +1,26 @@
+* Real Time Clock of the i.MX SoCs
+
+RTC controller for the i.MX SoCs
+
+Required properties:
+- compatible: Should be "fsl,imx1-rtc" or "fsl,imx21-rtc".
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- interrupts: IRQ line for the RTC.
+- clocks: should contain two entries:
+  * one for the input reference
+  * one for the the SoC RTC
+- clock-names: should contain:
+  * "ref" for the input reference clock
+  * "ipg" for the SoC RTC clock
+
+Example:
+
+rtc@10007000 {
+	compatible = "fsl,imx21-rtc";
+	reg = <0x10007000 0x1000>;
+	interrupts = <22>;
+	clocks = <&clks IMX27_CLK_CKIL>,
+		 <&clks IMX27_CLK_RTC_IPG_GATE>;
+	clock-names = "ref", "ipg";
+};
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index 4ba4dbd34289..43a83668673a 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -8,6 +8,7 @@ Required properties:
 			    Wakeup generation for event Alarm. It can also be
 			    used to control an external PMIC via the
 			    pmic_power_en pin.
+	- "ti,am4372-rtc" - for RTC IP used similar to that on AM437X SoC family.
 - reg: Address range of rtc register set
 - interrupts: rtc timer, alarm interrupts in order
 - interrupt-parent: phandle for the interrupt controller
diff --git a/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt b/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt
index 73407f502e4e..daf88265df32 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt
@@ -1,20 +1,23 @@
 STMicroelectronics Low Power Controller (LPC) - RTC
 ===================================================
 
-LPC currently supports Watchdog OR Real Time Clock functionality.
+LPC currently supports Watchdog OR Real Time Clock OR Clocksource
+functionality.
 
 [See: ../watchdog/st_lpc_wdt.txt for Watchdog options]
+[See: ../timer/st,stih407-lpc for Clocksource options]
 
 Required properties
 
-- compatible 	: Must be one of: "st,stih407-lpc" "st,stih416-lpc"
-				  "st,stih415-lpc" "st,stid127-lpc"
+- compatible 	: Must be: "st,stih407-lpc"
 - reg		: LPC registers base address + size
 - interrupts    : LPC interrupt line number and associated flags
 - clocks	: Clock used by LPC device (See: ../clock/clock-bindings.txt)
-- st,lpc-mode	: The LPC can run either one of two modes ST_LPC_MODE_RTC [0] or
-		  ST_LPC_MODE_WDT [1].  One (and only one) mode must be
-		  selected.
+- st,lpc-mode	: The LPC can run either one of three modes:
+                  ST_LPC_MODE_RTC    [0]
+                  ST_LPC_MODE_WDT    [1]
+                  ST_LPC_MODE_CLKSRC [2]
+		 One (and only one) mode must be selected.
 
 Example:
 	lpc@fde05000 {
diff --git a/Documentation/devicetree/bindings/serial/atmel-usart.txt b/Documentation/devicetree/bindings/serial/atmel-usart.txt
index 90787aa2e648..e6e6142e33ac 100644
--- a/Documentation/devicetree/bindings/serial/atmel-usart.txt
+++ b/Documentation/devicetree/bindings/serial/atmel-usart.txt
@@ -22,6 +22,8 @@ Optional properties:
 		memory peripheral interface and USART DMA channel ID, FIFO configuration.
 		Refer to dma.txt and atmel-dma.txt for details.
 	- dma-names: "rx" for RX channel, "tx" for TX channel.
+- atmel,fifo-size: maximum number of data the RX and TX FIFOs can store for FIFO
+  capable USARTs.
 
 <chip> compatible description:
 - at91rm9200:  legacy USART support
@@ -57,4 +59,5 @@ Example:
 		dmas = <&dma0 2 0x3>,
 		       <&dma0 2 0x204>;
 		dma-names = "tx", "rx";
+		atmel,fifo-size = <32>;
 	};
diff --git a/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt b/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt
index ebcbb62c0a76..51b3c9e80ad9 100644
--- a/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt
+++ b/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt
@@ -6,7 +6,7 @@ Required properties:
 - interrupts: device interrupt
 
 Optional properties:
-- {dtr,dsr,ri,cd}-gpios: specify a GPIO for DTR/DSR/RI/CD
+- {dtr,dsr,rng,dcd}-gpios: specify a GPIO for DTR/DSR/RI/DCD
   line respectively.
 
 Example:
@@ -16,4 +16,8 @@ serial@b00260000 {
 	reg = <0xb0026000 0x1000>;
 	interrupts = <68>;
 	status = "disabled";
+	dtr-gpios = <&sysgpio 0 GPIO_ACTIVE_LOW>;
+	dsr-gpios = <&sysgpio 1 GPIO_ACTIVE_LOW>;
+	rng-gpios = <&sysgpio 2 GPIO_ACTIVE_LOW>;
+	dcd-gpios = <&sysgpio 3 GPIO_ACTIVE_LOW>;
 };
diff --git a/Documentation/devicetree/bindings/serial/mtk-uart.txt b/Documentation/devicetree/bindings/serial/mtk-uart.txt
index 8d63f1da07aa..2d47add34765 100644
--- a/Documentation/devicetree/bindings/serial/mtk-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mtk-uart.txt
@@ -5,10 +5,12 @@ Required properties:
   * "mediatek,mt8135-uart" for MT8135 compatible UARTS
   * "mediatek,mt8127-uart" for MT8127 compatible UARTS
   * "mediatek,mt8173-uart" for MT8173 compatible UARTS
+  * "mediatek,mt6795-uart" for MT6795 compatible UARTS
   * "mediatek,mt6589-uart" for MT6589 compatible UARTS
   * "mediatek,mt6582-uart" for MT6582 compatible UARTS
-  * "mediatek,mt6577-uart" for all compatible UARTS (MT8173, MT6589, MT6582, 
-	MT6577)
+  * "mediatek,mt6580-uart" for MT6580 compatible UARTS
+  * "mediatek,mt6577-uart" for all compatible UARTS (MT8173, MT6795,
+        MT6589, MT6582, MT6580, MT6577)
 
 - reg: The base address of the UART register bank.
 
diff --git a/Documentation/devicetree/bindings/serial/omap_serial.txt b/Documentation/devicetree/bindings/serial/omap_serial.txt
index 54c2a155c783..7a71b5de77d6 100644
--- a/Documentation/devicetree/bindings/serial/omap_serial.txt
+++ b/Documentation/devicetree/bindings/serial/omap_serial.txt
@@ -4,6 +4,9 @@ Required properties:
 - compatible : should be "ti,omap2-uart" for OMAP2 controllers
 - compatible : should be "ti,omap3-uart" for OMAP3 controllers
 - compatible : should be "ti,omap4-uart" for OMAP4 controllers
+- compatible : should be "ti,am4372-uart" for AM437x controllers
+- compatible : should be "ti,am3352-uart" for AM335x controllers
+- compatible : should be "ti,dra742-uart" for DRA7x controllers
 - reg : address and length of the register space
 - interrupts or interrupts-extended : Should contain the uart interrupt
                                       specifier or both the interrupt
diff --git a/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt b/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
new file mode 100644
index 000000000000..c0511142b39c
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
@@ -0,0 +1,41 @@
+MediaTek SCPSYS
+===============
+
+The System Control Processor System (SCPSYS) has several power management
+related tasks in the system. The tasks include thermal measurement, dynamic
+voltage frequency scaling (DVFS), interrupt filter and lowlevel sleep control.
+The System Power Manager (SPM) inside the SCPSYS is for the MTCMOS power
+domain control.
+
+The driver implements the Generic PM domain bindings described in
+power/power_domain.txt. It provides the power domains defined in
+include/dt-bindings/power/mt8173-power.h.
+
+Required properties:
+- compatible: Must be "mediatek,mt8173-scpsys"
+- #power-domain-cells: Must be 1
+- reg: Address range of the SCPSYS unit
+- infracfg: must contain a phandle to the infracfg controller
+- clock, clock-names: clocks according to the common clock binding.
+                      The clocks needed "mm" and "mfg". These are the
+		      clocks which hardware needs to be enabled before
+		      enabling certain power domains.
+
+Example:
+
+	scpsys: scpsys@10006000 {
+		#power-domain-cells = <1>;
+		compatible = "mediatek,mt8173-scpsys";
+		reg = <0 0x10006000 0 0x1000>;
+		infracfg = <&infracfg>;
+		clocks = <&clk26m>,
+			 <&topckgen CLK_TOP_MM_SEL>;
+		clock-names = "mfg", "mm";
+	};
+
+Example consumer:
+
+	afe: mt8173-afe-pcm@11220000 {
+		compatible = "mediatek,mt8173-afe-pcm";
+		power-domains = <&scpsys MT8173_POWER_DOMAIN_AUDIO>;
+	};
diff --git a/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt b/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt
new file mode 100644
index 000000000000..e27f5c4c54fd
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt
@@ -0,0 +1,117 @@
+Qualcomm Resource Power Manager (RPM) over SMD
+
+This driver is used to interface with the Resource Power Manager (RPM) found in
+various Qualcomm platforms. The RPM allows each component in the system to vote
+for state of the system resources, such as clocks, regulators and bus
+frequencies.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,rpm-msm8974"
+
+- qcom,smd-channels:
+	Usage: required
+	Value type: <stringlist>
+	Definition: Shared Memory channel used for communication with the RPM
+
+= SUBDEVICES
+
+The RPM exposes resources to its subnodes. The below bindings specify the set
+of valid subnodes that can operate on these resources.
+
+== Regulators
+
+Regulator nodes are identified by their compatible:
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,rpm-pm8841-regulators"
+		    "qcom,rpm-pm8941-regulators"
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_s4-supply:
+- vdd_s5-supply:
+- vdd_s6-supply:
+- vdd_s7-supply:
+- vdd_s8-supply:
+	Usage: optional (pm8841 only)
+	Value type: <phandle>
+	Definition: reference to regulator supplying the input pin, as
+		    described in the data sheet
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_l1_l3-supply:
+- vdd_l2_lvs1_2_3-supply:
+- vdd_l4_l11-supply:
+- vdd_l5_l7-supply:
+- vdd_l6_l12_l14_l15-supply:
+- vdd_l8_l16_l18_l19-supply:
+- vdd_l9_l10_l17_l22-supply:
+- vdd_l13_l20_l23_l24-supply:
+- vdd_l21-supply:
+- vin_5vs-supply:
+	Usage: optional (pm8941 only)
+	Value type: <phandle>
+	Definition: reference to regulator supplying the input pin, as
+		    described in the data sheet
+
+The regulator node houses sub-nodes for each regulator within the device. Each
+sub-node is identified using the node's name, with valid values listed for each
+of the pmics below.
+
+pm8841:
+	s1, s2, s3, s4, s5, s6, s7, s8
+
+pm8941:
+	s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13,
+	l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2,
+	lvs3, 5vs1, 5vs2
+
+The content of each sub-node is defined by the standard binding for regulators -
+see regulator.txt.
+
+= EXAMPLE
+
+	smd {
+		compatible = "qcom,smd";
+
+		rpm {
+			interrupts = <0 168 1>;
+			qcom,ipc = <&apcs 8 0>;
+			qcom,smd-edge = <15>;
+
+			rpm_requests {
+				compatible = "qcom,rpm-msm8974";
+				qcom,smd-channels = "rpm_requests";
+
+				pm8941-regulators {
+					compatible = "qcom,rpm-pm8941-regulators";
+					vdd_l13_l20_l23_l24-supply = <&pm8941_boost>;
+
+					pm8941_s3: s3 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+					};
+
+					pm8941_boost: s4 {
+						regulator-min-microvolt = <5000000>;
+						regulator-max-microvolt = <5000000>;
+					};
+
+					pm8941_l20: l20 {
+						regulator-min-microvolt = <2950000>;
+						regulator-max-microvolt = <2950000>;
+					};
+				};
+			};
+		};
+	};
+
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt
new file mode 100644
index 000000000000..f65c76db9859
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt
@@ -0,0 +1,79 @@
+Qualcomm Shared Memory Driver (SMD) binding
+
+This binding describes the Qualcomm Shared Memory Driver, a fifo based
+communication channel for sending data between the various subsystems in
+Qualcomm platforms.
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,smd"
+
+= EDGES
+
+Each subnode of the SMD node represents a remote subsystem or a remote
+processor of some sort - or in SMD language an "edge". The name of the edges
+are not important.
+The edge is described by the following properties:
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: should specify the IRQ used by the remote processor to
+		    signal this processor about communication related updates
+
+- qcom,ipc:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: three entries specifying the outgoing ipc bit used for
+		    signaling the remote processor:
+		    - phandle to a syscon node representing the apcs registers
+		    - u32 representing offset to the register within the syscon
+		    - u32 representing the ipc bit within the register
+
+- qcom,smd-edge:
+	Usage: required
+	Value type: <u32>
+	Definition: the identifier of the remote processor in the smd channel
+		    allocation table
+
+= SMD DEVICES
+
+In turn, subnodes of the "edges" represent devices tied to SMD channels on that
+"edge". The names of the devices are not important. The properties of these
+nodes are defined by the individual bindings for the SMD devices - but must
+contain the following property:
+
+- qcom,smd-channels:
+	Usage: required
+	Value type: <stringlist>
+	Definition: a list of channels tied to this device, used for matching
+		    the device to channels
+
+= EXAMPLE
+
+The following example represents a smd node, with one edge representing the
+"rpm" subsystem. For the "rpm" subsystem we have a device tied to the
+"rpm_request" channel.
+
+	apcs: syscon@f9011000 {
+		compatible = "syscon";
+		reg = <0xf9011000 0x1000>;
+	};
+
+	smd {
+		compatible = "qcom,smd";
+
+		rpm {
+			interrupts = <0 168 1>;
+			qcom,ipc = <&apcs 8 0>;
+			qcom,smd-edge = <15>;
+
+			rpm_requests {
+				compatible = "qcom,rpm-msm8974";
+				qcom,smd-channels = "rpm_requests";
+
+				...
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/cs4349.txt b/Documentation/devicetree/bindings/sound/cs4349.txt
new file mode 100644
index 000000000000..54c117b59dba
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/cs4349.txt
@@ -0,0 +1,19 @@
+CS4349 audio CODEC
+
+Required properties:
+
+  - compatible : "cirrus,cs4349"
+
+  - reg : the I2C address of the device for I2C
+
+Optional properties:
+
+  - reset-gpios : a GPIO spec for the reset pin.
+
+Example:
+
+codec: cs4349@48 {
+        compatible = "cirrus,cs4349";
+        reg = <0x48>;
+        reset-gpios = <&gpio 54 0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/ics43432.txt b/Documentation/devicetree/bindings/sound/ics43432.txt
new file mode 100644
index 000000000000..b02e3a6c0fef
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ics43432.txt
@@ -0,0 +1,17 @@
+Invensense ICS-43432 MEMS microphone with I2S output.
+
+There are no software configuration options for this device, indeed, the only
+host connection is the I2S interface. Apart from requirements on clock
+frequency (460 kHz to 3.379 MHz according to the data sheet) there must be
+64 clock cycles in each stereo output frame; 24 of the 32 available bits
+contain audio data. A hardware pin determines if the device outputs data
+on the left or right channel of the I2S frame.
+
+Required properties:
+  - compatible : Must be "invensense,ics43432"
+
+Example:
+
+	ics43432: ics43432 {
+		compatible = "invensense,ics43432";
+	};
diff --git a/Documentation/devicetree/bindings/sound/max98357a.txt b/Documentation/devicetree/bindings/sound/max98357a.txt
index a7a149a236e5..28645a2ff885 100644
--- a/Documentation/devicetree/bindings/sound/max98357a.txt
+++ b/Documentation/devicetree/bindings/sound/max98357a.txt
@@ -4,7 +4,11 @@ This node models the Maxim MAX98357A DAC.
 
 Required properties:
 - compatible   : "maxim,max98357a"
-- sdmode-gpios : GPIO specifier for the GPIO -> DAC SDMODE pin
+
+Optional properties:
+- sdmode-gpios : GPIO specifier for the chip's SD_MODE pin.
+        If this option is not specified then driver does not manage
+        the pin state (e.g. chip is always on).
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
index 829bd26d17f8..519e97c8f1b8 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
@@ -3,11 +3,13 @@ MT8173 with MAX98090 CODEC
 Required properties:
 - compatible : "mediatek,mt8173-max98090"
 - mediatek,audio-codec: the phandle of the MAX98090 audio codec
+- mediatek,platform: the phandle of MT8173 ASoC platform
 
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-max98090";
 		mediatek,audio-codec = <&max98090>;
+		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
index 61e98c976bd4..f205ce9e31dd 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
@@ -3,11 +3,13 @@ MT8173 with RT5650 RT5676 CODECS
 Required properties:
 - compatible : "mediatek,mt8173-rt5650-rt5676"
 - mediatek,audio-codec: the phandles of rt5650 and rt5676 codecs
+- mediatek,platform: the phandle of MT8173 ASoC platform
 
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-rt5650-rt5676";
 		mediatek,audio-codec = <&rt5650 &rt5676>;
+		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.txt b/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.txt
index 13e2ef496724..275c6ea356f6 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.txt
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.txt
@@ -8,10 +8,10 @@ Required properties:
 - interrupts : The interrupt from the HDA controller.
 - clocks : Must contain an entry for each required entry in clock-names.
   See ../clocks/clock-bindings.txt for details.
-- clock-names : Must include the following entries: hda, hdacodec_2x, hda2hdmi
+- clock-names : Must include the following entries: hda, hda2hdmi, hda2codec_2x
 - resets : Must contain an entry for each entry in reset-names.
   See ../reset/reset.txt for details.
-- reset-names : Must include the following entries: hda, hdacodec_2x, hda2hdmi
+- reset-names : Must include the following entries: hda, hda2hdmi, hda2codec_2x
 
 Example:
 
@@ -24,7 +24,7 @@ hda@0,70030000 {
 		 <&tegra_car TEGRA124_CLK_HDA2CODEC_2X>;
 	clock-names = "hda", "hda2hdmi", "hda2codec_2x";
 	resets = <&tegra_car 125>, /* hda */
-		 <&tegra_car 128>; /* hda2hdmi */
-		 <&tegra_car 111>, /* hda2codec_2x */
+		 <&tegra_car 128>, /* hda2hdmi */
+		 <&tegra_car 111>; /* hda2codec_2x */
 	reset-names = "hda", "hda2hdmi", "hda2codec_2x";
 };
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index b6b3a786855f..1173395b5e5c 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -18,6 +18,12 @@ Required properties:
 - rcar_sound,src		: Should contain SRC feature.
 				  The number of SRC subnode should be same as HW.
 				  see below for detail.
+- rcar_sound,ctu		: Should contain CTU feature.
+				  The number of CTU subnode should be same as HW.
+				  see below for detail.
+- rcar_sound,mix		: Should contain MIX feature.
+				  The number of MIX subnode should be same as HW.
+				  see below for detail.
 - rcar_sound,dvc		: Should contain DVC feature.
 				  The number of DVC subnode should be same as HW.
 				  see below for detail.
@@ -90,6 +96,22 @@ rcar_sound: sound@ec500000 {
 		};
 	};
 
+	rcar_sound,mix {
+		mix0: mix@0 { };
+		mix1: mix@1 { };
+	};
+
+	rcar_sound,ctu {
+		ctu00: ctu@0 { };
+		ctu01: ctu@1 { };
+		ctu02: ctu@2 { };
+		ctu03: ctu@3 { };
+		ctu10: ctu@4 { };
+		ctu11: ctu@5 { };
+		ctu12: ctu@6 { };
+		ctu13: ctu@7 { };
+	};
+
 	rcar_sound,src {
 		src0: src@0 {
 			interrupts = <0 352 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt b/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt
index c64155027288..962748a8d919 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsrc-card.txt
@@ -6,6 +6,7 @@ Required properties:
 
 - compatible				: "renesas,rsrc-card,<board>"
 					  Examples with soctypes are:
+					    - "renesas,rsrc-card"
 					    - "renesas,rsrc-card,lager"
 					    - "renesas,rsrc-card,koelsch"
 Optional properties:
@@ -29,6 +30,12 @@ Optional subnode properties:
 - frame-inversion			: bool property. Add this if the
 					  dai-link uses frame clock inversion.
 - convert-rate				: platform specified sampling rate convert
+- audio-prefix				: see audio-routing
+- audio-routing				: A list of the connections between audio components.
+					  Each entry is a pair of strings, the first being the connection's sink,
+					  the second being the connection's source. Valid names for sources.
+					  use audio-prefix if some components is using same sink/sources naming.
+					  it can be used if compatible was "renesas,rsrc-card";
 
 Required CPU/CODEC subnodes properties:
 
diff --git a/Documentation/devicetree/bindings/sound/rockchip-max98090.txt b/Documentation/devicetree/bindings/sound/rockchip-max98090.txt
new file mode 100644
index 000000000000..a805aa99ad75
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rockchip-max98090.txt
@@ -0,0 +1,19 @@
+ROCKCHIP with MAX98090 CODEC
+
+Required properties:
+- compatible: "rockchip,rockchip-audio-max98090"
+- rockchip,model: The user-visible name of this sound complex
+- rockchip,i2s-controller: The phandle of the Rockchip I2S controller that's
+  connected to the CODEC
+- rockchip,audio-codec: The phandle of the MAX98090 audio codec
+- rockchip,headset-codec: The phandle of Ext chip for jack detection
+
+Example:
+
+sound {
+	compatible = "rockchip,rockchip-audio-max98090";
+	rockchip,model = "ROCKCHIP-I2S";
+	rockchip,i2s-controller = <&i2s>;
+	rockchip,audio-codec = <&max98090>;
+	rockchip,headset-codec = <&headsetcodec>;
+};
diff --git a/Documentation/devicetree/bindings/sound/rockchip-rt5645.txt b/Documentation/devicetree/bindings/sound/rockchip-rt5645.txt
new file mode 100644
index 000000000000..411a62b3ff41
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rockchip-rt5645.txt
@@ -0,0 +1,17 @@
+ROCKCHIP with RT5645/RT5650 CODECS
+
+Required properties:
+- compatible: "rockchip,rockchip-audio-rt5645"
+- rockchip,model: The user-visible name of this sound complex
+- rockchip,i2s-controller: The phandle of the Rockchip I2S controller that's
+  connected to the CODEC
+- rockchip,audio-codec: The phandle of the RT5645/RT5650 audio codec
+
+Example:
+
+sound {
+	compatible = "rockchip,rockchip-audio-rt5645";
+	rockchip,model = "ROCKCHIP-I2S";
+	rockchip,i2s-controller = <&i2s>;
+	rockchip,audio-codec = <&rt5645>;
+};
diff --git a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
new file mode 100644
index 000000000000..028fa1c82f50
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
@@ -0,0 +1,155 @@
+STMicroelectronics sti ASoC cards
+
+The sti ASoC Sound Card can be used, for all sti SoCs using internal sti-sas
+codec or external codecs.
+
+sti sound drivers allows to expose sti SoC audio interface through the
+generic ASoC simple card. For details about sound card declaration please refer to
+Documentation/devicetree/bindings/sound/simple-card.txt.
+
+1) sti-uniperiph-dai: audio dai device.
+---------------------------------------
+
+Required properties:
+  - compatible: "st,sti-uni-player" or "st,sti-uni-reader"
+
+  - st,syscfg: phandle to boot-device system configuration registers
+
+  - clock-names: name of the clocks listed in clocks property in the same order
+
+  - reg: CPU DAI IP Base address and size entries, listed  in same
+	 order than the CPU_DAI properties.
+
+  - reg-names: names of the mapped memory regions listed in regs property in
+	       the same order.
+
+  - interrupts: CPU_DAI interrupt line, listed in the same order than the
+		CPU_DAI properties.
+
+  - dma: CPU_DAI DMA controller phandle and DMA request line, listed in the same
+	 order than the CPU_DAI properties.
+
+  - dma-names: identifier string for each DMA request line in the dmas property.
+	"tx" for "st,sti-uni-player" compatibility
+	"rx" for "st,sti-uni-reader" compatibility
+
+  - version: IP version integrated in SOC.
+
+  - dai-name: DAI name that describes the IP.
+
+Required properties ("st,sti-uni-player" compatibility only):
+  - clocks: CPU_DAI IP clock source, listed in the same order than the
+	    CPU_DAI properties.
+
+  - uniperiph-id: internal SOC IP instance ID.
+
+  - IP mode: IP working mode depending on associated codec.
+	"HDMI" connected to HDMI codec IP and IEC HDMI formats.
+	"SPDIF"connected to SPDIF codec and support SPDIF formats.
+	"PCM"  PCM standard mode for I2S or TDM bus.
+
+Optional properties:
+  - pinctrl-0: defined for CPU_DAI@1 and CPU_DAI@4 to describe I2S PIOs for
+	       external codecs connection.
+
+  - pinctrl-names: should contain only one value - "default".
+
+Example:
+
+	sti_uni_player2: sti-uni-player@2 {
+		compatible = "st,sti-uni-player";
+		status = "okay";
+		#sound-dai-cells = <0>;
+		st,syscfg = <&syscfg_core>;
+		clocks = <&clk_s_d0_flexgen CLK_PCM_2>;
+		reg = <0x8D82000 0x158>;
+		interrupts = <GIC_SPI 86 IRQ_TYPE_NONE>;
+		dmas = <&fdma0 4 0 1>;
+		dai-name = "Uni Player #1 (DAC)";
+		dma-names = "tx";
+		uniperiph-id = <2>;
+		version = <5>;
+		mode = "PCM";
+	};
+
+	sti_uni_player3: sti-uni-player@3 {
+		compatible = "st,sti-uni-player";
+		status = "okay";
+		#sound-dai-cells = <0>;
+		st,syscfg = <&syscfg_core>;
+		clocks = <&clk_s_d0_flexgen CLK_SPDIFF>;
+		reg = <0x8D85000 0x158>;
+		interrupts = <GIC_SPI 89 IRQ_TYPE_NONE>;
+		dmas = <&fdma0 7 0 1>;
+		dma-names = "tx";
+		dai-name = "Uni Player #1 (PIO)";
+		uniperiph-id = <3>;
+		version = <5>;
+		mode = "SPDIF";
+	};
+
+	sti_uni_reader1: sti-uni-reader@1 {
+		compatible = "st,sti-uni-reader";
+		status = "disabled";
+		#sound-dai-cells = <0>;
+		st,syscfg = <&syscfg_core>;
+		reg = <0x8D84000 0x158>;
+		interrupts = <GIC_SPI 88 IRQ_TYPE_NONE>;
+		dmas = <&fdma0 6 0 1>;
+		dma-names = "rx";
+		dai-name = "Uni Reader #1 (HDMI RX)";
+		version = <3>;
+	};
+
+2) sti-sas-codec: internal audio codec IPs driver
+-------------------------------------------------
+
+Required properties:
+  - compatible: "st,sti<chip>-sas-codec" .
+	Should be chip "st,stih416-sas-codec" or "st,stih407-sas-codec"
+
+  - st,syscfg: phandle to boot-device system configuration registers.
+
+  - pinctrl-0: SPDIF PIO description.
+
+  - pinctrl-names: should contain only one value - "default".
+
+Example:
+	sti_sas_codec: sti-sas-codec {
+		compatible = "st,stih407-sas-codec";
+		#sound-dai-cells = <1>;
+		st,reg_audio = <&syscfg_core>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_spdif_out >;
+	};
+
+Example of audio card declaration:
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "sti audio card";
+		status = "okay";
+
+		simple-audio-card,dai-link@0 {
+			/* DAC */
+			format = "i2s";
+			dai-tdm-slot-width = <32>;
+			cpu {
+				sound-dai = <&sti_uni_player2>;
+			};
+
+			codec {
+				sound-dai = <&sti_sasg_codec 1>;
+			};
+		};
+		simple-audio-card,dai-link@1 {
+			/* SPDIF */
+			format = "left_j";
+			cpu {
+				sound-dai = <&sti_uni_player3>;
+			};
+
+			codec {
+				sound-dai = <&sti_sasg_codec 0>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
index bd99193e87b9..204b311e0400 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
@@ -10,6 +10,8 @@ Required properties:
 Optional properties:
 - cs-gpios : Specifies the gpio pis to be used for chipselects.
 - num-cs : The number of chipselects. If omitted, this will default to 4.
+- reg-io-width : The I/O register width (in bytes) implemented by this
+  device.  Supported values are 2 or 4 (the default).
 
 Child nodes as per the generic SPI binding.
 
diff --git a/Documentation/devicetree/bindings/spi/spi-ath79.txt b/Documentation/devicetree/bindings/spi/spi-ath79.txt
index f1ad9c367532..9c696fa66f81 100644
--- a/Documentation/devicetree/bindings/spi/spi-ath79.txt
+++ b/Documentation/devicetree/bindings/spi/spi-ath79.txt
@@ -3,7 +3,7 @@ Binding for Qualcomm Atheros AR7xxx/AR9xxx SPI controller
 Required properties:
 - compatible: has to be "qca,<soc-type>-spi", "qca,ar7100-spi" as fallback.
 - reg: Base address and size of the controllers memory area
-- clocks: phandle to the AHB clock.
+- clocks: phandle of the AHB clock.
 - clock-names: has to be "ahb".
 - #address-cells: <1>, as required by generic SPI binding.
 - #size-cells: <0>, also as required by generic SPI binding.
@@ -12,9 +12,9 @@ Child nodes as per the generic SPI binding.
 
 Example:
 
-	spi@1F000000 {
+	spi@1f000000 {
 		compatible = "qca,ar9132-spi", "qca,ar7100-spi";
-		reg = <0x1F000000 0x10>;
+		reg = <0x1f000000 0x10>;
 
 		clocks = <&pll 2>;
 		clock-names = "ahb";
diff --git a/Documentation/devicetree/bindings/spi/spi-davinci.txt b/Documentation/devicetree/bindings/spi/spi-davinci.txt
index 12ecfe9e3599..d1e914adcf6e 100644
--- a/Documentation/devicetree/bindings/spi/spi-davinci.txt
+++ b/Documentation/devicetree/bindings/spi/spi-davinci.txt
@@ -12,6 +12,8 @@ Required properties:
 - compatible:
 	- "ti,dm6441-spi" for SPI used similar to that on DM644x SoC family
 	- "ti,da830-spi" for SPI used similar to that on DA8xx SoC family
+	- "ti,keystone-spi" for SPI used similar to that on Keystone2 SoC
+		family
 - reg: Offset and length of SPI controller register space
 - num-cs: Number of chip selects. This includes internal as well as
 	GPIO chip selects.
diff --git a/Documentation/devicetree/bindings/spi/spi-img-spfi.txt b/Documentation/devicetree/bindings/spi/spi-img-spfi.txt
index e02fbf18c82c..494db6012d02 100644
--- a/Documentation/devicetree/bindings/spi/spi-img-spfi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-img-spfi.txt
@@ -21,6 +21,7 @@ Required properties:
 Optional properties:
 - img,supports-quad-mode: Should be set if the interface supports quad mode
   SPI transfers.
+- spfi-max-frequency: Maximum speed supported by the spfi block.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
new file mode 100644
index 000000000000..dcefc438272f
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
@@ -0,0 +1,51 @@
+Binding for MTK SPI controller
+
+Required properties:
+- compatible: should be one of the following.
+    - mediatek,mt8173-spi: for mt8173 platforms
+    - mediatek,mt8135-spi: for mt8135 platforms
+    - mediatek,mt6589-spi: for mt6589 platforms
+
+- #address-cells: should be 1.
+
+- #size-cells: should be 0.
+
+- reg: Address and length of the register set for the device
+
+- interrupts: Should contain spi interrupt
+
+- clocks: phandles to input clocks.
+  The first should be <&topckgen CLK_TOP_SPI_SEL>.
+  The second should be one of the following.
+   -  <&clk26m>: specify parent clock 26MHZ.
+   -  <&topckgen CLK_TOP_SYSPLL3_D2>: specify parent clock 109MHZ.
+				      It's the default one.
+   -  <&topckgen CLK_TOP_SYSPLL4_D2>: specify parent clock 78MHZ.
+   -  <&topckgen CLK_TOP_UNIVPLL2_D4>: specify parent clock 104MHZ.
+   -  <&topckgen CLK_TOP_UNIVPLL1_D8>: specify parent clock 78MHZ.
+
+- clock-names: shall be "spi-clk" for the controller clock, and
+  "parent-clk" for the parent clock.
+
+Optional properties:
+- mediatek,pad-select: specify which pins group(ck/mi/mo/cs) spi
+  controller used, this value should be 0~3, only required for MT8173.
+    0: specify GPIO69,70,71,72 for spi pins.
+    1: specify GPIO102,103,104,105 for spi pins.
+    2: specify GPIO128,129,130,131 for spi pins.
+    3: specify GPIO5,6,7,8 for spi pins.
+
+Example:
+
+- SoC Specific Portion:
+spi: spi@1100a000 {
+	compatible = "mediatek,mt8173-spi";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	reg = <0 0x1100a000 0 0x1000>;
+	interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_LOW>;
+	clocks = <&topckgen CLK_TOP_SPI_SEL>, <&topckgen CLK_TOP_SYSPLL3_D2>;
+	clock-names = "spi-clk", "parent-clk";
+	mediatek,pad-select = <0>;
+	status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-xlp.txt b/Documentation/devicetree/bindings/spi/spi-xlp.txt
new file mode 100644
index 000000000000..40e82d51efec
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-xlp.txt
@@ -0,0 +1,39 @@
+SPI Master controller for Netlogic XLP MIPS64 SOCs
+==================================================
+
+Currently this SPI controller driver is supported for the following
+Netlogic XLP SoCs:
+	XLP832, XLP316, XLP208, XLP980, XLP532
+
+Required properties:
+- compatible		: Should be "netlogic,xlp832-spi".
+- #address-cells	: Number of cells required to define a chip select address
+			  on the SPI bus.
+- #size-cells		: Should be zero.
+- reg			: Should contain register location and length.
+- clocks		: Phandle of the spi clock
+- interrupts		: Interrupt number used by this controller.
+- interrupt-parent	: Phandle of the parent interrupt controller.
+
+SPI slave nodes must be children of the SPI master node and can contain
+properties described in Documentation/devicetree/bindings/spi/spi-bus.txt.
+
+Example:
+
+	spi: xlp_spi@3a100 {
+		compatible = "netlogic,xlp832-spi";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0 0x3a100 0x100>;
+		clocks = <&spi_clk>;
+		interrupts = <34>;
+		interrupt-parent = <&pic>;
+
+		spi_nor@1 {
+			compatible = "spansion,s25sl12801";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <1>;	/* Chip Select */
+			spi-max-frequency = <40000000>;
+		};
+};
diff --git a/Documentation/devicetree/bindings/staging/iio/adc/mxs-lradc.txt b/Documentation/devicetree/bindings/staging/iio/adc/mxs-lradc.txt
index 307537787574..555fb117d4fa 100644
--- a/Documentation/devicetree/bindings/staging/iio/adc/mxs-lradc.txt
+++ b/Documentation/devicetree/bindings/staging/iio/adc/mxs-lradc.txt
@@ -1,4 +1,4 @@
-* Freescale i.MX28 LRADC device driver
+* Freescale MXS LRADC device driver
 
 Required properties:
 - compatible: Should be "fsl,imx23-lradc" for i.MX23 SoC and "fsl,imx28-lradc"
diff --git a/Documentation/devicetree/bindings/timer/img,pistachio-gptimer.txt b/Documentation/devicetree/bindings/timer/img,pistachio-gptimer.txt
new file mode 100644
index 000000000000..7afce80bf6a0
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/img,pistachio-gptimer.txt
@@ -0,0 +1,28 @@
+* Pistachio general-purpose timer based clocksource
+
+Required properties:
+ - compatible: "img,pistachio-gptimer".
+ - reg: Address range of the timer registers.
+ - interrupts: An interrupt for each of the four timers
+ - clocks: Should contain a clock specifier for each entry in clock-names
+ - clock-names: Should contain the following entries:
+                "sys", interface clock
+                "slow", slow counter clock
+                "fast", fast counter clock
+ - img,cr-periph: Must contain a phandle to the peripheral control
+		  syscon node.
+
+Example:
+	timer: timer@18102000 {
+		compatible = "img,pistachio-gptimer";
+		reg = <0x18102000 0x100>;
+		interrupts = <GIC_SHARED 60 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SHARED 61 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SHARED 62 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SHARED 63 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clk_periph PERIPH_CLK_COUNTER_FAST>,
+		         <&clk_periph PERIPH_CLK_COUNTER_SLOW>,
+			 <&cr_periph SYS_CLK_TIMER>;
+		clock-names = "fast", "slow", "sys";
+		img,cr-periph = <&cr_periph>;
+	};
diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
index 7c4408ff4b83..53a3029b7589 100644
--- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
+++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
@@ -2,7 +2,11 @@ Mediatek MT6577, MT6572 and MT6589 Timers
 ---------------------------------------
 
 Required properties:
-- compatible: Should be "mediatek,mt6577-timer"
+- compatible should contain:
+	* "mediatek,mt6589-timer" for MT6589 compatible timers
+	* "mediatek,mt6580-timer" for MT6580 compatible timers
+	* "mediatek,mt6577-timer" for all compatible timers (MT6589, MT6580,
+		MT6577)
 - reg: Should contain location and length for timers register.
 - clocks: Clocks driving the timer hardware. This list should include two
 	clocks. The order is system clock and as second clock the RTC clock.
diff --git a/Documentation/devicetree/bindings/timer/st,stih407-lpc b/Documentation/devicetree/bindings/timer/st,stih407-lpc
new file mode 100644
index 000000000000..72acb487b856
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/st,stih407-lpc
@@ -0,0 +1,28 @@
+STMicroelectronics Low Power Controller (LPC) - Clocksource
+===========================================================
+
+LPC currently supports Watchdog OR Real Time Clock OR Clocksource
+functionality.
+
+[See: ../watchdog/st_lpc_wdt.txt for Watchdog options]
+[See: ../rtc/rtc-st-lpc.txt for RTC options]
+
+Required properties
+
+- compatible   : Must be: "st,stih407-lpc"
+- reg          : LPC registers base address + size
+- interrupts   : LPC interrupt line number and associated flags
+- clocks       : Clock used by LPC device (See: ../clock/clock-bindings.txt)
+- st,lpc-mode  : The LPC can run either one of three modes:
+                  ST_LPC_MODE_RTC    [0]
+                  ST_LPC_MODE_WDT    [1]
+                  ST_LPC_MODE_CLKSRC [2]
+		 One (and only one) mode must be selected.
+
+Example:
+       lpc@fde05000 {
+               compatible      = "st,stih407-lpc";
+               reg             = <0xfde05000 0x1000>;
+               clocks          = <&clk_s_d3_flexgen CLK_LPC_0>;
+               st,lpc-mode     = <ST_LPC_MODE_CLKSRC>;
+       };
diff --git a/Documentation/devicetree/bindings/usb/allwinner,sun4i-a10-musb.txt b/Documentation/devicetree/bindings/usb/allwinner,sun4i-a10-musb.txt
new file mode 100644
index 000000000000..862cd7c79805
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/allwinner,sun4i-a10-musb.txt
@@ -0,0 +1,29 @@
+Allwinner sun4i A10 musb DRC/OTG controller
+-------------------------------------------
+
+Required properties:
+ - compatible      : "allwinner,sun4i-a10-musb", "allwinner,sun6i-a31-musb"
+                     or "allwinner,sun8i-a33-musb"
+ - reg             : mmio address range of the musb controller
+ - clocks          : clock specifier for the musb controller ahb gate clock
+ - reset           : reset specifier for the ahb reset (A31 and newer only)
+ - interrupts      : interrupt to which the musb controller is connected
+ - interrupt-names : must be "mc"
+ - phys            : phy specifier for the otg phy
+ - phy-names       : must be "usb"
+ - dr_mode         : Dual-Role mode must be "host" or "otg"
+ - extcon          : extcon specifier for the otg phy
+
+Example:
+
+	usb_otg: usb@01c13000 {
+		compatible = "allwinner,sun4i-a10-musb";
+		reg = <0x01c13000 0x0400>;
+		clocks = <&ahb_gates 0>;
+		interrupts = <38>;
+		interrupt-names = "mc";
+		phys = <&usbphy 0>;
+		phy-names = "usb";
+		extcon = <&usbphy 0>;
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
index 553e2fae3a76..d71ef07bca5d 100644
--- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
@@ -30,6 +30,21 @@ Optional properties:
   argument that indicate usb controller index
 - disable-over-current: (FSL only) disable over current detect
 - external-vbus-divider: (FSL only) enables off-chip resistor divider for Vbus
+- itc-setting: interrupt threshold control register control, the setting
+  should be aligned with ITC bits at register USBCMD.
+- ahb-burst-config: it is vendor dependent, the required value should be
+  aligned with AHBBRST at SBUSCFG, the range is from 0x0 to 0x7. This
+  property is used to change AHB burst configuration, check the chipidea
+  spec for meaning of each value. If this property is not existed, it
+  will use the reset value.
+- tx-burst-size-dword: it is vendor dependent, the tx burst size in dword
+  (4 bytes), This register represents the maximum length of a the burst
+  in 32-bit words while moving data from system memory to the USB
+  bus, changing this value takes effect only the SBUSCFG.AHBBRST is 0.
+- rx-burst-size-dword: it is vendor dependent, the rx burst size in dword
+  (4 bytes), This register represents the maximum length of a the burst
+  in 32-bit words while moving data from the USB bus to system memory,
+  changing this value takes effect only the SBUSCFG.AHBBRST is 0.
 
 Example:
 
@@ -41,4 +56,9 @@ Example:
 		phys = <&usb_phy0>;
 		phy-names = "usb-phy";
 		vbus-supply = <&reg_usb0_vbus>;
+		gadget-itc-setting = <0x4>; /* 4 micro-frames */
+		 /* Incremental burst of unspecified length */
+		ahb-burst-config = <0x0>;
+		tx-burst-size-dword = <0x10>; /* 64 bytes */
+		rx-burst-size-dword = <0x10>;
 	};
diff --git a/Documentation/devicetree/bindings/usb/generic.txt b/Documentation/devicetree/bindings/usb/generic.txt
index 477d5bb5e51c..bba825711873 100644
--- a/Documentation/devicetree/bindings/usb/generic.txt
+++ b/Documentation/devicetree/bindings/usb/generic.txt
@@ -11,6 +11,19 @@ Optional properties:
 			"peripheral" and "otg". In case this attribute isn't
 			passed via DT, USB DRD controllers should default to
 			OTG.
+ - otg-rev: tells usb driver the release number of the OTG and EH supplement
+			with which the device and its descriptors are compliant,
+			in binary-coded decimal (i.e. 2.0 is 0200H). This
+			property is used if any real OTG features(HNP/SRP/ADP)
+			is enabled, if ADP is required, otg-rev should be
+			0x0200 or above.
+ - hnp-disable: tells OTG controllers we want to disable OTG HNP, normally HNP
+			is the basic function of real OTG except you want it
+			to be a srp-capable only B device.
+ - srp-disable: tells OTG controllers we want to disable OTG SRP, SRP is
+			optional for OTG device.
+ - adp-disable: tells OTG controllers we want to disable OTG ADP, ADP is
+			optional for OTG device.
 
 This is an attribute to a USB controller such as:
 
@@ -21,4 +34,6 @@ dwc3@4a030000 {
 	usb-phy = <&usb2_phy>, <&usb3,phy>;
 	maximum-speed = "super-speed";
 	dr_mode = "otg";
+	otg-rev = <0x0200>;
+	adp-disable;
 };
diff --git a/Documentation/devicetree/bindings/usb/msm-hsusb.txt b/Documentation/devicetree/bindings/usb/msm-hsusb.txt
index bd8d9e753029..8654a3ec23e4 100644
--- a/Documentation/devicetree/bindings/usb/msm-hsusb.txt
+++ b/Documentation/devicetree/bindings/usb/msm-hsusb.txt
@@ -52,6 +52,10 @@ Required properties:
 Optional properties:
 - dr_mode:      One of "host", "peripheral" or "otg". Defaults to "otg"
 
+- switch-gpio:  A phandle + gpio-specifier pair. Some boards are using Dual
+                SPDT USB Switch, witch is cotrolled by GPIO to de/multiplex
+                D+/D- USB lines between connectors.
+
 - qcom,phy-init-sequence: PHY configuration sequence values. This is related to Device
                 Mode Eye Diagram test. Start address at which these values will be
                 written is ULPI_EXT_VENDOR_SPECIFIC. Value of -1 is reserved as
diff --git a/Documentation/devicetree/bindings/usb/qcom,usb-8x16-phy.txt b/Documentation/devicetree/bindings/usb/qcom,usb-8x16-phy.txt
new file mode 100644
index 000000000000..2cb2168cef41
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/qcom,usb-8x16-phy.txt
@@ -0,0 +1,76 @@
+Qualcomm's APQ8016/MSM8916 USB transceiver controller
+
+- compatible:
+    Usage: required
+    Value type: <string>
+    Definition: Should contain "qcom,usb-8x16-phy".
+
+- reg:
+    Usage: required
+    Value type: <prop-encoded-array>
+    Definition: USB PHY base address and length of the register map
+
+- clocks:
+    Usage: required
+    Value type: <prop-encoded-array>
+    Definition: See clock-bindings.txt section "consumers". List of
+                two clock specifiers for interface and core controller
+                clocks.
+
+- clock-names:
+    Usage: required
+    Value type: <string>
+    Definition: Must contain "iface" and "core" strings.
+
+- vddcx-supply:
+    Usage: required
+    Value type: <phandle>
+    Definition: phandle to the regulator VDCCX supply node.
+
+- v1p8-supply:
+    Usage: required
+    Value type: <phandle>
+    Definition: phandle to the regulator 1.8V supply node.
+
+- v3p3-supply:
+    Usage: required
+    Value type: <phandle>
+    Definition: phandle to the regulator 3.3V supply node.
+
+- resets:
+    Usage: required
+    Value type: <prop-encoded-array>
+    Definition: See reset.txt section "consumers". PHY reset specifier.
+
+- reset-names:
+    Usage: required
+    Value type: <string>
+    Definition: Must contain "phy" string.
+
+- switch-gpio:
+    Usage: optional
+    Value type: <prop-encoded-array>
+    Definition: Some boards are using Dual SPDT USB Switch, witch is
+                controlled by GPIO to de/multiplex D+/D- USB lines
+                between connectors.
+
+Example:
+	usb_phy: phy@78d9000 {
+		compatible = "qcom,usb-8x16-phy";
+		reg = <0x78d9000 0x400>;
+
+		vddcx-supply = <&pm8916_s1_corner>;
+		v1p8-supply = <&pm8916_l7>;
+		v3p3-supply = <&pm8916_l13>;
+
+		clocks = <&gcc GCC_USB_HS_AHB_CLK>,
+			     <&gcc GCC_USB_HS_SYSTEM_CLK>;
+		clock-names = "iface", "core";
+
+		resets = <&gcc GCC_USB2A_PHY_BCR>;
+		reset-names = "phy";
+
+		// D+/D- lines: 1 - Routed to HUB, 0 - Device connector
+		switch-gpio = <&pm8916_gpios 4 GPIO_ACTIVE_HIGH>;
+	};
+
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index d444757c4d9e..ac5f0c34ae00 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -46,6 +46,7 @@ chipone		ChipOne
 chipspark	ChipSPARK
 chrp	Common Hardware Reference Platform
 chunghwa	Chunghwa Picture Tubes Ltd.
+ciaa	Computadora Industrial Abierta Argentina
 cirrus	Cirrus Logic, Inc.
 cloudengines	Cloud Engines, Inc.
 cnm	Chips&Media, Inc.
@@ -54,6 +55,7 @@ cortina	Cortina Systems, Inc.
 cosmic	Cosmic Circuits
 crystalfontz	Crystalfontz America, Inc.
 cubietech	Cubietech, Ltd.
+cypress	Cypress Semiconductor Corporation
 dallas	Maxim Integrated Products (formerly Dallas Semiconductor)
 davicom	DAVICOM Semiconductor, Inc.
 delta	Delta Electronics, Inc.
@@ -110,8 +112,10 @@ ingenic	Ingenic Semiconductor
 innolux	Innolux Corporation
 intel	Intel Corporation
 intercontrol	Inter Control Group
+invensense	InvenSense Inc.
 isee	ISEE 2007 S.L.
 isil	Intersil
+jedec	JEDEC Solid State Technology Association
 karo	Ka-Ro electronics GmbH
 keymile	Keymile GmbH
 kinetic Kinetic Technologies
@@ -135,21 +139,27 @@ mitsubishi	Mitsubishi Electric Corporation
 mosaixtech	Mosaix Technologies, Inc.
 moxa	Moxa
 mpl	MPL AG
+msi	Micro-Star International Co. Ltd.
 mti	Imagination Technologies Ltd. (formerly MIPS Technologies Inc.)
 mundoreader	Mundo Reader S.L.
 murata	Murata Manufacturing Co., Ltd.
 mxicy	Macronix International Co., Ltd.
 national	National Semiconductor
+nec	NEC LCD Technologies, Ltd.
 neonode		Neonode Inc.
 netgear	NETGEAR
 netlogic	Broadcom Corporation (formerly NetLogic Microsystems)
+netxeon		Shenzhen Netxeon Technology CO., LTD
 newhaven	Newhaven Display International
 nintendo	Nintendo
 nokia	Nokia
+nuvoton	Nuvoton Technology Corporation
 nvidia	NVIDIA
 nxp	NXP Semiconductors
+okaya	Okaya Electric America, Inc.
 onnn	ON Semiconductor Corp.
 opencores	OpenCores.org
+option	Option NV
 ortustech	Ortus Technology Co., Ltd.
 ovti	OmniVision Technologies
 panasonic	Panasonic Corporation
@@ -181,6 +191,7 @@ sbs	Smart Battery System
 schindler	Schindler
 seagate	Seagate Technology PLC
 semtech	Semtech Corporation
+sharp	Sharp Corporation
 sil	Silicon Image
 silabs	Silicon Laboratories
 siliconmitus	Silicon Mitus, Inc.
diff --git a/Documentation/devicetree/bindings/leds/leds-pm8941-wled.txt b/Documentation/devicetree/bindings/video/backlight/pm8941-wled.txt
index a85a964d61f5..424f8444a6cd 100644
--- a/Documentation/devicetree/bindings/leds/leds-pm8941-wled.txt
+++ b/Documentation/devicetree/bindings/video/backlight/pm8941-wled.txt
@@ -5,10 +5,7 @@ Required properties:
 - reg: slave address
 
 Optional properties:
-- label: The label for this led
-  See Documentation/devicetree/bindings/leds/common.txt
-- linux,default-trigger: Default trigger assigned to the LED
-  See Documentation/devicetree/bindings/leds/common.txt
+- label: The name of the backlight device
 - qcom,cs-out: bool; enable current sink output
 - qcom,cabc: bool; enable content adaptive backlight control
 - qcom,ext-gen: bool; use externally generated modulator signal to dim
diff --git a/Documentation/devicetree/bindings/video/fsl,dcu.txt b/Documentation/devicetree/bindings/video/fsl,dcu.txt
new file mode 100644
index 000000000000..ebf1be9ae393
--- /dev/null
+++ b/Documentation/devicetree/bindings/video/fsl,dcu.txt
@@ -0,0 +1,22 @@
+Device Tree bindings for Freescale DCU DRM Driver
+
+Required properties:
+- compatible:		Should be one of
+	* "fsl,ls1021a-dcu".
+	* "fsl,vf610-dcu".
+
+- reg:			Address and length of the register set for dcu.
+- clocks:		From common clock binding: handle to dcu clock.
+- clock-names:		From common clock binding: Shall be "dcu".
+- big-endian		Boolean property, LS1021A DCU registers are big-endian.
+- fsl,panel:		The phandle to panel node.
+
+Examples:
+dcu: dcu@2ce0000 {
+	compatible = "fsl,ls1021a-dcu";
+	reg = <0x0 0x2ce0000 0x0 0x10000>;
+	clocks = <&platform_clk 0>;
+	clock-names = "dcu";
+	big-endian;
+	fsl,panel = <&panel>;
+};
diff --git a/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt b/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt
index a4d869744f59..86fa6de1019b 100644
--- a/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt
@@ -6,6 +6,7 @@ Required properties:
 - compatible: must be "atmel,at91sam9260-wdt".
 - reg: physical base address of the controller and length of memory mapped
   region.
+- clocks: phandle to input clock.
 
 Optional properties:
 - timeout-sec: contains the watchdog timeout in seconds.
@@ -39,6 +40,7 @@ Example:
 		compatible = "atmel,at91sam9260-wdt";
 		reg = <0xfffffd40 0x10>;
 		interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+		clocks = <&clk32k>;
 		timeout-sec = <15>;
 		atmel,watchdog-type = "hardware";
 		atmel,reset-type = "all";
diff --git a/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt b/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt
index 388c88a01222..039c5ca45577 100644
--- a/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt
@@ -1,9 +1,11 @@
 STMicroelectronics Low Power Controller (LPC) - Watchdog
 ========================================================
 
-LPC currently supports Watchdog OR Real Time Clock functionality.
+LPC currently supports Watchdog OR Real Time Clock OR Clocksource
+functionality.
 
 [See: ../rtc/rtc-st-lpc.txt for RTC options]
+[See: ../timer/st,stih407-lpc for Clocksource options]
 
 Required properties
 
@@ -12,9 +14,11 @@ Required properties
 - reg		: LPC registers base address + size
 - interrupts    : LPC interrupt line number and associated flags
 - clocks	: Clock used by LPC device (See: ../clock/clock-bindings.txt)
-- st,lpc-mode	: The LPC can run either one of two modes ST_LPC_MODE_RTC [0] or
-		  ST_LPC_MODE_WDT [1].  One (and only one) mode must be
-		  selected.
+- st,lpc-mode	: The LPC can run either one of three modes:
+                  ST_LPC_MODE_RTC    [0]
+                  ST_LPC_MODE_WDT    [1]
+                  ST_LPC_MODE_CLKSRC [2]
+		 One (and only one) mode must be selected.
 
 Required properties [watchdog mode]
 
diff --git a/Documentation/dmaengine/provider.txt b/Documentation/dmaengine/provider.txt
index ca67b0f04c6e..67d4ce4df109 100644
--- a/Documentation/dmaengine/provider.txt
+++ b/Documentation/dmaengine/provider.txt
@@ -345,12 +345,29 @@ where to put them)
       that abstracts it away.
 
   * DMA_CTRL_ACK
-    - If set, the transfer can be reused after being completed.
-    - There is a guarantee the transfer won't be freed until it is acked
-      by async_tx_ack().
+    - If clear, the descriptor cannot be reused by provider until the
+      client acknowledges receipt, i.e. has has a chance to establish any
+      dependency chains
+    - This can be acked by invoking async_tx_ack()
+    - If set, does not mean descriptor can be reused
+
+  * DMA_CTRL_REUSE
+    - If set, the descriptor can be reused after being completed. It should
+      not be freed by provider if this flag is set.
+    - The descriptor should be prepared for reuse by invoking
+      dmaengine_desc_set_reuse() which will set DMA_CTRL_REUSE.
+    - dmaengine_desc_set_reuse() will succeed only when channel support
+      reusable descriptor as exhibited by capablities
     - As a consequence, if a device driver wants to skip the dma_map_sg() and
       dma_unmap_sg() in between 2 transfers, because the DMA'd data wasn't used,
       it can resubmit the transfer right after its completion.
+    - Descriptor can be freed in few ways
+	- Clearing DMA_CTRL_REUSE by invoking dmaengine_desc_clear_reuse()
+	  and submitting for last txn
+	- Explicitly invoking dmaengine_desc_free(), this can succeed only
+	  when DMA_CTRL_REUSE is already set
+	- Terminating the channel
+
 
 General Design Notes
 --------------------
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index c7d49b885559..3fa450881ecb 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -93,7 +93,7 @@ Evolution (GUI)
 Some people use this successfully for patches.
 
 When composing mail select: Preformat
-  from Format->Heading->Preformatted (Ctrl-7)
+  from Format->Paragraph Style->Preformatted (Ctrl-7)
   or the toolbar
 
 Then use:
diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 4cf1a2a6bd72..415484f3d59a 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -15,6 +15,10 @@ o fail_page_alloc
 
   injects page allocation failures. (alloc_pages(), get_free_pages(), ...)
 
+o fail_futex
+
+  injects futex deadlock and uaddr fault errors.
+
 o fail_make_request
 
   injects disk IO errors on devices permitted by setting
@@ -113,6 +117,12 @@ configuration of fault-injection capabilities.
 	specifies the minimum page allocation order to be injected
 	failures.
 
+- /sys/kernel/debug/fail_futex/ignore-private:
+
+	Format: { 'Y' | 'N' }
+	default is 'N', setting it to 'Y' will disable failure injections
+	when dealing with private (address space) futexes.
+
 o Boot option
 
 In order to inject faults while debugfs is not available (early boot time),
@@ -121,6 +131,7 @@ use the boot option:
 	failslab=
 	fail_page_alloc=
 	fail_make_request=
+	fail_futex=
 	mmc_core.fail_request=<interval>,<probability>,<space>,<times>
 
 How to add new fault injection capability
diff --git a/Documentation/fb/sm712fb.txt b/Documentation/fb/sm712fb.txt
new file mode 100644
index 000000000000..c388442edf51
--- /dev/null
+++ b/Documentation/fb/sm712fb.txt
@@ -0,0 +1,31 @@
+What is sm712fb?
+=================
+
+This is a graphics framebuffer driver for Silicon Motion SM712 based processors.
+
+How to use it?
+==============
+
+Switching modes is done using the video=sm712fb:... boot parameter.
+
+If you want, for example, enable a resolution of 1280x1024x24bpp you should
+pass to the kernel this command line: "video=sm712fb:0x31B".
+
+You should not compile-in vesafb.
+
+Currently supported video modes are:
+
+[Graphic modes]
+
+bpp | 640x480  800x600  1024x768  1280x1024
+----+--------------------------------------------
+  8 | 0x301    0x303    0x305    0x307
+ 16 | 0x311    0x314    0x317    0x31A
+ 24 | 0x312    0x315    0x318    0x31B
+
+Missing Features
+================
+(alias TODO list)
+
+	* 2D acceleratrion
+	* dual-head support
diff --git a/Documentation/features/debug/uprobes/arch-support.txt b/Documentation/features/debug/uprobes/arch-support.txt
index 4efe36c3ace9..d605c3fc38fd 100644
--- a/Documentation/features/debug/uprobes/arch-support.txt
+++ b/Documentation/features/debug/uprobes/arch-support.txt
@@ -22,7 +22,7 @@
     |        m68k: | TODO |
     |       metag: | TODO |
     |  microblaze: | TODO |
-    |        mips: | TODO |
+    |        mips: |  ok  |
     |     mn10300: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
index bea800910342..76d39d66a5d7 100644
--- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -32,7 +32,7 @@
     |       score: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
-    |        tile: | TODO |
+    |        tile: |  ok  |
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
new file mode 100644
index 000000000000..261b92e2fb1a
--- /dev/null
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          batch-unmap-tlb-flush
+#         Kconfig:       ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+#         description:   arch supports deferral of TLB flush until multiple pages are unmapped
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: |  ..  |
+    |    blackfin: | TODO |
+    |         c6x: |  ..  |
+    |        cris: |  ..  |
+    |         frv: |  ..  |
+    |       h8300: |  ..  |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: |  ..  |
+    |       metag: | TODO |
+    |  microblaze: |  ..  |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: |  ..  |
+    |    openrisc: |  ..  |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: |  ..  |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: |  ..  |
+    |   unicore32: |  ..  |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt
index d11cc2f8077b..c772b47e7ef0 100644
--- a/Documentation/filesystems/btrfs.txt
+++ b/Documentation/filesystems/btrfs.txt
@@ -61,7 +61,7 @@ Options with (*) are default options and will not show in the mount options.
 
 	check_int enables the integrity checker module, which examines all
 	block write requests to ensure on-disk consistency, at a large
-	memory and CPU cost.  
+	memory and CPU cost.
 
 	check_int_data includes extent data in the integrity checks, and
 	implies the check_int option.
@@ -113,7 +113,7 @@ Options with (*) are default options and will not show in the mount options.
 	Disable/enable debugging option to be more verbose in some ENOSPC conditions.
 
   fatal_errors=<action>
-	Action to take when encountering a fatal error: 
+	Action to take when encountering a fatal error:
 	  "bug" - BUG() on a fatal error.  This is the default.
 	  "panic" - panic() on a fatal error.
 
@@ -132,10 +132,10 @@ Options with (*) are default options and will not show in the mount options.
 
   max_inline=<bytes>
 	Specify the maximum amount of space, in bytes, that can be inlined in
-	a metadata B-tree leaf.  The value is specified in bytes, optionally 
+	a metadata B-tree leaf.  The value is specified in bytes, optionally
 	with a K, M, or G suffix, case insensitive.  In practice, this value
 	is limited by the root sector size, with some space unavailable due
-	to leaf headers.  For a 4k sectorsize, max inline data is ~3900 bytes.
+	to leaf headers.  For a 4k sector size, max inline data is ~3900 bytes.
 
   metadata_ratio=<value>
 	Specify that 1 metadata chunk should be allocated after every <value>
@@ -170,7 +170,7 @@ Options with (*) are default options and will not show in the mount options.
 
   recovery
 	Enable autorecovery attempts if a bad tree root is found at mount time.
-	Currently this scans a list of several previous tree roots and tries to 
+	Currently this scans a list of several previous tree roots and tries to
 	use the first readable.
 
   rescan_uuid_tree
@@ -194,7 +194,7 @@ Options with (*) are default options and will not show in the mount options.
   ssd_spread
 	Options to control ssd allocation schemes.  By default, BTRFS will
 	enable or disable ssd allocation heuristics depending on whether a
-	rotational or nonrotational disk is in use.  The ssd and nossd options
+	rotational or non-rotational disk is in use.  The ssd and nossd options
 	can override this autodetection.
 
 	The ssd_spread mount option attempts to allocate into big chunks
@@ -216,13 +216,13 @@ Options with (*) are default options and will not show in the mount options.
 	This allows mounting of subvolumes which are not in the root of the mounted
 	filesystem.
 	You can use "btrfs subvolume show " to see the object ID for a subvolume.
-	
+
   thread_pool=<number>
 	The number of worker threads to allocate.  The default number is equal
 	to the number of CPUs + 2, or 8, whichever is smaller.
 
   user_subvol_rm_allowed
-	Allow subvolumes to be deleted by a non-root user. Use with caution. 
+	Allow subvolumes to be deleted by a non-root user. Use with caution.
 
 MAILING LIST
 ============
diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt
index 88ab81c79109..463f595733e8 100644
--- a/Documentation/filesystems/debugfs.txt
+++ b/Documentation/filesystems/debugfs.txt
@@ -51,6 +51,17 @@ operations should be provided; others can be included as needed.  Again,
 the return value will be a dentry pointer to the created file, NULL for
 error, or ERR_PTR(-ENODEV) if debugfs support is missing.
 
+Create a file with an initial size, the following function can be used
+instead:
+
+    struct dentry *debugfs_create_file_size(const char *name, umode_t mode,
+				struct dentry *parent, void *data,
+				const struct file_operations *fops,
+				loff_t file_size);
+
+file_size is the initial file size. The other parameters are the same
+as the function debugfs_create_file.
+
 In a number of cases, the creation of a set of file operations is not
 actually necessary; the debugfs code provides a number of helper functions
 for simple situations.  Files containing a single integer value can be
@@ -100,6 +111,14 @@ A read on the resulting file will yield either Y (for non-zero values) or
 N, followed by a newline.  If written to, it will accept either upper- or
 lower-case values, or 1 or 0.  Any other input will be silently ignored.
 
+Also, atomic_t values can be placed in debugfs with:
+
+    struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode,
+				struct dentry *parent, atomic_t *value)
+
+A read of this file will get atomic_t values, and a write of this file
+will set atomic_t values.
+
 Another option is exporting a block of arbitrary binary data, with
 this structure and function:
 
@@ -147,6 +166,27 @@ The "base" argument may be 0, but you may want to build the reg32 array
 using __stringify, and a number of register names (macros) are actually
 byte offsets over a base for the register block.
 
+If you want to dump an u32 array in debugfs, you can create file with:
+
+    struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+			struct dentry *parent,
+			u32 *array, u32 elements);
+
+The "array" argument provides data, and the "elements" argument is
+the number of elements in the array. Note: Once array is created its
+size can not be changed.
+
+There is a helper function to create device related seq_file:
+
+   struct dentry *debugfs_create_devm_seqfile(struct device *dev,
+				const char *name,
+				struct dentry *parent,
+				int (*read_fn)(struct seq_file *s,
+					void *data));
+
+The "dev" argument is the device related to this debugfs file, and
+the "read_fn" is a function pointer which to be called to print the
+seq_file content.
 
 There are a couple of other directory-oriented helper functions:
 
diff --git a/Documentation/filesystems/ext2.txt b/Documentation/filesystems/ext2.txt
index b9714569e472..55755395d3dc 100644
--- a/Documentation/filesystems/ext2.txt
+++ b/Documentation/filesystems/ext2.txt
@@ -360,8 +360,8 @@ and are copied into the filesystem.  If a transaction is incomplete at
 the time of the crash, then there is no guarantee of consistency for
 the blocks in that transaction so they are discarded (which means any
 filesystem changes they represent are also lost).
-Check Documentation/filesystems/ext3.txt if you want to read more about
-ext3 and journaling.
+Check Documentation/filesystems/ext4.txt if you want to read more about
+ext4 and journaling.
 
 References
 ==========
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 7ed0d17d6721..58758fbef9e0 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -6,210 +6,7 @@ Ext3 was originally released in September 1999. Written by Stephen Tweedie
 for the 2.2 branch, and ported to 2.4 kernels by Peter Braam, Andreas Dilger,
 Andrew Morton, Alexander Viro, Ted Ts'o and Stephen Tweedie.
 
-Ext3 is the ext2 filesystem enhanced with journalling capabilities.
+Ext3 is the ext2 filesystem enhanced with journalling capabilities. The
+filesystem is a subset of ext4 filesystem so use ext4 driver for accessing
+ext3 filesystems.
 
-Options
-=======
-
-When mounting an ext3 filesystem, the following option are accepted:
-(*) == default
-
-ro			Mount filesystem read only. Note that ext3 will replay
-			the journal (and thus write to the partition) even when
-			mounted "read only". Mount options "ro,noload" can be
-			used to prevent writes to the filesystem.
-
-journal=update		Update the ext3 file system's journal to the current
-			format.
-
-journal=inum		When a journal already exists, this option is ignored.
-			Otherwise, it specifies the number of the inode which
-			will represent the ext3 file system's journal file.
-
-journal_path=path
-journal_dev=devnum	When the external journal device's major/minor numbers
-			have changed, these options allow the user to specify
-			the new journal location.  The journal device is
-			identified through either its new major/minor numbers
-			encoded in devnum, or via a path to the device.
-
-norecovery		Don't load the journal on mounting. Note that this forces
-noload			mount of inconsistent filesystem, which can lead to
-			various problems.
-
-data=journal		All data are committed into the journal prior to being
-			written into the main file system.
-
-data=ordered	(*)	All data are forced directly out to the main file
-			system prior to its metadata being committed to the
-			journal.
-
-data=writeback		Data ordering is not preserved, data may be written
-			into the main file system after its metadata has been
-			committed to the journal.
-
-commit=nrsec	(*)	Ext3 can be told to sync all its data and metadata
-			every 'nrsec' seconds. The default value is 5 seconds.
-			This means that if you lose your power, you will lose
-			as much as the latest 5 seconds of work (your
-			filesystem will not be damaged though, thanks to the
-			journaling).  This default value (or any low value)
-			will hurt performance, but it's good for data-safety.
-			Setting it to 0 will have the same effect as leaving
-			it at the default (5 seconds).
-			Setting it to very large values will improve
-			performance.
-
-barrier=<0|1(*)>	This enables/disables the use of write barriers in
-barrier	(*)		the jbd code.  barrier=0 disables, barrier=1 enables.
-nobarrier		This also requires an IO stack which can support
-			barriers, and if jbd gets an error on a barrier
-			write, it will disable again with a warning.
-			Write barriers enforce proper on-disk ordering
-			of journal commits, making volatile disk write caches
-			safe to use, at some performance penalty.  If
-			your disks are battery-backed in one way or another,
-			disabling barriers may safely improve performance.
-			The mount options "barrier" and "nobarrier" can
-			also be used to enable or disable barriers, for
-			consistency with other ext3 mount options.
-
-user_xattr		Enables Extended User Attributes.  Additionally, you
-			need to have extended attribute support enabled in the
-			kernel configuration (CONFIG_EXT3_FS_XATTR).  See the
-			attr(5) manual page and http://acl.bestbits.at/ to
-			learn more about extended attributes.
-
-nouser_xattr		Disables Extended User Attributes.
-
-acl			Enables POSIX Access Control Lists support.
-			Additionally, you need to have ACL support enabled in
-			the kernel configuration (CONFIG_EXT3_FS_POSIX_ACL).
-			See the acl(5) manual page and http://acl.bestbits.at/
-			for more information.
-
-noacl			This option disables POSIX Access Control List
-			support.
-
-reservation
-
-noreservation
-
-bsddf 		(*)	Make 'df' act like BSD.
-minixdf			Make 'df' act like Minix.
-
-check=none		Don't do extra checking of bitmaps on mount.
-nocheck
-
-debug			Extra debugging information is sent to syslog.
-
-errors=remount-ro	Remount the filesystem read-only on an error.
-errors=continue		Keep going on a filesystem error.
-errors=panic		Panic and halt the machine if an error occurs.
-			(These mount options override the errors behavior
-			specified in the superblock, which can be
-			configured using tune2fs.)
-
-data_err=ignore(*)	Just print an error message if an error occurs
-			in a file data buffer in ordered mode.
-data_err=abort		Abort the journal if an error occurs in a file
-			data buffer in ordered mode.
-
-grpid			Give objects the same group ID as their creator.
-bsdgroups
-
-nogrpid		(*)	New objects have the group ID of their creator.
-sysvgroups
-
-resgid=n		The group ID which may use the reserved blocks.
-
-resuid=n		The user ID which may use the reserved blocks.
-
-sb=n			Use alternate superblock at this location.
-
-quota			These options are ignored by the filesystem. They
-noquota			are used only by quota tools to recognize volumes
-grpquota		where quota should be turned on. See documentation
-usrquota		in the quota-tools package for more details
-			(http://sourceforge.net/projects/linuxquota).
-
-jqfmt=<quota type>	These options tell filesystem details about quota
-usrjquota=<file>	so that quota information can be properly updated
-grpjquota=<file>	during journal replay. They replace the above
-			quota options. See documentation in the quota-tools
-			package for more details
-			(http://sourceforge.net/projects/linuxquota).
-
-Specification
-=============
-Ext3 shares all disk implementation with the ext2 filesystem, and adds
-transactions capabilities to ext2.  Journaling is done by the Journaling Block
-Device layer.
-
-Journaling Block Device layer
------------------------------
-The Journaling Block Device layer (JBD) isn't ext3 specific.  It was designed
-to add journaling capabilities to a block device.  The ext3 filesystem code
-will inform the JBD of modifications it is performing (called a transaction).
-The journal supports the transactions start and stop, and in case of a crash,
-the journal can replay the transactions to quickly put the partition back into
-a consistent state.
-
-Handles represent a single atomic update to a filesystem.  JBD can handle an
-external journal on a block device.
-
-Data Mode
----------
-There are 3 different data modes:
-
-* writeback mode
-In data=writeback mode, ext3 does not journal data at all.  This mode provides
-a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
-mode - metadata journaling.  A crash+recovery can cause incorrect data to
-appear in files which were written shortly before the crash.  This mode will
-typically provide the best ext3 performance.
-
-* ordered mode
-In data=ordered mode, ext3 only officially journals metadata, but it logically
-groups metadata and data blocks into a single unit called a transaction.  When
-it's time to write the new metadata out to disk, the associated data blocks
-are written first.  In general, this mode performs slightly slower than
-writeback but significantly faster than journal mode.
-
-* journal mode
-data=journal mode provides full data and metadata journaling.  All new data is
-written to the journal first, and then to its final location.
-In the event of a crash, the journal can be replayed, bringing both data and
-metadata into a consistent state.  This mode is the slowest except when data
-needs to be read from and written to disk at the same time where it
-outperforms all other modes.
-
-Compatibility
--------------
-
-Ext2 partitions can be easily convert to ext3, with `tune2fs -j <dev>`.
-Ext3 is fully compatible with Ext2.  Ext3 partitions can easily be mounted as
-Ext2.
-
-
-External Tools
-==============
-See manual pages to learn more.
-
-tune2fs: 	create a ext3 journal on a ext2 partition with the -j flag.
-mke2fs: 	create a ext3 partition with the -j flag.
-debugfs: 	ext2 and ext3 file system debugger.
-ext2online:	online (mounted) ext2 and ext3 filesystem resizer
-
-
-References
-==========
-
-kernel source:	<file:fs/ext3/>
-		<file:fs/jbd/>
-
-programs: 	http://e2fsprogs.sourceforge.net/
-		http://ext2resize.sourceforge.net
-
-useful links:	http://www.ibm.com/developerworks/library/l-fs7/index.html
-        http://www.ibm.com/developerworks/library/l-fs8/index.html
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e9e750e59efc..e2d5105b7214 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -143,7 +143,9 @@ fastboot               This option is used when a system wants to reduce mount
 extent_cache           Enable an extent cache based on rb-tree, it can cache
                        as many as extent which map between contiguous logical
                        address and physical address per inode, resulting in
-                       increasing the cache hit ratio.
+                       increasing the cache hit ratio. Set by default.
+noextent_cache         Diable an extent cache based on rb-tree explicitly, see
+                       the above extent_cache mount option.
 noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 
diff --git a/Documentation/filesystems/nfs/nfs-rdma.txt b/Documentation/filesystems/nfs/nfs-rdma.txt
index 95c13aa575ff..906b6c233f62 100644
--- a/Documentation/filesystems/nfs/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs/nfs-rdma.txt
@@ -138,9 +138,9 @@ Installation
   - Build, install, reboot
 
     The NFS/RDMA code will be enabled automatically if NFS and RDMA
-    are turned on. The NFS/RDMA client and server are configured via the
-    SUNRPC_XPRT_RDMA_CLIENT and SUNRPC_XPRT_RDMA_SERVER config options that both
-    depend on SUNRPC and INFINIBAND. The default value of both options will be:
+    are turned on. The NFS/RDMA client and server are configured via the hidden
+    SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The
+    value of SUNRPC_XPRT_RDMA will be:
 
      - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client
        and server will not be built
@@ -238,9 +238,8 @@ NFS/RDMA Setup
 
   - Start the NFS server
 
-    If the NFS/RDMA server was built as a module
-    (CONFIG_SUNRPC_XPRT_RDMA_SERVER=m in kernel config), load the RDMA
-    transport module:
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
+    kernel config), load the RDMA transport module:
 
     $ modprobe svcrdma
 
@@ -259,9 +258,8 @@ NFS/RDMA Setup
 
   - On the client system
 
-    If the NFS/RDMA client was built as a module
-    (CONFIG_SUNRPC_XPRT_RDMA_CLIENT=m in kernel config), load the RDMA client
-    module:
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
+    kernel config), load the RDMA client module:
 
     $ modprobe xprtrdma.ko
 
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index b35a64b82f9e..9494afb9476a 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -212,7 +212,10 @@ Other notes:
 - show() methods should return the number of bytes printed into the
   buffer. This is the return value of scnprintf().
 
-- show() should always use scnprintf().
+- show() must not use snprintf() when formatting the value to be
+  returned to user space. If you can guarantee that an overflow
+  will never happen you can use sprintf() otherwise you must use
+  scnprintf().
 
 - store() should return the number of bytes used from the buffer. If the
   entire buffer has been used, just return the count argument.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5eb8456fc41e..8c6f07ad373a 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -769,7 +769,7 @@ struct address_space_operations {
 	to stall to allow flushers a chance to complete some IO. Ordinarily
 	it can use PageDirty and PageWriteback but some filesystems have
 	more complex state (unstable pages in NFS prevent reclaim) or
-	do not set those flags due to locking problems (jbd). This callback
+	do not set those flags due to locking problems. This callback
 	allows a filesystem to indicate to the VM if a page should be
 	treated as dirty or writeback for the purposes of stalling.
 
diff --git a/Documentation/gpio/00-INDEX b/Documentation/gpio/00-INDEX
index 1de43ae46ae6..179beb234f98 100644
--- a/Documentation/gpio/00-INDEX
+++ b/Documentation/gpio/00-INDEX
@@ -6,6 +6,9 @@ consumer.txt
 	- How to obtain and use GPIOs in a driver
 driver.txt
 	- How to write a GPIO driver
+drivers-on-gpio.txt:
+	- Drivers in other subsystems that can use GPIO to provide more
+	  complex functionality.
 board.txt
 	- How to assign GPIOs to a consumer device and a function
 sysfs.txt
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index 75542b91b766..a206639454ab 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -237,6 +237,39 @@ Note that these functions should only be used with great moderation ; a driver
 should not have to care about the physical line level.
 
 
+The active-low property
+-----------------------
+
+As a driver should not have to care about the physical line level, all of the
+gpiod_set_value_xxx() or gpiod_set_array_value_xxx() functions operate with
+the *logical* value. With this they take the active-low property into account.
+This means that they check whether the GPIO is configured to be active-low,
+and if so, they manipulate the passed value before the physical line level is
+driven.
+
+With this, all the gpiod_set_(array)_value_xxx() functions interpret the
+parameter "value" as "active" ("1") or "inactive" ("0"). The physical line
+level will be driven accordingly.
+
+As an example, if the active-low property for a dedicated GPIO is set, and the
+gpiod_set_(array)_value_xxx() passes "active" ("1"), the physical line level
+will be driven low.
+
+To summarize:
+
+Function (example)               active-low proporty  physical line
+gpiod_set_raw_value(desc, 0);        don't care           low
+gpiod_set_raw_value(desc, 1);        don't care           high
+gpiod_set_value(desc, 0);       default (active-high)     low
+gpiod_set_value(desc, 1);       default (active-high)     high
+gpiod_set_value(desc, 0);             active-low          high
+gpiod_set_value(desc, 1);             active-low          low
+
+Please note again that the set_raw/get_raw functions should be avoided as much
+as possible, especially by drivers which should not care about the actual
+physical line level and worry about the logical value instead.
+
+
 Set multiple GPIO outputs with a single function call
 -----------------------------------------------------
 The following functions set the output values of an array of GPIOs:
diff --git a/Documentation/gpio/drivers-on-gpio.txt b/Documentation/gpio/drivers-on-gpio.txt
new file mode 100644
index 000000000000..f6121328630f
--- /dev/null
+++ b/Documentation/gpio/drivers-on-gpio.txt
@@ -0,0 +1,95 @@
+Subsystem drivers using GPIO
+============================
+
+Note that standard kernel drivers exist for common GPIO tasks and will provide
+the right in-kernel and userspace APIs/ABIs for the job, and that these
+drivers can quite easily interconnect with other kernel subsystems using
+hardware descriptions such as device tree or ACPI:
+
+- leds-gpio: drivers/leds/leds-gpio.c will handle LEDs connected to  GPIO
+  lines, giving you the LED sysfs interface
+
+- ledtrig-gpio: drivers/leds/trigger/ledtrig-gpio.c will provide a LED trigger,
+  i.e. a LED will turn on/off in response to a GPIO line going high or low
+  (and that LED may in turn use the leds-gpio as per above).
+
+- gpio-keys: drivers/input/keyboard/gpio_keys.c is used when your GPIO line
+  can generate interrupts in response to a key press. Also supports debounce.
+
+- gpio-keys-polled: drivers/input/keyboard/gpio_keys_polled.c is used when your
+  GPIO line cannot generate interrupts, so it needs to be periodically polled
+  by a timer.
+
+- gpio_mouse: drivers/input/mouse/gpio_mouse.c is used to provide a mouse with
+  up to three buttons by simply using GPIOs and no mouse port. You can cut the
+  mouse cable and connect the wires to GPIO lines or solder a mouse connector
+  to the lines for a more permanent solution of this type.
+
+- gpio-beeper: drivers/input/misc/gpio-beeper.c is used to provide a beep from
+  an external speaker connected to a GPIO line.
+
+- gpio-tilt-polled: drivers/input/misc/gpio_tilt_polled.c provides tilt
+  detection switches using GPIO, which is useful for your homebrewn pinball
+  machine if for nothing else. It can detect different tilt angles of the
+  monitored object.
+
+- extcon-gpio: drivers/extcon/extcon-gpio.c is used when you need to read an
+  external connector status, such as a headset line for an audio driver or an
+  HDMI connector. It will provide a better userspace sysfs interface than GPIO.
+
+- restart-gpio: drivers/power/gpio-restart.c is used to restart/reboot the
+  system by pulling a GPIO line and will register a restart handler so
+  userspace can issue the right system call to restart the system.
+
+- poweroff-gpio: drivers/power/gpio-poweroff.c is used to power the system down
+  by pulling a GPIO line and will register a pm_power_off() callback so that
+  userspace can issue the right system call to power down the system.
+
+- gpio-gate-clock: drivers/clk/clk-gpio-gate.c is used to control a gated clock
+  (off/on) that uses a GPIO, and integrated with the clock subsystem.
+
+- i2c-gpio: drivers/i2c/busses/i2c-gpio.c is used to drive an I2C bus
+  (two wires, SDA and SCL lines) by hammering (bitbang) two GPIO lines. It will
+  appear as any other I2C bus to the system and makes it possible to connect
+  drivers for the I2C devices on the bus like any other I2C bus driver.
+
+- spi_gpio: drivers/spi/spi-gpio.c is used to drive an SPI bus (variable number
+  of wires, atleast SCK and optionally MISO, MOSI and chip select lines) using
+  GPIO hammering (bitbang). It will appear as any other SPI bus on the system
+  and makes it possible to connect drivers for SPI devices on the bus like
+  any other SPI bus driver. For example any MMC/SD card can then be connected
+  to this SPI by using the mmc_spi host from the MMC/SD card subsystem.
+
+- w1-gpio: drivers/w1/masters/w1-gpio.c is used to drive a one-wire bus using
+  a GPIO line, integrating with the W1 subsystem and handling devices on
+  the bus like any other W1 device.
+
+- gpio-fan: drivers/hwmon/gpio-fan.c is used to control a fan for cooling the
+  system, connected to a GPIO line (and optionally a GPIO alarm line),
+  presenting all the right in-kernel and sysfs interfaces to make your system
+  not overheat.
+
+- gpio-regulator: drivers/regulator/gpio-regulator.c is used to control a
+  regulator providing a certain voltage by pulling a GPIO line, integrating
+  with the regulator subsystem and giving you all the right interfaces.
+
+- gpio-wdt: drivers/watchdog/gpio_wdt.c is used to provide a watchdog timer
+  that will periodically "ping" a hardware connected to a GPIO line by toggling
+  it from 1-to-0-to-1. If that hardware does not recieve its "ping"
+  periodically, it will reset the system.
+
+- gpio-nand: drivers/mtd/nand/gpio.c is used to connect a NAND flash chip to
+  a set of simple GPIO lines: RDY, NCE, ALE, CLE, NWP. It interacts with the
+  NAND flash MTD subsystem and provides chip access and partition parsing like
+  any other NAND driving hardware.
+
+Apart from this there are special GPIO drivers in subsystems like MMC/SD to
+read card detect and write protect GPIO lines, and in the TTY serial subsystem
+to emulate MCTRL (modem control) signals CTS/RTS by using two GPIO lines. The
+MTD NOR flash has add-ons for extra GPIO lines too, though the address bus is
+usually connected directly to the flash.
+
+Use those instead of talking directly to the GPIOs using sysfs; they integrate
+with kernel frameworks better than your userspace code could. Needless to say,
+just using the apropriate kernel drivers will simplify and speed up your
+embedded hacking in particular by providing ready-made components.
diff --git a/Documentation/gpio/sysfs.txt b/Documentation/gpio/sysfs.txt
index 535b6a8a7a7c..0700b55637f5 100644
--- a/Documentation/gpio/sysfs.txt
+++ b/Documentation/gpio/sysfs.txt
@@ -20,11 +20,10 @@ userspace GPIO can be used to determine system configuration data that
 standard kernels won't know about. And for some tasks, simple userspace
 GPIO drivers could be all that the system really needs.
 
-Note that standard kernel drivers exist for common "LEDs and Buttons"
-GPIO tasks:  "leds-gpio" and "gpio_keys", respectively. Use those
-instead of talking directly to the GPIOs; they integrate with kernel
-frameworks better than your userspace code could.
-
+DO NOT ABUSE SYFS TO CONTROL HARDWARE THAT HAS PROPER KERNEL DRIVERS.
+PLEASE READ THE DOCUMENT NAMED "drivers-on-gpio.txt" IN THIS DOCUMENTATION
+DIRECTORY TO AVOID REINVENTING KERNEL WHEELS IN USERSPACE. I MEAN IT.
+REALLY.
 
 Paths in Sysfs
 --------------
diff --git a/Documentation/hwmon/adm1275 b/Documentation/hwmon/adm1275
index 15b4a20d5062..d697229e3c18 100644
--- a/Documentation/hwmon/adm1275
+++ b/Documentation/hwmon/adm1275
@@ -14,6 +14,10 @@ Supported chips:
     Prefix: 'adm1276'
     Addresses scanned: -
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1276.pdf
+  * Analog Devices ADM1293/ADM1294
+    Prefix: 'adm1293', 'adm1294'
+    Addresses scanned: -
+    Datasheet: http://www.analog.com/media/en/technical-documentation/data-sheets/ADM1293_1294.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -22,12 +26,12 @@ Description
 -----------
 
 This driver supports hardware montoring for Analog Devices ADM1075, ADM1275,
-and ADM1276 Hot-Swap Controller and Digital Power Monitor.
+ADM1276, ADM1293, and ADM1294 Hot-Swap Controller and Digital Power Monitors.
 
-ADM1075, ADM1275, and ADM1276 are hot-swap controllers that allow a circuit
-board to be removed from or inserted into a live backplane. They also feature
-current and voltage readback via an integrated 12-bit analog-to-digital
-converter (ADC), accessed using a PMBus interface.
+ADM1075, ADM1275, ADM1276, ADM1293, and ADM1294 are hot-swap controllers that
+allow a circuit board to be removed from or inserted into a live backplane.
+They also feature current and voltage readback via an integrated 12
+bit analog-to-digital converter (ADC), accessed using a PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -58,16 +62,16 @@ Sysfs entries
 The following attributes are supported. Limits are read-write, history reset
 attributes are write-only, all other attributes are read-only.
 
-in1_label		"vin1" or "vout1" depending on chip variant and
-			configuration. On ADM1075, vout1 reports the voltage on
-			the VAUX pin.
-in1_input		Measured voltage.
-in1_min			Minimum Voltage.
-in1_max			Maximum voltage.
-in1_min_alarm		Voltage low alarm.
-in1_max_alarm		Voltage high alarm.
-in1_highest		Historical maximum voltage.
-in1_reset_history	Write any value to reset history.
+inX_label		"vin1" or "vout1" depending on chip variant and
+			configuration. On ADM1075, ADM1293, and ADM1294,
+			vout1 reports the voltage on the VAUX pin.
+inX_input		Measured voltage.
+inX_min			Minimum Voltage.
+inX_max			Maximum voltage.
+inX_min_alarm		Voltage low alarm.
+inX_max_alarm		Voltage high alarm.
+inX_highest		Historical maximum voltage.
+inX_reset_history	Write any value to reset history.
 
 curr1_label		"iout1"
 curr1_input		Measured current.
@@ -86,7 +90,9 @@ curr1_reset_history	Write any value to reset history.
 
 power1_label		"pin1"
 power1_input		Input power.
+power1_input_lowest	Lowest observed input power. ADM1293 and ADM1294 only.
+power1_input_highest	Highest observed input power.
 power1_reset_history	Write any value to reset history.
 
-			Power attributes are supported on ADM1075 and ADM1276
-			only.
+			Power attributes are supported on ADM1075, ADM1276,
+			ADM1293, and ADM1294.
diff --git a/Documentation/hwmon/fam15h_power b/Documentation/hwmon/fam15h_power
index 80654813d04a..e2b1b69eebea 100644
--- a/Documentation/hwmon/fam15h_power
+++ b/Documentation/hwmon/fam15h_power
@@ -3,12 +3,13 @@ Kernel driver fam15h_power
 
 Supported chips:
 * AMD Family 15h Processors
+* AMD Family 16h Processors
 
   Prefix: 'fam15h_power'
   Addresses scanned: PCI space
   Datasheets:
   BIOS and Kernel Developer's Guide (BKDG) For AMD Family 15h Processors
-    (not yet published)
+  BIOS and Kernel Developer's Guide (BKDG) For AMD Family 16h Processors
 
 Author: Andreas Herrmann <herrmann.der.user@googlemail.com>
 
@@ -16,10 +17,11 @@ Description
 -----------
 
 This driver permits reading of registers providing power information
-of AMD Family 15h processors.
+of AMD Family 15h and 16h processors.
 
-For AMD Family 15h processors the following power values can be
-calculated using different processor northbridge function registers:
+For AMD Family 15h and 16h processors the following power values can
+be calculated using different processor northbridge function
+registers:
 
 * BasePwrWatts: Specifies in watts the maximum amount of power
   consumed by the processor for NB and logic external to the core.
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index e87294878334..733296d65449 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -38,6 +38,10 @@ Supported chips:
     Prefix: 'it8728'
     Addresses scanned: from Super I/O config space (8 I/O ports)
     Datasheet: Not publicly available
+  * IT8732F
+    Prefix: 'it8732'
+    Addresses scanned: from Super I/O config space (8 I/O ports)
+    Datasheet: Not publicly available
   * IT8771E
     Prefix: 'it8771'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -111,9 +115,9 @@ Description
 -----------
 
 This driver implements support for the IT8603E, IT8620E, IT8623E, IT8705F,
-IT8712F, IT8716F, IT8718F, IT8720F, IT8721F, IT8726F, IT8728F, IT8758E,
-IT8771E, IT8772E, IT8781F, IT8782F, IT8783E/F, IT8786E, IT8790E, and SiS950
-chips.
+IT8712F, IT8716F, IT8718F, IT8720F, IT8721F, IT8726F, IT8728F, IT8732F,
+IT8758E, IT8771E, IT8772E, IT8781F, IT8782F, IT8783E/F, IT8786E, IT8790E, and
+SiS950 chips.
 
 These chips are 'Super I/O chips', supporting floppy disks, infrared ports,
 joysticks and other miscellaneous stuff. For hardware monitoring, they
@@ -137,10 +141,10 @@ The IT8716F, IT8718F, IT8720F, IT8721F/IT8758E and later IT8712F revisions
 have support for 2 additional fans. The additional fans are supported by the
 driver.
 
-The IT8716F, IT8718F, IT8720F, IT8721F/IT8758E, IT8781F, IT8782F, IT8783E/F,
-and late IT8712F and IT8705F also have optional 16-bit tachometer counters
-for fans 1 to 3. This is better (no more fan clock divider mess) but not
-compatible with the older chips and revisions. The 16-bit tachometer mode
+The IT8716F, IT8718F, IT8720F, IT8721F/IT8758E, IT8732F, IT8781F, IT8782F,
+IT8783E/F, and late IT8712F and IT8705F also have optional 16-bit tachometer
+counters for fans 1 to 3. This is better (no more fan clock divider mess) but
+not compatible with the older chips and revisions. The 16-bit tachometer mode
 is enabled by the driver when one of the above chips is detected.
 
 The IT8726F is just bit enhanced IT8716F with additional hardware
@@ -159,6 +163,9 @@ IT8728F. It only supports 16-bit fan mode.
 
 The IT8790E supports up to 3 fans. 16-bit fan mode is always enabled.
 
+The IT8732F supports a closed-loop mode for fan control, but this is not
+currently implemented by the driver.
+
 Temperatures are measured in degrees Celsius. An alarm is triggered once
 when the Overtemperature Shutdown limit is crossed.
 
@@ -173,12 +180,14 @@ is done.
 Voltage sensors (also known as IN sensors) report their values in volts. An
 alarm is triggered if the voltage has crossed a programmable minimum or
 maximum limit. Note that minimum in this case always means 'closest to
-zero'; this is important for negative voltage measurements. All voltage
-inputs can measure voltages between 0 and 4.08 volts, with a resolution of
-0.016 volt (except IT8603E, IT8721F/IT8758E and IT8728F: 0.012 volt.) The
-battery voltage in8 does not have limit registers.
-
-On the IT8603E, IT8721F/IT8758E, IT8781F, IT8782F, and IT8783E/F, some
+zero'; this is important for negative voltage measurements. On most chips, all
+voltage inputs can measure voltages between 0 and 4.08 volts, with a resolution
+of 0.016 volt.  IT8603E, IT8721F/IT8758E and IT8728F can measure between 0 and
+3.06 volts, with a resolution of 0.012 volt.  IT8732F can measure between 0 and
+2.8 volts with a resolution of 0.0109 volt.  The battery voltage in8 does not
+have limit registers.
+
+On the IT8603E, IT8721F/IT8758E, IT8732F, IT8781F, IT8782F, and IT8783E/F, some
 voltage inputs are internal and scaled inside the chip:
 * in3 (optional)
 * in7 (optional for IT8781F, IT8782F, and IT8783E/F)
diff --git a/Documentation/hwmon/ltc2978 b/Documentation/hwmon/ltc2978
index 686c078bb0e0..9a49d3c90cd1 100644
--- a/Documentation/hwmon/ltc2978
+++ b/Documentation/hwmon/ltc2978
@@ -6,6 +6,10 @@ Supported chips:
     Prefix: 'ltc2974'
     Addresses scanned: -
     Datasheet: http://www.linear.com/product/ltc2974
+  * Linear Technology LTC2975
+    Prefix: 'ltc2975'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc2975
   * Linear Technology LTC2977
     Prefix: 'ltc2977'
     Addresses scanned: -
@@ -15,14 +19,38 @@ Supported chips:
     Addresses scanned: -
     Datasheet: http://www.linear.com/product/ltc2978
     	       http://www.linear.com/product/ltc2978a
+  * Linear Technology LTC2980
+    Prefix: 'ltc2980'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc2980
   * Linear Technology LTC3880
     Prefix: 'ltc3880'
     Addresses scanned: -
     Datasheet: http://www.linear.com/product/ltc3880
+  * Linear Technology LTC3882
+    Prefix: 'ltc3882'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc3882
   * Linear Technology LTC3883
     Prefix: 'ltc3883'
     Addresses scanned: -
     Datasheet: http://www.linear.com/product/ltc3883
+  * Linear Technology LTC3886
+    Prefix: 'ltc3886'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc3886
+  * Linear Technology LTC3887
+    Prefix: 'ltc3887'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc3887
+  * Linear Technology LTM2987
+    Prefix: 'ltm2987'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltm2987
+  * Linear Technology LTM4675
+    Prefix: 'ltm4675'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltm4675
   * Linear Technology LTM4676
     Prefix: 'ltm4676'
     Addresses scanned: -
@@ -34,11 +62,20 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-LTC2974 is a quad digital power supply manager. LTC2978 is an octal power supply
-monitor. LTC2977 is a pin compatible replacement for LTC2978. LTC3880 is a dual
-output poly-phase step-down DC/DC controller. LTC3883 is a single phase
-step-down DC/DC controller. LTM4676 is a dual 13A or single 26A uModule
-regulator.
+LTC2974 and LTC2975 are quad digital power supply managers.
+LTC2978 is an octal power supply monitor.
+LTC2977 is a pin compatible replacement for LTC2978.
+LTC2980 is a 16-channel Power System Manager, consisting of two LTC2977
+in a single die. The chip is instantiated and reported as two separate chips
+on two different I2C bus addresses.
+LTC3880, LTC3882, LTC3886, and LTC3887 are dual output poly-phase step-down
+DC/DC controllers.
+LTC3883 is a single phase step-down DC/DC controller.
+LTM2987 is a 16-channel Power System Manager with two LTC2977 plus
+additional components on a single die. The chip is instantiated and reported
+as two separate chips on two different I2C bus addresses.
+LTM4675 is a dual 9A or single 18A μModule regulator
+LTM4676 is a dual 13A or single 26A uModule regulator.
 
 
 Usage Notes
@@ -61,26 +98,32 @@ in1_label		"vin"
 in1_input		Measured input voltage.
 in1_min			Minimum input voltage.
 in1_max			Maximum input voltage.
-			LTC2974, LTC2977, and LTC2978 only.
+			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
+			LTM2987 only.
 in1_lcrit		Critical minimum input voltage.
-			LTC2974, LTC2977, and LTC2978 only.
+			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
+			LTM2987 only.
 in1_crit		Critical maximum input voltage.
 in1_min_alarm		Input voltage low alarm.
 in1_max_alarm		Input voltage high alarm.
-			LTC2974, LTC2977, and LTC2978 only.
+			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
+			LTM2987 only.
 in1_lcrit_alarm		Input voltage critical low alarm.
-			LTC2974, LTC2977, and LTC2978 only.
+			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
+			LTM2987 only.
 in1_crit_alarm		Input voltage critical high alarm.
 in1_lowest		Lowest input voltage.
-			LTC2974, LTC2977, and LTC2978 only.
+			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
+			LTM2987 only.
 in1_highest		Highest input voltage.
 in1_reset_history	Reset input voltage history.
 
 in[N]_label		"vout[1-8]".
-			LTC2974: N=2-5
-			LTC2977: N=2-9
+			LTC2974, LTC2975: N=2-5
+			LTC2977, LTC2980, LTM2987: N=2-9
 			LTC2978: N=2-9
-			LTC3880, LTM4676: N=2-3
+			LTC3880, LTC3882, LTC23886 LTC3887, LTM4675, LTM4676:
+				N=2-3
 			LTC3883: N=2
 in[N]_input		Measured output voltage.
 in[N]_min		Minimum output voltage.
@@ -91,67 +134,78 @@ in[N]_min_alarm		Output voltage low alarm.
 in[N]_max_alarm		Output voltage high alarm.
 in[N]_lcrit_alarm	Output voltage critical low alarm.
 in[N]_crit_alarm	Output voltage critical high alarm.
-in[N]_lowest		Lowest output voltage. LTC2974 and LTC2978 only.
+in[N]_lowest		Lowest output voltage. LTC2974, LTC2975,
+			and LTC2978 only.
 in[N]_highest		Highest output voltage.
 in[N]_reset_history	Reset output voltage history.
 
 temp[N]_input		Measured temperature.
-			On LTC2974, temp[1-4] report external temperatures,
-			and temp5 reports the chip temperature.
-			On LTC2977 and LTC2978, only one temperature measurement
-			is supported and reports the chip temperature.
-			On LTC3880 and LTM4676, temp1 and temp2 report external
-			temperatures, and temp3 reports the chip temperature.
+			On LTC2974 and LTC2975, temp[1-4] report external
+			temperatures, and temp5 reports the chip temperature.
+			On LTC2977, LTC2980, LTC2978, and LTM2987, only one
+			temperature measurement is supported and reports
+			the chip temperature.
+			On LTC3880, LTC3882, LTC3887, LTM4675, and LTM4676,
+			temp1 and temp2 report external temperatures, and temp3
+			reports the chip temperature.
 			On LTC3883, temp1 reports an external temperature,
 			and temp2 reports the chip temperature.
-temp[N]_min		Mimimum temperature. LTC2974, LCT2977, and LTC2978 only.
+temp[N]_min		Mimimum temperature. LTC2974, LCT2977, LTM2980, LTC2978,
+			and LTM2987 only.
 temp[N]_max		Maximum temperature.
 temp[N]_lcrit		Critical low temperature.
 temp[N]_crit		Critical high temperature.
 temp[N]_min_alarm	Temperature low alarm.
-			LTC2974, LTC2977, and LTC2978 only.
+			LTC2974, LTC2975, LTC2977, LTM2980, LTC2978, and
+			LTM2987 only.
 temp[N]_max_alarm	Temperature high alarm.
 temp[N]_lcrit_alarm	Temperature critical low alarm.
 temp[N]_crit_alarm	Temperature critical high alarm.
 temp[N]_lowest		Lowest measured temperature.
-			LTC2974, LTC2977, and LTC2978 only.
-			Not supported for chip temperature sensor on LTC2974.
+			LTC2974, LTC2975, LTC2977, LTM2980, LTC2978, and
+			LTM2987 only.
+			Not supported for chip temperature sensor on LTC2974 and
+			LTC2975.
 temp[N]_highest		Highest measured temperature. Not supported for chip
-			temperature sensor on LTC2974.
+			temperature sensor on LTC2974 and LTC2975.
 temp[N]_reset_history	Reset temperature history. Not supported for chip
-			temperature sensor on LTC2974.
+			temperature sensor on LTC2974 and LTC2975.
 
-power1_label		"pin". LTC3883 only.
+power1_label		"pin". LTC3883 and LTC3886 only.
 power1_input		Measured input power.
 
 power[N]_label		"pout[1-4]".
-			LTC2974: N=1-4
-			LTC2977: Not supported
+			LTC2974, LTC2975: N=1-4
+			LTC2977, LTC2980, LTM2987: Not supported
 			LTC2978: Not supported
-			LTC3880, LTM4676: N=1-2
+			LTC3880, LTC3882, LTC3886, LTC3887, LTM4675, LTM4676:
+				N=1-2
 			LTC3883: N=2
 power[N]_input		Measured output power.
 
-curr1_label		"iin". LTC3880, LTC3883, and LTM4676 only.
+curr1_label		"iin". LTC3880, LTC3883, LTC3886, LTC3887, LTM4675,
+			and LTM4676 only.
 curr1_input		Measured input current.
 curr1_max		Maximum input current.
 curr1_max_alarm		Input current high alarm.
-curr1_highest		Highest input current. LTC3883 only.
-curr1_reset_history	Reset input current history. LTC3883 only.
+curr1_highest		Highest input current. LTC3883 and LTC3886 only.
+curr1_reset_history	Reset input current history. LTC3883 and LTC3886 only.
 
 curr[N]_label		"iout[1-4]".
-			LTC2974: N=1-4
-			LTC2977: not supported
+			LTC2974, LTC2975: N=1-4
+			LTC2977, LTC2980, LTM2987: not supported
 			LTC2978: not supported
-			LTC3880, LTM4676: N=2-3
+			LTC3880, LTC3882, LTC3886, LTC3887, LTM4675, LTM4676:
+				N=2-3
 			LTC3883: N=2
 curr[N]_input		Measured output current.
 curr[N]_max		Maximum output current.
 curr[N]_crit		Critical high output current.
-curr[N]_lcrit		Critical low output current. LTC2974 only.
+curr[N]_lcrit		Critical low output current. LTC2974 and LTC2975 only.
 curr[N]_max_alarm	Output current high alarm.
 curr[N]_crit_alarm	Output current critical high alarm.
-curr[N]_lcrit_alarm	Output current critical low alarm. LTC2974 only.
-curr[N]_lowest		Lowest output current. LTC2974 only.
+curr[N]_lcrit_alarm	Output current critical low alarm.
+			LTC2974 and LTC2975 only.
+curr[N]_lowest		Lowest output current. LTC2974 and LTC2975 only.
 curr[N]_highest		Highest output current.
 curr[N]_reset_history	Reset output current history.
diff --git a/Documentation/hwmon/max20751 b/Documentation/hwmon/max20751
new file mode 100644
index 000000000000..f9fa25ebb521
--- /dev/null
+++ b/Documentation/hwmon/max20751
@@ -0,0 +1,77 @@
+Kernel driver max20751
+======================
+
+Supported chips:
+  * maxim MAX20751
+    Prefix: 'max20751'
+    Addresses scanned: -
+    Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX20751.pdf
+    Application note: http://pdfserv.maximintegrated.com/en/an/AN5941.pdf
+
+Author: Guenter Roeck <linux@roeck-us.net>
+
+
+Description
+-----------
+
+This driver supports MAX20751 Multiphase Master with PMBus Interface
+and Internal Buck Converter.
+
+The driver is a client driver to the core PMBus driver.
+Please see Documentation/hwmon/pmbus for details on PMBus client drivers.
+
+
+Usage Notes
+-----------
+
+This driver does not auto-detect devices. You will have to instantiate the
+devices explicitly. Please see Documentation/i2c/instantiating-devices for
+details.
+
+
+Platform data support
+---------------------
+
+The driver supports standard PMBus driver platform data.
+
+
+Sysfs entries
+-------------
+
+The following attributes are supported.
+
+in1_label		"vin1"
+in1_input		Measured voltage.
+in1_min			Minimum input voltage.
+in1_max			Maximum input voltage.
+in1_lcrit		Critical minimum input voltage.
+in1_crit		Critical maximum input voltage.
+in1_min_alarm		Input voltage low alarm.
+in1_lcrit_alarm		Input voltage critical low alarm.
+in1_min_alarm		Input voltage low alarm.
+in1_max_alarm		Input voltage high alarm.
+
+in2_label		"vout1"
+in2_input		Measured voltage.
+in2_min			Minimum output voltage.
+in2_max			Maximum output voltage.
+in2_lcrit		Critical minimum output voltage.
+in2_crit		Critical maximum output voltage.
+in2_min_alarm		Output voltage low alarm.
+in2_lcrit_alarm		Output voltage critical low alarm.
+in2_min_alarm		Output voltage low alarm.
+in2_max_alarm		Output voltage high alarm.
+
+curr1_input		Measured output current.
+curr1_label		"iout1"
+curr1_max		Maximum output current.
+curr1_alarm		Current high alarm.
+
+temp1_input		Measured temperature.
+temp1_max		Maximum temperature.
+temp1_crit		Critical high temperature.
+temp1_max_alarm		Chip temperature high alarm.
+temp1_crit_alarm	Chip temperature critical high alarm.
+
+power1_input		Output power.
+power1_label		"pout1"
diff --git a/Documentation/hwmon/nct7802 b/Documentation/hwmon/nct7802
index 2e00f5e344bc..5438deb6be02 100644
--- a/Documentation/hwmon/nct7802
+++ b/Documentation/hwmon/nct7802
@@ -17,8 +17,7 @@ This driver implements support for the Nuvoton NCT7802Y hardware monitoring
 chip. NCT7802Y supports 6 temperature sensors, 5 voltage sensors, and 3 fan
 speed sensors.
 
-The chip also supports intelligent fan speed control. This functionality is
-not currently supported by the driver.
+Smart Fan™ speed control is available via pwmX_auto_point attributes.
 
 Tested Boards and BIOS Versions
 -------------------------------
diff --git a/Documentation/hwmon/nct7904 b/Documentation/hwmon/nct7904
index 014f112e2a14..57fffe33ebfc 100644
--- a/Documentation/hwmon/nct7904
+++ b/Documentation/hwmon/nct7904
@@ -35,11 +35,11 @@ temp1_input		Local temperature (1/1000 degree,
 temp[2-9]_input		CPU temperatures (1/1000 degree,
 			0.125 degree resolution)
 
-fan[1-4]_mode		R/W, 0/1 for manual or SmartFan mode
+pwm[1-4]_enable		R/W, 1/2 for manual or SmartFan mode
 			Setting SmartFan mode is supported only if it has been
 			previously configured by BIOS (or configuration EEPROM)
 
-fan[1-4]_pwm		R/O in SmartFan mode, R/W in manual control mode
+pwm[1-4]		R/O in SmartFan mode, R/W in manual control mode
 
 The driver checks sensor control registers and does not export the sensors
 that are not enabled. Anyway, a sensor that is enabled may actually be not
diff --git a/Documentation/hwmon/pmbus b/Documentation/hwmon/pmbus
index a3557da8f5b4..b397675e876d 100644
--- a/Documentation/hwmon/pmbus
+++ b/Documentation/hwmon/pmbus
@@ -23,11 +23,15 @@ Supported chips:
 	http://www.lineagepower.com/oem/pdf/PDT012A0X.pdf
 	http://www.lineagepower.com/oem/pdf/UDT020A0X.pdf
 	http://www.lineagepower.com/oem/pdf/MDT040A0X.pdf
-  * Texas Instruments TPS40400
-    Prefixes: 'tps40400'
+  * Texas Instruments TPS40400, TPS544B20, TPS544B25, TPS544C20, TPS544C25
+    Prefixes: 'tps40400', 'tps544b20', 'tps544b25', 'tps544c20', 'tps544c25'
     Addresses scanned: -
     Datasheets:
 	http://www.ti.com/lit/gpn/tps40400
+	http://www.ti.com/lit/gpn/tps544b20
+	http://www.ti.com/lit/gpn/tps544b25
+	http://www.ti.com/lit/gpn/tps544c20
+	http://www.ti.com/lit/gpn/tps544c25
   * Generic PMBus devices
     Prefix: 'pmbus'
     Addresses scanned: -
diff --git a/Documentation/input/alps.txt b/Documentation/input/alps.txt
index c86f2f1ae4f6..1fec1135791d 100644
--- a/Documentation/input/alps.txt
+++ b/Documentation/input/alps.txt
@@ -119,8 +119,10 @@ ALPS Absolute Mode - Protocol Version 2
  byte 5:  0   z6   z5   z4   z3   z2   z1   z0
 
 Protocol Version 2 DualPoint devices send standard PS/2 mouse packets for
-the DualPoint Stick. For non interleaved dualpoint devices the pointingstick
-buttons get reported separately in the PSM, PSR and PSL bits.
+the DualPoint Stick. The M, R and L bits signal the combined status of both
+the pointingstick and touchpad buttons, except for Dell dualpoint devices
+where the pointingstick buttons get reported separately in the PSM, PSR
+and PSL bits.
 
 Dualpoint device -- interleaved packet format
 ---------------------------------------------
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 611c52267d24..39ac6546d4a4 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -124,6 +124,8 @@ Code  Seq#(hex)	Include File		Comments
 'H'	00-7F	linux/hiddev.h		conflict!
 'H'	00-0F	linux/hidraw.h		conflict!
 'H'	01	linux/mei.h		conflict!
+'H'	02	linux/mei.h		conflict!
+'H'	03	linux/mei.h		conflict!
 'H'	00-0F	sound/asound.h		conflict!
 'H'	20-40	sound/asound_fm.h	conflict!
 'H'	80-8F	sound/sfnt_info.h	conflict!
@@ -301,6 +303,7 @@ Code  Seq#(hex)	Include File		Comments
 0xA3	80-8F	Port ACL		in development:
 					<mailto:tlewis@mindspring.com>
 0xA3	90-9F	linux/dtlk.h
+0xAA	00-3F	linux/uapi/linux/userfaultfd.h
 0xAB	00-1F	linux/nbd.h
 0xAC	00-1F	linux/raw.h
 0xAD	00	Netfilter device	in development:
@@ -314,6 +317,7 @@ Code  Seq#(hex)	Include File		Comments
 0xB3	00	linux/mmc/ioctl.h
 0xC0	00-0F	linux/usb/iowarrior.h
 0xCA	00-0F	uapi/misc/cxl.h
+0xCA	80-8F	uapi/scsi/cxlflash_ioctl.h
 0xCB	00-1F	CBM serial IEC bus	in development:
 					<mailto:michael.klein@puffin.lb.shuttle.de>
 0xCD	01	linux/reiserfs_fs.h
diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt
index 6466704d47b5..0ff6a466a05b 100644
--- a/Documentation/kbuild/kbuild.txt
+++ b/Documentation/kbuild/kbuild.txt
@@ -174,6 +174,11 @@ The output directory is often set using "O=..." on the commandline.
 
 The value can be overridden in which case the default value is ignored.
 
+KBUILD_SIGN_PIN
+--------------------------------------------------
+This variable allows a passphrase or PIN to be passed to the sign-file
+utility when signing kernel modules, if the private key requires such.
+
 KBUILD_MODPOST_WARN
 --------------------------------------------------
 KBUILD_MODPOST_WARN can be set to avoid errors in case of undefined
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index e63b446d973c..13f888a02a3d 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -952,6 +952,14 @@ When kbuild executes, the following steps are followed (roughly):
 	$(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic
 	mode) if this option is supported by $(AR).
 
+    ARCH_CPPFLAGS, ARCH_AFLAGS, ARCH_CFLAGS   Overrides the kbuild defaults
+
+	These variables are appended to the KBUILD_CPPFLAGS,
+	KBUILD_AFLAGS, and KBUILD_CFLAGS, respectively, after the
+	top-level Makefile has set any other flags. This provides a
+	means for an architecture to override the defaults.
+
+
 --- 6.2 Add prerequisites to archheaders:
 
 	The archheaders: rule is used to generate header files that
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index acbc1a3d0d91..78f69cdc9b3f 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -128,7 +128,7 @@ are:
   special place-holders for where the extracted documentation should
   go.
 
-- scripts/basic/docproc.c
+- scripts/docproc.c
 
   This is a program for converting SGML template files into SGML
   files. When a file is referenced it is searched for symbols
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1d6f0459cd7b..22a4b687ea5b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -910,6 +910,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Disable PIN 1 of APIC timer
 			Can be useful to work around chipset bugs.
 
+	dis_ucode_ldr	[X86] Disable the microcode loader.
+
 	dma_debug=off	If the kernel is compiled with DMA_API_DEBUG support,
 			this option disables the debugging code at boot.
 
@@ -1315,6 +1317,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			     <bus_id>,<clkrate>
 
 	i8042.debug	[HW] Toggle i8042 debug mode
+	i8042.unmask_kbd_data
+			[HW] Enable printing of interrupt data from the KBD port
+			     (disabled by default, and as a pre-condition
+			     requires that i8042.debug=1 be enabled)
 	i8042.direct	[HW] Put keyboard port into non-translated mode
 	i8042.dumbkbd	[HW] Pretend that controller can only read data from
 			     keyboard and cannot control its state
@@ -2279,6 +2285,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default parameter value of '0' causes the kernel
 			not to attempt recovery of lost locks.
 
+	nfs4.layoutstats_timer =
+			[NFSv4.2] Change the rate at which the kernel sends
+			layoutstats to the pNFS metadata server.
+
+			Setting this to value to 0 causes the kernel to use
+			whatever value is the default set by the layout
+			driver. A non-zero value sets the minimum interval
+			in seconds between layoutstats transmissions.
+
 	nfsd.nfs4_disable_idmapping=
 			[NFSv4] When set to the default of '1', the NFSv4
 			server will return only numeric uids and gids to
@@ -3135,22 +3150,35 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			in a given burst of a callback-flood test.
 
 	rcutorture.fqs_duration= [KNL]
-			Set duration of force_quiescent_state bursts.
+			Set duration of force_quiescent_state bursts
+			in microseconds.
 
 	rcutorture.fqs_holdoff= [KNL]
-			Set holdoff time within force_quiescent_state bursts.
+			Set holdoff time within force_quiescent_state bursts
+			in microseconds.
 
 	rcutorture.fqs_stutter= [KNL]
-			Set wait time between force_quiescent_state bursts.
+			Set wait time between force_quiescent_state bursts
+			in seconds.
+
+	rcutorture.gp_cond= [KNL]
+			Use conditional/asynchronous update-side
+			primitives, if available.
 
 	rcutorture.gp_exp= [KNL]
-			Use expedited update-side primitives.
+			Use expedited update-side primitives, if available.
 
 	rcutorture.gp_normal= [KNL]
-			Use normal (non-expedited) update-side primitives.
-			If both gp_exp and gp_normal are set, do both.
-			If neither gp_exp nor gp_normal are set, still
-			do both.
+			Use normal (non-expedited) asynchronous
+			update-side primitives, if available.
+
+	rcutorture.gp_sync= [KNL]
+			Use normal (non-expedited) synchronous
+			update-side primitives, if available.  If all
+			of rcutorture.gp_cond=, rcutorture.gp_exp=,
+			rcutorture.gp_normal=, and rcutorture.gp_sync=
+			are zero, rcutorture acts as if is interpreted
+			they are all non-zero.
 
 	rcutorture.n_barrier_cbs= [KNL]
 			Set callbacks/threads for rcu_barrier() testing.
@@ -3177,9 +3205,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set time (s) between CPU-hotplug operations, or
 			zero to disable CPU-hotplug testing.
 
-	rcutorture.torture_runnable= [BOOT]
-			Start rcutorture running at boot time.
-
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
 			allows some CPUs to go into dyntick-idle mode
@@ -3220,6 +3245,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Test RCU's dyntick-idle handling.  See also the
 			rcutorture.shuffle_interval parameter.
 
+	rcutorture.torture_runnable= [BOOT]
+			Start rcutorture running at boot time.
+
 	rcutorture.torture_type= [KNL]
 			Specify the RCU implementation to test.
 
@@ -4078,6 +4106,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			plus one apbt timer for broadcast timer.
 			x86_intel_mid_timer=apbt_only | lapic_and_apbt
 
+	xen_512gb_limit		[KNL,X86-64,XEN]
+			Restricts the kernel running paravirtualized under Xen
+			to use only up to 512 GB of RAM. The reason to do so is
+			crash analysis tools and Xen tools for doing domain
+			save/restore/migration must be enabled to handle larger
+			domains.
+
 	xen_emul_unplug=		[HW,X86,XEN]
 			Unplug Xen emulated devices
 			Format: [unplug0,][unplug1]
diff --git a/Documentation/mailbox.txt b/Documentation/mailbox.txt
index 1092ad9578da..7ed371c85204 100644
--- a/Documentation/mailbox.txt
+++ b/Documentation/mailbox.txt
@@ -51,8 +51,7 @@ struct demo_client {
  */
 static void message_from_remote(struct mbox_client *cl, void *mssg)
 {
-	struct demo_client *dc = container_of(mbox_client,
-						struct demo_client, cl);
+	struct demo_client *dc = container_of(cl, struct demo_client, cl);
 	if (dc->async) {
 		if (is_an_ack(mssg)) {
 			/* An ACK to our last sample sent */
@@ -68,8 +67,7 @@ static void message_from_remote(struct mbox_client *cl, void *mssg)
 
 static void sample_sent(struct mbox_client *cl, void *mssg, int r)
 {
-	struct demo_client *dc = container_of(mbox_client,
-						struct demo_client, cl);
+	struct demo_client *dc = container_of(cl, struct demo_client, cl);
 	complete(&dc->c);
 }
 
diff --git a/Documentation/md-cluster.txt b/Documentation/md-cluster.txt
index de1af7db3355..1b794369e03a 100644
--- a/Documentation/md-cluster.txt
+++ b/Documentation/md-cluster.txt
@@ -91,7 +91,7 @@ The algorithm is:
     this message inappropriate or redundant.
 
  3. sender write LVB.
-    sender down-convert MESSAGE from EX to CR
+    sender down-convert MESSAGE from EX to CW
     sender try to get EX of ACK
     [ wait until all receiver has *processed* the MESSAGE ]
 
@@ -112,7 +112,7 @@ The algorithm is:
     sender down-convert ACK from EX to CR
     sender release MESSAGE
     sender release TOKEN
-                               receiver upconvert to EX of MESSAGE
+                               receiver upconvert to PR of MESSAGE
                                receiver get CR of ACK
                                receiver release MESSAGE
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 13feb697271f..2ba8461b0631 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -194,22 +194,22 @@ There are some minimal guarantees that may be expected of a CPU:
  (*) On any given CPU, dependent memory accesses will be issued in order, with
      respect to itself.  This means that for:
 
-	ACCESS_ONCE(Q) = P; smp_read_barrier_depends(); D = ACCESS_ONCE(*Q);
+	WRITE_ONCE(Q, P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
 
      the CPU will issue the following memory operations:
 
 	Q = LOAD P, D = LOAD *Q
 
      and always in that order.  On most systems, smp_read_barrier_depends()
-     does nothing, but it is required for DEC Alpha.  The ACCESS_ONCE()
-     is required to prevent compiler mischief.  Please note that you
-     should normally use something like rcu_dereference() instead of
-     open-coding smp_read_barrier_depends().
+     does nothing, but it is required for DEC Alpha.  The READ_ONCE()
+     and WRITE_ONCE() are required to prevent compiler mischief.  Please
+     note that you should normally use something like rcu_dereference()
+     instead of open-coding smp_read_barrier_depends().
 
  (*) Overlapping loads and stores within a particular CPU will appear to be
      ordered within that CPU.  This means that for:
 
-	a = ACCESS_ONCE(*X); ACCESS_ONCE(*X) = b;
+	a = READ_ONCE(*X); WRITE_ONCE(*X, b);
 
      the CPU will only issue the following sequence of memory operations:
 
@@ -217,7 +217,7 @@ There are some minimal guarantees that may be expected of a CPU:
 
      And for:
 
-	ACCESS_ONCE(*X) = c; d = ACCESS_ONCE(*X);
+	WRITE_ONCE(*X, c); d = READ_ONCE(*X);
 
      the CPU will only issue:
 
@@ -228,11 +228,11 @@ There are some minimal guarantees that may be expected of a CPU:
 
 And there are a number of things that _must_ or _must_not_ be assumed:
 
- (*) It _must_not_ be assumed that the compiler will do what you want with
-     memory references that are not protected by ACCESS_ONCE().  Without
-     ACCESS_ONCE(), the compiler is within its rights to do all sorts
-     of "creative" transformations, which are covered in the Compiler
-     Barrier section.
+ (*) It _must_not_ be assumed that the compiler will do what you want
+     with memory references that are not protected by READ_ONCE() and
+     WRITE_ONCE().  Without them, the compiler is within its rights to
+     do all sorts of "creative" transformations, which are covered in
+     the Compiler Barrier section.
 
  (*) It _must_not_ be assumed that independent loads and stores will be issued
      in the order given.  This means that for:
@@ -520,8 +520,8 @@ following sequence of events:
 	{ A == 1, B == 2, C = 3, P == &A, Q == &C }
 	B = 4;
 	<write barrier>
-	ACCESS_ONCE(P) = &B
-			      Q = ACCESS_ONCE(P);
+	WRITE_ONCE(P, &B)
+			      Q = READ_ONCE(P);
 			      D = *Q;
 
 There's a clear data dependency here, and it would seem that by the end of the
@@ -547,8 +547,8 @@ between the address load and the data load:
 	{ A == 1, B == 2, C = 3, P == &A, Q == &C }
 	B = 4;
 	<write barrier>
-	ACCESS_ONCE(P) = &B
-			      Q = ACCESS_ONCE(P);
+	WRITE_ONCE(P, &B);
+			      Q = READ_ONCE(P);
 			      <data dependency barrier>
 			      D = *Q;
 
@@ -574,8 +574,8 @@ access:
 	{ M[0] == 1, M[1] == 2, M[3] = 3, P == 0, Q == 3 }
 	M[1] = 4;
 	<write barrier>
-	ACCESS_ONCE(P) = 1
-			      Q = ACCESS_ONCE(P);
+	WRITE_ONCE(P, 1);
+			      Q = READ_ONCE(P);
 			      <data dependency barrier>
 			      D = M[Q];
 
@@ -596,10 +596,10 @@ A load-load control dependency requires a full read memory barrier, not
 simply a data dependency barrier to make it work correctly.  Consider the
 following bit of code:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE(a);
 	if (q) {
 		<data dependency barrier>  /* BUG: No data dependency!!! */
-		p = ACCESS_ONCE(b);
+		p = READ_ONCE(b);
 	}
 
 This will not have the desired effect because there is no actual data
@@ -608,10 +608,10 @@ by attempting to predict the outcome in advance, so that other CPUs see
 the load from b as having happened before the load from a.  In such a
 case what's actually required is:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE(a);
 	if (q) {
 		<read barrier>
-		p = ACCESS_ONCE(b);
+		p = READ_ONCE(b);
 	}
 
 However, stores are not speculated.  This means that ordering -is- provided
@@ -619,7 +619,7 @@ for load-store control dependencies, as in the following example:
 
 	q = READ_ONCE_CTRL(a);
 	if (q) {
-		ACCESS_ONCE(b) = p;
+		WRITE_ONCE(b, p);
 	}
 
 Control dependencies pair normally with other types of barriers.  That
@@ -647,11 +647,11 @@ branches of the "if" statement as follows:
 	q = READ_ONCE_CTRL(a);
 	if (q) {
 		barrier();
-		ACCESS_ONCE(b) = p;
+		WRITE_ONCE(b, p);
 		do_something();
 	} else {
 		barrier();
-		ACCESS_ONCE(b) = p;
+		WRITE_ONCE(b, p);
 		do_something_else();
 	}
 
@@ -660,12 +660,12 @@ optimization levels:
 
 	q = READ_ONCE_CTRL(a);
 	barrier();
-	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
+	WRITE_ONCE(b, p);  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
-		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+		/* WRITE_ONCE(b, p); -- moved up, BUG!!! */
 		do_something();
 	} else {
-		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+		/* WRITE_ONCE(b, p); -- moved up, BUG!!! */
 		do_something_else();
 	}
 
@@ -676,7 +676,7 @@ assembly code even after all compiler optimizations have been applied.
 Therefore, if you need ordering in this example, you need explicit
 memory barriers, for example, smp_store_release():
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE(a);
 	if (q) {
 		smp_store_release(&b, p);
 		do_something();
@@ -690,10 +690,10 @@ ordering is guaranteed only when the stores differ, for example:
 
 	q = READ_ONCE_CTRL(a);
 	if (q) {
-		ACCESS_ONCE(b) = p;
+		WRITE_ONCE(b, p);
 		do_something();
 	} else {
-		ACCESS_ONCE(b) = r;
+		WRITE_ONCE(b, r);
 		do_something_else();
 	}
 
@@ -706,10 +706,10 @@ the needed conditional.  For example:
 
 	q = READ_ONCE_CTRL(a);
 	if (q % MAX) {
-		ACCESS_ONCE(b) = p;
+		WRITE_ONCE(b, p);
 		do_something();
 	} else {
-		ACCESS_ONCE(b) = r;
+		WRITE_ONCE(b, r);
 		do_something_else();
 	}
 
@@ -718,7 +718,7 @@ equal to zero, in which case the compiler is within its rights to
 transform the above code into the following:
 
 	q = READ_ONCE_CTRL(a);
-	ACCESS_ONCE(b) = p;
+	WRITE_ONCE(b, p);
 	do_something_else();
 
 Given this transformation, the CPU is not required to respect the ordering
@@ -731,10 +731,10 @@ one, perhaps as follows:
 	q = READ_ONCE_CTRL(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
 	if (q % MAX) {
-		ACCESS_ONCE(b) = p;
+		WRITE_ONCE(b, p);
 		do_something();
 	} else {
-		ACCESS_ONCE(b) = r;
+		WRITE_ONCE(b, r);
 		do_something_else();
 	}
 
@@ -746,18 +746,18 @@ You must also be careful not to rely too much on boolean short-circuit
 evaluation.  Consider this example:
 
 	q = READ_ONCE_CTRL(a);
-	if (a || 1 > 0)
-		ACCESS_ONCE(b) = 1;
+	if (q || 1 > 0)
+		WRITE_ONCE(b, 1);
 
 Because the first condition cannot fault and the second condition is
 always true, the compiler can transform this example as following,
 defeating control dependency:
 
 	q = READ_ONCE_CTRL(a);
-	ACCESS_ONCE(b) = 1;
+	WRITE_ONCE(b, 1);
 
 This example underscores the need to ensure that the compiler cannot
-out-guess your code.  More generally, although ACCESS_ONCE() does force
+out-guess your code.  More generally, although READ_ONCE() does force
 the compiler to actually emit code for a given load, it does not force
 the compiler to use the results.
 
@@ -769,7 +769,7 @@ x and y both being zero:
 	=======================   =======================
 	r1 = READ_ONCE_CTRL(x);   r2 = READ_ONCE_CTRL(y);
 	if (r1 > 0)               if (r2 > 0)
-	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
+	  WRITE_ONCE(y, 1);         WRITE_ONCE(x, 1);
 
 	assert(!(r1 == 1 && r2 == 1));
 
@@ -779,7 +779,7 @@ then adding the following CPU would guarantee a related assertion:
 
 	CPU 2
 	=====================
-	ACCESS_ONCE(x) = 2;
+	WRITE_ONCE(x, 2);
 
 	assert(!(r1 == 2 && r2 == 1 && x == 2)); /* FAILS!!! */
 
@@ -798,8 +798,7 @@ In summary:
 
   (*) Control dependencies must be headed by READ_ONCE_CTRL().
       Or, as a much less preferable alternative, interpose
-      be headed by READ_ONCE() or an ACCESS_ONCE() read and must
-      have smp_read_barrier_depends() between this read and the
+      smp_read_barrier_depends() between a READ_ONCE() and the
       control-dependent write.
 
   (*) Control dependencies can order prior loads against later stores.
@@ -815,15 +814,16 @@ In summary:
 
   (*) Control dependencies require at least one run-time conditional
       between the prior load and the subsequent store, and this
-      conditional must involve the prior load.  If the compiler
-      is able to optimize the conditional away, it will have also
-      optimized away the ordering.  Careful use of ACCESS_ONCE() can
-      help to preserve the needed conditional.
+      conditional must involve the prior load.  If the compiler is able
+      to optimize the conditional away, it will have also optimized
+      away the ordering.  Careful use of READ_ONCE_CTRL() READ_ONCE(),
+      and WRITE_ONCE() can help to preserve the needed conditional.
 
   (*) Control dependencies require that the compiler avoid reordering the
-      dependency into nonexistence.  Careful use of ACCESS_ONCE() or
-      barrier() can help to preserve your control dependency.  Please
-      see the Compiler Barrier section for more information.
+      dependency into nonexistence.  Careful use of READ_ONCE_CTRL()
+      or smp_read_barrier_depends() can help to preserve your control
+      dependency.  Please see the Compiler Barrier section for more
+      information.
 
   (*) Control dependencies pair normally with other types of barriers.
 
@@ -848,11 +848,11 @@ barrier, an acquire barrier, a release barrier, or a general barrier:
 
 	CPU 1		      CPU 2
 	===============	      ===============
-	ACCESS_ONCE(a) = 1;
+	WRITE_ONCE(a, 1);
 	<write barrier>
-	ACCESS_ONCE(b) = 2;   x = ACCESS_ONCE(b);
+	WRITE_ONCE(b, 2);     x = READ_ONCE(b);
 			      <read barrier>
-			      y = ACCESS_ONCE(a);
+			      y = READ_ONCE(a);
 
 Or:
 
@@ -860,7 +860,7 @@ Or:
 	===============	      ===============================
 	a = 1;
 	<write barrier>
-	ACCESS_ONCE(b) = &a;  x = ACCESS_ONCE(b);
+	WRITE_ONCE(b, &a);    x = READ_ONCE(b);
 			      <data dependency barrier>
 			      y = *x;
 
@@ -868,11 +868,11 @@ Or even:
 
 	CPU 1		      CPU 2
 	===============	      ===============================
-	r1 = ACCESS_ONCE(y);
+	r1 = READ_ONCE(y);
 	<general barrier>
-	ACCESS_ONCE(y) = 1;   if (r2 = ACCESS_ONCE(x)) {
+	WRITE_ONCE(y, 1);     if (r2 = READ_ONCE(x)) {
 			         <implicit control dependency>
-			         ACCESS_ONCE(y) = 1;
+			         WRITE_ONCE(y, 1);
 			      }
 
 	assert(r1 == 0 || r2 == 0);
@@ -886,11 +886,11 @@ versa:
 
 	CPU 1                               CPU 2
 	===================                 ===================
-	ACCESS_ONCE(a) = 1;  }----   --->{  v = ACCESS_ONCE(c);
-	ACCESS_ONCE(b) = 2;  }    \ /    {  w = ACCESS_ONCE(d);
+	WRITE_ONCE(a, 1);    }----   --->{  v = READ_ONCE(c);
+	WRITE_ONCE(b, 2);    }    \ /    {  w = READ_ONCE(d);
 	<write barrier>            \        <read barrier>
-	ACCESS_ONCE(c) = 3;  }    / \    {  x = ACCESS_ONCE(a);
-	ACCESS_ONCE(d) = 4;  }----   --->{  y = ACCESS_ONCE(b);
+	WRITE_ONCE(c, 3);    }    / \    {  x = READ_ONCE(a);
+	WRITE_ONCE(d, 4);    }----   --->{  y = READ_ONCE(b);
 
 
 EXAMPLES OF MEMORY BARRIER SEQUENCES
@@ -1340,10 +1340,10 @@ compiler from moving the memory accesses either side of it to the other side:
 
 	barrier();
 
-This is a general barrier -- there are no read-read or write-write variants
-of barrier().  However, ACCESS_ONCE() can be thought of as a weak form
-for barrier() that affects only the specific accesses flagged by the
-ACCESS_ONCE().
+This is a general barrier -- there are no read-read or write-write
+variants of barrier().  However, READ_ONCE() and WRITE_ONCE() can be
+thought of as weak forms of barrier() that affect only the specific
+accesses flagged by the READ_ONCE() or WRITE_ONCE().
 
 The barrier() function has the following effects:
 
@@ -1355,9 +1355,10 @@ The barrier() function has the following effects:
  (*) Within a loop, forces the compiler to load the variables used
      in that loop's conditional on each pass through that loop.
 
-The ACCESS_ONCE() function can prevent any number of optimizations that,
-while perfectly safe in single-threaded code, can be fatal in concurrent
-code.  Here are some examples of these sorts of optimizations:
+The READ_ONCE() and WRITE_ONCE() functions can prevent any number of
+optimizations that, while perfectly safe in single-threaded code, can
+be fatal in concurrent code.  Here are some examples of these sorts
+of optimizations:
 
  (*) The compiler is within its rights to reorder loads and stores
      to the same variable, and in some cases, the CPU is within its
@@ -1370,11 +1371,11 @@ code.  Here are some examples of these sorts of optimizations:
      Might result in an older value of x stored in a[1] than in a[0].
      Prevent both the compiler and the CPU from doing this as follows:
 
-	a[0] = ACCESS_ONCE(x);
-	a[1] = ACCESS_ONCE(x);
+	a[0] = READ_ONCE(x);
+	a[1] = READ_ONCE(x);
 
-     In short, ACCESS_ONCE() provides cache coherence for accesses from
-     multiple CPUs to a single variable.
+     In short, READ_ONCE() and WRITE_ONCE() provide cache coherence for
+     accesses from multiple CPUs to a single variable.
 
  (*) The compiler is within its rights to merge successive loads from
      the same variable.  Such merging can cause the compiler to "optimize"
@@ -1391,9 +1392,9 @@ code.  Here are some examples of these sorts of optimizations:
 		for (;;)
 			do_something_with(tmp);
 
-     Use ACCESS_ONCE() to prevent the compiler from doing this to you:
+     Use READ_ONCE() to prevent the compiler from doing this to you:
 
-	while (tmp = ACCESS_ONCE(a))
+	while (tmp = READ_ONCE(a))
 		do_something_with(tmp);
 
  (*) The compiler is within its rights to reload a variable, for example,
@@ -1415,9 +1416,9 @@ code.  Here are some examples of these sorts of optimizations:
      a was modified by some other CPU between the "while" statement and
      the call to do_something_with().
 
-     Again, use ACCESS_ONCE() to prevent the compiler from doing this:
+     Again, use READ_ONCE() to prevent the compiler from doing this:
 
-	while (tmp = ACCESS_ONCE(a))
+	while (tmp = READ_ONCE(a))
 		do_something_with(tmp);
 
      Note that if the compiler runs short of registers, it might save
@@ -1437,21 +1438,21 @@ code.  Here are some examples of these sorts of optimizations:
 
 	do { } while (0);
 
-     This transformation is a win for single-threaded code because it gets
-     rid of a load and a branch.  The problem is that the compiler will
-     carry out its proof assuming that the current CPU is the only one
-     updating variable 'a'.  If variable 'a' is shared, then the compiler's
-     proof will be erroneous.  Use ACCESS_ONCE() to tell the compiler
-     that it doesn't know as much as it thinks it does:
+     This transformation is a win for single-threaded code because it
+     gets rid of a load and a branch.  The problem is that the compiler
+     will carry out its proof assuming that the current CPU is the only
+     one updating variable 'a'.  If variable 'a' is shared, then the
+     compiler's proof will be erroneous.  Use READ_ONCE() to tell the
+     compiler that it doesn't know as much as it thinks it does:
 
-	while (tmp = ACCESS_ONCE(a))
+	while (tmp = READ_ONCE(a))
 		do_something_with(tmp);
 
      But please note that the compiler is also closely watching what you
-     do with the value after the ACCESS_ONCE().  For example, suppose you
+     do with the value after the READ_ONCE().  For example, suppose you
      do the following and MAX is a preprocessor macro with the value 1:
 
-	while ((tmp = ACCESS_ONCE(a)) % MAX)
+	while ((tmp = READ_ONCE(a)) % MAX)
 		do_something_with(tmp);
 
      Then the compiler knows that the result of the "%" operator applied
@@ -1475,12 +1476,12 @@ code.  Here are some examples of these sorts of optimizations:
      surprise if some other CPU might have stored to variable 'a' in the
      meantime.
 
-     Use ACCESS_ONCE() to prevent the compiler from making this sort of
+     Use WRITE_ONCE() to prevent the compiler from making this sort of
      wrong guess:
 
-	ACCESS_ONCE(a) = 0;
+	WRITE_ONCE(a, 0);
 	/* Code that does not store to variable a. */
-	ACCESS_ONCE(a) = 0;
+	WRITE_ONCE(a, 0);
 
  (*) The compiler is within its rights to reorder memory accesses unless
      you tell it not to.  For example, consider the following interaction
@@ -1509,40 +1510,43 @@ code.  Here are some examples of these sorts of optimizations:
 	}
 
      If the interrupt occurs between these two statement, then
-     interrupt_handler() might be passed a garbled msg.  Use ACCESS_ONCE()
+     interrupt_handler() might be passed a garbled msg.  Use WRITE_ONCE()
      to prevent this as follows:
 
 	void process_level(void)
 	{
-		ACCESS_ONCE(msg) = get_message();
-		ACCESS_ONCE(flag) = true;
+		WRITE_ONCE(msg, get_message());
+		WRITE_ONCE(flag, true);
 	}
 
 	void interrupt_handler(void)
 	{
-		if (ACCESS_ONCE(flag))
-			process_message(ACCESS_ONCE(msg));
+		if (READ_ONCE(flag))
+			process_message(READ_ONCE(msg));
 	}
 
-     Note that the ACCESS_ONCE() wrappers in interrupt_handler()
-     are needed if this interrupt handler can itself be interrupted
-     by something that also accesses 'flag' and 'msg', for example,
-     a nested interrupt or an NMI.  Otherwise, ACCESS_ONCE() is not
-     needed in interrupt_handler() other than for documentation purposes.
-     (Note also that nested interrupts do not typically occur in modern
-     Linux kernels, in fact, if an interrupt handler returns with
-     interrupts enabled, you will get a WARN_ONCE() splat.)
-
-     You should assume that the compiler can move ACCESS_ONCE() past
-     code not containing ACCESS_ONCE(), barrier(), or similar primitives.
-
-     This effect could also be achieved using barrier(), but ACCESS_ONCE()
-     is more selective:  With ACCESS_ONCE(), the compiler need only forget
-     the contents of the indicated memory locations, while with barrier()
-     the compiler must discard the value of all memory locations that
-     it has currented cached in any machine registers.  Of course,
-     the compiler must also respect the order in which the ACCESS_ONCE()s
-     occur, though the CPU of course need not do so.
+     Note that the READ_ONCE() and WRITE_ONCE() wrappers in
+     interrupt_handler() are needed if this interrupt handler can itself
+     be interrupted by something that also accesses 'flag' and 'msg',
+     for example, a nested interrupt or an NMI.  Otherwise, READ_ONCE()
+     and WRITE_ONCE() are not needed in interrupt_handler() other than
+     for documentation purposes.  (Note also that nested interrupts
+     do not typically occur in modern Linux kernels, in fact, if an
+     interrupt handler returns with interrupts enabled, you will get a
+     WARN_ONCE() splat.)
+
+     You should assume that the compiler can move READ_ONCE() and
+     WRITE_ONCE() past code not containing READ_ONCE(), WRITE_ONCE(),
+     barrier(), or similar primitives.
+
+     This effect could also be achieved using barrier(), but READ_ONCE()
+     and WRITE_ONCE() are more selective:  With READ_ONCE() and
+     WRITE_ONCE(), the compiler need only forget the contents of the
+     indicated memory locations, while with barrier() the compiler must
+     discard the value of all memory locations that it has currented
+     cached in any machine registers.  Of course, the compiler must also
+     respect the order in which the READ_ONCE()s and WRITE_ONCE()s occur,
+     though the CPU of course need not do so.
 
  (*) The compiler is within its rights to invent stores to a variable,
      as in the following example:
@@ -1562,16 +1566,16 @@ code.  Here are some examples of these sorts of optimizations:
      a branch.  Unfortunately, in concurrent code, this optimization
      could cause some other CPU to see a spurious value of 42 -- even
      if variable 'a' was never zero -- when loading variable 'b'.
-     Use ACCESS_ONCE() to prevent this as follows:
+     Use WRITE_ONCE() to prevent this as follows:
 
 	if (a)
-		ACCESS_ONCE(b) = a;
+		WRITE_ONCE(b, a);
 	else
-		ACCESS_ONCE(b) = 42;
+		WRITE_ONCE(b, 42);
 
      The compiler can also invent loads.  These are usually less
      damaging, but they can result in cache-line bouncing and thus in
-     poor performance and scalability.  Use ACCESS_ONCE() to prevent
+     poor performance and scalability.  Use READ_ONCE() to prevent
      invented loads.
 
  (*) For aligned memory locations whose size allows them to be accessed
@@ -1590,9 +1594,9 @@ code.  Here are some examples of these sorts of optimizations:
      This optimization can therefore be a win in single-threaded code.
      In fact, a recent bug (since fixed) caused GCC to incorrectly use
      this optimization in a volatile store.  In the absence of such bugs,
-     use of ACCESS_ONCE() prevents store tearing in the following example:
+     use of WRITE_ONCE() prevents store tearing in the following example:
 
-	ACCESS_ONCE(p) = 0x00010002;
+	WRITE_ONCE(p, 0x00010002);
 
      Use of packed structures can also result in load and store tearing,
      as in this example:
@@ -1609,22 +1613,23 @@ code.  Here are some examples of these sorts of optimizations:
 	foo2.b = foo1.b;
 	foo2.c = foo1.c;
 
-     Because there are no ACCESS_ONCE() wrappers and no volatile markings,
-     the compiler would be well within its rights to implement these three
-     assignment statements as a pair of 32-bit loads followed by a pair
-     of 32-bit stores.  This would result in load tearing on 'foo1.b'
-     and store tearing on 'foo2.b'.  ACCESS_ONCE() again prevents tearing
-     in this example:
+     Because there are no READ_ONCE() or WRITE_ONCE() wrappers and no
+     volatile markings, the compiler would be well within its rights to
+     implement these three assignment statements as a pair of 32-bit
+     loads followed by a pair of 32-bit stores.  This would result in
+     load tearing on 'foo1.b' and store tearing on 'foo2.b'.  READ_ONCE()
+     and WRITE_ONCE() again prevent tearing in this example:
 
 	foo2.a = foo1.a;
-	ACCESS_ONCE(foo2.b) = ACCESS_ONCE(foo1.b);
+	WRITE_ONCE(foo2.b, READ_ONCE(foo1.b));
 	foo2.c = foo1.c;
 
-All that aside, it is never necessary to use ACCESS_ONCE() on a variable
-that has been marked volatile.  For example, because 'jiffies' is marked
-volatile, it is never necessary to say ACCESS_ONCE(jiffies).  The reason
-for this is that ACCESS_ONCE() is implemented as a volatile cast, which
-has no effect when its argument is already marked volatile.
+All that aside, it is never necessary to use READ_ONCE() and
+WRITE_ONCE() on a variable that has been marked volatile.  For example,
+because 'jiffies' is marked volatile, it is never necessary to
+say READ_ONCE(jiffies).  The reason for this is that READ_ONCE() and
+WRITE_ONCE() are implemented as volatile casts, which has no effect when
+its argument is already marked volatile.
 
 Please note that these compiler barriers have no direct effect on the CPU,
 which may then reorder things however it wishes.
@@ -1646,14 +1651,15 @@ The Linux kernel has eight basic CPU memory barriers:
 All memory barriers except the data dependency barriers imply a compiler
 barrier. Data dependencies do not impose any additional compiler ordering.
 
-Aside: In the case of data dependencies, the compiler would be expected to
-issue the loads in the correct order (eg. `a[b]` would have to load the value
-of b before loading a[b]), however there is no guarantee in the C specification
-that the compiler may not speculate the value of b (eg. is equal to 1) and load
-a before b (eg. tmp = a[1]; if (b != 1) tmp = a[b]; ). There is also the
-problem of a compiler reloading b after having loaded a[b], thus having a newer
-copy of b than a[b]. A consensus has not yet been reached about these problems,
-however the ACCESS_ONCE macro is a good place to start looking.
+Aside: In the case of data dependencies, the compiler would be expected
+to issue the loads in the correct order (eg. `a[b]` would have to load
+the value of b before loading a[b]), however there is no guarantee in
+the C specification that the compiler may not speculate the value of b
+(eg. is equal to 1) and load a before b (eg. tmp = a[1]; if (b != 1)
+tmp = a[b]; ). There is also the problem of a compiler reloading b after
+having loaded a[b], thus having a newer copy of b than a[b]. A consensus
+has not yet been reached about these problems, however the READ_ONCE()
+macro is a good place to start looking.
 
 SMP memory barriers are reduced to compiler barriers on uniprocessor compiled
 systems because it is assumed that a CPU will appear to be self-consistent,
@@ -1848,15 +1854,10 @@ RELEASE are to the same lock variable, but only from the perspective of
 another CPU not holding that lock.  In short, a ACQUIRE followed by an
 RELEASE may -not- be assumed to be a full memory barrier.
 
-Similarly, the reverse case of a RELEASE followed by an ACQUIRE does not
-imply a full memory barrier.  If it is necessary for a RELEASE-ACQUIRE
-pair to produce a full barrier, the ACQUIRE can be followed by an
-smp_mb__after_unlock_lock() invocation.  This will produce a full barrier
-if either (a) the RELEASE and the ACQUIRE are executed by the same
-CPU or task, or (b) the RELEASE and ACQUIRE act on the same variable.
-The smp_mb__after_unlock_lock() primitive is free on many architectures.
-Without smp_mb__after_unlock_lock(), the CPU's execution of the critical
-sections corresponding to the RELEASE and the ACQUIRE can cross, so that:
+Similarly, the reverse case of a RELEASE followed by an ACQUIRE does
+not imply a full memory barrier.  Therefore, the CPU's execution of the
+critical sections corresponding to the RELEASE and the ACQUIRE can cross,
+so that:
 
 	*A = a;
 	RELEASE M
@@ -1894,29 +1895,6 @@ the RELEASE would simply complete, thereby avoiding the deadlock.
 	a sleep-unlock race, but the locking primitive needs to resolve
 	such races properly in any case.
 
-With smp_mb__after_unlock_lock(), the two critical sections cannot overlap.
-For example, with the following code, the store to *A will always be
-seen by other CPUs before the store to *B:
-
-	*A = a;
-	RELEASE M
-	ACQUIRE N
-	smp_mb__after_unlock_lock();
-	*B = b;
-
-The operations will always occur in one of the following orders:
-
-	STORE *A, RELEASE, ACQUIRE, smp_mb__after_unlock_lock(), STORE *B
-	STORE *A, ACQUIRE, RELEASE, smp_mb__after_unlock_lock(), STORE *B
-	ACQUIRE, STORE *A, RELEASE, smp_mb__after_unlock_lock(), STORE *B
-
-If the RELEASE and ACQUIRE were instead both operating on the same lock
-variable, only the first of these alternatives can occur.  In addition,
-the more strongly ordered systems may rule out some of the above orders.
-But in any case, as noted earlier, the smp_mb__after_unlock_lock()
-ensures that the store to *A will always be seen as happening before
-the store to *B.
-
 Locks and semaphores may not provide any guarantee of ordering on UP compiled
 systems, and so cannot be counted on in such a situation to actually achieve
 anything at all - especially with respect to I/O accesses - unless combined
@@ -2126,12 +2104,12 @@ three CPUs; then should the following sequence of events occur:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	ACCESS_ONCE(*A) = a;		ACCESS_ONCE(*E) = e;
+	WRITE_ONCE(*A, a);		WRITE_ONCE(*E, e);
 	ACQUIRE M			ACQUIRE Q
-	ACCESS_ONCE(*B) = b;		ACCESS_ONCE(*F) = f;
-	ACCESS_ONCE(*C) = c;		ACCESS_ONCE(*G) = g;
+	WRITE_ONCE(*B, b);		WRITE_ONCE(*F, f);
+	WRITE_ONCE(*C, c);		WRITE_ONCE(*G, g);
 	RELEASE M			RELEASE Q
-	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*H) = h;
+	WRITE_ONCE(*D, d);		WRITE_ONCE(*H, h);
 
 Then there is no guarantee as to what order CPU 3 will see the accesses to *A
 through *H occur in, other than the constraints imposed by the separate locks
@@ -2147,40 +2125,6 @@ But it won't see any of:
 	*E, *F or *G following RELEASE Q
 
 
-However, if the following occurs:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	ACCESS_ONCE(*A) = a;
-	ACQUIRE M		     [1]
-	ACCESS_ONCE(*B) = b;
-	ACCESS_ONCE(*C) = c;
-	RELEASE M	     [1]
-	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*E) = e;
-					ACQUIRE M		     [2]
-					smp_mb__after_unlock_lock();
-					ACCESS_ONCE(*F) = f;
-					ACCESS_ONCE(*G) = g;
-					RELEASE M	     [2]
-					ACCESS_ONCE(*H) = h;
-
-CPU 3 might see:
-
-	*E, ACQUIRE M [1], *C, *B, *A, RELEASE M [1],
-		ACQUIRE M [2], *H, *F, *G, RELEASE M [2], *D
-
-But assuming CPU 1 gets the lock first, CPU 3 won't see any of:
-
-	*B, *C, *D, *F, *G or *H preceding ACQUIRE M [1]
-	*A, *B or *C following RELEASE M [1]
-	*F, *G or *H preceding ACQUIRE M [2]
-	*A, *B, *C, *E, *F or *G following RELEASE M [2]
-
-Note that the smp_mb__after_unlock_lock() is critically important
-here: Without it CPU 3 might see some of the above orderings.
-Without smp_mb__after_unlock_lock(), the accesses are not guaranteed
-to be seen in order unless CPU 3 holds lock M.
-
 
 ACQUIRES VS I/O ACCESSES
 ------------------------
@@ -2383,9 +2327,7 @@ about the state (old or new) implies an SMP-conditional general memory barrier
 explicit lock operations, described later).  These include:
 
 	xchg();
-	cmpxchg();
 	atomic_xchg();			atomic_long_xchg();
-	atomic_cmpxchg();		atomic_long_cmpxchg();
 	atomic_inc_return();		atomic_long_inc_return();
 	atomic_dec_return();		atomic_long_dec_return();
 	atomic_add_return();		atomic_long_add_return();
@@ -2398,7 +2340,9 @@ explicit lock operations, described later).  These include:
 	test_and_clear_bit();
 	test_and_change_bit();
 
-	/* when succeeds (returns 1) */
+	/* when succeeds */
+	cmpxchg();
+	atomic_cmpxchg();		atomic_long_cmpxchg();
 	atomic_add_unless();		atomic_long_add_unless();
 
 These are used for such things as implementing ACQUIRE-class and RELEASE-class
@@ -2881,11 +2825,11 @@ A programmer might take it for granted that the CPU will perform memory
 operations in exactly the order specified, so that if the CPU is, for example,
 given the following piece of code to execute:
 
-	a = ACCESS_ONCE(*A);
-	ACCESS_ONCE(*B) = b;
-	c = ACCESS_ONCE(*C);
-	d = ACCESS_ONCE(*D);
-	ACCESS_ONCE(*E) = e;
+	a = READ_ONCE(*A);
+	WRITE_ONCE(*B, b);
+	c = READ_ONCE(*C);
+	d = READ_ONCE(*D);
+	WRITE_ONCE(*E, e);
 
 they would then expect that the CPU will complete the memory operation for each
 instruction before moving on to the next one, leading to a definite sequence of
@@ -2932,12 +2876,12 @@ However, it is guaranteed that a CPU will be self-consistent: it will see its
 _own_ accesses appear to be correctly ordered, without the need for a memory
 barrier.  For instance with the following code:
 
-	U = ACCESS_ONCE(*A);
-	ACCESS_ONCE(*A) = V;
-	ACCESS_ONCE(*A) = W;
-	X = ACCESS_ONCE(*A);
-	ACCESS_ONCE(*A) = Y;
-	Z = ACCESS_ONCE(*A);
+	U = READ_ONCE(*A);
+	WRITE_ONCE(*A, V);
+	WRITE_ONCE(*A, W);
+	X = READ_ONCE(*A);
+	WRITE_ONCE(*A, Y);
+	Z = READ_ONCE(*A);
 
 and assuming no intervention by an external influence, it can be assumed that
 the final result will appear to be:
@@ -2953,13 +2897,14 @@ accesses:
 	U=LOAD *A, STORE *A=V, STORE *A=W, X=LOAD *A, STORE *A=Y, Z=LOAD *A
 
 in that order, but, without intervention, the sequence may have almost any
-combination of elements combined or discarded, provided the program's view of
-the world remains consistent.  Note that ACCESS_ONCE() is -not- optional
-in the above example, as there are architectures where a given CPU might
-reorder successive loads to the same location.  On such architectures,
-ACCESS_ONCE() does whatever is necessary to prevent this, for example, on
-Itanium the volatile casts used by ACCESS_ONCE() cause GCC to emit the
-special ld.acq and st.rel instructions that prevent such reordering.
+combination of elements combined or discarded, provided the program's view
+of the world remains consistent.  Note that READ_ONCE() and WRITE_ONCE()
+are -not- optional in the above example, as there are architectures
+where a given CPU might reorder successive loads to the same location.
+On such architectures, READ_ONCE() and WRITE_ONCE() do whatever is
+necessary to prevent this, for example, on Itanium the volatile casts
+used by READ_ONCE() and WRITE_ONCE() cause GCC to emit the special ld.acq
+and st.rel instructions (respectively) that prevent such reordering.
 
 The compiler may also combine, discard or defer elements of the sequence before
 the CPU even sees them.
@@ -2973,13 +2918,14 @@ may be reduced to:
 
 	*A = W;
 
-since, without either a write barrier or an ACCESS_ONCE(), it can be
+since, without either a write barrier or an WRITE_ONCE(), it can be
 assumed that the effect of the storage of V to *A is lost.  Similarly:
 
 	*A = Y;
 	Z = *A;
 
-may, without a memory barrier or an ACCESS_ONCE(), be reduced to:
+may, without a memory barrier or an READ_ONCE() and WRITE_ONCE(), be
+reduced to:
 
 	*A = Y;
 	Z = Y;
diff --git a/Documentation/men-chameleon-bus.txt b/Documentation/men-chameleon-bus.txt
new file mode 100644
index 000000000000..30ded732027e
--- /dev/null
+++ b/Documentation/men-chameleon-bus.txt
@@ -0,0 +1,163 @@
+                               MEN Chameleon Bus
+                               =================
+
+Table of Contents
+=================
+1 Introduction
+    1.1 Scope of this Document
+    1.2 Limitations of the current implementation
+2 Architecture
+    2.1 MEN Chameleon Bus
+    2.2 Carrier Devices
+    2.3 Parser
+3 Resource handling
+    3.1 Memory Resources
+    3.2 IRQs
+4 Writing an MCB driver
+    4.1 The driver structure
+    4.2 Probing and attaching
+    4.3 Initializing the driver
+
+
+1 Introduction
+===============
+  This document describes the architecture and implementation of the MEN
+  Chameleon Bus (called MCB throughout this document).
+
+1.1 Scope of this Document
+---------------------------
+  This document is intended to be a short overview of the current
+  implementation and does by no means describe the complete possibilities of MCB
+  based devices.
+
+1.2 Limitations of the current implementation
+----------------------------------------------
+  The current implementation is limited to PCI and PCIe based carrier devices
+  that only use a single memory resource and share the PCI legacy IRQ.  Not
+  implemented are:
+  - Multi-resource MCB devices like the VME Controller or M-Module carrier.
+  - MCB devices that need another MCB device, like SRAM for a DMA Controller's
+    buffer descriptors or a video controller's video memory.
+  - A per-carrier IRQ domain for carrier devices that have one (or more) IRQs
+    per MCB device like PCIe based carriers with MSI or MSI-X support.
+
+2 Architecture
+===============
+  MCB is divided into 3 functional blocks:
+  - The MEN Chameleon Bus itself,
+  - drivers for MCB Carrier Devices and
+  - the parser for the Chameleon table.
+
+2.1 MEN Chameleon Bus
+----------------------
+   The MEN Chameleon Bus is an artificial bus system that attaches to a so
+   called Chameleon FPGA device found on some hardware produced my MEN Mikro
+   Elektronik GmbH. These devices are multi-function devices implemented in a
+   single FPGA and usually attached via some sort of PCI or PCIe link. Each
+   FPGA contains a header section describing the content of the FPGA. The
+   header lists the device id, PCI BAR, offset from the beginning of the PCI
+   BAR, size in the FPGA, interrupt number and some other properties currently
+   not handled by the MCB implementation.
+
+2.2 Carrier Devices
+--------------------
+   A carrier device is just an abstraction for the real world physical bus the
+   Chameleon FPGA is attached to. Some IP Core drivers may need to interact with
+   properties of the carrier device (like querying the IRQ number of a PCI
+   device). To provide abstraction from the real hardware bus, an MCB carrier
+   device provides callback methods to translate the driver's MCB function calls
+   to hardware related function calls. For example a carrier device may
+   implement the get_irq() method which can be translated into a hardware bus
+   query for the IRQ number the device should use.
+
+2.3 Parser
+-----------
+   The parser reads the first 512 bytes of a Chameleon device and parses the
+   Chameleon table. Currently the parser only supports the Chameleon v2 variant
+   of the Chameleon table but can easily be adopted to support an older or
+   possible future variant. While parsing the table's entries new MCB devices
+   are allocated and their resources are assigned according to the resource
+   assignment in the Chameleon table. After resource assignment is finished, the
+   MCB devices are registered at the MCB and thus at the driver core of the
+   Linux kernel.
+
+3 Resource handling
+====================
+  The current implementation assigns exactly one memory and one IRQ resource
+  per MCB device. But this is likely going to change in the future.
+
+3.1 Memory Resources
+---------------------
+   Each MCB device has exactly one memory resource, which can be requested from
+   the MCB bus. This memory resource is the physical address of the MCB device
+   inside the carrier and is intended to be passed to ioremap() and friends. It
+   is already requested from the kernel by calling request_mem_region().
+
+3.2 IRQs
+---------
+   Each MCB device has exactly one IRQ resource, which can be requested from the
+   MCB bus. If a carrier device driver implements the ->get_irq() callback
+   method, the IRQ number assigned by the carrier device will be returned,
+   otherwise the IRQ number inside the Chameleon table will be returned. This
+   number is suitable to be passed to request_irq().
+
+4 Writing an MCB driver
+=======================
+
+4.1 The driver structure
+-------------------------
+    Each MCB driver has a structure to identify the device driver as well as
+    device ids which identify the IP Core inside the FPGA. The driver structure
+    also contains callback methods which get executed on driver probe and
+    removal from the system.
+
+
+  static const struct mcb_device_id foo_ids[] = {
+          { .device = 0x123 },
+          { }
+  };
+  MODULE_DEVICE_TABLE(mcb, foo_ids);
+
+  static struct mcb_driver foo_driver = {
+          driver = {
+                  .name = "foo-bar",
+                  .owner = THIS_MODULE,
+          },
+          .probe = foo_probe,
+          .remove = foo_remove,
+          .id_table = foo_ids,
+  };
+
+4.2 Probing and attaching
+--------------------------
+   When a driver is loaded and the MCB devices it services are found, the MCB
+   core will call the driver's probe callback method. When the driver is removed
+   from the system, the MCB core will call the driver's remove callback method.
+
+
+  static init foo_probe(struct mcb_device *mdev, const struct mcb_device_id *id);
+  static void foo_remove(struct mcb_device *mdev);
+
+4.3 Initializing the driver
+----------------------------
+   When the kernel is booted or your foo driver module is inserted, you have to
+   perform driver initialization. Usually it is enough to register your driver
+   module at the MCB core.
+
+
+  static int __init foo_init(void)
+  {
+          return mcb_register_driver(&foo_driver);
+  }
+  module_init(foo_init);
+
+  static void __exit foo_exit(void)
+  {
+          mcb_unregister_driver(&foo_driver);
+  }
+  module_exit(foo_exit);
+
+   The module_mcb_driver() macro can be used to reduce the above code.
+
+
+  module_mcb_driver(foo_driver);
diff --git a/Documentation/misc-devices/mei/mei.txt b/Documentation/misc-devices/mei/mei.txt
index 8d47501bba0a..91c1fa34f48b 100644
--- a/Documentation/misc-devices/mei/mei.txt
+++ b/Documentation/misc-devices/mei/mei.txt
@@ -96,7 +96,7 @@ A code snippet for an application communicating with Intel AMTHI client:
 IOCTL
 =====
 
-The Intel MEI Driver supports the following IOCTL command:
+The Intel MEI Driver supports the following IOCTL commands:
 	IOCTL_MEI_CONNECT_CLIENT	Connect to firmware Feature (client).
 
 	usage:
@@ -125,6 +125,49 @@ The Intel MEI Driver supports the following IOCTL command:
         data that can be sent or received. (e.g. if MTU=2K, can send
         requests up to bytes 2k and received responses up to 2k bytes).
 
+	IOCTL_MEI_NOTIFY_SET: enable or disable event notifications
+
+	Usage:
+		uint32_t enable;
+		ioctl(fd, IOCTL_MEI_NOTIFY_SET, &enable);
+
+	Inputs:
+		uint32_t enable = 1;
+		or
+		uint32_t enable[disable] = 0;
+
+	Error returns:
+		EINVAL	Wrong IOCTL Number
+		ENODEV	Device  is not initialized or the client not connected
+		ENOMEM	Unable to allocate memory to client internal data.
+		EFAULT	Fatal Error (e.g. Unable to access user input data)
+		EOPNOTSUPP if the device doesn't support the feature
+
+	Notes:
+	The client must be connected in order to enable notification events
+
+
+	IOCTL_MEI_NOTIFY_GET : retrieve event
+
+	Usage:
+		uint32_t event;
+		ioctl(fd, IOCTL_MEI_NOTIFY_GET, &event);
+
+	Outputs:
+		1 - if an event is pending
+		0 - if there is no even pending
+
+	Error returns:
+		EINVAL	Wrong IOCTL Number
+		ENODEV	Device is not initialized or the client not connected
+		ENOMEM	Unable to allocate memory to client internal data.
+		EFAULT	Fatal Error (e.g. Unable to access user input data)
+		EOPNOTSUPP if the device doesn't support the feature
+
+	Notes:
+	The client must be connected and event notification has to be enabled
+	in order to receive an event
+
 
 Intel ME Applications
 =====================
diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt
index c72702ec1ded..a78bf1ffa68c 100644
--- a/Documentation/module-signing.txt
+++ b/Documentation/module-signing.txt
@@ -89,6 +89,32 @@ This has a number of options available:
      their signatures checked without causing a dependency loop.
 
 
+ (4) "File name or PKCS#11 URI of module signing key" (CONFIG_MODULE_SIG_KEY)
+
+     Setting this option to something other than its default of
+     "certs/signing_key.pem" will disable the autogeneration of signing keys
+     and allow the kernel modules to be signed with a key of your choosing.
+     The string provided should identify a file containing both a private key
+     and its corresponding X.509 certificate in PEM form, or — on systems where
+     the OpenSSL ENGINE_pkcs11 is functional — a PKCS#11 URI as defined by
+     RFC7512. In the latter case, the PKCS#11 URI should reference both a
+     certificate and a private key.
+
+     If the PEM file containing the private key is encrypted, or if the
+     PKCS#11 token requries a PIN, this can be provided at build time by
+     means of the KBUILD_SIGN_PIN variable.
+
+
+ (5) "Additional X.509 keys for default system keyring" (CONFIG_SYSTEM_TRUSTED_KEYS)
+
+     This option can be set to the filename of a PEM-encoded file containing
+     additional certificates which will be included in the system keyring by
+     default.
+
+Note that enabling module signing adds a dependency on the OpenSSL devel
+packages to the kernel build processes for the tool that does the signing.
+
+
 =======================
 GENERATING SIGNING KEYS
 =======================
@@ -100,16 +126,16 @@ it can be deleted or stored securely.  The public key gets built into the
 kernel so that it can be used to check the signatures as the modules are
 loaded.
 
-Under normal conditions, the kernel build will automatically generate a new
-keypair using openssl if one does not exist in the files:
+Under normal conditions, when CONFIG_MODULE_SIG_KEY is unchanged from its
+default, the kernel build will automatically generate a new keypair using
+openssl if one does not exist in the file:
 
-	signing_key.priv
-	signing_key.x509
+	certs/signing_key.pem
 
 during the building of vmlinux (the public part of the key needs to be built
 into vmlinux) using parameters in the:
 
-	x509.genkey
+	certs/x509.genkey
 
 file (which is also generated if it does not already exist).
 
@@ -135,8 +161,12 @@ kernel sources tree and the openssl command.  The following is an example to
 generate the public/private key files:
 
 	openssl req -new -nodes -utf8 -sha256 -days 36500 -batch -x509 \
-	   -config x509.genkey -outform DER -out signing_key.x509 \
-	   -keyout signing_key.priv
+	   -config x509.genkey -outform PEM -out kernel_key.pem \
+	   -keyout kernel_key.pem
+
+The full pathname for the resulting kernel_key.pem file can then be specified
+in the CONFIG_MODULE_SIG_KEY option, and the certificate and key therein will
+be used instead of an autogenerated keypair.
 
 
 =========================
@@ -152,10 +182,9 @@ in a keyring called ".system_keyring" that can be seen by:
 	302d2d52 I------     1 perm 1f010000     0     0 asymmetri Fedora kernel signing key: d69a84e6bce3d216b979e9505b3e3ef9a7118079: X509.RSA a7118079 []
 	...
 
-Beyond the public key generated specifically for module signing, any file
-placed in the kernel source root directory or the kernel build root directory
-whose name is suffixed with ".x509" will be assumed to be an X.509 public key
-and will be added to the keyring.
+Beyond the public key generated specifically for module signing, additional
+trusted certificates can be provided in a PEM-encoded file referenced by the
+CONFIG_SYSTEM_TRUSTED_KEYS configuration option.
 
 Further, the architecture code may take public keys from a hardware store and
 add those in also (e.g. from the UEFI key database).
@@ -181,7 +210,7 @@ To manually sign a module, use the scripts/sign-file tool available in
 the Linux kernel source tree.  The script requires 4 arguments:
 
 	1.  The hash algorithm (e.g., sha256)
-	2.  The private key filename
+	2.  The private key filename or PKCS#11 URI
 	3.  The public key filename
 	4.  The kernel module to be signed
 
@@ -194,6 +223,9 @@ The hash algorithm used does not have to match the one configured, but if it
 doesn't, you should make sure that hash algorithm is either built into the
 kernel or can be loaded without requiring itself.
 
+If the private key requires a passphrase or PIN, it can be provided in the
+$KBUILD_SIGN_PIN environment variable.
+
 
 ============================
 SIGNED MODULES AND STRIPPING
diff --git a/Documentation/networking/6lowpan.txt b/Documentation/networking/6lowpan.txt
new file mode 100644
index 000000000000..a7dc7e939c7a
--- /dev/null
+++ b/Documentation/networking/6lowpan.txt
@@ -0,0 +1,50 @@
+
+Netdev private dataroom for 6lowpan interfaces:
+
+All 6lowpan able net devices, means all interfaces with ARPHRD_6LOWPAN,
+must have "struct lowpan_priv" placed at beginning of netdev_priv.
+
+The priv_size of each interface should be calculate by:
+
+ dev->priv_size = LOWPAN_PRIV_SIZE(LL_6LOWPAN_PRIV_DATA);
+
+Where LL_PRIV_6LOWPAN_DATA is sizeof linklayer 6lowpan private data struct.
+To access the LL_PRIV_6LOWPAN_DATA structure you can cast:
+
+ lowpan_priv(dev)-priv;
+
+to your LL_6LOWPAN_PRIV_DATA structure.
+
+Before registering the lowpan netdev interface you must run:
+
+ lowpan_netdev_setup(dev, LOWPAN_LLTYPE_FOOBAR);
+
+wheres LOWPAN_LLTYPE_FOOBAR is a define for your 6LoWPAN linklayer type of
+enum lowpan_lltypes.
+
+Example to evaluate the private usually you can do:
+
+static inline sturct lowpan_priv_foobar *
+lowpan_foobar_priv(struct net_device *dev)
+{
+	return (sturct lowpan_priv_foobar *)lowpan_priv(dev)->priv;
+}
+
+switch (dev->type) {
+case ARPHRD_6LOWPAN:
+	lowpan_priv = lowpan_priv(dev);
+	/* do great stuff which is ARPHRD_6LOWPAN related */
+	switch (lowpan_priv->lltype) {
+	case LOWPAN_LLTYPE_FOOBAR:
+		/* do 802.15.4 6LoWPAN handling here */
+		lowpan_foobar_priv(dev)->bar = foo;
+		break;
+	...
+	}
+	break;
+...
+}
+
+In case of generic 6lowpan branch ("net/6lowpan") you can remove the check
+on ARPHRD_6LOWPAN, because you can be sure that these function are called
+by ARPHRD_6LOWPAN interfaces.
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index b48d4a149411..fd1a1aad49a9 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -510,7 +510,7 @@ solution for a couple of reasons:
 
   4.1.2 RAW socket option CAN_RAW_ERR_FILTER
 
-  As described in chapter 3.4 the CAN interface driver can generate so
+  As described in chapter 3.3 the CAN interface driver can generate so
   called Error Message Frames that can optionally be passed to the user
   application in the same way as other CAN frames. The possible
   errors are divided into different error classes that may be filtered
@@ -1152,7 +1152,7 @@ solution for a couple of reasons:
     $ ip link set canX type can restart
 
   Note that a restart will also create a CAN error message frame (see
-  also chapter 3.4).
+  also chapter 3.3).
 
   6.6 CAN FD (flexible data rate) driver support
 
diff --git a/Documentation/networking/dsa/bcm_sf2.txt b/Documentation/networking/dsa/bcm_sf2.txt
new file mode 100644
index 000000000000..d999d0c1c5b8
--- /dev/null
+++ b/Documentation/networking/dsa/bcm_sf2.txt
@@ -0,0 +1,114 @@
+Broadcom Starfighter 2 Ethernet switch driver
+=============================================
+
+Broadcom's Starfighter 2 Ethernet switch hardware block is commonly found and
+deployed in the following products:
+
+- xDSL gateways such as BCM63138
+- streaming/multimedia Set Top Box such as BCM7445
+- Cable Modem/residential gateways such as BCM7145/BCM3390
+
+The switch is typically deployed in a configuration involving between 5 to 13
+ports, offering a range of built-in and customizable interfaces:
+
+- single integrated Gigabit PHY
+- quad integrated Gigabit PHY
+- quad external Gigabit PHY w/ MDIO multiplexer
+- integrated MoCA PHY
+- several external MII/RevMII/GMII/RGMII interfaces
+
+The switch also supports specific congestion control features which allow MoCA
+fail-over not to lose packets during a MoCA role re-election, as well as out of
+band back-pressure to the host CPU network interface when downstream interfaces
+are connected at a lower speed.
+
+The switch hardware block is typically interfaced using MMIO accesses and
+contains a bunch of sub-blocks/registers:
+
+* SWITCH_CORE: common switch registers
+* SWITCH_REG: external interfaces switch register
+* SWITCH_MDIO: external MDIO bus controller (there is another one in SWITCH_CORE,
+  which is used for indirect PHY accesses)
+* SWITCH_INDIR_RW: 64-bits wide register helper block
+* SWITCH_INTRL2_0/1: Level-2 interrupt controllers
+* SWITCH_ACB: Admission control block
+* SWITCH_FCB: Fail-over control block
+
+Implementation details
+======================
+
+The driver is located in drivers/net/dsa/bcm_sf2.c and is implemented as a DSA
+driver; see Documentation/networking/dsa/dsa.txt for details on the subsytem
+and what it provides.
+
+The SF2 switch is configured to enable a Broadcom specific 4-bytes switch tag
+which gets inserted by the switch for every packet forwarded to the CPU
+interface, conversely, the CPU network interface should insert a similar tag for
+packets entering the CPU port. The tag format is described in
+net/dsa/tag_brcm.c.
+
+Overall, the SF2 driver is a fairly regular DSA driver; there are a few
+specifics covered below.
+
+Device Tree probing
+-------------------
+
+The DSA platform device driver is probed using a specific compatible string
+provided in net/dsa/dsa.c. The reason for that is because the DSA subsystem gets
+registered as a platform device driver currently. DSA will provide the needed
+device_node pointers which are then accessible by the switch driver setup
+function to setup resources such as register ranges and interrupts. This
+currently works very well because none of the of_* functions utilized by the
+driver require a struct device to be bound to a struct device_node, but things
+may change in the future.
+
+MDIO indirect accesses
+----------------------
+
+Due to a limitation in how Broadcom switches have been designed, external
+Broadcom switches connected to a SF2 require the use of the DSA slave MDIO bus
+in order to properly configure them. By default, the SF2 pseudo-PHY address, and
+an external switch pseudo-PHY address will both be snooping for incoming MDIO
+transactions, since they are at the same address (30), resulting in some kind of
+"double" programming. Using DSA, and setting ds->phys_mii_mask accordingly, we
+selectively divert reads and writes towards external Broadcom switches
+pseudo-PHY addresses. Newer revisions of the SF2 hardware have introduced a
+configurable pseudo-PHY address which circumvents the initial design limitation.
+
+Multimedia over CoAxial (MoCA) interfaces
+-----------------------------------------
+
+MoCA interfaces are fairly specific and require the use of a firmware blob which
+gets loaded onto the MoCA processor(s) for packet processing. The switch
+hardware contains logic which will assert/de-assert link states accordingly for
+the MoCA interface whenever the MoCA coaxial cable gets disconnected or the
+firmware gets reloaded. The SF2 driver relies on such events to properly set its
+MoCA interface carrier state and properly report this to the networking stack.
+
+The MoCA interfaces are supported using the PHY library's fixed PHY/emulated PHY
+device and the switch driver registers a fixed_link_update callback for such
+PHYs which reflects the link state obtained from the interrupt handler.
+
+
+Power Management
+----------------
+
+Whenever possible, the SF2 driver tries to minimize the overall switch power
+consumption by applying a combination of:
+
+- turning off internal buffers/memories
+- disabling packet processing logic
+- putting integrated PHYs in IDDQ/low-power
+- reducing the switch core clock based on the active port count
+- enabling and advertising EEE
+- turning off RGMII data processing logic when the link goes down
+
+Wake-on-LAN
+-----------
+
+Wake-on-LAN is currently implemented by utilizing the host processor Ethernet
+MAC controller wake-on logic. Whenever Wake-on-LAN is requested, an intersection
+between the user request and the supported host Ethernet interface WoL
+capabilities is done and the intersection result gets configured. During
+system-wide suspend/resume, only ports not participating in Wake-on-LAN are
+disabled.
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
new file mode 100644
index 000000000000..aa9c1f9313cd
--- /dev/null
+++ b/Documentation/networking/dsa/dsa.txt
@@ -0,0 +1,615 @@
+Distributed Switch Architecture
+===============================
+
+Introduction
+============
+
+This document describes the Distributed Switch Architecture (DSA) subsystem
+design principles, limitations, interactions with other subsystems, and how to
+develop drivers for this subsystem as well as a TODO for developers interested
+in joining the effort.
+
+Design principles
+=================
+
+The Distributed Switch Architecture is a subsystem which was primarily designed
+to support Marvell Ethernet switches (MV88E6xxx, a.k.a Linkstreet product line)
+using Linux, but has since evolved to support other vendors as well.
+
+The original philosophy behind this design was to be able to use unmodified
+Linux tools such as bridge, iproute2, ifconfig to work transparently whether
+they configured/queried a switch port network device or a regular network
+device.
+
+An Ethernet switch is typically comprised of multiple front-panel ports, and one
+or more CPU or management port. The DSA subsystem currently relies on the
+presence of a management port connected to an Ethernet controller capable of
+receiving Ethernet frames from the switch. This is a very common setup for all
+kinds of Ethernet switches found in Small Home and Office products: routers,
+gateways, or even top-of-the rack switches. This host Ethernet controller will
+be later referred to as "master" and "cpu" in DSA terminology and code.
+
+The D in DSA stands for Distributed, because the subsystem has been designed
+with the ability to configure and manage cascaded switches on top of each other
+using upstream and downstream Ethernet links between switches. These specific
+ports are referred to as "dsa" ports in DSA terminology and code. A collection
+of multiple switches connected to each other is called a "switch tree".
+
+For each front-panel port, DSA will create specialized network devices which are
+used as controlling and data-flowing endpoints for use by the Linux networking
+stack. These specialized network interfaces are referred to as "slave" network
+interfaces in DSA terminology and code.
+
+The ideal case for using DSA is when an Ethernet switch supports a "switch tag"
+which is a hardware feature making the switch insert a specific tag for each
+Ethernet frames it received to/from specific ports to help the management
+interface figure out:
+
+- what port is this frame coming from
+- what was the reason why this frame got forwarded
+- how to send CPU originated traffic to specific ports
+
+The subsystem does support switches not capable of inserting/stripping tags, but
+the features might be slightly limited in that case (traffic separation relies
+on Port-based VLAN IDs).
+
+Note that DSA does not currently create network interfaces for the "cpu" and
+"dsa" ports because:
+
+- the "cpu" port is the Ethernet switch facing side of the management
+  controller, and as such, would create a duplication of feature, since you
+  would get two interfaces for the same conduit: master netdev, and "cpu" netdev
+
+- the "dsa" port(s) are just conduits between two or more switches, and as such
+  cannot really be used as proper network interfaces either, only the
+  downstream, or the top-most upstream interface makes sense with that model
+
+Switch tagging protocols
+------------------------
+
+DSA currently supports 4 different tagging protocols, and a tag-less mode as
+well. The different protocols are implemented in:
+
+net/dsa/tag_trailer.c: Marvell's 4 trailer tag mode (legacy)
+net/dsa/tag_dsa.c: Marvell's original DSA tag
+net/dsa/tag_edsa.c: Marvell's enhanced DSA tag
+net/dsa/tag_brcm.c: Broadcom's 4 bytes tag
+
+The exact format of the tag protocol is vendor specific, but in general, they
+all contain something which:
+
+- identifies which port the Ethernet frame came from/should be sent to
+- provides a reason why this frame was forwarded to the management interface
+
+Master network devices
+----------------------
+
+Master network devices are regular, unmodified Linux network device drivers for
+the CPU/management Ethernet interface. Such a driver might occasionally need to
+know whether DSA is enabled (e.g.: to enable/disable specific offload features),
+but the DSA subsystem has been proven to work with industry standard drivers:
+e1000e, mv643xx_eth etc. without having to introduce modifications to these
+drivers. Such network devices are also often referred to as conduit network
+devices since they act as a pipe between the host processor and the hardware
+Ethernet switch.
+
+Networking stack hooks
+----------------------
+
+When a master netdev is used with DSA, a small hook is placed in in the
+networking stack is in order to have the DSA subsystem process the Ethernet
+switch specific tagging protocol. DSA accomplishes this by registering a
+specific (and fake) Ethernet type (later becoming skb->protocol) with the
+networking stack, this is also known as a ptype or packet_type. A typical
+Ethernet Frame receive sequence looks like this:
+
+Master network device (e.g.: e1000e):
+
+Receive interrupt fires:
+- receive function is invoked
+- basic packet processing is done: getting length, status etc.
+- packet is prepared to be processed by the Ethernet layer by calling
+  eth_type_trans
+
+net/ethernet/eth.c:
+
+eth_type_trans(skb, dev)
+	if (dev->dsa_ptr != NULL)
+		-> skb->protocol = ETH_P_XDSA
+
+drivers/net/ethernet/*:
+
+netif_receive_skb(skb)
+	-> iterate over registered packet_type
+		-> invoke handler for ETH_P_XDSA, calls dsa_switch_rcv()
+
+net/dsa/dsa.c:
+	-> dsa_switch_rcv()
+		-> invoke switch tag specific protocol handler in
+		   net/dsa/tag_*.c
+
+net/dsa/tag_*.c:
+	-> inspect and strip switch tag protocol to determine originating port
+	-> locate per-port network device
+	-> invoke eth_type_trans() with the DSA slave network device
+	-> invoked netif_receive_skb()
+
+Past this point, the DSA slave network devices get delivered regular Ethernet
+frames that can be processed by the networking stack.
+
+Slave network devices
+---------------------
+
+Slave network devices created by DSA are stacked on top of their master network
+device, each of these network interfaces will be responsible for being a
+controlling and data-flowing end-point for each front-panel port of the switch.
+These interfaces are specialized in order to:
+
+- insert/remove the switch tag protocol (if it exists) when sending traffic
+  to/from specific switch ports
+- query the switch for ethtool operations: statistics, link state,
+  Wake-on-LAN, register dumps...
+- external/internal PHY management: link, auto-negotiation etc.
+
+These slave network devices have custom net_device_ops and ethtool_ops function
+pointers which allow DSA to introduce a level of layering between the networking
+stack/ethtool, and the switch driver implementation.
+
+Upon frame transmission from these slave network devices, DSA will look up which
+switch tagging protocol is currently registered with these network devices, and
+invoke a specific transmit routine which takes care of adding the relevant
+switch tag in the Ethernet frames.
+
+These frames are then queued for transmission using the master network device
+ndo_start_xmit() function, since they contain the appropriate switch tag, the
+Ethernet switch will be able to process these incoming frames from the
+management interface and delivers these frames to the physical switch port.
+
+Graphical representation
+------------------------
+
+Summarized, this is basically how DSA looks like from a network device
+perspective:
+
+
+			|---------------------------
+			| CPU network device (eth0)|
+			----------------------------
+			| <tag added by switch     |
+			|                          |
+			|                          |
+			|        tag added by CPU> |
+		|--------------------------------------------|
+		| Switch driver				     |
+		|--------------------------------------------|
+                    ||        ||         ||
+		|-------|  |-------|  |-------|
+		| sw0p0 |  | sw0p1 |  | sw0p2 |
+		|-------|  |-------|  |-------|
+
+Slave MDIO bus
+--------------
+
+In order to be able to read to/from a switch PHY built into it, DSA creates a
+slave MDIO bus which allows a specific switch driver to divert and intercept
+MDIO reads/writes towards specific PHY addresses. In most MDIO-connected
+switches, these functions would utilize direct or indirect PHY addressing mode
+to return standard MII registers from the switch builtin PHYs, allowing the PHY
+library and/or to return link status, link partner pages, auto-negotiation
+results etc..
+
+For Ethernet switches which have both external and internal MDIO busses, the
+slave MII bus can be utilized to mux/demux MDIO reads and writes towards either
+internal or external MDIO devices this switch might be connected to: internal
+PHYs, external PHYs, or even external switches.
+
+Data structures
+---------------
+
+DSA data structures are defined in include/net/dsa.h as well as
+net/dsa/dsa_priv.h.
+
+dsa_chip_data: platform data configuration for a given switch device, this
+structure describes a switch device's parent device, its address, as well as
+various properties of its ports: names/labels, and finally a routing table
+indication (when cascading switches)
+
+dsa_platform_data: platform device configuration data which can reference a
+collection of dsa_chip_data structure if multiples switches are cascaded, the
+master network device this switch tree is attached to needs to be referenced
+
+dsa_switch_tree: structure assigned to the master network device under
+"dsa_ptr", this structure references a dsa_platform_data structure as well as
+the tagging protocol supported by the switch tree, and which receive/transmit
+function hooks should be invoked, information about the directly attached switch
+is also provided: CPU port. Finally, a collection of dsa_switch are referenced
+to address individual switches in the tree.
+
+dsa_switch: structure describing a switch device in the tree, referencing a
+dsa_switch_tree as a backpointer, slave network devices, master network device,
+and a reference to the backing dsa_switch_driver
+
+dsa_switch_driver: structure referencing function pointers, see below for a full
+description.
+
+Design limitations
+==================
+
+DSA is a platform device driver
+-------------------------------
+
+DSA is implemented as a DSA platform device driver which is convenient because
+it will register the entire DSA switch tree attached to a master network device
+in one-shot, facilitating the device creation and simplifying the device driver
+model a bit, this comes however with a number of limitations:
+
+- building DSA and its switch drivers as modules is currently not working
+- the device driver parenting does not necessarily reflect the original
+  bus/device the switch can be created from
+- supporting non-MDIO and non-MMIO (platform) switches is not possible
+
+Limits on the number of devices and ports
+-----------------------------------------
+
+DSA currently limits the number of maximum switches within a tree to 4
+(DSA_MAX_SWITCHES), and the number of ports per switch to 12 (DSA_MAX_PORTS).
+These limits could be extended to support larger configurations would this need
+arise.
+
+Lack of CPU/DSA network devices
+-------------------------------
+
+DSA does not currently create slave network devices for the CPU or DSA ports, as
+described before. This might be an issue in the following cases:
+
+- inability to fetch switch CPU port statistics counters using ethtool, which
+  can make it harder to debug MDIO switch connected using xMII interfaces
+
+- inability to configure the CPU port link parameters based on the Ethernet
+  controller capabilities attached to it: http://patchwork.ozlabs.org/patch/509806/
+
+- inability to configure specific VLAN IDs / trunking VLANs between switches
+  when using a cascaded setup
+
+Common pitfalls using DSA setups
+--------------------------------
+
+Once a master network device is configured to use DSA (dev->dsa_ptr becomes
+non-NULL), and the switch behind it expects a tagging protocol, this network
+interface can only exclusively be used as a conduit interface. Sending packets
+directly through this interface (e.g.: opening a socket using this interface)
+will not make us go through the switch tagging protocol transmit function, so
+the Ethernet switch on the other end, expecting a tag will typically drop this
+frame.
+
+Slave network devices check that the master network device is UP before allowing
+you to administratively bring UP these slave network devices. A common
+configuration mistake is forgetting to bring UP the master network device first.
+
+Interactions with other subsystems
+==================================
+
+DSA currently leverages the following subsystems:
+
+- MDIO/PHY library: drivers/net/phy/phy.c, mdio_bus.c
+- Switchdev: net/switchdev/*
+- Device Tree for various of_* functions
+- HWMON: drivers/hwmon/*
+
+MDIO/PHY library
+----------------
+
+Slave network devices exposed by DSA may or may not be interfacing with PHY
+devices (struct phy_device as defined in include/linux/phy.h), but the DSA
+subsystem deals with all possible combinations:
+
+- internal PHY devices, built into the Ethernet switch hardware
+- external PHY devices, connected via an internal or external MDIO bus
+- internal PHY devices, connected via an internal MDIO bus
+- special, non-autonegotiated or non MDIO-managed PHY devices: SFPs, MoCA; a.k.a
+  fixed PHYs
+
+The PHY configuration is done by the dsa_slave_phy_setup() function and the
+logic basically looks like this:
+
+- if Device Tree is used, the PHY device is looked up using the standard
+  "phy-handle" property, if found, this PHY device is created and registered
+  using of_phy_connect()
+
+- if Device Tree is used, and the PHY device is "fixed", that is, conforms to
+  the definition of a non-MDIO managed PHY as defined in
+  Documentation/devicetree/bindings/net/fixed-link.txt, the PHY is registered
+  and connected transparently using the special fixed MDIO bus driver
+
+- finally, if the PHY is built into the switch, as is very common with
+  standalone switch packages, the PHY is probed using the slave MII bus created
+  by DSA
+
+
+SWITCHDEV
+---------
+
+DSA directly utilizes SWITCHDEV when interfacing with the bridge layer, and
+more specifically with its VLAN filtering portion when configuring VLANs on top
+of per-port slave network devices. Since DSA primarily deals with
+MDIO-connected switches, although not exclusively, SWITCHDEV's
+prepare/abort/commit phases are often simplified into a prepare phase which
+checks whether the operation is supporte by the DSA switch driver, and a commit
+phase which applies the changes.
+
+As of today, the only SWITCHDEV objects supported by DSA are the FDB and VLAN
+objects.
+
+Device Tree
+-----------
+
+DSA features a standardized binding which is documented in
+Documentation/devicetree/bindings/net/dsa/dsa.txt. PHY/MDIO library helper
+functions such as of_get_phy_mode(), of_phy_connect() are also used to query
+per-port PHY specific details: interface connection, MDIO bus location etc..
+
+HWMON
+-----
+
+Some switch drivers feature internal temperature sensors which are exposed as
+regular HWMON devices in /sys/class/hwmon/.
+
+Driver development
+==================
+
+DSA switch drivers need to implement a dsa_switch_driver structure which will
+contain the various members described below.
+
+register_switch_driver() registers this dsa_switch_driver in its internal list
+of drivers to probe for. unregister_switch_driver() does the exact opposite.
+
+Unless requested differently by setting the priv_size member accordingly, DSA
+does not allocate any driver private context space.
+
+Switch configuration
+--------------------
+
+- priv_size: additional size needed by the switch driver for its private context
+
+- tag_protocol: this is to indicate what kind of tagging protocol is supported,
+  should be a valid value from the dsa_tag_protocol enum
+
+- probe: probe routine which will be invoked by the DSA platform device upon
+  registration to test for the presence/absence of a switch device. For MDIO
+  devices, it is recommended to issue a read towards internal registers using
+  the switch pseudo-PHY and return whether this is a supported device. For other
+  buses, return a non-NULL string
+
+- setup: setup function for the switch, this function is responsible for setting
+  up the dsa_switch_driver private structure with all it needs: register maps,
+  interrupts, mutexes, locks etc.. This function is also expected to properly
+  configure the switch to separate all network interfaces from each other, that
+  is, they should be isolated by the switch hardware itself, typically by creating
+  a Port-based VLAN ID for each port and allowing only the CPU port and the
+  specific port to be in the forwarding vector. Ports that are unused by the
+  platform should be disabled. Past this function, the switch is expected to be
+  fully configured and ready to serve any kind of request. It is recommended
+  to issue a software reset of the switch during this setup function in order to
+  avoid relying on what a previous software agent such as a bootloader/firmware
+  may have previously configured.
+
+- set_addr: Some switches require the programming of the management interface's
+  Ethernet MAC address, switch drivers can also disable ageing of MAC addresses
+  on the management interface and "hardcode"/"force" this MAC address for the
+  CPU/management interface as an optimization
+
+PHY devices and link management
+-------------------------------
+
+- get_phy_flags: Some switches are interfaced to various kinds of Ethernet PHYs,
+  if the PHY library PHY driver needs to know about information it cannot obtain
+  on its own (e.g.: coming from switch memory mapped registers), this function
+  should return a 32-bits bitmask of "flags", that is private between the switch
+  driver and the Ethernet PHY driver in drivers/net/phy/*.
+
+- phy_read: Function invoked by the DSA slave MDIO bus when attempting to read
+  the switch port MDIO registers. If unavailable, return 0xffff for each read.
+  For builtin switch Ethernet PHYs, this function should allow reading the link
+  status, auto-negotiation results, link partner pages etc..
+
+- phy_write: Function invoked by the DSA slave MDIO bus when attempting to write
+  to the switch port MDIO registers. If unavailable return a negative error
+  code.
+
+- poll_link: Function invoked by DSA to query the link state of the switch
+  builtin Ethernet PHYs, per port. This function is responsible for calling
+  netif_carrier_{on,off} when appropriate, and can be used to poll all ports in a
+  single call. Executes from workqueue context.
+
+- adjust_link: Function invoked by the PHY library when a slave network device
+  is attached to a PHY device. This function is responsible for appropriately
+  configuring the switch port link parameters: speed, duplex, pause based on
+  what the phy_device is providing.
+
+- fixed_link_update: Function invoked by the PHY library, and specifically by
+  the fixed PHY driver asking the switch driver for link parameters that could
+  not be auto-negotiated, or obtained by reading the PHY registers through MDIO.
+  This is particularly useful for specific kinds of hardware such as QSGMII,
+  MoCA or other kinds of non-MDIO managed PHYs where out of band link
+  information is obtained
+
+Ethtool operations
+------------------
+
+- get_strings: ethtool function used to query the driver's strings, will
+  typically return statistics strings, private flags strings etc.
+
+- get_ethtool_stats: ethtool function used to query per-port statistics and
+  return their values. DSA overlays slave network devices general statistics:
+  RX/TX counters from the network device, with switch driver specific statistics
+  per port
+
+- get_sset_count: ethtool function used to query the number of statistics items
+
+- get_wol: ethtool function used to obtain Wake-on-LAN settings per-port, this
+  function may, for certain implementations also query the master network device
+  Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN
+
+- set_wol: ethtool function used to configure Wake-on-LAN settings per-port,
+  direct counterpart to set_wol with similar restrictions
+
+- set_eee: ethtool function which is used to configure a switch port EEE (Green
+  Ethernet) settings, can optionally invoke the PHY library to enable EEE at the
+  PHY level if relevant. This function should enable EEE at the switch port MAC
+  controller and data-processing logic
+
+- get_eee: ethtool function which is used to query a switch port EEE settings,
+  this function should return the EEE state of the switch port MAC controller
+  and data-processing logic as well as query the PHY for its currently configured
+  EEE settings
+
+- get_eeprom_len: ethtool function returning for a given switch the EEPROM
+  length/size in bytes
+
+- get_eeprom: ethtool function returning for a given switch the EEPROM contents
+
+- set_eeprom: ethtool function writing specified data to a given switch EEPROM
+
+- get_regs_len: ethtool function returning the register length for a given
+  switch
+
+- get_regs: ethtool function returning the Ethernet switch internal register
+  contents. This function might require user-land code in ethtool to
+  pretty-print register values and registers
+
+Power management
+----------------
+
+- suspend: function invoked by the DSA platform device when the system goes to
+  suspend, should quiesce all Ethernet switch activities, but keep ports
+  participating in Wake-on-LAN active as well as additional wake-up logic if
+  supported
+
+- resume: function invoked by the DSA platform device when the system resumes,
+  should resume all Ethernet switch activities and re-configure the switch to be
+  in a fully active state
+
+- port_enable: function invoked by the DSA slave network device ndo_open
+  function when a port is administratively brought up, this function should be
+  fully enabling a given switch port. DSA takes care of marking the port with
+  BR_STATE_BLOCKING if the port is a bridge member, or BR_STATE_FORWARDING if it
+  was not, and propagating these changes down to the hardware
+
+- port_disable: function invoked by the DSA slave network device ndo_close
+  function when a port is administratively brought down, this function should be
+  fully disabling a given switch port. DSA takes care of marking the port with
+  BR_STATE_DISABLED and propagating changes to the hardware if this port is
+  disabled while being a bridge member
+
+Hardware monitoring
+-------------------
+
+These callbacks are only available if CONFIG_NET_DSA_HWMON is enabled:
+
+- get_temp: this function queries the given switch for its temperature
+
+- get_temp_limit: this function returns the switch current maximum temperature
+  limit
+
+- set_temp_limit: this function configures the maximum temperature limit allowed
+
+- get_temp_alarm: this function returns the critical temperature threshold
+  returning an alarm notification
+
+See Documentation/hwmon/sysfs-interface for details.
+
+Bridge layer
+------------
+
+- port_join_bridge: bridge layer function invoked when a given switch port is
+  added to a bridge, this function should be doing the necessary at the switch
+  level to permit the joining port from being added to the relevant logical
+  domain for it to ingress/egress traffic with other members of the bridge. DSA
+  does nothing but calculate a bitmask of switch ports currently members of the
+  specified bridge being requested the join
+
+- port_leave_bridge: bridge layer function invoked when a given switch port is
+  removed from a bridge, this function should be doing the necessary at the
+  switch level to deny the leaving port from ingress/egress traffic from the
+  remaining bridge members. When the port leaves the bridge, it should be aged
+  out at the switch hardware for the switch to (re) learn MAC addresses behind
+  this port. DSA calculates the bitmask of ports still members of the bridge
+  being left
+
+- port_stp_update: bridge layer function invoked when a given switch port STP
+  state is computed by the bridge layer and should be propagated to switch
+  hardware to forward/block/learn traffic. The switch driver is responsible for
+  computing a STP state change based on current and asked parameters and perform
+  the relevant ageing based on the intersection results
+
+Bridge VLAN filtering
+---------------------
+
+- port_pvid_get: bridge layer function invoked when a Port-based VLAN ID is
+  queried for the given switch port
+
+- port_pvid_set: bridge layer function invoked when a Port-based VLAN ID needs
+  to be configured on the given switch port
+
+- port_vlan_add: bridge layer function invoked when a VLAN is configured
+  (tagged or untagged) for the given switch port
+
+- port_vlan_del: bridge layer function invoked when a VLAN is removed from the
+  given switch port
+
+- vlan_getnext: bridge layer function invoked to query the next configured VLAN
+  in the switch, i.e. returns the bitmaps of members and untagged ports
+
+- port_fdb_add: bridge layer function invoked when the bridge wants to install a
+  Forwarding Database entry, the switch hardware should be programmed with the
+  specified address in the specified VLAN Id in the forwarding database
+  associated with this VLAN ID
+
+Note: VLAN ID 0 corresponds to the port private database, which, in the context
+of DSA, would be the its port-based VLAN, used by the associated bridge device.
+
+- port_fdb_del: bridge layer function invoked when the bridge wants to remove a
+  Forwarding Database entry, the switch hardware should be programmed to delete
+  the specified MAC address from the specified VLAN ID if it was mapped into
+  this port forwarding database
+
+TODO
+====
+
+The platform device problem
+---------------------------
+DSA is currently implemented as a platform device driver which is far from ideal
+as was discussed in this thread:
+
+http://permalink.gmane.org/gmane.linux.network/329848
+
+This basically prevents the device driver model to be properly used and applied,
+and support non-MDIO, non-MMIO Ethernet connected switches.
+
+Another problem with the platform device driver approach is that it prevents the
+use of a modular switch drivers build due to a circular dependency, illustrated
+here:
+
+http://comments.gmane.org/gmane.linux.network/345803
+
+Attempts of reworking this has been done here:
+
+https://lwn.net/Articles/643149/
+
+Making SWITCHDEV and DSA converge towards an unified codebase
+-------------------------------------------------------------
+
+SWITCHDEV properly takes care of abstracting the networking stack with offload
+capable hardware, but does not enforce a strict switch device driver model. On
+the other DSA enforces a fairly strict device driver model, and deals with most
+of the switch specific. At some point we should envision a merger between these
+two subsystems and get the best of both worlds.
+
+Other hanging fruits
+--------------------
+
+- making the number of ports fully dynamic and not dependent on DSA_MAX_PORTS
+- allowing more than one CPU/management interface:
+  http://comments.gmane.org/gmane.linux.network/365657
+- porting more drivers from other vendors:
+  http://comments.gmane.org/gmane.linux.network/365510
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 5fae7704daab..ebe94f2cab98 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -586,6 +586,21 @@ tcp_min_tso_segs - INTEGER
 	if available window is too small.
 	Default: 2
 
+tcp_pacing_ss_ratio - INTEGER
+	sk->sk_pacing_rate is set by TCP stack using a ratio applied
+	to current rate. (current_rate = cwnd * mss / srtt)
+	If TCP is in slow start, tcp_pacing_ss_ratio is applied
+	to let TCP probe for bigger speeds, assuming cwnd can be
+	doubled every other RTT.
+	Default: 200
+
+tcp_pacing_ca_ratio - INTEGER
+	sk->sk_pacing_rate is set by TCP stack using a ratio applied
+	to current rate. (current_rate = cwnd * mss / srtt)
+	If TCP is in congestion avoidance phase, tcp_pacing_ca_ratio
+	is applied to conservatively probe for bigger throughput.
+	Default: 120
+
 tcp_tso_win_divisor - INTEGER
 	This allows control over what percentage of the congestion window
 	can be consumed by a single TSO frame.
@@ -1181,6 +1196,16 @@ tag - INTEGER
 	Allows you to write a number, which can be used as required.
 	Default value is 0.
 
+xfrm4_gc_thresh - INTEGER
+	The threshold at which we will start garbage collecting for IPv4
+	destination cache entries.  At twice this value the system will
+	refuse new allocations.
+
+igmp_link_local_mcast_reports - BOOLEAN
+	Enable IGMP reports for link local multicast groups in the
+	224.0.0.X range.
+	Default TRUE
+
 Alexey Kuznetsov.
 kuznet@ms2.inr.ac.ru
 
@@ -1215,14 +1240,20 @@ flowlabel_consistency - BOOLEAN
 	FALSE: disabled
 	Default: TRUE
 
-auto_flowlabels - BOOLEAN
-	Automatically generate flow labels based based on a flow hash
-	of the packet. This allows intermediate devices, such as routers,
-	to idenfify packet flows for mechanisms like Equal Cost Multipath
+auto_flowlabels - INTEGER
+	Automatically generate flow labels based on a flow hash of the
+	packet. This allows intermediate devices, such as routers, to
+	identify packet flows for mechanisms like Equal Cost Multipath
 	Routing (see RFC 6438).
-	TRUE: enabled
-	FALSE: disabled
-	Default: false
+	0: automatic flow labels are completely disabled
+	1: automatic flow labels are enabled by default, they can be
+	   disabled on a per socket basis using the IPV6_AUTOFLOWLABEL
+	   socket option
+	2: automatic flow labels are allowed, they may be enabled on a
+	   per socket basis using the IPV6_AUTOFLOWLABEL socket option
+	3: automatic flow labels are enabled and enforced, they cannot
+	   be disabled by the socket option
+	Default: 1
 
 flowlabel_state_ranges - BOOLEAN
 	Split the flow label number space into two ranges. 0-0x7FFFF is
@@ -1340,6 +1371,14 @@ accept_ra_from_local - BOOLEAN
 	   disabled if accept_ra_from_local is disabled
                on a specific interface.
 
+accept_ra_min_hop_limit - INTEGER
+	Minimum hop limit Information in Router Advertisement.
+
+	Hop limit Information in Router Advertisement less than this
+	variable shall be ignored.
+
+	Default: 1
+
 accept_ra_pinfo - BOOLEAN
 	Learn Prefix Information in Router Advertisement.
 
@@ -1435,6 +1474,11 @@ mtu - INTEGER
 	Default Maximum Transfer Unit
 	Default: 1280 (IPv6 required minimum)
 
+ip_nonlocal_bind - BOOLEAN
+	If set, allows processes to bind() to non-local IPv6 addresses,
+	which can be quite useful - but may break some applications.
+	Default: 0
+
 router_probe_interval - INTEGER
 	Minimum interval (in seconds) between Router Probing described
 	in RFC4191.
@@ -1455,6 +1499,13 @@ router_solicitations - INTEGER
 	routers are present.
 	Default: 3
 
+use_oif_addrs_only - BOOLEAN
+	When enabled, the candidate source addresses for destinations
+	routed via this interface are restricted to the set of addresses
+	configured on this interface (vis. RFC 6724, section 4).
+
+	Default: false
+
 use_tempaddr - INTEGER
 	Preference for Privacy Extensions (RFC3041).
 	  <= 0 : disable Privacy Extensions
@@ -1591,6 +1642,11 @@ ratelimit - INTEGER
 	otherwise the minimal space between responses in milliseconds.
 	Default: 1000
 
+xfrm6_gc_thresh - INTEGER
+	The threshold at which we will start garbage collecting for IPv6
+	destination cache entries.  At twice this value the system will
+	refuse new allocations.
+
 
 IPv6 Update by:
 Pekka Savola <pekkas@netcore.fi>
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
index e655e2453c98..d64a14714236 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/stmmac.txt
@@ -135,12 +135,8 @@ struct plat_stmmacenet_data {
 	int maxmtu;
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	void (*bus_setup)(void __iomem *ioaddr);
-	void *(*setup)(struct platform_device *pdev);
-	void (*free)(struct platform_device *pdev, void *priv);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
-	void *custom_cfg;
-	void *custom_data;
 	void *bsp_priv;
 };
 
@@ -179,15 +175,11 @@ Where:
  o bus_setup: perform HW setup of the bus. For example, on some ST platforms
 	     this field is used to configure the AMBA  bridge to generate more
 	     efficient STBus traffic.
- o setup/init/exit: callbacks used for calling a custom initialization;
+ o init/exit: callbacks used for calling a custom initialization;
 	     this is sometime necessary on some platforms (e.g. ST boxes)
 	     where the HW needs to have set some PIO lines or system cfg
-	     registers. setup should return a pointer to private data,
-	     which will be stored in bsp_priv, and then passed to init and
-	     exit callbacks. init/exit callbacks should not use or modify
+	     registers.  init/exit callbacks should not use or modify
 	     platform data.
- o custom_cfg/custom_data: this is a custom configuration that can be passed
-			   while initializing the resources.
  o bsp_priv: another private pointer.
 
 For MDIO bus The we have:
@@ -262,7 +254,7 @@ static struct fixed_phy_status stmmac0_fixed_phy_status = {
 
 During the board's device_init we can configure the first
 MAC for fixed_link by calling:
-  fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status));)
+  fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status, -1);
 and the second one, with a real PHY device attached to the bus,
 by using the stmmac_mdio_bus_data structure (to provide the id, the
 reset procedure etc).
@@ -278,8 +270,6 @@ capability register can replace what has been passed from the platform.
 Please see the following document:
 	Documentation/devicetree/bindings/net/stmmac.txt
 
-and the stmmac_of_data structure inside the include/linux/stmmac.h header file.
-
 4.11) This is a summary of the content of some relevant files:
  o stmmac_main.c: to implement the main network device driver;
  o stmmac_mdio.c: to provide mdio functions;
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index c5d7ade10ff2..476df0496686 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -279,8 +279,18 @@ and unknown unicast packets to all ports in domain, if allowed by port's
 current STP state.  The switch driver, knowing which ports are within which
 vlan L2 domain, can program the switch device for flooding.  The packet should
 also be sent to the port netdev for processing by the bridge driver.  The
-bridge should not reflood the packet to the same ports the device flooded.
-XXX: the mechanism to avoid duplicate flood packets is being discuseed.
+bridge should not reflood the packet to the same ports the device flooded,
+otherwise there will be duplicate packets on the wire.
+
+To avoid duplicate packets, the device/driver should mark a packet as already
+forwarded using skb->offload_fwd_mark.  The same mark is set on the device
+ports in the domain using dev->offload_fwd_mark.  If the skb->offload_fwd_mark
+is non-zero and matches the forwarding egress port's dev->skb_mark, the kernel
+will drop the skb right before transmit on the egress port, with the
+understanding that the device already forwarded the packet on same egress port.
+The driver can use switchdev_port_fwd_mark_set() to set a globally unique mark
+for port's dev->offload_fwd_mark, based on the port's parent ID (switch ID) and
+a group ifindex.
 
 It is possible for the switch device to not handle flooding and push the
 packets up to the bridge driver for flooding.  This is not ideal as the number
@@ -357,4 +367,5 @@ driver's rocker_port_ipv4_resolve() for an example.
 
 The driver can monitor for updates to arp_tbl using the netevent notifier
 NETEVENT_NEIGH_UPDATE.  The device can be programmed with resolved nexthops
-for the routes as arp_tbl updates.
+for the routes as arp_tbl updates.  The driver implements ndo_neigh_destroy
+to know when arp_tbl neighbor entries are purged from the port.
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 5f0922613f1a..a977339fbe0a 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -359,6 +359,13 @@ the requested fine-grained filtering for incoming packets is not
 supported, the driver may time stamp more than just the requested types
 of packets.
 
+Drivers are free to use a more permissive configuration than the requested
+configuration. It is expected that drivers should only implement directly the
+most generic mode that can be supported. For example if the hardware can
+support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale
+HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT
+is more generic (and more useful to applications).
+
 A driver which supports hardware time stamping shall update the struct
 with the actual, possibly more permissive configuration. If the
 requested packets cannot be time stamped, then nothing should be
diff --git a/Documentation/networking/vxlan.txt b/Documentation/networking/vxlan.txt
index 6d993510f091..c28f4989c3f0 100644
--- a/Documentation/networking/vxlan.txt
+++ b/Documentation/networking/vxlan.txt
@@ -1,32 +1,36 @@
 Virtual eXtensible Local Area Networking documentation
 ======================================================
 
-The VXLAN protocol is a tunnelling protocol that is designed to
-solve the problem of limited number of available VLAN's (4096).
-With VXLAN identifier is expanded to 24 bits.
-
-It is a draft RFC standard, that is implemented by Cisco Nexus,
-Vmware and Brocade. The protocol runs over UDP using a single
-destination port (still not standardized by IANA).
-This document describes the Linux kernel tunnel device,
-there is also an implantation of VXLAN for Openvswitch.
-
-Unlike most tunnels, a VXLAN is a 1 to N network, not just point
-to point. A VXLAN device can either dynamically learn the IP address
-of the other end, in a manner similar to a learning bridge, or the
-forwarding entries can be configured statically.
-
-The management of vxlan is done in a similar fashion to it's
-too closest neighbors GRE and VLAN. Configuring VXLAN requires
-the version of iproute2 that matches the kernel release
-where VXLAN was first merged upstream.
+The VXLAN protocol is a tunnelling protocol designed to solve the
+problem of limited VLAN IDs (4096) in IEEE 802.1q.  With VXLAN the
+size of the identifier is expanded to 24 bits (16777216).
+
+VXLAN is described by IETF RFC 7348, and has been implemented by a
+number of vendors.  The protocol runs over UDP using a single
+destination port.  This document describes the Linux kernel tunnel
+device, there is also a separate implementation of VXLAN for
+Openvswitch.
+
+Unlike most tunnels, a VXLAN is a 1 to N network, not just point to
+point. A VXLAN device can learn the IP address of the other endpoint
+either dynamically in a manner similar to a learning bridge, or make
+use of statically-configured forwarding entries.
+
+The management of vxlan is done in a manner similar to its two closest
+neighbors GRE and VLAN. Configuring VXLAN requires the version of
+iproute2 that matches the kernel release where VXLAN was first merged
+upstream.
 
 1. Create vxlan device
-  # ip li add vxlan0 type vxlan id 42 group 239.1.1.1 dev eth1
-
-This creates a new device (vxlan0). The device uses the
-the multicast group 239.1.1.1 over eth1 to handle packets where
-no entry is in the forwarding table.
+ # ip link add vxlan0 type vxlan id 42 group 239.1.1.1 dev eth1 dstport 4789
+
+This creates a new device named vxlan0.  The device uses the multicast
+group 239.1.1.1 over eth1 to handle traffic for which there is no
+entry in the forwarding table.  The destination port number is set to
+the IANA-assigned value of 4789.  The Linux implementation of VXLAN
+pre-dates the IANA's selection of a standard destination port number
+and uses the Linux-selected value by default to maintain backwards
+compatibility.
 
 2. Delete vxlan device
   # ip link delete vxlan0
diff --git a/Documentation/nvmem/nvmem.txt b/Documentation/nvmem/nvmem.txt
new file mode 100644
index 000000000000..dbd40d879239
--- /dev/null
+++ b/Documentation/nvmem/nvmem.txt
@@ -0,0 +1,152 @@
+			    NVMEM SUBSYSTEM
+	  Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+This document explains the NVMEM Framework along with the APIs provided,
+and how to use it.
+
+1. Introduction
+===============
+*NVMEM* is the abbreviation for Non Volatile Memory layer. It is used to
+retrieve configuration of SOC or Device specific data from non volatile
+memories like eeprom, efuses and so on.
+
+Before this framework existed, NVMEM drivers like eeprom were stored in
+drivers/misc, where they all had to duplicate pretty much the same code to
+register a sysfs file, allow in-kernel users to access the content of the
+devices they were driving, etc.
+
+This was also a problem as far as other in-kernel users were involved, since
+the solutions used were pretty much different from one driver to another, there
+was a rather big abstraction leak.
+
+This framework aims at solve these problems. It also introduces DT
+representation for consumer devices to go get the data they require (MAC
+Addresses, SoC/Revision ID, part numbers, and so on) from the NVMEMs. This
+framework is based on regmap, so that most of the abstraction available in
+regmap can be reused, across multiple types of buses.
+
+NVMEM Providers
++++++++++++++++
+
+NVMEM provider refers to an entity that implements methods to initialize, read
+and write the non-volatile memory.
+
+2. Registering/Unregistering the NVMEM provider
+===============================================
+
+A NVMEM provider can register with NVMEM core by supplying relevant
+nvmem configuration to nvmem_register(), on success core would return a valid
+nvmem_device pointer.
+
+nvmem_unregister(nvmem) is used to unregister a previously registered provider.
+
+For example, a simple qfprom case:
+
+static struct nvmem_config econfig = {
+	.name = "qfprom",
+	.owner = THIS_MODULE,
+};
+
+static int qfprom_probe(struct platform_device *pdev)
+{
+	...
+	econfig.dev = &pdev->dev;
+	nvmem = nvmem_register(&econfig);
+	...
+}
+
+It is mandatory that the NVMEM provider has a regmap associated with its
+struct device. Failure to do would return error code from nvmem_register().
+
+NVMEM Consumers
++++++++++++++++
+
+NVMEM consumers are the entities which make use of the NVMEM provider to
+read from and to NVMEM.
+
+3. NVMEM cell based consumer APIs
+=================================
+
+NVMEM cells are the data entries/fields in the NVMEM.
+The NVMEM framework provides 3 APIs to read/write NVMEM cells.
+
+struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *name);
+struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *name);
+
+void nvmem_cell_put(struct nvmem_cell *cell);
+void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell);
+
+void *nvmem_cell_read(struct nvmem_cell *cell, ssize_t *len);
+int nvmem_cell_write(struct nvmem_cell *cell, void *buf, ssize_t len);
+
+*nvmem_cell_get() apis will get a reference to nvmem cell for a given id,
+and nvmem_cell_read/write() can then read or write to the cell.
+Once the usage of the cell is finished the consumer should call *nvmem_cell_put()
+to free all the allocation memory for the cell.
+
+4. Direct NVMEM device based consumer APIs
+==========================================
+
+In some instances it is necessary to directly read/write the NVMEM.
+To facilitate such consumers NVMEM framework provides below apis.
+
+struct nvmem_device *nvmem_device_get(struct device *dev, const char *name);
+struct nvmem_device *devm_nvmem_device_get(struct device *dev,
+					   const char *name);
+void nvmem_device_put(struct nvmem_device *nvmem);
+int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset,
+		      size_t bytes, void *buf);
+int nvmem_device_write(struct nvmem_device *nvmem, unsigned int offset,
+		       size_t bytes, void *buf);
+int nvmem_device_cell_read(struct nvmem_device *nvmem,
+			   struct nvmem_cell_info *info, void *buf);
+int nvmem_device_cell_write(struct nvmem_device *nvmem,
+			    struct nvmem_cell_info *info, void *buf);
+
+Before the consumers can read/write NVMEM directly, it should get hold
+of nvmem_controller from one of the *nvmem_device_get() api.
+
+The difference between these apis and cell based apis is that these apis always
+take nvmem_device as parameter.
+
+5. Releasing a reference to the NVMEM
+=====================================
+
+When a consumers no longer needs the NVMEM, it has to release the reference
+to the NVMEM it has obtained using the APIs mentioned in the above section.
+The NVMEM framework provides 2 APIs to release a reference to the NVMEM.
+
+void nvmem_cell_put(struct nvmem_cell *cell);
+void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell);
+void nvmem_device_put(struct nvmem_device *nvmem);
+void devm_nvmem_device_put(struct device *dev, struct nvmem_device *nvmem);
+
+Both these APIs are used to release a reference to the NVMEM and
+devm_nvmem_cell_put and devm_nvmem_device_put destroys the devres associated
+with this NVMEM.
+
+Userspace
++++++++++
+
+6. Userspace binary interface
+==============================
+
+Userspace can read/write the raw NVMEM file located at
+/sys/bus/nvmem/devices/*/nvmem
+
+ex:
+
+hexdump /sys/bus/nvmem/devices/qfprom0/nvmem
+
+0000000 0000 0000 0000 0000 0000 0000 0000 0000
+*
+00000a0 db10 2240 0000 e000 0c00 0c00 0000 0c00
+0000000 0000 0000 0000 0000 0000 0000 0000 0000
+...
+*
+0001000
+
+7. DeviceTree Binding
+=====================
+
+See Documentation/devicetree/bindings/nvmem/nvmem.txt
diff --git a/Documentation/pcmcia/locking.txt b/Documentation/pcmcia/locking.txt
index 68f622bc4064..b2c9b478906b 100644
--- a/Documentation/pcmcia/locking.txt
+++ b/Documentation/pcmcia/locking.txt
@@ -96,7 +96,7 @@ or single-use fields not mentioned):
 3. Per PCMCIA-device Data:
 --------------------------
 
-The "main" struct pcmcia_devie is protected as follows (read-only fields
+The "main" struct pcmcia_device is protected as follows (read-only fields
 or single-use fields not mentioned):
 
 
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index d172bce0fd49..8ba6625fdd63 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -341,6 +341,13 @@ the phases are:
 	and is entirely responsible for bringing the device back to the
 	functional state as appropriate.
 
+	Note that this direct-complete procedure applies even if the device is
+	disabled for runtime PM; only the runtime-PM status matters.  It follows
+	that if a device has system-sleep callbacks but does not support runtime
+	PM, then its prepare callback must never return a positive value.  This
+	is because all devices are initially set to runtime-suspended with
+	runtime PM disabled.
+
     2.	The suspend methods should quiesce the device to stop it from performing
 	I/O.  They also may save the device registers and put it into the
 	appropriate low-power state, depending on the bus type the device is on,
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index e76dc0ad4d2b..0784bc3a2ab5 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -445,10 +445,6 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
   bool pm_runtime_status_suspended(struct device *dev);
     - return true if the device's runtime PM status is 'suspended'
 
-  bool pm_runtime_suspended_if_enabled(struct device *dev);
-    - return true if the device's runtime PM status is 'suspended' and its
-      'power.disable_depth' field is equal to 1
-
   void pm_runtime_allow(struct device *dev);
     - set the power.runtime_auto flag for the device and decrease its usage
       counter (used by the /sys/devices/.../power/control interface to
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index 2850df3bf957..2fc909502db5 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -72,7 +72,7 @@ More details follow:
                                         |
                                         v
                            Disable regular cpu hotplug
-                        by setting cpu_hotplug_disabled=1
+                        by increasing cpu_hotplug_disabled
                                         |
                                         v
                             Release cpu_add_remove_lock
@@ -89,7 +89,7 @@ Resuming back is likewise, with the counterparts being (in the order of
 execution during resume):
 * enable_nonboot_cpus() which involves:
    |  Acquire cpu_add_remove_lock
-   |  Reset cpu_hotplug_disabled to 0, thereby enabling regular cpu hotplug
+   |  Decrease cpu_hotplug_disabled, thereby enabling regular cpu hotplug
    |  Call _cpu_up() [for all those cpus in the frozen_cpus mask, in a loop]
    |  Release cpu_add_remove_lock
    v
@@ -120,7 +120,7 @@ after the entire cycle is complete (i.e., suspend + resume).
                            Acquire cpu_add_remove_lock
                                         |
                                         v
-                          If cpu_hotplug_disabled is 1
+                          If cpu_hotplug_disabled > 0
                                 return gracefully
                                         |
                                         |
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index f732a8321e8a..8cc17ca71813 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -410,8 +410,17 @@ Documentation/usb/persist.txt.
 
 Q: Can I suspend-to-disk using a swap partition under LVM?
 
-A: No. You can suspend successfully, but you'll not be able to
-resume. uswsusp should be able to work with LVM. See suspend.sf.net.
+A: Yes and No.  You can suspend successfully, but the kernel will not be able
+to resume on its own.  You need an initramfs that can recognize the resume
+situation, activate the logical volume containing the swap volume (but not
+touch any filesystems!), and eventually call
+
+echo -n "$major:$minor" > /sys/power/resume
+
+where $major and $minor are the respective major and minor device numbers of
+the swap volume.
+
+uswsusp works with LVM, too.  See http://suspend.sourceforge.net/
 
 Q: I upgraded the kernel from 2.6.15 to 2.6.16. Both kernels were
 compiled with the similar configuration files. Anyway I found that
diff --git a/Documentation/powerpc/cxl.txt b/Documentation/powerpc/cxl.txt
index 2a230d01cd8c..205c1b81625c 100644
--- a/Documentation/powerpc/cxl.txt
+++ b/Documentation/powerpc/cxl.txt
@@ -133,7 +133,7 @@ User API
     The following file operations are supported on both slave and
     master devices.
 
-    A userspace library libcxl is avaliable here:
+    A userspace library libcxl is available here:
 	https://github.com/ibm-capi/libcxl
     This provides a C interface to this kernel API.
 
diff --git a/Documentation/powerpc/cxlflash.txt b/Documentation/powerpc/cxlflash.txt
new file mode 100644
index 000000000000..4202d1bc583c
--- /dev/null
+++ b/Documentation/powerpc/cxlflash.txt
@@ -0,0 +1,318 @@
+Introduction
+============
+
+    The IBM Power architecture provides support for CAPI (Coherent
+    Accelerator Power Interface), which is available to certain PCIe slots
+    on Power 8 systems. CAPI can be thought of as a special tunneling
+    protocol through PCIe that allow PCIe adapters to look like special
+    purpose co-processors which can read or write an application's
+    memory and generate page faults. As a result, the host interface to
+    an adapter running in CAPI mode does not require the data buffers to
+    be mapped to the device's memory (IOMMU bypass) nor does it require
+    memory to be pinned.
+
+    On Linux, Coherent Accelerator (CXL) kernel services present CAPI
+    devices as a PCI device by implementing a virtual PCI host bridge.
+    This abstraction simplifies the infrastructure and programming
+    model, allowing for drivers to look similar to other native PCI
+    device drivers.
+
+    CXL provides a mechanism by which user space applications can
+    directly talk to a device (network or storage) bypassing the typical
+    kernel/device driver stack. The CXL Flash Adapter Driver enables a
+    user space application direct access to Flash storage.
+
+    The CXL Flash Adapter Driver is a kernel module that sits in the
+    SCSI stack as a low level device driver (below the SCSI disk and
+    protocol drivers) for the IBM CXL Flash Adapter. This driver is
+    responsible for the initialization of the adapter, setting up the
+    special path for user space access, and performing error recovery. It
+    communicates directly the Flash Accelerator Functional Unit (AFU)
+    as described in Documentation/powerpc/cxl.txt.
+
+    The cxlflash driver supports two, mutually exclusive, modes of
+    operation at the device (LUN) level:
+
+        - Any flash device (LUN) can be configured to be accessed as a
+          regular disk device (i.e.: /dev/sdc). This is the default mode.
+
+        - Any flash device (LUN) can be configured to be accessed from
+          user space with a special block library. This mode further
+          specifies the means of accessing the device and provides for
+          either raw access to the entire LUN (referred to as direct
+          or physical LUN access) or access to a kernel/AFU-mediated
+          partition of the LUN (referred to as virtual LUN access). The
+          segmentation of a disk device into virtual LUNs is assisted
+          by special translation services provided by the Flash AFU.
+
+Overview
+========
+
+    The Coherent Accelerator Interface Architecture (CAIA) introduces a
+    concept of a master context. A master typically has special privileges
+    granted to it by the kernel or hypervisor allowing it to perform AFU
+    wide management and control. The master may or may not be involved
+    directly in each user I/O, but at the minimum is involved in the
+    initial setup before the user application is allowed to send requests
+    directly to the AFU.
+
+    The CXL Flash Adapter Driver establishes a master context with the
+    AFU. It uses memory mapped I/O (MMIO) for this control and setup. The
+    Adapter Problem Space Memory Map looks like this:
+
+                     +-------------------------------+
+                     |    512 * 64 KB User MMIO      |
+                     |        (per context)          |
+                     |       User Accessible         |
+                     +-------------------------------+
+                     |    512 * 128 B per context    |
+                     |    Provisioning and Control   |
+                     |   Trusted Process accessible  |
+                     +-------------------------------+
+                     |         64 KB Global          |
+                     |   Trusted Process accessible  |
+                     +-------------------------------+
+
+    This driver configures itself into the SCSI software stack as an
+    adapter driver. The driver is the only entity that is considered a
+    Trusted Process to program the Provisioning and Control and Global
+    areas in the MMIO Space shown above.  The master context driver
+    discovers all LUNs attached to the CXL Flash adapter and instantiates
+    scsi block devices (/dev/sdb, /dev/sdc etc.) for each unique LUN
+    seen from each path.
+
+    Once these scsi block devices are instantiated, an application
+    written to a specification provided by the block library may get
+    access to the Flash from user space (without requiring a system call).
+
+    This master context driver also provides a series of ioctls for this
+    block library to enable this user space access.  The driver supports
+    two modes for accessing the block device.
+
+    The first mode is called a virtual mode. In this mode a single scsi
+    block device (/dev/sdb) may be carved up into any number of distinct
+    virtual LUNs. The virtual LUNs may be resized as long as the sum of
+    the sizes of all the virtual LUNs, along with the meta-data associated
+    with it does not exceed the physical capacity.
+
+    The second mode is called the physical mode. In this mode a single
+    block device (/dev/sdb) may be opened directly by the block library
+    and the entire space for the LUN is available to the application.
+
+    Only the physical mode provides persistence of the data.  i.e. The
+    data written to the block device will survive application exit and
+    restart and also reboot. The virtual LUNs do not persist (i.e. do
+    not survive after the application terminates or the system reboots).
+
+
+Block library API
+=================
+
+    Applications intending to get access to the CXL Flash from user
+    space should use the block library, as it abstracts the details of
+    interfacing directly with the cxlflash driver that are necessary for
+    performing administrative actions (i.e.: setup, tear down, resize).
+    The block library can be thought of as a 'user' of services,
+    implemented as IOCTLs, that are provided by the cxlflash driver
+    specifically for devices (LUNs) operating in user space access
+    mode. While it is not a requirement that applications understand
+    the interface between the block library and the cxlflash driver,
+    a high-level overview of each supported service (IOCTL) is provided
+    below.
+
+    The block library can be found on GitHub:
+    http://www.github.com/mikehollinger/ibmcapikv
+
+
+CXL Flash Driver IOCTLs
+=======================
+
+    Users, such as the block library, that wish to interface with a flash
+    device (LUN) via user space access need to use the services provided
+    by the cxlflash driver. As these services are implemented as ioctls,
+    a file descriptor handle must first be obtained in order to establish
+    the communication channel between a user and the kernel.  This file
+    descriptor is obtained by opening the device special file associated
+    with the scsi disk device (/dev/sdb) that was created during LUN
+    discovery. As per the location of the cxlflash driver within the
+    SCSI protocol stack, this open is actually not seen by the cxlflash
+    driver. Upon successful open, the user receives a file descriptor
+    (herein referred to as fd1) that should be used for issuing the
+    subsequent ioctls listed below.
+
+    The structure definitions for these IOCTLs are available in:
+    uapi/scsi/cxlflash_ioctl.h
+
+DK_CXLFLASH_ATTACH
+------------------
+
+    This ioctl obtains, initializes, and starts a context using the CXL
+    kernel services. These services specify a context id (u16) by which
+    to uniquely identify the context and its allocated resources. The
+    services additionally provide a second file descriptor (herein
+    referred to as fd2) that is used by the block library to initiate
+    memory mapped I/O (via mmap()) to the CXL flash device and poll for
+    completion events. This file descriptor is intentionally installed by
+    this driver and not the CXL kernel services to allow for intermediary
+    notification and access in the event of a non-user-initiated close(),
+    such as a killed process. This design point is described in further
+    detail in the description for the DK_CXLFLASH_DETACH ioctl.
+
+    There are a few important aspects regarding the "tokens" (context id
+    and fd2) that are provided back to the user:
+
+        - These tokens are only valid for the process under which they
+          were created. The child of a forked process cannot continue
+          to use the context id or file descriptor created by its parent
+          (see DK_CXLFLASH_VLUN_CLONE for further details).
+
+        - These tokens are only valid for the lifetime of the context and
+          the process under which they were created. Once either is
+          destroyed, the tokens are to be considered stale and subsequent
+          usage will result in errors.
+
+        - When a context is no longer needed, the user shall detach from
+          the context via the DK_CXLFLASH_DETACH ioctl.
+
+        - A close on fd2 will invalidate the tokens. This operation is not
+          required by the user.
+
+DK_CXLFLASH_USER_DIRECT
+-----------------------
+    This ioctl is responsible for transitioning the LUN to direct
+    (physical) mode access and configuring the AFU for direct access from
+    user space on a per-context basis. Additionally, the block size and
+    last logical block address (LBA) are returned to the user.
+
+    As mentioned previously, when operating in user space access mode,
+    LUNs may be accessed in whole or in part. Only one mode is allowed
+    at a time and if one mode is active (outstanding references exist),
+    requests to use the LUN in a different mode are denied.
+
+    The AFU is configured for direct access from user space by adding an
+    entry to the AFU's resource handle table. The index of the entry is
+    treated as a resource handle that is returned to the user. The user
+    is then able to use the handle to reference the LUN during I/O.
+
+DK_CXLFLASH_USER_VIRTUAL
+------------------------
+    This ioctl is responsible for transitioning the LUN to virtual mode
+    of access and configuring the AFU for virtual access from user space
+    on a per-context basis. Additionally, the block size and last logical
+    block address (LBA) are returned to the user.
+
+    As mentioned previously, when operating in user space access mode,
+    LUNs may be accessed in whole or in part. Only one mode is allowed
+    at a time and if one mode is active (outstanding references exist),
+    requests to use the LUN in a different mode are denied.
+
+    The AFU is configured for virtual access from user space by adding
+    an entry to the AFU's resource handle table. The index of the entry
+    is treated as a resource handle that is returned to the user. The
+    user is then able to use the handle to reference the LUN during I/O.
+
+    By default, the virtual LUN is created with a size of 0. The user
+    would need to use the DK_CXLFLASH_VLUN_RESIZE ioctl to adjust the grow
+    the virtual LUN to a desired size. To avoid having to perform this
+    resize for the initial creation of the virtual LUN, the user has the
+    option of specifying a size as part of the DK_CXLFLASH_USER_VIRTUAL
+    ioctl, such that when success is returned to the user, the
+    resource handle that is provided is already referencing provisioned
+    storage. This is reflected by the last LBA being a non-zero value.
+
+DK_CXLFLASH_VLUN_RESIZE
+-----------------------
+    This ioctl is responsible for resizing a previously created virtual
+    LUN and will fail if invoked upon a LUN that is not in virtual
+    mode. Upon success, an updated last LBA is returned to the user
+    indicating the new size of the virtual LUN associated with the
+    resource handle.
+
+    The partitioning of virtual LUNs is jointly mediated by the cxlflash
+    driver and the AFU. An allocation table is kept for each LUN that is
+    operating in the virtual mode and used to program a LUN translation
+    table that the AFU references when provided with a resource handle.
+
+DK_CXLFLASH_RELEASE
+-------------------
+    This ioctl is responsible for releasing a previously obtained
+    reference to either a physical or virtual LUN. This can be
+    thought of as the inverse of the DK_CXLFLASH_USER_DIRECT or
+    DK_CXLFLASH_USER_VIRTUAL ioctls. Upon success, the resource handle
+    is no longer valid and the entry in the resource handle table is
+    made available to be used again.
+
+    As part of the release process for virtual LUNs, the virtual LUN
+    is first resized to 0 to clear out and free the translation tables
+    associated with the virtual LUN reference.
+
+DK_CXLFLASH_DETACH
+------------------
+    This ioctl is responsible for unregistering a context with the
+    cxlflash driver and release outstanding resources that were
+    not explicitly released via the DK_CXLFLASH_RELEASE ioctl. Upon
+    success, all "tokens" which had been provided to the user from the
+    DK_CXLFLASH_ATTACH onward are no longer valid.
+
+DK_CXLFLASH_VLUN_CLONE
+----------------------
+    This ioctl is responsible for cloning a previously created
+    context to a more recently created context. It exists solely to
+    support maintaining user space access to storage after a process
+    forks. Upon success, the child process (which invoked the ioctl)
+    will have access to the same LUNs via the same resource handle(s)
+    and fd2 as the parent, but under a different context.
+
+    Context sharing across processes is not supported with CXL and
+    therefore each fork must be met with establishing a new context
+    for the child process. This ioctl simplifies the state management
+    and playback required by a user in such a scenario. When a process
+    forks, child process can clone the parents context by first creating
+    a context (via DK_CXLFLASH_ATTACH) and then using this ioctl to
+    perform the clone from the parent to the child.
+
+    The clone itself is fairly simple. The resource handle and lun
+    translation tables are copied from the parent context to the child's
+    and then synced with the AFU.
+
+DK_CXLFLASH_VERIFY
+------------------
+    This ioctl is used to detect various changes such as the capacity of
+    the disk changing, the number of LUNs visible changing, etc. In cases
+    where the changes affect the application (such as a LUN resize), the
+    cxlflash driver will report the changed state to the application.
+
+    The user calls in when they want to validate that a LUN hasn't been
+    changed in response to a check condition. As the user is operating out
+    of band from the kernel, they will see these types of events without
+    the kernel's knowledge. When encountered, the user's architected
+    behavior is to call in to this ioctl, indicating what they want to
+    verify and passing along any appropriate information. For now, only
+    verifying a LUN change (ie: size different) with sense data is
+    supported.
+
+DK_CXLFLASH_RECOVER_AFU
+-----------------------
+    This ioctl is used to drive recovery (if such an action is warranted)
+    of a specified user context. Any state associated with the user context
+    is re-established upon successful recovery.
+
+    User contexts are put into an error condition when the device needs to
+    be reset or is terminating. Users are notified of this error condition
+    by seeing all 0xF's on an MMIO read. Upon encountering this, the
+    architected behavior for a user is to call into this ioctl to recover
+    their context. A user may also call into this ioctl at any time to
+    check if the device is operating normally. If a failure is returned
+    from this ioctl, the user is expected to gracefully clean up their
+    context via release/detach ioctls. Until they do, the context they
+    hold is not relinquished. The user may also optionally exit the process
+    at which time the context/resources they held will be freed as part of
+    the release fop.
+
+DK_CXLFLASH_MANAGE_LUN
+----------------------
+    This ioctl is used to switch a LUN from a mode where it is available
+    for file-system access (legacy), to a mode where it is set aside for
+    exclusive user space access (superpipe). In case a LUN is visible
+    across multiple ports and adapters, this ioctl is used to uniquely
+    identify each LUN by its World Wide Node Name (WWNN).
diff --git a/Documentation/powerpc/dscr.txt b/Documentation/powerpc/dscr.txt
index 1ff4400c57b3..ece300c64f76 100644
--- a/Documentation/powerpc/dscr.txt
+++ b/Documentation/powerpc/dscr.txt
@@ -4,7 +4,7 @@
 DSCR register in powerpc allows user to have some control of prefetch of data
 stream in the processor. Please refer to the ISA documents or related manual
 for more detailed information regarding how to use this DSCR to attain this
-control of the pefetches . This document here provides an overview of kernel
+control of the prefetches . This document here provides an overview of kernel
 support for DSCR, related kernel objects, it's functionalities and exported
 user interface.
 
@@ -44,7 +44,7 @@ user interface.
 	value into every CPU's DSCR register right away and updates the current
 	thread's DSCR value as well.
 
-	Changing the CPU specif DSCR default value in the sysfs does exactly
+	Changing the CPU specific DSCR default value in the sysfs does exactly
 	the same thing as above but unlike the global one above, it just changes
 	stuff for that particular CPU instead for all the CPUs on the system.
 
@@ -62,7 +62,7 @@ user interface.
 
 	Accessing DSCR through user level SPR (0x03) from user space will first
 	create a facility unavailable exception. Inside this exception handler
-	all mfspr isntruction based read attempts will get emulated and returned
+	all mfspr instruction based read attempts will get emulated and returned
 	where as the first mtspr instruction based write attempts will enable
 	the DSCR facility for the next time around (both for read and write) by
 	setting DSCR facility in the FSCR register.
diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.txt
index 2031ddb33d09..e7ac24aec4ff 100644
--- a/Documentation/powerpc/qe_firmware.txt
+++ b/Documentation/powerpc/qe_firmware.txt
@@ -117,7 +117,7 @@ specific been defined.  This table describes the structure.
 Extended Modes
 
 This is a double word bit array (64 bits) that defines special functionality
-which has an impact on the softwarew drivers.  Each bit has its own impact
+which has an impact on the software drivers.  Each bit has its own impact
 and has special instructions for the s/w associated with it.  This structure is
 described in this table:
 
diff --git a/Documentation/pps/pps.txt b/Documentation/pps/pps.txt
index c508cceeee7d..7cb7264ad598 100644
--- a/Documentation/pps/pps.txt
+++ b/Documentation/pps/pps.txt
@@ -125,7 +125,7 @@ The same function may also run the defined echo function
 (pps_ktimer_echo(), passing to it the "ptr" pointer) if the user
 asked for that... etc..
 
-Please see the file drivers/pps/clients/ktimer.c for example code.
+Please see the file drivers/pps/clients/pps-ktimer.c for example code.
 
 
 SYSFS support
diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX
index 10c874ebdfe5..9189535f6cd2 100644
--- a/Documentation/s390/00-INDEX
+++ b/Documentation/s390/00-INDEX
@@ -16,8 +16,6 @@ Debugging390.txt
 	- hints for debugging on s390 systems.
 driver-model.txt
 	- information on s390 devices and the driver model.
-kvm.txt
-	- ioctl calls to /dev/kvm on s390.
 monreader.txt
 	- information on accessing the z/VM monitor stream from Linux.
 qeth.txt
diff --git a/Documentation/s390/kvm.txt b/Documentation/s390/kvm.txt
deleted file mode 100644
index 85f3280d7ef6..000000000000
--- a/Documentation/s390/kvm.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-*** BIG FAT WARNING ***
-The kvm module is currently in EXPERIMENTAL state for s390. This means that
-the interface to the module is not yet considered to remain stable. Thus, be
-prepared that we keep breaking your userspace application and guest
-compatibility over and over again until we feel happy with the result. Make sure
-your guest kernel, your host kernel, and your userspace launcher are in a
-consistent state.
-
-This Documentation describes the unique ioctl calls to /dev/kvm, the resulting
-kvm-vm file descriptors, and the kvm-vcpu file descriptors that differ from x86.
-
-1. ioctl calls to /dev/kvm
-KVM does support the following ioctls on s390 that are common with other
-architectures and do behave the same:
-KVM_GET_API_VERSION
-KVM_CREATE_VM		(*) see note
-KVM_CHECK_EXTENSION
-KVM_GET_VCPU_MMAP_SIZE
-
-Notes:
-* KVM_CREATE_VM may fail on s390, if the calling process has multiple
-threads and has not called KVM_S390_ENABLE_SIE before.
-
-In addition, on s390 the following architecture specific ioctls are supported:
-ioctl:		KVM_S390_ENABLE_SIE
-args:		none
-see also:	include/linux/kvm.h
-This call causes the kernel to switch on PGSTE in the user page table. This
-operation is needed in order to run a virtual machine, and it requires the
-calling process to be single-threaded. Note that the first call to KVM_CREATE_VM
-will implicitly try to switch on PGSTE if the user process has not called
-KVM_S390_ENABLE_SIE before. User processes that want to launch multiple threads
-before creating a virtual machine have to call KVM_S390_ENABLE_SIE, or will
-observe an error calling KVM_CREATE_VM. Switching on PGSTE is a one-time
-operation, is not reversible, and will persist over the entire lifetime of
-the calling process. It does not have any user-visible effect other than a small
-performance penalty.
-
-2. ioctl calls to the kvm-vm file descriptor
-KVM does support the following ioctls on s390 that are common with other
-architectures and do behave the same:
-KVM_CREATE_VCPU
-KVM_SET_USER_MEMORY_REGION      (*) see note
-KVM_GET_DIRTY_LOG		(**) see note
-
-Notes:
-*  kvm does only allow exactly one memory slot on s390, which has to start
-   at guest absolute address zero and at a user address that is aligned on any
-   page boundary. This hardware "limitation" allows us to have a few unique
-   optimizations. The memory slot doesn't have to be filled
-   with memory actually, it may contain sparse holes. That said, with different
-   user memory layout this does still allow a large flexibility when
-   doing the guest memory setup.
-** KVM_GET_DIRTY_LOG doesn't work properly yet. The user will receive an empty
-log. This ioctl call is only needed for guest migration, and we intend to
-implement this one in the future.
-
-In addition, on s390 the following architecture specific ioctls for the kvm-vm
-file descriptor are supported:
-ioctl:		KVM_S390_INTERRUPT
-args:		struct kvm_s390_interrupt *
-see also:	include/linux/kvm.h
-This ioctl is used to submit a floating interrupt for a virtual machine.
-Floating interrupts may be delivered to any virtual cpu in the configuration.
-Only some interrupt types defined in include/linux/kvm.h make sense when
-submitted as floating interrupts. The following interrupts are not considered
-to be useful as floating interrupts, and a call to inject them will result in
--EINVAL error code: program interrupts and interprocessor signals. Valid
-floating interrupts are:
-KVM_S390_INT_VIRTIO
-KVM_S390_INT_SERVICE
-
-3. ioctl calls to the kvm-vcpu file descriptor
-KVM does support the following ioctls on s390 that are common with other
-architectures and do behave the same:
-KVM_RUN
-KVM_GET_REGS
-KVM_SET_REGS
-KVM_GET_SREGS
-KVM_SET_SREGS
-KVM_GET_FPU
-KVM_SET_FPU
-
-In addition, on s390 the following architecture specific ioctls for the
-kvm-vcpu file descriptor are supported:
-ioctl:		KVM_S390_INTERRUPT
-args:		struct kvm_s390_interrupt *
-see also:	include/linux/kvm.h
-This ioctl is used to submit an interrupt for a specific virtual cpu.
-Only some interrupt types defined in include/linux/kvm.h make sense when
-submitted for a specific cpu. The following interrupts are not considered
-to be useful, and a call to inject them will result in -EINVAL error code:
-service processor calls and virtio interrupts. Valid interrupt types are:
-KVM_S390_PROGRAM_INT
-KVM_S390_SIGP_STOP
-KVM_S390_RESTART
-KVM_S390_SIGP_SET_PREFIX
-KVM_S390_INT_EMERGENCY
-
-ioctl:		KVM_S390_STORE_STATUS
-args:		unsigned long
-see also:	include/linux/kvm.h
-This ioctl stores the state of the cpu at the guest real address given as
-argument, unless one of the following values defined in include/linux/kvm.h
-is given as argument:
-KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in
-absolute lowcore as defined by the principles of operation
-KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in
-its prefix page just like the dump tool that comes with zipl. This is useful
-to create a system dump for use with lkcdutils or crash.
-
-ioctl:		KVM_S390_SET_INITIAL_PSW
-args:		struct kvm_s390_psw *
-see also:	include/linux/kvm.h
-This ioctl can be used to set the processor status word (psw) of a stopped cpu
-prior to running it with KVM_RUN. Note that this call is not required to modify
-the psw during sie intercepts that fall back to userspace because struct kvm_run
-does contain the psw, and this value is evaluated during reentry of KVM_RUN
-after the intercept exit was recognized.
-
-ioctl:		KVM_S390_INITIAL_RESET
-args:		none
-see also:	include/linux/kvm.h
-This ioctl can be used to perform an initial cpu reset as defined by the
-principles of operation. The target cpu has to be in stopped state.
diff --git a/Documentation/security/Smack.txt b/Documentation/security/Smack.txt
index de5e1aeca7fb..5e6d07fbed07 100644
--- a/Documentation/security/Smack.txt
+++ b/Documentation/security/Smack.txt
@@ -28,6 +28,10 @@ Smack kernels use the CIPSO IP option. Some network
 configurations are intolerant of IP options and can impede
 access to systems that use them as Smack does.
 
+Smack is used in the Tizen operating system. Please
+go to http://wiki.tizen.org for information about how
+Smack is used in Tizen.
+
 The current git repository for Smack user space is:
 
 	git://github.com/smack-team/smack.git
@@ -108,6 +112,8 @@ in the smackfs filesystem. This pseudo-filesystem is mounted
 on /sys/fs/smackfs.
 
 access
+	Provided for backward compatibility. The access2 interface
+	is preferred and should be used instead.
 	This interface reports whether a subject with the specified
 	Smack label has a particular access to an object with a
 	specified Smack label. Write a fixed format access rule to
@@ -136,6 +142,8 @@ change-rule
 	those in the fourth string. If there is no such rule it will be
 	created using the access specified in the third and the fourth strings.
 cipso
+	Provided for backward compatibility. The cipso2 interface
+	is preferred and should be used instead.
 	This interface allows a specific CIPSO header to be assigned
 	to a Smack label. The format accepted on write is:
 		"%24s%4d%4d"["%4d"]...
@@ -157,7 +165,19 @@ direct
 doi
 	This contains the CIPSO domain of interpretation used in
 	network packets.
+ipv6host
+	This interface allows specific IPv6 internet addresses to be
+	treated as single label hosts. Packets are sent to single
+	label hosts only from processes that have Smack write access
+	to the host label. All packets received from single label hosts
+	are given the specified label. The format accepted on write is:
+		"%h:%h:%h:%h:%h:%h:%h:%h label" or
+		"%h:%h:%h:%h:%h:%h:%h:%h/%d label".
+	The "::" address shortcut is not supported.
+	If label is "-DELETE" a matched entry will be deleted.
 load
+	Provided for backward compatibility. The load2 interface
+	is preferred and should be used instead.
 	This interface allows access control rules in addition to
 	the system defined rules to be specified. The format accepted
 	on write is:
@@ -181,6 +201,8 @@ load2
 	permissions that are not allowed. The string "r-x--" would
 	specify read and execute access.
 load-self
+	Provided for backward compatibility. The load-self2 interface
+	is preferred and should be used instead.
 	This interface allows process specific access rules to be
 	defined. These rules are only consulted if access would
 	otherwise be permitted, and are intended to provide additional
@@ -205,6 +227,8 @@ netlabel
 	received from single label hosts are given the specified
 	label. The format accepted on write is:
 		"%d.%d.%d.%d label" or "%d.%d.%d.%d/%d label".
+	If the label specified is "-CIPSO" the address is treated
+	as a host that supports CIPSO headers.
 onlycap
 	This contains labels processes must have for CAP_MAC_ADMIN
 	and CAP_MAC_OVERRIDE to be effective. If this file is empty
@@ -232,7 +256,8 @@ unconfined
 	is dangerous and can ruin the proper labeling of your system.
 	It should never be used in production.
 
-You can add access rules in /etc/smack/accesses. They take the form:
+If you are using the smackload utility
+you can add access rules in /etc/smack/accesses. They take the form:
 
     subjectlabel objectlabel access
 
diff --git a/Documentation/security/Yama.txt b/Documentation/security/Yama.txt
index 227a63f018a2..d9ee7d7a6c7f 100644
--- a/Documentation/security/Yama.txt
+++ b/Documentation/security/Yama.txt
@@ -1,9 +1,7 @@
-Yama is a Linux Security Module that collects a number of system-wide DAC
-security protections that are not handled by the core kernel itself. To
-select it at boot time, specify "security=yama" (though this will disable
-any other LSM).
-
-Yama is controlled through sysctl in /proc/sys/kernel/yama:
+Yama is a Linux Security Module that collects system-wide DAC security
+protections that are not handled by the core kernel itself. This is
+selectable at build-time with CONFIG_SECURITY_YAMA, and can be controlled
+at run-time through sysctls in /proc/sys/kernel/yama:
 
 - ptrace_scope
 
diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt
index c4407a41b0fc..f4cb0b2d5cd7 100644
--- a/Documentation/static-keys.txt
+++ b/Documentation/static-keys.txt
@@ -1,7 +1,22 @@
 			Static Keys
 			-----------
 
-By: Jason Baron <jbaron@redhat.com>
+DEPRECATED API:
+
+The use of 'struct static_key' directly, is now DEPRECATED. In addition
+static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following:
+
+struct static_key false = STATIC_KEY_INIT_FALSE;
+struct static_key true = STATIC_KEY_INIT_TRUE;
+static_key_true()
+static_key_false()
+
+The updated API replacements are:
+
+DEFINE_STATIC_KEY_TRUE(key);
+DEFINE_STATIC_KEY_FALSE(key);
+static_key_likely()
+statick_key_unlikely()
 
 0) Abstract
 
@@ -9,22 +24,22 @@ Static keys allows the inclusion of seldom used features in
 performance-sensitive fast-path kernel code, via a GCC feature and a code
 patching technique. A quick example:
 
-	struct static_key key = STATIC_KEY_INIT_FALSE;
+	DEFINE_STATIC_KEY_FALSE(key);
 
 	...
 
-        if (static_key_false(&key))
+        if (static_branch_unlikely(&key))
                 do unlikely code
         else
                 do likely code
 
 	...
-	static_key_slow_inc();
+	static_branch_enable(&key);
 	...
-	static_key_slow_inc();
+	static_branch_disable(&key);
 	...
 
-The static_key_false() branch will be generated into the code with as little
+The static_branch_unlikely() branch will be generated into the code with as little
 impact to the likely code path as possible.
 
 
@@ -56,7 +71,7 @@ the branch site to change the branch direction.
 
 For example, if we have a simple branch that is disabled by default:
 
-	if (static_key_false(&key))
+	if (static_branch_unlikely(&key))
 		printk("I am the true branch\n");
 
 Thus, by default the 'printk' will not be emitted. And the code generated will
@@ -75,68 +90,55 @@ the basis for the static keys facility.
 
 In order to make use of this optimization you must first define a key:
 
-	struct static_key key;
-
-Which is initialized as:
-
-	struct static_key key = STATIC_KEY_INIT_TRUE;
+	DEFINE_STATIC_KEY_TRUE(key);
 
 or:
 
-	struct static_key key = STATIC_KEY_INIT_FALSE;
+	DEFINE_STATIC_KEY_FALSE(key);
+
 
-If the key is not initialized, it is default false. The 'struct static_key',
-must be a 'global'. That is, it can't be allocated on the stack or dynamically
+The key must be global, that is, it can't be allocated on the stack or dynamically
 allocated at run-time.
 
 The key is then used in code as:
 
-        if (static_key_false(&key))
+        if (static_branch_unlikely(&key))
                 do unlikely code
         else
                 do likely code
 
 Or:
 
-        if (static_key_true(&key))
+        if (static_branch_likely(&key))
                 do likely code
         else
                 do unlikely code
 
-A key that is initialized via 'STATIC_KEY_INIT_FALSE', must be used in a
-'static_key_false()' construct. Likewise, a key initialized via
-'STATIC_KEY_INIT_TRUE' must be used in a 'static_key_true()' construct. A
-single key can be used in many branches, but all the branches must match the
-way that the key has been initialized.
+Keys defined via DEFINE_STATIC_KEY_TRUE(), or DEFINE_STATIC_KEY_FALSE, may
+be used in either static_branch_likely() or static_branch_unlikely()
+statemnts.
 
-The branch(es) can then be switched via:
+Branch(es) can be set true via:
 
-	static_key_slow_inc(&key);
-	...
-	static_key_slow_dec(&key);
+static_branch_enable(&key);
 
-Thus, 'static_key_slow_inc()' means 'make the branch true', and
-'static_key_slow_dec()' means 'make the branch false' with appropriate
-reference counting. For example, if the key is initialized true, a
-static_key_slow_dec(), will switch the branch to false. And a subsequent
-static_key_slow_inc(), will change the branch back to true. Likewise, if the
-key is initialized false, a 'static_key_slow_inc()', will change the branch to
-true. And then a 'static_key_slow_dec()', will again make the branch false.
+or false via:
+
+static_branch_disable(&key);
 
-An example usage in the kernel is the implementation of tracepoints:
+The branch(es) can then be switched via reference counts:
 
-        static inline void trace_##name(proto)                          \
-        {                                                               \
-                if (static_key_false(&__tracepoint_##name.key))		\
-                        __DO_TRACE(&__tracepoint_##name,                \
-                                TP_PROTO(data_proto),                   \
-                                TP_ARGS(data_args),                     \
-                                TP_CONDITION(cond));                    \
-        }
+	static_branch_inc(&key);
+	...
+	static_branch_dec(&key);
 
-Tracepoints are disabled by default, and can be placed in performance critical
-pieces of the kernel. Thus, by using a static key, the tracepoints can have
-absolutely minimal impact when not in use.
+Thus, 'static_branch_inc()' means 'make the branch true', and
+'static_branch_dec()' means 'make the branch false' with appropriate
+reference counting. For example, if the key is initialized true, a
+static_branch_dec(), will switch the branch to false. And a subsequent
+static_branch_inc(), will change the branch back to true. Likewise, if the
+key is initialized false, a 'static_branch_inc()', will change the branch to
+true. And then a 'static_branch_dec()', will again make the branch false.
 
 
 4) Architecture level code patching interface, 'jump labels'
@@ -150,9 +152,12 @@ simply fall back to a traditional, load, test, and jump sequence.
 
 * #define JUMP_LABEL_NOP_SIZE, see: arch/x86/include/asm/jump_label.h
 
-* __always_inline bool arch_static_branch(struct static_key *key), see:
+* __always_inline bool arch_static_branch(struct static_key *key, bool branch), see:
 					arch/x86/include/asm/jump_label.h
 
+* __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch),
+					see: arch/x86/include/asm/jump_label.h
+
 * void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type),
 					see: arch/x86/kernel/jump_label.c
 
@@ -173,7 +178,7 @@ SYSCALL_DEFINE0(getppid)
 {
         int pid;
 
-+       if (static_key_false(&key))
++       if (static_branch_unlikely(&key))
 +               printk("I am the true branch\n");
 
         rcu_read_lock();
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 9832ec52f859..9c3f2f8054b5 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -225,11 +225,11 @@ with your system.  To disable them, echo 4 (bit 3) into drop_caches.
 extfrag_threshold
 
 This parameter affects whether the kernel will compact memory or direct
-reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what
-the fragmentation index for each order is in each zone in the system. Values
-tending towards 0 imply allocations would fail due to lack of memory,
-values towards 1000 imply failures are due to fragmentation and -1 implies
-that the allocation will succeed as long as watermarks are met.
+reclaim to satisfy a high-order allocation. The extfrag/extfrag_index file in
+debugfs shows what the fragmentation index for each order is in each zone in
+the system. Values tending towards 0 imply allocations would fail due to lack
+of memory, values towards 1000 imply failures are due to fragmentation and -1
+implies that the allocation will succeed as long as watermarks are met.
 
 The kernel will not compact memory in a zone if the
 fragmentation index is <= extfrag_threshold. The default value is 500.
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 0e307c94809a..267f39386f99 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -119,6 +119,7 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 
 'x'	- Used by xmon interface on ppc/powerpc platforms.
           Show global PMU Registers on sparc64.
+          Dump all TLB entries on MIPS.
 
 'y'	- Show global CPU Registers [SPARC-64 specific]
 
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 949de191fcdc..cda56df9b8a7 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -199,7 +199,8 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "#include <linux/string.h>\n"
 	buf += "#include <linux/configfs.h>\n"
 	buf += "#include <linux/ctype.h>\n"
-	buf += "#include <asm/unaligned.h>\n\n"
+	buf += "#include <asm/unaligned.h>\n"
+	buf += "#include <scsi/scsi_proto.h>\n\n"
 	buf += "#include <target/target_core_base.h>\n"
 	buf += "#include <target/target_core_fabric.h>\n"
 	buf += "#include <target/target_core_fabric_configfs.h>\n"
@@ -230,8 +231,14 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	}\n"
 	buf += "	tpg->" + fabric_mod_port + " = " + fabric_mod_port + ";\n"
 	buf += "	tpg->" + fabric_mod_port + "_tpgt = tpgt;\n\n"
-	buf += "	ret = core_tpg_register(&" + fabric_mod_name + "_ops, wwn,\n"
-	buf += "				&tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
+
+	if proto_ident == "FC":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);\n"
+	elif proto_ident == "SAS":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
+	elif proto_ident == "iSCSI":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_ISCSI);\n"
+
 	buf += "	if (ret < 0) {\n"
 	buf += "		kfree(tpg);\n"
 	buf += "		return NULL;\n"
@@ -292,7 +299,7 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 
 	buf += "static const struct target_core_fabric_ops " + fabric_mod_name + "_ops = {\n"
 	buf += "	.module				= THIS_MODULE,\n"
-	buf += "	.name				= " + fabric_mod_name + ",\n"
+	buf += "	.name				= \"" + fabric_mod_name + "\",\n"
 	buf += "	.get_fabric_name		= " + fabric_mod_name + "_get_fabric_name,\n"
 	buf += "	.tpg_get_wwn			= " + fabric_mod_name + "_get_fabric_wwn,\n"
 	buf += "	.tpg_get_tag			= " + fabric_mod_name + "_get_tag,\n"
@@ -322,17 +329,17 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	.fabric_make_tpg		= " + fabric_mod_name + "_make_tpg,\n"
 	buf += "	.fabric_drop_tpg		= " + fabric_mod_name + "_drop_tpg,\n"
 	buf += "\n"
-	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs;\n"
+	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs,\n"
 	buf += "};\n\n"
 
 	buf += "static int __init " + fabric_mod_name + "_init(void)\n"
 	buf += "{\n"
-	buf += "	return target_register_template(" + fabric_mod_name + "_ops);\n"
+	buf += "	return target_register_template(&" + fabric_mod_name + "_ops);\n"
 	buf += "};\n\n"
 
 	buf += "static void __exit " + fabric_mod_name + "_exit(void)\n"
 	buf += "{\n"
-	buf += "	target_unregister_template(" + fabric_mod_name + "_ops);\n"
+	buf += "	target_unregister_template(&" + fabric_mod_name + "_ops);\n"
 	buf += "};\n\n"
 
 	buf += "MODULE_DESCRIPTION(\"" + fabric_mod_name.upper() + " series fabric driver\");\n"
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
index 77d14d51a670..0a5c3290e732 100644
--- a/Documentation/trace/coresight.txt
+++ b/Documentation/trace/coresight.txt
@@ -15,7 +15,7 @@ HW assisted tracing is becoming increasingly useful when dealing with systems
 that have many SoCs and other components like GPU and DMA engines.  ARM has
 developed a HW assisted tracing solution by means of different components, each
 being added to a design at synthesis time to cater to specific tracing needs.
-Compoments are generally categorised as source, link and sinks and are
+Components are generally categorised as source, link and sinks and are
 (usually) discovered using the AMBA bus.
 
 "Sources" generate a compressed stream representing the processor instruction
@@ -138,7 +138,7 @@ void coresight_unregister(struct coresight_device *csdev);
 
 The registering function is taking a "struct coresight_device *csdev" and
 register the device with the core framework.  The unregister function takes
-a reference to a "strut coresight_device", obtained at registration time.
+a reference to a "struct coresight_device", obtained at registration time.
 
 If everything goes well during the registration process the new devices will
 show up under /sys/bus/coresight/devices, as showns here for a TC2 platform:
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 7ddb1e319f84..ef621d34ba5b 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -346,6 +346,11 @@ of ftrace. Here is a list of some of the key files:
 	  x86-tsc: Architectures may define their own clocks. For
 	  	   example, x86 uses its own TSC cycle clock here.
 
+	  ppc-tb: This uses the powerpc timebase register value.
+		  This is in sync across CPUs and can also be used
+		  to correlate events across hypervisor/guest if
+		  tb_offset is known.
+
 	To set a clock, simply echo the clock name into this file.
 
 	  echo global > trace_clock
@@ -686,6 +691,8 @@ The above is mostly meaningful for kernel developers.
 	 The marks are determined by the difference between this
 	 current trace and the next trace.
 	  '$' - greater than 1 second
+	  '@' - greater than 100 milisecond
+	  '*' - greater than 10 milisecond
 	  '#' - greater than 1000 microsecond
 	  '!' - greater than 100 microsecond
 	  '+' - greater than 10 microsecond
@@ -1939,26 +1946,49 @@ want, depending on your needs.
 
   ie:
 
-  0)               |    up_write() {
-  0)   0.646 us    |      _spin_lock_irqsave();
-  0)   0.684 us    |      _spin_unlock_irqrestore();
-  0)   3.123 us    |    }
-  0)   0.548 us    |    fput();
-  0) + 58.628 us   |  }
+  3) # 1837.709 us |          } /* __switch_to */
+  3)               |          finish_task_switch() {
+  3)   0.313 us    |            _raw_spin_unlock_irq();
+  3)   3.177 us    |          }
+  3) # 1889.063 us |        } /* __schedule */
+  3) ! 140.417 us  |      } /* __schedule */
+  3) # 2034.948 us |    } /* schedule */
+  3) * 33998.59 us |  } /* schedule_preempt_disabled */
 
   [...]
 
-  0)               |      putname() {
-  0)               |        kmem_cache_free() {
-  0)   0.518 us    |          __phys_addr();
-  0)   1.757 us    |        }
-  0)   2.861 us    |      }
-  0) ! 115.305 us  |    }
-  0) ! 116.402 us  |  }
+  1)   0.260 us    |              msecs_to_jiffies();
+  1)   0.313 us    |              __rcu_read_unlock();
+  1) + 61.770 us   |            }
+  1) + 64.479 us   |          }
+  1)   0.313 us    |          rcu_bh_qs();
+  1)   0.313 us    |          __local_bh_enable();
+  1) ! 217.240 us  |        }
+  1)   0.365 us    |        idle_cpu();
+  1)               |        rcu_irq_exit() {
+  1)   0.417 us    |          rcu_eqs_enter_common.isra.47();
+  1)   3.125 us    |        }
+  1) ! 227.812 us  |      }
+  1) ! 457.395 us  |    }
+  1) @ 119760.2 us |  }
+
+  [...]
+
+  2)               |    handle_IPI() {
+  1)   6.979 us    |                  }
+  2)   0.417 us    |      scheduler_ipi();
+  1)   9.791 us    |                }
+  1) + 12.917 us   |              }
+  2)   3.490 us    |    }
+  1) + 15.729 us   |            }
+  1) + 18.542 us   |          }
+  2) $ 3594274 us  |  }
 
   + means that the function exceeded 10 usecs.
   ! means that the function exceeded 100 usecs.
   # means that the function exceeded 1000 usecs.
+  * means that the function exceeded 10 msecs.
+  @ means that the function exceeded 100 msecs.
   $ means that the function exceeded 1 sec.
 
 
diff --git a/Documentation/usb/gadget-testing.txt b/Documentation/usb/gadget-testing.txt
index 592678009c15..b24d3ef89166 100644
--- a/Documentation/usb/gadget-testing.txt
+++ b/Documentation/usb/gadget-testing.txt
@@ -237,9 +237,7 @@ Testing the LOOPBACK function
 -----------------------------
 
 device: run the gadget
-host: test-usb
-
-http://www.linux-usb.org/usbtest/testusb.c
+host: test-usb (tools/usb/testusb.c)
 
 8. MASS STORAGE function
 ========================
@@ -586,9 +584,8 @@ Testing the SOURCESINK function
 -------------------------------
 
 device: run the gadget
-host: test-usb
+host: test-usb (tools/usb/testusb.c)
 
-http://www.linux-usb.org/usbtest/testusb.c
 
 16. UAC1 function
 =================
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index b5f83911732a..4a15c90bc11d 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -521,10 +521,10 @@ enabling hardware LPM, the host can automatically put the device into
 lower power state(L1 for usb2.0 devices, or U1/U2 for usb3.0 devices),
 which state device can enter and resume very quickly.
 
-The user interface for controlling USB2 hardware LPM is located in the
+The user interface for controlling hardware LPM is located in the
 power/ subdirectory of each USB device's sysfs directory, that is, in
 /sys/bus/usb/devices/.../power/ where "..." is the device's ID. The
-relevant attribute files is usb2_hardware_lpm.
+relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm.
 
 	power/usb2_hardware_lpm
 
@@ -537,6 +537,17 @@ relevant attribute files is usb2_hardware_lpm.
 		can write y/Y/1 or n/N/0 to the file to	enable/disable
 		USB2 hardware LPM manually. This is for	test purpose mainly.
 
+	power/usb3_hardware_lpm
+
+		When a USB 3.0 lpm-capable device is plugged in to a
+		xHCI host which supports link PM, it will check if U1
+		and U2 exit latencies have been set in the BOS
+		descriptor; if the check is is passed and the host
+		supports USB3 hardware LPM, USB3 hardware LPM will be
+		enabled for the device and this file will be created.
+		The file holds a string value (enable or disable)
+		indicating whether or not USB3 hardware LPM is
+		enabled for the device.
 
 	USB Port Power Control
 	----------------------
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a7926a90156f..a4ebcb712375 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3277,6 +3277,7 @@ should put the acknowledged interrupt vector into the 'epr' field.
 		struct {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #define KVM_SYSTEM_EVENT_RESET          2
+#define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
 			__u64 flags;
 		} system_event;
@@ -3296,6 +3297,10 @@ Valid values for 'type' are:
   KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
    As with SHUTDOWN, userspace can choose to ignore the request, or
    to schedule the reset to occur in the future and may call KVM_RUN again.
+  KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
+   has requested a crash condition maintenance. Userspace can choose
+   to ignore the request, or to gather VM memory core dump and/or
+   reset/shutdown of the VM.
 
 		/* Fix the size of the union. */
 		char padding[256];
diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/vm/userfaultfd.txt
new file mode 100644
index 000000000000..70a3c94d1941
--- /dev/null
+++ b/Documentation/vm/userfaultfd.txt
@@ -0,0 +1,144 @@
+= Userfaultfd =
+
+== Objective ==
+
+Userfaults allow the implementation of on-demand paging from userland
+and more generally they allow userland to take control of various
+memory page faults, something otherwise only the kernel code could do.
+
+For example userfaults allows a proper and more optimal implementation
+of the PROT_NONE+SIGSEGV trick.
+
+== Design ==
+
+Userfaults are delivered and resolved through the userfaultfd syscall.
+
+The userfaultfd (aside from registering and unregistering virtual
+memory ranges) provides two primary functionalities:
+
+1) read/POLLIN protocol to notify a userland thread of the faults
+   happening
+
+2) various UFFDIO_* ioctls that can manage the virtual memory regions
+   registered in the userfaultfd that allows userland to efficiently
+   resolve the userfaults it receives via 1) or to manage the virtual
+   memory in the background
+
+The real advantage of userfaults if compared to regular virtual memory
+management of mremap/mprotect is that the userfaults in all their
+operations never involve heavyweight structures like vmas (in fact the
+userfaultfd runtime load never takes the mmap_sem for writing).
+
+Vmas are not suitable for page- (or hugepage) granular fault tracking
+when dealing with virtual address spaces that could span
+Terabytes. Too many vmas would be needed for that.
+
+The userfaultfd once opened by invoking the syscall, can also be
+passed using unix domain sockets to a manager process, so the same
+manager process could handle the userfaults of a multitude of
+different processes without them being aware about what is going on
+(well of course unless they later try to use the userfaultfd
+themselves on the same region the manager is already tracking, which
+is a corner case that would currently return -EBUSY).
+
+== API ==
+
+When first opened the userfaultfd must be enabled invoking the
+UFFDIO_API ioctl specifying a uffdio_api.api value set to UFFD_API (or
+a later API version) which will specify the read/POLLIN protocol
+userland intends to speak on the UFFD and the uffdio_api.features
+userland requires. The UFFDIO_API ioctl if successful (i.e. if the
+requested uffdio_api.api is spoken also by the running kernel and the
+requested features are going to be enabled) will return into
+uffdio_api.features and uffdio_api.ioctls two 64bit bitmasks of
+respectively all the available features of the read(2) protocol and
+the generic ioctl available.
+
+Once the userfaultfd has been enabled the UFFDIO_REGISTER ioctl should
+be invoked (if present in the returned uffdio_api.ioctls bitmask) to
+register a memory range in the userfaultfd by setting the
+uffdio_register structure accordingly. The uffdio_register.mode
+bitmask will specify to the kernel which kind of faults to track for
+the range (UFFDIO_REGISTER_MODE_MISSING would track missing
+pages). The UFFDIO_REGISTER ioctl will return the
+uffdio_register.ioctls bitmask of ioctls that are suitable to resolve
+userfaults on the range registered. Not all ioctls will necessarily be
+supported for all memory types depending on the underlying virtual
+memory backend (anonymous memory vs tmpfs vs real filebacked
+mappings).
+
+Userland can use the uffdio_register.ioctls to manage the virtual
+address space in the background (to add or potentially also remove
+memory from the userfaultfd registered range). This means a userfault
+could be triggering just before userland maps in the background the
+user-faulted page.
+
+The primary ioctl to resolve userfaults is UFFDIO_COPY. That
+atomically copies a page into the userfault registered range and wakes
+up the blocked userfaults (unless uffdio_copy.mode &
+UFFDIO_COPY_MODE_DONTWAKE is set). Other ioctl works similarly to
+UFFDIO_COPY. They're atomic as in guaranteeing that nothing can see an
+half copied page since it'll keep userfaulting until the copy has
+finished.
+
+== QEMU/KVM ==
+
+QEMU/KVM is using the userfaultfd syscall to implement postcopy live
+migration. Postcopy live migration is one form of memory
+externalization consisting of a virtual machine running with part or
+all of its memory residing on a different node in the cloud. The
+userfaultfd abstraction is generic enough that not a single line of
+KVM kernel code had to be modified in order to add postcopy live
+migration to QEMU.
+
+Guest async page faults, FOLL_NOWAIT and all other GUP features work
+just fine in combination with userfaults. Userfaults trigger async
+page faults in the guest scheduler so those guest processes that
+aren't waiting for userfaults (i.e. network bound) can keep running in
+the guest vcpus.
+
+It is generally beneficial to run one pass of precopy live migration
+just before starting postcopy live migration, in order to avoid
+generating userfaults for readonly guest regions.
+
+The implementation of postcopy live migration currently uses one
+single bidirectional socket but in the future two different sockets
+will be used (to reduce the latency of the userfaults to the minimum
+possible without having to decrease /proc/sys/net/ipv4/tcp_wmem).
+
+The QEMU in the source node writes all pages that it knows are missing
+in the destination node, into the socket, and the migration thread of
+the QEMU running in the destination node runs UFFDIO_COPY|ZEROPAGE
+ioctls on the userfaultfd in order to map the received pages into the
+guest (UFFDIO_ZEROCOPY is used if the source page was a zero page).
+
+A different postcopy thread in the destination node listens with
+poll() to the userfaultfd in parallel. When a POLLIN event is
+generated after a userfault triggers, the postcopy thread read() from
+the userfaultfd and receives the fault address (or -EAGAIN in case the
+userfault was already resolved and waken by a UFFDIO_COPY|ZEROPAGE run
+by the parallel QEMU migration thread).
+
+After the QEMU postcopy thread (running in the destination node) gets
+the userfault address it writes the information about the missing page
+into the socket. The QEMU source node receives the information and
+roughly "seeks" to that page address and continues sending all
+remaining missing pages from that new page offset. Soon after that
+(just the time to flush the tcp_wmem queue through the network) the
+migration thread in the QEMU running in the destination node will
+receive the page that triggered the userfault and it'll map it as
+usual with the UFFDIO_COPY|ZEROPAGE (without actually knowing if it
+was spontaneously sent by the source or if it was an urgent page
+requested through an userfault).
+
+By the time the userfaults start, the QEMU in the destination node
+doesn't need to keep any per-page state bitmap relative to the live
+migration around and a single per-page bitmap has to be maintained in
+the QEMU running in the source node to know which pages are still
+missing in the destination node. The bitmap in the source node is
+checked to find which missing pages to send in round robin and we seek
+over it when receiving incoming userfaults. After sending each page of
+course the bitmap is updated accordingly. It's also useful to avoid
+sending the same page twice (in case the userfault is read by the
+postcopy thread just before UFFDIO_COPY|ZEROPAGE runs in the migration
+thread).
diff --git a/Documentation/x86/kernel-stacks b/Documentation/x86/kernel-stacks
index 0f3a6c201943..9a0aa4d3a866 100644
--- a/Documentation/x86/kernel-stacks
+++ b/Documentation/x86/kernel-stacks
@@ -16,7 +16,7 @@ associated with each CPU.  These stacks are only used while the kernel
 is in control on that CPU; when a CPU returns to user space the
 specialized stacks contain no useful data.  The main CPU stacks are:
 
-* Interrupt stack.  IRQSTACKSIZE
+* Interrupt stack.  IRQ_STACK_SIZE
 
   Used for external hardware interrupts.  If this is the first external
   hardware interrupt (i.e. not a nested hardware interrupt) then the
diff --git a/Documentation/x86/mtrr.txt b/Documentation/x86/mtrr.txt
index 860bc3adc223..dc3e703913ac 100644
--- a/Documentation/x86/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -6,10 +6,22 @@ Luis R. Rodriguez <mcgrof@do-not-panic.com> - April 9, 2015
 ===============================================================================
 Phasing out MTRR use
 
-MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
-of effective MTRR that is expected to be supported will be for write-combining.
-As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
-MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+MTRR use is replaced on modern x86 hardware with PAT. Direct MTRR use by
+drivers on Linux is now completely phased out, device drivers should use
+arch_phys_wc_add() in combination with ioremap_wc() to make MTRR effective on
+non-PAT systems while a no-op but equally effective on PAT enabled systems.
+
+Even if Linux does not use MTRRs directly, some x86 platform firmware may still
+set up MTRRs early before booting the OS. They do this as some platform
+firmware may still have implemented access to MTRRs which would be controlled
+and handled by the platform firmware directly. An example of platform use of
+MTRRs is through the use of SMI handlers, one case could be for fan control,
+the platform code would need uncachable access to some of its fan control
+registers. Such platform access does not need any Operating System MTRR code in
+place other than mtrr_type_lookup() to ensure any OS specific mapping requests
+are aligned with platform MTRR setup. If MTRRs are only set up by the platform
+firmware code though and the OS does not make any specific MTRR mapping
+requests mtrr_type_lookup() should always return MTRR_TYPE_INVALID.
 
 For details refer to Documentation/x86/pat.txt.
 
diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt
index 82fbdbc1e0b0..95a4d34af3fd 100644
--- a/Documentation/x86/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
@@ -17,7 +17,8 @@ Offset	Proto	Name		Meaning
 				(struct ist_info)
 080/010	ALL	hd0_info	hd0 disk parameter, OBSOLETE!!
 090/010	ALL	hd1_info	hd1 disk parameter, OBSOLETE!!
-0A0/010	ALL	sys_desc_table	System description table (struct sys_desc_table)
+0A0/010	ALL	sys_desc_table	System description table (struct sys_desc_table),
+				OBSOLETE!!
 0B0/010	ALL	olpc_ofw_header	OLPC's OpenFirmware CIF and friends
 0C0/004	ALL	ext_ramdisk_image ramdisk_image high 32bits
 0C4/004	ALL	ext_ramdisk_size  ramdisk_size high 32bits
diff --git a/MAINTAINERS b/MAINTAINERS
index 8133cefb6b6e..6dfc2242715d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -158,6 +158,7 @@ L:	linux-wpan@vger.kernel.org
 S:	Maintained
 F:	net/6lowpan/
 F:	include/net/6lowpan.h
+F:	Documentation/networking/6lowpan.txt
 
 6PACK NETWORK DRIVER FOR AX.25
 M:	Andreas Koensgen <ajk@comnets.uni-bremen.de>
@@ -361,11 +362,11 @@ S:	Supported
 F:	drivers/input/touchscreen/ad7879.c
 
 ADDRESS SPACE LAYOUT RANDOMIZATION (ASLR)
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 S:	Maintained
 
 ADM1025 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/adm1025
@@ -430,7 +431,7 @@ S:	Maintained
 F:	drivers/macintosh/therm_adt746x.c
 
 ADT7475 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/adt7475
@@ -445,7 +446,7 @@ F:	drivers/input/misc/adxl34x.c
 
 ADVANSYS SCSI DRIVER
 M:	Matthew Wilcox <matthew@wil.cx>
-M:	Hannes Reinecke <hare@suse.de>
+M:	Hannes Reinecke <hare@suse.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	Documentation/scsi/advansys.txt
@@ -506,7 +507,7 @@ F:	drivers/scsi/aha152x*
 F:	drivers/scsi/pcmcia/aha152x*
 
 AIC7XXX / AIC79XX SCSI DRIVER
-M:	Hannes Reinecke <hare@suse.de>
+M:	Hannes Reinecke <hare@suse.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/aic7xxx/
@@ -556,6 +557,12 @@ S:	Maintained
 F:	Documentation/i2c/busses/i2c-ali1563
 F:	drivers/i2c/busses/i2c-ali1563.c
 
+ALLWINNER SECURITY SYSTEM
+M:	Corentin Labbe <clabbe.montjoie@gmail.com>
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+F:	drivers/crypto/sunxi-ss/
+
 ALPHA PORT
 M:	Richard Henderson <rth@twiddle.net>
 M:	Ivan Kokshaysky <ink@jurassic.park.msu.ru>
@@ -636,9 +643,14 @@ M:	Oded Gabbay <oded.gabbay@gmail.com>
 L:	dri-devel@lists.freedesktop.org
 T:	git git://people.freedesktop.org/~gabbayo/linux.git
 S:	Supported
+F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
 F:	drivers/gpu/drm/amd/amdkfd/
 F:	drivers/gpu/drm/amd/include/cik_structs.h
 F:	drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+F:	drivers/gpu/drm/amd/include/vi_structs.h
 F:	drivers/gpu/drm/radeon/radeon_kfd.c
 F:	drivers/gpu/drm/radeon/radeon_kfd.h
 F:	include/uapi/linux/kfd_ioctl.h
@@ -728,6 +740,12 @@ X:	drivers/iio/*/adjd*
 F:	drivers/staging/iio/*/ad*
 F:	staging/iio/trigger/iio-trig-bfin-timer.c
 
+ANALOG DEVICES INC DMA DRIVERS
+M:	Lars-Peter Clausen <lars@metafoo.de>
+W:	http://ez.analog.com/community/linux-device-drivers
+S:	Supported
+F:	drivers/dma/dma-axi-dmac.c
+
 ANDROID DRIVERS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	Arve Hjønnevåg <arve@android.com>
@@ -746,7 +764,7 @@ S:	Maintained
 F:	sound/aoa/
 
 APM DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 S:	Odd fixes
 F:	arch/x86/kernel/apm_32.c
 F:	include/linux/apm_bios.h
@@ -799,11 +817,13 @@ F:	arch/arm/include/asm/floppy.h
 ARM PMU PROFILING AND DEBUGGING
 M:	Will Deacon <will.deacon@arm.com>
 S:	Maintained
-F:	arch/arm/kernel/perf_event*
+F:	arch/arm/kernel/perf_*
 F:	arch/arm/oprofile/common.c
-F:	arch/arm/include/asm/pmu.h
 F:	arch/arm/kernel/hw_breakpoint.c
 F:	arch/arm/include/asm/hw_breakpoint.h
+F:	arch/arm/include/asm/perf_event.h
+F:	drivers/perf/arm_pmu.c
+F:	include/linux/perf/arm_pmu.h
 
 ARM PORT
 M:	Russell King <linux@arm.linux.org.uk>
@@ -927,7 +947,7 @@ M:	Sunil Goutham <sgoutham@cavium.com>
 M:	Robert Richter <rric@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
-F:	drivers/net/ethernet/cavium/
+F:	drivers/net/ethernet/cavium/thunder/
 
 ARM/CIRRUS LOGIC CLPS711X ARM ARCHITECTURE
 M:	Alexander Shiyan <shc_work@mail.ru>
@@ -1001,6 +1021,7 @@ ARM/CONEXANT DIGICOLOR MACHINE SUPPORT
 M:	Baruch Siach <baruch@tkos.co.il>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
+F:	arch/arm/boot/dts/cx92755*
 N:	digicolor
 
 ARM/EBSA110 MACHINE SUPPORT
@@ -1324,7 +1345,7 @@ F:	arch/arm/mach-pxa/include/mach/palmtc.h
 F:	arch/arm/mach-pxa/palmtc.c
 
 ARM/PALM TREO SUPPORT
-M:	Tomas Cech <sleep_walker@suse.cz>
+M:	Tomas Cech <sleep_walker@suse.com>
 L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
@@ -1464,9 +1485,7 @@ F:	arch/arm/boot/dts/emev2*
 F:	arch/arm/boot/dts/r7s*
 F:	arch/arm/boot/dts/r8a*
 F:	arch/arm/boot/dts/sh*
-F:	arch/arm/configs/armadillo800eva_defconfig
 F:	arch/arm/configs/bockw_defconfig
-F:	arch/arm/configs/kzm9g_defconfig
 F:	arch/arm/configs/marzen_defconfig
 F:	arch/arm/configs/shmobile_defconfig
 F:	arch/arm/include/debug/renesas-scif.S
@@ -1503,8 +1522,10 @@ S:	Maintained
 F:	arch/arm/mach-sti/
 F:	arch/arm/boot/dts/sti*
 F:	drivers/clocksource/arm_global_timer.c
+F:	drivers/clocksource/clksrc_st_lpc.c
 F:	drivers/i2c/busses/i2c-st.c
 F:	drivers/media/rc/st_rc.c
+F:	drivers/media/platform/sti/c8sectpfe/
 F:	drivers/mmc/host/sdhci-st.c
 F:	drivers/phy/phy-miphy28lp.c
 F:	drivers/phy/phy-miphy365x.c
@@ -1578,7 +1599,10 @@ ARM/UNIPHIER ARCHITECTURE
 M:	Masahiro Yamada <yamada.masahiro@socionext.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
+F:	arch/arm/boot/dts/uniphier*
 F:	arch/arm/mach-uniphier/
+F:	drivers/pinctrl/uniphier/
+F:	drivers/tty/serial/8250/8250_uniphier.c
 N:	uniphier
 
 ARM/Ux500 ARM ARCHITECTURE
@@ -1614,6 +1638,7 @@ M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/boot/dts/vexpress*
+F:	arch/arm64/boot/dts/arm/vexpress*
 F:	arch/arm/mach-vexpress/
 F:	*/*/vexpress*
 F:	*/*/*/vexpress*
@@ -1672,7 +1697,7 @@ M:	Michal Simek <michal.simek@xilinx.com>
 R:	Sören Brinkmann <soren.brinkmann@xilinx.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://wiki.xilinx.com
-T:	git git://git.xilinx.com/linux-xlnx.git
+T:	git https://github.com/Xilinx/linux-xlnx.git
 S:	Supported
 F:	arch/arm/mach-zynq/
 F:	drivers/cpuidle/cpuidle-zynq.c
@@ -1913,6 +1938,14 @@ W:	http://atmelwlandriver.sourceforge.net/
 S:	Maintained
 F:	drivers/net/wireless/atmel*
 
+ATMEL MAXTOUCH DRIVER
+M:	Nick Dyer <nick.dyer@itdev.co.uk>
+T:	git git://github.com/atmel-maxtouch/linux.git
+S:	Supported
+F:	Documentation/devicetree/bindings/input/atmel,maxtouch.txt
+F:	drivers/input/touchscreen/atmel_mxt_ts.c
+F:	include/linux/platform_data/atmel_mxt_ts.h
+
 ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER
 M:	Bradley Grove <linuxdrivers@attotech.com>
 L:	linux-scsi@vger.kernel.org
@@ -2216,7 +2249,9 @@ F:	drivers/clocksource/bcm_kona_timer.c
 BROADCOM BCM2835 ARM ARCHITECTURE
 M:	Stephen Warren <swarren@wwwdotorg.org>
 M:	Lee Jones <lee@kernel.org>
+M:	Eric Anholt <eric@anholt.net>
 L:	linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rpi/linux-rpi.git
 S:	Maintained
 N:	bcm2835
@@ -2404,7 +2439,7 @@ F:	drivers/gpio/gpio-bt8xx.c
 BTRFS FILE SYSTEM
 M:	Chris Mason <clm@fb.com>
 M:	Josef Bacik <jbacik@fb.com>
-M:	David Sterba <dsterba@suse.cz>
+M:	David Sterba <dsterba@suse.com>
 L:	linux-btrfs@vger.kernel.org
 W:	http://btrfs.wiki.kernel.org/
 Q:	http://patchwork.kernel.org/project/linux-btrfs/list/
@@ -2540,7 +2575,6 @@ M:     Raghu Vatsavayi <raghu.vatsavayi@caviumnetworks.com>
 L:     netdev@vger.kernel.org
 W:     http://www.cavium.com
 S:     Supported
-F:     drivers/net/ethernet/cavium/
 F:     drivers/net/ethernet/cavium/liquidio/
 
 CC2520 IEEE-802.15.4 RADIO DRIVER
@@ -2562,19 +2596,40 @@ F:	arch/powerpc/include/uapi/asm/spu*.h
 F:	arch/powerpc/oprofile/*cell*
 F:	arch/powerpc/platforms/cell/
 
-CEPH DISTRIBUTED FILE SYSTEM CLIENT
+CEPH COMMON CODE (LIBCEPH)
+M:	Ilya Dryomov <idryomov@gmail.com>
 M:	"Yan, Zheng" <zyan@redhat.com>
 M:	Sage Weil <sage@redhat.com>
 L:	ceph-devel@vger.kernel.org
 W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
 S:	Supported
-F:	Documentation/filesystems/ceph.txt
-F:	fs/ceph/
 F:	net/ceph/
 F:	include/linux/ceph/
 F:	include/linux/crush/
 
+CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
+M:	"Yan, Zheng" <zyan@redhat.com>
+M:	Sage Weil <sage@redhat.com>
+M:	Ilya Dryomov <idryomov@gmail.com>
+L:	ceph-devel@vger.kernel.org
+W:	http://ceph.com/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
+S:	Supported
+F:	Documentation/filesystems/ceph.txt
+F:	fs/ceph/
+
+CERTIFICATE HANDLING:
+M:	David Howells <dhowells@redhat.com>
+M:	David Woodhouse <dwmw2@infradead.org>
+L:	keyrings@linux-nfs.org
+S:	Maintained
+F:	Documentation/module-signing.txt
+F:	certs/
+F:	scripts/extract-cert.c
+
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 L:	linux-usb@vger.kernel.org
 S:	Orphan
@@ -2735,7 +2790,7 @@ COCCINELLE/Semantic Patches (SmPL)
 M:	Julia Lawall <Julia.Lawall@lip6.fr>
 M:	Gilles Muller <Gilles.Muller@lip6.fr>
 M:	Nicolas Palix <nicolas.palix@imag.fr>
-M:	Michal Marek <mmarek@suse.cz>
+M:	Michal Marek <mmarek@suse.com>
 L:	cocci@systeme.lip6.fr (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git misc
 W:	http://coccinelle.lip6.fr/
@@ -2851,7 +2906,7 @@ F:	kernel/cpuset.c
 
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
-M:	Michal Hocko <mhocko@suse.cz>
+M:	Michal Hocko <mhocko@kernel.org>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -2932,7 +2987,7 @@ F:	arch/x86/kernel/cpuid.c
 F:	arch/x86/kernel/msr.c
 
 CPU POWER MONITORING SUBSYSTEM
-M:	Thomas Renninger <trenn@suse.de>
+M:	Thomas Renninger <trenn@suse.com>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 F:	tools/power/cpupower/
@@ -3162,7 +3217,7 @@ F:	Documentation/networking/dmfe.txt
 F:	drivers/net/ethernet/dec/tulip/dmfe.c
 
 DC390/AM53C974 SCSI driver
-M:	Hannes Reinecke <hare@suse.de>
+M:	Hannes Reinecke <hare@suse.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/am53c974.c
@@ -3366,7 +3421,7 @@ W:	http://www.win.tue.nl/~aeb/partitions/partition_types-1.html
 S:	Maintained
 
 DISKQUOTA
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 S:	Maintained
 F:	Documentation/filesystems/quota.txt
 F:	fs/quota/
@@ -3422,7 +3477,7 @@ F:	Documentation/hwmon/dme1737
 F:	drivers/hwmon/dme1737.c
 
 DMI/SMBIOS SUPPORT
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 S:	Maintained
 T:	quilt http://jdelvare.nerim.net/devel/linux/jdelvare-dmi/
 F:	Documentation/ABI/testing/sysfs-firmware-dmi-tables
@@ -3440,6 +3495,7 @@ X:	Documentation/devicetree/
 X:	Documentation/acpi
 X:	Documentation/power
 X:	Documentation/spi
+X:	Documentation/DocBook/media
 T:	git git://git.lwn.net/linux-2.6.git docs-next
 
 DOUBLETALK DRIVER
@@ -3536,6 +3592,15 @@ F:	drivers/gpu/drm/exynos/
 F:	include/drm/exynos*
 F:	include/uapi/drm/exynos*
 
+DRM DRIVERS FOR FREESCALE DCU
+M:	Jianwei Wang <jianwei.wang.chn@gmail.com>
+M:	Alison Wang <alison.wang@freescale.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Supported
+F:	drivers/gpu/drm/fsl-dcu/
+F:	Documentation/devicetree/bindings/video/fsl,dcu.txt
+F:	Documentation/devicetree/bindings/panel/nec,nl4827hc19_05b.txt
+
 DRM DRIVERS FOR FREESCALE IMX
 M:	Philipp Zabel <p.zabel@pengutronix.de>
 L:	dri-devel@lists.freedesktop.org
@@ -3573,6 +3638,15 @@ S:	Maintained
 F:	drivers/gpu/drm/rockchip/
 F:	Documentation/devicetree/bindings/video/rockchip*
 
+DRM DRIVERS FOR STI
+M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
+M:	Vincent Abriou <vincent.abriou@st.com>
+L:	dri-devel@lists.freedesktop.org
+T:	git http://git.linaro.org/people/benjamin.gaignard/kernel.git
+S:	Maintained
+F:	drivers/gpu/drm/sti
+F:	Documentation/devicetree/bindings/gpu/st,stih4xx.txt
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -4038,22 +4112,13 @@ F:	drivers/of/of_mdio.c
 F:	drivers/of/of_net.c
 
 EXT2 FILE SYSTEM
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 F:	Documentation/filesystems/ext2.txt
 F:	fs/ext2/
 F:	include/linux/ext2*
 
-EXT3 FILE SYSTEM
-M:	Jan Kara <jack@suse.cz>
-M:	Andrew Morton <akpm@linux-foundation.org>
-M:	Andreas Dilger <adilger.kernel@dilger.ca>
-L:	linux-ext4@vger.kernel.org
-S:	Maintained
-F:	Documentation/filesystems/ext3.txt
-F:	fs/ext3/
-
 EXT4 FILE SYSTEM
 M:	"Theodore Ts'o" <tytso@mit.edu>
 M:	Andreas Dilger <adilger.kernel@dilger.ca>
@@ -4096,7 +4161,7 @@ F:	drivers/video/fbdev/exynos/exynos_mipi*
 F:	include/video/exynos_mipi*
 
 F71805F HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/f71805f
@@ -4231,7 +4296,7 @@ S:	Maintained
 F:	drivers/block/rsxx/
 
 FLOPPY DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/floppy.git
 S:	Odd fixes
 F:	drivers/block/floppy.c
@@ -4392,6 +4457,7 @@ F:	include/linux/fscache*.h
 F2FS FILE SYSTEM
 M:	Jaegeuk Kim <jaegeuk@kernel.org>
 M:	Changman Lee <cm224.lee@samsung.com>
+R:	Chao Yu <chao2.yu@samsung.com>
 L:	linux-f2fs-devel@lists.sourceforge.net
 W:	http://en.wikipedia.org/wiki/F2FS
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
@@ -4400,6 +4466,7 @@ F:	Documentation/filesystems/f2fs.txt
 F:	Documentation/ABI/testing/sysfs-fs-f2fs
 F:	fs/f2fs/
 F:	include/linux/f2fs_fs.h
+F:	include/trace/events/f2fs.h
 
 FUJITSU FR-V (FRV) PORT
 M:	David Howells <dhowells@redhat.com>
@@ -4652,7 +4719,7 @@ F:	drivers/media/usb/stk1160/
 
 H8/300 ARCHITECTURE
 M:	Yoshinori Sato <ysato@users.sourceforge.jp>
-L:	uclinux-h8-devel@lists.sourceforge.jp
+L:	uclinux-h8-devel@lists.sourceforge.jp (moderated for non-subscribers)
 W:	http://uclinux-h8.sourceforge.jp
 T:	git git://git.sourceforge.jp/gitroot/uclinux-h8/linux.git
 S:	Maintained
@@ -4699,7 +4766,7 @@ S:	Maintained
 F:	drivers/media/usb/hackrf/
 
 HARDWARE MONITORING
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
@@ -4802,7 +4869,7 @@ F:	include/linux/pm.h
 F:	arch/*/include/asm/suspend*.h
 
 HID CORE LAYER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 L:	linux-input@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
 S:	Maintained
@@ -4811,7 +4878,7 @@ F:	include/linux/hid*
 F:	include/uapi/linux/hid*
 
 HID SENSOR HUB DRIVERS
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 M:	Jonathan Cameron <jic23@kernel.org>
 M:	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
 L:	linux-input@vger.kernel.org
@@ -4943,9 +5010,10 @@ F:	drivers/scsi/storvsc_drv.c
 F:	drivers/video/fbdev/hyperv_fb.c
 F:	include/linux/hyperv.h
 F:	tools/hv/
+F:	Documentation/ABI/stable/sysfs-bus-vmbus
 
 I2C OVER PARALLEL PORT
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	Documentation/i2c/busses/i2c-parport
@@ -4954,7 +5022,7 @@ F:	drivers/i2c/busses/i2c-parport.c
 F:	drivers/i2c/busses/i2c-parport-light.c
 
 I2C/SMBUS CONTROLLER DRIVERS FOR PC
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	Documentation/i2c/busses/i2c-ali1535
@@ -4995,7 +5063,7 @@ F:	drivers/i2c/busses/i2c-ismt.c
 F:	Documentation/i2c/busses/i2c-ismt
 
 I2C/SMBUS STUB DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/i2c-stub.c
@@ -5022,7 +5090,7 @@ L:	linux-acpi@vger.kernel.org
 S:	Maintained
 
 I2C-TAOS-EVM DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	Documentation/i2c/busses/i2c-taos-evm
@@ -5053,9 +5121,21 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git
 S:	Maintained
 F:	arch/ia64/
 
+IBM Power VMX Cryptographic instructions
+M:	Leonidas S. Barbosa <leosilva@linux.vnet.ibm.com>
+M:	Paulo Flabiano Smorigo <pfsmorigo@linux.vnet.ibm.com>
+L:	linux-crypto@vger.kernel.org
+S:	Supported
+F:	drivers/crypto/vmx/Makefile
+F:	drivers/crypto/vmx/Kconfig
+F:	drivers/crypto/vmx/vmx.c
+F:	drivers/crypto/vmx/aes*
+F:	drivers/crypto/vmx/ghash*
+F:	drivers/crypto/vmx/ppc-xlate.pl
+
 IBM Power in-Nest Crypto Acceleration
-M:	Marcelo Henrique Cerri <mhcerri@linux.vnet.ibm.com>
-M:	Fionnuala Gunter <fin@linux.vnet.ibm.com>
+M:	Leonidas S. Barbosa <leosilva@linux.vnet.ibm.com>
+M:	Paulo Flabiano Smorigo <pfsmorigo@linux.vnet.ibm.com>
 L:	linux-crypto@vger.kernel.org
 S:	Supported
 F:	drivers/crypto/nx/Makefile
@@ -5067,7 +5147,7 @@ F:	drivers/crypto/nx/nx_csbcpb.h
 F:	drivers/crypto/nx/nx_debugfs.h
 
 IBM Power 842 compression accelerator
-M:	Dan Streetman <ddstreet@us.ibm.com>
+M:	Dan Streetman <ddstreet@ieee.org>
 S:	Supported
 F:	drivers/crypto/nx/Makefile
 F:	drivers/crypto/nx/Kconfig
@@ -5551,8 +5631,8 @@ F:	include/uapi/linux/ip_vs.h
 F:	net/netfilter/ipvs/
 
 IPWIRELESS DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
-M:	David Sterba <dsterba@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
+M:	David Sterba <dsterba@suse.com>
 S:	Odd Fixes
 F:	drivers/tty/ipwireless/
 
@@ -5586,6 +5666,7 @@ F:	kernel/irq/
 IRQCHIP DRIVERS
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Jason Cooper <jason@lakedaemon.net>
+M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
@@ -5594,11 +5675,14 @@ F:	Documentation/devicetree/bindings/interrupt-controller/
 F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
-M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
+M:	Jiang Liu <jiang.liu@linux.intel.com>
+M:	Marc Zyngier <marc.zyngier@arm.com>
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
 F:	Documentation/IRQ-domain.txt
 F:	include/linux/irqdomain.h
 F:	kernel/irq/irqdomain.c
+F:	kernel/irq/msi.c
 
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
@@ -5672,7 +5756,7 @@ S:	Maintained
 F:	drivers/isdn/hardware/eicon/
 
 IT87 HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/it87
@@ -5737,21 +5821,20 @@ S:	Maintained
 F:	fs/jffs2/
 F:	include/uapi/linux/jffs2.h
 
-JOURNALLING LAYER FOR BLOCK DEVICES (JBD)
-M:	Andrew Morton <akpm@linux-foundation.org>
-M:	Jan Kara <jack@suse.cz>
-L:	linux-ext4@vger.kernel.org
-S:	Maintained
-F:	fs/jbd/
-F:	include/linux/jbd.h
-
 JOURNALLING LAYER FOR BLOCK DEVICES (JBD2)
 M:	"Theodore Ts'o" <tytso@mit.edu>
+M:	Jan Kara <jack@suse.com>
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 F:	fs/jbd2/
 F:	include/linux/jbd2.h
 
+JPU V4L2 MEM2MEM DRIVER FOR RENESAS
+M:	Mikhail Ulyanov <mikhail.ulyanov@cogentembedded.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/media/platform/rcar_jpu.c
+
 JSM Neo PCI based serial card
 M:	Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
 L:	linux-serial@vger.kernel.org
@@ -5803,7 +5886,7 @@ S:	Maintained
 F:	fs/autofs4/
 
 KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
-M:	Michal Marek <mmarek@suse.cz>
+M:	Michal Marek <mmarek@suse.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes
 L:	linux-kbuild@vger.kernel.org
@@ -5822,6 +5905,7 @@ S:	Odd Fixes
 
 KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
 M:	"J. Bruce Fields" <bfields@fieldses.org>
+M:	Jeff Layton <jlayton@poochiereds.net>
 L:	linux-nfs@vger.kernel.org
 W:	http://nfs.sourceforge.net/
 S:	Supported
@@ -5867,7 +5951,7 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
-M:	Alexander Graf <agraf@suse.de>
+M:	Alexander Graf <agraf@suse.com>
 L:	kvm-ppc@vger.kernel.org
 W:	http://kvm.qumranet.com
 T:	git git://github.com/agraf/linux-2.6.git
@@ -5878,14 +5962,12 @@ F:	arch/powerpc/kvm/
 KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
 M:	Christian Borntraeger <borntraeger@de.ibm.com>
 M:	Cornelia Huck <cornelia.huck@de.ibm.com>
-M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
 F:	Documentation/s390/kvm.txt
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/kvm/
-F:	drivers/s390/kvm/
 
 KERNEL VIRTUAL MACHINE (KVM) FOR ARM
 M:	Christoffer Dall <christoffer.dall@linaro.org>
@@ -5921,7 +6003,7 @@ F:	kernel/kexec.c
 
 KEYS/KEYRINGS:
 M:	David Howells <dhowells@redhat.com>
-L:	keyrings@linux-nfs.org
+L:	keyrings@vger.kernel.org
 S:	Maintained
 F:	Documentation/security/keys.txt
 F:	include/linux/key.h
@@ -5933,7 +6015,7 @@ KEYS-TRUSTED
 M:	David Safford <safford@us.ibm.com>
 M:	Mimi Zohar <zohar@linux.vnet.ibm.com>
 L:	linux-security-module@vger.kernel.org
-L:	keyrings@linux-nfs.org
+L:	keyrings@vger.kernel.org
 S:	Supported
 F:	Documentation/security/keys-trusted-encrypted.txt
 F:	include/keys/trusted-type.h
@@ -5944,7 +6026,7 @@ KEYS-ENCRYPTED
 M:	Mimi Zohar <zohar@linux.vnet.ibm.com>
 M:	David Safford <safford@us.ibm.com>
 L:	linux-security-module@vger.kernel.org
-L:	keyrings@linux-nfs.org
+L:	keyrings@vger.kernel.org
 S:	Supported
 F:	Documentation/security/keys-trusted-encrypted.txt
 F:	include/keys/encrypted-type.h
@@ -6014,17 +6096,16 @@ F:	Documentation/scsi/53c700.txt
 F:	drivers/scsi/53c700*
 
 LED SUBSYSTEM
-M:	Bryan Wu <cooloney@gmail.com>
 M:	Richard Purdie <rpurdie@rpsys.net>
 M:	Jacek Anaszewski <j.anaszewski@samsung.com>
 L:	linux-leds@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/linux-leds.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
 S:	Maintained
 F:	drivers/leds/
 F:	include/linux/leds.h
 
 LEGACY EEPROM DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 S:	Maintained
 F:	Documentation/misc-devices/eeprom
 F:	drivers/misc/eeprom/eeprom.c
@@ -6077,7 +6158,7 @@ F:	include/linux/ata.h
 F:	include/linux/libata.h
 
 LIBATA PATA ARASAN COMPACT FLASH CONTROLLER
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	linux-ide@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
 S:	Maintained
@@ -6147,6 +6228,7 @@ L:	linux-nvdimm@lists.01.org
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
 F:	drivers/nvdimm/pmem.c
+F:	include/linux/pmem.h
 
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
@@ -6161,7 +6243,7 @@ M:	Michael Ellerman <mpe@ellerman.id.au>
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@lists.ozlabs.org
 Q:	http://patchwork.ozlabs.org/project/linuxppc-dev/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
 S:	Supported
 F:	Documentation/powerpc/
 F:	arch/powerpc/
@@ -6237,8 +6319,8 @@ F:	drivers/platform/x86/hp_accel.c
 LIVE PATCHING
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Seth Jennings <sjenning@redhat.com>
-M:	Jiri Kosina <jkosina@suse.cz>
-M:	Vojtech Pavlik <vojtech@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
+M:	Vojtech Pavlik <vojtech@suse.com>
 S:	Maintained
 F:	kernel/livepatch/
 F:	include/linux/livepatch.h
@@ -6264,21 +6346,21 @@ S:	Maintained
 F:	drivers/hwmon/lm73.c
 
 LM78 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/lm78
 F:	drivers/hwmon/lm78.c
 
 LM83 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/lm83
 F:	drivers/hwmon/lm83.c
 
 LM90 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/lm90
@@ -6492,7 +6574,7 @@ F:	drivers/net/ethernet/marvell/mvneta.*
 
 MARVELL MWIFIEX WIRELESS DRIVER
 M:	Amitkumar Karwar <akarwar@marvell.com>
-M:	Avinash Patil <patila@marvell.com>
+M:	Nishant Sarmukadam <nishants@marvell.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wireless/mwifiex/
@@ -6521,6 +6603,13 @@ S:	Maintained
 F:	Documentation/hwmon/max16065
 F:	drivers/hwmon/max16065.c
 
+MAX20751 HARDWARE MONITOR DRIVER
+M:	Guenter Roeck <linux@roeck-us.net>
+L:	lm-sensors@lm-sensors.org
+S:	Maintained
+F:	Documentation/hwmon/max20751
+F:	drivers/hwmon/max20751.c
+
 MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	"Hans J. Koch" <hjk@hansjkoch.de>
 L:	lm-sensors@lm-sensors.org
@@ -6544,6 +6633,14 @@ S:	Supported
 F:	drivers/power/max14577_charger.c
 F:	drivers/power/max77693_charger.c
 
+MAXIM MAX77802 MULTIFUNCTION PMIC DEVICE DRIVERS
+M:	Javier Martinez Canillas <javier@osg.samsung.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+F:	drivers/*/*max77802.c
+F:	Documentation/devicetree/bindings/*/*max77802.txt
+F:	include/dt-bindings/*/*max77802.h
+
 MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS
 M:	Chanwoo Choi <cw00.choi@samsung.com>
 M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
@@ -6557,7 +6654,7 @@ F:	drivers/extcon/extcon-max77693.c
 F:	drivers/rtc/rtc-max77686.c
 F:	drivers/clk/clk-max77686.c
 F:	Documentation/devicetree/bindings/mfd/max14577.txt
-F:	Documentation/devicetree/bindings/mfd/max77686.txt
+F:	Documentation/devicetree/bindings/*/max77686.txt
 F:	Documentation/devicetree/bindings/mfd/max77693.txt
 F:	Documentation/devicetree/bindings/clock/maxim,max77686.txt
 F:	include/linux/mfd/max14577*.h
@@ -6581,6 +6678,51 @@ S:	Supported
 F:	Documentation/devicetree/bindings/media/renesas,vsp1.txt
 F:	drivers/media/platform/vsp1/
 
+MEDIA DRIVERS FOR ASCOT2E
+M:	Sergey Kozlov <serjk@netup.ru>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org
+W:	http://netup.tv/
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	drivers/media/dvb-frontends/ascot2e*
+
+MEDIA DRIVERS FOR CXD2841ER
+M:	Sergey Kozlov <serjk@netup.ru>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+W:	http://netup.tv/
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	drivers/media/dvb-frontends/cxd2841er*
+
+MEDIA DRIVERS FOR HORUS3A
+M:	Sergey Kozlov <serjk@netup.ru>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+W:	http://netup.tv/
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	drivers/media/dvb-frontends/horus3a*
+
+MEDIA DRIVERS FOR LNBH25
+M:	Sergey Kozlov <serjk@netup.ru>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+W:	http://netup.tv/
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	drivers/media/dvb-frontends/lnbh25*
+
+MEDIA DRIVERS FOR NETUP PCI UNIVERSAL DVB devices
+M:	Sergey Kozlov <serjk@netup.ru>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+W:	http://netup.tv/
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	drivers/media/pci/netup_unidvb/*
+
 MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 P:	LinuxTV.org Project
@@ -6630,6 +6772,15 @@ W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlx4/en_*
 
+MELLANOX ETHERNET SWITCH DRIVERS
+M:	Jiri Pirko <jiri@mellanox.com>
+M:	Ido Schimmel <idosch@mellanox.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+W:	http://www.mellanox.com
+Q:	http://patchwork.ozlabs.org/project/netdev/list/
+F:	drivers/net/ethernet/mellanox/mlxsw/
+
 MEMORY MANAGEMENT
 L:	linux-mm@kvack.org
 W:	http://www.linux-mm.org
@@ -6665,6 +6816,7 @@ M:	Johannes Thumshirn <morbidrsa@gmail.com>
 S:	Maintained
 F:	drivers/mcb/
 F:	include/linux/mcb.h
+F:	Documentation/men-chameleon-bus.txt
 
 MEN F21BMC (Board Management Controller)
 M:	Andreas Werner <andreas.werner@men.de>
@@ -6824,6 +6976,12 @@ T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/msi2500/
 
+MSYSTEMS DISKONCHIP G3 MTD DRIVER
+M:	Robert Jarzmik <robert.jarzmik@free.fr>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/devices/docg3*
+
 MT9M032 APTINA SENSOR DRIVER
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
@@ -7005,6 +7163,7 @@ F:	include/uapi/linux/netfilter/
 F:	net/*/netfilter.c
 F:	net/*/netfilter/
 F:	net/netfilter/
+F:	net/bridge/br_netfilter*.c
 
 NETLABEL
 M:	Paul Moore <paul@paul-moore.com>
@@ -7263,6 +7422,15 @@ S:	Supported
 F:	drivers/block/nvme*
 F:	include/linux/nvme.h
 
+NVMEM FRAMEWORK
+M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M:	Maxime Ripard <maxime.ripard@free-electrons.com>
+S:	Maintained
+F:	drivers/nvmem/
+F:	Documentation/devicetree/bindings/nvmem/
+F:	include/linux/nvmem-consumer.h
+F:	include/linux/nvmem-provider.h
+
 NXP-NCI NFC DRIVER
 M:	Clément Perrochaud <clement.perrochaud@effinnov.com>
 R:	Charles Gorand <charles.gorand@effinnov.com>
@@ -7500,8 +7668,9 @@ F:	Documentation/i2c/busses/i2c-ocores
 F:	drivers/i2c/busses/i2c-ocores.c
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
-M:	Grant Likely <grant.likely@linaro.org>
 M:	Rob Herring <robh+dt@kernel.org>
+M:	Frank Rowand <frowand.list@gmail.com>
+M:	Grant Likely <grant.likely@linaro.org>
 L:	devicetree@vger.kernel.org
 W:	http://www.devicetree.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/glikely/linux.git
@@ -7704,7 +7873,7 @@ S:	Maintained
 F:	drivers/char/pc8736x_gpio.c
 
 PC87427 HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/pc87427
@@ -7974,14 +8143,13 @@ F:	drivers/pinctrl/sh-pfc/
 
 PIN CONTROLLER - SAMSUNG
 M:	Tomasz Figa <tomasz.figa@gmail.com>
-M:	Thomas Abraham <thomas.abraham@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/pinctrl/samsung/
 
 PIN CONTROLLER - ST SPEAR
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.st.com/spear
@@ -7989,7 +8157,7 @@ S:	Maintained
 F:	drivers/pinctrl/spear/
 
 PKTCDVD DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 S:	Maintained
 F:	drivers/block/pktcdvd.c
 F:	include/linux/pktcdvd.h
@@ -8024,7 +8192,7 @@ S:	Supported
 F:	drivers/scsi/pmcraid.*
 
 PMC SIERRA PM8001 DRIVER
-M:	xjtuwjp@gmail.com
+M:	Jack Wang <jinpu.wang@profitbricks.com>
 M:	lindar_liu@usish.com
 L:	pmchba@pmcs.com
 L:	linux-scsi@vger.kernel.org
@@ -8049,6 +8217,16 @@ T:	git git://git.infradead.org/battery-2.6.git
 S:	Maintained
 F:	include/linux/power_supply.h
 F:	drivers/power/
+X:	drivers/power/avs/
+
+POWER STATE COORDINATION INTERFACE (PSCI)
+M:	Mark Rutland <mark.rutland@arm.com>
+M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	drivers/firmware/psci.c
+F:	include/linux/psci.h
+F:	include/uapi/linux/psci.h
 
 PNP SUPPORT
 M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
@@ -8366,10 +8544,12 @@ RADOS BLOCK DEVICE (RBD)
 M:	Ilya Dryomov <idryomov@gmail.com>
 M:	Sage Weil <sage@redhat.com>
 M:	Alex Elder <elder@kernel.org>
-M:	ceph-devel@vger.kernel.org
+L:	ceph-devel@vger.kernel.org
 W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
 S:	Supported
+F:	Documentation/ABI/testing/sysfs-bus-rbd
 F:	drivers/block/rbd.c
 F:	drivers/block/rbd_types.h
 
@@ -8445,7 +8625,7 @@ M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-R:	Lai Jiangshan <laijs@cn.fujitsu.com>
+R:	Lai Jiangshan <jiangshanlai@gmail.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
@@ -8472,7 +8652,7 @@ M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-R:	Lai Jiangshan <laijs@cn.fujitsu.com>
+R:	Lai Jiangshan <jiangshanlai@gmail.com>
 L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
@@ -8537,6 +8717,7 @@ M:	Philipp Zabel <p.zabel@pengutronix.de>
 S:	Maintained
 F:	drivers/reset/
 F:	Documentation/devicetree/bindings/reset/
+F:	include/dt-bindings/reset/
 F:	include/linux/reset.h
 F:	include/linux/reset-controller.h
 
@@ -8671,7 +8852,6 @@ F:	drivers/video/fbdev/savage/
 S390
 M:	Martin Schwidefsky <schwidefsky@de.ibm.com>
 M:	Heiko Carstens <heiko.carstens@de.ibm.com>
-M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
@@ -8699,7 +8879,6 @@ F:	block/partitions/ibm.c
 
 S390 NETWORK DRIVERS
 M:	Ursula Braun <ursula.braun@de.ibm.com>
-M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
@@ -8716,7 +8895,6 @@ F:	drivers/pci/hotplug/s390_pci_hpc.c
 
 S390 ZCRYPT DRIVER
 M:	Ingo Tuchscherer <ingo.tuchscherer@de.ibm.com>
-M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
@@ -8724,7 +8902,6 @@ F:	drivers/s390/crypto/
 
 S390 ZFCP DRIVER
 M:	Steffen Maier <maier@linux.vnet.ibm.com>
-M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
@@ -8732,7 +8909,6 @@ F:	drivers/s390/scsi/zfcp_*
 
 S390 IUCV NETWORK LAYER
 M:	Ursula Braun <ursula.braun@de.ibm.com>
-M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
@@ -8835,6 +9011,12 @@ L:	linux-media@vger.kernel.org
 S:	Supported
 F:	drivers/media/i2c/s5k5baf.c
 
+SAMSUNG S3FWRN5 NFC DRIVER
+M:	Robert Baldyga <r.baldyga@samsung.com>
+L:	linux-nfc@lists.01.org (moderated for non-subscribers)
+S:	Supported
+F:	drivers/nfc/s3fwrn5
+
 SAMSUNG SOC CLOCK DRIVERS
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 M:	Tomasz Figa <tomasz.figa@gmail.com>
@@ -8878,13 +9060,20 @@ S:	Maintained
 F:	drivers/tty/serial/
 
 SYNOPSYS DESIGNWARE DMAC DRIVER
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
 F:	include/linux/dma/dw.h
 F:	include/linux/platform_data/dma-dw.h
 F:	drivers/dma/dw/
 
+SYNOPSYS DESIGNWARE ETHERNET QOS 4.10a driver
+M: Lars Persson <lars.persson@axis.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
+F: drivers/net/ethernet/synopsys/dwc_eth_qos.c
+
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
 M:	Seungwon Jeon <tgih.jun@samsung.com>
 M:	Jaehoon Chung <jh80.chung@samsung.com>
@@ -9045,7 +9234,7 @@ S:	Maintained
 F:	drivers/mmc/host/sdhci-s3c*
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) ST SPEAR DRIVER
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
@@ -9084,6 +9273,12 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jj/apparmor-dev.git
 S:	Supported
 F:	security/apparmor/
 
+YAMA SECURITY MODULE
+M:	Kees Cook <keescook@chromium.org>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git yama/tip
+S:	Supported
+F:	security/yama/
+
 SENSABLE PHANTOM
 M:	Jiri Slaby <jirislaby@gmail.com>
 S:	Maintained
@@ -9301,6 +9496,15 @@ S:	Maintained
 F:	drivers/media/i2c/ov2659.c
 F:	include/media/ov2659.h
 
+SILICON MOTION SM712 FRAME BUFFER DRIVER
+M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
+M:	Teddy Wang <teddy.wang@siliconmotion.com>
+M:	Sudip Mukherjee <sudip@vectorindia.org>
+L:	linux-fbdev@vger.kernel.org
+S:	Maintained
+F:	drivers/video/fbdev/sm712*
+F:	Documentation/fb/sm712fb.txt
+
 SIS 190 ETHERNET DRIVER
 M:	Francois Romieu <romieu@fr.zoreil.com>
 L:	netdev@vger.kernel.org
@@ -9340,7 +9544,7 @@ F:	include/linux/sl?b*.h
 F:	mm/sl?b*
 
 SLEEPABLE READ-COPY UPDATE (SRCU)
-M:	Lai Jiangshan <laijs@cn.fujitsu.com>
+M:	Lai Jiangshan <jiangshanlai@gmail.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
@@ -9407,7 +9611,7 @@ F:	Documentation/hwmon/sch5627
 F:	drivers/hwmon/sch5627.c
 
 SMSC47B397 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/smsc47b397
@@ -9456,7 +9660,7 @@ S:	Supported
 F:	drivers/media/pci/solo6x10/
 
 SOFTWARE RAID (Multiple Disks) SUPPORT
-M:	Neil Brown <neilb@suse.de>
+M:	Neil Brown <neilb@suse.com>
 L:	linux-raid@vger.kernel.org
 S:	Supported
 F:	drivers/md/
@@ -9499,7 +9703,7 @@ F:	drivers/memstick/core/ms_block.*
 
 SOUND
 M:	Jaroslav Kysela <perex@perex.cz>
-M:	Takashi Iwai <tiwai@suse.de>
+M:	Takashi Iwai <tiwai@suse.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:	http://www.alsa-project.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
@@ -9583,7 +9787,7 @@ S:	Maintained
 F:	include/linux/compiler.h
 
 SPEAR PLATFORM SUPPORT
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 M:	Shiraz Hashim <shiraz.linux.kernel@gmail.com>
 L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -9592,7 +9796,7 @@ S:	Maintained
 F:	arch/arm/mach-spear/
 
 SPEAR CLOCK FRAMEWORK SUPPORT
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.st.com/spear
@@ -9698,11 +9902,6 @@ W:	http://wiki.laptop.org/go/DCON
 S:	Maintained
 F:	drivers/staging/olpc_dcon/
 
-STAGING - OZMO DEVICES USB OVER WIFI DRIVER
-M:	Shigekatsu Tateno <shigekatsu.tateno@atmel.com>
-S:	Maintained
-F:	drivers/staging/ozwpan/
-
 STAGING - PARALLEL LCD/KEYPAD PANEL DRIVER
 M:	Willy Tarreau <willy@meta-x.org>
 S:	Odd Fixes
@@ -9721,14 +9920,6 @@ L:	linux-wireless@vger.kernel.org
 S:	Maintained
 F:	drivers/staging/rtl8723au/
 
-STAGING - SILICON MOTION SM7XX FRAME BUFFER DRIVER
-M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
-M:	Teddy Wang <teddy.wang@siliconmotion.com>
-M:	Sudip Mukherjee <sudip@vectorindia.org>
-L:	linux-fbdev@vger.kernel.org
-S:	Maintained
-F:	drivers/staging/sm7xxfb/
-
 STAGING - SILICON MOTION SM750 FRAME BUFFER DRIVER
 M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
 M:	Teddy Wang <teddy.wang@siliconmotion.com>
@@ -9847,8 +10038,9 @@ SYNOPSYS ARC ARCHITECTURE
 M:	Vineet Gupta <vgupta@synopsys.com>
 S:	Supported
 F:	arch/arc/
-F:	Documentation/devicetree/bindings/arc/
+F:	Documentation/devicetree/bindings/arc/*
 F:	drivers/tty/serial/arc_uart.c
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc.git
 
 SYNOPSYS ARC SDP platform support
 M:	Alexey Brodkin <abrodkin@synopsys.com>
@@ -10303,6 +10495,13 @@ F:	drivers/char/toshiba.c
 F:	include/linux/toshiba.h
 F:	include/uapi/linux/toshiba.h
 
+TOSHIBA TC358743 DRIVER
+M:	Mats Randgaard <matrandg@cisco.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/media/i2c/tc358743*
+F:	include/media/tc358743.h
+
 TMIO MMC DRIVER
 M:	Ian Molton <ian@mnementh.co.uk>
 L:	linux-mmc@vger.kernel.org
@@ -10382,7 +10581,7 @@ K:	^Subject:.*(?i)trivial
 
 TTY LAYER
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-M:	Jiri Slaby <jslaby@suse.cz>
+M:	Jiri Slaby <jslaby@suse.com>
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty.git
 F:	Documentation/serial/
@@ -10456,7 +10655,7 @@ F:	arch/m68k/*/*_no.*
 F:	arch/m68k/include/asm/*_no.*
 
 UDF FILESYSTEM
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 S:	Maintained
 F:	Documentation/filesystems/udf.txt
 F:	fs/udf/
@@ -10599,7 +10798,7 @@ F:	drivers/usb/gadget/
 F:	include/linux/usb/gadget*
 
 USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...)
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jikos@kernel.org>
 L:	linux-usb@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
 S:	Maintained
@@ -10724,7 +10923,7 @@ S:	Maintained
 F:	drivers/usb/host/uhci*
 
 USB "USBNET" DRIVER FRAMEWORK
-M:	Oliver Neukum <oneukum@suse.de>
+M:	Oliver Neukum <oneukum@suse.com>
 L:	netdev@vger.kernel.org
 W:	http://www.linux-usb.org/usbnet
 S:	Maintained
@@ -10878,6 +11077,15 @@ F:	drivers/block/virtio_blk.c
 F:	include/linux/virtio_*.h
 F:	include/uapi/linux/virtio_*.h
 
+VIRTIO DRIVERS FOR S390
+M:	Christian Borntraeger <borntraeger@de.ibm.com>
+M:	Cornelia Huck <cornelia.huck@de.ibm.com>
+L:	linux-s390@vger.kernel.org
+L:	virtualization@lists.linux-foundation.org
+L:	kvm@vger.kernel.org
+S:	Supported
+F:	drivers/s390/virtio/
+
 VIRTIO GPU DRIVER
 M:	David Airlie <airlied@linux.ie>
 M:	Gerd Hoffmann <kraxel@redhat.com>
@@ -10985,7 +11193,7 @@ F:	drivers/input/mouse/vmmouse.c
 F:	drivers/input/mouse/vmmouse.h
 
 VMWARE VMXNET3 ETHERNET DRIVER
-M:	Shreyas Bhatewara <sbhatewara@vmware.com>
+M:	Shrikrishna Khare <skhare@vmware.com>
 M:	"VMware, Inc." <pv-drivers@vmware.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -11010,6 +11218,14 @@ S:	Supported
 F:	drivers/regulator/
 F:	include/linux/regulator/
 
+VRF
+M:	David Ahern <dsa@cumulusnetworks.com>
+M:	Shrijeet Mukherjee <shm@cumulusnetworks.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/vrf.c
+F:	include/net/vrf.h
+
 VT1211 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
 L:	lm-sensors@lm-sensors.org
@@ -11051,7 +11267,7 @@ F:	Documentation/hwmon/w83793
 F:	drivers/hwmon/w83793.c
 
 W83795 HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	drivers/hwmon/w83795.c
@@ -11165,6 +11381,7 @@ F:	sound/soc/codecs/wm*
 
 WORKQUEUE
 M:	Tejun Heo <tj@kernel.org>
+R:	Lai Jiangshan <jiangshanlai@gmail.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git
 S:	Maintained
 F:	include/linux/workqueue.h
diff --git a/Makefile b/Makefile
index 13270c0a9336..5461920ab02d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -597,6 +597,11 @@ endif # $(dot-config)
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
+# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
+# values of the respective KBUILD_* variables
+ARCH_CPPFLAGS :=
+ARCH_AFLAGS :=
+ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
@@ -661,14 +666,7 @@ endif
 endif
 KBUILD_CFLAGS += $(stackp-flag)
 
-ifeq ($(shell $(CC) -v 2>&1 | grep -c "clang version"), 1)
-COMPILER := clang
-else
-COMPILER := gcc
-endif
-export COMPILER
-
-ifeq ($(COMPILER),clang)
+ifeq ($(cc-name),clang)
 KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
 KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,)
 KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
@@ -780,10 +778,11 @@ endif
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 
-# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
-KBUILD_CPPFLAGS += $(KCPPFLAGS)
-KBUILD_AFLAGS += $(KAFLAGS)
-KBUILD_CFLAGS += $(KCFLAGS)
+# Add any arch overrides and user supplied CPPFLAGS, AFLAGS and CFLAGS as the
+# last assignments
+KBUILD_CPPFLAGS += $(ARCH_CPPFLAGS) $(KCPPFLAGS)
+KBUILD_AFLAGS   += $(ARCH_AFLAGS)   $(KAFLAGS)
+KBUILD_CFLAGS   += $(ARCH_CFLAGS)   $(KCFLAGS)
 
 # Use --build-id when available.
 LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\
@@ -847,10 +846,10 @@ export mod_strip_cmd
 mod_compress_cmd = true
 ifdef CONFIG_MODULE_COMPRESS
   ifdef CONFIG_MODULE_COMPRESS_GZIP
-    mod_compress_cmd = gzip -n
+    mod_compress_cmd = gzip -n -f
   endif # CONFIG_MODULE_COMPRESS_GZIP
   ifdef CONFIG_MODULE_COMPRESS_XZ
-    mod_compress_cmd = xz
+    mod_compress_cmd = xz -f
   endif # CONFIG_MODULE_COMPRESS_XZ
 endif # CONFIG_MODULE_COMPRESS
 export mod_compress_cmd
@@ -869,10 +868,9 @@ INITRD_COMPRESS-$(CONFIG_RD_LZ4)   := lz4
 # export INITRD_COMPRESS := $(INITRD_COMPRESS-y)
 
 ifdef CONFIG_MODULE_SIG_ALL
-MODSECKEY = ./signing_key.priv
-MODPUBKEY = ./signing_key.x509
-export MODPUBKEY
-mod_sign_cmd = perl $(srctree)/scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(MODSECKEY) $(MODPUBKEY)
+$(eval $(call config_filename,MODULE_SIG_KEY))
+
+mod_sign_cmd = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY) certs/signing_key.x509
 else
 mod_sign_cmd = true
 endif
@@ -880,7 +878,7 @@ export mod_sign_cmd
 
 
 ifeq ($(KBUILD_EXTMOD),)
-core-y		+= kernel/ mm/ fs/ ipc/ security/ crypto/ block/
+core-y		+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
 
 vmlinux-dirs	:= $(patsubst %/,%,$(filter %/, $(init-y) $(init-m) \
 		     $(core-y) $(core-m) $(drivers-y) $(drivers-m) \
@@ -1172,8 +1170,8 @@ MRPROPER_DIRS  += include/config usr/include include/generated          \
 		  arch/*/include/generated .tmp_objdiff
 MRPROPER_FILES += .config .config.old .version .old_version \
 		  Module.symvers tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS \
-		  signing_key.priv signing_key.x509 x509.genkey		\
-		  extra_certificates signing_key.x509.keyid		\
+		  signing_key.pem signing_key.priv signing_key.x509	\
+		  x509.genkey extra_certificates signing_key.x509.keyid	\
 		  signing_key.x509.signer vmlinux-gdb.py
 
 # clean - Delete most, but leave enough to build external modules
diff --git a/README b/README
index 69c68fb4a109..a326a6a6a46f 100644
--- a/README
+++ b/README
@@ -161,7 +161,7 @@ CONFIGURING the kernel:
 
      "make xconfig"     X windows (Qt) based configuration tool.
 
-     "make gconfig"     X windows (Gtk) based configuration tool.
+     "make gconfig"     X windows (GTK+) based configuration tool.
 
      "make oldconfig"   Default all questions based on the contents of
                         your existing ./.config file and asking about
diff --git a/arch/Kconfig b/arch/Kconfig
index bec6666a3cc4..8f3564930580 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -71,6 +71,12 @@ config JUMP_LABEL
 	 ( On 32-bit x86, the necessary options added to the compiler
 	   flags may increase the size of the kernel slightly. )
 
+config STATIC_KEYS_SELFTEST
+	bool "Static key selftest"
+	depends on JUMP_LABEL
+	help
+	  Boot time self-test of the branch patching code.
+
 config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
@@ -87,7 +93,6 @@ config KPROBES_ON_FTRACE
 
 config UPROBES
 	def_bool n
-	select PERCPU_RWSEM
 	help
 	  Uprobes is the user-space counterpart to kprobes: they
 	  enable instrumentation applications (such as 'perf probe')
@@ -221,6 +226,10 @@ config ARCH_TASK_STRUCT_ALLOCATOR
 config ARCH_THREAD_INFO_ALLOCATOR
 	bool
 
+# Select if arch wants to size task_struct dynamically via arch_task_struct_size:
+config ARCH_WANTS_DYNAMIC_TASK_STRUCT
+	bool
+
 config HAVE_REGS_AND_STACK_ACCESS_API
 	bool
 	help
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index bf9e9d3b3792..f515a4dbf7a0 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -3,6 +3,7 @@ config ALPHA
 	default y
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_AOUT
 	select HAVE_IDE
 	select HAVE_OPROFILE
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index cde23cd03609..ffd9cf5ec8c4 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 8f8eafbedd7c..e8c956098424 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -29,13 +29,13 @@
  * branch back to restart the operation.
  */
 
-#define ATOMIC_OP(op)							\
+#define ATOMIC_OP(op, asm_op)						\
 static __inline__ void atomic_##op(int i, atomic_t * v)			\
 {									\
 	unsigned long temp;						\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
-	"	" #op "l %0,%2,%0\n"					\
+	"	" #asm_op " %0,%2,%0\n"					\
 	"	stl_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -45,15 +45,15 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			\
 	:"Ir" (i), "m" (v->counter));					\
 }									\
 
-#define ATOMIC_OP_RETURN(op)						\
+#define ATOMIC_OP_RETURN(op, asm_op)					\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	long temp, result;						\
 	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
-	"	" #op "l %0,%3,%2\n"					\
-	"	" #op "l %0,%3,%0\n"					\
+	"	" #asm_op " %0,%3,%2\n"					\
+	"	" #asm_op " %0,%3,%0\n"					\
 	"	stl_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -65,13 +65,13 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return result;							\
 }
 
-#define ATOMIC64_OP(op)							\
+#define ATOMIC64_OP(op, asm_op)						\
 static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 {									\
 	unsigned long temp;						\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
-	"	" #op "q %0,%2,%0\n"					\
+	"	" #asm_op " %0,%2,%0\n"					\
 	"	stq_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -81,15 +81,15 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 	:"Ir" (i), "m" (v->counter));					\
 }									\
 
-#define ATOMIC64_OP_RETURN(op)						\
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
 static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
 {									\
 	long temp, result;						\
 	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
-	"	" #op "q %0,%3,%2\n"					\
-	"	" #op "q %0,%3,%0\n"					\
+	"	" #asm_op " %0,%3,%2\n"					\
+	"	" #asm_op " %0,%3,%0\n"					\
 	"	stq_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -101,15 +101,27 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
 	return result;							\
 }
 
-#define ATOMIC_OPS(opg)							\
-	ATOMIC_OP(opg)							\
-	ATOMIC_OP_RETURN(opg)						\
-	ATOMIC64_OP(opg)						\
-	ATOMIC64_OP_RETURN(opg)
+#define ATOMIC_OPS(op)							\
+	ATOMIC_OP(op, op##l)						\
+	ATOMIC_OP_RETURN(op, op##l)					\
+	ATOMIC64_OP(op, op##q)						\
+	ATOMIC64_OP_RETURN(op, op##q)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+#define atomic_andnot atomic_andnot
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC_OP(and, and)
+ATOMIC_OP(andnot, bic)
+ATOMIC_OP(or, bis)
+ATOMIC_OP(xor, xor)
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(andnot, bic)
+ATOMIC64_OP(or, bis)
+ATOMIC64_OP(xor, xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
diff --git a/arch/alpha/include/asm/mm-arch-hooks.h b/arch/alpha/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b07fd862fec3..000000000000
--- a/arch/alpha/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ALPHA_MM_ARCH_HOOKS_H
-#define _ASM_ALPHA_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ALPHA_MM_ARCH_HOOKS_H */
diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h
index 37b570d01202..fed9c6f44c19 100644
--- a/arch/alpha/include/asm/spinlock.h
+++ b/arch/alpha/include/asm/spinlock.h
@@ -16,6 +16,11 @@
 #define arch_spin_unlock_wait(x) \
 		do { cpu_relax(); } while ((x)->lock)
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+        return lock.lock == 0;
+}
+
 static inline void arch_spin_unlock(arch_spinlock_t * lock)
 {
 	mb();
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 51f2c8654253..2804648c8ff4 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -59,7 +59,7 @@ int irq_select_affinity(unsigned int irq)
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
-	cpumask_copy(data->affinity, cpumask_of(cpu));
+	cpumask_copy(irq_data_get_affinity_mask(data), cpumask_of(cpu));
 	chip->irq_set_affinity(data, cpumask_of(cpu), false);
 	return 0;
 }
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 36dc91ace83a..6cc08166ff00 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1138,6 +1138,7 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 {
 	struct rusage32 r;
 	cputime_t utime, stime;
+	unsigned long utime_jiffies, stime_jiffies;
 
 	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
 		return -EINVAL;
@@ -1146,14 +1147,18 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 	switch (who) {
 	case RUSAGE_SELF:
 		task_cputime(current, &utime, &stime);
-		jiffies_to_timeval32(utime, &r.ru_utime);
-		jiffies_to_timeval32(stime, &r.ru_stime);
+		utime_jiffies = cputime_to_jiffies(utime);
+		stime_jiffies = cputime_to_jiffies(stime);
+		jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
+		jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
 		r.ru_minflt = current->min_flt;
 		r.ru_majflt = current->maj_flt;
 		break;
 	case RUSAGE_CHILDREN:
-		jiffies_to_timeval32(current->signal->cutime, &r.ru_utime);
-		jiffies_to_timeval32(current->signal->cstime, &r.ru_stime);
+		utime_jiffies = cputime_to_jiffies(current->signal->cutime);
+		stime_jiffies = cputime_to_jiffies(current->signal->cstime);
+		jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
+		jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
 		r.ru_minflt = current->signal->cmin_flt;
 		r.ru_majflt = current->signal->cmaj_flt;
 		break;
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 82f738e5d54c..cded02c890aa 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -242,12 +242,7 @@ pci_restore_srm_config(void)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	struct pci_dev *dev = bus->self;
-
-	if (pci_has_flag(PCI_PROBE_ONLY) && dev &&
- 		   (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
- 		pci_read_bridge_bases(bus);
-	} 
+	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		pdev_save_srm_config(dev);
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index 643a9dcdf093..5b6202a825ff 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -93,7 +93,7 @@ rtc_timer_interrupt(int irq, void *dev)
 	struct clock_event_device *ce = &per_cpu(cpu_ce, cpu);
 
 	/* Don't run the hook for UNUSED or SHUTDOWN.  */
-	if (likely(ce->mode == CLOCK_EVT_MODE_PERIODIC))
+	if (likely(clockevent_state_periodic(ce)))
 		ce->event_handler(ce);
 
 	if (test_irq_work_pending()) {
@@ -104,13 +104,6 @@ rtc_timer_interrupt(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static void
-rtc_ce_set_mode(enum clock_event_mode mode, struct clock_event_device *ce)
-{
-	/* The mode member of CE is updated in generic code.
-	   Since we only support periodic events, nothing to do.  */
-}
-
 static int
 rtc_ce_set_next_event(unsigned long evt, struct clock_event_device *ce)
 {
@@ -129,7 +122,6 @@ init_rtc_clockevent(void)
 		.features = CLOCK_EVT_FEAT_PERIODIC,
 		.rating = 100,
 		.cpumask = cpumask_of(cpu),
-		.set_mode = rtc_ce_set_mode,
 		.set_next_event = rtc_ce_set_next_event,
 	};
 
@@ -161,12 +153,12 @@ static struct clocksource qemu_cs = {
  * The QEMU alarm as a clock_event_device primitive.
  */
 
-static void
-qemu_ce_set_mode(enum clock_event_mode mode, struct clock_event_device *ce)
+static int qemu_ce_shutdown(struct clock_event_device *ce)
 {
 	/* The mode member of CE is updated for us in generic code.
 	   Just make sure that the event is disabled.  */
 	qemu_set_alarm_abs(0);
+	return 0;
 }
 
 static int
@@ -197,7 +189,9 @@ init_qemu_clockevent(void)
 		.features = CLOCK_EVT_FEAT_ONESHOT,
 		.rating = 400,
 		.cpumask = cpumask_of(cpu),
-		.set_mode = qemu_ce_set_mode,
+		.set_state_shutdown = qemu_ce_shutdown,
+		.set_state_oneshot = qemu_ce_shutdown,
+		.tick_resume = qemu_ce_shutdown,
 		.set_next_event = qemu_ce_set_next_event,
 	};
 
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e7cee0a5c56d..78c0621d5819 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -8,6 +8,7 @@
 
 config ARC
 	def_bool y
+	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
 	select BUILDTIME_EXTABLE_SORT
 	select COMMON_CLK
 	select CLONE_BACKWARDS
@@ -22,6 +23,7 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_FUTEX_CMPXCHG
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
@@ -115,6 +117,7 @@ if ISA_ARCOMPACT
 
 config ARC_CPU_750D
 	bool "ARC750D"
+	select ARC_CANT_LLSC
 	help
 	  Support for ARC750 core
 
@@ -312,11 +315,11 @@ config ARC_PAGE_SIZE_8K
 
 config ARC_PAGE_SIZE_16K
 	bool "16KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 config ARC_PAGE_SIZE_4K
 	bool "4KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 endchoice
 
@@ -362,7 +365,12 @@ config ARC_CANT_LLSC
 config ARC_HAS_LLSC
 	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
 	default y
-	depends on !ARC_CPU_750D && !ARC_CANT_LLSC
+	depends on !ARC_CANT_LLSC
+
+config ARC_STAR_9000923308
+	bool "Workaround for llock/scond livelock"
+	default y
+	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
 
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
@@ -378,6 +386,10 @@ config ARC_HAS_LL64
 	  dest operands with 2 possible source operands.
 	default y
 
+config ARC_HAS_DIV_REM
+	bool "Insn: div, divu, rem, remu"
+	default y
+
 config ARC_HAS_RTC
 	bool "Local 64-bit r/o cycle counter"
 	default n
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 6107062c0111..8a27a48304a4 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -36,8 +36,16 @@ cflags-$(atleast_gcc44)			+= -fsection-anchors
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 
+ifdef CONFIG_ISA_ARCV2
+
 ifndef CONFIG_ARC_HAS_LL64
-cflags-$(CONFIG_ISA_ARCV2)		+= -mno-ll64
+cflags-y				+= -mno-ll64
+endif
+
+ifndef CONFIG_ARC_HAS_DIV_REM
+cflags-y				+= -mno-div-rem
+endif
+
 endif
 
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
@@ -49,7 +57,8 @@ endif
 
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
-cflags-y  += -O3
+# Note: No need to add to cflags-y as that happens anyways
+ARCH_CFLAGS += -O3
 endif
 
 # small data is default for elf32 tool-chain. If not usable, disable it
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 15c8d6226c9d..846481f37eef 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
@@ -72,12 +72,13 @@
 	};
 
 	/*
-	 * This INTC is actually connected to DW APB GPIO
-	 * which acts as a wire between MB INTC and CPU INTC.
-	 * GPIO INTC is configured in platform init code
-	 * and here we mimic direct connection from MB INTC to
-	 * CPU INTC, thus we set "interrupts = <7>" instead of
-	 * "interrupts = <12>"
+	 * The DW APB ICTL intc on MB is connected to CPU intc via a
+	 * DT "invisible" DW APB GPIO block, configured to simply pass thru
+	 * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c)
+	 *
+	 * So here we mimic a direct connection betwen them, ignoring the
+	 * ABPG GPIO. Thus set "interrupts = <24>" (DW APB GPIO to core)
+	 * instead of "interrupts = <12>" (DW APB ICTL to DW APB GPIO)
 	 *
 	 * This intc actually resides on MB, but we move it here to
 	 * avoid duplicating the MB dtsi file given that IRQ from
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 199d42820eca..2f0b33257db2 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 1a80cc91a03b..7611b10a2d23 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 070f58827a5c..d8023bc8d1ad 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -35,6 +35,7 @@
 #define ARC_REG_RTT_BCR		0xF2
 #define ARC_REG_IRQ_BCR		0xF3
 #define ARC_REG_SMART_BCR	0xFF
+#define ARC_REG_CLUSTER_BCR	0xcf
 
 /* status32 Bits Positions */
 #define STATUS_AE_BIT		5	/* Exception active */
@@ -89,11 +90,10 @@
 #define ECR_C_BIT_DTLB_LD_MISS		8
 #define ECR_C_BIT_DTLB_ST_MISS		9
 
-
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
 #define AUX_INTR_VEC_BASE	0x25
-
+#define AUX_NON_VOL		0x5e
 
 /*
  * Floating Pt Registers
@@ -240,9 +240,9 @@ struct bcr_extn_xymem {
 
 struct bcr_perip {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int start:8, pad2:8, sz:8, pad:8;
+	unsigned int start:8, pad2:8, sz:8, ver:8;
 #else
-	unsigned int pad:8, sz:8, pad2:8, start:8;
+	unsigned int ver:8, sz:8, pad2:8, start:8;
 #endif
 };
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 03484cb4d16d..c3ecda023e3a 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -23,33 +23,60 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-#ifdef CONFIG_ISA_ARCV2
-#define PREFETCHW	"	prefetchw   [%1]	\n"
-#else
-#define PREFETCHW
+#ifdef CONFIG_ARC_STAR_9000923308
+
+#define SCOND_FAIL_RETRY_VAR_DEF						\
+	unsigned int delay = 1, tmp;						\
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"	bz	4f			\n"				\
+	"   ; --- scond fail delay ---		\n"				\
+	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
+	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
+	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
+	"	b	1b			\n"	/* start over */	\
+	"4: ; --- success ---			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS							\
+	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
+
+#else	/* !CONFIG_ARC_STAR_9000923308 */
+
+#define SCOND_FAIL_RETRY_VAR_DEF
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"	bnz     1b			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS
+
 #endif
 
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -58,19 +85,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	smp_mb();							\
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)							\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val)						\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 									\
 	smp_mb();							\
 									\
-	return temp;							\
+	return val;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -143,13 +172,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
-ATOMIC_OP(and, &=, and)
 
-#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v))
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(andnot, &= ~, bic)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 99fe118d3730..57c1f33844d4 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -50,8 +50,7 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 	 * done for const @nr, but no code is generated due to gcc	\
 	 * const prop.							\
 	 */								\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock       %0, [%1]		\n"			\
@@ -82,8 +81,7 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 									\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -129,16 +127,13 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 	unsigned long temp, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	/*								\
 	 * spin lock/unlock provide the needed smp_mb() before/after	\
 	 */								\
 	bitops_lock(flags);						\
 									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));					\
 									\
 	bitops_unlock(flags);						\
 }
@@ -149,17 +144,14 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 	unsigned long old, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	bitops_lock(flags);						\
 									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
 	bitops_unlock(flags);						\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #endif /* CONFIG_ARC_HAS_LLSC */
@@ -174,11 +166,8 @@ static inline void __##op##_bit(unsigned long nr, volatile unsigned long *m)	\
 	unsigned long temp;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));				\
 }
 
 #define __TEST_N_BIT_OP(op, c_op, asm_op)				\
@@ -187,13 +176,10 @@ static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long
 	unsigned long old;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #define BIT_OPS(op, c_op, asm_op)					\
@@ -224,10 +210,7 @@ test_bit(unsigned int nr, const volatile unsigned long *addr)
 
 	addr += nr >> 5;
 
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	mask = 1 << nr;
+	mask = 1UL << (nr & 0x1f);
 
 	return ((mask & *addr) != 0);
 }
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index d67345d3e2d4..e23ea6e7633a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -53,6 +53,8 @@ extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
 
+extern int ioc_exists;
+
 #endif	/* !__ASSEMBLY__ */
 
 /* Instruction cache related Auxiliary registers */
@@ -94,4 +96,10 @@ extern void read_decode_cache_bcr(void);
 #define SLC_CTRL_BUSY		0x100
 #define SLC_CTRL_RGN_OP_INV	0x200
 
+/* IO coherency related Auxiliary registers */
+#define ARC_REG_IO_COH_ENABLE	0x500
+#define ARC_REG_IO_COH_PARTIAL	0x501
+#define ARC_REG_IO_COH_AP0_BASE	0x508
+#define ARC_REG_IO_COH_AP0_SIZE	0x509
+
 #endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index 44fd531f4d7b..af7a2db139c9 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -110,18 +110,18 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
 						 sizeof(*(ptr))))
 
 /*
- * On ARC700, EX insn is inherently atomic, so by default "vanilla" xchg() need
- * not require any locking. However there's a quirk.
- * ARC lacks native CMPXCHG, thus emulated (see above), using external locking -
- * incidently it "reuses" the same atomic_ops_lock used by atomic APIs.
- * Now, llist code uses cmpxchg() and xchg() on same data, so xchg() needs to
- * abide by same serializing rules, thus ends up using atomic_ops_lock as well.
+ * xchg() maps directly to ARC EX instruction which guarantees atomicity.
+ * However in !LLSC config, it also needs to be use @atomic_ops_lock spinlock
+ * due to a subtle reason:
+ *  - For !LLSC, cmpxchg() needs to use that lock (see above) and there is lot
+ *    of  kernel code which calls xchg()/cmpxchg() on same data (see llist.h)
+ *    Hence xchg() needs to follow same locking rules.
  *
- * This however is only relevant if SMP and/or ARC lacks LLSC
- *   if (UP or LLSC)
- *      xchg doesn't need serialization
- *   else <==> !(UP or LLSC) <==> (!UP and !LLSC) <==> (SMP and !LLSC)
- *      xchg needs serialization
+ * Technically the lock is also needed for UP (boils down to irq save/restore)
+ * but we can cheat a bit since cmpxchg() atomic_ops_lock() would cause irqs to
+ * be disabled thus can't possibly be interrpted/preempted/clobbered by xchg()
+ * Other way around, xchg is one instruction anyways, so can't be interrupted
+ * as such
  */
 
 #if !defined(CONFIG_ARC_HAS_LLSC) && defined(CONFIG_SMP)
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 05b5aaf5b0f9..11e1b1f3acda 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -16,18 +16,22 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
 							\
+	smp_mb();					\
 	__asm__ __volatile__(				\
-	"1:	ld  %1, [%2]			\n"	\
+	"1:	llock	%1, [%2]		\n"	\
 		insn				"\n"	\
-	"2:	st  %0, [%2]			\n"	\
+	"2:	scond	%0, [%2]		\n"	\
+	"	bnz	1b			\n"	\
 	"	mov %0, 0			\n"	\
 	"3:					\n"	\
 	"	.section .fixup,\"ax\"		\n"	\
 	"	.align  4			\n"	\
 	"4:	mov %0, %4			\n"	\
-	"	b   3b				\n"	\
+	"	j   3b				\n"	\
 	"	.previous			\n"	\
 	"	.section __ex_table,\"a\"	\n"	\
 	"	.align  4			\n"	\
@@ -37,7 +41,37 @@
 							\
 	: "=&r" (ret), "=&r" (oldval)			\
 	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
-	: "cc", "memory")
+	: "cc", "memory");				\
+	smp_mb()					\
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	smp_mb();					\
+	__asm__ __volatile__(				\
+	"1:	ld	%1, [%2]		\n"	\
+		insn				"\n"	\
+	"2:	st	%0, [%2]		\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	j   3b				\n"	\
+	"	.previous			\n"	\
+	"	.section __ex_table,\"a\"	\n"	\
+	"	.align  4			\n"	\
+	"	.word   1b, 4b			\n"	\
+	"	.word   2b, 4b			\n"	\
+	"	.previous			\n"	\
+							\
+	: "=&r" (ret), "=&r" (oldval)			\
+	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
+	: "cc", "memory");				\
+	smp_mb()					\
+
+#endif
 
 static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
@@ -53,6 +87,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
+#endif
 	pagefault_disable();
 
 	switch (op) {
@@ -60,6 +97,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 		__futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
+		/* oldval = *uaddr; *uaddr += oparg ; ret = *uaddr */
 		__futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
@@ -76,6 +114,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	}
 
 	pagefault_enable();
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_enable();
+#endif
 
 	if (!ret) {
 		switch (cmp) {
@@ -104,48 +145,57 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-/* Compare-xchg with pagefaults disabled.
- *  Notes:
- *      -Best-Effort: Exchg happens only if compare succeeds.
- *          If compare fails, returns; leaving retry/looping to upper layers
- *      -successful cmp-xchg: return orig value in @addr (same as cmp val)
- *      -Compare fails: return orig value in @addr
- *      -user access r/w fails: return -EFAULT
+/*
+ * cmpxchg of futex (pagefaults disabled by caller)
+ * Return 0 for success, -EFAULT otherwise
  */
 static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
-					u32 newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 expval,
+			      u32 newval)
 {
-	u32 val;
+	int ret = 0;
+	u32 existval;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
+#endif
+	smp_mb();
 
-	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
-	"1:	ld    %0, [%3]	\n"
-	"	brne  %0, %1, 3f	\n"
-	"2:	st    %2, [%3]	\n"
+#ifdef CONFIG_ARC_HAS_LLSC
+	"1:	llock	%1, [%4]		\n"
+	"	brne	%1, %2, 3f		\n"
+	"2:	scond	%3, [%4]		\n"
+	"	bnz	1b			\n"
+#else
+	"1:	ld	%1, [%4]		\n"
+	"	brne	%1, %2, 3f		\n"
+	"2:	st	%3, [%4]		\n"
+#endif
 	"3:	\n"
 	"	.section .fixup,\"ax\"	\n"
-	"4:	mov %0, %4	\n"
-	"	b   3b	\n"
+	"4:	mov %0, %5	\n"
+	"	j   3b	\n"
 	"	.previous	\n"
 	"	.section __ex_table,\"a\"	\n"
 	"	.align  4	\n"
 	"	.word   1b, 4b	\n"
 	"	.word   2b, 4b	\n"
 	"	.previous\n"
-	: "=&r"(val)
-	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
+	: "+&r"(ret), "=&r"(existval)
+	: "r"(expval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
 	: "cc", "memory");
 
-	pagefault_enable();
+	smp_mb();
 
-	*uval = val;
-	return val;
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_enable();
+#endif
+	*uval = existval;
+	return ret;
 }
 
 #endif
diff --git a/arch/arc/include/asm/mm-arch-hooks.h b/arch/arc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index c37541c5f8ba..000000000000
--- a/arch/arc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ARC_MM_ARCH_HOOKS_H
-#define _ASM_ARC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ARC_MM_ARCH_HOOKS_H */
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 2b8880e953a2..5f071762fb1c 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -1,6 +1,7 @@
 /*
  * Linux performance counter support for ARC
  *
+ * Copyright (C) 2014-2015 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2011-2013 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
@@ -12,8 +13,8 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
-/* real maximum varies per CPU, this is the maximum supported by the driver */
-#define ARC_PMU_MAX_HWEVENTS	64
+/* Max number of counters that PCT block may ever have */
+#define ARC_PERF_MAX_COUNTERS	32
 
 #define ARC_REG_CC_BUILD	0xF6
 #define ARC_REG_CC_INDEX	0x240
@@ -28,15 +29,22 @@
 #define ARC_REG_PCT_CONFIG	0x254
 #define ARC_REG_PCT_CONTROL	0x255
 #define ARC_REG_PCT_INDEX	0x256
+#define ARC_REG_PCT_INT_CNTL	0x25C
+#define ARC_REG_PCT_INT_CNTH	0x25D
+#define ARC_REG_PCT_INT_CTRL	0x25E
+#define ARC_REG_PCT_INT_ACT	0x25F
+
+#define ARC_REG_PCT_CONFIG_USER	(1 << 18)	/* count in user mode */
+#define ARC_REG_PCT_CONFIG_KERN	(1 << 19)	/* count in kernel mode */
 
 #define ARC_REG_PCT_CONTROL_CC	(1 << 16)	/* clear counts */
 #define ARC_REG_PCT_CONTROL_SN	(1 << 17)	/* snapshot */
 
 struct arc_reg_pct_build {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int m:8, c:8, r:6, s:2, v:8;
+	unsigned int m:8, c:8, r:5, i:1, s:2, v:8;
 #else
-	unsigned int v:8, s:2, r:6, c:8, m:8;
+	unsigned int v:8, s:2, i:1, r:5, c:8, m:8;
 #endif
 };
 
@@ -95,10 +103,13 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp",
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
+#ifdef CONFIG_ISA_ARCV2
+	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
+#else
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
-
+#endif
 	[PERF_COUNT_ARC_LDC] = "imemrdc",	/* Instr: mem read cached */
 	[PERF_COUNT_ARC_STC] = "imemwrc",	/* Instr: mem write cached */
 
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 91755972b9a2..69095da1fcfd 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -20,20 +20,20 @@
 struct pt_regs {
 
 	/* Real registers */
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long lp_start, lp_end, lp_count;
+	unsigned long lp_start, lp_end, lp_count;
 
-	long status32;	/* status32_l1, status32_l2, erstatus */
-	long ret;	/* ilink1, ilink2 or eret */
-	long blink;
-	long fp;
-	long r26;	/* gp */
+	unsigned long status32;	/* status32_l1, status32_l2, erstatus */
+	unsigned long ret;	/* ilink1, ilink2 or eret */
+	unsigned long blink;
+	unsigned long fp;
+	unsigned long r26;	/* gp */
 
-	long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+	unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
 
-	long sp;	/* user/kernel sp depending on where we came from  */
-	long orig_r0;
+	unsigned long sp;	/* User/Kernel depending on where we came from */
+	unsigned long orig_r0;
 
 	/*
 	 * To distinguish bet excp, syscall, irq
@@ -55,13 +55,13 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long user_r25;
+	unsigned long user_r25;
 };
 #else
 
 struct pt_regs {
 
-	long orig_r0;
+	unsigned long orig_r0;
 
 	union {
 		struct {
@@ -76,26 +76,26 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long user_r25;
+	unsigned long user_r25;
 
-	long r26;	/* gp */
-	long fp;
-	long sp;	/* user/kernel sp depending on where we came from  */
+	unsigned long r26;	/* gp */
+	unsigned long fp;
+	unsigned long sp;	/* user/kernel sp depending on where we came from  */
 
-	long r12;
+	unsigned long r12;
 
 	/*------- Below list auto saved by h/w -----------*/
-	long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
 
-	long blink;
-	long lp_end, lp_start, lp_count;
+	unsigned long blink;
+	unsigned long lp_end, lp_start, lp_count;
 
-	long ei, ldi, jli;
+	unsigned long ei, ldi, jli;
 
-	long ret;
-	long status32;
+	unsigned long ret;
+	unsigned long status32;
 };
 
 #endif
@@ -103,7 +103,7 @@ struct pt_regs {
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
 #define instruction_pointer(regs)	((regs)->ret)
@@ -142,7 +142,7 @@ struct callee_regs {
 
 static inline long regs_return_value(struct pt_regs *regs)
 {
-	return regs->r0;
+	return (long)regs->r0;
 }
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index e1651df6a93d..db8c59d1eaeb 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -18,9 +18,518 @@
 #define arch_spin_unlock_wait(x) \
 	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
+/*
+ * A normal LLOCK/SCOND based system, w/o need for livelock workaround
+ */
+#ifndef CONFIG_ARC_STAR_9000923308
+
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"	mov	%[got_it], 1		\n"
+	"4:					\n"
+	"					\n"
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 1b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 *
+	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+	 *		rw->counter = 0;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 1b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	smp_mb();
+
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+#else	/* CONFIG_ARC_STAR_9000923308 */
+
+/*
+ * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
+ * coherency transactions in the SCU. The exclusive line state keeps rotating
+ * among contenting cores leading to a never ending cycle. So break the cycle
+ * by deferring the retry of failed exclusive access (SCOND). The actual delay
+ * needed is function of number of contending cores as well as the unrelated
+ * coherency traffic from other cores. To keep the code simple, start off with
+ * small delay of 1 which would suffice most cases and in case of contention
+ * double the delay. Eventually the delay is sufficient such that the coherency
+ * pipeline is drained, thus a subsequent exclusive access would succeed.
+ */
+
+#define SCOND_FAIL_RETRY_VAR_DEF						\
+	unsigned int delay, tmp;						\
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"   ; --- scond fail delay ---		\n"				\
+	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
+	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
+	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
+	"	b	1b			\n"	/* start over */	\
+	"					\n"				\
+	"4: ; --- done ---			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS							\
+	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bz	4f			\n"	/* done */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz	4f			\n"	/* done */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 *
+	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+	 *		rw->counter = 0;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz	4f			\n"
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	scond	%[UNLOCKED], [%[rwlock]]\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
+
+#endif	/* CONFIG_ARC_STAR_9000923308 */
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	/*
 	 * This smp_mb() is technically superfluous, we only need the one
@@ -33,7 +542,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
-	: "+&r" (tmp)
+	: "+&r" (val)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
 
@@ -48,26 +557,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	smp_mb();
 }
 
+/* 1 - lock taken successfully */
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
 	smp_mb();
 
-	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+	return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
 
 	/*
 	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
@@ -77,7 +587,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
@@ -90,19 +600,12 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 /*
  * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
  *
  * The spinlock itself is contained in @counter and access to it is
  * serialized with @lock_mutex.
- *
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
  */
 
-/* Would read_trylock() succeed? */
-#define arch_read_can_lock(x)	((x)->counter > 0)
-
-/* Would write_trylock() succeed? */
-#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
 /* 1 - lock taken successfully */
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
@@ -173,6 +676,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	arch_spin_unlock(&(rw->lock_mutex));
 }
 
+#endif
+
+#define arch_read_can_lock(x)	((x)->counter > 0)
+#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
 #define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
 
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
index 662627ced4f2..4e1ef5f650c6 100644
--- a/arch/arc/include/asm/spinlock_types.h
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -26,7 +26,9 @@ typedef struct {
  */
 typedef struct {
 	volatile unsigned int	counter;
+#ifndef CONFIG_ARC_HAS_LLSC
 	arch_spinlock_t		lock_mutex;
+#endif
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED__	0x01000000
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 76a7739aab1c..0b3ef63d4a03 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -32,20 +32,20 @@
 */
 struct user_regs_struct {
 
-	long pad;
+	unsigned long pad;
 	struct {
-		long bta, lp_start, lp_end, lp_count;
-		long status32, ret, blink, fp, gp;
-		long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
-		long sp;
+		unsigned long bta, lp_start, lp_end, lp_count;
+		unsigned long status32, ret, blink, fp, gp;
+		unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		unsigned long sp;
 	} scratch;
-	long pad2;
+	unsigned long pad2;
 	struct {
-		long r25, r24, r23, r22, r21, r20;
-		long r19, r18, r17, r16, r15, r14, r13;
+		unsigned long r25, r24, r23, r22, r21, r20;
+		unsigned long r19, r18, r17, r16, r15, r14, r13;
 	} callee;
-	long efa;	/* break pt addr, for break points in delay slots */
-	long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
+	unsigned long efa;	/* break pt addr, for break points in delay slots */
+	unsigned long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
 };
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index bd7105d3172f..8fa76567e402 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -57,13 +57,8 @@ VECTOR	handle_interrupt	; (23) End of fixed IRQs
 
 	.section .text, "ax",@progbits
 
-res_service:		; processor restart
-	flag    0x1     ; not implemented
-	nop
-	nop
-
-reserved:		; processor restart
-	rtie            ; jump to processor initializations
+reserved:
+	flag 1		; Unexpected event, halt
 
 ;##################### Interrupt Handling ##############################
 
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index f7a82fd4d601..589abf5172d6 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -42,7 +42,7 @@ ENTRY(ret_from_fork)
 	; when the forked child comes here from the __switch_to function
 	; r0 has the last task pointer.
 	; put last task in scheduler queue
-	bl   @schedule_tail
+	jl   @schedule_tail
 
 	ld   r9, [sp, PT_status32]
 	brne r9, 0, 1f
@@ -320,7 +320,7 @@ resume_user_mode_begin:
 	; --- (Slow Path #1) task preemption ---
 	bbit0  r9, TIF_NEED_RESCHED, .Lchk_pend_signals
 	mov    blink, resume_user_mode_begin  ; tail-call to U mode ret chks
-	b      @schedule 	; BTST+Bnz causes relo error in link
+	j      @schedule 	; BTST+Bnz causes relo error in link
 
 .Lchk_pend_signals:
 	IRQ_ENABLE	r10
@@ -381,7 +381,7 @@ resume_kernel_mode:
 	bbit0  r9, TIF_NEED_RESCHED, .Lrestore_regs
 
 	; Invoke PREEMPTION
-	bl      preempt_schedule_irq
+	jl      preempt_schedule_irq
 
 	; preempt_schedule_irq() always returns with IRQ disabled
 #endif
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 6208c630abed..26c156827479 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index fcdddb631766..039fac30b5c1 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 30284e8de6ff..d9e44b62df05 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -175,7 +175,6 @@ void mcip_init_early_smp(void)
 #include <linux/irqchip.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include "../../drivers/irqchip/irqchip.h"
 
 /*
  * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core)
@@ -218,11 +217,28 @@ static void idu_irq_unmask(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
+#ifdef CONFIG_SMP
 static int
-idu_irq_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool f)
+idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
+		     bool force)
 {
+	unsigned long flags;
+	cpumask_t online;
+
+	/* errout if no online cpu per @cpumask */
+	if (!cpumask_and(&online, cpumask, cpu_online_mask))
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	idu_set_dest(data->hwirq, cpumask_bits(&online)[0]);
+	idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
 	return IRQ_SET_MASK_OK;
 }
+#endif
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
@@ -236,9 +252,10 @@ static struct irq_chip idu_irq_chip = {
 
 static int idu_first_irq;
 
-static void idu_cascade_isr(unsigned int core_irq, struct irq_desc *desc)
+static void idu_cascade_isr(unsigned int __core_irq, struct irq_desc *desc)
 {
 	struct irq_domain *domain = irq_desc_get_handler_data(desc);
+	unsigned int core_irq = irq_desc_get_irq(desc);
 	unsigned int idu_irq;
 
 	idu_irq = core_irq - idu_first_irq;
@@ -330,8 +347,7 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 		if (!i)
 			idu_first_irq = irq;
 
-		irq_set_handler_data(irq, domain);
-		irq_set_chained_handler(irq, idu_cascade_isr);
+		irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain);
 	}
 
 	__mcip_cmd(CMD_IDU_ENABLE, 0);
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 1287388c258a..0c08bb1ce15a 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -1,7 +1,7 @@
 /*
  * Linux performance counter support for ARC700 series
  *
- * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com)
  *
  * This code is inspired by the perf support of various other architectures.
  *
@@ -11,6 +11,7 @@
  *
  */
 #include <linux/errno.h>
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/perf_event.h>
@@ -20,12 +21,25 @@
 
 struct arc_pmu {
 	struct pmu	pmu;
-	int		counter_size;	/* in bits */
+	unsigned int	irq;
 	int		n_counters;
-	unsigned long	used_mask[BITS_TO_LONGS(ARC_PMU_MAX_HWEVENTS)];
+	u64		max_period;
 	int		ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
 };
 
+struct arc_pmu_cpu {
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long	used_mask[BITS_TO_LONGS(ARC_PERF_MAX_COUNTERS)];
+
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event *act_counter[ARC_PERF_MAX_COUNTERS];
+};
+
 struct arc_callchain_trace {
 	int depth;
 	void *perf_stuff;
@@ -65,6 +79,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 }
 
 static struct arc_pmu *arc_pmu;
+static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu);
 
 /* read counter #idx; note that counter# != event# on ARC! */
 static uint64_t arc_pmu_read_counter(int idx)
@@ -88,18 +103,15 @@ static uint64_t arc_pmu_read_counter(int idx)
 static void arc_perf_event_update(struct perf_event *event,
 				  struct hw_perf_event *hwc, int idx)
 {
-	uint64_t prev_raw_count, new_raw_count;
-	int64_t delta;
-
-	do {
-		prev_raw_count = local64_read(&hwc->prev_count);
-		new_raw_count = arc_pmu_read_counter(idx);
-	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-				 new_raw_count) != prev_raw_count);
-
-	delta = (new_raw_count - prev_raw_count) &
-		((1ULL << arc_pmu->counter_size) - 1ULL);
+	uint64_t prev_raw_count = local64_read(&hwc->prev_count);
+	uint64_t new_raw_count = arc_pmu_read_counter(idx);
+	int64_t delta = new_raw_count - prev_raw_count;
 
+	/*
+	 * We don't afaraid of hwc->prev_count changing beneath our feet
+	 * because there's no way for us to re-enter this function anytime.
+	 */
+	local64_set(&hwc->prev_count, new_raw_count);
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
 }
@@ -142,22 +154,41 @@ static int arc_pmu_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int ret;
 
+	if (!is_sampling_event(event)) {
+		hwc->sample_period  = arc_pmu->max_period;
+		hwc->last_period = hwc->sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+	}
+
+	hwc->config = 0;
+
+	if (is_isa_arcv2()) {
+		/* "exclude user" means "count only kernel" */
+		if (event->attr.exclude_user)
+			hwc->config |= ARC_REG_PCT_CONFIG_KERN;
+
+		/* "exclude kernel" means "count only user" */
+		if (event->attr.exclude_kernel)
+			hwc->config |= ARC_REG_PCT_CONFIG_USER;
+	}
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		if (event->attr.config >= PERF_COUNT_HW_MAX)
 			return -ENOENT;
 		if (arc_pmu->ev_hw_idx[event->attr.config] < 0)
 			return -ENOENT;
-		hwc->config = arc_pmu->ev_hw_idx[event->attr.config];
+		hwc->config |= arc_pmu->ev_hw_idx[event->attr.config];
 		pr_debug("init event %d with h/w %d \'%s\'\n",
 			 (int) event->attr.config, (int) hwc->config,
 			 arc_pmu_ev_hw_map[event->attr.config]);
 		return 0;
+
 	case PERF_TYPE_HW_CACHE:
 		ret = arc_pmu_cache_event(event->attr.config);
 		if (ret < 0)
 			return ret;
-		hwc->config = arc_pmu->ev_hw_idx[ret];
+		hwc->config |= arc_pmu->ev_hw_idx[ret];
 		return 0;
 	default:
 		return -ENOENT;
@@ -180,6 +211,47 @@ static void arc_pmu_disable(struct pmu *pmu)
 	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
 }
 
+static int arc_pmu_event_set_period(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	s64 left = local64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+	int idx = hwc->idx;
+	int overflow = 0;
+	u64 value;
+
+	if (unlikely(left <= -period)) {
+		/* left underflowed by more than period. */
+		left = period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		overflow = 1;
+	} else	if (unlikely(left <= 0)) {
+		/* left underflowed by less than period. */
+		left += period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		overflow = 1;
+	}
+
+	if (left > arc_pmu->max_period)
+		left = arc_pmu->max_period;
+
+	value = arc_pmu->max_period - left;
+	local64_set(&hwc->prev_count, value);
+
+	/* Select counter */
+	write_aux_reg(ARC_REG_PCT_INDEX, idx);
+
+	/* Write value */
+	write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value);
+	write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32));
+
+	perf_event_update_userpage(event);
+
+	return overflow;
+}
+
 /*
  * Assigns hardware counter to hardware condition.
  * Note that there is no separate start/stop mechanism;
@@ -194,13 +266,20 @@ static void arc_pmu_start(struct perf_event *event, int flags)
 		return;
 
 	if (flags & PERF_EF_RELOAD)
-		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
 
-	event->hw.state = 0;
+	arc_pmu_event_set_period(event);
+
+	/* Enable interrupt for this counter */
+	if (is_sampling_event(event))
+		write_aux_reg(ARC_REG_PCT_INT_CTRL,
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
 
 	/* enable ARC pmu here */
-	write_aux_reg(ARC_REG_PCT_INDEX, idx);
-	write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config);
+	write_aux_reg(ARC_REG_PCT_INDEX, idx);		/* counter # */
+	write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config);	/* condition */
 }
 
 static void arc_pmu_stop(struct perf_event *event, int flags)
@@ -208,6 +287,17 @@ static void arc_pmu_stop(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	/* Disable interrupt for this counter */
+	if (is_sampling_event(event)) {
+		/*
+		 * Reset interrupt flag by writing of 1. This is required
+		 * to make sure pending interrupt was not left.
+		 */
+		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+		write_aux_reg(ARC_REG_PCT_INT_CTRL,
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx));
+	}
+
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
 		/* stop ARC pmu here */
 		write_aux_reg(ARC_REG_PCT_INDEX, idx);
@@ -227,8 +317,12 @@ static void arc_pmu_stop(struct perf_event *event, int flags)
 
 static void arc_pmu_del(struct perf_event *event, int flags)
 {
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+
 	arc_pmu_stop(event, PERF_EF_UPDATE);
-	__clear_bit(event->hw.idx, arc_pmu->used_mask);
+	__clear_bit(event->hw.idx, pmu_cpu->used_mask);
+
+	pmu_cpu->act_counter[event->hw.idx] = 0;
 
 	perf_event_update_userpage(event);
 }
@@ -236,20 +330,31 @@ static void arc_pmu_del(struct perf_event *event, int flags)
 /* allocate hardware counter and optionally start counting */
 static int arc_pmu_add(struct perf_event *event, int flags)
 {
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	if (__test_and_set_bit(idx, arc_pmu->used_mask)) {
-		idx = find_first_zero_bit(arc_pmu->used_mask,
+	if (__test_and_set_bit(idx, pmu_cpu->used_mask)) {
+		idx = find_first_zero_bit(pmu_cpu->used_mask,
 					  arc_pmu->n_counters);
 		if (idx == arc_pmu->n_counters)
 			return -EAGAIN;
 
-		__set_bit(idx, arc_pmu->used_mask);
+		__set_bit(idx, pmu_cpu->used_mask);
 		hwc->idx = idx;
 	}
 
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);
+
+	pmu_cpu->act_counter[idx] = event;
+
+	if (is_sampling_event(event)) {
+		/* Mimic full counter overflow as other arches do */
+		write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period);
+		write_aux_reg(ARC_REG_PCT_INT_CNTH,
+			      (arc_pmu->max_period >> 32));
+	}
+
 	write_aux_reg(ARC_REG_PCT_CONFIG, 0);
 	write_aux_reg(ARC_REG_PCT_COUNTL, 0);
 	write_aux_reg(ARC_REG_PCT_COUNTH, 0);
@@ -264,11 +369,82 @@ static int arc_pmu_add(struct perf_event *event, int flags)
 	return 0;
 }
 
+#ifdef CONFIG_ISA_ARCV2
+static irqreturn_t arc_pmu_intr(int irq, void *dev)
+{
+	struct perf_sample_data data;
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+	struct pt_regs *regs;
+	int active_ints;
+	int idx;
+
+	arc_pmu_disable(&arc_pmu->pmu);
+
+	active_ints = read_aux_reg(ARC_REG_PCT_INT_ACT);
+
+	regs = get_irq_regs();
+
+	for (idx = 0; idx < arc_pmu->n_counters; idx++) {
+		struct perf_event *event = pmu_cpu->act_counter[idx];
+		struct hw_perf_event *hwc;
+
+		if (!(active_ints & (1 << idx)))
+			continue;
+
+		/* Reset interrupt flag by writing of 1 */
+		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+
+		/*
+		 * On reset of "interrupt active" bit corresponding
+		 * "interrupt enable" bit gets automatically reset as well.
+		 * Now we need to re-enable interrupt for the counter.
+		 */
+		write_aux_reg(ARC_REG_PCT_INT_CTRL,
+			read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+
+		hwc = &event->hw;
+
+		WARN_ON_ONCE(hwc->idx != idx);
+
+		arc_perf_event_update(event, &event->hw, event->hw.idx);
+		perf_sample_data_init(&data, 0, hwc->last_period);
+		if (!arc_pmu_event_set_period(event))
+			continue;
+
+		if (perf_event_overflow(event, &data, regs))
+			arc_pmu_stop(event, 0);
+	}
+
+	arc_pmu_enable(&arc_pmu->pmu);
+
+	return IRQ_HANDLED;
+}
+#else
+
+static irqreturn_t arc_pmu_intr(int irq, void *dev)
+{
+	return IRQ_NONE;
+}
+
+#endif /* CONFIG_ISA_ARCV2 */
+
+void arc_cpu_pmu_irq_init(void)
+{
+	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+
+	arc_request_percpu_irq(arc_pmu->irq, smp_processor_id(), arc_pmu_intr,
+			       "ARC perf counters", pmu_cpu);
+
+	/* Clear all pending interrupt flags */
+	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
+}
+
 static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, j;
+	int i, j, has_interrupts;
+	int counter_size;	/* in bits */
 
 	union cc_name {
 		struct {
@@ -284,7 +460,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		pr_err("This core does not have performance counters!\n");
 		return -ENODEV;
 	}
-	BUG_ON(pct_bcr.c > ARC_PMU_MAX_HWEVENTS);
+	BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);
 
 	READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
 	BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */
@@ -293,11 +469,16 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	if (!arc_pmu)
 		return -ENOMEM;
 
+	has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0;
+
 	arc_pmu->n_counters = pct_bcr.c;
-	arc_pmu->counter_size = 32 + (pct_bcr.s << 4);
+	counter_size = 32 + (pct_bcr.s << 4);
 
-	pr_info("ARC perf\t: %d counters (%d bits), %d countable conditions\n",
-		arc_pmu->n_counters, arc_pmu->counter_size, cc_bcr.c);
+	arc_pmu->max_period = (1ULL << counter_size) / 2 - 1ULL;
+
+	pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n",
+		arc_pmu->n_counters, counter_size, cc_bcr.c,
+		has_interrupts ? ", [overflow IRQ support]":"");
 
 	cc_name.str[8] = 0;
 	for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
@@ -332,8 +513,37 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.read		= arc_pmu_read,
 	};
 
-	/* ARC 700 PMU does not support sampling events */
-	arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	if (has_interrupts) {
+		int irq = platform_get_irq(pdev, 0);
+		unsigned long flags;
+
+		if (irq < 0) {
+			pr_err("Cannot get IRQ number for the platform\n");
+			return -ENODEV;
+		}
+
+		arc_pmu->irq = irq;
+
+		/*
+		 * arc_cpu_pmu_irq_init() needs to be called on all cores for
+		 * their respective local PMU.
+		 * However we use opencoded on_each_cpu() to ensure it is called
+		 * on core0 first, so that arc_request_percpu_irq() sets up
+		 * AUTOEN etc. Otherwise enable_percpu_irq() fails to enable
+		 * perf IRQ on non master cores.
+		 * see arc_request_percpu_irq()
+		 */
+		preempt_disable();
+		local_irq_save(flags);
+		arc_cpu_pmu_irq_init();
+		local_irq_restore(flags);
+		smp_call_function((smp_call_func_t)arc_cpu_pmu_irq_init, 0, 1);
+		preempt_enable();
+
+		/* Clean all pending interrupt flags */
+		write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
+	} else
+		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
 	return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
 }
@@ -341,6 +551,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 #ifdef CONFIG_OF
 static const struct of_device_id arc_pmu_match[] = {
 	{ .compatible = "snps,arc700-pct" },
+	{ .compatible = "snps,archs-pct" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, arc_pmu_match);
@@ -348,7 +559,7 @@ MODULE_DEVICE_TABLE(of, arc_pmu_match);
 
 static struct platform_driver arc_pmu_driver = {
 	.driver	= {
-		.name		= "arc700-pct",
+		.name		= "arc-pct",
 		.of_match_table = of_match_ptr(arc_pmu_match),
 	},
 	.probe		= arc_pmu_device_probe,
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 44092456776f..91d5a0f1f3f7 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -65,7 +65,7 @@ asmlinkage void ret_from_fork(void);
  * ------------------
  * |     r25        |   <==== top of Stack (thread.ksp)
  * ~                ~
- * |    --to--      |   (CALLEE Regs of user mode)
+ * |    --to--      |   (CALLEE Regs of kernel mode)
  * |     r13        |
  * ------------------
  * |     fp         |
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index a3d186211ed3..cabde9dc0696 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,6 +47,7 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_perip uncached_space;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	unsigned long perip_space;
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
@@ -56,7 +57,12 @@ static void read_arc_build_cfg_regs(void)
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
-	BUG_ON((uncached_space.start << 24) != ARC_UNCACHED_ADDR_SPACE);
+        if (uncached_space.ver < 3)
+		perip_space = uncached_space.start << 24;
+	else
+		perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
+
+	BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE);
 
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
@@ -142,17 +148,22 @@ static void read_arc_build_cfg_regs(void)
 }
 
 static const struct cpuinfo_data arc_cpu_tbl[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
 	{ {0x20, "ARC 600"      }, 0x2F},
 	{ {0x30, "ARC 700"      }, 0x33},
 	{ {0x34, "ARC 700 R4.10"}, 0x34},
 	{ {0x35, "ARC 700 R4.11"}, 0x35},
-	{ {0x50, "ARC HS38"	}, 0x51},
+#else
+	{ {0x50, "ARC HS38 R2.0"}, 0x51},
+	{ {0x52, "ARC HS38 R2.1"}, 0x52},
+#endif
 	{ {0x00, NULL		} }
 };
 
-#define IS_AVAIL1(v, str)	((v) ? str : "")
-#define IS_USED(cfg)		(IS_ENABLED(cfg) ? "" : "(not used) ")
-#define IS_AVAIL2(v, str, cfg)  IS_AVAIL1(v, str), IS_AVAIL1(v, IS_USED(cfg))
+#define IS_AVAIL1(v, s)		((v) ? s : "")
+#define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
+#define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
+#define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
 
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
@@ -226,7 +237,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
 		}
 		n += scnprintf(buf + n, len - n, "%s",
-			       IS_USED(CONFIG_ARC_HAS_HW_MPY));
+			       IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY));
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
@@ -325,6 +336,10 @@ static void arc_chk_core_config(void)
 		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
 	else if (!cpu->extn.fpu_dp && fpu_enabled)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
+
+	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
+		panic("llock/scond livelock workaround missing\n");
 }
 
 /*
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 3364d2bbc515..4294761a2b3e 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -203,34 +203,24 @@ static int arc_clkevent_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void arc_clkevent_set_mode(enum clock_event_mode mode,
-				  struct clock_event_device *dev)
+static int arc_clkevent_set_periodic(struct clock_event_device *dev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-                /*
-                 * At X Hz, 1 sec = 1000ms -> X cycles;
-                 *                    10ms -> X / 100 cycles
-                 */
-		arc_timer_event_setup(arc_get_core_freq() / HZ);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-	default:
-		break;
-	}
-
-	return;
+	/*
+	 * At X Hz, 1 sec = 1000ms -> X cycles;
+	 *		      10ms -> X / 100 cycles
+	 */
+	arc_timer_event_setup(arc_get_core_freq() / HZ);
+	return 0;
 }
 
 static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = {
-	.name		= "ARC Timer0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.mode		= CLOCK_EVT_MODE_UNUSED,
-	.rating		= 300,
-	.irq		= TIMER0_IRQ,	/* hardwired, no need for resources */
-	.set_next_event = arc_clkevent_set_next_event,
-	.set_mode	= arc_clkevent_set_mode,
+	.name			= "ARC Timer0",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 300,
+	.irq			= TIMER0_IRQ,	/* hardwired, no need for resources */
+	.set_next_event		= arc_clkevent_set_next_event,
+	.set_state_periodic	= arc_clkevent_set_periodic,
 };
 
 static irqreturn_t timer_irq_handler(int irq, void *dev_id)
@@ -240,7 +230,7 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id)
 	 * irq_set_chip_and_handler() asked for handle_percpu_devid_irq()
 	 */
 	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
-	int irq_reenable = evt->mode == CLOCK_EVT_MODE_PERIODIC;
+	int irq_reenable = clockevent_state_periodic(evt);
 
 	/*
 	 * Any write to CTRL reg ACks the interrupt, we rewrite the
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 807f7d61d7a7..a6f91e88ce36 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -58,7 +58,6 @@ static void show_callee_regs(struct callee_regs *cregs)
 
 static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 {
-	struct path path;
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index 74db59b6f392..abd961f3e763 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -34,7 +34,7 @@
 	"	.section .fixup,\"ax\"\n"		\
 	"	.align	4\n"				\
 	"3:	mov	%0, 1\n"			\
-	"	b	2b\n"				\
+	"	j	2b\n"				\
 	"	.previous\n"				\
 	"	.section __ex_table,\"a\"\n"		\
 	"	.align	4\n"				\
@@ -82,7 +82,7 @@
 		"	.section .fixup,\"ax\"\n"	\
 		"	.align	4\n"			\
 		"4:	mov	%0, 1\n"		\
-		"	b	3b\n"			\
+		"	j	3b\n"			\
 		"	.previous\n"			\
 		"	.section __ex_table,\"a\"\n"	\
 		"	.align	4\n"			\
@@ -113,7 +113,7 @@
 		"	.section .fixup,\"ax\"\n"	\
 		"	.align	4\n"			\
 		"6:	mov	%0, 1\n"		\
-		"	b	5b\n"			\
+		"	j	5b\n"			\
 		"	.previous\n"			\
 		"	.section __ex_table,\"a\"\n"	\
 		"	.align	4\n"			\
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index 1b2b3acfed52..0cab0b8a57c5 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -206,7 +206,7 @@ unalignedOffby3:
 	ld.ab	r6, [r1, 4]
 	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetch [r3, 32]	;Prefetch the next write location
+	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 8)
 	or	r7, r7, r5
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 92d573c734b5..365b18364815 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -10,12 +10,6 @@
 
 #undef PREALLOC_NOT_AVAIL
 
-#ifdef PREALLOC_NOT_AVAIL
-#define PREWRITE(A,B)	prefetchw [(A),(B)]
-#else
-#define PREWRITE(A,B)	prealloc [(A),(B)]
-#endif
-
 ENTRY(memset)
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
@@ -51,9 +45,15 @@ ENTRY(memset)
 
 ;;; Convert len to Dwords, unfold x8
 	lsr.f	lp_count, lp_count, 6
+
 	lpnz	@.Lset64bytes
 	;; LOOP START
-	PREWRITE(r3, 64)	;Prefetch the next write location
+#ifdef PREALLOC_NOT_AVAIL
+	prefetchw [r3, 64]	;Prefetch the next write location
+#else
+	prealloc  [r3, 64]
+#endif
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -62,16 +62,45 @@ ENTRY(memset)
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset64bytes:
 
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
 	prefetchw   [r3, 32]	;Prefetch the next write location
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset32bytes:
 
 	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index b29d62ed4f7e..0d1a6e96839f 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -22,15 +22,22 @@
 #include <asm/setup.h>
 
 static int l2_line_sz;
+int ioc_exists;
+volatile int slc_enable = 1, ioc_enable = 1;
 
 void (*_cache_line_loop_ic_fn)(unsigned long paddr, unsigned long vaddr,
 			       unsigned long sz, const int cacheop);
 
+void (*__dma_cache_wback_inv)(unsigned long start, unsigned long sz);
+void (*__dma_cache_inv)(unsigned long start, unsigned long sz);
+void (*__dma_cache_wback)(unsigned long start, unsigned long sz);
+
 char *arc_cache_mumbojumbo(int c, char *buf, int len)
 {
 	int n = 0;
 	struct cpuinfo_arc_cache *p;
 
+#define IS_USED_RUN(v)		((v) ? "" : "(disabled) ")
 #define PR_CACHE(p, cfg, str)						\
 	if (!(p)->ver)							\
 		n += scnprintf(buf + n, len - n, str"\t\t: N/A\n");	\
@@ -45,10 +52,18 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 	PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache");
 	PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
 
+	if (!is_isa_arcv2())
+                return buf;
+
 	p = &cpuinfo_arc700[c].slc;
 	if (p->ver)
 		n += scnprintf(buf + n, len - n,
-			"SLC\t\t: %uK, %uB Line\n", p->sz_k, p->line_len);
+			       "SLC\t\t: %uK, %uB Line%s\n",
+			       p->sz_k, p->line_len, IS_USED_RUN(slc_enable));
+
+	if (ioc_exists)
+		n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n",
+				IS_USED_RUN(ioc_enable));
 
 	return buf;
 }
@@ -58,18 +73,9 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
  * the cpuinfo structure for later use.
  * No Validation done here, simply read/convert the BCRs
  */
-void read_decode_cache_bcr(void)
+static void read_decode_cache_bcr_arcv2(int cpu)
 {
-	struct cpuinfo_arc_cache *p_ic, *p_dc, *p_slc;
-	unsigned int cpu = smp_processor_id();
-	struct bcr_cache {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-		unsigned int pad:12, line_len:4, sz:4, config:4, ver:8;
-#else
-		unsigned int ver:8, config:4, sz:4, line_len:4, pad:12;
-#endif
-	} ibcr, dbcr;
-
+	struct cpuinfo_arc_cache *p_slc = &cpuinfo_arc700[cpu].slc;
 	struct bcr_generic sbcr;
 
 	struct bcr_slc_cfg {
@@ -80,6 +86,39 @@ void read_decode_cache_bcr(void)
 #endif
 	} slc_cfg;
 
+	struct bcr_clust_cfg {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:7, c:1, num_entries:8, num_cores:8, ver:8;
+#else
+		unsigned int ver:8, num_cores:8, num_entries:8, c:1, pad:7;
+#endif
+	} cbcr;
+
+	READ_BCR(ARC_REG_SLC_BCR, sbcr);
+	if (sbcr.ver) {
+		READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
+		p_slc->ver = sbcr.ver;
+		p_slc->sz_k = 128 << slc_cfg.sz;
+		l2_line_sz = p_slc->line_len = (slc_cfg.lsz == 0) ? 128 : 64;
+	}
+
+	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
+	if (cbcr.c && ioc_enable)
+		ioc_exists = 1;
+}
+
+void read_decode_cache_bcr(void)
+{
+	struct cpuinfo_arc_cache *p_ic, *p_dc;
+	unsigned int cpu = smp_processor_id();
+	struct bcr_cache {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:12, line_len:4, sz:4, config:4, ver:8;
+#else
+		unsigned int ver:8, config:4, sz:4, line_len:4, pad:12;
+#endif
+	} ibcr, dbcr;
+
 	p_ic = &cpuinfo_arc700[cpu].icache;
 	READ_BCR(ARC_REG_IC_BCR, ibcr);
 
@@ -122,17 +161,8 @@ dc_chk:
 	p_dc->ver = dbcr.ver;
 
 slc_chk:
-	if (!is_isa_arcv2())
-		return;
-
-	p_slc = &cpuinfo_arc700[cpu].slc;
-	READ_BCR(ARC_REG_SLC_BCR, sbcr);
-	if (sbcr.ver) {
-		READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
-		p_slc->ver = sbcr.ver;
-		p_slc->sz_k = 128 << slc_cfg.sz;
-		l2_line_sz = p_slc->line_len = (slc_cfg.lsz == 0) ? 128 : 64;
-	}
+	if (is_isa_arcv2())
+                read_decode_cache_bcr_arcv2(cpu);
 }
 
 /*
@@ -468,10 +498,18 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
 noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 {
 #ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
 
-	local_irq_save(flags);
+	spin_lock_irqsave(&lock, flags);
 
 	/*
 	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
@@ -504,15 +542,10 @@ noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&lock, flags);
 #endif
 }
 
-static inline int need_slc_flush(void)
-{
-	return is_isa_arcv2() && l2_line_sz;
-}
-
 /***********************************************************
  * Exported APIs
  */
@@ -561,30 +594,74 @@ void flush_dcache_page(struct page *page)
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
-void dma_cache_wback_inv(unsigned long start, unsigned long sz)
+/*
+ * DMA ops for systems with L1 cache only
+ * Make memory coherent with L1 cache by flushing/invalidating L1 lines
+ */
+static void __dma_cache_wback_inv_l1(unsigned long start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
+}
 
-	if (need_slc_flush())
-		slc_op(start, sz, OP_FLUSH_N_INV);
+static void __dma_cache_inv_l1(unsigned long start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_INV);
 }
-EXPORT_SYMBOL(dma_cache_wback_inv);
 
-void dma_cache_inv(unsigned long start, unsigned long sz)
+static void __dma_cache_wback_l1(unsigned long start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH);
+}
+
+/*
+ * DMA ops for systems with both L1 and L2 caches, but without IOC
+ * Both L1 and L2 lines need to be explicity flushed/invalidated
+ */
+static void __dma_cache_wback_inv_slc(unsigned long start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
+	slc_op(start, sz, OP_FLUSH_N_INV);
+}
+
+static void __dma_cache_inv_slc(unsigned long start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_INV);
+	slc_op(start, sz, OP_INV);
+}
+
+static void __dma_cache_wback_slc(unsigned long start, unsigned long sz)
+{
+	__dc_line_op_k(start, sz, OP_FLUSH);
+	slc_op(start, sz, OP_FLUSH);
+}
 
-	if (need_slc_flush())
-		slc_op(start, sz, OP_INV);
+/*
+ * DMA ops for systems with IOC
+ * IOC hardware snoops all DMA traffic keeping the caches consistent with
+ * memory - eliding need for any explicit cache maintenance of DMA buffers
+ */
+static void __dma_cache_wback_inv_ioc(unsigned long start, unsigned long sz) {}
+static void __dma_cache_inv_ioc(unsigned long start, unsigned long sz) {}
+static void __dma_cache_wback_ioc(unsigned long start, unsigned long sz) {}
+
+/*
+ * Exported DMA API
+ */
+void dma_cache_wback_inv(unsigned long start, unsigned long sz)
+{
+	__dma_cache_wback_inv(start, sz);
+}
+EXPORT_SYMBOL(dma_cache_wback_inv);
+
+void dma_cache_inv(unsigned long start, unsigned long sz)
+{
+	__dma_cache_inv(start, sz);
 }
 EXPORT_SYMBOL(dma_cache_inv);
 
 void dma_cache_wback(unsigned long start, unsigned long sz)
 {
-	__dc_line_op_k(start, sz, OP_FLUSH);
-
-	if (need_slc_flush())
-		slc_op(start, sz, OP_FLUSH);
+	__dma_cache_wback(start, sz);
 }
 EXPORT_SYMBOL(dma_cache_wback);
 
@@ -840,4 +917,41 @@ void arc_cache_init(void)
 				panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
 		}
 	}
+
+	if (is_isa_arcv2() && l2_line_sz && !slc_enable) {
+
+		/* IM set : flush before invalidate */
+		write_aux_reg(ARC_REG_SLC_CTRL,
+			read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_IM);
+
+		write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
+
+		/* Important to wait for flush to complete */
+		while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
+		write_aux_reg(ARC_REG_SLC_CTRL,
+			read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE);
+	}
+
+	if (is_isa_arcv2() && ioc_exists) {
+		/* IO coherency base - 0x8z */
+		write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
+		/* IO coherency aperture size - 512Mb: 0x8z-0xAz */
+		write_aux_reg(ARC_REG_IO_COH_AP0_SIZE, 0x11);
+		/* Enable partial writes */
+		write_aux_reg(ARC_REG_IO_COH_PARTIAL, 1);
+		/* Enable IO coherency */
+		write_aux_reg(ARC_REG_IO_COH_ENABLE, 1);
+
+		__dma_cache_wback_inv = __dma_cache_wback_inv_ioc;
+		__dma_cache_inv = __dma_cache_inv_ioc;
+		__dma_cache_wback = __dma_cache_wback_ioc;
+	} else if (is_isa_arcv2() && l2_line_sz && slc_enable) {
+		__dma_cache_wback_inv = __dma_cache_wback_inv_slc;
+		__dma_cache_inv = __dma_cache_inv_slc;
+		__dma_cache_wback = __dma_cache_wback_slc;
+	} else {
+		__dma_cache_wback_inv = __dma_cache_wback_inv_l1;
+		__dma_cache_inv = __dma_cache_inv_l1;
+		__dma_cache_wback = __dma_cache_wback_l1;
+	}
 }
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 74a637a1cfc4..29a46bb198cc 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -19,6 +19,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/dma-debug.h>
 #include <linux/export.h>
+#include <asm/cache.h>
 #include <asm/cacheflush.h>
 
 /*
@@ -53,6 +54,20 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 {
 	void *paddr, *kvaddr;
 
+	/*
+	 * IOC relies on all data (even coherent DMA data) being in cache
+	 * Thus allocate normal cached memory
+	 *
+	 * The gains with IOC are two pronged:
+	 *   -For streaming data, elides needs for cache maintenance, saving
+	 *    cycles in flush code, and bus bandwidth as all the lines of a
+	 *    buffer need to be flushed out to memory
+	 *   -For coherent data, Read/Write to buffers terminate early in cache
+	 *   (vs. always going to memory - thus are faster)
+	 */
+	if (is_isa_arcv2() && ioc_exists)
+		return dma_alloc_noncoherent(dev, size, dma_handle, gfp);
+
 	/* This is linear addr (0x8000_0000 based) */
 	paddr = alloc_pages_exact(size, gfp);
 	if (!paddr)
@@ -60,8 +75,8 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	kvaddr = ioremap_nocache((unsigned long)paddr, size);
-	if (kvaddr != NULL)
-		memset(kvaddr, 0, size);
+	if (kvaddr == NULL)
+		return NULL;
 
 	/* This is bus address, platform dependent */
 	*dma_handle = (dma_addr_t)paddr;
@@ -85,6 +100,9 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
 		       dma_addr_t dma_handle)
 {
+	if (is_isa_arcv2() && ioc_exists)
+		return dma_free_noncoherent(dev, size, kvaddr, dma_handle);
+
 	iounmap((void __force __iomem *)kvaddr);
 
 	free_pages_exact((void *)dma_handle, size);
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index 99f7da513a48..ad9825d4026a 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -46,7 +46,7 @@ static void __init axs10x_enable_gpio_intc_wire(void)
 	 * -------------------   -------------------
 	 * | snps,dw-apb-gpio |  | snps,dw-apb-gpio |
 	 * -------------------   -------------------
-	 *        |                         |
+	 *        | #12                     |
 	 *        |                 [ Debug UART on cpu card ]
 	 *        |
 	 * ------------------------
@@ -389,6 +389,21 @@ axs103_set_freq(unsigned int id, unsigned int fd, unsigned int od)
 
 static void __init axs103_early_init(void)
 {
+	/*
+	 * AXS103 configurations for SMP/QUAD configurations share device tree
+	 * which defaults to 90 MHz. However recent failures of Quad config
+	 * revealed P&R timing violations so clamp it down to safe 50 MHz
+	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
+	 *
+	 * This hack is really hacky as of now. Fix it properly by getting the
+	 * number of cores as return value of platform's early SMP callback
+	 */
+#ifdef CONFIG_ARC_MCIP
+	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
+	if (num_cores > 2)
+		arc_set_core_freq(50 * 1000000);
+#endif
+
 	switch (arc_get_core_freq()/1000000) {
 	case 33:
 		axs103_set_freq(1, 1, 1);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a750c1425c3a..0d1b717e1eca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -188,6 +188,9 @@ config ARCH_HAS_ILOG2_U64
 config ARCH_HAS_BANDGAP
 	bool
 
+config FIX_EARLYCON_MEM
+	def_bool y if MMU
+
 config GENERIC_HWEIGHT
 	bool
 	default y
@@ -268,7 +271,6 @@ config PHYS_OFFSET
 	depends on !ARM_PATCH_PHYS_VIRT
 	default DRAM_BASE if !MMU
 	default 0x00000000 if ARCH_EBSA110 || \
-			EP93XX_SDCE3_SYNC_PHYS_OFFSET || \
 			ARCH_FOOTBRIDGE || \
 			ARCH_INTEGRATOR || \
 			ARCH_IOP13XX || \
@@ -277,10 +279,7 @@ config PHYS_OFFSET
 	default 0x10000000 if ARCH_OMAP1 || ARCH_RPC
 	default 0x20000000 if ARCH_S5PV210
 	default 0x70000000 if REALVIEW_HIGH_PHYS_OFFSET
-	default 0xc0000000 if EP93XX_SDCE0_PHYS_OFFSET || ARCH_SA1100
-	default 0xd0000000 if EP93XX_SDCE1_PHYS_OFFSET
-	default 0xe0000000 if EP93XX_SDCE2_PHYS_OFFSET
-	default 0xf0000000 if EP93XX_SDCE3_ASYNC_PHYS_OFFSET
+	default 0xc0000000 if ARCH_SA1100
 	help
 	  Please provide the physical address corresponding to the
 	  location of main memory in your system.
@@ -418,11 +417,14 @@ config ARCH_EP93XX
 	bool "EP93xx-based"
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_REQUIRE_GPIOLIB
-	select ARCH_USES_GETTIMEOFFSET
 	select ARM_AMBA
+	select ARM_PATCH_PHYS_VIRT
 	select ARM_VIC
+	select AUTO_ZRELADDR
 	select CLKDEV_LOOKUP
+	select CLKSRC_MMIO
 	select CPU_ARM920T
+	select GENERIC_CLOCKEVENTS
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 
@@ -536,6 +538,7 @@ config ARCH_ORION5X
 	select MVEBU_MBUS
 	select PCI
 	select PLAT_ORION_LEGACY
+	select MULTI_IRQ_HANDLER
 	help
 	  Support for the following Marvell Orion 5x series SoCs:
 	  Orion-1 (5181), Orion-VoIP (5181L), Orion-NAS (5182),
@@ -1496,6 +1499,7 @@ config HOTPLUG_CPU
 config ARM_PSCI
 	bool "Support for the ARM Power State Coordination Interface (PSCI)"
 	depends on CPU_V7
+	select ARM_PSCI_FW
 	help
 	  Say Y here if you want Linux to communicate with system firmware
 	  implementing the PSCI specification for CPU-centric power
@@ -1693,14 +1697,31 @@ config HIGHMEM
 config HIGHPTE
 	bool "Allocate 2nd-level pagetables from highmem"
 	depends on HIGHMEM
+	help
+	  The VM uses one page of physical memory for each page table.
+	  For systems with a lot of processes, this can use a lot of
+	  precious low memory, eventually leading to low memory being
+	  consumed by page tables.  Setting this option will allow
+	  user-space 2nd level page tables to reside in high memory.
 
-config HW_PERF_EVENTS
-	bool "Enable hardware performance counter support for perf events"
-	depends on PERF_EVENTS
+config CPU_SW_DOMAIN_PAN
+	bool "Enable use of CPU domains to implement privileged no-access"
+	depends on MMU && !ARM_LPAE
 	default y
 	help
-	  Enable hardware performance counter support for perf events. If
-	  disabled, perf events will use software events only.
+	  Increase kernel security by ensuring that normal kernel accesses
+	  are unable to access userspace addresses.  This can help prevent
+	  use-after-free bugs becoming an exploitable privilege escalation
+	  by ensuring that magic values (such as LIST_POISON) will always
+	  fault when dereferenced.
+
+	  CPUs with low-vector mappings use a best-efforts implementation.
+	  Their lower 1MB needs to remain accessible for the vectors, but
+	  the remainder of userspace will become appropriately inaccessible.
+
+config HW_PERF_EVENTS
+	def_bool y
+	depends on ARM_PMU
 
 config SYS_SUPPORTS_HUGETLBFS
        def_bool y
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f1b157971366..0cfd7f947f6b 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -141,6 +141,12 @@ choice
 		depends on ARCH_AT91
 		depends on SOC_SAMA5
 
+	config AT91_DEBUG_LL_DBGU3
+		bool "Kernel low-level debugging on sama5d2"
+		select DEBUG_AT91_UART
+		depends on ARCH_AT91
+		depends on SOC_SAMA5
+
 	config DEBUG_BCM2835
 		bool "Kernel low-level debugging on BCM2835 PL011 UART"
 		depends on ARCH_BCM2835
@@ -411,6 +417,13 @@ choice
 		  Say Y here if you want kernel low-level debugging support
 		  on i.MX6SX.
 
+	config DEBUG_IMX6UL_UART
+		bool "i.MX6UL Debug UART"
+		depends on SOC_IMX6UL
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on i.MX6UL.
+
 	config DEBUG_IMX7D_UART
 		bool "i.MX7D Debug UART"
 		depends on SOC_IMX7D
@@ -1269,6 +1282,7 @@ config DEBUG_IMX_UART_PORT
 						DEBUG_IMX6Q_UART || \
 						DEBUG_IMX6SL_UART || \
 						DEBUG_IMX6SX_UART || \
+						DEBUG_IMX6UL_UART || \
 						DEBUG_IMX7D_UART
 	default 1
 	depends on ARCH_MXC
@@ -1320,6 +1334,7 @@ config DEBUG_LL_INCLUDE
 				 DEBUG_IMX6Q_UART || \
 				 DEBUG_IMX6SL_UART || \
 				 DEBUG_IMX6SX_UART || \
+				 DEBUG_IMX6UL_UART || \
 				 DEBUG_IMX7D_UART
 	default "debug/ks8695.S" if DEBUG_KS8695_UART
 	default "debug/msm.S" if DEBUG_QCOM_UARTDM
@@ -1635,7 +1650,7 @@ config PID_IN_CONTEXTIDR
 
 config DEBUG_SET_MODULE_RONX
 	bool "Set loadable kernel module data as NX and text as RO"
-	depends on MODULES
+	depends on MODULES && MMU
 	---help---
 	  This option helps catch unintended modifications to loadable
 	  kernel module's text and read-only data. It also prevents execution
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 07ab3d203916..7451b447cc2d 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -312,6 +312,9 @@ INSTALL_TARGETS	= zinstall uinstall install
 
 PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
 
+bootpImage uImage: zImage
+zImage: Image
+
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 7a13aebacf81..3f9a9ebc77c3 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -51,10 +51,6 @@ else
 endif
 endif
 
-ifeq ($(CONFIG_ARCH_SHMOBILE_LEGACY),y)
-OBJS		+= head-shmobile.o
-endif
-
 #
 # We now have a PIC decompressor implementation.  Decompressors running
 # from RAM should not define ZTEXTADDR.  Decompressors running directly
diff --git a/arch/arm/boot/compressed/head-shmobile.S b/arch/arm/boot/compressed/head-shmobile.S
deleted file mode 100644
index 22a75259faa3..000000000000
--- a/arch/arm/boot/compressed/head-shmobile.S
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * The head-file for SH-Mobile ARM platforms
- *
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- * Simon Horman <horms@verge.net.au>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-
-#ifdef CONFIG_ZBOOT_ROM
-
-	.section	".start", "ax"
-
-	/* load board-specific initialization code */
-#include <mach/zboot.h>
-
-	adr	r0, dtb_info
-	ldmia	r0, {r1, r3, r4, r5, r7}
-
-	sub	r0, r0, r1		@ calculate the delta offset
-	add	r5, r5, r0		@ _edata
-
-	ldr	lr, [r5, #0]		@ check if valid DTB is present
-	cmp	lr, r3
-	bne	0f
-
-	add	r9, r7, #31		@ rounded up to a multiple
-	bic	r9, r9, #31		@ ... of 32 bytes
-
-	add	r6, r9, r5		@ copy from _edata
-	add	r9, r9, r4		@ to MEMORY_START
-
-1:	ldmdb	r6!, {r0 - r3, r10 - r12, lr}
-	cmp	r6, r5
-	stmdb	r9!, {r0 - r3, r10 - r12, lr}
-	bhi	1b
-
-	/* Success: Zero board ID, pointer to start of memory for atag/dtb */
-	mov	r7, #0
-	mov	r8, r4
-	b	2f
-
-	.align	2
-dtb_info:
-	.word	dtb_info
-#ifndef __ARMEB__
-	.word	0xedfe0dd0		@ sig is 0xd00dfeed big endian
-#else
-	.word	0xd00dfeed
-#endif
-	.word	MEMORY_START
-	.word	_edata
-	.word	0x4000			@ maximum DTB size
-0:
-	/* Failure: Zero board ID, NULL atag/dtb */
-	mov 	r7, #0
-	mov	r8, #0			@ pass null pointer as atag
-2 :
-
-#endif /* CONFIG_ZBOOT_ROM */
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 246473a244f6..233159d2eaab 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -41,6 +41,7 @@ dtb-$(CONFIG_SOC_SAM_V4_V5) += \
 	at91sam9x35ek.dtb
 dtb-$(CONFIG_SOC_SAM_V7) += \
 	at91-kizbox2.dtb \
+	at91-sama5d2_xplained.dtb \
 	at91-sama5d3_xplained.dtb \
 	sama5d31ek.dtb \
 	sama5d33ek.dtb \
@@ -176,6 +177,8 @@ dtb-$(CONFIG_MACH_KIRKWOOD) += \
 	kirkwood-km_kirkwood.dtb \
 	kirkwood-laplug.dtb \
 	kirkwood-lschlv2.dtb \
+	kirkwood-lswvl.dtb \
+	kirkwood-lswxl.dtb \
 	kirkwood-lsxhl.dtb \
 	kirkwood-mplcec4.dtb \
 	kirkwood-mv88f6281gtw-ge.dtb \
@@ -211,6 +214,7 @@ dtb-$(CONFIG_MACH_KIRKWOOD) += \
 	kirkwood-ts419-6281.dtb \
 	kirkwood-ts419-6282.dtb
 dtb-$(CONFIG_ARCH_LPC18XX) += \
+	lpc4337-ciaa.dtb \
 	lpc4350-hitex-eval.dtb \
 	lpc4357-ea4357-devkit.dtb
 dtb-$(CONFIG_ARCH_LPC32XX) += \
@@ -331,6 +335,8 @@ dtb-$(CONFIG_SOC_IMX6SX) += \
 	imx6sx-sabreauto.dtb \
 	imx6sx-sdb-reva.dtb \
 	imx6sx-sdb.dtb
+dtb-$(CONFIG_SOC_IMX6UL) += \
+	imx6ul-14x14-evk.dtb
 dtb-$(CONFIG_SOC_IMX7D) += \
 	imx7d-sdb.dtb
 dtb-$(CONFIG_SOC_LS1021A) += \
@@ -390,6 +396,8 @@ dtb-$(CONFIG_ARCH_OMAP3) += \
 	omap3-cm-t3530.dtb \
 	omap3-cm-t3730.dtb \
 	omap3-devkit8000.dtb \
+	omap3-devkit8000-lcd43.dtb \
+	omap3-devkit8000-lcd70.dtb \
 	omap3-evm.dtb \
 	omap3-evm-37xx.dtb \
 	omap3-gta04a3.dtb \
@@ -409,15 +417,19 @@ dtb-$(CONFIG_ARCH_OMAP3) += \
 	omap3-overo-alto35.dtb \
 	omap3-overo-chestnut43.dtb \
 	omap3-overo-gallop43.dtb \
+	omap3-overo-palo35.dtb \
 	omap3-overo-palo43.dtb \
 	omap3-overo-storm-alto35.dtb \
 	omap3-overo-storm-chestnut43.dtb \
 	omap3-overo-storm-gallop43.dtb \
+	omap3-overo-storm-palo35.dtb \
 	omap3-overo-storm-palo43.dtb \
 	omap3-overo-storm-summit.dtb \
 	omap3-overo-storm-tobi.dtb \
+	omap3-overo-storm-tobiduo.dtb \
 	omap3-overo-summit.dtb \
 	omap3-overo-tobi.dtb \
+	omap3-overo-tobiduo.dtb \
 	omap3-pandora-600mhz.dtb \
 	omap3-pandora-1ghz.dtb \
 	omap3-sbc-t3517.dtb \
@@ -426,6 +438,8 @@ dtb-$(CONFIG_ARCH_OMAP3) += \
 	omap3-thunder.dtb \
 	omap3-zoom3.dtb
 dtb-$(CONFIG_SOC_TI81XX) += \
+	dm8148-evm.dtb \
+	dm8148-t410.dtb \
 	dm8168-evm.dtb
 dtb-$(CONFIG_SOC_AM33XX) += \
 	am335x-baltos-ir5221.dtb \
@@ -438,7 +452,8 @@ dtb-$(CONFIG_SOC_AM33XX) += \
 	am335x-nano.dtb \
 	am335x-pepper.dtb \
 	am335x-lxm.dtb \
-	am335x-chiliboard.dtb
+	am335x-chiliboard.dtb \
+	am335x-wega-rdk.dtb
 dtb-$(CONFIG_ARCH_OMAP4) += \
 	omap4-duovero-parlor.dtb \
 	omap4-panda.dtb \
@@ -464,6 +479,8 @@ dtb-$(CONFIG_SOC_DRA7XX) += \
 dtb-$(CONFIG_ARCH_ORION5X) += \
 	orion5x-lacie-d2-network.dtb \
 	orion5x-lacie-ethernet-disk-mini-v2.dtb \
+	orion5x-linkstation-lswtgl.dtb \
+	orion5x-lswsgl.dtb \
 	orion5x-maxtor-shared-storage-2.dtb \
 	orion5x-rd88f5182-nas.dtb
 dtb-$(CONFIG_ARCH_PRIMA2) += \
@@ -488,7 +505,12 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += \
 	rk3288-evb-act8846.dtb \
 	rk3288-evb-rk808.dtb \
 	rk3288-firefly-beta.dtb \
-	rk3288-firefly.dtb
+	rk3288-firefly.dtb \
+	rk3288-r89.dtb \
+	rk3288-veyron-jerry.dtb \
+	rk3288-veyron-minnie.dtb \
+	rk3288-veyron-pinky.dtb \
+	rk3288-veyron-speedy.dtb
 dtb-$(CONFIG_ARCH_S3C24XX) += \
 	s3c2416-smdk2416.dtb
 dtb-$(CONFIG_ARCH_S3C64XX) += \
@@ -501,11 +523,8 @@ dtb-$(CONFIG_ARCH_S5PV210) += \
 	s5pv210-smdkv210.dtb \
 	s5pv210-torbreck.dtb
 dtb-$(CONFIG_ARCH_SHMOBILE_LEGACY) += \
-	r8a7740-armadillo800eva.dtb \
 	r8a7778-bockw.dtb \
-	r8a7778-bockw-reference.dtb \
-	r8a7779-marzen.dtb \
-	sh73a0-kzm9g.dtb
+	r8a7778-bockw-reference.dtb
 dtb-$(CONFIG_ARCH_SHMOBILE_MULTI) += \
 	emev2-kzm9d.dtb \
 	r7s72100-genmai.dtb \
@@ -516,12 +535,15 @@ dtb-$(CONFIG_ARCH_SHMOBILE_MULTI) += \
 	r8a7790-lager.dtb \
 	r8a7791-henninger.dtb \
 	r8a7791-koelsch.dtb \
+	r8a7793-gose.dtb \
 	r8a7794-alt.dtb \
+	r8a7794-silk.dtb \
 	sh73a0-kzm9g.dtb
 dtb-$(CONFIG_ARCH_SOCFPGA) += \
 	socfpga_arria5_socdk.dtb \
 	socfpga_arria10_socdk_sdmmc.dtb \
 	socfpga_cyclone5_socdk.dtb \
+	socfpga_cyclone5_de0_sockit.dtb \
 	socfpga_cyclone5_sockit.dtb \
 	socfpga_cyclone5_socrates.dtb \
 	socfpga_vt.dtb
@@ -544,7 +566,9 @@ dtb-$(CONFIG_ARCH_STI) += \
 	stih416-b2020.dtb \
 	stih416-b2020e.dtb \
 	stih418-b2199.dtb
-dtb-$(CONFIG_ARCH_STM32)+= stm32f429-disco.dtb
+dtb-$(CONFIG_ARCH_STM32)+= \
+	stm32f429-disco.dtb \
+	stm32429i-eval.dtb
 dtb-$(CONFIG_MACH_SUN4I) += \
 	sun4i-a10-a1000.dtb \
 	sun4i-a10-ba10-tvbox.dtb \
@@ -554,6 +578,7 @@ dtb-$(CONFIG_MACH_SUN4I) += \
 	sun4i-a10-hackberry.dtb \
 	sun4i-a10-hyundai-a7hd.dtb \
 	sun4i-a10-inet97fv2.dtb \
+	sun4i-a10-itead-iteaduino-plus.dts \
 	sun4i-a10-jesurun-q5.dtb \
 	sun4i-a10-marsboard.dtb \
 	sun4i-a10-mini-xplus.dtb \
@@ -601,6 +626,7 @@ dtb-$(CONFIG_MACH_SUN8I) += \
 	sun8i-a23-ippo-q8h-v1.2.dtb \
 	sun8i-a33-et-q8-v1.6.dtb \
 	sun8i-a33-ga10h-v1.1.dtb \
+	sun8i-a33-ippo-q8h-v1.2.dtb \
 	sun8i-a33-sinlinx-sina33.dtb
 dtb-$(CONFIG_MACH_SUN9I) += \
 	sun9i-a80-optimus.dtb \
@@ -642,10 +668,11 @@ dtb-$(CONFIG_ARCH_U8500) += \
 	ste-ccu8540.dtb \
 	ste-ccu9540.dtb
 dtb-$(CONFIG_ARCH_UNIPHIER) += \
-	uniphier-ph1-sld3-ref.dtb \
 	uniphier-ph1-ld4-ref.dtb \
+	uniphier-ph1-ld6b-ref.dtb \
 	uniphier-ph1-pro4-ref.dtb \
-	uniphier-ph1-sld8-ref.dtb
+	uniphier-ph1-sld3-ref.dtb \
+	uniphier-ph1-sld8-ref.dtb 
 dtb-$(CONFIG_ARCH_VERSATILE) += \
 	versatile-ab.dtb \
 	versatile-pb.dtb
@@ -705,6 +732,7 @@ dtb-$(CONFIG_MACH_DOVE) += \
 	dove-dove-db.dtb \
 	dove-sbc-a510.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += \
+	mt6580-evbp1.dtb \
 	mt6589-aquaris5.dtb \
 	mt6592-evb.dtb \
 	mt8127-moose.dtb \
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 901739fcb85a..eadbba32386d 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -68,15 +68,29 @@
 
 &lcdc {
 	status = "okay";
+	port {
+		lcdc_0: endpoint@0 {
+			remote-endpoint = <&hdmi_0>;
+		};
+	};
 };
 
-/ {
-	hdmi {
-		compatible = "ti,tilcdc,slave";
-		i2c = <&i2c0>;
+&i2c0 {
+	tda19988 {
+		compatible = "nxp,tda998x";
+		reg = <0x70>;
 		pinctrl-names = "default", "off";
 		pinctrl-0 = <&nxp_hdmi_bonelt_pins>;
 		pinctrl-1 = <&nxp_hdmi_bonelt_off_pins>;
-		status = "okay";
+
+		port {
+			hdmi_0: endpoint@0 {
+				remote-endpoint = <&lcdc_0>;
+			};
+		};
 	};
 };
+
+&rtc {
+	system-power-controller;
+};
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 765be2766eb0..1942a5c8132d 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -136,16 +136,29 @@
 	};
 
 	sound {
-		compatible = "ti,da830-evm-audio";
-		ti,model = "AM335x-EVM";
-		ti,audio-codec = <&tlv320aic3106>;
-		ti,mcasp-controller = <&mcasp1>;
-		ti,codec-clock-rate = <12000000>;
-		ti,audio-routing =
-			"Headphone Jack",       "HPLOUT",
-			"Headphone Jack",       "HPROUT",
-			"LINE1L",               "Line In",
-			"LINE1R",               "Line In";
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "AM335x-EVM";
+		simple-audio-card,widgets =
+			"Headphone", "Headphone Jack",
+			"Line", "Line In";
+		simple-audio-card,routing =
+			"Headphone Jack",	"HPLOUT",
+			"Headphone Jack",	"HPROUT",
+			"LINE1L",		"Line In",
+			"LINE1R",		"Line In";
+		simple-audio-card,format = "dsp_b";
+		simple-audio-card,bitclock-master = <&sound_master>;
+		simple-audio-card,frame-master = <&sound_master>;
+		simple-audio-card,bitclock-inversion;
+
+		simple-audio-card,cpu {
+			sound-dai = <&mcasp1>;
+		};
+
+		sound_master: simple-audio-card,codec {
+			sound-dai = <&tlv320aic3106>;
+			system-clock-frequency = <12000000>;
+		};
 	};
 };
 
@@ -342,7 +355,7 @@
 		>;
 	};
 
-	am335x_evm_audio_pins: am335x_evm_audio_pins {
+	mcasp1_pins: mcasp1_pins {
 		pinctrl-single,pins = <
 			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE4) /* mii1_crs.mcasp1_aclkx */
 			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE4) /* mii1_rxerr.mcasp1_fsx */
@@ -351,6 +364,15 @@
 		>;
 	};
 
+	mcasp1_pins_sleep: mcasp1_pins_sleep {
+		pinctrl-single,pins = <
+			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x108 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x144 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+		>;
+	};
+
 	dcan1_pins_default: dcan1_pins_default {
 		pinctrl-single,pins = <
 			0x168 (PIN_OUTPUT | MUX_MODE2) /* uart0_ctsn.d_can1_tx */
@@ -460,6 +482,7 @@
 	};
 
 	tlv320aic3106: tlv320aic3106@1b {
+		#sound-dai-cells = <0>;
 		compatible = "ti,tlv320aic3106";
 		reg = <0x1b>;
 		status = "okay";
@@ -575,19 +598,21 @@
 #include "tps65910.dtsi"
 
 &mcasp1 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&am335x_evm_audio_pins>;
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&mcasp1_pins>;
+	pinctrl-1 = <&mcasp1_pins_sleep>;
 
-		status = "okay";
+	status = "okay";
 
-		op-mode = <0>;          /* MCASP_IIS_MODE */
-		tdm-slots = <2>;
-		/* 4 serializers */
-		serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
-			0 0 1 2
-		>;
-		tx-num-evt = <32>;
-		rx-num-evt = <32>;
+	op-mode = <0>;          /* MCASP_IIS_MODE */
+	tdm-slots = <2>;
+	/* 4 serializers */
+	serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
+		0 0 1 2
+	>;
+	tx-num-evt = <32>;
+	rx-num-evt = <32>;
 };
 
 &tps {
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 156d05efcb70..315bb02c9920 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -141,14 +141,26 @@
 	};
 
 	sound {
-		compatible = "ti,da830-evm-audio";
-		ti,model = "AM335x-EVMSK";
-		ti,audio-codec = <&tlv320aic3106>;
-		ti,mcasp-controller = <&mcasp1>;
-		ti,codec-clock-rate = <24000000>;
-		ti,audio-routing =
-			"Headphone Jack",       "HPLOUT",
-			"Headphone Jack",       "HPROUT";
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "AM335x-EVMSK";
+		simple-audio-card,widgets =
+			"Headphone", "Headphone Jack";
+		simple-audio-card,routing =
+			"Headphone Jack",	"HPLOUT",
+			"Headphone Jack",	"HPROUT";
+		simple-audio-card,format = "dsp_b";
+		simple-audio-card,bitclock-master = <&sound_master>;
+		simple-audio-card,frame-master = <&sound_master>;
+		simple-audio-card,bitclock-inversion;
+
+		simple-audio-card,cpu {
+			sound-dai = <&mcasp1>;
+		};
+
+		sound_master: simple-audio-card,codec {
+			sound-dai = <&tlv320aic3106>;
+			system-clock-frequency = <24000000>;
+		};
 	};
 
 	panel {
@@ -396,6 +408,15 @@
 		>;
 	};
 
+	mcasp1_pins_sleep: mcasp1_pins_sleep {
+		pinctrl-single,pins = <
+			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x108 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x144 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+		>;
+	};
+
 	mmc2_pins: pinmux_mmc2_pins {
 		pinctrl-single,pins = <
 			0x74 (PIN_INPUT_PULLUP | MUX_MODE7) /* gpmc_wpn.gpio0_31 */
@@ -462,6 +483,7 @@
 	};
 
 	tlv320aic3106: tlv320aic3106@1b {
+		#sound-dai-cells = <0>;
 		compatible = "ti,tlv320aic3106";
 		reg = <0x1b>;
 		status = "okay";
@@ -661,19 +683,21 @@
 };
 
 &mcasp1 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&mcasp1_pins>;
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&mcasp1_pins>;
+	pinctrl-1 = <&mcasp1_pins_sleep>;
 
-		status = "okay";
+	status = "okay";
 
-		op-mode = <0>;          /* MCASP_IIS_MODE */
-		tdm-slots = <2>;
-		/* 4 serializers */
-		serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
-			0 0 1 2
-		>;
-		tx-num-evt = <32>;
-		rx-num-evt = <32>;
+	op-mode = <0>;          /* MCASP_IIS_MODE */
+	tdm-slots = <2>;
+	/* 4 serializers */
+	serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
+		0 0 1 2
+	>;
+	tx-num-evt = <32>;
+	rx-num-evt = <32>;
 };
 
 &tscadc {
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 0d35ab64641c..7106114c7464 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -74,6 +74,7 @@
 	audio_codec: tlv320aic3106@1b {
 		compatible = "ti,tlv320aic3106";
 		reg = <0x1b>;
+		ai3x-micbias-vg = <0x2>;
 	};
 
 	accel: lis331dlh@1d {
@@ -153,7 +154,7 @@
 	ti,audio-routing =
 		"Headphone Jack",	"HPLOUT",
 		"Headphone Jack",	"HPROUT",
-		"LINE1L",		"Line In";
+		"MIC3L",		"Mic3L Switch";
 };
 
 &mcasp0 {
@@ -438,41 +439,50 @@
 	regulators {
 		dcdc1_reg: regulator@0 {
 			/* VDD_1V8 system supply */
+			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
 			/* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1325000>;
+			regulator-max-microvolt = <1150000>;
 			regulator-boot-on;
+			regulator-always-on;
 		};
 
 		dcdc3_reg: regulator@2 {
 			/* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1150000>;
+			regulator-max-microvolt = <1325000>;
 			regulator-boot-on;
+			regulator-always-on;
 		};
 
 		ldo1_reg: regulator@3 {
 			/* VRTC 1.8V always-on supply */
+			regulator-name = "vrtc,vdds";
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
 			/* 3.3V rail */
+			regulator-name = "vdd_3v3aux";
+			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
 			/* VDD_3V3A 3.3V rail */
+			regulator-name = "vdd_3v3a";
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 		};
 
 		ldo4_reg: regulator@6 {
 			/* VDD_3V3B 3.3V rail */
+			regulator-name = "vdd_3v3b";
+			regulator-always-on;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
new file mode 100644
index 000000000000..4d28fc3aac69
--- /dev/null
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -0,0 +1,368 @@
+/*
+ * Copyright (C) 2015 Phytec Messtechnik GmbH
+ * Author: Teresa Remmet <t.remmet@phytec.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "am33xx.dtsi"
+
+/ {
+	model = "Phytec AM335x phyCORE";
+	compatible = "phytec,am335x-phycore-som", "ti,am33xx";
+
+	aliases {
+		rtc0 = &i2c_rtc;
+		rtc1 = &rtc;
+	};
+
+	cpus {
+		cpu@0 {
+			cpu0-supply = <&vdd1_reg>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>; /* 256 MB */
+	};
+
+	vbat: fixedregulator@0 {
+		compatible = "regulator-fixed";
+	};
+};
+
+/* Crypto Module */
+&aes {
+	status = "okay";
+};
+
+&sham {
+	status = "okay";
+};
+
+/* Ethernet */
+&am33xx_pinmux {
+	ethernet0_pins: pinmux_ethernet0 {
+		pinctrl-single,pins = <
+			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_crs.rmii1_crs_dv */
+			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxerr.rmii1_rxerr */
+			0x114 (PIN_OUTPUT | MUX_MODE1)		/* mii1_txen.rmii1_txen */
+			0x124 (PIN_OUTPUT | MUX_MODE1)		/* mii1_txd1.rmii1_txd1 */
+			0x128 (PIN_OUTPUT | MUX_MODE1)		/* mii1_txd0.rmii1_txd0 */
+			0x13c (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxd1.rmii1_rxd1 */
+			0x140 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxd0.rmii1_rxd0 */
+			0x144 (PIN_INPUT_PULLDOWN | MUX_MODE0)	/* rmii1_refclk.rmii1_refclk */
+		>;
+	};
+
+	mdio_pins: pinmux_mdio {
+		pinctrl-single,pins = <
+			/* MDIO */
+			0x148 (PIN_INPUT_PULLUP | SLEWCTRL_FAST | MUX_MODE0)	/* mdio_data.mdio_data */
+			0x14c (PIN_OUTPUT_PULLUP | MUX_MODE0)			/* mdio_clk.mdio_clk */
+		>;
+	};
+};
+
+&cpsw_emac0 {
+	phy_id = <&davinci_mdio>, <0>;
+	phy-mode = "rmii";
+	dual_emac_res_vlan = <1>;
+};
+
+&davinci_mdio {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mdio_pins>;
+	status = "okay";
+};
+
+&mac {
+	slaves = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&ethernet0_pins>;
+	status = "okay";
+};
+
+&phy_sel {
+	rmii-clock-ext;
+};
+
+/* I2C Busses */
+&am33xx_pinmux {
+	i2c0_pins: pinmux_i2c0 {
+		pinctrl-single,pins = <
+			0x188 (PIN_INPUT | MUX_MODE0)	/* i2c0_sda.i2c0_sda */
+			0x18c (PIN_INPUT | MUX_MODE0)	/* i2c0_scl.i2c0_scl */
+		>;
+	};
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	tps: pmic@2d {
+		reg = <0x2d>;
+	};
+
+	i2c_eeprom: eeprom@52 {
+		compatible = "atmel,24c32";
+		pagesize = <32>;
+		reg = <0x52>;
+		status = "disabled";
+	};
+
+	i2c_rtc: rtc@68 {
+		compatible = "rv4162";
+		reg = <0x68>;
+		status = "disabled";
+	};
+};
+
+/* NAND memory */
+&am33xx_pinmux {
+		nandflash_pins: pinmux_nandflash {
+			pinctrl-single,pins = <
+			0x0 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad0.gpmc_ad0 */
+			0x4 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad1.gpmc_ad1 */
+			0x8 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad2.gpmc_ad2 */
+			0xc (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad3.gpmc_ad3 */
+			0x10 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad4.gpmc_ad4 */
+			0x14 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad5.gpmc_ad5 */
+			0x18 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad6.gpmc_ad6 */
+			0x1c (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_ad7.gpmc_ad7 */
+			0x70 (PIN_INPUT_PULLUP | MUX_MODE0)	/* gpmc_wait0.gpmc_wait0 */
+			0x7c (PIN_OUTPUT | MUX_MODE0)		/* gpmc_csn0.gpmc_csn0 */
+			0x90 (PIN_OUTPUT | MUX_MODE0)		/* gpmc_advn_ale.gpmc_advn_ale */
+			0x94 (PIN_OUTPUT | MUX_MODE0)		/* gpmc_oen_ren.gpmc_oen_ren */
+			0x98 (PIN_OUTPUT | MUX_MODE0)		/* gpmc_wen.gpmc_wen */
+			0x9c (PIN_OUTPUT | MUX_MODE0)		/* gpmc_be0n_cle.gpmc_be0n_cle */
+		>;
+	};
+};
+
+&elm {
+	status = "okay";
+};
+
+&gpmc {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&nandflash_pins>;
+	ranges = <0 0 0x08000000 0x1000000>;   /* CS0: NAND */
+	nandflash: nand@0,0 {
+		reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
+		nand-bus-width = <8>;
+		ti,nand-ecc-opt = "bch8";
+		gpmc,device-nand = "true";
+		gpmc,device-width = <1>;
+		gpmc,sync-clk-ps = <0>;
+		gpmc,cs-on-ns = <0>;
+		gpmc,cs-rd-off-ns = <30>;
+		gpmc,cs-wr-off-ns = <30>;
+		gpmc,adv-on-ns = <0>;
+		gpmc,adv-rd-off-ns = <30>;
+		gpmc,adv-wr-off-ns = <30>;
+		gpmc,we-on-ns = <0>;
+		gpmc,we-off-ns = <20>;
+		gpmc,oe-on-ns = <10>;
+		gpmc,oe-off-ns = <30>;
+		gpmc,access-ns = <30>;
+		gpmc,rd-cycle-ns = <30>;
+		gpmc,wr-cycle-ns = <30>;
+		gpmc,wait-on-read = "true";
+		gpmc,wait-on-write = "true";
+		gpmc,bus-turnaround-ns = <0>;
+		gpmc,cycle2cycle-delay-ns = <50>;
+		gpmc,cycle2cycle-diffcsen;
+		gpmc,clk-activation-ns = <0>;
+		gpmc,wait-monitoring-ns = <0>;
+		gpmc,wr-access-ns = <30>;
+		gpmc,wr-data-mux-bus-ns = <0>;
+
+		elm_id = <&elm>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "xload";
+			reg = <0x0 0x20000>;
+		};
+		partition@1 {
+			label = "xload_backup1";
+			reg = <0x20000 0x20000>;
+		};
+		partition@2 {
+			label = "xload_backup2";
+			reg = <0x40000 0x20000>;
+		};
+		partition@3 {
+			label = "xload_backup3";
+			reg = <0x60000 0x20000>;
+		};
+		partition@4 {
+			label = "barebox";
+			reg = <0x80000 0x80000>;
+		};
+		partition@5 {
+			label = "bareboxenv";
+			reg = <0x100000 0x40000>;
+		};
+		partition@6 {
+			label = "oftree";
+			reg = <0x140000 0x40000>;
+		};
+		partition@7 {
+			label = "kernel";
+			reg = <0x180000 0x800000>;
+		};
+		partition@8 {
+			label = "root";
+			reg = <0x980000 0x0>;
+		};
+	};
+};
+
+/* Power */
+#include "tps65910.dtsi"
+
+&tps {
+	vcc1-supply = <&vbat>;
+	vcc2-supply = <&vbat>;
+	vcc3-supply = <&vbat>;
+	vcc4-supply = <&vbat>;
+	vcc5-supply = <&vbat>;
+	vcc6-supply = <&vbat>;
+	vcc7-supply = <&vbat>;
+	vccio-supply = <&vbat>;
+
+	regulators {
+		vrtc_reg: regulator@0 {
+			regulator-always-on;
+		};
+
+		vio_reg: regulator@1 {
+			regulator-always-on;
+		};
+
+		vdd1_reg: regulator@2 {
+			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
+			regulator-name = "vdd_mpu";
+			regulator-min-microvolt = <912500>;
+			regulator-max-microvolt = <1312500>;
+			regulator-boot-on;
+			regulator-always-on;
+		};
+
+		vdd2_reg: regulator@3 {
+			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
+			regulator-name = "vdd_core";
+			regulator-min-microvolt = <912500>;
+			regulator-max-microvolt = <1150000>;
+			regulator-boot-on;
+			regulator-always-on;
+		};
+
+		vdd3_reg: regulator@4 {
+			regulator-always-on;
+		};
+
+		vdig1_reg: regulator@5 {
+			regulator-name = "vdig1_1p8v";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		vdig2_reg: regulator@6 {
+			regulator-always-on;
+		};
+
+		vpll_reg: regulator@7 {
+			regulator-always-on;
+		};
+
+		vdac_reg: regulator@8 {
+			regulator-always-on;
+		};
+
+		vaux1_reg: regulator@9 {
+			regulator-always-on;
+		};
+
+		vaux2_reg: regulator@10 {
+			regulator-always-on;
+		};
+
+		vaux33_reg: regulator@11 {
+			regulator-always-on;
+		};
+
+		vmmc_reg: regulator@12 {
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+	};
+};
+
+&vbat {
+	regulator-name = "vbat";
+	regulator-min-microvolt = <5000000>;
+	regulator-max-microvolt = <5000000>;
+	regulator-boot-on;
+};
+
+/* SPI Busses */
+&am33xx_pinmux {
+	spi0_pins: pinmux_spi0 {
+		pinctrl-single,pins = <
+			0x150 (PIN_INPUT_PULLDOWN | MUX_MODE0)	/* spi0_clk.spi0_clk */
+			0x154 (PIN_INPUT_PULLDOWN | MUX_MODE0)	/* spi0_d0.spi0_d0 */
+			0x158 (PIN_INPUT_PULLUP | MUX_MODE0)	/* spi0_d1.spi0_d1 */
+			0x15c (PIN_INPUT_PULLUP | MUX_MODE0)	/* spi0_cs0.spi0_cs0 */
+		>;
+	};
+};
+
+&spi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi0_pins>;
+	status = "okay";
+
+	serial_flash: m25p80@0 {
+		compatible = "m25p80";
+		spi-max-frequency = <48000000>;
+		reg = <0x0>;
+		m25p,fast-read;
+		status = "disabled";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "xload";
+			reg = <0x0 0x20000>;
+		};
+		partition@1 {
+			label = "barebox";
+			reg = <0x20000 0x80000>;
+		};
+		partition@2 {
+			label = "bareboxenv";
+			reg = <0xa0000 0x20000>;
+		};
+		partition@3 {
+			label = "oftree";
+			reg = <0xc0000 0x20000>;
+		};
+		partition@4 {
+			label = "kernel";
+			reg = <0xe0000 0x0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/am335x-wega-rdk.dts b/arch/arm/boot/dts/am335x-wega-rdk.dts
new file mode 100644
index 000000000000..6431b7db8109
--- /dev/null
+++ b/arch/arm/boot/dts/am335x-wega-rdk.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2015 Phytec Messtechnik GmbH
+ * Author: Teresa Remmet <t.remmet@phytec.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/dts-v1/;
+
+#include "am335x-phycore-som.dtsi"
+#include "am335x-wega.dtsi"
+
+/* SoM */
+&i2c_eeprom {
+	status = "okay";
+};
+
+&i2c_rtc {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/am335x-wega.dtsi b/arch/arm/boot/dts/am335x-wega.dtsi
new file mode 100644
index 000000000000..5e541bd1b45a
--- /dev/null
+++ b/arch/arm/boot/dts/am335x-wega.dtsi
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2015 Phytec Messtechnik GmbH
+ * Author: Teresa Remmet <t.remmet@phytec.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	model = "Phytec AM335x phyBOARD-WEGA";
+	compatible = "phytec,am335x-wega", "phytec,am335x-phycore-som", "ti,am33xx";
+
+};
+
+/* CAN Busses */
+&am33xx_pinmux {
+	dcan1_pins: pinmux_dcan1 {
+		pinctrl-single,pins = <
+			0x168 (PIN_OUTPUT_PULLUP | MUX_MODE2) /* uart0_ctsn.d_can1_tx */
+			0x16c (PIN_INPUT_PULLUP | MUX_MODE2) /* uart0_rtsn.d_can1_rx */
+		>;
+	};
+};
+
+&dcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&dcan1_pins>;
+	status = "okay";
+};
+
+/* Ethernet */
+&am33xx_pinmux {
+	ethernet1_pins: pinmux_ethernet1 {
+		pinctrl-single,pins = <
+			0x40 (PIN_OUTPUT | MUX_MODE1)		/* gpmc_a0.mii2_txen */
+			0x44 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a1.mii2_rxdv */
+			0x48 (PIN_OUTPUT | MUX_MODE1)		/* gpmc_a2.mii2_txd3 */
+			0x4c (PIN_OUTPUT | MUX_MODE1)		/* gpmc_a3.mii2_txd2 */
+			0x50 (PIN_OUTPUT | MUX_MODE1)		/* gpmc_a4.mii2_txd1 */
+			0x54 (PIN_OUTPUT | MUX_MODE1)		/* gpmc_a5.mii2_txd0 */
+			0x58 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a6.mii2_txclk */
+			0x5c (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a7.mii2_rxclk */
+			0x60 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a8.mii2_rxd3 */
+			0x64 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a9.mii2_rxd2 */
+			0x68 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a10.mii2_rxd1 */
+			0x6c (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_a11.mii2_rxd0 */
+			0x74 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_wpn.mii2_rxerr */
+			0x78 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* gpmc_ben1.mii2_col */
+		>;
+	};
+};
+
+&cpsw_emac1 {
+	phy_id = <&davinci_mdio>, <1>;
+	phy-mode = "mii";
+	dual_emac_res_vlan = <2>;
+};
+
+&mac {
+	slaves = <2>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&ethernet0_pins &ethernet1_pins>;
+	dual_emac = <1>;
+};
+
+/* MMC */
+&am33xx_pinmux {
+	mmc1_pins: pinmux_mmc1 {
+		pinctrl-single,pins = <
+			0x0F0 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_dat3.mmc0_dat3 */
+			0x0F4 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_dat2.mmc0_dat2 */
+			0x0F8 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_dat1.mmc0_dat1 */
+			0x0FC (PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_dat0.mmc0_dat0 */
+			0x100 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_clk.mmc0_clk */
+			0x104 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_cmd.mmc0_cmd */
+			0x160 (PIN_INPUT_PULLUP | MUX_MODE7)	/* spi0_cs1.mmc0_sdcd */
+		>;
+	};
+};
+
+&mmc1 {
+	vmmc-supply = <&vmmc_reg>;
+	bus-width = <4>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins>;
+	cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+/* UARTs */
+&am33xx_pinmux {
+	uart0_pins: pinmux_uart0 {
+		pinctrl-single,pins = <
+			0x170 (PIN_INPUT_PULLUP | MUX_MODE0)    /* uart0_rxd.uart0_rxd */
+			0x174 (PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* uart0_txd.uart0_txd */
+		>;
+	};
+
+	uart1_pins: pinmux_uart1_pins {
+		pinctrl-single,pins = <
+			0x180 (PIN_INPUT_PULLUP | MUX_MODE0)	/* uart1_rxd.uart1_rxd */
+			0x184 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* uart1_txd.uart1_txd */
+			0x178 (PIN_INPUT | MUX_MODE0)		/* uart1_ctsn.uart1_ctsn */
+			0x17c (PIN_OUTPUT_PULLDOWN | MUX_MODE0)		/* uart1_rtsn.uart1_rtsn */
+		>;
+	};
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins>;
+	status = "okay";
+};
+
+/* USB */
+&cppi41dma {
+	status = "okay";
+};
+
+&usb_ctrl_mod {
+	status = "okay";
+};
+
+&usb {
+	status = "okay";
+};
+
+&usb0 {
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&usb0_phy {
+	status = "okay";
+};
+
+&usb1 {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usb1_phy {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 21fcc440fc1a..d23e2524d694 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -103,6 +103,15 @@
 			#size-cells = <1>;
 			ranges = <0 0x44c00000 0x280000>;
 
+			wkup_m3: wkup_m3@100000 {
+				compatible = "ti,am3352-wkup-m3";
+				reg = <0x100000 0x4000>,
+				      <0x180000	0x2000>;
+				reg-names = "umem", "dmem";
+				ti,hwmods = "wkup_m3";
+				ti,pm-firmware = "am335x-pm-firmware.elf";
+			};
+
 			prcm: prcm@200000 {
 				compatible = "ti,am3-prcm";
 				reg = <0x200000 0x4000>;
@@ -144,6 +153,14 @@
 					};
 				};
 
+				wkup_m3_ipc: wkup_m3_ipc@1324 {
+					compatible = "ti,am3352-wkup-m3-ipc";
+					reg = <0x1324 0x24>;
+					interrupts = <78>;
+					ti,rproc = <&wkup_m3>;
+					mboxes = <&mailbox &mbox_wkupm3>;
+				};
+
 				scm_clockdomains: clockdomains {
 				};
 			};
@@ -210,7 +227,7 @@
 		};
 
 		uart0: serial@44e09000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart1";
 			clock-frequency = <48000000>;
 			reg = <0x44e09000 0x2000>;
@@ -221,7 +238,7 @@
 		};
 
 		uart1: serial@48022000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart2";
 			clock-frequency = <48000000>;
 			reg = <0x48022000 0x2000>;
@@ -232,7 +249,7 @@
 		};
 
 		uart2: serial@48024000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart3";
 			clock-frequency = <48000000>;
 			reg = <0x48024000 0x2000>;
@@ -243,7 +260,7 @@
 		};
 
 		uart3: serial@481a6000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart4";
 			clock-frequency = <48000000>;
 			reg = <0x481a6000 0x2000>;
@@ -252,7 +269,7 @@
 		};
 
 		uart4: serial@481a8000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart5";
 			clock-frequency = <48000000>;
 			reg = <0x481a8000 0x2000>;
@@ -261,7 +278,7 @@
 		};
 
 		uart5: serial@481aa000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart6";
 			clock-frequency = <48000000>;
 			reg = <0x481aa000 0x2000>;
@@ -700,7 +717,7 @@
 		};
 
 		mac: ethernet@4a100000 {
-			compatible = "ti,cpsw";
+			compatible = "ti,am335x-cpsw","ti,cpsw";
 			ti,hwmods = "cpgmac0";
 			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
 			clock-names = "fck", "cpts";
@@ -762,14 +779,6 @@
 			reg = <0x40300000 0x10000>; /* 64k */
 		};
 
-		wkup_m3: wkup_m3@44d00000 {
-			compatible = "ti,am3353-wkup-m3";
-			reg = <0x44d00000 0x4000	/* M3 UMEM */
-			       0x44d80000 0x2000>;	/* M3 DMEM */
-			ti,hwmods = "wkup_m3";
-			ti,no-reset-on-init;
-		};
-
 		elm: elm@48080000 {
 			compatible = "ti,am3352-elm";
 			reg = <0x48080000 0x2000>;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index c80a3e233792..564900b9fcce 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -23,6 +23,11 @@
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
 		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+		serial4 = &uart4;
+		serial5 = &uart5;
 		ethernet0 = &cpsw_emac0;
 		ethernet1 = &cpsw_emac1;
 	};
@@ -59,6 +64,27 @@
 		interrupt-parent = <&gic>;
 	};
 
+	scu: scu@48240000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x48240000 0x100>;
+	};
+
+	global_timer: timer@48240200 {
+		compatible = "arm,cortex-a9-global-timer";
+		reg = <0x48240200 0x100>;
+		interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-parent = <&gic>;
+		clocks = <&dpll_mpu_m2_ck>;
+	};
+
+	local_timer: timer@48240600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x48240600 0x100>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-parent = <&gic>;
+		clocks = <&dpll_mpu_m2_ck>;
+	};
+
 	l2-cache-controller@48242000 {
 		compatible = "arm,pl310-cache";
 		reg = <0x48242000 0x1000>;
@@ -83,9 +109,19 @@
 			#size-cells = <1>;
 			ranges = <0 0x44c00000 0x287000>;
 
+			wkup_m3: wkup_m3@100000 {
+				compatible = "ti,am4372-wkup-m3";
+				reg = <0x100000 0x4000>,
+				      <0x180000	0x2000>;
+				reg-names = "umem", "dmem";
+				ti,hwmods = "wkup_m3";
+				ti,pm-firmware = "am335x-pm-firmware.elf";
+			};
+
 			prcm: prcm@1f0000 {
 				compatible = "ti,am4-prcm";
 				reg = <0x1f0000 0x11000>;
+				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
 
 				prcm_clocks: clocks {
 					#address-cells = <1>;
@@ -127,11 +163,25 @@
 					};
 				};
 
+				wkup_m3_ipc: wkup_m3_ipc@1324 {
+					compatible = "ti,am4372-wkup-m3-ipc";
+					reg = <0x1324 0x44>;
+					interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
+					ti,rproc = <&wkup_m3>;
+					mboxes = <&mailbox &mbox_wkupm3>;
+				};
+
 				scm_clockdomains: clockdomains {
 				};
 			};
 		};
 
+		emif: emif@4c000000 {
+			compatible = "ti,emif-am4372";
+			reg = <0x4c000000 0x1000000>;
+			ti,hwmods = "emif";
+		};
+
 		edma: edma@49000000 {
 			compatible = "ti,edma3";
 			ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
@@ -302,7 +352,8 @@
 		};
 
 		rtc: rtc@44e3e000 {
-			compatible = "ti,am4372-rtc","ti,da830-rtc";
+			compatible = "ti,am4372-rtc", "ti,am3352-rtc",
+				     "ti,da830-rtc";
 			reg = <0x44e3e000 0x1000>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH
 				      GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
@@ -521,8 +572,11 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ti,hwmods = "cpgmac0";
-			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
-			clock-names = "fck", "cpts";
+			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>,
+				 <&dpll_clksel_mac_clk>;
+			clock-names = "fck", "cpts", "50mclk";
+			assigned-clocks = <&dpll_clksel_mac_clk>;
+			assigned-clock-rates = <50000000>;
 			status = "disabled";
 			cpdma_channels = <8>;
 			ale_entries = <1024>;
@@ -859,7 +913,12 @@
 			usb1: usb@48390000 {
 				compatible = "synopsys,dwc3";
 				reg = <0x48390000 0x10000>;
-				interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				phys = <&usb2_phy1>;
 				phy-names = "usb2-phy";
 				maximum-speed = "high-speed";
@@ -883,7 +942,12 @@
 			usb2: usb@483d0000 {
 				compatible = "synopsys,dwc3";
 				reg = <0x483d0000 0x10000>;
-				interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				phys = <&usb2_phy2>;
 				phy-names = "usb2-phy";
 				maximum-speed = "high-speed";
@@ -941,6 +1005,7 @@
 				ti,hwmods = "dss_rfbi";
 				clocks = <&disp_clk>;
 				clock-names = "fck";
+				status = "disabled";
 			};
 		};
 
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index 84aa30c3235a..215775dc6948 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -21,12 +21,11 @@
 
 	aliases {
 		display0 = &lcd0;
-		serial3 = &uart3;
 	};
 
-	vmmcsd_fixed: fixedregulator-sd {
+	evm_v3_3d: fixedregulator-v3_3d {
 		compatible = "regulator-fixed";
-		regulator-name = "vmmcsd_fixed";
+		regulator-name = "evm_v3_3d";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 		enable-active-high;
@@ -83,17 +82,6 @@
 		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
 		label = "lcd";
 
-		pinctrl-names = "default";
-		pinctrl-0 = <&lcd_pins>;
-
-		/*
-		 * SelLCDorHDMI, LOW to select HDMI. This is not really the
-		 * panel's enable GPIO, but we don't have HDMI driver support nor
-		 * support to switch between two displays, so using this gpio as
-		 * panel's enable should be safe.
-		 */
-		enable-gpios = <&gpio5 8 GPIO_ACTIVE_HIGH>;
-
 		panel-timing {
 			clock-frequency = <33000000>;
 			hactive = <800>;
@@ -124,6 +112,32 @@
 		clock-frequency = <12000000>;
 	};
 
+	sound0: sound@0 {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "AM437x-GP-EVM";
+		simple-audio-card,widgets =
+			"Headphone", "Headphone Jack",
+			"Line", "Line In";
+		simple-audio-card,routing =
+			"Headphone Jack",	"HPLOUT",
+			"Headphone Jack",	"HPROUT",
+			"LINE1L",		"Line In",
+			"LINE1R",		"Line In";
+		simple-audio-card,format = "dsp_b";
+		simple-audio-card,bitclock-master = <&sound0_master>;
+		simple-audio-card,frame-master = <&sound0_master>;
+		simple-audio-card,bitclock-inversion;
+
+		simple-audio-card,cpu {
+			sound-dai = <&mcasp1>;
+			system-clock-frequency = <12000000>;
+		};
+
+		sound0_master: simple-audio-card,codec {
+			sound-dai = <&tlv320aic3106>;
+			system-clock-frequency = <12000000>;
+		};
+	};
 };
 
 &am43xx_pinmux {
@@ -217,7 +231,6 @@
 
 	nand_flash_x8: nand_flash_x8 {
 		pinctrl-single,pins = <
-			0x26c(PIN_OUTPUT_PULLDOWN | MUX_MODE7)	/* spi2_cs0.gpio/eMMCorNANDsel */
 			0x0  (PIN_INPUT  | MUX_MODE0)	/* gpmc_ad0.gpmc_ad0 */
 			0x4  (PIN_INPUT  | MUX_MODE0)	/* gpmc_ad1.gpmc_ad1 */
 			0x8  (PIN_INPUT  | MUX_MODE0)	/* gpmc_ad2.gpmc_ad2 */
@@ -270,7 +283,7 @@
 		>;
 	};
 
-	lcd_pins: lcd_pins {
+	display_mux_pins: display_mux_pins {
 		pinctrl-single,pins = <
 			/* GPIO 5_8 to select LCD / HDMI */
 			0x238 (PIN_OUTPUT_PULLUP | MUX_MODE7)
@@ -409,6 +422,60 @@
 			0x234 (PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* uart3_rtsn.uart3_rtsn */
 		>;
 	};
+
+	mcasp1_pins: mcasp1_pins {
+		pinctrl-single,pins = <
+			0x108 (PIN_OUTPUT_PULLDOWN | MUX_MODE4)	/* mii1_col.mcasp1_axr2 */
+			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE4)	/* mii1_crs.mcasp1_aclkx */
+			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE4)	/* mii1_rxerr.mcasp1_fsx */
+			0x144 (PIN_INPUT_PULLDOWN | MUX_MODE4)	/* rmii1_ref_clk.mcasp1_axr3 */
+		>;
+	};
+
+	mcasp1_sleep_pins: mcasp1_sleep_pins {
+		pinctrl-single,pins = <
+			0x108 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x144 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+		>;
+	};
+
+	gpio0_pins: gpio0_pins {
+		pinctrl-single,pins = <
+			0x26c (PIN_OUTPUT | MUX_MODE9) /* spi2_cs0.gpio0_23 SEL_eMMCorNANDn */
+		>;
+	};
+
+	emmc_pins_default: emmc_pins_default {
+		pinctrl-single,pins = <
+			0x00 (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad0.mmc1_dat0 */
+			0x04 (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad1.mmc1_dat1 */
+			0x08 (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad2.mmc1_dat2 */
+			0x0c (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad3.mmc1_dat3 */
+			0x10 (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad4.mmc1_dat4 */
+			0x14 (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad5.mmc1_dat5 */
+			0x18 (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad6.mmc1_dat6 */
+			0x1c (PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_ad7.mmc1_dat7 */
+			0x80 (PIN_INPUT_PULLUP | MUX_MODE2) /* gpmc_csn1.mmc1_clk */
+			0x84 (PIN_INPUT_PULLUP | MUX_MODE2) /* gpmc_csn2.mmc1_cmd */
+		>;
+	};
+
+	emmc_pins_sleep: emmc_pins_sleep {
+		pinctrl-single,pins = <
+			0x00 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad0.gpio1_0 */
+			0x04 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad1.gpio1_1 */
+			0x08 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad2.gpio1_2 */
+			0x0c (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad3.gpio1_3 */
+			0x10 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad4.gpio1_4 */
+			0x14 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad5.gpio1_5 */
+			0x18 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad6.gpio1_6 */
+			0x1c (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_ad7.gpio1_7 */
+			0x80 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_csn1.gpio1_30 */
+			0x84 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* gpmc_csn2.gpio1_31 */
+		>;
+	};
 };
 
 &i2c0 {
@@ -455,6 +522,8 @@
 			regulator-name = "v1_0bat";
 			regulator-min-microvolt = <1000000>;
 			regulator-max-microvolt = <1000000>;
+			regulator-boot-on;
+			regulator-always-on;
 		};
 
 		dcdc6: regulator-dcdc6 {
@@ -462,6 +531,8 @@
 			regulator-name = "v1_8bat";
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
+			regulator-boot-on;
+			regulator-always-on;
 		};
 
 		ldo1: regulator-ldo1 {
@@ -521,6 +592,19 @@
 			};
 		};
 	};
+
+	tlv320aic3106: tlv320aic3106@1b {
+		#sound-dai-cells = <0>;
+		compatible = "ti,tlv320aic3106";
+		reg = <0x1b>;
+		status = "okay";
+
+		/* Regulators */
+		IOVDD-supply = <&evm_v3_3d>; /* V3_3D -> <tps63031> EN: V1_8D -> VBAT */
+		AVDD-supply = <&evm_v3_3d>; /* v3_3AUD -> V3_3D -> ... */
+		DRVDD-supply = <&evm_v3_3d>; /* v3_3AUD -> V3_3D -> ... */
+		DVDD-supply = <&ldo1>; /* V1_8D -> LDO1 */
+	};
 };
 
 &epwmss0 {
@@ -542,7 +626,23 @@
 };
 
 &gpio0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&gpio0_pins>;
 	status = "okay";
+
+	p23 {
+		gpio-hog;
+		gpios = <23 GPIO_ACTIVE_HIGH>;
+		/* SelEMMCorNAND selects between eMMC and NAND:
+		 * Low: NAND
+		 * High: eMMC
+		 * When changing this line make sure the newly
+		 * selected device node is enabled and the previously
+		 * selected device node is disabled.
+		 */
+		output-low;
+		line-name = "SelEMMCorNAND";
+	};
 };
 
 &gpio1 {
@@ -558,19 +658,48 @@
 };
 
 &gpio5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&display_mux_pins>;
 	status = "okay";
 	ti,no-reset-on-init;
+
+	p8 {
+		/*
+		 * SelLCDorHDMI selects between display and audio paths:
+		 * Low: HDMI display with audio via HDMI
+		 * High: LCD display with analog audio via aic3111 codec
+		 */
+		gpio-hog;
+		gpios = <8 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "SelLCDorHDMI";
+	};
 };
 
 &mmc1 {
 	status = "okay";
-	vmmc-supply = <&vmmcsd_fixed>;
+	vmmc-supply = <&evm_v3_3d>;
 	bus-width = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins>;
 	cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
 };
 
+/* eMMC sits on mmc2 */
+&mmc2 {
+	/*
+	 * When enabling eMMC, disable GPMC/NAND and set
+	 * SelEMMCorNAND to output-high
+	 */
+	status = "disabled";
+	vmmc-supply = <&evm_v3_3d>;
+	bus-width = <8>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&emmc_pins_default>;
+	pinctrl-1 = <&emmc_pins_sleep>;
+	ti,non-removable;
+};
+
 &mmc3 {
 	status = "okay";
 	/* these are on the crossbar and are outlined in the
@@ -651,6 +780,10 @@
 };
 
 &gpmc {
+	/*
+	 * When enabling GPMC, disable eMMC and set
+	 * SelEMMCorNAND to output-low
+	 */
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&nand_flash_x8>;
@@ -790,3 +923,21 @@
 		};
 	};
 };
+
+&mcasp1 {
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&mcasp1_pins>;
+	pinctrl-1 = <&mcasp1_sleep_pins>;
+
+	status = "okay";
+
+	op-mode = <0>; /* MCASP_IIS_MODE */
+	tdm-slots = <2>;
+	/* 4 serializers */
+	serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
+		0 0 1 2
+	>;
+	tx-num-evt = <32>;
+	rx-num-evt = <32>;
+};
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index c17097d2c167..22af44894c66 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -32,14 +32,29 @@
 	};
 
 	sound {
-		compatible = "ti,da830-evm-audio";
-		ti,model = "AM437x-SK-EVM";
-		ti,audio-codec = <&tlv320aic3106>;
-		ti,mcasp-controller = <&mcasp1>;
-		ti,codec-clock-rate = <24000000>;
-		ti,audio-routing =
-			"Headphone Jack",       "HPLOUT",
-			"Headphone Jack",       "HPROUT";
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "AM437x-SK-EVM";
+		simple-audio-card,widgets =
+			"Headphone", "Headphone Jack",
+			"Line", "Line In";
+		simple-audio-card,routing =
+			"Headphone Jack",	"HPLOUT",
+			"Headphone Jack",	"HPROUT",
+			"LINE1L",		"Line In",
+			"LINE1R",		"Line In";
+		simple-audio-card,format = "dsp_b";
+		simple-audio-card,bitclock-master = <&sound_master>;
+		simple-audio-card,frame-master = <&sound_master>;
+		simple-audio-card,bitclock-inversion;
+
+		simple-audio-card,cpu {
+			sound-dai = <&mcasp1>;
+		};
+
+		sound_master: simple-audio-card,codec {
+			sound-dai = <&tlv320aic3106>;
+			system-clock-frequency = <24000000>;
+		};
 	};
 
 	matrix_keypad: matrix_keypad@0 {
@@ -364,6 +379,15 @@
 		>;
 	};
 
+	mcasp1_pins_sleep: mcasp1_pins_sleep {
+		pinctrl-single,pins = <
+			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x108 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			0x144 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+		>;
+	};
+
 	lcd_pins: lcd_pins {
 		pinctrl-single,pins = <
 			0x1c (PIN_OUTPUT_PULLDOWN | MUX_MODE7) /* gpcm_ad7.gpio1_7 */
@@ -480,6 +504,7 @@
 	};
 
 	tlv320aic3106: tlv320aic3106@1b {
+		#sound-dai-cells = <0>;
 		compatible = "ti,tlv320aic3106";
 		reg = <0x1b>;
 		status = "okay";
@@ -640,8 +665,10 @@
 };
 
 &mcasp1 {
-	pinctrl-names = "default";
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&mcasp1_pins>;
+	pinctrl-1 = <&mcasp1_pins_sleep>;
 
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 795d68af6df9..86c2dfbe8875 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -14,6 +14,7 @@
 #include <dt-bindings/pinctrl/am43xx.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/sound/tlv320aic31xx-micbias.h>
 
 / {
 	model = "TI AM43x EPOS EVM";
@@ -31,21 +32,18 @@
 		enable-active-high;
 	};
 
+	vbat: fixedregulator@0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vbat";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-boot-on;
+	};
+
 	lcd0: display {
 		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
 		label = "lcd";
 
-		pinctrl-names = "default";
-		pinctrl-0 = <&lcd_pins>;
-
-		/*
-		 * SelLCDorHDMI, LOW to select HDMI. This is not really the
-		 * panel's enable GPIO, but we don't have HDMI driver support nor
-		 * support to switch between two displays, so using this gpio as
-		 * panel's enable should be safe.
-		 */
-		enable-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
-
 		panel-timing {
 			clock-frequency = <33000000>;
 			hactive = <800>;
@@ -108,6 +106,38 @@
 		brightness-levels = <0 51 53 56 62 75 101 152 255>;
 		default-brightness-level = <8>;
 	};
+
+	sound0: sound@0 {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "AM43-EPOS-EVM";
+		simple-audio-card,widgets =
+			"Microphone", "Microphone Jack",
+			"Headphone", "Headphone Jack",
+			"Speaker", "Speaker";
+		simple-audio-card,routing =
+			"MIC1LP", "Microphone Jack",
+			"MIC1RP", "Microphone Jack",
+			"MIC1LP", "MICBIAS",
+			"MIC1RP", "MICBIAS",
+			"Headphone Jack", "HPL",
+			"Headphone Jack", "HPR",
+			"Speaker", "SPL",
+			"Speaker", "SPR";
+		simple-audio-card,format = "dsp_b";
+		simple-audio-card,bitclock-master = <&sound0_master>;
+		simple-audio-card,frame-master = <&sound0_master>;
+		simple-audio-card,bitclock-inversion;
+
+		simple-audio-card,cpu {
+			sound-dai = <&mcasp1>;
+			system-clock-frequency = <12000000>;
+		};
+
+		sound0_master: simple-audio-card,codec {
+			sound-dai = <&tlv320aic3111>;
+			system-clock-frequency = <12000000>;
+		};
+	};
 };
 
 &am43xx_pinmux {
@@ -278,7 +308,7 @@
 			>;
 		};
 
-		lcd_pins: lcd_pins {
+		display_mux_pins: display_mux_pins {
 			pinctrl-single,pins = <
 				/* GPMC CLK -> GPIO 2_1 to select LCD / HDMI */
 				0x08C (PIN_OUTPUT_PULLUP | MUX_MODE7)
@@ -320,6 +350,24 @@
 				0x204 (DS0_PULL_UP_DOWN_EN | INPUT_EN | MUX_MODE7)
 			>;
 		};
+
+		mcasp1_pins: mcasp1_pins {
+			pinctrl-single,pins = <
+				0x1a0 (PIN_INPUT_PULLDOWN | MUX_MODE3) /* MCASP0_ACLKR/MCASP1_ACLKX */
+				0x1a4 (PIN_INPUT_PULLDOWN | MUX_MODE3) /* MCASP0_FSR/MCASP1_FSX */
+				0x1a8 (PIN_OUTPUT_PULLDOWN | MUX_MODE3)/* MCASP0_AXR1/MCASP1_AXR0 */
+				0x1ac (PIN_INPUT_PULLDOWN | MUX_MODE3) /* MCASP0_AHCLKX/MCASP1_AXR1 */
+			>;
+		};
+
+		mcasp1_sleep_pins: mcasp1_sleep_pins {
+			pinctrl-single,pins = <
+				0x1a0 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x1a4 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x1a8 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x1ac (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			>;
+		};
 };
 
 &mmc1 {
@@ -399,6 +447,15 @@
 			regulator-always-on;
 		};
 
+		dcdc4: regulator-dcdc4 {
+			compatible = "ti,tps65218-dcdc4";
+			regulator-name = "vdcdc4";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-boot-on;
+			regulator-always-on;
+		};
+
 		dcdc5: regulator-dcdc5 {
 			compatible = "ti,tps65218-dcdc5";
 			regulator-name = "v1_0bat";
@@ -441,6 +498,23 @@
 		touchscreen-size-x = <1024>;
 		touchscreen-size-y = <600>;
 	};
+
+	tlv320aic3111: tlv320aic3111@18 {
+		#sound-dai-cells = <0>;
+		compatible = "ti,tlv320aic3111";
+		reg = <0x18>;
+		status = "okay";
+
+		ai31xx-micbias-vg = <MICBIAS_2_0V>;
+
+		/* Regulators */
+		HPVDD-supply = <&dcdc4>; /* v3_3AUD -> V3_3D -> DCDC4 */
+		SPRVDD-supply = <&vbat>; /* vbat */
+		SPLVDD-supply = <&vbat>; /* vbat */
+		AVDD-supply = <&dcdc4>; /* v3_3AUD -> V3_3D -> DCDC4 */
+		IOVDD-supply = <&dcdc4>; /* V3_3D -> DCDC4 */
+		DVDD-supply = <&ldo1>; /* V1_8AUD -> V1_8D -> LDO1 */
+	};
 };
 
 &i2c2 {
@@ -458,7 +532,21 @@
 };
 
 &gpio2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&display_mux_pins>;
 	status = "okay";
+
+	p1 {
+		/*
+		 * SelLCDorHDMI selects between display and audio paths:
+		 * Low: HDMI display with audio via HDMI
+		 * High: LCD display with analog audio via aic3111 codec
+		 */
+		gpio-hog;
+		gpios = <1 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "SelLCDorHDMI";
+	};
 };
 
 &gpio3 {
@@ -686,3 +774,21 @@
 		};
 	};
 };
+
+&mcasp1 {
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&mcasp1_pins>;
+	pinctrl-1 = <&mcasp1_sleep_pins>;
+
+	status = "okay";
+
+	op-mode = <0>;          /* MCASP_IIS_MODE */
+	tdm-slots = <2>;
+	/* 4 serializer */
+	serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
+		1 2 0 0
+	>;
+	tx-num-evt = <32>;
+	rx-num-evt = <32>;
+};
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index d0c0dfa4ec48..cc88728d751d 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -486,6 +486,15 @@
 		reg = <0x4238>;
 	};
 
+	dpll_clksel_mac_clk: dpll_clksel_mac_clk {
+		#clock-cells = <0>;
+		compatible = "ti,divider-clock";
+		clocks = <&dpll_core_m5_ck>;
+		reg = <0x4234>;
+		ti,bit-shift = <2>;
+		ti,dividers = <2>, <5>;
+	};
+
 	clk_32k_mosc_ck: clk_32k_mosc_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index a42cc377a862..3a05b94f59ed 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -580,7 +580,6 @@
 
 	vmmc-supply = <&ldo1_reg>;
 	vmmc_aux-supply = <&vdd_3v3>;
-	pbias-supply = <&pbias_mmc_reg>;
 	bus-width = <4>;
 	cd-gpios = <&gpio6 27 0>; /* gpio 219 */
 };
@@ -605,6 +604,10 @@
 	phy-supply = <&ldousb_reg>;
 };
 
+&usb2_phy2 {
+	phy-supply = <&ldousb_reg>;
+};
+
 &usb1 {
 	dr_mode = "host";
 	pinctrl-names = "default";
@@ -689,3 +692,7 @@
 		};
 	};
 };
+
+&pcie1 {
+	gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
+};
diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi
index 67a0ab0f71e0..e9a381741ce1 100644
--- a/arch/arm/boot/dts/armada-375.dtsi
+++ b/arch/arm/boot/dts/armada-375.dtsi
@@ -176,6 +176,10 @@
 				reg = <0x8000 0x1000>;
 				cache-unified;
 				cache-level = <2>;
+				arm,double-linefill-incr = <1>;
+				arm,double-linefill-wrap = <0>;
+				arm,double-linefill = <1>;
+				prefetch-data = <1>;
 			};
 
 			scu@c000 {
diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index fd4f6fd8a2e8..353c92532e7a 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -81,10 +81,6 @@
 				pinctrl-0 = <&i2c0_pins>;
 				status = "okay";
 				clock-frequency = <100000>;
-				/*
-				 * The EEPROM located at adresse 54 is needed
-				 * for the boot - DO NOT ERASE IT -
-				 */
 
 				expander0: pca9555@20 {
 					compatible = "nxp,pca9555";
@@ -111,6 +107,10 @@
 					reg = <0x21>;
 				};
 
+				eeprom@57 {
+					compatible = "atmel,24c64";
+					reg = <0x57>;
+				};
 			};
 
 			serial@12000 {
@@ -301,9 +301,11 @@
 	reg_sata0: pwr-sata0 {
 		compatible = "regulator-fixed";
 		regulator-name = "pwr_en_sata0";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
 		enable-active-high;
 		regulator-always-on;
-
+		gpio = <&expander0 2 GPIO_ACTIVE_HIGH>;
 	};
 
 	reg_5v_sata0: v5-sata0 {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 04ecfe6e2bc6..f9f2347d9995 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -143,6 +143,10 @@
 				reg = <0x8000 0x1000>;
 				cache-unified;
 				cache-level = <2>;
+				arm,double-linefill-incr = <1>;
+				arm,double-linefill-wrap = <0>;
+				arm,double-linefill = <1>;
+				prefetch-data = <1>;
 			};
 
 			scu@c000 {
@@ -450,7 +454,7 @@
 			};
 
 			xor@60800 {
-				compatible = "marvell,orion-xor";
+				compatible = "marvell,armada-380-xor", "marvell,orion-xor";
 				reg = <0x60800 0x100
 				       0x60a00 0x100>;
 				clocks = <&gateclk 22>;
@@ -470,7 +474,7 @@
 			};
 
 			xor@60900 {
-				compatible = "marvell,orion-xor";
+				compatible = "marvell,armada-380-xor", "marvell,orion-xor";
 				reg = <0x60900 0x100
 				       0x60b00 0x100>;
 				clocks = <&gateclk 28>;
diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi
index fc9864f85fc2..dc6efd386dbc 100644
--- a/arch/arm/boot/dts/armada-39x.dtsi
+++ b/arch/arm/boot/dts/armada-39x.dtsi
@@ -104,6 +104,10 @@
 				reg = <0x8000 0x1000>;
 				cache-unified;
 				cache-level = <2>;
+				arm,double-linefill-incr = <1>;
+				arm,double-linefill-wrap = <0>;
+				arm,double-linefill = <1>;
+				prefetch-data = <1>;
 			};
 
 			scu@c000 {
@@ -325,7 +329,7 @@
 			};
 
 			xor@60800 {
-				compatible = "marvell,orion-xor";
+				compatible = "marvell,armada-380-xor", "marvell,orion-xor";
 				reg = <0x60800 0x100
 				       0x60a00 0x100>;
 				clocks = <&gateclk 22>;
@@ -345,7 +349,7 @@
 			};
 
 			xor@60900 {
-				compatible = "marvell,orion-xor";
+				compatible = "marvell,armada-380-xor", "marvell,orion-xor";
 				reg = <0x60900 0x100
 				       0x60b00 0x100>;
 				clocks = <&gateclk 28>;
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
new file mode 100644
index 000000000000..e8d63afdb135
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -0,0 +1,134 @@
+/*
+ * at91-sama5d2_xplained.dts - Device Tree file for SAMA5D2 Xplained board
+ *
+ *  Copyright (C) 2015 Atmel,
+ *                2015 Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+#include "sama5d2.dtsi"
+
+/ {
+	model = "Atmel SAMA5D2 Xplained";
+	compatible = "atmel,sama5d2-xplained", "atmel,sama5d2", "atmel,sama5";
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		reg = <0x20000000 0x80000>;
+	};
+
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		main_clock: clock@0 {
+			compatible = "atmel,osc", "fixed-clock";
+			clock-frequency = <12000000>;
+		};
+
+		slow_xtal {
+			clock-frequency = <32768>;
+		};
+
+		main_xtal {
+			clock-frequency = <12000000>;
+		};
+	};
+
+	ahb {
+		usb0: gadget@00300000 {
+			status = "okay";
+		};
+
+		usb1: ohci@00400000 {
+			num-ports = <3>;
+			status = "okay";
+		};
+
+		usb2: ehci@00500000 {
+			status = "okay";
+		};
+
+		apb {
+			spi0: spi@f8000000 {
+				status = "okay";
+
+				m25p80@0 {
+					compatible = "atmel,at25df321a";
+					reg = <0>;
+					spi-max-frequency = <50000000>;
+				};
+			};
+
+			macb0: ethernet@f8008000 {
+				phy-mode = "rmii";
+				status = "okay";
+			};
+
+			uart1: serial@f8020000 {
+				status = "okay";
+			};
+
+			i2c0: i2c@f8028000 {
+				dmas = <0>, <0>;
+				status = "okay";
+			};
+
+			uart3: serial@fc008000 {
+				status = "okay";
+			};
+
+			i2c1: i2c@fc028000 {
+				dmas = <0>, <0>;
+				status = "okay";
+
+				at24@54 {
+					compatible = "atmel,24c02";
+					reg = <0x54>;
+					pagesize = <16>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 22ad7c959103..07f46963335b 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -131,6 +131,15 @@
 			};
 
 			adc0: adc@fc034000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <
+					/* external trigger conflicts with USBA_VBUS */
+					&pinctrl_adc0_ad0
+					&pinctrl_adc0_ad1
+					&pinctrl_adc0_ad2
+					&pinctrl_adc0_ad3
+					&pinctrl_adc0_ad4
+					>;
 				atmel,adc-vref = <3300>;
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index d782f2926b73..49a59c7e4a5d 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -100,6 +100,15 @@
 			};
 
 			adc0: adc@fc034000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <
+					/* external trigger conflicts with USBA_VBUS */
+					&pinctrl_adc0_ad0
+					&pinctrl_adc0_ad1
+					&pinctrl_adc0_ad2
+					&pinctrl_adc0_ad3
+					&pinctrl_adc0_ad4
+					>;
 				/* The vref depends on JP22 of EK. If connect 1-2 then use 3.3V. connect 2-3 use 3.0V */
 				atmel,adc-vref = <3300>;
 				/*atmel,adc-ts-wires = <4>;*/	/* Set up ADC touch screen */
diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index e3cfb9972f54..60edd8baebb8 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -359,6 +359,7 @@
 				compatible = "atmel,at91rm9200-st", "syscon", "simple-mfd";
 				reg = <0xfffffd00 0x100>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&slow_xtal>;
 
 				watchdog {
 					compatible = "atmel,at91rm9200-wdt";
@@ -369,6 +370,7 @@
 				compatible = "atmel,at91rm9200-rtc";
 				reg = <0xfffffe00 0x40>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&slow_xtal>;
 				status = "disabled";
 			};
 
@@ -378,8 +380,8 @@
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0
 					      18 IRQ_TYPE_LEVEL_HIGH 0
 					      19 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>, <&slow_xtal>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			tcb1: timer@fffa4000 {
@@ -388,8 +390,8 @@
 				interrupts = <20 IRQ_TYPE_LEVEL_HIGH 0
 					      21 IRQ_TYPE_LEVEL_HIGH 0
 					      22 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tc3_clk>, <&tc4_clk>, <&tc5_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tc3_clk>, <&tc4_clk>, <&tc5_clk>, <&slow_xtal>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			i2c0: i2c@fffb8000 {
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index 4bc347549102..be9c027ddd97 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -359,11 +359,13 @@
 			rstc@fffffd00 {
 				compatible = "atmel,at91sam9260-rstc";
 				reg = <0xfffffd00 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			shdwc@fffffd10 {
 				compatible = "atmel,at91sam9260-shdwc";
 				reg = <0xfffffd10 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fffffd30 {
@@ -379,8 +381,8 @@
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0
 					      18 IRQ_TYPE_LEVEL_HIGH 0
 					      19 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>, <&clk32k>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			tcb1: timer@fffdc000 {
@@ -389,8 +391,8 @@
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 0
 					      27 IRQ_TYPE_LEVEL_HIGH 0
 					      28 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tc3_clk>, <&tc4_clk>, <&tc5_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tc3_clk>, <&tc4_clk>, <&tc5_clk>, <&clk32k>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			pinctrl@fffff400 {
@@ -973,6 +975,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffd40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index b2c44a07a3d0..ce1e3e94a40c 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -119,8 +119,8 @@
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>,
 					     <18 IRQ_TYPE_LEVEL_HIGH 0>,
 					     <19 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>, <&slow_xtal>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			usb1: gadget@fffa4000 {
@@ -820,11 +820,13 @@
 			rstc@fffffd00 {
 				compatible = "atmel,at91sam9260-rstc";
 				reg = <0xfffffd00 0x10>;
+				clocks = <&slow_xtal>;
 			};
 
 			shdwc@fffffd10 {
 				compatible = "atmel,at91sam9260-shdwc";
 				reg = <0xfffffd10 0x10>;
+				clocks = <&slow_xtal>;
 			};
 
 			pit: timer@fffffd30 {
@@ -846,6 +848,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffd40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&slow_xtal>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index e36d966ef5e8..f1f5fa3a9e6e 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -377,18 +377,20 @@
 				compatible = "atmel,at91rm9200-tcb";
 				reg = <0xfff7c000 0x100>;
 				interrupts = <19 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb_clk>, <&slow_xtal>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			rstc@fffffd00 {
 				compatible = "atmel,at91sam9260-rstc";
 				reg = <0xfffffd00 0x10>;
+				clocks = <&slow_xtal>;
 			};
 
 			shdwc@fffffd10 {
 				compatible = "atmel,at91sam9260-shdwc";
 				reg = <0xfffffd10 0x10>;
+				clocks = <&slow_xtal>;
 			};
 
 			pinctrl@fffff200 {
@@ -902,6 +904,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffd40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&slow_xtal>;
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
diff --git a/arch/arm/boot/dts/at91sam9g15.dtsi b/arch/arm/boot/dts/at91sam9g15.dtsi
index cfd7044616d7..27de7dc0f0e0 100644
--- a/arch/arm/boot/dts/at91sam9g15.dtsi
+++ b/arch/arm/boot/dts/at91sam9g15.dtsi
@@ -7,6 +7,7 @@
  */
 
 #include "at91sam9x5.dtsi"
+#include "at91sam9x5_lcd.dtsi"
 
 / {
 	model = "Atmel AT91SAM9G15 SoC";
diff --git a/arch/arm/boot/dts/at91sam9g15ek.dts b/arch/arm/boot/dts/at91sam9g15ek.dts
index 26b0444b0f96..d1d2b400f1c6 100644
--- a/arch/arm/boot/dts/at91sam9g15ek.dts
+++ b/arch/arm/boot/dts/at91sam9g15ek.dts
@@ -8,9 +8,34 @@
  */
 /dts-v1/;
 #include "at91sam9g15.dtsi"
+#include "at91sam9x5dm.dtsi"
 #include "at91sam9x5ek.dtsi"
 
 / {
 	model = "Atmel AT91SAM9G15-EK";
 	compatible = "atmel,at91sam9g15ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9";
+
+	ahb {
+		apb {
+			hlcdc: hlcdc@f8038000 {
+				status = "okay";
+			};
+		};
+	};
+
+	backlight: backlight {
+		status = "okay";
+	};
+
+	bl_reg: backlight_regulator {
+		status = "okay";
+	};
+
+	panel: panel {
+		status = "okay";
+	};
+
+	panel_reg: panel_regulator {
+		status = "okay";
+	};
 };
diff --git a/arch/arm/boot/dts/at91sam9g35.dtsi b/arch/arm/boot/dts/at91sam9g35.dtsi
index e35c2fcf8298..ff4115886f97 100644
--- a/arch/arm/boot/dts/at91sam9g35.dtsi
+++ b/arch/arm/boot/dts/at91sam9g35.dtsi
@@ -7,6 +7,7 @@
  */
 
 #include "at91sam9x5.dtsi"
+#include "at91sam9x5_lcd.dtsi"
 #include "at91sam9x5_macb0.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/at91sam9g35ek.dts b/arch/arm/boot/dts/at91sam9g35ek.dts
index 641a9bf89ed1..23ec8b13f30a 100644
--- a/arch/arm/boot/dts/at91sam9g35ek.dts
+++ b/arch/arm/boot/dts/at91sam9g35ek.dts
@@ -8,6 +8,7 @@
  */
 /dts-v1/;
 #include "at91sam9g35.dtsi"
+#include "at91sam9x5dm.dtsi"
 #include "at91sam9x5ek.dtsi"
 
 / {
@@ -20,6 +21,26 @@
 				phy-mode = "rmii";
 				status = "okay";
 			};
+
+			hlcdc: hlcdc@f8038000 {
+				status = "okay";
+			};
 		};
 	};
+
+	backlight: backlight {
+		status = "okay";
+	};
+
+	bl_reg: backlight_regulator {
+		status = "okay";
+	};
+
+	panel: panel {
+		status = "okay";
+	};
+
+	panel_reg: panel_regulator {
+		status = "okay";
+	};
 };
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 18177f5a7464..18b8b9e29704 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -387,6 +387,7 @@
 			rstc@fffffd00 {
 				compatible = "atmel,at91sam9g45-rstc";
 				reg = <0xfffffd00 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fffffd30 {
@@ -400,22 +401,23 @@
 			shdwc@fffffd10 {
 				compatible = "atmel,at91sam9rl-shdwc";
 				reg = <0xfffffd10 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			tcb0: timer@fff7c000 {
 				compatible = "atmel,at91rm9200-tcb";
 				reg = <0xfff7c000 0x100>;
 				interrupts = <18 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb0_clk>, <&tcb0_clk>, <&tcb0_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tcb0_clk>, <&tcb0_clk>, <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			tcb1: timer@fffd4000 {
 				compatible = "atmel,at91rm9200-tcb";
 				reg = <0xfffd4000 0x100>;
 				interrupts = <18 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb0_clk>, <&tcb0_clk>, <&tcb0_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tcb0_clk>, <&tcb0_clk>, <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			dma: dma-controller@ffffec00 {
@@ -498,23 +500,31 @@
 				};
 
 				isi {
-					pinctrl_isi: isi-0 {
-						atmel,pins = <AT91_PIOB 8 AT91_PERIPH_B AT91_PINCTRL_NONE /* D8 */
-							      AT91_PIOB 9 AT91_PERIPH_B AT91_PINCTRL_NONE /* D9 */
-							      AT91_PIOB 10 AT91_PERIPH_B AT91_PINCTRL_NONE /* D10 */
-							      AT91_PIOB 11 AT91_PERIPH_B AT91_PINCTRL_NONE /* D11 */
-							      AT91_PIOB 20 AT91_PERIPH_A AT91_PINCTRL_NONE /* D0 */
-							      AT91_PIOB 21 AT91_PERIPH_A AT91_PINCTRL_NONE /* D1 */
-							      AT91_PIOB 22 AT91_PERIPH_A AT91_PINCTRL_NONE /* D2 */
-							      AT91_PIOB 23 AT91_PERIPH_A AT91_PINCTRL_NONE /* D3 */
-							      AT91_PIOB 24 AT91_PERIPH_A AT91_PINCTRL_NONE /* D4 */
-							      AT91_PIOB 25 AT91_PERIPH_A AT91_PINCTRL_NONE /* D5 */
-							      AT91_PIOB 26 AT91_PERIPH_A AT91_PINCTRL_NONE /* D6 */
-							      AT91_PIOB 27 AT91_PERIPH_A AT91_PINCTRL_NONE /* D7 */
-							      AT91_PIOB 28 AT91_PERIPH_A AT91_PINCTRL_NONE /* PCK */
-							      AT91_PIOB 29 AT91_PERIPH_A AT91_PINCTRL_NONE /* VSYNC */
-							      AT91_PIOB 30 AT91_PERIPH_A AT91_PINCTRL_NONE /* HSYNC */
-							      AT91_PIOB 31 AT91_PERIPH_A AT91_PINCTRL_NONE /* MCK */>;
+					pinctrl_isi_data_0_7: isi-0-data-0-7 {
+						atmel,pins =
+							<AT91_PIOB 20 AT91_PERIPH_A AT91_PINCTRL_NONE /* D0 */
+							AT91_PIOB 21 AT91_PERIPH_A AT91_PINCTRL_NONE /* D1 */
+							AT91_PIOB 22 AT91_PERIPH_A AT91_PINCTRL_NONE /* D2 */
+							AT91_PIOB 23 AT91_PERIPH_A AT91_PINCTRL_NONE /* D3 */
+							AT91_PIOB 24 AT91_PERIPH_A AT91_PINCTRL_NONE /* D4 */
+							AT91_PIOB 25 AT91_PERIPH_A AT91_PINCTRL_NONE /* D5 */
+							AT91_PIOB 26 AT91_PERIPH_A AT91_PINCTRL_NONE /* D6 */
+							AT91_PIOB 27 AT91_PERIPH_A AT91_PINCTRL_NONE /* D7 */
+							AT91_PIOB 28 AT91_PERIPH_A AT91_PINCTRL_NONE /* PCK */
+							AT91_PIOB 29 AT91_PERIPH_A AT91_PINCTRL_NONE /* VSYNC */
+							AT91_PIOB 30 AT91_PERIPH_A AT91_PINCTRL_NONE>; /* HSYNC */
+					};
+
+					pinctrl_isi_data_8_9: isi-0-data-8-9 {
+						atmel,pins =
+							<AT91_PIOB 8 AT91_PERIPH_B AT91_PINCTRL_NONE /* D8 */
+							AT91_PIOB 9 AT91_PERIPH_B AT91_PINCTRL_NONE>; /* D9 */
+					};
+
+					pinctrl_isi_data_10_11: isi-0-data-10-11 {
+						atmel,pins =
+							<AT91_PIOB 10 AT91_PERIPH_B AT91_PINCTRL_NONE /* D10 */
+							AT91_PIOB 11 AT91_PERIPH_B AT91_PINCTRL_NONE>; /* D11 */
 					};
 				};
 
@@ -1067,9 +1077,11 @@
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 5>;
 				clocks = <&isi_clk>;
 				clock-names = "isi_clk";
-				pinctrl-names = "default";
-				pinctrl-0 = <&pinctrl_isi>;
 				status = "disabled";
+				port {
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
 			};
 
 			pwm0: pwm@fffb8000 {
@@ -1113,6 +1125,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffd40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
@@ -1247,6 +1260,7 @@
 				compatible = "atmel,at91rm9200-rtc";
 				reg = <0xfffffdb0 0x30>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index 1375d3362603..d1ae60a855d4 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -63,6 +63,25 @@
 
 			i2c0: i2c@fff84000 {
 				status = "okay";
+				ov2640: camera@30 {
+					compatible = "ovti,ov2640";
+					reg = <0x30>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_pck1_as_isi_mck &pinctrl_sensor_power &pinctrl_sensor_reset>;
+					resetb-gpios = <&pioD 12 GPIO_ACTIVE_LOW>;
+					pwdn-gpios = <&pioD 13 GPIO_ACTIVE_HIGH>;
+					clocks = <&pck1>;
+					clock-names = "xvclk";
+					assigned-clocks = <&pck1>;
+					assigned-clock-rates = <25000000>;
+
+					port {
+						ov2640_0: endpoint {
+							remote-endpoint = <&isi_0>;
+							bus-width = <8>;
+						};
+					};
+				};
 			};
 
 			i2c1: i2c@fff88000 {
@@ -101,6 +120,22 @@
 			};
 
 			pinctrl@fffff200 {
+				camera_sensor {
+					pinctrl_pck1_as_isi_mck: pck1_as_isi_mck-0 {
+						atmel,pins =
+							<AT91_PIOB 31 AT91_PERIPH_B AT91_PINCTRL_NONE>;
+					};
+
+					pinctrl_sensor_reset: sensor_reset-0 {
+						atmel,pins =
+							<AT91_PIOD 12 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>;
+					};
+
+					pinctrl_sensor_power: sensor_power-0 {
+						atmel,pins =
+							<AT91_PIOD 13 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>;
+					};
+				};
 				mmc0 {
 					pinctrl_board_mmc0: mmc0-board {
 						atmel,pins =
@@ -155,6 +190,18 @@
 				status = "okay";
 			};
 
+			isi@fffb4000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_isi_data_0_7>;
+				status = "okay";
+				port {
+					isi_0: endpoint {
+						remote-endpoint = <&ov2640_0>;
+						bus-width = <8>;
+					};
+				};
+			};
+
 			pwm0: pwm@fffb8000 {
 				status = "okay";
 
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 5c2a8c8c8bd4..32bc9a189db0 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -376,6 +376,7 @@
 			rstc@fffffe00 {
 				compatible = "atmel,at91sam9g45-rstc";
 				reg = <0xfffffe00 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fffffe30 {
@@ -388,6 +389,7 @@
 			shdwc@fffffe10 {
 				compatible = "atmel,at91sam9x5-shdwc";
 				reg = <0xfffffe10 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			sckc@fffffe50 {
@@ -431,16 +433,44 @@
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf8008000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			tcb1: timer@f800c000 {
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf800c000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
+			};
+
+			hlcdc: hlcdc@f8038000 {
+				compatible = "atmel,at91sam9n12-hlcdc";
+				reg = <0xf8038000 0x2000>;
+				interrupts = <25 IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&lcdc_clk>, <&lcdck>, <&clk32k>;
+				clock-names = "periph_clk", "sys_clk", "slow_clk";
+				status = "disabled";
+
+				hlcdc-display-controller {
+					compatible = "atmel,hlcdc-display-controller";
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						#address-cells = <1>;
+						#size-cells = <0>;
+						reg = <0>;
+					};
+				};
+
+				hlcdc_pwm: hlcdc-pwm {
+					compatible = "atmel,hlcdc-pwm";
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_lcd_pwm>;
+					#pwm-cells = <3>;
+				};
 			};
 
 			dma: dma-controller@ffffec00 {
@@ -475,6 +505,49 @@
 					};
 				};
 
+				lcd {
+					pinctrl_lcd_base: lcd-base-0 {
+						atmel,pins =
+							<AT91_PIOC 27 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDVSYNC */
+							 AT91_PIOC 28 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDHSYNC */
+							 AT91_PIOC 24 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDDISP */
+							 AT91_PIOC 29 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDDEN */
+							 AT91_PIOC 30 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDPCK */
+					};
+
+					pinctrl_lcd_pwm: lcd-pwm-0 {
+						atmel,pins = <AT91_PIOC 26 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDPWM */
+					};
+
+					pinctrl_lcd_rgb888: lcd-rgb-3 {
+						atmel,pins =
+							<AT91_PIOC 0 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD0 pin */
+							 AT91_PIOC 1 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD1 pin */
+							 AT91_PIOC 2 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD2 pin */
+							 AT91_PIOC 3 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD3 pin */
+							 AT91_PIOC 4 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD4 pin */
+							 AT91_PIOC 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD5 pin */
+							 AT91_PIOC 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD6 pin */
+							 AT91_PIOC 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD7 pin */
+							 AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD8 pin */
+							 AT91_PIOC 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD9 pin */
+							 AT91_PIOC 10 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD10 pin */
+							 AT91_PIOC 11 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD11 pin */
+							 AT91_PIOC 12 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD12 pin */
+							 AT91_PIOC 13 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD13 pin */
+							 AT91_PIOC 14 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD14 pin */
+							 AT91_PIOC 15 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD15 pin */
+							 AT91_PIOC 16 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD16 pin */
+							 AT91_PIOC 17 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD17 pin */
+							 AT91_PIOC 18 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD18 pin */
+							 AT91_PIOC 19 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD19 pin */
+							 AT91_PIOC 20 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD20 pin */
+							 AT91_PIOC 21 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD21 pin */
+							 AT91_PIOC 22 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD22 pin */
+							 AT91_PIOC 23 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDD23 pin */
+					};
+				};
+
 				usart0 {
 					pinctrl_usart0: usart0-0 {
 						atmel,pins =
@@ -891,6 +964,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffe40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
@@ -901,6 +975,7 @@
 				compatible = "atmel,at91rm9200-rtc";
 				reg = <0xfffffeb0 0x40>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index eab17fcace6d..efa75064d38a 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -128,6 +128,22 @@
 				};
 			};
 
+			hlcdc: hlcdc@f8038000 {
+				status = "okay";
+
+				hlcdc-display-controller {
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_lcd_base &pinctrl_lcd_rgb888>;
+
+					port@0 {
+						hlcdc_panel_output: endpoint@0 {
+							reg = <0>;
+							remote-endpoint = <&panel_input>;
+						};
+					};
+				};
+			};
+
 			usb1: gadget@f803c000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_usb1_vbus_sense>;
@@ -161,6 +177,23 @@
 		};
 	};
 
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&hlcdc_pwm 0 50000 0>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+		power-supply = <&bl_reg>;
+		status = "okay";
+	};
+
+	bl_reg: backlight_regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "backlight-power-supply";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		status = "okay";
+	};
+
 	leds {
 		compatible = "gpio-leds";
 
@@ -194,6 +227,34 @@
 		};
 	};
 
+	panel: panel {
+		compatible = "qd,qd43003c0-40", "simple-panel";
+		backlight = <&backlight>;
+		power-supply = <&panel_reg>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "okay";
+
+		port@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			panel_input: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&hlcdc_panel_output>;
+			};
+		};
+	};
+
+	panel_reg: panel_regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "panel-power-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		status = "okay";
+	};
+
 	sound {
 		compatible = "atmel,asoc-wm8904";
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/at91sam9rl.dtsi b/arch/arm/boot/dts/at91sam9rl.dtsi
index c9920c64791c..a0b90aedd3b8 100644
--- a/arch/arm/boot/dts/at91sam9rl.dtsi
+++ b/arch/arm/boot/dts/at91sam9rl.dtsi
@@ -121,8 +121,8 @@
 				interrupts = <16 IRQ_TYPE_LEVEL_HIGH 0>,
 					     <17 IRQ_TYPE_LEVEL_HIGH 0>,
 					     <18 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>;
-				clock-names = "t0_clk", "t1_clk", "t2_clk";
+				clocks = <&tc0_clk>, <&tc1_clk>, <&tc2_clk>, <&clk32k>;
+				clock-names = "t0_clk", "t1_clk", "t2_clk", "slow_clk";
 			};
 
 			mmc0: mmc@fffa4000 {
@@ -1018,11 +1018,13 @@
 			rstc@fffffd00 {
 				compatible = "atmel,at91sam9260-rstc";
 				reg = <0xfffffd00 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			shdwc@fffffd10 {
 				compatible = "atmel,at91sam9260-shdwc";
 				reg = <0xfffffd10 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fffffd30 {
@@ -1036,6 +1038,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffd40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				status = "disabled";
 			};
 
@@ -1083,6 +1086,7 @@
 				compatible = "atmel,at91rm9200-rtc";
 				reg = <0xfffffe00 0x40>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9x35.dtsi b/arch/arm/boot/dts/at91sam9x35.dtsi
index 499cdc81f4c0..d9054e8167b7 100644
--- a/arch/arm/boot/dts/at91sam9x35.dtsi
+++ b/arch/arm/boot/dts/at91sam9x35.dtsi
@@ -7,6 +7,7 @@
  */
 
 #include "at91sam9x5.dtsi"
+#include "at91sam9x5_lcd.dtsi"
 #include "at91sam9x5_macb0.dtsi"
 #include "at91sam9x5_can.dtsi"
 
diff --git a/arch/arm/boot/dts/at91sam9x35ek.dts b/arch/arm/boot/dts/at91sam9x35ek.dts
index 343d32818ca3..fcb67180ea26 100644
--- a/arch/arm/boot/dts/at91sam9x35ek.dts
+++ b/arch/arm/boot/dts/at91sam9x35ek.dts
@@ -8,6 +8,7 @@
  */
 /dts-v1/;
 #include "at91sam9x35.dtsi"
+#include "at91sam9x5dm.dtsi"
 #include "at91sam9x5ek.dtsi"
 
 / {
@@ -20,6 +21,25 @@
 				phy-mode = "rmii";
 				status = "okay";
 			};
+			hlcdc: hlcdc@f8038000 {
+				status = "okay";
+			};
 		};
 	};
+
+	backlight: backlight {
+		status = "okay";
+	};
+
+	bl_reg: backlight_regulator {
+		status = "okay";
+	};
+
+	panel: panel {
+		status = "okay";
+	};
+
+	panel_reg: panel_regulator {
+		status = "okay";
+	};
 };
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index b6c8df8d380e..747d8f070a5c 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -376,11 +376,13 @@
 			rstc@fffffe00 {
 				compatible = "atmel,at91sam9g45-rstc";
 				reg = <0xfffffe00 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			shdwc@fffffe10 {
 				compatible = "atmel,at91sam9x5-shdwc";
 				reg = <0xfffffe10 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fffffe30 {
@@ -418,16 +420,16 @@
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf8008000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb0_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			tcb1: timer@f800c000 {
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf800c000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb0_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			dma0: dma-controller@ffffec00 {
@@ -1173,6 +1175,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffe40 0x10>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
@@ -1183,6 +1186,7 @@
 				compatible = "atmel,at91sam9x5-rtc";
 				reg = <0xfffffeb0 0x40>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9x5_lcd.dtsi b/arch/arm/boot/dts/at91sam9x5_lcd.dtsi
index 485302e8233d..1629db9dd563 100644
--- a/arch/arm/boot/dts/at91sam9x5_lcd.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5_lcd.dtsi
@@ -13,6 +13,137 @@
 / {
 	ahb {
 		apb {
+			hlcdc: hlcdc@f8038000 {
+				compatible = "atmel,at91sam9x5-hlcdc";
+				reg = <0xf8038000 0x4000>;
+				interrupts = <25 IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&lcdc_clk>, <&lcdck>, <&clk32k>;
+				clock-names = "periph_clk","sys_clk", "slow_clk";
+				status = "disabled";
+
+				hlcdc-display-controller {
+					compatible = "atmel,hlcdc-display-controller";
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						#address-cells = <1>;
+						#size-cells = <0>;
+						reg = <0>;
+					};
+				};
+
+				hlcdc_pwm: hlcdc-pwm {
+					compatible = "atmel,hlcdc-pwm";
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_lcd_pwm>;
+					#pwm-cells = <3>;
+				};
+			};
+
+			pinctrl@fffff400 {
+				lcd {
+					pinctrl_lcd_base: lcd-base-0 {
+						atmel,pins =
+							<AT91_PIOC 27 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDVSYNC */
+							 AT91_PIOC 28 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDHSYNC */
+							 AT91_PIOC 24 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDDISP */
+							 AT91_PIOC 29 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDDEN */
+							 AT91_PIOC 30 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDPCK */
+					};
+
+					pinctrl_lcd_pwm: lcd-pwm-0 {
+						atmel,pins = <AT91_PIOC 26 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDPWM */
+					};
+
+					pinctrl_lcd_rgb444: lcd-rgb-0 {
+						atmel,pins =
+							<AT91_PIOC 0 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD0 pin */
+							 AT91_PIOC 1 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD1 pin */
+							 AT91_PIOC 2 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD2 pin */
+							 AT91_PIOC 3 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD3 pin */
+							 AT91_PIOC 4 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD4 pin */
+							 AT91_PIOC 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD5 pin */
+							 AT91_PIOC 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD6 pin */
+							 AT91_PIOC 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD7 pin */
+							 AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD8 pin */
+							 AT91_PIOC 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD9 pin */
+							 AT91_PIOC 10 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD10 pin */
+							 AT91_PIOC 11 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDD11 pin */
+					};
+
+					pinctrl_lcd_rgb565: lcd-rgb-1 {
+						atmel,pins =
+							<AT91_PIOC 0 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD0 pin */
+							 AT91_PIOC 1 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD1 pin */
+							 AT91_PIOC 2 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD2 pin */
+							 AT91_PIOC 3 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD3 pin */
+							 AT91_PIOC 4 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD4 pin */
+							 AT91_PIOC 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD5 pin */
+							 AT91_PIOC 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD6 pin */
+							 AT91_PIOC 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD7 pin */
+							 AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD8 pin */
+							 AT91_PIOC 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD9 pin */
+							 AT91_PIOC 10 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD10 pin */
+							 AT91_PIOC 11 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD11 pin */
+							 AT91_PIOC 12 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD12 pin */
+							 AT91_PIOC 13 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD13 pin */
+							 AT91_PIOC 14 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD14 pin */
+							 AT91_PIOC 15 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDD15 pin */
+					};
+
+					pinctrl_lcd_rgb666: lcd-rgb-2 {
+						atmel,pins =
+							<AT91_PIOC 0 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD0 pin */
+							 AT91_PIOC 1 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD1 pin */
+							 AT91_PIOC 2 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD2 pin */
+							 AT91_PIOC 3 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD3 pin */
+							 AT91_PIOC 4 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD4 pin */
+							 AT91_PIOC 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD5 pin */
+							 AT91_PIOC 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD6 pin */
+							 AT91_PIOC 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD7 pin */
+							 AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD8 pin */
+							 AT91_PIOC 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD9 pin */
+							 AT91_PIOC 10 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD10 pin */
+							 AT91_PIOC 11 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD11 pin */
+							 AT91_PIOC 12 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD12 pin */
+							 AT91_PIOC 13 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD13 pin */
+							 AT91_PIOC 14 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD14 pin */
+							 AT91_PIOC 15 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD15 pin */
+							 AT91_PIOC 16 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD16 pin */
+							 AT91_PIOC 17 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDD17 pin */
+					};
+
+					pinctrl_lcd_rgb888: lcd-rgb-3 {
+						atmel,pins =
+							<AT91_PIOC 0 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD0 pin */
+							 AT91_PIOC 1 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD1 pin */
+							 AT91_PIOC 2 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD2 pin */
+							 AT91_PIOC 3 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD3 pin */
+							 AT91_PIOC 4 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD4 pin */
+							 AT91_PIOC 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD5 pin */
+							 AT91_PIOC 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD6 pin */
+							 AT91_PIOC 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD7 pin */
+							 AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD8 pin */
+							 AT91_PIOC 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD9 pin */
+							 AT91_PIOC 10 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD10 pin */
+							 AT91_PIOC 11 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD11 pin */
+							 AT91_PIOC 12 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD12 pin */
+							 AT91_PIOC 13 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD13 pin */
+							 AT91_PIOC 14 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD14 pin */
+							 AT91_PIOC 15 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD15 pin */
+							 AT91_PIOC 16 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD16 pin */
+							 AT91_PIOC 17 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD17 pin */
+							 AT91_PIOC 18 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD18 pin */
+							 AT91_PIOC 19 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD19 pin */
+							 AT91_PIOC 20 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD20 pin */
+							 AT91_PIOC 21 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD21 pin */
+							 AT91_PIOC 22 AT91_PERIPH_A AT91_PINCTRL_NONE	/* LCDD22 pin */
+							 AT91_PIOC 23 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* LCDD23 pin */
+					};
+				};
+			};
+
 			pmc: pmc@fffffc00 {
 				periphck {
 					lcdc_clk: lcdc_clk {
@@ -20,6 +151,14 @@
 						reg = <25>;
 					};
 				};
+
+				systemck {
+					lcdck: lcdck {
+						#clock-cells = <0>;
+						reg = <3>;
+						clocks = <&mck>;
+					};
+				};
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/at91sam9x5dm.dtsi b/arch/arm/boot/dts/at91sam9x5dm.dtsi
new file mode 100644
index 000000000000..34c089fe0bc0
--- /dev/null
+++ b/arch/arm/boot/dts/at91sam9x5dm.dtsi
@@ -0,0 +1,101 @@
+/*
+ * at91sam9x5dm.dtsi - Device Tree file for SAM9x5 display module
+ *
+ *  Copyright (C) 2014 Atmel,
+ *                2014 Free Electrons
+ *
+ *  Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+
+/ {
+	ahb {
+		apb {
+			i2c0: i2c@f8010000 {
+				qt1070: keyboard@1b {
+					compatible = "qt1070";
+					reg = <0x1b>;
+					interrupt-parent = <&pioA>;
+					interrupts = <7 0x0>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_qt1070_irq>;
+					wakeup-source;
+				};
+			};
+
+			hlcdc: hlcdc@f8038000 {
+				hlcdc-display-controller {
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_lcd_base &pinctrl_lcd_rgb888>;
+
+					port@0 {
+						hlcdc_panel_output: endpoint@0 {
+							reg = <0>;
+							remote-endpoint = <&panel_input>;
+						};
+					};
+				};
+			};
+
+			adc0: adc@f804c000 {
+				atmel,adc-ts-wires = <4>;
+				atmel,adc-ts-pressure-threshold = <10000>;
+				status = "okay";
+			};
+
+			pinctrl@fffff400 {
+				board {
+					pinctrl_qt1070_irq: qt1070_irq {
+						atmel,pins =
+							<AT91_PIOA 7 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+				};
+			};
+		};
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&hlcdc_pwm 0 50000 0>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+		power-supply = <&bl_reg>;
+		status = "disabled";
+	};
+
+	bl_reg: backlight_regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "backlight-power-supply";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		status = "disabled";
+	};
+
+	panel: panel {
+		compatible = "foxlink,fl500wvr00-a0t", "simple-panel";
+		backlight = <&backlight>;
+		power-supply = <&panel_reg>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			panel_input: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&hlcdc_panel_output>;
+			};
+		};
+	};
+
+	panel_reg: panel_regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "panel-power-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		status = "disabled";
+	};
+};
diff --git a/arch/arm/boot/dts/atlas7-evb.dts b/arch/arm/boot/dts/atlas7-evb.dts
index 49cf59a95572..1e9cd1a8508e 100644
--- a/arch/arm/boot/dts/atlas7-evb.dts
+++ b/arch/arm/boot/dts/atlas7-evb.dts
@@ -10,6 +10,9 @@
 
 /include/ "atlas7.dtsi"
 
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/gpio/gpio.h>
+
 / {
 	model = "CSR SiRFatlas7 Evaluation Board";
 	compatible = "sirf,atlas7-cb", "sirf,atlas7";
@@ -106,5 +109,20 @@
 				};
 			};
 		};
+
+		gpio_keys {
+			compatible = "gpio-keys";
+			status = "okay";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			rearview_key {
+				label = "rearview key";
+				linux,code = <KEY_CAMERA>;
+				gpios = <&gpio_1 3 GPIO_ACTIVE_LOW>;
+				debounce_interval = <100>;
+			};
+		};
+
 	};
 };
diff --git a/arch/arm/boot/dts/atlas7.dtsi b/arch/arm/boot/dts/atlas7.dtsi
index 5dfd3a44bf82..83449b33de6b 100644
--- a/arch/arm/boot/dts/atlas7.dtsi
+++ b/arch/arm/boot/dts/atlas7.dtsi
@@ -21,6 +21,10 @@
 		serial5 = &uart5;
 		serial6 = &uart6;
 		serial9 = &usp2;
+		spi1 = &spi1;
+		spi2 = &usp1;
+		spi3 = &usp2;
+		spi4 = &usp3;
 	};
 	cpus {
 		#address-cells = <1>;
@@ -53,6 +57,11 @@
 		};
 	};
 
+	arm-pmu {
+		compatible = "arm,cortex-a7-pmu";
+		interrupts = <0 29 4>, <0 82 4>;
+	};
+
 	noc {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -135,6 +144,1025 @@
 			compatible = "sirf,atlas7-ioc";
 			reg = <0x18880000 0x1000>,
 				<0x10E40000 0x1000>;
+
+			audio_ac97_pmx: audio_ac97@0 {
+				audio_ac97 {
+					groups = "audio_ac97_grp";
+					function = "audio_ac97";
+				};
+			};
+
+			audio_func_dbg_pmx: audio_func_dbg@0 {
+				audio_func_dbg {
+					groups = "audio_func_dbg_grp";
+					function = "audio_func_dbg";
+				};
+			};
+
+			audio_i2s_pmx: audio_i2s@0 {
+				audio_i2s {
+					groups = "audio_i2s_grp";
+					function = "audio_i2s";
+				};
+			};
+
+			audio_i2s_2ch_pmx: audio_i2s_2ch@0 {
+				audio_i2s_2ch {
+					groups = "audio_i2s_2ch_grp";
+					function = "audio_i2s_2ch";
+				};
+			};
+
+			audio_i2s_extclk_pmx: audio_i2s_extclk@0 {
+				audio_i2s_extclk {
+					groups = "audio_i2s_extclk_grp";
+					function = "audio_i2s_extclk";
+				};
+			};
+
+			audio_uart0_pmx: audio_uart0@0 {
+				audio_uart0 {
+					groups = "audio_uart0_grp";
+					function = "audio_uart0";
+				};
+			};
+
+			audio_uart1_pmx: audio_uart1@0 {
+				audio_uart1 {
+					groups = "audio_uart1_grp";
+					function = "audio_uart1";
+				};
+			};
+
+			audio_uart2_pmx0: audio_uart2@0 {
+				audio_uart2_0 {
+					groups = "audio_uart2_grp0";
+					function = "audio_uart2_m0";
+				};
+			};
+
+			audio_uart2_pmx1: audio_uart2@1 {
+				audio_uart2_1 {
+					groups = "audio_uart2_grp1";
+					function = "audio_uart2_m1";
+				};
+			};
+
+			c_can_trnsvr_pmx: c_can_trnsvr@0 {
+				c_can_trnsvr {
+					groups = "c_can_trnsvr_grp";
+					function = "c_can_trnsvr";
+				};
+			};
+
+			c0_can_pmx0: c0_can@0 {
+				c0_can_0 {
+					groups = "c0_can_grp0";
+					function = "c0_can_m0";
+				};
+			};
+
+			c0_can_pmx1: c0_can@1 {
+				c0_can_1 {
+					groups = "c0_can_grp1";
+					function = "c0_can_m1";
+				};
+			};
+
+			c1_can_pmx0: c1_can@0 {
+				c1_can_0 {
+					groups = "c1_can_grp0";
+					function = "c1_can_m0";
+				};
+			};
+
+			c1_can_pmx1: c1_can@1 {
+				c1_can_1 {
+					groups = "c1_can_grp1";
+					function = "c1_can_m1";
+				};
+			};
+
+			c1_can_pmx2: c1_can@2 {
+				c1_can_2 {
+					groups = "c1_can_grp2";
+					function = "c1_can_m2";
+				};
+			};
+
+			ca_audio_lpc_pmx: ca_audio_lpc@0 {
+				ca_audio_lpc {
+					groups = "ca_audio_lpc_grp";
+					function = "ca_audio_lpc";
+				};
+			};
+
+			ca_bt_lpc_pmx: ca_bt_lpc@0 {
+				ca_bt_lpc {
+					groups = "ca_bt_lpc_grp";
+					function = "ca_bt_lpc";
+				};
+			};
+
+			ca_coex_pmx: ca_coex@0 {
+				ca_coex {
+					groups = "ca_coex_grp";
+					function = "ca_coex";
+				};
+			};
+
+			ca_curator_lpc_pmx: ca_curator_lpc@0 {
+				ca_curator_lpc {
+					groups = "ca_curator_lpc_grp";
+					function = "ca_curator_lpc";
+				};
+			};
+
+			ca_pcm_debug_pmx: ca_pcm_debug@0 {
+				ca_pcm_debug {
+					groups = "ca_pcm_debug_grp";
+					function = "ca_pcm_debug";
+				};
+			};
+
+			ca_pio_pmx: ca_pio@0 {
+				ca_pio {
+					groups = "ca_pio_grp";
+					function = "ca_pio";
+				};
+			};
+
+			ca_sdio_debug_pmx: ca_sdio_debug@0 {
+				ca_sdio_debug {
+					groups = "ca_sdio_debug_grp";
+					function = "ca_sdio_debug";
+				};
+			};
+
+			ca_spi_pmx: ca_spi@0 {
+				ca_spi {
+					groups = "ca_spi_grp";
+					function = "ca_spi";
+				};
+			};
+
+			ca_trb_pmx: ca_trb@0 {
+				ca_trb {
+					groups = "ca_trb_grp";
+					function = "ca_trb";
+				};
+			};
+
+			ca_uart_debug_pmx: ca_uart_debug@0 {
+				ca_uart_debug {
+					groups = "ca_uart_debug_grp";
+					function = "ca_uart_debug";
+				};
+			};
+
+			clkc_pmx0: clkc@0 {
+				clkc_0 {
+					groups = "clkc_grp0";
+					function = "clkc_m0";
+				};
+			};
+
+			clkc_pmx1: clkc@1 {
+				clkc_1 {
+					groups = "clkc_grp1";
+					function = "clkc_m1";
+				};
+			};
+
+			gn_gnss_i2c_pmx: gn_gnss_i2c@0 {
+				gn_gnss_i2c {
+					groups = "gn_gnss_i2c_grp";
+					function = "gn_gnss_i2c";
+				};
+			};
+
+			gn_gnss_uart_nopause_pmx: gn_gnss_uart_nopause@0 {
+				gn_gnss_uart_nopause {
+					groups = "gn_gnss_uart_nopause_grp";
+					function = "gn_gnss_uart_nopause";
+				};
+			};
+
+			gn_gnss_uart_pmx: gn_gnss_uart@0 {
+				gn_gnss_uart {
+					groups = "gn_gnss_uart_grp";
+					function = "gn_gnss_uart";
+				};
+			};
+
+			gn_trg_spi_pmx0: gn_trg_spi@0 {
+				gn_trg_spi_0 {
+					groups = "gn_trg_spi_grp0";
+					function = "gn_trg_spi_m0";
+				};
+			};
+
+			gn_trg_spi_pmx1: gn_trg_spi@1 {
+				gn_trg_spi_1 {
+					groups = "gn_trg_spi_grp1";
+					function = "gn_trg_spi_m1";
+				};
+			};
+
+			cvbs_dbg_pmx: cvbs_dbg@0 {
+				cvbs_dbg {
+					groups = "cvbs_dbg_grp";
+					function = "cvbs_dbg";
+				};
+			};
+
+			cvbs_dbg_test_pmx0: cvbs_dbg_test@0 {
+				cvbs_dbg_test_0 {
+					groups = "cvbs_dbg_test_grp0";
+					function = "cvbs_dbg_test_m0";
+				};
+			};
+
+			cvbs_dbg_test_pmx1: cvbs_dbg_test@1 {
+				cvbs_dbg_test_1 {
+					groups = "cvbs_dbg_test_grp1";
+					function = "cvbs_dbg_test_m1";
+				};
+			};
+
+			cvbs_dbg_test_pmx2: cvbs_dbg_test@2 {
+				cvbs_dbg_test_2 {
+					groups = "cvbs_dbg_test_grp2";
+					function = "cvbs_dbg_test_m2";
+				};
+			};
+
+			cvbs_dbg_test_pmx3: cvbs_dbg_test@3 {
+				cvbs_dbg_test_3 {
+					groups = "cvbs_dbg_test_grp3";
+					function = "cvbs_dbg_test_m3";
+				};
+			};
+
+			cvbs_dbg_test_pmx4: cvbs_dbg_test@4 {
+				cvbs_dbg_test_4 {
+					groups = "cvbs_dbg_test_grp4";
+					function = "cvbs_dbg_test_m4";
+				};
+			};
+
+			cvbs_dbg_test_pmx5: cvbs_dbg_test@5 {
+				cvbs_dbg_test_5 {
+					groups = "cvbs_dbg_test_grp5";
+					function = "cvbs_dbg_test_m5";
+				};
+			};
+
+			cvbs_dbg_test_pmx6: cvbs_dbg_test@6 {
+				cvbs_dbg_test_6 {
+					groups = "cvbs_dbg_test_grp6";
+					function = "cvbs_dbg_test_m6";
+				};
+			};
+
+			cvbs_dbg_test_pmx7: cvbs_dbg_test@7 {
+				cvbs_dbg_test_7 {
+					groups = "cvbs_dbg_test_grp7";
+					function = "cvbs_dbg_test_m7";
+				};
+			};
+
+			cvbs_dbg_test_pmx8: cvbs_dbg_test@8 {
+				cvbs_dbg_test_8 {
+					groups = "cvbs_dbg_test_grp8";
+					function = "cvbs_dbg_test_m8";
+				};
+			};
+
+			cvbs_dbg_test_pmx9: cvbs_dbg_test@9 {
+				cvbs_dbg_test_9 {
+					groups = "cvbs_dbg_test_grp9";
+					function = "cvbs_dbg_test_m9";
+				};
+			};
+
+			cvbs_dbg_test_pmx10: cvbs_dbg_test@10 {
+				cvbs_dbg_test_10 {
+					groups = "cvbs_dbg_test_grp10";
+					function = "cvbs_dbg_test_m10";
+				};
+			};
+
+			cvbs_dbg_test_pmx11: cvbs_dbg_test@11 {
+				cvbs_dbg_test_11 {
+					groups = "cvbs_dbg_test_grp11";
+					function = "cvbs_dbg_test_m11";
+				};
+			};
+
+			cvbs_dbg_test_pmx12: cvbs_dbg_test@12 {
+				cvbs_dbg_test_12 {
+					groups = "cvbs_dbg_test_grp12";
+					function = "cvbs_dbg_test_m12";
+				};
+			};
+
+			cvbs_dbg_test_pmx13: cvbs_dbg_test@13 {
+				cvbs_dbg_test_13 {
+					groups = "cvbs_dbg_test_grp13";
+					function = "cvbs_dbg_test_m13";
+				};
+			};
+
+			cvbs_dbg_test_pmx14: cvbs_dbg_test@14 {
+				cvbs_dbg_test_14 {
+					groups = "cvbs_dbg_test_grp14";
+					function = "cvbs_dbg_test_m14";
+				};
+			};
+
+			cvbs_dbg_test_pmx15: cvbs_dbg_test@15 {
+				cvbs_dbg_test_15 {
+					groups = "cvbs_dbg_test_grp15";
+					function = "cvbs_dbg_test_m15";
+				};
+			};
+
+			gn_gnss_power_pmx: gn_gnss_power@0 {
+				gn_gnss_power {
+					groups = "gn_gnss_power_grp";
+					function = "gn_gnss_power";
+				};
+			};
+
+			gn_gnss_sw_status_pmx: gn_gnss_sw_status@0 {
+				gn_gnss_sw_status {
+					groups = "gn_gnss_sw_status_grp";
+					function = "gn_gnss_sw_status";
+				};
+			};
+
+			gn_gnss_eclk_pmx: gn_gnss_eclk@0 {
+				gn_gnss_eclk {
+					groups = "gn_gnss_eclk_grp";
+					function = "gn_gnss_eclk";
+				};
+			};
+
+			gn_gnss_irq1_pmx0: gn_gnss_irq1@0 {
+				gn_gnss_irq1_0 {
+					groups = "gn_gnss_irq1_grp0";
+					function = "gn_gnss_irq1_m0";
+				};
+			};
+
+			gn_gnss_irq2_pmx0: gn_gnss_irq2@0 {
+				gn_gnss_irq2_0 {
+					groups = "gn_gnss_irq2_grp0";
+					function = "gn_gnss_irq2_m0";
+				};
+			};
+
+			gn_gnss_tm_pmx: gn_gnss_tm@0 {
+				gn_gnss_tm {
+					groups = "gn_gnss_tm_grp";
+					function = "gn_gnss_tm";
+				};
+			};
+
+			gn_gnss_tsync_pmx: gn_gnss_tsync@0 {
+				gn_gnss_tsync {
+					groups = "gn_gnss_tsync_grp";
+					function = "gn_gnss_tsync";
+				};
+			};
+
+			gn_io_gnsssys_sw_cfg_pmx: gn_io_gnsssys_sw_cfg@0 {
+				gn_io_gnsssys_sw_cfg {
+					groups = "gn_io_gnsssys_sw_cfg_grp";
+					function = "gn_io_gnsssys_sw_cfg";
+				};
+			};
+
+			gn_trg_pmx0: gn_trg@0 {
+				gn_trg_0 {
+					groups = "gn_trg_grp0";
+					function = "gn_trg_m0";
+				};
+			};
+
+			gn_trg_pmx1: gn_trg@1 {
+				gn_trg_1 {
+					groups = "gn_trg_grp1";
+					function = "gn_trg_m1";
+				};
+			};
+
+			gn_trg_shutdown_pmx0: gn_trg_shutdown@0 {
+				gn_trg_shutdown_0 {
+					groups = "gn_trg_shutdown_grp0";
+					function = "gn_trg_shutdown_m0";
+				};
+			};
+
+			gn_trg_shutdown_pmx1: gn_trg_shutdown@1 {
+				gn_trg_shutdown_1 {
+					groups = "gn_trg_shutdown_grp1";
+					function = "gn_trg_shutdown_m1";
+				};
+			};
+
+			gn_trg_shutdown_pmx2: gn_trg_shutdown@2 {
+				gn_trg_shutdown_2 {
+					groups = "gn_trg_shutdown_grp2";
+					function = "gn_trg_shutdown_m2";
+				};
+			};
+
+			gn_trg_shutdown_pmx3: gn_trg_shutdown@3 {
+				gn_trg_shutdown_3 {
+					groups = "gn_trg_shutdown_grp3";
+					function = "gn_trg_shutdown_m3";
+				};
+			};
+
+			i2c0_pmx: i2c0@0 {
+				i2c0 {
+					groups = "i2c0_grp";
+					function = "i2c0";
+				};
+			};
+
+			i2c1_pmx: i2c1@0 {
+				i2c1 {
+					groups = "i2c1_grp";
+					function = "i2c1";
+				};
+			};
+
+			jtag_pmx0: jtag@0 {
+				jtag_0 {
+					groups = "jtag_grp0";
+					function = "jtag_m0";
+				};
+			};
+
+			ks_kas_spi_pmx0: ks_kas_spi@0 {
+				ks_kas_spi_0 {
+					groups = "ks_kas_spi_grp0";
+					function = "ks_kas_spi_m0";
+				};
+			};
+
+			ld_ldd_pmx: ld_ldd@0 {
+				ld_ldd {
+					groups = "ld_ldd_grp";
+					function = "ld_ldd";
+				};
+			};
+
+			ld_ldd_16bit_pmx: ld_ldd_16bit@0 {
+				ld_ldd_16bit {
+					groups = "ld_ldd_16bit_grp";
+					function = "ld_ldd_16bit";
+				};
+			};
+
+			ld_ldd_fck_pmx: ld_ldd_fck@0 {
+				ld_ldd_fck {
+					groups = "ld_ldd_fck_grp";
+					function = "ld_ldd_fck";
+				};
+			};
+
+			ld_ldd_lck_pmx: ld_ldd_lck@0 {
+				ld_ldd_lck {
+					groups = "ld_ldd_lck_grp";
+					function = "ld_ldd_lck";
+				};
+			};
+
+			lr_lcdrom_pmx: lr_lcdrom@0 {
+				lr_lcdrom {
+					groups = "lr_lcdrom_grp";
+					function = "lr_lcdrom";
+				};
+			};
+
+			lvds_analog_pmx: lvds_analog@0 {
+				lvds_analog {
+					groups = "lvds_analog_grp";
+					function = "lvds_analog";
+				};
+			};
+
+			nd_df_pmx: nd_df@0 {
+				nd_df {
+					groups = "nd_df_grp";
+					function = "nd_df";
+				};
+			};
+
+			nd_df_nowp_pmx: nd_df_nowp@0 {
+				nd_df_nowp {
+					groups = "nd_df_nowp_grp";
+					function = "nd_df_nowp";
+				};
+			};
+
+			ps_pmx: ps@0 {
+				ps {
+					groups = "ps_grp";
+					function = "ps";
+				};
+			};
+
+			pwc_core_on_pmx: pwc_core_on@0 {
+				pwc_core_on {
+					groups = "pwc_core_on_grp";
+					function = "pwc_core_on";
+				};
+			};
+
+			pwc_ext_on_pmx: pwc_ext_on@0 {
+				pwc_ext_on {
+					groups = "pwc_ext_on_grp";
+					function = "pwc_ext_on";
+				};
+			};
+
+			pwc_gpio3_clk_pmx: pwc_gpio3_clk@0 {
+				pwc_gpio3_clk {
+					groups = "pwc_gpio3_clk_grp";
+					function = "pwc_gpio3_clk";
+				};
+			};
+
+			pwc_io_on_pmx: pwc_io_on@0 {
+				pwc_io_on {
+					groups = "pwc_io_on_grp";
+					function = "pwc_io_on";
+				};
+			};
+
+			pwc_lowbatt_b_pmx0: pwc_lowbatt_b@0 {
+				pwc_lowbatt_b_0 {
+					groups = "pwc_lowbatt_b_grp0";
+					function = "pwc_lowbatt_b_m0";
+				};
+			};
+
+			pwc_mem_on_pmx: pwc_mem_on@0 {
+				pwc_mem_on {
+					groups = "pwc_mem_on_grp";
+					function = "pwc_mem_on";
+				};
+			};
+
+			pwc_on_key_b_pmx0: pwc_on_key_b@0 {
+				pwc_on_key_b_0 {
+					groups = "pwc_on_key_b_grp0";
+					function = "pwc_on_key_b_m0";
+				};
+			};
+
+			pwc_wakeup_src0_pmx: pwc_wakeup_src0@0 {
+				pwc_wakeup_src0 {
+					groups = "pwc_wakeup_src0_grp";
+					function = "pwc_wakeup_src0";
+				};
+			};
+
+			pwc_wakeup_src1_pmx: pwc_wakeup_src1@0 {
+				pwc_wakeup_src1 {
+					groups = "pwc_wakeup_src1_grp";
+					function = "pwc_wakeup_src1";
+				};
+			};
+
+			pwc_wakeup_src2_pmx: pwc_wakeup_src2@0 {
+				pwc_wakeup_src2 {
+					groups = "pwc_wakeup_src2_grp";
+					function = "pwc_wakeup_src2";
+				};
+			};
+
+			pwc_wakeup_src3_pmx: pwc_wakeup_src3@0 {
+				pwc_wakeup_src3 {
+					groups = "pwc_wakeup_src3_grp";
+					function = "pwc_wakeup_src3";
+				};
+			};
+
+			pw_cko0_pmx0: pw_cko0@0 {
+				pw_cko0_0 {
+					groups = "pw_cko0_grp0";
+					function = "pw_cko0_m0";
+				};
+			};
+
+			pw_cko0_pmx1: pw_cko0@1 {
+				pw_cko0_1 {
+					groups = "pw_cko0_grp1";
+					function = "pw_cko0_m1";
+				};
+			};
+
+			pw_cko0_pmx2: pw_cko0@2 {
+				pw_cko0_2 {
+					groups = "pw_cko0_grp2";
+					function = "pw_cko0_m2";
+				};
+			};
+
+			pw_cko1_pmx0: pw_cko1@0 {
+				pw_cko1_0 {
+					groups = "pw_cko1_grp0";
+					function = "pw_cko1_m0";
+				};
+			};
+
+			pw_cko1_pmx1: pw_cko1@1 {
+				pw_cko1_1 {
+					groups = "pw_cko1_grp1";
+					function = "pw_cko1_m1";
+				};
+			};
+
+			pw_i2s01_clk_pmx0: pw_i2s01_clk@0 {
+				pw_i2s01_clk_0 {
+					groups = "pw_i2s01_clk_grp0";
+					function = "pw_i2s01_clk_m0";
+				};
+			};
+
+			pw_i2s01_clk_pmx1: pw_i2s01_clk@1 {
+				pw_i2s01_clk_1 {
+					groups = "pw_i2s01_clk_grp1";
+					function = "pw_i2s01_clk_m1";
+				};
+			};
+
+			pw_pwm0_pmx: pw_pwm0@0 {
+				pw_pwm0 {
+					groups = "pw_pwm0_grp";
+					function = "pw_pwm0";
+				};
+			};
+
+			pw_pwm1_pmx: pw_pwm1@0 {
+				pw_pwm1 {
+					groups = "pw_pwm1_grp";
+					function = "pw_pwm1";
+				};
+			};
+
+			pw_pwm2_pmx0: pw_pwm2@0 {
+				pw_pwm2_0 {
+					groups = "pw_pwm2_grp0";
+					function = "pw_pwm2_m0";
+				};
+			};
+
+			pw_pwm2_pmx1: pw_pwm2@1 {
+				pw_pwm2_1 {
+					groups = "pw_pwm2_grp1";
+					function = "pw_pwm2_m1";
+				};
+			};
+
+			pw_pwm3_pmx0: pw_pwm3@0 {
+				pw_pwm3_0 {
+					groups = "pw_pwm3_grp0";
+					function = "pw_pwm3_m0";
+				};
+			};
+
+			pw_pwm3_pmx1: pw_pwm3@1 {
+				pw_pwm3_1 {
+					groups = "pw_pwm3_grp1";
+					function = "pw_pwm3_m1";
+				};
+			};
+
+			pw_pwm_cpu_vol_pmx0: pw_pwm_cpu_vol@0 {
+				pw_pwm_cpu_vol_0 {
+					groups = "pw_pwm_cpu_vol_grp0";
+					function = "pw_pwm_cpu_vol_m0";
+				};
+			};
+
+			pw_pwm_cpu_vol_pmx1: pw_pwm_cpu_vol@1 {
+				pw_pwm_cpu_vol_1 {
+					groups = "pw_pwm_cpu_vol_grp1";
+					function = "pw_pwm_cpu_vol_m1";
+				};
+			};
+
+			pw_backlight_pmx0: pw_backlight@0 {
+				pw_backlight_0 {
+					groups = "pw_backlight_grp0";
+					function = "pw_backlight_m0";
+				};
+			};
+
+			pw_backlight_pmx1: pw_backlight@1 {
+				pw_backlight_1 {
+					groups = "pw_backlight_grp1";
+					function = "pw_backlight_m1";
+				};
+			};
+
+			rg_eth_mac_pmx: rg_eth_mac@0 {
+				rg_eth_mac {
+					groups = "rg_eth_mac_grp";
+					function = "rg_eth_mac";
+				};
+			};
+
+			rg_gmac_phy_intr_n_pmx: rg_gmac_phy_intr_n@0 {
+				rg_gmac_phy_intr_n {
+					groups = "rg_gmac_phy_intr_n_grp";
+					function = "rg_gmac_phy_intr_n";
+				};
+			};
+
+			rg_rgmii_mac_pmx: rg_rgmii_mac@0 {
+				rg_rgmii_mac {
+					groups = "rg_rgmii_mac_grp";
+					function = "rg_rgmii_mac";
+				};
+			};
+
+			rg_rgmii_phy_ref_clk_pmx0: rg_rgmii_phy_ref_clk@0 {
+				rg_rgmii_phy_ref_clk_0 {
+					groups =
+						"rg_rgmii_phy_ref_clk_grp0";
+					function =
+						"rg_rgmii_phy_ref_clk_m0";
+				};
+			};
+
+			rg_rgmii_phy_ref_clk_pmx1: rg_rgmii_phy_ref_clk@1 {
+				rg_rgmii_phy_ref_clk_1 {
+					groups =
+						"rg_rgmii_phy_ref_clk_grp1";
+					function =
+						"rg_rgmii_phy_ref_clk_m1";
+				};
+			};
+
+			sd0_pmx: sd0@0 {
+				sd0 {
+					groups = "sd0_grp";
+					function = "sd0";
+				};
+			};
+
+			sd0_4bit_pmx: sd0_4bit@0 {
+				sd0_4bit {
+					groups = "sd0_4bit_grp";
+					function = "sd0_4bit";
+				};
+			};
+
+			sd1_pmx: sd1@0 {
+				sd1 {
+					groups = "sd1_grp";
+					function = "sd1";
+				};
+			};
+
+			sd1_4bit_pmx0: sd1_4bit@0 {
+				sd1_4bit_0 {
+					groups = "sd1_4bit_grp0";
+					function = "sd1_4bit_m0";
+				};
+			};
+
+			sd1_4bit_pmx1: sd1_4bit@1 {
+				sd1_4bit_1 {
+					groups = "sd1_4bit_grp1";
+					function = "sd1_4bit_m1";
+				};
+			};
+
+			sd2_pmx0: sd2@0 {
+				sd2_0 {
+					groups = "sd2_grp0";
+					function = "sd2_m0";
+				};
+			};
+
+			sd2_no_cdb_pmx0: sd2_no_cdb@0 {
+				sd2_no_cdb_0 {
+					groups = "sd2_no_cdb_grp0";
+					function = "sd2_no_cdb_m0";
+				};
+			};
+
+			sd3_pmx: sd3@0 {
+				sd3 {
+					groups = "sd3_grp";
+					function = "sd3";
+				};
+			};
+
+			sd5_pmx: sd5@0 {
+				sd5 {
+					groups = "sd5_grp";
+					function = "sd5";
+				};
+			};
+
+			sd6_pmx0: sd6@0 {
+				sd6_0 {
+					groups = "sd6_grp0";
+					function = "sd6_m0";
+				};
+			};
+
+			sd6_pmx1: sd6@1 {
+				sd6_1 {
+					groups = "sd6_grp1";
+					function = "sd6_m1";
+				};
+			};
+
+			sp0_ext_ldo_on_pmx: sp0_ext_ldo_on@0 {
+				sp0_ext_ldo_on {
+					groups = "sp0_ext_ldo_on_grp";
+					function = "sp0_ext_ldo_on";
+				};
+			};
+
+			sp0_qspi_pmx: sp0_qspi@0 {
+				sp0_qspi {
+					groups = "sp0_qspi_grp";
+					function = "sp0_qspi";
+				};
+			};
+
+			sp1_spi_pmx: sp1_spi@0 {
+				sp1_spi {
+					groups = "sp1_spi_grp";
+					function = "sp1_spi";
+				};
+			};
+
+			tpiu_trace_pmx: tpiu_trace@0 {
+				tpiu_trace {
+					groups = "tpiu_trace_grp";
+					function = "tpiu_trace";
+				};
+			};
+
+			uart0_pmx: uart0@0 {
+				uart0 {
+					groups = "uart0_grp";
+					function = "uart0";
+				};
+			};
+
+			uart0_nopause_pmx: uart0_nopause@0 {
+				uart0_nopause {
+					groups = "uart0_nopause_grp";
+					function = "uart0_nopause";
+				};
+			};
+
+			uart1_pmx: uart1@0 {
+				uart1 {
+					groups = "uart1_grp";
+					function = "uart1";
+				};
+			};
+
+			uart2_pmx: uart2@0 {
+				uart2 {
+					groups = "uart2_grp";
+					function = "uart2";
+				};
+			};
+
+			uart3_pmx0: uart3@0 {
+				uart3_0 {
+					groups = "uart3_grp0";
+					function = "uart3_m0";
+				};
+			};
+
+			uart3_pmx1: uart3@1 {
+				uart3_1 {
+					groups = "uart3_grp1";
+					function = "uart3_m1";
+				};
+			};
+
+			uart3_pmx2: uart3@2 {
+				uart3_2 {
+					groups = "uart3_grp2";
+					function = "uart3_m2";
+				};
+			};
+
+			uart3_pmx3: uart3@3 {
+				uart3_3 {
+					groups = "uart3_grp3";
+					function = "uart3_m3";
+				};
+			};
+
+			uart3_nopause_pmx0: uart3_nopause@0 {
+				uart3_nopause_0 {
+					groups = "uart3_nopause_grp0";
+					function = "uart3_nopause_m0";
+				};
+			};
+
+			uart3_nopause_pmx1: uart3_nopause@1 {
+				uart3_nopause_1 {
+					groups = "uart3_nopause_grp1";
+					function = "uart3_nopause_m1";
+				};
+			};
+
+			uart4_pmx0: uart4@0 {
+				uart4_0 {
+					groups = "uart4_grp0";
+					function = "uart4_m0";
+				};
+			};
+
+			uart4_pmx1: uart4@1 {
+				uart4_1 {
+					groups = "uart4_grp1";
+					function = "uart4_m1";
+				};
+			};
+
+			uart4_pmx2: uart4@2 {
+				uart4_2 {
+					groups = "uart4_grp2";
+					function = "uart4_m2";
+				};
+			};
+
+			uart4_nopause_pmx: uart4_nopause@0 {
+				uart4_nopause {
+					groups = "uart4_nopause_grp";
+					function = "uart4_nopause";
+				};
+			};
+
+			usb0_drvvbus_pmx: usb0_drvvbus@0 {
+				usb0_drvvbus {
+					groups = "usb0_drvvbus_grp";
+					function = "usb0_drvvbus";
+				};
+			};
+
+			usb1_drvvbus_pmx: usb1_drvvbus@0 {
+				usb1_drvvbus {
+					groups = "usb1_drvvbus_grp";
+					function = "usb1_drvvbus";
+				};
+			};
+
+			visbus_dout_pmx: visbus_dout@0 {
+				visbus_dout {
+					groups = "visbus_dout_grp";
+					function = "visbus_dout";
+				};
+			};
+
+			vi_vip1_pmx: vi_vip1@0 {
+				vi_vip1 {
+					groups = "vi_vip1_grp";
+					function = "vi_vip1";
+				};
+			};
+
+			vi_vip1_ext_pmx: vi_vip1_ext@0 {
+				vi_vip1_ext {
+					groups = "vi_vip1_ext_grp";
+					function = "vi_vip1_ext";
+				};
+			};
+
+			vi_vip1_low8bit_pmx: vi_vip1_low8bit@0 {
+				vi_vip1_low8bit {
+					groups = "vi_vip1_low8bit_grp";
+					function = "vi_vip1_low8bit";
+				};
+			};
+
+			vi_vip1_high8bit_pmx: vi_vip1_high8bit@0 {
+				vi_vip1_high8bit {
+					groups = "vi_vip1_high8bit_grp";
+					function = "vi_vip1_high8bit";
+				};
+			};
 		};
 
 		pmipc {
@@ -186,7 +1214,8 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x18641000 0x18641000 0x3000>,
-					 <0x18620000 0x18620000 0x1000>;
+					 <0x18620000 0x18620000 0x1000>,
+					<0x18630000 0x18630000 0x10000>;
 
 			cgum@18641000 {
 				compatible = "sirf,nocfw-cgum";
@@ -199,6 +1228,15 @@
 				#clock-cells = <1>;
 				#reset-cells = <1>;
 			};
+			pwm: pwm@18630000 {
+				compatible = "sirf,prima2-pwm";
+				#pwm-cells = <2>;
+				reg = <0x18630000 0x10000>;
+				clocks = <&car 138>, <&car 139>, <&car 237>,
+					<&car 240>,  <&car 140>, <&car 246>;
+				clock-names = "pwmc", "sigsrc0", "sigsrc1",
+					"sigsrc2", "sigsrc3", "sigsrc4";
+			};
 		};
 
 		gnssm {
@@ -212,6 +1250,7 @@
 				<0x18040000 0x18040000 0x1000>,
 				<0x18050000 0x18050000 0x1000>,
 				<0x18060000 0x18060000 0x1000>,
+				<0x180b0000 0x180b0000 0x4000>,
 				<0x18100000 0x18100000 0x3000>,
 				<0x18250000 0x18250000 0x10000>,
 				<0x18200000 0x18200000 0x1000>;
@@ -295,6 +1334,18 @@
 				dma-names = "rx", "tx";
 				status = "disabled";
 			};
+			gmac: eth@180b0000 {
+				compatible = "snps, dwc-eth-qos";
+				reg = <0x180b0000 0x4000>;
+				interrupts = <0 59 0>, <0 70 0>;
+				interrupt-names = "macirq", "macpmt";
+				clocks = <&car 39>, <&car 45>,
+				       <&car 86>, <&car 87>;
+				clock-names = "gnssm_rgmii", "gnssm_gmac",
+					"rgmii", "gmac";
+				local-mac-address = [00 00 00 00 00 00];
+				phy-mode = "rgmii";
+			};
 			dspub@18250000 {
 				compatible = "dx,cc44p";
 				reg = <0x18250000 0x10000>;
@@ -319,18 +1370,51 @@
 			compatible = "arteris, flexnoc", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0x13000000 0x13000000 0x3000>;
+			ranges = <0x13000000 0x13000000 0x3000>,
+				<0x13010000 0x13010000 0x1400>,
+				<0x13010800 0x13010800 0x100>,
+				<0x13011000 0x13011000 0x100>;
 			gpum@0x13000000 {
 				compatible = "sirf,nocfw-gpum";
 				reg = <0x13000000 0x3000>;
 			};
+			dmacsdrr: dma-controller@13010800 {
+				cell-index = <5>;
+				compatible = "sirf,atlas7-dmac-v2";
+				reg = <0x13010800 0x100>;
+				interrupts = <0 8 0>;
+				clocks = <&car 127>;
+				#dma-cells = <1>;
+				#dma-channels = <1>;
+			};
+			dmacsdrw: dma-controller@13011000 {
+				cell-index = <6>;
+				compatible = "sirf,atlas7-dmac-v2";
+				reg = <0x13011000 0x100>;
+				interrupts = <0 9 0>;
+				clocks = <&car 127>;
+				#dma-cells = <1>;
+				#dma-channels = <1>;
+			};
+			sdr@0x13010000 {
+				compatible = "sirf,atlas7-sdr";
+				reg = <0x13010000 0x1400>;
+				interrupts = <0 7 0>,
+					   <0 8 0>,
+					   <0 9 0>;
+				clocks = <&car 127>;
+				dmas = <&dmacsdrr 0>, <&dmacsdrw 0>;
+				dma-names = "tx", "rx";
+			};
 		};
 
 		mediam {
 			compatible = "arteris, flexnoc", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0x16000000 0x16000000 0x00200000>,
+			ranges = <0x15000000 0x15000000 0x00600000>,
+				<0x16000000 0x16000000 0x00200000>,
+				<0x17000000 0x17000000 0x10000>,
 				<0x17020000 0x17020000 0x1000>,
 				<0x17030000 0x17030000 0x1000>,
 				<0x17040000 0x17040000 0x1000>,
@@ -341,6 +1425,13 @@
 				<0x17070200 0x17070200 0x100>,
 				<0x170A0000 0x170A0000 0x3000>;
 
+			multimedia@15000000 {
+				compatible = "sirf,atlas7-video-codec";
+				reg = <0x15000000 0x10000>;
+				interrupts = <0 5 0>;
+				clocks = <&car 102>;
+			};
+
 			mediam@170A0000 {
 				compatible = "sirf,nocfw-mediam";
 				reg = <0x170A0000 0x3000>;
@@ -356,11 +1447,19 @@
 				clock-names = "gpio0_io";
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <2>;
+				gpio-ranges = <&pinctrl 0 0 0>,
+						<&pinctrl 32 0 0>;
+				gpio-ranges-group-names = "lvds_gpio_grp",
+							"uart_nand_gpio_grp";
 			};
 
 			nand@17050000 {
 				compatible = "sirf,atlas7-nand";
 				reg = <0x17050000 0x10000>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&nd_df_pmx>;
 				interrupts = <0 41 0>;
 				clocks = <&car 108>, <&car 112>;
 				clock-names = "nand_io", "nand_nand";
@@ -391,6 +1490,14 @@
 				bus-width = <8>;
 			};
 
+			jpeg@17000000 {
+				compatible = "sirf,atlas7-jpeg";
+				reg = <0x17000000 0x10000>;
+				interrupts = <0 72 0>,
+					<0 73 0>;
+				clocks = <&car 103>;
+			};
+
 			usb0: usb@17060000 {
 				cell-index = <0>;
 				compatible = "sirf,atlas7-usb";
@@ -461,11 +1568,22 @@
 				#interrupt-cells = <2>;
 				compatible = "sirf,atlas7-gpio";
 				reg = <0x13300000 0x1000>;
-				interrupts = <0 43 0>, <0 44 0>, <0 45 0>;
+				interrupts = <0 43 0>, <0 44 0>,
+						<0 45 0>, <0 46 0>;
 				clocks = <&car 84>;
 				clock-names = "gpio1_io";
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <4>;
+				gpio-ranges = <&pinctrl 0 0 0>,
+						<&pinctrl 32 0 0>,
+						<&pinctrl 64 0 0>,
+						<&pinctrl 96 0 0>;
+				gpio-ranges-group-names = "gnss_gpio_grp",
+							"lcd_vip_gpio_grp",
+							"sdio_i2s_gpio_grp",
+							"sp_rgmii_gpio_grp";
 			};
 
 			sd2: sdhci@14200000 {
@@ -744,6 +1862,10 @@
 				interrupts = <0 47 0>;
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <1>;
+				gpio-ranges = <&pinctrl 0 0 0>;
+				gpio-ranges-group-names = "rtc_gpio_grp";
 			};
 
 			rtc-iobg@18840000 {
@@ -786,7 +1908,8 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x13100000 0x13100000 0x20000>,
-				 <0x10e10000 0x10e10000 0x10000>;
+				<0x10e10000 0x10e10000 0x10000>,
+				<0x17010000 0x17010000 0x10000>;
 
 			lcd@13100000 {
 				compatible = "sirf,atlas7-lcdc";
@@ -808,6 +1931,12 @@
 				clocks = <&car 54>;
 				resets = <&car 29>;
 			};
+			g2d@17010000 {
+				compatible = "sirf, atlas7-g2d";
+				reg = <0x17010000 0x10000>;
+				interrupts = <0 61 0>;
+				clocks = <&car 104>;
+			};
 
 		};
 
diff --git a/arch/arm/boot/dts/axp152.dtsi b/arch/arm/boot/dts/axp152.dtsi
new file mode 100644
index 000000000000..f90ad6c64a07
--- /dev/null
+++ b/arch/arm/boot/dts/axp152.dtsi
@@ -0,0 +1,49 @@
+/*
+ * Copyright 2015 Chen-Yu Tsai
+ *
+ * Chen-Yu Tsai <wens@csie.org>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&axp152 {
+	compatible = "x-powers,axp152";
+	interrupt-controller;
+	#interrupt-cells = <1>;
+};
diff --git a/arch/arm/boot/dts/bcm-cygnus-clock.dtsi b/arch/arm/boot/dts/bcm-cygnus-clock.dtsi
index 60d8389fdb6c..32bcd45ef22b 100644
--- a/arch/arm/boot/dts/bcm-cygnus-clock.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus-clock.dtsi
@@ -36,56 +36,89 @@ clocks {
 	ranges;
 
 	osc: oscillator {
+		#clock-cells = <0>;
 		compatible = "fixed-clock";
-		#clock-cells = <1>;
 		clock-frequency = <25000000>;
 	};
 
-	apb_clk: apb_clk {
-		compatible = "fixed-clock";
+	/* Cygnus ARM PLL */
+	armpll: armpll {
 		#clock-cells = <0>;
-		clock-frequency = <1000000000>;
+		compatible = "brcm,cygnus-armpll";
+		clocks = <&osc>;
+		reg = <0x19000000 0x1000>;
 	};
 
-	periph_clk: periph_clk {
-		compatible = "fixed-clock";
+	/* peripheral clock for system timer */
+	periph_clk: arm_periph_clk {
 		#clock-cells = <0>;
-		clock-frequency = <500000000>;
+		compatible = "fixed-factor-clock";
+		clocks = <&armpll>;
+		clock-div = <2>;
+		clock-mult = <1>;
 	};
 
-	sdio_clk: lcpll_ch2 {
-		compatible = "fixed-clock";
+	/* APB bus clock */
+	apb_clk: apb_clk {
 		#clock-cells = <0>;
-		clock-frequency = <200000000>;
+		compatible = "fixed-factor-clock";
+		clocks = <&armpll>;
+		clock-div = <4>;
+		clock-mult = <1>;
 	};
 
-	axi81_clk: axi81_clk {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <100000000>;
+	genpll: genpll {
+		#clock-cells = <1>;
+		compatible = "brcm,cygnus-genpll";
+		reg = <0x0301d000 0x2c>, <0x0301c020 0x4>;
+		clocks = <&osc>;
+		clock-output-names = "genpll", "axi21", "250mhz", "ihost_sys",
+				     "enet_sw", "audio_125", "can";
 	};
 
-	keypad_clk: keypad_clk {
-		compatible = "fixed-clock";
+	/* always 1/2 of the axi21 clock */
+	axi41_clk: axi41_clk {
 		#clock-cells = <0>;
-		clock-frequency = <31806>;
+		compatible = "fixed-factor-clock";
+		clocks = <&genpll 1>;
+		clock-div = <2>;
+		clock-mult = <1>;
 	};
 
-	adc_clk: adc_clk {
-		compatible = "fixed-clock";
+	/* always 1/4 of the axi21 clock */
+	axi81_clk: axi81_clk {
 		#clock-cells = <0>;
-		clock-frequency = <1562500>;
+		compatible = "fixed-factor-clock";
+		clocks = <&genpll 1>;
+		clock-div = <4>;
+		clock-mult = <1>;
 	};
 
-	pwm_clk: pwm_clk {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <1000000>;
+	lcpll0: lcpll0 {
+		#clock-cells = <1>;
+		compatible = "brcm,cygnus-lcpll0";
+		reg = <0x0301d02c 0x1c>, <0x0301c020 0x4>;
+		clocks = <&osc>;
+		clock-output-names = "lcpll0", "pcie_phy", "ddr_phy", "sdio",
+				     "usb_phy", "smart_card", "ch5";
 	};
 
-	lcd_clk: mipipll_ch1 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <100000000>;
+	mipipll: mipipll {
+		#clock-cells = <1>;
+		compatible = "brcm,cygnus-mipipll";
+		reg = <0x180a9800 0x2c>, <0x0301c020 0x4>, <0x180aa024 0x4>;
+		clocks = <&osc>;
+		clock-output-names = "mipipll", "ch0_unused", "ch1_lcd",
+				     "ch2_v3d", "ch3_unused", "ch4_unused",
+				     "ch5_unused";
+	};
+
+	asiu_clks: asiu_clks {
+		#clock-cells = <1>;
+		compatible = "brcm,cygnus-asiu-clk";
+		reg = <0x0301d048 0xc>, <0x180aa024 0x4>;
+
+		clocks = <&osc>;
+		clock-output-names = "keypad", "adc/touch", "pwm";
 	};
 };
diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index 46780bb48bbf..ab5474e5d1c8 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -14,6 +14,13 @@
 			linux,default-trigger = "heartbeat";
 		};
 	};
+
+	soc {
+		firmware: firmware {
+			compatible = "raspberrypi,bcm2835-firmware";
+			mboxes = <&mailbox>;
+		};
+	};
 };
 
 &gpio {
diff --git a/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts b/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts
index 24f0ab59bf1b..42dcdfb769b2 100644
--- a/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts
+++ b/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts
@@ -135,3 +135,7 @@
 		};
 	};
 };
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm4708-luxul-xwc-1000.dts b/arch/arm/boot/dts/bcm4708-luxul-xwc-1000.dts
index f03939311717..f18e80e0b61d 100644
--- a/arch/arm/boot/dts/bcm4708-luxul-xwc-1000.dts
+++ b/arch/arm/boot/dts/bcm4708-luxul-xwc-1000.dts
@@ -55,3 +55,7 @@
 		};
 	};
 };
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm4708-netgear-r6250.dts b/arch/arm/boot/dts/bcm4708-netgear-r6250.dts
index 326ce8f4e49c..64b8d10ccff8 100644
--- a/arch/arm/boot/dts/bcm4708-netgear-r6250.dts
+++ b/arch/arm/boot/dts/bcm4708-netgear-r6250.dts
@@ -24,16 +24,6 @@
 		reg = <0x00000000 0x08000000>;
 	};
 
-	chipcommonA {
-		uart0: serial@0300 {
-			status = "okay";
-		};
-
-		uart1: serial@0400 {
-			status = "okay";
-		};
-	};
-
 	leds {
 		compatible = "gpio-leds";
 
@@ -92,3 +82,7 @@
 		};
 	};
 };
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts b/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts
index d6a033b97c70..64a5e8ab65e0 100644
--- a/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts
+++ b/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts
@@ -118,3 +118,7 @@
 		};
 	};
 };
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm47081-buffalo-wzr-600dhp2.dts b/arch/arm/boot/dts/bcm47081-buffalo-wzr-600dhp2.dts
index bb0cb0bfafaf..38f0c00d1aca 100644
--- a/arch/arm/boot/dts/bcm47081-buffalo-wzr-600dhp2.dts
+++ b/arch/arm/boot/dts/bcm47081-buffalo-wzr-600dhp2.dts
@@ -122,3 +122,7 @@
 		};
 	};
 };
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 21fefd4cdc25..6f50f672efbd 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -78,10 +78,20 @@
 			compatible = "arm,pl310-cache";
 			reg = <0x2000 0x1000>;
 			cache-unified;
+			arm,shared-override;
+			prefetch-data = <1>;
+			prefetch-instr = <1>;
 			cache-level = <2>;
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupts =
+			<GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
 	clocks {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/boot/dts/bcm7445.dtsi b/arch/arm/boot/dts/bcm7445.dtsi
index 58dcd666257c..3b6b17560687 100644
--- a/arch/arm/boot/dts/bcm7445.dtsi
+++ b/arch/arm/boot/dts/bcm7445.dtsi
@@ -109,6 +109,20 @@
 			brcm,int-fwd-mask = <0x70000>;
 		};
 
+		irq0_aon_intc: interrupt-controller@417280 {
+			compatible = "brcm,bcm7120-l2-intc";
+			reg = <0x417280 0x8>;
+			interrupt-parent = <&gic>;
+			#interrupt-cells = <1>;
+			interrupt-controller;
+			interrupts = <GIC_SPI 0x46 0x0>,
+				     <GIC_SPI 0x44 0x0>,
+				     <GIC_SPI 0x49 0x0>;
+			brcm,int-map-mask = <0x1e3 0x18000000 0x100000>;
+			brcm,int-fwd-mask = <0x0>;
+			brcm,irq-can-wake;
+		};
+
 		hif_intr2_intc: interrupt-controller@3e1000 {
 			compatible = "brcm,l2-intc";
 			reg = <0x3e1000 0x30>;
@@ -119,6 +133,16 @@
 			interrupt-names = "hif";
 		};
 
+                aon_pm_l2_intc: interrupt-controller@410640 {
+			compatible = "brcm,l2-intc";
+			reg = <0x410640 0x30>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupts = <GIC_SPI 0x40 0x0>;
+			interrupt-parent = <&gic>;
+			brcm,irq-can-wake;
+		};
+
 		nand: nand@3e2800 {
 			status = "disabled";
 			#address-cells = <1>;
@@ -167,6 +191,32 @@
 				#phy-cells = <0>;
 			};
 		};
+
+		upg_gio: gpio@40a700 {
+			compatible = "brcm,bcm7445-gpio", "brcm,brcmstb-gpio";
+			reg = <0x40a700 0x80>;
+			#gpio-cells = <2>;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			interrupt-controller;
+			interrupt-parent = <&irq0_intc>;
+			interrupts = <6>;
+			brcm,gpio-bank-widths = <32 32 32 24>;
+		};
+
+		upg_gio_aon: gpio@4172c0 {
+			compatible = "brcm,bcm7445-gpio", "brcm,brcmstb-gpio";
+			reg = <0x4172c0 0x40>;
+			#gpio-cells = <2>;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			interrupt-controller;
+			interrupts-extended = <&irq0_aon_intc 0x6>,
+					      <&aon_pm_l2_intc 0x5>;
+			wakeup-source;
+			brcm,gpio-bank-widths = <18 4>;
+		};
+
 	};
 
 	smpboot {
diff --git a/arch/arm/boot/dts/cros-ec-keyboard.dtsi b/arch/arm/boot/dts/cros-ec-keyboard.dtsi
index 9c7fb0acae79..4e42f30cb318 100644
--- a/arch/arm/boot/dts/cros-ec-keyboard.dtsi
+++ b/arch/arm/boot/dts/cros-ec-keyboard.dtsi
@@ -22,6 +22,7 @@
 			MATRIX_KEY(0x00, 0x02, KEY_F1)
 			MATRIX_KEY(0x00, 0x03, KEY_B)
 			MATRIX_KEY(0x00, 0x04, KEY_F10)
+			MATRIX_KEY(0x00, 0x05, KEY_RO)
 			MATRIX_KEY(0x00, 0x06, KEY_N)
 			MATRIX_KEY(0x00, 0x08, KEY_EQUAL)
 			MATRIX_KEY(0x00, 0x0a, KEY_RIGHTALT)
@@ -34,6 +35,7 @@
 			MATRIX_KEY(0x01, 0x08, KEY_APOSTROPHE)
 			MATRIX_KEY(0x01, 0x09, KEY_F9)
 			MATRIX_KEY(0x01, 0x0b, KEY_BACKSPACE)
+			MATRIX_KEY(0x01, 0x0c, KEY_HENKAN)
 
 			MATRIX_KEY(0x02, 0x00, KEY_LEFTCTRL)
 			MATRIX_KEY(0x02, 0x01, KEY_TAB)
@@ -45,6 +47,7 @@
 			MATRIX_KEY(0x02, 0x07, KEY_102ND)
 			MATRIX_KEY(0x02, 0x08, KEY_LEFTBRACE)
 			MATRIX_KEY(0x02, 0x09, KEY_F8)
+			MATRIX_KEY(0x02, 0x0a, KEY_YEN)
 
 			MATRIX_KEY(0x03, 0x01, KEY_GRAVE)
 			MATRIX_KEY(0x03, 0x02, KEY_F2)
@@ -53,6 +56,7 @@
 			MATRIX_KEY(0x03, 0x06, KEY_6)
 			MATRIX_KEY(0x03, 0x08, KEY_MINUS)
 			MATRIX_KEY(0x03, 0x0b, KEY_BACKSLASH)
+			MATRIX_KEY(0x03, 0x0c, KEY_MUHENKAN)
 
 			MATRIX_KEY(0x04, 0x00, KEY_RIGHTCTRL)
 			MATRIX_KEY(0x04, 0x01, KEY_A)
diff --git a/arch/arm/boot/dts/cros-ec-sbs.dtsi b/arch/arm/boot/dts/cros-ec-sbs.dtsi
new file mode 100644
index 000000000000..71f5c5ecce46
--- /dev/null
+++ b/arch/arm/boot/dts/cros-ec-sbs.dtsi
@@ -0,0 +1,52 @@
+/*
+ * Smart battery dts fragment for devices that use cros-ec-sbs
+ *
+ * Copyright (c) 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&i2c_tunnel {
+	battery: sbs-battery@b {
+		compatible = "sbs,sbs-battery";
+		reg = <0xb>;
+		sbs,i2c-retry-count = <2>;
+		sbs,poll-retry-count = <1>;
+	};
+};
diff --git a/arch/arm/boot/dts/cx92755.dtsi b/arch/arm/boot/dts/cx92755.dtsi
index af333261d046..df4c6f1f93f9 100644
--- a/arch/arm/boot/dts/cx92755.dtsi
+++ b/arch/arm/boot/dts/cx92755.dtsi
@@ -88,6 +88,13 @@
 		interrupts = <25>;
 	};
 
+	watchdog@f0000fc0 {
+		compatible = "cnxt,cx92755-wdt";
+		reg = <0xf0000fc0 0x8>;
+		clocks = <&main_clk>;
+		timeout-sec = <15>;
+	};
+
 	uc_regs: syscon@f00003a0 {
 		compatible = "cnxt,cx92755-uc", "syscon";
 		reg = <0xf00003a0 0x10>;
diff --git a/arch/arm/boot/dts/cx92755_equinox.dts b/arch/arm/boot/dts/cx92755_equinox.dts
index 90d52cc416dc..5da00806c41e 100644
--- a/arch/arm/boot/dts/cx92755_equinox.dts
+++ b/arch/arm/boot/dts/cx92755_equinox.dts
@@ -64,8 +64,7 @@
 	};
 
 	chosen {
-		bootargs = "console=ttyS0,115200";
-		stdout-path = &uart0;
+		stdout-path = "serial0:115200n8";
 	};
 };
 
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
new file mode 100644
index 000000000000..92bacd3c8fab
--- /dev/null
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -0,0 +1,28 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+#include "dm814x.dtsi"
+
+/ {
+	model = "DM8148 EVM";
+	compatible = "ti,dm8148-evm", "ti,dm8148";
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x40000000>;	/* 1 GB */
+	};
+};
+
+&cpsw_emac0 {
+	phy_id = <&davinci_mdio>, <0>;
+	phy-mode = "mii";
+};
+
+&cpsw_emac1 {
+	phy_id = <&davinci_mdio>, <1>;
+	phy-mode = "mii";
+};
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
new file mode 100644
index 000000000000..8c4bbc7573df
--- /dev/null
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -0,0 +1,28 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+#include "dm814x.dtsi"
+
+/ {
+	model = "DM8148 EVM";
+	compatible = "hp,t410", "ti,dm8148";
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x40000000>;	/* 1 GB */
+	};
+};
+
+&cpsw_emac0 {
+	phy_id = <&davinci_mdio>, <0>;
+	phy-mode = "mii";
+};
+
+&cpsw_emac1 {
+	phy_id = <&davinci_mdio>, <1>;
+	phy-mode = "mii";
+};
diff --git a/arch/arm/boot/dts/dm814x-clocks.dtsi b/arch/arm/boot/dts/dm814x-clocks.dtsi
new file mode 100644
index 000000000000..ef1e8e7a6cc6
--- /dev/null
+++ b/arch/arm/boot/dts/dm814x-clocks.dtsi
@@ -0,0 +1,109 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+&scm_clocks {
+
+	tclkin_ck: tclkin_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <32768>;
+	};
+
+	devosc_ck: devosc_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <20000000>;
+	};
+
+	/* Optional auxosc, 20 - 30 MHz range, assume 27 MHz by default */
+	auxosc_ck: auxosc_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <27000000>;
+	};
+
+	mpu_ck: mpu_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <1000000000>;
+	};
+
+	sysclk4_ck: sysclk4_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <222000000>;
+	};
+
+	sysclk6_ck: sysclk6_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <100000000>;
+	};
+
+	sysclk10_ck: sysclk10_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <48000000>;
+	};
+
+	sysclk18_ck: sysclk18_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <32768>;
+	};
+
+        cpsw_125mhz_gclk: cpsw_125mhz_gclk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <125000000>;
+	};
+
+	cpsw_cpts_rft_clk: cpsw_cpts_rft_clk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <250000000>;
+	};
+
+};
+
+&pllss_clocks {
+
+	aud_clkin0_ck: aud_clkin0_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <20000000>;
+	};
+
+	aud_clkin1_ck: aud_clkin1_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <20000000>;
+	};
+
+	aud_clkin2_ck: aud_clkin2_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <20000000>;
+	};
+
+	timer1_mux_ck: timer1_mux_ck {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sysclk18_ck &aud_clkin0_ck &aud_clkin1_ck
+			  &aud_clkin2_ck &devosc_ck &auxosc_ck &tclkin_ck>;
+		ti,bit-shift = <3>;
+		reg = <0x2e0>;
+	};
+
+	timer2_mux_ck: timer2_mux_ck {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sysclk18_ck &aud_clkin0_ck &aud_clkin1_ck
+			  &aud_clkin2_ck &devosc_ck &auxosc_ck &tclkin_ck>;
+		ti,bit-shift = <6>;
+		reg = <0x2e0>;
+	};
+};
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
new file mode 100644
index 000000000000..972c9c9e885b
--- /dev/null
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -0,0 +1,333 @@
+/*
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/omap.h>
+
+#include "skeleton.dtsi"
+
+/ {
+	compatible = "ti,dm814";
+	interrupt-parent = <&intc>;
+
+	aliases {
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		ethernet0 = &cpsw_emac0;
+		ethernet1 = &cpsw_emac1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			compatible = "arm,cortex-a8";
+			device_type = "cpu";
+			reg = <0>;
+		};
+	};
+
+	pmu {
+		compatible = "arm,cortex-a8-pmu";
+		interrupts = <3>;
+	};
+
+	/*
+	 * The soc node represents the soc top level view. It is used for IPs
+	 * that are not memory mapped in the MPU view or for the MPU itself.
+	 */
+	soc {
+		compatible = "ti,omap-infra";
+		mpu {
+			compatible = "ti,omap3-mpu";
+			ti,hwmods = "mpu";
+		};
+	};
+
+	ocp {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+		ti,hwmods = "l3_main";
+
+		/*
+		 * See TRM "Table 1-317. L4LS Instance Summary", just deduct
+		 * 0x1000 from the 1-317 addresses to get the device address
+		 */
+		l4ls: l4ls@48000000 {
+			compatible = "ti,dm814-l4ls", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x48000000 0x2000000>;
+
+			i2c1: i2c@28000 {
+				compatible = "ti,omap4-i2c";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				ti,hwmods = "i2c1";
+				reg = <0x28000 0x1000>;
+				interrupts = <70>;
+			};
+
+			elm: elm@80000 {
+				compatible = "ti,814-elm";
+				ti,hwmods = "elm";
+				reg = <0x80000 0x2000>;
+				interrupts = <4>;
+			};
+
+			gpio1: gpio@32000 {
+				compatible = "ti,omap4-gpio";
+				ti,hwmods = "gpio1";
+				ti,gpio-always-on;
+				reg = <0x32000 0x2000>;
+				interrupts = <96>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio2: gpio@4c000 {
+				compatible = "ti,omap4-gpio";
+				ti,hwmods = "gpio2";
+				ti,gpio-always-on;
+				reg = <0x4c000 0x2000>;
+				interrupts = <98>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			i2c2: i2c@2a000 {
+				compatible = "ti,omap4-i2c";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				ti,hwmods = "i2c2";
+				reg = <0x2a000 0x1000>;
+				interrupts = <71>;
+			};
+
+			mcspi1: spi@30000 {
+				compatible = "ti,omap4-mcspi";
+				reg = <0x30000 0x1000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <65>;
+				ti,spi-num-cs = <4>;
+				ti,hwmods = "mcspi1";
+				dmas = <&edma 16 &edma 17
+					&edma 18 &edma 19>;
+				dma-names = "tx0", "rx0", "tx1", "rx1";
+			};
+
+			timer1: timer@2e000 {
+				compatible = "ti,dm814-timer";
+				reg = <0x2e000 0x2000>;
+				interrupts = <67>;
+				ti,hwmods = "timer1";
+				ti,timer-alwon;
+			};
+
+			uart1: uart@20000 {
+				compatible = "ti,omap3-uart";
+				ti,hwmods = "uart1";
+				reg = <0x20000 0x2000>;
+				clock-frequency = <48000000>;
+				interrupts = <72>;
+				dmas = <&edma 26 &edma 27>;
+				dma-names = "tx", "rx";
+			};
+
+			uart2: uart@22000 {
+				compatible = "ti,omap3-uart";
+				ti,hwmods = "uart2";
+				reg = <0x22000 0x2000>;
+				clock-frequency = <48000000>;
+				interrupts = <73>;
+				dmas = <&edma 28 &edma 29>;
+				dma-names = "tx", "rx";
+			};
+
+			uart3: uart@24000 {
+				compatible = "ti,omap3-uart";
+				ti,hwmods = "uart3";
+				reg = <0x24000 0x2000>;
+				clock-frequency = <48000000>;
+				interrupts = <74>;
+				dmas = <&edma 30 &edma 31>;
+				dma-names = "tx", "rx";
+			};
+
+			timer2: timer@40000 {
+				compatible = "ti,dm814-timer";
+				reg = <0x40000 0x2000>;
+				interrupts = <68>;
+				ti,hwmods = "timer2";
+			};
+
+			timer3: timer@42000 {
+				compatible = "ti,dm814-timer";
+				reg = <0x42000 0x2000>;
+				interrupts = <69>;
+				ti,hwmods = "timer3";
+			};
+
+			control: control@160000 {
+				compatible = "ti,dm814-scm", "simple-bus";
+				reg = <0x160000 0x16d000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x160000 0x16d000>;
+
+				scm_conf: scm_conf@0 {
+					compatible = "syscon";
+					reg = <0x0 0x800>;
+					#address-cells = <1>;
+					#size-cells = <1>;
+
+					scm_clocks: clocks {
+						#address-cells = <1>;
+						#size-cells = <0>;
+					};
+
+					scm_clockdomains: clockdomains {
+					};
+				};
+
+				pincntl: pinmux@800 {
+					compatible = "pinctrl-single";
+					reg = <0x800 0xc38>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+					pinctrl-single,register-width = <32>;
+					pinctrl-single,function-mask = <0x300ff>;
+				};
+			};
+
+			prcm: prcm@180000 {
+				compatible = "ti,dm814-prcm", "simple-bus";
+				reg = <0x180000 0x4000>;
+
+				prcm_clocks: clocks {
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+
+				prcm_clockdomains: clockdomains {
+				};
+			};
+
+			pllss: pllss@1c5000 {
+				compatible = "ti,dm814-pllss", "simple-bus";
+				reg = <0x1c5000 0x2000>;
+
+				pllss_clocks: clocks {
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+
+				pllss_clockdomains: clockdomains {
+				};
+			};
+
+			wdt1: wdt@1c7000 {
+				compatible = "ti,omap3-wdt";
+				ti,hwmods = "wd_timer";
+				reg = <0x1c7000 0x1000>;
+				interrupts = <91>;
+			};
+		};
+
+		intc: interrupt-controller@48200000 {
+			compatible = "ti,dm814-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			reg = <0x48200000 0x1000>;
+		};
+
+		edma: edma@49000000 {
+			compatible = "ti,edma3";
+			ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
+			reg =	<0x49000000 0x10000>,
+				<0x44e10f90 0x40>;
+			interrupts = <12 13 14>;
+			#dma-cells = <1>;
+		};
+
+		/* See TRM "Table 1-318. L4HS Instance Summary" */
+		l4hs: l4hs@4a000000 {
+			compatible = "ti,dm814-l4hs", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x4a000000 0x1b4040>;
+		};
+
+		/* REVISIT: Move to live under l4hs once driver is fixed */
+		mac: ethernet@4a100000 {
+			compatible = "ti,cpsw";
+			ti,hwmods = "cpgmac0";
+			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
+			clock-names = "fck", "cpts";
+			cpdma_channels = <8>;
+			ale_entries = <1024>;
+			bd_ram_size = <0x2000>;
+			no_bd_ram = <0>;
+			rx_descs = <64>;
+			mac_control = <0x20>;
+			slaves = <2>;
+			active_slave = <0>;
+			cpts_clock_mult = <0x80000000>;
+			cpts_clock_shift = <29>;
+			reg = <0x4a100000 0x800
+			       0x4a100900 0x100>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			interrupt-parent = <&intc>;
+			/*
+			 * c0_rx_thresh_pend
+			 * c0_rx_pend
+			 * c0_tx_pend
+			 * c0_misc_pend
+			 */
+			interrupts = <40 41 42 43>;
+			ranges;
+			syscon = <&scm_conf>;
+
+			davinci_mdio: mdio@4a100800 {
+				compatible = "ti,davinci_mdio";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				ti,hwmods = "davinci_mdio";
+				bus_freq = <1000000>;
+				reg = <0x4a100800 0x100>;
+			};
+
+			cpsw_emac0: slave@4a100200 {
+				/* Filled in by U-Boot */
+				mac-address = [ 00 00 00 00 00 00 ];
+			};
+
+			cpsw_emac1: slave@4a100300 {
+				/* Filled in by U-Boot */
+				mac-address = [ 00 00 00 00 00 00 ];
+			};
+
+			phy_sel: cpsw-phy-sel@0x48160650 {
+				compatible = "ti,am3352-cpsw-phy-sel";
+				reg= <0x48160650 0x4>;
+				reg-names = "gmii-sel";
+			};
+		};
+	};
+};
+
+#include "dm814x-clocks.dtsi"
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 289806adb343..3c99cfa1a876 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -58,7 +58,7 @@
 	 * the whole bus hierarchy.
 	 */
 	ocp {
-		compatible = "ti,omap3-l3-smx", "simple-bus";
+		compatible = "simple-bus";
 		reg = <0x44000000 0x10000>;
 		interrupts = <9 10>;
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index 38b1f7e6004e..179121630ad7 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -419,293 +419,325 @@
 				status = "disabled";
 			};
 
-			thermal: thermal-diode@d001c {
-				compatible = "marvell,dove-thermal";
-				reg = <0xd001c 0x0c>, <0xd005c 0x08>;
-			};
-
-			gate_clk: clock-gating-ctrl@d0038 {
-				compatible = "marvell,dove-gating-clock";
-				reg = <0xd0038 0x4>;
-				clocks = <&core_clk 0>;
-				#clock-cells = <1>;
-			};
-
-			pinctrl: pin-ctrl@d0200 {
-				compatible = "marvell,dove-pinctrl";
-				reg = <0xd0200 0x14>,
-				      <0xd0440 0x04>;
-				clocks = <&gate_clk 22>;
-
-				pmx_gpio_0: pmx-gpio-0 {
-					marvell,pins = "mpp0";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_1: pmx-gpio-1 {
-					marvell,pins = "mpp1";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_2: pmx-gpio-2 {
-					marvell,pins = "mpp2";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_3: pmx-gpio-3 {
-					marvell,pins = "mpp3";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_4: pmx-gpio-4 {
-					marvell,pins = "mpp4";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_5: pmx-gpio-5 {
-					marvell,pins = "mpp5";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_6: pmx-gpio-6 {
-					marvell,pins = "mpp6";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_7: pmx-gpio-7 {
-					marvell,pins = "mpp7";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_8: pmx-gpio-8 {
-					marvell,pins = "mpp8";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_9: pmx-gpio-9 {
-					marvell,pins = "mpp9";
-					marvell,function = "gpio";
-				};
-
-				pmx_pcie1_clkreq: pmx-pcie1-clkreq {
-					marvell,pins = "mpp9";
-					marvell,function = "pex1";
-				};
-
-				pmx_gpio_10: pmx-gpio-10 {
-					marvell,pins = "mpp10";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_11: pmx-gpio-11 {
-					marvell,pins = "mpp11";
-					marvell,function = "gpio";
-				};
-
-				pmx_pcie0_clkreq: pmx-pcie0-clkreq {
-					marvell,pins = "mpp11";
-					marvell,function = "pex0";
-				};
-
-				pmx_gpio_12: pmx-gpio-12 {
-					marvell,pins = "mpp12";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_13: pmx-gpio-13 {
-					marvell,pins = "mpp13";
-					marvell,function = "gpio";
-				};
-
-				pmx_audio1_extclk: pmx-audio1-extclk {
-					marvell,pins = "mpp13";
-					marvell,function = "audio1";
-				};
-
-				pmx_gpio_14: pmx-gpio-14 {
-					marvell,pins = "mpp14";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_15: pmx-gpio-15 {
-					marvell,pins = "mpp15";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_16: pmx-gpio-16 {
-					marvell,pins = "mpp16";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_17: pmx-gpio-17 {
-					marvell,pins = "mpp17";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_18: pmx-gpio-18 {
-					marvell,pins = "mpp18";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_19: pmx-gpio-19 {
-					marvell,pins = "mpp19";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_20: pmx-gpio-20 {
-					marvell,pins = "mpp20";
-					marvell,function = "gpio";
-				};
-
-				pmx_gpio_21: pmx-gpio-21 {
-					marvell,pins = "mpp21";
-					marvell,function = "gpio";
-				};
-
-				pmx_camera: pmx-camera {
-					marvell,pins = "mpp_camera";
-					marvell,function = "camera";
-				};
-
-				pmx_camera_gpio: pmx-camera-gpio {
-					marvell,pins = "mpp_camera";
-					marvell,function = "gpio";
-				};
-
-				pmx_sdio0: pmx-sdio0 {
-					marvell,pins = "mpp_sdio0";
-					marvell,function = "sdio0";
-				};
-
-				pmx_sdio0_gpio: pmx-sdio0-gpio {
-					marvell,pins = "mpp_sdio0";
-					marvell,function = "gpio";
-				};
-
-				pmx_sdio1: pmx-sdio1 {
-					marvell,pins = "mpp_sdio1";
-					marvell,function = "sdio1";
-				};
-
-				pmx_sdio1_gpio: pmx-sdio1-gpio {
-					marvell,pins = "mpp_sdio1";
-					marvell,function = "gpio";
-				};
-
-				pmx_audio1_gpio: pmx-audio1-gpio {
-					marvell,pins = "mpp_audio1";
-					marvell,function = "gpio";
-				};
-
-				pmx_audio1_i2s1_spdifo: pmx-audio1-i2s1-spdifo {
-					marvell,pins = "mpp_audio1";
-					marvell,function = "i2s1/spdifo";
-				};
-
-				pmx_spi0: pmx-spi0 {
-					marvell,pins = "mpp_spi0";
-					marvell,function = "spi0";
-				};
-
-				pmx_spi0_gpio: pmx-spi0-gpio {
-					marvell,pins = "mpp_spi0";
-					marvell,function = "gpio";
-				};
-
-				pmx_spi1_4_7: pmx-spi1-4-7 {
-					marvell,pins = "mpp4", "mpp5",
-						"mpp6", "mpp7";
-					marvell,function = "spi1";
-				};
-
-				pmx_spi1_20_23: pmx-spi1-20-23 {
-					marvell,pins = "mpp20", "mpp21",
-						"mpp22", "mpp23";
-					marvell,function = "spi1";
-				};
-
-				pmx_uart1: pmx-uart1 {
-					marvell,pins = "mpp_uart1";
-					marvell,function = "uart1";
-				};
-
-				pmx_uart1_gpio: pmx-uart1-gpio {
-					marvell,pins = "mpp_uart1";
-					marvell,function = "gpio";
-				};
-
-				pmx_nand: pmx-nand {
-					marvell,pins = "mpp_nand";
-					marvell,function = "nand";
-				};
-
-				pmx_nand_gpo: pmx-nand-gpo {
-					marvell,pins = "mpp_nand";
-					marvell,function = "gpo";
-				};
-
-				pmx_i2c1: pmx-i2c1 {
-					marvell,pins = "mpp17", "mpp19";
-					marvell,function = "twsi";
-				};
-
-				pmx_i2c2: pmx-i2c2 {
-					marvell,pins = "mpp_audio1";
-					marvell,function = "twsi";
-				};
-
-				pmx_ssp_i2c2: pmx-ssp-i2c2 {
-					marvell,pins = "mpp_audio1";
-					marvell,function = "ssp/twsi";
-				};
-
-				pmx_i2cmux_0: pmx-i2cmux-0 {
-					marvell,pins = "twsi";
-					marvell,function = "twsi-opt1";
-				};
-
-				pmx_i2cmux_1: pmx-i2cmux-1 {
-					marvell,pins = "twsi";
-					marvell,function = "twsi-opt2";
-				};
-
-				pmx_i2cmux_2: pmx-i2cmux-2 {
-					marvell,pins = "twsi";
-					marvell,function = "twsi-opt3";
-				};
-			};
-
-			core_clk: core-clocks@d0214 {
-				compatible = "marvell,dove-core-clock";
-				reg = <0xd0214 0x4>;
-				#clock-cells = <1>;
-			};
-
-			gpio0: gpio-ctrl@d0400 {
-				compatible = "marvell,orion-gpio";
-				#gpio-cells = <2>;
-				gpio-controller;
-				reg = <0xd0400 0x20>;
-				ngpios = <32>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				interrupts = <12>, <13>, <14>, <60>;
-			};
-
-			gpio1: gpio-ctrl@d0420 {
-				compatible = "marvell,orion-gpio";
-				#gpio-cells = <2>;
-				gpio-controller;
-				reg = <0xd0420 0x20>;
-				ngpios = <32>;
+			pmu: power-management@d0000 {
+				compatible = "marvell,dove-pmu", "simple-bus";
+				reg = <0xd0000 0x8000>, <0xd8000 0x8000>;
+				ranges = <0x00000000 0x000d0000 0x8000
+					  0x00008000 0x000d8000 0x8000>;
+				interrupts = <33>;
 				interrupt-controller;
-				#interrupt-cells = <2>;
-				interrupts = <61>;
-			};
-
-			rtc: real-time-clock@d8500 {
-				compatible = "marvell,orion-rtc";
-				reg = <0xd8500 0x20>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				#interrupt-cells = <1>;
+				#reset-cells = <1>;
+
+				domains {
+					vpu_domain: vpu-domain {
+						#power-domain-cells = <0>;
+						marvell,pmu_pwr_mask = <0x00000008>;
+						marvell,pmu_iso_mask = <0x00000001>;
+						resets = <&pmu 16>;
+					};
+
+					gpu_domain: gpu-domain {
+						#power-domain-cells = <0>;
+						marvell,pmu_pwr_mask = <0x00000004>;
+						marvell,pmu_iso_mask = <0x00000002>;
+						resets = <&pmu 18>;
+					};
+				};
+
+				thermal: thermal-diode@001c {
+					compatible = "marvell,dove-thermal";
+					reg = <0x001c 0x0c>, <0x005c 0x08>;
+				};
+
+				gate_clk: clock-gating-ctrl@0038 {
+					compatible = "marvell,dove-gating-clock";
+					reg = <0x0038 0x4>;
+					clocks = <&core_clk 0>;
+					#clock-cells = <1>;
+				};
+
+				pinctrl: pin-ctrl@0200 {
+					compatible = "marvell,dove-pinctrl";
+					reg = <0x0200 0x14>,
+					      <0x0440 0x04>;
+					clocks = <&gate_clk 22>;
+
+					pmx_gpio_0: pmx-gpio-0 {
+						marvell,pins = "mpp0";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_1: pmx-gpio-1 {
+						marvell,pins = "mpp1";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_2: pmx-gpio-2 {
+						marvell,pins = "mpp2";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_3: pmx-gpio-3 {
+						marvell,pins = "mpp3";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_4: pmx-gpio-4 {
+						marvell,pins = "mpp4";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_5: pmx-gpio-5 {
+						marvell,pins = "mpp5";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_6: pmx-gpio-6 {
+						marvell,pins = "mpp6";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_7: pmx-gpio-7 {
+						marvell,pins = "mpp7";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_8: pmx-gpio-8 {
+						marvell,pins = "mpp8";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_9: pmx-gpio-9 {
+						marvell,pins = "mpp9";
+						marvell,function = "gpio";
+					};
+
+					pmx_pcie1_clkreq: pmx-pcie1-clkreq {
+						marvell,pins = "mpp9";
+						marvell,function = "pex1";
+					};
+
+					pmx_gpio_10: pmx-gpio-10 {
+						marvell,pins = "mpp10";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_11: pmx-gpio-11 {
+						marvell,pins = "mpp11";
+						marvell,function = "gpio";
+					};
+
+					pmx_pcie0_clkreq: pmx-pcie0-clkreq {
+						marvell,pins = "mpp11";
+						marvell,function = "pex0";
+					};
+
+					pmx_gpio_12: pmx-gpio-12 {
+						marvell,pins = "mpp12";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_13: pmx-gpio-13 {
+						marvell,pins = "mpp13";
+						marvell,function = "gpio";
+					};
+
+					pmx_audio1_extclk: pmx-audio1-extclk {
+						marvell,pins = "mpp13";
+						marvell,function = "audio1";
+					};
+
+					pmx_gpio_14: pmx-gpio-14 {
+						marvell,pins = "mpp14";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_15: pmx-gpio-15 {
+						marvell,pins = "mpp15";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_16: pmx-gpio-16 {
+						marvell,pins = "mpp16";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_17: pmx-gpio-17 {
+						marvell,pins = "mpp17";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_18: pmx-gpio-18 {
+						marvell,pins = "mpp18";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_19: pmx-gpio-19 {
+						marvell,pins = "mpp19";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_20: pmx-gpio-20 {
+						marvell,pins = "mpp20";
+						marvell,function = "gpio";
+					};
+
+					pmx_gpio_21: pmx-gpio-21 {
+						marvell,pins = "mpp21";
+						marvell,function = "gpio";
+					};
+
+					pmx_camera: pmx-camera {
+						marvell,pins = "mpp_camera";
+						marvell,function = "camera";
+					};
+
+					pmx_camera_gpio: pmx-camera-gpio {
+						marvell,pins = "mpp_camera";
+						marvell,function = "gpio";
+					};
+
+					pmx_sdio0: pmx-sdio0 {
+						marvell,pins = "mpp_sdio0";
+						marvell,function = "sdio0";
+					};
+
+					pmx_sdio0_gpio: pmx-sdio0-gpio {
+						marvell,pins = "mpp_sdio0";
+						marvell,function = "gpio";
+					};
+
+					pmx_sdio1: pmx-sdio1 {
+						marvell,pins = "mpp_sdio1";
+						marvell,function = "sdio1";
+					};
+
+					pmx_sdio1_gpio: pmx-sdio1-gpio {
+						marvell,pins = "mpp_sdio1";
+						marvell,function = "gpio";
+					};
+
+					pmx_audio1_gpio: pmx-audio1-gpio {
+						marvell,pins = "mpp_audio1";
+						marvell,function = "gpio";
+					};
+
+					pmx_audio1_i2s1_spdifo: pmx-audio1-i2s1-spdifo {
+						marvell,pins = "mpp_audio1";
+						marvell,function = "i2s1/spdifo";
+					};
+
+					pmx_spi0: pmx-spi0 {
+						marvell,pins = "mpp_spi0";
+						marvell,function = "spi0";
+					};
+
+					pmx_spi0_gpio: pmx-spi0-gpio {
+						marvell,pins = "mpp_spi0";
+						marvell,function = "gpio";
+					};
+
+					pmx_spi1_4_7: pmx-spi1-4-7 {
+						marvell,pins = "mpp4", "mpp5",
+							"mpp6", "mpp7";
+						marvell,function = "spi1";
+					};
+
+					pmx_spi1_20_23: pmx-spi1-20-23 {
+						marvell,pins = "mpp20", "mpp21",
+							"mpp22", "mpp23";
+						marvell,function = "spi1";
+					};
+
+					pmx_uart1: pmx-uart1 {
+						marvell,pins = "mpp_uart1";
+						marvell,function = "uart1";
+					};
+
+					pmx_uart1_gpio: pmx-uart1-gpio {
+						marvell,pins = "mpp_uart1";
+						marvell,function = "gpio";
+					};
+
+					pmx_nand: pmx-nand {
+						marvell,pins = "mpp_nand";
+						marvell,function = "nand";
+					};
+
+					pmx_nand_gpo: pmx-nand-gpo {
+						marvell,pins = "mpp_nand";
+						marvell,function = "gpo";
+					};
+
+					pmx_i2c1: pmx-i2c1 {
+						marvell,pins = "mpp17", "mpp19";
+						marvell,function = "twsi";
+					};
+
+					pmx_i2c2: pmx-i2c2 {
+						marvell,pins = "mpp_audio1";
+						marvell,function = "twsi";
+					};
+
+					pmx_ssp_i2c2: pmx-ssp-i2c2 {
+						marvell,pins = "mpp_audio1";
+						marvell,function = "ssp/twsi";
+					};
+
+					pmx_i2cmux_0: pmx-i2cmux-0 {
+						marvell,pins = "twsi";
+						marvell,function = "twsi-opt1";
+					};
+
+					pmx_i2cmux_1: pmx-i2cmux-1 {
+						marvell,pins = "twsi";
+						marvell,function = "twsi-opt2";
+					};
+
+					pmx_i2cmux_2: pmx-i2cmux-2 {
+						marvell,pins = "twsi";
+						marvell,function = "twsi-opt3";
+					};
+				};
+
+				core_clk: core-clocks@0214 {
+					compatible = "marvell,dove-core-clock";
+					reg = <0x0214 0x4>;
+					#clock-cells = <1>;
+				};
+
+				gpio0: gpio-ctrl@0400 {
+					compatible = "marvell,orion-gpio";
+					#gpio-cells = <2>;
+					gpio-controller;
+					reg = <0x0400 0x20>;
+					ngpios = <32>;
+					interrupt-controller;
+					#interrupt-cells = <2>;
+					interrupt-parent = <&intc>;
+					interrupts = <12>, <13>, <14>, <60>;
+				};
+
+				gpio1: gpio-ctrl@0420 {
+					compatible = "marvell,orion-gpio";
+					#gpio-cells = <2>;
+					gpio-controller;
+					reg = <0x0420 0x20>;
+					ngpios = <32>;
+					interrupt-controller;
+					#interrupt-cells = <2>;
+					interrupt-parent = <&intc>;
+					interrupts = <61>;
+				};
+
+				rtc: real-time-clock@8500 {
+					compatible = "marvell,orion-rtc";
+					reg = <0x8500 0x20>;
+					interrupts = <5>;
+				};
 			};
 
 			gconf: global-config@e802c {
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index aa465904f6cc..a6c82e5b64fe 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -19,6 +19,15 @@
 		reg = <0x80000000 0x60000000>; /* 1536 MB */
 	};
 
+	evm_3v3_sd: fixedregulator-sd {
+		compatible = "regulator-fixed";
+		regulator-name = "evm_3v3_sd";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		enable-active-high;
+		gpio = <&pcf_gpio_21 5 GPIO_ACTIVE_HIGH>;
+	};
+
 	mmc2_3v3: fixedregulator-mmc2 {
 		compatible = "regulator-fixed";
 		regulator-name = "mmc2_3v3";
@@ -349,6 +358,7 @@
 					regulator-name = "ldo1";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <3300000>;
+					regulator-always-on;
 					regulator-boot-on;
 				};
 
@@ -462,8 +472,14 @@
 
 &mmc1 {
 	status = "okay";
-	vmmc-supply = <&ldo1_reg>;
+	vmmc-supply = <&evm_3v3_sd>;
+	vmmc_aux-supply = <&ldo1_reg>;
 	bus-width = <4>;
+	/*
+	 * SDCD signal is not being used here - using the fact that GPIO mode
+	 * is always hardwired.
+	 */
+	cd-gpios = <&gpio6 27 0>;
 };
 
 &mmc2 {
@@ -686,7 +702,8 @@
 
 &dcan1 {
 	status = "ok";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&dcan1_pins_default>;
+	pinctrl-names = "default", "sleep", "active";
+	pinctrl-0 = <&dcan1_pins_sleep>;
 	pinctrl-1 = <&dcan1_pins_sleep>;
+	pinctrl-2 = <&dcan1_pins_default>;
 };
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 8f1e25bcecbd..5d65db9ebc2b 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -116,7 +116,7 @@
 				ranges = <0 0x2000 0x2000>;
 
 				scm_conf: scm_conf@0 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x0 0x1400>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -141,7 +141,7 @@
 				dra7_pmx_core: pinmux@1400 {
 					compatible = "ti,dra7-padconf",
 						     "pinctrl-single";
-					reg = <0x1400 0x0464>;
+					reg = <0x1400 0x0468>;
 					#address-cells = <1>;
 					#size-cells = <0>;
 					#interrupt-cells = <1>;
@@ -149,6 +149,11 @@
 					pinctrl-single,register-width = <32>;
 					pinctrl-single,function-mask = <0x3fffffff>;
 				};
+
+				scm_conf1: scm_conf@1c04 {
+					compatible = "syscon";
+					reg = <0x1c04 0x0020>;
+				};
 			};
 
 			cm_core_aon: cm_core_aon@5000 {
@@ -211,7 +216,7 @@
 			#address-cells = <1>;
 			ranges = <0x51000000 0x51000000 0x3000
 				  0x0	     0x20000000 0x10000000>;
-			pcie@51000000 {
+			pcie1: pcie@51000000 {
 				compatible = "ti,dra7-pcie";
 				reg = <0x51000000 0x2000>, <0x51002000 0x14c>, <0x1000 0x2000>;
 				reg-names = "rc_dbics", "ti_conf", "config";
@@ -286,16 +291,6 @@
 				#thermal-sensor-cells = <1>;
 		};
 
-		dra7_ctrl_core: ctrl_core@4a002000 {
-			compatible = "syscon";
-			reg = <0x4a002000 0x6d0>;
-		};
-
-		dra7_ctrl_general: tisyscon@4a002e00 {
-			compatible = "syscon";
-			reg = <0x4a002e00 0x7c>;
-		};
-
 		sdma: dma-controller@4a056000 {
 			compatible = "ti,omap4430-sdma";
 			reg = <0x4a056000 0x1000>;
@@ -308,6 +303,15 @@
 			dma-requests = <127>;
 		};
 
+		sdma_xbar: dma-router@4a002b78 {
+			compatible = "ti,dra7-dma-crossbar";
+			reg = <0x4a002b78 0xfc>;
+			#dma-cells = <1>;
+			dma-requests = <205>;
+			ti,dma-safe-map = <0>;
+			dma-masters = <&sdma>;
+		};
+
 		gpio1: gpio@4ae10000 {
 			compatible = "ti,omap4-gpio";
 			reg = <0x4ae10000 0x200>;
@@ -397,73 +401,73 @@
 		};
 
 		uart1: serial@4806a000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x4806a000 0x100>;
 			interrupts-extended = <&crossbar_mpu GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart1";
 			clock-frequency = <48000000>;
 			status = "disabled";
-			dmas = <&sdma 49>, <&sdma 50>;
+			dmas = <&sdma_xbar 49>, <&sdma_xbar 50>;
 			dma-names = "tx", "rx";
 		};
 
 		uart2: serial@4806c000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x4806c000 0x100>;
 			interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart2";
 			clock-frequency = <48000000>;
 			status = "disabled";
-			dmas = <&sdma 51>, <&sdma 52>;
+			dmas = <&sdma_xbar 51>, <&sdma_xbar 52>;
 			dma-names = "tx", "rx";
 		};
 
 		uart3: serial@48020000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x48020000 0x100>;
 			interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart3";
 			clock-frequency = <48000000>;
 			status = "disabled";
-			dmas = <&sdma 53>, <&sdma 54>;
+			dmas = <&sdma_xbar 53>, <&sdma_xbar 54>;
 			dma-names = "tx", "rx";
 		};
 
 		uart4: serial@4806e000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x4806e000 0x100>;
 			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart4";
 			clock-frequency = <48000000>;
                         status = "disabled";
-			dmas = <&sdma 55>, <&sdma 56>;
+			dmas = <&sdma_xbar 55>, <&sdma_xbar 56>;
 			dma-names = "tx", "rx";
 		};
 
 		uart5: serial@48066000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x48066000 0x100>;
 			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart5";
 			clock-frequency = <48000000>;
 			status = "disabled";
-			dmas = <&sdma 63>, <&sdma 64>;
+			dmas = <&sdma_xbar 63>, <&sdma_xbar 64>;
 			dma-names = "tx", "rx";
 		};
 
 		uart6: serial@48068000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x48068000 0x100>;
 			interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart6";
 			clock-frequency = <48000000>;
 			status = "disabled";
-			dmas = <&sdma 79>, <&sdma 80>;
+			dmas = <&sdma_xbar 79>, <&sdma_xbar 80>;
 			dma-names = "tx", "rx";
 		};
 
 		uart7: serial@48420000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x48420000 0x100>;
 			interrupts = <GIC_SPI 218 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart7";
@@ -472,7 +476,7 @@
 		};
 
 		uart8: serial@48422000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x48422000 0x100>;
 			interrupts = <GIC_SPI 219 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart8";
@@ -481,7 +485,7 @@
 		};
 
 		uart9: serial@48424000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x48424000 0x100>;
 			interrupts = <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart9";
@@ -490,7 +494,7 @@
 		};
 
 		uart10: serial@4ae2b000 {
-			compatible = "ti,omap4-uart";
+			compatible = "ti,dra742-uart", "ti,omap4-uart";
 			reg = <0x4ae2b000 0x100>;
 			interrupts = <GIC_SPI 221 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "uart10";
@@ -867,7 +871,7 @@
 			ti,hwmods = "mmc1";
 			ti,dual-volt;
 			ti,needs-special-reset;
-			dmas = <&sdma 61>, <&sdma 62>;
+			dmas = <&sdma_xbar 61>, <&sdma_xbar 62>;
 			dma-names = "tx", "rx";
 			status = "disabled";
 			pbias-supply = <&pbias_mmc_reg>;
@@ -879,7 +883,7 @@
 			interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmc2";
 			ti,needs-special-reset;
-			dmas = <&sdma 47>, <&sdma 48>;
+			dmas = <&sdma_xbar 47>, <&sdma_xbar 48>;
 			dma-names = "tx", "rx";
 			status = "disabled";
 		};
@@ -890,7 +894,7 @@
 			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmc3";
 			ti,needs-special-reset;
-			dmas = <&sdma 77>, <&sdma 78>;
+			dmas = <&sdma_xbar 77>, <&sdma_xbar 78>;
 			dma-names = "tx", "rx";
 			status = "disabled";
 		};
@@ -901,7 +905,7 @@
 			interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmc4";
 			ti,needs-special-reset;
-			dmas = <&sdma 57>, <&sdma 58>;
+			dmas = <&sdma_xbar 57>, <&sdma_xbar 58>;
 			dma-names = "tx", "rx";
 			status = "disabled";
 		};
@@ -1046,14 +1050,14 @@
 			#size-cells = <0>;
 			ti,hwmods = "mcspi1";
 			ti,spi-num-cs = <4>;
-			dmas = <&sdma 35>,
-			       <&sdma 36>,
-			       <&sdma 37>,
-			       <&sdma 38>,
-			       <&sdma 39>,
-			       <&sdma 40>,
-			       <&sdma 41>,
-			       <&sdma 42>;
+			dmas = <&sdma_xbar 35>,
+			       <&sdma_xbar 36>,
+			       <&sdma_xbar 37>,
+			       <&sdma_xbar 38>,
+			       <&sdma_xbar 39>,
+			       <&sdma_xbar 40>,
+			       <&sdma_xbar 41>,
+			       <&sdma_xbar 42>;
 			dma-names = "tx0", "rx0", "tx1", "rx1",
 				    "tx2", "rx2", "tx3", "rx3";
 			status = "disabled";
@@ -1067,10 +1071,10 @@
 			#size-cells = <0>;
 			ti,hwmods = "mcspi2";
 			ti,spi-num-cs = <2>;
-			dmas = <&sdma 43>,
-			       <&sdma 44>,
-			       <&sdma 45>,
-			       <&sdma 46>;
+			dmas = <&sdma_xbar 43>,
+			       <&sdma_xbar 44>,
+			       <&sdma_xbar 45>,
+			       <&sdma_xbar 46>;
 			dma-names = "tx0", "rx0", "tx1", "rx1";
 			status = "disabled";
 		};
@@ -1083,7 +1087,7 @@
 			#size-cells = <0>;
 			ti,hwmods = "mcspi3";
 			ti,spi-num-cs = <2>;
-			dmas = <&sdma 15>, <&sdma 16>;
+			dmas = <&sdma_xbar 15>, <&sdma_xbar 16>;
 			dma-names = "tx0", "rx0";
 			status = "disabled";
 		};
@@ -1096,7 +1100,7 @@
 			#size-cells = <0>;
 			ti,hwmods = "mcspi4";
 			ti,spi-num-cs = <1>;
-			dmas = <&sdma 70>, <&sdma 71>;
+			dmas = <&sdma_xbar 70>, <&sdma_xbar 71>;
 			dma-names = "tx0", "rx0";
 			status = "disabled";
 		};
@@ -1140,6 +1144,7 @@
 				ctrl-module = <&omap_control_sata>;
 				clocks = <&sys_clkin1>, <&sata_ref_clk>;
 				clock-names = "sysclk", "refclk";
+				syscon-pllreset = <&scm_conf 0x3fc>;
 				#phy-cells = <0>;
 			};
 
@@ -1295,7 +1300,12 @@
 			usb1: usb@48890000 {
 				compatible = "snps,dwc3";
 				reg = <0x48890000 0x17000>;
-				interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				phys = <&usb2_phy1>, <&usb3_phy1>;
 				phy-names = "usb2-phy", "usb3-phy";
 				tx-fifo-resize;
@@ -1318,7 +1328,12 @@
 			usb2: usb@488d0000 {
 				compatible = "snps,dwc3";
 				reg = <0x488d0000 0x17000>;
-				interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				phys = <&usb2_phy2>;
 				phy-names = "usb2-phy";
 				tx-fifo-resize;
@@ -1343,7 +1358,12 @@
 			usb3: usb@48910000 {
 				compatible = "snps,dwc3";
 				reg = <0x48910000 0x17000>;
-				interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				tx-fifo-resize;
 				maximum-speed = "high-speed";
 				dr_mode = "otg";
@@ -1398,7 +1418,7 @@
 		};
 
 		mac: ethernet@4a100000 {
-			compatible = "ti,cpsw";
+			compatible = "ti,dra7-cpsw","ti,cpsw";
 			ti,hwmods = "gmac";
 			clocks = <&dpll_gmac_ck>, <&gmac_gmii_ref_clk_div>;
 			clock-names = "fck", "cpts";
diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts
index 4e1b60581782..6f6bd98c98df 100644
--- a/arch/arm/boot/dts/dra72-evm.dts
+++ b/arch/arm/boot/dts/dra72-evm.dts
@@ -30,6 +30,15 @@
 		regulator-max-microvolt = <3300000>;
 	};
 
+	evm_3v3_sd: fixedregulator-sd {
+		compatible = "regulator-fixed";
+		regulator-name = "evm_3v3_sd";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		enable-active-high;
+		gpio = <&pcf_gpio_21 5 GPIO_ACTIVE_HIGH>;
+	};
+
 	extcon_usb1: extcon_usb1 {
 		compatible = "linux,extcon-usb-gpio";
 		id-gpio = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>;
@@ -286,6 +295,7 @@
 					regulator-name = "ldo1";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <3300000>;
+					regulator-always-on;
 					regulator-boot-on;
 				};
 
@@ -343,6 +353,12 @@
 		interrupts = <11 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
+
+		cpsw_sel_s0 {
+			gpio-hog;
+			gpios = <4 GPIO_ACTIVE_HIGH>;
+			output-low;
+		};
 	};
 };
 
@@ -491,14 +507,15 @@
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins_default>;
-
-	vmmc-supply = <&ldo1_reg>;
+	vmmc-supply = <&evm_3v3_sd>;
+	vmmc_aux-supply = <&ldo1_reg>;
 	bus-width = <4>;
 	/*
 	 * SDCD signal is not being used here - using the fact that GPIO mode
 	 * is a viable alternative
 	 */
 	cd-gpios = <&gpio6 27 0>;
+	max-frequency = <192000000>;
 };
 
 &mmc2 {
@@ -510,6 +527,7 @@
 	vmmc-supply = <&evm_3v3>;
 	bus-width = <8>;
 	ti,non-removable;
+	max-frequency = <192000000>;
 };
 
 &dra7_pmx_core {
@@ -571,9 +589,10 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&cpsw_default>;
 	pinctrl-1 = <&cpsw_sleep>;
+	slaves = <1>;
 };
 
-&cpsw_emac1 {
+&cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <3>;
 	phy-mode = "rgmii";
 };
@@ -582,14 +601,14 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&davinci_mdio_default>;
 	pinctrl-1 = <&davinci_mdio_sleep>;
-	active_slave = <1>;
 };
 
 &dcan1 {
 	status = "ok";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&dcan1_pins_default>;
+	pinctrl-names = "default", "sleep", "active";
+	pinctrl-0 = <&dcan1_pins_sleep>;
 	pinctrl-1 = <&dcan1_pins_sleep>;
+	pinctrl-2 = <&dcan1_pins_default>;
 };
 
 &qspi {
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index fa995d0ca1f2..feea98e0a4b5 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -65,7 +65,12 @@
 			usb4: usb@48950000 {
 				compatible = "snps,dwc3";
 				reg = <0x48950000 0x17000>;
-				interrupts = <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 346 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				tx-fifo-resize;
 				maximum-speed = "high-speed";
 				dr_mode = "otg";
diff --git a/arch/arm/boot/dts/emev2-kzm9d.dts b/arch/arm/boot/dts/emev2-kzm9d.dts
index 1dee0aa4f40c..955c24ee4a8c 100644
--- a/arch/arm/boot/dts/emev2-kzm9d.dts
+++ b/arch/arm/boot/dts/emev2-kzm9d.dts
@@ -95,6 +95,14 @@
 	};
 };
 
+&iic0 {
+	status = "okay";
+};
+
+&iic1 {
+	status = "okay";
+};
+
 &pfc {
 	uart1_pins: serial@e1030000 {
 		renesas,groups = "uart1_ctrl", "uart1_data";
diff --git a/arch/arm/boot/dts/emev2.dtsi b/arch/arm/boot/dts/emev2.dtsi
index bb45694d91bc..edad0c4eea35 100644
--- a/arch/arm/boot/dts/emev2.dtsi
+++ b/arch/arm/boot/dts/emev2.dtsi
@@ -21,6 +21,8 @@
 		gpio2 = &gpio2;
 		gpio3 = &gpio3;
 		gpio4 = &gpio4;
+		i2c0 = &iic0;
+		i2c1 = &iic1;
 	};
 
 	cpus {
@@ -66,6 +68,30 @@
 			clock-frequency = <32768>;
 			#clock-cells = <0>;
 		};
+		iic0_sclkdiv: iic0_sclkdiv {
+			compatible = "renesas,emev2-smu-clkdiv";
+			reg = <0x624 0>;
+			clocks = <&pll3_fo>;
+			#clock-cells = <0>;
+		};
+		iic0_sclk: iic0_sclk {
+			compatible = "renesas,emev2-smu-gclk";
+			reg = <0x48c 1>;
+			clocks = <&iic0_sclkdiv>;
+			#clock-cells = <0>;
+		};
+		iic1_sclkdiv: iic1_sclkdiv {
+			compatible = "renesas,emev2-smu-clkdiv";
+			reg = <0x624 16>;
+			clocks = <&pll3_fo>;
+			#clock-cells = <0>;
+		};
+		iic1_sclk: iic1_sclk {
+			compatible = "renesas,emev2-smu-gclk";
+			reg = <0x490 1>;
+			clocks = <&iic1_sclkdiv>;
+			#clock-cells = <0>;
+		};
 		pll3_fo: pll3_fo {
 			compatible = "fixed-factor-clock";
 			clocks = <&c32ki>;
@@ -234,4 +260,26 @@
 		interrupt-controller;
 		#interrupt-cells = <2>;
 	};
+
+	iic0: i2c@e0070000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,iic-emev2";
+		reg = <0xe0070000 0x28>;
+		interrupts = <0 32 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&iic0_sclk>;
+		clock-names = "sclk";
+		status = "disabled";
+	};
+
+	iic1: i2c@e10a0000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,iic-emev2";
+		reg = <0xe10a0000 0x28>;
+		interrupts = <0 33 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&iic1_sclk>;
+		clock-names = "sclk";
+		status = "disabled";
+	};
 };
diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts
index 031853b75528..baa9b2f52009 100644
--- a/arch/arm/boot/dts/exynos3250-rinato.dts
+++ b/arch/arm/boot/dts/exynos3250-rinato.dts
@@ -182,7 +182,7 @@
 
 		display-timings {
 			timing-0 {
-				clock-frequency = <0>;
+				clock-frequency = <4600000>;
 				hactive = <320>;
 				vactive = <320>;
 				hfront-porch = <1>;
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index d7201333e3bc..2db99433e17f 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -138,8 +138,8 @@
 
 		mipi_phy: video-phy@10020710 {
 			compatible = "samsung,s5pv210-mipi-video-phy";
-			reg = <0x10020710 8>;
 			#phy-cells = <1>;
+			syscon = <&pmu_system_controller>;
 		};
 
 		pd_cam: cam-power-domain@10023C00 {
diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts
index e0abfc3324d1..e050d85cdacd 100644
--- a/arch/arm/boot/dts/exynos4210-origen.dts
+++ b/arch/arm/boot/dts/exynos4210-origen.dts
@@ -127,6 +127,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&buck1_reg>;
+};
+
 &fimd {
 	pinctrl-0 = <&lcd_en &lcd_clk &lcd_data24 &pwm0_out>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 98f3ce65cb9a..ba34886f8b65 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -188,6 +188,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&varm_breg>;
+};
+
 &dsi_0 {
 	vddcore-supply = <&vusb_reg>;
 	vddio-supply = <&vmipi_reg>;
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index d4f2b11319dd..eb379526e234 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -69,66 +69,6 @@
 		enable-active-high;
 	};
 
-	hsotg@12480000 {
-		vusb_d-supply = <&ldo3_reg>;
-		vusb_a-supply = <&ldo8_reg>;
-		dr_mode = "peripheral";
-		status = "okay";
-	};
-
-	sdhci_emmc: sdhci@12510000 {
-		bus-width = <8>;
-		non-removable;
-		pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus8>;
-		pinctrl-names = "default";
-		vmmc-supply = <&vemmc_reg>;
-		status = "okay";
-	};
-
-	sdhci_sd: sdhci@12530000 {
-		bus-width = <4>;
-		pinctrl-0 = <&sd2_clk &sd2_cmd &sd2_bus4>;
-		pinctrl-names = "default";
-		vmmc-supply = <&ldo5_reg>;
-		cd-gpios = <&gpx3 4 0>;
-		cd-inverted;
-		status = "okay";
-	};
-
-	ehci@12580000 {
-		status = "okay";
-		port@0 {
-			status = "okay";
-		};
-	};
-
-	ohci@12590000 {
-		status = "okay";
-		port@0 {
-			status = "okay";
-		};
-	};
-
-	exynos-usbphy@125B0000 {
-		status = "okay";
-	};
-
-	serial@13800000 {
-		status = "okay";
-	};
-
-	serial@13810000 {
-		status = "okay";
-	};
-
-	serial@13820000 {
-		status = "okay";
-	};
-
-	serial@13830000 {
-		status = "okay";
-	};
-
 	gpio-keys {
 		compatible = "gpio-keys";
 
@@ -186,218 +126,6 @@
 		enable-active-high;
 	};
 
-	i2c@13890000 {
-		samsung,i2c-sda-delay = <100>;
-		samsung,i2c-slave-addr = <0x10>;
-		samsung,i2c-max-bus-freq = <100000>;
-		pinctrl-0 = <&i2c3_bus>;
-		pinctrl-names = "default";
-		status = "okay";
-
-		tsp@4a {
-			/* TBD: Atmel maXtouch touchscreen */
-			reg = <0x4a>;
-		};
-	};
-
-	i2c@138B0000 {
-		samsung,i2c-sda-delay = <100>;
-		samsung,i2c-slave-addr = <0x10>;
-		samsung,i2c-max-bus-freq = <100000>;
-		pinctrl-0 = <&i2c5_bus>;
-		pinctrl-names = "default";
-		status = "okay";
-
-		vdd_arm_reg: pmic@60 {
-			compatible = "maxim,max8952";
-			reg = <0x60>;
-
-			max8952,vid-gpios = <&gpx0 3 0>, <&gpx0 4 0>;
-			max8952,default-mode = <0>;
-			max8952,dvs-mode-microvolt = <1250000>, <1200000>,
-							<1050000>, <950000>;
-			max8952,sync-freq = <0>;
-			max8952,ramp-speed = <0>;
-
-			regulator-name = "vdd_arm";
-			regulator-min-microvolt = <770000>;
-			regulator-max-microvolt = <1400000>;
-			regulator-always-on;
-			regulator-boot-on;
-		};
-
-		pmic@66 {
-			compatible = "national,lp3974";
-			reg = <0x66>;
-
-			max8998,pmic-buck1-default-dvs-idx = <0>;
-			max8998,pmic-buck1-dvs-gpios = <&gpx0 5 0>,
-							<&gpx0 6 0>;
-			max8998,pmic-buck1-dvs-voltage = <1100000>, <1000000>,
-							<1100000>, <1000000>;
-
-			max8998,pmic-buck2-default-dvs-idx = <0>;
-			max8998,pmic-buck2-dvs-gpio = <&gpe2 0 0>;
-			max8998,pmic-buck2-dvs-voltage = <1200000>, <1100000>;
-
-			regulators {
-				ldo2_reg: LDO2 {
-					regulator-name = "VALIVE_1.2V";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
-					regulator-always-on;
-				};
-
-				ldo3_reg: LDO3 {
-					regulator-name = "VUSB+MIPI_1.1V";
-					regulator-min-microvolt = <1100000>;
-					regulator-max-microvolt = <1100000>;
-					regulator-always-on;
-				};
-
-				ldo4_reg: LDO4 {
-					regulator-name = "VADC_3.3V";
-					regulator-min-microvolt = <3300000>;
-					regulator-max-microvolt = <3300000>;
-				};
-
-				ldo5_reg: LDO5 {
-					regulator-name = "VTF_2.8V";
-					regulator-min-microvolt = <2800000>;
-					regulator-max-microvolt = <2800000>;
-				};
-
-				ldo6_reg: LDO6 {
-					regulator-name = "LDO6";
-					regulator-min-microvolt = <2000000>;
-					regulator-max-microvolt = <2000000>;
-				};
-
-				ldo7_reg: LDO7 {
-					regulator-name = "VLCD+VMIPI_1.8V";
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <1800000>;
-				};
-
-				ldo8_reg: LDO8 {
-					regulator-name = "VUSB+VDAC_3.3V";
-					regulator-min-microvolt = <3300000>;
-					regulator-max-microvolt = <3300000>;
-					regulator-always-on;
-				};
-
-				ldo9_reg: LDO9 {
-					regulator-name = "VCC_2.8V";
-					regulator-min-microvolt = <2800000>;
-					regulator-max-microvolt = <2800000>;
-					regulator-always-on;
-				};
-
-				ldo10_reg: LDO10 {
-					regulator-name = "VPLL_1.1V";
-					regulator-min-microvolt = <1100000>;
-					regulator-max-microvolt = <1100000>;
-					regulator-boot-on;
-					regulator-always-on;
-				};
-
-				ldo11_reg: LDO11 {
-					regulator-name = "CAM_AF_3.3V";
-					regulator-min-microvolt = <3300000>;
-					regulator-max-microvolt = <3300000>;
-				};
-
-				ldo12_reg: LDO12 {
-					regulator-name = "PS_2.8V";
-					regulator-min-microvolt = <2800000>;
-					regulator-max-microvolt = <2800000>;
-				};
-
-				ldo13_reg: LDO13 {
-					regulator-name = "VHIC_1.2V";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
-				};
-
-				ldo14_reg: LDO14 {
-					regulator-name = "CAM_I_HOST_1.8V";
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <1800000>;
-				};
-
-				ldo15_reg: LDO15 {
-					regulator-name = "CAM_S_DIG+FM33_CORE_1.2V";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
-				};
-
-				ldo16_reg: LDO16 {
-					regulator-name = "CAM_S_ANA_2.8V";
-					regulator-min-microvolt = <2800000>;
-					regulator-max-microvolt = <2800000>;
-				};
-
-				ldo17_reg: LDO17 {
-					regulator-name = "VCC_3.0V_LCD";
-					regulator-min-microvolt = <3000000>;
-					regulator-max-microvolt = <3000000>;
-				};
-
-				buck1_reg: BUCK1 {
-					regulator-name = "VINT_1.1V";
-					regulator-min-microvolt = <750000>;
-					regulator-max-microvolt = <1500000>;
-					regulator-boot-on;
-					regulator-always-on;
-				};
-
-				buck2_reg: BUCK2 {
-					regulator-name = "VG3D_1.1V";
-					regulator-min-microvolt = <750000>;
-					regulator-max-microvolt = <1500000>;
-					regulator-boot-on;
-				};
-
-				buck3_reg: BUCK3 {
-					regulator-name = "VCC_1.8V";
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <1800000>;
-					regulator-always-on;
-				};
-
-				buck4_reg: BUCK4 {
-					regulator-name = "VMEM_1.2V";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
-					regulator-always-on;
-				};
-
-				ap32khz_reg: EN32KHz-AP {
-					regulator-name = "32KHz AP";
-					regulator-always-on;
-				};
-
-				cp32khz_reg: EN32KHz-CP {
-					regulator-name = "32KHz CP";
-				};
-
-				vichg_reg: ENVICHG {
-					regulator-name = "VICHG";
-				};
-
-				safeout1_reg: ESAFEOUT1 {
-					regulator-name = "SAFEOUT1";
-					regulator-always-on;
-				};
-
-				safeout2_reg: ESAFEOUT2 {
-					regulator-name = "SAFEOUT2";
-					regulator-boot-on;
-				};
-			};
-		};
-	};
-
 	spi-lcd {
 		compatible = "spi-gpio";
 		#address-cells = <1>;
@@ -446,27 +174,6 @@
 		};
 	};
 
-	fimd: fimd@11c00000 {
-		pinctrl-0 = <&lcd_clk>, <&lcd_data24>;
-		pinctrl-names = "default";
-		status = "okay";
-		samsung,invert-vden;
-		samsung,invert-vclk;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		port@3 {
-			reg = <3>;
-			fimd_dpi_ep: endpoint {
-				remote-endpoint = <&lcd_ep>;
-			};
-		};
-	};
-
-	pwm@139D0000 {
-		compatible = "samsung,s5p6440-pwm";
-		status = "okay";
-	};
-
 	camera {
 		status = "okay";
 
@@ -526,24 +233,285 @@
 		pinctrl-names = "default";
 		status = "okay";
 	};
+};
+
+&cpu0 {
+	cpu0-supply = <&vdd_arm_reg>;
+};
 
-	mixer@12C10000 {
+&ehci {
+	status = "okay";
+	port@0 {
 		status = "okay";
 	};
+};
 
-	hdmi@12D00000 {
-		hpd-gpio = <&gpx3 7 0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&hdmi_hpd>;
-		hdmi-en-supply = <&hdmi_en>;
-		vdd-supply = <&ldo3_reg>;
-		vdd_osc-supply = <&ldo4_reg>;
-		vdd_pll-supply = <&ldo3_reg>;
-		ddc = <&hdmi_ddc>;
-		status = "okay";
+&exynos_usbphy {
+	status = "okay";
+};
+
+&fimd {
+	pinctrl-0 = <&lcd_clk>, <&lcd_data24>;
+	pinctrl-names = "default";
+	status = "okay";
+	samsung,invert-vden;
+	samsung,invert-vclk;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	port@3 {
+		reg = <3>;
+		fimd_dpi_ep: endpoint {
+			remote-endpoint = <&lcd_ep>;
+		};
+	};
+};
+
+&hdmi {
+	hpd-gpio = <&gpx3 7 0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmi_hpd>;
+	hdmi-en-supply = <&hdmi_en>;
+	vdd-supply = <&ldo3_reg>;
+	vdd_osc-supply = <&ldo4_reg>;
+	vdd_pll-supply = <&ldo3_reg>;
+	ddc = <&hdmi_ddc>;
+	status = "okay";
+};
+
+&hsotg {
+	vusb_d-supply = <&ldo3_reg>;
+	vusb_a-supply = <&ldo8_reg>;
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&i2c_3 {
+	samsung,i2c-sda-delay = <100>;
+	samsung,i2c-slave-addr = <0x10>;
+	samsung,i2c-max-bus-freq = <100000>;
+	pinctrl-0 = <&i2c3_bus>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	tsp@4a {
+		/* TBD: Atmel maXtouch touchscreen */
+		reg = <0x4a>;
+	};
+};
+
+&i2c_5 {
+	samsung,i2c-sda-delay = <100>;
+	samsung,i2c-slave-addr = <0x10>;
+	samsung,i2c-max-bus-freq = <100000>;
+	pinctrl-0 = <&i2c5_bus>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	vdd_arm_reg: pmic@60 {
+		compatible = "maxim,max8952";
+		reg = <0x60>;
+
+		max8952,vid-gpios = <&gpx0 3 0>, <&gpx0 4 0>;
+		max8952,default-mode = <0>;
+		max8952,dvs-mode-microvolt = <1250000>, <1200000>,
+						<1050000>, <950000>;
+		max8952,sync-freq = <0>;
+		max8952,ramp-speed = <0>;
+
+		regulator-name = "vdd_arm";
+		regulator-min-microvolt = <770000>;
+		regulator-max-microvolt = <1400000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	pmic@66 {
+		compatible = "national,lp3974";
+		reg = <0x66>;
+
+		max8998,pmic-buck1-default-dvs-idx = <0>;
+		max8998,pmic-buck1-dvs-gpios = <&gpx0 5 0>,
+						<&gpx0 6 0>;
+		max8998,pmic-buck1-dvs-voltage = <1100000>, <1000000>,
+						<1100000>, <1000000>;
+
+		max8998,pmic-buck2-default-dvs-idx = <0>;
+		max8998,pmic-buck2-dvs-gpio = <&gpe2 0 0>;
+		max8998,pmic-buck2-dvs-voltage = <1200000>, <1100000>;
+
+		regulators {
+			ldo2_reg: LDO2 {
+				regulator-name = "VALIVE_1.2V";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+			};
+
+			ldo3_reg: LDO3 {
+				regulator-name = "VUSB+MIPI_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+
+			ldo4_reg: LDO4 {
+				regulator-name = "VADC_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo5_reg: LDO5 {
+				regulator-name = "VTF_2.8V";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+			};
+
+			ldo6_reg: LDO6 {
+				regulator-name = "LDO6";
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+			};
+
+			ldo7_reg: LDO7 {
+				regulator-name = "VLCD+VMIPI_1.8V";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+
+			ldo8_reg: LDO8 {
+				regulator-name = "VUSB+VDAC_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			ldo9_reg: LDO9 {
+				regulator-name = "VCC_2.8V";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-always-on;
+			};
+
+			ldo10_reg: LDO10 {
+				regulator-name = "VPLL_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldo11_reg: LDO11 {
+				regulator-name = "CAM_AF_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo12_reg: LDO12 {
+				regulator-name = "PS_2.8V";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+			};
+
+			ldo13_reg: LDO13 {
+				regulator-name = "VHIC_1.2V";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+			};
+
+			ldo14_reg: LDO14 {
+				regulator-name = "CAM_I_HOST_1.8V";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+
+			ldo15_reg: LDO15 {
+				regulator-name = "CAM_S_DIG+FM33_CORE_1.2V";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+			};
+
+			ldo16_reg: LDO16 {
+				regulator-name = "CAM_S_ANA_2.8V";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+			};
+
+			ldo17_reg: LDO17 {
+				regulator-name = "VCC_3.0V_LCD";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "VINT_1.1V";
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buck2_reg: BUCK2 {
+				regulator-name = "VG3D_1.1V";
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-boot-on;
+			};
+
+			buck3_reg: BUCK3 {
+				regulator-name = "VCC_1.8V";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			buck4_reg: BUCK4 {
+				regulator-name = "VMEM_1.2V";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+			};
+
+			ap32khz_reg: EN32KHz-AP {
+				regulator-name = "32KHz AP";
+				regulator-always-on;
+			};
+
+			cp32khz_reg: EN32KHz-CP {
+				regulator-name = "32KHz CP";
+			};
+
+			vichg_reg: ENVICHG {
+				regulator-name = "VICHG";
+			};
+
+			safeout1_reg: ESAFEOUT1 {
+				regulator-name = "SAFEOUT1";
+				regulator-always-on;
+			};
+
+			safeout2_reg: ESAFEOUT2 {
+				regulator-name = "SAFEOUT2";
+				regulator-boot-on;
+			};
+		};
 	};
+};
 
-	i2c@138E0000 {
+&i2c_8 {
+	status = "okay";
+};
+
+&mdma1 {
+	reg = <0x12840000 0x1000>;
+};
+
+&mixer {
+	status = "okay";
+};
+
+&ohci {
+	status = "okay";
+	port@0 {
 		status = "okay";
 	};
 };
@@ -564,6 +532,42 @@
 	};
 };
 
-&mdma1 {
-	reg = <0x12840000 0x1000>;
+&pwm {
+	compatible = "samsung,s5p6440-pwm";
+	status = "okay";
+};
+
+&sdhci_0 {
+	bus-width = <8>;
+	non-removable;
+	pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus8>;
+	pinctrl-names = "default";
+	vmmc-supply = <&vemmc_reg>;
+	status = "okay";
+};
+
+&sdhci_2 {
+	bus-width = <4>;
+	pinctrl-0 = <&sd2_clk &sd2_cmd &sd2_bus4>;
+	pinctrl-names = "default";
+	vmmc-supply = <&ldo5_reg>;
+	cd-gpios = <&gpx3 4 0>;
+	cd-inverted;
+	status = "okay";
+};
+
+&serial_0 {
+	status = "okay";
+};
+
+&serial_1 {
+	status = "okay";
+};
+
+&serial_2 {
+	status = "okay";
+};
+
+&serial_3 {
+	status = "okay";
 };
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index 10d3c173396e..3e5ba665d200 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -40,6 +40,18 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0x900>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
+			clock-latency = <160000>;
+
+			operating-points = <
+				1200000 1250000
+				1000000 1150000
+				800000	1075000
+				500000	975000
+				400000	975000
+				200000	950000
+			>;
 			cooling-min-level = <4>;
 			cooling-max-level = <2>;
 			#cooling-cells = <2>; /* min followed by max */
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index afc199d78cb9..884840059018 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -190,6 +190,9 @@
 			interrupt-parent = <&gpx2>;
 			interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
 			reg = <0x36>;
+
+			maxim,over-heat-temp = <700>;
+			maxim,over-volt = <4500>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
index 886cfca044ac..880917e508b2 100644
--- a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
@@ -12,807 +12,805 @@
  * published by the Free Software Foundation.
 */
 
-/ {
-	pinctrl@11400000 {
-		gpa0: gpa0 {
-			gpio-controller;
-			#gpio-cells = <2>;
+&pinctrl_0 {
+	gpa0: gpa0 {
+		gpio-controller;
+		#gpio-cells = <2>;
 
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpa1: gpa1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpa2: gpa2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb0: gpb0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb1: gpb1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb2: gpb2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb3: gpb3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc0: gpc0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc1: gpc1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc2: gpc2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc3: gpc3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpd0: gpd0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpd1: gpd1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpy0: gpy0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy1: gpy1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy2: gpy2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy3: gpy3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy4: gpy4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy5: gpy5 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy6: gpy6 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpc4: gpc4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpx0: gpx0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			interrupt-parent = <&combiner>;
-			#interrupt-cells = <2>;
-			interrupts = <23 0>, <24 0>, <25 0>, <25 1>,
-				     <26 0>, <26 1>, <27 0>, <27 1>;
-		};
-
-		gpx1: gpx1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			interrupt-parent = <&combiner>;
-			#interrupt-cells = <2>;
-			interrupts = <28 0>, <28 1>, <29 0>, <29 1>,
-				     <30 0>, <30 1>, <31 0>, <31 1>;
-		};
-
-		gpx2: gpx2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpx3: gpx3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		uart0_data: uart0-data {
-			samsung,pins = "gpa0-0", "gpa0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart0_fctl: uart0-fctl {
-			samsung,pins = "gpa0-2", "gpa0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c2_bus: i2c2-bus {
-			samsung,pins = "gpa0-6", "gpa0-7";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c2_hs_bus: i2c2-hs-bus {
-			samsung,pins = "gpa0-6", "gpa0-7";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart2_data: uart2-data {
-			samsung,pins = "gpa1-0", "gpa1-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart2_fctl: uart2-fctl {
-			samsung,pins = "gpa1-2", "gpa1-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c3_bus: i2c3-bus {
-			samsung,pins = "gpa1-2", "gpa1-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c3_hs_bus: i2c3-hs-bus {
-			samsung,pins = "gpa1-2", "gpa1-3";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart3_data: uart3-data {
-			samsung,pins = "gpa1-4", "gpa1-4";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		spi0_bus: spi0-bus {
-			samsung,pins = "gpa2-0", "gpa2-2", "gpa2-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c4_bus: i2c4-bus {
-			samsung,pins = "gpa2-0", "gpa2-1";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c5_bus: i2c5-bus {
-			samsung,pins = "gpa2-2", "gpa2-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		spi1_bus: spi1-bus {
-			samsung,pins = "gpa2-4", "gpa2-6", "gpa2-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2s1_bus: i2s1-bus {
-			samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
-					"gpb0-4";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pcm1_bus: pcm1-bus {
-			samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
-					"gpb0-4";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		ac97_bus: ac97-bus {
-			samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
-					"gpb0-4";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2s2_bus: i2s2-bus {
-			samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
-					"gpb1-4";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pcm2_bus: pcm2-bus {
-			samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
-					"gpb1-4";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		spdif_bus: spdif-bus {
-			samsung,pins = "gpb1-0", "gpb1-1";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		spi2_bus: spi2-bus {
-			samsung,pins = "gpb1-1", "gpb1-3", "gpb1-4";
-			samsung,pin-function = <5>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c6_bus: i2c6-bus {
-			samsung,pins = "gpb1-3", "gpb1-4";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm0_out: pwm0-out {
-			samsung,pins = "gpb2-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm1_out: pwm1-out {
-			samsung,pins = "gpb2-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm2_out: pwm2-out {
-			samsung,pins = "gpb2-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm3_out: pwm3-out {
-			samsung,pins = "gpb2-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c7_bus: i2c7-bus {
-			samsung,pins = "gpb2-2", "gpb2-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c0_bus: i2c0-bus {
-			samsung,pins = "gpb3-0", "gpb3-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c1_bus: i2c1-bus {
-			samsung,pins = "gpb3-2", "gpb3-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c0_hs_bus: i2c0-hs-bus {
-			samsung,pins = "gpb3-0", "gpb3-1";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c1_hs_bus: i2c1-hs-bus {
-			samsung,pins = "gpb3-2", "gpb3-3";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		sd0_clk: sd0-clk {
-			samsung,pins = "gpc0-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_cmd: sd0-cmd {
-			samsung,pins = "gpc0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_cd: sd0-cd {
-			samsung,pins = "gpc0-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_bus1: sd0-bus-width1 {
-			samsung,pins = "gpc0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_bus4: sd0-bus-width4 {
-			samsung,pins = "gpc0-3", "gpc0-4", "gpc0-5", "gpc0-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_bus8: sd0-bus-width8 {
-			samsung,pins = "gpc1-0", "gpc1-1", "gpc1-2", "gpc1-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_clk: sd1-clk {
-			samsung,pins = "gpc2-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_cmd: sd1-cmd {
-			samsung,pins = "gpc2-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_cd: sd1-cd {
-			samsung,pins = "gpc2-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_bus1: sd1-bus-width1 {
-			samsung,pins = "gpc2-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_bus4: sd1-bus-width4 {
-			samsung,pins = "gpc2-3", "gpc2-4", "gpc2-5", "gpc2-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_clk: sd2-clk {
-			samsung,pins = "gpc3-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_cmd: sd2-cmd {
-			samsung,pins = "gpc3-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_cd: sd2-cd {
-			samsung,pins = "gpc3-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_bus1: sd2-bus-width1 {
-			samsung,pins = "gpc3-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_bus4: sd2-bus-width4 {
-			samsung,pins = "gpc3-3", "gpc3-4", "gpc3-5", "gpc3-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_bus8: sd2-bus-width8 {
-			samsung,pins = "gpc4-3", "gpc4-4", "gpc4-5", "gpc4-6";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd3_clk: sd3-clk {
-			samsung,pins = "gpc4-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd3_cmd: sd3-cmd {
-			samsung,pins = "gpc4-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd3_cd: sd3-cd {
-			samsung,pins = "gpc4-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd3_bus1: sd3-bus-width1 {
-			samsung,pins = "gpc4-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd3_bus4: sd3-bus-width4 {
-			samsung,pins = "gpc4-3", "gpc4-4", "gpc4-5", "gpc4-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		uart1_data: uart1-data {
-			samsung,pins = "gpd0-0", "gpd0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart1_fctl: uart1-fctl {
-			samsung,pins = "gpd0-2", "gpd0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		dp_hpd: dp_hpd {
-			samsung,pins = "gpx0-7";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-	};
-
-	pinctrl@13400000 {
-		gpe0: gpe0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpe1: gpe1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpf0: gpf0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpf1: gpf1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpg0: gpg0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpg1: gpg1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpg2: gpg2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gph0: gph0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gph1: gph1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		cam_gpio_a: cam-gpio-a {
-			samsung,pins = "gpe0-0", "gpe0-1", "gpe0-2", "gpe0-3",
-				       "gpe0-4", "gpe0-5", "gpe0-6", "gpe0-7",
-				       "gpe1-0", "gpe1-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_gpio_b: cam-gpio-b {
-			samsung,pins = "gpf0-0", "gpf0-1", "gpf0-2", "gpf0-3",
-				       "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_i2c2_bus: cam-i2c2-bus {
-			samsung,pins = "gpe0-6", "gpe1-0";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_spi1_bus: cam-spi1-bus {
-			samsung,pins = "gpe0-4", "gpe0-5", "gpf0-2", "gpf0-3";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_i2c1_bus: cam-i2c1-bus {
-			samsung,pins = "gpf0-2", "gpf0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_i2c0_bus: cam-i2c0-bus {
-			samsung,pins = "gpf0-0", "gpf0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_spi0_bus: cam-spi0-bus {
-			samsung,pins = "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_bayrgb_bus: cam-bayrgb-bus {
-			samsung,pins = "gpg0-0", "gpg0-1", "gpg0-2", "gpg0-3",
-				       "gpg0-4", "gpg0-5", "gpg0-6", "gpg0-7",
-				       "gpg1-0", "gpg1-1", "gpg1-2", "gpg1-3",
-				       "gpg1-4", "gpg1-5", "gpg1-6", "gpg1-7",
-				       "gpg2-0", "gpg2-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_port_a: cam-port-a {
-			samsung,pins = "gph0-0", "gph0-1", "gph0-2", "gph0-3",
-				       "gph1-0", "gph1-1", "gph1-2", "gph1-3",
-				       "gph1-4", "gph1-5", "gph1-6", "gph1-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-	};
-
-	pinctrl@10d10000 {
-		gpv0: gpv0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpv1: gpv1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpv2: gpv2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpv3: gpv3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpv4: gpv4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		c2c_rxd: c2c-rxd {
-			samsung,pins = "gpv0-0", "gpv0-1", "gpv0-2", "gpv0-3",
-				       "gpv0-4", "gpv0-5", "gpv0-6", "gpv0-7",
-				       "gpv1-0", "gpv1-1", "gpv1-2", "gpv1-3",
-				       "gpv1-4", "gpv1-5", "gpv1-6", "gpv1-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		c2c_txd: c2c-txd {
-			samsung,pins = "gpv2-0", "gpv2-1", "gpv2-2", "gpv2-3",
-				       "gpv2-4", "gpv2-5", "gpv2-6", "gpv2-7",
-				       "gpv3-0", "gpv3-1", "gpv3-2", "gpv3-3",
-				       "gpv3-4", "gpv3-5", "gpv3-6", "gpv3-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-	};
-
-	pinctrl@03860000 {
-		gpz: gpz {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		i2s0_bus: i2s0-bus {
-			samsung,pins = "gpz-0", "gpz-1", "gpz-2", "gpz-3",
-					"gpz-4", "gpz-5", "gpz-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpa1: gpa1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpa2: gpa2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb0: gpb0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb1: gpb1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb2: gpb2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb3: gpb3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc0: gpc0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc1: gpc1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc2: gpc2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc3: gpc3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpd0: gpd0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpd1: gpd1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpy0: gpy0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy1: gpy1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy2: gpy2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy3: gpy3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy4: gpy4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy5: gpy5 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy6: gpy6 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpc4: gpc4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpx0: gpx0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		interrupt-parent = <&combiner>;
+		#interrupt-cells = <2>;
+		interrupts = <23 0>, <24 0>, <25 0>, <25 1>,
+			     <26 0>, <26 1>, <27 0>, <27 1>;
+	};
+
+	gpx1: gpx1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		interrupt-parent = <&combiner>;
+		#interrupt-cells = <2>;
+		interrupts = <28 0>, <28 1>, <29 0>, <29 1>,
+			     <30 0>, <30 1>, <31 0>, <31 1>;
+	};
+
+	gpx2: gpx2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpx3: gpx3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	uart0_data: uart0-data {
+		samsung,pins = "gpa0-0", "gpa0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart0_fctl: uart0-fctl {
+		samsung,pins = "gpa0-2", "gpa0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c2_bus: i2c2-bus {
+		samsung,pins = "gpa0-6", "gpa0-7";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c2_hs_bus: i2c2-hs-bus {
+		samsung,pins = "gpa0-6", "gpa0-7";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart2_data: uart2-data {
+		samsung,pins = "gpa1-0", "gpa1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart2_fctl: uart2-fctl {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c3_bus: i2c3-bus {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c3_hs_bus: i2c3-hs-bus {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart3_data: uart3-data {
+		samsung,pins = "gpa1-4", "gpa1-4";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	spi0_bus: spi0-bus {
+		samsung,pins = "gpa2-0", "gpa2-2", "gpa2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c4_bus: i2c4-bus {
+		samsung,pins = "gpa2-0", "gpa2-1";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c5_bus: i2c5-bus {
+		samsung,pins = "gpa2-2", "gpa2-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	spi1_bus: spi1-bus {
+		samsung,pins = "gpa2-4", "gpa2-6", "gpa2-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2s1_bus: i2s1-bus {
+		samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
+			       "gpb0-4";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pcm1_bus: pcm1-bus {
+		samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
+			       "gpb0-4";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	ac97_bus: ac97-bus {
+		samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
+			       "gpb0-4";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2s2_bus: i2s2-bus {
+		samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
+			       "gpb1-4";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pcm2_bus: pcm2-bus {
+		samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
+			       "gpb1-4";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	spdif_bus: spdif-bus {
+		samsung,pins = "gpb1-0", "gpb1-1";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	spi2_bus: spi2-bus {
+		samsung,pins = "gpb1-1", "gpb1-3", "gpb1-4";
+		samsung,pin-function = <5>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c6_bus: i2c6-bus {
+		samsung,pins = "gpb1-3", "gpb1-4";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm0_out: pwm0-out {
+		samsung,pins = "gpb2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm1_out: pwm1-out {
+		samsung,pins = "gpb2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm2_out: pwm2-out {
+		samsung,pins = "gpb2-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm3_out: pwm3-out {
+		samsung,pins = "gpb2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c7_bus: i2c7-bus {
+		samsung,pins = "gpb2-2", "gpb2-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c0_bus: i2c0-bus {
+		samsung,pins = "gpb3-0", "gpb3-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c1_bus: i2c1-bus {
+		samsung,pins = "gpb3-2", "gpb3-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c0_hs_bus: i2c0-hs-bus {
+		samsung,pins = "gpb3-0", "gpb3-1";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c1_hs_bus: i2c1-hs-bus {
+		samsung,pins = "gpb3-2", "gpb3-3";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	sd0_clk: sd0-clk {
+		samsung,pins = "gpc0-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_cmd: sd0-cmd {
+		samsung,pins = "gpc0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_cd: sd0-cd {
+		samsung,pins = "gpc0-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus1: sd0-bus-width1 {
+		samsung,pins = "gpc0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus4: sd0-bus-width4 {
+		samsung,pins = "gpc0-3", "gpc0-4", "gpc0-5", "gpc0-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus8: sd0-bus-width8 {
+		samsung,pins = "gpc1-0", "gpc1-1", "gpc1-2", "gpc1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_clk: sd1-clk {
+		samsung,pins = "gpc2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_cmd: sd1-cmd {
+		samsung,pins = "gpc2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_cd: sd1-cd {
+		samsung,pins = "gpc2-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_bus1: sd1-bus-width1 {
+		samsung,pins = "gpc2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_bus4: sd1-bus-width4 {
+		samsung,pins = "gpc2-3", "gpc2-4", "gpc2-5", "gpc2-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_clk: sd2-clk {
+		samsung,pins = "gpc3-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_cmd: sd2-cmd {
+		samsung,pins = "gpc3-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_cd: sd2-cd {
+		samsung,pins = "gpc3-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus1: sd2-bus-width1 {
+		samsung,pins = "gpc3-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus4: sd2-bus-width4 {
+		samsung,pins = "gpc3-3", "gpc3-4", "gpc3-5", "gpc3-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus8: sd2-bus-width8 {
+		samsung,pins = "gpc4-3", "gpc4-4", "gpc4-5", "gpc4-6";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd3_clk: sd3-clk {
+		samsung,pins = "gpc4-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd3_cmd: sd3-cmd {
+		samsung,pins = "gpc4-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd3_cd: sd3-cd {
+		samsung,pins = "gpc4-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd3_bus1: sd3-bus-width1 {
+		samsung,pins = "gpc4-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd3_bus4: sd3-bus-width4 {
+		samsung,pins = "gpc4-3", "gpc4-4", "gpc4-5", "gpc4-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	uart1_data: uart1-data {
+		samsung,pins = "gpd0-0", "gpd0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart1_fctl: uart1-fctl {
+		samsung,pins = "gpd0-2", "gpd0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	dp_hpd: dp_hpd {
+		samsung,pins = "gpx0-7";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pinctrl_1 {
+	gpe0: gpe0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpe1: gpe1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf0: gpf0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf1: gpf1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg0: gpg0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg1: gpg1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg2: gpg2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph0: gph0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph1: gph1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	cam_gpio_a: cam-gpio-a {
+		samsung,pins = "gpe0-0", "gpe0-1", "gpe0-2", "gpe0-3",
+			       "gpe0-4", "gpe0-5", "gpe0-6", "gpe0-7",
+			       "gpe1-0", "gpe1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_gpio_b: cam-gpio-b {
+		samsung,pins = "gpf0-0", "gpf0-1", "gpf0-2", "gpf0-3",
+			       "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_i2c2_bus: cam-i2c2-bus {
+		samsung,pins = "gpe0-6", "gpe1-0";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_spi1_bus: cam-spi1-bus {
+		samsung,pins = "gpe0-4", "gpe0-5", "gpf0-2", "gpf0-3";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_i2c1_bus: cam-i2c1-bus {
+		samsung,pins = "gpf0-2", "gpf0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_i2c0_bus: cam-i2c0-bus {
+		samsung,pins = "gpf0-0", "gpf0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_spi0_bus: cam-spi0-bus {
+		samsung,pins = "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_bayrgb_bus: cam-bayrgb-bus {
+		samsung,pins = "gpg0-0", "gpg0-1", "gpg0-2", "gpg0-3",
+			       "gpg0-4", "gpg0-5", "gpg0-6", "gpg0-7",
+			       "gpg1-0", "gpg1-1", "gpg1-2", "gpg1-3",
+			       "gpg1-4", "gpg1-5", "gpg1-6", "gpg1-7",
+			       "gpg2-0", "gpg2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_port_a: cam-port-a {
+		samsung,pins = "gph0-0", "gph0-1", "gph0-2", "gph0-3",
+			       "gph1-0", "gph1-1", "gph1-2", "gph1-3",
+			       "gph1-4", "gph1-5", "gph1-6", "gph1-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pinctrl_2 {
+	gpv0: gpv0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpv1: gpv1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpv2: gpv2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpv3: gpv3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpv4: gpv4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	c2c_rxd: c2c-rxd {
+		samsung,pins = "gpv0-0", "gpv0-1", "gpv0-2", "gpv0-3",
+			       "gpv0-4", "gpv0-5", "gpv0-6", "gpv0-7",
+			       "gpv1-0", "gpv1-1", "gpv1-2", "gpv1-3",
+			       "gpv1-4", "gpv1-5", "gpv1-6", "gpv1-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	c2c_txd: c2c-txd {
+		samsung,pins = "gpv2-0", "gpv2-1", "gpv2-2", "gpv2-3",
+			       "gpv2-4", "gpv2-5", "gpv2-6", "gpv2-7",
+			       "gpv3-0", "gpv3-1", "gpv3-2", "gpv3-3",
+			       "gpv3-4", "gpv3-5", "gpv3-6", "gpv3-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pinctrl_3 {
+	gpz: gpz {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	i2s0_bus: i2s0-bus {
+		samsung,pins = "gpz-0", "gpz-1", "gpz-2", "gpz-3",
+				"gpz-4", "gpz-5", "gpz-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
 	};
 };
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index bf9bee67c416..4a1f88300a28 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -19,7 +19,6 @@
 
 #include <dt-bindings/clock/exynos5250.h>
 #include "exynos5.dtsi"
-#include "exynos5250-pinctrl.dtsi"
 #include "exynos4-cpu-thermal.dtsi"
 #include <dt-bindings/clock/exynos-audss-clk.h>
 
@@ -1062,3 +1061,5 @@
 	clocks = <&clock CLK_UART3>, <&clock CLK_SCLK_UART3>;
 	clock-names = "uart", "clk_uart_baud0";
 };
+
+#include "exynos5250-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/exynos5410-smdk5410.dts b/arch/arm/boot/dts/exynos5410-smdk5410.dts
index be3e02530b42..cebeaab3abec 100644
--- a/arch/arm/boot/dts/exynos5410-smdk5410.dts
+++ b/arch/arm/boot/dts/exynos5410-smdk5410.dts
@@ -62,13 +62,13 @@
 };
 
 &uart0 {
-		status = "okay";
+	status = "okay";
 };
 
 &uart1 {
-		status = "okay";
+	status = "okay";
 };
 
 &uart2 {
-		status = "okay";
+	status = "okay";
 };
diff --git a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
index 8b153166ebdb..130563b2ca95 100644
--- a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
@@ -12,711 +12,710 @@
  * published by the Free Software Foundation.
 */
 
-/ {
-	pinctrl@13400000 {
-		gpy7: gpy7 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpx0: gpx0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			interrupt-parent = <&combiner>;
-			#interrupt-cells = <2>;
-			interrupts = <23 0>, <24 0>, <25 0>, <25 1>,
-				     <26 0>, <26 1>, <27 0>, <27 1>;
-		};
-
-		gpx1: gpx1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			interrupt-parent = <&combiner>;
-			#interrupt-cells = <2>;
-			interrupts = <28 0>, <28 1>, <29 0>, <29 1>,
-				     <30 0>, <30 1>, <31 0>, <31 1>;
-		};
-
-		gpx2: gpx2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpx3: gpx3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		dp_hpd: dp_hpd {
-			samsung,pins = "gpx0-7";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-	};
-
-	pinctrl@13410000 {
-		gpc0: gpc0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc1: gpc1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc2: gpc2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc3: gpc3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpc4: gpc4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpd1: gpd1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpy0: gpy0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy1: gpy1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy2: gpy2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy3: gpy3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy4: gpy4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy5: gpy5 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		gpy6: gpy6 {
-			gpio-controller;
-			#gpio-cells = <2>;
-		};
-
-		sd0_clk: sd0-clk {
-			samsung,pins = "gpc0-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_cmd: sd0-cmd {
-			samsung,pins = "gpc0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_cd: sd0-cd {
-			samsung,pins = "gpc0-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_bus1: sd0-bus-width1 {
-			samsung,pins = "gpc0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_bus4: sd0-bus-width4 {
-			samsung,pins = "gpc0-4", "gpc0-5", "gpc0-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_bus8: sd0-bus-width8 {
-			samsung,pins = "gpc3-0", "gpc3-1", "gpc3-2", "gpc3-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_clk: sd1-clk {
-			samsung,pins = "gpc1-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd0_rclk: sd0-rclk {
-			samsung,pins = "gpc0-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <1>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_cmd: sd1-cmd {
-			samsung,pins = "gpc1-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_cd: sd1-cd {
-			samsung,pins = "gpc1-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_int: sd1-int {
-			samsung,pins = "gpd1-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		sd1_bus1: sd1-bus-width1 {
-			samsung,pins = "gpc1-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_bus4: sd1-bus-width4 {
-			samsung,pins = "gpc1-4", "gpc1-5", "gpc1-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd1_bus8: sd1-bus-width8 {
-			samsung,pins = "gpd1-4", "gpd1-5", "gpd1-6", "gpd1-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_clk: sd2-clk {
-			samsung,pins = "gpc2-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_cmd: sd2-cmd {
-			samsung,pins = "gpc2-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_cd: sd2-cd {
-			samsung,pins = "gpc2-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_bus1: sd2-bus-width1 {
-			samsung,pins = "gpc2-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-
-		sd2_bus4: sd2-bus-width4 {
-			samsung,pins = "gpc2-4", "gpc2-5", "gpc2-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <3>;
-		};
-	};
-
-	pinctrl@14000000 {
-		gpe0: gpe0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpe1: gpe1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpf0: gpf0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpf1: gpf1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpg0: gpg0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpg1: gpg1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpg2: gpg2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpj4: gpj4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		cam_gpio_a: cam-gpio-a {
-			samsung,pins = "gpe0-0", "gpe0-1", "gpe0-2", "gpe0-3",
-				       "gpe0-4", "gpe0-5", "gpe0-6", "gpe0-7",
-				       "gpe1-0", "gpe1-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_gpio_b: cam-gpio-b {
-			samsung,pins = "gpf0-0", "gpf0-1", "gpf0-2", "gpf0-3",
-				       "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_i2c2_bus: cam-i2c2-bus {
-			samsung,pins = "gpf0-4", "gpf0-5";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-		cam_spi1_bus: cam-spi1-bus {
-			samsung,pins = "gpe0-4", "gpe0-5", "gpf0-2", "gpf0-3";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_i2c1_bus: cam-i2c1-bus {
-			samsung,pins = "gpf0-2", "gpf0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_i2c0_bus: cam-i2c0-bus {
-			samsung,pins = "gpf0-0", "gpf0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_spi0_bus: cam-spi0-bus {
-			samsung,pins = "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		cam_bayrgb_bus: cam-bayrgb-bus {
-			samsung,pins = "gpg0-0", "gpg0-1", "gpg0-2", "gpg0-3",
-				       "gpg0-4", "gpg0-5", "gpg0-6", "gpg0-7",
-				       "gpg1-0", "gpg1-1", "gpg1-2", "gpg1-3",
-				       "gpg1-4", "gpg1-5", "gpg1-6", "gpg1-7",
-				       "gpg2-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-	};
-
-	pinctrl@14010000 {
-		gpa0: gpa0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpa1: gpa1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpa2: gpa2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb0: gpb0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb1: gpb1 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb2: gpb2 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb3: gpb3 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gpb4: gpb4 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		gph0: gph0 {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		uart0_data: uart0-data {
-			samsung,pins = "gpa0-0", "gpa0-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart0_fctl: uart0-fctl {
-			samsung,pins = "gpa0-2", "gpa0-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart1_data: uart1-data {
-			samsung,pins = "gpa0-4", "gpa0-5";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart1_fctl: uart1-fctl {
-			samsung,pins = "gpa0-6", "gpa0-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c2_bus: i2c2-bus {
-			samsung,pins = "gpa0-6", "gpa0-7";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart2_data: uart2-data {
-			samsung,pins = "gpa1-0", "gpa1-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart2_fctl: uart2-fctl {
-			samsung,pins = "gpa1-2", "gpa1-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c3_bus: i2c3-bus {
-			samsung,pins = "gpa1-2", "gpa1-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		uart3_data: uart3-data {
-			samsung,pins = "gpa1-4", "gpa1-5";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		spi0_bus: spi0-bus {
-			samsung,pins = "gpa2-0", "gpa2-1", "gpa2-2", "gpa2-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		spi1_bus: spi1-bus {
-			samsung,pins = "gpa2-4", "gpa2-6", "gpa2-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c4_hs_bus: i2c4-hs-bus {
-			samsung,pins = "gpa2-0", "gpa2-1";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c5_hs_bus: i2c5-hs-bus {
-			samsung,pins = "gpa2-2", "gpa2-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2s1_bus: i2s1-bus {
-			samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
-					"gpb0-4";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pcm1_bus: pcm1-bus {
-			samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
-					"gpb0-4";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2s2_bus: i2s2-bus {
-			samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
-					"gpb1-4";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pcm2_bus: pcm2-bus {
-			samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
-					"gpb1-4";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		spdif_bus: spdif-bus {
-			samsung,pins = "gpb1-0", "gpb1-1";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		spi2_bus: spi2-bus {
-			samsung,pins = "gpb1-1", "gpb1-3", "gpb1-4";
-			samsung,pin-function = <5>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c6_hs_bus: i2c6-hs-bus {
-			samsung,pins = "gpb1-3", "gpb1-4";
-			samsung,pin-function = <4>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm0_out: pwm0-out {
-			samsung,pins = "gpb2-0";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm1_out: pwm1-out {
-			samsung,pins = "gpb2-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm2_out: pwm2-out {
-			samsung,pins = "gpb2-2";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		pwm3_out: pwm3-out {
-			samsung,pins = "gpb2-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c7_hs_bus: i2c7-hs-bus {
-			samsung,pins = "gpb2-2", "gpb2-3";
-			samsung,pin-function = <3>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c0_bus: i2c0-bus {
-			samsung,pins = "gpb3-0", "gpb3-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c1_bus: i2c1-bus {
-			samsung,pins = "gpb3-2", "gpb3-3";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c8_hs_bus: i2c8-hs-bus {
-			samsung,pins = "gpb3-4", "gpb3-5";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c9_hs_bus: i2c9-hs-bus {
-			samsung,pins = "gpb3-6", "gpb3-7";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-
-		i2c10_hs_bus: i2c10-hs-bus {
-			samsung,pins = "gpb4-0", "gpb4-1";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
-			samsung,pin-drv = <0>;
-		};
-	};
-
-	pinctrl@03860000 {
-		gpz: gpz {
-			gpio-controller;
-			#gpio-cells = <2>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-		};
-
-		i2s0_bus: i2s0-bus {
-			samsung,pins = "gpz-0", "gpz-1", "gpz-2", "gpz-3",
-					"gpz-4", "gpz-5", "gpz-6";
-			samsung,pin-function = <2>;
-			samsung,pin-pud = <0>;
-			samsung,pin-drv = <0>;
-		};
+&pinctrl_0 {
+	gpy7: gpy7 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpx0: gpx0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		interrupt-parent = <&combiner>;
+		#interrupt-cells = <2>;
+		interrupts = <23 0>, <24 0>, <25 0>, <25 1>,
+			     <26 0>, <26 1>, <27 0>, <27 1>;
+	};
+
+	gpx1: gpx1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		interrupt-parent = <&combiner>;
+		#interrupt-cells = <2>;
+		interrupts = <28 0>, <28 1>, <29 0>, <29 1>,
+			     <30 0>, <30 1>, <31 0>, <31 1>;
+	};
+
+	gpx2: gpx2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpx3: gpx3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	dp_hpd: dp_hpd {
+		samsung,pins = "gpx0-7";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pinctrl_1 {
+	gpc0: gpc0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc1: gpc1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc2: gpc2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc3: gpc3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpc4: gpc4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpd1: gpd1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpy0: gpy0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy1: gpy1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy2: gpy2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy3: gpy3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy4: gpy4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy5: gpy5 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	gpy6: gpy6 {
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	sd0_clk: sd0-clk {
+		samsung,pins = "gpc0-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_cmd: sd0-cmd {
+		samsung,pins = "gpc0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_cd: sd0-cd {
+		samsung,pins = "gpc0-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus1: sd0-bus-width1 {
+		samsung,pins = "gpc0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus4: sd0-bus-width4 {
+		samsung,pins = "gpc0-4", "gpc0-5", "gpc0-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus8: sd0-bus-width8 {
+		samsung,pins = "gpc3-0", "gpc3-1", "gpc3-2", "gpc3-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_clk: sd1-clk {
+		samsung,pins = "gpc1-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_rclk: sd0-rclk {
+		samsung,pins = "gpc0-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <1>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_cmd: sd1-cmd {
+		samsung,pins = "gpc1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_cd: sd1-cd {
+		samsung,pins = "gpc1-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_int: sd1-int {
+		samsung,pins = "gpd1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	sd1_bus1: sd1-bus-width1 {
+		samsung,pins = "gpc1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_bus4: sd1-bus-width4 {
+		samsung,pins = "gpc1-4", "gpc1-5", "gpc1-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd1_bus8: sd1-bus-width8 {
+		samsung,pins = "gpd1-4", "gpd1-5", "gpd1-6", "gpd1-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_clk: sd2-clk {
+		samsung,pins = "gpc2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_cmd: sd2-cmd {
+		samsung,pins = "gpc2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_cd: sd2-cd {
+		samsung,pins = "gpc2-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus1: sd2-bus-width1 {
+		samsung,pins = "gpc2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus4: sd2-bus-width4 {
+		samsung,pins = "gpc2-4", "gpc2-5", "gpc2-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+};
+
+&pinctrl_2 {
+	gpe0: gpe0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpe1: gpe1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf0: gpf0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf1: gpf1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg0: gpg0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg1: gpg1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg2: gpg2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpj4: gpj4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	cam_gpio_a: cam-gpio-a {
+		samsung,pins = "gpe0-0", "gpe0-1", "gpe0-2", "gpe0-3",
+			       "gpe0-4", "gpe0-5", "gpe0-6", "gpe0-7",
+			       "gpe1-0", "gpe1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_gpio_b: cam-gpio-b {
+		samsung,pins = "gpf0-0", "gpf0-1", "gpf0-2", "gpf0-3",
+			       "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_i2c2_bus: cam-i2c2-bus {
+		samsung,pins = "gpf0-4", "gpf0-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_spi1_bus: cam-spi1-bus {
+		samsung,pins = "gpe0-4", "gpe0-5", "gpf0-2", "gpf0-3";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_i2c1_bus: cam-i2c1-bus {
+		samsung,pins = "gpf0-2", "gpf0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_i2c0_bus: cam-i2c0-bus {
+		samsung,pins = "gpf0-0", "gpf0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_spi0_bus: cam-spi0-bus {
+		samsung,pins = "gpf1-0", "gpf1-1", "gpf1-2", "gpf1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	cam_bayrgb_bus: cam-bayrgb-bus {
+		samsung,pins = "gpg0-0", "gpg0-1", "gpg0-2", "gpg0-3",
+			       "gpg0-4", "gpg0-5", "gpg0-6", "gpg0-7",
+			       "gpg1-0", "gpg1-1", "gpg1-2", "gpg1-3",
+			       "gpg1-4", "gpg1-5", "gpg1-6", "gpg1-7",
+			       "gpg2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pinctrl_3 {
+	gpa0: gpa0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpa1: gpa1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpa2: gpa2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb0: gpb0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb1: gpb1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb2: gpb2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb3: gpb3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb4: gpb4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph0: gph0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	uart0_data: uart0-data {
+		samsung,pins = "gpa0-0", "gpa0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart0_fctl: uart0-fctl {
+		samsung,pins = "gpa0-2", "gpa0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart1_data: uart1-data {
+		samsung,pins = "gpa0-4", "gpa0-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart1_fctl: uart1-fctl {
+		samsung,pins = "gpa0-6", "gpa0-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c2_bus: i2c2-bus {
+		samsung,pins = "gpa0-6", "gpa0-7";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart2_data: uart2-data {
+		samsung,pins = "gpa1-0", "gpa1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart2_fctl: uart2-fctl {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c3_bus: i2c3-bus {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart3_data: uart3-data {
+		samsung,pins = "gpa1-4", "gpa1-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	spi0_bus: spi0-bus {
+		samsung,pins = "gpa2-0", "gpa2-1", "gpa2-2", "gpa2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	spi1_bus: spi1-bus {
+		samsung,pins = "gpa2-4", "gpa2-6", "gpa2-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c4_hs_bus: i2c4-hs-bus {
+		samsung,pins = "gpa2-0", "gpa2-1";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c5_hs_bus: i2c5-hs-bus {
+		samsung,pins = "gpa2-2", "gpa2-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2s1_bus: i2s1-bus {
+		samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
+			       "gpb0-4";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pcm1_bus: pcm1-bus {
+		samsung,pins = "gpb0-0", "gpb0-1", "gpb0-2", "gpb0-3",
+			       "gpb0-4";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2s2_bus: i2s2-bus {
+		samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
+			       "gpb1-4";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pcm2_bus: pcm2-bus {
+		samsung,pins = "gpb1-0", "gpb1-1", "gpb1-2", "gpb1-3",
+			       "gpb1-4";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	spdif_bus: spdif-bus {
+		samsung,pins = "gpb1-0", "gpb1-1";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	spi2_bus: spi2-bus {
+		samsung,pins = "gpb1-1", "gpb1-3", "gpb1-4";
+		samsung,pin-function = <5>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c6_hs_bus: i2c6-hs-bus {
+		samsung,pins = "gpb1-3", "gpb1-4";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm0_out: pwm0-out {
+		samsung,pins = "gpb2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm1_out: pwm1-out {
+		samsung,pins = "gpb2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm2_out: pwm2-out {
+		samsung,pins = "gpb2-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm3_out: pwm3-out {
+		samsung,pins = "gpb2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c7_hs_bus: i2c7-hs-bus {
+		samsung,pins = "gpb2-2", "gpb2-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c0_bus: i2c0-bus {
+		samsung,pins = "gpb3-0", "gpb3-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c1_bus: i2c1-bus {
+		samsung,pins = "gpb3-2", "gpb3-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c8_hs_bus: i2c8-hs-bus {
+		samsung,pins = "gpb3-4", "gpb3-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c9_hs_bus: i2c9-hs-bus {
+		samsung,pins = "gpb3-6", "gpb3-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c10_hs_bus: i2c10-hs-bus {
+		samsung,pins = "gpb4-0", "gpb4-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pinctrl_4 {
+	gpz: gpz {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	i2s0_bus: i2s0-bus {
+		samsung,pins = "gpz-0", "gpz-1", "gpz-2", "gpz-3",
+				"gpz-4", "gpz-5", "gpz-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
 	};
 };
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 534f27ceb10b..df9aee92ecf4 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -15,7 +15,6 @@
 
 #include <dt-bindings/clock/exynos5420.h>
 #include "exynos5.dtsi"
-#include "exynos5420-pinctrl.dtsi"
 
 #include <dt-bindings/clock/exynos-audss-clk.h>
 
@@ -1166,3 +1165,5 @@
 	clocks = <&clock CLK_UART3>, <&clock CLK_SCLK_UART3>;
 	clock-names = "uart", "clk_uart_baud0";
 };
+
+#include "exynos5420-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/exynos5422-cpu-thermal.dtsi b/arch/arm/boot/dts/exynos5422-cpu-thermal.dtsi
new file mode 100644
index 000000000000..2b289d7c0d13
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5422-cpu-thermal.dtsi
@@ -0,0 +1,59 @@
+/*
+ * Device tree sources for Exynos5422 thermal zone
+ *
+ * Copyright (c) 2015 Lukasz Majewski <l.majewski@samsung.com>
+ *			Anand Moon <linux.amoon@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <dt-bindings/thermal/thermal.h>
+
+/ {
+	thermal-zones {
+		cpu0_thermal: cpu0-thermal {
+			thermal-sensors = <&tmu_cpu0 0>;
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			trips {
+				cpu_alert0: cpu-alert-0 {
+					temperature = <50000>; /* millicelsius */
+					hysteresis = <5000>; /* millicelsius */
+					type = "active";
+				};
+				cpu_alert1: cpu-alert-1 {
+					temperature = <60000>; /* millicelsius */
+					hysteresis = <5000>; /* millicelsius */
+					type = "active";
+				};
+				cpu_alert2: cpu-alert-2 {
+					temperature = <70000>; /* millicelsius */
+					hysteresis = <5000>; /* millicelsius */
+					type = "active";
+				};
+				cpu_crit0: cpu-crit-0 {
+					temperature = <120000>; /* millicelsius */
+					hysteresis = <0>; /* millicelsius */
+					type = "critical";
+				};
+			};
+			cooling-maps {
+				map0 {
+				     trip = <&cpu_alert0>;
+				     cooling-device = <&fan0 0 1>;
+				};
+				map1 {
+				     trip = <&cpu_alert1>;
+				     cooling-device = <&fan0 1 2>;
+				};
+				map2 {
+				     trip = <&cpu_alert2>;
+				     cooling-device = <&fan0 2 3>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
index 8adf455744e9..1565667e6f69 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
@@ -15,6 +15,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/sound/samsung-i2s.h>
 #include "exynos5800.dtsi"
+#include "exynos5422-cpu-thermal.dtsi"
 
 / {
 	memory {
@@ -107,6 +108,15 @@
 			clocks = <&i2s0 CLK_I2S_CDCLK>;
 		};
 	};
+
+	fan0: pwm-fan {
+		compatible = "pwm-fan";
+		pwms = <&pwm 0 20972 0>;
+		cooling-min-state = <0>;
+		cooling-max-state = <3>;
+		#cooling-cells = <2>;
+		cooling-levels = <0 130 170 230>;
+	};
 };
 
 &clock_audss {
@@ -461,6 +471,32 @@
 	 */
 	pinctrl-0 = <&pwm0_out &pwm1_out &pwm2_out &pwm3_out>;
 	pinctrl-names = "default";
+	samsung,pwm-outputs = <0>;
+	status = "okay";
+};
+
+&tmu_cpu0 {
+	vtmu-supply = <&ldo7_reg>;
+	status = "okay";
+};
+
+&tmu_cpu1 {
+	vtmu-supply = <&ldo7_reg>;
+	status = "okay";
+};
+
+&tmu_cpu2 {
+	vtmu-supply = <&ldo7_reg>;
+	status = "okay";
+};
+
+&tmu_cpu3 {
+	vtmu-supply = <&ldo7_reg>;
+	status = "okay";
+};
+
+&tmu_gpu {
+	vtmu-supply = <&ldo7_reg>;
 	status = "okay";
 };
 
@@ -477,3 +513,13 @@
 &usbdrd_dwc3_1 {
 	dr_mode = "otg";
 };
+
+&usbdrd3_0 {
+	vdd33-supply = <&ldo9_reg>;
+	vdd10-supply = <&ldo11_reg>;
+};
+
+&usbdrd3_1 {
+	vdd33-supply = <&ldo9_reg>;
+	vdd10-supply = <&ldo11_reg>;
+};
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index c892d58e8dad..b995333ea22b 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -468,6 +468,7 @@
 				interrupts = <36 37 38 39 40 41 42 43 44>;
 				status = "disabled";
 				clocks = <&clks 26>;
+				#io-channel-cells = <1>;
 			};
 
 			spdif@80054000 {
diff --git a/arch/arm/boot/dts/imx25-pdk.dts b/arch/arm/boot/dts/imx25-pdk.dts
index dd45e6971bc3..9351296356dc 100644
--- a/arch/arm/boot/dts/imx25-pdk.dts
+++ b/arch/arm/boot/dts/imx25-pdk.dts
@@ -10,6 +10,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include "imx25.dtsi"
 
@@ -114,8 +115,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio2 1 0>;
-	wp-gpios = <&gpio2 0 0>;
+	cd-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 0 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index bc215e4b75fd..feb9d34b239c 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -108,7 +108,7 @@
 			};
 
 			gpt1: timer@10003000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10003000 0x1000>;
 				interrupts = <26>;
 				clocks = <&clks IMX27_CLK_GPT1_IPG_GATE>,
@@ -117,7 +117,7 @@
 			};
 
 			gpt2: timer@10004000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10004000 0x1000>;
 				interrupts = <25>;
 				clocks = <&clks IMX27_CLK_GPT2_IPG_GATE>,
@@ -126,7 +126,7 @@
 			};
 
 			gpt3: timer@10005000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10005000 0x1000>;
 				interrupts = <24>;
 				clocks = <&clks IMX27_CLK_GPT3_IPG_GATE>,
@@ -144,6 +144,15 @@
 				clock-names = "ipg", "per";
 			};
 
+			rtc: rtc@10007000 {
+				compatible = "fsl,imx21-rtc";
+				reg = <0x10007000 0x1000>;
+				interrupts = <22>;
+				clocks = <&clks IMX27_CLK_CKIL>,
+					 <&clks IMX27_CLK_RTC_IPG_GATE>;
+				clock-names = "ref", "ipg";
+			};
+
 			kpp: kpp@10008000 {
 				compatible = "fsl,imx27-kpp", "fsl,imx21-kpp";
 				reg = <0x10008000 0x1000>;
@@ -376,7 +385,7 @@
 			};
 
 			gpt4: timer@10019000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10019000 0x1000>;
 				interrupts = <4>;
 				clocks = <&clks IMX27_CLK_GPT4_IPG_GATE>,
@@ -385,7 +394,7 @@
 			};
 
 			gpt5: timer@1001a000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x1001a000 0x1000>;
 				interrupts = <3>;
 				clocks = <&clks IMX27_CLK_GPT5_IPG_GATE>,
@@ -436,7 +445,7 @@
 			};
 
 			gpt6: timer@1001f000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x1001f000 0x1000>;
 				interrupts = <2>;
 				clocks = <&clks IMX27_CLK_GPT6_IPG_GATE>,
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index b6478e97d6a7..e6540b5cfa4c 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -286,8 +286,8 @@
 			can1: can@53fe4000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe4000 0x1000>;
-				clocks = <&clks 33>;
-				clock-names = "ipg";
+				clocks = <&clks 33>, <&clks 33>;
+				clock-names = "ipg", "per";
 				interrupts = <43>;
 				status = "disabled";
 			};
@@ -295,8 +295,8 @@
 			can2: can@53fe8000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe8000 0x1000>;
-				clocks = <&clks 34>;
-				clock-names = "ipg";
+				clocks = <&clks 34>, <&clks 34>;
+				clock-names = "ipg", "per";
 				interrupts = <44>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/imx51-apf51dev.dts b/arch/arm/boot/dts/imx51-apf51dev.dts
index 93d3ea12328c..0f3fe29b816e 100644
--- a/arch/arm/boot/dts/imx51-apf51dev.dts
+++ b/arch/arm/boot/dts/imx51-apf51dev.dts
@@ -98,7 +98,7 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio2 29 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 29 GPIO_ACTIVE_LOW>;
 	bus-width = <4>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx53-ard.dts b/arch/arm/boot/dts/imx53-ard.dts
index e9337ad52f59..3bc18835fb4b 100644
--- a/arch/arm/boot/dts/imx53-ard.dts
+++ b/arch/arm/boot/dts/imx53-ard.dts
@@ -103,8 +103,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio1 1 0>;
-	wp-gpios = <&gpio1 9 0>;
+	cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 9 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-m53evk.dts b/arch/arm/boot/dts/imx53-m53evk.dts
index d0e0f57eb432..53f40885c530 100644
--- a/arch/arm/boot/dts/imx53-m53evk.dts
+++ b/arch/arm/boot/dts/imx53-m53evk.dts
@@ -124,8 +124,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio1 1 0>;
-	wp-gpios = <&gpio1 9 0>;
+	cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 9 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-qsb-common.dtsi b/arch/arm/boot/dts/imx53-qsb-common.dtsi
index 181ae5ebf23f..53fd75c8ffcf 100644
--- a/arch/arm/boot/dts/imx53-qsb-common.dtsi
+++ b/arch/arm/boot/dts/imx53-qsb-common.dtsi
@@ -147,8 +147,8 @@
 &esdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc3>;
-	cd-gpios = <&gpio3 11 0>;
-	wp-gpios = <&gpio3 12 0>;
+	cd-gpios = <&gpio3 11 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio3 12 GPIO_ACTIVE_HIGH>;
 	bus-width = <8>;
 	status = "okay";
 };
@@ -228,10 +228,11 @@
 			>;
 		};
 
+		/* open drain */
 		pinctrl_i2c1: i2c1grp {
 			fsl,pins = <
-				MX53_PAD_CSI0_DAT8__I2C1_SDA		0xc0000000
-				MX53_PAD_CSI0_DAT9__I2C1_SCL		0xc0000000
+				MX53_PAD_CSI0_DAT8__I2C1_SDA		0x400001ec
+				MX53_PAD_CSI0_DAT9__I2C1_SCL		0x400001ec
 			>;
 		};
 
@@ -295,9 +296,10 @@
 &tve {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_vga_sync>;
+	ddc-i2c-bus = <&i2c2>;
 	fsl,tve-mode = "vga";
-	fsl,hsync-pin = <4>;
-	fsl,vsync-pin = <6>;
+	fsl,hsync-pin = <7>;	/* IPU DI1 PIN7 via EIM_OE */
+	fsl,vsync-pin = <8>;	/* IPU DI1 PIN8 via EIM_RW */
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-qsrb.dts b/arch/arm/boot/dts/imx53-qsrb.dts
index 82d623d05915..66e47de5e826 100644
--- a/arch/arm/boot/dts/imx53-qsrb.dts
+++ b/arch/arm/boot/dts/imx53-qsrb.dts
@@ -20,15 +20,7 @@
 };
 
 &iomuxc {
-	i2c1 {
-		/* open drain */
-		pinctrl_i2c1_qsrb: i2c1grp-1 {
-			fsl,pins = <
-				MX53_PAD_CSI0_DAT8__I2C1_SDA      0x400001ec
-				MX53_PAD_CSI0_DAT9__I2C1_SCL      0x400001ec
-			>;
-		};
-
+	imx53-qsrb {
 		pinctrl_pmic: pmicgrp {
 			fsl,pins = <
 				MX53_PAD_CSI0_DAT5__GPIO5_23	0x1e4 /* IRQ */
@@ -38,10 +30,6 @@
 };
 
 &i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_i2c1_qsrb>;
-	status = "okay";
-
 	pmic: mc34708@8 {
 		compatible = "fsl,mc34708";
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/imx53-smd.dts b/arch/arm/boot/dts/imx53-smd.dts
index 1d325576bcc0..fc89ce1e5763 100644
--- a/arch/arm/boot/dts/imx53-smd.dts
+++ b/arch/arm/boot/dts/imx53-smd.dts
@@ -41,8 +41,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio3 13 0>;
-	wp-gpios = <&gpio4 11 0>;
+	cd-gpios = <&gpio3 13 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-tqma53.dtsi b/arch/arm/boot/dts/imx53-tqma53.dtsi
index 4f1f0e2868bf..e03373a58760 100644
--- a/arch/arm/boot/dts/imx53-tqma53.dtsi
+++ b/arch/arm/boot/dts/imx53-tqma53.dtsi
@@ -41,8 +41,8 @@
 	pinctrl-0 = <&pinctrl_esdhc2>,
 		    <&pinctrl_esdhc2_cdwp>;
 	vmmc-supply = <&reg_3p3v>;
-	wp-gpios = <&gpio1 2 0>;
-	cd-gpios = <&gpio1 4 0>;
+	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/imx53-tx53.dtsi b/arch/arm/boot/dts/imx53-tx53.dtsi
index 704bd72cbfec..d3e50b22064f 100644
--- a/arch/arm/boot/dts/imx53-tx53.dtsi
+++ b/arch/arm/boot/dts/imx53-tx53.dtsi
@@ -183,7 +183,7 @@
 };
 
 &esdhc1 {
-	cd-gpios = <&gpio3 24 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
@@ -191,7 +191,7 @@
 };
 
 &esdhc2 {
-	cd-gpios = <&gpio3 25 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio3 25 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc2>;
diff --git a/arch/arm/boot/dts/imx53-voipac-bsb.dts b/arch/arm/boot/dts/imx53-voipac-bsb.dts
index c17d3ad6dba5..fc51b87ad208 100644
--- a/arch/arm/boot/dts/imx53-voipac-bsb.dts
+++ b/arch/arm/boot/dts/imx53-voipac-bsb.dts
@@ -119,8 +119,8 @@
 &esdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc2>;
-	cd-gpios = <&gpio3 25 0>;
-	wp-gpios = <&gpio2 19 0>;
+	cd-gpios = <&gpio3 25 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 19 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6dl-riotboard.dts b/arch/arm/boot/dts/imx6dl-riotboard.dts
index 43cb3fd76be7..5111f5170d53 100644
--- a/arch/arm/boot/dts/imx6dl-riotboard.dts
+++ b/arch/arm/boot/dts/imx6dl-riotboard.dts
@@ -305,8 +305,8 @@
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio1 4 0>;
-	wp-gpios = <&gpio1 2 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -314,8 +314,8 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 0>;
-	wp-gpios = <&gpio7 1 0>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-arm2.dts b/arch/arm/boot/dts/imx6q-arm2.dts
index 78df05e9d1ce..d6515f7a56c4 100644
--- a/arch/arm/boot/dts/imx6q-arm2.dts
+++ b/arch/arm/boot/dts/imx6q-arm2.dts
@@ -11,6 +11,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx6q.dtsi"
 
 / {
@@ -196,8 +197,8 @@
 };
 
 &usdhc3 {
-	cd-gpios = <&gpio6 11 0>;
-	wp-gpios = <&gpio6 14 0>;
+	cd-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3
diff --git a/arch/arm/boot/dts/imx6q-gk802.dts b/arch/arm/boot/dts/imx6q-gk802.dts
index 703539cf36d3..00bd63e63d0c 100644
--- a/arch/arm/boot/dts/imx6q-gk802.dts
+++ b/arch/arm/boot/dts/imx6q-gk802.dts
@@ -7,6 +7,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx6q.dtsi"
 
 / {
@@ -161,7 +162,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
-	cd-gpios = <&gpio6 11 0>;
+	cd-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts
index a43abfa21e33..5645d52850a7 100644
--- a/arch/arm/boot/dts/imx6q-tbs2910.dts
+++ b/arch/arm/boot/dts/imx6q-tbs2910.dts
@@ -251,7 +251,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
-	cd-gpios = <&gpio2 2 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -260,7 +260,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
-	cd-gpios = <&gpio2 0 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
index e6d9195a1da7..f4d6ae564ead 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
@@ -173,7 +173,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio4 7 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
@@ -181,7 +181,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio4 8 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
index 1d85de2befb3..a47a0399a172 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
@@ -392,7 +392,7 @@
 &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
-	cd-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
 	no-1-8-v;
 	status = "okay";
 };
@@ -400,7 +400,7 @@
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio4 5 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio2 10 GPIO_ACTIVE_HIGH>;
 	no-1-8-v;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
index 59e5d15e3ec4..ff41f83551de 100644
--- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
@@ -258,6 +258,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_cubox_i_usdhc2_aux &pinctrl_cubox_i_usdhc2>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio1 4 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi b/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
index 2c253d6d20bd..45e7c39e80d5 100644
--- a/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
@@ -1,3 +1,5 @@
+#include <dt-bindings/gpio/gpio.h>
+
 / {
 	regulators {
 		compatible = "simple-bus";
@@ -181,7 +183,7 @@
 &usdhc2 { /* module slot */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio2 2 0>;
+	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
index f2867c4b34a8..7b31fdb79ced 100644
--- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
@@ -248,7 +248,6 @@
 				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
 				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
 				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
 				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
 				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
 				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
index b5756c21ea1d..1b66328a8498 100644
--- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
@@ -316,10 +316,13 @@
 };
 
 &usdhc3 {
-	pinctrl-names = "default";
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
+	no-1-8-v; /* firmware will remove if board revision supports */
 	status = "okay";
 };
 
@@ -380,7 +383,6 @@
 				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
 				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
 				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
 				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
 				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
 				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
@@ -469,7 +471,34 @@
 				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x17059
 				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x17059
 				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x17059
-				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00	0x1b0b0 /* CD */
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x17059 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x17059
+			>;
+		};
+
+		pinctrl_usdhc3_100mhz: usdhc3grp100mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x170b9
+				MX6QDL_PAD_SD3_CLK__SD3_CLK		0x170b9
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x170b9
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x170b9
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x170b9
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x170b9
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x170b9 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x170b9
+			>;
+		};
+
+		pinctrl_usdhc3_200mhz: usdhc3grp200mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x170f9
+				MX6QDL_PAD_SD3_CLK__SD3_CLK		0x100f9
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x170f9
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x170f9
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x170f9
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x170f9
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x170f9 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x170f9
 			>;
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
index 86f03c1b147c..7c51839ff934 100644
--- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
@@ -322,10 +322,13 @@
 };
 
 &usdhc3 {
-	pinctrl-names = "default";
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
+	no-1-8-v; /* firmware will remove if board revision supports */
 	status = "okay";
 };
 
@@ -385,7 +388,6 @@
 				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
 				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
 				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
 				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
 				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
 				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
@@ -476,7 +478,34 @@
 				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x17059
 				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x17059
 				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x17059
-				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x1b0b0 /* CD */
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x17059 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x17059
+			>;
+		};
+
+		pinctrl_usdhc3_100mhz: usdhc3grp100mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x170b9
+				MX6QDL_PAD_SD3_CLK__SD3_CLK		0x100b9
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x170b9
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x170b9
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x170b9
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x170b9
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x170b9 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x170b9
+			>;
+		};
+
+		pinctrl_usdhc3_200mhz: usdhc3grp200mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x170f9
+				MX6QDL_PAD_SD3_CLK__SD3_CLK		0x100f9
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x170f9
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x170f9
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x170f9
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x170f9
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x170f9 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x170f9
 			>;
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
index 4a8d97f47759..929e0b37bd9e 100644
--- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
@@ -415,10 +415,13 @@
 };
 
 &usdhc3 {
-	pinctrl-names = "default";
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
+	no-1-8-v; /* firmware will remove if board revision supports */
 	status = "okay";
 };
 
@@ -478,7 +481,6 @@
 				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
 				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
 				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
 				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
 				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
 				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
@@ -568,6 +570,34 @@
 				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x17059
 				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x17059
 				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x17059
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x17059 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x17059
+			>;
+		};
+
+		pinctrl_usdhc3_100mhz: usdhc3grp100mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x170b9
+				MX6QDL_PAD_SD3_CLK__SD3_CLK		0x100b9
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x170b9
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x170b9
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x170b9
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x170b9
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x170b9 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x170b9
+			>;
+		};
+
+		pinctrl_usdhc3_200mhz: usdhc3grp200mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x170f9
+				MX6QDL_PAD_SD3_CLK__SD3_CLK		0x100f9
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x170f9
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x170f9
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x170f9
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x170f9
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00		0x170f9 /* CD */
+				MX6QDL_PAD_NANDF_CS1__SD3_VSELECT	0x170f9
 			>;
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
index d1866a0a2f13..741f3d529e3e 100644
--- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
@@ -250,7 +250,6 @@
 				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
 				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
 				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
 				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
 				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
 				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
diff --git a/arch/arm/boot/dts/imx6qdl-gw552x.dtsi b/arch/arm/boot/dts/imx6qdl-gw552x.dtsi
index 5c6587f6c420..d1e5048b00b5 100644
--- a/arch/arm/boot/dts/imx6qdl-gw552x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw552x.dtsi
@@ -202,7 +202,6 @@
 				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
 				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
 				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
 				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
 				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
 				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
diff --git a/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi b/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
index 62a82f3eba88..6dd0b764e036 100644
--- a/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
@@ -299,6 +299,6 @@
 		&pinctrl_hummingboard_usdhc2
 	>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio1 4 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
index 3af16dfe417b..340bc8e42650 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
@@ -54,6 +54,17 @@
 			gpio = <&gpio3 22 0>;
 			enable-active-high;
 		};
+
+		reg_can_xcvr: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "CAN XCVR";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_can_xcvr>;
+			gpio = <&gpio1 2 GPIO_ACTIVE_LOW>;
+		};
 	};
 
 	gpio-keys {
@@ -149,6 +160,20 @@
 	status = "okay";
 };
 
+&can1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_can1>;
+	xceiver-supply = <&reg_can_xcvr>;
+	status = "okay";
+};
+
+&clks {
+	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
+				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
+};
+
 &ecspi1 {
 	fsl,spi-num-chipselects = <1>;
 	cs-gpios = <&gpio3 19 0>;
@@ -245,6 +270,20 @@
 			>;
 		};
 
+		pinctrl_can1: can1grp {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX	0x1b0b0
+				MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX	0x1b0b0
+			>;
+		};
+
+		pinctrl_can_xcvr: can-xcvrgrp {
+			fsl,pins = <
+				/* Flexcan XCVR enable */
+				MX6QDL_PAD_GPIO_2__GPIO1_IO02		0x1b0b0
+			>;
+		};
+
 		pinctrl_ecspi1: ecspi1grp {
 			fsl,pins = <
 				MX6QDL_PAD_EIM_D17__ECSPI1_MISO		0x100b1
@@ -453,7 +492,7 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 0>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -461,7 +500,7 @@
 &usdhc4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
-	cd-gpios = <&gpio2 6 0>;
+	cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 1ce6133b67f5..9e6ecd99b472 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -409,8 +409,8 @@
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio1 4 0>;
-	wp-gpios = <&gpio1 2 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 	status = "disabled";
 };
 
@@ -418,7 +418,7 @@
         pinctrl-names = "default";
         pinctrl-0 = <&pinctrl_usdhc3
 		     &pinctrl_usdhc3_cdwp>;
-        cd-gpios = <&gpio1 27 0>;
-        wp-gpios = <&gpio1 29 0>;
+	cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
         status = "disabled";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi
index 488a640796ac..3373fd958e95 100644
--- a/arch/arm/boot/dts/imx6qdl-rex.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi
@@ -342,7 +342,7 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 3 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -351,6 +351,6 @@
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index 3b24b12651b2..c37bb9ff9fac 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -28,6 +28,71 @@
 		};
 	};
 
+	clocks {
+		codec_osc: anaclk2 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <24576000>;
+		};
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reg_audio: regulator@0 {
+			compatible = "regulator-fixed";
+			reg = <0>;
+			regulator-name = "cs42888_supply";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+
+		reg_usb_h1_vbus: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "usb_h1_vbus";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&max7310_b 7 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+		};
+
+		reg_usb_otg_vbus: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "usb_otg_vbus";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&max7310_c 1 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+		};
+	};
+
+	sound-cs42888 {
+		compatible = "fsl,imx6-sabreauto-cs42888",
+			"fsl,imx-audio-cs42888";
+		model = "imx-cs42888";
+		audio-cpu = <&esai>;
+		audio-asrc = <&asrc>;
+		audio-codec = <&codec>;
+		audio-routing =
+			"Line Out Jack", "AOUT1L",
+			"Line Out Jack", "AOUT1R",
+			"Line Out Jack", "AOUT2L",
+			"Line Out Jack", "AOUT2R",
+			"Line Out Jack", "AOUT3L",
+			"Line Out Jack", "AOUT3R",
+			"Line Out Jack", "AOUT4L",
+			"Line Out Jack", "AOUT4R",
+			"AIN1L", "Line In Jack",
+			"AIN1R", "Line In Jack",
+			"AIN2L", "Line In Jack",
+			"AIN2R", "Line In Jack";
+	};
+
 	sound-spdif {
 		compatible = "fsl,imx-audio-spdif",
 			   "fsl,imx-sabreauto-spdif";
@@ -45,6 +110,19 @@
 	};
 };
 
+&clks {
+	assigned-clocks = <&clks IMX6QDL_PLL4_BYPASS_SRC>,
+			  <&clks IMX6QDL_PLL4_BYPASS>,
+			  <&clks IMX6QDL_CLK_PLL4_POST_DIV>,
+			  <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_LVDS2_IN>,
+				 <&clks IMX6QDL_PLL4_BYPASS_SRC>,
+				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
+				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
+	assigned-clock-rates = <0>, <0>, <24576000>;
+};
+
 &ecspi1 {
 	fsl,spi-num-chipselects = <1>;
 	cs-gpios = <&gpio3 19 0>;
@@ -61,6 +139,16 @@
 	};
 };
 
+&esai {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_esai>;
+	assigned-clocks = <&clks IMX6QDL_CLK_ESAI_SEL>,
+			  <&clks IMX6QDL_CLK_ESAI_EXTAL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL4_AUDIO_DIV>;
+	assigned-clock-rates = <0>, <24576000>;
+	status = "okay";
+};
+
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
@@ -76,6 +164,10 @@
 	status = "okay";
 };
 
+&hdmi {
+	status = "okay";
+};
+
 &i2c2 {
 	clock-frequency = <100000>;
 	pinctrl-names = "default";
@@ -180,6 +272,18 @@
 			};
 		};
 	};
+
+	codec: cs42888@48 {
+		compatible = "cirrus,cs42888";
+		reg = <0x48>;
+		clocks = <&codec_osc>;
+		clock-names = "mclk";
+		VA-supply = <&reg_audio>;
+		VD-supply = <&reg_audio>;
+		VLS-supply = <&reg_audio>;
+		VLC-supply = <&reg_audio>;
+        };
+
 };
 
 &i2c3 {
@@ -257,6 +361,21 @@
 			>;
 		};
 
+		pinctrl_esai: esaigrp {
+			fsl,pins = <
+				MX6QDL_PAD_ENET_CRS_DV__ESAI_TX_CLK 0x1b030
+				MX6QDL_PAD_ENET_RXD1__ESAI_TX_FS    0x1b030
+				MX6QDL_PAD_ENET_TX_EN__ESAI_TX3_RX2 0x1b030
+				MX6QDL_PAD_GPIO_5__ESAI_TX2_RX3     0x1b030
+				MX6QDL_PAD_ENET_TXD0__ESAI_TX4_RX1  0x1b030
+				MX6QDL_PAD_ENET_MDC__ESAI_TX5_RX0   0x1b030
+				MX6QDL_PAD_GPIO_17__ESAI_TX0        0x1b030
+				MX6QDL_PAD_NANDF_CS3__ESAI_TX1      0x1b030
+				MX6QDL_PAD_ENET_MDIO__ESAI_RX_CLK   0x1b030
+				MX6QDL_PAD_GPIO_9__ESAI_RX_FS       0x1b030
+			>;
+		};
+
 		pinctrl_gpio_leds: gpioledsgrp {
 			fsl,pins = <
 				MX6QDL_PAD_DISP0_DAT21__GPIO5_IO15	0x80000000
@@ -318,6 +437,12 @@
 			>;
 		};
 
+		pinctrl_usbotg: usbotggrp {
+			fsl,pins = <
+				MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
+			>;
+		};
+
 		pinctrl_usdhc3: usdhc3grp {
 			fsl,pins = <
 				MX6QDL_PAD_SD3_CMD__SD3_CMD		0x17059
@@ -462,13 +587,25 @@
 	status = "okay";
 };
 
+&usbh1 {
+	vbus-supply = <&reg_usb_h1_vbus>;
+	status = "okay";
+};
+
+&usbotg {
+	vbus-supply = <&reg_usb_otg_vbus>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg>;
+	status = "okay";
+};
+
 &usdhc3 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
-	cd-gpios = <&gpio6 15 0>;
-	wp-gpios = <&gpio1 13 0>;
+	cd-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 13 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
index e00c44f6a0df..ce4c7313f509 100644
--- a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
@@ -53,6 +53,17 @@
 			gpio = <&gpio3 22 0>;
 			enable-active-high;
 		};
+
+		reg_can_xcvr: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "CAN XCVR";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_can_xcvr>;
+			gpio = <&gpio1 2 GPIO_ACTIVE_LOW>;
+		};
 	};
 
 	gpio-keys {
@@ -148,6 +159,20 @@
 	status = "okay";
 };
 
+&can1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_can1>;
+	xceiver-supply = <&reg_can_xcvr>;
+	status = "okay";
+};
+
+&clks {
+	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
+				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
+};
+
 &ecspi1 {
 	fsl,spi-num-chipselects = <1>;
 	cs-gpios = <&gpio3 19 0>;
@@ -239,6 +264,20 @@
 			>;
 		};
 
+		pinctrl_can1: can1grp {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX	0x1b0b0
+				MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX	0x1b0b0
+			>;
+		};
+
+		pinctrl_can_xcvr: can-xcvrgrp {
+			fsl,pins = <
+				/* Flexcan XCVR enable */
+				MX6QDL_PAD_GPIO_2__GPIO1_IO02		0x1b0b0
+			>;
+		};
+
 		pinctrl_ecspi1: ecspi1grp {
 			fsl,pins = <
 				MX6QDL_PAD_EIM_D17__ECSPI1_MISO		0x100b1
@@ -448,8 +487,8 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 0>;
-	wp-gpios = <&gpio7 1 0>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -457,7 +496,7 @@
 &usdhc4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
-	cd-gpios = <&gpio2 6 0>;
+	cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index a626e6dd8022..2c07d3a86b61 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -141,6 +141,13 @@
 	status = "okay";
 };
 
+&clks {
+	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
+				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
+};
+
 &ecspi1 {
 	fsl,spi-num-chipselects = <1>;
 	cs-gpios = <&gpio4 9 0>;
@@ -562,8 +569,8 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <8>;
-	cd-gpios = <&gpio2 2 0>;
-	wp-gpios = <&gpio2 3 0>;
+	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -571,8 +578,8 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <8>;
-	cd-gpios = <&gpio2 0 0>;
-	wp-gpios = <&gpio2 1 0>;
+	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-tx6.dtsi b/arch/arm/boot/dts/imx6qdl-tx6.dtsi
index f02b80b41d4f..da08de324e9e 100644
--- a/arch/arm/boot/dts/imx6qdl-tx6.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-tx6.dtsi
@@ -680,7 +680,7 @@
 	pinctrl-0 = <&pinctrl_usdhc1>;
 	bus-width = <4>;
 	no-1-8-v;
-	cd-gpios = <&gpio7 2 0>;
+	cd-gpios = <&gpio7 2 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	status = "okay";
 };
@@ -690,7 +690,7 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
 	no-1-8-v;
-	cd-gpios = <&gpio7 3 0>;
+	cd-gpios = <&gpio7 3 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
index 5fb091675582..9e096d811bed 100644
--- a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
@@ -9,6 +9,8 @@
  *
  */
 
+#include <dt-bindings/gpio/gpio.h>
+
 / {
 	regulators {
 		compatible = "simple-bus";
@@ -250,13 +252,13 @@
 &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
-	cd-gpios = <&gpio1 2 0>;
+	cd-gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio3 9 0>;
+	cd-gpios = <&gpio3 9 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index e6d13592080d..e716e6f301c6 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -181,10 +181,10 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 1 &gpc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 2 &gpc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 3 &gpc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 4 &gpc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clks IMX6QDL_CLK_PCIE_AXI>,
 				 <&clks IMX6QDL_CLK_LVDS1_GATE>,
 				 <&clks IMX6QDL_CLK_PCIE_REF_125M>;
@@ -300,8 +300,19 @@
 				};
 
 				esai: esai@02024000 {
+					#sound-dai-cells = <0>;
+					compatible = "fsl,imx35-esai";
 					reg = <0x02024000 0x4000>;
 					interrupts = <0 51 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6QDL_CLK_ESAI_IPG>,
+						 <&clks IMX6QDL_CLK_ESAI_MEM>,
+						 <&clks IMX6QDL_CLK_ESAI_EXTAL>,
+						 <&clks IMX6QDL_CLK_ESAI_IPG>,
+						 <&clks IMX6QDL_CLK_SPBA>;
+					clock-names = "core", "mem", "extal", "fsys", "dma";
+					dmas = <&sdma 23 21 0>, <&sdma 24 21 0>;
+					dma-names = "rx", "tx";
+					status = "disabled";
 				};
 
 				ssi1: ssi@02028000 {
@@ -353,8 +364,28 @@
 				};
 
 				asrc: asrc@02034000 {
+					compatible = "fsl,imx53-asrc";
 					reg = <0x02034000 0x4000>;
 					interrupts = <0 50 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6QDL_CLK_ASRC_IPG>,
+						<&clks IMX6QDL_CLK_ASRC_MEM>, <&clks 0>,
+						<&clks 0>, <&clks 0>, <&clks 0>, <&clks 0>,
+						<&clks 0>, <&clks 0>, <&clks 0>, <&clks 0>,
+						<&clks 0>, <&clks 0>, <&clks 0>, <&clks 0>,
+						<&clks IMX6QDL_CLK_ASRC>, <&clks 0>, <&clks 0>,
+						<&clks IMX6QDL_CLK_SPBA>;
+					clock-names = "mem", "ipg", "asrck_0",
+						"asrck_1", "asrck_2", "asrck_3", "asrck_4",
+						"asrck_5", "asrck_6", "asrck_7", "asrck_8",
+						"asrck_9", "asrck_a", "asrck_b", "asrck_c",
+						"asrck_d", "asrck_e", "asrck_f", "dma";
+					dmas = <&sdma 17 23 1>, <&sdma 18 23 1>, <&sdma 19 23 1>,
+						<&sdma 20 23 1>, <&sdma 21 23 1>, <&sdma 22 23 1>;
+					dma-names = "rxa", "rxb", "rxc",
+							"txa", "txb", "txc";
+					fsl,asrc-rate  = <48000>;
+					fsl,asrc-width = <16>;
+					status = "okay";
 				};
 
 				spba@0203c000 {
@@ -687,22 +718,23 @@
 				fsl,anatop = <&anatop>;
 			};
 
-			snvs@020cc000 {
-				compatible = "fsl,sec-v4.0-mon", "simple-bus";
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0 0x020cc000 0x4000>;
+			snvs: snvs@020cc000 {
+				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x020cc000 0x4000>;
 
-				snvs_rtc: snvs-rtc-lp@34 {
+				snvs_rtc: snvs-rtc-lp {
 					compatible = "fsl,sec-v4.0-mon-rtc-lp";
-					reg = <0x34 0x58>;
+					regmap = <&snvs>;
+					offset = <0x34>;
 					interrupts = <0 19 IRQ_TYPE_LEVEL_HIGH>,
 						     <0 20 IRQ_TYPE_LEVEL_HIGH>;
 				};
 
-				snvs_poweroff: snvs-poweroff@38 {
-					compatible = "fsl,sec-v4.0-poweroff";
-					reg = <0x38 0x4>;
+				snvs_poweroff: snvs-poweroff {
+					compatible = "syscon-poweroff";
+					regmap = <&snvs>;
+					offset = <0x38>;
+					mask = <0x60>;
 					status = "disabled";
 				};
 			};
@@ -836,10 +868,31 @@
 			reg = <0x02100000 0x100000>;
 			ranges;
 
-			caam@02100000 {
-				reg = <0x02100000 0x40000>;
-				interrupts = <0 105 IRQ_TYPE_LEVEL_HIGH>,
-					     <0 106 IRQ_TYPE_LEVEL_HIGH>;
+			crypto: caam@2100000 {
+				compatible = "fsl,sec-v4.0";
+				fsl,sec-era = <4>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0x2100000 0x10000>;
+				ranges = <0 0x2100000 0x10000>;
+				interrupt-parent = <&intc>;
+				clocks = <&clks IMX6QDL_CLK_CAAM_MEM>,
+					 <&clks IMX6QDL_CLK_CAAM_ACLK>,
+					 <&clks IMX6QDL_CLK_CAAM_IPG>,
+					 <&clks IMX6QDL_CLK_EIM_SLOW>;
+				clock-names = "mem", "aclk", "ipg", "emi_slow";
+
+				sec_jr0: jr0@1000 {
+					compatible = "fsl,sec-v4.0-job-ring";
+					reg = <0x1000 0x1000>;
+					interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
+				};
+
+				sec_jr1: jr1@2000 {
+					compatible = "fsl,sec-v4.0-job-ring";
+					reg = <0x2000 0x1000>;
+					interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
+				};
 			};
 
 			aipstz@0217c000 { /* AIPSTZ2 */
diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts
index 945887d3fdb3..b84dff2e94ea 100644
--- a/arch/arm/boot/dts/imx6sl-evk.dts
+++ b/arch/arm/boot/dts/imx6sl-evk.dts
@@ -617,8 +617,8 @@
 	pinctrl-1 = <&pinctrl_usdhc1_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
 	bus-width = <8>;
-	cd-gpios = <&gpio4 7 0>;
-	wp-gpios = <&gpio4 6 0>;
+	cd-gpios = <&gpio4 7 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -627,8 +627,8 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	pinctrl-1 = <&pinctrl_usdhc2_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>;
-	cd-gpios = <&gpio5 0 0>;
-	wp-gpios = <&gpio4 29 0>;
+	cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio4 29 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -637,6 +637,6 @@
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
-	cd-gpios = <&gpio3 22 0>;
+	cd-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6sl-warp.dts b/arch/arm/boot/dts/imx6sl-warp.dts
index 0da906bd8df2..10c69963100f 100644
--- a/arch/arm/boot/dts/imx6sl-warp.dts
+++ b/arch/arm/boot/dts/imx6sl-warp.dts
@@ -61,7 +61,9 @@
 	usdhc3_pwrseq: usdhc3_pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		reset-gpios = <&gpio4 5 GPIO_ACTIVE_LOW>, 	/* WL_REG_ON */
+			      <&gpio4 7 GPIO_ACTIVE_LOW>, 	/* WL_HOSTWAKE */
 			      <&gpio3 25 GPIO_ACTIVE_LOW>, 	/* BT_REG_ON */
+			      <&gpio3 27 GPIO_ACTIVE_LOW>,	/* BT_HOSTWAKE */
 			      <&gpio4 4 GPIO_ACTIVE_LOW>, 	/* BT_WAKE */
 			      <&gpio4 6 GPIO_ACTIVE_LOW>; 	/* BT_RST_N */
 	};
@@ -73,16 +75,16 @@
 	status = "okay";
 };
 
-&uart2 {
+&uart3 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	pinctrl-0 = <&pinctrl_uart3>;
 	status = "okay";
 };
 
-&uart3 {
+&uart5 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_uart3>;
+	pinctrl-0 = <&pinctrl_uart5>;
+	fsl,uart-has-rtscts;
 	status = "okay";
 };
 
@@ -130,14 +132,6 @@
 			>;
 		};
 
-		pinctrl_uart2: uart2grp {
-			fsl,pins = <
-				MX6SL_PAD_EPDC_D12__UART2_RX_DATA	0x41b0b1
-				MX6SL_PAD_EPDC_D13__UART2_TX_DATA	0x41b0b1
-				MX6SL_PAD_EPDC_D14__UART2_RTS_B		0x4130B1
-				MX6SL_PAD_EPDC_D15__UART2_CTS_B		0x4130B1
-			>;
-		};
 
 		pinctrl_uart3: uart3grp {
 			fsl,pins = <
@@ -146,6 +140,15 @@
 			>;
 		};
 
+		pinctrl_uart5: uart5grp {
+			fsl,pins = <
+				MX6SL_PAD_ECSPI1_SCLK__UART5_RX_DATA	0x41b0b1
+				MX6SL_PAD_ECSPI1_MOSI__UART5_TX_DATA	0x41b0b1
+				MX6SL_PAD_ECSPI1_MISO__UART5_RTS_B	0x4130b1
+				MX6SL_PAD_ECSPI1_SS0__UART5_CTS_B	0x4130b1
+			>;
+		};
+
 		pinctrl_usdhc2: usdhc2grp {
 			fsl,pins = <
 				MX6SL_PAD_SD2_CMD__SD2_CMD		0x417059
@@ -158,6 +161,7 @@
 				MX6SL_PAD_SD2_DAT5__SD2_DATA5		0x417059
 				MX6SL_PAD_SD2_DAT6__SD2_DATA6		0x417059
 				MX6SL_PAD_SD2_DAT7__SD2_DATA7		0x417059
+				MX6SL_PAD_SD2_RST__SD2_RESET		0x417059
 			>;
 		};
 
@@ -173,6 +177,7 @@
 				MX6SL_PAD_SD2_DAT5__SD2_DATA5		0x4170b9
 				MX6SL_PAD_SD2_DAT6__SD2_DATA6		0x4170b9
 				MX6SL_PAD_SD2_DAT7__SD2_DATA7		0x4170b9
+				MX6SL_PAD_SD2_RST__SD2_RESET		0x4170b9
 			>;
 		};
 
@@ -188,6 +193,7 @@
 				MX6SL_PAD_SD2_DAT5__SD2_DATA5		0x4170f9
 				MX6SL_PAD_SD2_DAT6__SD2_DATA6		0x4170f9
 				MX6SL_PAD_SD2_DAT7__SD2_DATA7		0x4170f9
+				MX6SL_PAD_SD2_RST__SD2_RESET		0x4170f9
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index a78e715e3982..320a27f8889e 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -563,22 +563,23 @@
 				fsl,anatop = <&anatop>;
 			};
 
-			snvs@020cc000 {
-				compatible = "fsl,sec-v4.0-mon", "simple-bus";
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0 0x020cc000 0x4000>;
+			snvs: snvs@020cc000 {
+				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x020cc000 0x4000>;
 
-				snvs_rtc: snvs-rtc-lp@34 {
+				snvs_rtc: snvs-rtc-lp {
 					compatible = "fsl,sec-v4.0-mon-rtc-lp";
-					reg = <0x34 0x58>;
+					regmap = <&snvs>;
+					offset = <0x34>;
 					interrupts = <0 19 IRQ_TYPE_LEVEL_HIGH>,
 						     <0 20 IRQ_TYPE_LEVEL_HIGH>;
 				};
 
-				snvs_poweroff: snvs-poweroff@38 {
-					compatible = "fsl,sec-v4.0-poweroff";
-					reg = <0x38 0x4>;
+				snvs_poweroff: snvs-poweroff {
+					compatible = "syscon-poweroff";
+					regmap = <&snvs>;
+					offset = <0x38>;
+					mask = <0x60>;
 					status = "disabled";
 				};
 			};
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index e3c0b63c2205..115f3fd78971 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -49,7 +49,7 @@
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
 	bus-width = <8>;
-	cd-gpios = <&gpio7 10 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
 	keep-power-in-suspend;
 	enable-sdio-wakeup;
@@ -61,7 +61,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
 	bus-width = <8>;
-	cd-gpios = <&gpio7 11 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 11 GPIO_ACTIVE_LOW>;
 	no-1-8-v;
 	keep-power-in-suspend;
 	enable-sdio-wakup;
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index cef04cef3a80..ac88c3467078 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -293,7 +293,7 @@
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
 	bus-width = <8>;
-	cd-gpios = <&gpio2 10 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio2 15 GPIO_ACTIVE_HIGH>;
 	keep-power-in-suspend;
 	enable-sdio-wakeup;
@@ -304,7 +304,7 @@
 &usdhc4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
-	cd-gpios = <&gpio6 21 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio6 21 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio6 20 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 708175d59b9c..c94f2ea2316e 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -8,6 +8,7 @@
 
 #include <dt-bindings/clock/imx6sx-clock.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include "imx6sx-pinfunc.h"
 #include "skeleton.dtsi"
@@ -662,22 +663,31 @@
 			};
 
 			snvs: snvs@020cc000 {
-				compatible = "fsl,sec-v4.0-mon", "simple-bus";
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0 0x020cc000 0x4000>;
+				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x020cc000 0x4000>;
 
-				snvs_rtc: snvs-rtc-lp@34 {
+				snvs_rtc: snvs-rtc-lp {
 					compatible = "fsl,sec-v4.0-mon-rtc-lp";
-					reg = <0x34 0x58>;
+					regmap = <&snvs>;
+					offset = <0x34>;
 					interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 				};
 
-				snvs_poweroff: snvs-poweroff@38 {
-					compatible = "fsl,sec-v4.0-poweroff";
-					reg = <0x38 0x4>;
+				snvs_poweroff: snvs-poweroff {
+					compatible = "syscon-poweroff";
+					regmap = <&snvs>;
+					offset = <0x38>;
+					mask = <0x60>;
 					status = "disabled";
 				};
+
+				snvs_pwrkey: snvs-powerkey {
+					compatible = "fsl,sec-v4.0-pwrkey";
+					regmap = <&snvs>;
+					interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+					linux,keycode = <KEY_POWER>;
+					wakeup-source;
+				};
 			};
 
 			epit1: epit@020d0000 {
@@ -738,6 +748,33 @@
 			reg = <0x02100000 0x100000>;
 			ranges;
 
+			crypto: caam@2100000 {
+				compatible = "fsl,sec-v4.0";
+				fsl,sec-era = <4>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0x2100000 0x10000>;
+				ranges = <0 0x2100000 0x10000>;
+				interrupt-parent = <&intc>;
+				clocks = <&clks IMX6SX_CLK_CAAM_MEM>,
+					 <&clks IMX6SX_CLK_CAAM_ACLK>,
+					 <&clks IMX6SX_CLK_CAAM_IPG>,
+					 <&clks IMX6SX_CLK_EIM_SLOW>;
+				clock-names = "mem", "aclk", "ipg", "emi_slow";
+
+				sec_jr0: jr0@1000 {
+					compatible = "fsl,sec-v4.0-job-ring";
+					reg = <0x1000 0x1000>;
+					interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
+				};
+
+				sec_jr1: jr1@2000 {
+					compatible = "fsl,sec-v4.0-job-ring";
+					reg = <0x2000 0x1000>;
+					interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
+				};
+			};
+
 			usbotg1: usb@02184000 {
 				compatible = "fsl,imx6sx-usb", "fsl,imx27-usb";
 				reg = <0x02184000 0x200>;
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dts b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
new file mode 100644
index 000000000000..25746b122ea6
--- /dev/null
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
@@ -0,0 +1,343 @@
+/*
+ * Copyright (C) 2015 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include "imx6ul.dtsi"
+
+/ {
+	model = "Freescale i.MX6 UltraLite 14x14 EVK Board";
+	compatible = "fsl,imx6ul-14x14-evk", "fsl,imx6ul";
+
+	chosen {
+		stdout-path = &uart1;
+	};
+
+	memory {
+		reg = <0x80000000 0x20000000>;
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reg_sd1_vmmc: sd1_regulator {
+			compatible = "regulator-fixed";
+			regulator-name = "VSD_3V3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+		};
+	};
+};
+
+&cpu0 {
+	arm-supply = <&reg_arm>;
+	soc-supply = <&reg_soc>;
+};
+
+&fec1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet1>;
+	phy-mode = "rmii";
+	phy-handle = <&ethphy0>;
+	status = "okay";
+};
+
+&fec2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet2>;
+	phy-mode = "rmii";
+	phy-handle = <&ethphy1>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy0: ethernet-phy@2 {
+			reg = <2>;
+		};
+
+		ethphy1: ethernet-phy@1 {
+			reg = <1>;
+		};
+	};
+};
+
+&qspi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_qspi>;
+	status = "okay";
+
+	flash0: n25q256a@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "micron,n25q256a";
+		spi-max-frequency = <29000000>;
+		reg = <0>;
+	};
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	fsl,uart-has-rtscts;
+	status = "okay";
+};
+
+&usbotg1 {
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&usbotg2 {
+	dr_mode = "host";
+	disable-over-current;
+	status = "okay";
+};
+
+&usdhc1 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	pinctrl-1 = <&pinctrl_usdhc1_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
+	cd-gpios = <&gpio1 19 GPIO_ACTIVE_LOW>;
+	keep-power-in-suspend;
+	enable-sdio-wakeup;
+	vmmc-supply = <&reg_sd1_vmmc>;
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc2>;
+	no-1-8-v;
+	keep-power-in-suspend;
+	enable-sdio-wakeup;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+
+	pinctrl_csi1: csi1grp {
+		fsl,pins = <
+			MX6UL_PAD_CSI_MCLK__CSI_MCLK		0x1b088
+			MX6UL_PAD_CSI_PIXCLK__CSI_PIXCLK	0x1b088
+			MX6UL_PAD_CSI_VSYNC__CSI_VSYNC		0x1b088
+			MX6UL_PAD_CSI_HSYNC__CSI_HSYNC		0x1b088
+			MX6UL_PAD_CSI_DATA00__CSI_DATA02	0x1b088
+			MX6UL_PAD_CSI_DATA01__CSI_DATA03	0x1b088
+			MX6UL_PAD_CSI_DATA02__CSI_DATA04	0x1b088
+			MX6UL_PAD_CSI_DATA03__CSI_DATA05	0x1b088
+			MX6UL_PAD_CSI_DATA04__CSI_DATA06	0x1b088
+			MX6UL_PAD_CSI_DATA05__CSI_DATA07	0x1b088
+			MX6UL_PAD_CSI_DATA06__CSI_DATA08	0x1b088
+			MX6UL_PAD_CSI_DATA07__CSI_DATA09	0x1b088
+		>;
+	};
+
+	pinctrl_enet1: enet1grp {
+		fsl,pins = <
+			MX6UL_PAD_ENET1_RX_EN__ENET1_RX_EN	0x1b0b0
+			MX6UL_PAD_ENET1_RX_ER__ENET1_RX_ER	0x1b0b0
+			MX6UL_PAD_ENET1_RX_DATA0__ENET1_RDATA00	0x1b0b0
+			MX6UL_PAD_ENET1_RX_DATA1__ENET1_RDATA01	0x1b0b0
+			MX6UL_PAD_ENET1_TX_EN__ENET1_TX_EN	0x1b0b0
+			MX6UL_PAD_ENET1_TX_DATA0__ENET1_TDATA00	0x1b0b0
+			MX6UL_PAD_ENET1_TX_DATA1__ENET1_TDATA01	0x1b0b0
+			MX6UL_PAD_ENET1_TX_CLK__ENET1_REF_CLK1	0x4001b031
+		>;
+	};
+
+	pinctrl_enet2: enet2grp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO07__ENET2_MDC		0x1b0b0
+			MX6UL_PAD_GPIO1_IO06__ENET2_MDIO	0x1b0b0
+			MX6UL_PAD_ENET2_RX_EN__ENET2_RX_EN	0x1b0b0
+			MX6UL_PAD_ENET2_RX_ER__ENET2_RX_ER	0x1b0b0
+			MX6UL_PAD_ENET2_RX_DATA0__ENET2_RDATA00	0x1b0b0
+			MX6UL_PAD_ENET2_RX_DATA1__ENET2_RDATA01	0x1b0b0
+			MX6UL_PAD_ENET2_TX_EN__ENET2_TX_EN	0x1b0b0
+			MX6UL_PAD_ENET2_TX_DATA0__ENET2_TDATA00	0x1b0b0
+			MX6UL_PAD_ENET2_TX_DATA1__ENET2_TDATA01	0x1b0b0
+			MX6UL_PAD_ENET2_TX_CLK__ENET2_REF_CLK2	0x4001b031
+			MX6UL_PAD_SNVS_TAMPER0__GPIO5_IO00	0x17059
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp{
+		fsl,pins = <
+			MX6UL_PAD_UART3_RTS_B__FLEXCAN1_RX	0x1b020
+			MX6UL_PAD_UART3_CTS_B__FLEXCAN1_TX	0x1b020
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2grp{
+		fsl,pins = <
+			MX6UL_PAD_UART2_RTS_B__FLEXCAN2_RX	0x1b020
+			MX6UL_PAD_UART2_CTS_B__FLEXCAN2_TX	0x1b020
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX6UL_PAD_UART4_TX_DATA__I2C1_SCL 0x4001b8b0
+			MX6UL_PAD_UART4_RX_DATA__I2C1_SDA 0x4001b8b0
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX6UL_PAD_UART5_TX_DATA__I2C2_SCL 0x4001b8b0
+			MX6UL_PAD_UART5_RX_DATA__I2C2_SDA 0x4001b8b0
+		>;
+	};
+
+	pinctrl_lcdif_dat: lcdifdatgrp {
+		fsl,pins = <
+			MX6UL_PAD_LCD_DATA00__LCDIF_DATA00  0x79
+			MX6UL_PAD_LCD_DATA01__LCDIF_DATA01  0x79
+			MX6UL_PAD_LCD_DATA02__LCDIF_DATA02  0x79
+			MX6UL_PAD_LCD_DATA03__LCDIF_DATA03  0x79
+			MX6UL_PAD_LCD_DATA04__LCDIF_DATA04  0x79
+			MX6UL_PAD_LCD_DATA05__LCDIF_DATA05  0x79
+			MX6UL_PAD_LCD_DATA06__LCDIF_DATA06  0x79
+			MX6UL_PAD_LCD_DATA07__LCDIF_DATA07  0x79
+			MX6UL_PAD_LCD_DATA08__LCDIF_DATA08  0x79
+			MX6UL_PAD_LCD_DATA09__LCDIF_DATA09  0x79
+			MX6UL_PAD_LCD_DATA10__LCDIF_DATA10  0x79
+			MX6UL_PAD_LCD_DATA11__LCDIF_DATA11  0x79
+			MX6UL_PAD_LCD_DATA12__LCDIF_DATA12  0x79
+			MX6UL_PAD_LCD_DATA13__LCDIF_DATA13  0x79
+			MX6UL_PAD_LCD_DATA14__LCDIF_DATA14  0x79
+			MX6UL_PAD_LCD_DATA15__LCDIF_DATA15  0x79
+			MX6UL_PAD_LCD_DATA16__LCDIF_DATA16  0x79
+			MX6UL_PAD_LCD_DATA17__LCDIF_DATA17  0x79
+			MX6UL_PAD_LCD_DATA18__LCDIF_DATA18  0x79
+			MX6UL_PAD_LCD_DATA19__LCDIF_DATA19  0x79
+			MX6UL_PAD_LCD_DATA20__LCDIF_DATA20  0x79
+			MX6UL_PAD_LCD_DATA21__LCDIF_DATA21  0x79
+			MX6UL_PAD_LCD_DATA22__LCDIF_DATA22  0x79
+			MX6UL_PAD_LCD_DATA23__LCDIF_DATA23  0x79
+		>;
+	};
+
+	pinctrl_lcdif_ctrl: lcdifctrlgrp {
+		fsl,pins = <
+			MX6UL_PAD_LCD_CLK__LCDIF_CLK	    0x79
+			MX6UL_PAD_LCD_ENABLE__LCDIF_ENABLE  0x79
+			MX6UL_PAD_LCD_HSYNC__LCDIF_HSYNC    0x79
+			MX6UL_PAD_LCD_VSYNC__LCDIF_VSYNC    0x79
+			/* used for lcd reset */
+			MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09  0x79
+		>;
+	};
+
+	pinctrl_qspi: qspigrp {
+		fsl,pins = <
+			MX6UL_PAD_NAND_WP_B__QSPI_A_SCLK	0x70a1
+			MX6UL_PAD_NAND_READY_B__QSPI_A_DATA00	0x70a1
+			MX6UL_PAD_NAND_CE0_B__QSPI_A_DATA01	0x70a1
+			MX6UL_PAD_NAND_CE1_B__QSPI_A_DATA02	0x70a1
+			MX6UL_PAD_NAND_CLE__QSPI_A_DATA03	0x70a1
+			MX6UL_PAD_NAND_DQS__QSPI_A_SS0_B	0x70a1
+		>;
+	};
+
+	pinctrl_pwm1: pwm1grp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO08__PWM1_OUT   0x110b0
+		>;
+	};
+
+	pinctrl_sim2: sim2grp {
+		fsl,pins = <
+			MX6UL_PAD_CSI_DATA03__SIM2_PORT1_PD		0xb808
+			MX6UL_PAD_CSI_DATA04__SIM2_PORT1_CLK		0x31
+			MX6UL_PAD_CSI_DATA05__SIM2_PORT1_RST_B		0xb808
+			MX6UL_PAD_CSI_DATA06__SIM2_PORT1_SVEN		0xb808
+			MX6UL_PAD_CSI_DATA07__SIM2_PORT1_TRXD		0xb809
+			MX6UL_PAD_CSI_DATA02__GPIO4_IO23		0x3008
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX6UL_PAD_UART1_TX_DATA__UART1_DCE_TX 0x1b0b1
+			MX6UL_PAD_UART1_RX_DATA__UART1_DCE_RX 0x1b0b1
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX6UL_PAD_UART2_TX_DATA__UART2_DCE_TX	0x1b0b1
+			MX6UL_PAD_UART2_RX_DATA__UART2_DCE_RX	0x1b0b1
+			MX6UL_PAD_UART3_RX_DATA__UART2_DCE_RTS	0x1b0b1
+			MX6UL_PAD_UART3_TX_DATA__UART2_DCE_CTS	0x1b0b1
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			MX6UL_PAD_SD1_CMD__USDHC1_CMD     	0x17059
+			MX6UL_PAD_SD1_CLK__USDHC1_CLK     	0x10059
+			MX6UL_PAD_SD1_DATA0__USDHC1_DATA0 	0x17059
+			MX6UL_PAD_SD1_DATA1__USDHC1_DATA1 	0x17059
+			MX6UL_PAD_SD1_DATA2__USDHC1_DATA2 	0x17059
+			MX6UL_PAD_SD1_DATA3__USDHC1_DATA3 	0x17059
+			MX6UL_PAD_UART1_RTS_B__GPIO1_IO19       0x17059 /* SD1 CD */
+			MX6UL_PAD_GPIO1_IO05__USDHC1_VSELECT    0x17059 /* SD1 VSELECT */
+			MX6UL_PAD_GPIO1_IO09__GPIO1_IO09        0x17059 /* SD1 RESET */
+		>;
+	};
+
+	pinctrl_usdhc1_100mhz: usdhc1grp100mhz {
+		fsl,pins = <
+			MX6UL_PAD_SD1_CMD__USDHC1_CMD     0x170b9
+			MX6UL_PAD_SD1_CLK__USDHC1_CLK     0x100b9
+			MX6UL_PAD_SD1_DATA0__USDHC1_DATA0 0x170b9
+			MX6UL_PAD_SD1_DATA1__USDHC1_DATA1 0x170b9
+			MX6UL_PAD_SD1_DATA2__USDHC1_DATA2 0x170b9
+			MX6UL_PAD_SD1_DATA3__USDHC1_DATA3 0x170b9
+
+		>;
+	};
+
+	pinctrl_usdhc1_200mhz: usdhc1grp200mhz {
+		fsl,pins = <
+			MX6UL_PAD_SD1_CMD__USDHC1_CMD     0x170f9
+			MX6UL_PAD_SD1_CLK__USDHC1_CLK     0x100f9
+			MX6UL_PAD_SD1_DATA0__USDHC1_DATA0 0x170f9
+			MX6UL_PAD_SD1_DATA1__USDHC1_DATA1 0x170f9
+			MX6UL_PAD_SD1_DATA2__USDHC1_DATA2 0x170f9
+			MX6UL_PAD_SD1_DATA3__USDHC1_DATA3 0x170f9
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX6UL_PAD_NAND_RE_B__USDHC2_CLK     0x17059
+			MX6UL_PAD_NAND_WE_B__USDHC2_CMD     0x17059
+			MX6UL_PAD_NAND_DATA00__USDHC2_DATA0 0x17059
+			MX6UL_PAD_NAND_DATA01__USDHC2_DATA1 0x17059
+			MX6UL_PAD_NAND_DATA02__USDHC2_DATA2 0x17059
+			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3 0x17059
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx6ul-pinfunc.h b/arch/arm/boot/dts/imx6ul-pinfunc.h
new file mode 100644
index 000000000000..20c7da1affce
--- /dev/null
+++ b/arch/arm/boot/dts/imx6ul-pinfunc.h
@@ -0,0 +1,938 @@
+/*
+ * Copyright (C) 2015 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __DTS_IMX6UL_PINFUNC_H
+#define __DTS_IMX6UL_PINFUNC_H
+
+/*
+ * The pin function ID is a tuple of
+ * <mux_reg conf_reg input_reg mux_mode input_val>
+ */
+#define MX6UL_PAD_BOOT_MODE0__GPIO5_IO10				0x0014 0x02a0 0x0000 5 0
+#define MX6UL_PAD_BOOT_MODE1__GPIO5_IO11				0x0018 0x02a4 0x0000 5 0
+
+#define MX6UL_PAD_SNVS_TAMPER0__GPIO5_IO00				0x001c 0x02a8 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER1__GPIO5_IO01				0x0020 0x02ac 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER2__GPIO5_IO02				0x0024 0x02b0 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER3__GPIO5_IO03				0x0028 0x02b4 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER4__GPIO5_IO04				0x002c 0x02b8 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER5__GPIO5_IO05				0x0030 0x02bc 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER6__GPIO5_IO06				0x0034 0x02c0 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER7__GPIO5_IO07				0x0038 0x02c4 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER8__GPIO5_IO08				0x003c 0x02c8 0x0000 5 0
+#define MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09				0x0040 0x02cc 0x0000 5 0
+
+#define MX6UL_PAD_JTAG_MOD__SJC_MOD                              	0x0044 0x02d0 0x0000 0 0
+#define MX6UL_PAD_JTAG_MOD__GPT2_CLK                             	0x0044 0x02d0 0x05a0 1 0
+#define MX6UL_PAD_JTAG_MOD__SPDIF_OUT                            	0x0044 0x02d0 0x0000 2 0
+#define MX6UL_PAD_JTAG_MOD__ENET1_REF_CLK_25M                    	0x0044 0x02d0 0x0000 3 0
+#define MX6UL_PAD_JTAG_MOD__CCM_PMIC_RDY                         	0x0044 0x02d0 0x04c0 4 0
+#define MX6UL_PAD_JTAG_MOD__GPIO1_IO10                           	0x0044 0x02d0 0x0000 5 0
+#define MX6UL_PAD_JTAG_MOD__SDMA_EXT_EVENT00                     	0x0044 0x02d0 0x0000 6 0
+#define MX6UL_PAD_JTAG_TMS__SJC_TMS                              	0x0048 0x02d4 0x0000 0 0
+#define MX6UL_PAD_JTAG_TMS__GPT2_CAPTURE1                        	0x0048 0x02d4 0x0598 1 0
+#define MX6UL_PAD_JTAG_TMS__SAI2_MCLK                            	0x0048 0x02d4 0x0000 2 0
+#define MX6UL_PAD_JTAG_TMS__CCM_CLKO1                            	0x0048 0x02d4 0x0000 3 0
+#define MX6UL_PAD_JTAG_TMS__CCM_WAIT                             	0x0048 0x02d4 0x0000 4 0
+#define MX6UL_PAD_JTAG_TMS__GPIO1_IO11                           	0x0048 0x02d4 0x0000 5 0
+#define MX6UL_PAD_JTAG_TMS__SDMA_EXT_EVENT01                     	0x0048 0x02d4 0x0000 6 0
+#define MX6UL_PAD_JTAG_TMS__EPIT1_OUT                            	0x0048 0x02d4 0x0000 8 0
+#define MX6UL_PAD_JTAG_TDO__SJC_TDO                              	0x004c 0x02d8 0x0000 0 0
+#define MX6UL_PAD_JTAG_TDO__GPT2_CAPTURE2                        	0x004c 0x02d8 0x059c 1 0
+#define MX6UL_PAD_JTAG_TDO__SAI2_TX_SYNC                         	0x004c 0x02d8 0x05fc 2 0
+#define MX6UL_PAD_JTAG_TDO__CCM_CLKO2                            	0x004c 0x02d8 0x0000 3 0
+#define MX6UL_PAD_JTAG_TDO__CCM_STOP                             	0x004c 0x02d8 0x0000 4 0
+#define MX6UL_PAD_JTAG_TDO__GPIO1_IO12                           	0x004c 0x02d8 0x0000 5 0
+#define MX6UL_PAD_JTAG_TDO__MQS_RIGHT                            	0x004c 0x02d8 0x0000 6 0
+#define MX6UL_PAD_JTAG_TDO__EPIT2_OUT                            	0x004c 0x02d8 0x0000 8 0
+#define MX6UL_PAD_JTAG_TDI__SJC_TDI                              	0x0050 0x02dc 0x0000 0 0
+#define MX6UL_PAD_JTAG_TDI__GPT2_COMPARE1                        	0x0050 0x02dc 0x0000 1 0
+#define MX6UL_PAD_JTAG_TDI__SAI2_TX_BCLK                         	0x0050 0x02dc 0x05f8 2 0
+#define MX6UL_PAD_JTAG_TDI__PWM6_OUT                             	0x0050 0x02dc 0x0000 4 0
+#define MX6UL_PAD_JTAG_TDI__GPIO1_IO13                           	0x0050 0x02dc 0x0000 5 0
+#define MX6UL_PAD_JTAG_TDI__MQS_LEFT                             	0x0050 0x02dc 0x0000 6 0
+#define MX6UL_PAD_JTAG_TDI__SIM1_POWER_FAIL                      	0x0050 0x02dc 0x0000 8 0
+#define MX6UL_PAD_JTAG_TCK__SJC_TCK                              	0x0054 0x02e0 0x0000 0 0
+#define MX6UL_PAD_JTAG_TCK__GPT2_COMPARE2                        	0x0054 0x02e0 0x0000 1 0
+#define MX6UL_PAD_JTAG_TCK__SAI2_RX_DATA                         	0x0054 0x02e0 0x0000 2 0
+#define MX6UL_PAD_JTAG_TCK__PWM7_OUT                             	0x0054 0x02e0 0x0000 4 0
+#define MX6UL_PAD_JTAG_TCK__GPIO1_IO14                           	0x0054 0x02e0 0x0000 5 0
+#define MX6UL_PAD_JTAG_TCK__SIM2_POWER_FAIL                      	0x0054 0x02e0 0x0000 8 0
+#define MX6UL_PAD_JTAG_TRST_B__SJC_TRSTB                         	0x0058 0x02e4 0x0000 0 0
+#define MX6UL_PAD_JTAG_TRST_B__GPT2_COMPARE3                     	0x0058 0x02e4 0x0000 1 0
+#define MX6UL_PAD_JTAG_TRST_B__SAI2_TX_DATA                      	0x0058 0x02e4 0x0000 2 0
+#define MX6UL_PAD_JTAG_TRST_B__PWM8_OUT                          	0x0058 0x02e4 0x0000 4 0
+#define MX6UL_PAD_JTAG_TRST_B__GPIO1_IO15                        	0x0058 0x02e4 0x0000 5 0
+#define MX6UL_PAD_JTAG_TRST_B__CAAM_RNG_OSC_OBS                  	0x0058 0x02e4 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO00__I2C2_SCL                           	0x005c 0x02e8 0x05ac 0 1
+#define MX6UL_PAD_GPIO1_IO00__GPT1_CAPTURE1                      	0x005c 0x02e8 0x058c 1 0
+#define MX6UL_PAD_GPIO1_IO00__ANATOP_OTG1_ID                     	0x005c 0x02e8 0x04b8 2 0
+#define MX6UL_PAD_GPIO1_IO00__ENET1_REF_CLK1                     	0x005c 0x02e8 0x0574 3 0
+#define MX6UL_PAD_GPIO1_IO00__MQS_RIGHT                          	0x005c 0x02e8 0x0000 4 0
+#define MX6UL_PAD_GPIO1_IO00__GPIO1_IO00                         	0x005c 0x02e8 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO00__ENET1_1588_EVENT0_IN               	0x005c 0x02e8 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO00__SRC_SYSTEM_RESET                   	0x005c 0x02e8 0x0000 7 0
+#define MX6UL_PAD_GPIO1_IO00__WDOG3_WDOG_B                       	0x005c 0x02e8 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO01__I2C2_SDA                           	0x0060 0x02ec 0x05b0 0 1
+#define MX6UL_PAD_GPIO1_IO01__GPT1_COMPARE1                      	0x0060 0x02ec 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO01__USB_OTG1_OC                        	0x0060 0x02ec 0x0664 2 0
+#define MX6UL_PAD_GPIO1_IO01__ENET2_REF_CLK2                     	0x0060 0x02ec 0x057c 3 0
+#define MX6UL_PAD_GPIO1_IO01__MQS_LEFT                           	0x0060 0x02ec 0x0000 4 0
+#define MX6UL_PAD_GPIO1_IO01__GPIO1_IO01                         	0x0060 0x02ec 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO01__ENET1_1588_EVENT0_OUT              	0x0060 0x02ec 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO01__SRC_EARLY_RESET                    	0x0060 0x02ec 0x0000 7 0
+#define MX6UL_PAD_GPIO1_IO01__WDOG1_WDOG_B                       	0x0060 0x02ec 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO02__I2C1_SCL                           	0x0064 0x02f0 0x05a4 0 0
+#define MX6UL_PAD_GPIO1_IO02__GPT1_COMPARE2                      	0x0064 0x02f0 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO02__USB_OTG2_PWR                       	0x0064 0x02f0 0x0000 2 0
+#define MX6UL_PAD_GPIO1_IO02__ENET1_REF_CLK_25M                  	0x0064 0x02f0 0x0000 3 0
+#define MX6UL_PAD_GPIO1_IO02__USDHC1_WP                          	0x0064 0x02f0 0x066c 4 0
+#define MX6UL_PAD_GPIO1_IO02__GPIO1_IO02                         	0x0064 0x02f0 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO02__SDMA_EXT_EVENT00                   	0x0064 0x02f0 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO02__SRC_ANY_PU_RESET                   	0x0064 0x02f0 0x0000 7 0
+#define MX6UL_PAD_GPIO1_IO02__UART1_DCE_TX                           	0x0064 0x02f0 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO02__UART1_DTE_RX                           	0x0064 0x02f0 0x0624 8 0
+#define MX6UL_PAD_GPIO1_IO03__I2C1_SDA                           	0x0068 0x02f4 0x05a8 0 1
+#define MX6UL_PAD_GPIO1_IO03__GPT1_COMPARE3                      	0x0068 0x02f4 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO03__USB_OTG2_OC                        	0x0068 0x02f4 0x0660 2 0
+#define MX6UL_PAD_GPIO1_IO03__USDHC1_CD_B                        	0x0068 0x02f4 0x0668 4 0
+#define MX6UL_PAD_GPIO1_IO03__GPIO1_IO03                         	0x0068 0x02f4 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO03__CCM_DI0_eXT_CLK                    	0x0068 0x02f4 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO03__SRC_TESTER_ACK                     	0x0068 0x02f4 0x0000 7 0
+#define MX6UL_PAD_GPIO1_IO03__UART1_DTE_TX                           	0x0068 0x02f4 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO03__UART1_DCE_RX                           	0x0068 0x02f4 0x0624 8 1
+#define MX6UL_PAD_GPIO1_IO04__ENET1_REF_CLK1                     	0x006c 0x02f8 0x0574 0 1
+#define MX6UL_PAD_GPIO1_IO04__PWM3_OUT                           	0x006c 0x02f8 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO04__USB_OTG1_PWR                       	0x006c 0x02f8 0x0000 2 0
+#define MX6UL_PAD_GPIO1_IO04__USDHC1_RESET_B                     	0x006c 0x02f8 0x0000 4 0
+#define MX6UL_PAD_GPIO1_IO04__GPIO1_IO04                         	0x006c 0x02f8 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO04__ENET2_1588_EVENT0_IN               	0x006c 0x02f8 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO04__UART5_DCE_TX                           	0x006c 0x02f8 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO04__UART5_DTE_RX                           	0x006c 0x02f8 0x0644 8 2
+#define MX6UL_PAD_GPIO1_IO05__ENET2_REF_CLK2                     	0x0070 0x02fc 0x057c 0 1
+#define MX6UL_PAD_GPIO1_IO05__PWM4_OUT                           	0x0070 0x02fc 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO05__ANATOP_OTG2_ID                     	0x0070 0x02fc 0x04bc 2 0
+#define MX6UL_PAD_GPIO1_IO05__CSI_FIELD                          	0x0070 0x02fc 0x0530 3 0
+#define MX6UL_PAD_GPIO1_IO05__USDHC1_VSELECT                     	0x0070 0x02fc 0x0000 4 0
+#define MX6UL_PAD_GPIO1_IO05__GPIO1_IO05                         	0x0070 0x02fc 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO05__ENET2_1588_EVENT0_OUT              	0x0070 0x02fc 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO05__UART5_DCE_RX                           	0x0070 0x02fc 0x0644 8 3
+#define MX6UL_PAD_GPIO1_IO05__UART5_DTE_TX                           	0x0070 0x02fc 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO06__ENET1_MDIO                         	0x0074 0x0300 0x0578 0 0
+#define MX6UL_PAD_GPIO1_IO06__ENET2_MDIO                         	0x0074 0x0300 0x0580 1 0
+#define MX6UL_PAD_GPIO1_IO06__USB_OTG_PWR_WAKE                   	0x0074 0x0300 0x0000 2 0
+#define MX6UL_PAD_GPIO1_IO06__CSI_MCLK                           	0x0074 0x0300 0x0000 3 0
+#define MX6UL_PAD_GPIO1_IO06__USDHC2_WP                          	0x0074 0x0300 0x069c 4 0
+#define MX6UL_PAD_GPIO1_IO06__GPIO1_IO06                         	0x0074 0x0300 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO06__CCM_WAIT                           	0x0074 0x0300 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO06__CCM_REF_EN_B                       	0x0074 0x0300 0x0000 7 0
+#define MX6UL_PAD_GPIO1_IO06__UART1_DCE_CTS                      	0x0074 0x0300 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO06__UART1_DTE_RTS                      	0x0074 0x0300 0x0620 8 0
+#define MX6UL_PAD_GPIO1_IO07__ENET1_MDC                          	0x0078 0x0304 0x0000 0 0
+#define MX6UL_PAD_GPIO1_IO07__ENET2_MDC                          	0x0078 0x0304 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO07__USB_OTG_HOST_MODE                  	0x0078 0x0304 0x0000 2 0
+#define MX6UL_PAD_GPIO1_IO07__CSI_PIXCLK                         	0x0078 0x0304 0x0528 3 0
+#define MX6UL_PAD_GPIO1_IO07__USDHC2_CD_B                        	0x0078 0x0304 0x0674 4 1
+#define MX6UL_PAD_GPIO1_IO07__GPIO1_IO07                         	0x0078 0x0304 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO07__CCM_STOP                           	0x0078 0x0304 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO07__UART1_DCE_RTS                      	0x0078 0x0304 0x0620 8 1
+#define MX6UL_PAD_GPIO1_IO07__UART1_DTE_CTS                      	0x0078 0x0304 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO08__PWM1_OUT                           	0x007c 0x0308 0x0000 0 0
+#define MX6UL_PAD_GPIO1_IO08__WDOG1_WDOG_B                       	0x007c 0x0308 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO08__SPDIF_OUT                          	0x007c 0x0308 0x0000 2 0
+#define MX6UL_PAD_GPIO1_IO08__CSI_VSYNC                          	0x007c 0x0308 0x052c 3 1
+#define MX6UL_PAD_GPIO1_IO08__USDHC2_VSELECT                     	0x007c 0x0308 0x0000 4 0
+#define MX6UL_PAD_GPIO1_IO08__GPIO1_IO08                         	0x007c 0x0308 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO08__CCM_PMIC_RDY                       	0x007c 0x0308 0x04c0 6 1
+#define MX6UL_PAD_GPIO1_IO08__UART5_DCE_RTS                      	0x007c 0x0308 0x0640 8 1
+#define MX6UL_PAD_GPIO1_IO08__UART5_DTE_CTS                      	0x007c 0x0308 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO09__PWM2_OUT                           	0x0080 0x030c 0x0000 0 0
+#define MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY                     	0x0080 0x030c 0x0000 1 0
+#define MX6UL_PAD_GPIO1_IO09__SPDIF_IN                           	0x0080 0x030c 0x0618 2 0
+#define MX6UL_PAD_GPIO1_IO09__CSI_HSYNC                          	0x0080 0x030c 0x0524 3 1
+#define MX6UL_PAD_GPIO1_IO09__USDHC2_RESET_B                     	0x0080 0x030c 0x0000 4 0
+#define MX6UL_PAD_GPIO1_IO09__GPIO1_IO09                         	0x0080 0x030c 0x0000 5 0
+#define MX6UL_PAD_GPIO1_IO09__USDHC1_RESET_B                     	0x0080 0x030c 0x0000 6 0
+#define MX6UL_PAD_GPIO1_IO09__UART5_DCE_CTS                      	0x0080 0x030c 0x0000 8 0
+#define MX6UL_PAD_GPIO1_IO09__UART5_DTE_RTS                      	0x0080 0x030c 0x0640 8 2
+#define MX6UL_PAD_UART1_TX_DATA__UART1_DCE_TX                        	0x0084 0x0310 0x0000 0 0
+#define MX6UL_PAD_UART1_TX_DATA__UART1_DTE_RX                        	0x0084 0x0310 0x0624 0 2
+#define MX6UL_PAD_UART1_TX_DATA__ENET1_RDATA02                   	0x0084 0x0310 0x0000 1 0
+#define MX6UL_PAD_UART1_TX_DATA__I2C3_SCL                        	0x0084 0x0310 0x05b4 2 0
+#define MX6UL_PAD_UART1_TX_DATA__CSI_DATA02                      	0x0084 0x0310 0x0000 3 0
+#define MX6UL_PAD_UART1_TX_DATA__GPT1_COMPARE1                   	0x0084 0x0310 0x0000 4 0
+#define MX6UL_PAD_UART1_TX_DATA__GPIO1_IO16                      	0x0084 0x0310 0x0000 5 0
+#define MX6UL_PAD_UART1_TX_DATA__SPDIF_OUT                       	0x0084 0x0310 0x0000 8 0
+#define MX6UL_PAD_UART1_RX_DATA__UART1_DCE_RX                        	0x0088 0x0314 0x0624 0 3
+#define MX6UL_PAD_UART1_RX_DATA__UART1_DTE_TX                        	0x0088 0x0314 0x0000 0 0
+#define MX6UL_PAD_UART1_RX_DATA__ENET1_RDATA03                   	0x0088 0x0314 0x0000 1 0
+#define MX6UL_PAD_UART1_RX_DATA__I2C3_SDA                        	0x0088 0x0314 0x05b8 2 0
+#define MX6UL_PAD_UART1_RX_DATA__CSI_DATA03                      	0x0088 0x0314 0x0000 3 0
+#define MX6UL_PAD_UART1_RX_DATA__GPT1_CLK                        	0x0088 0x0314 0x0594 4 0
+#define MX6UL_PAD_UART1_RX_DATA__GPIO1_IO17                      	0x0088 0x0314 0x0000 5 0
+#define MX6UL_PAD_UART1_RX_DATA__SPDIF_IN                        	0x0088 0x0314 0x0000 8 0
+#define MX6UL_PAD_UART1_CTS_B__UART1_DCE_CTS                     	0x008c 0x0318 0x0000 0 0
+#define MX6UL_PAD_UART1_CTS_B__UART1_DTE_RTS                     	0x008c 0x0318 0x0620 0 2
+#define MX6UL_PAD_UART1_CTS_B__ENET1_RX_CLK                      	0x008c 0x0318 0x0000 1 0
+#define MX6UL_PAD_UART1_CTS_B__USDHC1_WP                         	0x008c 0x0318 0x066c 2 1
+#define MX6UL_PAD_UART1_CTS_B__CSI_DATA04                        	0x008c 0x0318 0x0000 3 0
+#define MX6UL_PAD_UART1_CTS_B__ENET2_1588_EVENT1_IN              	0x008c 0x0318 0x0000 4 0
+#define MX6UL_PAD_UART1_CTS_B__GPIO1_IO18                        	0x008c 0x0318 0x0000 5 0
+#define MX6UL_PAD_UART1_CTS_B__USDHC2_WP                         	0x008c 0x0318 0x0000 8 0
+#define MX6UL_PAD_UART1_RTS_B__UART1_DCE_RTS                     	0x0090 0x031c 0x0620 0 3
+#define MX6UL_PAD_UART1_RTS_B__UART1_DTE_CTS                     	0x0090 0x031c 0x0000 0 0
+#define MX6UL_PAD_UART1_RTS_B__ENET1_TX_ER                       	0x0090 0x031c 0x0000 1 0
+#define MX6UL_PAD_UART1_RTS_B__USDHC1_CD_B                       	0x0090 0x031c 0x0668 2 1
+#define MX6UL_PAD_UART1_RTS_B__CSI_DATA05                        	0x0090 0x031c 0x0000 3 0
+#define MX6UL_PAD_UART1_RTS_B__ENET2_1588_EVENT1_OUT             	0x0090 0x031c 0x0000 4 0
+#define MX6UL_PAD_UART1_RTS_B__GPIO1_IO19                        	0x0090 0x031c 0x0000 5 0
+#define MX6UL_PAD_UART1_RTS_B__USDHC2_CD_B                       	0x0090 0x031c 0x0000 8 0
+#define MX6UL_PAD_UART2_TX_DATA__UART2_DCE_TX                        	0x0094 0x0320 0x0000 0 0
+#define MX6UL_PAD_UART2_TX_DATA__UART2_DTE_RX                        	0x0094 0x0320 0x062c 0 0
+#define MX6UL_PAD_UART2_TX_DATA__ENET1_TDATA02                   	0x0094 0x0320 0x0000 1 0
+#define MX6UL_PAD_UART2_TX_DATA__I2C4_SCL                        	0x0094 0x0320 0x05bc 2 0
+#define MX6UL_PAD_UART2_TX_DATA__CSI_DATA06                      	0x0094 0x0320 0x0000 3 0
+#define MX6UL_PAD_UART2_TX_DATA__GPT1_CAPTURE1                   	0x0094 0x0320 0x058c 4 1
+#define MX6UL_PAD_UART2_TX_DATA__GPIO1_IO20                      	0x0094 0x0320 0x0000 5 0
+#define MX6UL_PAD_UART2_TX_DATA__ECSPI3_SS0                      	0x0094 0x0320 0x0000 8 0
+#define MX6UL_PAD_UART2_RX_DATA__UART2_DCE_RX                        	0x0098 0x0324 0x062c 0 1
+#define MX6UL_PAD_UART2_RX_DATA__UART2_DTE_TX                        	0x0098 0x0324 0x0000 0 0
+#define MX6UL_PAD_UART2_RX_DATA__ENET1_TDATA03                   	0x0098 0x0324 0x0000 1 0
+#define MX6UL_PAD_UART2_RX_DATA__I2C4_SDA                        	0x0098 0x0324 0x05c0 2 0
+#define MX6UL_PAD_UART2_RX_DATA__CSI_DATA07                      	0x0098 0x0324 0x0000 3 0
+#define MX6UL_PAD_UART2_RX_DATA__GPT1_CAPTURE2                   	0x0098 0x0324 0x0590 4 0
+#define MX6UL_PAD_UART2_RX_DATA__GPIO1_IO21                      	0x0098 0x0324 0x0000 5 0
+#define MX6UL_PAD_UART2_RX_DATA__SJC_DONE                        	0x0098 0x0324 0x0000 7 0
+#define MX6UL_PAD_UART2_RX_DATA__ECSPI3_SCLK                     	0x0098 0x0324 0x0000 8 0
+#define MX6UL_PAD_UART2_CTS_B__UART2_DCE_CTS                     	0x009c 0x0328 0x0000 0 0
+#define MX6UL_PAD_UART2_CTS_B__UART2_DTE_RTS                     	0x009c 0x0328 0x0628 0 0
+#define MX6UL_PAD_UART2_CTS_B__ENET1_CRS                         	0x009c 0x0328 0x0000 1 0
+#define MX6UL_PAD_UART2_CTS_B__FLEXCAN2_TX                       	0x009c 0x0328 0x0000 2 0
+#define MX6UL_PAD_UART2_CTS_B__CSI_DATA08                        	0x009c 0x0328 0x0000 3 0
+#define MX6UL_PAD_UART2_CTS_B__GPT1_COMPARE2                     	0x009c 0x0328 0x0000 4 0
+#define MX6UL_PAD_UART2_CTS_B__GPIO1_IO22                        	0x009c 0x0328 0x0000 5 0
+#define MX6UL_PAD_UART2_CTS_B__SJC_DE_B                          	0x009c 0x0328 0x0000 7 0
+#define MX6UL_PAD_UART2_CTS_B__ECSPI3_MOSI                       	0x009c 0x0328 0x0000 8 0
+#define MX6UL_PAD_UART2_RTS_B__UART2_DCE_RTS                     	0x00a0 0x032c 0x0628 0 1
+#define MX6UL_PAD_UART2_RTS_B__UART2_DTE_CTS                     	0x00a0 0x032c 0x0000 0 0
+#define MX6UL_PAD_UART2_RTS_B__ENET1_COL                         	0x00a0 0x032c 0x0000 1 0
+#define MX6UL_PAD_UART2_RTS_B__FLEXCAN2_RX                       	0x00a0 0x032c 0x0588 2 0
+#define MX6UL_PAD_UART2_RTS_B__CSI_DATA09                        	0x00a0 0x032c 0x0000 3 0
+#define MX6UL_PAD_UART2_RTS_B__GPT1_COMPARE3                     	0x00a0 0x032c 0x0000 4 0
+#define MX6UL_PAD_UART2_RTS_B__GPIO1_IO23                        	0x00a0 0x032c 0x0000 5 0
+#define MX6UL_PAD_UART2_RTS_B__SJC_FAIL                          	0x00a0 0x032c 0x0000 7 0
+#define MX6UL_PAD_UART2_RTS_B__ECSPI3_MISO                       	0x00a0 0x032c 0x0000 8 0
+#define MX6UL_PAD_UART3_TX_DATA__UART3_DCE_TX                        	0x00a4 0x0330 0x0000 0 0
+#define MX6UL_PAD_UART3_TX_DATA__UART3_DTE_RX                        	0x00a4 0x0330 0x0634 0 0
+#define MX6UL_PAD_UART3_TX_DATA__ENET2_RDATA02                   	0x00a4 0x0330 0x0000 1 0
+#define MX6UL_PAD_UART3_TX_DATA__SIM1_PORT0_PD                   	0x00a4 0x0330 0x0000 2 0
+#define MX6UL_PAD_UART3_TX_DATA__CSI_DATA01                      	0x00a4 0x0330 0x0000 3 0
+#define MX6UL_PAD_UART3_TX_DATA__UART2_DCE_CTS                   	0x00a4 0x0330 0x0000 4 0
+#define MX6UL_PAD_UART3_TX_DATA__UART2_DTE_RTS                   	0x00a4 0x0330 0x0628 4 2
+#define MX6UL_PAD_UART3_TX_DATA__GPIO1_IO24                      	0x00a4 0x0330 0x0000 5 0
+#define MX6UL_PAD_UART3_TX_DATA__SJC_JTAG_ACT                    	0x00a4 0x0330 0x0000 7 0
+#define MX6UL_PAD_UART3_TX_DATA__ANATOP_OTG1_ID                  	0x00a4 0x0330 0x0000 8 0
+#define MX6UL_PAD_UART3_RX_DATA__UART3_DCE_RX                        	0x00a8 0x0334 0x0634 0 1
+#define MX6UL_PAD_UART3_RX_DATA__UART3_DTE_TX                        	0x00a8 0x0334 0x0000 0 0
+#define MX6UL_PAD_UART3_RX_DATA__ENET2_RDATA03                   	0x00a8 0x0334 0x0000 1 0
+#define MX6UL_PAD_UART3_RX_DATA__SIM2_PORT0_PD                   	0x00a8 0x0334 0x0000 2 0
+#define MX6UL_PAD_UART3_RX_DATA__CSI_DATA00                      	0x00a8 0x0334 0x0000 3 0
+#define MX6UL_PAD_UART3_RX_DATA__UART2_DCE_RTS                   	0x00a8 0x0334 0x0628 4 3
+#define MX6UL_PAD_UART3_RX_DATA__UART2_DTE_CTS                   	0x00a8 0x0334 0x0000 4 0
+#define MX6UL_PAD_UART3_RX_DATA__GPIO1_IO25                      	0x00a8 0x0334 0x0000 5 0
+#define MX6UL_PAD_UART3_RX_DATA__EPIT1_OUT                       	0x00a8 0x0334 0x0000 8 0
+#define MX6UL_PAD_UART3_CTS_B__UART3_DCE_CTS                     	0x00ac 0x0338 0x0000 0 0
+#define MX6UL_PAD_UART3_CTS_B__UART3_DTE_RTS                     	0x00ac 0x0338 0x0630 0 0
+#define MX6UL_PAD_UART3_CTS_B__ENET2_RX_CLK                      	0x00ac 0x0338 0x0000 1 0
+#define MX6UL_PAD_UART3_CTS_B__FLEXCAN1_TX                       	0x00ac 0x0338 0x0000 2 0
+#define MX6UL_PAD_UART3_CTS_B__CSI_DATA10                        	0x00ac 0x0338 0x0000 3 0
+#define MX6UL_PAD_UART3_CTS_B__ENET1_1588_EVENT1_IN              	0x00ac 0x0338 0x0000 4 0
+#define MX6UL_PAD_UART3_CTS_B__GPIO1_IO26                        	0x00ac 0x0338 0x0000 5 0
+#define MX6UL_PAD_UART3_CTS_B__EPIT2_OUT                         	0x00ac 0x0338 0x0000 8 0
+#define MX6UL_PAD_UART3_RTS_B__UART3_DCE_RTS                     	0x00b0 0x033c 0x0630 0 1
+#define MX6UL_PAD_UART3_RTS_B__UART3_DTE_CTS                     	0x00b0 0x033c 0x0000 0 0
+#define MX6UL_PAD_UART3_RTS_B__ENET2_TX_ER                       	0x00b0 0x033c 0x0000 1 0
+#define MX6UL_PAD_UART3_RTS_B__FLEXCAN1_RX                       	0x00b0 0x033c 0x0584 2 0
+#define MX6UL_PAD_UART3_RTS_B__CSI_DATA11                        	0x00b0 0x033c 0x0000 3 0
+#define MX6UL_PAD_UART3_RTS_B__ENET1_1588_EVENT1_OUT             	0x00b0 0x033c 0x0000 4 0
+#define MX6UL_PAD_UART3_RTS_B__GPIO1_IO27                        	0x00b0 0x033c 0x0000 5 0
+#define MX6UL_PAD_UART3_RTS_B__WDOG1_WDOG_B                      	0x00b0 0x033c 0x0000 8 0
+#define MX6UL_PAD_UART4_TX_DATA__UART4_DCE_TX                        	0x00b4 0x0340 0x0000 0 0
+#define MX6UL_PAD_UART4_TX_DATA__UART4_DTE_RX                        	0x00b4 0x0340 0x063c 0 0
+#define MX6UL_PAD_UART4_TX_DATA__ENET2_TDATA02                   	0x00b4 0x0340 0x0000 1 0
+#define MX6UL_PAD_UART4_TX_DATA__I2C1_SCL                        	0x00b4 0x0340 0x05a4 2 1
+#define MX6UL_PAD_UART4_TX_DATA__CSI_DATA12                      	0x00b4 0x0340 0x0000 3 0
+#define MX6UL_PAD_UART4_TX_DATA__CSU_CSU_ALARM_AUT02             	0x00b4 0x0340 0x0000 4 0
+#define MX6UL_PAD_UART4_TX_DATA__GPIO1_IO28                      	0x00b4 0x0340 0x0000 5 0
+#define MX6UL_PAD_UART4_TX_DATA__ECSPI2_SCLK                     	0x00b4 0x0340 0x0000 8 0
+#define MX6UL_PAD_UART4_RX_DATA__UART4_DCE_RX                        	0x00b8 0x0344 0x063c 0 1
+#define MX6UL_PAD_UART4_RX_DATA__UART4_DTE_TX                        	0x00b8 0x0344 0x0000 0 0
+#define MX6UL_PAD_UART4_RX_DATA__ENET2_TDATA03                   	0x00b8 0x0344 0x0000 1 0
+#define MX6UL_PAD_UART4_RX_DATA__I2C1_SDA                        	0x00b8 0x0344 0x05a8 2 2
+#define MX6UL_PAD_UART4_RX_DATA__CSI_DATA13                      	0x00b8 0x0344 0x0000 3 0
+#define MX6UL_PAD_UART4_RX_DATA__CSU_CSU_ALARM_AUT01             	0x00b8 0x0344 0x0000 4 0
+#define MX6UL_PAD_UART4_RX_DATA__GPIO1_IO29                      	0x00b8 0x0344 0x0000 5 0
+#define MX6UL_PAD_UART4_RX_DATA__ECSPI2_SS0                      	0x00b8 0x0344 0x0000 8 0
+#define MX6UL_PAD_UART5_TX_DATA__GPIO1_IO30                      	0x00bc 0x0348 0x0000 5 0
+#define MX6UL_PAD_UART5_TX_DATA__ECSPI2_MOSI                     	0x00bc 0x0348 0x0000 8 0
+#define MX6UL_PAD_UART5_TX_DATA__UART5_DCE_TX                        	0x00bc 0x0348 0x0000 0 0
+#define MX6UL_PAD_UART5_TX_DATA__UART5_DTE_RX                        	0x00bc 0x0348 0x0644 0 4
+#define MX6UL_PAD_UART5_TX_DATA__ENET2_CRS                       	0x00bc 0x0348 0x0000 1 0
+#define MX6UL_PAD_UART5_TX_DATA__I2C2_SCL                        	0x00bc 0x0348 0x05ac 2 2
+#define MX6UL_PAD_UART5_TX_DATA__CSI_DATA14                      	0x00bc 0x0348 0x0000 3 0
+#define MX6UL_PAD_UART5_TX_DATA__CSU_CSU_ALARM_AUT00             	0x00bc 0x0348 0x0000 4 0
+#define MX6UL_PAD_UART5_RX_DATA__UART5_DCE_RX                        	0x00c0 0x034c 0x0644 0 5
+#define MX6UL_PAD_UART5_RX_DATA__UART5_DTE_TX                        	0x00c0 0x034c 0x0000 0 0
+#define MX6UL_PAD_UART5_RX_DATA__ENET2_COL                       	0x00c0 0x034c 0x0000 1 0
+#define MX6UL_PAD_UART5_RX_DATA__I2C2_SDA                        	0x00c0 0x034c 0x05b0 2 2
+#define MX6UL_PAD_UART5_RX_DATA__CSI_DATA15                      	0x00c0 0x034c 0x0000 3 0
+#define MX6UL_PAD_UART5_RX_DATA__CSU_CSU_INT_DEB                 	0x00c0 0x034c 0x0000 4 0
+#define MX6UL_PAD_UART5_RX_DATA__GPIO1_IO31                      	0x00c0 0x034c 0x0000 5 0
+#define MX6UL_PAD_UART5_RX_DATA__ECSPI2_MISO                     	0x00c0 0x034c 0x0000 8 0
+#define MX6UL_PAD_ENET1_RX_DATA0__ENET1_RDATA00                  	0x00c4 0x0350 0x0000 0 0
+#define MX6UL_PAD_ENET1_RX_DATA0__UART4_DCE_RTS                  	0x00c4 0x0350 0x0638 1 0
+#define MX6UL_PAD_ENET1_RX_DATA0__UART4_DTE_CTS                  	0x00c4 0x0350 0x0000 1 0
+#define MX6UL_PAD_ENET1_RX_DATA0__PWM1_OUT                       	0x00c4 0x0350 0x0000 2 0
+#define MX6UL_PAD_ENET1_RX_DATA0__CSI_DATA16                     	0x00c4 0x0350 0x0000 3 0
+#define MX6UL_PAD_ENET1_RX_DATA0__FLEXCAN1_TX                    	0x00c4 0x0350 0x0000 4 0
+#define MX6UL_PAD_ENET1_RX_DATA0__GPIO2_IO00                     	0x00c4 0x0350 0x0000 5 0
+#define MX6UL_PAD_ENET1_RX_DATA0__KPP_ROW00                      	0x00c4 0x0350 0x0000 6 0
+#define MX6UL_PAD_ENET1_RX_DATA0__USDHC1_LCTL                    	0x00c4 0x0350 0x0000 8 0
+#define MX6UL_PAD_ENET1_RX_DATA1__ENET1_RDATA01                  	0x00c8 0x0354 0x0000 0 0
+#define MX6UL_PAD_ENET1_RX_DATA1__UART4_DCE_CTS                  	0x00c8 0x0354 0x0000 1 0
+#define MX6UL_PAD_ENET1_RX_DATA1__UART4_DTE_RTS                  	0x00c8 0x0354 0x0638 1 1
+#define MX6UL_PAD_ENET1_RX_DATA1__PWM2_OUT                       	0x00c8 0x0354 0x0000 2 0
+#define MX6UL_PAD_ENET1_RX_DATA1__CSI_DATA17                     	0x00c8 0x0354 0x0000 3 0
+#define MX6UL_PAD_ENET1_RX_DATA1__FLEXCAN1_RX                    	0x00c8 0x0354 0x0584 4 1
+#define MX6UL_PAD_ENET1_RX_DATA1__GPIO2_IO01                     	0x00c8 0x0354 0x0000 5 0
+#define MX6UL_PAD_ENET1_RX_DATA1__KPP_COL00                      	0x00c8 0x0354 0x0000 6 0
+#define MX6UL_PAD_ENET1_RX_DATA1__USDHC2_LCTL                    	0x00c8 0x0354 0x0000 8 0
+#define MX6UL_PAD_ENET1_RX_EN__ENET1_RX_EN                       	0x00cc 0x0358 0x0000 0 0
+#define MX6UL_PAD_ENET1_RX_EN__UART5_DCE_RTS                     	0x00cc 0x0358 0x0640 1 3
+#define MX6UL_PAD_ENET1_RX_EN__UART5_DTE_CTS                     	0x00cc 0x0358 0x0000 1 0
+#define MX6UL_PAD_ENET1_RX_EN__CSI_DATA18                        	0x00cc 0x0358 0x0000 3 0
+#define MX6UL_PAD_ENET1_RX_EN__FLEXCAN2_TX                       	0x00cc 0x0358 0x0000 4 0
+#define MX6UL_PAD_ENET1_RX_EN__GPIO2_IO02                        	0x00cc 0x0358 0x0000 5 0
+#define MX6UL_PAD_ENET1_RX_EN__KPP_ROW01                         	0x00cc 0x0358 0x0000 6 0
+#define MX6UL_PAD_ENET1_RX_EN__USDHC1_VSELECT                    	0x00cc 0x0358 0x0000 8 0
+#define MX6UL_PAD_ENET1_TX_DATA0__ENET1_TDATA00                  	0x00d0 0x035c 0x0000 0 0
+#define MX6UL_PAD_ENET1_TX_DATA0__UART5_DCE_CTS                  	0x00d0 0x035c 0x0000 1 0
+#define MX6UL_PAD_ENET1_TX_DATA0__UART5_DTE_RTS                  	0x00d0 0x035c 0x0640 1 4
+#define MX6UL_PAD_ENET1_TX_DATA0__CSI_DATA19                     	0x00d0 0x035c 0x0000 3 0
+#define MX6UL_PAD_ENET1_TX_DATA0__FLEXCAN2_RX                    	0x00d0 0x035c 0x0588 4 1
+#define MX6UL_PAD_ENET1_TX_DATA0__GPIO2_IO03                     	0x00d0 0x035c 0x0000 5 0
+#define MX6UL_PAD_ENET1_TX_DATA0__KPP_COL01                      	0x00d0 0x035c 0x0000 6 0
+#define MX6UL_PAD_ENET1_TX_DATA0__USDHC2_VSELECT                 	0x00d0 0x035c 0x0000 8 0
+#define MX6UL_PAD_ENET1_TX_DATA1__ENET1_TDATA01                  	0x00d4 0x0360 0x0000 0 0
+#define MX6UL_PAD_ENET1_TX_DATA1__UART6_DCE_CTS                  	0x00d4 0x0360 0x0000 1 0
+#define MX6UL_PAD_ENET1_TX_DATA1__UART6_DTE_RTS                  	0x00d4 0x0360 0x0648 1 2
+#define MX6UL_PAD_ENET1_TX_DATA1__PWM5_OUT                       	0x00d4 0x0360 0x0000 2 0
+#define MX6UL_PAD_ENET1_TX_DATA1__CSI_DATA20                     	0x00d4 0x0360 0x0000 3 0
+#define MX6UL_PAD_ENET1_TX_DATA1__ENET2_MDIO                     	0x00d4 0x0360 0x0580 4 1
+#define MX6UL_PAD_ENET1_TX_DATA1__GPIO2_IO04                     	0x00d4 0x0360 0x0000 5 0
+#define MX6UL_PAD_ENET1_TX_DATA1__KPP_ROW02                      	0x00d4 0x0360 0x0000 6 0
+#define MX6UL_PAD_ENET1_TX_DATA1__WDOG1_WDOG_RST_B_DEB           	0x00d4 0x0360 0x0000 8 0
+#define MX6UL_PAD_ENET1_TX_EN__ENET1_TX_EN                       	0x00d8 0x0364 0x0000 0 0
+#define MX6UL_PAD_ENET1_TX_EN__UART6_DCE_RTS                     	0x00d8 0x0364 0x0648 1 3
+#define MX6UL_PAD_ENET1_TX_EN__UART6_DTE_CTS                     	0x00d8 0x0364 0x0000 1 0
+#define MX6UL_PAD_ENET1_TX_EN__PWM6_OUT                          	0x00d8 0x0364 0x0000 2 0
+#define MX6UL_PAD_ENET1_TX_EN__CSI_DATA21                        	0x00d8 0x0364 0x0000 3 0
+#define MX6UL_PAD_ENET1_TX_EN__ENET2_MDC                         	0x00d8 0x0364 0x0000 4 0
+#define MX6UL_PAD_ENET1_TX_EN__GPIO2_IO05                        	0x00d8 0x0364 0x0000 5 0
+#define MX6UL_PAD_ENET1_TX_EN__KPP_COL02                         	0x00d8 0x0364 0x0000 6 0
+#define MX6UL_PAD_ENET1_TX_EN__WDOG2_WDOG_RST_B_DEB              	0x00d8 0x0364 0x0000 8 0
+#define MX6UL_PAD_ENET1_TX_CLK__ENET1_TX_CLK                     	0x00dc 0x0368 0x0000 0 0
+#define MX6UL_PAD_ENET1_TX_CLK__UART7_DCE_CTS                    	0x00dc 0x0368 0x0000 1 0
+#define MX6UL_PAD_ENET1_TX_CLK__UART7_DTE_RTS                    	0x00dc 0x0368 0x0650 1 0
+#define MX6UL_PAD_ENET1_TX_CLK__PWM7_OUT                         	0x00dc 0x0368 0x0000 2 0
+#define MX6UL_PAD_ENET1_TX_CLK__CSI_DATA22                       	0x00dc 0x0368 0x0000 3 0
+#define MX6UL_PAD_ENET1_TX_CLK__ENET1_REF_CLK1                   	0x00dc 0x0368 0x0574 4 2
+#define MX6UL_PAD_ENET1_TX_CLK__GPIO2_IO06                       	0x00dc 0x0368 0x0000 5 0
+#define MX6UL_PAD_ENET1_TX_CLK__KPP_ROW03                        	0x00dc 0x0368 0x0000 6 0
+#define MX6UL_PAD_ENET1_TX_CLK__GPT1_CLK                         	0x00dc 0x0368 0x0000 8 0
+#define MX6UL_PAD_ENET1_RX_ER__ENET1_RX_ER                       	0x00e0 0x036c 0x0000 0 0
+#define MX6UL_PAD_ENET1_RX_ER__UART7_DCE_RTS                     	0x00e0 0x036c 0x0650 1 1
+#define MX6UL_PAD_ENET1_RX_ER__UART7_DTE_CTS                     	0x00e0 0x036c 0x0000 1 0
+#define MX6UL_PAD_ENET1_RX_ER__PWM8_OUT                          	0x00e0 0x036c 0x0000 2 0
+#define MX6UL_PAD_ENET1_RX_ER__CSI_DATA23                        	0x00e0 0x036c 0x0000 3 0
+#define MX6UL_PAD_ENET1_RX_ER__EIM_CRE                           	0x00e0 0x036c 0x0000 4 0
+#define MX6UL_PAD_ENET1_RX_ER__GPIO2_IO07                        	0x00e0 0x036c 0x0000 5 0
+#define MX6UL_PAD_ENET1_RX_ER__KPP_COL03                         	0x00e0 0x036c 0x0000 6 0
+#define MX6UL_PAD_ENET1_RX_ER__GPT1_CAPTURE2                     	0x00e0 0x036c 0x0000 8 0
+#define MX6UL_PAD_ENET2_RX_DATA0__ENET2_RDATA00                  	0x00e4 0x0370 0x0000 0 0
+#define MX6UL_PAD_ENET2_RX_DATA0__UART6_DCE_TX                       	0x00e4 0x0370 0x0000 1 0
+#define MX6UL_PAD_ENET2_RX_DATA0__UART6_DTE_RX                    	0x00e4 0x0370 0x064c 1 1
+#define MX6UL_PAD_ENET2_RX_DATA0__SIM1_PORT0_TRXD                	0x00e4 0x0370 0x0000 2 0
+#define MX6UL_PAD_ENET2_RX_DATA0__I2C3_SCL                       	0x00e4 0x0370 0x05b4 3 1
+#define MX6UL_PAD_ENET2_RX_DATA0__ENET1_MDIO                     	0x00e4 0x0370 0x0578 4 1
+#define MX6UL_PAD_ENET2_RX_DATA0__GPIO2_IO08                     	0x00e4 0x0370 0x0000 5 0
+#define MX6UL_PAD_ENET2_RX_DATA0__KPP_ROW04                      	0x00e4 0x0370 0x0000 6 0
+#define MX6UL_PAD_ENET2_RX_DATA0__USB_OTG1_PWR                   	0x00e4 0x0370 0x0000 8 0
+#define MX6UL_PAD_ENET2_RX_DATA1__ENET2_RDATA01                  	0x00e8 0x0374 0x0000 0 0
+#define MX6UL_PAD_ENET2_RX_DATA1__UART6_DCE_RX                       	0x00e8 0x0374 0x064c 1 2
+#define MX6UL_PAD_ENET2_RX_DATA1__UART6_DTE_TX                       	0x00e8 0x0374 0x0000 1 0
+#define MX6UL_PAD_ENET2_RX_DATA1__SIM1_PORT0_cLK                 	0x00e8 0x0374 0x0000 2 0
+#define MX6UL_PAD_ENET2_RX_DATA1__I2C3_SDA                       	0x00e8 0x0374 0x05b8 3 1
+#define MX6UL_PAD_ENET2_RX_DATA1__ENET1_MDC                      	0x00e8 0x0374 0x0000 4 0
+#define MX6UL_PAD_ENET2_RX_DATA1__GPIO2_IO09                     	0x00e8 0x0374 0x0000 5 0
+#define MX6UL_PAD_ENET2_RX_DATA1__KPP_COL04                      	0x00e8 0x0374 0x0000 6 0
+#define MX6UL_PAD_ENET2_RX_DATA1__USB_OTG1_OC                    	0x00e8 0x0374 0x0000 8 0
+#define MX6UL_PAD_ENET2_RX_EN__ENET2_RX_EN                       	0x00ec 0x0378 0x0000 0 0
+#define MX6UL_PAD_ENET2_RX_EN__UART7_DCE_TX                          	0x00ec 0x0378 0x0000 1 0
+#define MX6UL_PAD_ENET2_RX_EN__UART7_DTE_RX                          	0x00ec 0x0378 0x0654 1 0
+#define MX6UL_PAD_ENET2_RX_EN__SIM1_PORT0_RST_B                  	0x00ec 0x0378 0x0000 2 0
+#define MX6UL_PAD_ENET2_RX_EN__I2C4_SCL                          	0x00ec 0x0378 0x05bc 3 1
+#define MX6UL_PAD_ENET2_RX_EN__EIM_ADDR26                        	0x00ec 0x0378 0x0000 4 0
+#define MX6UL_PAD_ENET2_RX_EN__GPIO2_IO10                        	0x00ec 0x0378 0x0000 5 0
+#define MX6UL_PAD_ENET2_RX_EN__KPP_ROW05                         	0x00ec 0x0378 0x0000 6 0
+#define MX6UL_PAD_ENET2_RX_EN__ENET1_REF_CLK_25M                 	0x00ec 0x0378 0x0000 8 0
+#define MX6UL_PAD_ENET2_TX_DATA0__ENET2_TDATA00                  	0x00f0 0x037c 0x0000 0 0
+#define MX6UL_PAD_ENET2_TX_DATA0__UART7_DCE_RX                       	0x00f0 0x037c 0x0654 1 1
+#define MX6UL_PAD_ENET2_TX_DATA0__UART7_DTE_TX                       	0x00f0 0x037c 0x0000 1 0
+#define MX6UL_PAD_ENET2_TX_DATA0__SIM1_PORT0_SVEN                	0x00f0 0x037c 0x0000 2 0
+#define MX6UL_PAD_ENET2_TX_DATA0__I2C4_SDA                       	0x00f0 0x037c 0x05c0 3 1
+#define MX6UL_PAD_ENET2_TX_DATA0__EIM_EB_B02                     	0x00f0 0x037c 0x0000 4 0
+#define MX6UL_PAD_ENET2_TX_DATA0__GPIO2_IO11                     	0x00f0 0x037c 0x0000 5 0
+#define MX6UL_PAD_ENET2_TX_DATA0__KPP_COL05                      	0x00f0 0x037c 0x0000 6 0
+#define MX6UL_PAD_ENET2_TX_DATA1__ENET2_TDATA01                  	0x00f4 0x0380 0x0000 0 0
+#define MX6UL_PAD_ENET2_TX_DATA1__UART8_DCE_TX                       	0x00f4 0x0380 0x0000 1 0
+#define MX6UL_PAD_ENET2_TX_DATA1__UART8_DTE_RX                       	0x00f4 0x0380 0x065c 1 0
+#define MX6UL_PAD_ENET2_TX_DATA1__SIM2_PORT0_TRXD                	0x00f4 0x0380 0x0000 2 0
+#define MX6UL_PAD_ENET2_TX_DATA1__ECSPI4_SCLK                    	0x00f4 0x0380 0x0564 3 0
+#define MX6UL_PAD_ENET2_TX_DATA1__EIM_EB_B03                     	0x00f4 0x0380 0x0000 4 0
+#define MX6UL_PAD_ENET2_TX_DATA1__GPIO2_IO12                     	0x00f4 0x0380 0x0000 5 0
+#define MX6UL_PAD_ENET2_TX_DATA1__KPP_ROW06                      	0x00f4 0x0380 0x0000 6 0
+#define MX6UL_PAD_ENET2_TX_DATA1__USB_OTG2_PWR                   	0x00f4 0x0380 0x0000 8 0
+#define MX6UL_PAD_ENET2_TX_EN__ENET2_TX_EN                       	0x00f8 0x0384 0x0000 0 0
+#define MX6UL_PAD_ENET2_TX_EN__UART8_DCE_RX                          	0x00f8 0x0384 0x065c 1 1
+#define MX6UL_PAD_ENET2_TX_EN__UART8_DTE_TX                          	0x00f8 0x0384 0x0000 1 0
+#define MX6UL_PAD_ENET2_TX_EN__SIM2_PORT0_cLK                    	0x00f8 0x0384 0x0000 2 0
+#define MX6UL_PAD_ENET2_TX_EN__ECSPI4_MOSI                       	0x00f8 0x0384 0x056c 3 0
+#define MX6UL_PAD_ENET2_TX_EN__EIM_ACLK_FREERUN                  	0x00f8 0x0384 0x0000 4 0
+#define MX6UL_PAD_ENET2_TX_EN__GPIO2_IO13                        	0x00f8 0x0384 0x0000 5 0
+#define MX6UL_PAD_ENET2_TX_EN__KPP_COL06                         	0x00f8 0x0384 0x0000 6 0
+#define MX6UL_PAD_ENET2_TX_EN__USB_OTG2_OC                       	0x00f8 0x0384 0x0000 8 0
+#define MX6UL_PAD_ENET2_TX_CLK__ENET2_TX_CLK                     	0x00fc 0x0388 0x0000 0 0
+#define MX6UL_PAD_ENET2_TX_CLK__UART8_DCE_CTS                    	0x00fc 0x0388 0x0000 1 0
+#define MX6UL_PAD_ENET2_TX_CLK__UART8_DTE_RTS                    	0x00fc 0x0388 0x0658 1 0
+#define MX6UL_PAD_ENET2_TX_CLK__SIM2_PORT0_RST_B                 	0x00fc 0x0388 0x0000 2 0
+#define MX6UL_PAD_ENET2_TX_CLK__ECSPI4_MISO                      	0x00fc 0x0388 0x0568 3 0
+#define MX6UL_PAD_ENET2_TX_CLK__ENET2_REF_CLK2                   	0x00fc 0x0388 0x057c 4 2
+#define MX6UL_PAD_ENET2_TX_CLK__GPIO2_IO14                       	0x00fc 0x0388 0x0000 5 0
+#define MX6UL_PAD_ENET2_TX_CLK__KPP_ROW07                        	0x00fc 0x0388 0x0000 6 0
+#define MX6UL_PAD_ENET2_TX_CLK__ANATOP_OTG2_ID                   	0x00fc 0x0388 0x0000 8 0
+#define MX6UL_PAD_ENET2_RX_ER__ENET2_RX_ER                       	0x0100 0x038c 0x0000 0 0
+#define MX6UL_PAD_ENET2_RX_ER__UART8_DCE_RTS                     	0x0100 0x038c 0x0658 1 1
+#define MX6UL_PAD_ENET2_RX_ER__UART8_DTE_CTS                     	0x0100 0x038c 0x0000 1 0
+#define MX6UL_PAD_ENET2_RX_ER__SIM2_PORT0_SVEN                   	0x0100 0x038c 0x0000 2 0
+#define MX6UL_PAD_ENET2_RX_ER__ECSPI4_SS0                        	0x0100 0x038c 0x0000 3 0
+#define MX6UL_PAD_ENET2_RX_ER__EIM_ADDR25                        	0x0100 0x038c 0x0000 4 0
+#define MX6UL_PAD_ENET2_RX_ER__GPIO2_IO15                        	0x0100 0x038c 0x0000 5 0
+#define MX6UL_PAD_ENET2_RX_ER__KPP_COL07                         	0x0100 0x038c 0x0000 6 0
+#define MX6UL_PAD_ENET2_RX_ER__WDOG1_WDOG_ANY                    	0x0100 0x038c 0x0000 8 0
+#define MX6UL_PAD_LCD_CLK__LCDIF_CLK                             	0x0104 0x0390 0x0000 0 0
+#define MX6UL_PAD_LCD_CLK__LCDIF_WR_RWN                          	0x0104 0x0390 0x0000 1 0
+#define MX6UL_PAD_LCD_CLK__UART4_DCE_TX                              	0x0104 0x0390 0x0000 2 0
+#define MX6UL_PAD_LCD_CLK__UART4_DTE_RX                              	0x0104 0x0390 0x063c 2 2
+#define MX6UL_PAD_LCD_CLK__SAI3_MCLK                             	0x0104 0x0390 0x0000 3 0
+#define MX6UL_PAD_LCD_CLK__EIM_CS2_B                             	0x0104 0x0390 0x0000 4 0
+#define MX6UL_PAD_LCD_CLK__GPIO3_IO00                            	0x0104 0x0390 0x0000 5 0
+#define MX6UL_PAD_LCD_CLK__WDOG1_WDOG_RST_B_DEB                  	0x0104 0x0390 0x0000 8 0
+#define MX6UL_PAD_LCD_ENABLE__LCDIF_ENABLE                       	0x0108 0x0394 0x0000 0 0
+#define MX6UL_PAD_LCD_ENABLE__LCDIF_RD_E                         	0x0108 0x0394 0x0000 1 0
+#define MX6UL_PAD_LCD_ENABLE__UART4_DCE_RX                           	0x0108 0x0394 0x063c 2 3
+#define MX6UL_PAD_LCD_ENABLE__UART4_DTE_TX                           	0x0108 0x0394 0x0000 2 0
+#define MX6UL_PAD_LCD_ENABLE__SAI3_TX_SYNC                       	0x0108 0x0394 0x060c 3 0
+#define MX6UL_PAD_LCD_ENABLE__EIM_CS3_B                          	0x0108 0x0394 0x0000 4 0
+#define MX6UL_PAD_LCD_ENABLE__GPIO3_IO01                         	0x0108 0x0394 0x0000 5 0
+#define MX6UL_PAD_LCD_ENABLE__ECSPI2_RDY                         	0x0108 0x0394 0x0000 8 0
+#define MX6UL_PAD_LCD_HSYNC__LCDIF_HSYNC                         	0x010c 0x0398 0x05dc 0 0
+#define MX6UL_PAD_LCD_HSYNC__LCDIF_RS                            	0x010c 0x0398 0x0000 1 0
+#define MX6UL_PAD_LCD_HSYNC__UART4_DCE_CTS                       	0x010c 0x0398 0x0000 2 0
+#define MX6UL_PAD_LCD_HSYNC__UART4_DTE_RTS                       	0x010c 0x0398 0x0638 2 2
+#define MX6UL_PAD_LCD_HSYNC__SAI3_TX_BCLK                        	0x010c 0x0398 0x0608 3 0
+#define MX6UL_PAD_LCD_HSYNC__WDOG3_WDOG_RST_B_DEB                	0x010c 0x0398 0x0000 4 0
+#define MX6UL_PAD_LCD_HSYNC__GPIO3_IO02                          	0x010c 0x0398 0x0000 5 0
+#define MX6UL_PAD_LCD_HSYNC__ECSPI2_SS1                          	0x010c 0x0398 0x0000 8 0
+#define MX6UL_PAD_LCD_VSYNC__LCDIF_VSYNC                         	0x0110 0x039c 0x0000 0 0
+#define MX6UL_PAD_LCD_VSYNC__LCDIF_BUSY                          	0x0110 0x039c 0x05dc 1 1
+#define MX6UL_PAD_LCD_VSYNC__UART4_DCE_RTS                       	0x0110 0x039c 0x0638 2 3
+#define MX6UL_PAD_LCD_VSYNC__UART4_DTE_CTS                       	0x0110 0x039c 0x0000 2 0
+#define MX6UL_PAD_LCD_VSYNC__SAI3_RX_DATA                        	0x0110 0x039c 0x0000 3 0
+#define MX6UL_PAD_LCD_VSYNC__WDOG2_WDOG_B                        	0x0110 0x039c 0x0000 4 0
+#define MX6UL_PAD_LCD_VSYNC__GPIO3_IO03                          	0x0110 0x039c 0x0000 5 0
+#define MX6UL_PAD_LCD_VSYNC__ECSPI2_SS2                          	0x0110 0x039c 0x0000 8 0
+#define MX6UL_PAD_LCD_RESET__LCDIF_RESET                         	0x0114 0x03a0 0x0000 0 0
+#define MX6UL_PAD_LCD_RESET__LCDIF_CS                            	0x0114 0x03a0 0x0000 1 0
+#define MX6UL_PAD_LCD_RESET__CA7_MX6UL_EVENTI                    	0x0114 0x03a0 0x0000 2 0
+#define MX6UL_PAD_LCD_RESET__SAI3_TX_DATA                        	0x0114 0x03a0 0x0000 3 0
+#define MX6UL_PAD_LCD_RESET__WDOG1_WDOG_ANY                      	0x0114 0x03a0 0x0000 4 0
+#define MX6UL_PAD_LCD_RESET__GPIO3_IO04                          	0x0114 0x03a0 0x0000 5 0
+#define MX6UL_PAD_LCD_RESET__ECSPI2_SS3                          	0x0114 0x03a0 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA00__LCDIF_DATA00                       	0x0118 0x03a4 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA00__PWM1_OUT                           	0x0118 0x03a4 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA00__ENET1_1588_EVENT2_IN               	0x0118 0x03a4 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA00__I2C3_SDA                           	0x0118 0x03a4 0x05b8 4 2
+#define MX6UL_PAD_LCD_DATA00__GPIO3_IO05                         	0x0118 0x03a4 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA00__SRC_BT_CFG00                       	0x0118 0x03a4 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA00__SAI1_MCLK                          	0x0118 0x03a4 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA01__LCDIF_DATA01                       	0x011c 0x03a8 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA01__PWM2_OUT                           	0x011c 0x03a8 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA01__ENET1_1588_EVENT2_OUT              	0x011c 0x03a8 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA01__I2C3_SCL                           	0x011c 0x03a8 0x05b4 4 2
+#define MX6UL_PAD_LCD_DATA01__GPIO3_IO06                         	0x011c 0x03a8 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA01__SRC_BT_CFG01                       	0x011c 0x03a8 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA01__SAI1_TX_SYNC                       	0x011c 0x03a8 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA02__LCDIF_DATA02                       	0x0120 0x03ac 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA02__PWM3_OUT                           	0x0120 0x03ac 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA02__ENET1_1588_EVENT3_IN               	0x0120 0x03ac 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA02__I2C4_SDA                           	0x0120 0x03ac 0x05c0 4 2
+#define MX6UL_PAD_LCD_DATA02__GPIO3_IO07                         	0x0120 0x03ac 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA02__SRC_BT_CFG02                       	0x0120 0x03ac 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA02__SAI1_TX_BCLK                       	0x0120 0x03ac 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA03__LCDIF_DATA03                       	0x0124 0x03b0 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA03__PWM4_OUT                           	0x0124 0x03b0 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA03__ENET1_1588_EVENT3_OUT              	0x0124 0x03b0 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA03__I2C4_SCL                           	0x0124 0x03b0 0x05bc 4 2
+#define MX6UL_PAD_LCD_DATA03__GPIO3_IO08                         	0x0124 0x03b0 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA03__SRC_BT_CFG03                       	0x0124 0x03b0 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA03__SAI1_RX_DATA                       	0x0124 0x03b0 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA04__LCDIF_DATA04                       	0x0128 0x03b4 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA04__UART8_DCE_CTS                      	0x0128 0x03b4 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA04__UART8_DTE_RTS                      	0x0128 0x03b4 0x0658 1 2
+#define MX6UL_PAD_LCD_DATA04__ENET2_1588_EVENT2_IN               	0x0128 0x03b4 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA04__SPDIF_SR_CLK                       	0x0128 0x03b4 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA04__GPIO3_IO09                         	0x0128 0x03b4 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA04__SRC_BT_CFG04                       	0x0128 0x03b4 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA04__SAI1_TX_DATA                       	0x0128 0x03b4 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA05__LCDIF_DATA05                       	0x012c 0x03b8 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA05__UART8_DCE_RTS                      	0x012c 0x03b8 0x0658 1 3
+#define MX6UL_PAD_LCD_DATA05__UART8_DTE_CTS                      	0x012c 0x03b8 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA05__ENET2_1588_EVENT2_OUT              	0x012c 0x03b8 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA05__SPDIF_OUT                          	0x012c 0x03b8 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA05__GPIO3_IO10                         	0x012c 0x03b8 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA05__SRC_BT_CFG05                       	0x012c 0x03b8 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA05__ECSPI1_SS1                         	0x012c 0x03b8 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA06__LCDIF_DATA06                       	0x0130 0x03bc 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA06__UART7_DCE_CTS                      	0x0130 0x03bc 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA06__UART7_DTE_RTS                      	0x0130 0x03bc 0x0650 1 2
+#define MX6UL_PAD_LCD_DATA06__ENET2_1588_EVENT3_IN               	0x0130 0x03bc 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA06__SPDIF_LOCK                         	0x0130 0x03bc 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA06__GPIO3_IO11                         	0x0130 0x03bc 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA06__SRC_BT_CFG06                       	0x0130 0x03bc 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA06__ECSPI1_SS2                         	0x0130 0x03bc 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA07__LCDIF_DATA07                       	0x0134 0x03c0 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA07__UART7_DCE_RTS                      	0x0134 0x03c0 0x0650 1 3
+#define MX6UL_PAD_LCD_DATA07__UART7_DTE_CTS                      	0x0134 0x03c0 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA07__ENET2_1588_EVENT3_OUT              	0x0134 0x03c0 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA07__SPDIF_EXT_CLK                      	0x0134 0x03c0 0x061c 4 0
+#define MX6UL_PAD_LCD_DATA07__GPIO3_IO12                         	0x0134 0x03c0 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA07__SRC_BT_CFG07                       	0x0134 0x03c0 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA07__ECSPI1_SS3                         	0x0134 0x03c0 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA08__LCDIF_DATA08                       	0x0138 0x03c4 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA08__SPDIF_IN                           	0x0138 0x03c4 0x0618 1 2
+#define MX6UL_PAD_LCD_DATA08__CSI_DATA16                         	0x0138 0x03c4 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA08__EIM_DATA00                         	0x0138 0x03c4 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA08__GPIO3_IO13                         	0x0138 0x03c4 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA08__SRC_BT_CFG08                       	0x0138 0x03c4 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA08__FLEXCAN1_TX                        	0x0138 0x03c4 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA09__LCDIF_DATA09                       	0x013c 0x03c8 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA09__SAI3_MCLK                          	0x013c 0x03c8 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA09__CSI_DATA17                         	0x013c 0x03c8 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA09__EIM_DATA01                         	0x013c 0x03c8 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA09__GPIO3_IO14                         	0x013c 0x03c8 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA09__SRC_BT_CFG09                       	0x013c 0x03c8 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA09__FLEXCAN1_RX                        	0x013c 0x03c8 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA10__LCDIF_DATA10                       	0x0140 0x03cc 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA10__SAI3_RX_SYNC                       	0x0140 0x03cc 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA10__CSI_DATA18                         	0x0140 0x03cc 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA10__EIM_DATA02                         	0x0140 0x03cc 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA10__GPIO3_IO15                         	0x0140 0x03cc 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA10__SRC_BT_CFG10                       	0x0140 0x03cc 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA10__FLEXCAN2_TX                        	0x0140 0x03cc 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA11__LCDIF_DATA11                       	0x0144 0x03d0 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA11__SAI3_RX_BCLK                       	0x0144 0x03d0 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA11__CSI_DATA19                         	0x0144 0x03d0 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA11__EIM_DATA03                         	0x0144 0x03d0 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA11__GPIO3_IO16                         	0x0144 0x03d0 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA11__SRC_BT_CFG11                       	0x0144 0x03d0 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA11__FLEXCAN2_RX                        	0x0144 0x03d0 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA12__LCDIF_DATA12                       	0x0148 0x03d4 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA12__SAI3_TX_SYNC                       	0x0148 0x03d4 0x060c 1 1
+#define MX6UL_PAD_LCD_DATA12__CSI_DATA20                         	0x0148 0x03d4 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA12__EIM_DATA04                         	0x0148 0x03d4 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA12__GPIO3_IO17                         	0x0148 0x03d4 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA12__SRC_BT_CFG12                       	0x0148 0x03d4 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA12__ECSPI1_RDY                         	0x0148 0x03d4 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA13__LCDIF_DATA13                       	0x014c 0x03d8 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA13__SAI3_TX_BCLK                       	0x014c 0x03d8 0x0608 1 1
+#define MX6UL_PAD_LCD_DATA13__CSI_DATA21                         	0x014c 0x03d8 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA13__EIM_DATA05                         	0x014c 0x03d8 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA13__GPIO3_IO18                         	0x014c 0x03d8 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA13__SRC_BT_CFG13                       	0x014c 0x03d8 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA13__USDHC2_RESET_B                     	0x014c 0x03d8 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA14__LCDIF_DATA14                       	0x0150 0x03dc 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA14__SAI3_RX_DATA                       	0x0150 0x03dc 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA14__CSI_DATA22                         	0x0150 0x03dc 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA14__EIM_DATA06                         	0x0150 0x03dc 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA14__GPIO3_IO19                         	0x0150 0x03dc 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA14__SRC_BT_CFG14                       	0x0150 0x03dc 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA14__USDHC2_DATA4                       	0x0150 0x03dc 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA15__LCDIF_DATA15                       	0x0154 0x03e0 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA15__SAI3_TX_DATA                       	0x0154 0x03e0 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA15__CSI_DATA23                         	0x0154 0x03e0 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA15__EIM_DATA07                         	0x0154 0x03e0 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA15__GPIO3_IO20                         	0x0154 0x03e0 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA15__SRC_BT_CFG15                       	0x0154 0x03e0 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA15__USDHC2_DATA5                       	0x0154 0x03e0 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA16__LCDIF_DATA16                       	0x0158 0x03e4 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA16__UART7_DCE_TX                           	0x0158 0x03e4 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA16__UART7_DTE_RX                           	0x0158 0x03e4 0x0654 1 2
+#define MX6UL_PAD_LCD_DATA16__CSI_DATA01                         	0x0158 0x03e4 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA16__EIM_DATA08                         	0x0158 0x03e4 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA16__GPIO3_IO21                         	0x0158 0x03e4 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA16__SRC_BT_CFG24                       	0x0158 0x03e4 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA16__USDHC2_DATA6                       	0x0158 0x03e4 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA17__LCDIF_DATA17                       	0x015c 0x03e8 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA17__UART7_DCE_RX                           	0x015c 0x03e8 0x0654 1 3
+#define MX6UL_PAD_LCD_DATA17__UART7_DTE_TX                           	0x015c 0x03e8 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA17__CSI_DATA00                         	0x015c 0x03e8 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA17__EIM_DATA09                         	0x015c 0x03e8 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA17__GPIO3_IO22                         	0x015c 0x03e8 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA17__SRC_BT_CFG25                       	0x015c 0x03e8 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA17__USDHC2_DATA7                       	0x015c 0x03e8 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA18__LCDIF_DATA18                       	0x0160 0x03ec 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA18__PWM5_OUT                           	0x0160 0x03ec 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA18__CA7_MX6UL_EVENTO                   	0x0160 0x03ec 0x0000 2 0
+#define MX6UL_PAD_LCD_DATA18__CSI_DATA10                         	0x0160 0x03ec 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA18__EIM_DATA10                         	0x0160 0x03ec 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA18__GPIO3_IO23                         	0x0160 0x03ec 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA18__SRC_BT_CFG26                       	0x0160 0x03ec 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA18__USDHC2_CMD                         	0x0160 0x03ec 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA19__EIM_DATA11                         	0x0164 0x03f0 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA19__GPIO3_IO24                         	0x0164 0x03f0 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA19__SRC_BT_CFG27                       	0x0164 0x03f0 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA19__USDHC2_CLK                         	0x0164 0x03f0 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA19__LCDIF_DATA19                       	0x0164 0x03f0 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA19__PWM6_OUT                           	0x0164 0x03f0 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA19__WDOG1_WDOG_ANY                     	0x0164 0x03f0 0x0000 2 0
+#define MX6UL_PAD_LCD_DATA19__CSI_DATA11                         	0x0164 0x03f0 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA20__EIM_DATA12                         	0x0168 0x03f4 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA20__GPIO3_IO25                         	0x0168 0x03f4 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA20__SRC_BT_CFG28                       	0x0168 0x03f4 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA20__USDHC2_DATA0                       	0x0168 0x03f4 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA20__LCDIF_DATA20                       	0x0168 0x03f4 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA20__UART8_DCE_TX                           	0x0168 0x03f4 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA20__UART8_DTE_RX                           	0x0168 0x03f4 0x065c 1 2
+#define MX6UL_PAD_LCD_DATA20__ECSPI1_SCLK                        	0x0168 0x03f4 0x0534 2 0
+#define MX6UL_PAD_LCD_DATA20__CSI_DATA12                         	0x0168 0x03f4 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA21__LCDIF_DATA21                       	0x016c 0x03f8 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA21__UART8_DCE_RX                           	0x016c 0x03f8 0x065c 1 3
+#define MX6UL_PAD_LCD_DATA21__UART8_DTE_TX                           	0x016c 0x03f8 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA21__ECSPI1_SS0                         	0x016c 0x03f8 0x0000 2 0
+#define MX6UL_PAD_LCD_DATA21__CSI_DATA13                         	0x016c 0x03f8 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA21__EIM_DATA13                         	0x016c 0x03f8 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA21__GPIO3_IO26                         	0x016c 0x03f8 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA21__SRC_BT_CFG29                       	0x016c 0x03f8 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA21__USDHC2_DATA1                       	0x016c 0x03f8 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA22__LCDIF_DATA22                       	0x0170 0x03fc 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA22__MQS_RIGHT                          	0x0170 0x03fc 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA22__ECSPI1_MOSI                        	0x0170 0x03fc 0x053c 2 0
+#define MX6UL_PAD_LCD_DATA22__CSI_DATA14                         	0x0170 0x03fc 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA22__EIM_DATA14                         	0x0170 0x03fc 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA22__GPIO3_IO27                         	0x0170 0x03fc 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA22__SRC_BT_CFG30                       	0x0170 0x03fc 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA22__USDHC2_DATA2                       	0x0170 0x03fc 0x0000 8 0
+#define MX6UL_PAD_LCD_DATA23__LCDIF_DATA23                       	0x0174 0x0400 0x0000 0 0
+#define MX6UL_PAD_LCD_DATA23__MQS_LEFT                           	0x0174 0x0400 0x0000 1 0
+#define MX6UL_PAD_LCD_DATA23__ECSPI1_MISO                        	0x0174 0x0400 0x0538 2 0
+#define MX6UL_PAD_LCD_DATA23__CSI_DATA15                         	0x0174 0x0400 0x0000 3 0
+#define MX6UL_PAD_LCD_DATA23__EIM_DATA15                         	0x0174 0x0400 0x0000 4 0
+#define MX6UL_PAD_LCD_DATA23__GPIO3_IO28                         	0x0174 0x0400 0x0000 5 0
+#define MX6UL_PAD_LCD_DATA23__SRC_BT_CFG31                       	0x0174 0x0400 0x0000 6 0
+#define MX6UL_PAD_LCD_DATA23__USDHC2_DATA3                       	0x0174 0x0400 0x0000 8 0
+#define MX6UL_PAD_NAND_RE_B__RAWNAND_RE_B                        	0x0178 0x0404 0x0000 0 0
+#define MX6UL_PAD_NAND_RE_B__USDHC2_CLK                          	0x0178 0x0404 0x0670 1 2
+#define MX6UL_PAD_NAND_RE_B__QSPI_B_SCLK                         	0x0178 0x0404 0x0000 2 0
+#define MX6UL_PAD_NAND_RE_B__KPP_ROW00                           	0x0178 0x0404 0x0000 3 0
+#define MX6UL_PAD_NAND_RE_B__EIM_EB_B00                          	0x0178 0x0404 0x0000 4 0
+#define MX6UL_PAD_NAND_RE_B__GPIO4_IO00                          	0x0178 0x0404 0x0000 5 0
+#define MX6UL_PAD_NAND_RE_B__ECSPI3_SS2                          	0x0178 0x0404 0x0000 8 0
+#define MX6UL_PAD_NAND_WE_B__RAWNAND_WE_B                        	0x017c 0x0408 0x0000 0 0
+#define MX6UL_PAD_NAND_WE_B__USDHC2_CMD                          	0x017c 0x0408 0x0678 1 2
+#define MX6UL_PAD_NAND_WE_B__QSPI_B_SS0_B                        	0x017c 0x0408 0x0000 2 0
+#define MX6UL_PAD_NAND_WE_B__KPP_COL00                           	0x017c 0x0408 0x0000 3 0
+#define MX6UL_PAD_NAND_WE_B__EIM_EB_B01                          	0x017c 0x0408 0x0000 4 0
+#define MX6UL_PAD_NAND_WE_B__GPIO4_IO01                          	0x017c 0x0408 0x0000 5 0
+#define MX6UL_PAD_NAND_WE_B__ECSPI3_SS3                          	0x017c 0x0408 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA00__RAWNAND_DATA00                    	0x0180 0x040c 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA00__USDHC2_DATA0                      	0x0180 0x040c 0x067c 1 2
+#define MX6UL_PAD_NAND_DATA00__QSPI_B_SS1_B                      	0x0180 0x040c 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA00__KPP_ROW01                         	0x0180 0x040c 0x0000 3 0
+#define MX6UL_PAD_NAND_DATA00__EIM_AD08                          	0x0180 0x040c 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA00__GPIO4_IO02                        	0x0180 0x040c 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA00__ECSPI4_RDY                        	0x0180 0x040c 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA01__RAWNAND_DATA01                    	0x0184 0x0410 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA01__USDHC2_DATA1                      	0x0184 0x0410 0x0680 1 2
+#define MX6UL_PAD_NAND_DATA01__QSPI_B_DQS                        	0x0184 0x0410 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA01__KPP_COL01                         	0x0184 0x0410 0x0000 3 0
+#define MX6UL_PAD_NAND_DATA01__EIM_AD09                          	0x0184 0x0410 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA01__GPIO4_IO03                        	0x0184 0x0410 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA01__ECSPI4_SS1                        	0x0184 0x0410 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA02__RAWNAND_DATA02                    	0x0188 0x0414 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA02__USDHC2_DATA2                      	0x0188 0x0414 0x0684 1 1
+#define MX6UL_PAD_NAND_DATA02__QSPI_B_DATA00                     	0x0188 0x0414 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA02__KPP_ROW02                         	0x0188 0x0414 0x0000 3 0
+#define MX6UL_PAD_NAND_DATA02__EIM_AD10                          	0x0188 0x0414 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA02__GPIO4_IO04                        	0x0188 0x0414 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA02__ECSPI4_SS2                        	0x0188 0x0414 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA03__RAWNAND_DATA03                    	0x018c 0x0418 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA03__USDHC2_DATA3                      	0x018c 0x0418 0x0688 1 2
+#define MX6UL_PAD_NAND_DATA03__QSPI_B_DATA01                     	0x018c 0x0418 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA03__KPP_COL02                         	0x018c 0x0418 0x0000 3 0
+#define MX6UL_PAD_NAND_DATA03__EIM_AD11                          	0x018c 0x0418 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA03__GPIO4_IO05                        	0x018c 0x0418 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA03__ECSPI4_SS3                        	0x018c 0x0418 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA04__RAWNAND_DATA04                    	0x0190 0x041c 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA04__USDHC2_DATA4                      	0x0190 0x041c 0x068c 1 1
+#define MX6UL_PAD_NAND_DATA04__QSPI_B_DATA02                     	0x0190 0x041c 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA04__ECSPI4_SCLK                       	0x0190 0x041c 0x0564 3 1
+#define MX6UL_PAD_NAND_DATA04__EIM_AD12                          	0x0190 0x041c 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA04__GPIO4_IO06                        	0x0190 0x041c 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA04__UART2_DCE_TX                          	0x0190 0x041c 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA04__UART2_DTE_RX                          	0x0190 0x041c 0x062c 8 2
+#define MX6UL_PAD_NAND_DATA05__RAWNAND_DATA05                    	0x0194 0x0420 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA05__USDHC2_DATA5                      	0x0194 0x0420 0x0690 1 1
+#define MX6UL_PAD_NAND_DATA05__QSPI_B_DATA03                     	0x0194 0x0420 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA05__ECSPI4_MOSI                       	0x0194 0x0420 0x056c 3 1
+#define MX6UL_PAD_NAND_DATA05__EIM_AD13                          	0x0194 0x0420 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA05__GPIO4_IO07                        	0x0194 0x0420 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA05__UART2_DCE_RX                          	0x0194 0x0420 0x062c 8 3
+#define MX6UL_PAD_NAND_DATA05__UART2_DTE_TX                          	0x0194 0x0420 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA06__RAWNAND_DATA06                    	0x0198 0x0424 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA06__USDHC2_DATA6                      	0x0198 0x0424 0x0694 1 1
+#define MX6UL_PAD_NAND_DATA06__SAI2_RX_BCLK                      	0x0198 0x0424 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA06__ECSPI4_MISO                       	0x0198 0x0424 0x0568 3 1
+#define MX6UL_PAD_NAND_DATA06__EIM_AD14                          	0x0198 0x0424 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA06__GPIO4_IO08                        	0x0198 0x0424 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA06__UART2_DCE_CTS                     	0x0198 0x0424 0x0000 8 0
+#define MX6UL_PAD_NAND_DATA06__UART2_DTE_RTS                     	0x0198 0x0424 0x0628 8 4
+#define MX6UL_PAD_NAND_DATA07__RAWNAND_DATA07                    	0x019c 0x0428 0x0000 0 0
+#define MX6UL_PAD_NAND_DATA07__USDHC2_DATA7                      	0x019c 0x0428 0x0698 1 1
+#define MX6UL_PAD_NAND_DATA07__QSPI_A_SS1_B                      	0x019c 0x0428 0x0000 2 0
+#define MX6UL_PAD_NAND_DATA07__ECSPI4_SS0                        	0x019c 0x0428 0x0000 3 0
+#define MX6UL_PAD_NAND_DATA07__EIM_AD15                          	0x019c 0x0428 0x0000 4 0
+#define MX6UL_PAD_NAND_DATA07__GPIO4_IO09                        	0x019c 0x0428 0x0000 5 0
+#define MX6UL_PAD_NAND_DATA07__UART2_DCE_RTS                     	0x019c 0x0428 0x0628 8 5
+#define MX6UL_PAD_NAND_DATA07__UART2_DTE_CTS                     	0x019c 0x0428 0x0000 8 0
+#define MX6UL_PAD_NAND_ALE__RAWNAND_ALE                          	0x01a0 0x042c 0x0000 0 0
+#define MX6UL_PAD_NAND_ALE__USDHC2_RESET_B                       	0x01a0 0x042c 0x0000 1 0
+#define MX6UL_PAD_NAND_ALE__QSPI_A_DQS                           	0x01a0 0x042c 0x0000 2 0
+#define MX6UL_PAD_NAND_ALE__PWM3_OUT                             	0x01a0 0x042c 0x0000 3 0
+#define MX6UL_PAD_NAND_ALE__EIM_ADDR17                           	0x01a0 0x042c 0x0000 4 0
+#define MX6UL_PAD_NAND_ALE__GPIO4_IO10                           	0x01a0 0x042c 0x0000 5 0
+#define MX6UL_PAD_NAND_ALE__ECSPI3_SS1                           	0x01a0 0x042c 0x0000 8 0
+#define MX6UL_PAD_NAND_WP_B__RAWNAND_WP_B                        	0x01a4 0x0430 0x0000 0 0
+#define MX6UL_PAD_NAND_WP_B__USDHC1_RESET_B                      	0x01a4 0x0430 0x0000 1 0
+#define MX6UL_PAD_NAND_WP_B__QSPI_A_SCLK                         	0x01a4 0x0430 0x0000 2 0
+#define MX6UL_PAD_NAND_WP_B__PWM4_OUT                            	0x01a4 0x0430 0x0000 3 0
+#define MX6UL_PAD_NAND_WP_B__EIM_BCLK                            	0x01a4 0x0430 0x0000 4 0
+#define MX6UL_PAD_NAND_WP_B__GPIO4_IO11                          	0x01a4 0x0430 0x0000 5 0
+#define MX6UL_PAD_NAND_WP_B__ECSPI3_RDY                          	0x01a4 0x0430 0x0000 8 0
+#define MX6UL_PAD_NAND_READY_B__RAWNAND_READY_B                  	0x01a8 0x0434 0x0000 0 0
+#define MX6UL_PAD_NAND_READY_B__USDHC1_DATA4                     	0x01a8 0x0434 0x0000 1 0
+#define MX6UL_PAD_NAND_READY_B__QSPI_A_DATA00                    	0x01a8 0x0434 0x0000 2 0
+#define MX6UL_PAD_NAND_READY_B__ECSPI3_SS0                       	0x01a8 0x0434 0x0000 3 0
+#define MX6UL_PAD_NAND_READY_B__EIM_CS1_B                        	0x01a8 0x0434 0x0000 4 0
+#define MX6UL_PAD_NAND_READY_B__GPIO4_IO12                       	0x01a8 0x0434 0x0000 5 0
+#define MX6UL_PAD_NAND_READY_B__UART3_DCE_TX                         	0x01a8 0x0434 0x0000 8 0
+#define MX6UL_PAD_NAND_READY_B__UART3_DTE_RX                         	0x01a8 0x0434 0x0634 8 2
+#define MX6UL_PAD_NAND_CE0_B__RAWNAND_CE0_B                      	0x01ac 0x0438 0x0000 0 0
+#define MX6UL_PAD_NAND_CE0_B__USDHC1_DATA5                       	0x01ac 0x0438 0x0000 1 0
+#define MX6UL_PAD_NAND_CE0_B__QSPI_A_DATA01                      	0x01ac 0x0438 0x0000 2 0
+#define MX6UL_PAD_NAND_CE0_B__ECSPI3_SCLK                        	0x01ac 0x0438 0x0554 3 1
+#define MX6UL_PAD_NAND_CE0_B__EIM_DTACK_B                        	0x01ac 0x0438 0x0000 4 0
+#define MX6UL_PAD_NAND_CE0_B__GPIO4_IO13                         	0x01ac 0x0438 0x0000 5 0
+#define MX6UL_PAD_NAND_CE0_B__UART3_DCE_RX                           	0x01ac 0x0438 0x0634 8 3
+#define MX6UL_PAD_NAND_CE0_B__UART3_DTE_TX                           	0x01ac 0x0438 0x0000 8 0
+#define MX6UL_PAD_NAND_CE1_B__RAWNAND_CE1_B                      	0x01b0 0x043c 0x0000 0 0
+#define MX6UL_PAD_NAND_CE1_B__USDHC1_DATA6                       	0x01b0 0x043c 0x0000 1 0
+#define MX6UL_PAD_NAND_CE1_B__QSPI_A_DATA02                      	0x01b0 0x043c 0x0000 2 0
+#define MX6UL_PAD_NAND_CE1_B__ECSPI3_MOSI                        	0x01b0 0x043c 0x055c 3 1
+#define MX6UL_PAD_NAND_CE1_B__EIM_ADDR18                         	0x01b0 0x043c 0x0000 4 0
+#define MX6UL_PAD_NAND_CE1_B__GPIO4_IO14                         	0x01b0 0x043c 0x0000 5 0
+#define MX6UL_PAD_NAND_CE1_B__UART3_DCE_CTS                      	0x01b0 0x043c 0x0000 8 0
+#define MX6UL_PAD_NAND_CE1_B__UART3_DTE_RTS                      	0x01b0 0x043c 0x0630 8 2
+#define MX6UL_PAD_NAND_CLE__RAWNAND_CLE                          	0x01b4 0x0440 0x0000 0 0
+#define MX6UL_PAD_NAND_CLE__USDHC1_DATA7                         	0x01b4 0x0440 0x0000 1 0
+#define MX6UL_PAD_NAND_CLE__QSPI_A_DATA03                        	0x01b4 0x0440 0x0000 2 0
+#define MX6UL_PAD_NAND_CLE__ECSPI3_MISO                          	0x01b4 0x0440 0x0558 3 1
+#define MX6UL_PAD_NAND_CLE__EIM_ADDR16                           	0x01b4 0x0440 0x0000 4 0
+#define MX6UL_PAD_NAND_CLE__GPIO4_IO15                           	0x01b4 0x0440 0x0000 5 0
+#define MX6UL_PAD_NAND_CLE__UART3_DCE_RTS                        	0x01b4 0x0440 0x0630 8 3
+#define MX6UL_PAD_NAND_CLE__UART3_DTE_CTS                        	0x01b4 0x0440 0x0000 8 0
+#define MX6UL_PAD_NAND_DQS__RAWNAND_DQS                          	0x01b8 0x0444 0x0000 0 0
+#define MX6UL_PAD_NAND_DQS__CSI_FIELD                            	0x01b8 0x0444 0x0530 1 1
+#define MX6UL_PAD_NAND_DQS__QSPI_A_SS0_B                         	0x01b8 0x0444 0x0000 2 0
+#define MX6UL_PAD_NAND_DQS__PWM5_OUT                             	0x01b8 0x0444 0x0000 3 0
+#define MX6UL_PAD_NAND_DQS__EIM_WAIT                             	0x01b8 0x0444 0x0000 4 0
+#define MX6UL_PAD_NAND_DQS__GPIO4_IO16                           	0x01b8 0x0444 0x0000 5 0
+#define MX6UL_PAD_NAND_DQS__SDMA_EXT_EVENT01                     	0x01b8 0x0444 0x0000 6 0
+#define MX6UL_PAD_NAND_DQS__SPDIF_EXT_CLK                        	0x01b8 0x0444 0x0000 8 0
+#define MX6UL_PAD_SD1_CMD__USDHC1_CMD                            	0x01bc 0x0448 0x0000 0 0
+#define MX6UL_PAD_SD1_CMD__GPT2_COMPARE1                         	0x01bc 0x0448 0x0000 1 0
+#define MX6UL_PAD_SD1_CMD__SAI2_RX_SYNC                          	0x01bc 0x0448 0x0000 2 0
+#define MX6UL_PAD_SD1_CMD__SPDIF_OUT                             	0x01bc 0x0448 0x0000 3 0
+#define MX6UL_PAD_SD1_CMD__EIM_ADDR19                            	0x01bc 0x0448 0x0000 4 0
+#define MX6UL_PAD_SD1_CMD__GPIO2_IO16                            	0x01bc 0x0448 0x0000 5 0
+#define MX6UL_PAD_SD1_CMD__SDMA_EXT_EVENT00                      	0x01bc 0x0448 0x0000 6 0
+#define MX6UL_PAD_SD1_CMD__USB_OTG1_PWR                          	0x01bc 0x0448 0x0000 8 0
+#define MX6UL_PAD_SD1_CLK__USDHC1_CLK                            	0x01c0 0x044c 0x0000 0 0
+#define MX6UL_PAD_SD1_CLK__GPT2_COMPARE2                         	0x01c0 0x044c 0x0000 1 0
+#define MX6UL_PAD_SD1_CLK__SAI2_MCLK                             	0x01c0 0x044c 0x0000 2 0
+#define MX6UL_PAD_SD1_CLK__SPDIF_IN                              	0x01c0 0x044c 0x0618 3 3
+#define MX6UL_PAD_SD1_CLK__EIM_ADDR20                            	0x01c0 0x044c 0x0000 4 0
+#define MX6UL_PAD_SD1_CLK__GPIO2_IO17                            	0x01c0 0x044c 0x0000 5 0
+#define MX6UL_PAD_SD1_CLK__USB_OTG1_OC                           	0x01c0 0x044c 0x0000 8 0
+#define MX6UL_PAD_SD1_DATA0__USDHC1_DATA0                        	0x01c4 0x0450 0x0000 0 0
+#define MX6UL_PAD_SD1_DATA0__GPT2_COMPARE3                       	0x01c4 0x0450 0x0000 1 0
+#define MX6UL_PAD_SD1_DATA0__SAI2_TX_SYNC                        	0x01c4 0x0450 0x05fc 2 1
+#define MX6UL_PAD_SD1_DATA0__FLEXCAN1_TX                         	0x01c4 0x0450 0x0000 3 0
+#define MX6UL_PAD_SD1_DATA0__EIM_ADDR21                          	0x01c4 0x0450 0x0000 4 0
+#define MX6UL_PAD_SD1_DATA0__GPIO2_IO18                          	0x01c4 0x0450 0x0000 5 0
+#define MX6UL_PAD_SD1_DATA0__ANATOP_OTG1_ID                      	0x01c4 0x0450 0x0000 8 0
+#define MX6UL_PAD_SD1_DATA1__USDHC1_DATA1                        	0x01c8 0x0454 0x0000 0 0
+#define MX6UL_PAD_SD1_DATA1__GPT2_CLK                            	0x01c8 0x0454 0x05a0 1 1
+#define MX6UL_PAD_SD1_DATA1__SAI2_TX_BCLK                        	0x01c8 0x0454 0x05f8 2 1
+#define MX6UL_PAD_SD1_DATA1__FLEXCAN1_RX                         	0x01c8 0x0454 0x0584 3 3
+#define MX6UL_PAD_SD1_DATA1__EIM_ADDR22                          	0x01c8 0x0454 0x0000 4 0
+#define MX6UL_PAD_SD1_DATA1__GPIO2_IO19                          	0x01c8 0x0454 0x0000 5 0
+#define MX6UL_PAD_SD1_DATA1__USB_OTG2_PWR                        	0x01c8 0x0454 0x0000 8 0
+#define MX6UL_PAD_SD1_DATA2__USDHC1_DATA2                        	0x01cc 0x0458 0x0000 0 0
+#define MX6UL_PAD_SD1_DATA2__GPT2_CAPTURE1                       	0x01cc 0x0458 0x0598 1 1
+#define MX6UL_PAD_SD1_DATA2__SAI2_RX_DATA                        	0x01cc 0x0458 0x05f4 2 1
+#define MX6UL_PAD_SD1_DATA2__FLEXCAN2_TX                         	0x01cc 0x0458 0x0000 3 0
+#define MX6UL_PAD_SD1_DATA2__EIM_ADDR23                          	0x01cc 0x0458 0x0000 4 0
+#define MX6UL_PAD_SD1_DATA2__GPIO2_IO20                          	0x01cc 0x0458 0x0000 5 0
+#define MX6UL_PAD_SD1_DATA2__CCM_CLKO1                           	0x01cc 0x0458 0x0000 6 0
+#define MX6UL_PAD_SD1_DATA2__USB_OTG2_OC                         	0x01cc 0x0458 0x0000 8 0
+#define MX6UL_PAD_SD1_DATA3__USDHC1_DATA3                        	0x01d0 0x045c 0x0000 0 0
+#define MX6UL_PAD_SD1_DATA3__GPT2_CAPTURE2                       	0x01d0 0x045c 0x059c 1 1
+#define MX6UL_PAD_SD1_DATA3__SAI2_TX_DATA                        	0x01d0 0x045c 0x0000 2 0
+#define MX6UL_PAD_SD1_DATA3__FLEXCAN2_RX                         	0x01d0 0x045c 0x0588 3 3
+#define MX6UL_PAD_SD1_DATA3__EIM_ADDR24                          	0x01d0 0x045c 0x0000 4 0
+#define MX6UL_PAD_SD1_DATA3__GPIO2_IO21                          	0x01d0 0x045c 0x0000 5 0
+#define MX6UL_PAD_SD1_DATA3__CCM_CLKO2                           	0x01d0 0x045c 0x0000 6 0
+#define MX6UL_PAD_SD1_DATA3__ANATOP_OTG2_ID                      	0x01d0 0x045c 0x0000 8 0
+#define MX6UL_PAD_CSI_MCLK__CSI_MCLK                             	0x01d4 0x0460 0x0000 0 0
+#define MX6UL_PAD_CSI_MCLK__USDHC2_CD_B                          	0x01d4 0x0460 0x0674 1 0
+#define MX6UL_PAD_CSI_MCLK__RAWNAND_CE2_B                        	0x01d4 0x0460 0x0000 2 0
+#define MX6UL_PAD_CSI_MCLK__I2C1_SDA                             	0x01d4 0x0460 0x05a8 3 0
+#define MX6UL_PAD_CSI_MCLK__EIM_CS0_B                            	0x01d4 0x0460 0x0000 4 0
+#define MX6UL_PAD_CSI_MCLK__GPIO4_IO17                           	0x01d4 0x0460 0x0000 5 0
+#define MX6UL_PAD_CSI_MCLK__SNVS_HP_VIO_5_CTL                    	0x01d4 0x0460 0x0000 6 0
+#define MX6UL_PAD_CSI_MCLK__UART6_DCE_TX                             	0x01d4 0x0460 0x0000 8 0
+#define MX6UL_PAD_CSI_MCLK__UART6_DTE_RX                             	0x01d4 0x0460 0x064c 8 0
+#define MX6UL_PAD_CSI_PIXCLK__CSI_PIXCLK                         	0x01d8 0x0464 0x0528 0 1
+#define MX6UL_PAD_CSI_PIXCLK__USDHC2_WP                          	0x01d8 0x0464 0x069c 1 2
+#define MX6UL_PAD_CSI_PIXCLK__RAWNAND_CE3_B                      	0x01d8 0x0464 0x0000 2 0
+#define MX6UL_PAD_CSI_PIXCLK__I2C1_SCL                           	0x01d8 0x0464 0x05a4 3 2
+#define MX6UL_PAD_CSI_PIXCLK__EIM_OE                             	0x01d8 0x0464 0x0000 4 0
+#define MX6UL_PAD_CSI_PIXCLK__GPIO4_IO18                         	0x01d8 0x0464 0x0000 5 0
+#define MX6UL_PAD_CSI_PIXCLK__SNVS_HP_VIO_5                      	0x01d8 0x0464 0x0000 6 0
+#define MX6UL_PAD_CSI_PIXCLK__UART6_DCE_RX                           	0x01d8 0x0464 0x064c 8 3
+#define MX6UL_PAD_CSI_PIXCLK__UART6_DTE_TX                           	0x01d8 0x0464 0x0000 8 0
+#define MX6UL_PAD_CSI_VSYNC__CSI_VSYNC                           	0x01dc 0x0468 0x052c 0 0
+#define MX6UL_PAD_CSI_VSYNC__USDHC2_CLK                          	0x01dc 0x0468 0x0670 1 0
+#define MX6UL_PAD_CSI_VSYNC__SIM1_PORT1_CLK                      	0x01dc 0x0468 0x0000 2 0
+#define MX6UL_PAD_CSI_VSYNC__I2C2_SDA                            	0x01dc 0x0468 0x05b0 3 0
+#define MX6UL_PAD_CSI_VSYNC__EIM_RW                              	0x01dc 0x0468 0x0000 4 0
+#define MX6UL_PAD_CSI_VSYNC__GPIO4_IO19                          	0x01dc 0x0468 0x0000 5 0
+#define MX6UL_PAD_CSI_VSYNC__PWM7_OUT                            	0x01dc 0x0468 0x0000 6 0
+#define MX6UL_PAD_CSI_VSYNC__UART6_DCE_RTS                       	0x01dc 0x0468 0x0648 8 0
+#define MX6UL_PAD_CSI_VSYNC__UART6_DTE_CTS                       	0x01dc 0x0468 0x0000 8 0
+#define MX6UL_PAD_CSI_HSYNC__CSI_HSYNC                           	0x01e0 0x046c 0x0524 0 0
+#define MX6UL_PAD_CSI_HSYNC__USDHC2_CMD                          	0x01e0 0x046c 0x0678 1 0
+#define MX6UL_PAD_CSI_HSYNC__SIM1_PORT1_PD                       	0x01e0 0x046c 0x0000 2 0
+#define MX6UL_PAD_CSI_HSYNC__I2C2_SCL                            	0x01e0 0x046c 0x05ac 3 0
+#define MX6UL_PAD_CSI_HSYNC__EIM_LBA_B                           	0x01e0 0x046c 0x0000 4 0
+#define MX6UL_PAD_CSI_HSYNC__GPIO4_IO20                          	0x01e0 0x046c 0x0000 5 0
+#define MX6UL_PAD_CSI_HSYNC__PWM8_OUT                            	0x01e0 0x046c 0x0000 6 0
+#define MX6UL_PAD_CSI_HSYNC__UART6_DCE_CTS                       	0x01e0 0x046c 0x0000 8 0
+#define MX6UL_PAD_CSI_HSYNC__UART6_DTE_RTS                       	0x01e0 0x046c 0x0648 8 1
+#define MX6UL_PAD_CSI_DATA00__CSI_DATA02                         	0x01e4 0x0470 0x04c4 0 0
+#define MX6UL_PAD_CSI_DATA00__USDHC2_DATA0                       	0x01e4 0x0470 0x067c 1 0
+#define MX6UL_PAD_CSI_DATA00__SIM1_PORT1_RST_B                   	0x01e4 0x0470 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA00__ECSPI2_SCLK                        	0x01e4 0x0470 0x0544 3 0
+#define MX6UL_PAD_CSI_DATA00__EIM_AD00                           	0x01e4 0x0470 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA00__GPIO4_IO21                         	0x01e4 0x0470 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA00__SRC_INT_BOOT                       	0x01e4 0x0470 0x0000 6 0
+#define MX6UL_PAD_CSI_DATA00__UART5_DCE_TX                           	0x01e4 0x0470 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA00__UART5_DTE_RX                           	0x01e4 0x0470 0x0644 8 0
+#define MX6UL_PAD_CSI_DATA01__CSI_DATA03                         	0x01e8 0x0474 0x04c8 0 0
+#define MX6UL_PAD_CSI_DATA01__USDHC2_DATA1                       	0x01e8 0x0474 0x0680 1 0
+#define MX6UL_PAD_CSI_DATA01__SIM1_PORT1_SVEN                    	0x01e8 0x0474 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA01__ECSPI2_SS0                         	0x01e8 0x0474 0x0000 3 0
+#define MX6UL_PAD_CSI_DATA01__EIM_AD01                           	0x01e8 0x0474 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA01__GPIO4_IO22                         	0x01e8 0x0474 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA01__SAI1_MCLK                          	0x01e8 0x0474 0x0000 6 0
+#define MX6UL_PAD_CSI_DATA01__UART5_DCE_RX                           	0x01e8 0x0474 0x0644 8 1
+#define MX6UL_PAD_CSI_DATA01__UART5_DTE_TX                           	0x01e8 0x0474 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA02__CSI_DATA04                         	0x01ec 0x0478 0x04d8 0 1
+#define MX6UL_PAD_CSI_DATA02__USDHC2_DATA2                       	0x01ec 0x0478 0x0684 1 2
+#define MX6UL_PAD_CSI_DATA02__SIM1_PORT1_TRXD                    	0x01ec 0x0478 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA02__ECSPI2_MOSI                        	0x01ec 0x0478 0x054c 3 1
+#define MX6UL_PAD_CSI_DATA02__EIM_AD02                           	0x01ec 0x0478 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA02__GPIO4_IO23                         	0x01ec 0x0478 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA02__SAI1_RX_SYNC                       	0x01ec 0x0478 0x0000 6 0
+#define MX6UL_PAD_CSI_DATA02__UART5_DCE_RTS                      	0x01ec 0x0478 0x0640 8 5
+#define MX6UL_PAD_CSI_DATA02__UART5_DTE_CTS                      	0x01ec 0x0478 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA03__CSI_DATA05                         	0x01f0 0x047c 0x04cc 0 0
+#define MX6UL_PAD_CSI_DATA03__USDHC2_DATA3                       	0x01f0 0x047c 0x0688 1 0
+#define MX6UL_PAD_CSI_DATA03__SIM2_PORT1_PD                      	0x01f0 0x047c 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA03__ECSPI2_MISO                        	0x01f0 0x047c 0x0548 3 0
+#define MX6UL_PAD_CSI_DATA03__EIM_AD03                           	0x01f0 0x047c 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA03__GPIO4_IO24                         	0x01f0 0x047c 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA03__SAI1_RX_BCLK                       	0x01f0 0x047c 0x0000 6 0
+#define MX6UL_PAD_CSI_DATA03__UART5_DCE_CTS                      	0x01f0 0x047c 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA03__UART5_DTE_RTS                      	0x01f0 0x047c 0x0640 8 0
+#define MX6UL_PAD_CSI_DATA04__CSI_DATA06                         	0x01f4 0x0480 0x04dc 0 1
+#define MX6UL_PAD_CSI_DATA04__USDHC2_DATA4                       	0x01f4 0x0480 0x068c 1 2
+#define MX6UL_PAD_CSI_DATA04__SIM2_PORT1_CLK                     	0x01f4 0x0480 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA04__ECSPI1_SCLK                        	0x01f4 0x0480 0x0534 3 1
+#define MX6UL_PAD_CSI_DATA04__EIM_AD04                           	0x01f4 0x0480 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA04__GPIO4_IO25                         	0x01f4 0x0480 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA04__SAI1_TX_SYNC                       	0x01f4 0x0480 0x05ec 6 1
+#define MX6UL_PAD_CSI_DATA04__USDHC1_WP                          	0x01f4 0x0480 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA05__CSI_DATA07                         	0x01f8 0x0484 0x04e0 0 1
+#define MX6UL_PAD_CSI_DATA05__USDHC2_DATA5                       	0x01f8 0x0484 0x0690 1 2
+#define MX6UL_PAD_CSI_DATA05__SIM2_PORT1_RST_B                   	0x01f8 0x0484 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA05__ECSPI1_SS0                         	0x01f8 0x0484 0x0000 3 0
+#define MX6UL_PAD_CSI_DATA05__EIM_AD05                           	0x01f8 0x0484 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA05__GPIO4_IO26                         	0x01f8 0x0484 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA05__SAI1_TX_BCLK                       	0x01f8 0x0484 0x05e8 6 1
+#define MX6UL_PAD_CSI_DATA05__USDHC1_CD_B                        	0x01f8 0x0484 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA06__CSI_DATA08                         	0x01fc 0x0488 0x04e4 0 1
+#define MX6UL_PAD_CSI_DATA06__USDHC2_DATA6                       	0x01fc 0x0488 0x0694 1 2
+#define MX6UL_PAD_CSI_DATA06__SIM2_PORT1_SVEN                    	0x01fc 0x0488 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA06__ECSPI1_MOSI                        	0x01fc 0x0488 0x053c 3 1
+#define MX6UL_PAD_CSI_DATA06__EIM_AD06                           	0x01fc 0x0488 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA06__GPIO4_IO27                         	0x01fc 0x0488 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA06__SAI1_RX_DATA                       	0x01fc 0x0488 0x0000 6 0
+#define MX6UL_PAD_CSI_DATA06__USDHC1_RESET_B                     	0x01fc 0x0488 0x0000 8 0
+#define MX6UL_PAD_CSI_DATA07__CSI_DATA09                         	0x0200 0x048c 0x04e8 0 1
+#define MX6UL_PAD_CSI_DATA07__USDHC2_DATA7                       	0x0200 0x048c 0x0698 1 2
+#define MX6UL_PAD_CSI_DATA07__SIM2_PORT1_TRXD                    	0x0200 0x048c 0x0000 2 0
+#define MX6UL_PAD_CSI_DATA07__ECSPI1_MISO                        	0x0200 0x048c 0x0538 3 1
+#define MX6UL_PAD_CSI_DATA07__EIM_AD07                           	0x0200 0x048c 0x0000 4 0
+#define MX6UL_PAD_CSI_DATA07__GPIO4_IO28                         	0x0200 0x048c 0x0000 5 0
+#define MX6UL_PAD_CSI_DATA07__SAI1_TX_DATA                       	0x0200 0x048c 0x0000 6 0
+#define MX6UL_PAD_CSI_DATA07__USDHC1_VSELECT                     	0x0200 0x048c 0x0000 8 0
+
+#endif /* __DTS_IMX6UL_PINFUNC_H */
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
new file mode 100644
index 000000000000..09edbedfd908
--- /dev/null
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -0,0 +1,707 @@
+/*
+ * Copyright 2015 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <dt-bindings/clock/imx6ul-clock.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include "imx6ul-pinfunc.h"
+#include "skeleton.dtsi"
+
+/ {
+	aliases {
+		ethernet0 = &fec1;
+		ethernet1 = &fec2;
+		gpio0 = &gpio1;
+		gpio1 = &gpio2;
+		gpio2 = &gpio3;
+		gpio3 = &gpio4;
+		gpio4 = &gpio5;
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		i2c2 = &i2c3;
+		i2c3 = &i2c4;
+		mmc0 = &usdhc1;
+		mmc1 = &usdhc2;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+		serial5 = &uart6;
+		serial6 = &uart7;
+		serial7 = &uart8;
+		spi0 = &ecspi1;
+		spi1 = &ecspi2;
+		spi2 = &ecspi3;
+		spi3 = &ecspi4;
+		usbphy0 = &usbphy1;
+		usbphy1 = &usbphy2;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <0>;
+			clock-latency = <61036>; /* two CLK32 periods */
+			operating-points = <
+				/* kHz	uV */
+				528000	1250000
+				396000	1150000
+				198000	1150000
+			>;
+			fsl,soc-operating-points = <
+				/* KHz	uV */
+				528000	1250000
+				396000	1150000
+				198000	1150000
+			>;
+			clocks = <&clks IMX6UL_CLK_ARM>,
+				 <&clks IMX6UL_CLK_PLL2_BUS>,
+				 <&clks IMX6UL_CLK_PLL2_PFD2>,
+				 <&clks IMX6UL_CA7_SECONDARY_SEL>,
+				 <&clks IMX6UL_CLK_STEP>,
+				 <&clks IMX6UL_CLK_PLL1_SW>,
+				 <&clks IMX6UL_CLK_PLL1_SYS>,
+				 <&clks IMX6UL_PLL1_BYPASS>,
+				 <&clks IMX6UL_CLK_PLL1>,
+				 <&clks IMX6UL_PLL1_BYPASS_SRC>,
+				 <&clks IMX6UL_CLK_OSC>;
+			clock-names = "arm", "pll2_bus",  "pll2_pfd2_396m",
+				      "secondary_sel", "step", "pll1_sw",
+				      "pll1_sys", "pll1_bypass", "pll1",
+				      "pll1_bypass_src", "osc";
+			arm-supply = <&reg_arm>;
+			soc-supply = <&reg_soc>;
+		};
+	};
+
+	intc: interrupt-controller@00a01000 {
+		compatible = "arm,cortex-a7-gic";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		reg = <0x00a01000 0x1000>,
+		      <0x00a02000 0x1000>,
+		      <0x00a04000 0x2000>,
+		      <0x00a06000 0x2000>;
+	};
+
+	ckil: clock-cli {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "ckil";
+	};
+
+	osc: clock-osc {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "osc";
+	};
+
+	ipp_di0: clock-di0 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+		clock-output-names = "ipp_di0";
+	};
+
+	ipp_di1: clock-di1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+		clock-output-names = "ipp_di1";
+	};
+
+	soc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&gpc>;
+		ranges;
+
+		pmu {
+			compatible = "arm,cortex-a7-pmu";
+			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		aips1: aips-bus@02000000 {
+			compatible = "fsl,aips-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x02000000 0x100000>;
+			ranges;
+
+			spba-bus@02000000 {
+				compatible = "fsl,spba-bus", "simple-bus";
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0x02000000 0x40000>;
+				ranges;
+
+				ecspi1: ecspi@02008000 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible = "fsl,imx6ul-ecspi", "fsl,imx51-ecspi";
+					reg = <0x02008000 0x4000>;
+					interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_ECSPI1>,
+						 <&clks IMX6UL_CLK_ECSPI1>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+
+				ecspi2: ecspi@0200c000 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible = "fsl,imx6ul-ecspi", "fsl,imx51-ecspi";
+					reg = <0x0200c000 0x4000>;
+					interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_ECSPI2>,
+						 <&clks IMX6UL_CLK_ECSPI2>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+
+				ecspi3: ecspi@02010000 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible = "fsl,imx6ul-ecspi", "fsl,imx51-ecspi";
+					reg = <0x02010000 0x4000>;
+					interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_ECSPI3>,
+						 <&clks IMX6UL_CLK_ECSPI3>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+
+				ecspi4: ecspi@02014000 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible = "fsl,imx6ul-ecspi", "fsl,imx51-ecspi";
+					reg = <0x02014000 0x4000>;
+					interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_ECSPI4>,
+						 <&clks IMX6UL_CLK_ECSPI4>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+
+				uart7: serial@02018000 {
+					compatible = "fsl,imx6ul-uart",
+						     "fsl,imx6q-uart";
+					reg = <0x02018000 0x4000>;
+					interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_UART7_IPG>,
+						 <&clks IMX6UL_CLK_UART7_SERIAL>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+
+				uart1: serial@02020000 {
+					compatible = "fsl,imx6ul-uart",
+						     "fsl,imx6q-uart";
+					reg = <0x02020000 0x4000>;
+					interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_UART1_IPG>,
+						 <&clks IMX6UL_CLK_UART1_SERIAL>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+
+				uart8: serial@02024000 {
+					compatible = "fsl,imx6ul-uart",
+						     "fsl,imx6q-uart";
+					reg = <0x02024000 0x4000>;
+					interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&clks IMX6UL_CLK_UART8_IPG>,
+						 <&clks IMX6UL_CLK_UART8_SERIAL>;
+					clock-names = "ipg", "per";
+					status = "disabled";
+				};
+			};
+
+			gpt1: gpt@02098000 {
+				compatible = "fsl,imx6ul-gpt", "fsl,imx6sx-gpt";
+				reg = <0x02098000 0x4000>;
+				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_GPT1_BUS>,
+					 <&clks IMX6UL_CLK_GPT1_SERIAL>;
+				clock-names = "ipg", "per";
+			};
+
+			gpio1: gpio@0209c000 {
+				compatible = "fsl,imx6ul-gpio", "fsl,imx35-gpio";
+				reg = <0x0209c000 0x4000>;
+				interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio2: gpio@020a0000 {
+				compatible = "fsl,imx6ul-gpio", "fsl,imx35-gpio";
+				reg = <0x020a0000 0x4000>;
+				interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio3: gpio@020a4000 {
+				compatible = "fsl,imx6ul-gpio", "fsl,imx35-gpio";
+				reg = <0x020a4000 0x4000>;
+				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio4: gpio@020a8000 {
+				compatible = "fsl,imx6ul-gpio", "fsl,imx35-gpio";
+				reg = <0x020a8000 0x4000>;
+				interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio5: gpio@020ac000 {
+				compatible = "fsl,imx6ul-gpio", "fsl,imx35-gpio";
+				reg = <0x020ac000 0x4000>;
+				interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			fec2: ethernet@020b4000 {
+				compatible = "fsl,imx6ul-fec", "fsl,imx6q-fec";
+				reg = <0x020b4000 0x4000>;
+				interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_ENET>,
+					 <&clks IMX6UL_CLK_ENET_AHB>,
+					 <&clks IMX6UL_CLK_ENET_PTP>,
+					 <&clks IMX6UL_CLK_ENET2_REF_125M>,
+					 <&clks IMX6UL_CLK_ENET2_REF_125M>;
+				clock-names = "ipg", "ahb", "ptp",
+					      "enet_clk_ref", "enet_out";
+				fsl,num-tx-queues=<1>;
+				fsl,num-rx-queues=<1>;
+				status = "disabled";
+			};
+
+			wdog1: wdog@020bc000 {
+				compatible = "fsl,imx6ul-wdt", "fsl,imx21-wdt";
+				reg = <0x020bc000 0x4000>;
+				interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_WDOG1>;
+			};
+
+			wdog2: wdog@020c0000 {
+				compatible = "fsl,imx6ul-wdt", "fsl,imx21-wdt";
+				reg = <0x020c0000 0x4000>;
+				interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_WDOG2>;
+				status = "disabled";
+			};
+
+			clks: ccm@020c4000 {
+				compatible = "fsl,imx6ul-ccm";
+				reg = <0x020c4000 0x4000>;
+				interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
+				#clock-cells = <1>;
+				clocks = <&ckil>, <&osc>, <&ipp_di0>, <&ipp_di1>;
+				clock-names = "ckil", "osc", "ipp_di0", "ipp_di1";
+			};
+
+			anatop: anatop@020c8000 {
+				compatible = "fsl,imx6ul-anatop", "fsl,imx6q-anatop",
+					     "syscon", "simple-bus";
+				reg = <0x020c8000 0x1000>;
+				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+
+				reg_3p0: regulator-3p0@120 {
+					compatible = "fsl,anatop-regulator";
+					regulator-name = "vdd3p0";
+					regulator-min-microvolt = <2625000>;
+					regulator-max-microvolt = <3400000>;
+					anatop-reg-offset = <0x120>;
+					anatop-vol-bit-shift = <8>;
+					anatop-vol-bit-width = <5>;
+					anatop-min-bit-val = <0>;
+					anatop-min-voltage = <2625000>;
+					anatop-max-voltage = <3400000>;
+					anatop-enable-bit = <0>;
+				};
+
+				reg_arm: regulator-vddcore@140 {
+					compatible = "fsl,anatop-regulator";
+					regulator-name = "cpu";
+					regulator-min-microvolt = <725000>;
+					regulator-max-microvolt = <1450000>;
+					regulator-always-on;
+					anatop-reg-offset = <0x140>;
+					anatop-vol-bit-shift = <0>;
+					anatop-vol-bit-width = <5>;
+					anatop-delay-reg-offset = <0x170>;
+					anatop-delay-bit-shift = <24>;
+					anatop-delay-bit-width = <2>;
+					anatop-min-bit-val = <1>;
+					anatop-min-voltage = <725000>;
+					anatop-max-voltage = <1450000>;
+				};
+
+				reg_soc: regulator-vddsoc@140 {
+					compatible = "fsl,anatop-regulator";
+					regulator-name = "vddsoc";
+					regulator-min-microvolt = <725000>;
+					regulator-max-microvolt = <1450000>;
+					regulator-always-on;
+					anatop-reg-offset = <0x140>;
+					anatop-vol-bit-shift = <18>;
+					anatop-vol-bit-width = <5>;
+					anatop-delay-reg-offset = <0x170>;
+					anatop-delay-bit-shift = <28>;
+					anatop-delay-bit-width = <2>;
+					anatop-min-bit-val = <1>;
+					anatop-min-voltage = <725000>;
+					anatop-max-voltage = <1450000>;
+				};
+			};
+
+			usbphy1: usbphy@020c9000 {
+				compatible = "fsl,imx6ul-usbphy", "fsl,imx23-usbphy";
+				reg = <0x020c9000 0x1000>;
+				interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_USBPHY1>;
+				phy-3p0-supply = <&reg_3p0>;
+				fsl,anatop = <&anatop>;
+			};
+
+			usbphy2: usbphy@020ca000 {
+				compatible = "fsl,imx6ul-usbphy", "fsl,imx23-usbphy";
+				reg = <0x020ca000 0x1000>;
+				interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_USBPHY2>;
+				phy-3p0-supply = <&reg_3p0>;
+				fsl,anatop = <&anatop>;
+			};
+
+			snvs: snvs@020cc000 {
+				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x020cc000 0x4000>;
+
+				snvs_rtc: snvs-rtc-lp {
+					compatible = "fsl,sec-v4.0-mon-rtc-lp";
+					regmap = <&snvs>;
+					offset = <0x34>;
+					interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+						     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+				};
+
+				snvs_pwrkey: snvs-powerkey {
+					compatible = "fsl,sec-v4.0-pwrkey";
+					regmap = <&snvs>;
+					interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+					linux,keycode = <KEY_POWER>;
+					wakeup-source;
+				};
+			};
+
+			epit1: epit@020d0000 {
+				reg = <0x020d0000 0x4000>;
+				interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			epit2: epit@020d4000 {
+				reg = <0x020d4000 0x4000>;
+				interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			src: src@020d8000 {
+				compatible = "fsl,imx6ul-src", "fsl,imx51-src";
+				reg = <0x020d8000 0x4000>;
+				interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+				#reset-cells = <1>;
+			};
+
+			gpc: gpc@020dc000 {
+				compatible = "fsl,imx6ul-gpc", "fsl,imx6q-gpc";
+				reg = <0x020dc000 0x4000>;
+				interrupt-controller;
+				#interrupt-cells = <3>;
+				interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&intc>;
+			};
+
+			iomuxc: iomuxc@020e0000 {
+				compatible = "fsl,imx6ul-iomuxc";
+				reg = <0x020e0000 0x4000>;
+			};
+
+			gpr: iomuxc-gpr@020e4000 {
+				compatible = "fsl,imx6ul-iomuxc-gpr", "syscon";
+				reg = <0x020e4000 0x4000>;
+			};
+
+			gpt2: gpt@020e8000 {
+				compatible = "fsl,imx6ul-gpt", "fsl,imx6sx-gpt";
+				reg = <0x020e8000 0x4000>;
+				interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_DUMMY>,
+					 <&clks IMX6UL_CLK_DUMMY>;
+				clock-names = "ipg", "per";
+			};
+
+			pwm5: pwm@020f0000 {
+				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
+				reg = <0x020f0000 0x4000>;
+				interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_DUMMY>,
+					 <&clks IMX6UL_CLK_DUMMY>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+			};
+
+			pwm6: pwm@020f4000 {
+				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
+				reg = <0x020f4000 0x4000>;
+				interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_DUMMY>,
+					 <&clks IMX6UL_CLK_DUMMY>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+			};
+
+			pwm7: pwm@020f8000 {
+				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
+				reg = <0x020f8000 0x4000>;
+				interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_DUMMY>,
+					 <&clks IMX6UL_CLK_DUMMY>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+			};
+
+			pwm8: pwm@020fc000 {
+				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
+				reg = <0x020fc000 0x4000>;
+				interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_DUMMY>,
+					 <&clks IMX6UL_CLK_DUMMY>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+			};
+		};
+
+		aips2: aips-bus@02100000 {
+			compatible = "fsl,aips-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x02100000 0x100000>;
+			ranges;
+
+			usbotg1: usb@02184000 {
+				compatible = "fsl,imx6ul-usb", "fsl,imx27-usb";
+				reg = <0x02184000 0x200>;
+				interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_USBOH3>;
+				fsl,usbphy = <&usbphy1>;
+				fsl,usbmisc = <&usbmisc 0>;
+				fsl,anatop = <&anatop>;
+				status = "disabled";
+			};
+
+			usbotg2: usb@02184200 {
+				compatible = "fsl,imx6ul-usb", "fsl,imx27-usb";
+				reg = <0x02184200 0x200>;
+				interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_USBOH3>;
+				fsl,usbphy = <&usbphy2>;
+				fsl,usbmisc = <&usbmisc 1>;
+				status = "disabled";
+			};
+
+			usbmisc: usbmisc@02184800 {
+				#index-cells = <1>;
+				compatible = "fsl,imx6ul-usbmisc", "fsl,imx6q-usbmisc";
+				reg = <0x02184800 0x200>;
+			};
+
+			fec1: ethernet@02188000 {
+				compatible = "fsl,imx6ul-fec", "fsl,imx6q-fec";
+				reg = <0x02188000 0x4000>;
+				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_ENET>,
+					 <&clks IMX6UL_CLK_ENET_AHB>,
+					 <&clks IMX6UL_CLK_ENET_PTP>,
+					 <&clks IMX6UL_CLK_ENET_REF>,
+					 <&clks IMX6UL_CLK_ENET_REF>;
+				clock-names = "ipg", "ahb", "ptp",
+					      "enet_clk_ref", "enet_out";
+				fsl,num-tx-queues=<1>;
+				fsl,num-rx-queues=<1>;
+				status = "disabled";
+			};
+
+			usdhc1: usdhc@02190000 {
+				compatible = "fsl,imx6ul-usdhc", "fsl,imx6sx-usdhc";
+				reg = <0x02190000 0x4000>;
+				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_USDHC1>,
+					 <&clks IMX6UL_CLK_USDHC1>,
+					 <&clks IMX6UL_CLK_USDHC1>;
+				clock-names = "ipg", "ahb", "per";
+				bus-width = <4>;
+				status = "disabled";
+			};
+
+			usdhc2: usdhc@02194000 {
+				compatible = "fsl,imx6ul-usdhc", "fsl,imx6sx-usdhc";
+				reg = <0x02194000 0x4000>;
+				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_USDHC2>,
+					 <&clks IMX6UL_CLK_USDHC2>,
+					 <&clks IMX6UL_CLK_USDHC2>;
+				clock-names = "ipg", "ahb", "per";
+				bus-width = <4>;
+				status = "disabled";
+			};
+
+			i2c1: i2c@021a0000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx6ul-i2c", "fsl,imx21-i2c";
+				reg = <0x021a0000 0x4000>;
+				interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_I2C1>;
+				status = "disabled";
+			};
+
+			i2c2: i2c@021a4000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx6ul-i2c", "fsl,imx21-i2c";
+				reg = <0x021a4000 0x4000>;
+				interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_I2C2>;
+				status = "disabled";
+			};
+
+			i2c3: i2c@021a8000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx6ul-i2c", "fsl,imx21-i2c";
+				reg = <0x021a8000 0x4000>;
+				interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_I2C3>;
+				status = "disabled";
+			};
+
+			qspi: qspi@021e0000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx6ul-qspi", "fsl,imx6sx-qspi";
+				reg = <0x021e0000 0x4000>, <0x60000000 0x10000000>;
+				reg-names = "QuadSPI", "QuadSPI-memory";
+				interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_QSPI>,
+					 <&clks IMX6UL_CLK_QSPI>;
+				clock-names = "qspi_en", "qspi";
+				status = "disabled";
+			};
+
+			uart2: serial@021e8000 {
+				compatible = "fsl,imx6ul-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x021e8000 0x4000>;
+				interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_UART2_IPG>,
+					 <&clks IMX6UL_CLK_UART2_SERIAL>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart3: serial@021ec000 {
+				compatible = "fsl,imx6ul-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x021ec000 0x4000>;
+				interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_UART3_IPG>,
+					 <&clks IMX6UL_CLK_UART3_SERIAL>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart4: serial@021f0000 {
+				compatible = "fsl,imx6ul-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x021f0000 0x4000>;
+				interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_UART4_IPG>,
+					 <&clks IMX6UL_CLK_UART4_SERIAL>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart5: serial@021f4000 {
+				compatible = "fsl,imx6ul-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x021f4000 0x4000>;
+				interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_UART5_IPG>,
+					 <&clks IMX6UL_CLK_UART5_SERIAL>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			i2c4: i2c@021f8000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx6ul-i2c", "fsl,imx21-i2c";
+				reg = <0x021f8000 0x4000>;
+				interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_I2C4>;
+				status = "disabled";
+			};
+
+			uart6: serial@021fc000 {
+				compatible = "fsl,imx6ul-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x021fc000 0x4000>;
+				interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX6UL_CLK_UART6_IPG>,
+					 <&clks IMX6UL_CLK_UART6_SERIAL>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index 4d1a4b977d84..fdd1d7c9a5cc 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -234,8 +234,8 @@
 &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
-	cd-gpios = <&gpio5 0 0>;
-	wp-gpios = <&gpio5 1 0>;
+	cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>;
 	enable-sdio-wakeup;
 	keep-power-in-suspend;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index c42cf8db0451..b738ce0f9d9b 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -121,6 +121,209 @@
 		clock-output-names = "osc";
 	};
 
+	etr@30086000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0x30086000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			etr_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	tpiu@30087000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0x30087000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			tpiu_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	replicator {
+		/*
+		 * non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell"
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&etr_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etf_out_port>;
+				};
+			};
+		};
+	};
+
+	etf@30084000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0x30084000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				etf_in_port: endpoint {
+					slave-mode;
+					remote-endpoint = <&hugo_funnel_out_port0>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				etf_out_port: endpoint {
+					remote-endpoint = <&replicator_in_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@30083000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0x30083000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel input ports */
+			port@0 {
+				reg = <0>;
+				hugo_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ca_funnel_out_port0>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				hugo_funnel_in_port1: endpoint {
+					slave-mode; /* M4 input */
+				};
+			};
+
+			port@2 {
+				reg = <0>;
+				hugo_funnel_out_port0: endpoint {
+					remote-endpoint = <&etf_in_port>;
+				};
+			};
+
+			/* the other input ports are not connect to anything */
+		};
+	};
+
+	funnel@30041000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0x30041000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel input ports */
+			port@0 {
+				reg = <0>;
+				ca_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				ca_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm1_out_port>;
+				};
+			};
+
+			/* funnel output port */
+			port@2 {
+				reg = <0>;
+				ca_funnel_out_port0: endpoint {
+					remote-endpoint = <&hugo_funnel_in_port0>;
+				};
+			};
+
+			/* the other input ports are not connect to anything */
+		};
+	};
+
+	etm@3007c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0x3007c000 0x1000>;
+		cpu = <&cpu0>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			etm0_out_port: endpoint {
+				remote-endpoint = <&ca_funnel_in_port0>;
+			};
+		};
+	};
+
+	etm@3007d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0x3007d000 0x1000>;
+
+		/*
+		 * System will hang if added nosmp in kernel command line
+		 * without arm,primecell-periphid because amba bus try to
+		 * read id and core1 power off at this time.
+		 */
+		arm,primecell-periphid = <0xbb956>;
+		cpu = <&cpu1>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			etm1_out_port: endpoint {
+				remote-endpoint = <&ca_funnel_in_port1>;
+			};
+		};
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -212,6 +415,37 @@
 				#interrupt-cells = <2>;
 			};
 
+			wdog1: wdog@30280000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x30280000 0x10000>;
+				interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG1_ROOT_CLK>;
+			};
+
+			wdog2: wdog@30290000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x30290000 0x10000>;
+				interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG2_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			wdog3: wdog@302a0000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x302a0000 0x10000>;
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG3_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			wdog4: wdog@302b0000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x302b0000 0x10000>;
+				interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG4_ROOT_CLK>;
+				status = "disabled";
+			};
+
 			gpt1: gpt@302d0000 {
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302d0000 0x10000>;
@@ -291,17 +525,31 @@
 			};
 
 			snvs: snvs@30370000 {
-				compatible = "fsl,sec-v4.0-mon", "simple-bus";
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0 0x30370000 0x10000>;
+				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x30370000 0x10000>;
 
-				snvs-rtc-lp@34 {
+				snvs_rtc: snvs-rtc-lp {
 					compatible = "fsl,sec-v4.0-mon-rtc-lp";
-					reg = <0x34 0x58>;
+					regmap = <&snvs>;
+					offset = <0x34>;
 					interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
 						     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 				};
+
+				snvs_poweroff: snvs-poweroff {
+					compatible = "syscon-poweroff";
+					regmap = <&snvs>;
+					offset = <0x38>;
+					mask = <0x60>;
+				};
+
+				snvs_pwrkey: snvs-powerkey {
+					compatible = "fsl,sec-v4.0-pwrkey";
+					regmap = <&snvs>;
+					interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+					linux,keycode = <KEY_POWER>;
+					wakeup-source;
+				};
 			};
 
 			clks: ccm@30380000 {
diff --git a/arch/arm/boot/dts/k2e-clocks.dtsi b/arch/arm/boot/dts/k2e-clocks.dtsi
index 4773d6af66a0..d56d68fe7ffc 100644
--- a/arch/arm/boot/dts/k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/k2e-clocks.dtsi
@@ -13,9 +13,8 @@ clocks {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2e.dtsi b/arch/arm/boot/dts/k2e.dtsi
index 50e555eab50d..675fb8e492c6 100644
--- a/arch/arm/boot/dts/k2e.dtsi
+++ b/arch/arm/boot/dts/k2e.dtsi
@@ -86,7 +86,7 @@
 			gpio,syscon-dev = <&devctrl 0x240>;
 		};
 
-		pcie@21020000 {
+		pcie1: pcie@21020000 {
 			compatible = "ti,keystone-pcie","snps,dw-pcie";
 			clocks = <&clkpcie1>;
 			clock-names = "pcie";
@@ -96,6 +96,7 @@
 			ranges = <0x81000000 0 0 0x23260000 0x4000 0x4000
 				0x82000000 0 0x60000000 0x60000000 0 0x10000000>;
 
+			status = "disabled";
 			device_type = "pci";
 			num-lanes = <2>;
 
@@ -130,10 +131,17 @@
 					<GIC_SPI 376 IRQ_TYPE_EDGE_RISING>;
 			};
 		};
+
+		mdio: mdio@24200f00 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x24200f00 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2e-netcp.dtsi"
 	};
 };
-
-&mdio {
-	reg = <0x24200f00 0x100>;
-};
diff --git a/arch/arm/boot/dts/k2hk-clocks.dtsi b/arch/arm/boot/dts/k2hk-clocks.dtsi
index d5adee3c0067..af9b7190533a 100644
--- a/arch/arm/boot/dts/k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/k2hk-clocks.dtsi
@@ -22,9 +22,8 @@ clocks {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2hk.dtsi b/arch/arm/boot/dts/k2hk.dtsi
index ae6472407b22..d0810a5f2968 100644
--- a/arch/arm/boot/dts/k2hk.dtsi
+++ b/arch/arm/boot/dts/k2hk.dtsi
@@ -98,6 +98,17 @@
 			#gpio-cells = <2>;
 			gpio,syscon-dev = <&devctrl 0x25c>;
 		};
+
+		mdio: mdio@02090300 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x02090300 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2hk-netcp.dtsi"
 	};
 };
diff --git a/arch/arm/boot/dts/k2l-clocks.dtsi b/arch/arm/boot/dts/k2l-clocks.dtsi
index eb1e3e29f073..ef8464bb11ff 100644
--- a/arch/arm/boot/dts/k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/k2l-clocks.dtsi
@@ -22,9 +22,8 @@ clocks {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2l.dtsi b/arch/arm/boot/dts/k2l.dtsi
index 0e007483615e..49fd414f680c 100644
--- a/arch/arm/boot/dts/k2l.dtsi
+++ b/arch/arm/boot/dts/k2l.dtsi
@@ -29,7 +29,6 @@
 	};
 
 	soc {
-
 		/include/ "k2l-clocks.dtsi"
 
 		uart2: serial@02348400 {
@@ -79,6 +78,17 @@
 			#gpio-cells = <2>;
 			gpio,syscon-dev = <&devctrl 0x24c>;
 		};
+
+		mdio: mdio@26200f00 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x26200f00 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2l-netcp.dtsi"
 	};
 };
@@ -96,7 +106,3 @@
        /* Pin muxed. Enabled and configured by Bootloader */
        status = "disabled";
 };
-
-&mdio {
-	reg = <0x26200f00 0x100>;
-};
diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi
index c06542b2c954..72816d65f7ec 100644
--- a/arch/arm/boot/dts/keystone.dtsi
+++ b/arch/arm/boot/dts/keystone.dtsi
@@ -267,17 +267,6 @@
 				  1 0 0x21000A00 0x00000100>;
 		};
 
-		mdio: mdio@02090300 {
-			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg		= <0x02090300 0x100>;
-			status = "disabled";
-			clocks = <&clkpa>;
-			clock-names = "fck";
-			bus_freq	= <2500000>;
-		};
-
 		kirq0: keystone_irq@26202a0 {
 			compatible = "ti,keystone-irq";
 			interrupts = <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;
@@ -286,7 +275,7 @@
 			ti,syscon-dev = <&devctrl 0x2a0>;
 		};
 
-		pcie@21800000 {
+		pcie0: pcie@21800000 {
 			compatible = "ti,keystone-pcie", "snps,dw-pcie";
 			clocks = <&clkpcie>;
 			clock-names = "pcie";
@@ -296,6 +285,7 @@
 			ranges = <0x81000000 0 0 0x23250000 0 0x4000
 				0x82000000 0 0x50000000 0x50000000 0 0x10000000>;
 
+			status = "disabled";
 			device_type = "pci";
 			num-lanes = <2>;
 
diff --git a/arch/arm/boot/dts/kirkwood-d2net.dts b/arch/arm/boot/dts/kirkwood-d2net.dts
index 6b7856025001..e1c25c35e9ce 100644
--- a/arch/arm/boot/dts/kirkwood-d2net.dts
+++ b/arch/arm/boot/dts/kirkwood-d2net.dts
@@ -10,6 +10,7 @@
 
 /dts-v1/;
 
+#include <dt-bindings/leds/leds-ns2.h>
 #include "kirkwood-netxbig.dtsi"
 
 / {
@@ -28,6 +29,10 @@
 			label = "d2net_v2:blue:sata";
 			slow-gpio = <&gpio0 29 GPIO_ACTIVE_HIGH>;
 			cmd-gpio = <&gpio0 30 GPIO_ACTIVE_HIGH>;
+			modes-map = <NS_V2_LED_OFF  1 0
+				     NS_V2_LED_ON   0 1
+				     NS_V2_LED_ON   1 1
+				     NS_V2_LED_SATA 0 0>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/kirkwood-is2.dts b/arch/arm/boot/dts/kirkwood-is2.dts
index da674bbd49a8..4121674abd1c 100644
--- a/arch/arm/boot/dts/kirkwood-is2.dts
+++ b/arch/arm/boot/dts/kirkwood-is2.dts
@@ -1,5 +1,6 @@
 /dts-v1/;
 
+#include <dt-bindings/leds/leds-ns2.h>
 #include "kirkwood-ns2-common.dtsi"
 
 / {
@@ -27,6 +28,10 @@
 			label = "ns2:blue:sata";
 			slow-gpio = <&gpio0 29 0>;
 			cmd-gpio = <&gpio0 30 0>;
+			modes-map = <NS_V2_LED_OFF  1 0
+				     NS_V2_LED_ON   0 1
+				     NS_V2_LED_ON   1 1
+				     NS_V2_LED_SATA 0 0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood-lswvl.dts b/arch/arm/boot/dts/kirkwood-lswvl.dts
new file mode 100644
index 000000000000..09eed3cea0af
--- /dev/null
+++ b/arch/arm/boot/dts/kirkwood-lswvl.dts
@@ -0,0 +1,301 @@
+/*
+ * Device Tree file for Buffalo Linkstation LS-WVL/VL
+ *
+ * Copyright (C) 2015, rogershimizu@gmail.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/dts-v1/;
+
+#include "kirkwood.dtsi"
+#include "kirkwood-6282.dtsi"
+
+/ {
+	model = "Buffalo Linkstation LS-WVL/VL";
+	compatible = "buffalo,lswvl", "buffalo,lsvl", "marvell,kirkwood-88f6282", "marvell,kirkwood";
+
+	memory { /* 256 MB */
+		device_type = "memory";
+		reg = <0x00000000 0x10000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200n8 earlyprintk";
+		stdout-path = &uart0;
+	};
+
+	mbus {
+		pcie-controller {
+			status = "okay";
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
+	ocp@f1000000 {
+		pinctrl: pin-controller@10000 {
+			pmx_power_hdd0: pmx-power-hdd0 {
+				marvell,pins = "mpp8";
+				marvell,function = "gpio";
+			};
+			pmx_power_hdd1: pmx-power-hdd1 {
+				marvell,pins = "mpp9";
+				marvell,function = "gpio";
+			};
+			pmx_usb_vbus: pmx-usb-vbus {
+				marvell,pins = "mpp12";
+				marvell,function = "gpio";
+			};
+			pmx_fan_high: pmx-fan-high {
+				marvell,pins = "mpp16";
+				marvell,function = "gpio";
+			};
+			pmx_fan_low: pmx-fan-low {
+				marvell,pins = "mpp17";
+				marvell,function = "gpio";
+			};
+			pmx_led_hdderr0: pmx-led-hdderr0 {
+				marvell,pins = "mpp34";
+				marvell,function = "gpio";
+			};
+			pmx_led_hdderr1: pmx-led-hdderr1 {
+				marvell,pins = "mpp35";
+				marvell,function = "gpio";
+			};
+			pmx_led_alarm: pmx-led-alarm {
+				marvell,pins = "mpp36";
+				marvell,function = "gpio";
+			};
+			pmx_led_function_red: pmx-led-function-red {
+				marvell,pins = "mpp37";
+				marvell,function = "gpio";
+			};
+			pmx_led_info: pmx-led-info {
+				marvell,pins = "mpp38";
+				marvell,function = "gpio";
+			};
+			pmx_led_function_blue: pmx-led-function-blue {
+				marvell,pins = "mpp39";
+				marvell,function = "gpio";
+			};
+			pmx_led_power: pmx-led-power {
+				marvell,pins = "mpp40";
+				marvell,function = "gpio";
+			};
+			pmx_fan_lock: pmx-fan-lock {
+				marvell,pins = "mpp43";
+				marvell,function = "gpio";
+			};
+			pmx_button_function: pmx-button-function {
+				marvell,pins = "mpp45";
+				marvell,function = "gpio";
+			};
+			pmx_power_switch: pmx-power-switch {
+				marvell,pins = "mpp46";
+				marvell,function = "gpio";
+			};
+			pmx_power_auto_switch: pmx-power-auto-switch {
+				marvell,pins = "mpp47";
+				marvell,function = "gpio";
+			};
+		};
+
+		serial@12000 {
+			status = "okay";
+		};
+
+		sata@80000 {
+			status = "okay";
+			nr-ports = <2>;
+		};
+
+		spi@10600 {
+			status = "okay";
+
+			m25p40@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "st,m25p40", "jedec,spi-nor";
+				reg = <0>;
+				spi-max-frequency = <25000000>;
+				mode = <0>;
+
+				partition@0 {
+					reg = <0x0 0x60000>;
+					label = "uboot";
+					read-only;
+				};
+
+				partition@60000 {
+					reg = <0x60000 0x10000>;
+					label = "dtb";
+					read-only;
+				};
+
+				partition@70000 {
+					reg = <0x70000 0x10000>;
+					label = "uboot_env";
+				};
+			};
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_button_function &pmx_power_switch
+			     &pmx_power_auto_switch>;
+		pinctrl-names = "default";
+
+		button@1 {
+			label = "Function Button";
+			linux,code = <KEY_OPTION>;
+			gpios = <&gpio0 45 GPIO_ACTIVE_LOW>;
+		};
+
+		button@2 {
+			label = "Power-on Switch";
+			linux,code = <KEY_RESERVED>;
+			linux,input-type = <5>;
+			gpios = <&gpio0 46 GPIO_ACTIVE_LOW>;
+		};
+
+		button@3 {
+			label = "Power-auto Switch";
+			linux,code = <KEY_ESC>;
+			linux,input-type = <5>;
+			gpios = <&gpio0 47 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio_leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&pmx_led_function_red &pmx_led_alarm
+			     &pmx_led_info &pmx_led_power
+			     &pmx_led_function_blue
+			     &pmx_led_hdderr0
+			     &pmx_led_hdderr1>;
+		pinctrl-names = "default";
+
+		led@1 {
+			label = "lswvl:red:alarm";
+			gpios = <&gpio0 36 GPIO_ACTIVE_LOW>;
+		};
+
+		led@2 {
+			label = "lswvl:red:func";
+			gpios = <&gpio0 37 GPIO_ACTIVE_LOW>;
+		};
+
+		led@3 {
+			label = "lswvl:amber:info";
+			gpios = <&gpio0 38 GPIO_ACTIVE_LOW>;
+		};
+
+		led@4 {
+			label = "lswvl:blue:func";
+			gpios = <&gpio0 39 GPIO_ACTIVE_LOW>;
+		};
+
+		led@5 {
+			label = "lswvl:blue:power";
+			gpios = <&gpio0 40 GPIO_ACTIVE_LOW>;
+			default-state = "keep";
+		};
+
+		led@6 {
+			label = "lswvl:red:hdderr0";
+			gpios = <&gpio0 34 GPIO_ACTIVE_LOW>;
+		};
+
+		led@7 {
+			label = "lswvl:red:hdderr1";
+			gpios = <&gpio0 35 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio_fan {
+		compatible = "gpio-fan";
+		pinctrl-0 = <&pmx_fan_low &pmx_fan_high &pmx_fan_lock>;
+		pinctrl-names = "default";
+
+		gpios = <&gpio0 17 GPIO_ACTIVE_LOW
+			 &gpio0 16 GPIO_ACTIVE_LOW>;
+
+		gpio-fan,speed-map = <0 3
+				1500 2
+				3250 1
+				5000 0>;
+
+		alarm-gpios = <&gpio0 43 GPIO_ACTIVE_HIGH>;
+	};
+
+	restart_poweroff {
+		compatible = "restart-poweroff";
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_power_hdd0 &pmx_power_hdd1 &pmx_usb_vbus>;
+		pinctrl-names = "default";
+
+		usb_power: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "USB Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 12 GPIO_ACTIVE_HIGH>;
+		};
+		hdd_power0: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "HDD0 Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 8 GPIO_ACTIVE_HIGH>;
+		};
+		hdd_power1: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "HDD1 Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 9 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-lswxl.dts b/arch/arm/boot/dts/kirkwood-lswxl.dts
new file mode 100644
index 000000000000..f5db16a08597
--- /dev/null
+++ b/arch/arm/boot/dts/kirkwood-lswxl.dts
@@ -0,0 +1,301 @@
+/*
+ * Device Tree file for Buffalo Linkstation LS-WXL/WSXL
+ *
+ * Copyright (C) 2015, rogershimizu@gmail.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/dts-v1/;
+
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
+
+/ {
+	model = "Buffalo Linkstation LS-WXL/WSXL";
+	compatible = "buffalo,lswxl", "marvell,kirkwood-88f6281", "marvell,kirkwood";
+
+	memory { /* 128 MB */
+		device_type = "memory";
+		reg = <0x00000000 0x8000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200n8 earlyprintk";
+		stdout-path = &uart0;
+	};
+
+	mbus {
+		pcie-controller {
+			status = "okay";
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
+	ocp@f1000000 {
+		pinctrl: pin-controller@10000 {
+			pmx_power_hdd0: pmx-power-hdd0 {
+				marvell,pins = "mpp28";
+				marvell,function = "gpio";
+			};
+			pmx_power_hdd1: pmx-power-hdd1 {
+				marvell,pins = "mpp29";
+				marvell,function = "gpio";
+			};
+			pmx_usb_vbus: pmx-usb-vbus {
+				marvell,pins = "mpp37";
+				marvell,function = "gpio";
+			};
+			pmx_fan_high: pmx-fan-high {
+				marvell,pins = "mpp47";
+				marvell,function = "gpio";
+			};
+			pmx_fan_low: pmx-fan-low {
+				marvell,pins = "mpp48";
+				marvell,function = "gpio";
+			};
+			pmx_led_hdderr0: pmx-led-hdderr0 {
+				marvell,pins = "mpp8";
+				marvell,function = "gpio";
+			};
+			pmx_led_hdderr1: pmx-led-hdderr1 {
+				marvell,pins = "mpp46";
+				marvell,function = "gpio";
+			};
+			pmx_led_alarm: pmx-led-alarm {
+				marvell,pins = "mpp49";
+				marvell,function = "gpio";
+			};
+			pmx_led_function_red: pmx-led-function-red {
+				marvell,pins = "mpp34";
+				marvell,function = "gpio";
+			};
+			pmx_led_function_blue: pmx-led-function-blue {
+				marvell,pins = "mpp36";
+				marvell,function = "gpio";
+			};
+			pmx_led_info: pmx-led-info {
+				marvell,pins = "mpp38";
+				marvell,function = "gpio";
+			};
+			pmx_led_power: pmx-led-power {
+				marvell,pins = "mpp39";
+				marvell,function = "gpio";
+			};
+			pmx_fan_lock: pmx-fan-lock {
+				marvell,pins = "mpp40";
+				marvell,function = "gpio";
+			};
+			pmx_button_function: pmx-button-function {
+				marvell,pins = "mpp41";
+				marvell,function = "gpio";
+			};
+			pmx_power_switch: pmx-power-switch {
+				marvell,pins = "mpp42";
+				marvell,function = "gpio";
+			};
+			pmx_power_auto_switch: pmx-power-auto-switch {
+				marvell,pins = "mpp43";
+				marvell,function = "gpio";
+			};
+		};
+
+		serial@12000 {
+			status = "okay";
+		};
+
+		sata@80000 {
+			status = "okay";
+			nr-ports = <2>;
+		};
+
+		spi@10600 {
+			status = "okay";
+
+			m25p40@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "st,m25p40", "jedec,spi-nor";
+				reg = <0>;
+				spi-max-frequency = <25000000>;
+				mode = <0>;
+
+				partition@0 {
+					reg = <0x0 0x60000>;
+					label = "uboot";
+					read-only;
+				};
+
+				partition@60000 {
+					reg = <0x60000 0x10000>;
+					label = "dtb";
+					read-only;
+				};
+
+				partition@70000 {
+					reg = <0x70000 0x10000>;
+					label = "uboot_env";
+				};
+			};
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_button_function &pmx_power_switch
+			     &pmx_power_auto_switch>;
+		pinctrl-names = "default";
+
+		button@1 {
+			label = "Function Button";
+			linux,code = <KEY_OPTION>;
+			gpios = <&gpio1 41 GPIO_ACTIVE_LOW>;
+		};
+
+		button@2 {
+			label = "Power-on Switch";
+			linux,code = <KEY_RESERVED>;
+			linux,input-type = <5>;
+			gpios = <&gpio1 42 GPIO_ACTIVE_LOW>;
+		};
+
+		button@3 {
+			label = "Power-auto Switch";
+			linux,code = <KEY_ESC>;
+			linux,input-type = <5>;
+			gpios = <&gpio1 43 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio_leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&pmx_led_function_red &pmx_led_alarm
+			     &pmx_led_info &pmx_led_power
+			     &pmx_led_function_blue
+			     &pmx_led_hdderr0
+			     &pmx_led_hdderr1>;
+		pinctrl-names = "default";
+
+		led@1 {
+			label = "lswxl:blue:func";
+			gpios = <&gpio1 36 GPIO_ACTIVE_LOW>;
+		};
+
+		led@2 {
+			label = "lswxl:red:alarm";
+			gpios = <&gpio1 49 GPIO_ACTIVE_LOW>;
+		};
+
+		led@3 {
+			label = "lswxl:amber:info";
+			gpios = <&gpio1 6 GPIO_ACTIVE_LOW>;
+		};
+
+		led@4 {
+			label = "lswxl:blue:power";
+			gpios = <&gpio1 8 GPIO_ACTIVE_LOW>;
+		};
+
+		led@5 {
+			label = "lswxl:red:func";
+			gpios = <&gpio1 5 GPIO_ACTIVE_LOW>;
+			default-state = "keep";
+		};
+
+		led@6 {
+			label = "lswxl:red:hdderr0";
+			gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;
+		};
+
+		led@7 {
+			label = "lswxl:red:hdderr1";
+			gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio_fan {
+		compatible = "gpio-fan";
+		pinctrl-0 = <&pmx_fan_low &pmx_fan_high &pmx_fan_lock>;
+		pinctrl-names = "default";
+
+		gpios = <&gpio0 47 GPIO_ACTIVE_LOW
+			 &gpio0 48 GPIO_ACTIVE_LOW>;
+
+		gpio-fan,speed-map = <0 3
+				1500 2
+				3250 1
+				5000 0>;
+
+		alarm-gpios = <&gpio1 49 GPIO_ACTIVE_HIGH>;
+	};
+
+	restart_poweroff {
+		compatible = "restart-poweroff";
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_power_hdd0 &pmx_power_hdd1 &pmx_usb_vbus>;
+		pinctrl-names = "default";
+
+		usb_power: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "USB Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 37 GPIO_ACTIVE_HIGH>;
+		};
+		hdd_power0: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "HDD0 Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 28 GPIO_ACTIVE_HIGH>;
+		};
+		hdd_power1: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "HDD1 Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 29 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&mdio {
+	status = "okay";
+
+	ethphy1: ethernet-phy@8 {
+		device_type = "ethernet-phy";
+		reg = <8>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+
+	ethernet1-port@0 {
+		phy-handle = <&ethphy1>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-ns2.dts b/arch/arm/boot/dts/kirkwood-ns2.dts
index 53368d1022cc..190189d235e6 100644
--- a/arch/arm/boot/dts/kirkwood-ns2.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2.dts
@@ -1,5 +1,6 @@
 /dts-v1/;
 
+#include <dt-bindings/leds/leds-ns2.h>
 #include "kirkwood-ns2-common.dtsi"
 
 / {
@@ -27,6 +28,10 @@
 			label = "ns2:blue:sata";
 			slow-gpio = <&gpio0 29 0>;
 			cmd-gpio = <&gpio0 30 0>;
+			modes-map = <NS_V2_LED_OFF  1 0
+				     NS_V2_LED_ON   0 1
+				     NS_V2_LED_ON   1 1
+				     NS_V2_LED_SATA 0 0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood-ns2max.dts b/arch/arm/boot/dts/kirkwood-ns2max.dts
index 72c78d0b1116..55cc41d9c80c 100644
--- a/arch/arm/boot/dts/kirkwood-ns2max.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2max.dts
@@ -1,5 +1,6 @@
 /dts-v1/;
 
+#include <dt-bindings/leds/leds-ns2.h>
 #include "kirkwood-ns2-common.dtsi"
 
 / {
@@ -46,6 +47,10 @@
 			label = "ns2:blue:sata";
 			slow-gpio = <&gpio0 29 0>;
 			cmd-gpio = <&gpio0 30 0>;
+			modes-map = <NS_V2_LED_OFF  1 0
+				     NS_V2_LED_ON   0 1
+				     NS_V2_LED_ON   1 1
+				     NS_V2_LED_SATA 0 0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood-ns2mini.dts b/arch/arm/boot/dts/kirkwood-ns2mini.dts
index c441bf62c09f..9935f3ec29b4 100644
--- a/arch/arm/boot/dts/kirkwood-ns2mini.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2mini.dts
@@ -1,5 +1,6 @@
 /dts-v1/;
 
+#include <dt-bindings/leds/leds-ns2.h>
 #include "kirkwood-ns2-common.dtsi"
 
 / {
@@ -47,6 +48,10 @@
 			label = "ns2:blue:sata";
 			slow-gpio = <&gpio0 29 0>;
 			cmd-gpio = <&gpio0 30 0>;
+			modes-map = <NS_V2_LED_OFF  1 0
+				     NS_V2_LED_ON   0 1
+				     NS_V2_LED_ON   1 1
+				     NS_V2_LED_SATA 0 0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/lpc18xx.dtsi b/arch/arm/boot/dts/lpc18xx.dtsi
index 204da5b52ef9..2c569a6ddc9a 100644
--- a/arch/arm/boot/dts/lpc18xx.dtsi
+++ b/arch/arm/boot/dts/lpc18xx.dtsi
@@ -13,6 +13,12 @@
 
 #include "armv7-m.dtsi"
 
+#include "dt-bindings/clock/lpc18xx-cgu.h"
+#include "dt-bindings/clock/lpc18xx-ccu.h"
+
+#define LPC_PIN(port, pin)	(0x##port * 32 + pin)
+#define LPC_GPIO(port, pin)	(port * 32 + pin)
+
 / {
 	cpus {
 		#address-cells = <1>;
@@ -22,6 +28,7 @@
 			compatible = "arm,cortex-m3";
 			device_type = "cpu";
 			reg = <0x0>;
+			clocks = <&ccu1 CLK_CPU_CORE>;
 		};
 	};
 
@@ -32,32 +39,173 @@
 			clock-frequency = <12000000>;
 		};
 
-		/* Temporary hardcode PLL1 until clk drivers are merged */
-		pll1: pll1 {
-			compatible = "fixed-factor-clock";
-			clocks = <&xtal>;
+		xtal32: xtal32 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+		};
+
+		enet_rx_clk: enet_rx_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+			clock-output-names = "enet_rx_clk";
+		};
+
+		enet_tx_clk: enet_tx_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+			clock-output-names = "enet_tx_clk";
+		};
+
+		gp_clkin: gp_clkin {
+			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-div = <1>;
-			clock-mult = <12>;
+			clock-frequency = <0>;
+			clock-output-names = "gp_clkin";
 		};
 	};
 
 	soc {
+		mmcsd: mmcsd@40004000 {
+			compatible = "snps,dw-mshc";
+			reg = <0x40004000 0x1000>;
+			interrupts = <6>;
+			num-slots = <1>;
+			clocks = <&ccu2 CLK_SDIO>, <&ccu1 CLK_CPU_SDIO>;
+			clock-names = "ciu", "biu";
+			status = "disabled";
+		};
+
+		usb0: ehci@40006100 {
+			compatible = "nxp,lpc1850-ehci", "generic-ehci";
+			reg = <0x40006100 0x100>;
+			interrupts = <8>;
+			clocks = <&ccu1 CLK_CPU_USB0>;
+			phys = <&usb0_otg_phy>;
+			phy-names = "usb";
+			has-transaction-translator;
+			status = "disabled";
+		};
+
+		usb1: ehci@40007100 {
+			compatible = "nxp,lpc1850-ehci", "generic-ehci";
+			reg = <0x40007100 0x100>;
+			interrupts = <9>;
+			clocks = <&ccu1 CLK_CPU_USB1>;
+			status = "disabled";
+		};
+
+		emc: memory-controller@40005000 {
+			compatible = "arm,pl172", "arm,primecell";
+			reg = <0x40005000 0x1000>;
+			clocks = <&ccu1 CLK_CPU_EMCDIV>, <&ccu1 CLK_CPU_EMC>;
+			clock-names = "mpmcclk", "apb_pclk";
+			#address-cells = <2>;
+			#size-cells = <1>;
+			ranges = <0 0 0x1c000000 0x1000000
+				  1 0 0x1d000000 0x1000000
+				  2 0 0x1e000000 0x1000000
+				  3 0 0x1f000000 0x1000000>;
+			status = "disabled";
+		};
+
+		lcdc: lcd-controller@40008000 {
+			compatible = "arm,pl111", "arm,primecell";
+			reg = <0x40008000 0x1000>;
+			interrupts = <7>;
+			interrupt-names = "combined";
+			clocks = <&cgu BASE_LCD_CLK>, <&ccu1 CLK_CPU_LCD>;
+			clock-names = "clcdclk", "apb_pclk";
+			status = "disabled";
+		};
+
+		mac: ethernet@40010000 {
+			compatible = "nxp,lpc1850-dwmac", "snps,dwmac-3.611", "snps,dwmac";
+			reg = <0x40010000 0x2000>;
+			interrupts = <5>;
+			interrupt-names	= "macirq";
+			clocks = <&ccu1 CLK_CPU_ETHERNET>;
+			clock-names = "stmmaceth";
+			status = "disabled";
+		};
+
+		creg: syscon@40043000 {
+			compatible = "nxp,lpc1850-creg", "syscon", "simple-mfd";
+			reg = <0x40043000 0x1000>;
+			clocks = <&ccu1 CLK_CPU_CREG>;
+
+			usb0_otg_phy: phy@004 {
+				compatible = "nxp,lpc1850-usb-otg-phy";
+				clocks = <&ccu1 CLK_USB0>;
+				#phy-cells = <0>;
+			};
+		};
+
+		cgu: clock-controller@40050000 {
+			compatible = "nxp,lpc1850-cgu";
+			reg = <0x40050000 0x1000>;
+			#clock-cells = <1>;
+			clocks = <&xtal>, <&xtal32>, <&enet_rx_clk>, <&enet_tx_clk>, <&gp_clkin>;
+		};
+
+		ccu1: clock-controller@40051000 {
+			compatible = "nxp,lpc1850-ccu";
+			reg = <0x40051000 0x1000>;
+			#clock-cells = <1>;
+			clocks = <&cgu BASE_APB3_CLK>,   <&cgu BASE_APB1_CLK>,
+				 <&cgu BASE_SPIFI_CLK>,  <&cgu BASE_CPU_CLK>,
+				 <&cgu BASE_PERIPH_CLK>, <&cgu BASE_USB0_CLK>,
+				 <&cgu BASE_USB1_CLK>,   <&cgu BASE_SPI_CLK>;
+			clock-names = "base_apb3_clk",   "base_apb1_clk",
+				      "base_spifi_clk",  "base_cpu_clk",
+				      "base_periph_clk", "base_usb0_clk",
+				      "base_usb1_clk",   "base_spi_clk";
+		};
+
+		ccu2: clock-controller@40052000 {
+			compatible = "nxp,lpc1850-ccu";
+			reg = <0x40052000 0x1000>;
+			#clock-cells = <1>;
+			clocks = <&cgu BASE_AUDIO_CLK>, <&cgu BASE_UART3_CLK>,
+				 <&cgu BASE_UART2_CLK>, <&cgu BASE_UART1_CLK>,
+				 <&cgu BASE_UART0_CLK>, <&cgu BASE_SSP1_CLK>,
+				 <&cgu BASE_SSP0_CLK>,  <&cgu BASE_SDIO_CLK>;
+			clock-names = "base_audio_clk", "base_uart3_clk",
+				      "base_uart2_clk", "base_uart1_clk",
+				      "base_uart0_clk", "base_ssp1_clk",
+				      "base_ssp0_clk",  "base_sdio_clk";
+		};
+
 		uart0: serial@40081000 {
-			compatible = "ns16550a";
+			compatible = "nxp,lpc1850-uart", "ns16550a";
 			reg = <0x40081000 0x1000>;
 			reg-shift = <2>;
 			interrupts = <24>;
-			clocks = <&pll1>;
+			clocks = <&ccu2 CLK_APB0_UART0>, <&ccu1 CLK_CPU_UART0>;
+			clock-names = "uartclk", "reg";
 			status = "disabled";
 		};
 
 		uart1: serial@40082000 {
-			compatible = "ns16550a";
+			compatible = "nxp,lpc1850-uart", "ns16550a";
 			reg = <0x40082000 0x1000>;
 			reg-shift = <2>;
 			interrupts = <25>;
-			clocks = <&pll1>;
+			clocks = <&ccu2 CLK_APB0_UART1>, <&ccu1 CLK_CPU_UART1>;
+			clock-names = "uartclk", "reg";
+			status = "disabled";
+		};
+
+		ssp0: spi@40083000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x40083000 0x1000>;
+			interrupts = <22>;
+			clocks = <&ccu2 CLK_APB0_SSP0>, <&ccu1 CLK_CPU_SSP0>;
+			clock-names = "sspclk", "apb_pclk";
+			#address-cells = <1>;
+			#size-cells = <0>;
 			status = "disabled";
 		};
 
@@ -65,7 +213,7 @@
 			compatible = "nxp,lpc3220-timer";
 			reg = <0x40084000 0x1000>;
 			interrupts = <12>;
-			clocks = <&pll1>;
+			clocks = <&ccu1 CLK_CPU_TIMER0>;
 			clock-names = "timerclk";
 		};
 
@@ -73,25 +221,41 @@
 			compatible = "nxp,lpc3220-timer";
 			reg = <0x40085000 0x1000>;
 			interrupts = <13>;
-			clocks = <&pll1>;
+			clocks = <&ccu1 CLK_CPU_TIMER1>;
 			clock-names = "timerclk";
 		};
 
+		pinctrl: pinctrl@40086000 {
+			compatible = "nxp,lpc1850-scu";
+			reg = <0x40086000 0x1000>;
+			clocks = <&ccu1 CLK_CPU_SCU>;
+		};
+
+		can1: can@400a4000 {
+			compatible = "bosch,c_can";
+			reg = <0x400a4000 0x1000>;
+			interrupts = <43>;
+			clocks = <&ccu1 CLK_APB1_CAN1>;
+			status = "disabled";
+		};
+
 		uart2: serial@400c1000 {
-			compatible = "ns16550a";
+			compatible = "nxp,lpc1850-uart", "ns16550a";
 			reg = <0x400c1000 0x1000>;
 			reg-shift = <2>;
 			interrupts = <26>;
-			clocks = <&pll1>;
+			clocks = <&ccu2 CLK_APB2_UART2>, <&ccu1 CLK_CPU_UART2>;
+			clock-names = "uartclk", "reg";
 			status = "disabled";
 		};
 
 		uart3: serial@400c2000 {
-			compatible = "ns16550a";
+			compatible = "nxp,lpc1850-uart", "ns16550a";
 			reg = <0x400c2000 0x1000>;
 			reg-shift = <2>;
 			interrupts = <27>;
-			clocks = <&pll1>;
+			clocks = <&ccu2 CLK_APB2_UART3>, <&ccu1 CLK_CPU_UART3>;
+			clock-names = "uartclk", "reg";
 			status = "disabled";
 		};
 
@@ -99,7 +263,7 @@
 			compatible = "nxp,lpc3220-timer";
 			reg = <0x400c3000 0x1000>;
 			interrupts = <14>;
-			clocks = <&pll1>;
+			clocks = <&ccu1 CLK_CPU_TIMER2>;
 			clock-names = "timerclk";
 		};
 
@@ -107,8 +271,75 @@
 			compatible = "nxp,lpc3220-timer";
 			reg = <0x400c4000 0x1000>;
 			interrupts = <15>;
-			clocks = <&pll1>;
+			clocks = <&ccu1 CLK_CPU_TIMER3>;
 			clock-names = "timerclk";
 		};
+
+		ssp1: spi@400c5000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x400c5000 0x1000>;
+			interrupts = <23>;
+			clocks = <&ccu2 CLK_APB2_SSP1>, <&ccu1 CLK_CPU_SSP1>;
+			clock-names = "sspclk", "apb_pclk";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		can0: can@400e2000 {
+			compatible = "bosch,c_can";
+			reg = <0x400e2000 0x1000>;
+			interrupts = <51>;
+			clocks = <&ccu1 CLK_APB3_CAN0>;
+			status = "disabled";
+		};
+
+		gpio: gpio@400f4000 {
+			compatible = "nxp,lpc1850-gpio";
+			reg = <0x400f4000 0x4000>;
+			clocks = <&ccu1 CLK_CPU_GPIO>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges =	<&pinctrl LPC_GPIO(0,0)  LPC_PIN(0,0)  2>,
+					<&pinctrl LPC_GPIO(0,4)  LPC_PIN(1,0)  1>,
+					<&pinctrl LPC_GPIO(0,8)  LPC_PIN(1,1)  4>,
+					<&pinctrl LPC_GPIO(1,8)  LPC_PIN(1,5)  2>,
+					<&pinctrl LPC_GPIO(1,0)  LPC_PIN(1,7)  8>,
+					<&pinctrl LPC_GPIO(0,2)  LPC_PIN(1,15) 2>,
+					<&pinctrl LPC_GPIO(0,12) LPC_PIN(1,17) 2>,
+					<&pinctrl LPC_GPIO(0,15) LPC_PIN(1,20) 1>,
+					<&pinctrl LPC_GPIO(5,0)  LPC_PIN(2,0)  7>,
+					<&pinctrl LPC_GPIO(0,7)  LPC_PIN(2,7)  1>,
+					<&pinctrl LPC_GPIO(5,7)  LPC_PIN(2,8)  1>,
+					<&pinctrl LPC_GPIO(1,10) LPC_PIN(2,9)  1>,
+					<&pinctrl LPC_GPIO(0,14) LPC_PIN(2,10) 1>,
+					<&pinctrl LPC_GPIO(1,11) LPC_PIN(2,11) 3>,
+					<&pinctrl LPC_GPIO(5,8)  LPC_PIN(3,1)  2>,
+					<&pinctrl LPC_GPIO(1,14) LPC_PIN(3,4)  2>,
+					<&pinctrl LPC_GPIO(0,6)  LPC_PIN(3,6)  1>,
+					<&pinctrl LPC_GPIO(5,10) LPC_PIN(3,7)  2>,
+					<&pinctrl LPC_GPIO(2,0)  LPC_PIN(4,0)  7>,
+					<&pinctrl LPC_GPIO(5,12) LPC_PIN(4,8)  3>,
+					<&pinctrl LPC_GPIO(2,9)  LPC_PIN(5,0)  7>,
+					<&pinctrl LPC_GPIO(2,7)  LPC_PIN(5,7)  1>,
+					<&pinctrl LPC_GPIO(3,0)  LPC_PIN(6,1)  5>,
+					<&pinctrl LPC_GPIO(0,5)  LPC_PIN(6,6)  1>,
+					<&pinctrl LPC_GPIO(5,15) LPC_PIN(6,7)  2>,
+					<&pinctrl LPC_GPIO(3,5)  LPC_PIN(6,9)  3>,
+					<&pinctrl LPC_GPIO(2,8)  LPC_PIN(6,12) 1>,
+					<&pinctrl LPC_GPIO(3,8)  LPC_PIN(7,0)  8>,
+					<&pinctrl LPC_GPIO(4,0)  LPC_PIN(8,0)  8>,
+					<&pinctrl LPC_GPIO(4,12) LPC_PIN(9,0)  4>,
+					<&pinctrl LPC_GPIO(5,17) LPC_PIN(9,4)  2>,
+					<&pinctrl LPC_GPIO(4,11) LPC_PIN(9,6)  1>,
+					<&pinctrl LPC_GPIO(4,8)  LPC_PIN(a,1)  3>,
+					<&pinctrl LPC_GPIO(5,19) LPC_PIN(a,4)  1>,
+					<&pinctrl LPC_GPIO(5,20) LPC_PIN(b,0)  7>,
+					<&pinctrl LPC_GPIO(6,0)  LPC_PIN(c,1) 14>,
+					<&pinctrl LPC_GPIO(6,14) LPC_PIN(d,0) 17>,
+					<&pinctrl LPC_GPIO(7,0)  LPC_PIN(e,0) 16>,
+					<&pinctrl LPC_GPIO(7,16) LPC_PIN(f,1)  3>,
+					<&pinctrl LPC_GPIO(7,19) LPC_PIN(f,5)  7>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/lpc4337-ciaa.dts b/arch/arm/boot/dts/lpc4337-ciaa.dts
new file mode 100644
index 000000000000..5f500c1ad89c
--- /dev/null
+++ b/arch/arm/boot/dts/lpc4337-ciaa.dts
@@ -0,0 +1,187 @@
+/*
+ * CIAA NXP LPC4337 (http://www.proyecto-ciaa.com.ar)
+ *
+ * Copyright (C) 2015 VanguardiaSur - www.vanguardiasur.com.ar
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+/dts-v1/;
+
+#include "lpc18xx.dtsi"
+#include "lpc4357.dtsi"
+
+#include "dt-bindings/gpio/gpio.h"
+
+/ {
+	model = "CIAA NXP LPC4337";
+	compatible = "ciaa,lpc4337", "nxp,lpc4337", "nxp,lpc4350";
+
+	aliases {
+		serial0 = &uart2;
+		serial1 = &uart3;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200 earlyprintk";
+		stdout-path = &uart2;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x28000000 0x0800000>; /* 8 MB */
+	};
+};
+
+&pinctrl {
+	enet_rmii_pins: enet-rmii-pins {
+		enet_rmii_rxd_cfg {
+			pins = "p1_15", "p0_0";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_rmii_txd_cfg {
+			pins = "p1_18", "p1_20";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_rmii_rx_dv_cfg {
+			pins = "p1_16";
+			function = "enet";
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_rmii_tx_en_cfg {
+			pins = "p0_1";
+			function = "enet";
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_ref_clk_cfg {
+			pins = "p1_19";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_mdio_cfg {
+			pins = "p1_17";
+			function = "enet";
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_mdc_cfg {
+			pins = "p7_7";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+	};
+
+	ssp_pins: ssp-pins {
+		ssp1_cs {
+			pins = "p6_7";
+			function = "gpio";
+			bias-pull-up;
+			bias-disable;
+		};
+
+		ssp1_miso_mosi {
+			pins = "p1_3", "p1_4";
+			function = "ssp1";
+			slew-rate = <1>;
+			bias-pull-down;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		ssp1_sck {
+			pins = "pf_4";
+			function = "ssp1";
+			slew-rate = <1>;
+			bias-disable;
+		};
+	};
+
+	uart2_pins: uart2-pins {
+		uart2_rx_cfg {
+			pins = "p7_2";
+			function = "uart2";
+			bias-disable;
+			input-enable;
+		};
+
+		uart2_tx_cfg {
+			pins = "p7_1";
+			function = "uart2";
+			bias-disable;
+		};
+	};
+
+	uart3_pins: uart3-pins {
+		uart3_rx_cfg {
+			pins = "p2_4";
+			function = "uart3";
+			bias-disable;
+			input-enable;
+		};
+
+		uart3_tx_cfg {
+			pins = "p2_3";
+			function = "uart3";
+			bias-disable;
+		};
+	};
+};
+
+&enet_tx_clk {
+	clock-frequency = <50000000>;
+};
+
+&mac {
+	status = "okay";
+	phy-mode = "rmii";
+	pinctrl-names = "default";
+	pinctrl-0 = <&enet_rmii_pins>;
+};
+
+&ssp1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&ssp_pins>;
+	cs-gpios = <&gpio LPC_GPIO(5,15) GPIO_ACTIVE_HIGH>;
+	num-cs = <1>;
+};
+
+&uart2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart2_pins>;
+};
+
+&uart3 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart3_pins>;
+};
diff --git a/arch/arm/boot/dts/lpc4350-hitex-eval.dts b/arch/arm/boot/dts/lpc4350-hitex-eval.dts
index d04072f40817..32bc7ff4eb2a 100644
--- a/arch/arm/boot/dts/lpc4350-hitex-eval.dts
+++ b/arch/arm/boot/dts/lpc4350-hitex-eval.dts
@@ -36,10 +36,250 @@
 	};
 };
 
-&pll1 {
-	clock-mult = <15>;
+&pinctrl {
+	emc_pins: emc-pins {
+		emc_addr0_23_cfg {
+			pins =	"p2_9",  "p2_10", "p2_11", "p2_12",
+				"p2_13", "p1_0",  "p1_1",  "p1_2",
+				"p2_8",  "p2_7",  "p2_6",  "p2_2",
+				"p2_1",  "p2_0",  "p6_8",  "p6_7",
+				"pd_16", "pd_15", "pe_0",  "pe_1",
+				"pe_2",  "pe_3",  "pe_4",  "pa_4";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_data0_15_cfg {
+			pins =	"p1_7",  "p1_8",  "p1_9",  "p1_10",
+				"p1_11", "p1_12", "p1_13", "p1_14",
+				"p5_4",  "p5_5",  "p5_6",  "p5_7",
+				"p5_0",  "p5_1",  "p5_2",  "p5_3";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_we_oe_cfg {
+			pins = "p1_6", "p1_3";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_bls0_3_cfg {
+			pins = "p1_4", "p6_6", "pd_13", "pd_10";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_cs0_cs2_cfg {
+			pins = "p1_5", "pd_12";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_dqm0_3_cfg {
+			pins = "p6_12", "p6_10", "pd_0", "pe_13";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_ras_cas_cfg {
+			pins = "p6_5", "p6_4";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_dycs0_cfg {
+			pins = "p6_9";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_cke_cfg {
+			pins = "p6_11";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_clock_cfg {
+			pins = "clk0", "clk1", "clk2", "clk3";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+	};
+
+	enet_mii_pins: enet-mii-pins {
+		enet_mii_rxd0_3_cfg {
+			pins = "p1_15", "p0_0", "p9_3", "p9_2";
+			function = "enet";
+			bias-disable;
+			input-enable;
+		};
+
+		enet_mii_txd0_3_cfg {
+			pins = "p1_18", "p1_20", "p9_4", "p9_5";
+			function = "enet";
+			bias-disable;
+		};
+
+		enet_mii_crs_col_cfg {
+			pins = "p9_0", "p9_6";
+			function = "enet";
+			bias-disable;
+			input-enable;
+		};
+
+		enet_mii_rx_clk_dv_er_cfg {
+			pins = "pc_0", "p1_16", "p9_1";
+			function = "enet";
+			bias-disable;
+			input-enable;
+		};
+
+		enet_mii_tx_clk_en_cfg {
+			pins = "p1_19", "p0_1";
+			function = "enet";
+			bias-disable;
+			input-enable;
+		};
+
+		enet_mdio_cfg {
+			pins = "p1_17";
+			function = "enet";
+			bias-disable;
+			input-enable;
+		};
+
+		enet_mdc_cfg {
+			pins = "pc_1";
+			function = "enet";
+			bias-disable;
+		};
+	};
+
+	uart0_pins: uart0-pins {
+		uart0_rx_cfg {
+			pins = "pf_11";
+			function = "uart0";
+			input-schmitt-disable;
+			bias-disable;
+			input-enable;
+		};
+
+		uart0_tx_cfg {
+			pins = "pf_10";
+			function = "uart0";
+			bias-pull-down;
+		};
+	};
+};
+
+&emc {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&emc_pins>;
+
+	cs0 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+
+		mpmc,cs = <0>;
+		mpmc,memory-width = <16>;
+		mpmc,byte-lane-low;
+		mpmc,write-enable-delay = <0>;
+		mpmc,output-enable-delay = <0>;
+		mpmc,read-access-delay = <70>;
+		mpmc,page-mode-read-delay = <70>;
+
+		flash@0,0 {
+			compatible = "sst,sst39vf320", "cfi-flash";
+			reg = <0 0 0x400000>;
+			bank-width = <2>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "bootloader";
+				reg = <0x000000 0x040000>; /* 256 KiB */
+			};
+
+			partition@1 {
+				label = "kernel";
+				reg = <0x040000 0x2C0000>; /* 2.75 MiB */
+			};
+
+			partition@2 {
+				label = "rootfs";
+				reg = <0x300000 0x100000>; /* 1 MiB */
+			};
+		};
+	};
+
+	cs2 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+
+		mpmc,cs = <2>;
+		mpmc,memory-width = <16>;
+		mpmc,byte-lane-low;
+		mpmc,write-enable-delay = <0>;
+		mpmc,output-enable-delay = <30>;
+		mpmc,read-access-delay = <90>;
+		mpmc,page-mode-read-delay = <55>;
+		mpmc,write-access-delay = <55>;
+		mpmc,turn-round-delay = <55>;
+
+		ext_sram: sram@2,0 {
+			compatible = "mmio-sram";
+			reg = <2 0 0x80000>; /* 512 KiB SRAM on IS62WV25616 */
+		};
+	};
+};
+
+&enet_tx_clk {
+	clock-frequency = <25000000>;
+};
+
+&mac {
+	status = "okay";
+	phy-mode = "mii";
+	pinctrl-names = "default";
+	pinctrl-0 = <&enet_mii_pins>;
 };
 
 &uart0 {
 	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins>;
 };
diff --git a/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts b/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts
index 08a6f757f924..5f7bdad80963 100644
--- a/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts
+++ b/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts
@@ -15,6 +15,9 @@
 #include "lpc18xx.dtsi"
 #include "lpc4357.dtsi"
 
+#include "dt-bindings/input/input.h"
+#include "dt-bindings/gpio/gpio.h"
+
 / {
 	model = "Embedded Artists' LPC4357 Developer's Kit";
 	compatible = "ea,lpc4357-developers-kit", "nxp,lpc4357", "nxp,lpc4350";
@@ -34,8 +37,472 @@
 		device_type = "memory";
 		reg = <0x28000000 0x2000000>; /* 32 MB */
 	};
+
+	/* vmmc is controlled by sdmmc host internally */
+	vmmc: vmmc_fixed {
+		compatible = "regulator-fixed";
+		regulator-name = "vmmc-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	gpio_joystick {
+		compatible = "gpio-keys-polled";
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio_joystick_pins>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		poll-interval = <100>;
+		autorepeat;
+
+		button@0 {
+			label = "joy_enter";
+			linux,code = <KEY_ENTER>;
+			gpios = <&gpio LPC_GPIO(4,8) GPIO_ACTIVE_LOW>;
+		};
+
+		button@1 {
+			label = "joy_left";
+			linux,code = <KEY_LEFT>;
+			gpios = <&gpio LPC_GPIO(4,9) GPIO_ACTIVE_LOW>;
+		};
+
+		button@2 {
+			label = "joy_up";
+			linux,code = <KEY_UP>;
+			gpios = <&gpio LPC_GPIO(4,10) GPIO_ACTIVE_LOW>;
+		};
+
+		button@3 {
+			label = "joy_right";
+			linux,code = <KEY_RIGHT>;
+			gpios = <&gpio LPC_GPIO(4,12) GPIO_ACTIVE_LOW>;
+		};
+
+		button@4 {
+			label = "joy_down";
+			linux,code = <KEY_DOWN>;
+			gpios = <&gpio LPC_GPIO(4,13) GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	leds_mmio {
+		compatible = "gpio-leds";
+
+		led1 {
+			gpios = <&mmio_leds 15 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+
+		led2 {
+			gpios = <&mmio_leds 14 GPIO_ACTIVE_HIGH>;
+		};
+
+		led3 {
+			gpios = <&mmio_leds 13 GPIO_ACTIVE_HIGH>;
+		};
+
+		led4 {
+			gpios = <&mmio_leds 12 GPIO_ACTIVE_HIGH>;
+		};
+
+		led5 {
+			gpios = <&mmio_leds 11 GPIO_ACTIVE_HIGH>;
+		};
+
+		led6 {
+			gpios = <&mmio_leds 10 GPIO_ACTIVE_HIGH>;
+		};
+
+		led7 {
+			gpios = <&mmio_leds 9 GPIO_ACTIVE_HIGH>;
+		};
+
+		led8 {
+			gpios = <&mmio_leds 8 GPIO_ACTIVE_HIGH>;
+		};
+
+		led9 {
+			gpios = <&mmio_leds 7 GPIO_ACTIVE_HIGH>;
+		};
+
+		led10 {
+			gpios = <&mmio_leds 6 GPIO_ACTIVE_HIGH>;
+		};
+
+		led11 {
+			gpios = <&mmio_leds 5 GPIO_ACTIVE_HIGH>;
+		};
+
+		led12 {
+			gpios = <&mmio_leds 4 GPIO_ACTIVE_HIGH>;
+		};
+
+		led13 {
+			gpios = <&mmio_leds 3 GPIO_ACTIVE_HIGH>;
+		};
+
+		led14 {
+			gpios = <&mmio_leds 2 GPIO_ACTIVE_HIGH>;
+		};
+
+		led15 {
+			gpios = <&mmio_leds 1 GPIO_ACTIVE_HIGH>;
+		};
+
+		led16 {
+			gpios = <&mmio_leds 0 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&pinctrl {
+	emc_pins: emc-pins {
+		emc_addr0_23_cfg {
+			pins =	"p2_9",  "p2_10", "p2_11", "p2_12",
+				"p2_13", "p1_0",  "p1_1",  "p1_2",
+				"p2_8",  "p2_7",  "p2_6",  "p2_2",
+				"p2_1",  "p2_0",  "p6_8",  "p6_7",
+				"pd_16", "pd_15", "pe_0",  "pe_1",
+				"pe_2",  "pe_3",  "pe_4",  "pa_4";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_data0_31_cfg {
+			pins =	"p1_7",  "p1_8",  "p1_9",  "p1_10",
+				"p1_11", "p1_12", "p1_13", "p1_14",
+				"p5_4",  "p5_5",  "p5_6",  "p5_7",
+				"p5_0",  "p5_1",  "p5_2",  "p5_3",
+				"pd_2",  "pd_3",  "pd_4",  "pd_5",
+				"pd_6",  "pd_7",  "pd_8",  "pd_9",
+				"pe_5",  "pe_6",  "pe_7",  "pe_8",
+				"pe_9",  "pe_10", "pe_11", "pe_12";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_we_oe_cfg {
+			pins = "p1_6", "p1_3";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_bls0_3_cfg {
+			pins = "p1_4", "p6_6", "pd_13", "pd_10";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_cs0_3_cfg {
+			pins = "p1_5", "p6_3", "pd_12", "pd_11";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_dqm0_3_cfg {
+			pins = "p6_12", "p6_10", "pd_0", "pe_13";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_ras_cas_cfg {
+			pins = "p6_5", "p6_4";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_dycs0_cfg {
+			pins = "p6_9";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_cke_cfg {
+			pins = "p6_11";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		emc_sdram_clock_cfg {
+			pins = "clk0", "clk1", "clk2", "clk3";
+			function = "emc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+	};
+
+	enet_rmii_pins: enet-rmii-pins {
+		enet_rmii_rxd_cfg {
+			pins = "p1_15", "p0_0";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_rmii_txd_cfg {
+			pins = "p1_18", "p1_20";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_rmii_rx_dv_cfg {
+			pins = "p1_16";
+			function = "enet";
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_rmii_tx_en_cfg {
+			pins = "p0_1";
+			function = "enet";
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_ref_clk_cfg {
+			pins = "p1_19";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_mdio_cfg {
+			pins = "p1_17";
+			function = "enet";
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		enet_mdc_cfg {
+			pins = "pc_1";
+			function = "enet";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+	};
+
+	gpio_joystick_pins: gpio-joystick-pins {
+		gpio_joystick_cfg {
+			pins =	"p9_0", "p9_1", "pa_1", "pa_2", "pa_3";
+			function = "gpio";
+			input-enable;
+			bias-disable;
+		};
+	};
+
+	sdmmc_pins: sdmmc-pins {
+		sdmmc_clk_cfg {
+			pins = "pc_0";
+			function = "sdmmc";
+			slew-rate = <1>;
+			bias-pull-down;
+		};
+
+		sdmmc_cmd_dat0_3_cfg {
+			pins = "pc_4", "pc_5", "pc_6", "pc_7", "pc_10";
+			function = "sdmmc";
+			slew-rate = <1>;
+			bias-disable;
+			input-enable;
+			input-schmitt-disable;
+		};
+
+		sdmmc_cd_cfg {
+			pins = "pc_8";
+			function = "sdmmc";
+			bias-pull-down;
+			input-enable;
+		};
+
+		sdmmc_pow_cfg {
+			pins = "pc_9";
+			function = "sdmmc";
+			bias-pull-down;
+		};
+	};
+
+	uart0_pins: uart0-pins {
+		uart0_rx_cfg {
+			pins = "pf_11";
+			function = "uart0";
+			input-schmitt-disable;
+			bias-disable;
+			input-enable;
+		};
+
+		uart0_tx_cfg {
+			pins = "pf_10";
+			function = "uart0";
+			bias-pull-down;
+		};
+	};
+
+	uart3_pins: uart3-pins {
+		uart3_rx_cfg {
+			pins = "p2_4";
+			function = "uart3";
+			input-schmitt-disable;
+			bias-disable;
+			input-enable;
+		};
+
+		uart3_tx_cfg {
+			pins = "p9_3";
+			function = "uart3";
+			bias-pull-down;
+		};
+	};
+
+	usb0_pins: usb0-pins {
+		usb0_pwr_enable {
+			pins = "p2_3";
+			function = "usb0";
+		};
+
+		usb0_pwr_fault {
+			pins = "p8_0";
+			function = "usb0";
+			bias-disable;
+			input-enable;
+		};
+	};
+};
+
+&emc {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&emc_pins>;
+
+	cs0 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+
+		mpmc,cs = <0>;
+		mpmc,memory-width = <16>;
+		mpmc,byte-lane-low;
+		mpmc,write-enable-delay = <0>;
+		mpmc,output-enable-delay = <0>;
+		mpmc,read-access-delay = <70>;
+		mpmc,page-mode-read-delay = <70>;
+
+		flash@0,0 {
+			compatible = "sst,sst39vf320", "cfi-flash";
+			reg = <0 0 0x400000>;
+			bank-width = <2>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "bootloader";
+				reg = <0x000000 0x040000>; /* 256 KiB */
+			};
+
+			partition@1 {
+				label = "kernel";
+				reg = <0x040000 0x2c0000>; /* 2.75 MiB */
+			};
+
+			partition@2 {
+				label = "rootfs";
+				reg = <0x300000 0x100000>; /* 1 MiB */
+			};
+		};
+	};
+
+	cs2 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+
+		mpmc,cs = <2>;
+		mpmc,memory-width = <16>;
+
+		mmio_leds: gpio@2,0 {
+			compatible = "ti,7416374";
+			reg = <2 0 0x2>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+
+	};
+};
+
+&enet_tx_clk {
+	clock-frequency = <50000000>;
+};
+
+&mac {
+	status = "okay";
+	phy-mode = "rmii";
+	pinctrl-names = "default";
+	pinctrl-0 = <&enet_rmii_pins>;
+};
+
+&mmcsd {
+	status = "okay";
+	bus-width = <4>;
+	vmmc-supply = <&vmmc>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_pins>;
 };
 
 &uart0 {
 	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins>;
+};
+
+&uart3 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart3_pins>;
+};
+
+&usb0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_pins>;
 };
diff --git a/arch/arm/boot/dts/ls1021a-qds.dts b/arch/arm/boot/dts/ls1021a-qds.dts
index 9c5e16ba8c95..0521e6864cb7 100644
--- a/arch/arm/boot/dts/ls1021a-qds.dts
+++ b/arch/arm/boot/dts/ls1021a-qds.dts
@@ -58,6 +58,55 @@
 		enet0_sgmii_phy = &sgmii_phy1c;
 		enet1_sgmii_phy = &sgmii_phy1d;
 	};
+
+	sys_mclk: clock-mclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24576000>;
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reg_3p3v: regulator@0 {
+			compatible = "regulator-fixed";
+			reg = <0>;
+			regulator-name = "3P3V";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+	};
+
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,widgets =
+			"Microphone", "Microphone Jack",
+			"Headphone", "Headphone Jack",
+			"Speaker", "Speaker Ext",
+			"Line", "Line In Jack";
+		simple-audio-card,routing =
+			"MIC_IN", "Microphone Jack",
+			"Microphone Jack", "Mic Bias",
+			"LINE_IN", "Line In Jack",
+			"Headphone Jack", "HP_OUT",
+			"Speaker Ext", "LINE_OUT";
+
+		simple-audio-card,cpu {
+			sound-dai = <&sai2>;
+			frame-master;
+			bitclock-master;
+		};
+
+		simple-audio-card,codec {
+			sound-dai = <&codec>;
+			frame-master;
+			bitclock-master;
+		};
+	};
 };
 
 &dspi0 {
@@ -75,10 +124,31 @@
 	};
 };
 
+&enet0 {
+	tbi-handle = <&tbi0>;
+	phy-handle = <&sgmii_phy1c>;
+	phy-connection-type = "sgmii";
+	status = "okay";
+};
+
+&enet1 {
+	tbi-handle = <&tbi0>;
+	phy-handle = <&sgmii_phy1d>;
+	phy-connection-type = "sgmii";
+	status = "okay";
+};
+
+&enet2 {
+	phy-handle = <&rgmii_phy3>;
+	phy-connection-type = "rgmii-id";
+	status = "okay";
+};
+
 &i2c0 {
 	status = "okay";
 
 	pca9547: mux@77 {
+		compatible = "nxp,pca9547";
 		reg = <0x77>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -133,6 +203,21 @@
 				reg = <0x4c>;
 			};
 		};
+
+		i2c@4 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x4>;
+
+			codec: sgtl5000@2a {
+				#sound-dai-cells = <0>;
+				compatible = "fsl,sgtl5000";
+				reg = <0x2a>;
+				VDDA-supply = <&reg_3p3v>;
+				VDDIO-supply = <&reg_3p3v>;
+				clocks = <&sys_mclk 1>;
+			};
+		};
 	};
 };
 
@@ -231,6 +316,10 @@
 	};
 };
 
+&sai2 {
+	status = "okay";
+};
+
 &uart0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/ls1021a-twr.dts b/arch/arm/boot/dts/ls1021a-twr.dts
index a2c591e2d918..e008f9367510 100644
--- a/arch/arm/boot/dts/ls1021a-twr.dts
+++ b/arch/arm/boot/dts/ls1021a-twr.dts
@@ -56,6 +56,55 @@
 		enet0_sgmii_phy = &sgmii_phy2;
 		enet1_sgmii_phy = &sgmii_phy0;
 	};
+
+	sys_mclk: clock-mclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24576000>;
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reg_3p3v: regulator@0 {
+			compatible = "regulator-fixed";
+			reg = <0>;
+			regulator-name = "3P3V";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+	};
+
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,widgets =
+			"Microphone", "Microphone Jack",
+			"Headphone", "Headphone Jack",
+			"Speaker", "Speaker Ext",
+			"Line", "Line In Jack";
+		simple-audio-card,routing =
+			"MIC_IN", "Microphone Jack",
+			"Microphone Jack", "Mic Bias",
+			"LINE_IN", "Line In Jack",
+			"Headphone Jack", "HP_OUT",
+			"Speaker Ext", "LINE_OUT";
+
+		simple-audio-card,cpu {
+			sound-dai = <&sai1>;
+			frame-master;
+			bitclock-master;
+		};
+
+		simple-audio-card,codec {
+			sound-dai = <&codec>;
+			frame-master;
+			bitclock-master;
+		};
+	};
 };
 
 &dspi1 {
@@ -73,12 +122,40 @@
 	};
 };
 
+&enet0 {
+	tbi-handle = <&tbi1>;
+	phy-handle = <&sgmii_phy2>;
+	phy-connection-type = "sgmii";
+	status = "okay";
+};
+
+&enet1 {
+	tbi-handle = <&tbi1>;
+	phy-handle = <&sgmii_phy0>;
+	phy-connection-type = "sgmii";
+	status = "okay";
+};
+
+&enet2 {
+	phy-handle = <&rgmii_phy1>;
+	phy-connection-type = "rgmii-id";
+	status = "okay";
+};
+
 &i2c0 {
 	status = "okay";
 };
 
 &i2c1 {
 	status = "okay";
+	codec: sgtl5000@a {
+		#sound-dai-cells = <0>;
+		compatible = "fsl,sgtl5000";
+		reg = <0x0a>;
+		VDDA-supply = <&reg_3p3v>;
+		VDDIO-supply = <&reg_3p3v>;
+		clocks = <&sys_mclk 1>;
+	};
 };
 
 &ifc {
@@ -118,6 +195,10 @@
 	};
 };
 
+&sai1 {
+	status = "okay";
+};
+
 &uart0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index c70bb27ac65a..973a496207fc 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -53,6 +53,9 @@
 	interrupt-parent = <&gic>;
 
 	aliases {
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
+		ethernet2 = &enet2;
 		serial0 = &lpuart0;
 		serial1 = &lpuart1;
 		serial2 = &lpuart2;
@@ -184,7 +187,7 @@
 		};
 
 		dspi0: dspi@2100000 {
-			compatible = "fsl,vf610-dspi";
+			compatible = "fsl,ls1021a-v1.0-dspi";
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x2100000 0x0 0x10000>;
@@ -197,7 +200,7 @@
 		};
 
 		dspi1: dspi@2110000 {
-			compatible = "fsl,vf610-dspi";
+			compatible = "fsl,ls1021a-v1.0-dspi";
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x2110000 0x0 0x10000>;
@@ -342,28 +345,30 @@
 		};
 
 		sai1: sai@2b50000 {
+			#sound-dai-cells = <0>;
 			compatible = "fsl,vf610-sai";
 			reg = <0x0 0x2b50000 0x0 0x10000>;
 			interrupts = <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&platform_clk 1>;
-			clock-names = "sai";
+			clocks = <&platform_clk 1>, <&platform_clk 1>,
+				 <&platform_clk 1>, <&platform_clk 1>;
+			clock-names = "bus", "mclk1", "mclk2", "mclk3";
 			dma-names = "tx", "rx";
 			dmas = <&edma0 1 47>,
 			       <&edma0 1 46>;
-			big-endian;
 			status = "disabled";
 		};
 
 		sai2: sai@2b60000 {
+			#sound-dai-cells = <0>;
 			compatible = "fsl,vf610-sai";
 			reg = <0x0 0x2b60000 0x0 0x10000>;
 			interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&platform_clk 1>;
-			clock-names = "sai";
+			clocks = <&platform_clk 1>, <&platform_clk 1>,
+				 <&platform_clk 1>, <&platform_clk 1>;
+			clock-names = "bus", "mclk1", "mclk2", "mclk3";
 			dma-names = "tx", "rx";
 			dmas = <&edma0 1 45>,
 			       <&edma0 1 44>;
-			big-endian;
 			status = "disabled";
 		};
 
@@ -391,6 +396,91 @@
 			reg = <0x0 0x2d24000 0x0 0x4000>;
 		};
 
+		enet0: ethernet@2d10000 {
+			compatible = "fsl,etsec2";
+			device_type = "network";
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupt-parent = <&gic>;
+			model = "eTSEC";
+			fsl,magic-packet;
+			ranges;
+
+			queue-group@2d10000 {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				reg = <0x0 0x2d10000 0x0 0x1000>;
+				interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			queue-group@2d14000  {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				reg = <0x0 0x2d14000 0x0 0x1000>;
+				interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
+		enet1: ethernet@2d50000 {
+			compatible = "fsl,etsec2";
+			device_type = "network";
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupt-parent = <&gic>;
+			model = "eTSEC";
+			ranges;
+
+			queue-group@2d50000  {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				reg = <0x0 0x2d50000 0x0 0x1000>;
+				interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			queue-group@2d54000  {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				reg = <0x0 0x2d54000 0x0 0x1000>;
+				interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
+		enet2: ethernet@2d90000 {
+			compatible = "fsl,etsec2";
+			device_type = "network";
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupt-parent = <&gic>;
+			model = "eTSEC";
+			ranges;
+
+			queue-group@2d90000  {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				reg = <0x0 0x2d90000 0x0 0x1000>;
+				interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			queue-group@2d94000  {
+				#address-cells = <2>;
+				#size-cells = <2>;
+				reg = <0x0 0x2d94000 0x0 0x1000>;
+				interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
 		usb@8600000 {
 			compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
 			reg = <0x0 0x8600000 0x0 0x1000>;
diff --git a/arch/arm/boot/dts/mt6580-evbp1.dts b/arch/arm/boot/dts/mt6580-evbp1.dts
new file mode 100644
index 000000000000..17daeae6bbe8
--- /dev/null
+++ b/arch/arm/boot/dts/mt6580-evbp1.dts
@@ -0,0 +1,38 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Mars.C <mars.cheng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/dts-v1/;
+#include "mt6580.dtsi"
+
+/ {
+	model = "MediaTek MT6580 evaluation board";
+	compatible = "mediatek,mt6580-evbp1", "mediatek,mt6580";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
+	chosen {
+		stdout-path = "serial0:921600n8";
+	};
+
+	memory {
+		reg = <0x80000000 0x20000000>;
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/mt6580.dtsi b/arch/arm/boot/dts/mt6580.dtsi
new file mode 100644
index 000000000000..06fdf6c2d5fd
--- /dev/null
+++ b/arch/arm/boot/dts/mt6580.dtsi
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Mars.C <mars.cheng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include "skeleton.dtsi"
+
+/ {
+	compatible = "mediatek,mt6580";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&sysirq>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x0>;
+		};
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x1>;
+		};
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x2>;
+		};
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x3>;
+		};
+
+	};
+
+	system_clk: dummy13m {
+		compatible = "fixed-clock";
+		clock-frequency = <13000000>;
+		#clock-cells = <0>;
+	};
+
+	rtc_clk: dummy32k {
+		compatible = "fixed-clock";
+		clock-frequency = <32000>;
+		#clock-cells = <0>;
+	};
+
+	uart_clk: dummy26m {
+		compatible = "fixed-clock";
+		clock-frequency = <26000000>;
+		#clock-cells = <0>;
+	};
+
+	timer: timer@10008000 {
+		compatible = "mediatek,mt6580-timer",
+			     "mediatek,mt6577-timer";
+		reg = <0x10008000 0x80>;
+		interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&system_clk>, <&rtc_clk>;
+		clock-names = "system-clk", "rtc-clk";
+	};
+
+	sysirq: interrupt-controller@10200100 {
+		compatible = "mediatek,mt6580-sysirq",
+			     "mediatek,mt6577-sysirq";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		interrupt-parent = <&gic>;
+		reg = <0x10200100 0x1c>;
+	};
+
+	gic: interrupt-controller@10211000 {
+		compatible = "arm,cortex-a7-gic";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		interrupt-parent = <&gic>;
+		reg = <0x10211000 0x1000>,
+		      <0x10212000 0x1000>,
+		      <0x10214000 0x2000>,
+		      <0x10216000 0x2000>;
+	};
+
+	uart0: serial@11005000 {
+		compatible = "mediatek,mt6580-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0x11005000 0x400>;
+		interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+
+	uart1: serial@11006000 {
+		compatible = "mediatek,mt6580-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0x11006000 0x400>;
+		interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+};
diff --git a/arch/arm/boot/dts/mt8135-evbp1.dts b/arch/arm/boot/dts/mt8135-evbp1.dts
index 36677382bdd8..357a91fc2d1d 100644
--- a/arch/arm/boot/dts/mt8135-evbp1.dts
+++ b/arch/arm/boot/dts/mt8135-evbp1.dts
@@ -24,6 +24,199 @@
 	};
 };
 
+&pwrap {
+	pmic: mt6397 {
+		compatible = "mediatek,mt6397";
+
+		mt6397regulator: mt6397regulator {
+			compatible = "mediatek,mt6397-regulator";
+
+			mt6397_vpca15_reg: buck_vpca15 {
+				regulator-compatible = "buck_vpca15";
+				regulator-name = "vpca15";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vpca7_reg: buck_vpca7 {
+				regulator-compatible = "buck_vpca7";
+				regulator-name = "vpca7";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vsramca15_reg: buck_vsramca15 {
+				regulator-compatible = "buck_vsramca15";
+				regulator-name = "vsramca15";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vsramca7_reg: buck_vsramca7 {
+				regulator-compatible = "buck_vsramca7";
+				regulator-name = "vsramca7";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vcore_reg: buck_vcore {
+				regulator-compatible = "buck_vcore";
+				regulator-name = "vcore";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vgpu_reg: buck_vgpu {
+				regulator-compatible = "buck_vgpu";
+				regulator-name = "vgpu";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+			};
+
+			mt6397_vdrm_reg: buck_vdrm {
+				regulator-compatible = "buck_vdrm";
+				regulator-name = "vdrm";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vio18_reg: buck_vio18 {
+				regulator-compatible = "buck_vio18";
+				regulator-name = "vio18";
+				regulator-min-microvolt = <1620000>;
+				regulator-max-microvolt = <1980000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vtcxo_reg: ldo_vtcxo {
+				regulator-compatible = "ldo_vtcxo";
+				regulator-name = "vtcxo";
+				regulator-always-on;
+			};
+
+			mt6397_va28_reg: ldo_va28 {
+				regulator-compatible = "ldo_va28";
+				regulator-name = "va28";
+				regulator-always-on;
+			};
+
+			mt6397_vcama_reg: ldo_vcama {
+				regulator-compatible = "ldo_vcama";
+				regulator-name = "vcama";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vio28_reg: ldo_vio28 {
+				regulator-compatible = "ldo_vio28";
+				regulator-name = "vio28";
+				regulator-always-on;
+			};
+
+			mt6397_vusb_reg: ldo_vusb {
+				regulator-compatible = "ldo_vusb";
+				regulator-name = "vusb";
+			};
+
+			mt6397_vmc_reg: ldo_vmc {
+				regulator-compatible = "ldo_vmc";
+				regulator-name = "vmc";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vmch_reg: ldo_vmch {
+				regulator-compatible = "ldo_vmch";
+				regulator-name = "vmch";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vemc_3v3_reg: ldo_vemc3v3 {
+				regulator-compatible = "ldo_vemc3v3";
+				regulator-name = "vemc_3v3";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp1_reg: ldo_vgp1 {
+				regulator-compatible = "ldo_vgp1";
+				regulator-name = "vcamd";
+				regulator-min-microvolt = <1220000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <240>;
+			};
+
+			mt6397_vgp2_reg: ldo_vgp2 {
+				regulator-compatible = "ldo_vgp2";
+				regulator-name = "vcamio";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp3_reg: ldo_vgp3 {
+				regulator-compatible = "ldo_vgp3";
+				regulator-name = "vcamaf";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp4_reg: ldo_vgp4 {
+				regulator-compatible = "ldo_vgp4";
+				regulator-name = "vgp4";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp5_reg: ldo_vgp5 {
+				regulator-compatible = "ldo_vgp5";
+				regulator-name = "vgp5";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp6_reg: ldo_vgp6 {
+				regulator-compatible = "ldo_vgp6";
+				regulator-name = "vgp6";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vibr_reg: ldo_vibr {
+				regulator-compatible = "ldo_vibr";
+				regulator-name = "vibr";
+				regulator-min-microvolt = <1300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+		};
+	};
+};
+
 &uart3 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/mt8135.dtsi b/arch/arm/boot/dts/mt8135.dtsi
index 0aba9eb28e2b..08371dbae543 100644
--- a/arch/arm/boot/dts/mt8135.dtsi
+++ b/arch/arm/boot/dts/mt8135.dtsi
@@ -12,8 +12,10 @@
  * GNU General Public License for more details.
  */
 
+#include <dt-bindings/clock/mt8135-clk.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/reset-controller/mt8135-resets.h>
 #include "skeleton64.dtsi"
 #include "mt8135-pinfunc.h"
 
@@ -88,12 +90,11 @@
 			#clock-cells = <0>;
 		};
 
-		uart_clk: dummy26m {
+		clk26m: clk26m {
 			compatible = "fixed-clock";
-			clock-frequency = <26000000>;
 			#clock-cells = <0>;
+			clock-frequency = <26000000>;
 		};
-
 	};
 
 	soc {
@@ -102,6 +103,26 @@
 		compatible = "simple-bus";
 		ranges;
 
+		topckgen: topckgen@10000000 {
+			compatible = "mediatek,mt8135-topckgen";
+			reg = <0 0x10000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		infracfg: infracfg@10001000 {
+			#reset-cells = <1>;
+			#clock-cells = <1>;
+			compatible = "mediatek,mt8135-infracfg", "syscon";
+			reg = <0 0x10001000 0 0x1000>;
+		};
+
+		pericfg: pericfg@10003000 {
+			#reset-cells = <1>;
+			#clock-cells = <1>;
+			compatible = "mediatek,mt8135-pericfg", "syscon";
+			reg = <0 0x10003000 0 0x1000>;
+		};
+
 		/*
 		 * Pinctrl access register at 0x10005000 and 0x1020c000 through
 		 * regmap. Register 0x1000b000 is used by EINT.
@@ -134,6 +155,19 @@
 			clock-names = "system-clk", "rtc-clk";
 		};
 
+		pwrap: pwrap@1000f000 {
+			compatible = "mediatek,mt8135-pwrap";
+			reg = <0 0x1000f000 0 0x1000>,
+				<0 0x11017000 0 0x1000>;
+			reg-names = "pwrap", "pwrap-bridge";
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>;
+			resets = <&infracfg MT8135_INFRA_PMIC_WRAP_RST>,
+					<&pericfg MT8135_PERI_PWRAP_BRIDGE_SW_RST>;
+			reset-names = "pwrap", "pwrap-bridge";
+			clocks = <&clk26m>, <&clk26m>;
+			clock-names = "spi", "wrap";
+		};
+
 		sysirq: interrupt-controller@10200030 {
 			compatible = "mediatek,mt8135-sysirq",
 				     "mediatek,mt6577-sysirq";
@@ -143,6 +177,12 @@
 			reg = <0 0x10200030 0 0x1c>;
 		};
 
+		apmixedsys: apmixedsys@10209000 {
+			compatible = "mediatek,mt8135-apmixedsys";
+			reg = <0 0x10209000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
 		syscfg_pctl_b: syscfg_pctl_b@1020c000 {
 			compatible = "mediatek,mt8135-pctl-b-syscfg", "syscon";
 			reg = <0 0x1020c000 0 0x1000>;
@@ -163,7 +203,8 @@
 			compatible = "mediatek,mt8135-uart","mediatek,mt6577-uart";
 			reg = <0 0x11006000 0 0x400>;
 			interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART0_SEL>, <&pericfg CLK_PERI_UART0>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
@@ -171,7 +212,8 @@
 			compatible = "mediatek,mt8135-uart","mediatek,mt6577-uart";
 			reg = <0 0x11007000 0 0x400>;
 			interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART1_SEL>, <&pericfg CLK_PERI_UART1>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
@@ -179,7 +221,8 @@
 			compatible = "mediatek,mt8135-uart","mediatek,mt6577-uart";
 			reg = <0 0x11008000 0 0x400>;
 			interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART2_SEL>, <&pericfg CLK_PERI_UART2>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
@@ -187,7 +230,8 @@
 			compatible = "mediatek,mt8135-uart","mediatek,mt6577-uart";
 			reg = <0 0x11009000 0 0x400>;
 			interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART3_SEL>, <&pericfg CLK_PERI_UART3>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/omap2430.dtsi b/arch/arm/boot/dts/omap2430.dtsi
index 11a7963be003..2390f387c271 100644
--- a/arch/arm/boot/dts/omap2430.dtsi
+++ b/arch/arm/boot/dts/omap2430.dtsi
@@ -51,7 +51,8 @@
 				};
 
 				scm_conf: scm_conf@270 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x270 0x240>;
 					#address-cells = <1>;
 					#size-cells = <1>;
diff --git a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi
new file mode 100644
index 000000000000..9ca2865a83d6
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi
@@ -0,0 +1,369 @@
+/*
+ * Author: Anil Kumar <anilk4.v@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <dt-bindings/input/input.h>
+
+#include "omap34xx.dtsi"
+/ {
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>;	/* 256 MB */
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		heartbeat {
+			label = "devkit8000::led1";
+			gpios = <&gpio6 26 GPIO_ACTIVE_HIGH>;	/* 186 -> LED1 */
+			default-state = "on";
+			linux,default-trigger = "heartbeat";
+		};
+
+		mmc {
+			label = "devkit8000::led2";
+			gpios = <&gpio6 3 GPIO_ACTIVE_HIGH>;	/* 163 -> LED2 */
+			default-state = "on";
+			linux,default-trigger = "none";
+		};
+
+		usr {
+			label = "devkit8000::led3";
+			gpios = <&gpio6 4 GPIO_ACTIVE_HIGH>;	/* 164 -> LED3 */
+			default-state = "on";
+			linux,default-trigger = "usr";
+		};
+
+		pmu_stat {
+			label = "devkit8000::pmu_stat";
+			gpios = <&twl_gpio 19 GPIO_ACTIVE_HIGH>; /* LEDB */
+		};
+	};
+
+	sound {
+		compatible = "ti,omap-twl4030";
+		ti,model = "devkit8000";
+
+		ti,mcbsp = <&mcbsp2>;
+		ti,audio-routing =
+			"Ext Spk", "PREDRIVEL",
+			"Ext Spk", "PREDRIVER",
+			"MAINMIC", "Main Mic",
+			"Main Mic", "Mic Bias 1";
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		user {
+			label = "user";
+			gpios = <&gpio1 26 GPIO_ACTIVE_HIGH>;
+			linux,code = <BTN_EXTRA>;
+			gpio-key,wakeup;
+		};
+	};
+
+	tfp410: encoder@0 {
+		compatible = "ti,tfp410";
+		powerdown-gpios = <&twl_gpio 7 GPIO_ACTIVE_LOW>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				tfp410_in: endpoint@0 {
+					remote-endpoint = <&dpi_dvi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				tfp410_out: endpoint@0 {
+					remote-endpoint = <&dvi_connector_in>;
+				};
+			};
+		};
+	};
+
+	dvi0: connector@0 {
+		compatible = "dvi-connector";
+		label = "dvi";
+
+		digital;
+
+		ddc-i2c-bus = <&i2c2>;
+
+		port {
+			dvi_connector_in: endpoint {
+				remote-endpoint = <&tfp410_out>;
+			};
+		};
+	};
+
+	tv0: connector@1 {
+		compatible = "svideo-connector";
+		label = "tv";
+
+		port {
+			tv_connector_in: endpoint {
+				remote-endpoint = <&venc_out>;
+			};
+		};
+	};
+};
+
+&i2c1 {
+	clock-frequency = <2600000>;
+
+	twl: twl@48 {
+		reg = <0x48>;
+		interrupts = <7>;	/* SYS_NIRQ cascaded to intc */
+
+		twl_audio: audio {
+			compatible = "ti,twl4030-audio";
+			codec {
+			};
+		};
+	};
+};
+
+&i2c2 {
+	clock-frequency = <400000>;
+};
+
+&i2c3 {
+	status = "disabled";
+};
+
+#include "twl4030.dtsi"
+#include "twl4030_omap3.dtsi"
+
+&mmc1 {
+	vmmc-supply = <&vmmc1>;
+	vmmc_aux-supply = <&vsim>;
+	bus-width = <8>;
+};
+
+&mmc2 {
+	status = "disabled";
+};
+
+&mmc3 {
+	status = "disabled";
+};
+
+&twl_gpio {
+	ti,use-leds;
+	/*
+	 * pulldowns:
+	 * BIT(1), BIT(2), BIT(6), BIT(7), BIT(8), BIT(13)
+	 * BIT(15), BIT(16), BIT(17)
+	 */
+	ti,pulldowns = <0x03a1c6>;
+};
+
+&twl_keypad {
+	linux,keymap = <MATRIX_KEY(0, 0, KEY_1)
+			MATRIX_KEY(1, 0, KEY_2)
+			MATRIX_KEY(2, 0, KEY_3)
+			MATRIX_KEY(0, 1, KEY_4)
+			MATRIX_KEY(1, 1, KEY_5)
+			MATRIX_KEY(2, 1, KEY_6)
+			MATRIX_KEY(3, 1, KEY_F5)
+			MATRIX_KEY(0, 2, KEY_7)
+			MATRIX_KEY(1, 2, KEY_8)
+			MATRIX_KEY(2, 2, KEY_9)
+			MATRIX_KEY(3, 2, KEY_F6)
+			MATRIX_KEY(0, 3, KEY_F7)
+			MATRIX_KEY(1, 3, KEY_0)
+			MATRIX_KEY(2, 3, KEY_F8)
+			MATRIX_KEY(4, 5, KEY_RESERVED)
+			MATRIX_KEY(4, 4, KEY_VOLUMEUP)
+			MATRIX_KEY(5, 5, KEY_VOLUMEDOWN)
+			>;
+};
+
+&wdt2 {
+	status = "disabled";
+};
+
+&mcbsp2 {
+	status = "okay";
+};
+
+&gpmc {
+	ranges = <0 0 0x30000000 0x1000000>;       /* CS0: 16MB for NAND */
+
+	nand@0,0 {
+		reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
+		nand-bus-width = <16>;
+		gpmc,device-width = <2>;
+		ti,nand-ecc-opt = "sw";
+
+		gpmc,sync-clk-ps = <0>;
+		gpmc,cs-on-ns = <0>;
+		gpmc,cs-rd-off-ns = <44>;
+		gpmc,cs-wr-off-ns = <44>;
+		gpmc,adv-on-ns = <6>;
+		gpmc,adv-rd-off-ns = <34>;
+		gpmc,adv-wr-off-ns = <44>;
+		gpmc,we-off-ns = <40>;
+		gpmc,oe-off-ns = <54>;
+		gpmc,access-ns = <64>;
+		gpmc,rd-cycle-ns = <82>;
+		gpmc,wr-cycle-ns = <82>;
+		gpmc,wr-access-ns = <40>;
+		gpmc,wr-data-mux-bus-ns = <0>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		x-loader@0 {
+			label = "X-Loader";
+			reg = <0 0x80000>;
+		};
+
+		bootloaders@80000 {
+			label = "U-Boot";
+			reg = <0x80000 0x1e0000>;
+		};
+
+		bootloaders_env@260000 {
+			label = "U-Boot Env";
+			reg = <0x260000 0x20000>;
+		};
+
+		kernel@280000 {
+			label = "Kernel";
+			reg = <0x280000 0x400000>;
+		};
+
+		filesystem@680000 {
+			label = "File System";
+			reg = <0x680000 0xf980000>;
+		};
+	};
+};
+
+&gpmc {
+	ranges = <6 0 0x2c000000 0x1000000>;       /* CS6: 16MB for DM9000 */
+
+	ethernet@0,0 {
+		compatible = "davicom,dm9000";
+		reg =  <6 0x000 2
+			6 0x400 2>; /* CS6, offset 0 and 0x400, IO size 2 */
+		bank-width = <2>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <25 IRQ_TYPE_LEVEL_LOW>;
+		davicom,no-eeprom;
+
+		gpmc,mux-add-data = <0>;
+		gpmc,device-width = <1>;
+		gpmc,wait-pin = <0>;
+		gpmc,cycle2cycle-samecsen = <1>;
+		gpmc,cycle2cycle-diffcsen = <1>;
+
+		gpmc,cs-on-ns = <6>;
+		gpmc,cs-rd-off-ns = <180>;
+		gpmc,cs-wr-off-ns = <180>;
+		gpmc,adv-on-ns = <0>;
+		gpmc,adv-rd-off-ns = <18>;
+		gpmc,adv-wr-off-ns = <48>;
+		gpmc,oe-on-ns = <54>;
+		gpmc,oe-off-ns = <168>;
+		gpmc,we-on-ns = <54>;
+		gpmc,we-off-ns = <168>;
+		gpmc,rd-cycle-ns = <186>;
+		gpmc,wr-cycle-ns = <186>;
+		gpmc,access-ns = <144>;
+		gpmc,page-burst-access-ns = <24>;
+		gpmc,bus-turnaround-ns = <90>;
+		gpmc,cycle2cycle-delay-ns = <90>;
+		gpmc,wait-monitoring-ns = <0>;
+		gpmc,clk-activation-ns = <0>;
+		gpmc,wr-data-mux-bus-ns = <0>;
+		gpmc,wr-access-ns = <0>;
+	};
+};
+
+&omap3_pmx_core {
+	dss_dpi_pins: pinmux_dss_dpi_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0)	/* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0)	/* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0)	/* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0)	/* dss_acbias.dss_acbias */
+			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0)	/* dss_data0.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0)	/* dss_data1.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0)	/* dss_data2.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0)	/* dss_data3.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0)	/* dss_data4.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0)	/* dss_data5.dss_data5 */
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0)	/* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0)	/* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0)	/* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0)	/* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0)	/* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0)	/* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0)	/* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0)	/* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0)	/* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0)	/* dss_data15.dss_data15 */
+			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0)	/* dss_data16.dss_data16 */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0)	/* dss_data17.dss_data17 */
+			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0)	/* dss_data18.dss_data18 */
+			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0)	/* dss_data19.dss_data19 */
+			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0)	/* dss_data20.dss_data20 */
+			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0)	/* dss_data21.dss_data21 */
+			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0)	/* dss_data22.dss_data22 */
+			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0)	/* dss_data23.dss_data23 */
+		>;
+	};
+};
+
+&vpll1 {
+	/* Needed for DSS */
+	regulator-name = "vdds_dsi";
+
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+};
+
+&dss {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_dpi_pins>;
+
+	vdds_dsi-supply = <&vpll1>;
+	vdda_dac-supply = <&vdac>;
+
+	port {
+		dpi_dvi_out: endpoint@0 {
+			remote-endpoint = <&tfp410_in>;
+			data-lines = <24>;
+		};
+	};
+};
+
+&venc {
+	status = "ok";
+
+	vdda-supply = <&vdac>;
+
+	port {
+		venc_out: endpoint {
+			remote-endpoint = <&tv_connector_in>;
+			ti,channels = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi
new file mode 100644
index 000000000000..e84184de2a4a
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi
@@ -0,0 +1,73 @@
+/*
+ * Author: Anthoine Bourgeois <anthoine.bourgois@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "omap3-devkit8000-common.dtsi"
+/ {
+	aliases {
+		display0 = &lcd0;
+		display1 = &dvi0;
+		display2 = &tv0;
+	};
+
+	lcd0: display@0 {
+		compatible = "panel-dpi";
+		label = "lcd";
+
+		enable-gpios = <&twl_gpio 18 GPIO_ACTIVE_HIGH>;
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_lcd_out>;
+			};
+		};
+	};
+};
+
+&dss {
+	port {
+		dpi_lcd_out: endpoint@1 {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <24>;
+		};
+	};
+};
+
+&vio {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+};
+
+&mcspi2 {
+
+	/* touch controller */
+	ads7846@0 {
+		compatible = "ti,ads7846";
+		vcc-supply = <&vio>;
+
+		reg = <0>;			/* CS0 */
+		spi-max-frequency = <1500000>;
+
+		interrupt-parent = <&gpio1>;
+		interrupts = <27 0>;		/* gpio_27 */
+		pendown-gpio = <&gpio1 27 0>;
+
+		ti,x-min = /bits/ 16 <0x0>;
+		ti,x-max = /bits/ 16 <0x0fff>;
+		ti,y-min = /bits/ 16 <0x0>;
+		ti,y-max = /bits/ 16 <0x0fff>;
+		ti,x-plate-ohms = /bits/ 16 <180>;
+		ti,pressure-max = /bits/ 16 <255>;
+		ti,debounce-max = /bits/ 16 <10>;
+		ti,debounce-tol = /bits/ 16 <5>;
+		ti,debounce-rep = /bits/ 16 <1>;
+		ti,keep-vref-on = <1>;
+		ti,settle-delay-usec = /bits/ 16 <150>;
+
+		linux,wakeup;
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts b/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
new file mode 100644
index 000000000000..d5705356d52c
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
@@ -0,0 +1,37 @@
+/*
+ * Author: Anthoine Bourgeois <anthoine.bourgois@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/*
+ * 4.3'' LCD panel sold with devkit8000 board
+ */
+
+#include "omap3-devkit8000-lcd-common.dtsi"
+/ {
+	model = "TimLL OMAP3 Devkit8000 with 4.3'' LCD panel";
+	compatible = "timll,omap3-devkit8000", "ti,omap3";
+
+	lcd0: display@0 {
+		panel-timing {
+			clock-frequency = <10164705>;
+			hactive = <480>;
+			vactive = <272>;
+			hfront-porch = <2>;
+			hback-porch = <2>;
+			hsync-len = <41>;
+			vback-porch = <2>;
+			vfront-porch = <2>;
+			vsync-len = <10>;
+
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts b/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
new file mode 100644
index 000000000000..4afad4b233ec
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
@@ -0,0 +1,37 @@
+/*
+ * Author: Anthoine Bourgeois <anthoine.bourgois@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/*
+ * 7.0'' LCD panel sold with some devkit8000 board
+ */
+
+#include "omap3-devkit8000-lcd-common.dtsi"
+/ {
+	model = "TimLL OMAP3 Devkit8000 with 7.0'' LCD panel";
+	compatible = "timll,omap3-devkit8000", "ti,omap3";
+
+	lcd0: display@0 {
+		panel-timing {
+			clock-frequency = <40000000>;
+			hactive = <800>;
+			vactive = <480>;
+			hfront-porch = <1>;
+			hback-porch = <1>;
+			hsync-len = <48>;
+			vback-porch = <25>;
+			vfront-porch = <12>;
+			vsync-len = <3>;
+
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts
index be2297116a14..40ac89482f5d 100644
--- a/arch/arm/boot/dts/omap3-devkit8000.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000.dts
@@ -1,5 +1,5 @@
 /*
- * Author: Anil Kumar <anilk4.v@gmail.com>
+ * Author: Anthoine Bourgeois <anthoine.bourgeois@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -7,194 +7,13 @@
  */
 /dts-v1/;
 
-#include "omap34xx.dtsi"
+#include "omap3-devkit8000-common.dtsi"
 / {
 	model = "TimLL OMAP3 Devkit8000";
 	compatible = "timll,omap3-devkit8000", "ti,omap3";
 
-	memory {
-		device_type = "memory";
-		reg = <0x80000000 0x10000000>;	/* 256 MB */
-	};
-
-	leds {
-		compatible = "gpio-leds";
-
-		heartbeat {
-			label = "devkit8000::led1";
-			gpios = <&gpio6 26 GPIO_ACTIVE_HIGH>;	/* 186 -> LED1 */
-			default-state = "on";
-			linux,default-trigger = "heartbeat";
-		};
-
-		mmc {
-			label = "devkit8000::led2";
-			gpios = <&gpio6 3 GPIO_ACTIVE_HIGH>;	/* 163 -> LED2 */
-			default-state = "on";
-			linux,default-trigger = "none";
-		};
-
-		usr {
-			label = "devkit8000::led3";
-			gpios = <&gpio6 4 GPIO_ACTIVE_HIGH>;	/* 164 -> LED3 */
-			default-state = "on";
-			linux,default-trigger = "usr";
-                };
-
-	};
-
-	sound {
-		compatible = "ti,omap-twl4030";
-		ti,model = "devkit8000";
-
-		ti,mcbsp = <&mcbsp2>;
-		ti,audio-routing =
-			"Ext Spk", "PREDRIVEL",
-			"Ext Spk", "PREDRIVER",
-			"MAINMIC", "Main Mic",
-			"Main Mic", "Mic Bias 1";
-	};
-};
-
-&i2c1 {
-	clock-frequency = <2600000>;
-
-	twl: twl@48 {
-		reg = <0x48>;
-		interrupts = <7>;	/* SYS_NIRQ cascaded to intc */
-
-		twl_audio: audio {
-			compatible = "ti,twl4030-audio";
-			codec {
-			};
-		};
-	};
-};
-
-&i2c2 {
-	status = "disabled";
-};
-
-&i2c3 {
-	status = "disabled";
-};
-
-#include "twl4030.dtsi"
-#include "twl4030_omap3.dtsi"
-
-&mmc1 {
-	vmmc-supply = <&vmmc1>;
-	vmmc_aux-supply = <&vsim>;
-	bus-width = <8>;
-};
-
-&mmc2 {
-	status = "disabled";
-};
-
-&mmc3 {
-	status = "disabled";
-};
-
-&wdt2 {
-	status = "disabled";
-};
-
-&mcbsp2 {
-	status = "okay";
-};
-
-&gpmc {
-	ranges = <0 0 0x30000000 0x1000000>;       /* CS0: 16MB for NAND */
-
-	nand@0,0 {
-		reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
-		nand-bus-width = <16>;
-		gpmc,device-width = <2>;
-		ti,nand-ecc-opt = "sw";
-
-		gpmc,sync-clk-ps = <0>;
-		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <44>;
-		gpmc,cs-wr-off-ns = <44>;
-		gpmc,adv-on-ns = <6>;
-		gpmc,adv-rd-off-ns = <34>;
-		gpmc,adv-wr-off-ns = <44>;
-		gpmc,we-off-ns = <40>;
-		gpmc,oe-off-ns = <54>;
-		gpmc,access-ns = <64>;
-		gpmc,rd-cycle-ns = <82>;
-		gpmc,wr-cycle-ns = <82>;
-		gpmc,wr-access-ns = <40>;
-		gpmc,wr-data-mux-bus-ns = <0>;
-
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		x-loader@0 {
-			label = "X-Loader";
-			reg = <0 0x80000>;
-		};
-
-		bootloaders@80000 {
-			label = "U-Boot";
-			reg = <0x80000 0x1e0000>;
-		};
-
-		bootloaders_env@260000 {
-			label = "U-Boot Env";
-			reg = <0x260000 0x20000>;
-		};
-
-		kernel@280000 {
-			label = "Kernel";
-			reg = <0x280000 0x400000>;
-		};
-
-		filesystem@680000 {
-			label = "File System";
-			reg = <0x680000 0xf980000>;
-		};
-	};
-};
-
-&gpmc {
-	ranges = <6 0 0x2c000000 0x1000000>;       /* CS6: 16MB for DM9000 */
-
-	ethernet@0,0 {
-		compatible = "davicom,dm9000";
-		reg =  <6 0x000 2
-			6 0x400 2>; /* CS6, offset 0 and 0x400, IO size 2 */
-		bank-width = <2>;
-		interrupt-parent = <&gpio1>;
-		interrupts = <25 IRQ_TYPE_LEVEL_LOW>;
-		davicom,no-eeprom;
-
-		gpmc,mux-add-data = <0>;
-		gpmc,device-width = <1>;
-		gpmc,wait-pin = <0>;
-		gpmc,cycle2cycle-samecsen = <1>;
-		gpmc,cycle2cycle-diffcsen = <1>;
-
-		gpmc,cs-on-ns = <6>;
-		gpmc,cs-rd-off-ns = <180>;
-		gpmc,cs-wr-off-ns = <180>;
-		gpmc,adv-on-ns = <0>;
-		gpmc,adv-rd-off-ns = <18>;
-		gpmc,adv-wr-off-ns = <48>;
-		gpmc,oe-on-ns = <54>;
-		gpmc,oe-off-ns = <168>;
-		gpmc,we-on-ns = <54>;
-		gpmc,we-off-ns = <168>;
-		gpmc,rd-cycle-ns = <186>;
-		gpmc,wr-cycle-ns = <186>;
-		gpmc,access-ns = <144>;
-		gpmc,page-burst-access-ns = <24>;
-		gpmc,bus-turnaround-ns = <90>;
-		gpmc,cycle2cycle-delay-ns = <90>;
-		gpmc,wait-monitoring-ns = <0>;
-		gpmc,clk-activation-ns = <0>;
-		gpmc,wr-data-mux-bus-ns = <0>;
-		gpmc,wr-access-ns = <0>;
+	aliases {
+		display1 = &dvi0;
+		display2 = &tv0;
 	};
 };
diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
index e63133304a34..d0dd0365bfda 100644
--- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
+++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
@@ -319,12 +319,12 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&tsc2048_pins>;
 
-		ti,x-min = <300>;
-		ti,x-max = <3000>;
-		ti,y-min = <600>;
-		ti,y-max = <3600>;
-		ti,x-plate-ohms = <80>;
-		ti,pressure-max = <255>;
+		ti,x-min = /bits/ 16 <300>;
+		ti,x-max = /bits/ 16 <3000>;
+		ti,y-min = /bits/ 16 <600>;
+		ti,y-max = /bits/ 16 <3600>;
+		ti,x-plate-ohms = /bits/ 16 <80>;
+		ti,pressure-max = /bits/ 16 <255>;
 		ti,swap-xy;
 
 		linux,wakeup;
diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi
index 18e1649681c1..28430f1596f2 100644
--- a/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-base.dtsi
@@ -218,3 +218,58 @@
 	pinctrl-0 = <&uart2_pins>;
 };
 
+&mcbsp2 {
+	status = "okay";
+};
+
+&gpmc {
+	ranges = <0 0 0x00000000 0x20000000>;
+
+	nand@0,0 {
+		linux,mtd-name= "micron,mt29c4g96maz";
+		reg = <0 0 0>;
+		nand-bus-width = <16>;
+		gpmc,device-width = <2>;
+		ti,nand-ecc-opt = "bch8";
+
+		gpmc,sync-clk-ps = <0>;
+		gpmc,cs-on-ns = <0>;
+		gpmc,cs-rd-off-ns = <44>;
+		gpmc,cs-wr-off-ns = <44>;
+		gpmc,adv-on-ns = <6>;
+		gpmc,adv-rd-off-ns = <34>;
+		gpmc,adv-wr-off-ns = <44>;
+		gpmc,we-off-ns = <40>;
+		gpmc,oe-off-ns = <54>;
+		gpmc,access-ns = <64>;
+		gpmc,rd-cycle-ns = <82>;
+		gpmc,wr-cycle-ns = <82>;
+		gpmc,wr-access-ns = <40>;
+		gpmc,wr-data-mux-bus-ns = <0>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "SPL";
+			reg = <0 0x80000>; /* 512KiB */
+		};
+		partition@80000 {
+			label = "U-Boot";
+			reg = <0x80000 0x1C0000>; /* 1792KiB */
+		};
+		partition@1c0000 {
+			label = "Environment";
+			reg = <0x240000 0x40000>; /* 256KiB */
+		};
+		partition@280000 {
+			label = "Kernel";
+			reg = <0x280000 0x800000>; /* 8192KiB */
+		};
+		partition@780000 {
+			label = "Filesystem";
+			reg = <0xA80000 0>;
+			/* HACK: MTDPART_SIZ_FULL=0 so fill to end */
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
index 233c69e50ae3..80d236ac64a5 100644
--- a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
@@ -62,6 +62,7 @@
 			OMAP3_CORE1_IOPAD(0x21ca, PIN_INPUT | MUX_MODE0)	/* mcspi1_simo.mcspi1_simo */
 			OMAP3_CORE1_IOPAD(0x21cc, PIN_INPUT | MUX_MODE0)	/* mcspi1_somi.mcspi1_somi */
 			OMAP3_CORE1_IOPAD(0x21ce, PIN_INPUT | MUX_MODE0)	/* mcspi1_cs0.mcspi1_cs0 */
+			OMAP3_CORE1_IOPAD(0x21d0, PIN_INPUT | MUX_MODE0)	/* mcspi1_cs1.mcspi1_cs1 */
 		>;
 	};
 
@@ -120,10 +121,10 @@
 
 	lcd0: display@0 {
 		compatible = "lgphilips,lb035q02";
-		label = "lcd";
+		label = "lcd35";
 
 		reg = <1>;					/* CS1 */
-		spi-max-frequency = <10000000>;
+		spi-max-frequency = <500000>;
 		spi-cpol;
 		spi-cpha;
 
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
index f5395b7da912..048fd216970a 100644
--- a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
@@ -98,7 +98,7 @@
 
 	lcd0: display@0 {
 		compatible = "samsung,lte430wq-f0c", "panel-dpi";
-		label = "lcd";
+		label = "lcd43";
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&lte430_pins>;
diff --git a/arch/arm/boot/dts/omap3-overo-palo35-common.dtsi b/arch/arm/boot/dts/omap3-overo-palo35-common.dtsi
new file mode 100644
index 000000000000..680d7262399c
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-palo35-common.dtsi
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2015 Ash Charles, Gumstix Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Palo35 expansion board is manufactured by Gumstix Inc.
+ */
+
+#include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-lcd35.dtsi"
+
+#include <dt-bindings/input/input.h>
+
+/ {
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins>;
+		heartbeat {
+			label = "overo:red:gpio21";
+			gpios = <&gpio1 21 GPIO_ACTIVE_LOW>;		/* gpio_21 */
+			linux,default-trigger = "heartbeat";
+		};
+		gpio22 {
+			label = "overo:blue:gpio22";
+			gpios = <&gpio1 22 GPIO_ACTIVE_LOW>;		/* gpio_22 */
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&button_pins>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		button0@23 {
+			label = "button0";
+			linux,code = <BTN_0>;
+			gpios = <&gpio1 23 GPIO_ACTIVE_LOW>;		/* gpio_23 */
+			gpio-key,wakeup;
+		};
+		button1@14 {
+			label = "button1";
+			linux,code = <BTN_1>;
+			gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;		/* gpio_14 */
+			gpio-key,wakeup;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-overo-palo35.dts b/arch/arm/boot/dts/omap3-overo-palo35.dts
new file mode 100644
index 000000000000..e3e2bce6edbb
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-palo35.dts
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2015 Ash Charles, Gumstix Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Palo35 expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap3-overo.dtsi"
+#include "omap3-overo-palo35-common.dtsi"
+
+/ {
+	model = "OMAP35xx Gumstix Overo on Palo35";
+	compatible = "gumstix,omap3-overo-palo35", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3";
+};
+
+&omap3_pmx_core2 {
+	led_pins: pinmux_led_pins {
+		pinctrl-single,pins = <
+			OMAP3430_CORE2_IOPAD(0x25ea, PIN_OUTPUT | MUX_MODE4)	/* etk_d7.gpio_21 */
+			OMAP3430_CORE2_IOPAD(0x25ec, PIN_OUTPUT | MUX_MODE4)	/* etk_d8.gpio_22 */
+		>;
+	};
+
+	button_pins: pinmux_button_pins {
+		pinctrl-single,pins = <
+			OMAP3430_CORE2_IOPAD(0x25ee, PIN_INPUT | MUX_MODE4)	/* etk_d9.gpio_23 */
+			OMAP3430_CORE2_IOPAD(0x25dc, PIN_INPUT | MUX_MODE4)	/* etk_d0.gpio_14 */
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-overo-storm-palo35.dts b/arch/arm/boot/dts/omap3-overo-storm-palo35.dts
new file mode 100644
index 000000000000..4e725d2d0038
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-storm-palo35.dts
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2015 Ash Charles, Gumstix, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Palo35 expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap3-overo-storm.dtsi"
+#include "omap3-overo-palo35-common.dtsi"
+
+/ {
+	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Palo35";
+	compatible = "gumstix,omap3-overo-palo35", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+};
+
+&omap3_pmx_core2 {
+	led_pins: pinmux_led_pins {
+		pinctrl-single,pins = <
+			OMAP3630_CORE2_IOPAD(0x25ea, PIN_OUTPUT | MUX_MODE4)	/* etk_d7.gpio_21 */
+			OMAP3630_CORE2_IOPAD(0x25ec, PIN_OUTPUT | MUX_MODE4)	/* etk_d8.gpio_22 */
+		>;
+	};
+
+	button_pins: pinmux_button_pins {
+		pinctrl-single,pins = <
+			OMAP3630_CORE2_IOPAD(0x25ee, PIN_INPUT | MUX_MODE4)	/* etk_d9.gpio_23 */
+			OMAP3630_CORE2_IOPAD(0x25dc, PIN_INPUT | MUX_MODE4)	/* etk_d0.gpio_14 */
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts b/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts
new file mode 100644
index 000000000000..da6afafcc6c1
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2015 Ash Charles, Gumstix, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * TobiDuo expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap3-overo-storm.dtsi"
+#include "omap3-overo-tobiduo-common.dtsi"
+
+/ {
+	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on TobiDuo";
+	compatible = "gumstix,omap3-overo-tobiduo", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+};
diff --git a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
new file mode 100644
index 000000000000..334109e14613
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) 2015 Ash Charles, Gumstix, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * TobiDuo expansion board is manufactured by Gumstix Inc.
+ */
+
+#include "omap3-overo-common-peripherals.dtsi"
+
+#include "omap-gpmc-smsc9221.dtsi"
+
+&gpmc {
+	ranges = <4 0 0x2b000000 0x1000000>,	/* CS4 */
+		 <5 0 0x2c000000 0x1000000>;	/* CS5 */
+
+	smsc1: ethernet@gpmc {
+		reg = <5 0 0xff>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <16 IRQ_TYPE_LEVEL_LOW>;	/* GPIO 176 */
+	};
+
+	smsc2: ethernet@4,0 {
+		compatible = "smsc,lan9221","smsc,lan9115";
+		bank-width = <2>;
+
+		gpmc,mux-add-data;
+		gpmc,cs-on-ns = <0>;
+		gpmc,cs-rd-off-ns = <42>;
+		gpmc,cs-wr-off-ns = <36>;
+		gpmc,adv-on-ns = <6>;
+		gpmc,adv-rd-off-ns = <12>;
+		gpmc,adv-wr-off-ns = <12>;
+		gpmc,oe-on-ns = <0>;
+		gpmc,oe-off-ns = <42>;
+		gpmc,we-on-ns = <0>;
+		gpmc,we-off-ns = <36>;
+		gpmc,rd-cycle-ns = <60>;
+		gpmc,wr-cycle-ns = <54>;
+		gpmc,access-ns = <36>;
+		gpmc,page-burst-access-ns = <0>;
+		gpmc,bus-turnaround-ns = <0>;
+		gpmc,cycle2cycle-delay-ns = <0>;
+		gpmc,wr-data-mux-bus-ns = <18>;
+		gpmc,wr-access-ns = <42>;
+		gpmc,cycle2cycle-samecsen;
+		gpmc,cycle2cycle-diffcsen;
+		vddvario-supply = <&vddvario>;
+		vdd33a-supply = <&vdd33a>;
+		reg-io-width = <4>;
+		smsc,save-mac-address;
+
+		reg = <4 0 0xff>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;	/* GPIO 65 */
+	};
+};
+
+&lis33de {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/omap3-overo-tobiduo.dts b/arch/arm/boot/dts/omap3-overo-tobiduo.dts
new file mode 100644
index 000000000000..b9ce310f6e82
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-tobiduo.dts
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2015 Ash Charles, Gumstix, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * TobiDuo expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap3-overo.dtsi"
+#include "omap3-overo-tobiduo-common.dtsi"
+
+/ {
+	model = "OMAP35xx Gumstix Overo on TobiDuo";
+	compatible = "gumstix,omap3-overo-tobiduo", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3";
+};
diff --git a/arch/arm/boot/dts/omap3-overo.dtsi b/arch/arm/boot/dts/omap3-overo.dtsi
index 69ca7c45bca2..932a02ff552a 100644
--- a/arch/arm/boot/dts/omap3-overo.dtsi
+++ b/arch/arm/boot/dts/omap3-overo.dtsi
@@ -32,7 +32,3 @@
 		>;
 	};
 };
-
-&mcbsp2 {
-	status = "okay";
-};
diff --git a/arch/arm/boot/dts/omap3-pandora-1ghz.dts b/arch/arm/boot/dts/omap3-pandora-1ghz.dts
index 9619a28dfd7d..25498f756a29 100644
--- a/arch/arm/boot/dts/omap3-pandora-1ghz.dts
+++ b/arch/arm/boot/dts/omap3-pandora-1ghz.dts
@@ -19,7 +19,7 @@
 / {
 	model = "Pandora Handheld Console 1GHz";
 
-	compatible = "ti,omap36xx", "ti,omap3";
+	compatible = "openpandora,omap3-pandora-1ghz", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-pandora-600mhz.dts b/arch/arm/boot/dts/omap3-pandora-600mhz.dts
index fb803a70a2bb..8775897a4ce7 100644
--- a/arch/arm/boot/dts/omap3-pandora-600mhz.dts
+++ b/arch/arm/boot/dts/omap3-pandora-600mhz.dts
@@ -19,7 +19,7 @@
 / {
 	model = "Pandora Handheld Console";
 
-	compatible = "ti,omap3";
+	compatible = "openpandora,omap3-pandora-600mhz", "ti,omap3430", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi
index 782ab1ff1d08..f2084e6d01e7 100644
--- a/arch/arm/boot/dts/omap3-pandora-common.dtsi
+++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi
@@ -199,6 +199,38 @@
 			gpios = <&gpio4 12 GPIO_ACTIVE_HIGH>;   /* GPIO_108 */
 		};
 	};
+
+	/* HS USB Host PHY on PORT 2 */
+	hsusb2_phy: hsusb2_phy {
+		compatible = "usb-nop-xceiv";
+		reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>; /* GPIO_16 */
+		vcc-supply = <&vaux2>;
+	};
+
+	/* HS USB Host VBUS supply
+	 * disabling this regulator causes current leakage, and LCD flicker
+	 * on earlier (CC) board revisions, so keep it always on */
+	usb_host_5v: fixed-regulator-usb_host_5v {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_host_5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+		enable-active-high;
+		gpio = <&gpio6 4 0>;	/* GPIO_164 */
+	};
+
+	/* wg7210 (wifi+bt module) 32k clock buffer */
+	wg7210_32k: fixed-regulator-wg7210_32k {
+		compatible = "regulator-fixed";
+		regulator-name = "wg7210_32k";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		enable-active-high;
+		gpio = <&twl_gpio 13 GPIO_ACTIVE_HIGH>;
+	};
 };
 
 &omap3_pmx_core {
@@ -459,13 +491,18 @@
 	power = <50>;
 };
 
+/*
+ * Many pandora boards have been produced with defective write-protect switches
+ * on either slot, so it was decided not to use this feature. If you know
+ * your board has good switches, feel free to uncomment wp-gpios below.
+ */
 &mmc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vmmc1>;
 	bus-width = <4>;
 	cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio4 30 GPIO_ACTIVE_LOW>;	/* GPIO_126 */
+	/*wp-gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>;*/	/* GPIO_126 */
 };
 
 &mmc2 {
@@ -473,8 +510,13 @@
 	pinctrl-0 = <&mmc2_pins>;
 	vmmc-supply = <&vmmc2>;
 	bus-width = <4>;
-	cd-gpios = <&twl_gpio 1 GPIO_ACTIVE_HIGH>;
-	wp-gpios = <&gpio4 31 GPIO_ACTIVE_LOW>;	/* GPIO_127 */
+	cd-gpios = <&twl_gpio 1 GPIO_ACTIVE_LOW>;
+	/*wp-gpios = <&gpio4 31 GPIO_ACTIVE_HIGH>;*/	/* GPIO_127 */
+};
+
+/* mmc3 is probed using pdata-quirks to pass wl1251 card data */
+&mmc3 {
+	status = "disabled";
 };
 
 /* bluetooth*/
@@ -496,6 +538,10 @@
 	port2-mode = "ehci-phy";
 };
 
+&usbhsehci {
+	phys = <0 &hsusb2_phy>;
+};
+
 &gpmc {
 	ranges = <0 0 0x30000000 0x1000000>; /* CS0: 16MB for NAND */
 
@@ -545,7 +591,7 @@
 			reg = <0x280000 0xa00000>;
 		};
 
-		filesystem@680000 {
+		filesystem@c80000 {
 			label = "rootfs";
 			reg = <0xc80000 0>;	/* 0 = MTDPART_SIZ_FULL */
 		};
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index f884d6adb71e..abc4473e6f8a 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -191,7 +191,8 @@
 				};
 
 				omap4_padconf_global: omap4_padconf_global@5a0 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x5a0 0x170>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -551,6 +552,7 @@
 			reg = <0x4a066000 0x100>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_dsp";
+			#iommu-cells = <0>;
 		};
 
 		mmu_ipu: mmu@55082000 {
@@ -558,6 +560,7 @@
 			reg = <0x55082000 0x100>;
 			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_ipu";
+			#iommu-cells = <0>;
 			ti,iommu-bus-err-back;
 		};
 
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 275618f19a43..3cc8f357d5b8 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -510,6 +510,13 @@
 				};
 			};
 		};
+
+		palmas_power_button: palmas_power_button {
+			compatible = "ti,palmas-pwrbutton";
+			interrupt-parent = <&palmas>;
+			interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
+			wakeup-source;
+		};
 	};
 
 	twl6040: twl@4b {
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 7d24ae0306b5..4205a8ac9ddb 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -180,7 +180,8 @@
 				};
 
 				omap5_padconf_global: omap5_padconf_global@5a0 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x5a0 0xec>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -612,6 +613,7 @@
 			reg = <0x4a066000 0x100>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_dsp";
+			#iommu-cells = <0>;
 		};
 
 		mmu_ipu: mmu@55082000 {
@@ -619,6 +621,7 @@
 			reg = <0x55082000 0x100>;
 			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_ipu";
+			#iommu-cells = <0>;
 			ti,iommu-bus-err-back;
 		};
 
@@ -870,7 +873,12 @@
 			dwc3@4a030000 {
 				compatible = "snps,dwc3";
 				reg = <0x4a030000 0x10000>;
-				interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "peripheral",
+						  "host",
+						  "otg";
 				phys = <&usb2_phy>, <&usb3_phy>;
 				phy-names = "usb2-phy", "usb3-phy";
 				dr_mode = "peripheral";
diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
new file mode 100644
index 000000000000..3daec912b4bf
--- /dev/null
+++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
@@ -0,0 +1,273 @@
+/*
+ * Device Tree file for Buffalo Linkstation LS-WTGL
+ *
+ * Copyright (C) 2015, Roger Shimizu <rogershimizu@gmail.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include "orion5x-mv88f5182.dtsi"
+
+/ {
+	model = "Buffalo Linkstation LS-WTGL";
+	compatible = "buffalo,lswtgl", "marvell,orion5x-88f5182", "marvell,orion5x";
+
+	memory { /* 64 MB */
+		device_type = "memory";
+		reg = <0x00000000 0x4000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200n8 earlyprintk";
+		linux,stdout-path = &uart0;
+	};
+
+	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>,
+		         <MBUS_ID(0x09, 0x00) 0 0xf2200000 0x800>,
+			 <MBUS_ID(0x01, 0x0f) 0 0xf4000000 0x40000>;
+
+		internal-regs {
+			pinctrl: pinctrl@10000 {
+				pinctrl-0 = <&pmx_usb_power &pmx_power_hdd
+					&pmx_fan_low &pmx_fan_high &pmx_fan_lock>;
+				pinctrl-names = "default";
+
+				pmx_led_power: pmx-leds {
+					marvell,pins = "mpp0";
+					marvell,function = "gpio";
+				};
+
+				pmx_led_alarm: pmx-leds {
+					marvell,pins = "mpp2";
+					marvell,function = "gpio";
+				};
+
+				pmx_led_info: pmx-leds {
+					marvell,pins = "mpp3";
+					marvell,function = "gpio";
+				};
+
+				pmx_power_hdd: pmx-power-hdd {
+					marvell,pins = "mpp1";
+					marvell,function = "gpio";
+				};
+
+				pmx_usb_power: pmx-usb-power {
+					marvell,pins = "mpp9";
+					marvell,function = "gpio";
+				};
+
+				pmx_sata0: pmx-sata0 {
+					marvell,pins = "mpp12";
+					marvell,function = "sata0";
+				};
+
+				pmx_sata1: pmx-sata1 {
+					marvell,pins = "mpp13";
+					marvell,function = "sata1";
+				};
+
+				pmx_fan_high: pmx-fan-high {
+					marvell,pins = "mpp14";
+					marvell,function = "gpio";
+				};
+
+				pmx_fan_low: pmx-fan-low {
+					marvell,pins = "mpp17";
+					marvell,function = "gpio";
+				};
+
+				pmx_fan_lock: pmx-fan-lock {
+					marvell,pins = "mpp6";
+					marvell,function = "gpio";
+				};
+
+				pmx_power_switch: pmx-power-switch {
+					marvell,pins = "mpp8", "mpp10";
+					marvell,function = "gpio";
+				};
+			};
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_power_switch>;
+		pinctrl-names = "default";
+
+		button@1 {
+			label = "Power-on Switch";
+			linux,code = <KEY_RESERVED>;
+			linux,input-type = <5>;
+			gpios = <&gpio0 8 GPIO_ACTIVE_LOW>;
+		};
+
+		button@2 {
+			label = "Power-auto Switch";
+			linux,code = <KEY_ESC>;
+			linux,input-type = <5>;
+			gpios = <&gpio0 10 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio_leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&pmx_led_power &pmx_led_alarm
+			     &pmx_led_info>;
+		pinctrl-names = "default";
+
+		led@1 {
+			label = "lswtgl:blue:power";
+			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+		};
+
+		led@2 {
+			label = "lswtgl:red:alarm";
+			gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
+		};
+
+		led@3 {
+			label = "lswtgl:amber:info";
+			gpios = <&gpio0 3 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio_fan {
+		compatible = "gpio-fan";
+		pinctrl-0 = <&pmx_fan_low &pmx_fan_high &pmx_fan_lock>;
+		pinctrl-names = "default";
+
+		gpios = <&gpio0 14 GPIO_ACTIVE_LOW
+			 &gpio0 17 GPIO_ACTIVE_LOW>;
+
+		gpio-fan,speed-map = <0 3
+				1500 2
+				3250 1
+				5000 0>;
+
+		alarm-gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+	};
+
+	restart_poweroff {
+		compatible = "restart-poweroff";
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_power_hdd &pmx_usb_power>;
+		pinctrl-names = "default";
+
+		usb_power: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "USB Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpios = <&gpio0 9 GPIO_ACTIVE_HIGH>;
+		};
+
+		hdd_power: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "HDD Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&mdio {
+	status = "okay";
+
+	ethphy: ethernet-phy {
+		reg = <8>;
+	};
+};
+
+&eth {
+	status = "okay";
+
+	ethernet-port@0 {
+		phy-handle = <&ethphy>;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&i2c {
+	status = "okay";
+
+	rtc {
+		compatible = "ricoh,rs5c372a";
+		reg = <0x32>;
+	};
+};
+
+&wdt {
+	status = "disabled";
+};
+
+&sata {
+	pinctrl-0 = <&pmx_sata0 &pmx_sata1>;
+	pinctrl-names = "default";
+	status = "okay";
+	nr-ports = <2>;
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/orion5x-lswsgl.dts b/arch/arm/boot/dts/orion5x-lswsgl.dts
new file mode 100644
index 000000000000..6b47a52ceb9c
--- /dev/null
+++ b/arch/arm/boot/dts/orion5x-lswsgl.dts
@@ -0,0 +1,276 @@
+/*
+ * Copyright (C) 2015 Benjamin Cama <benoar@dolka.fr>
+ * Copyright (C) 2014 Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ * Based on the board file arch/arm/mach-orion5x/lsmini-setup.c,
+ * Copyright (C) 2008 Alexey Kopytko <alexey@kopytko.ru>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include "orion5x-mv88f5182.dtsi"
+
+/ {
+	model = "Buffalo Linkstation Mini (LS-WSGL)";
+	compatible = "buffalo,lswsgl", "marvell,orion5x-88f5182", "marvell,orion5x";
+
+	memory {
+		reg = <0x00000000 0x8000000>; /* 128 MB */
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200 earlyprintk";
+		linux,stdout-path = &uart0;
+	};
+
+	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>,
+			 <MBUS_ID(0x09, 0x00) 0 0xf2200000 0x800>,
+			 <MBUS_ID(0x01, 0x0f) 0 0xf4000000 0x40000>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-0 = <&pmx_buttons>;
+		pinctrl-names = "default";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		func {
+			label = "Function Button";
+			linux,code = <KEY_OPTION>;
+			gpios = <&gpio0 15 GPIO_ACTIVE_LOW>;
+		};
+
+		power {
+			label = "Power-on Switch";
+			linux,input-type = <5>; /* EV_SW */
+			linux,code = <KEY_RESERVED>; /* LSMINI_SW_POWER */
+			gpios = <&gpio0 18 GPIO_ACTIVE_LOW>;
+		};
+
+		autopower {
+			label = "Power-auto Switch";
+			linux,input-type = <5>; /* EV_SW */
+			linux,code = <KEY_ESC>; /* LSMINI_SW_AUTOPOWER */
+			gpios = <&gpio0 17 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&pmx_led_alarm &pmx_led_info &pmx_led_func
+			     &pmx_led_power>;
+		pinctrl-names = "default";
+
+		alarm {
+			label = "lswsgl:alarm:red";
+			gpio = <&gpio0 2 GPIO_ACTIVE_LOW>;
+		};
+
+		info {
+			label = "lswsgl:info:amber";
+			gpio = <&gpio0 3 GPIO_ACTIVE_LOW>;
+		};
+
+		func {
+			label = "lswsgl:func:blue:top";
+			gpio = <&gpio0 9 GPIO_ACTIVE_LOW>;
+		};
+
+		power {
+			label = "lswsgl:power:blue:bottom";
+			gpio = <&gpio0 14 GPIO_ACTIVE_LOW>;
+			default-state = "on";
+		};
+	};
+
+	restart_poweroff {
+		compatible = "restart-poweroff";
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_sata0_power &pmx_sata1_power &pmx_usb_power>;
+		pinctrl-names = "default";
+
+		sata0_power: regulator@0 {
+			compatible = "regulator-fixed";
+			reg = <0>;
+			regulator-name = "SATA0 Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 1 GPIO_ACTIVE_HIGH>;
+		};
+
+		sata1_power: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "SATA1 Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 19 GPIO_ACTIVE_HIGH>;
+		};
+
+		usb_power: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "USB Power";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			enable-active-high;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 16 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&devbus_bootcs {
+	status = "okay";
+
+	devbus,keep-config;
+
+	flash@0 {
+		compatible = "cfi-flash";
+		reg = <0 0x40000>;
+		bank-width = <1>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "Full256Kb";
+			reg = <0 0x40000>;
+			read-only;
+		};
+	};
+};
+
+&mdio {
+	status = "okay";
+
+	ethphy: ethernet-phy {
+		reg = <8>;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&eth {
+	status = "okay";
+
+	ethernet-port@0 {
+		phy-handle = <&ethphy>;
+	};
+};
+
+&i2c {
+	status = "okay";
+	clock-frequency = <100000>;
+	#address-cells = <1>;
+
+	rtc@32 {
+		compatible = "ricoh,rs5c372a";
+		reg = <0x32>;
+	};
+};
+
+&pinctrl {
+	pmx_buttons: pmx-buttons {
+		marvell,pins = "mpp15", "mpp17", "mpp18";
+		marvell,function = "gpio";
+	};
+
+	pmx_led_alarm: pmx-leds {
+		marvell,pins = "mpp2";
+		marvell,function = "gpio";
+	};
+
+	pmx_led_info: pmx-leds {
+		marvell,pins = "mpp3";
+		marvell,function = "gpio";
+	};
+
+	pmx_led_func: pmx-leds {
+		marvell,pins = "mpp9";
+		marvell,function = "gpio";
+	};
+
+	pmx_led_power: pmx-leds {
+		marvell,pins = "mpp14";
+		marvell,function = "gpio";
+	};
+
+	pmx_sata0_power: pmx-sata0-power {
+		marvell,pins = "mpp1";
+		marvell,function = "gpio";
+	};
+
+	pmx_sata1_power: pmx-sata1-power {
+		marvell,pins = "mpp19";
+		marvell,function = "gpio";
+	};
+
+	pmx_usb_power: pmx-usb-power {
+		marvell,pins = "mpp16";
+		marvell,function = "gpio";
+	};
+};
+
+&sata {
+	status = "okay";
+	nr-ports = <2>;
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/pxa27x.dtsi b/arch/arm/boot/dts/pxa27x.dtsi
index 90b99714ad80..7f68a1ee7073 100644
--- a/arch/arm/boot/dts/pxa27x.dtsi
+++ b/arch/arm/boot/dts/pxa27x.dtsi
@@ -7,6 +7,15 @@
 	compatible = "marvell,pxa27x";
 
 	pxabus {
+		pdma: dma-controller@40000000 {
+			compatible = "marvell,pdma-1.0";
+			reg = <0x40000000 0x10000>;
+			interrupts = <25>;
+			#dma-channels = <32>;
+			#dma-cells = <2>;
+			status = "okay";
+		};
+
 		pxairq: interrupt-controller@40d00000 {
 			marvell,intc-priority;
 			marvell,intc-nr-irqs = <34>;
@@ -17,6 +26,14 @@
 			clocks = <&clks CLK_NONE>;
 		};
 
+		pxa27x_ohci: usb@4c000000 {
+			compatible = "marvell,pxa-ohci";
+			reg = <0x4c000000 0x10000>;
+			interrupts = <3>;
+			clocks = <&clks CLK_USBHOST>;
+			status = "disabled";
+		};
+
 		pwm0: pwm@40b00000 {
 			compatible = "marvell,pxa270-pwm", "marvell,pxa250-pwm";
 			reg = <0x40b00000 0x10>;
@@ -50,6 +67,8 @@
 			reg = <0x40f00180 0x24>;
 			interrupts = <6>;
 			clocks = <&clks CLK_PWRI2C>;
+			#address-cells = <0x1>;
+			#size-cells = <0>;
 			status = "disabled";
 		};
 
@@ -68,6 +87,23 @@
 			clocks = <&clks CLK_KEYPAD>;
 			status = "disabled";
 		};
+
+		pxa_camera: imaging@50000000 {
+			compatible = "marvell,pxa270-qci";
+			reg = <0x50000000 0x1000>;
+			interrupts = <33>;
+			dmas = <&pdma 68 0	/* Y channel */
+				&pdma 69 0	/* U channel */
+				&pdma 70 0>;	/* V channel */
+			dma-names = "CI_Y", "CI_U", "CI_V";
+
+			clocks = <&clks CLK_CAMERA>;
+			clock-names = "ciclk";
+			clock-frequency = <5000000>;
+			clock-output-names = "qci_mclk";
+
+			status = "disabled";
+		};
 	};
 
 	clocks {
diff --git a/arch/arm/boot/dts/pxa2xx.dtsi b/arch/arm/boot/dts/pxa2xx.dtsi
index 71a0cd7388d1..5e5af078b9b5 100644
--- a/arch/arm/boot/dts/pxa2xx.dtsi
+++ b/arch/arm/boot/dts/pxa2xx.dtsi
@@ -128,6 +128,10 @@
 			compatible = "marvell,pxa-mmc";
 			reg = <0x41100000 0x1000>;
 			interrupts = <23>;
+			clocks = <&clks CLK_MMC>;
+			dmas = <&pdma 21 3
+				&pdma 22 3>;
+			dma-names = "rx", "tx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi
index 7ad0b1771098..cf6998a0804d 100644
--- a/arch/arm/boot/dts/pxa3xx.dtsi
+++ b/arch/arm/boot/dts/pxa3xx.dtsi
@@ -6,6 +6,15 @@
 	compatible = "marvell,pxa3xx";
 
 	pxabus {
+		pdma: dma-controller@40000000 {
+			compatible = "marvell,pdma-1.0";
+			reg = <0x40000000 0x10000>;
+			interrupts = <25>;
+			#dma-channels = <32>;
+			#dma-cells = <2>;
+			status = "okay";
+		};
+
 		pwri2c: i2c@40f500c0 {
 			compatible = "mrvl,pwri2c";
 			reg = <0x40f500c0 0x30>;
@@ -21,6 +30,8 @@
 			reg = <0x43100000 90>;
 			interrupts = <45>;
 			clocks = <&clks CLK_NAND>;
+			dmas = <&pdma 97>;
+			dma-names = "data";
 			#address-cells = <1>;
 			#size-cells = <1>;	
 			status = "disabled";
@@ -42,6 +53,47 @@
 			interrupt-controller;
 			#interrupt-cells = <0x2>;
 		};
+
+		mmc0: mmc@41100000 {
+			compatible = "marvell,pxa-mmc";
+			reg = <0x41100000 0x1000>;
+			interrupts = <23>;
+			clocks = <&clks CLK_MMC>;
+			dmas = <&pdma 21 3
+				&pdma 22 3>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
+		mmc1: mmc@42000000 {
+			compatible = "marvell,pxa-mmc";
+			reg = <0x42000000 0x1000>;
+			interrupts = <41>;
+			clocks = <&clks CLK_MMC1>;
+			dmas = <&pdma 93 3
+				&pdma 94 3>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
+		mmc2: mmc@42500000 {
+			compatible = "marvell,pxa-mmc";
+			reg = <0x42500000 0x1000>;
+			interrupts = <55>;
+			clocks = <&clks CLK_MMC2>;
+			dmas = <&pdma 46 3
+				&pdma 47 3>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
+		pxa3xx_ohci: usb@4c000000 {
+			compatible = "marvell,pxa-ohci";
+			reg = <0x4c000000 0x10000>;
+			interrupts = <3>;
+			clocks = <&clks CLK_USBHOST>;
+			status = "disabled";
+		};
 	};
 
 	clocks {
diff --git a/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts b/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts
index 71512b3ca444..34ccb260f12a 100644
--- a/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts
+++ b/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts
@@ -67,6 +67,12 @@
 					bias-pull-down;
 				};
 
+				pm8921_l5: l5 {
+					regulator-min-microvolt = <2750000>;
+					regulator-max-microvolt = <3000000>;
+					bias-pull-down;
+				};
+
 				pm8921_l23: l23 {
 					regulator-min-microvolt = <1700000>;
 					regulator-max-microvolt = <1900000>;
@@ -140,19 +146,33 @@
 			status = "okay";
 		};
 
+		/* on board fixed 3.3v supply */
+		v3p3_fixed: v3p3 {
+			compatible = "regulator-fixed";
+			regulator-name = "PCIE V3P3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+
 		amba {
 			/* eMMC */
 			sdcc1: sdcc@12400000 {
 				status = "okay";
+				vmmc-supply = <&pm8921_l5>;
+				vqmmc-supply = <&pm8921_s4>;
 			};
 
 			/* External micro SD card */
 			sdcc3: sdcc@12180000 {
 				status = "okay";
+				vmmc-supply = <&v3p3_fixed>;
 			};
 			/* WLAN */
 			sdcc4: sdcc@121c0000 {
 				status = "okay";
+				vmmc-supply = <&v3p3_fixed>;
+				vqmmc-supply = <&v3p3_fixed>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts b/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts
index a7c939ba8873..88d6655ddaf6 100644
--- a/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts
+++ b/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts
@@ -7,6 +7,7 @@
 
 	aliases {
 		serial0 = &gsbi7_serial;
+		serial1 = &gsbi6_serial;
 	};
 
 	soc {
@@ -73,6 +74,12 @@
 					bias-pull-down;
 				};
 
+				pm8921_l5: l5 {
+					regulator-min-microvolt = <2750000>;
+					regulator-max-microvolt = <3000000>;
+					bias-pull-down;
+				};
+
 				pm8921_l6: l6 {
 					regulator-min-microvolt = <2950000>;
 					regulator-max-microvolt = <2950000>;
@@ -84,9 +91,25 @@
 					regulator-max-microvolt = <1900000>;
 					bias-pull-down;
 				};
+
+				pm8921_lvs1: lvs1 {
+					bias-pull-down;
+				};
 			};
 		};
 
+		ext_3p3v: regulator-fixed@1 {
+			compatible = "regulator-fixed";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-name = "ext_3p3v";
+			regulator-type = "voltage";
+			startup-delay-us = <0>;
+			gpio = <&tlmm_pinmux 77 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			regulator-boot-on;
+		};
+
 		gsbi3: gsbi@16200000 {
 			status = "okay";
 			qcom,mode = <GSBI_PROT_I2C>;
@@ -115,6 +138,18 @@
 			};
 		};
 
+		gsbi@16500000 {
+			status = "ok";
+			qcom,mode = <GSBI_PROT_I2C_UART>;
+
+			serial@16540000 {
+				status = "ok";
+
+				pinctrl-names = "default";
+				pinctrl-0 = <&uart_pins>;
+			};
+		};
+
 		gsbi@16600000 {
 			status = "ok";
 			qcom,mode = <GSBI_PROT_I2C_UART>;
@@ -175,11 +210,14 @@
 			/* eMMC */
 			sdcc1: sdcc@12400000 {
 				status = "okay";
+				vmmc-supply = <&pm8921_l5>;
+				vqmmc-supply = <&pm8921_s4>;
 			};
 
 			/* External micro SD card */
 			sdcc3: sdcc@12180000 {
 				status = "okay";
+				vmmc-supply = <&pm8921_l6>;
 				pinctrl-names	= "default";
 				pinctrl-0	= <&card_detect>;
 				cd-gpios	= <&tlmm_pinmux 26 GPIO_ACTIVE_LOW>;
@@ -187,6 +225,8 @@
 			/* WLAN */
 			sdcc4: sdcc@121c0000 {
 				status = "okay";
+				vmmc-supply = <&ext_3p3v>;
+				vqmmc-supply = <&pm8921_lvs1>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi
index df2061ec630d..d2e94d647c27 100644
--- a/arch/arm/boot/dts/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064.dtsi
@@ -6,7 +6,6 @@
 #include <dt-bindings/clock/qcom,mmcc-msm8960.h>
 #include <dt-bindings/soc/qcom,gsbi.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
-
 / {
 	model = "Qualcomm APQ8064";
 	compatible = "qcom,apq8064";
@@ -127,6 +126,13 @@
 					function = "gsbi3";
 				};
 			};
+
+			uart_pins: uart_pins {
+				mux {
+					pins = "gpio14", "gpio15", "gpio16", "gpio17";
+					function = "gsbi6";
+				};
+			};
 		};
 
 		intc: interrupt-controller@2000000 {
@@ -243,13 +249,13 @@
 		gsbi3: gsbi@16200000 {
 			status = "disabled";
 			compatible = "qcom,gsbi-v1.0.0";
+			cell-index = <3>;
 			reg = <0x16200000 0x100>;
 			clocks = <&gcc GSBI3_H_CLK>;
 			clock-names = "iface";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
-
 			i2c3: i2c@16280000 {
 				compatible = "qcom,i2c-qup-v1.1.1";
 				reg = <0x16280000 0x1000>;
@@ -260,6 +266,28 @@
 			};
 		};
 
+		gsbi6: gsbi@16500000 {
+			status = "disabled";
+			compatible = "qcom,gsbi-v1.0.0";
+			cell-index = <6>;
+			reg = <0x16500000 0x03>;
+			clocks = <&gcc GSBI6_H_CLK>;
+			clock-names = "iface";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			gsbi6_serial: serial@16540000 {
+				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
+				reg = <0x16540000 0x100>,
+				      <0x16500000 0x03>;
+				interrupts = <0 156 0x0>;
+				clocks = <&gcc GSBI6_UART_CLK>, <&gcc GSBI6_H_CLK>;
+				clock-names = "core", "iface";
+				status = "disabled";
+			};
+		};
+
 		gsbi7: gsbi@16600000 {
 			status = "disabled";
 			compatible = "qcom,gsbi-v1.0.0";
@@ -287,6 +315,53 @@
 			compatible = "qcom,ssbi";
 			reg = <0x00500000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
+
+			pmicintc: pmic@0 {
+				compatible = "qcom,pm8921";
+				interrupt-parent = <&tlmm_pinmux>;
+				interrupts = <74 8>;
+				#interrupt-cells = <2>;
+				interrupt-controller;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pm8921_gpio: gpio@150 {
+
+					compatible = "qcom,pm8921-gpio";
+					reg = <0x150>;
+					interrupts = <192 1>, <193 1>, <194 1>,
+						     <195 1>, <196 1>, <197 1>,
+						     <198 1>, <199 1>, <200 1>,
+						     <201 1>, <202 1>, <203 1>,
+						     <204 1>, <205 1>, <206 1>,
+						     <207 1>, <208 1>, <209 1>,
+						     <210 1>, <211 1>, <212 1>,
+						     <213 1>, <214 1>, <215 1>,
+						     <216 1>, <217 1>, <218 1>,
+						     <219 1>, <220 1>, <221 1>,
+						     <222 1>, <223 1>, <224 1>,
+						     <225 1>, <226 1>, <227 1>,
+						     <228 1>, <229 1>, <230 1>,
+						     <231 1>, <232 1>, <233 1>,
+						     <234 1>, <235 1>;
+
+					gpio-controller;
+					#gpio-cells = <2>;
+
+				};
+
+				pm8921_mpps: mpps@50 {
+					compatible = "qcom,pm8921-mpp";
+					reg = <0x50>;
+					gpio-controller;
+					#gpio-cells = <2>;
+					interrupts =
+					<128 1>, <129 1>, <130 1>, <131 1>,
+					<132 1>, <133 1>, <134 1>, <135 1>,
+					<136 1>, <137 1>, <138 1>, <139 1>;
+				};
+
+			};
 		};
 
 		gcc: clock-controller@900000 {
@@ -448,14 +523,6 @@
 		};
 
 		/* Temporary fixed regulator */
-		vsdcc_fixed: vsdcc-regulator {
-			compatible = "regulator-fixed";
-			regulator-name = "SDCC Power";
-			regulator-min-microvolt = <2700000>;
-			regulator-max-microvolt = <2700000>;
-			regulator-always-on;
-		};
-
 		sdcc1bam:dma@12402000{
 			compatible = "qcom,bam-v1.3.0";
 			reg = <0x12402000 0x8000>;
@@ -505,7 +572,6 @@
 				non-removable;
 				cap-sd-highspeed;
 				cap-mmc-highspeed;
-				vmmc-supply = <&vsdcc_fixed>;
 				dmas = <&sdcc1bam 2>, <&sdcc1bam 1>;
 				dma-names = "tx", "rx";
 			};
@@ -524,7 +590,6 @@
 				cap-mmc-highspeed;
 				max-frequency	= <192000000>;
 				no-1-8-v;
-				vmmc-supply = <&vsdcc_fixed>;
 				dmas = <&sdcc3bam 2>, <&sdcc3bam 1>;
 				dma-names = "tx", "rx";
 			};
@@ -542,8 +607,6 @@
 				cap-sd-highspeed;
 				cap-mmc-highspeed;
 				max-frequency	= <48000000>;
-				vmmc-supply = <&vsdcc_fixed>;
-				vqmmc-supply = <&vsdcc_fixed>;
 				dmas = <&sdcc4bam 2>, <&sdcc4bam 1>;
 				dma-names = "tx", "rx";
 				pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/qcom-msm8660.dtsi b/arch/arm/boot/dts/qcom-msm8660.dtsi
index e0b2ce2910e0..ef2fe72b54c9 100644
--- a/arch/arm/boot/dts/qcom-msm8660.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8660.dtsi
@@ -67,15 +67,16 @@
 			cpu-offset = <0x40000>;
 		};
 
-		msmgpio: gpio@800000 {
-			compatible = "qcom,msm-gpio";
-			reg = <0x00800000 0x4000>;
+		tlmm: pinctrl@800000 {
+			compatible = "qcom,msm8660-pinctrl";
+			reg = <0x800000 0x4000>;
+
 			gpio-controller;
 			#gpio-cells = <2>;
-			ngpio = <173>;
 			interrupts = <0 16 0x4>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
+
 		};
 
 		gcc: clock-controller@900000 {
@@ -115,7 +116,7 @@
 
 			pmicintc: pmic@0 {
 				compatible = "qcom,pm8058";
-				interrupt-parent = <&msmgpio>;
+				interrupt-parent = <&tlmm>;
 				interrupts = <88 8>;
 				#interrupt-cells = <2>;
 				interrupt-controller;
diff --git a/arch/arm/boot/dts/qcom-msm8960-cdp.dts b/arch/arm/boot/dts/qcom-msm8960-cdp.dts
index 7f70fae90959..fad71d5527b0 100644
--- a/arch/arm/boot/dts/qcom-msm8960-cdp.dts
+++ b/arch/arm/boot/dts/qcom-msm8960-cdp.dts
@@ -26,6 +26,308 @@
 				status = "okay";
 			};
 		};
+
+		rpm@108000 {
+			regulators {
+				compatible = "qcom,rpm-pm8921-regulators";
+				vin_lvs1_3_6-supply = <&pm8921_s4>;
+				vin_lvs2-supply = <&pm8921_s4>;
+				vin_lvs4_5_7-supply = <&pm8921_s4>;
+				vdd_ncp-supply = <&pm8921_l6>;
+				vdd_l1_l2_l12_l18-supply = <&pm8921_s4>;
+				vdd_l21_l23_l29-supply = <&pm8921_s8>;
+				vdd_l24-supply = <&pm8921_s1>;
+				vdd_l25-supply = <&pm8921_s1>;
+				vdd_l27-supply = <&pm8921_s7>;
+				vdd_l28-supply = <&pm8921_s7>;
+
+				/* Buck SMPS */
+				pm8921_s1: s1 {
+					regulator-always-on;
+					regulator-min-microvolt = <1225000>;
+					regulator-max-microvolt = <1225000>;
+					qcom,switch-mode-frequency = <3200000>;
+					bias-pull-down;
+				};
+
+				pm8921_s2: s2 {
+					regulator-min-microvolt = <1300000>;
+					regulator-max-microvolt = <1300000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+
+				pm8921_s3: s3 {
+					regulator-min-microvolt = <500000>;
+					regulator-max-microvolt = <1150000>;
+					qcom,switch-mode-frequency = <4800000>;
+					bias-pull-down;
+				};
+
+				pm8921_s4: s4 {
+					regulator-always-on;
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+					qcom,force-mode = <QCOM_RPM_FORCE_MODE_AUTO>;
+				};
+
+				pm8921_s7: s7 {
+					regulator-min-microvolt = <1150000>;
+					regulator-max-microvolt = <1150000>;
+					qcom,switch-mode-frequency = <3200000>;
+					bias-pull-down;
+				};
+
+				pm8921_s8: s8 {
+					regulator-always-on;
+					regulator-min-microvolt = <2050000>;
+					regulator-max-microvolt = <2050000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+
+				/* PMOS LDO */
+				pm8921_l1: l1 {
+					regulator-always-on;
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+					bias-pull-down;
+				};
+
+				pm8921_l2: l2 {
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+
+				pm8921_l3: l3 {
+					regulator-min-microvolt = <3075000>;
+					regulator-max-microvolt = <3075000>;
+					bias-pull-down;
+				};
+
+				pm8921_l4: l4 {
+					regulator-always-on;
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+
+				pm8921_l5: l5 {
+					regulator-min-microvolt = <2950000>;
+					regulator-max-microvolt = <2950000>;
+					bias-pull-down;
+				};
+
+				pm8921_l6: l6 {
+					regulator-min-microvolt = <2950000>;
+					regulator-max-microvolt = <2950000>;
+					bias-pull-down;
+				};
+
+				pm8921_l7: l7 {
+					regulator-always-on;
+					regulator-min-microvolt = <1850000>;
+					regulator-max-microvolt = <2950000>;
+					bias-pull-down;
+				};
+
+				pm8921_l8: l8 {
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <3000000>;
+					bias-pull-down;
+				};
+
+				pm8921_l9: l9 {
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3000000>;
+					bias-pull-down;
+				};
+
+				pm8921_l10: l10 {
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3000000>;
+					bias-pull-down;
+				};
+
+				pm8921_l11: l11 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					bias-pull-down;
+				};
+
+				pm8921_l12: l12 {
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+
+				pm8921_l14: l14 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+
+				pm8921_l15: l15 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <2950000>;
+					bias-pull-down;
+				};
+
+				pm8921_l16: l16 {
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					bias-pull-down;
+				};
+
+				pm8921_l17: l17 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <2950000>;
+					bias-pull-down;
+				};
+
+				pm8921_l18: l18 {
+					regulator-min-microvolt = <1300000>;
+					regulator-max-microvolt = <1300000>;
+					bias-pull-down;
+				};
+
+				pm8921_l21: l21 {
+					regulator-min-microvolt = <1900000>;
+					regulator-max-microvolt = <1900000>;
+					bias-pull-down;
+				};
+
+				pm8921_l22: l22 {
+					regulator-min-microvolt = <2750000>;
+					regulator-max-microvolt = <2750000>;
+					bias-pull-down;
+				};
+
+				pm8921_l23: l23 {
+					regulator-always-on;
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+
+				pm8921_l24: l24 {
+					regulator-min-microvolt = <750000>;
+					regulator-max-microvolt = <1150000>;
+					bias-pull-down;
+				};
+
+				pm8921_l25: l25 {
+					regulator-always-on;
+					regulator-min-microvolt = <1250000>;
+					regulator-max-microvolt = <1250000>;
+					bias-pull-down;
+				};
+
+				/* Low Voltage Switch */
+				pm8921_lvs1: lvs1 {
+					bias-pull-down;
+				};
+
+				pm8921_lvs2: lvs2 {
+					bias-pull-down;
+				};
+
+				pm8921_lvs3: lvs3 {
+					bias-pull-down;
+				};
+
+				pm8921_lvs4: lvs4 {
+					bias-pull-down;
+				};
+
+				pm8921_lvs5: lvs5 {
+					bias-pull-down;
+				};
+
+				pm8921_lvs6: lvs6 {
+					bias-pull-down;
+				};
+
+				pm8921_lvs7: lvs7 {
+					bias-pull-down;
+				};
+
+				pm8921_ncp: ncp {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					qcom,switch-mode-frequency = <1600000>;
+				};
+			};
+		};
+
+		gsbi@16000000 {
+			status = "ok";
+			qcom,mode = <GSBI_PROT_SPI>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi1_default>;
+			spi@16080000 {
+				status = "ok";
+				eth@0 {
+					compatible = "micrel,ks8851";
+					reg = <0>;
+					interrupt-parent = <&msmgpio>;
+					interrupts = <90 8>;
+					spi-max-frequency = <5400000>;
+					vdd-supply = <&ext_l2>;
+					vdd-io-supply = <&pm8921_lvs6>;
+					reset-gpios = <&msmgpio 89 0>;
+				};
+			};
+		};
+
+		pinctrl@800000 {
+			spi1_default: spi1_default {
+				mux {
+					pins = "gpio6", "gpio7", "gpio9";
+					function = "gsbi1";
+				};
+
+				mosi {
+					pins = "gpio6";
+					drive-strength = <12>;
+					bias-disable;
+				};
+
+				miso {
+					pins = "gpio7";
+					drive-strength = <12>;
+					bias-disable;
+				};
+
+				cs {
+					pins = "gpio8";
+					drive-strength = <12>;
+					bias-disable;
+					output-low;
+				};
+
+				clk {
+					pins = "gpio9";
+					drive-strength = <12>;
+					bias-disable;
+				};
+			};
+		};
+	};
+
+	regulators {
+		compatible = "simple-bus";
+
+		ext_l2: gpio-regulator@91 {
+			compatible = "regulator-fixed";
+			regulator-name = "ext_l2";
+			gpio = <&msmgpio 91 0>;
+			startup-delay-us = <10000>;
+			enable-active-high;
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/qcom-msm8960.dtsi b/arch/arm/boot/dts/qcom-msm8960.dtsi
index a02b984cc68d..2096a94c9b52 100644
--- a/arch/arm/boot/dts/qcom-msm8960.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8960.dtsi
@@ -4,6 +4,7 @@
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/clock/qcom,gcc-msm8960.h>
+#include <dt-bindings/mfd/qcom-rpm.h>
 #include <dt-bindings/soc/qcom,gsbi.h>
 
 / {
@@ -73,11 +74,10 @@
 			cpu-offset = <0x80000>;
 		};
 
-		msmgpio: gpio@800000 {
-			compatible = "qcom,msm-gpio";
+		msmgpio: pinctrl@800000 {
+			compatible = "qcom,msm8960-pinctrl";
 			gpio-controller;
 			#gpio-cells = <2>;
-			ngpio = <150>;
 			interrupts = <0 16 0x4>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -105,6 +105,24 @@
 			#reset-cells = <1>;
 		};
 
+		l2cc: clock-controller@2011000 {
+			compatible	= "syscon";
+			reg		= <0x2011000 0x1000>;
+		};
+
+		rpm@108000 {
+			compatible	= "qcom,rpm-msm8960";
+			reg		= <0x108000 0x1000>;
+			qcom,ipc	= <&l2cc 0x8 2>;
+
+			interrupts	= <0 19 0>, <0 21 0>, <0 22 0>;
+			interrupt-names	= "ack", "err", "wakeup";
+
+			regulators {
+				compatible = "qcom,rpm-pm8921-regulators";
+			};
+		};
+
 		acc0: clock-controller@2088000 {
 			compatible = "qcom,kpss-acc-v1";
 			reg = <0x02088000 0x1000>, <0x02008000 0x1000>;
@@ -253,5 +271,30 @@
 			compatible = "qcom,tcsr-msm8960", "syscon";
 			reg = <0x1a400000 0x100>;
 		};
+
+		gsbi@16000000 {
+			compatible = "qcom,gsbi-v1.0.0";
+			cell-index = <1>;
+			reg = <0x16000000 0x100>;
+			clocks = <&gcc GSBI1_H_CLK>;
+			clock-names = "iface";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			spi@16080000 {
+				compatible = "qcom,spi-qup-v1.1.1";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x16080000 0x1000>;
+				interrupts = <0 147 0>;
+				spi-max-frequency = <24000000>;
+				cs-gpios = <&msmgpio 8 0>;
+
+				clocks = <&gcc GSBI1_QUP_CLK>, <&gcc GSBI1_H_CLK>;
+				clock-names = "core", "iface";
+				status = "disabled";
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
index bd35b0674ff6..9bc72a3356e4 100644
--- a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
+++ b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
@@ -17,3 +17,13 @@
 		status = "ok";
 	};
 };
+
+&spmi_bus {
+	pm8941@0 {
+		coincell@2800 {
+			status = "ok";
+			qcom,rset-ohms = <2100>;
+			qcom,vset-millivolts = <3000>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi
index 37b47b5538b8..d7c99b894a49 100644
--- a/arch/arm/boot/dts/qcom-msm8974.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8974.dtsi
@@ -9,6 +9,17 @@
 	compatible = "qcom,msm8974";
 	interrupt-parent = <&intc>;
 
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		smem_region: smem@fa00000 {
+			reg = <0xfa00000 0x200000>;
+			no-map;
+		};
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -220,6 +231,11 @@
 			reg = <0xfc400000 0x4000>;
 		};
 
+		tcsr_mutex_block: syscon@fd484000 {
+			compatible = "syscon";
+			reg = <0xfd484000 0x2000>;
+		};
+
 		mmcc: clock-controller@fd8c0000 {
 			compatible = "qcom,mmcc-msm8974";
 			#clock-cells = <1>;
@@ -227,6 +243,22 @@
 			reg = <0xfd8c0000 0x6000>;
 		};
 
+		tcsr_mutex: tcsr-mutex {
+			compatible = "qcom,tcsr-mutex";
+			syscon = <&tcsr_mutex_block 0 0x80>;
+
+			#hwlock-cells = <1>;
+		};
+
+		smem@fa00000 {
+			compatible = "qcom,smem";
+
+			memory-region = <&smem_region>;
+			reg = <0xfc428000 0x4000>;
+
+			hwlocks = <&tcsr_mutex 3>;
+		};
+
 		serial@f991e000 {
 			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
 			reg = <0xf991e000 0x1000>;
diff --git a/arch/arm/boot/dts/qcom-pm8941.dtsi b/arch/arm/boot/dts/qcom-pm8941.dtsi
index aa774e685018..968f1043d4f5 100644
--- a/arch/arm/boot/dts/qcom-pm8941.dtsi
+++ b/arch/arm/boot/dts/qcom-pm8941.dtsi
@@ -125,6 +125,12 @@
 			interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>;
 			qcom,external-resistor-micro-ohms = <10000>;
 		};
+
+		coincell@2800 {
+			compatible = "qcom,pm8941-coincell";
+			reg = <0x2800>;
+			status = "disabled";
+		};
 	};
 
 	usid1: pm8941@1 {
diff --git a/arch/arm/boot/dts/r7s72100.dtsi b/arch/arm/boot/dts/r7s72100.dtsi
index 277e73c110e5..060c32cbd669 100644
--- a/arch/arm/boot/dts/r7s72100.dtsi
+++ b/arch/arm/boot/dts/r7s72100.dtsi
@@ -86,6 +86,7 @@
 			reg = <0xfcfe0000 0x18>;
 			clocks = <&extal_clk>, <&usb_x1_clk>;
 			clock-output-names = "pll", "i", "g";
+			#power-domain-cells = <0>;
 		};
 
 		/* MSTP clocks */
@@ -157,6 +158,7 @@
 			     <0 189 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF0>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -169,6 +171,7 @@
 			     <0 193 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF1>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -181,6 +184,7 @@
 			     <0 197 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF2>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -193,6 +197,7 @@
 			     <0 201 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF3>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -205,6 +210,7 @@
 			     <0 205 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF4>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -217,6 +223,7 @@
 			     <0 209 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF5>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -229,6 +236,7 @@
 			     <0 213 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF6>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -241,6 +249,7 @@
 			     <0 217 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R7S72100_CLK_SCIF7>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -252,6 +261,7 @@
 			     <0 240 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "error", "rx", "tx";
 		clocks = <&mstp10_clks R7S72100_CLK_SPI0>;
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -266,6 +276,7 @@
 			     <0 243 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "error", "rx", "tx";
 		clocks = <&mstp10_clks R7S72100_CLK_SPI1>;
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -280,6 +291,7 @@
 			     <0 246 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "error", "rx", "tx";
 		clocks = <&mstp10_clks R7S72100_CLK_SPI2>;
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -294,6 +306,7 @@
 			     <0 249 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "error", "rx", "tx";
 		clocks = <&mstp10_clks R7S72100_CLK_SPI3>;
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -308,6 +321,7 @@
 			     <0 252 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "error", "rx", "tx";
 		clocks = <&mstp10_clks R7S72100_CLK_SPI4>;
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -338,6 +352,7 @@
 			     <0 164 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R7S72100_CLK_I2C0>;
 		clock-frequency = <100000>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -356,6 +371,7 @@
 			     <0 172 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R7S72100_CLK_I2C1>;
 		clock-frequency = <100000>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -374,6 +390,7 @@
 			     <0 180 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R7S72100_CLK_I2C2>;
 		clock-frequency = <100000>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -392,6 +409,7 @@
 			     <0 188 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R7S72100_CLK_I2C3>;
 		clock-frequency = <100000>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -402,6 +420,7 @@
 		interrupt-names = "tgi0a";
 		clocks = <&mstp3_clks R7S72100_CLK_MTU2>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 };
diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi
index 7ee22a41c6c9..cb4f7b2798fe 100644
--- a/arch/arm/boot/dts/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/r8a73a4.dtsi
@@ -207,6 +207,13 @@
 		reg = <0 0xe6050000 0 0x9000>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges =
+			<&pfc 0 0 31>, <&pfc 32 32 9>,
+			<&pfc 64 64 22>, <&pfc 96 96 31>,
+			<&pfc 128 128 7>, <&pfc 160 160 19>,
+			<&pfc 192 192 31>, <&pfc 224 224 27>,
+			<&pfc 256 256 28>, <&pfc 288 288 21>,
+			<&pfc 320 320 10>;
 		interrupts-extended =
 			<&irqc0  0 0>, <&irqc0  1 0>, <&irqc0  2 0>, <&irqc0  3 0>,
 			<&irqc0  4 0>, <&irqc0  5 0>, <&irqc0  6 0>, <&irqc0  7 0>,
@@ -434,7 +441,7 @@
 	};
 
 	gic: interrupt-controller@f1001000 {
-		compatible = "arm,cortex-a15-gic";
+		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
 		#address-cells = <0>;
 		interrupt-controller;
diff --git a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
index 2e31d8c01cbf..105d9c95de4a 100644
--- a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
+++ b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
@@ -224,6 +224,9 @@
 };
 
 &pfc {
+	pinctrl-0 = <&lcd0_pins>;
+	pinctrl-names = "default";
+
 	ether_pins: ether {
 		renesas,groups = "gether_mii", "gether_int";
 		renesas,function = "gether";
@@ -259,6 +262,16 @@
 				 "fsia_data_in_1", "fsia_data_out_0";
 		renesas,function = "fsia";
 	};
+
+	lcd0_pins: lcd0 {
+		renesas,groups = "lcd0_data24_0", "lcd0_lclk_1", "lcd0_sync";
+		renesas,function = "lcd0";
+
+		/* DBGMD/LCDC0/FSIA MUX */
+		gpio-hog;
+		gpios = <176 0>;
+		output-high;
+	};
 };
 
 &tpu {
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index d84714468cce..e14cb1438216 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -291,6 +291,7 @@
 		      <0xe605800c 0x20>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&pfc 0 0 212>;
 		interrupts-extended =
 			<&irqpin0 0 0>, <&irqpin0 1 0>, <&irqpin0 2 0>, <&irqpin0 3 0>,
 			<&irqpin0 4 0>, <&irqpin0 5 0>, <&irqpin0 6 0>, <&irqpin0 7 0>,
diff --git a/arch/arm/boot/dts/r8a7778.dtsi b/arch/arm/boot/dts/r8a7778.dtsi
index 7ce9f5fd5865..4b1fa9f42ad5 100644
--- a/arch/arm/boot/dts/r8a7778.dtsi
+++ b/arch/arm/boot/dts/r8a7778.dtsi
@@ -53,6 +53,7 @@
 		reg = <0xfde00000 0x400>;
 		interrupts = <0 105 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7778_CLK_ETHER>;
+		power-domains = <&cpg_clocks>;
 		phy-mode = "rmii";
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -152,6 +153,7 @@
 		reg = <0xffc70000 0x1000>;
 		interrupts = <0 67 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_I2C0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -162,6 +164,7 @@
 		reg = <0xffc71000 0x1000>;
 		interrupts = <0 78 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_I2C1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -172,6 +175,7 @@
 		reg = <0xffc72000 0x1000>;
 		interrupts = <0 76 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_I2C2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -182,6 +186,7 @@
 		reg = <0xffc73000 0x1000>;
 		interrupts = <0 77 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_I2C3>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -193,6 +198,7 @@
 			     <0 34 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_TMU0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		#renesas,channels = <3>;
 
@@ -207,6 +213,7 @@
 			     <0 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_TMU1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		#renesas,channels = <3>;
 
@@ -221,6 +228,7 @@
 			     <0 42 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_TMU2>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		#renesas,channels = <3>;
 
@@ -288,6 +296,7 @@
 		interrupts = <0 70 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_SCIF0>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -297,6 +306,7 @@
 		interrupts = <0 71 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_SCIF1>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -306,6 +316,7 @@
 		interrupts = <0 72 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_SCIF2>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -315,6 +326,7 @@
 		interrupts = <0 73 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_SCIF3>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -324,6 +336,7 @@
 		interrupts = <0 74 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_SCIF4>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -333,6 +346,7 @@
 		interrupts = <0 75 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_SCIF5>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -341,6 +355,7 @@
 		reg = <0xffe4e000 0x100>;
 		interrupts = <0 61 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_MMC>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -349,6 +364,7 @@
 		reg = <0xffe4c000 0x100>;
 		interrupts = <0 87 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_SDHI0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -357,6 +373,7 @@
 		reg = <0xffe4d000 0x100>;
 		interrupts = <0 88 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_SDHI1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -365,6 +382,7 @@
 		reg = <0xffe4f000 0x100>;
 		interrupts = <0 86 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_SDHI2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -373,6 +391,7 @@
 		reg = <0xfffc7000 0x18>;
 		interrupts = <0 63 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_HSPI>;
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -383,6 +402,7 @@
 		reg = <0xfffc8000 0x18>;
 		interrupts = <0 84 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_HSPI>;
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -393,6 +413,7 @@
 		reg = <0xfffc6000 0x18>;
 		interrupts = <0 85 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7778_CLK_HSPI>;
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -419,6 +440,7 @@
 			clocks = <&extal_clk>;
 			clock-output-names = "plla", "pllb", "b",
 					     "out", "p", "s", "s1";
+			#power-domain-cells = <0>;
 		};
 
 		/* Audio clocks; frequencies are set by boards if applicable. */
diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi
index 5c8071e87ae9..6afa909865b5 100644
--- a/arch/arm/boot/dts/r8a7779.dtsi
+++ b/arch/arm/boot/dts/r8a7779.dtsi
@@ -148,7 +148,7 @@
 		interrupt-controller;
 	};
 
-	irqpin0: interrupt-controller@fe780010 {
+	irqpin0: interrupt-controller@fe78001c {
 		compatible = "renesas,intc-irqpin-r8a7779", "renesas,intc-irqpin";
 		#interrupt-cells = <2>;
 		status = "disabled";
@@ -157,7 +157,8 @@
 			<0xfe780010 4>,
 			<0xfe780024 4>,
 			<0xfe780044 4>,
-			<0xfe780064 4>;
+			<0xfe780064 4>,
+			<0xfe780000 4>;
 		interrupts = <0 27 IRQ_TYPE_LEVEL_HIGH
 			      0 28 IRQ_TYPE_LEVEL_HIGH
 			      0 29 IRQ_TYPE_LEVEL_HIGH
@@ -172,6 +173,7 @@
 		reg = <0xffc70000 0x1000>;
 		interrupts = <0 79 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_I2C0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -182,6 +184,7 @@
 		reg = <0xffc71000 0x1000>;
 		interrupts = <0 82 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_I2C1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -192,6 +195,7 @@
 		reg = <0xffc72000 0x1000>;
 		interrupts = <0 80 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_I2C2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -202,6 +206,7 @@
 		reg = <0xffc73000 0x1000>;
 		interrupts = <0 81 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_I2C3>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -211,6 +216,7 @@
 		interrupts = <0 88 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_SCIF0>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -220,6 +226,7 @@
 		interrupts = <0 89 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_SCIF1>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -229,6 +236,7 @@
 		interrupts = <0 90 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_SCIF2>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -238,6 +246,7 @@
 		interrupts = <0 91 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_SCIF3>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -247,6 +256,7 @@
 		interrupts = <0 92 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_SCIF4>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -256,6 +266,7 @@
 		interrupts = <0 93 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_SCIF5>;
 		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -277,6 +288,7 @@
 			     <0 34 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_TMU0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		#renesas,channels = <3>;
 
@@ -291,6 +303,7 @@
 			     <0 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_TMU1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		#renesas,channels = <3>;
 
@@ -305,6 +318,7 @@
 			     <0 42 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7779_CLK_TMU2>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		#renesas,channels = <3>;
 
@@ -316,6 +330,7 @@
 		reg = <0xfc600000 0x2000>;
 		interrupts = <0 100 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7779_CLK_SATA>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	sdhi0: sd@ffe4c000 {
@@ -323,6 +338,7 @@
 		reg = <0xffe4c000 0x100>;
 		interrupts = <0 104 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -331,6 +347,7 @@
 		reg = <0xffe4d000 0x100>;
 		interrupts = <0 105 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -339,6 +356,7 @@
 		reg = <0xffe4e000 0x100>;
 		interrupts = <0 107 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -347,6 +365,7 @@
 		reg = <0xffe4f000 0x100>;
 		interrupts = <0 106 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI3>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -357,6 +376,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&mstp0_clks R8A7779_CLK_HSPI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -367,6 +387,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&mstp0_clks R8A7779_CLK_HSPI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -377,6 +398,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&mstp0_clks R8A7779_CLK_HSPI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -385,6 +407,7 @@
 		reg = <0 0xfff80000 0 0x40000>;
 		interrupts = <0 31 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7779_CLK_DU>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		ports {
@@ -426,6 +449,7 @@
 			#clock-cells = <1>;
 			clock-output-names = "plla", "z", "zs", "s",
 					     "s1", "p", "b", "out";
+			#power-domain-cells = <0>;
 		};
 
 		/* Fixed factor clocks */
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 2eb8a995ae9f..37dec5269491 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -174,7 +174,7 @@
 			  1800000 0>;
 	};
 
-	sound {
+	rsnd_ak4643: sound {
 		compatible = "simple-audio-card";
 
 		simple-audio-card,format = "left_j";
@@ -548,7 +548,7 @@
 		compatible = "adi,adv7511w";
 		reg = <0x39>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <15 IRQ_TYPE_EDGE_FALLING>;
+		interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
 
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 51ab8865ea37..a0b2a79cbfbd 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -113,7 +113,7 @@
 	};
 
 	gic: interrupt-controller@f1001000 {
-		compatible = "arm,cortex-a15-gic";
+		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
 		#address-cells = <0>;
 		interrupt-controller;
@@ -134,6 +134,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7790_CLK_GPIO0>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio1: gpio@e6051000 {
@@ -146,6 +147,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7790_CLK_GPIO1>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio2: gpio@e6052000 {
@@ -158,6 +160,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7790_CLK_GPIO2>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio3: gpio@e6053000 {
@@ -170,6 +173,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7790_CLK_GPIO3>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio4: gpio@e6054000 {
@@ -182,6 +186,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7790_CLK_GPIO4>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio5: gpio@e6055000 {
@@ -194,6 +199,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7790_CLK_GPIO5>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	thermal@e61f0000 {
@@ -201,6 +207,7 @@
 		reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
 		interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	timer {
@@ -218,6 +225,7 @@
 			     <0 143 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_CMT0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		renesas,channels-mask = <0x60>;
 
@@ -237,6 +245,7 @@
 			     <0 127 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_CMT1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		renesas,channels-mask = <0xff>;
 
@@ -253,6 +262,7 @@
 			     <0 2 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 3 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R8A7790_CLK_IRQC>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	dmac0: dma-controller@e6700000 {
@@ -281,6 +291,7 @@
 				"ch12", "ch13", "ch14";
 		clocks = <&mstp2_clks R8A7790_CLK_SYS_DMAC0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
@@ -311,6 +322,7 @@
 				"ch12", "ch13", "ch14";
 		clocks = <&mstp2_clks R8A7790_CLK_SYS_DMAC1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
@@ -339,6 +351,7 @@
 				"ch12";
 		clocks = <&mstp5_clks R8A7790_CLK_AUDIO_DMAC0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <13>;
 	};
@@ -367,6 +380,7 @@
 				"ch12";
 		clocks = <&mstp5_clks R8A7790_CLK_AUDIO_DMAC1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <13>;
 	};
@@ -378,6 +392,7 @@
 			      0 109 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "ch0", "ch1";
 		clocks = <&mstp3_clks R8A7790_CLK_USBDMAC0>;
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <2>;
 	};
@@ -389,6 +404,7 @@
 			      0 110 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "ch0", "ch1";
 		clocks = <&mstp3_clks R8A7790_CLK_USBDMAC1>;
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <2>;
 	};
@@ -400,6 +416,7 @@
 		reg = <0 0xe6508000 0 0x40>;
 		interrupts = <0 287 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7790_CLK_I2C0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -410,6 +427,7 @@
 		reg = <0 0xe6518000 0 0x40>;
 		interrupts = <0 288 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7790_CLK_I2C1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -420,6 +438,7 @@
 		reg = <0 0xe6530000 0 0x40>;
 		interrupts = <0 286 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7790_CLK_I2C2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -430,6 +449,7 @@
 		reg = <0 0xe6540000 0 0x40>;
 		interrupts = <0 290 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7790_CLK_I2C3>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -442,6 +462,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_IIC0>;
 		dmas = <&dmac0 0x61>, <&dmac0 0x62>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -454,6 +475,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_IIC1>;
 		dmas = <&dmac0 0x65>, <&dmac0 0x66>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -466,6 +488,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_IIC2>;
 		dmas = <&dmac0 0x69>, <&dmac0 0x6a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -478,6 +501,7 @@
 		clocks = <&mstp9_clks R8A7790_CLK_IICDVFS>;
 		dmas = <&dmac0 0x77>, <&dmac0 0x78>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -488,6 +512,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_MMCIF0>;
 		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		reg-io-width = <4>;
 		status = "disabled";
 		max-frequency = <97500000>;
@@ -500,6 +525,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_MMCIF1>;
 		dmas = <&dmac0 0xe1>, <&dmac0 0xe2>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		reg-io-width = <4>;
 		status = "disabled";
 		max-frequency = <97500000>;
@@ -517,6 +543,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI0>;
 		dmas = <&dmac1 0xcd>, <&dmac1 0xce>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -527,6 +554,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI1>;
 		dmas = <&dmac1 0xc9>, <&dmac1 0xca>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -537,6 +565,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI2>;
 		dmas = <&dmac1 0xc1>, <&dmac1 0xc2>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -547,6 +576,7 @@
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI3>;
 		dmas = <&dmac1 0xd3>, <&dmac1 0xd4>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -558,6 +588,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -569,6 +600,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -580,6 +612,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -591,6 +624,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -602,6 +636,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -613,6 +648,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -624,6 +660,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -635,6 +672,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -646,6 +684,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -657,6 +696,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -665,17 +705,30 @@
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7790_CLK_ETHER>;
+		power-domains = <&cpg_clocks>;
 		phy-mode = "rmii";
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
 	};
 
+	avb: ethernet@e6800000 {
+		compatible = "renesas,etheravb-r8a7790";
+		reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>;
+		interrupts = <0 163 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7790_CLK_ETHERAVB>;
+		power-domains = <&cpg_clocks>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
 	sata0: sata@ee300000 {
 		compatible = "renesas,sata-r8a7790";
 		reg = <0 0xee300000 0 0x2000>;
 		interrupts = <0 105 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7790_CLK_SATA0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -684,6 +737,7 @@
 		reg = <0 0xee500000 0 0x2000>;
 		interrupts = <0 106 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7790_CLK_SATA1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -692,12 +746,13 @@
 		reg = <0 0xe6590000 0 0x100>;
 		interrupts = <0 107 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp7_clks R8A7790_CLK_HSUSB>;
-		renesas,buswait = <4>;
-		phys = <&usb0 1>;
-		phy-names = "usb";
 		dmas = <&usb_dmac0 0>, <&usb_dmac0 1>,
 		       <&usb_dmac1 0>, <&usb_dmac1 1>;
 		dma-names = "ch0", "ch1", "ch2", "ch3";
+		power-domains = <&cpg_clocks>;
+		renesas,buswait = <4>;
+		phys = <&usb0 1>;
+		phy-names = "usb";
 		status = "disabled";
 	};
 
@@ -708,6 +763,7 @@
 		#size-cells = <0>;
 		clocks = <&mstp7_clks R8A7790_CLK_HSUSB>;
 		clock-names = "usbhs";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		usb0: usb-channel@0 {
@@ -722,33 +778,37 @@
 
 	vin0: video@e6ef0000 {
 		compatible = "renesas,vin-r8a7790";
-		clocks = <&mstp8_clks R8A7790_CLK_VIN0>;
 		reg = <0 0xe6ef0000 0 0x1000>;
 		interrupts = <0 188 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7790_CLK_VIN0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
 	vin1: video@e6ef1000 {
 		compatible = "renesas,vin-r8a7790";
-		clocks = <&mstp8_clks R8A7790_CLK_VIN1>;
 		reg = <0 0xe6ef1000 0 0x1000>;
 		interrupts = <0 189 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7790_CLK_VIN1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
 	vin2: video@e6ef2000 {
 		compatible = "renesas,vin-r8a7790";
-		clocks = <&mstp8_clks R8A7790_CLK_VIN2>;
 		reg = <0 0xe6ef2000 0 0x1000>;
 		interrupts = <0 190 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7790_CLK_VIN2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
 	vin3: video@e6ef3000 {
 		compatible = "renesas,vin-r8a7790";
-		clocks = <&mstp8_clks R8A7790_CLK_VIN3>;
 		reg = <0 0xe6ef3000 0 0x1000>;
 		interrupts = <0 191 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7790_CLK_VIN3>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -757,6 +817,7 @@
 		reg = <0 0xfe920000 0 0x8000>;
 		interrupts = <0 266 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_VSP1_R>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-sru;
 		renesas,#rpf = <5>;
@@ -769,6 +830,7 @@
 		reg = <0 0xfe928000 0 0x8000>;
 		interrupts = <0 267 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_VSP1_S>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-lut;
 		renesas,has-sru;
@@ -782,6 +844,7 @@
 		reg = <0 0xfe930000 0 0x8000>;
 		interrupts = <0 246 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_VSP1_DU0>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-lif;
 		renesas,has-lut;
@@ -795,6 +858,7 @@
 		reg = <0 0xfe938000 0 0x8000>;
 		interrupts = <0 247 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_VSP1_DU1>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-lif;
 		renesas,has-lut;
@@ -849,6 +913,7 @@
 		clocks = <&mstp9_clks R8A7790_CLK_RCAN0>,
 			 <&cpg_clocks R8A7790_CLK_RCAN>, <&can_clk>;
 		clock-names = "clkp1", "clkp2", "can_clk";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -859,9 +924,18 @@
 		clocks = <&mstp9_clks R8A7790_CLK_RCAN1>,
 			 <&cpg_clocks R8A7790_CLK_RCAN>, <&can_clk>;
 		clock-names = "clkp1", "clkp2", "can_clk";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
+	jpu: jpeg-codec@fe980000 {
+		compatible = "renesas,jpu-r8a7790";
+		reg = <0 0xfe980000 0 0x10300>;
+		interrupts = <0 272 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7790_CLK_JPU>;
+		power-domains = <&cpg_clocks>;
+	};
+
 	clocks {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -936,6 +1010,7 @@
 			clock-output-names = "main", "pll0", "pll1", "pll3",
 					     "lb", "qspi", "sdh", "sd0", "sd1",
 					     "z", "rcan", "adsp";
+			#power-domain-cells = <0>;
 		};
 
 		/* Variable factor clocks */
@@ -1249,16 +1324,18 @@
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150990 0 4>, <0 0xe61509a0 0 4>;
 			clocks = <&hp_clk>, <&zg_clk>, <&zg_clk>, <&zg_clk>,
-			         <&zg_clk>, <&p_clk>, <&zs_clk>, <&zs_clk>;
+			         <&zg_clk>, <&hp_clk>, <&p_clk>, <&zs_clk>,
+				 <&zs_clk>;
 			#clock-cells = <1>;
 			clock-indices = <
 				R8A7790_CLK_MLB R8A7790_CLK_VIN3 R8A7790_CLK_VIN2
-				R8A7790_CLK_VIN1 R8A7790_CLK_VIN0 R8A7790_CLK_ETHER
+				R8A7790_CLK_VIN1 R8A7790_CLK_VIN0
+				R8A7790_CLK_ETHERAVB R8A7790_CLK_ETHER
 				R8A7790_CLK_SATA1 R8A7790_CLK_SATA0
 			>;
 			clock-output-names =
-				"mlb", "vin3", "vin2", "vin1", "vin0", "ether",
-				"sata1", "sata0";
+				"mlb", "vin3", "vin2", "vin1", "vin0",
+				"etheravb", "ether", "sata1", "sata0";
 		};
 		mstp9_clks: mstp9_clks@e6150994 {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
@@ -1291,6 +1368,7 @@
 				<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>,
 				<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>,
 				<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>,
+				<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>,
 				<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>;
 
 			#clock-cells = <1>;
@@ -1300,6 +1378,7 @@
 				R8A7790_CLK_SSI4 R8A7790_CLK_SSI3 R8A7790_CLK_SSI2 R8A7790_CLK_SSI1 R8A7790_CLK_SSI0
 				R8A7790_CLK_SCU_ALL
 				R8A7790_CLK_SCU_DVC1 R8A7790_CLK_SCU_DVC0
+				R8A7790_CLK_SCU_CTU1_MIX1 R8A7790_CLK_SCU_CTU0_MIX0
 				R8A7790_CLK_SCU_SRC9 R8A7790_CLK_SCU_SRC8 R8A7790_CLK_SCU_SRC7 R8A7790_CLK_SCU_SRC6 R8A7790_CLK_SCU_SRC5
 				R8A7790_CLK_SCU_SRC4 R8A7790_CLK_SCU_SRC3 R8A7790_CLK_SCU_SRC2 R8A7790_CLK_SCU_SRC1 R8A7790_CLK_SCU_SRC0
 			>;
@@ -1309,6 +1388,7 @@
 				"ssi4", "ssi3", "ssi2", "ssi1", "ssi0",
 				"scu-all",
 				"scu-dvc1", "scu-dvc0",
+				"scu-ctu1-mix1", "scu-ctu0-mix0",
 				"scu-src9", "scu-src8", "scu-src7", "scu-src6", "scu-src5",
 				"scu-src4", "scu-src3", "scu-src2", "scu-src1", "scu-src0";
 		};
@@ -1321,6 +1401,7 @@
 		clocks = <&mstp9_clks R8A7790_CLK_QSPI_MOD>;
 		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1334,6 +1415,7 @@
 		clocks = <&mstp0_clks R8A7790_CLK_MSIOF0>;
 		dmas = <&dmac0 0x51>, <&dmac0 0x52>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1346,6 +1428,7 @@
 		clocks = <&mstp2_clks R8A7790_CLK_MSIOF1>;
 		dmas = <&dmac0 0x55>, <&dmac0 0x56>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1358,6 +1441,7 @@
 		clocks = <&mstp2_clks R8A7790_CLK_MSIOF2>;
 		dmas = <&dmac0 0x41>, <&dmac0 0x42>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1370,6 +1454,7 @@
 		clocks = <&mstp2_clks R8A7790_CLK_MSIOF3>;
 		dmas = <&dmac0 0x45>, <&dmac0 0x46>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1380,6 +1465,7 @@
 		reg = <0 0xee000000 0 0xc00>;
 		interrupts = <0 101 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_SSUSB>;
+		power-domains = <&cpg_clocks>;
 		phys = <&usb2 1>;
 		phy-names = "usb";
 		status = "disabled";
@@ -1388,10 +1474,11 @@
 	pci0: pci@ee090000 {
 		compatible = "renesas,pci-r8a7790";
 		device_type = "pci";
-		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
 		reg = <0 0xee090000 0 0xc00>,
 		      <0 0xee080000 0 0x1100>;
 		interrupts = <0 108 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		bus-range = <0 0>;
@@ -1422,10 +1509,11 @@
 	pci1: pci@ee0b0000 {
 		compatible = "renesas,pci-r8a7790";
 		device_type = "pci";
-		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
 		reg = <0 0xee0b0000 0 0xc00>,
 		      <0 0xee0a0000 0 0x1100>;
 		interrupts = <0 112 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		bus-range = <1 1>;
@@ -1443,6 +1531,7 @@
 		compatible = "renesas,pci-r8a7790";
 		device_type = "pci";
 		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
+		power-domains = <&cpg_clocks>;
 		reg = <0 0xee0d0000 0 0xc00>,
 		      <0 0xee0c0000 0 0x1100>;
 		interrupts = <0 113 IRQ_TYPE_LEVEL_HIGH>;
@@ -1495,6 +1584,7 @@
 		interrupt-map = <0 0 0 0 &gic 0 116 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_PCIEC>, <&pcie_bus_clk>;
 		clock-names = "pcie", "pcie_bus";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -1524,6 +1614,8 @@
 			<&mstp10_clks R8A7790_CLK_SCU_SRC5>, <&mstp10_clks R8A7790_CLK_SCU_SRC4>,
 			<&mstp10_clks R8A7790_CLK_SCU_SRC3>, <&mstp10_clks R8A7790_CLK_SCU_SRC2>,
 			<&mstp10_clks R8A7790_CLK_SCU_SRC1>, <&mstp10_clks R8A7790_CLK_SCU_SRC0>,
+			<&mstp10_clks R8A7790_CLK_SCU_CTU0_MIX0>, <&mstp10_clks R8A7790_CLK_SCU_CTU1_MIX1>,
+			<&mstp10_clks R8A7790_CLK_SCU_CTU0_MIX0>, <&mstp10_clks R8A7790_CLK_SCU_CTU1_MIX1>,
 			<&mstp10_clks R8A7790_CLK_SCU_DVC0>, <&mstp10_clks R8A7790_CLK_SCU_DVC1>,
 			<&audio_clk_a>, <&audio_clk_b>, <&audio_clk_c>, <&m2_clk>;
 		clock-names = "ssi-all",
@@ -1531,6 +1623,8 @@
 				"ssi.4", "ssi.3", "ssi.2", "ssi.1", "ssi.0",
 				"src.9", "src.8", "src.7", "src.6", "src.5",
 				"src.4", "src.3", "src.2", "src.1", "src.0",
+				"ctu.0", "ctu.1",
+				"mix.0", "mix.1",
 				"dvc.0", "dvc.1",
 				"clk_a", "clk_b", "clk_c", "clk_i";
 
@@ -1547,6 +1641,22 @@
 			};
 		};
 
+		rcar_sound,mix {
+			mix0: mix@0 { };
+			mix1: mix@1 { };
+		};
+
+		rcar_sound,ctu {
+			ctu00: ctu@0 { };
+			ctu01: ctu@1 { };
+			ctu02: ctu@2 { };
+			ctu03: ctu@3 { };
+			ctu10: ctu@4 { };
+			ctu11: ctu@5 { };
+			ctu12: ctu@6 { };
+			ctu13: ctu@7 { };
+		};
+
 		rcar_sound,src {
 			src0: src@0 {
 				interrupts = <0 352 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index cffe33ff4d16..dc158845afdc 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -242,7 +242,7 @@
 			  1800000 0>;
 	};
 
-	sound {
+	rsnd_ak4643: sound {
 		compatible = "simple-audio-card";
 
 		simple-audio-card,format = "left_j";
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index dc1cd3f16606..831525dd39a6 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -70,7 +70,7 @@
 	};
 
 	gic: interrupt-controller@f1001000 {
-		compatible = "arm,cortex-a15-gic";
+		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
 		#address-cells = <0>;
 		interrupt-controller;
@@ -91,6 +91,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO0>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio1: gpio@e6051000 {
@@ -103,6 +104,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO1>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio2: gpio@e6052000 {
@@ -115,6 +117,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO2>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio3: gpio@e6053000 {
@@ -127,6 +130,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO3>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio4: gpio@e6054000 {
@@ -139,6 +143,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO4>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio5: gpio@e6055000 {
@@ -151,6 +156,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO5>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio6: gpio@e6055400 {
@@ -163,6 +169,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO6>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	gpio7: gpio@e6055800 {
@@ -175,6 +182,7 @@
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		clocks = <&mstp9_clks R8A7791_CLK_GPIO7>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	thermal@e61f0000 {
@@ -182,6 +190,7 @@
 		reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
 		interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp5_clks R8A7791_CLK_THERMAL>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	timer {
@@ -199,6 +208,7 @@
 			     <0 143 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7791_CLK_CMT0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		renesas,channels-mask = <0x60>;
 
@@ -218,6 +228,7 @@
 			     <0 127 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_CMT1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		renesas,channels-mask = <0xff>;
 
@@ -240,6 +251,7 @@
 			     <0 16 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 17 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R8A7791_CLK_IRQC>;
+		power-domains = <&cpg_clocks>;
 	};
 
 	dmac0: dma-controller@e6700000 {
@@ -268,6 +280,7 @@
 				"ch12", "ch13", "ch14";
 		clocks = <&mstp2_clks R8A7791_CLK_SYS_DMAC0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
@@ -298,6 +311,7 @@
 				"ch12", "ch13", "ch14";
 		clocks = <&mstp2_clks R8A7791_CLK_SYS_DMAC1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
@@ -326,6 +340,7 @@
 				"ch12";
 		clocks = <&mstp5_clks R8A7791_CLK_AUDIO_DMAC0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <13>;
 	};
@@ -354,6 +369,7 @@
 				"ch12";
 		clocks = <&mstp5_clks R8A7791_CLK_AUDIO_DMAC1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <13>;
 	};
@@ -365,6 +381,7 @@
 			      0 109 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "ch0", "ch1";
 		clocks = <&mstp3_clks R8A7791_CLK_USBDMAC0>;
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <2>;
 	};
@@ -376,6 +393,7 @@
 			      0 110 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "ch0", "ch1";
 		clocks = <&mstp3_clks R8A7791_CLK_USBDMAC1>;
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <2>;
 	};
@@ -388,6 +406,7 @@
 		reg = <0 0xe6508000 0 0x40>;
 		interrupts = <0 287 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_I2C0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -398,6 +417,7 @@
 		reg = <0 0xe6518000 0 0x40>;
 		interrupts = <0 288 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_I2C1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -408,6 +428,7 @@
 		reg = <0 0xe6530000 0 0x40>;
 		interrupts = <0 286 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_I2C2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -418,6 +439,7 @@
 		reg = <0 0xe6540000 0 0x40>;
 		interrupts = <0 290 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_I2C3>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -428,6 +450,7 @@
 		reg = <0 0xe6520000 0 0x40>;
 		interrupts = <0 19 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_I2C4>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -439,6 +462,7 @@
 		reg = <0 0xe6528000 0 0x40>;
 		interrupts = <0 20 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_I2C5>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -452,6 +476,7 @@
 		clocks = <&mstp9_clks R8A7791_CLK_IICDVFS>;
 		dmas = <&dmac0 0x77>, <&dmac0 0x78>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -464,6 +489,7 @@
 		clocks = <&mstp3_clks R8A7791_CLK_IIC0>;
 		dmas = <&dmac0 0x61>, <&dmac0 0x62>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -476,6 +502,7 @@
 		clocks = <&mstp3_clks R8A7791_CLK_IIC1>;
 		dmas = <&dmac0 0x65>, <&dmac0 0x66>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -492,6 +519,7 @@
 		clocks = <&mstp3_clks R8A7791_CLK_MMCIF0>;
 		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		reg-io-width = <4>;
 		status = "disabled";
 		max-frequency = <97500000>;
@@ -504,6 +532,7 @@
 		clocks = <&mstp3_clks R8A7791_CLK_SDHI0>;
 		dmas = <&dmac1 0xcd>, <&dmac1 0xce>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -514,6 +543,7 @@
 		clocks = <&mstp3_clks R8A7791_CLK_SDHI1>;
 		dmas = <&dmac1 0xc1>, <&dmac1 0xc2>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -524,6 +554,7 @@
 		clocks = <&mstp3_clks R8A7791_CLK_SDHI2>;
 		dmas = <&dmac1 0xd3>, <&dmac1 0xd4>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -535,6 +566,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -546,6 +578,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -557,6 +590,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -568,6 +602,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -579,6 +614,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -590,6 +626,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x23>, <&dmac0 0x24>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -601,6 +638,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -612,6 +650,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -623,6 +662,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -634,6 +674,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -645,6 +686,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -656,6 +698,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -667,6 +710,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -678,6 +722,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -689,6 +734,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -700,6 +746,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -711,6 +758,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -722,6 +770,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -730,6 +779,7 @@
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7791_CLK_ETHER>;
+		power-domains = <&cpg_clocks>;
 		phy-mode = "rmii";
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -741,6 +791,7 @@
 		reg = <0 0xee300000 0 0x2000>;
 		interrupts = <0 105 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7791_CLK_SATA0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -749,6 +800,7 @@
 		reg = <0 0xee500000 0 0x2000>;
 		interrupts = <0 106 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7791_CLK_SATA1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -757,12 +809,13 @@
 		reg = <0 0xe6590000 0 0x100>;
 		interrupts = <0 107 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp7_clks R8A7791_CLK_HSUSB>;
-		renesas,buswait = <4>;
-		phys = <&usb0 1>;
-		phy-names = "usb";
 		dmas = <&usb_dmac0 0>, <&usb_dmac0 1>,
 		       <&usb_dmac1 0>, <&usb_dmac1 1>;
 		dma-names = "ch0", "ch1", "ch2", "ch3";
+		power-domains = <&cpg_clocks>;
+		renesas,buswait = <4>;
+		phys = <&usb0 1>;
+		phy-names = "usb";
 		status = "disabled";
 	};
 
@@ -773,6 +826,7 @@
 		#size-cells = <0>;
 		clocks = <&mstp7_clks R8A7791_CLK_HSUSB>;
 		clock-names = "usbhs";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		usb0: usb-channel@0 {
@@ -787,25 +841,28 @@
 
 	vin0: video@e6ef0000 {
 		compatible = "renesas,vin-r8a7791";
-		clocks = <&mstp8_clks R8A7791_CLK_VIN0>;
 		reg = <0 0xe6ef0000 0 0x1000>;
 		interrupts = <0 188 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7791_CLK_VIN0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
 	vin1: video@e6ef1000 {
 		compatible = "renesas,vin-r8a7791";
-		clocks = <&mstp8_clks R8A7791_CLK_VIN1>;
 		reg = <0 0xe6ef1000 0 0x1000>;
 		interrupts = <0 189 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7791_CLK_VIN1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
 	vin2: video@e6ef2000 {
 		compatible = "renesas,vin-r8a7791";
-		clocks = <&mstp8_clks R8A7791_CLK_VIN2>;
 		reg = <0 0xe6ef2000 0 0x1000>;
 		interrupts = <0 190 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7791_CLK_VIN2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -814,6 +871,7 @@
 		reg = <0 0xfe928000 0 0x8000>;
 		interrupts = <0 267 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7791_CLK_VSP1_S>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-lut;
 		renesas,has-sru;
@@ -827,6 +885,7 @@
 		reg = <0 0xfe930000 0 0x8000>;
 		interrupts = <0 246 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7791_CLK_VSP1_DU0>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-lif;
 		renesas,has-lut;
@@ -840,6 +899,7 @@
 		reg = <0 0xfe938000 0 0x8000>;
 		interrupts = <0 247 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7791_CLK_VSP1_DU1>;
+		power-domains = <&cpg_clocks>;
 
 		renesas,has-lif;
 		renesas,has-lut;
@@ -885,6 +945,7 @@
 		clocks = <&mstp9_clks R8A7791_CLK_RCAN0>,
 			 <&cpg_clocks R8A7791_CLK_RCAN>, <&can_clk>;
 		clock-names = "clkp1", "clkp2", "can_clk";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -895,9 +956,18 @@
 		clocks = <&mstp9_clks R8A7791_CLK_RCAN1>,
 			 <&cpg_clocks R8A7791_CLK_RCAN>, <&can_clk>;
 		clock-names = "clkp1", "clkp2", "can_clk";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
+	jpu: jpeg-codec@fe980000 {
+		compatible = "renesas,jpu-r8a7791";
+		reg = <0 0xfe980000 0 0x10300>;
+		interrupts = <0 272 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7791_CLK_JPU>;
+		power-domains = <&cpg_clocks>;
+	};
+
 	clocks {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -972,6 +1042,7 @@
 			clock-output-names = "main", "pll0", "pll1", "pll3",
 					     "lb", "qspi", "sdh", "sd0", "z",
 					     "rcan", "adsp";
+			#power-domain-cells = <0>;
 		};
 
 		/* Variable factor clocks */
@@ -1311,6 +1382,7 @@
 				<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>,
 				<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>,
 				<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>,
+				<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>,
 				<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>;
 
 			#clock-cells = <1>;
@@ -1320,6 +1392,7 @@
 				R8A7791_CLK_SSI4 R8A7791_CLK_SSI3 R8A7791_CLK_SSI2 R8A7791_CLK_SSI1 R8A7791_CLK_SSI0
 				R8A7791_CLK_SCU_ALL
 				R8A7791_CLK_SCU_DVC1 R8A7791_CLK_SCU_DVC0
+				R8A7791_CLK_SCU_CTU1_MIX1 R8A7791_CLK_SCU_CTU0_MIX0
 				R8A7791_CLK_SCU_SRC9 R8A7791_CLK_SCU_SRC8 R8A7791_CLK_SCU_SRC7 R8A7791_CLK_SCU_SRC6 R8A7791_CLK_SCU_SRC5
 				R8A7791_CLK_SCU_SRC4 R8A7791_CLK_SCU_SRC3 R8A7791_CLK_SCU_SRC2 R8A7791_CLK_SCU_SRC1 R8A7791_CLK_SCU_SRC0
 			>;
@@ -1329,6 +1402,7 @@
 				"ssi4", "ssi3", "ssi2", "ssi1", "ssi0",
 				"scu-all",
 				"scu-dvc1", "scu-dvc0",
+				"scu-ctu1-mix1", "scu-ctu0-mix0",
 				"scu-src9", "scu-src8", "scu-src7", "scu-src6", "scu-src5",
 				"scu-src4", "scu-src3", "scu-src2", "scu-src1", "scu-src0";
 		};
@@ -1351,6 +1425,7 @@
 		clocks = <&mstp9_clks R8A7791_CLK_QSPI_MOD>;
 		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		num-cs = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1364,6 +1439,7 @@
 		clocks = <&mstp0_clks R8A7791_CLK_MSIOF0>;
 		dmas = <&dmac0 0x51>, <&dmac0 0x52>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1376,6 +1452,7 @@
 		clocks = <&mstp2_clks R8A7791_CLK_MSIOF1>;
 		dmas = <&dmac0 0x55>, <&dmac0 0x56>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1388,6 +1465,7 @@
 		clocks = <&mstp2_clks R8A7791_CLK_MSIOF2>;
 		dmas = <&dmac0 0x41>, <&dmac0 0x42>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
@@ -1398,6 +1476,7 @@
 		reg = <0 0xee000000 0 0xc00>;
 		interrupts = <0 101 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_SSUSB>;
+		power-domains = <&cpg_clocks>;
 		phys = <&usb2 1>;
 		phy-names = "usb";
 		status = "disabled";
@@ -1406,10 +1485,11 @@
 	pci0: pci@ee090000 {
 		compatible = "renesas,pci-r8a7791";
 		device_type = "pci";
-		clocks = <&mstp7_clks R8A7791_CLK_EHCI>;
 		reg = <0 0xee090000 0 0xc00>,
 		      <0 0xee080000 0 0x1100>;
 		interrupts = <0 108 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7791_CLK_EHCI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		bus-range = <0 0>;
@@ -1440,10 +1520,11 @@
 	pci1: pci@ee0d0000 {
 		compatible = "renesas,pci-r8a7791";
 		device_type = "pci";
-		clocks = <&mstp7_clks R8A7791_CLK_EHCI>;
 		reg = <0 0xee0d0000 0 0xc00>,
 		      <0 0xee0c0000 0 0x1100>;
 		interrupts = <0 113 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7791_CLK_EHCI>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 
 		bus-range = <1 1>;
@@ -1493,6 +1574,7 @@
 		interrupt-map = <0 0 0 0 &gic 0 116 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_PCIEC>, <&pcie_bus_clk>;
 		clock-names = "pcie", "pcie_bus";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -1582,6 +1664,8 @@
 			<&mstp10_clks R8A7791_CLK_SCU_SRC5>, <&mstp10_clks R8A7791_CLK_SCU_SRC4>,
 			<&mstp10_clks R8A7791_CLK_SCU_SRC3>, <&mstp10_clks R8A7791_CLK_SCU_SRC2>,
 			<&mstp10_clks R8A7791_CLK_SCU_SRC1>, <&mstp10_clks R8A7791_CLK_SCU_SRC0>,
+			<&mstp10_clks R8A7791_CLK_SCU_CTU0_MIX0>, <&mstp10_clks R8A7791_CLK_SCU_CTU1_MIX1>,
+			<&mstp10_clks R8A7791_CLK_SCU_CTU0_MIX0>, <&mstp10_clks R8A7791_CLK_SCU_CTU1_MIX1>,
 			<&mstp10_clks R8A7791_CLK_SCU_DVC0>, <&mstp10_clks R8A7791_CLK_SCU_DVC1>,
 			<&audio_clk_a>, <&audio_clk_b>, <&audio_clk_c>, <&m2_clk>;
 		clock-names = "ssi-all",
@@ -1589,6 +1673,8 @@
 				"ssi.4", "ssi.3", "ssi.2", "ssi.1", "ssi.0",
 				"src.9", "src.8", "src.7", "src.6", "src.5",
 				"src.4", "src.3", "src.2", "src.1", "src.0",
+				"ctu.0", "ctu.1",
+				"mix.0", "mix.1",
 				"dvc.0", "dvc.1",
 				"clk_a", "clk_b", "clk_c", "clk_i";
 
@@ -1605,6 +1691,22 @@
 			};
 		};
 
+		rcar_sound,mix {
+			mix0: mix@0 { };
+			mix1: mix@1 { };
+		};
+
+		rcar_sound,ctu {
+			ctu00: ctu@0 { };
+			ctu01: ctu@1 { };
+			ctu02: ctu@2 { };
+			ctu03: ctu@3 { };
+			ctu10: ctu@4 { };
+			ctu11: ctu@5 { };
+			ctu12: ctu@6 { };
+			ctu13: ctu@7 { };
+		};
+
 		rcar_sound,src {
 			src0: src@0 {
 				interrupts = <0 352 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts
new file mode 100644
index 000000000000..96443ec5f6ab
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7793-gose.dts
@@ -0,0 +1,63 @@
+/*
+ * Device Tree Source for the Gose board
+ *
+ * Copyright (C) 2014-2015 Renesas Electronics Corporation
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "r8a7793.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Gose";
+	compatible = "renesas,gose", "renesas,r8a7793";
+
+	aliases {
+		serial0 = &scif0;
+		serial1 = &scif1;
+	};
+
+	chosen {
+		bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp";
+		stdout-path = &scif0;
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x40000000>;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <20000000>;
+};
+
+&ether {
+	phy-handle = <&phy1>;
+	renesas,ether-link-active-low;
+	status = "okay";
+
+	phy1: ethernet-phy@1 {
+		reg = <1>;
+		interrupt-parent = <&irqc0>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		micrel,led-mode = <1>;
+	};
+};
+
+&cmt0 {
+	status = "okay";
+};
+
+&scif0 {
+	status = "okay";
+};
+
+&scif1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
new file mode 100644
index 000000000000..c4654047e684
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -0,0 +1,374 @@
+/*
+ * Device Tree Source for the r8a7793 SoC
+ *
+ * Copyright (C) 2014-2015 Renesas Electronics Corporation
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <dt-bindings/clock/r8a7793-clock.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	compatible = "renesas,r8a7793";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			clock-frequency = <1500000000>;
+			voltage-tolerance = <1>; /* 1% */
+			clocks = <&cpg_clocks R8A7793_CLK_Z>;
+			clock-latency = <300000>; /* 300 us */
+
+			/* kHz - uV - OPPs unknown yet */
+			operating-points = <1500000 1000000>,
+					   <1312500 1000000>,
+					   <1125000 1000000>,
+					   < 937500 1000000>,
+					   < 750000 1000000>,
+					   < 375000 1000000>;
+		};
+	};
+
+	gic: interrupt-controller@f1001000 {
+		compatible = "arm,gic-400";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0xf1001000 0 0x1000>,
+			<0 0xf1002000 0 0x1000>,
+			<0 0xf1004000 0 0x2000>,
+			<0 0xf1006000 0 0x2000>;
+		interrupts = <1 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <1 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <1 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <1 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	cmt0: timer@ffca0000 {
+		compatible = "renesas,cmt-48-r8a7793", "renesas,cmt-48-gen2";
+		reg = <0 0xffca0000 0 0x1004>;
+		interrupts = <0 142 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 143 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7793_CLK_CMT0>;
+		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
+
+		renesas,channels-mask = <0x60>;
+
+		status = "disabled";
+	};
+
+	cmt1: timer@e6130000 {
+		compatible = "renesas,cmt-48-r8a7793", "renesas,cmt-48-gen2";
+		reg = <0 0xe6130000 0 0x1004>;
+		interrupts = <0 120 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 121 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 122 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 123 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 124 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 125 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 126 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 127 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp3_clks R8A7793_CLK_CMT1>;
+		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
+
+		renesas,channels-mask = <0xff>;
+
+		status = "disabled";
+	};
+
+	irqc0: interrupt-controller@e61c0000 {
+		compatible = "renesas,irqc-r8a7793", "renesas,irqc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0 0xe61c0000 0 0x200>;
+		interrupts = <0 0 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 1 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 2 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 3 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 12 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 13 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 14 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 15 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 16 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 17 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp4_clks R8A7793_CLK_IRQC>;
+		power-domains = <&cpg_clocks>;
+	};
+
+	scif0: serial@e6e60000 {
+		compatible = "renesas,scif-r8a7793", "renesas,scif";
+		reg = <0 0xe6e60000 0 64>;
+		interrupts = <0 152 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7793_CLK_SCIF0>;
+		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
+		status = "disabled";
+	};
+
+	scif1: serial@e6e68000 {
+		compatible = "renesas,scif-r8a7793", "renesas,scif";
+		reg = <0 0xe6e68000 0 64>;
+		interrupts = <0 153 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7793_CLK_SCIF1>;
+		clock-names = "sci_ick";
+		power-domains = <&cpg_clocks>;
+		status = "disabled";
+	};
+
+	ether: ethernet@ee700000 {
+		compatible = "renesas,ether-r8a7793";
+		reg = <0 0xee700000 0 0x400>;
+		interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7793_CLK_ETHER>;
+		power-domains = <&cpg_clocks>;
+		phy-mode = "rmii";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	clocks {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/* External root clock */
+		extal_clk: extal_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			/* This value must be overridden by the board. */
+			clock-frequency = <0>;
+			clock-output-names = "extal";
+		};
+
+		/* Special CPG clocks */
+		cpg_clocks: cpg_clocks@e6150000 {
+			compatible = "renesas,r8a7793-cpg-clocks",
+				     "renesas,rcar-gen2-cpg-clocks";
+			reg = <0 0xe6150000 0 0x1000>;
+			clocks = <&extal_clk>;
+			#clock-cells = <1>;
+			clock-output-names = "main", "pll0", "pll1", "pll3",
+					     "lb", "qspi", "sdh", "sd0", "z",
+					     "rcan", "adsp";
+			#power-domain-cells = <0>;
+		};
+
+		/* Variable factor clocks */
+		sd2_clk: sd2_clk@e6150078 {
+			compatible = "renesas,r8a7793-div6-clock",
+				     "renesas,cpg-div6-clock";
+			reg = <0 0xe6150078 0 4>;
+			clocks = <&pll1_div2_clk>;
+			#clock-cells = <0>;
+			clock-output-names = "sd2";
+		};
+		sd3_clk: sd3_clk@e615026c {
+			compatible = "renesas,r8a7793-div6-clock",
+				     "renesas,cpg-div6-clock";
+			reg = <0 0xe615026c 0 4>;
+			clocks = <&pll1_div2_clk>;
+			#clock-cells = <0>;
+			clock-output-names = "sd3";
+		};
+		mmc0_clk: mmc0_clk@e6150240 {
+			compatible = "renesas,r8a7793-div6-clock",
+				     "renesas,cpg-div6-clock";
+			reg = <0 0xe6150240 0 4>;
+			clocks = <&pll1_div2_clk>;
+			#clock-cells = <0>;
+			clock-output-names = "mmc0";
+		};
+
+		/* Fixed factor clocks */
+		pll1_div2_clk: pll1_div2_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <2>;
+			clock-mult = <1>;
+			clock-output-names = "pll1_div2";
+		};
+		zg_clk: zg_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <5>;
+			clock-mult = <1>;
+			clock-output-names = "zg";
+		};
+		zx_clk: zx_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <3>;
+			clock-mult = <1>;
+			clock-output-names = "zx";
+		};
+		zs_clk: zs_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <6>;
+			clock-mult = <1>;
+			clock-output-names = "zs";
+		};
+		hp_clk: hp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <12>;
+			clock-mult = <1>;
+			clock-output-names = "hp";
+		};
+		p_clk: p_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <24>;
+			clock-mult = <1>;
+			clock-output-names = "p";
+		};
+		rclk_clk: rclk_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7793_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <(48 * 1024)>;
+			clock-mult = <1>;
+			clock-output-names = "rclk";
+		};
+		mp_clk: mp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&pll1_div2_clk>;
+			#clock-cells = <0>;
+			clock-div = <15>;
+			clock-mult = <1>;
+			clock-output-names = "mp";
+		};
+		cp_clk: cp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&extal_clk>;
+			#clock-cells = <0>;
+			clock-div = <2>;
+			clock-mult = <1>;
+			clock-output-names = "cp";
+		};
+
+		/* Gate clocks */
+		mstp1_clks: mstp1_clks@e6150134 {
+			compatible = "renesas,r8a7793-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
+			clocks = <&zs_clk>, <&zs_clk>, <&zs_clk>, <&p_clk>,
+				 <&zg_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>,
+				 <&p_clk>, <&p_clk>, <&rclk_clk>, <&cp_clk>,
+				 <&zs_clk>, <&zs_clk>, <&zs_clk>;
+			#clock-cells = <1>;
+			clock-indices = <
+				R8A7793_CLK_VCP0 R8A7793_CLK_VPC0
+				R8A7793_CLK_SSP1 R8A7793_CLK_TMU1
+				R8A7793_CLK_3DG R8A7793_CLK_2DDMAC
+				R8A7793_CLK_FDP1_1 R8A7793_CLK_FDP1_0
+				R8A7793_CLK_TMU3 R8A7793_CLK_TMU2
+				R8A7793_CLK_CMT0 R8A7793_CLK_TMU0
+				R8A7793_CLK_VSP1_DU1 R8A7793_CLK_VSP1_DU0
+				R8A7793_CLK_VSP1_S
+			>;
+			clock-output-names =
+				"vcp0", "vpc0", "ssp_dev", "tmu1",
+				"pvrsrvkm", "tddmac", "fdp1", "fdp0",
+				"tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
+				"vsp1-du0", "vsps";
+		};
+		mstp3_clks: mstp3_clks@e615013c {
+			compatible = "renesas,r8a7793-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe615013c 0 4>, <0 0xe6150048 0 4>;
+			clocks = <&cp_clk>, <&sd3_clk>, <&sd2_clk>,
+				 <&cpg_clocks R8A7793_CLK_SD0>, <&mmc0_clk>,
+				 <&hp_clk>, <&mp_clk>, <&hp_clk>, <&mp_clk>,
+				 <&rclk_clk>, <&hp_clk>, <&hp_clk>;
+			#clock-cells = <1>;
+			clock-indices = <
+				R8A7793_CLK_TPU0 R8A7793_CLK_SDHI2
+				R8A7793_CLK_SDHI1 R8A7793_CLK_SDHI0
+				R8A7793_CLK_MMCIF0 R8A7793_CLK_IIC0
+				R8A7793_CLK_PCIEC R8A7793_CLK_IIC1
+				R8A7793_CLK_SSUSB R8A7793_CLK_CMT1
+				R8A7793_CLK_USBDMAC0 R8A7793_CLK_USBDMAC1
+			>;
+			clock-output-names =
+				"tpu0", "sdhi2", "sdhi1", "sdhi0", "mmcif0",
+				"i2c7", "pciec", "i2c8", "ssusb", "cmt1",
+				"usbdmac0", "usbdmac1";
+		};
+		mstp4_clks: mstp4_clks@e6150140 {
+			compatible = "renesas,r8a7793-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150140 0 4>, <0 0xe615004c 0 4>;
+			clocks = <&cp_clk>;
+			#clock-cells = <1>;
+			clock-indices = <R8A7793_CLK_IRQC>;
+			clock-output-names = "irqc";
+		};
+		mstp7_clks: mstp7_clks@e615014c {
+			compatible = "renesas,r8a7793-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe615014c 0 4>, <0 0xe61501c4 0 4>;
+			clocks = <&mp_clk>,  <&hp_clk>, <&zs_clk>, <&p_clk>,
+				 <&p_clk>, <&zs_clk>, <&zs_clk>, <&p_clk>,
+				 <&p_clk>, <&p_clk>, <&p_clk>, <&zx_clk>,
+				 <&zx_clk>, <&zx_clk>;
+			#clock-cells = <1>;
+			clock-indices = <
+				R8A7793_CLK_EHCI R8A7793_CLK_HSUSB
+				R8A7793_CLK_HSCIF2 R8A7793_CLK_SCIF5
+				R8A7793_CLK_SCIF4 R8A7793_CLK_HSCIF1
+				R8A7793_CLK_HSCIF0 R8A7793_CLK_SCIF3
+				R8A7793_CLK_SCIF2 R8A7793_CLK_SCIF1
+				R8A7793_CLK_SCIF0 R8A7793_CLK_DU1
+				R8A7793_CLK_DU0 R8A7793_CLK_LVDS0
+			>;
+			clock-output-names =
+				"ehci", "hsusb", "hscif2", "scif5", "scif4",
+				"hscif1", "hscif0", "scif3", "scif2",
+				"scif1", "scif0", "du1", "du0", "lvds0";
+		};
+		mstp8_clks: mstp8_clks@e6150990 {
+			compatible = "renesas,r8a7793-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150990 0 4>, <0 0xe61509a0 0 4>;
+			clocks = <&zx_clk>, <&zg_clk>, <&zg_clk>, <&zg_clk>,
+				 <&p_clk>, <&zs_clk>, <&zs_clk>;
+			#clock-cells = <1>;
+			clock-indices = <
+				R8A7793_CLK_IPMMU_SGX R8A7793_CLK_VIN2
+				R8A7793_CLK_VIN1 R8A7793_CLK_VIN0
+				R8A7793_CLK_ETHER R8A7793_CLK_SATA1
+				R8A7793_CLK_SATA0
+			>;
+			clock-output-names =
+				"ipmmu_sgx", "vin2", "vin1", "vin0", "ether",
+				"sata1", "sata0";
+		};
+	};
+
+};
diff --git a/arch/arm/boot/dts/r8a7794-silk.dts b/arch/arm/boot/dts/r8a7794-silk.dts
new file mode 100644
index 000000000000..d4dd5a30ccdf
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7794-silk.dts
@@ -0,0 +1,102 @@
+/*
+ * Device Tree Source for the SILK board
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2014-2015 Renesas Solutions Corp.
+ * Copyright (C) 2014-2015 Cogent Embedded, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "r8a7794.dtsi"
+
+/ {
+	model = "SILK";
+	compatible = "renesas,silk", "renesas,r8a7794";
+
+	aliases {
+		serial0 = &scif2;
+	};
+
+	chosen {
+		bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp";
+		stdout-path = &scif2;
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x40000000>;
+	};
+
+	d3_3v: regulator@0 {
+		compatible = "regulator-fixed";
+		regulator-name = "D3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <20000000>;
+};
+
+&pfc {
+	scif2_pins: serial2 {
+		renesas,groups = "scif2_data";
+		renesas,function = "scif2";
+	};
+
+	ether_pins: ether {
+		renesas,groups = "eth_link", "eth_mdio", "eth_rmii";
+		renesas,function = "eth";
+	};
+
+	phy1_pins: phy1 {
+		renesas,groups = "intc_irq8";
+		renesas,function = "intc";
+	};
+
+	mmcif0_pins: mmcif0 {
+		renesas,groups = "mmc_data8", "mmc_ctrl";
+		renesas,function = "mmc";
+	};
+};
+
+&scif2 {
+	pinctrl-0 = <&scif2_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&ether {
+	pinctrl-0 = <&ether_pins &phy1_pins>;
+	pinctrl-names = "default";
+
+	phy-handle = <&phy1>;
+	renesas,ether-link-active-low;
+	status = "okay";
+
+	phy1: ethernet-phy@1 {
+		reg = <1>;
+		interrupt-parent = <&irqc0>;
+		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
+		micrel,led-mode = <1>;
+	};
+};
+
+&mmcif0 {
+	pinctrl-0 = <&mmcif0_pins>;
+	pinctrl-names = "default";
+
+	vmmc-supply = <&d3_3v>;
+	vqmmc-supply = <&d3_3v>;
+	bus-width = <8>;
+	non-removable;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index b73819423311..97c8e9ace5eb 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -39,7 +39,7 @@
 	};
 
 	gic: interrupt-controller@f1001000 {
-		compatible = "arm,cortex-a7-gic";
+		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
 		#address-cells = <0>;
 		interrupt-controller;
@@ -57,6 +57,7 @@
 			     <0 143 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7794_CLK_CMT0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		renesas,channels-mask = <0x60>;
 
@@ -76,6 +77,7 @@
 			     <0 127 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_CMT1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 
 		renesas,channels-mask = <0xff>;
 
@@ -106,6 +108,13 @@
 			     <0 16 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 17 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp4_clks R8A7794_CLK_IRQC>;
+		power-domains = <&cpg_clocks>;
+	};
+
+	pfc: pin-controller@e6060000 {
+		compatible = "renesas,pfc-r8a7794";
+		reg = <0 0xe6060000 0 0x11c>;
+		#gpio-range-cells = <3>;
 	};
 
 	dmac0: dma-controller@e6700000 {
@@ -134,6 +143,7 @@
 				"ch12", "ch13", "ch14";
 		clocks = <&mstp2_clks R8A7794_CLK_SYS_DMAC0>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
@@ -164,6 +174,7 @@
 				"ch12", "ch13", "ch14";
 		clocks = <&mstp2_clks R8A7794_CLK_SYS_DMAC1>;
 		clock-names = "fck";
+		power-domains = <&cpg_clocks>;
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
@@ -176,6 +187,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -187,6 +199,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -198,6 +211,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -209,6 +223,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -220,6 +235,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -231,6 +247,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x23>, <&dmac0 0x24>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -242,6 +259,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -253,6 +271,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -264,6 +283,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -275,6 +295,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -286,6 +307,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -297,6 +319,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -308,6 +331,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -319,6 +343,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -330,6 +355,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -341,6 +367,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -352,6 +379,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -363,6 +391,7 @@
 		clock-names = "sci_ick";
 		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
 		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -371,17 +400,31 @@
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp8_clks R8A7794_CLK_ETHER>;
+		power-domains = <&cpg_clocks>;
 		phy-mode = "rmii";
 		#address-cells = <1>;
 		#size-cells = <0>;
 		status = "disabled";
 	};
 
+	mmcif0: mmc@ee200000 {
+		compatible = "renesas,mmcif-r8a7794", "renesas,sh-mmcif";
+		reg = <0 0xee200000 0 0x80>;
+		interrupts = <0 169 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp3_clks R8A7794_CLK_MMCIF0>;
+		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
+		dma-names = "tx", "rx";
+		power-domains = <&cpg_clocks>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
 	sdhi0: sd@ee100000 {
 		compatible = "renesas,sdhi-r8a7794";
 		reg = <0 0xee100000 0 0x200>;
 		interrupts = <0 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_SDHI0>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -390,6 +433,7 @@
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <0 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_SDHI1>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -398,6 +442,7 @@
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <0 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_SDHI2>;
+		power-domains = <&cpg_clocks>;
 		status = "disabled";
 	};
 
@@ -424,6 +469,7 @@
 			#clock-cells = <1>;
 			clock-output-names = "main", "pll0", "pll1", "pll3",
 					     "lb", "qspi", "sdh", "sd0", "z";
+			#power-domain-cells = <0>;
 		};
 		/* Variable factor clocks */
 		sd2_clk: sd2_clk@e6150078 {
diff --git a/arch/arm/boot/dts/rk3066a-bqcurie2.dts b/arch/arm/boot/dts/rk3066a-bqcurie2.dts
index b299b26926d4..c0273755431a 100644
--- a/arch/arm/boot/dts/rk3066a-bqcurie2.dts
+++ b/arch/arm/boot/dts/rk3066a-bqcurie2.dts
@@ -49,6 +49,7 @@
 	compatible = "mundoreader,bq-curie2", "rockchip,rk3066a";
 
 	memory {
+		device_type = "memory";
 		reg = <0x60000000 0x40000000>;
 	};
 
diff --git a/arch/arm/boot/dts/rk3066a-marsboard.dts b/arch/arm/boot/dts/rk3066a-marsboard.dts
index 0a7304beb417..bae965c123c1 100644
--- a/arch/arm/boot/dts/rk3066a-marsboard.dts
+++ b/arch/arm/boot/dts/rk3066a-marsboard.dts
@@ -48,6 +48,7 @@
 	compatible = "haoyu,marsboard-rk3066", "rockchip,rk3066a";
 
 	memory {
+		device_type = "memory";
 		reg = <0x60000000 0x40000000>;
 	};
 
@@ -201,6 +202,18 @@
 	status = "okay";
 };
 
+&usbphy {
+	status = "okay";
+};
+
+&usb_host {
+	status = "okay";
+};
+
+&usb_otg {
+	status = "okay";
+};
+
 &wdt {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/rk3066a-rayeager.dts b/arch/arm/boot/dts/rk3066a-rayeager.dts
index 3ac151102c2f..e36383c701dc 100644
--- a/arch/arm/boot/dts/rk3066a-rayeager.dts
+++ b/arch/arm/boot/dts/rk3066a-rayeager.dts
@@ -48,6 +48,7 @@
 	compatible = "chipspark,rayeager-px2", "rockchip,rk3066a";
 
 	memory {
+		device_type = "memory";
 		reg = <0x60000000 0x40000000>;
 	};
 
@@ -459,6 +460,10 @@
 	status = "okay";
 };
 
+&usbphy {
+	status = "okay";
+};
+
 &usb_otg {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/rk3066a.dtsi b/arch/arm/boot/dts/rk3066a.dtsi
index d32229b8a996..946f18705e96 100644
--- a/arch/arm/boot/dts/rk3066a.dtsi
+++ b/arch/arm/boot/dts/rk3066a.dtsi
@@ -169,6 +169,28 @@
 		clock-names = "timer", "pclk";
 	};
 
+	usbphy: phy {
+		compatible = "rockchip,rk3066a-usb-phy", "rockchip,rk3288-usb-phy";
+		rockchip,grf = <&grf>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+
+		usbphy0: usb-phy0 {
+			#phy-cells = <0>;
+			reg = <0x17c>;
+			clocks = <&cru SCLK_OTGPHY0>;
+			clock-names = "phyclk";
+		};
+
+		usbphy1: usb-phy1 {
+			#phy-cells = <0>;
+			reg = <0x188>;
+			clocks = <&cru SCLK_OTGPHY1>;
+			clock-names = "phyclk";
+		};
+	};
+
 	pinctrl: pinctrl {
 		compatible = "rockchip,rk3066a-pinctrl";
 		rockchip,grf = <&grf>;
diff --git a/arch/arm/boot/dts/rk3188-radxarock.dts b/arch/arm/boot/dts/rk3188-radxarock.dts
index 42faa19edb7e..d2180e5d2b05 100644
--- a/arch/arm/boot/dts/rk3188-radxarock.dts
+++ b/arch/arm/boot/dts/rk3188-radxarock.dts
@@ -48,6 +48,7 @@
 	compatible = "radxa,rock", "rockchip,rk3188";
 
 	memory {
+		device_type = "memory";
 		reg = <0x60000000 0x80000000>;
 	};
 
@@ -358,6 +359,10 @@
 	status = "okay";
 };
 
+&usbphy {
+	status = "okay";
+};
+
 &usb_host {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/rk3188.dtsi b/arch/arm/boot/dts/rk3188.dtsi
index 0f23aedf9349..316304272118 100644
--- a/arch/arm/boot/dts/rk3188.dtsi
+++ b/arch/arm/boot/dts/rk3188.dtsi
@@ -130,6 +130,28 @@
 		#reset-cells = <1>;
 	};
 
+	usbphy: phy {
+		compatible = "rockchip,rk3188-usb-phy", "rockchip,rk3288-usb-phy";
+		rockchip,grf = <&grf>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+
+		usbphy0: usb-phy0 {
+			#phy-cells = <0>;
+			reg = <0x10c>;
+			clocks = <&cru SCLK_OTGPHY0>;
+			clock-names = "phyclk";
+		};
+
+		usbphy1: usb-phy1 {
+			#phy-cells = <0>;
+			reg = <0x11c>;
+			clocks = <&cru SCLK_OTGPHY1>;
+			clock-names = "phyclk";
+		};
+	};
+
 	pinctrl: pinctrl {
 		compatible = "rockchip,rk3188-pinctrl";
 		rockchip,grf = <&grf>;
diff --git a/arch/arm/boot/dts/rk3288-evb.dtsi b/arch/arm/boot/dts/rk3288-evb.dtsi
index 844a6fb64658..f6d2e7894b05 100644
--- a/arch/arm/boot/dts/rk3288-evb.dtsi
+++ b/arch/arm/boot/dts/rk3288-evb.dtsi
@@ -43,6 +43,7 @@
 
 / {
 	memory {
+		device_type = "memory";
 		reg = <0x0 0x80000000>;
 	};
 
diff --git a/arch/arm/boot/dts/rk3288-firefly.dtsi b/arch/arm/boot/dts/rk3288-firefly.dtsi
index 0b42372e4379..20fa0ef0b96b 100644
--- a/arch/arm/boot/dts/rk3288-firefly.dtsi
+++ b/arch/arm/boot/dts/rk3288-firefly.dtsi
@@ -44,6 +44,7 @@
 
 / {
 	memory {
+		device_type = "memory";
 		reg = <0 0x80000000>;
 	};
 
@@ -213,6 +214,8 @@
 		regulator-max-microvolt = <1350000>;
 		regulator-always-on;
 		regulator-boot-on;
+		regulator-enable-ramp-delay = <300>;
+		regulator-ramp-delay = <8000>;
 		vin-supply = <&vcc_sys>;
 	};
 
diff --git a/arch/arm/boot/dts/rk3288-popmetal.dts b/arch/arm/boot/dts/rk3288-popmetal.dts
index d582811fbd7b..f82b956ebf17 100644
--- a/arch/arm/boot/dts/rk3288-popmetal.dts
+++ b/arch/arm/boot/dts/rk3288-popmetal.dts
@@ -49,6 +49,7 @@
 	compatible = "chipspark,popmetal-rk3288", "rockchip,rk3288";
 
 	memory{
+		device_type = "memory";
 		reg = <0 0x80000000>;
 	};
 
diff --git a/arch/arm/boot/dts/rk3288-r89.dts b/arch/arm/boot/dts/rk3288-r89.dts
new file mode 100644
index 000000000000..14b9fc73c8a4
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-r89.dts
@@ -0,0 +1,413 @@
+/*
+ * Copyright (c) 2015 Heiko Stuebner <heiko@sntech.de>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include <dt-bindings/pwm/pwm.h>
+#include "rk3288.dtsi"
+
+/ {
+	compatible = "netxeon,r89", "rockchip,rk3288";
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x80000000>;
+	};
+
+	ext_gmac: external-gmac-clock {
+		compatible = "fixed-clock";
+		clock-frequency = <125000000>;
+		clock-output-names = "ext_gmac";
+		#clock-cells = <0>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		autorepeat;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pwrbtn>;
+
+		button@0 {
+			gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
+			linux,code = <116>;
+			label = "GPIO Key Power";
+			linux,input-type = <1>;
+			gpio-key,wakeup = <1>;
+			debounce-interval = <100>;
+		};
+	};
+
+	vcc_host: vcc-host-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 14 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&host_vbus_drv>;
+		regulator-name = "vcc_host";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_otg: vcc-otg-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 12 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&otg_vbus_drv>;
+		regulator-name = "vcc_otg";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_sdmmc: sdmmc-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "sdmmc-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio7 11 GPIO_ACTIVE_LOW>;
+		startup-delay-us = <100000>;
+		vin-supply = <&vcc_io>;
+	};
+
+	vcc_sys: sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "sys-supply";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&cpu0 {
+	cpu0-supply = <&vdd_cpu>;
+};
+
+&gmac {
+	phy-supply = <&vcc_lan>;
+	phy-mode = "rgmii";
+	clock_in_out = "input";
+	snps,reset-gpio = <&gpio4 7 0>;
+	snps,reset-active-low;
+	snps,reset-delays-us = <0 10000 1000000>;
+	assigned-clocks = <&cru SCLK_MAC>;
+	assigned-clock-parents = <&ext_gmac>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&rgmii_pins>;
+	tx_delay = <0x30>;
+	rx_delay = <0x10>;
+	status = "ok";
+};
+
+&hdmi {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	vdd_cpu: pmic@40 {
+		compatible = "silergy,syr827";
+		reg = <0x40>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "VDD_CPU";
+		regulator-enable-ramp-delay = <300>;
+		regulator-min-microvolt = <850000>;
+		regulator-max-microvolt = <1350000>;
+		regulator-ramp-delay = <8000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+
+	vdd_gpu: pmic@41 {
+		compatible = "silergy,syr828";
+		reg = <0x41>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "VDD_GPU";
+		regulator-enable-ramp-delay = <300>;
+		regulator-min-microvolt = <850000>;
+		regulator-max-microvolt = <1350000>;
+		regulator-ramp-delay = <8000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+
+	rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		clock-output-names = "xin32k";
+		interrupt-parent = <&gpio0>;
+		interrupts = <4 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_int>;
+	};
+
+	act8846: pmic@5a {
+		compatible = "active-semi,act8846";
+		reg = <0x5a>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_vsel>, <&pwr_hold>;
+		system-power-controller;
+
+		regulators {
+			vcc_ddr: REG1 {
+				regulator-name = "VCC_DDR";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+			};
+
+			vcc_io: REG2 {
+				regulator-name = "VCC_IO";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_log: REG3 {
+				regulator-name = "VDD_LOG";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			vcc_20: REG4 {
+				regulator-name = "VCC_20";
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-always-on;
+			};
+
+			vccio_sd: REG5 {
+				regulator-name = "VCCIO_SD";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd10_lcd: REG6 {
+				regulator-name = "VDD10_LCD";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			vcc_wl: REG7 {
+				regulator-name = "VCC_WL";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vcca_33: REG8 {
+				regulator-name = "VCCA_33";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vcc_lan: REG9 {
+				regulator-name = "VCC_LAN";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_10: REG10 {
+				regulator-name = "VDD_10";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			vcc_18: REG11 {
+				regulator-name = "VCC_18";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			vcc18_lcd: REG12 {
+				regulator-name = "VCC18_LCD";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+		};
+	};
+};
+
+&i2c5 {
+	status = "okay";
+};
+
+&pinctrl {
+	pcfg_output_high: pcfg-output-high {
+		output-high;
+	};
+
+	pcfg_output_low: pcfg-output-low {
+		output-low;
+	};
+
+	act8846 {
+		pmic_vsel: pmic-vsel {
+			rockchip,pins = <7 1 RK_FUNC_GPIO &pcfg_output_low>;
+		};
+
+		pwr_hold: pwr-hold {
+			rockchip,pins = <0 6 RK_FUNC_GPIO &pcfg_output_high>;
+		};
+	};
+
+	buttons {
+		pwrbtn: pwrbtn {
+			rockchip,pins = <0 5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	pmic {
+		pmic_int: pmic-int {
+			rockchip,pins = <RK_GPIO0 4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	usb {
+		host_vbus_drv: host-vbus-drv {
+			rockchip,pins = <0 14 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		otg_vbus_drv: otg-vbus-drv {
+			rockchip,pins = <0 12 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pwm0 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_18>;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	card-detect-delay = <200>;
+	disable-wp;
+	num-slots = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;
+	vmmc-supply = <&vcc_sdmmc>;
+	vqmmc-supply = <&vccio_sd>;
+	status = "okay";
+};
+
+&tsadc {
+	rockchip,hw-tshut-mode = <0>;
+	rockchip,hw-tshut-polarity = <0>;
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&uart3 {
+	status = "okay";
+};
+
+&uart4 {
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host1 {
+	status = "okay";
+};
+
+&usb_otg {
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
+
+&vopb {
+	status = "okay";
+};
+
+&vopb_mmu {
+	status = "okay";
+};
+
+&vopl {
+	status = "okay";
+};
+
+&vopl_mmu {
+	status = "okay";
+};
+
+&wdt {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi b/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi
new file mode 100644
index 000000000000..136d650dd05f
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi
@@ -0,0 +1,232 @@
+/*
+ * Google Veyron (and derivatives) board device tree source
+ * Chromebook specific parts
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/clock/rockchip,rk808.h>
+#include <dt-bindings/input/input.h>
+#include "rk3288-veyron.dtsi"
+#include "rk3288-veyron-sdmmc.dtsi"
+
+/ {
+	aliases {
+		/* Assign 20 so we don't get confused w/ builtin ones */
+		i2c20 = &i2c_tunnel;
+	};
+
+	gpio-charger {
+		compatible = "gpio-charger";
+		charger-type = "mains";
+		gpios = <&gpio0 8 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ac_present_ap>;
+	};
+
+	/* A non-regulated voltage from power supply or battery */
+	vccsys: vccsys {
+		compatible = "regulator-fixed";
+		regulator-name = "vccsys";
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	vcc33_sys: vcc33-sys {
+		vin-supply = <&vccsys>;
+	};
+
+	vcc_5v: vcc-5v {
+		vin-supply = <&vccsys>;
+	};
+
+	/* This turns on vbus for host1 (dwc2) */
+	vcc5_host1: vcc5-host1-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 11 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&host1_pwr_en>;
+		regulator-name = "vcc5_host1";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	/* This turns on vbus for otg for host mode (dwc2) */
+	vcc5v_otg: vcc5v-otg-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 12 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usbotg_pwren_h>;
+		regulator-name = "vcc5_host2";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&gpio_keys {
+	pinctrl-0 = <&pwr_key_l &ap_lid_int_l>;
+	lid {
+		label = "Lid";
+		gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
+		gpio-key,wakeup;
+		linux,code = <0>; /* SW_LID */
+		linux,input-type = <5>; /* EV_SW */
+		debounce-interval = <1>;
+	};
+};
+
+&rk808 {
+	vcc11-supply = <&vcc_5v>;
+
+	regulators {
+		vcc33_ccd: LDO_REG8 {
+			regulator-name = "vcc33_ccd";
+			regulator-always-on;
+			regulator-boot-on;
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-state-mem {
+				regulator-on-in-suspend;
+				regulator-suspend-microvolt = <3300000>;
+			};
+		};
+	};
+};
+
+&spi0 {
+	status = "okay";
+
+	cros_ec: ec@0 {
+		compatible = "google,cros-ec-spi";
+		reg = <0>;
+		google,cros-ec-spi-pre-delay = <30>;
+		interrupt-parent = <&gpio7>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ec_int>;
+		spi-max-frequency = <3000000>;
+
+		i2c_tunnel: i2c-tunnel {
+			compatible = "google,cros-ec-i2c-tunnel";
+			google,remote-bus = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+	};
+};
+
+&i2c4 {
+	trackpad@15 {
+		compatible = "elan,ekth3000";
+		reg = <0x15>;
+		interrupt-parent = <&gpio7>;
+		interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&trackpad_int>;
+		vcc-supply = <&vcc33_io>;
+		wakeup-source;
+	};
+};
+
+&pinctrl {
+	pinctrl-0 = <
+		/* Common for sleep and wake, but no owners */
+		&global_pwroff
+
+		/* Wake only */
+		&suspend_l_wake
+	>;
+	pinctrl-1 = <
+		/* Common for sleep and wake, but no owners */
+		&global_pwroff
+
+		/* Sleep only */
+		&suspend_l_sleep
+	>;
+
+	buttons {
+		ap_lid_int_l: ap-lid-int-l {
+			rockchip,pins = <0 6 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	charger {
+		ac_present_ap: ac-present-ap {
+			rockchip,pins = <0 8 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	cros-ec {
+		ec_int: ec-int {
+			rockchip,pins = <7 7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	suspend {
+		suspend_l_wake: suspend-l-wake {
+			rockchip,pins = <0 17 RK_FUNC_GPIO &pcfg_output_low>;
+		};
+
+		suspend_l_sleep: suspend-l-sleep {
+			rockchip,pins = <0 17 RK_FUNC_GPIO &pcfg_output_high>;
+		};
+	};
+
+	trackpad {
+		trackpad_int: trackpad-int {
+			rockchip,pins = <7 3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	usb-host {
+		host1_pwr_en: host1-pwr-en {
+			rockchip,pins = <0 11 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usbotg_pwren_h: usbotg-pwren-h {
+			rockchip,pins = <0 12 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+#include "cros-ec-keyboard.dtsi"
diff --git a/arch/arm/boot/dts/rk3288-veyron-jerry.dts b/arch/arm/boot/dts/rk3288-veyron-jerry.dts
new file mode 100644
index 000000000000..60bd6e91e308
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-jerry.dts
@@ -0,0 +1,197 @@
+/*
+ * Google Veyron Jerry Rev 3+ board device tree source
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "rk3288-veyron-chromebook.dtsi"
+#include "cros-ec-sbs.dtsi"
+
+/ {
+	model = "Google Jerry";
+	compatible = "google,veyron-jerry-rev7", "google,veyron-jerry-rev6",
+		     "google,veyron-jerry-rev5", "google,veyron-jerry-rev4",
+		     "google,veyron-jerry-rev3", "google,veyron-jerry",
+		     "google,veyron", "rockchip,rk3288";
+
+	panel_regulator: panel-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio7 14 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_enable_h>;
+		regulator-name = "panel_regulator";
+		vin-supply = <&vcc33_sys>;
+	};
+
+	vcc18_lcd: vcc18-lcd {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 13 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&avdd_1v8_disp_en>;
+		regulator-name = "vcc18_lcd";
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc18_wl>;
+	};
+
+	backlight_regulator: backlight-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 12 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bl_pwr_en>;
+		regulator-name = "backlight_regulator";
+		vin-supply = <&vcc33_sys>;
+		startup-delay-us = <15000>;
+	};
+};
+
+&rk808 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pmic_int_l>;
+
+	regulators {
+		mic_vcc: LDO_REG2 {
+			regulator-name = "mic_vcc";
+			regulator-always-on;
+			regulator-boot-on;
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+	};
+};
+
+&sdmmc {
+	disable-wp;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd_disabled &sdmmc_cd_gpio
+			&sdmmc_bus4>;
+};
+
+&vcc_5v {
+	enable-active-high;
+	gpio = <&gpio7 21 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&drv_5v>;
+};
+
+&vcc50_hdmi {
+	enable-active-high;
+	gpio = <&gpio5 19 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&vcc50_hdmi_en>;
+};
+
+&pinctrl {
+	backlight {
+		bl_pwr_en: bl_pwr_en {
+			rockchip,pins = <2 12 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	buck-5v {
+		drv_5v: drv-5v {
+			rockchip,pins = <7 21 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	hdmi {
+		vcc50_hdmi_en: vcc50-hdmi-en {
+			rockchip,pins = <5 19 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	lcd {
+		lcd_enable_h: lcd-en {
+			rockchip,pins = <7 14 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		avdd_1v8_disp_en: avdd-1v8-disp-en {
+			rockchip,pins = <2 13 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		dvs_1: dvs-1 {
+			rockchip,pins = <7 12 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		dvs_2: dvs-2 {
+			rockchip,pins = <7 15 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+};
+
+&i2c4 {
+	status = "okay";
+
+	/*
+	 * Trackpad pin control is shared between Elan and Synaptics devices
+	 * so we have to pull it up to the bus level.
+	 */
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c4_xfer &trackpad_int>;
+
+	trackpad@15 {
+		/*
+		 * Remove the inherited pinctrl settings to avoid clashing
+		 * with bus-wide ones.
+		 */
+		/delete-property/pinctrl-names;
+		/delete-property/pinctrl-0;
+	};
+
+	trackpad@2c {
+		compatible = "hid-over-i2c";
+		interrupt-parent = <&gpio7>;
+		interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+		reg = <0x2c>;
+		hid-descr-addr = <0x0020>;
+		vcc-supply = <&vcc33_io>;
+		wakeup-source;
+	};
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron-minnie.dts b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
new file mode 100644
index 000000000000..8fd8ef2c72da
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
@@ -0,0 +1,230 @@
+/*
+ * Google Veyron Minnie Rev 0+ board device tree source
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "rk3288-veyron-chromebook.dtsi"
+
+/ {
+	model = "Google Minnie";
+	compatible = "google,veyron-minnie-rev4", "google,veyron-minnie-rev3",
+		     "google,veyron-minnie-rev2", "google,veyron-minnie-rev1",
+		     "google,veyron-minnie-rev0", "google,veyron-minnie",
+		     "google,veyron", "rockchip,rk3288";
+
+	backlight_regulator: backlight-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 12 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bl_pwr_en>;
+		regulator-name = "backlight_regulator";
+		vin-supply = <&vcc33_sys>;
+		startup-delay-us = <15000>;
+	};
+
+	panel_regulator: panel-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio7 14 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_enable_h>;
+		regulator-name = "panel_regulator";
+		vin-supply = <&vcc33_sys>;
+	};
+
+	vcc18_lcd: vcc18-lcd {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 13 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&avdd_1v8_disp_en>;
+		regulator-name = "vcc18_lcd";
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc18_wl>;
+	};
+};
+
+&gpio_keys {
+	pinctrl-0 = <&pwr_key_l &ap_lid_int_l &volum_down_l &volum_up_l>;
+
+	volum_down {
+		label = "Volum_down";
+		gpios = <&gpio5 11 GPIO_ACTIVE_LOW>;
+		linux,code = <KEY_VOLUMEDOWN>;
+		debounce-interval = <100>;
+	};
+
+	volum_up {
+		label = "Volum_up";
+		gpios = <&gpio5 10 GPIO_ACTIVE_LOW>;
+		linux,code = <KEY_VOLUMEUP>;
+		debounce-interval = <100>;
+	};
+};
+
+&i2c_tunnel {
+	battery: bq27500@55 {
+		compatible = "ti,bq27500";
+		reg = <0x55>;
+	};
+};
+
+&i2c3 {
+	status = "okay";
+
+	clock-frequency = <400000>;
+	i2c-scl-falling-time-ns = <50>;
+	i2c-scl-rising-time-ns = <300>;
+};
+
+&rk808 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pmic_int_l &dvs_1 &dvs_2>;
+
+	regulators {
+		vcc33_touch: LDO_REG2 {
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-name = "vcc33_touch";
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+
+		vcc5v_touch: SWITCH_REG2 {
+			regulator-name = "vcc5v_touch";
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+	};
+};
+
+&sdmmc {
+	disable-wp;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd_disabled &sdmmc_cd_gpio
+			&sdmmc_bus4>;
+};
+
+&vcc_5v {
+	enable-active-high;
+	gpio = <&gpio7 21 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&drv_5v>;
+};
+
+&vcc50_hdmi {
+	enable-active-high;
+	gpio = <&gpio5 19 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&vcc50_hdmi_en>;
+};
+
+&pinctrl {
+	backlight {
+		bl_pwr_en: bl_pwr_en {
+			rockchip,pins = <2 12 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	buck-5v {
+		drv_5v: drv-5v {
+			rockchip,pins = <7 21 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	buttons {
+		volum_down_l: volum-down-l {
+			rockchip,pins = <5 11 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		volum_up_l: volum-up-l {
+			rockchip,pins = <5 10 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	hdmi {
+		vcc50_hdmi_en: vcc50-hdmi-en {
+			rockchip,pins = <5 19 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	lcd {
+		lcd_enable_h: lcd-en {
+			rockchip,pins = <7 14 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		avdd_1v8_disp_en: avdd-1v8-disp-en {
+			rockchip,pins = <2 13 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		dvs_1: dvs-1 {
+			rockchip,pins = <7 12 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		dvs_2: dvs-2 {
+			rockchip,pins = <7 15 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+
+	prochot {
+		gpio_prochot: gpio-prochot {
+			rockchip,pins = <2 8 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	touchscreen {
+		touch_int: touch-int {
+			rockchip,pins = <2 14 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		touch_rst: touch-rst {
+			rockchip,pins = <2 15 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron-pinky.dts b/arch/arm/boot/dts/rk3288-veyron-pinky.dts
new file mode 100644
index 000000000000..94b56e33d947
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-pinky.dts
@@ -0,0 +1,128 @@
+/*
+ * Google Veyron Pinky Rev 2 board device tree source
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "rk3288-veyron-chromebook.dtsi"
+#include "cros-ec-sbs.dtsi"
+
+/ {
+	model = "Google Pinky";
+	compatible = "google,veyron-pinky-rev2", "google,veyron-pinky",
+		     "google,veyron", "rockchip,rk3288";
+
+	/delete-node/emmc-pwrseq;
+};
+
+&emmc {
+	/*
+	 * Use a pullup instead of a drive since the output is 3.3V and
+	 * really should be 1.8V (oops).  The external pulldown will help
+	 * bring the voltage down if we only drive with a pullup here.
+	 * Therefore disable the powerseq (and actual reset) for pinky.
+	 */
+	/delete-property/mmc-pwrseq;
+	pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8 &emmc_reset>;
+};
+
+&gpio_keys {
+	pinctrl-0 = <&pwr_key_h &ap_lid_int_l>;
+
+	power {
+		gpios = <&gpio0 5 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+/* Touchpad connector */
+&i2c3 {
+	status = "okay";
+
+	clock-frequency = <400000>;
+	i2c-scl-falling-time-ns = <50>;
+	i2c-scl-rising-time-ns = <300>;
+};
+
+&pinctrl {
+	buttons {
+		pwr_key_h: pwr-key-h {
+			rockchip,pins = <0 5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	emmc {
+		emmc_reset: emmc-reset {
+			rockchip,pins = <7 12 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdmmc {
+		sdmmc_wp_gpio: sdmmc-wp-gpio {
+			rockchip,pins = <7 10 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+};
+
+&rk808 {
+	regulators {
+		vcc18_lcd: SWITCH_REG2 {
+			regulator-always-on;
+			regulator-boot-on;
+			regulator-name = "vcc18_lcd";
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+	};
+};
+
+&sdmmc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd_disabled &sdmmc_cd_gpio
+		     &sdmmc_wp_gpio &sdmmc_bus4>;
+	wp-gpios = <&gpio7 10 GPIO_ACTIVE_HIGH>;
+};
+
+&tsadc {
+	/* Some connection is flaky making the tsadc hang the system */
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi b/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi
new file mode 100644
index 000000000000..b5334ecff13c
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi
@@ -0,0 +1,122 @@
+/*
+ * Google Veyron (and derivatives) fragment for sdmmc cards
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&io_domains {
+	sdcard-supply = <&vccio_sd>;
+};
+
+&pinctrl {
+	sdmmc {
+		/*
+		 * We run sdmmc at max speed; bump up drive strength.
+		 * We also have external pulls, so disable the internal ones.
+		 */
+		sdmmc_bus4: sdmmc-bus4 {
+			rockchip,pins = <6 16 RK_FUNC_1 &pcfg_pull_none_drv_8ma>,
+					<6 17 RK_FUNC_1 &pcfg_pull_none_drv_8ma>,
+					<6 18 RK_FUNC_1 &pcfg_pull_none_drv_8ma>,
+					<6 19 RK_FUNC_1 &pcfg_pull_none_drv_8ma>;
+		};
+
+		sdmmc_clk: sdmmc-clk {
+			rockchip,pins = <6 20 RK_FUNC_1 &pcfg_pull_none_drv_8ma>;
+		};
+
+		sdmmc_cmd: sdmmc-cmd {
+			rockchip,pins = <6 21 RK_FUNC_1 &pcfg_pull_none_drv_8ma>;
+		};
+
+		/*
+		 * Builtin CD line is hooked to ground to prevent JTAG at boot
+		 * (and also to get the voltage rail correct).
+		 * Configure gpio6_C6 as GPIO so dw_mmc builtin CD doesn't
+		 * think there's a card inserted
+		 */
+		sdmmc_cd_disabled: sdmmc-cd-disabled {
+			rockchip,pins = <6 22 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		/* This is where we actually hook up CD */
+		sdmmc_cd_gpio: sdmmc-cd-gpio {
+			rockchip,pins = <7 5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&rk808 {
+	vcc9-supply = <&vcc_5v>;
+
+	regulators {
+		vccio_sd: LDO_REG4 {
+			regulator-name = "vccio_sd";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+
+		vcc33_sd: LDO_REG5 {
+			regulator-name = "vcc33_sd";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+	};
+};
+
+&sdmmc {
+	status = "okay";
+
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	card-detect-delay = <200>;
+	cd-gpios = <&gpio7 5 GPIO_ACTIVE_LOW>;
+	num-slots = <1>;
+	vmmc-supply = <&vcc33_sd>;
+	vqmmc-supply = <&vccio_sd>;
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron-speedy.dts b/arch/arm/boot/dts/rk3288-veyron-speedy.dts
new file mode 100644
index 000000000000..a7ea7d06cf7f
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-speedy.dts
@@ -0,0 +1,155 @@
+/*
+ * Google Veyron Speedy Rev 1+ board device tree source
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "rk3288-veyron-chromebook.dtsi"
+#include "cros-ec-sbs.dtsi"
+
+/ {
+	model = "Google Speedy";
+	compatible = "google,veyron-speedy-rev9", "google,veyron-speedy-rev8",
+		     "google,veyron-speedy-rev7", "google,veyron-speedy-rev6",
+		     "google,veyron-speedy-rev5", "google,veyron-speedy-rev4",
+		     "google,veyron-speedy-rev3", "google,veyron-speedy-rev2",
+		     "google,veyron-speedy", "google,veyron", "rockchip,rk3288";
+
+	panel_regulator: panel-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio7 14 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_enable_h>;
+		regulator-name = "panel_regulator";
+		vin-supply = <&vcc33_sys>;
+	};
+
+	vcc18_lcd: vcc18-lcd {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 13 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&avdd_1v8_disp_en>;
+		regulator-name = "vcc18_lcd";
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc18_wl>;
+	};
+
+	backlight_regulator: backlight-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 12 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bl_pwr_en>;
+		regulator-name = "backlight_regulator";
+		vin-supply = <&vcc33_sys>;
+		startup-delay-us = <15000>;
+	};
+};
+
+&rk808 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pmic_int_l>;
+};
+
+&sdmmc {
+	disable-wp;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd_disabled &sdmmc_cd_gpio
+			&sdmmc_bus4>;
+};
+
+&vcc_5v {
+	enable-active-high;
+	gpio = <&gpio7 21 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&drv_5v>;
+};
+
+&vcc50_hdmi {
+	enable-active-high;
+	gpio = <&gpio5 19 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&vcc50_hdmi_en>;
+};
+
+&pinctrl {
+	backlight {
+		bl_pwr_en: bl_pwr_en {
+			rockchip,pins = <2 12 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	buck-5v {
+		drv_5v: drv-5v {
+			rockchip,pins = <7 21 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	hdmi {
+		vcc50_hdmi_en: vcc50-hdmi-en {
+			rockchip,pins = <5 19 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	lcd {
+		lcd_enable_h: lcd-en {
+			rockchip,pins = <7 14 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		avdd_1v8_disp_en: avdd-1v8-disp-en {
+			rockchip,pins = <2 13 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		dvs_1: dvs-1 {
+			rockchip,pins = <7 12 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		dvs_2: dvs-2 {
+			rockchip,pins = <7 15 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
new file mode 100644
index 000000000000..2fa7a0dc83f7
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -0,0 +1,563 @@
+/*
+ * Google Veyron (and derivatives) board device tree source
+ *
+ * Copyright 2015 Google, Inc
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/clock/rockchip,rk808.h>
+#include <dt-bindings/input/input.h>
+#include "rk3288.dtsi"
+
+/ {
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x80000000>;
+	};
+
+	gpio_keys: gpio-keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pwr_key_l>;
+		power {
+			label = "Power";
+			gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_POWER>;
+			debounce-interval = <100>;
+			gpio-key,wakeup;
+		};
+	};
+
+	gpio-restart {
+		compatible = "gpio-restart";
+		gpios = <&gpio0 13 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ap_warm_reset_h>;
+		priority = <200>;
+	};
+
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		pinctrl-0 = <&emmc_reset>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio2 9 GPIO_ACTIVE_HIGH>;
+	};
+
+	io_domains: io-domains {
+		compatible = "rockchip,rk3288-io-voltage-domain";
+		rockchip,grf = <&grf>;
+
+		bb-supply = <&vcc33_io>;
+		dvp-supply = <&vcc_18>;
+		flash0-supply = <&vcc18_flashio>;
+		gpio1830-supply = <&vcc33_io>;
+		gpio30-supply = <&vcc33_io>;
+		lcdc-supply = <&vcc33_lcd>;
+		wifi-supply = <&vcc18_wl>;
+	};
+
+	sdio_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&rk808 RK808_CLKOUT1>;
+		clock-names = "ext_clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_enable_l>, <&wifi_enable_h>;
+
+		/*
+		 * On the module itself this is one of these (depending
+		 * on the actual card populated):
+		 * - SDIO_RESET_L_WL_REG_ON
+		 * - PDN (power down when low)
+		 */
+		reset-gpios = <&gpio4 28 GPIO_ACTIVE_LOW>;
+	};
+
+	vcc_5v: vcc-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_5v";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	vcc33_sys: vcc33-sys {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc33_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	vcc50_hdmi: vcc50-hdmi {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc50_hdmi";
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_5v>;
+	};
+};
+
+&cpu0 {
+	cpu0-supply = <&vdd_cpu>;
+};
+
+&emmc {
+	status = "okay";
+
+	broken-cd;
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	disable-wp;
+	mmc-pwrseq = <&emmc_pwrseq>;
+	non-removable;
+	num-slots = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>;
+};
+
+&hdmi {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	clock-frequency = <400000>;
+	i2c-scl-falling-time-ns = <50>;		/* 2.5ns measured */
+	i2c-scl-rising-time-ns = <100>;		/* 45ns measured */
+
+	rk808: pmic@1b {
+		compatible = "rockchip,rk808";
+		reg = <0x1b>;
+		clock-output-names = "xin32k", "wifibt_32kin";
+		interrupt-parent = <&gpio0>;
+		interrupts = <4 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_int_l>;
+		rockchip,system-power-controller;
+		wakeup-source;
+		#clock-cells = <1>;
+
+		vcc1-supply = <&vcc33_sys>;
+		vcc2-supply = <&vcc33_sys>;
+		vcc3-supply = <&vcc33_sys>;
+		vcc4-supply = <&vcc33_sys>;
+		vcc6-supply = <&vcc_5v>;
+		vcc7-supply = <&vcc33_sys>;
+		vcc8-supply = <&vcc33_sys>;
+		vcc12-supply = <&vcc_18>;
+		vddio-supply = <&vcc33_io>;
+
+		regulators {
+			vdd_cpu: DCDC_REG1 {
+				regulator-name = "vdd_arm";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <1450000>;
+				regulator-ramp-delay = <6001>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_gpu: DCDC_REG2 {
+				regulator-name = "vdd_gpu";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1250000>;
+				regulator-ramp-delay = <6001>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1000000>;
+				};
+			};
+
+			vcc135_ddr: DCDC_REG3 {
+				regulator-name = "vcc135_ddr";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			/*
+			 * vcc_18 has several aliases.  (vcc18_flashio and
+			 * vcc18_wl).  We'll add those aliases here just to
+			 * make it easier to follow the schematic.  The signals
+			 * are actually hooked together and only separated for
+			 * power measurement purposes).
+			 */
+			vcc18_wl: vcc18_flashio: vcc_18: DCDC_REG4 {
+				regulator-name = "vcc_18";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			/*
+			 * Note that both vcc33_io and vcc33_pmuio are always
+			 * powered together. To simplify the logic in the dts
+			 * we just refer to vcc33_io every time something is
+			 * powered from vcc33_pmuio. In fact, on later boards
+			 * (such as danger) they're the same net.
+			 */
+			vcc33_io: LDO_REG1 {
+				regulator-name = "vcc33_io";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vdd_10: LDO_REG3 {
+				regulator-name = "vdd_10";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1000000>;
+				};
+			};
+
+			vdd10_lcd_pwren_h: LDO_REG7 {
+				regulator-name = "vdd10_lcd_pwren_h";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc33_lcd: SWITCH_REG1 {
+				regulator-name = "vcc33_lcd";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&i2c1 {
+	status = "okay";
+
+	clock-frequency = <400000>;
+	i2c-scl-falling-time-ns = <50>;		/* 2.5ns measured */
+	i2c-scl-rising-time-ns = <100>;		/* 40ns measured */
+
+	tpm: tpm@20 {
+		compatible = "infineon,slb9645tt";
+		reg = <0x20>;
+		powered-while-suspended;
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	/* 100kHz since 4.7k resistors don't rise fast enough */
+	clock-frequency = <100000>;
+	i2c-scl-falling-time-ns = <50>;		/* 10ns measured */
+	i2c-scl-rising-time-ns = <800>;		/* 600ns measured */
+};
+
+&i2c4 {
+	status = "okay";
+
+	clock-frequency = <400000>;
+	i2c-scl-falling-time-ns = <50>;		/* 11ns measured */
+	i2c-scl-rising-time-ns = <300>;		/* 225ns measured */
+};
+
+&i2c5 {
+	status = "okay";
+
+	clock-frequency = <100000>;
+	i2c-scl-falling-time-ns = <300>;
+	i2c-scl-rising-time-ns = <1000>;
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&sdio0 {
+	status = "okay";
+
+	broken-cd;
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&sdio_pwrseq>;
+	non-removable;
+	num-slots = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdio0_clk &sdio0_cmd &sdio0_bus4>;
+	vmmc-supply = <&vcc33_sys>;
+	vqmmc-supply = <&vcc18_wl>;
+};
+
+&spi2 {
+	status = "okay";
+
+	rx-sample-delay-ns = <12>;
+};
+
+&tsadc {
+	status = "okay";
+
+	rockchip,hw-tshut-mode = <1>; /* tshut mode 0:CRU 1:GPIO */
+	rockchip,hw-tshut-polarity = <1>; /* tshut polarity 0:LOW 1:HIGH */
+};
+
+&uart0 {
+	status = "okay";
+
+	/* We need to go faster than 24MHz, so adjust clock parents / rates */
+	assigned-clocks = <&cru SCLK_UART0>;
+	assigned-clock-rates = <48000000>;
+
+	/* Pins don't include flow control by default; add that in */
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_xfer &uart0_cts &uart0_rts>;
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+
+	needs-reset-on-resume;
+};
+
+&usb_host1 {
+	status = "okay";
+};
+
+&usb_otg {
+	status = "okay";
+
+	assigned-clocks = <&cru SCLK_USBPHY480M_SRC>;
+	assigned-clock-parents = <&cru SCLK_OTGPHY0>;
+	dr_mode = "host";
+};
+
+&vopb {
+	status = "okay";
+};
+
+&vopb_mmu {
+	status = "okay";
+};
+
+&wdt {
+	status = "okay";
+};
+
+&pinctrl {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <
+		/* Common for sleep and wake, but no owners */
+		&global_pwroff
+	>;
+	pinctrl-1 = <
+		/* Common for sleep and wake, but no owners */
+		&global_pwroff
+	>;
+
+	pcfg_pull_none_drv_8ma: pcfg-pull-none-drv-8ma {
+		bias-disable;
+		drive-strength = <8>;
+	};
+
+	pcfg_pull_up_drv_8ma: pcfg-pull-up-drv-8ma {
+		bias-pull-up;
+		drive-strength = <8>;
+	};
+
+	pcfg_output_high: pcfg-output-high {
+		output-high;
+	};
+
+	pcfg_output_low: pcfg-output-low {
+		output-low;
+	};
+
+	buttons {
+		pwr_key_l: pwr-key-l {
+			rockchip,pins = <0 5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	emmc {
+		emmc_reset: emmc-reset {
+			rockchip,pins = <2 9 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		/*
+		 * We run eMMC at max speed; bump up drive strength.
+		 * We also have external pulls, so disable the internal ones.
+		 */
+		emmc_clk: emmc-clk {
+			rockchip,pins = <3 18 RK_FUNC_2 &pcfg_pull_none_drv_8ma>;
+		};
+
+		emmc_cmd: emmc-cmd {
+			rockchip,pins = <3 16 RK_FUNC_2 &pcfg_pull_none_drv_8ma>;
+		};
+
+		emmc_bus8: emmc-bus8 {
+			rockchip,pins = <3 0 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 1 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 2 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 3 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 4 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 5 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 6 RK_FUNC_2 &pcfg_pull_none_drv_8ma>,
+					<3 7 RK_FUNC_2 &pcfg_pull_none_drv_8ma>;
+		};
+	};
+
+	pmic {
+		pmic_int_l: pmic-int-l {
+			rockchip,pins = <RK_GPIO0 4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	reboot {
+		ap_warm_reset_h: ap-warm-reset-h {
+			rockchip,pins = <RK_GPIO0 13 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	recovery-switch {
+		rec_mode_l: rec-mode-l {
+			rockchip,pins = <0 9 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdio0 {
+		wifi_enable_h: wifienable-h {
+			rockchip,pins = <4 28 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		/* NOTE: mislabelled on schematic; should be bt_enable_h */
+		bt_enable_l: bt-enable-l {
+			rockchip,pins = <4 29 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		/*
+		 * We run sdio0 at max speed; bump up drive strength.
+		 * We also have external pulls, so disable the internal ones.
+		 */
+		sdio0_bus4: sdio0-bus4 {
+			rockchip,pins = <4 20 RK_FUNC_1 &pcfg_pull_none_drv_8ma>,
+					<4 21 RK_FUNC_1 &pcfg_pull_none_drv_8ma>,
+					<4 22 RK_FUNC_1 &pcfg_pull_none_drv_8ma>,
+					<4 23 RK_FUNC_1 &pcfg_pull_none_drv_8ma>;
+		};
+
+		sdio0_cmd: sdio0-cmd {
+			rockchip,pins = <4 24 RK_FUNC_1 &pcfg_pull_none_drv_8ma>;
+		};
+
+		sdio0_clk: sdio0-clk {
+			rockchip,pins = <4 25 RK_FUNC_1 &pcfg_pull_none_drv_8ma>;
+		};
+	};
+
+	tpm {
+		tpm_int_h: tpm-int-h {
+			rockchip,pins = <7 4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	/*
+	 * On Marvell-based hardware this is a no-connect.  Make sure we enable
+	 * the pullup so that the line doesn't float.  The pullup shouldn't
+	 * hurt on Broadcom-based hardware since the other side is actively
+	 * driving this signal.  As proof: we've already got a pullup on RX.
+	 */
+	uart0 {
+		uart0_cts: uart0-cts {
+			rockchip,pins = <4 18 RK_FUNC_1 &pcfg_pull_up>;
+		};
+	};
+
+	write-protect {
+		fw_wp_ap: fw-wp-ap {
+			rockchip,pins = <7 6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 22316d00493e..906e938fb6bf 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -78,6 +78,7 @@
 			     <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
 	};
 
 	cpus {
@@ -110,19 +111,19 @@
 			clock-latency = <40000>;
 			clocks = <&cru ARMCLK>;
 		};
-		cpu@501 {
+		cpu1: cpu@501 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a12";
 			reg = <0x501>;
 			resets = <&cru SRST_CORE1>;
 		};
-		cpu@502 {
+		cpu2: cpu@502 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a12";
 			reg = <0x502>;
 			resets = <&cru SRST_CORE2>;
 		};
-		cpu@503 {
+		cpu3: cpu@503 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a12";
 			reg = <0x503>;
@@ -168,6 +169,26 @@
 		};
 	};
 
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		/*
+		 * The rk3288 cannot use the memory area above 0xfe000000
+		 * for dma operations for some reason. While there is
+		 * probably a better solution available somewhere, we
+		 * haven't found it yet and while devices with 2GB of ram
+		 * are not affected, this issue prevents 4GB from booting.
+		 * So to make these devices at least bootable, block
+		 * this area for the time being until the real solution
+		 * is found.
+		 */
+		dma-unusable@fe000000 {
+			reg = <0xfe000000 0x1000000>;
+		};
+	};
+
 	xin24m: oscillator {
 		compatible = "fixed-clock";
 		clock-frequency = <24000000>;
@@ -447,6 +468,8 @@
 			"mac_clk_rx", "mac_clk_tx",
 			"clk_mac_ref", "clk_mac_refout",
 			"aclk_mac", "pclk_mac";
+		resets = <&cru SRST_MAC>;
+		reset-names = "stmmaceth";
 		status = "disabled";
 	};
 
@@ -626,7 +649,7 @@
 		compatible = "rockchip,rk3288-wdt", "snps,dw-wdt";
 		reg = <0xff800000 0x100>;
 		clocks = <&cru PCLK_WDT>;
-		interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi
index a2ae9f32464d..4497d288a7cb 100644
--- a/arch/arm/boot/dts/rk3xxx.dtsi
+++ b/arch/arm/boot/dts/rk3xxx.dtsi
@@ -172,6 +172,13 @@
 		interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_OTG0>;
 		clock-names = "otg";
+		dr_mode = "otg";
+		g-np-tx-fifo-size = <16>;
+		g-rx-fifo-size = <275>;
+		g-tx-fifo-size = <256 128 128 64 64 32>;
+		g-use-dma;
+		phys = <&usbphy0>;
+		phy-names = "usb2-phy";
 		status = "disabled";
 	};
 
@@ -181,6 +188,9 @@
 		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_OTG1>;
 		clock-names = "otg";
+		dr_mode = "host";
+		phys = <&usbphy1>;
+		phy-names = "usb2-phy";
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
new file mode 100644
index 000000000000..034cd48ae28b
--- /dev/null
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -0,0 +1,926 @@
+/*
+ * sama5d2.dtsi - Device Tree Include file for SAMA5D2 family SoC
+ *
+ *  Copyright (C) 2015 Atmel,
+ *                2015 Ludovic Desroches <ludovic.desroches@atmel.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "skeleton.dtsi"
+#include <dt-bindings/dma/at91.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/at91.h>
+
+/ {
+	model = "Atmel SAMA5D2 family SoC";
+	compatible = "atmel,sama5d2";
+	interrupt-parent = <&aic>;
+
+	aliases {
+		serial0 = &uart1;
+		serial1 = &uart3;
+		tcb0 = &tcb0;
+		tcb1 = &tcb1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a5";
+			reg = <0>;
+			next-level-cache = <&L2>;
+		};
+	};
+
+	memory {
+		reg = <0x20000000 0x20000000>;
+	};
+
+	clocks {
+		slow_xtal: slow_xtal {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+		};
+
+		main_xtal: main_xtal {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+		};
+
+		adc_op_clk: adc_op_clk{
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <1000000>;
+		};
+	};
+
+	ns_sram: sram@00200000 {
+		compatible = "mmio-sram";
+		reg = <0x00200000 0x20000>;
+	};
+
+	ahb {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		usb0: gadget@00300000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "atmel,sama5d3-udc";
+			reg = <0x00300000 0x100000
+			       0xfc02c000 0x400>;
+			interrupts = <42 IRQ_TYPE_LEVEL_HIGH 2>;
+			clocks = <&udphs_clk>, <&utmi>;
+			clock-names = "pclk", "hclk";
+			status = "disabled";
+
+			ep0 {
+				reg = <0>;
+				atmel,fifo-size = <64>;
+				atmel,nb-banks = <1>;
+			};
+
+			ep1 {
+				reg = <1>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <3>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep2 {
+				reg = <2>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <3>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep3 {
+				reg = <3>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep4 {
+				reg = <4>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep5 {
+				reg = <5>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep6 {
+				reg = <6>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep7 {
+				reg = <7>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-dma;
+				atmel,can-isoc;
+			};
+
+			ep8 {
+				reg = <8>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep9 {
+				reg = <9>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep10 {
+				reg = <10>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep11 {
+				reg = <11>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep12 {
+				reg = <12>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep13 {
+				reg = <13>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep14 {
+				reg = <14>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+
+			ep15 {
+				reg = <15>;
+				atmel,fifo-size = <1024>;
+				atmel,nb-banks = <2>;
+				atmel,can-isoc;
+			};
+		};
+
+		usb1: ohci@00400000 {
+			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
+			reg = <0x00400000 0x100000>;
+			interrupts = <41 IRQ_TYPE_LEVEL_HIGH 2>;
+			clocks = <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
+			clock-names = "ohci_clk", "hclk", "uhpck";
+			status = "disabled";
+		};
+
+		usb2: ehci@00500000 {
+			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
+			reg = <0x00500000 0x100000>;
+			interrupts = <41 IRQ_TYPE_LEVEL_HIGH 2>;
+			clocks = <&utmi>, <&uhphs_clk>;
+			clock-names = "usb_clk", "ehci_clk";
+			status = "disabled";
+		};
+
+		L2: cache-controller@00a00000 {
+			compatible = "arm,pl310-cache";
+			reg = <0x00a00000 0x1000>;
+			interrupts = <63 IRQ_TYPE_LEVEL_HIGH 4>;
+			cache-unified;
+			cache-level = <2>;
+		};
+
+		apb {
+			compatible = "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			ramc0: ramc@f000c000 {
+				compatible = "atmel,sama5d3-ddramc";
+				reg = <0xf000c000 0x200>;
+				clocks = <&ddrck>, <&mpddr_clk>;
+				clock-names = "ddrck", "mpddr";
+			};
+
+			dma0: dma-controller@f0010000 {
+				compatible = "atmel,sama5d4-dma";
+				reg = <0xf0010000 0x1000>;
+				interrupts = <6 IRQ_TYPE_LEVEL_HIGH 0>;
+				#dma-cells = <1>;
+				clocks = <&dma0_clk>;
+				clock-names = "dma_clk";
+			};
+
+			pmc: pmc@f0014000 {
+				compatible = "atmel,sama5d2-pmc";
+				reg = <0xf0014000 0x160>;
+				interrupts = <74 IRQ_TYPE_LEVEL_HIGH 7>;
+				interrupt-controller;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				#interrupt-cells = <1>;
+
+				main_rc_osc: main_rc_osc {
+					compatible = "atmel,at91sam9x5-clk-main-rc-osc";
+					#clock-cells = <0>;
+					interrupt-parent = <&pmc>;
+					interrupts = <AT91_PMC_MOSCRCS>;
+					clock-frequency = <12000000>;
+					clock-accuracy = <100000000>;
+				};
+
+				main_osc: main_osc {
+					compatible = "atmel,at91rm9200-clk-main-osc";
+					#clock-cells = <0>;
+					interrupt-parent = <&pmc>;
+					interrupts = <AT91_PMC_MOSCS>;
+					clocks = <&main_xtal>;
+				};
+
+				main: mainck {
+					compatible = "atmel,at91sam9x5-clk-main";
+					#clock-cells = <0>;
+					interrupt-parent = <&pmc>;
+					interrupts = <AT91_PMC_MOSCSELS>;
+					clocks = <&main_rc_osc &main_osc>;
+				};
+
+				plla: pllack {
+					compatible = "atmel,sama5d3-clk-pll";
+					#clock-cells = <0>;
+					interrupt-parent = <&pmc>;
+					interrupts = <AT91_PMC_LOCKA>;
+					clocks = <&main>;
+					reg = <0>;
+					atmel,clk-input-range = <12000000 12000000>;
+					#atmel,pll-clk-output-range-cells = <4>;
+					atmel,pll-clk-output-ranges = <600000000 1200000000 0 0>;
+				};
+
+				plladiv: plladivck {
+					compatible = "atmel,at91sam9x5-clk-plldiv";
+					#clock-cells = <0>;
+					clocks = <&plla>;
+				};
+
+				utmi: utmick {
+					compatible = "atmel,at91sam9x5-clk-utmi";
+					#clock-cells = <0>;
+					interrupt-parent = <&pmc>;
+					interrupts = <AT91_PMC_LOCKU>;
+					clocks = <&main>;
+				};
+
+				mck: masterck {
+					compatible = "atmel,at91sam9x5-clk-master";
+					#clock-cells = <0>;
+					interrupt-parent = <&pmc>;
+					interrupts = <AT91_PMC_MCKRDY>;
+					clocks = <&clk32k>, <&main>, <&plladiv>, <&utmi>;
+					atmel,clk-output-range = <124000000 166000000>;
+					atmel,clk-divisors = <1 2 4 3>;
+				};
+
+				h32ck: h32mxck {
+					#clock-cells = <0>;
+					compatible = "atmel,sama5d4-clk-h32mx";
+					clocks = <&mck>;
+				};
+
+				usb: usbck {
+					compatible = "atmel,at91sam9x5-clk-usb";
+					#clock-cells = <0>;
+					clocks = <&plladiv>, <&utmi>;
+				};
+
+				prog: progck {
+					compatible = "atmel,at91sam9x5-clk-programmable";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					interrupt-parent = <&pmc>;
+					clocks = <&clk32k>, <&main>, <&plladiv>, <&utmi>, <&mck>;
+
+					prog0: prog0 {
+						#clock-cells = <0>;
+						reg = <0>;
+						interrupts = <AT91_PMC_PCKRDY(0)>;
+					};
+
+					prog1: prog1 {
+						#clock-cells = <0>;
+						reg = <1>;
+						interrupts = <AT91_PMC_PCKRDY(1)>;
+					};
+
+					prog2: prog2 {
+						#clock-cells = <0>;
+						reg = <2>;
+						interrupts = <AT91_PMC_PCKRDY(2)>;
+					};
+				};
+
+				systemck {
+					compatible = "atmel,at91rm9200-clk-system";
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					ddrck: ddrck {
+						#clock-cells = <0>;
+						reg = <2>;
+						clocks = <&mck>;
+					};
+
+					lcdck: lcdck {
+						#clock-cells = <0>;
+						reg = <3>;
+						clocks = <&mck>;
+					};
+
+					uhpck: uhpck {
+						#clock-cells = <0>;
+						reg = <6>;
+						clocks = <&usb>;
+					};
+
+					udpck: udpck {
+						#clock-cells = <0>;
+						reg = <7>;
+						clocks = <&usb>;
+					};
+
+					pck0: pck0 {
+						#clock-cells = <0>;
+						reg = <8>;
+						clocks = <&prog0>;
+					};
+
+					pck1: pck1 {
+						#clock-cells = <0>;
+						reg = <9>;
+						clocks = <&prog1>;
+					};
+
+					pck2: pck2 {
+						#clock-cells = <0>;
+						reg = <10>;
+						clocks = <&prog2>;
+					};
+
+					iscck: iscck {
+						#clock-cells = <0>;
+						reg = <18>;
+						clocks = <&mck>;
+					};
+				};
+
+				periph32ck {
+					compatible = "atmel,at91sam9x5-clk-peripheral";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					clocks = <&h32ck>;
+
+					macb0_clk: macb0_clk {
+						#clock-cells = <0>;
+						reg = <5>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					tdes_clk: tdes_clk {
+						#clock-cells = <0>;
+						reg = <11>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					matrix1_clk: matrix1_clk {
+						#clock-cells = <0>;
+						reg = <14>;
+					};
+
+					hsmc_clk: hsmc_clk {
+						#clock-cells = <0>;
+						reg = <17>;
+					};
+
+					pioA_clk: pioA_clk {
+						#clock-cells = <0>;
+						reg = <18>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					flx0_clk: flx0_clk {
+						#clock-cells = <0>;
+						reg = <19>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					flx1_clk: flx1_clk {
+						#clock-cells = <0>;
+						reg = <20>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					flx2_clk: flx2_clk {
+						#clock-cells = <0>;
+						reg = <21>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					flx3_clk: flx3_clk {
+						#clock-cells = <0>;
+						reg = <22>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					flx4_clk: flx4_clk {
+						#clock-cells = <0>;
+						reg = <23>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					uart0_clk: uart0_clk {
+						#clock-cells = <0>;
+						reg = <24>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					uart1_clk: uart1_clk {
+						#clock-cells = <0>;
+						reg = <25>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					uart2_clk: uart2_clk {
+						#clock-cells = <0>;
+						reg = <26>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					uart3_clk: uart3_clk {
+						#clock-cells = <0>;
+						reg = <27>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					uart4_clk: uart4_clk {
+						#clock-cells = <0>;
+						reg = <28>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					twi0_clk: twi0_clk {
+						reg = <29>;
+						#clock-cells = <0>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					twi1_clk: twi1_clk {
+						#clock-cells = <0>;
+						reg = <30>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					spi0_clk: spi0_clk {
+						#clock-cells = <0>;
+						reg = <33>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					spi1_clk: spi1_clk {
+						#clock-cells = <0>;
+						reg = <34>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					tcb0_clk: tcb0_clk {
+						#clock-cells = <0>;
+						reg = <35>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					tcb1_clk: tcb1_clk {
+						#clock-cells = <0>;
+						reg = <36>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					pwm_clk: pwm_clk {
+						#clock-cells = <0>;
+						reg = <38>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					adc_clk: adc_clk {
+						#clock-cells = <0>;
+						reg = <40>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					uhphs_clk: uhphs_clk {
+						#clock-cells = <0>;
+						reg = <41>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					udphs_clk: udphs_clk {
+						#clock-cells = <0>;
+						reg = <42>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					ssc0_clk: ssc0_clk {
+						#clock-cells = <0>;
+						reg = <43>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					ssc1_clk: ssc1_clk {
+						#clock-cells = <0>;
+						reg = <44>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					trng_clk: trng_clk {
+						#clock-cells = <0>;
+						reg = <47>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+
+					classd_clk: classd_clk {
+						#clock-cells = <0>;
+						reg = <59>;
+						atmel,clk-output-range = <0 83000000>;
+					};
+				};
+
+				periph64ck {
+					compatible = "atmel,at91sam9x5-clk-peripheral";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					clocks = <&mck>;
+
+					dma0_clk: dma0_clk {
+						#clock-cells = <0>;
+						reg = <6>;
+					};
+
+					dma1_clk: dma1_clk {
+						#clock-cells = <0>;
+						reg = <7>;
+					};
+
+					aes_clk: aes_clk {
+						#clock-cells = <0>;
+						reg = <9>;
+					};
+
+					aesb_clk: aesb_clk {
+						#clock-cells = <0>;
+						reg = <10>;
+					};
+
+					sha_clk: sha_clk {
+						#clock-cells = <0>;
+						reg = <12>;
+					};
+
+					mpddr_clk: mpddr_clk {
+						#clock-cells = <0>;
+						reg = <13>;
+					};
+
+					matrix0_clk: matrix0_clk {
+						#clock-cells = <0>;
+						reg = <15>;
+					};
+
+					sdmmc0_hclk: sdmmc0_hclk {
+						#clock-cells = <0>;
+						reg = <31>;
+					};
+
+					sdmmc1_hclk: sdmmc1_hclk {
+						#clock-cells = <0>;
+						reg = <32>;
+					};
+
+					lcdc_clk: lcdc_clk {
+						#clock-cells = <0>;
+						reg = <45>;
+					};
+
+					isc_clk: isc_clk {
+						#clock-cells = <0>;
+						reg = <46>;
+					};
+
+					qspi0_clk: qspi0_clk {
+						#clock-cells = <0>;
+						reg = <52>;
+					};
+
+					qspi1_clk: qspi1_clk {
+						#clock-cells = <0>;
+						reg = <53>;
+					};
+				};
+			};
+
+			sha@f0028000 {
+				compatible = "atmel,at91sam9g46-sha";
+				reg = <0xf0028000 0x100>;
+				interrupts = <12 IRQ_TYPE_LEVEL_HIGH 0>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(30))>;
+				dma-names = "tx";
+				clocks = <&sha_clk>;
+				clock-names = "sha_clk";
+				status = "disabled";
+			};
+
+			aes@f002c000 {
+				compatible = "atmel,at91sam9g46-aes";
+				reg = <0xf002c000 0x100>;
+				interrupts = <9 IRQ_TYPE_LEVEL_HIGH 0>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(26))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(27))>;
+				dma-names = "tx", "rx";
+				clocks = <&aes_clk>;
+				clock-names = "aes_clk";
+				status = "disabled";
+			};
+
+			spi0: spi@f8000000 {
+				compatible = "atmel,at91rm9200-spi";
+				reg = <0xf8000000 0x100>;
+				interrupts = <33 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(6))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(7))>;
+				dma-names = "tx", "rx";
+				clocks = <&spi0_clk>;
+				clock-names = "spi_clk";
+				atmel,fifo-size = <16>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			macb0: ethernet@f8008000 {
+				compatible = "atmel,sama5d2-gem";
+				reg = <0xf8008000 0x1000>;
+				interrupts = <5  IRQ_TYPE_LEVEL_HIGH 3		/* Queue 0 */
+					      66 IRQ_TYPE_LEVEL_HIGH 3          /* Queue 1 */
+					      67 IRQ_TYPE_LEVEL_HIGH 3>;        /* Queue 2 */
+				#address-cells = <1>;
+				#size-cells = <0>;
+				clocks = <&macb0_clk>, <&macb0_clk>;
+				clock-names = "hclk", "pclk";
+				status = "disabled";
+			};
+
+			tcb0: timer@f800c000 {
+				compatible = "atmel,at91sam9x5-tcb";
+				reg = <0xf800c000 0x100>;
+				interrupts = <35 IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
+			};
+
+			tcb1: timer@f8010000 {
+				compatible = "atmel,at91sam9x5-tcb";
+				reg = <0xf8010000 0x100>;
+				interrupts = <36 IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&tcb1_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
+			};
+
+			uart0: serial@f801c000 {
+				compatible = "atmel,at91sam9260-usart";
+				reg = <0xf801c000 0x100>;
+				interrupts = <24 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&uart0_clk>;
+				clock-names = "usart";
+				status = "disabled";
+			};
+
+			uart1: serial@f8020000 {
+				compatible = "atmel,at91sam9260-usart";
+				reg = <0xf8020000 0x100>;
+				interrupts = <25 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&uart1_clk>;
+				clock-names = "usart";
+				status = "disabled";
+			};
+
+			uart2: serial@f8024000 {
+				compatible = "atmel,at91sam9260-usart";
+				reg = <0xf8024000 0x100>;
+				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&uart2_clk>;
+				clock-names = "usart";
+				status = "disabled";
+			};
+
+			i2c0: i2c@f8028000 {
+				compatible = "atmel,sama5d2-i2c";
+				reg = <0xf8028000 0x100>;
+				interrupts = <29 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(0))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(1))>;
+				dma-names = "tx", "rx";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				clocks = <&twi0_clk>;
+				status = "disabled";
+			};
+
+			pit: timer@f8048030 {
+				compatible = "atmel,at91sam9260-pit";
+				reg = <0xf8048030 0x10>;
+				interrupts = <3 IRQ_TYPE_LEVEL_HIGH 5>;
+				clocks = <&h32ck>;
+			};
+
+			sckc@f8048050 {
+				compatible = "atmel,at91sam9x5-sckc";
+				reg = <0xf8048050 0x4>;
+
+				slow_rc_osc: slow_rc_osc {
+					compatible = "atmel,at91sam9x5-clk-slow-rc-osc";
+					#clock-cells = <0>;
+					clock-frequency = <32768>;
+					clock-accuracy = <250000000>;
+					atmel,startup-time-usec = <75>;
+				};
+
+				slow_osc: slow_osc {
+					compatible = "atmel,at91sam9x5-clk-slow-osc";
+					#clock-cells = <0>;
+					clocks = <&slow_xtal>;
+					atmel,startup-time-usec = <1200000>;
+				};
+
+				clk32k: slowck {
+					compatible = "atmel,at91sam9x5-clk-slow";
+					#clock-cells = <0>;
+					clocks = <&slow_rc_osc &slow_osc>;
+				};
+			};
+
+			rtc@f80480b0 {
+				compatible = "atmel,at91rm9200-rtc";
+				reg = <0xf80480b0 0x30>;
+				interrupts = <74 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
+			};
+
+			spi1: spi@fc000000 {
+				compatible = "atmel,at91rm9200-spi";
+				reg = <0xfc000000 0x100>;
+				interrupts = <34 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(8))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(9))>;
+				dma-names = "tx", "rx";
+				clocks = <&spi1_clk>;
+				clock-names = "spi_clk";
+				atmel,fifo-size = <16>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			uart3: serial@fc008000 {
+				compatible = "atmel,at91sam9260-usart";
+				reg = <0xfc008000 0x100>;
+				interrupts = <27 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&uart3_clk>;
+				clock-names = "usart";
+				status = "disabled";
+			};
+
+			uart4: serial@fc00c000 {
+				compatible = "atmel,at91sam9260-usart";
+				reg = <0xfc00c000 0x100>;
+				interrupts = <28 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&uart4_clk>;
+				clock-names = "usart";
+				status = "disabled";
+			};
+
+			aic: interrupt-controller@fc020000 {
+				#interrupt-cells = <3>;
+				compatible = "atmel,sama5d2-aic";
+				interrupt-controller;
+				reg = <0xfc020000 0x200>;
+				atmel,external-irqs = <49>;
+			};
+
+			i2c1: i2c@fc028000 {
+				compatible = "atmel,sama5d2-i2c";
+				reg = <0xfc028000 0x100>;
+				interrupts = <30 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(2))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(3))>;
+				dma-names = "tx", "rx";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				clocks = <&twi1_clk>;
+				status = "disabled";
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 9e2444b07bce..7fa276515f11 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -145,8 +145,8 @@
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf0010000 0x100>;
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb0_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			i2c0: i2c@f0014000 {
@@ -1259,13 +1259,15 @@
 			};
 
 			rstc@fffffe00 {
-				compatible = "atmel,at91sam9g45-rstc";
+				compatible = "atmel,sama5d3-rstc", "atmel,at91sam9g45-rstc";
 				reg = <0xfffffe00 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			shutdown-controller@fffffe10 {
 				compatible = "atmel,at91sam9x5-shdwc";
 				reg = <0xfffffe10 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fffffe30 {
@@ -1279,6 +1281,7 @@
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfffffe40 0x10>;
 				interrupts = <4 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
@@ -1315,6 +1318,7 @@
 				compatible = "atmel,at91rm9200-rtc";
 				reg = <0xfffffeb0 0x30>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/sama5d3_tcb1.dtsi b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
index f7fa58fe09f1..801f9745e82f 100644
--- a/arch/arm/boot/dts/sama5d3_tcb1.dtsi
+++ b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
@@ -31,8 +31,8 @@
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf8014000 0x100>;
 				interrupts = <27 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb1_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb1_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 3ee22ee13c5a..8d1de29e8da1 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -957,8 +957,8 @@
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xf801c000 0x100>;
 				interrupts = <40 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb0_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb0_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			macb0: ethernet@f8020000 {
@@ -1185,29 +1185,20 @@
 				compatible = "atmel,at91sam9x5-tcb";
 				reg = <0xfc020000 0x100>;
 				interrupts = <41 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&tcb1_clk>;
-				clock-names = "t0_clk";
+				clocks = <&tcb1_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
 			};
 
 			adc0: adc@fc034000 {
 				compatible = "atmel,at91sam9x5-adc";
 				reg = <0xfc034000 0x100>;
 				interrupts = <44 IRQ_TYPE_LEVEL_HIGH 5>;
-				pinctrl-names = "default";
-				pinctrl-0 = <
-					/* external trigger is conflict with USBA_VBUS */
-					&pinctrl_adc0_ad0
-					&pinctrl_adc0_ad1
-					&pinctrl_adc0_ad2
-					&pinctrl_adc0_ad3
-					&pinctrl_adc0_ad4
-					>;
 				clocks = <&adc_clk>,
 					 <&adc_op_clk>;
 				clock-names = "adc_clk", "adc_op_clk";
 				atmel,adc-channels-used = <0x01f>;
 				atmel,adc-startup-time = <40>;
-				atmel,adc-use-external;
+				atmel,adc-use-external-triggers;
 				atmel,adc-vref = <3000>;
 				atmel,adc-res = <8 10>;
 				atmel,adc-sample-hold-time = <11>;
@@ -1277,13 +1268,15 @@
 			};
 
 			rstc@fc068600 {
-				compatible = "atmel,at91sam9g45-rstc";
+				compatible = "atmel,sama5d3-rstc", "atmel,at91sam9g45-rstc";
 				reg = <0xfc068600 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			shdwc@fc068610 {
 				compatible = "atmel,at91sam9x5-shdwc";
 				reg = <0xfc068610 0x10>;
+				clocks = <&clk32k>;
 			};
 
 			pit: timer@fc068630 {
@@ -1296,6 +1289,7 @@
 			watchdog@fc068640 {
 				compatible = "atmel,at91sam9260-wdt";
 				reg = <0xfc068640 0x10>;
+				clocks = <&clk32k>;
 				status = "disabled";
 			};
 
@@ -1329,6 +1323,7 @@
 				compatible = "atmel,at91rm9200-rtc";
 				reg = <0xfc0686b0 0x30>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+				clocks = <&clk32k>;
 			};
 
 			dbgu: serial@fc069000 {
diff --git a/arch/arm/boot/dts/sh73a0.dtsi b/arch/arm/boot/dts/sh73a0.dtsi
index 11e17c5f26e2..ff7c8f298f30 100644
--- a/arch/arm/boot/dts/sh73a0.dtsi
+++ b/arch/arm/boot/dts/sh73a0.dtsi
@@ -392,6 +392,9 @@
 		      <0xe605801c 0x1c>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges =
+			<&pfc 0 0 119>, <&pfc 128 128 37>, <&pfc 192 192 91>,
+			<&pfc 288 288 22>;
 		interrupts-extended =
 			<&irqpin0 0 0>, <&irqpin0 1 0>, <&irqpin0 2 0>, <&irqpin0 3 0>,
 			<&irqpin0 4 0>, <&irqpin0 5 0>, <&irqpin0 6 0>, <&irqpin0 7 0>,
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 80f924deed37..314e589cfa00 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -164,7 +164,7 @@
 						dbg_base_clk: dbg_base_clk {
 							#clock-cells = <0>;
 							compatible = "altr,socfpga-perip-clk";
-							clocks = <&main_pll>;
+							clocks = <&main_pll>, <&osc1>;
 							div-reg = <0xe8 0 9>;
 							reg = <0x50>;
 						};
@@ -318,7 +318,7 @@
 					l3_sp_clk: l3_sp_clk {
 						#clock-cells = <0>;
 						compatible = "altr,socfpga-gate-clk";
-						clocks = <&mainclk>;
+						clocks = <&l3_mp_clk>;
 						div-reg = <0x64 2 2>;
 					};
 
@@ -349,7 +349,7 @@
 					dbg_clk: dbg_clk {
 						#clock-cells = <0>;
 						compatible = "altr,socfpga-gate-clk";
-						clocks = <&dbg_base_clk>;
+						clocks = <&dbg_at_clk>;
 						div-reg = <0x68 2 2>;
 						clk-gate = <0x60 5>;
 					};
@@ -481,8 +481,37 @@
 						clocks = <&f2s_periph_ref_clk>, <&main_qspi_clk>, <&per_qspi_clk>;
 						clk-gate = <0xa0 11>;
 					};
+
+					ddr_dqs_clk_gate: ddr_dqs_clk_gate {
+						#clock-cells = <0>;
+						compatible = "altr,socfpga-gate-clk";
+						clocks = <&ddr_dqs_clk>;
+						clk-gate = <0xd8 0>;
+					};
+
+					ddr_2x_dqs_clk_gate: ddr_2x_dqs_clk_gate {
+						#clock-cells = <0>;
+						compatible = "altr,socfpga-gate-clk";
+						clocks = <&ddr_2x_dqs_clk>;
+						clk-gate = <0xd8 1>;
+					};
+
+					ddr_dq_clk_gate: ddr_dq_clk_gate {
+						#clock-cells = <0>;
+						compatible = "altr,socfpga-gate-clk";
+						clocks = <&ddr_dq_clk>;
+						clk-gate = <0xd8 2>;
+					};
+
+					h2f_user2_clk: h2f_user2_clk {
+						#clock-cells = <0>;
+						compatible = "altr,socfpga-gate-clk";
+						clocks = <&h2f_usr2_clk>;
+						clk-gate = <0xd8 3>;
+					};
+
 				};
-			};
+		};
 
 		gmac0: ethernet@ff700000 {
 			compatible = "altr,socfpga-stmmac", "snps,dwmac-3.70a", "snps,dwmac";
@@ -565,7 +594,7 @@
 			#size-cells = <0>;
 			compatible = "snps,dw-apb-gpio";
 			reg = <0xff708000 0x1000>;
-			clocks = <&per_base_clk>;
+			clocks = <&l4_mp_clk>;
 			status = "disabled";
 
 			porta: gpio-controller@0 {
@@ -585,7 +614,7 @@
 			#size-cells = <0>;
 			compatible = "snps,dw-apb-gpio";
 			reg = <0xff709000 0x1000>;
-			clocks = <&per_base_clk>;
+			clocks = <&l4_mp_clk>;
 			status = "disabled";
 
 			portb: gpio-controller@0 {
@@ -605,7 +634,7 @@
 			#size-cells = <0>;
 			compatible = "snps,dw-apb-gpio";
 			reg = <0xff70a000 0x1000>;
-			clocks = <&per_base_clk>;
+			clocks = <&l4_mp_clk>;
 			status = "disabled";
 
 			portc: gpio-controller@0 {
@@ -639,6 +668,8 @@
 			cache-level = <2>;
 			arm,tag-latency = <1 1 1>;
 			arm,data-latency = <2 1 1>;
+			prefetch-data = <1>;
+			prefetch-instr = <1>;
 		};
 
 		mmc: dwmmc0@ff704000 {
@@ -752,6 +783,7 @@
 			#reset-cells = <1>;
 			compatible = "altr,rst-mgr";
 			reg = <0xffd05000 0x1000>;
+			altr,modrst-offset = <0x10>;
 		};
 
 		usbphy0: usbphy@0 {
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 4779b07310df..2340fcb2b535 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -16,11 +16,17 @@
 
 #include "skeleton.dtsi"
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/reset/altr,rst-mgr-a10.h>
 
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -409,6 +415,8 @@
 			rx-fifo-depth = <16384>;
 			clocks = <&l4_mp_clk>;
 			clock-names = "stmmaceth";
+			resets = <&rst EMAC0_RESET>;
+			reset-names = "stmmaceth";
 			status = "disabled";
 		};
 
@@ -426,6 +434,8 @@
 			rx-fifo-depth = <16384>;
 			clocks = <&l4_mp_clk>;
 			clock-names = "stmmaceth";
+			resets = <&rst EMAC1_RESET>;
+			reset-names = "stmmaceth";
 			status = "disabled";
 		};
 
@@ -588,6 +598,7 @@
 			#reset-cells = <1>;
 			compatible = "altr,rst-mgr";
 			reg = <0xffd05000 0x100>;
+			altr,modrst-offset = <0x20>;
 		};
 
 		scu: snoop-control-unit@ffffc000 {
diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi b/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
index 94a0709b2fe6..99aa9a1c8af0 100644
--- a/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
@@ -21,7 +21,8 @@
 	compatible = "altr,socfpga-arria10", "altr,socfpga";
 
 	chosen {
-		bootargs = "console=ttyS0,115200 rootwait";
+		bootargs = "earlyprintk";
+		stdout-path = "serial1:115200n8";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/socfpga_arria5_socdk.dts b/arch/arm/boot/dts/socfpga_arria5_socdk.dts
index ccaf41742fc3..a75a666032b2 100644
--- a/arch/arm/boot/dts/socfpga_arria5_socdk.dts
+++ b/arch/arm/boot/dts/socfpga_arria5_socdk.dts
@@ -22,7 +22,8 @@
 	compatible = "altr,socfpga-arria5", "altr,socfpga";
 
 	chosen {
-		bootargs = "console=ttyS0,115200";
+		bootargs = "earlyprintk";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts
new file mode 100644
index 000000000000..555e9caf21e1
--- /dev/null
+++ b/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts
@@ -0,0 +1,111 @@
+/*
+ * Copyright Altera Corporation (C) 2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "socfpga_cyclone5.dtsi"
+
+/ {
+	model = "Terasic DE-0(Atlas)";
+	compatible = "altr,socfpga-cyclone5", "altr,socfpga";
+
+	chosen {
+		bootargs = "earlyprintk";
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		name = "memory";
+		device_type = "memory";
+		reg = <0x0 0x40000000>; /* 1GB */
+	};
+
+	aliases {
+		ethernet0 = &gmac1;
+	};
+
+	regulator_3_3v: 3-3-v-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		hps0 {
+			label = "hps_led0";
+			gpios = <&portb 24 0>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+};
+
+&gmac1 {
+	status = "okay";
+	phy-mode = "rgmii";
+
+	txd0-skew-ps = <0>; /* -420ps */
+	txd1-skew-ps = <0>; /* -420ps */
+	txd2-skew-ps = <0>; /* -420ps */
+	txd3-skew-ps = <0>; /* -420ps */
+	rxd0-skew-ps = <420>; /* 0ps */
+	rxd1-skew-ps = <420>; /* 0ps */
+	rxd2-skew-ps = <420>; /* 0ps */
+	rxd3-skew-ps = <420>; /* 0ps */
+	txen-skew-ps = <0>; /* -420ps */
+	txc-skew-ps = <1860>; /* 960ps */
+	rxdv-skew-ps = <420>; /* 0ps */
+	rxc-skew-ps = <1680>; /* 780ps */
+
+	max-frame-size = <3800>;
+};
+
+&gpio0 {
+	status = "okay";
+};
+
+&gpio1 {
+	status = "okay";
+};
+
+&gpio2 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+	speed-mode = <0>;
+
+	adxl345: adxl345@0 {
+		compatible = "adi,adxl345";
+		reg = <0x53>;
+
+		interrupt-parent = <&portc>;
+		interrupts = <3 2>;
+	};
+};
+
+&mmc0 {
+	vmmc-supply = <&regulator_3_3v>;
+	vqmmc-supply = <&regulator_3_3v>;
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&usb1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts
index 258865da8f6a..d4d0a28fb331 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts
@@ -22,7 +22,8 @@
 	compatible = "altr,socfpga-cyclone5", "altr,socfpga";
 
 	chosen {
-		bootargs = "console=ttyS0,115200";
+		bootargs = "earlyprintk";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
index 71468a7eb28f..48bf651bd762 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
@@ -22,7 +22,8 @@
 	compatible = "altr,socfpga-cyclone5", "altr,socfpga";
 
 	chosen {
-		bootargs = "console=ttyS0,115200";
+		bootargs = "earlyprintk";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory {
@@ -60,27 +61,27 @@
 	rxc-skew-ps = <2000>;
 };
 
-&mmc0 {
-	vmmc-supply = <&regulator_3_3v>;
-	vqmmc-supply = <&regulator_3_3v>;
-};
-
-&usb1 {
-	status = "okay";
-};
-
 &gpio2 {
 	status = "okay";
 };
 
-&i2c1{
+&i2c1 {
 	status = "okay";
 
-	accel1: accel1@53{
-		compatible = "adxl34x";
+	accel1: accelerometer@53 {
+		compatible = "adi,adxl345";
 		reg = <0x53>;
 
-		interrupt-parent = < &portc >;
+		interrupt-parent = <&portc>;
 		interrupts = <3 2>;
 	};
 };
+
+&mmc0 {
+	vmmc-supply = <&regulator_3_3v>;
+	vqmmc-supply = <&regulator_3_3v>;
+};
+
+&usb1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts
index d42c84b1df8d..e48857249ce7 100644
--- a/arch/arm/boot/dts/spear1310-evb.dts
+++ b/arch/arm/boot/dts/spear1310-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr1310 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi
index 9d342920695a..54bc6d3cf290 100644
--- a/arch/arm/boot/dts/spear1310.dtsi
+++ b/arch/arm/boot/dts/spear1310.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr1310 SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts
index b23e05ed1d60..c611f5606dfe 100644
--- a/arch/arm/boot/dts/spear1340-evb.dts
+++ b/arch/arm/boot/dts/spear1340-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr1340 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index 13e1aa33daa2..df2232d767ed 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr1340 SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index 40accc87e3a2..14594ce8c18a 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr13xx SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear300-evb.dts b/arch/arm/boot/dts/spear300-evb.dts
index 5de1431653e4..e859e8288bcd 100644
--- a/arch/arm/boot/dts/spear300-evb.dts
+++ b/arch/arm/boot/dts/spear300-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr300 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear300.dtsi b/arch/arm/boot/dts/spear300.dtsi
index f79b3dfaabe6..f4e92e599729 100644
--- a/arch/arm/boot/dts/spear300.dtsi
+++ b/arch/arm/boot/dts/spear300.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr300 SoC
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear310-evb.dts b/arch/arm/boot/dts/spear310-evb.dts
index b09632963d15..070f2c1b7851 100644
--- a/arch/arm/boot/dts/spear310-evb.dts
+++ b/arch/arm/boot/dts/spear310-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr310 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi
index 95372080eea6..da210b454753 100644
--- a/arch/arm/boot/dts/spear310.dtsi
+++ b/arch/arm/boot/dts/spear310.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr310 SoC
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear320-evb.dts b/arch/arm/boot/dts/spear320-evb.dts
index fdedbb514102..1b1034477923 100644
--- a/arch/arm/boot/dts/spear320-evb.dts
+++ b/arch/arm/boot/dts/spear320-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr320 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi
index ffea342aeec9..22be6e5edaac 100644
--- a/arch/arm/boot/dts/spear320.dtsi
+++ b/arch/arm/boot/dts/spear320.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr320 SoC
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear3xx.dtsi b/arch/arm/boot/dts/spear3xx.dtsi
index f0e3fcf8e323..118135d75899 100644
--- a/arch/arm/boot/dts/spear3xx.dtsi
+++ b/arch/arm/boot/dts/spear3xx.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr3xx SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/ste-ccu8540.dts b/arch/arm/boot/dts/ste-ccu8540.dts
index 32dd55e5f4e6..6eaaf638e52e 100644
--- a/arch/arm/boot/dts/ste-ccu8540.dts
+++ b/arch/arm/boot/dts/ste-ccu8540.dts
@@ -17,6 +17,13 @@
 	model = "ST-Ericsson U8540 platform with Device Tree";
 	compatible = "st-ericsson,ccu8540", "st-ericsson,u8540";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	memory@0 {
 		device_type = "memory";
 		reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>;
diff --git a/arch/arm/boot/dts/ste-ccu9540.dts b/arch/arm/boot/dts/ste-ccu9540.dts
index 651c56d400a4..c8b815819cfe 100644
--- a/arch/arm/boot/dts/ste-ccu9540.dts
+++ b/arch/arm/boot/dts/ste-ccu9540.dts
@@ -16,6 +16,13 @@
 	model = "ST-Ericsson CCU9540 platform with Device Tree";
 	compatible = "st-ericsson,ccu9540", "st-ericsson,u9540";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	memory {
 		reg = <0x00000000 0x20000000>;
 	};
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index 853684ad7773..50f5e9d09203 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -15,6 +15,33 @@
 #include "skeleton.dtsi"
 
 / {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		enable-method = "ste,dbx500-smp";
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+			};
+		};
+		CPU0: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0x300>;
+		};
+		CPU1: cpu@301 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0x301>;
+		};
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -22,32 +49,6 @@
 		interrupt-parent = <&intc>;
 		ranges;
 
-		cpus {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			cpu-map {
-				cluster0 {
-					core0 {
-						cpu = <&CPU0>;
-					};
-					core1 {
-						cpu = <&CPU1>;
-					};
-				};
-			};
-			CPU0: cpu@0 {
-				device_type = "cpu";
-				compatible = "arm,cortex-a9";
-				reg = <0>;
-			};
-			CPU1: cpu@1 {
-				device_type = "cpu";
-				compatible = "arm,cortex-a9";
-				reg = <1>;
-			};
-		};
-
 		ptm@801ae000 {
 			compatible = "arm,coresight-etm3x", "arm,primecell";
 			reg = <0x801ae000 0x1000>;
@@ -219,6 +220,13 @@
 
 		clocks {
 			compatible = "stericsson,u8500-clks";
+			/*
+			 * Registers for the CLKRST block on peripheral
+			 * groups 1, 2, 3, 5, 6,
+			 */
+			reg = <0x8012f000 0x1000>, <0x8011f000 0x1000>,
+			    <0x8000f000 0x1000>, <0xa03ff000 0x1000>,
+			    <0xa03cf000 0x1000>;
 
 			prcmu_clk: prcmu-clock {
 				#clock-cells = <1>;
@@ -286,7 +294,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <0>;
-
+			gpio-ranges = <&pinctrl 0 0 32>;
 			clocks = <&prcc_pclk 1 9>;
 		};
 
@@ -301,7 +309,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <1>;
-
+			gpio-ranges = <&pinctrl 0 32 5>;
 			clocks = <&prcc_pclk 1 9>;
 		};
 
@@ -316,7 +324,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <2>;
-
+			gpio-ranges = <&pinctrl 0 64 32>;
 			clocks = <&prcc_pclk 3 8>;
 		};
 
@@ -331,7 +339,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <3>;
-
+			gpio-ranges = <&pinctrl 0 96 2>;
 			clocks = <&prcc_pclk 3 8>;
 		};
 
@@ -346,7 +354,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <4>;
-
+			gpio-ranges = <&pinctrl 0 128 32>;
 			clocks = <&prcc_pclk 3 8>;
 		};
 
@@ -361,7 +369,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <5>;
-
+			gpio-ranges = <&pinctrl 0 160 12>;
 			clocks = <&prcc_pclk 3 8>;
 		};
 
@@ -376,7 +384,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <6>;
-
+			gpio-ranges = <&pinctrl 0 192 32>;
 			clocks = <&prcc_pclk 2 11>;
 		};
 
@@ -391,7 +399,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <7>;
-
+			gpio-ranges = <&pinctrl 0 224 7>;
 			clocks = <&prcc_pclk 2 11>;
 		};
 
@@ -406,12 +414,15 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-bank = <8>;
-
+			gpio-ranges = <&pinctrl 0 256 12>;
 			clocks = <&prcc_pclk 5 1>;
 		};
 
-		pinctrl {
+		pinctrl: pinctrl {
 			compatible = "stericsson,db8500-pinctrl";
+			nomadik-gpio-chips = <&gpio0>, <&gpio1>, <&gpio2>, <&gpio3>,
+						<&gpio4>, <&gpio5>, <&gpio6>, <&gpio7>,
+						<&gpio8>;
 			prcm = <&prcmu>;
 		};
 
@@ -971,7 +982,7 @@
 			power-domains = <&pm_domains DOMAIN_VAPE>;
 		};
 
-		uart@80120000 {
+		ux500_serial0: uart@80120000 {
 			compatible = "arm,pl011", "arm,primecell";
 			reg = <0x80120000 0x1000>;
 			interrupts = <0 11 IRQ_TYPE_LEVEL_HIGH>;
@@ -986,7 +997,7 @@
 			status = "disabled";
 		};
 
-		uart@80121000 {
+		ux500_serial1: uart@80121000 {
 			compatible = "arm,pl011", "arm,primecell";
 			reg = <0x80121000 0x1000>;
 			interrupts = <0 19 IRQ_TYPE_LEVEL_HIGH>;
@@ -1001,7 +1012,7 @@
 			status = "disabled";
 		};
 
-		uart@80007000 {
+		ux500_serial2: uart@80007000 {
 			compatible = "arm,pl011", "arm,primecell";
 			reg = <0x80007000 0x1000>;
 			interrupts = <0 26 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 744c1e3a744d..6d8ce154347e 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -32,11 +32,11 @@
 			status = "okay";
 		};
 
+		/* This UART is unused and thus left disabled */
 		uart@80121000 {
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&uart1_default_mode>;
 			pinctrl-1 = <&uart1_sleep_mode>;
-			status = "okay";
 		};
 
 		uart@80007000 {
diff --git a/arch/arm/boot/dts/ste-hrefprev60-stuib.dts b/arch/arm/boot/dts/ste-hrefprev60-stuib.dts
index 2b1cb5b584b6..18e9795a94f9 100644
--- a/arch/arm/boot/dts/ste-hrefprev60-stuib.dts
+++ b/arch/arm/boot/dts/ste-hrefprev60-stuib.dts
@@ -17,6 +17,13 @@
 	model = "ST-Ericsson HREF (pre-v60) and ST UIB";
 	compatible = "st-ericsson,mop500", "st-ericsson,u8500";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	soc {
 		/* Reset line for the BU21013 touchscreen */
 		i2c@80110000 {
diff --git a/arch/arm/boot/dts/ste-hrefprev60-tvk.dts b/arch/arm/boot/dts/ste-hrefprev60-tvk.dts
index 59523f866812..24739914e689 100644
--- a/arch/arm/boot/dts/ste-hrefprev60-tvk.dts
+++ b/arch/arm/boot/dts/ste-hrefprev60-tvk.dts
@@ -16,4 +16,11 @@
 / {
 	model = "ST-Ericsson HREF (pre-v60) and TVK1281618 UIB";
 	compatible = "st-ericsson,mop500", "st-ericsson,u8500";
+
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
 };
diff --git a/arch/arm/boot/dts/ste-hrefprev60.dtsi b/arch/arm/boot/dts/ste-hrefprev60.dtsi
index 7f3975b58d16..b0278f4c486c 100644
--- a/arch/arm/boot/dts/ste-hrefprev60.dtsi
+++ b/arch/arm/boot/dts/ste-hrefprev60.dtsi
@@ -23,6 +23,11 @@
 	};
 
 	soc {
+		/* Enable UART1 on this board */
+		uart@80121000 {
+			status = "okay";
+		};
+
 		i2c@80004000 {
 			tps61052@33 {
 				compatible = "tps61052";
diff --git a/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts b/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts
index 8c6a2de56cf1..c2e1ba019a2f 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts
+++ b/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts
@@ -19,6 +19,13 @@
 	model = "ST-Ericsson HREF (v60+) and ST UIB";
 	compatible = "st-ericsson,hrefv60+", "st-ericsson,u8500";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	soc {
 		/* Reset line for the BU21013 touchscreen */
 		i2c@80110000 {
diff --git a/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts b/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts
index d53cccdce776..ebd8547e98f1 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts
+++ b/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts
@@ -18,4 +18,11 @@
 / {
 	model = "ST-Ericsson HREF (v60+) and TVK1281618 UIB";
 	compatible = "st-ericsson,hrefv60+", "st-ericsson,u8500";
+
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
 };
diff --git a/arch/arm/boot/dts/ste-hrefv60plus.dtsi b/arch/arm/boot/dts/ste-hrefv60plus.dtsi
index a4bc9e77d640..810cda743b6d 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus.dtsi
+++ b/arch/arm/boot/dts/ste-hrefv60plus.dtsi
@@ -43,15 +43,26 @@
 				  <&vaudio_hf_hrefv60_mode>,
 				  <&gbf_hrefv60_mode>,
 				  <&hdtv_hrefv60_mode>,
-				  <&touch_hrefv60_mode>;
+				  <&touch_hrefv60_mode>,
+				  <&gpios_hrefv60_mode>;
 
 			sdi0 {
-				/* SD card detect GPIO pin, extend default state */
 				sdi0_default_mode: sdi0_default {
+					/* SD card detect GPIO pin, extend default state */
 					default_hrefv60_cfg1 {
 						pins = "GPIO95_E8";
 						ste,config = <&gpio_in_pu>;
 					};
+					/* VMMCI level-shifter enable */
+					default_hrefv60_cfg2 {
+						pins = "GPIO169_D22";
+						ste,config = <&gpio_out_lo>;
+					};
+					/* VMMCI level-shifter voltage select */
+					default_hrefv60_cfg3 {
+						pins = "GPIO5_AG6";
+						ste,config = <&gpio_out_hi>;
+					};
 				};
 			};
 			ipgpio {
@@ -213,6 +224,16 @@
 					};
 				};
 			};
+			gpios {
+				/* Dangling GPIO pins */
+				gpios_hrefv60_mode: gpios_hrefv60 {
+					default_cfg1 {
+						/* Normally UART1 RXD, now dangling */
+						pins = "GPIO4_AH6";
+						ste,config = <&in_pu>;
+					};
+				};
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/ste-nomadik-nhk15.dts b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
index 3d0b8755caee..4a21c6492dbb 100644
--- a/arch/arm/boot/dts/ste-nomadik-nhk15.dts
+++ b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
@@ -17,11 +17,22 @@
 	};
 
 	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
 		stmpe-i2c0 = &stmpe0;
 		stmpe-i2c1 = &stmpe1;
 	};
 
 	pinctrl {
+		uart0 {
+			uart0_nhk_mode: uart0_mux {
+				u0_default_mux {
+					function = "u0";
+					groups = "u0txrx_a_1", "u0ctsrts_a_1";
+				};
+			};
+		};
+
 		stmpe2401_1 {
 			stmpe2401_1_nhk_mode: stmpe2401_1_nhk {
 				nhk_cfg1 {
@@ -72,6 +83,11 @@
 	};
 
 	i2c0 {
+		lis3lv02dl@1d {
+			/* Accelerometer */
+			compatible = "st,lis3lv02dl-accel";
+			reg = <0x1d>;
+		};
 		stmpe0: stmpe2401@43 {
 			compatible = "st,stmpe2401";
 			reg = <0x43>;
@@ -130,22 +146,30 @@
 				#gpio-cells = <2>;
 				interrupt-controller;
 				#interrupt-cells = <2>;
+				/*
+				 * This will turn off SATA so that MMC/SD
+				 * can thrive
+				 */
+				mmcsd-gpio {
+					gpio-hog;
+					gpios = <2 0x0>;
+					output-low;
+					line-name = "SATA EN";
+				};
 			};
 		};
 	};
 
 	amba {
+		/* Activate RX/TX and CTS/RTS on UART 0 */
+		uart0: uart@101fd000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_nhk_mode>;
+			status = "okay";
+		};
 		mmcsd: sdi@101f6000 {
 			cd-gpios = <&stmpe_gpio44 7 GPIO_ACTIVE_LOW>;
 			wp-gpios = <&stmpe_gpio44 18 GPIO_ACTIVE_HIGH>;
 		};
 	};
-
-	/* Custom board node with GPIO pins to active etc */
-	usb-s8815 {
-		/* This will turn off SATA so that MMC/SD can thrive */
-		mmcsd-gpio {
-			gpios = <&stmpe_gpio44 2 0x1>;
-		};
-	};
 };
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index 85d3b95dfdba..35282c0105c6 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -15,6 +15,21 @@
 		bootargs = "root=/dev/ram0 console=ttyAMA1,115200n8 earlyprintk";
 	};
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
+	gpio3: gpio@101e7000 {
+		/* This hog will bias the MMC/SD card detect line */
+		mmcsd-gpio {
+			gpio-hog;
+			gpios = <16 0x0>;
+			output-low;
+			line-name = "card detect bias";
+		};
+	};
+
 	src@101e0000 {
 		/* These chrystal drivers are not used on this board */
 		disable-sxtalo;
@@ -26,6 +41,15 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&cd_default_mode>;
 
+		uart0 {
+			/* Only use RX/TX pins */
+			uart0_s8815_mode: uart0_mux {
+				u0_default_mux {
+					function = "u0";
+					groups = "u0txrx_a_1";
+				};
+			};
+		};
 		mmcsd-cd {
 			cd_default_mode: cd_default {
 				cd_default_cfg1 {
@@ -81,6 +105,14 @@
 		};
 	};
 
+	i2c1 {
+		lis3lv02dl@1d {
+			/* Accelerometer */
+			compatible = "st,lis3lv02dl-accel";
+			reg = <0x1d>;
+		};
+	};
+
 	/* GPIO I2C connected to the USB portions of the STw4811 only */
 	gpio-i2c {
 		compatible = "i2c-gpio";
@@ -98,21 +130,19 @@
 	};
 
 
-	/* Configure card detect for the uSD slot */
 	amba {
+		/* Activate RXTX on UART 0 */
+		uart0: uart@101fd000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_s8815_mode>;
+			status = "okay";
+		};
+		/* Configure card detect for the uSD slot */
 		mmcsd: sdi@101f6000 {
 			cd-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>;
 		};
 	};
 
-	/* Custom board node with GPIO pins to active etc */
-	usb-s8815 {
-		/* This will bias the MMC/SD card detect line */
-		mmcsd-gpio {
-			gpios = <&gpio3 16 0x1>;
-		};
-	};
-
 	/* The user LED on the board is set up to be used for heartbeat */
 	leds {
 		compatible = "gpio-leds";
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index 9a5f2ba139b7..314f59c12162 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -21,6 +21,13 @@
 		interrupts = <30>;
 		cache-unified;
 		cache-level = <2>;
+		cache-size = <131072>;
+		cache-sets = <512>;
+		cache-line-size = <32>;
+		/* At full speed latency must be >=2 */
+		arm,tag-latency = <2>;
+		arm,data-latency = <2 2>;
+		arm,dirty-latency = <2>;
 	};
 
 	mtu0: mtu@101e2000 {
@@ -52,6 +59,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		gpio-bank = <0>;
+		gpio-ranges = <&pinctrl 0 0 32>;
 		clocks = <&pclk>;
 	};
 
@@ -65,6 +73,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		gpio-bank = <1>;
+		gpio-ranges = <&pinctrl 0 32 32>;
 		clocks = <&pclk>;
 	};
 
@@ -78,12 +87,14 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		gpio-bank = <2>;
+		gpio-ranges = <&pinctrl 0 64 32>;
 		clocks = <&pclk>;
 	};
 
 	gpio3: gpio@101e7000 {
 		compatible = "st,nomadik-gpio";
 		reg =  <0x101e7000 0x80>;
+		ngpio = <28>;
 		interrupt-parent = <&vica>;
 		interrupts = <9>;
 		interrupt-controller;
@@ -91,20 +102,14 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		gpio-bank = <3>;
+		gpio-ranges = <&pinctrl 0 96 28>;
 		clocks = <&pclk>;
 	};
 
-	pinctrl {
+	pinctrl: pinctrl {
 		compatible = "stericsson,stn8815-pinctrl";
+		nomadik-gpio-chips = <&gpio0>, <&gpio1>, <&gpio2>, <&gpio3>;
 		/* Pin configurations */
-		uart0 {
-			uart0_default_mux: uart0_mux {
-				u0_default_mux {
-					function = "u0";
-					groups = "u0_a_1";
-				};
-			};
-		};
 		uart1 {
 			uart1_default_mux: uart1_mux {
 				u1_default_mux {
@@ -721,11 +726,6 @@
 			   compatible = "st,stw5095";
 			   reg = <0x1a>;
 		};
-		lis3lv02dl@1d {
-			/* Accelerometer */
-			compatible = "st,lis3lv02dl-accel";
-			reg = <0x1d>;
-		};
 	};
 
 	amba {
@@ -755,8 +755,7 @@
 			interrupts = <12>;
 			clocks = <&uart0clk>, <&pclkuart0>;
 			clock-names = "uartclk", "apb_pclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&uart0_default_mux>;
+			status = "disabled";
 		};
 
 		uart1: uart@101fb000 {
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 9edadc37719f..32a5ccb14e7e 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -18,6 +18,13 @@
 	model = "Calao Systems Snowball platform with device tree";
 	compatible = "calaosystems,snowball-a9500", "st-ericsson,u9500";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	memory {
 		reg = <0x00000000 0x20000000>;
 	};
@@ -223,11 +230,11 @@
 			status = "okay";
 		};
 
+		/* This UART is unused and thus left disabled */
 		uart@80121000 {
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&uart1_default_mode>;
 			pinctrl-1 = <&uart1_sleep_mode>;
-			status = "okay";
 		};
 
 		uart@80007000 {
@@ -452,7 +459,21 @@
 						pins = "GPIO21_AB3"; /* DAT31DIR */
 						ste,config = <&out_hi>;
 					};
-
+					/* SD card detect GPIO pin, extend default state */
+					snowball_cfg2 {
+						pins = "GPIO218_AH11";
+						ste,config = <&gpio_in_pu>;
+					};
+					/* VMMCI level-shifter enable */
+					snowball_cfg3 {
+						pins = "GPIO217_AH12";
+						ste,config = <&gpio_out_lo>;
+					};
+					/* VMMCI level-shifter voltage select */
+					snowball_cfg4 {
+						pins = "GPIO228_AJ6";
+						ste,config = <&gpio_out_hi>;
+					};
 				};
 			};
 			ssp0 {
diff --git a/arch/arm/boot/dts/stih407-clock.dtsi b/arch/arm/boot/dts/stih407-clock.dtsi
index e65744fc12ab..ad45f5e8fac7 100644
--- a/arch/arm/boot/dts/stih407-clock.dtsi
+++ b/arch/arm/boot/dts/stih407-clock.dtsi
@@ -134,7 +134,7 @@
 
 			clk_s_c0_pll0: clk-s-c0-pll0 {
 				#clock-cells = <1>;
-				compatible = "st,stih407-plls-c32-c0_0", "st,clkgen-plls-c32";
+				compatible = "st,plls-c32-cx_0", "st,clkgen-plls-c32";
 
 				clocks = <&clk_sysin>;
 
@@ -143,7 +143,7 @@
 
 			clk_s_c0_pll1: clk-s-c0-pll1 {
 				#clock-cells = <1>;
-				compatible = "st,stih407-plls-c32-c0_1", "st,clkgen-plls-c32";
+				compatible = "st,plls-c32-cx_1", "st,clkgen-plls-c32";
 
 				clocks = <&clk_sysin>;
 
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index 838b812cbda1..ae0527754000 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -9,7 +9,7 @@
 #include "stih407-pinctrl.dtsi"
 #include <dt-bindings/mfd/st-lpc.h>
 #include <dt-bindings/phy/phy.h>
-#include <dt-bindings/reset-controller/stih407-resets.h>
+#include <dt-bindings/reset/stih407-resets.h>
 #include <dt-bindings/interrupt-controller/irq-st.h>
 / {
 	#address-cells = <1>;
@@ -22,11 +22,15 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0>;
+			/* u-boot puts hpen in SBC dmem at 0xa4 offset */
+			cpu-release-addr = <0x94100A4>;
 		};
 		cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <1>;
+			/* u-boot puts hpen in SBC dmem at 0xa4 offset */
+			cpu-release-addr = <0x94100A4>;
 		};
 	};
 
@@ -65,6 +69,17 @@
 		interrupts = <GIC_PPI 15 IRQ_TYPE_LEVEL_HIGH>;
 	};
 
+	pwm_regulator: pwm-regulator {
+		compatible = "pwm-regulator";
+		pwms = <&pwm1 3 8448>;
+		regulator-name = "CPU_1V0_AVS";
+		regulator-min-microvolt = <784000>;
+		regulator-max-microvolt = <1299000>;
+		regulator-always-on;
+		max-duty-cycle = <255>;
+		status = "okay";
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -539,6 +554,7 @@
 			status = "disabled";
 		};
 
+
 		st_dwc3: dwc3@8f94000 {
 			compatible	= "st,stih407-dwc3";
 			reg		= <0x08f94000 0x1000>, <0x110 0x4>;
@@ -565,5 +581,34 @@
 						  <&phy_port2 PHY_TYPE_USB3>;
 			};
 		};
+
+		/* COMMS PWM Module */
+		pwm0: pwm@9810000 {
+			compatible	= "st,sti-pwm";
+			status		= "okay";
+			#pwm-cells	= <2>;
+			reg		= <0x9810000 0x68>;
+			pinctrl-names	= "default";
+			pinctrl-0	= <&pinctrl_pwm0_chan0_default>;
+			clock-names	= "pwm";
+			clocks		= <&clk_sysin>;
+			st,pwm-num-chan = <1>;
+		};
+
+		/* SBC PWM Module */
+		pwm1: pwm@9510000 {
+			compatible	= "st,sti-pwm";
+			status		= "okay";
+			#pwm-cells	= <2>;
+			reg		= <0x9510000 0x68>;
+			pinctrl-names	= "default";
+			pinctrl-0	= <&pinctrl_pwm1_chan0_default
+					&pinctrl_pwm1_chan1_default
+					&pinctrl_pwm1_chan2_default
+					&pinctrl_pwm1_chan3_default>;
+			clock-names	= "pwm";
+			clocks		= <&clk_sysin>;
+			st,pwm-num-chan = <4>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/stih407-pinctrl.dtsi b/arch/arm/boot/dts/stih407-pinctrl.dtsi
index 0a754f275212..1683debd0854 100644
--- a/arch/arm/boot/dts/stih407-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stih407-pinctrl.dtsi
@@ -439,6 +439,194 @@
 					};
 				};
 			};
+
+			tsin0 {
+				pinctrl_tsin0_parallel: tsin0_parallel {
+					st,pins {
+						DATA7 = <&pio10 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA6 = <&pio10 5 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA5 = <&pio10 6 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA4 = <&pio10 7 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA3 = <&pio11 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA2 = <&pio11 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA1 = <&pio11 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA0 = <&pio11 3 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio10 3 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio10 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio10 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio10 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+				pinctrl_tsin0_serial: tsin0_serial {
+					st,pins {
+						DATA7 = <&pio10 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio10 3 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio10 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio10 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio10 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsin1 {
+				pinctrl_tsin1_parallel: tsin1_parallel {
+					st,pins {
+						DATA7 = <&pio12 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA6 = <&pio12 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA5 = <&pio12 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA4 = <&pio12 3 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA3 = <&pio12 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA2 = <&pio12 5 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA1 = <&pio12 6 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA0 = <&pio12 7 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio11 7 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio11 5 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio11 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio11 6 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+				pinctrl_tsin1_serial: tsin1_serial {
+					st,pins {
+						DATA7 = <&pio12 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio11 7 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio11 5 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio11 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio11 6 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsin2 {
+				pinctrl_tsin2_parallel: tsin2_parallel {
+					st,pins {
+						DATA7 = <&pio13 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						DATA6 = <&pio13 5 ALT2 IN SE_NICLK_IO 0 CLK_B>;
+						DATA5 = <&pio13 6 ALT2 IN SE_NICLK_IO 0 CLK_B>;
+						DATA4 = <&pio13 7 ALT2 IN SE_NICLK_IO 0 CLK_B>;
+						DATA3 = <&pio14 0 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+						DATA2 = <&pio14 1 ALT2 IN SE_NICLK_IO 0 CLK_B>;
+						DATA1 = <&pio14 2 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+						DATA0 = <&pio14 3 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio13 3 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio13 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio13 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio13 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+				pinctrl_tsin2_serial: tsin2_serial {
+					st,pins {
+						DATA7 = <&pio13 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio13 3 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio13 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio13 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio13 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsin3 {
+				pinctrl_tsin3_serial: tsin3_serial {
+					st,pins {
+						DATA7 = <&pio14 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio14 0 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio13 6 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio13 5 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio13 7 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsin4 {
+				pinctrl_tsin4_serial_alt3: tsin4_serial_alt3 {
+					st,pins {
+						DATA7 = <&pio14 6 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio14 5 ALT3 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio14 3 ALT3 IN SE_NICLK_IO 0 CLK_B>;
+						ERROR = <&pio14 2 ALT3 IN SE_NICLK_IO 0 CLK_B>;
+						PKCLK = <&pio14 4 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsin5 {
+				pinctrl_tsin5_serial_alt1: tsin5_serial_alt1 {
+					st,pins {
+						DATA7 = <&pio18 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio18 3 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio18 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio18 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio18 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+				pinctrl_tsin5_serial_alt2: tsin5_serial_alt2 {
+					st,pins {
+						DATA7 = <&pio19 4 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio19 3 ALT2 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio19 1 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio19 0 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio19 2 ALT2 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsout0 {
+				pinctrl_tsout0_parallel: tsout0_parallel {
+					st,pins {
+						DATA7 = <&pio12 0 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA6 = <&pio12 1 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA5 = <&pio12 2 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA4 = <&pio12 3 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA3 = <&pio12 4 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA2 = <&pio12 5 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA1 = <&pio12 6 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						DATA0 = <&pio12 7 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio11 7 ALT3 OUT NICLK 0 CLK_A>;
+						VALID = <&pio11 5 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio11 4 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio11 6 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+				pinctrl_tsout0_serial: tsout0_serial {
+					st,pins {
+						DATA7 = <&pio12 0 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio11 7 ALT3 OUT NICLK 0 CLK_A>;
+						VALID = <&pio11 5 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio11 4 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio11 6 ALT3 OUT SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			tsout1 {
+				pinctrl_tsout1_serial: tsout1_serial {
+					st,pins {
+						DATA7 = <&pio19 4 ALT1 OUT SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio19 3 ALT1 OUT NICLK 0 CLK_A>;
+						VALID = <&pio19 1 ALT1 OUT SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio19 0 ALT1 OUT SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio19 2 ALT1 OUT SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
+			mtsin0 {
+				pinctrl_mtsin0_parallel: mtsin0_parallel {
+					st,pins {
+						DATA7 = <&pio10 4 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA6 = <&pio10 5 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA5 = <&pio10 6 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA4 = <&pio10 7 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA3 = <&pio11 0 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA2 = <&pio11 1 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA1 = <&pio11 2 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						DATA0 = <&pio11 3 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio10 3 ALT3 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio10 1 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio10 0 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio10 2 ALT3 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
 		};
 
 		pin-controller-front1 {
@@ -452,6 +640,18 @@
 			interrupts-names = "irqmux";
 			ranges = <0 0x09210000 0x10000>;
 
+			tsin4 {
+				pinctrl_tsin4_serial_alt1: tsin4_serial_alt1 {
+					st,pins {
+						DATA7 = <&pio20 4 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						CLKIN = <&pio20 3 ALT1 IN CLKNOTDATA 0 CLK_A>;
+						VALID = <&pio20 1 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						ERROR = <&pio20 0 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+						PKCLK = <&pio20 2 ALT1 IN SE_NICLK_IO 0 CLK_A>;
+					};
+				};
+			};
+
 			pio20: pio@09210000 {
 				gpio-controller;
 				#gpio-cells = <1>;
diff --git a/arch/arm/boot/dts/stih407.dtsi b/arch/arm/boot/dts/stih407.dtsi
index 2c560fc30503..3efa3b2ebe90 100644
--- a/arch/arm/boot/dts/stih407.dtsi
+++ b/arch/arm/boot/dts/stih407.dtsi
@@ -147,33 +147,5 @@
 				};
 			};
 		};
-
-		/* COMMS PWM Module */
-		pwm0: pwm@9810000 {
-			compatible	= "st,sti-pwm";
-			status		= "disabled";
-			#pwm-cells	= <2>;
-			reg		= <0x9810000 0x68>;
-			pinctrl-names	= "default";
-			pinctrl-0	= <&pinctrl_pwm0_chan0_default>;
-			clock-names	= "pwm";
-			clocks		= <&clk_sysin>;
-		};
-
-		/* SBC PWM Module */
-		pwm1: pwm@9510000 {
-			compatible	= "st,sti-pwm";
-			status		= "disabled";
-			#pwm-cells	= <2>;
-			reg		= <0x9510000 0x68>;
-			pinctrl-names	= "default";
-			pinctrl-0	= <&pinctrl_pwm1_chan0_default
-					&pinctrl_pwm1_chan1_default
-					&pinctrl_pwm1_chan2_default
-					&pinctrl_pwm1_chan3_default>;
-			clock-names	= "pwm";
-			clocks		= <&clk_sysin>;
-			st,pwm-num-chan = <4>;
-		};
 	};
 };
diff --git a/arch/arm/boot/dts/stih410-clock.dtsi b/arch/arm/boot/dts/stih410-clock.dtsi
index 6b5803a30096..d1f2acafc9b6 100644
--- a/arch/arm/boot/dts/stih410-clock.dtsi
+++ b/arch/arm/boot/dts/stih410-clock.dtsi
@@ -137,7 +137,7 @@
 
 			clk_s_c0_pll0: clk-s-c0-pll0 {
 				#clock-cells = <1>;
-				compatible = "st,stih407-plls-c32-c0_0", "st,clkgen-plls-c32";
+				compatible = "st,plls-c32-cx_0", "st,clkgen-plls-c32";
 
 				clocks = <&clk_sysin>;
 
@@ -146,7 +146,7 @@
 
 			clk_s_c0_pll1: clk-s-c0-pll1 {
 				#clock-cells = <1>;
-				compatible = "st,stih407-plls-c32-c0_1", "st,clkgen-plls-c32";
+				compatible = "st,plls-c32-cx_1", "st,clkgen-plls-c32";
 
 				clocks = <&clk_sysin>;
 
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index 208b5e89036a..6f40bc99c22f 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -10,6 +10,10 @@
 #include "stih407-family.dtsi"
 #include "stih410-pinctrl.dtsi"
 / {
+	aliases {
+		bdisp0 = &bdisp0;
+	};
+
 	soc {
 		usb2_picophy1: phy2 {
 			compatible = "st,stih407-usb2-phy";
@@ -218,5 +222,13 @@
 				};
 			};
 		};
+
+		bdisp0:bdisp@9f10000 {
+			compatible = "st,stih407-bdisp";
+			reg = <0x9f10000 0x1000>;
+			interrupts = <GIC_SPI 38 IRQ_TYPE_NONE>;
+			clock-names = "bdisp";
+			clocks = <&clk_s_c0_flexgen CLK_IC_BDISP_0>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/stih415.dtsi b/arch/arm/boot/dts/stih415.dtsi
index 19b019b5f30e..12427e651e5e 100644
--- a/arch/arm/boot/dts/stih415.dtsi
+++ b/arch/arm/boot/dts/stih415.dtsi
@@ -10,7 +10,7 @@
 #include "stih415-clock.dtsi"
 #include "stih415-pinctrl.dtsi"
 #include <dt-bindings/interrupt-controller/arm-gic.h>
-#include <dt-bindings/reset-controller/stih415-resets.h>
+#include <dt-bindings/reset/stih415-resets.h>
 / {
 
 	L2: cache-controller {
diff --git a/arch/arm/boot/dts/stih416.dtsi b/arch/arm/boot/dts/stih416.dtsi
index 9dca173e694a..9e3170ccd18c 100644
--- a/arch/arm/boot/dts/stih416.dtsi
+++ b/arch/arm/boot/dts/stih416.dtsi
@@ -12,7 +12,7 @@
 
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
-#include <dt-bindings/reset-controller/stih416-resets.h>
+#include <dt-bindings/reset/stih416-resets.h>
 #include <dt-bindings/interrupt-controller/irq-st.h>
 / {
 	L2: cache-controller {
diff --git a/arch/arm/boot/dts/stih418-clock.dtsi b/arch/arm/boot/dts/stih418-clock.dtsi
index 0ab23daa2829..148e1772465f 100644
--- a/arch/arm/boot/dts/stih418-clock.dtsi
+++ b/arch/arm/boot/dts/stih418-clock.dtsi
@@ -137,7 +137,7 @@
 
 			clk_s_c0_pll0: clk-s-c0-pll0 {
 				#clock-cells = <1>;
-				compatible = "st,stih407-plls-c32-c0_0", "st,clkgen-plls-c32";
+				compatible = "st,plls-c32-cx_0", "st,clkgen-plls-c32";
 
 				clocks = <&clk_sysin>;
 
@@ -146,7 +146,7 @@
 
 			clk_s_c0_pll1: clk-s-c0-pll1 {
 				#clock-cells = <1>;
-				compatible = "st,stih407-plls-c32-c0_1", "st,clkgen-plls-c32";
+				compatible = "st,plls-c32-cx_1", "st,clkgen-plls-c32";
 
 				clocks = <&clk_sysin>;
 
diff --git a/arch/arm/boot/dts/stih418.dtsi b/arch/arm/boot/dts/stih418.dtsi
index 354d90f521b6..8160a75539a4 100644
--- a/arch/arm/boot/dts/stih418.dtsi
+++ b/arch/arm/boot/dts/stih418.dtsi
@@ -17,11 +17,15 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <2>;
+			/* u-boot puts hpen in SBC dmem at 0xa4 offset */
+			cpu-release-addr = <0x94100A4>;
 		};
 		cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <3>;
+			/* u-boot puts hpen in SBC dmem at 0xa4 offset */
+			cpu-release-addr = <0x94100A4>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/stm32429i-eval.dts b/arch/arm/boot/dts/stm32429i-eval.dts
new file mode 100644
index 000000000000..6964fc9e97cf
--- /dev/null
+++ b/arch/arm/boot/dts/stm32429i-eval.dts
@@ -0,0 +1,75 @@
+/*
+ * Copyright 2015 - Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this file; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "stm32f429.dtsi"
+
+/ {
+	model = "STMicroelectronics STM32429i-EVAL board";
+	compatible = "st,stm32429i-eval", "st,stm32f429";
+
+	chosen {
+		bootargs = "root=/dev/ram rdinit=/linuxrc";
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		reg = <0xc0000000 0x2000000>;
+	};
+
+	aliases {
+		serial0 = &usart1;
+	};
+};
+
+&clk_hse {
+	clock-frequency = <25000000>;
+};
+
+&usart1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/stm32f429-disco.dts b/arch/arm/boot/dts/stm32f429-disco.dts
index 6b9aa59d978a..f0b731db6f53 100644
--- a/arch/arm/boot/dts/stm32f429-disco.dts
+++ b/arch/arm/boot/dts/stm32f429-disco.dts
@@ -53,8 +53,8 @@
 	compatible = "st,stm32f429i-disco", "st,stm32f429";
 
 	chosen {
-		bootargs = "console=ttyS0,115200 root=/dev/ram rdinit=/linuxrc";
-		linux,stdout-path = &usart1;
+		bootargs = "root=/dev/ram rdinit=/linuxrc";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory {
@@ -66,6 +66,10 @@
 	};
 };
 
+&clk_hse {
+	clock-frequency = <8000000>;
+};
+
 &usart1 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi
index aa73b4f4172c..d78a4815da8f 100644
--- a/arch/arm/boot/dts/stm32f429.dtsi
+++ b/arch/arm/boot/dts/stm32f429.dtsi
@@ -49,48 +49,10 @@
 
 / {
 	clocks {
-		clk_sysclk: clk-sysclk {
+		clk_hse: clk-hse {
 			#clock-cells = <0>;
 			compatible = "fixed-clock";
-			clock-frequency = <180000000>;
-		};
-
-		clk_hclk: clk-hclk {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <180000000>;
-		};
-
-		clk_pclk1: clk-pclk1 {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <45000000>;
-		};
-
-		clk_pclk2: clk-pclk2 {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <90000000>;
-		};
-
-		clk_pmtr1: clk-pmtr1 {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <90000000>;
-		};
-
-		clk_pmtr2: clk-pmtr2 {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <180000000>;
-		};
-
-		clk_systick: clk-systick {
-			compatible = "fixed-factor-clock";
-			clocks = <&clk_hclk>;
-			#clock-cells = <0>;
-			clock-div = <8>;
-			clock-mult = <1>;
+			clock-frequency = <0>;
 		};
 	};
 
@@ -99,7 +61,7 @@
 			compatible = "st,stm32-timer";
 			reg = <0x40000000 0x400>;
 			interrupts = <28>;
-			clocks = <&clk_pmtr1>;
+			clocks = <&rcc 0 128>;
 			status = "disabled";
 		};
 
@@ -107,7 +69,7 @@
 			compatible = "st,stm32-timer";
 			reg = <0x40000400 0x400>;
 			interrupts = <29>;
-			clocks = <&clk_pmtr1>;
+			clocks = <&rcc 0 129>;
 			status = "disabled";
 		};
 
@@ -115,7 +77,7 @@
 			compatible = "st,stm32-timer";
 			reg = <0x40000800 0x400>;
 			interrupts = <30>;
-			clocks = <&clk_pmtr1>;
+			clocks = <&rcc 0 130>;
 			status = "disabled";
 		};
 
@@ -123,14 +85,14 @@
 			compatible = "st,stm32-timer";
 			reg = <0x40000c00 0x400>;
 			interrupts = <50>;
-			clocks = <&clk_pmtr1>;
+			clocks = <&rcc 0 131>;
 		};
 
 		timer6: timer@40001000 {
 			compatible = "st,stm32-timer";
 			reg = <0x40001000 0x400>;
 			interrupts = <54>;
-			clocks = <&clk_pmtr1>;
+			clocks = <&rcc 0 132>;
 			status = "disabled";
 		};
 
@@ -138,7 +100,7 @@
 			compatible = "st,stm32-timer";
 			reg = <0x40001400 0x400>;
 			interrupts = <55>;
-			clocks = <&clk_pmtr1>;
+			clocks = <&rcc 0 133>;
 			status = "disabled";
 		};
 
@@ -146,7 +108,7 @@
 			compatible = "st,stm32-usart", "st,stm32-uart";
 			reg = <0x40004400 0x400>;
 			interrupts = <38>;
-			clocks = <&clk_pclk1>;
+			clocks =  <&rcc 0 145>;
 			status = "disabled";
 		};
 
@@ -154,7 +116,7 @@
 			compatible = "st,stm32-usart", "st,stm32-uart";
 			reg = <0x40004800 0x400>;
 			interrupts = <39>;
-			clocks = <&clk_pclk1>;
+			clocks = <&rcc 0 146>;
 			status = "disabled";
 		};
 
@@ -162,7 +124,7 @@
 			compatible = "st,stm32-uart";
 			reg = <0x40004c00 0x400>;
 			interrupts = <52>;
-			clocks = <&clk_pclk1>;
+			clocks = <&rcc 0 147>;
 			status = "disabled";
 		};
 
@@ -170,7 +132,7 @@
 			compatible = "st,stm32-uart";
 			reg = <0x40005000 0x400>;
 			interrupts = <53>;
-			clocks = <&clk_pclk1>;
+			clocks = <&rcc 0 148>;
 			status = "disabled";
 		};
 
@@ -178,7 +140,7 @@
 			compatible = "st,stm32-usart", "st,stm32-uart";
 			reg = <0x40007800 0x400>;
 			interrupts = <82>;
-			clocks = <&clk_pclk1>;
+			clocks = <&rcc 0 158>;
 			status = "disabled";
 		};
 
@@ -186,7 +148,7 @@
 			compatible = "st,stm32-usart", "st,stm32-uart";
 			reg = <0x40007c00 0x400>;
 			interrupts = <83>;
-			clocks = <&clk_pclk1>;
+			clocks = <&rcc 0 159>;
 			status = "disabled";
 		};
 
@@ -194,7 +156,7 @@
 			compatible = "st,stm32-usart", "st,stm32-uart";
 			reg = <0x40011000 0x400>;
 			interrupts = <37>;
-			clocks = <&clk_pclk2>;
+			clocks = <&rcc 0 164>;
 			status = "disabled";
 		};
 
@@ -202,13 +164,20 @@
 			compatible = "st,stm32-usart", "st,stm32-uart";
 			reg = <0x40011400 0x400>;
 			interrupts = <71>;
-			clocks = <&clk_pclk2>;
+			clocks = <&rcc 0 165>;
 			status = "disabled";
 		};
+
+		rcc: rcc@40023810 {
+			#clock-cells = <2>;
+			compatible = "st,stm32f42xx-rcc", "st,stm32-rcc";
+			reg = <0x40023800 0x400>;
+			clocks = <&clk_hse>;
+		};
 	};
 };
 
 &systick {
-	clocks = <&clk_systick>;
+	clocks = <&rcc 1 0>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts b/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts
index 93d435670ef1..f3cb297fd1db 100644
--- a/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts
+++ b/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts
@@ -125,12 +125,21 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	usb2_vbus_pin_a: usb2_vbus_pin@0 {
 		allwinner,pins = "PH12";
 	};
 };
 
+&reg_usb0_vbus {
+	regulator-boot-on;
+	status = "okay";
+};
+
 &reg_usb1_vbus {
 	status = "okay";
 };
@@ -146,7 +155,13 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
 &usbphy {
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts b/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts
index 5878a0b11f7b..143056872650 100644
--- a/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts
+++ b/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts
@@ -114,6 +114,30 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
+&pio {
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PH5";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
+	};
+};
+
+&reg_usb0_vbus {
+	status = "okay";
+};
+
 &reg_usb2_vbus {
 	status = "okay";
 };
@@ -124,7 +148,17 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
+	usb0_vbus_det-gpio = <&pio 7 5 GPIO_ACTIVE_HIGH>; /* PH5 */
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun4i-a10-cubieboard.dts b/arch/arm/boot/dts/sun4i-a10-cubieboard.dts
index 9afb4e018593..046a84d9719d 100644
--- a/arch/arm/boot/dts/sun4i-a10-cubieboard.dts
+++ b/arch/arm/boot/dts/sun4i-a10-cubieboard.dts
@@ -155,6 +155,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	led_pins_cubieboard: led_pins@0 {
 		allwinner,pins = "PH20", "PH21";
@@ -162,6 +166,13 @@
 		allwinner,drive = <SUN4I_PINCTRL_20_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
 };
 
 &reg_ahci_5v {
@@ -216,7 +227,15 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>;
+	usb0_id_det-gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts b/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts
new file mode 100644
index 000000000000..985e15503378
--- /dev/null
+++ b/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts
@@ -0,0 +1,202 @@
+/*
+ * Copyright 2015 Josef Gajdusek <atx@atx.name>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun4i-a10.dtsi"
+#include "sunxi-common-regulators.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/sun4i-a10.h>
+
+/ {
+	model = "Iteaduino Plus A10";
+	compatible = "itead,iteaduino-plus-a10", "allwinner,sun4i-a10";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&ahci {
+	target-supply = <&reg_ahci_5v>;
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&reg_dcdc2>;
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&emac {
+	pinctrl-names = "default";
+	pinctrl-0 = <&emac_pins_a>;
+	phy = <&phy1>;
+	status = "okay";
+};
+
+&emac_sram {
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins_a>;
+	status = "okay";
+
+	axp209: pmic@34 {
+		reg = <0x34>;
+		interrupts = <0>;
+	};
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins_a>;
+	status = "okay";
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_pins_a>;
+	status = "okay";
+};
+
+&ir0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ir0_rx_pins_a>;
+	status = "okay";
+};
+
+&mdio {
+	status = "okay";
+
+	phy1: ethernet-phy@1 {
+		reg = <1>;
+	};
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>;
+	vmmc-supply = <&reg_vcc3v3>;
+	bus-width = <4>;
+	cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */
+	cd-inverted;
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&reg_ahci_5v {
+	status = "okay";
+};
+
+#include "axp209.dtsi"
+
+&reg_dcdc2 {
+	regulator-always-on;
+	regulator-min-microvolt = <1000000>;
+	regulator-max-microvolt = <1450000>;
+	regulator-name = "vdd-cpu";
+};
+
+&reg_dcdc3 {
+	regulator-always-on;
+	regulator-min-microvolt = <1000000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-int-dll";
+};
+
+&reg_ldo1 {
+	regulator-name = "vdd-rtc";
+};
+
+&reg_ldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "avcc";
+};
+
+&reg_usb1_vbus {
+	status = "okay";
+};
+
+&reg_usb2_vbus {
+	status = "okay";
+};
+
+&spi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi0_pins_a>,
+		    <&spi0_cs0_pins_a>;
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins_a>;
+	status = "okay";
+};
+
+&usbphy {
+	usb1_vbus-supply = <&reg_usb1_vbus>;
+	usb2_vbus-supply = <&reg_usb2_vbus>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
index ebe2a04ef649..a7dd86d30fa2 100644
--- a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
+++ b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
@@ -114,6 +114,15 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
+&reg_usb0_vbus {
+	regulator-boot-on;
+	status = "okay";
+};
+
 &reg_usb1_vbus {
 	status = "okay";
 };
@@ -128,7 +137,13 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
 &usbphy {
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
index b64aa4eb071e..28e32ad705cd 100644
--- a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
+++ b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
@@ -150,6 +150,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	ahci_pwr_pin_olinuxinolime: ahci_pwr_pin@1 {
 		allwinner,pins = "PC3";
@@ -164,6 +168,20 @@
 		allwinner,drive = <SUN4I_PINCTRL_20_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PH5";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
+	};
 };
 
 &reg_ahci_5v {
@@ -172,6 +190,10 @@
 	status = "okay";
 };
 
+&reg_usb0_vbus {
+	status = "okay";
+};
+
 &reg_usb1_vbus {
 	status = "okay";
 };
@@ -186,7 +208,17 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpio   = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
+	usb0_vbus_det-gpio = <&pio 7 5 GPIO_ACTIVE_HIGH>; /* PH5 */
+	usb0_vbus-supply   = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 61c03d1fe530..1f3c51a08113 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -241,6 +241,7 @@
 			compatible = "allwinner,sun4i-a10-axi-gates-clk";
 			reg = <0x01c2005c 0x4>;
 			clocks = <&axi>;
+			clock-indices = <0>;
 			clock-output-names = "axi_dram";
 		};
 
@@ -257,17 +258,36 @@
 			compatible = "allwinner,sun4i-a10-ahb-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb>;
+			clock-indices = <0>, <1>,
+					<2>, <3>,
+					<4>, <5>, <6>,
+					<7>, <8>, <9>,
+					<10>, <11>, <12>,
+					<13>, <14>, <16>,
+					<17>, <18>, <20>,
+					<21>, <22>, <23>,
+					<24>, <25>, <26>,
+					<32>, <33>, <34>,
+					<35>, <36>, <37>,
+					<40>, <41>, <43>,
+					<44>, <45>,
+					<46>, <47>,
+					<50>, <52>;
 			clock-output-names = "ahb_usb0", "ahb_ehci0",
-				"ahb_ohci0", "ahb_ehci1", "ahb_ohci1", "ahb_ss",
-				"ahb_dma", "ahb_bist", "ahb_mmc0", "ahb_mmc1",
-				"ahb_mmc2", "ahb_mmc3", "ahb_ms", "ahb_nand",
-				"ahb_sdram", "ahb_ace",	"ahb_emac", "ahb_ts",
-				"ahb_spi0", "ahb_spi1", "ahb_spi2", "ahb_spi3",
-				"ahb_pata", "ahb_sata", "ahb_gps", "ahb_ve",
-				"ahb_tvd", "ahb_tve0", "ahb_tve1", "ahb_lcd0",
-				"ahb_lcd1", "ahb_csi0", "ahb_csi1", "ahb_hdmi",
-				"ahb_de_be0", "ahb_de_be1", "ahb_de_fe0",
-				"ahb_de_fe1", "ahb_mp", "ahb_mali400";
+					     "ahb_ohci0", "ahb_ehci1",
+					     "ahb_ohci1", "ahb_ss", "ahb_dma",
+					     "ahb_bist", "ahb_mmc0", "ahb_mmc1",
+					     "ahb_mmc2", "ahb_mmc3", "ahb_ms",
+					     "ahb_nand", "ahb_sdram", "ahb_ace",
+					     "ahb_emac", "ahb_ts", "ahb_spi0",
+					     "ahb_spi1", "ahb_spi2", "ahb_spi3",
+					     "ahb_pata", "ahb_sata", "ahb_gps",
+					     "ahb_ve", "ahb_tvd", "ahb_tve0",
+					     "ahb_tve1", "ahb_lcd0", "ahb_lcd1",
+					     "ahb_csi0", "ahb_csi1", "ahb_hdmi",
+					     "ahb_de_be0", "ahb_de_be1",
+					     "ahb_de_fe0", "ahb_de_fe1",
+					     "ahb_mp", "ahb_mali400";
 		};
 
 		apb0: apb0@01c20054 {
@@ -283,9 +303,14 @@
 			compatible = "allwinner,sun4i-a10-apb0-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb0>;
+			clock-indices = <0>, <1>,
+					<2>, <3>,
+					<5>, <6>,
+					<7>, <10>;
 			clock-output-names = "apb0_codec", "apb0_spdif",
-				"apb0_ac97", "apb0_iis", "apb0_pio", "apb0_ir0",
-				"apb0_ir1", "apb0_keypad";
+					     "apb0_ac97", "apb0_iis",
+					     "apb0_pio", "apb0_ir0",
+					     "apb0_ir1", "apb0_keypad";
 		};
 
 		apb1: clk@01c20058 {
@@ -301,12 +326,22 @@
 			compatible = "allwinner,sun4i-a10-apb1-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb1>;
+			clock-indices = <0>, <1>,
+					<2>, <4>,
+					<5>, <6>,
+					<7>, <16>,
+					<17>, <18>,
+					<19>, <20>,
+					<21>, <22>,
+					<23>;
 			clock-output-names = "apb1_i2c0", "apb1_i2c1",
-				"apb1_i2c2", "apb1_can", "apb1_scr",
-				"apb1_ps20", "apb1_ps21", "apb1_uart0",
-				"apb1_uart1", "apb1_uart2", "apb1_uart3",
-				"apb1_uart4", "apb1_uart5", "apb1_uart6",
-				"apb1_uart7";
+					     "apb1_i2c2", "apb1_can",
+					     "apb1_scr", "apb1_ps20",
+					     "apb1_ps21", "apb1_uart0",
+					     "apb1_uart1", "apb1_uart2",
+					     "apb1_uart3", "apb1_uart4",
+					     "apb1_uart5", "apb1_uart6",
+					     "apb1_uart7";
 		};
 
 		nand_clk: clk@01c20080 {
@@ -611,6 +646,19 @@
 			#size-cells = <0>;
 		};
 
+		usb_otg: usb@01c13000 {
+			compatible = "allwinner,sun4i-a10-musb";
+			reg = <0x01c13000 0x0400>;
+			clocks = <&ahb_gates 0>;
+			interrupts = <38>;
+			interrupt-names = "mc";
+			phys = <&usbphy 0>;
+			phy-names = "usb";
+			extcon = <&usbphy 0>;
+			allwinner,sram = <&otg_sram 1>;
+			status = "disabled";
+		};
+
 		usbphy: phy@01c13400 {
 			#phy-cells = <1>;
 			compatible = "allwinner,sun4i-a10-usb-phy";
@@ -643,6 +691,14 @@
 			status = "disabled";
 		};
 
+		crypto: crypto-engine@01c15000 {
+			compatible = "allwinner,sun4i-a10-crypto";
+			reg = <0x01c15000 0x1000>;
+			interrupts = <86>;
+			clocks = <&ahb_gates 5>, <&ss_clk>;
+			clock-names = "ahb", "mod";
+		};
+
 		spi2: spi@01c17000 {
 			compatible = "allwinner,sun4i-a10-spi";
 			reg = <0x01c17000 0x1000>;
@@ -713,8 +769,7 @@
 			clocks = <&apb0_gates 5>;
 			gpio-controller;
 			interrupt-controller;
-			#interrupt-cells = <2>;
-			#size-cells = <0>;
+			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
 			pwm0_pins_a: pwm0@0 {
diff --git a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
index a7e19e4847f7..5a422c1ff725 100644
--- a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
@@ -96,8 +96,15 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0_pins_a>;
 	status = "okay";
+
+	axp152: pmic@30 {
+		reg = <0x30>;
+		interrupts = <0>;
+	};
 };
 
+#include "axp152.dtsi"
+
 &i2c1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c1_pins_a>;
@@ -189,6 +196,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	mmc0_cd_pin_olinuxino_micro: mmc0_cd_pin@0 {
 		allwinner,pins = "PG1";
@@ -217,6 +228,18 @@
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PG12";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+};
+
+&reg_usb0_vbus {
+	gpio = <&pio 6 11 GPIO_ACTIVE_HIGH>; /* PG11 */
+	status = "okay";
 };
 
 &reg_usb1_vbus {
@@ -243,8 +266,20 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usb0_vbus_pin_a {
+	allwinner,pins = "PG11";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>;
+	usb0_id_det-gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
 };
-
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index f11efb722bbb..a513b416a807 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -85,6 +85,17 @@
 			compatible = "allwinner,sun5i-a10s-ahb-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb>;
+			clock-indices = <0>, <1>,
+					<2>, <5>, <6>,
+					<7>, <8>, <9>,
+					<10>, <13>,
+					<14>, <17>, <18>,
+					<20>, <21>, <22>,
+					<26>, <28>, <32>,
+					<34>, <36>, <40>,
+					<43>, <44>,
+					<46>, <51>,
+					<52>;
 			clock-output-names = "ahb_usbotg", "ahb_ehci",
 					     "ahb_ohci", "ahb_ss", "ahb_dma",
 					     "ahb_bist", "ahb_mmc0", "ahb_mmc1",
@@ -103,6 +114,9 @@
 			compatible = "allwinner,sun5i-a10s-apb0-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb0>;
+			clock-indices = <0>, <3>,
+					<5>, <6>,
+					<10>;
 			clock-output-names = "apb0_codec", "apb0_iis",
 					     "apb0_pio", "apb0_ir",
 					     "apb0_keypad";
@@ -113,9 +127,14 @@
 			compatible = "allwinner,sun5i-a10s-apb1-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb1>;
+			clock-indices = <0>, <1>,
+					<2>, <16>,
+					<17>, <18>,
+					<19>;
 			clock-output-names = "apb1_i2c0", "apb1_i2c1",
-				"apb1_i2c2", "apb1_uart0", "apb1_uart1",
-				"apb1_uart2", "apb1_uart3";
+					     "apb1_i2c2", "apb1_uart0",
+					     "apb1_uart1", "apb1_uart2",
+					     "apb1_uart3";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
index 990f9d61ae4d..3724b988064e 100644
--- a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
+++ b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
@@ -45,6 +45,7 @@
 #include "sunxi-common-regulators.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
 #include <dt-bindings/pinctrl/sun4i-a10.h>
 
 / {
@@ -96,6 +97,25 @@
 	status = "okay";
 };
 
+&lradc {
+	vref-supply = <&reg_ldo2>;
+	status = "okay";
+
+	button@200 {
+		label = "Volume Up";
+		linux,code = <KEY_VOLUMEUP>;
+		channel = <0>;
+		voltage = <200000>;
+	};
+
+	button@400 {
+		label = "Volume Down";
+		linux,code = <KEY_VOLUMEDOWN>;
+		channel = <0>;
+		voltage = <400000>;
+	};
+};
+
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_h702>;
@@ -110,6 +130,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	mmc0_cd_pin_h702: mmc0_cd_pin@0 {
 		allwinner,pins = "PG0";
@@ -117,6 +141,20 @@
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PG2";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PG1";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
 };
 
 #include "axp209.dtsi"
@@ -152,13 +190,33 @@
 	regulator-name = "vcc-wifi";
 };
 
+&reg_usb0_vbus {
+	pinctrl-0 = <&usb0_vbus_pin_a>;
+	gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
+	status = "okay";
+};
+
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart1_pins_b>;
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usb0_vbus_pin_a {
+	allwinner,pins = "PG12";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpios = <&pio 6 2 GPIO_ACTIVE_HIGH>; /* PG2 */
+	usb0_vbus_det-gpios = <&pio 6 1 GPIO_ACTIVE_HIGH>; /* PG1 */
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_ldo3>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
index 42324005eb7c..b3c234c65ea1 100644
--- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
+++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
@@ -159,6 +159,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	mmc0_cd_pin_olinuxino: mmc0_cd_pin@0 {
 		allwinner,pins = "PG0";
@@ -174,6 +178,20 @@
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
 
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PG2";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PG1";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
+	};
+
 	usb1_vbus_pin_olinuxino: usb1_vbus_pin@0 {
 		allwinner,pins = "PG11";
 		allwinner,function = "gpio_out";
@@ -182,6 +200,11 @@
 	};
 };
 
+&reg_usb0_vbus {
+	status = "okay";
+	gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
+};
+
 &reg_usb1_vbus {
 	pinctrl-0 = <&usb1_vbus_pin_olinuxino>;
 	gpio = <&pio 6 11 GPIO_ACTIVE_HIGH>;
@@ -194,7 +217,21 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usb0_vbus_pin_a {
+	allwinner,pins = "PG12";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpio = <&pio 6 2 GPIO_ACTIVE_HIGH>; /* PG2 */
+	usb0_vbus_det-gpio = <&pio 6 1 GPIO_ACTIVE_HIGH>; /* PG1 */
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts b/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts
index 514f159a14d4..eb793d5a2bd6 100644
--- a/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts
+++ b/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts
@@ -93,7 +93,7 @@
 		compatible = "chipone,icn8318";
 		reg = <0x40>;
 		interrupt-parent = <&pio>;
-		interrupts = <9 IRQ_TYPE_EDGE_FALLING>; /* EINT9 (PG9) */
+		interrupts = <6 9 IRQ_TYPE_EDGE_FALLING>; /* EINT9 (PG9) */
 		pinctrl-names = "default";
 		pinctrl-0 = <&ts_wake_pin_p66>;
 		wake-gpios = <&pio 1 3 GPIO_ACTIVE_HIGH>; /* PB3 */
@@ -153,6 +153,10 @@
 	};
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	mmc0_cd_pin_p66: mmc0_cd_pin@0 {
 		allwinner,pins = "PG0";
@@ -161,6 +165,20 @@
 		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
 	};
 
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PG1";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
+	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PG2";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
 	i2c_lcd_pins: i2c_lcd_pin@0 {
 		allwinner,pins = "PG10", "PG12";
 		allwinner,function = "gpio_out";
@@ -219,7 +237,16 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpio = <&pio 6 2 GPIO_ACTIVE_HIGH>; /* PG2 */
+	usb0_vbus_det-gpio = <&pio 6 1 GPIO_ACTIVE_HIGH>; /* PG1 */
 	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_ldo3>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 976d4faa2179..f3631c9c6fa2 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -104,6 +104,16 @@
 			compatible = "allwinner,sun5i-a13-ahb-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb>;
+			clock-indices = <0>, <1>,
+					<2>, <5>, <6>,
+					<7>, <8>, <9>,
+					<10>, <13>,
+					<14>, <20>,
+					<21>, <22>,
+				        <28>, <32>, <36>,
+				        <40>, <44>,
+					<46>, <51>,
+					<52>;
 			clock-output-names = "ahb_usbotg", "ahb_ehci",
 					     "ahb_ohci", "ahb_ss", "ahb_dma",
 					     "ahb_bist", "ahb_mmc0", "ahb_mmc1",
@@ -121,6 +131,8 @@
 			compatible = "allwinner,sun5i-a13-apb0-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb0>;
+			clock-indices = <0>, <5>,
+					<6>;
 			clock-output-names = "apb0_codec", "apb0_pio",
 					     "apb0_ir";
 		};
@@ -130,8 +142,12 @@
 			compatible = "allwinner,sun5i-a13-apb1-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb1>;
+			clock-indices = <0>, <1>,
+					<2>, <17>,
+					<19>;
 			clock-output-names = "apb1_i2c0", "apb1_i2c1",
-				"apb1_i2c2", "apb1_uart1", "apb1_uart3";
+					     "apb1_i2c2", "apb1_uart1",
+					     "apb1_uart3";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index 54b097830434..78b993abbaa3 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -178,6 +178,7 @@
 			compatible = "allwinner,sun4i-a10-axi-gates-clk";
 			reg = <0x01c2005c 0x4>;
 			clocks = <&axi>;
+			clock-indices = <0>;
 			clock-output-names = "axi_dram";
 		};
 
@@ -416,6 +417,19 @@
 			#size-cells = <0>;
 		};
 
+		usb_otg: usb@01c13000 {
+			compatible = "allwinner,sun4i-a10-musb";
+			reg = <0x01c13000 0x0400>;
+			clocks = <&ahb_gates 0>;
+			interrupts = <38>;
+			interrupt-names = "mc";
+			phys = <&usbphy 0>;
+			phy-names = "usb";
+			extcon = <&usbphy 0>;
+			allwinner,sram = <&otg_sram 1>;
+			status = "disabled";
+		};
+
 		usbphy: phy@01c13400 {
 			#phy-cells = <1>;
 			compatible = "allwinner,sun5i-a13-usb-phy";
@@ -475,8 +489,7 @@
 			clocks = <&apb0_gates 5>;
 			gpio-controller;
 			interrupt-controller;
-			#interrupt-cells = <2>;
-			#size-cells = <0>;
+			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
 			i2c0_pins_a: i2c0@0 {
diff --git a/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts b/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts
index 4404f37d132e..4dd70cce2127 100644
--- a/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts
+++ b/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts
@@ -143,6 +143,11 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
 &usbphy {
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index 008047a018cf..54bb83b58f42 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -252,6 +252,20 @@
 			compatible = "allwinner,sun6i-a31-ahb1-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb1>;
+			clock-indices = <1>, <5>,
+					<6>, <8>, <9>,
+					<10>, <11>, <12>,
+					<13>, <14>,
+					<17>, <18>, <19>,
+					<20>, <21>, <22>,
+					<23>, <24>, <26>,
+					<27>, <29>,
+					<30>, <31>, <32>,
+					<36>, <37>, <40>,
+					<43>, <44>, <45>,
+					<46>, <47>, <50>,
+					<52>, <55>, <56>,
+					<57>, <58>;
 			clock-output-names = "ahb1_mipidsi", "ahb1_ss",
 					"ahb1_dma", "ahb1_mmc0", "ahb1_mmc1",
 					"ahb1_mmc2", "ahb1_mmc3", "ahb1_nand1",
@@ -281,6 +295,9 @@
 			compatible = "allwinner,sun6i-a31-apb1-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb1>;
+			clock-indices = <0>, <4>,
+					<5>, <12>,
+					<13>;
 			clock-output-names = "apb1_codec", "apb1_digital_mic",
 					"apb1_pio", "apb1_daudio0",
 					"apb1_daudio1";
@@ -299,6 +316,10 @@
 			compatible = "allwinner,sun6i-a31-apb2-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb2>;
+			clock-indices = <0>, <1>,
+					<2>, <3>, <16>,
+					<17>, <18>, <19>,
+					<20>, <21>;
 			clock-output-names = "apb2_i2c0", "apb2_i2c1",
 					     "apb2_i2c2", "apb2_i2c3",
 					     "apb2_uart0", "apb2_uart1",
@@ -346,6 +367,14 @@
 					     "mmc3_sample";
 		};
 
+		ss_clk: clk@01c2009c {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-mod0-clk";
+			reg = <0x01c2009c 0x4>;
+			clocks = <&osc24M>, <&pll6 0>;
+			clock-output-names = "ss";
+		};
+
 		spi0_clk: clk@01c200a0 {
 			#clock-cells = <0>;
 			compatible = "allwinner,sun4i-a10-mod0-clk";
@@ -384,6 +413,9 @@
 			compatible = "allwinner,sun6i-a31-usb-clk";
 			reg = <0x01c200cc 0x4>;
 			clocks = <&osc24M>;
+			clock-indices = <8>, <9>, <10>,
+					<16>, <17>,
+					<18>;
 			clock-output-names = "usb_phy0", "usb_phy1", "usb_phy2",
 					     "usb_ohci0", "usb_ohci1",
 					     "usb_ohci2";
@@ -512,6 +544,19 @@
 			#size-cells = <0>;
 		};
 
+		usb_otg: usb@01c19000 {
+			compatible = "allwinner,sun6i-a31-musb";
+			reg = <0x01c19000 0x0400>;
+			clocks = <&ahb1_gates 24>;
+			resets = <&ahb1_rst 24>;
+			interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mc";
+			phys = <&usbphy 0>;
+			phy-names = "usb";
+			extcon = <&usbphy 0>;
+			status = "disabled";
+		};
+
 		usbphy: phy@01c19400 {
 			compatible = "allwinner,sun6i-a31-usb-phy";
 			reg = <0x01c19400 0x10>,
@@ -599,8 +644,7 @@
 			clocks = <&apb1_gates 5>;
 			gpio-controller;
 			interrupt-controller;
-			#interrupt-cells = <2>;
-			#size-cells = <0>;
+			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
 			uart0_pins_a: uart0@0 {
@@ -870,6 +914,16 @@
 			#size-cells = <0>;
 		};
 
+		crypto: crypto-engine@01c15000 {
+			compatible = "allwinner,sun4i-a10-crypto";
+			reg = <0x01c15000 0x1000>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ahb1_gates 5>, <&ss_clk>;
+			clock-names = "ahb", "mod";
+			resets = <&ahb1_rst 5>;
+			reset-names = "ahb";
+		};
+
 		timer@01c60000 {
 			compatible = "allwinner,sun6i-a31-hstimer",
 				     "allwinner,sun7i-a20-hstimer";
diff --git a/arch/arm/boot/dts/sun6i-a31s-cs908.dts b/arch/arm/boot/dts/sun6i-a31s-cs908.dts
index 1e2411a2bcea..5e8f8c4f2b30 100644
--- a/arch/arm/boot/dts/sun6i-a31s-cs908.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-cs908.dts
@@ -93,6 +93,11 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
 &usbphy {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
index 4611e2f5a99e..e6b019232a9e 100644
--- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
+++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
@@ -88,15 +88,11 @@
 		};
 	};
 
-	reg_vmmc3: vmmc3 {
-		compatible = "regulator-fixed";
+	mmc3_pwrseq: mmc3_pwrseq {
+		compatible = "mmc-pwrseq-simple";
 		pinctrl-names = "default";
-		pinctrl-0 = <&vmmc3_pin_cubietruck>;
-		regulator-name = "vmmc3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		enable-active-high;
-		gpio = <&pio 7 9 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&mmc3_pwrseq_pin_cubietruck>;
+		reset-gpios = <&pio 7 9 GPIO_ACTIVE_LOW>; /* PH9 WIFI_EN */
 	};
 };
 
@@ -172,7 +168,8 @@
 &mmc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins_a>;
-	vmmc-supply = <&reg_vmmc3>;
+	vmmc-supply = <&reg_vcc3v3>;
+	mmc-pwrseq = <&mmc3_pwrseq>;
 	bus-width = <4>;
 	non-removable;
 	status = "okay";
@@ -181,7 +178,7 @@
 		reg = <1>;
 		compatible = "brcm,bcm4329-fmac";
 		interrupt-parent = <&pio>;
-		interrupts = <10 IRQ_TYPE_LEVEL_LOW>; /* PH10 / EINT10 */
+		interrupts = <7 10 IRQ_TYPE_LEVEL_LOW>; /* PH10 / EINT10 */
 		interrupt-names = "host-wake";
 	};
 };
@@ -199,23 +196,27 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
-	vmmc3_pin_cubietruck: vmmc3_pin@0 {
-		allwinner,pins = "PH9";
+	ahci_pwr_pin_cubietruck: ahci_pwr_pin@1 {
+		allwinner,pins = "PH12";
 		allwinner,function = "gpio_out";
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
 
-	ahci_pwr_pin_cubietruck: ahci_pwr_pin@1 {
-		allwinner,pins = "PH12";
+	led_pins_cubietruck: led_pins@0 {
+		allwinner,pins = "PH7", "PH11", "PH20", "PH21";
 		allwinner,function = "gpio_out";
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
 
-	led_pins_cubietruck: led_pins@0 {
-		allwinner,pins = "PH7", "PH11", "PH20", "PH21";
+	mmc3_pwrseq_pin_cubietruck: mmc3_pwrseq_pin@0 {
+		allwinner,pins = "PH9";
 		allwinner,function = "gpio_out";
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
@@ -227,6 +228,20 @@
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH19";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PH22";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
 };
 
 &pwm {
@@ -288,7 +303,16 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpios = <&pio 7 19 GPIO_ACTIVE_HIGH>; /* PH19 */
+	usb0_vbus_det-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>; /* PH22 */
 	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
diff --git a/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts b/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts
index f32f6f20d923..1e6bd360dac0 100644
--- a/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts
+++ b/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts
@@ -178,7 +178,7 @@
 		reg = <1>;
 		compatible = "brcm,bcm4329-fmac";
 		interrupt-parent = <&pio>;
-		interrupts = <10 IRQ_TYPE_LEVEL_LOW>; /* PH10 / EINT10 */
+		interrupts = <7 10 IRQ_TYPE_LEVEL_LOW>; /* PH10 / EINT10 */
 		interrupt-names = "host-wake";
 	};
 };
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts
index 769726dfb046..04237085dc39 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts
@@ -135,6 +135,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	ahci_pwr_pin_olinuxinolime: ahci_pwr_pin@1 {
 		allwinner,pins = "PC3";
@@ -149,6 +153,20 @@
 		allwinner,drive = <SUN4I_PINCTRL_20_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PH5";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
+	};
 };
 
 &reg_ahci_5v {
@@ -157,6 +175,10 @@
 	status = "okay";
 };
 
+&reg_usb0_vbus {
+	status = "okay";
+};
+
 &reg_usb1_vbus {
 	status = "okay";
 };
@@ -171,7 +193,17 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
+	usb0_vbus_det-gpio = <&pio 7 5 GPIO_ACTIVE_HIGH>; /* PH5 */
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
index 00f8f25eccae..c5d70caade82 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
@@ -215,6 +215,10 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	mmc3_cd_pin_olinuxinom: mmc3_cd_pin@0 {
 		allwinner,pins = "PH11";
@@ -229,12 +233,30 @@
 		allwinner,drive = <SUN4I_PINCTRL_20_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
+		allwinner,pins = "PH5";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
+	};
 };
 
 &reg_ahci_5v {
 	status = "okay";
 };
 
+&reg_usb0_vbus {
+	status = "okay";
+};
+
 &reg_usb1_vbus {
 	status = "okay";
 };
@@ -275,7 +297,17 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
+	usb0_id_det-gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
+	usb0_vbus_det-gpio = <&pio 7 5 GPIO_ACTIVE_HIGH>; /* PH5 */
+	usb0_vbus-supply = <&reg_usb0_vbus>;
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 6a63f30c9a69..2bebaa286f9a 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -267,6 +267,19 @@
 			compatible = "allwinner,sun7i-a20-ahb-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb>;
+			clock-indices = <0>, <1>,
+					<2>, <3>, <4>,
+					<5>, <6>, <7>, <8>,
+					<9>, <10>, <11>, <12>,
+					<13>, <14>, <16>,
+					<17>, <18>, <20>, <21>,
+					<22>, <23>, <25>,
+					<28>, <32>, <33>, <34>,
+					<35>, <36>, <37>, <40>,
+					<41>, <42>, <43>,
+					<44>, <45>, <46>,
+					<47>, <49>, <50>,
+					<52>;
 			clock-output-names = "ahb_usb0", "ahb_ehci0",
 				"ahb_ohci0", "ahb_ehci1", "ahb_ohci1",
 				"ahb_ss", "ahb_dma", "ahb_bist", "ahb_mmc0",
@@ -295,6 +308,10 @@
 			compatible = "allwinner,sun7i-a20-apb0-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb0>;
+			clock-indices = <0>, <1>,
+					<2>, <3>, <4>,
+					<5>, <6>, <7>,
+					<8>, <10>;
 			clock-output-names = "apb0_codec", "apb0_spdif",
 				"apb0_ac97", "apb0_iis0", "apb0_iis1",
 				"apb0_pio", "apb0_ir0", "apb0_ir1",
@@ -314,6 +331,12 @@
 			compatible = "allwinner,sun7i-a20-apb1-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb1>;
+			clock-indices = <0>, <1>,
+					<2>, <3>, <4>,
+					<5>, <6>, <7>,
+					<15>, <16>, <17>,
+					<18>, <19>, <20>,
+					<21>, <22>, <23>;
 			clock-output-names = "apb1_i2c0", "apb1_i2c1",
 				"apb1_i2c2", "apb1_i2c3", "apb1_can",
 				"apb1_scr", "apb1_ps20", "apb1_ps21",
@@ -699,6 +722,19 @@
 			#size-cells = <0>;
 		};
 
+		usb_otg: usb@01c13000 {
+			compatible = "allwinner,sun4i-a10-musb";
+			reg = <0x01c13000 0x0400>;
+			clocks = <&ahb_gates 0>;
+			interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mc";
+			phys = <&usbphy 0>;
+			phy-names = "usb";
+			extcon = <&usbphy 0>;
+			allwinner,sram = <&otg_sram 1>;
+			status = "disabled";
+		};
+
 		usbphy: phy@01c13400 {
 			#phy-cells = <1>;
 			compatible = "allwinner,sun7i-a20-usb-phy";
@@ -731,6 +767,14 @@
 			status = "disabled";
 		};
 
+		crypto: crypto-engine@01c15000 {
+			compatible = "allwinner,sun4i-a10-crypto";
+			reg = <0x01c15000 0x1000>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ahb_gates 5>, <&ss_clk>;
+			clock-names = "ahb", "mod";
+		};
+
 		spi2: spi@01c17000 {
 			compatible = "allwinner,sun4i-a10-spi";
 			reg = <0x01c17000 0x1000>;
@@ -794,8 +838,7 @@
 			clocks = <&apb0_gates 5>;
 			gpio-controller;
 			interrupt-controller;
-			#interrupt-cells = <2>;
-			#size-cells = <0>;
+			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
 			pwm0_pins_a: pwm0@0 {
diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
index 7abd0ae3143d..27a925ec17d2 100644
--- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
@@ -180,6 +180,15 @@
 			compatible = "allwinner,sun8i-a23-ahb1-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb1>;
+			clock-indices = <1>, <6>,
+					<8>, <9>, <10>,
+					<13>, <14>,
+					<19>, <20>,
+					<21>, <24>, <26>,
+					<29>, <32>, <36>,
+					<40>, <44>, <46>,
+					<52>, <54>,
+					<57>;
 			clock-output-names = "ahb1_mipidsi", "ahb1_dma",
 					"ahb1_mmc0", "ahb1_mmc1", "ahb1_mmc2",
 					"ahb1_nand", "ahb1_sdram",
@@ -196,6 +205,8 @@
 			compatible = "allwinner,sun8i-a23-apb1-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb1>;
+			clock-indices = <0>, <5>,
+					<12>, <13>;
 			clock-output-names = "apb1_codec", "apb1_pio",
 					"apb1_daudio0",	"apb1_daudio1";
 		};
@@ -213,6 +224,10 @@
 			compatible = "allwinner,sun8i-a23-apb2-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb2>;
+			clock-indices = <0>, <1>,
+					<2>, <16>,
+					<17>, <18>,
+					<19>, <20>;
 			clock-output-names = "apb2_i2c0", "apb2_i2c1",
 					"apb2_i2c2", "apb2_uart0",
 					"apb2_uart1", "apb2_uart2",
@@ -332,6 +347,28 @@
 			#size-cells = <0>;
 		};
 
+		ehci0: usb@01c1a000 {
+			compatible = "allwinner,sun8i-a23-ehci", "generic-ehci";
+			reg = <0x01c1a000 0x100>;
+			interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ahb1_gates 26>;
+			resets = <&ahb1_rst 26>;
+			phys = <&usbphy 1>;
+			phy-names = "usb";
+			status = "disabled";
+		};
+
+		ohci0: usb@01c1a400 {
+			compatible = "allwinner,sun8i-a23-ohci", "generic-ohci";
+			reg = <0x01c1a400 0x100>;
+			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ahb1_gates 29>, <&usb_clk 16>;
+			resets = <&ahb1_rst 29>;
+			phys = <&usbphy 1>;
+			phy-names = "usb";
+			status = "disabled";
+		};
+
 		pio: pinctrl@01c20800 {
 			/* compatible gets set in SoC specific dtsi file */
 			reg = <0x01c20800 0x400>;
@@ -339,8 +376,7 @@
 			clocks = <&apb1_gates 5>;
 			gpio-controller;
 			interrupt-controller;
-			#address-cells = <1>;
-			#size-cells = <0>;
+			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
 			uart0_pins_a: uart0@0 {
diff --git a/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts b/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
index 95134c69cfc1..8d9da6886a4c 100644
--- a/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
+++ b/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
@@ -125,3 +125,12 @@
 	pinctrl-0 = <&r_uart_pins_a>;
 	status = "okay";
 };
+
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun8i-a23.dtsi b/arch/arm/boot/dts/sun8i-a23.dtsi
index 8698f7aa31c7..2cc27c7a59dc 100644
--- a/arch/arm/boot/dts/sun8i-a23.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23.dtsi
@@ -58,6 +58,39 @@
 			clock-output-names = "mbus";
 		};
 	};
+
+	soc@01c00000 {
+		usb_otg: usb@01c19000 {
+			compatible = "allwinner,sun6i-a31-musb";
+			reg = <0x01c19000 0x0400>;
+			clocks = <&ahb1_gates 24>;
+			resets = <&ahb1_rst 24>;
+			interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mc";
+			phys = <&usbphy 0>;
+			phy-names = "usb";
+			extcon = <&usbphy 0>;
+			status = "disabled";
+		};
+
+		usbphy: phy@01c19400 {
+			compatible = "allwinner,sun8i-a23-usb-phy";
+			reg = <0x01c19400 0x10>,
+			      <0x01c1a800 0x4>;
+			reg-names = "phy_ctrl",
+				    "pmu1";
+			clocks = <&usb_clk 8>,
+				 <&usb_clk 9>;
+			clock-names = "usb0_phy",
+				      "usb1_phy";
+			resets = <&usb_clk 0>,
+				 <&usb_clk 1>;
+			reset-names = "usb0_reset",
+				      "usb1_reset";
+			status = "disabled";
+			#phy-cells = <1>;
+		};
+	};
 };
 
 &pio {
diff --git a/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts b/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts
index 866703355b9c..1aefc6793e25 100644
--- a/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts
+++ b/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts
@@ -61,6 +61,10 @@
 	};
 };
 
+&ehci0 {
+	status = "okay";
+};
+
 &i2c0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0_pins_a>;
@@ -109,6 +113,10 @@
 	status = "okay";
 };
 
+&ohci0 {
+	status = "okay";
+};
+
 &pio {
 	mmc0_cd_pin_q8h: mmc0_cd_pin@0 {
 		allwinner,pins = "PB4";
@@ -123,3 +131,12 @@
 	pinctrl-0 = <&r_uart_pins_a>;
 	status = "okay";
 };
+
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun8i-a33-ippo-q8h-v1.2.dts b/arch/arm/boot/dts/sun8i-a33-ippo-q8h-v1.2.dts
new file mode 100644
index 000000000000..a43897515fb6
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-a33-ippo-q8h-v1.2.dts
@@ -0,0 +1,133 @@
+/*
+ * Copyright 2015 Hans de Goede <hdegoede@redhat.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun8i-a33.dtsi"
+#include "sunxi-common-regulators.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/pinctrl/sun4i-a10.h>
+
+/ {
+	model = "Ippo Q8H Quad Core Tablet (v1.2)";
+	compatible = "ippo,a33-q8h-v1.2", "allwinner,sun8i-a33";
+
+	aliases {
+		serial0 = &r_uart;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins_a>;
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins_a>;
+	status = "okay";
+};
+
+&lradc {
+	vref-supply = <&reg_vcc3v0>;
+	status = "okay";
+
+	button@200 {
+		label = "Volume Up";
+		linux,code = <KEY_VOLUMEUP>;
+		channel = <0>;
+		voltage = <200000>;
+	};
+
+	button@400 {
+		label = "Volume Down";
+		linux,code = <KEY_VOLUMEDOWN>;
+		channel = <0>;
+		voltage = <400000>;
+	};
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_q8h>;
+	vmmc-supply = <&reg_vcc3v0>;
+	bus-width = <4>;
+	cd-gpios = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
+	cd-inverted;
+	status = "okay";
+};
+
+&pio {
+	mmc0_cd_pin_q8h: mmc0_cd_pin@0 {
+		allwinner,pins = "PB4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+};
+
+&r_uart {
+	pinctrl-names = "default";
+	pinctrl-0 = <&r_uart_pins_a>;
+	status = "okay";
+};
+
+/*
+ * FIXME for now we only support host mode and rely on u-boot to have
+ * turned on Vbus which is controlled by the axp223 pmic on the board.
+ *
+ * Once we have axp223 support we should switch to fully supporting otg.
+ */
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts b/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts
index 5788c29cb56a..1d5390d4e03a 100644
--- a/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts
+++ b/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts
@@ -63,6 +63,10 @@
 	};
 };
 
+&ehci0 {
+	status = "okay";
+};
+
 &lradc {
 	vref-supply = <&reg_vcc3v0>;
 	status = "okay";
@@ -113,6 +117,10 @@
 	allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
 };
 
+&ohci0 {
+	status = "okay";
+};
+
 &pio {
 	mmc0_cd_pin_sina33: mmc0_cd_pin@0 {
 		allwinner,pins = "PB4";
@@ -127,3 +135,8 @@
 	pinctrl-0 = <&uart0_pins_b>;
 	status = "okay";
 };
+
+&usbphy {
+	status = "okay";
+	usb1_vbus-supply = <&reg_vcc5v0>; /* USB1 VBUS is always on */
+};
diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi
index 85ee08098b7b..faa7d3c1fcea 100644
--- a/arch/arm/boot/dts/sun8i-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a33.dtsi
@@ -80,6 +80,39 @@
 			clock-output-names = "mbus";
 		};
 	};
+
+	soc@01c00000 {
+		usb_otg: usb@01c19000 {
+			compatible = "allwinner,sun8i-a33-musb";
+			reg = <0x01c19000 0x0400>;
+			clocks = <&ahb1_gates 24>;
+			resets = <&ahb1_rst 24>;
+			interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mc";
+			phys = <&usbphy 0>;
+			phy-names = "usb";
+			extcon = <&usbphy 0>;
+			status = "disabled";
+		};
+
+		usbphy: phy@01c19400 {
+			compatible = "allwinner,sun8i-a33-usb-phy";
+			reg = <0x01c19400 0x14>,
+			      <0x01c1a800 0x4>;
+			reg-names = "phy_ctrl",
+				    "pmu1";
+			clocks = <&usb_clk 8>,
+				 <&usb_clk 9>;
+			clock-names = "usb0_phy",
+				      "usb1_phy";
+			resets = <&usb_clk 0>,
+				 <&usb_clk 1>;
+			reset-names = "usb0_reset",
+				      "usb1_reset";
+			status = "disabled";
+			#phy-cells = <1>;
+		};
+	};
 };
 
 &pio {
diff --git a/arch/arm/boot/dts/sun9i-a80.dtsi b/arch/arm/boot/dts/sun9i-a80.dtsi
index a43ad779ee2f..5908e3dcf965 100644
--- a/arch/arm/boot/dts/sun9i-a80.dtsi
+++ b/arch/arm/boot/dts/sun9i-a80.dtsi
@@ -277,9 +277,12 @@
 			compatible = "allwinner,sun9i-a80-ahb0-gates-clk";
 			reg = <0x06000580 0x4>;
 			clocks = <&ahb0>;
-			clock-indices = <0>, <1>, <3>, <5>, <8>, <12>, <13>,
-					<14>, <15>, <16>, <18>, <20>, <21>,
-					<22>, <23>;
+			clock-indices = <0>, <1>, <3>,
+					<5>, <8>, <12>,
+					<13>, <14>,
+					<15>, <16>, <18>,
+					<20>, <21>, <22>,
+					<23>;
 			clock-output-names = "ahb0_fd", "ahb0_ve", "ahb0_gpu",
 					"ahb0_ss", "ahb0_sd", "ahb0_nand1",
 					"ahb0_nand0", "ahb0_sdram",
@@ -293,7 +296,10 @@
 			compatible = "allwinner,sun9i-a80-ahb1-gates-clk";
 			reg = <0x06000584 0x4>;
 			clocks = <&ahb1>;
-			clock-indices = <0>, <1>, <17>, <21>, <22>, <23>, <24>;
+			clock-indices = <0>, <1>,
+					<17>, <21>,
+					<22>, <23>,
+					<24>;
 			clock-output-names = "ahb1_usbotg", "ahb1_usbhci",
 					"ahb1_gmac", "ahb1_msgbox",
 					"ahb1_spinlock", "ahb1_hstimer",
@@ -305,8 +311,9 @@
 			compatible = "allwinner,sun9i-a80-ahb2-gates-clk";
 			reg = <0x06000588 0x4>;
 			clocks = <&ahb2>;
-			clock-indices = <0>, <1>, <2>, <4>, <5>, <7>, <8>,
-					<11>;
+			clock-indices = <0>, <1>,
+					<2>, <4>, <5>,
+					<7>, <8>, <11>;
 			clock-output-names = "ahb2_lcd0", "ahb2_lcd1",
 					"ahb2_edp", "ahb2_csi", "ahb2_hdmi",
 					"ahb2_de", "ahb2_mp", "ahb2_mipi_dsi";
@@ -317,8 +324,10 @@
 			compatible = "allwinner,sun9i-a80-apb0-gates-clk";
 			reg = <0x06000590 0x4>;
 			clocks = <&apb0>;
-			clock-indices = <1>, <5>, <11>, <12>, <13>, <15>,
-					<17>, <18>, <19>;
+			clock-indices = <1>, <5>,
+					<11>, <12>, <13>,
+					<15>, <17>, <18>,
+					<19>;
 			clock-output-names = "apb0_spdif", "apb0_pio",
 					"apb0_ac97", "apb0_i2s0", "apb0_i2s1",
 					"apb0_lradc", "apb0_gpadc", "apb0_twd",
@@ -330,8 +339,11 @@
 			compatible = "allwinner,sun9i-a80-apb1-gates-clk";
 			reg = <0x06000594 0x4>;
 			clocks = <&apb1>;
-			clock-indices = <0>, <1>, <2>, <3>, <4>,
-					<16>, <17>, <18>, <19>, <20>, <21>;
+			clock-indices = <0>, <1>,
+					<2>, <3>, <4>,
+					<16>, <17>,
+					<18>, <19>,
+					<20>, <21>;
 			clock-output-names = "apb1_i2c0", "apb1_i2c1",
 					"apb1_i2c2", "apb1_i2c3", "apb1_i2c4",
 					"apb1_uart0", "apb1_uart1",
diff --git a/arch/arm/boot/dts/sunxi-common-regulators.dtsi b/arch/arm/boot/dts/sunxi-common-regulators.dtsi
index 51cc8383f70f..f1953b0c5059 100644
--- a/arch/arm/boot/dts/sunxi-common-regulators.dtsi
+++ b/arch/arm/boot/dts/sunxi-common-regulators.dtsi
@@ -108,6 +108,7 @@
 		regulator-name = "usb1-vbus";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
+		regulator-boot-on;
 		enable-active-high;
 		gpio = <&pio 7 6 GPIO_ACTIVE_HIGH>;
 		status = "disabled";
@@ -120,6 +121,7 @@
 		regulator-name = "usb2-vbus";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
+		regulator-boot-on;
 		enable-active-high;
 		gpio = <&pio 7 3 GPIO_ACTIVE_HIGH>;
 		status = "disabled";
diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi
index f58a3d9d5f13..9d4f86e9c50a 100644
--- a/arch/arm/boot/dts/tegra114.dtsi
+++ b/arch/arm/boot/dts/tegra114.dtsi
@@ -214,9 +214,9 @@
 		#dma-cells = <1>;
 	};
 
-	ahb: ahb@6000c004 {
+	ahb: ahb@6000c000 {
 		compatible = "nvidia,tegra114-ahb", "nvidia,tegra30-ahb";
-		reg = <0x6000c004 0x14c>;
+		reg = <0x6000c000 0x150>;
 	};
 
 	gpio: gpio@6000d000 {
@@ -234,6 +234,7 @@
 		gpio-controller;
 		#interrupt-cells = <2>;
 		interrupt-controller;
+		gpio-ranges = <&pinmux 0 0 246>;
 	};
 
 	apbmisc@70000800 {
diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
index bd43ed6d6ec7..66b4451eb2ca 100644
--- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts
+++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
@@ -53,6 +53,14 @@
 		};
 	};
 
+	gpu@0,57000000 {
+		/*
+		 * Node left disabled on purpose - the bootloader will enable
+		 * it after having set the VPR up
+		 */
+		vdd-supply = <&vdd_gpu>;
+	};
+
 	pinmux: pinmux@0,70000868 {
 		pinctrl-names = "boot";
 		pinctrl-0 = <&state_boot>;
@@ -1462,7 +1470,7 @@
 				vin-ldo9-10-supply = <&vdd_5v0_sys>;
 				vin-ldo11-supply = <&vdd_3v3_run>;
 
-				sd0 {
+				vdd_cpu: sd0 {
 					regulator-name = "+VDD_CPU_AP";
 					regulator-min-microvolt = <700000>;
 					regulator-max-microvolt = <1400000>;
@@ -1514,7 +1522,7 @@
 					regulator-always-on;
 				};
 
-				sd6 {
+				vdd_gpu: sd6 {
 					regulator-name = "+VDD_GPU_AP";
 					regulator-min-microvolt = <650000>;
 					regulator-max-microvolt = <1200000>;
@@ -1694,6 +1702,13 @@
 		non-removable;
 	};
 
+	/* CPU DFLL clock */
+	clock@0,70110000 {
+		status = "okay";
+		vdd-cpu-supply = <&vdd_cpu>;
+		nvidia,i2c-fs-rate = <400000>;
+	};
+
 	ahub@0,70300000 {
 		i2s@0,70301100 {
 			status = "okay";
@@ -1732,6 +1747,12 @@
 		};
 	};
 
+	cpus {
+		cpu@0 {
+			vdd-cpu-supply = <&vdd_cpu>;
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 
diff --git a/arch/arm/boot/dts/tegra124-venice2.dts b/arch/arm/boot/dts/tegra124-venice2.dts
index 79e724bb7df7..cfbdf429b45d 100644
--- a/arch/arm/boot/dts/tegra124-venice2.dts
+++ b/arch/arm/boot/dts/tegra124-venice2.dts
@@ -43,6 +43,14 @@
 		};
 	};
 
+	gpu@0,57000000 {
+		/*
+		 * Node left disabled on purpose - the bootloader will enable
+		 * it after having set the VPR up
+		 */
+		vdd-supply = <&vdd_gpu>;
+	};
+
 	pinmux: pinmux@0,70000868 {
 		pinctrl-names = "boot";
 		pinctrl-0 = <&pinmux_boot>;
@@ -735,7 +743,7 @@
 					regulator-always-on;
 				};
 
-				sd6 {
+				vdd_gpu: sd6 {
 					regulator-name = "+VDD_GPU_AP";
 					regulator-min-microvolt = <650000>;
 					regulator-max-microvolt = <1200000>;
diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi
index 01a9f742b08f..1e204a6de12c 100644
--- a/arch/arm/boot/dts/tegra124.dtsi
+++ b/arch/arm/boot/dts/tegra124.dtsi
@@ -4,6 +4,7 @@
 #include <dt-bindings/pinctrl/pinctrl-tegra.h>
 #include <dt-bindings/pinctrl/pinctrl-tegra-xusb.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/reset/tegra124-car.h>
 #include <dt-bindings/thermal/tegra124-soctherm.h>
 
 #include "skeleton.dtsi"
@@ -188,6 +189,9 @@
 		clock-names = "gpu", "pwr";
 		resets = <&tegra_car 184>;
 		reset-names = "gpu";
+
+		iommus = <&mc TEGRA_SWGROUP_GPU>;
+
 		status = "disabled";
 	};
 
@@ -254,6 +258,7 @@
 		gpio-controller;
 		#interrupt-cells = <2>;
 		interrupt-controller;
+		gpio-ranges = <&pinmux 0 0 251>;
 	};
 
 	apbdma: dma@0,60020000 {
@@ -702,6 +707,30 @@
 		#thermal-sensor-cells = <1>;
 	};
 
+	dfll: clock@0,70110000 {
+		compatible = "nvidia,tegra124-dfll";
+		reg = <0 0x70110000 0 0x100>, /* DFLL control */
+		      <0 0x70110000 0 0x100>, /* I2C output control */
+		      <0 0x70110100 0 0x100>, /* Integrated I2C controller */
+		      <0 0x70110200 0 0x100>; /* Look-up table RAM */
+		interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&tegra_car TEGRA124_CLK_DFLL_SOC>,
+			 <&tegra_car TEGRA124_CLK_DFLL_REF>,
+			 <&tegra_car TEGRA124_CLK_I2C5>;
+		clock-names = "soc", "ref", "i2c";
+		resets = <&tegra_car TEGRA124_RST_DFLL_DVCO>;
+		reset-names = "dvco";
+		#clock-cells = <0>;
+		clock-output-names = "dfllCPU_out";
+		nvidia,sample-rate = <12500>;
+		nvidia,droop-ctrl = <0x00000f00>;
+		nvidia,force-mode = <1>;
+		nvidia,cf = <10>;
+		nvidia,ci = <0>;
+		nvidia,cg = <2>;
+		status = "disabled";
+	};
+
 	ahub@0,70300000 {
 		compatible = "nvidia,tegra124-ahub";
 		reg = <0x0 0x70300000 0x0 0x200>,
@@ -922,6 +951,15 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0>;
+
+			clocks = <&tegra_car TEGRA124_CLK_CCLK_G>,
+				 <&tegra_car TEGRA124_CLK_CCLK_LP>,
+				 <&tegra_car TEGRA124_CLK_PLL_X>,
+				 <&tegra_car TEGRA124_CLK_PLL_P>,
+				 <&dfll>;
+			clock-names = "cpu_g", "cpu_lp", "pll_x", "pll_p", "dfll";
+			/* FIXME: what's the actual transition time? */
+			clock-latency = <300000>;
 		};
 
 		cpu@1 {
@@ -943,6 +981,18 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a15-pmu";
+		interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&{/cpus/cpu@0}>,
+				     <&{/cpus/cpu@1}>,
+				     <&{/cpus/cpu@2}>,
+				     <&{/cpus/cpu@3}>;
+	};
+
 	thermal-zones {
 		cpu {
 			polling-delay-passive = <1000>;
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index f444b67f55c6..e058709e6d98 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -225,9 +225,9 @@
 		#dma-cells = <1>;
 	};
 
-	ahb@6000c004 {
+	ahb@6000c000 {
 		compatible = "nvidia,tegra20-ahb";
-		reg = <0x6000c004 0x10c>; /* AHB Arbitration + Gizmo Controller */
+		reg = <0x6000c000 0x110>; /* AHB Arbitration + Gizmo Controller */
 	};
 
 	gpio: gpio@6000d000 {
@@ -244,6 +244,7 @@
 		gpio-controller;
 		#interrupt-cells = <2>;
 		interrupt-controller;
+		gpio-ranges = <&pinmux 0 0 224>;
 	};
 
 	apbmisc@70000800 {
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index 782b11b2af6a..fe04fb5e155f 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -329,9 +329,9 @@
 		#dma-cells = <1>;
 	};
 
-	ahb: ahb@6000c004 {
+	ahb: ahb@6000c000 {
 		compatible = "nvidia,tegra30-ahb";
-		reg = <0x6000c004 0x14c>; /* AHB Arbitration + Gizmo Controller */
+		reg = <0x6000c000 0x150>; /* AHB Arbitration + Gizmo Controller */
 	};
 
 	gpio: gpio@6000d000 {
@@ -349,6 +349,7 @@
 		gpio-controller;
 		#interrupt-cells = <2>;
 		interrupt-controller;
+		gpio-ranges = <&pinmux 0 0 248>;
 	};
 
 	apbmisc@70000800 {
diff --git a/arch/arm/boot/dts/uniphier-ph1-ld4-ref.dts b/arch/arm/boot/dts/uniphier-ph1-ld4-ref.dts
index 200b0c99ed34..bfd3bb8c8285 100644
--- a/arch/arm/boot/dts/uniphier-ph1-ld4-ref.dts
+++ b/arch/arm/boot/dts/uniphier-ph1-ld4-ref.dts
@@ -44,6 +44,7 @@
 
 /dts-v1/;
 /include/ "uniphier-ph1-ld4.dtsi"
+/include/ "uniphier-ref-daughter.dtsi"
 /include/ "uniphier-support-card.dtsi"
 
 / {
@@ -57,11 +58,18 @@
 
 	chosen {
 		bootargs = "console=ttyS0,115200";
-		stdout-path = &serialsc;
+		stdout-path = &serial0;
 	};
 
 	aliases {
-		serial0 = &serialsc;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
 	};
 };
 
@@ -74,6 +82,30 @@
 	ranges = <0x00000000 1 0x03f00000 0x00100000>;
 };
 
-&serialsc {
+&ethsc {
 	interrupts = <0 49 4>;
 };
+
+&serial0 {
+	status = "okay";
+};
+
+&serial2 {
+	status = "okay";
+};
+
+&serial3 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&usb0 {
+	status = "okay";
+};
+
+&usb1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi b/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi
index 6a34c56e4693..a6a185fae8f1 100644
--- a/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi
@@ -64,6 +64,18 @@
 			compatible = "fixed-clock";
 			clock-frequency = <50000000>;
 		};
+
+		uart_clk: uart_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <36864000>;
+		};
+
+		iobus_clk: iobus_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <100000000>;
+		};
 	};
 
 	soc {
@@ -79,12 +91,141 @@
 			#size-cells = <1>;
 		};
 
+		serial0: serial@54006800 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006800 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart0>;
+			interrupts = <0 33 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial1: serial@54006900 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006900 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart1>;
+			interrupts = <0 35 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial2: serial@54006a00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006a00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart2>;
+			interrupts = <0 37 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial3: serial@54006b00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006b00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart3>;
+			interrupts = <0 29 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		i2c0: i2c@58400000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58400000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c0>;
+			interrupts = <0 41 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c1: i2c@58480000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58480000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c1>;
+			interrupts = <0 42 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		/* chip-internal connection for DMD */
+		i2c2: i2c@58500000 {
+			compatible = "socionext,uniphier-i2c";
+			reg = <0x58500000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c2>;
+			interrupts = <0 43 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <400000>;
+		};
+
+		i2c3: i2c@58580000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58580000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c3>;
+			interrupts = <0 44 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
 		system-bus-controller-misc@59800000 {
 			compatible = "socionext,uniphier-system-bus-controller-misc",
 				     "syscon";
 			reg = <0x59800000 0x2000>;
 		};
 
+		usb0: usb@5a800100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a800100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb0>;
+			interrupts = <0 80 4>;
+		};
+
+		usb1: usb@5a810100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a810100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb1>;
+			interrupts = <0 81 4>;
+		};
+
+		usb2: usb@5a820100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a820100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb2>;
+			interrupts = <0 82 4>;
+		};
+
+		pinctrl: pinctrl@5f801000 {
+			compatible = "socionext,ph1-ld4-pinctrl",
+				     "syscon";
+			reg = <0x5f801000 0xe00>;
+		};
+
 		timer@60000200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x60000200 0x20>;
@@ -108,3 +249,5 @@
 		};
 	};
 };
+
+/include/ "uniphier-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts b/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts
new file mode 100644
index 000000000000..33963acd7e8f
--- /dev/null
+++ b/arch/arm/boot/dts/uniphier-ph1-ld6b-ref.dts
@@ -0,0 +1,105 @@
+/*
+ * Device Tree Source for UniPhier PH1-LD6b Reference Board
+ *
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+/include/ "uniphier-ph1-ld6b.dtsi"
+/include/ "uniphier-ref-daughter.dtsi"
+/include/ "uniphier-support-card.dtsi"
+
+/ {
+	model = "UniPhier PH1-LD6b Reference Board";
+	compatible = "socionext,ph1-ld6b-ref", "socionext,ph1-ld6b";
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200";
+		stdout-path = &serial0;
+	};
+
+	aliases {
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
+		i2c5 = &i2c5;
+		i2c6 = &i2c6;
+	};
+};
+
+&extbus {
+	ranges = <0 0x00000000 0x0f000000 0x01000000
+		  1 0x00000000 0x00000000 0x08000000>;
+};
+
+&support_card {
+	ranges = <0x00000000 1 0x03f00000 0x00100000>;
+};
+
+&ethsc {
+	interrupts = <0 50 4>;
+};
+
+&serial0 {
+	status = "okay";
+};
+
+&serial1 {
+	status = "okay";
+};
+
+&serial2 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi b/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi
new file mode 100644
index 000000000000..c6499ee65bc6
--- /dev/null
+++ b/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi
@@ -0,0 +1,67 @@
+/*
+ * Device Tree Source for UniPhier PH1-LD6b SoC
+ *
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * PH1-LD6b consists of two silicon dies: D-chip and A-chip.
+ * The D-chip (digital chip) is the same as the ProXstream2 die.
+ * Reuse the ProXstream2 device tree with some properties overridden.
+ */
+/include/ "uniphier-proxstream2.dtsi"
+
+/ {
+	compatible = "socionext,ph1-ld6b";
+};
+
+/* UART3 unavilable: the pads are not wired to the package balls */
+&serial3 {
+	status = "disabled";
+};
+
+/*
+ * PH1-LD6b and ProXstream2 have completely different packages,
+ * which makes the pinctrl driver unshareable.
+ */
+&pinctrl {
+	compatible = "socionext,ph1-ld6b-pinctrl", "syscon";
+};
diff --git a/arch/arm/boot/dts/uniphier-ph1-pro4-ref.dts b/arch/arm/boot/dts/uniphier-ph1-pro4-ref.dts
index d891135a70c2..69a5b7d39629 100644
--- a/arch/arm/boot/dts/uniphier-ph1-pro4-ref.dts
+++ b/arch/arm/boot/dts/uniphier-ph1-pro4-ref.dts
@@ -44,6 +44,7 @@
 
 /dts-v1/;
 /include/ "uniphier-ph1-pro4.dtsi"
+/include/ "uniphier-ref-daughter.dtsi"
 /include/ "uniphier-support-card.dtsi"
 
 / {
@@ -57,11 +58,20 @@
 
 	chosen {
 		bootargs = "console=ttyS0,115200";
-		stdout-path = &serialsc;
+		stdout-path = &serial0;
 	};
 
 	aliases {
-		serial0 = &serialsc;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c5 = &i2c5;
+		i2c6 = &i2c6;
 	};
 };
 
@@ -74,6 +84,30 @@
 	ranges = <0x00000000 1 0x03f00000 0x00100000>;
 };
 
-&serialsc {
+&ethsc {
 	interrupts = <0 50 4>;
 };
+
+&serial0 {
+	status = "okay";
+};
+
+&serial1 {
+	status = "okay";
+};
+
+&serial2 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&usb2 {
+	status = "okay";
+};
+
+&usb3 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi b/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi
index dc633603aed2..e8bbc454d788 100644
--- a/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi
@@ -71,6 +71,18 @@
 			compatible = "fixed-clock";
 			clock-frequency = <50000000>;
 		};
+
+		uart_clk: uart_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <73728000>;
+		};
+
+		i2c_clk: i2c_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
 	};
 
 	soc {
@@ -86,12 +98,156 @@
 			#size-cells = <1>;
 		};
 
+		serial0: serial@54006800 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006800 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart0>;
+			interrupts = <0 33 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial1: serial@54006900 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006900 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart1>;
+			interrupts = <0 35 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial2: serial@54006a00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006a00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart2>;
+			interrupts = <0 37 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial3: serial@54006b00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006b00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart3>;
+			interrupts = <0 29 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		i2c0: i2c@58780000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58780000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c0>;
+			interrupts = <0 41 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c1: i2c@58781000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58781000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c1>;
+			interrupts = <0 42 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c2: i2c@58782000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58782000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c2>;
+			interrupts = <0 43 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c3: i2c@58783000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58783000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c3>;
+			interrupts = <0 44 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		/* i2c4 does not exist */
+
+		/* chip-internal connection for DMD */
+		i2c5: i2c@58785000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58785000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 25 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
+		/* chip-internal connection for HDMI */
+		i2c6: i2c@58786000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58786000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 26 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
 		system-bus-controller-misc@59800000 {
 			compatible = "socionext,uniphier-system-bus-controller-misc",
 				     "syscon";
 			reg = <0x59800000 0x2000>;
 		};
 
+		usb2: usb@5a800100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a800100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb2>;
+			interrupts = <0 80 4>;
+		};
+
+		usb3: usb@5a810100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a810100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb3>;
+			interrupts = <0 81 4>;
+		};
+
+		pinctrl: pinctrl@5f801000 {
+			compatible = "socionext,ph1-pro4-pinctrl",
+				     "syscon";
+			reg = <0x5f801000 0xe00>;
+		};
+
 		timer@60000200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x60000200 0x20>;
@@ -115,3 +271,5 @@
 		};
 	};
 };
+
+/include/ "uniphier-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi b/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi
new file mode 100644
index 000000000000..59c2b127cffa
--- /dev/null
+++ b/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi
@@ -0,0 +1,252 @@
+/*
+ * Device Tree Source for UniPhier PH1-Pro5 SoC
+ *
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "socionext,ph1-pro5";
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		enable-method = "socionext,uniphier-smp";
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+	};
+
+	clocks {
+		arm_timer_clk: arm_timer_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+
+		uart_clk: uart_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <73728000>;
+		};
+
+		i2c_clk: i2c_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+		interrupt-parent = <&intc>;
+
+		extbus: extbus {
+			compatible = "simple-bus";
+			#address-cells = <2>;
+			#size-cells = <1>;
+		};
+
+		serial0: serial@54006800 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006800 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart0>;
+			interrupts = <0 33 4>;
+			clocks = <&uart_clk>;
+		};
+
+		serial1: serial@54006900 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006900 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart1>;
+			interrupts = <0 35 4>;
+			clocks = <&uart_clk>;
+		};
+
+		serial2: serial@54006a00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006a00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart2>;
+			interrupts = <0 37 4>;
+			clocks = <&uart_clk>;
+		};
+
+		serial3: serial@54006b00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006b00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart3>;
+			interrupts = <0 177 4>;
+			clocks = <&uart_clk>;
+		};
+
+		i2c0: i2c@58780000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58780000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c0>;
+			interrupts = <0 41 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c1: i2c@58781000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58781000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c1>;
+			interrupts = <0 42 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c2: i2c@58782000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58782000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c2>;
+			interrupts = <0 43 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c3: i2c@58783000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58783000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c3>;
+			interrupts = <0 44 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		/* i2c4 does not exist */
+
+		/* chip-internal connection for DMD */
+		i2c5: i2c@58785000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58785000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 25 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
+		/* chip-internal connection for HDMI */
+		i2c6: i2c@58786000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58786000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 26 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
+		system-bus-controller-misc@59800000 {
+			compatible = "socionext,uniphier-system-bus-controller-misc",
+				     "syscon";
+			reg = <0x59800000 0x2000>;
+		};
+
+		pinctrl: pinctrl@5f801000 {
+			compatible = "socionext,ph1-pro5-pinctrl", "syscon";
+			reg = <0x5f801000 0xe00>;
+		};
+
+		timer@60000200 {
+			compatible = "arm,cortex-a9-global-timer";
+			reg = <0x60000200 0x20>;
+			interrupts = <1 11 0x304>;
+			clocks = <&arm_timer_clk>;
+		};
+
+		timer@60000600 {
+			compatible = "arm,cortex-a9-twd-timer";
+			reg = <0x60000600 0x20>;
+			interrupts = <1 13 0x304>;
+			clocks = <&arm_timer_clk>;
+		};
+
+		intc: interrupt-controller@60001000 {
+			compatible = "arm,cortex-a9-gic";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg = <0x60001000 0x1000>,
+			      <0x60000100 0x100>;
+		};
+	};
+};
+
+/include/ "uniphier-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/uniphier-ph1-sld3-ref.dts b/arch/arm/boot/dts/uniphier-ph1-sld3-ref.dts
index 3ea64ae009e9..1a440f87fa92 100644
--- a/arch/arm/boot/dts/uniphier-ph1-sld3-ref.dts
+++ b/arch/arm/boot/dts/uniphier-ph1-sld3-ref.dts
@@ -44,6 +44,7 @@
 
 /dts-v1/;
 /include/ "uniphier-ph1-sld3.dtsi"
+/include/ "uniphier-ref-daughter.dtsi"
 /include/ "uniphier-support-card.dtsi"
 
 / {
@@ -58,11 +59,18 @@
 
 	chosen {
 		bootargs = "console=ttyS0,115200";
-		stdout-path = &serialsc;
+		stdout-path = &serial0;
 	};
 
 	aliases {
-		serial0 = &serialsc;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
 	};
 };
 
@@ -75,6 +83,38 @@
 	ranges = <0x00000000 1 0x03f00000 0x00100000>;
 };
 
-&serialsc {
+&ethsc {
 	interrupts = <0 49 4>;
 };
+
+&serial0 {
+	status = "okay";
+};
+
+&serial1 {
+	status = "okay";
+};
+
+&serial2 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&usb0 {
+	status = "okay";
+};
+
+&usb1 {
+	status = "okay";
+};
+
+&usb2 {
+	status = "okay";
+};
+
+&usb3 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/uniphier-ph1-sld3.dtsi b/arch/arm/boot/dts/uniphier-ph1-sld3.dtsi
index 248b1886834f..3cc90cd37a26 100644
--- a/arch/arm/boot/dts/uniphier-ph1-sld3.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-sld3.dtsi
@@ -71,6 +71,18 @@
 			compatible = "fixed-clock";
 			clock-frequency = <50000000>;
 		};
+
+		uart_clk: uart_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <36864000>;
+		};
+
+		iobus_clk: iobus_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <100000000>;
+		};
 	};
 
 	soc {
@@ -108,10 +120,120 @@
 			      <0x20000100 0x100>;
 		};
 
+		serial0: serial@54006800 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006800 0x40>;
+			interrupts = <0 33 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial1: serial@54006900 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006900 0x40>;
+			interrupts = <0 35 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial2: serial@54006a00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006a00 0x40>;
+			interrupts = <0 37 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		i2c0: i2c@58400000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58400000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 41 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c1: i2c@58480000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58480000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 42 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c2: i2c@58500000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58500000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 43 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c3: i2c@58580000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58580000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 44 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		/* chip-internal connection for DMD */
+		i2c4: i2c@58600000 {
+			compatible = "socionext,uniphier-i2c";
+			reg = <0x58600000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 45 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <400000>;
+		};
+
 		system-bus-controller-misc@59800000 {
 			compatible = "socionext,uniphier-system-bus-controller-misc",
 				     "syscon";
 			reg = <0x59800000 0x2000>;
 		};
+
+		usb0: usb@5a800100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a800100 0x100>;
+			interrupts = <0 80 4>;
+		};
+
+		usb1: usb@5a810100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a810100 0x100>;
+			interrupts = <0 81 4>;
+		};
+
+		usb2: usb@5a820100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a820100 0x100>;
+			interrupts = <0 82 4>;
+		};
+
+		usb3: usb@5a830100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a830100 0x100>;
+			interrupts = <0 83 4>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-ph1-sld8-ref.dts b/arch/arm/boot/dts/uniphier-ph1-sld8-ref.dts
index dcdc4f74387d..955d417a5c42 100644
--- a/arch/arm/boot/dts/uniphier-ph1-sld8-ref.dts
+++ b/arch/arm/boot/dts/uniphier-ph1-sld8-ref.dts
@@ -44,6 +44,7 @@
 
 /dts-v1/;
 /include/ "uniphier-ph1-sld8.dtsi"
+/include/ "uniphier-ref-daughter.dtsi"
 /include/ "uniphier-support-card.dtsi"
 
 / {
@@ -57,11 +58,18 @@
 
 	chosen {
 		bootargs = "console=ttyS0,115200";
-		stdout-path = &serialsc;
+		stdout-path = &serial0;
 	};
 
 	aliases {
-		serial0 = &serialsc;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
 	};
 };
 
@@ -74,6 +82,34 @@
 	ranges = <0x00000000 1 0x03f00000 0x00100000>;
 };
 
-&serialsc {
+&ethsc {
 	interrupts = <0 48 4>;
 };
+
+&serial0 {
+	status = "okay";
+};
+
+&serial2 {
+	status = "okay";
+};
+
+&serial3 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&usb0 {
+	status = "okay";
+};
+
+&usb1 {
+	status = "okay";
+};
+
+&usb2 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi b/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi
index baa71e1febb8..58067dfc16e5 100644
--- a/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi
@@ -64,6 +64,18 @@
 			compatible = "fixed-clock";
 			clock-frequency = <50000000>;
 		};
+
+		uart_clk: uart_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <80000000>;
+		};
+
+		iobus_clk: iobus_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <100000000>;
+		};
 	};
 
 	soc {
@@ -79,12 +91,141 @@
 			#size-cells = <1>;
 		};
 
+		serial0: serial@54006800 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006800 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart0>;
+			interrupts = <0 33 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial1: serial@54006900 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006900 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart1>;
+			interrupts = <0 35 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial2: serial@54006a00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006a00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart2>;
+			interrupts = <0 37 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		serial3: serial@54006b00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006b00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart3>;
+			interrupts = <0 29 4>;
+			clocks = <&uart_clk>;
+			fifo-size = <64>;
+		};
+
+		i2c0: i2c@58400000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58400000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c0>;
+			interrupts = <0 41 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c1: i2c@58480000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58480000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c1>;
+			interrupts = <0 42 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
+		/* chip-internal connection for DMD */
+		i2c2: i2c@58500000 {
+			compatible = "socionext,uniphier-i2c";
+			reg = <0x58500000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c2>;
+			interrupts = <0 43 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <400000>;
+		};
+
+		i2c3: i2c@58580000 {
+			compatible = "socionext,uniphier-i2c";
+			status = "disabled";
+			reg = <0x58580000 0x40>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c3>;
+			interrupts = <0 44 1>;
+			clocks = <&iobus_clk>;
+			clock-frequency = <100000>;
+		};
+
 		system-bus-controller-misc@59800000 {
 			compatible = "socionext,uniphier-system-bus-controller-misc",
 				     "syscon";
 			reg = <0x59800000 0x2000>;
 		};
 
+		usb0: usb@5a800100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a800100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb0>;
+			interrupts = <0 80 4>;
+		};
+
+		usb1: usb@5a810100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a810100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb1>;
+			interrupts = <0 81 4>;
+		};
+
+		usb2: usb@5a820100 {
+			compatible = "socionext,uniphier-ehci", "generic-ehci";
+			status = "disabled";
+			reg = <0x5a820100 0x100>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb2>;
+			interrupts = <0 82 4>;
+		};
+
+		pinctrl: pinctrl@5f801000 {
+			compatible = "socionext,ph1-sld8-pinctrl",
+				     "syscon";
+			reg = <0x5f801000 0xe00>;
+		};
+
 		timer@60000200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x60000200 0x20>;
@@ -108,3 +249,5 @@
 		};
 	};
 };
+
+/include/ "uniphier-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/uniphier-pinctrl.dtsi b/arch/arm/boot/dts/uniphier-pinctrl.dtsi
new file mode 100644
index 000000000000..f67445f4f10d
--- /dev/null
+++ b/arch/arm/boot/dts/uniphier-pinctrl.dtsi
@@ -0,0 +1,105 @@
+/*
+ * Device Tree Source for UniPhier SoCs default pinctrl settings
+ *
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&pinctrl {
+	pinctrl_i2c0: i2c0_grp {
+		groups = "i2c0";
+		function = "i2c0";
+	};
+
+	pinctrl_i2c1: i2c1_grp {
+		groups = "i2c1";
+		function = "i2c1";
+	};
+
+	pinctrl_i2c2: i2c2_grp {
+		groups = "i2c2";
+		function = "i2c2";
+	};
+
+	pinctrl_i2c3: i2c3_grp {
+		groups = "i2c3";
+		function = "i2c3";
+	};
+
+	pinctrl_uart0: uart0_grp {
+		groups = "uart0";
+		function = "uart0";
+	};
+
+	pinctrl_uart1: uart1_grp {
+		groups = "uart1";
+		function = "uart1";
+	};
+
+	pinctrl_uart2: uart2_grp {
+		groups = "uart2";
+		function = "uart2";
+	};
+
+	pinctrl_uart3: uart3_grp {
+		groups = "uart3";
+		function = "uart3";
+	};
+
+	pinctrl_usb0: usb0_grp {
+		groups = "usb0";
+		function = "usb0";
+	};
+
+	pinctrl_usb1: usb1_grp {
+		groups = "usb1";
+		function = "usb1";
+	};
+
+	pinctrl_usb2: usb2_grp {
+		groups = "usb2";
+		function = "usb2";
+	};
+
+	pinctrl_usb3: usb3_grp {
+		groups = "usb3";
+		function = "usb3";
+	};
+};
diff --git a/arch/arm/boot/dts/uniphier-proxstream2.dtsi b/arch/arm/boot/dts/uniphier-proxstream2.dtsi
new file mode 100644
index 000000000000..4c7b24611012
--- /dev/null
+++ b/arch/arm/boot/dts/uniphier-proxstream2.dtsi
@@ -0,0 +1,273 @@
+/*
+ * Device Tree Source for UniPhier ProXstream2 SoC
+ *
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "socionext,proxstream2";
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		enable-method = "socionext,uniphier-smp";
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <3>;
+		};
+	};
+
+	clocks {
+		arm_timer_clk: arm_timer_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+
+		uart_clk: uart_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <88900000>;
+		};
+
+		i2c_clk: i2c_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+		interrupt-parent = <&intc>;
+
+		extbus: extbus {
+			compatible = "simple-bus";
+			#address-cells = <2>;
+			#size-cells = <1>;
+		};
+
+		serial0: serial@54006800 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006800 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart0>;
+			interrupts = <0 33 4>;
+			clocks = <&uart_clk>;
+		};
+
+		serial1: serial@54006900 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006900 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart1>;
+			interrupts = <0 35 4>;
+			clocks = <&uart_clk>;
+		};
+
+		serial2: serial@54006a00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006a00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart2>;
+			interrupts = <0 37 4>;
+			clocks = <&uart_clk>;
+		};
+
+		serial3: serial@54006b00 {
+			compatible = "socionext,uniphier-uart";
+			status = "disabled";
+			reg = <0x54006b00 0x40>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_uart3>;
+			interrupts = <0 177 4>;
+			clocks = <&uart_clk>;
+		};
+
+		i2c0: i2c@58780000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58780000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c0>;
+			interrupts = <0 41 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c1: i2c@58781000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58781000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c1>;
+			interrupts = <0 42 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c2: i2c@58782000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58782000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c2>;
+			interrupts = <0 43 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		i2c3: i2c@58783000 {
+			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
+			reg = <0x58783000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c3>;
+			interrupts = <0 44 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <100000>;
+		};
+
+		/* chip-internal connection for DMD */
+		i2c4: i2c@58784000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58784000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 45 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
+		/* chip-internal connection for STM */
+		i2c5: i2c@58785000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58785000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 25 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
+		/* chip-internal connection for HDMI */
+		i2c6: i2c@58786000 {
+			compatible = "socionext,uniphier-fi2c";
+			reg = <0x58786000 0x80>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <0 26 4>;
+			clocks = <&i2c_clk>;
+			clock-frequency = <400000>;
+		};
+
+		system-bus-controller-misc@59800000 {
+			compatible = "socionext,uniphier-system-bus-controller-misc",
+				     "syscon";
+			reg = <0x59800000 0x2000>;
+		};
+
+		pinctrl: pinctrl@5f801000 {
+			compatible = "socionext,proxstream2-pinctrl", "syscon";
+			reg = <0x5f801000 0xe00>;
+		};
+
+		timer@60000200 {
+			compatible = "arm,cortex-a9-global-timer";
+			reg = <0x60000200 0x20>;
+			interrupts = <1 11 0xf04>;
+			clocks = <&arm_timer_clk>;
+		};
+
+		timer@60000600 {
+			compatible = "arm,cortex-a9-twd-timer";
+			reg = <0x60000600 0x20>;
+			interrupts = <1 13 0xf04>;
+			clocks = <&arm_timer_clk>;
+		};
+
+		intc: interrupt-controller@60001000 {
+			compatible = "arm,cortex-a9-gic";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg = <0x60001000 0x1000>,
+			      <0x60000100 0x100>;
+		};
+	};
+};
+
+/include/ "uniphier-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/uniphier-ref-daughter.dtsi b/arch/arm/boot/dts/uniphier-ref-daughter.dtsi
new file mode 100644
index 000000000000..3d29d2806cc0
--- /dev/null
+++ b/arch/arm/boot/dts/uniphier-ref-daughter.dtsi
@@ -0,0 +1,50 @@
+/*
+ * Device Tree Source for UniPhier Reference Daughter Board
+ *
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&i2c0 {
+	eeprom {
+		compatible = "microchip,24lc128";
+		reg = <0x50>;
+	};
+};
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index 2efb2058ba49..21b02874bea3 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -101,6 +101,8 @@
 				clock-names = "refclk", "timclk", "apb_pclk";
 				#clock-cells = <1>;
 				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+				assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>;
+				assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>;
 			};
 
 			/* PCI-E I2C bus */
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index cb3090f919a7..e712c0af149b 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -100,6 +100,8 @@
 				clock-names = "refclk", "timclk", "apb_pclk";
 				#clock-cells = <1>;
 				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+				assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>;
+				assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>;
 			};
 
 			/* PCI-E I2C bus */
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 107395c32d82..17f63f7dfd9e 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -150,6 +150,16 @@
 			interface-type = "ace";
 			reg = <0x5000 0x1000>;
 		};
+
+		pmu@9000 {
+			 compatible = "arm,cci-400-pmu,r0";
+			 reg = <0x9000 0x5000>;
+			 interrupts = <0 105 4>,
+				      <0 101 4>,
+				      <0 102 4>,
+				      <0 103 4>,
+				      <0 104 4>;
+		};
 	};
 
 	memory-controller@7ffd0000 {
@@ -187,11 +197,22 @@
 			     <1 10 0xf08>;
 	};
 
-	pmu {
+	pmu_a15 {
 		compatible = "arm,cortex-a15-pmu";
 		interrupts = <0 68 4>,
 			     <0 69 4>;
-		interrupt-affinity = <&cpu0>, <&cpu1>;
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>;
+	};
+
+	pmu_a7 {
+		compatible = "arm,cortex-a7-pmu";
+		interrupts = <0 128 4>,
+			     <0 129 4>,
+			     <0 130 4>;
+		interrupt-affinity = <&cpu2>,
+				     <&cpu3>,
+				     <&cpu4>;
 	};
 
 	oscclk6a: oscclk6a {
diff --git a/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi b/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
index 606753eb72c8..ed65e0f7dfc0 100644
--- a/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
+++ b/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
@@ -9,7 +9,7 @@
 
 / {
 	chosen {
-		bootargs = "console=ttyLP0,115200";
+		stdout-path = "serial0:115200n8";
 	};
 
 	clk16m: clk16m {
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 4aa335166be7..6865137fd114 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -226,7 +226,10 @@
 				interrupts = <53 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_ADC0>;
 				clock-names = "adc";
+				#io-channel-cells = <1>;
 				status = "disabled";
+				fsl,adck-max-frequency = <30000000>, <40000000>,
+							<20000000>;
 			};
 
 			wdoga5: wdog@4003e000 {
@@ -242,7 +245,8 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "fsl,vf610-qspi";
-				reg = <0x40044000 0x1000>;
+				reg = <0x40044000 0x1000>, <0x20000000 0x10000000>;
+				reg-names = "QuadSPI", "QuadSPI-memory";
 				interrupts = <24 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_QSPI0_EN>,
 					<&clks VF610_CLK_QSPI0>;
@@ -347,6 +351,20 @@
 				status = "disabled";
 			};
 
+			i2c1: i2c@40067000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,vf610-i2c";
+				reg = <0x40067000 0x1000>;
+				interrupts = <72 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks VF610_CLK_I2C1>;
+				clock-names = "ipg";
+				dmas = <&edma0 0 52>,
+					<&edma0 0 53>;
+				dma-names = "rx","tx";
+				status = "disabled";
+			};
+
 			clks: ccm@4006b000 {
 				compatible = "fsl,vf610-ccm";
 				reg = <0x4006b000 0x1000>;
@@ -404,14 +422,13 @@
 			};
 
 			snvs0: snvs@400a7000 {
-			    compatible = "fsl,sec-v4.0-mon", "simple-bus";
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0 0x400a7000 0x2000>;
+			    compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x400a7000 0x2000>;
 
-				snvsrtc: snvs-rtc-lp@34 {
+				snvsrtc: snvs-rtc-lp {
 					compatible = "fsl,sec-v4.0-mon-rtc-lp";
-					reg = <0x34 0x58>;
+					regmap = <&snvs0>;
+					offset = <0x34>;
 					interrupts = <100 IRQ_TYPE_LEVEL_HIGH>;
 					clocks = <&clks VF610_CLK_SNVS>;
 					clock-names = "snvs-rtc";
@@ -442,9 +459,23 @@
 				interrupts = <54 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_ADC1>;
 				clock-names = "adc";
+				#io-channel-cells = <1>;
 				status = "disabled";
 			};
 
+			esdhc0: esdhc@400b1000 {
+				compatible = "fsl,imx53-esdhc";
+				reg = <0x400b1000 0x1000>;
+				interrupts = <27 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks VF610_CLK_IPG_BUS>,
+					<&clks VF610_CLK_PLATFORM_BUS>,
+					<&clks VF610_CLK_ESDHC0>;
+				clock-names = "ipg", "ahb", "per";
+				status = "disabled";
+				fsl,adck-max-frequency = <30000000>, <40000000>,
+							<20000000>;
+			};
+
 			esdhc1: esdhc@400b2000 {
 				compatible = "fsl,imx53-esdhc";
 				reg = <0x400b2000 0x1000>;
@@ -488,6 +519,19 @@
 				status = "disabled";
 			};
 
+			qspi1: quadspi@400c4000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,vf610-qspi";
+				reg = <0x400c4000 0x1000>, <0x50000000 0x10000000>;
+				reg-names = "QuadSPI", "QuadSPI-memory";
+				interrupts = <25 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks VF610_CLK_QSPI1_EN>,
+					<&clks VF610_CLK_QSPI1>;
+				clock-names = "qspi_en", "qspi";
+				status = "disabled";
+			};
+
 			fec0: ethernet@400d0000 {
 				compatible = "fsl,mvf600-fec";
 				reg = <0x400d0000 0x1000>;
@@ -520,6 +564,33 @@
 				status = "disabled";
 			};
 
+			i2c2: i2c@400e6000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,vf610-i2c";
+				reg = <0x400e6000 0x1000>;
+				interrupts = <73 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks VF610_CLK_I2C2>;
+				clock-names = "ipg";
+				dmas = <&edma0 1 36>,
+					<&edma0 1 37>;
+				dma-names = "rx","tx";
+				status = "disabled";
+			};
+
+			i2c3: i2c@400e7000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,vf610-i2c";
+				reg = <0x400e7000 0x1000>;
+				interrupts = <74 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks VF610_CLK_I2C3>;
+				clock-names = "ipg";
+				dmas = <&edma0 1 38>,
+					<&edma0 1 39>;
+				dma-names = "rx","tx";
+				status = "disabled";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index 06915080b875..dc0457e40775 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -57,7 +57,7 @@
 		regulator-always-on;
 	};
 
-	amba {
+	amba: amba {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -139,6 +139,7 @@
 		L2: cache-controller@f8f02000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xF8F02000 0x1000>;
+			interrupts = <0 2 4>;
 			arm,data-latency = <3 2 2>;
 			arm,tag-latency = <2 2 2>;
 			cache-unified;
@@ -258,6 +259,13 @@
 				reg = <0x100 0x100>;
 			};
 
+			rstc: rstc@200 {
+				compatible = "xlnx,zynq-reset";
+				reg = <0x200 0x48>;
+				#reset-cells = <1>;
+				syscon = <&slcr>;
+			};
+
 			pinctrl0: pinctrl@700 {
 				compatible = "xlnx,pinctrl-zynq";
 				reg = <0x700 0x200>;
diff --git a/arch/arm/boot/dts/zynq-zc702.dts b/arch/arm/boot/dts/zynq-zc702.dts
index fb59d34e8ee6..5df8f81f4217 100644
--- a/arch/arm/boot/dts/zynq-zc702.dts
+++ b/arch/arm/boot/dts/zynq-zc702.dts
@@ -34,6 +34,27 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	gpio-keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		autorepeat;
+		sw14 {
+			label = "sw14";
+			gpios = <&gpio0 12 0>;
+			linux,code = <108>; /* down */
+			gpio-key,wakeup;
+			autorepeat;
+		};
+		sw13 {
+			label = "sw13";
+			gpios = <&gpio0 14 0>;
+			linux,code = <103>; /* up */
+			gpio-key,wakeup;
+			autorepeat;
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 
@@ -50,6 +71,13 @@
 	};
 };
 
+&amba {
+	ocm: sram@fffc0000 {
+		compatible = "mmio-sram";
+		reg = <0xfffc0000 0x10000>;
+	};
+};
+
 &can0 {
 	status = "okay";
 	pinctrl-names = "default";
diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c
index 5114b68e99d5..96dabcb6c621 100644
--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@@ -91,7 +91,7 @@ void it8152_init_irq(void)
 	for (irq = IT8152_IRQ(0); irq <= IT8152_LAST_IRQ; irq++) {
 		irq_set_chip_and_handler(irq, &it8152_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 }
 
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index b55c3625d7ee..304adea4bc52 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -138,9 +138,9 @@ static struct locomo_dev_info locomo_devices[] = {
 	},
 };
 
-static void locomo_handler(unsigned int irq, struct irq_desc *desc)
+static void locomo_handler(unsigned int __irq, struct irq_desc *desc)
 {
-	struct locomo *lchip = irq_get_chip_data(irq);
+	struct locomo *lchip = irq_desc_get_chip_data(desc);
 	int req, i;
 
 	/* Acknowledge the parent IRQ */
@@ -150,6 +150,8 @@ static void locomo_handler(unsigned int irq, struct irq_desc *desc)
 	req = locomo_readl(lchip->base + LOCOMO_ICR) & 0x0f00;
 
 	if (req) {
+		unsigned int irq;
+
 		/* generate the next interrupt(s) */
 		irq = lchip->irq_base;
 		for (i = 0; i <= 3; i++, irq++) {
@@ -205,7 +207,7 @@ static void locomo_setup_irq(struct locomo *lchip)
 	for ( ; irq <= lchip->irq_base + 3; irq++) {
 		irq_set_chip_and_handler(irq, &locomo_chip, handle_level_irq);
 		irq_set_chip_data(irq, lchip);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 }
 
@@ -475,8 +477,7 @@ static void __locomo_remove(struct locomo *lchip)
 	device_for_each_child(lchip->dev, NULL, locomo_remove_child);
 
 	if (lchip->irq != NO_IRQ) {
-		irq_set_chained_handler(lchip->irq, NULL);
-		irq_set_handler_data(lchip->irq, NULL);
+		irq_set_chained_handler_and_data(lchip->irq, NULL, NULL);
 	}
 
 	iounmap(lchip->base);
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 92e54d7c6f46..2b25b6038f66 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -65,14 +65,10 @@ static int mcpm_cpu_kill(unsigned int cpu)
 	return !mcpm_wait_for_cpu_powerdown(pcpu, pcluster);
 }
 
-static int mcpm_cpu_disable(unsigned int cpu)
+static bool mcpm_cpu_can_disable(unsigned int cpu)
 {
-	/*
-	 * We assume all CPUs may be shut down.
-	 * This would be the hook to use for eventual Secure
-	 * OS migration requests as described in the PSCI spec.
-	 */
-	return 0;
+	/* We assume all CPUs may be shut down. */
+	return true;
 }
 
 static void mcpm_cpu_die(unsigned int cpu)
@@ -92,7 +88,7 @@ static struct smp_operations __initdata mcpm_smp_ops = {
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_kill		= mcpm_cpu_kill,
-	.cpu_disable		= mcpm_cpu_disable,
+	.cpu_can_disable	= mcpm_cpu_can_disable,
 	.cpu_die		= mcpm_cpu_die,
 #endif
 };
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 93ee70dbbdd3..4f290250fa93 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -197,10 +197,11 @@ static struct sa1111_dev_info sa1111_devices[] = {
  * will call us again if there are more interrupts to process.
  */
 static void
-sa1111_irq_handler(unsigned int irq, struct irq_desc *desc)
+sa1111_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned int stat0, stat1, i;
-	struct sa1111 *sachip = irq_get_handler_data(irq);
+	struct sa1111 *sachip = irq_desc_get_handler_data(desc);
 	void __iomem *mapbase = sachip->base + SA1111_INTC;
 
 	stat0 = sa1111_readl(mapbase + SA1111_INTSTATCLR0);
@@ -486,7 +487,7 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 		irq_set_chip_and_handler(irq, &sa1111_low_chip,
 					 handle_edge_irq);
 		irq_set_chip_data(irq, sachip);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	for (i = AUDXMTDMADONEA; i <= IRQ_S1_BVD1_STSCHG; i++) {
@@ -494,7 +495,7 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 		irq_set_chip_and_handler(irq, &sa1111_high_chip,
 					 handle_edge_irq);
 		irq_set_chip_data(irq, sachip);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	/*
diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig
deleted file mode 100644
index 5666e3700a82..000000000000
--- a/arch/arm/configs/armadillo800eva_defconfig
+++ /dev/null
@@ -1,162 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_PID_NS is not set
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_PERF_EVENTS=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_SHMOBILE_LEGACY=y
-CONFIG_ARCH_R8A7740=y
-CONFIG_MACH_ARMADILLO800EVA=y
-# CONFIG_SH_TIMER_TMU is not set
-CONFIG_ARM_THUMB=y
-CONFIG_CACHE_L2X0=y
-CONFIG_ARM_ERRATA_430973=y
-CONFIG_ARM_ERRATA_458693=y
-CONFIG_ARM_ERRATA_460075=y
-CONFIG_PL310_ERRATA_588369=y
-CONFIG_ARM_ERRATA_720789=y
-CONFIG_PL310_ERRATA_727915=y
-CONFIG_ARM_ERRATA_743622=y
-CONFIG_ARM_ERRATA_751472=y
-CONFIG_PL310_ERRATA_753970=y
-CONFIG_ARM_ERRATA_754322=y
-CONFIG_PL310_ERRATA_769419=y
-CONFIG_ARM_ERRATA_775420=y
-CONFIG_AEABI=y
-# CONFIG_OABI_COMPAT is not set
-CONFIG_FORCE_MAX_ZONEORDER=13
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_ARM_APPENDED_DTB=y
-CONFIG_KEXEC=y
-CONFIG_VFP=y
-CONFIG_NEON=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_MD=y
-CONFIG_BLK_DEV_DM=y
-CONFIG_NETDEVICES=y
-# CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
-# CONFIG_NET_VENDOR_CIRRUS is not set
-# CONFIG_NET_VENDOR_FARADAY is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MARVELL is not set
-# CONFIG_NET_VENDOR_MICREL is not set
-# CONFIG_NET_VENDOR_NATSEMI is not set
-CONFIG_SH_ETH=y
-# CONFIG_NET_VENDOR_SEEQ is not set
-# CONFIG_NET_VENDOR_SMSC is not set
-# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_WLAN is not set
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=y
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ST1232=y
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=9
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_GPIO=y
-CONFIG_I2C_SH_MOBILE=y
-# CONFIG_HWMON is not set
-CONFIG_REGULATOR=y
-CONFIG_REGULATOR_GPIO=y
-CONFIG_MEDIA_SUPPORT=y
-CONFIG_VIDEO_DEV=y
-CONFIG_MEDIA_CAMERA_SUPPORT=y
-CONFIG_V4L_PLATFORM_DRIVERS=y
-CONFIG_SOC_CAMERA=y
-CONFIG_SOC_CAMERA_MT9T112=y
-CONFIG_VIDEO_SH_MOBILE_CEU=y
-CONFIG_FB=y
-CONFIG_FB_SH_MOBILE_LCDC=y
-CONFIG_FB_SH_MOBILE_HDMI=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_PWM=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-# CONFIG_SND_DRIVERS is not set
-# CONFIG_SND_ARM is not set
-CONFIG_SND_SOC_SH4_FSI=y
-# CONFIG_HID_SUPPORT is not set
-CONFIG_USB=y
-CONFIG_USB_RENESAS_USBHS=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_RENESAS_USBHS_UDC=y
-CONFIG_USB_ETH=m
-CONFIG_MMC=y
-CONFIG_MMC_SDHI=y
-CONFIG_MMC_SH_MMCIF=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_S35390A=y
-CONFIG_DMADEVICES=y
-CONFIG_SH_DMAE=y
-CONFIG_UIO=y
-CONFIG_UIO_PDRV_GENIRQ=y
-CONFIG_PWM=y
-CONFIG_PWM_RENESAS_TPU=y
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-# CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFS_V4_1=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_ARM_UNWIND is not set
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
-CONFIG_CRYPTO_ANSI_CPRNG=y
-CONFIG_XZ_DEC=y
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index 94b5dcabdecc..090c5b25dbed 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -73,7 +73,6 @@ CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
-CONFIG_ARM_AT91_ETHER=y
 CONFIG_MACB=y
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_DM9000=y
@@ -131,8 +130,18 @@ CONFIG_POWER_RESET=y
 CONFIG_WATCHDOG=y
 CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_SSB=m
+CONFIG_MFD_ATMEL_HLCDC=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_SOC_CAMERA=y
+CONFIG_VIDEO_ATMEL_ISI=y
+CONFIG_SOC_CAMERA_OV2640=m
+CONFIG_DRM=y
+CONFIG_DRM_ATMEL_HLCDC=y
+CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_FB=y
 CONFIG_FB_ATMEL=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
@@ -140,6 +149,7 @@ CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_ATMEL_LCDC=y
 # CONFIG_BACKLIGHT_GENERIC is not set
+CONFIG_BACKLIGHT_PWM=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
@@ -186,6 +196,7 @@ CONFIG_IIO=y
 CONFIG_AT91_ADC=y
 CONFIG_PWM=y
 CONFIG_PWM_ATMEL=y
+CONFIG_PWM_ATMEL_HLCDC_PWM=y
 CONFIG_PWM_ATMEL_TCB=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig
index 72233b9c9d07..a7846d64b396 100644
--- a/arch/arm/configs/ep93xx_defconfig
+++ b/arch/arm/configs/ep93xx_defconfig
@@ -1,4 +1,6 @@
 CONFIG_SYSVIPC=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -15,19 +17,25 @@ CONFIG_CRUNCH=y
 CONFIG_MACH_ADSSPHERE=y
 CONFIG_MACH_EDB9301=y
 CONFIG_MACH_EDB9302=y
+CONFIG_MACH_EDB9302A=y
 CONFIG_MACH_EDB9307=y
+CONFIG_MACH_EDB9307A=y
 CONFIG_MACH_EDB9312=y
 CONFIG_MACH_EDB9315=y
+CONFIG_MACH_EDB9315A=y
 CONFIG_MACH_GESBC9312=y
 CONFIG_MACH_MICRO9H=y
+CONFIG_MACH_MICRO9M=y
 CONFIG_MACH_MICRO9L=y
+CONFIG_MACH_MICRO9S=y
+CONFIG_MACH_SIM_ONE=y
+CONFIG_MACH_SNAPPER_CL15=y
 CONFIG_MACH_TS72XX=y
+CONFIG_MACH_VISION_EP9307=y
 CONFIG_AEABI=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="console=ttyAM0,115200 root=/dev/nfs ip=bootp"
-CONFIG_FPE_NWFPE=y
-CONFIG_FPE_NWFPE_XP=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -74,11 +82,18 @@ CONFIG_SERIAL_AMBA_PL010_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_GPIO=y
 CONFIG_I2C_DEBUG_CORE=y
 CONFIG_I2C_DEBUG_ALGO=y
 CONFIG_I2C_DEBUG_BUS=y
+CONFIG_SPI=y
+CONFIG_SPI_EP93XX=y
 CONFIG_WATCHDOG=y
 CONFIG_EP93XX_WATCHDOG=y
+CONFIG_FB=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_EP93XX=y
+CONFIG_LOGO=y
 CONFIG_USB=y
 CONFIG_USB_DYNAMIC_MINORS=y
 CONFIG_USB_OHCI_HCD=y
@@ -87,13 +102,23 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_SERIAL=y
 CONFIG_USB_SERIAL_CONSOLE=y
 CONFIG_USB_SERIAL_PL2303=y
+CONFIG_MMC=y
+CONFIG_MMC_SPI=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_M48T86=y
 CONFIG_RTC_DRV_EP93XX=y
+CONFIG_DMADEVICES=y
+CONFIG_EP93XX_DMA=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 9504e7790288..3eaf8fbaf603 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -124,14 +124,14 @@ CONFIG_REGULATOR_S2MPS11=y
 CONFIG_REGULATOR_S5M8767=y
 CONFIG_REGULATOR_TPS65090=y
 CONFIG_DRM=y
-CONFIG_DRM_PTN3460=y
-CONFIG_DRM_PS8622=y
+CONFIG_DRM_NXP_PTN3460=y
+CONFIG_DRM_PARADE_PS8622=y
 CONFIG_DRM_EXYNOS=y
 CONFIG_DRM_EXYNOS_FIMD=y
 CONFIG_DRM_EXYNOS_DSI=y
 CONFIG_DRM_EXYNOS_HDMI=y
 CONFIG_DRM_PANEL_SIMPLE=y
-CONFIG_DRM_PANEL_S6E8AA0=y
+CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=y
 CONFIG_FB_SIMPLE=y
 CONFIG_EXYNOS_VIDEO=y
 CONFIG_EXYNOS_MIPI_DSI=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index b47863d49ac6..79194c60c78c 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -3,6 +3,8 @@ CONFIG_SYSVIPC=y
 CONFIG_FHANDLE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 CONFIG_RELAY=y
@@ -38,9 +40,10 @@ CONFIG_SOC_IMX53=y
 CONFIG_SOC_IMX6Q=y
 CONFIG_SOC_IMX6SL=y
 CONFIG_SOC_IMX6SX=y
+CONFIG_SOC_IMX6UL=y
 CONFIG_SOC_IMX7D=y
-CONFIG_SOC_VF610=y
 CONFIG_SOC_LS1021A=y
+CONFIG_SOC_VF610=y
 CONFIG_PCI=y
 CONFIG_PCI_IMX6=y
 CONFIG_SMP=y
@@ -50,13 +53,13 @@ CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_CMA=y
 CONFIG_CMDLINE="noinitrd console=ttymxc0,115200"
+CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_ARM_IMX6Q_CPUFREQ=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_BINFMT_MISC=m
-CONFIG_PM=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TEST_SUSPEND=y
 CONFIG_NET=y
@@ -75,8 +78,8 @@ CONFIG_CAN=y
 CONFIG_CAN_FLEXCAN=y
 CONFIG_BT=y
 CONFIG_BT_HCIUART=y
+CONFIG_BT_HCIUART_H4=y
 CONFIG_BT_HCIUART_LL=y
-CONFIG_BT_HCIUART_3WIRE=y
 CONFIG_CFG80211=y
 CONFIG_MAC80211=y
 CONFIG_RFKILL=y
@@ -150,6 +153,7 @@ CONFIG_WLCORE_SDIO=m
 CONFIG_INPUT_EVDEV=y
 CONFIG_INPUT_EVBUG=m
 CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_SNVS_PWRKEY=y
 CONFIG_KEYBOARD_IMX=y
 CONFIG_MOUSE_PS2=m
 CONFIG_MOUSE_PS2_ELANTECH=y
@@ -185,6 +189,7 @@ CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_IMX=y
 CONFIG_POWER_RESET_SYSCON=y
+CONFIG_POWER_RESET_SYSCON_POWEROFF=y
 CONFIG_SENSORS_GPIO_FAN=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
@@ -219,10 +224,16 @@ CONFIG_SOC_CAMERA_OV2640=y
 CONFIG_IMX_IPUV3_CORE=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_IMX=y
+CONFIG_DRM_IMX_FB_HELPER=y
+CONFIG_DRM_IMX_PARALLEL_DISPLAY=y
+CONFIG_DRM_IMX_TVE=y
+CONFIG_DRM_IMX_LDB=y
+CONFIG_DRM_IMX_HDMI=y
+CONFIG_FB_MXS=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_L4F00242T03=y
 CONFIG_LCD_PLATFORM=y
-CONFIG_FB_MXS=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_BACKLIGHT_GPIO=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -231,7 +242,7 @@ CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_USB_AUDIO=m
 CONFIG_SND_SOC=y
-CONFIG_SND_SOC_FSL_SAI=y
+CONFIG_SND_SOC_FSL_ASRC=y
 CONFIG_SND_IMX_SOC=y
 CONFIG_SND_SOC_PHYCORE_AC97=y
 CONFIG_SND_SOC_EUKREA_TLV320=y
@@ -239,6 +250,8 @@ CONFIG_SND_SOC_IMX_WM8962=y
 CONFIG_SND_SOC_IMX_SGTL5000=y
 CONFIG_SND_SOC_IMX_SPDIF=y
 CONFIG_SND_SOC_IMX_MC13783=y
+CONFIG_SND_SOC_FSL_ASOC_CARD=y
+CONFIG_SND_SOC_CS42XX8_I2C=y
 CONFIG_SND_SOC_TLV320AIC3X=y
 CONFIG_SND_SIMPLE_CARD=y
 CONFIG_USB=y
@@ -301,13 +314,6 @@ CONFIG_IMX_SDMA=y
 CONFIG_MXS_DMA=y
 CONFIG_FSL_EDMA=y
 CONFIG_STAGING=y
-CONFIG_DRM_IMX=y
-CONFIG_DRM_IMX_FB_HELPER=y
-CONFIG_DRM_IMX_PARALLEL_DISPLAY=y
-CONFIG_DRM_IMX_TVE=y
-CONFIG_DRM_IMX_LDB=y
-CONFIG_DRM_IMX_IPUV3=y
-CONFIG_DRM_IMX_HDMI=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PWM=y
 CONFIG_PWM_IMX=y
@@ -354,8 +360,7 @@ CONFIG_PROVE_LOCKING=y
 # CONFIG_FTRACE is not set
 # CONFIG_ARM_UNWIND is not set
 CONFIG_SECURITYFS=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
 CONFIG_CRC_CCITT=m
 CONFIG_CRC_T10DIF=y
 CONFIG_CRC7=m
diff --git a/arch/arm/configs/kzm9g_defconfig b/arch/arm/configs/kzm9g_defconfig
deleted file mode 100644
index 23e8d146dc16..000000000000
--- a/arch/arm/configs/kzm9g_defconfig
+++ /dev/null
@@ -1,154 +0,0 @@
-# CONFIG_ARM_PATCH_PHYS_VIRT is not set
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_NAMESPACES=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_USER_NS is not set
-# CONFIG_PID_NS is not set
-# CONFIG_NET_NS is not set
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_SYSCTL_SYSCALL=y
-CONFIG_EMBEDDED=y
-CONFIG_PERF_EVENTS=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_FORCE_LOAD=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_SHMOBILE_LEGACY=y
-CONFIG_ARCH_SH73A0=y
-CONFIG_MACH_KZM9G=y
-CONFIG_MEMORY_START=0x41000000
-CONFIG_MEMORY_SIZE=0x1f000000
-CONFIG_ARM_ERRATA_743622=y
-CONFIG_ARM_ERRATA_754322=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_SMP=y
-CONFIG_SCHED_MC=y
-CONFIG_AEABI=y
-# CONFIG_OABI_COMPAT is not set
-CONFIG_HIGHMEM=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_ARM_APPENDED_DTB=y
-CONFIG_KEXEC=y
-CONFIG_VFP=y
-CONFIG_NEON=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-CONFIG_IRDA=y
-CONFIG_SH_IRDA=y
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_NETDEVICES=y
-CONFIG_SMSC911X=y
-# CONFIG_WLAN is not set
-CONFIG_INPUT_SPARSEKMAP=y
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=y
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ST1232=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_ADXL34X=y
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=9
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_SH_MOBILE=y
-CONFIG_GPIO_PCF857X=y
-# CONFIG_HWMON is not set
-CONFIG_MFD_AS3711=y
-CONFIG_REGULATOR=y
-CONFIG_REGULATOR_AS3711=y
-CONFIG_FB=y
-CONFIG_FB_SH_MOBILE_LCDC=y
-CONFIG_BACKLIGHT_AS3711=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-CONFIG_FB_SH_MOBILE_MERAM=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-# CONFIG_SND_DRIVERS is not set
-# CONFIG_SND_ARM is not set
-# CONFIG_SND_USB is not set
-CONFIG_SND_SOC=y
-CONFIG_SND_SOC_SH4_FSI=y
-# CONFIG_HID_SUPPORT is not set
-CONFIG_USB=y
-CONFIG_USB_R8A66597_HCD=y
-CONFIG_USB_RENESAS_USBHS=y
-CONFIG_USB_STORAGE=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_RENESAS_USBHS_UDC=y
-CONFIG_USB_ETH=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_MMC=y
-# CONFIG_MMC_BLOCK_BOUNCE is not set
-CONFIG_MMC_SDHI=y
-CONFIG_MMC_SH_MMCIF=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_RS5C372=y
-CONFIG_DMADEVICES=y
-CONFIG_SH_DMAE=y
-CONFIG_ASYNC_TX_DMA=y
-CONFIG_STAGING=y
-CONFIG_IIO=y
-CONFIG_AK8975=y
-# CONFIG_DNOTIFY is not set
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-# CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFS_V4_1=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_SCHED_DEBUG is not set
-# CONFIG_DEBUG_PREEMPT is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_FTRACE is not set
-# CONFIG_ARM_UNWIND is not set
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
-CONFIG_CRC16=y
diff --git a/arch/arm/configs/marzen_defconfig b/arch/arm/configs/marzen_defconfig
deleted file mode 100644
index 3c8b6d823189..000000000000
--- a/arch/arm/configs/marzen_defconfig
+++ /dev/null
@@ -1,124 +0,0 @@
-# CONFIG_ARM_PATCH_PHYS_VIRT is not set
-CONFIG_EXPERIMENTAL=y
-CONFIG_KERNEL_LZMA=y
-CONFIG_NO_HZ=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_SYSCTL_SYSCALL=y
-CONFIG_EMBEDDED=y
-CONFIG_SLAB=y
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_SHMOBILE_LEGACY=y
-CONFIG_ARCH_R8A7779=y
-CONFIG_MACH_MARZEN=y
-CONFIG_MEMORY_START=0x60000000
-CONFIG_MEMORY_SIZE=0x10000000
-CONFIG_SHMOBILE_TIMER_HZ=1024
-# CONFIG_SH_TIMER_CMT is not set
-# CONFIG_SWP_EMULATE is not set
-CONFIG_ARM_ERRATA_430973=y
-CONFIG_ARM_ERRATA_458693=y
-CONFIG_ARM_ERRATA_460075=y
-CONFIG_ARM_ERRATA_743622=y
-CONFIG_ARM_ERRATA_754322=y
-CONFIG_SMP=y
-# CONFIG_ARM_CPU_TOPOLOGY is not set
-CONFIG_AEABI=y
-# CONFIG_OABI_COMPAT is not set
-CONFIG_HIGHMEM=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_ARM_APPENDED_DTB=y
-CONFIG_VFP=y
-CONFIG_KEXEC=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_ATA=y
-CONFIG_ATA_SFF=y
-CONFIG_ATA_BMDMA=y
-CONFIG_SATA_RCAR=y
-CONFIG_NETDEVICES=y
-# CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_FARADAY is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MICREL is not set
-# CONFIG_NET_VENDOR_NATSEMI is not set
-# CONFIG_NET_VENDOR_SEEQ is not set
-CONFIG_SMSC911X=y
-# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_WLAN is not set
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=6
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_RCAR=y
-CONFIG_SPI=y
-CONFIG_SPI_SH_HSPI=y
-CONFIG_GPIO_SYSFS=y
-CONFIG_GPIO_RCAR=y
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-CONFIG_RCAR_THERMAL=y
-CONFIG_SSB=y
-CONFIG_REGULATOR=y
-CONFIG_MEDIA_SUPPORT=y
-CONFIG_MEDIA_CAMERA_SUPPORT=y
-CONFIG_V4L_PLATFORM_DRIVERS=y
-CONFIG_SOC_CAMERA=y
-CONFIG_VIDEO_RCAR_VIN=y
-# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
-CONFIG_VIDEO_ADV7180=y
-CONFIG_DRM=y
-CONFIG_DRM_RCAR_DU=y
-CONFIG_USB=y
-CONFIG_USB_RCAR_PHY=y
-CONFIG_MMC=y
-CONFIG_MMC_SDHI=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_STORAGE=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_DMADEVICES=y
-CONFIG_RCAR_HPB_DMAE=y
-CONFIG_UIO=y
-CONFIG_UIO_PDRV_GENIRQ=y
-# CONFIG_IOMMU_SUPPORT is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_TMPFS=y
-# CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_REDUCED=y
-# CONFIG_FTRACE is not set
-CONFIG_DEBUG_USER=y
-CONFIG_AVERAGE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 6d83a1bf0c74..f84471d5d2db 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -49,6 +49,8 @@ CONFIG_SOC_IMX53=y
 CONFIG_SOC_IMX6Q=y
 CONFIG_SOC_IMX6SL=y
 CONFIG_SOC_IMX6SX=y
+CONFIG_SOC_IMX6UL=y
+CONFIG_SOC_IMX7D=y
 CONFIG_SOC_VF610=y
 CONFIG_SOC_LS1021A=y
 CONFIG_ARCH_OMAP3=y
@@ -80,6 +82,7 @@ CONFIG_ARCH_R8A7778=y
 CONFIG_ARCH_R8A7779=y
 CONFIG_ARCH_R8A7790=y
 CONFIG_ARCH_R8A7791=y
+CONFIG_ARCH_R8A7793=y
 CONFIG_ARCH_R8A7794=y
 CONFIG_ARCH_SH73A0=y
 CONFIG_MACH_MARZEN=y
@@ -98,6 +101,7 @@ CONFIG_MACH_SNOWBALL=y
 CONFIG_MACH_UX500_DT=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_ARCH_VEXPRESS_TC2_PM=y
 CONFIG_ARCH_WM8850=y
 CONFIG_ARCH_ZYNQ=y
 CONFIG_TRUSTED_FOUNDATIONS=y
@@ -251,6 +255,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_8250_EM=y
 CONFIG_SERIAL_8250_MT6577=y
+CONFIG_SERIAL_8250_UNIPHIER=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_ATMEL=y
@@ -301,6 +306,7 @@ CONFIG_I2C_S3C2410=y
 CONFIG_I2C_SH_MOBILE=y
 CONFIG_I2C_SIRF=y
 CONFIG_I2C_ST=y
+CONFIG_I2C_SUN6I_P2WI=y
 CONFIG_I2C_TEGRA=y
 CONFIG_I2C_XILINX=y
 CONFIG_I2C_RCAR=y
@@ -353,7 +359,6 @@ CONFIG_POWER_RESET_AS3722=y
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_POWER_RESET_KEYSTONE=y
-CONFIG_POWER_RESET_SUN6I=y
 CONFIG_POWER_RESET_RMOBILE=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM95245=y
@@ -371,7 +376,9 @@ CONFIG_ARM_SP805_WATCHDOG=y
 CONFIG_ORION_WATCHDOG=y
 CONFIG_ST_LPC_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
+CONFIG_TEGRA_WATCHDOG=m
 CONFIG_MESON_WATCHDOG=y
+CONFIG_DIGICOLOR_WATCHDOG=y
 CONFIG_MFD_AS3711=y
 CONFIG_MFD_AS3722=y
 CONFIG_MFD_BCM590XX=y
@@ -404,6 +411,7 @@ CONFIG_REGULATOR_MAX8973=y
 CONFIG_REGULATOR_MAX77686=y
 CONFIG_REGULATOR_MAX77693=m
 CONFIG_REGULATOR_PALMAS=y
+CONFIG_REGULATOR_PWM=m
 CONFIG_REGULATOR_S2MPS11=y
 CONFIG_REGULATOR_S5M8767=y
 CONFIG_REGULATOR_TPS51632=y
@@ -430,15 +438,18 @@ CONFIG_VIDEO_RENESAS_VSP1=m
 CONFIG_VIDEO_ADV7180=m
 CONFIG_VIDEO_ML86V7667=m
 CONFIG_DRM=y
-CONFIG_DRM_PTN3460=m
-CONFIG_DRM_PS8622=m
+# CONFIG_DRM_I2C_CH7006 is not set
+# CONFIG_DRM_I2C_SIL164 is not set
+CONFIG_DRM_NXP_PTN3460=m
+CONFIG_DRM_PARADE_PS8622=m
+CONFIG_DRM_NOUVEAU=m
 CONFIG_DRM_EXYNOS=m
 CONFIG_DRM_EXYNOS_DSI=y
 CONFIG_DRM_EXYNOS_FIMD=y
 CONFIG_DRM_EXYNOS_HDMI=y
 CONFIG_DRM_RCAR_DU=m
 CONFIG_DRM_TEGRA=y
-CONFIG_DRM_PANEL_S6E8AA0=m
+CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_FB_ARMCLCD=y
 CONFIG_FB_WM8505=y
@@ -455,12 +466,18 @@ CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_SOUND=m
 CONFIG_SND=m
 CONFIG_SND_DYNAMIC_MINORS=y
+CONFIG_SND_HDA_TEGRA=m
+CONFIG_SND_HDA_INPUT_BEEP=y
+CONFIG_SND_HDA_PATCH_LOADER=y
+CONFIG_SND_HDA_CODEC_REALTEK=m
+CONFIG_SND_HDA_CODEC_HDMI=m
 CONFIG_SND_USB_AUDIO=y
 CONFIG_SND_SOC=m
 CONFIG_SND_ATMEL_SOC=m
 CONFIG_SND_ATMEL_SOC_WM8904=m
 CONFIG_SND_SOC_SH4_FSI=m
 CONFIG_SND_SOC_RCAR=m
+CONFIG_SND_SOC_RSRC_CARD=m
 CONFIG_SND_SOC_TEGRA=m
 CONFIG_SND_SOC_TEGRA_RT5640=m
 CONFIG_SND_SOC_TEGRA_WM8753=m
@@ -588,6 +605,7 @@ CONFIG_IMX_DMA=y
 CONFIG_MXS_DMA=y
 CONFIG_DMA_OMAP=y
 CONFIG_XILINX_VDMA=y
+CONFIG_DMA_SUN6I=y
 CONFIG_STAGING=y
 CONFIG_SENSORS_ISL29018=y
 CONFIG_SENSORS_ISL29028=y
@@ -613,6 +631,7 @@ CONFIG_TEGRA_IOMMU_SMMU=y
 CONFIG_PM_DEVFREQ=y
 CONFIG_ARM_TEGRA_DEVFREQ=m
 CONFIG_MEMORY=y
+CONFIG_EXTCON=y
 CONFIG_TI_AEMIF=y
 CONFIG_IIO=y
 CONFIG_AT91_ADC=m
@@ -623,9 +642,11 @@ CONFIG_PWM_ATMEL=m
 CONFIG_PWM_ATMEL_TCB=m
 CONFIG_PWM_RENESAS_TPU=y
 CONFIG_PWM_SAMSUNG=m
+CONFIG_PWM_SUN4I=y
 CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
 CONFIG_PHY_HIX5HD2_SATA=y
+CONFIG_PWM_STI=m
 CONFIG_OMAP_USB2=y
 CONFIG_TI_PIPE3=y
 CONFIG_PHY_MIPHY28LP=y
@@ -661,6 +682,7 @@ CONFIG_LOCKUP_DETECTOR=y
 CONFIG_CRYPTO_DEV_TEGRA_AES=y
 CONFIG_CPUFREQ_DT=y
 CONFIG_KEYSTONE_IRQ=y
+CONFIG_CRYPTO_DEV_SUN4I_SS=m
 CONFIG_ARM_CRYPTO=y
 CONFIG_CRYPTO_SHA1_ARM=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
diff --git a/arch/arm/configs/mvebu_v7_defconfig b/arch/arm/configs/mvebu_v7_defconfig
index cacc9f4055a7..13fcd020e375 100644
--- a/arch/arm/configs/mvebu_v7_defconfig
+++ b/arch/arm/configs/mvebu_v7_defconfig
@@ -58,6 +58,7 @@ CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_PXA3xx=y
 CONFIG_MTD_SPI_NOR=y
+CONFIG_EEPROM_AT24=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_AHCI_MVEBU=y
@@ -83,11 +84,14 @@ CONFIG_I2C_MV64XXX=y
 CONFIG_SPI=y
 CONFIG_SPI_ORION=y
 CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_PCA953X=y
 CONFIG_SENSORS_GPIO_FAN=y
 CONFIG_THERMAL=y
 CONFIG_ARMADA_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_ORION_WATCHDOG=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_SOC=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index ac521e764d10..50c84e1876fc 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -136,6 +136,8 @@ CONFIG_MTD_ONENAND=y
 CONFIG_MTD_ONENAND_VERIFY_WRITE=y
 CONFIG_MTD_ONENAND_OMAP2=y
 CONFIG_MTD_UBI=y
+CONFIG_MTD_SPI_NOR=m
+CONFIG_MTD_M25P80=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=16384
@@ -169,6 +171,7 @@ CONFIG_SMSC911X=y
 # CONFIG_NET_VENDOR_STMICRO is not set
 CONFIG_TI_DAVINCI_EMAC=y
 CONFIG_TI_CPSW=y
+CONFIG_TI_CPTS=y
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_AT803X_PHY=y
@@ -208,6 +211,7 @@ CONFIG_TOUCHSCREEN_EDT_FT5X06=m
 CONFIG_TOUCHSCREEN_PIXCIR=m
 CONFIG_TOUCHSCREEN_TSC2005=m
 CONFIG_TOUCHSCREEN_TSC2007=m
+CONFIG_TOUCHSCREEN_TI_AM335X_TSC=m
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_TPS65218_PWRBUTTON=m
 CONFIG_INPUT_TWL4030_PWRBUTTON=m
@@ -269,6 +273,7 @@ CONFIG_MFD_PALMAS=y
 CONFIG_MFD_TPS65217=y
 CONFIG_MFD_TPS65218=y
 CONFIG_MFD_TPS65910=y
+CONFIG_MFD_TI_AM335X_TSCADC=m
 CONFIG_TWL6040_CORE=y
 CONFIG_REGULATOR_PALMAS=y
 CONFIG_REGULATOR_PBIAS=y
@@ -324,10 +329,13 @@ CONFIG_SND_USB_AUDIO=m
 CONFIG_SND_SOC=m
 CONFIG_SND_EDMA_SOC=m
 CONFIG_SND_AM33XX_SOC_EVM=m
+CONFIG_SND_DAVINCI_SOC_MCASP=m
 CONFIG_SND_OMAP_SOC=m
 CONFIG_SND_OMAP_SOC_OMAP_TWL4030=m
 CONFIG_SND_OMAP_SOC_OMAP_ABE_TWL6040=m
 CONFIG_SND_OMAP_SOC_OMAP3_PANDORA=m
+CONFIG_SND_SIMPLE_CARD=m
+CONFIG_SND_SOC_TLV320AIC3X=m
 CONFIG_HID_GENERIC=m
 CONFIG_USB_HIDDEV=y
 CONFIG_USB_KBD=m
@@ -398,6 +406,8 @@ CONFIG_EXTCON=m
 CONFIG_EXTCON_USB_GPIO=m
 CONFIG_EXTCON_PALMAS=m
 CONFIG_TI_EMIF=m
+CONFIG_IIO=m
+CONFIG_TI_AM335X_ADC=m
 CONFIG_PWM=y
 CONFIG_PWM_TIECAP=m
 CONFIG_PWM_TIEHRPWM=m
diff --git a/arch/arm/configs/orion5x_defconfig b/arch/arm/configs/orion5x_defconfig
index 855143fac6bd..8099417a9466 100644
--- a/arch/arm/configs/orion5x_defconfig
+++ b/arch/arm/configs/orion5x_defconfig
@@ -14,8 +14,10 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_ARCH_ORION5X=y
+CONFIG_ARCH_ORION5X_DT=y
 CONFIG_MACH_DB88F5281=y
 CONFIG_MACH_RD88F5182=y
+CONFIG_MACH_RD88F5182_DT=y
 CONFIG_MACH_KUROBOX_PRO=y
 CONFIG_MACH_DNS323=y
 CONFIG_MACH_TS209=y
@@ -41,6 +43,7 @@ CONFIG_AEABI=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_FPE_NWFPE=y
 CONFIG_VFP=y
 CONFIG_NET=y
diff --git a/arch/arm/configs/prima2_defconfig b/arch/arm/configs/prima2_defconfig
index f610230b9c1f..7cc8e8e4d296 100644
--- a/arch/arm/configs/prima2_defconfig
+++ b/arch/arm/configs/prima2_defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_RELAY=y
@@ -11,14 +10,12 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_SOLARIS_X86_PARTITION=y
 CONFIG_ARCH_SIRF=y
-# CONFIG_SWP_EMULATE is not set
 CONFIG_SMP=y
 CONFIG_SCHED_MC=y
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
 CONFIG_KEXEC=y
 CONFIG_BINFMT_MISC=y
-CONFIG_PM=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
@@ -29,6 +26,7 @@ CONFIG_CHR_DEV_SG=y
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_INPUT_MISC=y
 CONFIG_SERIAL_SIRFSOC=y
 CONFIG_SERIAL_SIRFSOC_CONSOLE=y
 CONFIG_HW_RANDOM=y
@@ -45,10 +43,14 @@ CONFIG_USB_MASS_STORAGE=m
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_SDHCI_SIRF=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_SIRFSOC=y
 CONFIG_DMADEVICES=y
 CONFIG_DMADEVICES_DEBUG=y
 CONFIG_DMADEVICES_VDEBUG=y
 CONFIG_SIRF_DMA=y
+CONFIG_HWSPINLOCK_SIRF=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_MSDOS_FS=y
@@ -60,12 +62,12 @@ CONFIG_ROMFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_PREEMPT is not set
 CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_INFO=y
 CONFIG_CRC_CCITT=y
diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig
index e6a6f282e3de..ff7985ba226e 100644
--- a/arch/arm/configs/qcom_defconfig
+++ b/arch/arm/configs/qcom_defconfig
@@ -67,6 +67,7 @@ CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
+CONFIG_KS8851=y
 CONFIG_MDIO_BITBANG=y
 CONFIG_MDIO_GPIO=y
 CONFIG_SLIP=y
@@ -104,8 +105,10 @@ CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_MSM=y
 CONFIG_THERMAL=y
+CONFIG_MFD_QCOM_RPM=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_QCOM_RPM=y
 CONFIG_MEDIA_SUPPORT=y
 CONFIG_FB=y
 CONFIG_SOUND=y
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index 9961fbd633f8..89bf31ccfbfa 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -18,6 +18,7 @@ CONFIG_ARCH_R8A7778=y
 CONFIG_ARCH_R8A7779=y
 CONFIG_ARCH_R8A7790=y
 CONFIG_ARCH_R8A7791=y
+CONFIG_ARCH_R8A7793=y
 CONFIG_ARCH_R8A7794=y
 CONFIG_ARCH_SH73A0=y
 CONFIG_MACH_MARZEN=y
@@ -121,6 +122,7 @@ CONFIG_WATCHDOG=y
 CONFIG_DA9063_WATCHDOG=y
 CONFIG_MFD_AS3711=y
 CONFIG_MFD_DA9063=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_AS3711=y
 CONFIG_REGULATOR_DA9210=y
 CONFIG_REGULATOR_GPIO=y
@@ -151,6 +153,7 @@ CONFIG_SND=y
 CONFIG_SND_SOC=y
 CONFIG_SND_SOC_SH4_FSI=y
 CONFIG_SND_SOC_RCAR=y
+CONFIG_SND_SOC_RSRC_CARD=y
 CONFIG_SND_SOC_AK4642=y
 CONFIG_SND_SOC_WM8978=y
 CONFIG_USB=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 8ecba00dcd83..51eea220baae 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -1,7 +1,10 @@
+CONFIG_FHANDLE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_PERF_EVENTS=y
+CONFIG_MODULES=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
@@ -71,13 +74,12 @@ CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MV64XXX=y
+CONFIG_I2C_SUN6I_P2WI=y
 CONFIG_SPI=y
 CONFIG_SPI_SUN4I=y
 CONFIG_SPI_SUN6I=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_SUPPLY=y
-CONFIG_POWER_RESET=y
-CONFIG_POWER_RESET_SUN6I=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
 CONFIG_WATCHDOG=y
@@ -87,6 +89,10 @@ CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_AXP20X=y
 CONFIG_REGULATOR_GPIO=y
+CONFIG_FB=y
+CONFIG_FB_SIMPLE=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
@@ -105,7 +111,12 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_INTF_PROC is not set
 CONFIG_RTC_DRV_SUN6I=y
 CONFIG_RTC_DRV_SUNXI=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_SUN6I=y
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXTCON=y
+CONFIG_PWM=y
+CONFIG_PWM_SUN4I=y
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_SUN9I_USB=y
 CONFIG_EXT4_FS=y
@@ -119,3 +130,4 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_FS=y
+CONFIG_CRYPTO_DEV_SUN4I_SS=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index cdf9abb46015..9808581176cc 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -42,6 +42,7 @@ CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT_DETAILS=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPUFREQ_DT=y
 CONFIG_CPU_IDLE=y
 CONFIG_VFP=y
 CONFIG_NEON=y
@@ -146,7 +147,6 @@ CONFIG_GPIO_PCA953X_IRQ=y
 CONFIG_GPIO_PALMAS=y
 CONFIG_GPIO_TPS6586X=y
 CONFIG_GPIO_TPS65910=y
-CONFIG_POWER_SUPPLY=y
 CONFIG_BATTERY_SBS=y
 CONFIG_CHARGER_TPS65090=y
 CONFIG_POWER_RESET=y
@@ -182,11 +182,10 @@ CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=y
 CONFIG_USB_GSPCA=y
 CONFIG_DRM=y
+CONFIG_DRM_NOUVEAU=m
 CONFIG_DRM_TEGRA=y
 CONFIG_DRM_PANEL_SIMPLE=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
 # CONFIG_BACKLIGHT_GENERIC is not set
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -196,14 +195,11 @@ CONFIG_SOUND=y
 CONFIG_SND=y
 # CONFIG_SND_SUPPORT_OLD_API is not set
 # CONFIG_SND_DRIVERS is not set
-CONFIG_SND_HDA=y
 CONFIG_SND_HDA_TEGRA=y
 CONFIG_SND_HDA_INPUT_BEEP=y
-CONFIG_SND_HDA_INPUT_JACK=y
 CONFIG_SND_HDA_PATCH_LOADER=y
 CONFIG_SND_HDA_CODEC_REALTEK=y
 CONFIG_SND_HDA_CODEC_HDMI=y
-CONFIG_SND_HDA_GENERIC=y
 # CONFIG_SND_ARM is not set
 # CONFIG_SND_SPI is not set
 # CONFIG_SND_USB is not set
@@ -300,5 +296,4 @@ CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_LL=y
 CONFIG_EARLY_PRINTK=y
 CONFIG_CRYPTO_TWOFISH=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRC_CCITT=y
diff --git a/arch/arm/crypto/.gitignore b/arch/arm/crypto/.gitignore
index 6231d36b3635..31e1f538df7d 100644
--- a/arch/arm/crypto/.gitignore
+++ b/arch/arm/crypto/.gitignore
@@ -1 +1,3 @@
 aesbs-core.S
+sha256-core.S
+sha512-core.S
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 83c50193626c..be648eb47cd9 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -12,7 +12,7 @@ generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
-generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
 generic-y += param.h
 generic-y += parport.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 4abe57279c66..7bbf325a4f31 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -108,33 +108,37 @@
 	.endm
 #endif
 
-	.macro asm_trace_hardirqs_off
+	.macro asm_trace_hardirqs_off, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl	trace_hardirqs_off
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on_cond, cond
+	.macro asm_trace_hardirqs_on, cond=al, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
 	/*
 	 * actually the registers should be pushed and pop'd conditionally, but
 	 * after bl the flags are certainly clobbered
 	 */
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl\cond	trace_hardirqs_on
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on
-	asm_trace_hardirqs_on_cond al
-	.endm
-
-	.macro disable_irq
+	.macro disable_irq, save=1
 	disable_irq_notrace
-	asm_trace_hardirqs_off
+	asm_trace_hardirqs_off \save
 	.endm
 
 	.macro enable_irq
@@ -173,7 +177,7 @@
 
 	.macro restore_irqs, oldcpsr
 	tst	\oldcpsr, #PSR_I_BIT
-	asm_trace_hardirqs_on_cond eq
+	asm_trace_hardirqs_on cond=eq
 	restore_irqs_notrace \oldcpsr
 	.endm
 
@@ -445,6 +449,53 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_save, tmp
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	mrc	p15, 0, \tmp, c3, c0, 0
+	str	\tmp, [sp, #S_FRAME_SIZE]
+#endif
+	.endm
+
+	.macro	uaccess_restore
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	ldr	r0, [sp, #S_FRAME_SIZE]
+	mcr	p15, 0, r0, c3, c0, 0
+#endif
+	.endm
+
+	.macro	uaccess_save_and_disable, tmp
+	uaccess_save \tmp
+	uaccess_disable \tmp
+	.endm
+
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index e22c11970b7b..fe3ef397f5a4 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -57,12 +57,11 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
+static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 {									\
 	unsigned long tmp;						\
 	int result;							\
 									\
-	smp_mb();							\
 	prefetchw(&v->counter);						\
 									\
 	__asm__ __volatile__("@ atomic_" #op "_return\n"		\
@@ -75,17 +74,17 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	: "r" (&v->counter), "Ir" (i)					\
 	: "cc");							\
 									\
-	smp_mb();							\
-									\
 	return result;							\
 }
 
-static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+
+static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 {
 	int oldval;
 	unsigned long res;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	do {
@@ -99,10 +98,9 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 		    : "cc");
 	} while (res);
 
-	smp_mb();
-
 	return oldval;
 }
+#define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
@@ -194,6 +192,13 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(andnot, &= ~, bic)
+ATOMIC_OP(or,  |=, orr)
+ATOMIC_OP(xor, ^=, eor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -290,12 +295,12 @@ static inline void atomic64_##op(long long i, atomic64_t *v)		\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, op1, op2)				\
-static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
+static inline long long							\
+atomic64_##op##_return_relaxed(long long i, atomic64_t *v)		\
 {									\
 	long long result;						\
 	unsigned long tmp;						\
 									\
-	smp_mb();							\
 	prefetchw(&v->counter);						\
 									\
 	__asm__ __volatile__("@ atomic64_" #op "_return\n"		\
@@ -309,8 +314,6 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 	: "r" (&v->counter), "r" (i)					\
 	: "cc");							\
 									\
-	smp_mb();							\
-									\
 	return result;							\
 }
 
@@ -321,17 +324,26 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 ATOMIC64_OPS(add, adds, adc)
 ATOMIC64_OPS(sub, subs, sbc)
 
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC64_OP(and, and, and)
+ATOMIC64_OP(andnot, bic, bic)
+ATOMIC64_OP(or,  orr, orr)
+ATOMIC64_OP(xor, eor, eor)
+
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
-					long long new)
+static inline long long
+atomic64_cmpxchg_relaxed(atomic64_t *ptr, long long old, long long new)
 {
 	long long oldval;
 	unsigned long res;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	do {
@@ -346,17 +358,15 @@ static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
 		: "cc");
 	} while (res);
 
-	smp_mb();
-
 	return oldval;
 }
+#define atomic64_cmpxchg_relaxed	atomic64_cmpxchg_relaxed
 
-static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+static inline long long atomic64_xchg_relaxed(atomic64_t *ptr, long long new)
 {
 	long long result;
 	unsigned long tmp;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
@@ -368,10 +378,9 @@ static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
 	: "r" (&ptr->counter), "r" (new)
 	: "cc");
 
-	smp_mb();
-
 	return result;
 }
+#define atomic64_xchg_relaxed		atomic64_xchg_relaxed
 
 static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 6c2327e1c732..3ff5642d9788 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -2,7 +2,6 @@
 #define __ASM_BARRIER_H
 
 #ifndef __ASSEMBLY__
-#include <asm/outercache.h>
 
 #define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
 
@@ -37,12 +36,20 @@
 #define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #endif
 
+#ifdef CONFIG_ARM_HEAVY_MB
+extern void (*soc_mb)(void);
+extern void arm_heavy_mb(void);
+#define __arm_heavy_mb(x...) do { dsb(x); arm_heavy_mb(); } while (0)
+#else
+#define __arm_heavy_mb(x...) dsb(x)
+#endif
+
 #ifdef CONFIG_ARCH_HAS_BARRIERS
 #include <mach/barriers.h>
 #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
-#define mb()		do { dsb(); outer_sync(); } while (0)
+#define mb()		__arm_heavy_mb()
 #define rmb()		dsb()
-#define wmb()		do { dsb(st); outer_sync(); } while (0)
+#define wmb()		__arm_heavy_mb(st)
 #define dma_rmb()	dmb(osh)
 #define dma_wmb()	dmb(oshst)
 #else
@@ -67,12 +74,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 56380995f4c3..e943e6cee254 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -35,9 +35,9 @@
 static inline void ____atomic_set_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p |= mask;
@@ -47,9 +47,9 @@ static inline void ____atomic_set_bit(unsigned int bit, volatile unsigned long *
 static inline void ____atomic_clear_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p &= ~mask;
@@ -59,9 +59,9 @@ static inline void ____atomic_clear_bit(unsigned int bit, volatile unsigned long
 static inline void ____atomic_change_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p ^= mask;
@@ -73,9 +73,9 @@ ____atomic_test_and_set_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
@@ -90,9 +90,9 @@ ____atomic_test_and_clear_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
@@ -107,9 +107,9 @@ ____atomic_test_and_change_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 4812cda8fd17..d5525bfc7e3e 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -140,8 +140,6 @@ extern struct cpu_cache_fns cpu_cache;
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-#define dmac_map_area			cpu_cache.dma_map_area
-#define dmac_unmap_area			cpu_cache.dma_unmap_area
 #define dmac_flush_range		cpu_cache.dma_flush_range
 
 #else
@@ -161,8 +159,6 @@ extern void __cpuc_flush_dcache_area(void *, size_t);
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-extern void dmac_map_area(const void *, size_t, int);
-extern void dmac_unmap_area(const void *, size_t, int);
 extern void dmac_flush_range(const void *, const void *);
 
 #endif
@@ -506,4 +502,21 @@ static inline void set_kernel_text_ro(void) { }
 void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
 			     void *kaddr, unsigned long len);
 
+/**
+ * secure_flush_area - ensure coherency across the secure boundary
+ * @addr: virtual address
+ * @size: size of region
+ *
+ * Ensure that the specified area of memory is coherent across the secure
+ * boundary from the non-secure side.  This is used when calling secure
+ * firmware where the secure firmware does not ensure coherency.
+ */
+static inline void secure_flush_area(const void *addr, size_t size)
+{
+	phys_addr_t phys = __pa(addr);
+
+	__cpuc_flush_dcache_area((void *)addr, size);
+	outer_flush_range(phys, phys + size);
+}
+
 #endif
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 1692a05d3207..916a2744d5c6 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -35,7 +35,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	unsigned int tmp;
 #endif
 
-	smp_mb();
 	prefetchw((const void *)ptr);
 
 	switch (size) {
@@ -98,12 +97,11 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
-	smp_mb();
 
 	return ret;
 }
 
-#define xchg(ptr, x) ({							\
+#define xchg_relaxed(ptr, x) ({						\
 	(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr),		\
 				   sizeof(*(ptr)));			\
 })
@@ -117,6 +115,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 #error "SMP is not supported on this platform"
 #endif
 
+#define xchg xchg_relaxed
+
 /*
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
@@ -194,23 +194,11 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return oldval;
 }
 
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
-					 unsigned long new, int size)
-{
-	unsigned long ret;
-
-	smp_mb();
-	ret = __cmpxchg(ptr, old, new, size);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg(ptr,o,n) ({						\
-	(__typeof__(*(ptr)))__cmpxchg_mb((ptr),				\
-					 (unsigned long)(o),		\
-					 (unsigned long)(n),		\
-					 sizeof(*(ptr)));		\
+#define cmpxchg_relaxed(ptr,o,n) ({					\
+	(__typeof__(*(ptr)))__cmpxchg((ptr),				\
+				      (unsigned long)(o),		\
+				      (unsigned long)(n),		\
+				      sizeof(*(ptr)));			\
 })
 
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
@@ -273,25 +261,6 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 
 #define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
 
-static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
-						unsigned long long old,
-						unsigned long long new)
-{
-	unsigned long long ret;
-
-	smp_mb();
-	ret = __cmpxchg64(ptr, old, new);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg64(ptr, o, n) ({						\
-	(__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					   (unsigned long long)(o),	\
-					   (unsigned long long)(n));	\
-})
-
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
 #endif /* __ASM_ARM_CMPXCHG_H */
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index b52101d37ec7..a68b9d8a71fe 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -14,7 +14,7 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define DMA_ERROR_CODE	(~0)
+#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 extern struct dma_map_ops arm_dma_ops;
 extern struct dma_map_ops arm_coherent_dma_ops;
 
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 6ddbe446425e..e878129f2fee 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -34,15 +34,14 @@
  */
 #ifndef CONFIG_IO_36
 #define DOMAIN_KERNEL	0
-#define DOMAIN_TABLE	0
 #define DOMAIN_USER	1
 #define DOMAIN_IO	2
 #else
 #define DOMAIN_KERNEL	2
-#define DOMAIN_TABLE	2
 #define DOMAIN_USER	1
 #define DOMAIN_IO	0
 #endif
+#define DOMAIN_VECTORS	3
 
 /*
  * Domain types
@@ -55,11 +54,46 @@
 #define DOMAIN_MANAGER	1
 #endif
 
-#define domain_val(dom,type)	((type) << (2*(dom)))
+#define domain_mask(dom)	((3) << (2 * (dom)))
+#define domain_val(dom,type)	((type) << (2 * (dom)))
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_NOACCESS) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#else
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#endif
+
+#define __DACR_DEFAULT \
+	domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)
+
+#define DACR_UACCESS_DISABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+#define DACR_UACCESS_ENABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_CLIENT))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_CPU_USE_DOMAINS
+static inline unsigned int get_domain(void)
+{
+	unsigned int domain;
+
+	asm(
+	"mrc	p15, 0, %0, c3, c0	@ get domain"
+	 : "=r" (domain));
+
+	return domain;
+}
+
 static inline void set_domain(unsigned val)
 {
 	asm volatile(
@@ -68,17 +102,16 @@ static inline void set_domain(unsigned val)
 	isb();
 }
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define modify_domain(dom,type)					\
 	do {							\
-	struct thread_info *thread = current_thread_info();	\
-	unsigned int domain = thread->cpu_domain;		\
-	domain &= ~domain_val(dom, DOMAIN_MANAGER);		\
-	thread->cpu_domain = domain | domain_val(dom, type);	\
-	set_domain(thread->cpu_domain);				\
+		unsigned int domain = get_domain();		\
+		domain &= ~domain_mask(dom);			\
+		domain = domain | domain_val(dom, type);	\
+		set_domain(domain);				\
 	} while (0)
 
 #else
-static inline void set_domain(unsigned val) { }
 static inline void modify_domain(unsigned dom, unsigned type)	{ }
 #endif
 
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 0415eae1df27..58cfe9f1a687 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -6,9 +6,13 @@
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
 #include <asm/kmap_types.h>
+#include <asm/pgtable.h>
 
 enum fixed_addresses {
-	FIX_KMAP_BEGIN,
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_permanent_fixed_addresses,
+
+	FIX_KMAP_BEGIN = __end_of_permanent_fixed_addresses,
 	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
 
 	/* Support writing RO kernel text via kprobes, jump labels, etc. */
@@ -18,7 +22,16 @@ enum fixed_addresses {
 	__end_of_fixed_addresses
 };
 
+#define FIXMAP_PAGE_COMMON	(L_PTE_YOUNG | L_PTE_PRESENT | L_PTE_XN | L_PTE_DIRTY)
+
+#define FIXMAP_PAGE_NORMAL	(FIXMAP_PAGE_COMMON | L_PTE_MT_WRITEBACK)
+
+/* Used by set_fixmap_(io|nocache), both meant for mapping a device */
+#define FIXMAP_PAGE_IO		(FIXMAP_PAGE_COMMON | L_PTE_MT_DEV_SHARED | L_PTE_SHARED)
+#define FIXMAP_PAGE_NOCACHE	FIXMAP_PAGE_IO
+
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
+void __init early_fixmap_init(void);
 
 #include <asm-generic/fixmap.h>
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 5eed82809d82..6795368ad023 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -22,8 +22,11 @@
 #ifdef CONFIG_SMP
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags;				\
 	smp_mb();						\
 	prefetchw(uaddr);					\
+	__ua_flags = uaccess_save_and_enable();			\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -34,12 +37,15 @@
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret;
 	u32 val;
 
@@ -49,6 +55,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	smp_mb();
 	/* Prefetching cannot fault */
 	prefetchw(uaddr);
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -61,6 +68,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "=&r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 	smp_mb();
 
 	*uval = val;
@@ -73,6 +81,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags = uaccess_save_and_enable();	\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
@@ -81,12 +91,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret = 0;
 	u32 val;
 
@@ -94,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	preempt_disable();
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -103,6 +117,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 
 	*uval = val;
 	preempt_enable();
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index a3c24cd5b7c8..cab07f69382d 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -158,8 +158,6 @@ static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
 #define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
 #define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
 
-#define dmac_map_area			__glue(_CACHE,_dma_map_area)
-#define dmac_unmap_area			__glue(_CACHE,_dma_unmap_area)
 #define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
 #endif
 
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1c3938f26beb..485982084fe9 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -140,16 +140,11 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
  * The _caller variety takes a __builtin_return_address(0) value for
  * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
-	size_t, unsigned int, void *);
 extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
-
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
@@ -321,21 +316,24 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 static inline void memset_io(volatile void __iomem *dst, unsigned c,
 	size_t count)
 {
-	memset((void __force *)dst, c, count);
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
 }
 #define memset_io(dst,c,count) memset_io(dst,c,count)
 
 static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
 	size_t count)
 {
-	memcpy(to, (const void __force *)from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
 }
 #define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
 
 static inline void memcpy_toio(volatile void __iomem *to, const void *from,
 	size_t count)
 {
-	memcpy((void __force *)to, from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
 }
 #define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
 
@@ -348,18 +346,61 @@ static inline void memcpy_toio(volatile void __iomem *to, const void *from,
 #endif	/* readl */
 
 /*
- * ioremap and friends.
+ * ioremap() and friends.
+ *
+ * ioremap() takes a resource address, and size.  Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
+ *
+ * Function		Memory type	Cacheability	Cache hint
+ * ioremap()		Device		n/a		n/a
+ * ioremap_nocache()	Device		n/a		n/a
+ * ioremap_cache()	Normal		Writeback	Read allocate
+ * ioremap_wc()		Normal		Non-cacheable	n/a
+ * ioremap_wt()		Normal		Non-cacheable	n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
  *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different.  This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
  *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ *   instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
  */
-#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define ioremap_wt(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define iounmap				__arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
 
 /*
  * io{read,write}{16,32}be() macros
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 53c15dec7af6..be1d07d59ee9 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -35,6 +35,11 @@ extern void (*handle_arch_irq)(struct pt_regs *);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 #endif
 
+#ifdef CONFIG_SMP
+extern void arch_trigger_all_cpu_backtrace(bool);
+#define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x)
+#endif
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index 5f337dc5c108..34f7b6980d21 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -4,23 +4,32 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <asm/unified.h>
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-#ifdef CONFIG_THUMB2_KERNEL
-#define JUMP_LABEL_NOP	"nop.w"
-#else
-#define JUMP_LABEL_NOP	"nop"
-#endif
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		 WASM(nop) "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
-		 JUMP_LABEL_NOP "\n\t"
+		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (key) :  : l_yes);
+		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
 
 	return false;
 l_yes:
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
index 28b9bb35949e..8857d2869a5f 100644
--- a/arch/arm/include/asm/mach/pci.h
+++ b/arch/arm/include/asm/mach/pci.h
@@ -19,9 +19,7 @@ struct pci_bus;
 struct device;
 
 struct hw_pci {
-#ifdef CONFIG_PCI_MSI
 	struct msi_controller *msi_ctrl;
-#endif
 	struct pci_ops	*ops;
 	int		nr_controllers;
 	void		**private_data;
@@ -42,9 +40,6 @@ struct hw_pci {
  * Per-controller structure
  */
 struct pci_sys_data {
-#ifdef CONFIG_PCI_MSI
-	struct msi_controller *msi_ctrl;
-#endif
 	struct list_head node;
 	int		busnr;		/* primary bus number			*/
 	u64		mem_offset;	/* bus->cpu memory mapping offset	*/
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 3a72d69b3255..b7f6fb462ea0 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -275,7 +275,7 @@ static inline void *phys_to_virt(phys_addr_t x)
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)	__va((phys_addr_t)(pfn) << PAGE_SHIFT)
 
 extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
 
@@ -286,7 +286,7 @@ extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
  */
 static inline phys_addr_t __virt_to_idmap(unsigned long x)
 {
-	if (arch_virt_to_idmap)
+	if (IS_ENABLED(CONFIG_MMU) && arch_virt_to_idmap)
 		return arch_virt_to_idmap(x);
 	else
 		return __virt_to_phys(x);
diff --git a/arch/arm/include/asm/mm-arch-hooks.h b/arch/arm/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 7056660c7cc4..000000000000
--- a/arch/arm/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ARM_MM_ARCH_HOOKS_H
-#define _ASM_ARM_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ARM_MM_ARCH_HOOKS_H */
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index 563b92fc2f41..c2bf24f40177 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -129,21 +129,4 @@ static inline void outer_resume(void) { }
 
 #endif
 
-#ifdef CONFIG_OUTER_CACHE_SYNC
-/**
- * outer_sync - perform a sync point for outer cache
- *
- * Ensure that all outer cache operations are complete and any store
- * buffers are drained.
- */
-static inline void outer_sync(void)
-{
-	if (outer_cache.sync)
-		outer_cache.sync();
-}
-#else
-static inline void outer_sync(void)
-{ }
-#endif
-
 #endif	/* __ASM_OUTERCACHE_H */
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 5e68278e953e..d0131ee6f6af 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -23,6 +23,7 @@
 #define PMD_PXNTABLE		(_AT(pmdval_t, 1) << 2)     /* v7 */
 #define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_DOMAIN_MASK		PMD_DOMAIN(0x0f)
 #define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
 /*
  *   - section
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index bfd662e49a25..aeddd28b3595 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -129,7 +129,36 @@
 
 /*
  * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
+ * UNCACHED		Uncached	Strongly ordered
+ * BUFFERABLE		Bufferable	Normal memory / non-cacheable
+ * WRITETHROUGH		Writethrough	Normal memory / write through
+ * WRITEBACK		Writeback	Normal memory / write back, read alloc
+ * MINICACHE		Minicache	N/A
+ * WRITEALLOC		Writeback	Normal memory / write back, write alloc
+ * DEV_SHARED		Uncached	Device memory (shared)
+ * DEV_NONSHARED	Uncached	Device memory (non-shared)
+ * DEV_WC		Bufferable	Normal memory / non-cacheable
+ * DEV_CACHED		Writeback	Normal memory / write back, read alloc
+ * VECTORS		Variable	Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index c25ef3ec6d1f..68ee3ce17b82 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -14,34 +14,11 @@
 #ifndef __ASM_ARM_PSCI_H
 #define __ASM_ARM_PSCI_H
 
-#define PSCI_POWER_STATE_TYPE_STANDBY		0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
-
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
-
-struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
-	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-	int (*migrate)(unsigned long cpuid);
-	int (*affinity_info)(unsigned long target_affinity,
-			unsigned long lowest_affinity_level);
-	int (*migrate_info_type)(void);
-};
-
-extern struct psci_operations psci_ops;
 extern struct smp_operations psci_smp_ops;
 
 #ifdef CONFIG_ARM_PSCI
-int psci_init(void);
 bool psci_smp_available(void);
 #else
-static inline int psci_init(void) { return 0; }
 static inline bool psci_smp_available(void) { return false; }
 #endif
 
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 2f3ac1ba6fb4..ef356659b4f4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -74,7 +74,6 @@ extern void secondary_startup_arm(void);
 extern int __cpu_disable(void);
 
 extern void __cpu_die(unsigned int cpu);
-extern void cpu_die(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
@@ -105,6 +104,7 @@ struct smp_operations {
 #ifdef CONFIG_HOTPLUG_CPU
 	int  (*cpu_kill)(unsigned int cpu);
 	void (*cpu_die)(unsigned int cpu);
+	bool  (*cpu_can_disable)(unsigned int cpu);
 	int  (*cpu_disable)(unsigned int cpu);
 #endif
 #endif
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 993e5224d8f7..f9080717fc88 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -107,4 +107,13 @@ static inline u32 mpidr_hash_size(void)
 extern int platform_can_secondary_boot(void);
 extern int platform_can_cpu_hotplug(void);
 
+#ifdef CONFIG_HOTPLUG_CPU
+extern int platform_can_hotplug_cpu(unsigned int cpu);
+#else
+static inline int platform_can_hotplug_cpu(unsigned int cpu)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index c99e259469f7..12ebfcc1d539 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -10,7 +10,9 @@
  * CPU.
  */
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
-#define finish_arch_switch(prev)	dsb(ish)
+#define __complete_pending_tlbi()	dsb(ish)
+#else
+#define __complete_pending_tlbi()
 #endif
 
 /*
@@ -22,6 +24,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 
 #define switch_to(prev,next,last)					\
 do {									\
+	__complete_pending_tlbi();					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index bd32eded3e50..d0a1119dcaf3 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -74,9 +74,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -136,22 +133,18 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 
 /*
  * thread information flags:
- *  TIF_SYSCALL_TRACE	- syscall trace active
- *  TIF_SYSCAL_AUDIT	- syscall auditing active
- *  TIF_SIGPENDING	- signal pending
- *  TIF_NEED_RESCHED	- rescheduling necessary
- *  TIF_NOTIFY_RESUME	- callback before returning to user
  *  TIF_USEDFPU		- FPU was used by this task this quantum (SMP)
  *  TIF_POLLING_NRFLAG	- true if poll_idle() is polling TIF_NEED_RESCHED
  */
-#define TIF_SIGPENDING		0
-#define TIF_NEED_RESCHED	1
+#define TIF_SIGPENDING		0	/* signal pending */
+#define TIF_NEED_RESCHED	1	/* rescheduling necessary */
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
-#define TIF_UPROBE		7
-#define TIF_SYSCALL_TRACE	8
-#define TIF_SYSCALL_AUDIT	9
-#define TIF_SYSCALL_TRACEPOINT	10
-#define TIF_SECCOMP		11	/* seccomp syscall filtering active */
+#define TIF_UPROBE		3	/* breakpointed or singlestepping */
+#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
+
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 74b17d09ef7a..8cc85a4ebec2 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -50,6 +50,35 @@ struct exception_table_entry
 extern int fixup_exception(struct pt_regs *regs);
 
 /*
+ * These two functions allow hooking accesses to userspace to increase
+ * system integrity by ensuring that the kernel can not inadvertantly
+ * perform such accesses (eg, via list poison values) which could then
+ * be exploited for priviledge escalation.
+ */
+static inline unsigned int uaccess_save_and_enable(void)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	unsigned int old_domain = get_domain();
+
+	/* Set the current domain access to permit user accesses */
+	set_domain((old_domain & ~domain_mask(DOMAIN_USER)) |
+		   domain_val(DOMAIN_USER, DOMAIN_CLIENT));
+
+	return old_domain;
+#else
+	return 0;
+#endif
+}
+
+static inline void uaccess_restore(unsigned int flags)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/* Restore the user access mask */
+	set_domain(flags);
+#endif
+}
+
+/*
  * These two are intentionally not defined anywhere - if the kernel
  * code generates any references to them, that's a bug.
  */
@@ -165,6 +194,7 @@ extern int __get_user_64t_4(void *);
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			if (sizeof((x)) >= 8)				\
@@ -192,6 +222,7 @@ extern int __get_user_64t_4(void *);
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
 		__e;							\
 	})
@@ -224,6 +255,7 @@ extern int __put_user_8(void *, unsigned long long);
 		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			__put_user_x(__r2, __p, __e, __l, 1);		\
@@ -239,6 +271,7 @@ extern int __put_user_8(void *, unsigned long long);
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		__e;							\
 	})
 
@@ -300,20 +333,23 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
+	unsigned int __ua_flags;					\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err);	break;	\
 	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err);	break;	\
 	default: (__gu_val) = __get_user_bad();				\
 	}								\
+	uaccess_restore(__ua_flags);					\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
 } while (0)
 
-#define __get_user_asm_byte(x, addr, err)			\
+#define __get_user_asm(x, addr, err, instr)			\
 	__asm__ __volatile__(					\
-	"1:	" TUSER(ldrb) "	%1,[%2],#0\n"			\
+	"1:	" TUSER(instr) " %1, [%2], #0\n"		\
 	"2:\n"							\
 	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
@@ -329,6 +365,9 @@ do {									\
 	: "r" (addr), "i" (-EFAULT)				\
 	: "cc")
 
+#define __get_user_asm_byte(x, addr, err)			\
+	__get_user_asm(x, addr, err, ldrb)
+
 #ifndef __ARMEB__
 #define __get_user_asm_half(x, __gu_addr, err)			\
 ({								\
@@ -348,22 +387,7 @@ do {									\
 #endif
 
 #define __get_user_asm_word(x, addr, err)			\
-	__asm__ __volatile__(					\
-	"1:	" TUSER(ldr) "	%1,[%2],#0\n"			\
-	"2:\n"							\
-	"	.pushsection .text.fixup,\"ax\"\n"		\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	mov	%1, #0\n"				\
-	"	b	2b\n"					\
-	"	.popsection\n"					\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.popsection"					\
-	: "+r" (err), "=&r" (x)					\
-	: "r" (addr), "i" (-EFAULT)				\
-	: "cc")
+	__get_user_asm(x, addr, err, ldr)
 
 #define __put_user(x, ptr)						\
 ({									\
@@ -381,9 +405,11 @@ do {									\
 #define __put_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
+	unsigned int __ua_flags;					\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val, __pu_addr, err);	break;	\
 	case 2: __put_user_asm_half(__pu_val, __pu_addr, err);	break;	\
@@ -391,11 +417,12 @@ do {									\
 	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
 	default: __put_user_bad();					\
 	}								\
+	uaccess_restore(__ua_flags);					\
 } while (0)
 
-#define __put_user_asm_byte(x, __pu_addr, err)			\
+#define __put_user_asm(x, __pu_addr, err, instr)		\
 	__asm__ __volatile__(					\
-	"1:	" TUSER(strb) "	%1,[%2],#0\n"			\
+	"1:	" TUSER(instr) " %1, [%2], #0\n"		\
 	"2:\n"							\
 	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
@@ -410,6 +437,9 @@ do {									\
 	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
 	: "cc")
 
+#define __put_user_asm_byte(x, __pu_addr, err)			\
+	__put_user_asm(x, __pu_addr, err, strb)
+
 #ifndef __ARMEB__
 #define __put_user_asm_half(x, __pu_addr, err)			\
 ({								\
@@ -427,21 +457,7 @@ do {									\
 #endif
 
 #define __put_user_asm_word(x, __pu_addr, err)			\
-	__asm__ __volatile__(					\
-	"1:	" TUSER(str) "	%1,[%2],#0\n"			\
-	"2:\n"							\
-	"	.pushsection .text.fixup,\"ax\"\n"		\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	b	2b\n"					\
-	"	.popsection\n"					\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.popsection"					\
-	: "+r" (err)						\
-	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
-	: "cc")
+	__put_user_asm(x, __pu_addr, err, str)
 
 #ifndef __ARMEB__
 #define	__reg_oper0	"%R2"
@@ -474,11 +490,46 @@ do {									\
 
 
 #ifdef CONFIG_MMU
-extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+arm_copy_from_user(void *to, const void __user *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_from_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+__copy_to_user_std(void __user *to, const void *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_to_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+__clear_user_std(void __user *addr, unsigned long n);
+
+static inline unsigned long __must_check
+__clear_user(void __user *addr, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_clear_user(addr, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
 #else
 #define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
 #define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
@@ -511,6 +562,7 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return n;
 }
 
+/* These are from lib/ code, and use __get_user() and friends */
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
 extern __must_check long strlen_user(const char __user *str);
diff --git a/arch/arm/include/asm/xen/events.h b/arch/arm/include/asm/xen/events.h
index 8b1f37bfeeec..71e473d05fcc 100644
--- a/arch/arm/include/asm/xen/events.h
+++ b/arch/arm/include/asm/xen/events.h
@@ -20,4 +20,10 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 							    atomic64_t,	\
 							    counter), (val))
 
+/* Rebind event channel is supported by default */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return true;
+}
+
 #endif /* _ASM_ARM_XEN_EVENTS_H */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 1bee8ca12494..98b1084f8282 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -54,26 +54,14 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 
 #define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn)
 
-static inline xmaddr_t phys_to_machine(xpaddr_t phys)
-{
-	unsigned offset = phys.paddr & ~PAGE_MASK;
-	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
-}
-
-static inline xpaddr_t machine_to_phys(xmaddr_t machine)
-{
-	unsigned offset = machine.maddr & ~PAGE_MASK;
-	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
-}
 /* VIRT <-> MACHINE conversion */
-#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
 #define virt_to_mfn(v)		(pfn_to_mfn(virt_to_pfn(v)))
 #define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
+/* Only used in PV code. But ARM guests are always HVM. */
 static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 {
-	/* TODO: assuming it is mapped in the kernel 1:1 */
-	return virt_to_machine(vaddr);
+	BUG();
 }
 
 /* TODO: this shouldn't be here but it is because the frontend drivers
diff --git a/arch/arm/include/debug/at91.S b/arch/arm/include/debug/at91.S
index c3c45e628e33..2556a8801c8c 100644
--- a/arch/arm/include/debug/at91.S
+++ b/arch/arm/include/debug/at91.S
@@ -13,9 +13,12 @@
 #define AT91_DBGU 0xfffff200 /* AT91_BASE_DBGU0 */
 #elif defined(CONFIG_AT91_DEBUG_LL_DBGU1)
 #define AT91_DBGU 0xffffee00 /* AT91_BASE_DBGU1 */
-#else
+#elif defined(CONFIG_AT91_DEBUG_LL_DBGU2)
 /* On sama5d4, use USART3 as low level serial console */
 #define AT91_DBGU 0xfc00c000 /* SAMA5D4_BASE_USART3 */
+#else
+/* On sama5d2, use UART1 as low level serial console */
+#define AT91_DBGU 0xf8020000
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/include/debug/imx-uart.h b/arch/arm/include/debug/imx-uart.h
index 66f736f74684..bce58e975ad1 100644
--- a/arch/arm/include/debug/imx-uart.h
+++ b/arch/arm/include/debug/imx-uart.h
@@ -90,6 +90,17 @@
 #define IMX6SX_UART_BASE_ADDR(n) IMX6SX_UART##n##_BASE_ADDR
 #define IMX6SX_UART_BASE(n)	IMX6SX_UART_BASE_ADDR(n)
 
+#define IMX6UL_UART1_BASE_ADDR	0x02020000
+#define IMX6UL_UART2_BASE_ADDR	0x021e8000
+#define IMX6UL_UART3_BASE_ADDR	0x021ec000
+#define IMX6UL_UART4_BASE_ADDR	0x021f0000
+#define IMX6UL_UART5_BASE_ADDR	0x021f4000
+#define IMX6UL_UART6_BASE_ADDR	0x021fc000
+#define IMX6UL_UART7_BASE_ADDR	0x02018000
+#define IMX6UL_UART8_BASE_ADDR	0x02024000
+#define IMX6UL_UART_BASE_ADDR(n) IMX6UL_UART##n##_BASE_ADDR
+#define IMX6UL_UART_BASE(n)	IMX6UL_UART_BASE_ADDR(n)
+
 #define IMX7D_UART1_BASE_ADDR	0x30860000
 #define IMX7D_UART2_BASE_ADDR	0x30890000
 #define IMX7D_UART3_BASE_ADDR	0x30880000
@@ -124,6 +135,8 @@
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6SL)
 #elif defined(CONFIG_DEBUG_IMX6SX_UART)
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6SX)
+#elif defined(CONFIG_DEBUG_IMX6UL_UART)
+#define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6UL)
 #elif defined(CONFIG_DEBUG_IMX7D_UART)
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX7D)
 
diff --git a/arch/arm/include/debug/zynq.S b/arch/arm/include/debug/zynq.S
index bd13dedbdeff..de86b9247564 100644
--- a/arch/arm/include/debug/zynq.S
+++ b/arch/arm/include/debug/zynq.S
@@ -38,7 +38,7 @@
 		.endm
 
 		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_FIFO_OFFSET]	@ TXDATA
+		strb	\rd, [\rx, #UART_FIFO_OFFSET]	@ TXDATA
 		.endm
 
 		.macro	waituart,rd,rx
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index e69f7a19735d..af9e59bf3831 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -71,8 +71,7 @@ obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_CPU_PJ4B)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o \
-				   perf_event_xscale.o perf_event_v6.o \
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_xscale.o perf_event_v6.o \
 				   perf_event_v7.o
 CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
@@ -89,7 +88,7 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y				+= psci.o psci-call.o
+obj-y				+= psci-call.o
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
 
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index a88671cfe1ff..f89811fb9a55 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -50,6 +50,9 @@ extern void __aeabi_ulcmp(void);
 
 extern void fpundefinstr(void);
 
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
 	/* platform dependent support */
 EXPORT_SYMBOL(arm_delay_ops);
 
@@ -88,12 +91,15 @@ EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
+
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
 
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index fcbbbb1b9e95..874e1823f803 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -18,15 +18,6 @@
 
 static int debug_pci;
 
-#ifdef CONFIG_PCI_MSI
-struct msi_controller *pcibios_msi_controller(struct pci_dev *dev)
-{
-	struct pci_sys_data *sysdata = dev->bus->sysdata;
-
-	return sysdata->msi_ctrl;
-}
-#endif
-
 /*
  * We can't use pci_get_device() here since we are
  * called from interrupt context.
@@ -459,12 +450,9 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 
 	for (nr = busnr = 0; nr < hw->nr_controllers; nr++) {
 		sys = kzalloc(sizeof(struct pci_sys_data), GFP_KERNEL);
-		if (!sys)
-			panic("PCI: unable to allocate sys data!");
+		if (WARN(!sys, "PCI: unable to allocate sys data!"))
+			break;
 
-#ifdef CONFIG_PCI_MSI
-		sys->msi_ctrl = hw->msi_ctrl;
-#endif
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
@@ -486,11 +474,14 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 			if (hw->scan)
 				sys->bus = hw->scan(nr, sys);
 			else
-				sys->bus = pci_scan_root_bus(parent, sys->busnr,
-						hw->ops, sys, &sys->resources);
+				sys->bus = pci_scan_root_bus_msi(parent,
+					sys->busnr, hw->ops, sys,
+					&sys->resources, hw->msi_ctrl);
 
-			if (!sys->bus)
-				panic("PCI: unable to scan bus!");
+			if (WARN(!sys->bus, "PCI: unable to scan bus!")) {
+				kfree(sys);
+				break;
+			}
 
 			busnr = sys->bus->busn_res.end + 1;
 
@@ -521,6 +512,8 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw)
 		struct pci_bus *bus = sys->bus;
 
 		if (!pci_has_flag(PCI_PROBE_ONLY)) {
+			struct pci_bus *child;
+
 			/*
 			 * Size the bridge windows.
 			 */
@@ -530,25 +523,15 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw)
 			 * Assign resources.
 			 */
 			pci_bus_assign_resources(bus);
-		}
 
+			list_for_each_entry(child, &bus->children, node)
+				pcie_bus_configure_settings(child);
+		}
 		/*
 		 * Tell drivers about devices found.
 		 */
 		pci_bus_add_devices(bus);
 	}
-
-	list_for_each_entry(sys, &head, node) {
-		struct pci_bus *bus = sys->bus;
-
-		/* Configure PCI Express settings */
-		if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
-			struct pci_bus *child;
-
-			list_for_each_entry(child, &bus->children, node)
-				pcie_bus_configure_settings(child);
-		}
-	}
 }
 
 #ifndef CONFIG_PCI_HOST_ITE8152
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7dac3086e361..3e1c26eb32b4 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -149,10 +149,10 @@ ENDPROC(__und_invalid)
 #define SPFIX(code...)
 #endif
 
-	.macro	svc_entry, stack_hole=0, trace=1
+	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,11 @@ ENDPROC(__und_invalid)
 	@
 	stmia	r7, {r2 - r6}
 
+	uaccess_save r0
+	.if \uaccess
+	uaccess_disable r0
+	.endif
+
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -194,7 +199,7 @@ ENDPROC(__und_invalid)
 
 	.align	5
 __dabt_svc:
-	svc_entry
+	svc_entry uaccess=0
 	mov	r2, sp
 	dabt_helper
  THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
@@ -368,7 +373,7 @@ ENDPROC(__fiq_abt)
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
-	.macro	usr_entry, trace=1
+	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@ ENDPROC(__fiq_abt)
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
+	.if \uaccess
+	uaccess_disable ip
+	.endif
+
 	@ Enable the alignment trap while in kernel mode
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
@@ -410,7 +419,7 @@ ENDPROC(__fiq_abt)
 	zero_fp
 
 	.if	\trace
-#ifdef CONFIG_IRQSOFF_TRACER
+#ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 	ct_user_exit save = 0
@@ -435,7 +444,7 @@ ENDPROC(__fiq_abt)
 
 	.align	5
 __dabt_usr:
-	usr_entry
+	usr_entry uaccess=0
 	kuser_cmpxchg_check
 	mov	r2, sp
 	dabt_helper
@@ -458,7 +467,7 @@ ENDPROC(__irq_usr)
 
 	.align	5
 __und_usr:
-	usr_entry
+	usr_entry uaccess=0
 
 	mov	r2, r4
 	mov	r3, r5
@@ -484,6 +493,8 @@ __und_usr:
 1:	ldrt	r0, [r4]
  ARM_BE8(rev	r0, r0)				@ little endian instruction
 
+	uaccess_disable ip
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@ __und_usr_thumb:
 2:	ldrht	r5, [r4]
 ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
+	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
 ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	uaccess_disable ip
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@ ENDPROC(no_fp)
 __und_usr_fault_32:
 	mov	r1, #4
 	b	1f
+__und_usr_fault_16_pan:
+	uaccess_disable ip
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
@@ -770,6 +784,8 @@ ENTRY(__switch_to)
 	ldr	r4, [r2, #TI_TP_VALUE]
 	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
+	mrc	p15, 0, r6, c3, c0, 0		@ Get domain register
+	str	r6, [r1, #TI_CPU_DOMAIN]	@ Save old domain register
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	switch_tls r1, r4, r5, r3, r7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 92828a1dec80..30a7228eaceb 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -24,35 +24,55 @@
 
 
 	.align	5
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
 /*
- * This is the fast syscall return path.  We do as little as
- * possible here, and this includes saving r0 back into the SVC
- * stack.
+ * This is the fast syscall return path.  We do as little as possible here,
+ * such as avoiding writing r0 to the stack.  We only use this path if we
+ * have tracing and context tracking disabled - the overheads from those
+ * features make this path too inefficient.
  */
 ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK
-	bne	__sys_trace_return
-	tst	r1, #_TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	bne	fast_work_pending
-	asm_trace_hardirqs_on
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
-	ct_user_enter
 
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
 
-/*
- * Ok, we need to do extra processing, enter the slow path.
- */
+	/* Ok, we need to do extra processing, enter the slow path. */
 fast_work_pending:
 	str	r0, [sp, #S_R0+S_OFF]!		@ returned r0
-work_pending:
+	/* fall through to work_pending */
+#else
+/*
+ * The "replacement" ret_fast_syscall for when tracing or context tracking
+ * is enabled.  As we will need to call out to some C functions, we save
+ * r0 first to avoid needing to save registers around each C function call.
+ */
+ret_fast_syscall:
+ UNWIND(.fnstart	)
+ UNWIND(.cantunwind	)
+	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
+	disable_irq_notrace			@ disable interrupts
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	beq	no_work_pending
+ UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
+
+	/* Slower path - fall through to work_pending */
+#endif
+
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return_nosave
+slow_work_pending:
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
 	bl	do_work_pending
@@ -61,19 +81,23 @@ work_pending:
 	movlt	scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
 	ldmia	sp, {r0 - r6}			@ have to reload r0 - r6
 	b	local_restart			@ ... and off we go
+ENDPROC(ret_fast_syscall)
 
 /*
  * "slow" syscall return path.  "why" tells us if this was a real syscall.
+ * IRQs may be enabled here, so always disable them.  Note that we use the
+ * "notrace" version to avoid calling into the tracing code unnecessarily.
+ * do_work_pending() will update this state if necessary.
  */
 ENTRY(ret_to_user)
 ret_slow_syscall:
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
-	bne	work_pending
+	bne	slow_work_pending
 no_work_pending:
-	asm_trace_hardirqs_on
+	asm_trace_hardirqs_on save = 0
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -173,6 +197,8 @@ ENTRY(vector_swi)
  USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
+	uaccess_disable tbl
+
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -251,6 +277,12 @@ __sys_trace_return:
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
+__sys_trace_return_nosave:
+	enable_irq_notrace
+	mov	r0, sp
+	bl	syscall_trace_exit
+	b	ret_slow_syscall
+
 	.align	5
 #ifdef CONFIG_ALIGNMENT_TRAP
 	.type	__cr_alignment, #object
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1a0045abead7..0d22ad206d52 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -196,7 +196,7 @@
 	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
 	.endm
 
-#ifndef CONFIG_THUMB2_KERNEL
+
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
 	@ IRQs already off
@@ -215,6 +215,10 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	uaccess_restore
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +226,20 @@
 	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
 	.endm
 
 	@
@@ -241,6 +259,9 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	uaccess_restore
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r0, sp
 	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
 				@ clobber state restored below)
@@ -250,9 +271,27 @@
 	msr	spsr_cxsf, r9
 	ldr	r0, [r0, #S_R0]
 	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
 	.endm
 
+
 	.macro	restore_user_regs, fast = 0, offset = 0
+	uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
@@ -270,72 +309,16 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-
-#else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr, irq = 0
-	.if	\irq != 0
-	@ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	.else
-	@ IRQs off again before pulling preserved data off the stack
-	disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	\rpsr, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	\rpsr, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
-	.endif
-	ldr	lr, [sp, #S_SP]			@ top of the stack
-	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-
-	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
-
-	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
-	ldmia	sp, {r0 - r12}
-	mov	sp, lr
-	ldr	lr, [sp], #4
-	rfeia	sp!
-	.endm
-
-	@
-	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
-	@
-	@ For full details see non-Thumb implementation above.
-	@
-	.macro  svc_exit_via_fiq
-	add	r0, sp, #S_R2
-	ldr	lr, [sp, #S_LR]
-	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
-			        @ clobber state restored below)
-	ldmia	r0, {r2 - r12}
-	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
-	msr	cpsr_c, r1
-	sub	r0, #S_R2
-	add	r8, r0, #S_PC
-	ldmia	r0, {r0 - r1}
-	rfeia	r8
-	.endm
-
-#ifdef CONFIG_CPU_V7M
-	/*
-	 * Note we don't need to do clrex here as clearing the local monitor is
-	 * part of each exception entry and exit sequence.
-	 */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
 	.if	\offset
 	add	sp, #\offset
 	.endif
 	v7m_exception_slow_exit ret_r0 = \fast
-	.endm
-#else	/* ifdef CONFIG_CPU_V7M */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#else
+	@ Thumb mode restore
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
@@ -353,9 +336,8 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-#endif	/* ifdef CONFIG_CPU_V7M / else */
 #endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
 
 /*
  * Context tracking subsystem.  Used to instrument transitions
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index bd755d97e459..04286fd9e09c 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -399,6 +399,9 @@ ENTRY(secondary_startup)
 	sub	lr, r4, r5			@ mmu has been enabled
 	add	r3, r7, lr
 	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+ARM_BE8(eor	r4, r4, r5)			@ Swap r5 and r4 in BE:
+ARM_BE8(eor	r5, r4, r5)			@ it can be done in 3 steps
+ARM_BE8(eor	r4, r4, r5)			@ without using a temp reg.
 	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
 	badr	lr, __enable_mmu		@ return address
 	mov	r13, r12			@ __secondary_switched address
@@ -461,10 +464,7 @@ __enable_mmu:
 #ifdef CONFIG_ARM_LPAE
 	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
 #else
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mov	r5, #DACR_INIT
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 #endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 350f188c92d2..5ff4826cb154 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -39,6 +39,7 @@
 #include <linux/export.h>
 
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/outercache.h>
 #include <asm/exception.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -140,7 +141,7 @@ int __init arch_probe_nr_irqs(void)
 static bool migrate_one_irq(struct irq_desc *desc)
 {
 	struct irq_data *d = irq_desc_get_irq_data(desc);
-	const struct cpumask *affinity = d->affinity;
+	const struct cpumask *affinity = irq_data_get_affinity_mask(d);
 	struct irq_chip *c;
 	bool ret = false;
 
@@ -160,7 +161,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
-		cpumask_copy(d->affinity, affinity);
+		cpumask_copy(irq_data_get_affinity_mask(d), affinity);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c
index e39cbf488cfe..845a5dd9c42b 100644
--- a/arch/arm/kernel/jump_label.c
+++ b/arch/arm/kernel/jump_label.c
@@ -12,7 +12,7 @@ static void __arch_jump_label_transform(struct jump_entry *entry,
 	void *addr = (void *)entry->code;
 	unsigned int insn;
 
-	if (type == JUMP_LABEL_ENABLE)
+	if (type == JUMP_LABEL_JMP)
 		insn = arm_gen_branch(entry->code, entry->target);
 	else
 		insn = arm_gen_nop();
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 09f83e414a72..09413e7b49aa 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -34,9 +34,9 @@
 
 #include <asm/cputype.h>
 #include <asm/irq_regs.h>
-#include <asm/pmu.h>
 
 #include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 
 enum armv6_perf_types {
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f9b37f876e20..126dc679b230 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -21,11 +21,11 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/irq_regs.h>
-#include <asm/pmu.h>
 #include <asm/vfp.h>
 #include "../vfp/vfpinstr.h"
 
 #include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 
 /*
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 304d056d5b25..aa0499e2eef7 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -16,9 +16,9 @@
 
 #include <asm/cputype.h>
 #include <asm/irq_regs.h>
-#include <asm/pmu.h>
 
 #include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 
 enum xscale_perf_types {
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f192a2a41719..a3089bacb8d8 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -91,13 +91,6 @@ void arch_cpu_idle_exit(void)
 	ledtrig_cpu(CPU_LED_IDLE_END);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead(void)
-{
-	cpu_die();
-}
-#endif
-
 void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
@@ -129,12 +122,36 @@ void __show_regs(struct pt_regs *regs)
 	buf[4] = '\0';
 
 #ifndef CONFIG_CPU_V7M
-	printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
-		buf, interrupts_enabled(regs) ? "n" : "ff",
-		fast_interrupts_enabled(regs) ? "n" : "ff",
-		processor_modes[processor_mode(regs)],
-		isa_modes[isa_mode(regs)],
-		get_fs() == get_ds() ? "kernel" : "user");
+	{
+		unsigned int domain = get_domain();
+		const char *segment;
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		/*
+		 * Get the domain register for the parent context. In user
+		 * mode, we don't save the DACR, so lets use what it should
+		 * be. For other modes, we place it after the pt_regs struct.
+		 */
+		if (user_mode(regs))
+			domain = DACR_UACCESS_ENABLE;
+		else
+			domain = *(unsigned int *)(regs + 1);
+#endif
+
+		if ((domain & domain_mask(DOMAIN_USER)) ==
+		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+			segment = "none";
+		else if (get_fs() == get_ds())
+			segment = "kernel";
+		else
+			segment = "user";
+
+		printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
+			buf, interrupts_enabled(regs) ? "n" : "ff",
+			fast_interrupts_enabled(regs) ? "n" : "ff",
+			processor_modes[processor_mode(regs)],
+			isa_modes[isa_mode(regs)], segment);
+	}
 #else
 	printk("xPSR: %08lx\n", regs->ARM_cpsr);
 #endif
@@ -146,10 +163,9 @@ void __show_regs(struct pt_regs *regs)
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac;
+			unsigned int transbase, dac = get_domain();
 			asm("mrc p15, 0, %0, c2, c0\n\t"
-			    "mrc p15, 0, %1, c3, c0\n"
-			    : "=r" (transbase), "=r" (dac));
+			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
 			  	transbase, dac);
 		}
@@ -210,6 +226,14 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+	/*
+	 * Copy the initial value of the domain access control register
+	 * from the current thread: thread->addr_limit will have been
+	 * copied from the current thread via setup_thread_stack() in
+	 * kernel/fork.c
+	 */
+	thread->cpu_domain = get_domain();
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
deleted file mode 100644
index f90fdf4ce7c7..000000000000
--- a/arch/arm/kernel/psci.c
+++ /dev/null
@@ -1,299 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2012 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#define pr_fmt(fmt) "psci: " fmt
-
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/reboot.h>
-#include <linux/pm.h>
-#include <uapi/linux/psci.h>
-
-#include <asm/compiler.h>
-#include <asm/errno.h>
-#include <asm/psci.h>
-#include <asm/system_misc.h>
-
-struct psci_operations psci_ops;
-
-static int (*invoke_psci_fn)(u32, u32, u32, u32);
-typedef int (*psci_initcall_t)(const struct device_node *);
-
-asmlinkage int __invoke_psci_fn_hvc(u32, u32, u32, u32);
-asmlinkage int __invoke_psci_fn_smc(u32, u32, u32, u32);
-
-enum psci_function {
-	PSCI_FN_CPU_SUSPEND,
-	PSCI_FN_CPU_ON,
-	PSCI_FN_CPU_OFF,
-	PSCI_FN_MIGRATE,
-	PSCI_FN_AFFINITY_INFO,
-	PSCI_FN_MIGRATE_INFO_TYPE,
-	PSCI_FN_MAX,
-};
-
-static u32 psci_function_id[PSCI_FN_MAX];
-
-static int psci_to_linux_errno(int errno)
-{
-	switch (errno) {
-	case PSCI_RET_SUCCESS:
-		return 0;
-	case PSCI_RET_NOT_SUPPORTED:
-		return -EOPNOTSUPP;
-	case PSCI_RET_INVALID_PARAMS:
-		return -EINVAL;
-	case PSCI_RET_DENIED:
-		return -EPERM;
-	};
-
-	return -EINVAL;
-}
-
-static u32 psci_power_state_pack(struct psci_power_state state)
-{
-	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
-			& PSCI_0_2_POWER_STATE_ID_MASK) |
-		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
-		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
-		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
-		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
-}
-
-static int psci_get_version(void)
-{
-	int err;
-
-	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
-	return err;
-}
-
-static int psci_cpu_suspend(struct psci_power_state state,
-			    unsigned long entry_point)
-{
-	int err;
-	u32 fn, power_state;
-
-	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
-	power_state = psci_power_state_pack(state);
-	err = invoke_psci_fn(fn, power_state, entry_point, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_cpu_off(struct psci_power_state state)
-{
-	int err;
-	u32 fn, power_state;
-
-	fn = psci_function_id[PSCI_FN_CPU_OFF];
-	power_state = psci_power_state_pack(state);
-	err = invoke_psci_fn(fn, power_state, 0, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_CPU_ON];
-	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_migrate(unsigned long cpuid)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_MIGRATE];
-	err = invoke_psci_fn(fn, cpuid, 0, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_affinity_info(unsigned long target_affinity,
-		unsigned long lowest_affinity_level)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
-	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
-	return err;
-}
-
-static int psci_migrate_info_type(void)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
-	err = invoke_psci_fn(fn, 0, 0, 0);
-	return err;
-}
-
-static int get_set_conduit_method(struct device_node *np)
-{
-	const char *method;
-
-	pr_info("probing for conduit method from DT.\n");
-
-	if (of_property_read_string(np, "method", &method)) {
-		pr_warn("missing \"method\" property\n");
-		return -ENXIO;
-	}
-
-	if (!strcmp("hvc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_hvc;
-	} else if (!strcmp("smc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_smc;
-	} else {
-		pr_warn("invalid \"method\" property: %s\n", method);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
-{
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
-}
-
-static void psci_sys_poweroff(void)
-{
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
-}
-
-/*
- * PSCI Function IDs for v0.2+ are well defined so use
- * standard values.
- */
-static int psci_0_2_init(struct device_node *np)
-{
-	int err, ver;
-
-	err = get_set_conduit_method(np);
-
-	if (err)
-		goto out_put_node;
-
-	ver = psci_get_version();
-
-	if (ver == PSCI_RET_NOT_SUPPORTED) {
-		/* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
-		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
-		err = -EOPNOTSUPP;
-		goto out_put_node;
-	} else {
-		pr_info("PSCIv%d.%d detected in firmware.\n",
-				PSCI_VERSION_MAJOR(ver),
-				PSCI_VERSION_MINOR(ver));
-
-		if (PSCI_VERSION_MAJOR(ver) == 0 &&
-				PSCI_VERSION_MINOR(ver) < 2) {
-			err = -EINVAL;
-			pr_err("Conflicting PSCI version detected.\n");
-			goto out_put_node;
-		}
-	}
-
-	pr_info("Using standard PSCI v0.2 function IDs\n");
-	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND;
-	psci_ops.cpu_suspend = psci_cpu_suspend;
-
-	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
-	psci_ops.cpu_off = psci_cpu_off;
-
-	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON;
-	psci_ops.cpu_on = psci_cpu_on;
-
-	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE;
-	psci_ops.migrate = psci_migrate;
-
-	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO;
-	psci_ops.affinity_info = psci_affinity_info;
-
-	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
-		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
-	psci_ops.migrate_info_type = psci_migrate_info_type;
-
-	arm_pm_restart = psci_sys_reset;
-
-	pm_power_off = psci_sys_poweroff;
-
-out_put_node:
-	of_node_put(np);
-	return err;
-}
-
-/*
- * PSCI < v0.2 get PSCI Function IDs via DT.
- */
-static int psci_0_1_init(struct device_node *np)
-{
-	u32 id;
-	int err;
-
-	err = get_set_conduit_method(np);
-
-	if (err)
-		goto out_put_node;
-
-	pr_info("Using PSCI v0.1 Function IDs from DT\n");
-
-	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
-		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
-		psci_ops.cpu_suspend = psci_cpu_suspend;
-	}
-
-	if (!of_property_read_u32(np, "cpu_off", &id)) {
-		psci_function_id[PSCI_FN_CPU_OFF] = id;
-		psci_ops.cpu_off = psci_cpu_off;
-	}
-
-	if (!of_property_read_u32(np, "cpu_on", &id)) {
-		psci_function_id[PSCI_FN_CPU_ON] = id;
-		psci_ops.cpu_on = psci_cpu_on;
-	}
-
-	if (!of_property_read_u32(np, "migrate", &id)) {
-		psci_function_id[PSCI_FN_MIGRATE] = id;
-		psci_ops.migrate = psci_migrate;
-	}
-
-out_put_node:
-	of_node_put(np);
-	return err;
-}
-
-static const struct of_device_id psci_of_match[] __initconst = {
-	{ .compatible = "arm,psci", .data = psci_0_1_init},
-	{ .compatible = "arm,psci-0.2", .data = psci_0_2_init},
-	{},
-};
-
-int __init psci_init(void)
-{
-	struct device_node *np;
-	const struct of_device_id *matched_np;
-	psci_initcall_t init_fn;
-
-	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
-	if (!np)
-		return -ENODEV;
-
-	init_fn = (psci_initcall_t)matched_np->data;
-	return init_fn(np);
-}
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
index 28a1db4da704..61c04b02faeb 100644
--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@@ -17,6 +17,8 @@
 #include <linux/smp.h>
 #include <linux/of.h>
 #include <linux/delay.h>
+#include <linux/psci.h>
+
 #include <uapi/linux/psci.h>
 
 #include <asm/psci.h>
@@ -51,22 +53,34 @@ static int psci_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	if (psci_ops.cpu_on)
 		return psci_ops.cpu_on(cpu_logical_map(cpu),
-				       __pa(secondary_startup));
+					virt_to_idmap(&secondary_startup));
 	return -ENODEV;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+int psci_cpu_disable(unsigned int cpu)
+{
+	/* Fail early if we don't have CPU_OFF support */
+	if (!psci_ops.cpu_off)
+		return -EOPNOTSUPP;
+
+	/* Trusted OS will deny CPU_OFF */
+	if (psci_tos_resident_on(cpu))
+		return -EPERM;
+
+	return 0;
+}
+
 void __ref psci_cpu_die(unsigned int cpu)
 {
-       const struct psci_power_state ps = {
-               .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
-       };
+	u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
+		    PSCI_0_2_POWER_STATE_TYPE_SHIFT;
 
-       if (psci_ops.cpu_off)
-               psci_ops.cpu_off(ps);
+	if (psci_ops.cpu_off)
+		psci_ops.cpu_off(state);
 
-       /* We should never return */
-       panic("psci: cpu %d failed to shutdown\n", cpu);
+	/* We should never return */
+	panic("psci: cpu %d failed to shutdown\n", cpu);
 }
 
 int __ref psci_cpu_kill(unsigned int cpu)
@@ -109,6 +123,7 @@ bool __init psci_smp_available(void)
 struct smp_operations __initdata psci_smp_ops = {
 	.smp_boot_secondary	= psci_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable		= psci_cpu_disable,
 	.cpu_die		= psci_cpu_die,
 	.cpu_kill		= psci_cpu_kill,
 #endif
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 1a4d232796be..38269358fd25 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -50,7 +50,7 @@ static void __soft_restart(void *addr)
 	flush_cache_all();
 
 	/* Switch to the identity mapping. */
-	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_idmap(cpu_reset);
 	phys_reset((unsigned long)addr);
 
 	/* Should never get here. */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 36c18b73c1f4..20edd349d379 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -31,12 +31,14 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/sort.h>
+#include <linux/psci.h>
 
 #include <asm/unified.h>
 #include <asm/cp15.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
+#include <asm/fixmap.h>
 #include <asm/procinfo.h>
 #include <asm/psci.h>
 #include <asm/sections.h>
@@ -954,6 +956,9 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = cmd_line;
 
+	if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM))
+		early_fixmap_init();
+
 	parse_early_param();
 
 #ifdef CONFIG_MMU
@@ -972,7 +977,7 @@ void __init setup_arch(char **cmdline_p)
 	unflatten_device_tree();
 
 	arm_dt_init_cpu_maps();
-	psci_init();
+	psci_dt_init();
 	xen_early_init();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
@@ -1015,7 +1020,7 @@ static int __init topology_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_arm *cpuinfo = &per_cpu(cpu_data, cpu);
-		cpuinfo->cpu.hotpluggable = 1;
+		cpuinfo->cpu.hotpluggable = platform_can_hotplug_cpu(cpu);
 		register_cpu(&cpuinfo->cpu, cpu);
 	}
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 423663e23791..b6cda06b455f 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -562,6 +562,12 @@ static int do_signal(struct pt_regs *regs, int syscall)
 asmlinkage int
 do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 {
+	/*
+	 * The assembly code enters us with IRQs off, but it hasn't
+	 * informed the tracing code of that for efficiency reasons.
+	 * Update the trace code with the current status.
+	 */
+	trace_hardirqs_off();
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 90dfbedfbfb8..48185a773852 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/cpu.h>
 #include <linux/seq_file.h>
 #include <linux/irq.h>
+#include <linux/nmi.h>
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
 #include <linux/completion.h>
@@ -72,6 +73,7 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
+	IPI_CPU_BACKTRACE = 15,
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -175,13 +177,26 @@ static int platform_cpu_disable(unsigned int cpu)
 	if (smp_ops.cpu_disable)
 		return smp_ops.cpu_disable(cpu);
 
+	return 0;
+}
+
+int platform_can_hotplug_cpu(unsigned int cpu)
+{
+	/* cpu_die must be specified to support hotplug */
+	if (!smp_ops.cpu_die)
+		return 0;
+
+	if (smp_ops.cpu_can_disable)
+		return smp_ops.cpu_can_disable(cpu);
+
 	/*
 	 * By default, allow disabling all CPUs except the first one,
 	 * since this is special on a lot of platforms, e.g. because
 	 * of clock tick interrupts.
 	 */
-	return cpu == 0 ? -EPERM : 0;
+	return cpu != 0;
 }
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -253,7 +268,7 @@ void __cpu_die(unsigned int cpu)
  * of the other hotplug-cpu capable cores, so presumably coming
  * out of idle fixes this.
  */
-void __ref cpu_die(void)
+void arch_cpu_idle_dead(void)
 {
 	unsigned int cpu = smp_processor_id();
 
@@ -578,7 +593,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry(ipi_types[ipinr]);
+		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 	}
 
@@ -630,6 +645,12 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+	case IPI_CPU_BACKTRACE:
+		irq_enter();
+		nmi_cpu_backtrace(regs);
+		irq_exit();
+		break;
+
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n",
 		        cpu, ipinr);
@@ -637,7 +658,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit(ipi_types[ipinr]);
+		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 	set_irq_regs(old_regs);
 }
 
@@ -724,3 +745,13 @@ static int __init register_cpufreq_notifier(void)
 core_initcall(register_cpufreq_notifier);
 
 #endif
+
+static void raise_nmi(cpumask_t *mask)
+{
+	smp_cross_call(mask, IPI_CPU_BACKTRACE);
+}
+
+void arch_trigger_all_cpu_backtrace(bool include_self)
+{
+	nmi_trigger_all_cpu_backtrace(include_self, raise_nmi);
+}
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 172c6a05d27f..e9035cda1485 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -36,29 +36,30 @@ static DEFINE_PER_CPU(bool, percpu_setup_called);
 static struct clock_event_device __percpu *twd_evt;
 static int twd_ppi;
 
-static void twd_set_mode(enum clock_event_mode mode,
-			struct clock_event_device *clk)
+static int twd_shutdown(struct clock_event_device *clk)
 {
-	unsigned long ctrl;
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE
-			| TWD_TIMER_CONTROL_PERIODIC;
-		writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
-			twd_base + TWD_TIMER_LOAD);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* period set, and timer enabled in 'next_event' hook */
-		ctrl = TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_ONESHOT;
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		ctrl = 0;
-	}
+	writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
+	return 0;
+}
 
+static int twd_set_oneshot(struct clock_event_device *clk)
+{
+	/* period set, and timer enabled in 'next_event' hook */
+	writel_relaxed(TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_ONESHOT,
+		       twd_base + TWD_TIMER_CONTROL);
+	return 0;
+}
+
+static int twd_set_periodic(struct clock_event_device *clk)
+{
+	unsigned long ctrl = TWD_TIMER_CONTROL_ENABLE |
+			     TWD_TIMER_CONTROL_IT_ENABLE |
+			     TWD_TIMER_CONTROL_PERIODIC;
+
+	writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
+		       twd_base + TWD_TIMER_LOAD);
 	writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
+	return 0;
 }
 
 static int twd_set_next_event(unsigned long evt,
@@ -94,7 +95,7 @@ static void twd_timer_stop(void)
 {
 	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 
-	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
+	twd_shutdown(clk);
 	disable_percpu_irq(clk->irq);
 }
 
@@ -296,7 +297,10 @@ static void twd_timer_setup(void)
 	clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
 			CLOCK_EVT_FEAT_C3STOP;
 	clk->rating = 350;
-	clk->set_mode = twd_set_mode;
+	clk->set_state_shutdown = twd_shutdown;
+	clk->set_state_periodic = twd_set_periodic;
+	clk->set_state_oneshot = twd_set_oneshot;
+	clk->tick_resume = twd_shutdown;
 	clk->set_next_event = twd_set_next_event;
 	clk->irq = twd_ppi;
 	clk->cpumask = cpumask_of(cpu);
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 1361756782c7..5b26e7efa9ea 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -141,11 +141,14 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 
 	while (1) {
 		unsigned long temp;
+		unsigned int __ua_flags;
 
+		__ua_flags = uaccess_save_and_enable();
 		if (type == TYPE_SWPB)
 			__user_swpb_asm(*data, address, res, temp);
 		else
 			__user_swp_asm(*data, address, res, temp);
+		uaccess_restore(__ua_flags);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d358226236f2..969f9d9e665f 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -870,7 +870,6 @@ void __init early_trap_init(void *vectors_base)
 	kuser_init(vectors_base);
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
-	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index efe17dd9b921..54a5aeab988d 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -296,7 +296,6 @@ static bool tk_is_cntvct(const struct timekeeper *tk)
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	struct timespec64 *wtm = &tk->wall_to_monotonic;
 
 	if (!cntvct_ok) {
@@ -308,10 +307,10 @@ void update_vsyscall(struct timekeeper *tk)
 
 	vdso_write_begin(vdso_data);
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->tk_is_cntvct			= tk_is_cntvct(tk);
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= (u32)(tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift);
 	vdso_data->wtm_clock_sec		= wtm->tv_sec;
 	vdso_data->wtm_clock_nsec		= wtm->tv_nsec;
 
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 1710fd7db2d5..970d6c043774 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -12,14 +12,14 @@
 
 		.text
 
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz)
  * Purpose  : clear some user memory
  * Params   : addr - user memory address to clear
  *          : sz   - number of bytes to clear
  * Returns  : number of bytes NOT cleared
  */
 ENTRY(__clear_user_std)
-WEAK(__clear_user)
+WEAK(arm_clear_user)
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4
@@ -44,7 +44,7 @@ WEAK(__clear_user)
 USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
-ENDPROC(__clear_user)
+ENDPROC(arm_clear_user)
 ENDPROC(__clear_user_std)
 
 		.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a235b9952be..1512bebfbf1b 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_from_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_from_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -89,11 +89,11 @@
 
 	.text
 
-ENTRY(__copy_from_user)
+ENTRY(arm_copy_from_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_from_user)
+ENDPROC(arm_copy_from_user)
 
 	.pushsection .fixup,"ax"
 	.align 0
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 9648b0675a3e..caf5019d8161 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_to_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_to_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -93,11 +93,11 @@
 	.text
 
 ENTRY(__copy_to_user_std)
-WEAK(__copy_to_user)
+WEAK(arm_copy_to_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_to_user)
+ENDPROC(arm_copy_to_user)
 ENDPROC(__copy_to_user_std)
 
 	.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1d0957e61f89..1712f132b80d 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -17,6 +17,19 @@
 
 		.text
 
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		.macro	save_regs
+		mrc	p15, 0, ip, c3, c0, 0
+		stmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		uaccess_enable ip
+		.endm
+
+		.macro	load_regs
+		ldmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		mcr	p15, 0, ip, c3, c0, 0
+		ret	lr
+		.endm
+#else
 		.macro	save_regs
 		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
@@ -24,6 +37,7 @@
 		.macro	load_regs
 		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
+#endif
 
 		.macro	load1b,	reg1
 		ldrusr	\reg1, r0, 1
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 7797e81e40e0..64111bd4440b 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -61,8 +61,10 @@
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
 
+ENTRY(mmiocpy)
 ENTRY(memcpy)
 
 #include "copy_template.S"
 
 ENDPROC(memcpy)
+ENDPROC(mmiocpy)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index a4ee97b5a2bf..3c65e3bd790f 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -16,6 +16,7 @@
 	.text
 	.align	5
 
+ENTRY(mmioset)
 ENTRY(memset)
 UNWIND( .fnstart         )
 	ands	r3, r0, #3		@ 1 unaligned?
@@ -133,3 +134,4 @@ UNWIND( .fnstart            )
 	b	1b
 UNWIND( .fnend   )
 ENDPROC(memset)
+ENDPROC(mmioset)
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 3e58d710013c..d72b90905132 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -96,7 +96,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 	}
 
 	/* the mmap semaphore is taken only if not in an atomic context */
-	atomic = in_atomic();
+	atomic = faulthandler_disabled();
 
 	if (!atomic)
 		down_read(&current->mm->mmap_sem);
@@ -136,7 +136,7 @@ out:
 }
 
 unsigned long
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	/*
 	 * This test is stubbed out of the main function above to keep
@@ -190,7 +190,7 @@ out:
 	return n;
 }
 
-unsigned long __clear_user(void __user *addr, unsigned long n)
+unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
 	if (n < 64)
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index fd95f34945f4..89a755b90db2 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -8,6 +8,18 @@ menuconfig ARCH_AT91
 	select SOC_BUS
 
 if ARCH_AT91
+config SOC_SAMA5D2
+	bool "SAMA5D2 family" if ARCH_MULTI_V7
+	select SOC_SAMA5
+	select CACHE_L2X0
+	select HAVE_FB_ATMEL
+	select HAVE_AT91_UTMI
+	select HAVE_AT91_USB_CLK
+	select HAVE_AT91_H32MX
+	select HAVE_AT91_GENERATED_CLK
+	help
+	  Select this if ou are using one of Atmel's SAMA5D2 family SoC.
+
 config SOC_SAMA5D3
 	bool "SAMA5D3 family" if ARCH_MULTI_V7
 	select SOC_SAMA5
diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index eaf58f88ef5d..c1a7c6cc00e1 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -8,7 +8,6 @@
  * Licensed under GPLv2 or later.
  */
 
-#include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 
@@ -38,7 +37,7 @@ static void __init at91rm9200_dt_device_init(void)
 	at91rm9200_pm_init();
 }
 
-static const char *at91rm9200_dt_board_compat[] __initconst = {
+static const char *const at91rm9200_dt_board_compat[] __initconst = {
 	"atmel,at91rm9200",
 	NULL
 };
diff --git a/arch/arm/mach-at91/at91sam9.c b/arch/arm/mach-at91/at91sam9.c
index e47a2093a0e7..7eb64f763034 100644
--- a/arch/arm/mach-at91/at91sam9.c
+++ b/arch/arm/mach-at91/at91sam9.c
@@ -72,7 +72,7 @@ static void __init at91sam9_dt_device_init(void)
 	at91sam9260_pm_init();
 }
 
-static const char *at91_dt_board_compat[] __initconst = {
+static const char *const at91_dt_board_compat[] __initconst = {
 	"atmel,at91sam9",
 	NULL
 };
@@ -89,7 +89,7 @@ static void __init at91sam9g45_dt_device_init(void)
 	at91sam9g45_pm_init();
 }
 
-static const char *at91sam9g45_board_compat[] __initconst = {
+static const char *const at91sam9g45_board_compat[] __initconst = {
 	"atmel,at91sam9g45",
 	NULL
 };
@@ -106,7 +106,7 @@ static void __init at91sam9x5_dt_device_init(void)
 	at91sam9x5_pm_init();
 }
 
-static const char *at91sam9x5_board_compat[] __initconst = {
+static const char *const at91sam9x5_board_compat[] __initconst = {
 	"atmel,at91sam9x5",
 	"atmel,at91sam9n12",
 	NULL
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index e24df77abd79..80e277cfcc8b 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -311,7 +311,7 @@ static void at91sam9_sdram_standby(void)
 		at91_ramc_write(1, AT91_SDRAMC_LPR, saved_lpr1);
 }
 
-static const struct of_device_id ramc_ids[] __initconst = {
+static const struct of_device_id const ramc_ids[] __initconst = {
 	{ .compatible = "atmel,at91rm9200-sdramc", .data = at91rm9200_standby },
 	{ .compatible = "atmel,at91sam9260-sdramc", .data = at91sam9_sdram_standby },
 	{ .compatible = "atmel,at91sam9g45-ddramc", .data = at91_ddr_standby },
@@ -369,7 +369,7 @@ static void __init at91_pm_sram_init(void)
 		return;
 	}
 
-	sram_pool = gen_pool_get(&pdev->dev);
+	sram_pool = gen_pool_get(&pdev->dev, NULL);
 	if (!sram_pool) {
 		pr_warn("%s: sram pool unavailable!\n", __func__);
 		return;
diff --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c
index 41d829d8e7d5..d9cf6799aec0 100644
--- a/arch/arm/mach-at91/sama5.c
+++ b/arch/arm/mach-at91/sama5.c
@@ -18,6 +18,8 @@
 #include "soc.h"
 
 static const struct at91_soc sama5_socs[] = {
+	AT91_SOC(SAMA5D2_CIDR_MATCH, SAMA5D27_EXID_MATCH,
+		 "sama5d27", "sama5d2"),
 	AT91_SOC(SAMA5D3_CIDR_MATCH, SAMA5D31_EXID_MATCH,
 		 "sama5d31", "sama5d3"),
 	AT91_SOC(SAMA5D3_CIDR_MATCH, SAMA5D33_EXID_MATCH,
@@ -52,7 +54,7 @@ static void __init sama5_dt_device_init(void)
 	at91sam9x5_pm_init();
 }
 
-static const char *sama5_dt_board_compat[] __initconst = {
+static const char *const sama5_dt_board_compat[] __initconst = {
 	"atmel,sama5",
 	NULL
 };
@@ -63,7 +65,8 @@ DT_MACHINE_START(sama5_dt, "Atmel SAMA5")
 	.dt_compat	= sama5_dt_board_compat,
 MACHINE_END
 
-static const char *sama5_alt_dt_board_compat[] __initconst = {
+static const char *const sama5_alt_dt_board_compat[] __initconst = {
+	"atmel,sama5d2",
 	"atmel,sama5d4",
 	NULL
 };
diff --git a/arch/arm/mach-at91/soc.h b/arch/arm/mach-at91/soc.h
index be23c400596b..8ede0ef86172 100644
--- a/arch/arm/mach-at91/soc.h
+++ b/arch/arm/mach-at91/soc.h
@@ -62,6 +62,9 @@ at91_soc_init(const struct at91_soc *socs);
 #define AT91SAM9XE256_CIDR_MATCH	0x329a93a0
 #define AT91SAM9XE512_CIDR_MATCH	0x329aa3a0
 
+#define SAMA5D2_CIDR_MATCH		0x0a5c08c0
+#define SAMA5D27_EXID_MATCH		0x00000021
+
 #define SAMA5D3_CIDR_MATCH		0x0a5c07c0
 #define SAMA5D31_EXID_MATCH		0x00444300
 #define SAMA5D33_EXID_MATCH		0x00414300
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 0ac9e4b3b265..1319c3c14327 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -140,10 +140,12 @@ config ARCH_BCM_63XX
 config ARCH_BRCMSTB
 	bool "Broadcom BCM7XXX based boards" if ARCH_MULTI_V7
 	select ARM_GIC
+	select ARM_ERRATA_798181 if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select BRCMSTB_GISB_ARB
 	select BRCMSTB_L2_IRQ
 	select BCM7120_L2_IRQ
+	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	help
 	  Say Y if you intend to run the kernel on a Broadcom ARM-based STB
diff --git a/arch/arm/mach-bcm/Makefile b/arch/arm/mach-bcm/Makefile
index 4fb0da458e91..1780a3ff42f9 100644
--- a/arch/arm/mach-bcm/Makefile
+++ b/arch/arm/mach-bcm/Makefile
@@ -39,10 +39,8 @@ obj-$(CONFIG_ARCH_BCM_5301X)	+= bcm_5301x.o
 
 # BCM63XXx
 ifeq ($(CONFIG_ARCH_BCM_63XX),y)
-CFLAGS_bcm63xx_headsmp.o	+= -march=armv7-a
 obj-y				+= bcm63xx.o
-obj-$(CONFIG_SMP)		+= bcm63xx_smp.o bcm63xx_headsmp.o \
-				   bcm63xx_pmb.o
+obj-$(CONFIG_SMP)		+= bcm63xx_smp.o bcm63xx_pmb.o
 endif
 
 ifeq ($(CONFIG_ARCH_BRCMSTB),y)
diff --git a/arch/arm/mach-bcm/bcm63xx_headsmp.S b/arch/arm/mach-bcm/bcm63xx_headsmp.S
deleted file mode 100644
index c7af397c7f14..000000000000
--- a/arch/arm/mach-bcm/bcm63xx_headsmp.S
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- *  Copyright (C) 2015, Broadcom Corporation
- *  All Rights Reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/assembler.h>
-
-ENTRY(bcm63138_secondary_startup)
- ARM_BE8(setend	be)
-	/*
-	 * L1 cache does have unpredictable contents at power-up clean its
-	 * contents without flushing
-	 */
-	bl      v7_invalidate_l1
-	nop
-
-	b	secondary_startup
-ENDPROC(bcm63138_secondary_startup)
diff --git a/arch/arm/mach-bcm/bcm63xx_smp.c b/arch/arm/mach-bcm/bcm63xx_smp.c
index 3f014f18cea5..19be90421f4d 100644
--- a/arch/arm/mach-bcm/bcm63xx_smp.c
+++ b/arch/arm/mach-bcm/bcm63xx_smp.c
@@ -127,7 +127,7 @@ static int bcm63138_smp_boot_secondary(unsigned int cpu,
 	}
 
 	/* Locate the secondary CPU node */
-	dn = of_get_cpu_node(cpu_logical_map(cpu), NULL);
+	dn = of_get_cpu_node(cpu, NULL);
 	if (!dn) {
 		pr_err("SMP: failed to locate secondary CPU%d node\n", cpu);
 		ret = -ENODEV;
@@ -135,7 +135,7 @@ static int bcm63138_smp_boot_secondary(unsigned int cpu,
 	}
 
 	/* Write the secondary init routine to the BootLUT reset vector */
-	val = virt_to_phys(bcm63138_secondary_startup);
+	val = virt_to_phys(secondary_startup);
 	writel_relaxed(val, bootlut_base + BOOTLUT_RESET_VECT);
 
 	/* Power up the core, will jump straight to its reset vector when we
diff --git a/arch/arm/mach-bcm/bcm63xx_smp.h b/arch/arm/mach-bcm/bcm63xx_smp.h
index 50b76044536e..9c6d50e2b111 100644
--- a/arch/arm/mach-bcm/bcm63xx_smp.h
+++ b/arch/arm/mach-bcm/bcm63xx_smp.h
@@ -3,7 +3,6 @@
 
 struct device_node;
 
-extern void bcm63138_secondary_startup(void);
 extern int bcm63xx_pmb_power_on_cpu(struct device_node *dn);
 
 #endif /* __BCM63XX_SMP_H */
diff --git a/arch/arm/mach-bcm/bcm_5301x.c b/arch/arm/mach-bcm/bcm_5301x.c
index 7aef92720eb4..5478fe6bcce6 100644
--- a/arch/arm/mach-bcm/bcm_5301x.c
+++ b/arch/arm/mach-bcm/bcm_5301x.c
@@ -44,7 +44,7 @@ static void __init bcm5301x_init_early(void)
 			"imprecise external abort");
 }
 
-static const char __initconst *bcm5301x_dt_compat[] = {
+static const char *const bcm5301x_dt_compat[] __initconst = {
 	"brcm,bcm4708",
 	NULL,
 };
diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c
index a55a7ecf146a..cf3f8658f0e5 100644
--- a/arch/arm/mach-bcm/bcm_kona_smc.c
+++ b/arch/arm/mach-bcm/bcm_kona_smc.c
@@ -33,7 +33,7 @@ struct bcm_kona_smc_data {
 	unsigned result;
 };
 
-static const struct of_device_id bcm_kona_smc_ids[] __initconst = {
+static const struct of_device_id const bcm_kona_smc_ids[] __initconst = {
 	{.compatible = "brcm,kona-smc"},
 	{.compatible = "bcm,kona-smc"}, /* deprecated name */
 	{},
diff --git a/arch/arm/mach-clps711x/board-autcpu12.c b/arch/arm/mach-clps711x/board-autcpu12.c
index 45abf6bd5f68..c3d964221767 100644
--- a/arch/arm/mach-clps711x/board-autcpu12.c
+++ b/arch/arm/mach-clps711x/board-autcpu12.c
@@ -160,7 +160,7 @@ static struct platform_device autcpu12_mmgpio_pdev __initdata = {
 	},
 };
 
-static const struct gpio autcpu12_gpios[] __initconst = {
+static const struct gpio const autcpu12_gpios[] __initconst = {
 	{ AUTCPU12_DPOT_CS,	GPIOF_OUT_INIT_HIGH,	"DPOT CS" },
 	{ AUTCPU12_DPOT_CLK,	GPIOF_OUT_INIT_LOW,	"DPOT CLK" },
 	{ AUTCPU12_DPOT_UD,	GPIOF_OUT_INIT_LOW,	"DPOT UD" },
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index 4e9837ded96d..9b1dc223d8d3 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -113,30 +113,33 @@ void cns3xxx_power_off(void)
  */
 static void __iomem *cns3xxx_tmr1;
 
-static void cns3xxx_timer_set_mode(enum clock_event_mode mode,
-				   struct clock_event_device *clk)
+static int cns3xxx_shutdown(struct clock_event_device *clk)
+{
+	writel(0, cns3xxx_tmr1 + TIMER1_2_CONTROL_OFFSET);
+	return 0;
+}
+
+static int cns3xxx_set_oneshot(struct clock_event_device *clk)
+{
+	unsigned long ctrl = readl(cns3xxx_tmr1 + TIMER1_2_CONTROL_OFFSET);
+
+	/* period set, and timer enabled in 'next_event' hook */
+	ctrl |= (1 << 2) | (1 << 9);
+	writel(ctrl, cns3xxx_tmr1 + TIMER1_2_CONTROL_OFFSET);
+	return 0;
+}
+
+static int cns3xxx_set_periodic(struct clock_event_device *clk)
 {
 	unsigned long ctrl = readl(cns3xxx_tmr1 + TIMER1_2_CONTROL_OFFSET);
 	int pclk = cns3xxx_cpu_clock() / 8;
 	int reload;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		reload = pclk * 20 / (3 * HZ) * 0x25000;
-		writel(reload, cns3xxx_tmr1 + TIMER1_AUTO_RELOAD_OFFSET);
-		ctrl |= (1 << 0) | (1 << 2) | (1 << 9);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* period set, and timer enabled in 'next_event' hook */
-		ctrl |= (1 << 2) | (1 << 9);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		ctrl = 0;
-	}
-
+	reload = pclk * 20 / (3 * HZ) * 0x25000;
+	writel(reload, cns3xxx_tmr1 + TIMER1_AUTO_RELOAD_OFFSET);
+	ctrl |= (1 << 0) | (1 << 2) | (1 << 9);
 	writel(ctrl, cns3xxx_tmr1 + TIMER1_2_CONTROL_OFFSET);
+	return 0;
 }
 
 static int cns3xxx_timer_set_next_event(unsigned long evt,
@@ -151,12 +154,16 @@ static int cns3xxx_timer_set_next_event(unsigned long evt,
 }
 
 static struct clock_event_device cns3xxx_tmr1_clockevent = {
-	.name		= "cns3xxx timer1",
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= cns3xxx_timer_set_mode,
-	.set_next_event	= cns3xxx_timer_set_next_event,
-	.rating		= 350,
-	.cpumask	= cpu_all_mask,
+	.name			= "cns3xxx timer1",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= cns3xxx_shutdown,
+	.set_state_periodic	= cns3xxx_set_periodic,
+	.set_state_oneshot	= cns3xxx_set_oneshot,
+	.tick_resume		= cns3xxx_shutdown,
+	.set_next_event		= cns3xxx_timer_set_next_event,
+	.rating			= 350,
+	.cpumask		= cpu_all_mask,
 };
 
 static void __init cns3xxx_clockevents_init(unsigned int timer_irq)
@@ -339,7 +346,7 @@ static struct usb_ohci_pdata cns3xxx_usb_ohci_pdata = {
 	.power_off	= csn3xxx_usb_power_off,
 };
 
-static struct of_dev_auxdata cns3xxx_auxdata[] __initconst = {
+static const struct of_dev_auxdata const cns3xxx_auxdata[] __initconst = {
 	{ "intel,usb-ehci", CNS3XXX_USB_BASE, "ehci-platform", &cns3xxx_usb_ehci_pdata },
 	{ "intel,usb-ohci", CNS3XXX_USB_OHCI_BASE, "ohci-platform", &cns3xxx_usb_ohci_pdata },
 	{ "cavium,cns3420-ahci", CNS3XXX_SATA2_BASE, "ahci", NULL },
@@ -392,7 +399,7 @@ static void __init cns3xxx_init(void)
                         cns3xxx_auxdata, NULL);
 }
 
-static const char *cns3xxx_dt_compat[] __initdata = {
+static const char *const cns3xxx_dt_compat[] __initconst = {
 	"cavium,cns3410",
 	"cavium,cns3420",
 	NULL,
diff --git a/arch/arm/mach-davinci/cp_intc.c b/arch/arm/mach-davinci/cp_intc.c
index 006dae8dfe44..507aad4b8dd9 100644
--- a/arch/arm/mach-davinci/cp_intc.c
+++ b/arch/arm/mach-davinci/cp_intc.c
@@ -85,23 +85,13 @@ static int cp_intc_set_irq_type(struct irq_data *d, unsigned int flow_type)
 	return 0;
 }
 
-/*
- * Faking this allows us to to work with suspend functions of
- * generic drivers which call {enable|disable}_irq_wake for
- * wake up interrupt sources (eg RTC on DA850).
- */
-static int cp_intc_set_wake(struct irq_data *d, unsigned int on)
-{
-	return 0;
-}
-
 static struct irq_chip cp_intc_irq_chip = {
 	.name		= "cp_intc",
 	.irq_ack	= cp_intc_ack_irq,
 	.irq_mask	= cp_intc_mask_irq,
 	.irq_unmask	= cp_intc_unmask_irq,
 	.irq_set_type	= cp_intc_set_irq_type,
-	.irq_set_wake	= cp_intc_set_wake,
+	.flags		= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static struct irq_domain *cp_intc_domain;
@@ -112,7 +102,7 @@ static int cp_intc_host_map(struct irq_domain *h, unsigned int virq,
 	pr_debug("cp_intc_host_map(%d, 0x%lx)\n", virq, hw);
 
 	irq_set_chip(virq, &cp_intc_irq_chip);
-	set_irq_flags(virq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(virq);
 	irq_set_handler(virq, handle_edge_irq);
 	return 0;
 }
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 3b8740c083c4..676997895e13 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -715,7 +715,7 @@ const short da850_lcdcntl_pins[] __initconst = {
 	-1
 };
 
-const short da850_vpif_capture_pins[] __initdata = {
+const short da850_vpif_capture_pins[] __initconst = {
 	DA850_VPIF_DIN0, DA850_VPIF_DIN1, DA850_VPIF_DIN2, DA850_VPIF_DIN3,
 	DA850_VPIF_DIN4, DA850_VPIF_DIN5, DA850_VPIF_DIN6, DA850_VPIF_DIN7,
 	DA850_VPIF_DIN8, DA850_VPIF_DIN9, DA850_VPIF_DIN10, DA850_VPIF_DIN11,
@@ -725,7 +725,7 @@ const short da850_vpif_capture_pins[] __initdata = {
 	-1
 };
 
-const short da850_vpif_display_pins[] __initdata = {
+const short da850_vpif_display_pins[] __initconst = {
 	DA850_VPIF_DOUT0, DA850_VPIF_DOUT1, DA850_VPIF_DOUT2, DA850_VPIF_DOUT3,
 	DA850_VPIF_DOUT4, DA850_VPIF_DOUT5, DA850_VPIF_DOUT6, DA850_VPIF_DOUT7,
 	DA850_VPIF_DOUT8, DA850_VPIF_DOUT9, DA850_VPIF_DOUT10,
diff --git a/arch/arm/mach-davinci/da8xx-dt.c b/arch/arm/mach-davinci/da8xx-dt.c
index 438f68547f4c..06b6451225c1 100644
--- a/arch/arm/mach-davinci/da8xx-dt.c
+++ b/arch/arm/mach-davinci/da8xx-dt.c
@@ -20,7 +20,7 @@
 
 #define DA8XX_NUM_UARTS	3
 
-static const struct of_device_id da8xx_irq_match[] __initconst = {
+static const struct of_device_id const da8xx_irq_match[] __initconst = {
 	{ .compatible = "ti,cp-intc", .data = cp_intc_of_init, },
 	{ }
 };
@@ -59,7 +59,7 @@ static void __init da850_init_machine(void)
 
 }
 
-static const char *da850_boards_compat[] __initdata = {
+static const char *const da850_boards_compat[] __initconst = {
 	"enbw,cmc",
 	"ti,da850-evm",
 	"ti,da850",
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index ddfdd820e6f2..29e08aac8294 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -1010,11 +1010,13 @@ static struct davinci_spi_platform_data da8xx_spi_pdata[] = {
 		.version	= SPI_VERSION_2,
 		.intr_line	= 1,
 		.dma_event_q	= EVENTQ_0,
+		.prescaler_limit = 2,
 	},
 	[1] = {
 		.version	= SPI_VERSION_2,
 		.intr_line	= 1,
 		.dma_event_q	= EVENTQ_0,
+		.prescaler_limit = 2,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 9cbeda798584..567dc56fe8cd 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -411,6 +411,7 @@ static struct davinci_spi_platform_data dm355_spi0_pdata = {
 	.num_chipselect = 2,
 	.cshold_bug	= true,
 	.dma_event_q	= EVENTQ_1,
+	.prescaler_limit = 1,
 };
 static struct platform_device dm355_spi0_device = {
 	.name = "spi_davinci",
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index e3a3c54b6832..6a890a8486d0 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -646,6 +646,7 @@ static struct davinci_spi_platform_data dm365_spi0_pdata = {
 	.version 	= SPI_VERSION_1,
 	.num_chipselect = 2,
 	.dma_event_q	= EVENTQ_3,
+	.prescaler_limit = 1,
 };
 
 static struct resource dm365_spi0_resources[] = {
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index 160c9602f490..6c18445a4639 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -303,36 +303,42 @@ static int davinci_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void davinci_set_mode(enum clock_event_mode mode,
-			     struct clock_event_device *evt)
+static int davinci_shutdown(struct clock_event_device *evt)
 {
 	struct timer_s *t = &timers[TID_CLOCKEVENT];
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		t->period = davinci_clock_tick_rate / (HZ);
-		t->opts &= ~TIMER_OPTS_STATE_MASK;
-		t->opts |= TIMER_OPTS_PERIODIC;
-		timer32_config(t);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		t->opts &= ~TIMER_OPTS_STATE_MASK;
-		t->opts |= TIMER_OPTS_ONESHOT;
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		t->opts &= ~TIMER_OPTS_STATE_MASK;
-		t->opts |= TIMER_OPTS_DISABLED;
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	t->opts &= ~TIMER_OPTS_STATE_MASK;
+	t->opts |= TIMER_OPTS_DISABLED;
+	return 0;
+}
+
+static int davinci_set_oneshot(struct clock_event_device *evt)
+{
+	struct timer_s *t = &timers[TID_CLOCKEVENT];
+
+	t->opts &= ~TIMER_OPTS_STATE_MASK;
+	t->opts |= TIMER_OPTS_ONESHOT;
+	return 0;
+}
+
+static int davinci_set_periodic(struct clock_event_device *evt)
+{
+	struct timer_s *t = &timers[TID_CLOCKEVENT];
+
+	t->period = davinci_clock_tick_rate / (HZ);
+	t->opts &= ~TIMER_OPTS_STATE_MASK;
+	t->opts |= TIMER_OPTS_PERIODIC;
+	timer32_config(t);
+	return 0;
 }
 
 static struct clock_event_device clockevent_davinci = {
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event	= davinci_set_next_event,
-	.set_mode	= davinci_set_mode,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= davinci_set_next_event,
+	.set_state_shutdown	= davinci_shutdown,
+	.set_state_periodic	= davinci_set_periodic,
+	.set_state_oneshot	= davinci_set_oneshot,
 };
 
 
diff --git a/arch/arm/mach-digicolor/digicolor.c b/arch/arm/mach-digicolor/digicolor.c
index cfc88d1caa47..4d62f1bde4ed 100644
--- a/arch/arm/mach-digicolor/digicolor.c
+++ b/arch/arm/mach-digicolor/digicolor.c
@@ -8,7 +8,7 @@
 
 #include <asm/mach/arch.h>
 
-static const char *digicolor_dt_compat[] __initconst = {
+static const char *const digicolor_dt_compat[] __initconst = {
 	"cnxt,cx92755",
 	NULL,
 };
diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c
index df0223f76fa9..305d7c6242bb 100644
--- a/arch/arm/mach-dove/irq.c
+++ b/arch/arm/mach-dove/irq.c
@@ -69,8 +69,9 @@ static struct irq_chip pmu_irq_chip = {
 	.irq_ack	= pmu_irq_ack,
 };
 
-static void pmu_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void pmu_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned long cause = readl(PMU_INTERRUPT_CAUSE);
 
 	cause &= readl(PMU_INTERRUPT_MASK);
@@ -172,7 +173,7 @@ void __init dove_init_irq(void)
 	for (i = IRQ_DOVE_PMU_START; i < NR_IRQS; i++) {
 		irq_set_chip_and_handler(i, &pmu_irq_chip, handle_level_irq);
 		irq_set_status_flags(i, IRQ_LEVEL);
-		set_irq_flags(i, IRQF_VALID);
+		irq_clear_status_flags(i, IRQ_NOREQUEST);
 	}
 	irq_set_chained_handler(IRQ_DOVE_PMU, pmu_irq_handler);
 }
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index 8254e716b095..688e5fed49a7 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -65,7 +65,7 @@ static void __init ebsa110_init_irq(void)
 	for (irq = 0; irq < NR_IRQS; irq++) {
 		irq_set_chip_and_handler(irq, &ebsa110_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 }
 
diff --git a/arch/arm/mach-ep93xx/Kconfig b/arch/arm/mach-ep93xx/Kconfig
index bec570ae6494..61a75ca3684e 100644
--- a/arch/arm/mach-ep93xx/Kconfig
+++ b/arch/arm/mach-ep93xx/Kconfig
@@ -15,45 +15,8 @@ config CRUNCH
 
 comment "EP93xx Platforms"
 
-choice
-	prompt "EP93xx first SDRAM bank selection"
-	default EP93XX_SDCE3_SYNC_PHYS_OFFSET
-
-config EP93XX_SDCE3_SYNC_PHYS_OFFSET
-	bool "0x00000000 - SDCE3/SyncBoot"
-	help
-	  Select this option if you want support for EP93xx boards with the
-	  first SDRAM bank at 0x00000000.
-
-config EP93XX_SDCE0_PHYS_OFFSET
-	bool "0xc0000000 - SDCEO"
-	help
-	  Select this option if you want support for EP93xx boards with the
-	  first SDRAM bank at 0xc0000000.
-
-config EP93XX_SDCE1_PHYS_OFFSET
-	bool "0xd0000000 - SDCE1"
-	help
-	  Select this option if you want support for EP93xx boards with the
-	  first SDRAM bank at 0xd0000000.
-
-config EP93XX_SDCE2_PHYS_OFFSET
-	bool "0xe0000000 - SDCE2"
-	help
-	  Select this option if you want support for EP93xx boards with the
-	  first SDRAM bank at 0xe0000000.
-
-config EP93XX_SDCE3_ASYNC_PHYS_OFFSET
-	bool "0xf0000000 - SDCE3/AsyncBoot"
-	help
-	  Select this option if you want support for EP93xx boards with the
-	  first SDRAM bank at 0xf0000000.
-
-endchoice
-
 config MACH_ADSSPHERE
 	bool "Support ADS Sphere"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	help
 	  Say 'Y' here if you want your kernel to support the ADS
 	  Sphere board.
@@ -63,7 +26,6 @@ config MACH_EDB93XX
 
 config MACH_EDB9301
 	bool "Support Cirrus Logic EDB9301"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -71,7 +33,6 @@ config MACH_EDB9301
 
 config MACH_EDB9302
 	bool "Support Cirrus Logic EDB9302"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -79,7 +40,6 @@ config MACH_EDB9302
 
 config MACH_EDB9302A
 	bool "Support Cirrus Logic EDB9302A"
-	depends on EP93XX_SDCE0_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -87,7 +47,6 @@ config MACH_EDB9302A
 
 config MACH_EDB9307
 	bool "Support Cirrus Logic EDB9307"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -95,7 +54,6 @@ config MACH_EDB9307
 
 config MACH_EDB9307A
 	bool "Support Cirrus Logic EDB9307A"
-	depends on EP93XX_SDCE0_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -103,7 +61,6 @@ config MACH_EDB9307A
 
 config MACH_EDB9312
 	bool "Support Cirrus Logic EDB9312"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -111,7 +68,6 @@ config MACH_EDB9312
 
 config MACH_EDB9315
 	bool "Support Cirrus Logic EDB9315"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
@@ -119,14 +75,12 @@ config MACH_EDB9315
 
 config MACH_EDB9315A
 	bool "Support Cirrus Logic EDB9315A"
-	depends on EP93XX_SDCE0_PHYS_OFFSET
 	select MACH_EDB93XX
 	help
 	  Say 'Y' here if you want your kernel to support the Cirrus
 	  Logic EDB9315A Evaluation Board.
 
 config MACH_GESBC9312
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	bool "Support Glomation GESBC-9312-sx"
 	help
 	  Say 'Y' here if you want your kernel to support the Glomation
@@ -137,7 +91,6 @@ config MACH_MICRO9
 
 config MACH_MICRO9H
 	bool "Support Contec Micro9-High"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_MICRO9
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -145,7 +98,6 @@ config MACH_MICRO9H
 
 config MACH_MICRO9M
 	bool "Support Contec Micro9-Mid"
-	depends on EP93XX_SDCE3_ASYNC_PHYS_OFFSET
 	select MACH_MICRO9
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -153,7 +105,6 @@ config MACH_MICRO9M
 
 config MACH_MICRO9L
 	bool "Support Contec Micro9-Lite"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	select MACH_MICRO9
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -161,7 +112,6 @@ config MACH_MICRO9L
 
 config MACH_MICRO9S
 	bool "Support Contec Micro9-Slim"
-	depends on EP93XX_SDCE3_ASYNC_PHYS_OFFSET
 	select MACH_MICRO9
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -169,28 +119,24 @@ config MACH_MICRO9S
 
 config MACH_SIM_ONE
         bool "Support Simplemachines Sim.One board"
-        depends on EP93XX_SDCE0_PHYS_OFFSET
         help
           Say 'Y' here if you want your kernel to support the
           Simplemachines Sim.One board.
 
 config MACH_SNAPPER_CL15
 	bool "Support Bluewater Systems Snapper CL15 Module"
-	depends on EP93XX_SDCE0_PHYS_OFFSET
 	help
 	  Say 'Y' here if you want your kernel to support the Bluewater
 	  Systems Snapper CL15 Module.
 
 config MACH_TS72XX
 	bool "Support Technologic Systems TS-72xx SBC"
-	depends on EP93XX_SDCE3_SYNC_PHYS_OFFSET
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  Technologic Systems TS-72xx board.
 
 config MACH_VISION_EP9307
 	bool "Support Vision Engraving Systems EP9307 SoM"
-	depends on EP93XX_SDCE0_PHYS_OFFSET
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  Vision Engraving Systems EP9307 SoM.
diff --git a/arch/arm/mach-ep93xx/Makefile b/arch/arm/mach-ep93xx/Makefile
index 78d427b34b1f..b7ae4345ac08 100644
--- a/arch/arm/mach-ep93xx/Makefile
+++ b/arch/arm/mach-ep93xx/Makefile
@@ -1,7 +1,7 @@
 #
 # Makefile for the linux kernel.
 #
-obj-y			:= core.o clock.o
+obj-y			:= core.o clock.o timer-ep93xx.o
 
 obj-$(CONFIG_EP93XX_DMA)	+= dma.o
 
diff --git a/arch/arm/mach-ep93xx/Makefile.boot b/arch/arm/mach-ep93xx/Makefile.boot
index d3113a71cb40..ed82ed7c949f 100644
--- a/arch/arm/mach-ep93xx/Makefile.boot
+++ b/arch/arm/mach-ep93xx/Makefile.boot
@@ -1,14 +1 @@
-   zreladdr-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET)	+= 0x00008000
-params_phys-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET)	:= 0x00000100
-
-   zreladdr-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET)		+= 0xc0008000
-params_phys-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET)		:= 0xc0000100
-
-   zreladdr-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET)		+= 0xd0008000
-params_phys-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET)		:= 0xd0000100
-
-   zreladdr-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET)		+= 0xe0008000
-params_phys-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET)		:= 0xe0000100
-
-   zreladdr-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET)	+= 0xf0008000
-params_phys-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET)	:= 0xf0000100
+# Empty file waiting for deletion once Makefile.boot isn't needed any more.
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index 0e571f1749d6..c393b1b0310d 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -22,7 +22,6 @@
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/sys_soc.h>
-#include <linux/timex.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
@@ -38,6 +37,7 @@
 #include <linux/irqchip/arm-vic.h>
 #include <linux/reboot.h>
 #include <linux/usb/ohci_pdriver.h>
+#include <linux/random.h>
 
 #include <mach/hardware.h>
 #include <linux/platform_data/video-ep93xx.h>
@@ -47,7 +47,6 @@
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <asm/mach/time.h>
 
 #include "soc.h"
 
@@ -73,113 +72,6 @@ void __init ep93xx_map_io(void)
 	iotable_init(ep93xx_io_desc, ARRAY_SIZE(ep93xx_io_desc));
 }
 
-
-/*************************************************************************
- * Timer handling for EP93xx
- *************************************************************************
- * The ep93xx has four internal timers.  Timers 1, 2 (both 16 bit) and
- * 3 (32 bit) count down at 508 kHz, are self-reloading, and can generate
- * an interrupt on underflow.  Timer 4 (40 bit) counts down at 983.04 kHz,
- * is free-running, and can't generate interrupts.
- *
- * The 508 kHz timers are ideal for use for the timer interrupt, as the
- * most common values of HZ divide 508 kHz nicely.  We pick one of the 16
- * bit timers (timer 1) since we don't need more than 16 bits of reload
- * value as long as HZ >= 8.
- *
- * The higher clock rate of timer 4 makes it a better choice than the
- * other timers for use in gettimeoffset(), while the fact that it can't
- * generate interrupts means we don't have to worry about not being able
- * to use this timer for something else.  We also use timer 4 for keeping
- * track of lost jiffies.
- */
-#define EP93XX_TIMER_REG(x)		(EP93XX_TIMER_BASE + (x))
-#define EP93XX_TIMER1_LOAD		EP93XX_TIMER_REG(0x00)
-#define EP93XX_TIMER1_VALUE		EP93XX_TIMER_REG(0x04)
-#define EP93XX_TIMER1_CONTROL		EP93XX_TIMER_REG(0x08)
-#define EP93XX_TIMER123_CONTROL_ENABLE	(1 << 7)
-#define EP93XX_TIMER123_CONTROL_MODE	(1 << 6)
-#define EP93XX_TIMER123_CONTROL_CLKSEL	(1 << 3)
-#define EP93XX_TIMER1_CLEAR		EP93XX_TIMER_REG(0x0c)
-#define EP93XX_TIMER2_LOAD		EP93XX_TIMER_REG(0x20)
-#define EP93XX_TIMER2_VALUE		EP93XX_TIMER_REG(0x24)
-#define EP93XX_TIMER2_CONTROL		EP93XX_TIMER_REG(0x28)
-#define EP93XX_TIMER2_CLEAR		EP93XX_TIMER_REG(0x2c)
-#define EP93XX_TIMER4_VALUE_LOW		EP93XX_TIMER_REG(0x60)
-#define EP93XX_TIMER4_VALUE_HIGH	EP93XX_TIMER_REG(0x64)
-#define EP93XX_TIMER4_VALUE_HIGH_ENABLE	(1 << 8)
-#define EP93XX_TIMER3_LOAD		EP93XX_TIMER_REG(0x80)
-#define EP93XX_TIMER3_VALUE		EP93XX_TIMER_REG(0x84)
-#define EP93XX_TIMER3_CONTROL		EP93XX_TIMER_REG(0x88)
-#define EP93XX_TIMER3_CLEAR		EP93XX_TIMER_REG(0x8c)
-
-#define EP93XX_TIMER123_CLOCK		508469
-#define EP93XX_TIMER4_CLOCK		983040
-
-#define TIMER1_RELOAD			((EP93XX_TIMER123_CLOCK / HZ) - 1)
-#define TIMER4_TICKS_PER_JIFFY		DIV_ROUND_CLOSEST(EP93XX_TIMER4_CLOCK, HZ)
-
-static unsigned int last_jiffy_time;
-
-static irqreturn_t ep93xx_timer_interrupt(int irq, void *dev_id)
-{
-	/* Writing any value clears the timer interrupt */
-	__raw_writel(1, EP93XX_TIMER1_CLEAR);
-
-	/* Recover lost jiffies */
-	while ((signed long)
-		(__raw_readl(EP93XX_TIMER4_VALUE_LOW) - last_jiffy_time)
-						>= TIMER4_TICKS_PER_JIFFY) {
-		last_jiffy_time += TIMER4_TICKS_PER_JIFFY;
-		timer_tick();
-	}
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction ep93xx_timer_irq = {
-	.name		= "ep93xx timer",
-	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
-	.handler	= ep93xx_timer_interrupt,
-};
-
-static u32 ep93xx_gettimeoffset(void)
-{
-	int offset;
-
-	offset = __raw_readl(EP93XX_TIMER4_VALUE_LOW) - last_jiffy_time;
-
-	/*
-	 * Timer 4 is based on a 983.04 kHz reference clock,
-	 * so dividing by 983040 gives the fraction of a second,
-	 * so dividing by 0.983040 converts to uS.
-	 * Refactor the calculation to avoid overflow.
-	 * Finally, multiply by 1000 to give nS.
-	 */
-	return (offset + (53 * offset / 3072)) * 1000;
-}
-
-void __init ep93xx_timer_init(void)
-{
-	u32 tmode = EP93XX_TIMER123_CONTROL_MODE |
-		    EP93XX_TIMER123_CONTROL_CLKSEL;
-
-	arch_gettimeoffset = ep93xx_gettimeoffset;
-
-	/* Enable periodic HZ timer.  */
-	__raw_writel(tmode, EP93XX_TIMER1_CONTROL);
-	__raw_writel(TIMER1_RELOAD, EP93XX_TIMER1_LOAD);
-	__raw_writel(tmode | EP93XX_TIMER123_CONTROL_ENABLE,
-			EP93XX_TIMER1_CONTROL);
-
-	/* Enable lost jiffy timer.  */
-	__raw_writel(EP93XX_TIMER4_VALUE_HIGH_ENABLE,
-			EP93XX_TIMER4_VALUE_HIGH);
-
-	setup_irq(IRQ_EP93XX_TIMER1, &ep93xx_timer_irq);
-}
-
-
 /*************************************************************************
  * EP93xx IRQ handling
  *************************************************************************/
@@ -971,6 +863,12 @@ static const char __init *ep93xx_get_soc_id(void)
 	if (id != id2)
 		return "invalid";
 
+	/* Toss the unique ID into the entropy pool */
+	add_device_randomness(&id2, 4);
+	add_device_randomness(&id3, 4);
+	add_device_randomness(&id4, 4);
+	add_device_randomness(&id5, 4);
+
 	snprintf(ep93xx_soc_id, sizeof(ep93xx_soc_id),
 		 "%08x%08x%08x%08x", id2, id3, id4, id5);
 
diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index 27b14ae92c7e..ad92d9f7e4df 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -205,8 +205,6 @@ static void __init edb93xx_register_pwm(void)
  * EDB93xx framebuffer
  *************************************************************************/
 static struct ep93xxfb_mach_info __initdata edb93xxfb_info = {
-	.num_modes	= EP93XXFB_USE_MODEDB,
-	.bpp		= 16,
 	.flags		= 0,
 };
 
diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c
index 3c950f5864f3..7bb540c421ee 100644
--- a/arch/arm/mach-ep93xx/simone.c
+++ b/arch/arm/mach-ep93xx/simone.c
@@ -40,8 +40,6 @@ static struct ep93xx_eth_data __initdata simone_eth_data = {
 };
 
 static struct ep93xxfb_mach_info __initdata simone_fb_info = {
-	.num_modes	= EP93XXFB_USE_MODEDB,
-	.bpp		= 16,
 	.flags		= EP93XXFB_USE_SDCSN0 | EP93XXFB_PCLK_FALLING,
 };
 
@@ -169,6 +167,7 @@ static struct spi_board_info simone_spi_devices[] __initdata = {
 
 static struct ep93xx_spi_info simone_spi_info __initdata = {
 	.num_chipselect	= ARRAY_SIZE(simone_spi_devices),
+	.use_dma = 1,
 };
 
 static struct i2c_gpio_platform_data __initdata simone_i2c_gpio_data = {
diff --git a/arch/arm/mach-ep93xx/snappercl15.c b/arch/arm/mach-ep93xx/snappercl15.c
index aa86f86638dd..c4904264256a 100644
--- a/arch/arm/mach-ep93xx/snappercl15.c
+++ b/arch/arm/mach-ep93xx/snappercl15.c
@@ -144,8 +144,6 @@ static struct i2c_board_info __initdata snappercl15_i2c_data[] = {
 };
 
 static struct ep93xxfb_mach_info __initdata snappercl15_fb_info = {
-	.num_modes		= EP93XXFB_USE_MODEDB,
-	.bpp			= 16,
 };
 
 static struct platform_device snappercl15_audio_device = {
diff --git a/arch/arm/mach-ep93xx/timer-ep93xx.c b/arch/arm/mach-ep93xx/timer-ep93xx.c
new file mode 100644
index 000000000000..e5f791145bd0
--- /dev/null
+++ b/arch/arm/mach-ep93xx/timer-ep93xx.c
@@ -0,0 +1,143 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/sched_clock.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <asm/mach/time.h>
+#include "soc.h"
+
+/*************************************************************************
+ * Timer handling for EP93xx
+ *************************************************************************
+ * The ep93xx has four internal timers.  Timers 1, 2 (both 16 bit) and
+ * 3 (32 bit) count down at 508 kHz, are self-reloading, and can generate
+ * an interrupt on underflow.  Timer 4 (40 bit) counts down at 983.04 kHz,
+ * is free-running, and can't generate interrupts.
+ *
+ * The 508 kHz timers are ideal for use for the timer interrupt, as the
+ * most common values of HZ divide 508 kHz nicely.  We pick the 32 bit
+ * timer (timer 3) to get as long sleep intervals as possible when using
+ * CONFIG_NO_HZ.
+ *
+ * The higher clock rate of timer 4 makes it a better choice than the
+ * other timers for use as clock source and for sched_clock(), providing
+ * a stable 40 bit time base.
+ *************************************************************************
+ */
+#define EP93XX_TIMER_REG(x)		(EP93XX_TIMER_BASE + (x))
+#define EP93XX_TIMER1_LOAD		EP93XX_TIMER_REG(0x00)
+#define EP93XX_TIMER1_VALUE		EP93XX_TIMER_REG(0x04)
+#define EP93XX_TIMER1_CONTROL		EP93XX_TIMER_REG(0x08)
+#define EP93XX_TIMER123_CONTROL_ENABLE	(1 << 7)
+#define EP93XX_TIMER123_CONTROL_MODE	(1 << 6)
+#define EP93XX_TIMER123_CONTROL_CLKSEL	(1 << 3)
+#define EP93XX_TIMER1_CLEAR		EP93XX_TIMER_REG(0x0c)
+#define EP93XX_TIMER2_LOAD		EP93XX_TIMER_REG(0x20)
+#define EP93XX_TIMER2_VALUE		EP93XX_TIMER_REG(0x24)
+#define EP93XX_TIMER2_CONTROL		EP93XX_TIMER_REG(0x28)
+#define EP93XX_TIMER2_CLEAR		EP93XX_TIMER_REG(0x2c)
+#define EP93XX_TIMER4_VALUE_LOW		EP93XX_TIMER_REG(0x60)
+#define EP93XX_TIMER4_VALUE_HIGH	EP93XX_TIMER_REG(0x64)
+#define EP93XX_TIMER4_VALUE_HIGH_ENABLE	(1 << 8)
+#define EP93XX_TIMER3_LOAD		EP93XX_TIMER_REG(0x80)
+#define EP93XX_TIMER3_VALUE		EP93XX_TIMER_REG(0x84)
+#define EP93XX_TIMER3_CONTROL		EP93XX_TIMER_REG(0x88)
+#define EP93XX_TIMER3_CLEAR		EP93XX_TIMER_REG(0x8c)
+
+#define EP93XX_TIMER123_RATE		508469
+#define EP93XX_TIMER4_RATE		983040
+
+static u64 notrace ep93xx_read_sched_clock(void)
+{
+	u64 ret;
+
+	ret = readl(EP93XX_TIMER4_VALUE_LOW);
+	ret |= ((u64) (readl(EP93XX_TIMER4_VALUE_HIGH) & 0xff) << 32);
+	return ret;
+}
+
+cycle_t ep93xx_clocksource_read(struct clocksource *c)
+{
+	u64 ret;
+
+	ret = readl(EP93XX_TIMER4_VALUE_LOW);
+	ret |= ((u64) (readl(EP93XX_TIMER4_VALUE_HIGH) & 0xff) << 32);
+	return (cycle_t) ret;
+}
+
+static int ep93xx_clkevt_set_next_event(unsigned long next,
+					struct clock_event_device *evt)
+{
+	/* Default mode: periodic, off, 508 kHz */
+	u32 tmode = EP93XX_TIMER123_CONTROL_MODE |
+		    EP93XX_TIMER123_CONTROL_CLKSEL;
+
+	/* Clear timer */
+	writel(tmode, EP93XX_TIMER3_CONTROL);
+
+	/* Set next event */
+	writel(next, EP93XX_TIMER3_LOAD);
+	writel(tmode | EP93XX_TIMER123_CONTROL_ENABLE,
+	       EP93XX_TIMER3_CONTROL);
+        return 0;
+}
+
+
+static int ep93xx_clkevt_shutdown(struct clock_event_device *evt)
+{
+	/* Disable timer */
+	writel(0, EP93XX_TIMER3_CONTROL);
+
+	return 0;
+}
+
+static struct clock_event_device ep93xx_clockevent = {
+	.name			= "timer1",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= ep93xx_clkevt_shutdown,
+	.set_state_oneshot	= ep93xx_clkevt_shutdown,
+	.tick_resume		= ep93xx_clkevt_shutdown,
+	.set_next_event		= ep93xx_clkevt_set_next_event,
+	.rating			= 300,
+};
+
+static irqreturn_t ep93xx_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	/* Writing any value clears the timer interrupt */
+	writel(1, EP93XX_TIMER3_CLEAR);
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction ep93xx_timer_irq = {
+	.name		= "ep93xx timer",
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
+	.handler	= ep93xx_timer_interrupt,
+	.dev_id		= &ep93xx_clockevent,
+};
+
+void __init ep93xx_timer_init(void)
+{
+	/* Enable and register clocksource and sched_clock on timer 4 */
+	writel(EP93XX_TIMER4_VALUE_HIGH_ENABLE,
+	       EP93XX_TIMER4_VALUE_HIGH);
+	clocksource_mmio_init(NULL, "timer4",
+			      EP93XX_TIMER4_RATE, 200, 40,
+			      ep93xx_clocksource_read);
+	sched_clock_register(ep93xx_read_sched_clock, 40,
+			     EP93XX_TIMER4_RATE);
+
+	/* Set up clockevent on timer 3 */
+	setup_irq(IRQ_EP93XX_TIMER3, &ep93xx_timer_irq);
+	clockevents_config_and_register(&ep93xx_clockevent,
+					EP93XX_TIMER123_RATE,
+					1,
+					0xffffffffU);
+}
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index 6bc1c181581d..5cced5988498 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -29,6 +29,8 @@
 #include <linux/spi/mmc_spi.h>
 #include <linux/mmc/host.h>
 
+#include <sound/cs4271.h>
+
 #include <mach/hardware.h>
 #include <linux/platform_data/video-ep93xx.h>
 #include <linux/platform_data/spi-ep93xx.h>
@@ -104,8 +106,6 @@ static void vision_lcd_blank(int blank_mode, struct fb_info *info)
 }
 
 static struct ep93xxfb_mach_info ep93xxfb_info __initdata = {
-	.num_modes	= EP93XXFB_USE_MODEDB,
-	.bpp		= 16,
 	.flags		= EP93XXFB_USE_SDCSN0 | EP93XXFB_PCLK_FALLING,
 	.setup		= vision_lcd_setup,
 	.teardown	= vision_lcd_teardown,
@@ -169,6 +169,35 @@ static struct i2c_board_info vision_i2c_info[] __initdata = {
 };
 
 /*************************************************************************
+ * SPI CS4271 Audio Codec
+ *************************************************************************/
+static struct cs4271_platform_data vision_cs4271_data = {
+	.gpio_nreset	= EP93XX_GPIO_LINE_H(2),
+};
+
+static int vision_cs4271_hw_setup(struct spi_device *spi)
+{
+	return gpio_request_one(EP93XX_GPIO_LINE_EGPIO6,
+				GPIOF_OUT_INIT_HIGH, spi->modalias);
+}
+
+static void vision_cs4271_hw_cleanup(struct spi_device *spi)
+{
+	gpio_free(EP93XX_GPIO_LINE_EGPIO6);
+}
+
+static void vision_cs4271_hw_cs_control(struct spi_device *spi, int value)
+{
+	gpio_set_value(EP93XX_GPIO_LINE_EGPIO6, value);
+}
+
+static struct ep93xx_spi_chip_ops vision_cs4271_hw = {
+	.setup		= vision_cs4271_hw_setup,
+	.cleanup	= vision_cs4271_hw_cleanup,
+	.cs_control	= vision_cs4271_hw_cs_control,
+};
+
+/*************************************************************************
  * SPI Flash
  *************************************************************************/
 #define VISION_SPI_FLASH_CS	EP93XX_GPIO_LINE_EGPIO7
@@ -262,12 +291,20 @@ static struct ep93xx_spi_chip_ops vision_spi_mmc_hw = {
  *************************************************************************/
 static struct spi_board_info vision_spi_board_info[] __initdata = {
 	{
+		.modalias		= "cs4271",
+		.platform_data		= &vision_cs4271_data,
+		.controller_data	= &vision_cs4271_hw,
+		.max_speed_hz		= 6000000,
+		.bus_num		= 0,
+		.chip_select		= 0,
+		.mode			= SPI_MODE_3,
+	}, {
 		.modalias		= "sst25l",
 		.platform_data		= &vision_spi_flash_data,
 		.controller_data	= &vision_spi_flash_hw,
 		.max_speed_hz		= 20000000,
 		.bus_num		= 0,
-		.chip_select		= 0,
+		.chip_select		= 1,
 		.mode			= SPI_MODE_3,
 	}, {
 		.modalias		= "mmc_spi",
@@ -275,16 +312,31 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 		.controller_data	= &vision_spi_mmc_hw,
 		.max_speed_hz		= 20000000,
 		.bus_num		= 0,
-		.chip_select		= 1,
+		.chip_select		= 2,
 		.mode			= SPI_MODE_3,
 	},
 };
 
 static struct ep93xx_spi_info vision_spi_master __initdata = {
-	.num_chipselect		= ARRAY_SIZE(vision_spi_board_info),
+	.num_chipselect	= ARRAY_SIZE(vision_spi_board_info),
+	.use_dma	= 1,
 };
 
 /*************************************************************************
+ * I2S Audio
+ *************************************************************************/
+static struct platform_device vision_audio_device = {
+	.name		= "edb93xx-audio",
+	.id		= -1,
+};
+
+static void __init vision_register_i2s(void)
+{
+	ep93xx_register_i2s();
+	platform_device_register(&vision_audio_device);
+}
+
+/*************************************************************************
  * Machine Initialization
  *************************************************************************/
 static void __init vision_init_machine(void)
@@ -309,6 +361,7 @@ static void __init vision_init_machine(void)
 				ARRAY_SIZE(vision_i2c_info));
 	ep93xx_register_spi(&vision_spi_master, vision_spi_board_info,
 				ARRAY_SIZE(vision_spi_board_info));
+	vision_register_i2s();
 }
 
 MACHINE_START(VISION_EP9307, "Vision Engraving Systems EP9307")
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 81064cd61a0a..4c4858c566d8 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -30,6 +30,11 @@ menuconfig ARCH_EXYNOS
 
 if ARCH_EXYNOS
 
+config S5P_DEV_MFC
+	bool
+	help
+	  Compile in setup memory (init) code for MFC
+
 config ARCH_EXYNOS3
 	bool "SAMSUNG EXYNOS3"
 	select ARM_CPU_SUSPEND if PM
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index bcefb5473ee4..2f306767cdfe 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -23,3 +23,5 @@ AFLAGS_sleep.o			:=-Wa,-march=armv7-a$(plus_sec)
 
 obj-$(CONFIG_EXYNOS5420_MCPM)	+= mcpm-exynos.o
 CFLAGS_mcpm-exynos.o		+= -march=armv7-a
+
+obj-$(CONFIG_S5P_DEV_MFC)	+= s5p-dev-mfc.o
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index e3a9256ed55f..153492513c40 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -128,6 +128,12 @@ void exynos_firmware_init(void);
 
 /* CPU BOOT mode flag for Exynos3250 SoC bootloader */
 #define C2_STATE	(1 << 3)
+/*
+ * Magic values for bootloader indicating chosen low power mode.
+ * See also Documentation/arm/Samsung/Bootloader-interface.txt
+ */
+#define EXYNOS_SLEEP_MAGIC	0x00000bad
+#define EXYNOS_AFTR_MAGIC	0xfcba0d10
 
 void exynos_set_boot_flag(unsigned int cpu, unsigned int mode);
 void exynos_clear_boot_flag(unsigned int cpu, unsigned int mode);
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index 245f6dec1ded..111cfbf66fdb 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -25,8 +25,6 @@
 #include "common.h"
 #include "smc.h"
 
-#define EXYNOS_SLEEP_MAGIC	0x00000bad
-#define EXYNOS_AFTR_MAGIC	0xfcba0d10
 #define EXYNOS_BOOT_ADDR	0x8
 #define EXYNOS_BOOT_FLAG	0xc
 
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 58e05a2eae57..98a2c0cbb833 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -182,7 +182,7 @@ static inline void __iomem *cpu_boot_reg(int cpu)
 
 	boot_reg = cpu_boot_reg_base();
 	if (!boot_reg)
-		return ERR_PTR(-ENODEV);
+		return IOMEM_ERR_PTR(-ENODEV);
 	if (soc_is_exynos4412())
 		boot_reg += 4*cpu;
 	else if (soc_is_exynos5420() || soc_is_exynos5800())
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index 6001f1c9d136..4a87e86dec45 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -146,9 +146,8 @@ static __init int exynos4_pm_init_power_domain(void)
 		pd->base = of_iomap(np, 0);
 		if (!pd->base) {
 			pr_warn("%s: failed to map memory\n", __func__);
-			kfree(pd->pd.name);
+			kfree_const(pd->pd.name);
 			kfree(pd);
-			of_node_put(np);
 			continue;
 		}
 
diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c
index e812c1c85624..de68938ee6aa 100644
--- a/arch/arm/mach-exynos/pmu.c
+++ b/arch/arm/mach-exynos/pmu.c
@@ -698,7 +698,7 @@ static void exynos_power_off(void)
 		;
 }
 
-void exynos5420_powerdown_conf(enum sys_powerdown mode)
+static void exynos5420_powerdown_conf(enum sys_powerdown mode)
 {
 	u32 this_cluster;
 
@@ -991,7 +991,6 @@ static int exynos_pmu_probe(struct platform_device *pdev)
 static struct platform_driver exynos_pmu_driver = {
 	.driver  = {
 		.name   = "exynos-pmu",
-		.owner	= THIS_MODULE,
 		.of_match_table = exynos_pmu_of_device_ids,
 	},
 	.probe = exynos_pmu_probe,
diff --git a/arch/arm/plat-samsung/include/plat/regs-srom.h b/arch/arm/mach-exynos/regs-srom.h
index 9b6729c81cda..5c4d4427db7b 100644
--- a/arch/arm/plat-samsung/include/plat/regs-srom.h
+++ b/arch/arm/mach-exynos/regs-srom.h
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-samsung/include/plat/regs-srom.h
- *
+/*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
diff --git a/arch/arm/plat-samsung/s5p-dev-mfc.c b/arch/arm/mach-exynos/s5p-dev-mfc.c
index 0b04b6b0fa30..0b04b6b0fa30 100644
--- a/arch/arm/plat-samsung/s5p-dev-mfc.c
+++ b/arch/arm/mach-exynos/s5p-dev-mfc.c
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index f572219c7a40..e00eb39453a4 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -32,13 +32,11 @@
 #include <asm/suspend.h>
 
 #include <plat/pm-common.h>
-#include <plat/regs-srom.h>
 
 #include "common.h"
-#include "regs-pmu.h"
 #include "exynos-pmu.h"
-
-#define S5P_CHECK_SLEEP 0x00000BAD
+#include "regs-pmu.h"
+#include "regs-srom.h"
 
 #define REG_TABLE_END (-1U)
 
@@ -331,7 +329,7 @@ static void exynos_pm_enter_sleep_mode(void)
 {
 	/* Set value of power down register for sleep mode */
 	exynos_sys_powerdown_conf(SYS_SLEEP);
-	pmu_raw_writel(S5P_CHECK_SLEEP, S5P_INFORM1);
+	pmu_raw_writel(EXYNOS_SLEEP_MAGIC, S5P_INFORM1);
 }
 
 static void exynos_pm_prepare(void)
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index 9e8220e38398..0f0c9e040fcc 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -106,7 +106,7 @@ static void __init __fb_init_irq(void)
 
 	for (irq = _DC21285_IRQ(0); irq < _DC21285_IRQ(20); irq++) {
 		irq_set_chip_and_handler(irq, &fb_chip, handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 }
 
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index bf7aa7d298e7..810edc78c817 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -57,34 +57,32 @@ static int ckevt_dc21285_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void ckevt_dc21285_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *c)
+static int ckevt_dc21285_shutdown(struct clock_event_device *c)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		*CSR_TIMER1_CLR = 0;
-		*CSR_TIMER1_LOAD = (mem_fclk_21285 + 8 * HZ) / (16 * HZ);
-		*CSR_TIMER1_CNTL = TIMER_CNTL_ENABLE | TIMER_CNTL_AUTORELOAD |
-				   TIMER_CNTL_DIV16;
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		*CSR_TIMER1_CNTL = 0;
-		break;
-	}
+	*CSR_TIMER1_CNTL = 0;
+	return 0;
+}
+
+static int ckevt_dc21285_set_periodic(struct clock_event_device *c)
+{
+	*CSR_TIMER1_CLR = 0;
+	*CSR_TIMER1_LOAD = (mem_fclk_21285 + 8 * HZ) / (16 * HZ);
+	*CSR_TIMER1_CNTL = TIMER_CNTL_ENABLE | TIMER_CNTL_AUTORELOAD |
+			   TIMER_CNTL_DIV16;
+	return 0;
 }
 
 static struct clock_event_device ckevt_dc21285 = {
-	.name		= "dc21285_timer1",
-	.features	= CLOCK_EVT_FEAT_PERIODIC |
-			  CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.irq		= IRQ_TIMER1,
-	.set_next_event	= ckevt_dc21285_set_next_event,
-	.set_mode	= ckevt_dc21285_set_mode,
+	.name			= "dc21285_timer1",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.irq			= IRQ_TIMER1,
+	.set_next_event		= ckevt_dc21285_set_next_event,
+	.set_state_shutdown	= ckevt_dc21285_shutdown,
+	.set_state_periodic	= ckevt_dc21285_set_periodic,
+	.set_state_oneshot	= ckevt_dc21285_shutdown,
+	.tick_resume		= ckevt_dc21285_set_periodic,
 };
 
 static irqreturn_t timer1_interrupt(int irq, void *dev_id)
@@ -94,7 +92,7 @@ static irqreturn_t timer1_interrupt(int irq, void *dev_id)
 	*CSR_TIMER1_CLR = 0;
 
 	/* Stop the timer if in one-shot mode */
-	if (ce->mode == CLOCK_EVT_MODE_ONESHOT)
+	if (clockevent_state_oneshot(ce))
 		*CSR_TIMER1_CNTL = 0;
 
 	ce->event_handler(ce);
diff --git a/arch/arm/mach-footbridge/isa-irq.c b/arch/arm/mach-footbridge/isa-irq.c
index c3a0abbc9049..fcd79bc3a3e1 100644
--- a/arch/arm/mach-footbridge/isa-irq.c
+++ b/arch/arm/mach-footbridge/isa-irq.c
@@ -153,13 +153,13 @@ void __init isa_init_irq(unsigned int host_irq)
 		for (irq = _ISA_IRQ(0); irq < _ISA_IRQ(8); irq++) {
 			irq_set_chip_and_handler(irq, &isa_lo_chip,
 						 handle_level_irq);
-			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+			irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 		}
 
 		for (irq = _ISA_IRQ(8); irq < _ISA_IRQ(16); irq++) {
 			irq_set_chip_and_handler(irq, &isa_hi_chip,
 						 handle_level_irq);
-			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+			irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 		}
 
 		request_resource(&ioport_resource, &pic1_resource);
@@ -175,8 +175,8 @@ void __init isa_init_irq(unsigned int host_irq)
 		 * resistor on this line.
 		 */
 		if (machine_is_netwinder())
-			set_irq_flags(_ISA_IRQ(11), IRQF_VALID |
-				      IRQF_PROBE | IRQF_NOAUTOEN);
+			irq_modify_status(_ISA_IRQ(11),
+				IRQ_NOREQUEST | IRQ_NOPROBE, IRQ_NOAUTOEN);
 	}
 }
 
diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c
index 3292f2e6ed6f..220333ed741d 100644
--- a/arch/arm/mach-gemini/gpio.c
+++ b/arch/arm/mach-gemini/gpio.c
@@ -220,7 +220,7 @@ void __init gemini_gpio_init(void)
 		     j < GPIO_IRQ_BASE + (i + 1) * 32; j++) {
 			irq_set_chip_and_handler(j, &gpio_irq_chip,
 						 handle_edge_irq);
-			set_irq_flags(j, IRQF_VALID);
+			irq_clear_status_flags(j, IRQ_NOREQUEST);
 		}
 
 		irq_set_chained_handler_and_data(IRQ_GPIO(i), gpio_irq_handler,
diff --git a/arch/arm/mach-gemini/include/mach/hardware.h b/arch/arm/mach-gemini/include/mach/hardware.h
index 98e7b0f286bf..f0390f184742 100644
--- a/arch/arm/mach-gemini/include/mach/hardware.h
+++ b/arch/arm/mach-gemini/include/mach/hardware.h
@@ -57,9 +57,6 @@
 #define GEMINI_USB1_BASE	0x69000000
 #define GEMINI_BIG_ENDIAN_BASE	0x80000000
 
-#define GEMINI_TIMER1_BASE	GEMINI_TIMER_BASE
-#define GEMINI_TIMER2_BASE	(GEMINI_TIMER_BASE + 0x10)
-#define GEMINI_TIMER3_BASE	(GEMINI_TIMER_BASE + 0x20)
 
 /*
  * UART Clock when System clk is 150MHz
diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c
index 44f50dcb616d..d929b3ff18fd 100644
--- a/arch/arm/mach-gemini/irq.c
+++ b/arch/arm/mach-gemini/irq.c
@@ -92,7 +92,7 @@ void __init gemini_init_irq(void)
 		} else {			
 			irq_set_handler(i, handle_level_irq);
 		}
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(i, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	/* Disable all interrupts */
diff --git a/arch/arm/mach-gemini/time.c b/arch/arm/mach-gemini/time.c
index 0a63c4d25b64..f5f18df5aacd 100644
--- a/arch/arm/mach-gemini/time.c
+++ b/arch/arm/mach-gemini/time.c
@@ -15,93 +15,147 @@
 #include <asm/mach/time.h>
 #include <linux/clockchips.h>
 #include <linux/clocksource.h>
+#include <linux/sched_clock.h>
 
 /*
  * Register definitions for the timers
  */
-#define TIMER_COUNT(BASE_ADDR)		(BASE_ADDR  + 0x00)
-#define TIMER_LOAD(BASE_ADDR)		(BASE_ADDR  + 0x04)
-#define TIMER_MATCH1(BASE_ADDR)		(BASE_ADDR  + 0x08)
-#define TIMER_MATCH2(BASE_ADDR)		(BASE_ADDR  + 0x0C)
-#define TIMER_CR(BASE_ADDR)		(BASE_ADDR  + 0x30)
-
-#define TIMER_1_CR_ENABLE		(1 << 0)
-#define TIMER_1_CR_CLOCK		(1 << 1)
-#define TIMER_1_CR_INT			(1 << 2)
-#define TIMER_2_CR_ENABLE		(1 << 3)
-#define TIMER_2_CR_CLOCK		(1 << 4)
-#define TIMER_2_CR_INT			(1 << 5)
-#define TIMER_3_CR_ENABLE		(1 << 6)
-#define TIMER_3_CR_CLOCK		(1 << 7)
-#define TIMER_3_CR_INT			(1 << 8)
+
+#define TIMER1_BASE		GEMINI_TIMER_BASE
+#define TIMER2_BASE		(GEMINI_TIMER_BASE + 0x10)
+#define TIMER3_BASE		(GEMINI_TIMER_BASE + 0x20)
+
+#define TIMER_COUNT(BASE)	(IO_ADDRESS(BASE) + 0x00)
+#define TIMER_LOAD(BASE)	(IO_ADDRESS(BASE) + 0x04)
+#define TIMER_MATCH1(BASE)	(IO_ADDRESS(BASE) + 0x08)
+#define TIMER_MATCH2(BASE)	(IO_ADDRESS(BASE) + 0x0C)
+#define TIMER_CR		(IO_ADDRESS(GEMINI_TIMER_BASE) + 0x30)
+#define TIMER_INTR_STATE	(IO_ADDRESS(GEMINI_TIMER_BASE) + 0x34)
+#define TIMER_INTR_MASK		(IO_ADDRESS(GEMINI_TIMER_BASE) + 0x38)
+
+#define TIMER_1_CR_ENABLE	(1 << 0)
+#define TIMER_1_CR_CLOCK	(1 << 1)
+#define TIMER_1_CR_INT		(1 << 2)
+#define TIMER_2_CR_ENABLE	(1 << 3)
+#define TIMER_2_CR_CLOCK	(1 << 4)
+#define TIMER_2_CR_INT		(1 << 5)
+#define TIMER_3_CR_ENABLE	(1 << 6)
+#define TIMER_3_CR_CLOCK	(1 << 7)
+#define TIMER_3_CR_INT		(1 << 8)
+#define TIMER_1_CR_UPDOWN	(1 << 9)
+#define TIMER_2_CR_UPDOWN	(1 << 10)
+#define TIMER_3_CR_UPDOWN	(1 << 11)
+#define TIMER_DEFAULT_FLAGS	(TIMER_1_CR_UPDOWN | \
+				 TIMER_3_CR_ENABLE | \
+				 TIMER_3_CR_UPDOWN)
+
+#define TIMER_1_INT_MATCH1	(1 << 0)
+#define TIMER_1_INT_MATCH2	(1 << 1)
+#define TIMER_1_INT_OVERFLOW	(1 << 2)
+#define TIMER_2_INT_MATCH1	(1 << 3)
+#define TIMER_2_INT_MATCH2	(1 << 4)
+#define TIMER_2_INT_OVERFLOW	(1 << 5)
+#define TIMER_3_INT_MATCH1	(1 << 6)
+#define TIMER_3_INT_MATCH2	(1 << 7)
+#define TIMER_3_INT_OVERFLOW	(1 << 8)
+#define TIMER_INT_ALL_MASK	0x1ff
+
 
 static unsigned int tick_rate;
 
+static u64 notrace gemini_read_sched_clock(void)
+{
+	return readl(TIMER_COUNT(TIMER3_BASE));
+}
+
 static int gemini_timer_set_next_event(unsigned long cycles,
 				       struct clock_event_device *evt)
 {
 	u32 cr;
 
-	cr = readl(TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
+	/* Setup the match register */
+	cr = readl(TIMER_COUNT(TIMER1_BASE));
+	writel(cr + cycles, TIMER_MATCH1(TIMER1_BASE));
+	if (readl(TIMER_COUNT(TIMER1_BASE)) - cr > cycles)
+		return -ETIME;
 
-	/* This may be overdoing it, feel free to test without this */
-	cr &= ~TIMER_2_CR_ENABLE;
-	cr &= ~TIMER_2_CR_INT;
-	writel(cr, TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
+	return 0;
+}
 
-	/* Set next event */
-	writel(cycles, TIMER_COUNT(IO_ADDRESS(GEMINI_TIMER2_BASE)));
-	writel(cycles, TIMER_LOAD(IO_ADDRESS(GEMINI_TIMER2_BASE)));
-	cr |= TIMER_2_CR_ENABLE;
-	cr |= TIMER_2_CR_INT;
-	writel(cr, TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
+static int gemini_timer_shutdown(struct clock_event_device *evt)
+{
+	u32 cr;
+
+	/*
+	 * Disable also for oneshot: the set_next() call will arm the timer
+	 * instead.
+	 */
+	/* Stop timer and interrupt. */
+	cr = readl(TIMER_CR);
+	cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT);
+	writel(cr, TIMER_CR);
+
+	/* Setup counter start from 0 */
+	writel(0, TIMER_COUNT(TIMER1_BASE));
+	writel(0, TIMER_LOAD(TIMER1_BASE));
+
+	/* enable interrupt */
+	cr = readl(TIMER_INTR_MASK);
+	cr &= ~(TIMER_1_INT_OVERFLOW | TIMER_1_INT_MATCH2);
+	cr |= TIMER_1_INT_MATCH1;
+	writel(cr, TIMER_INTR_MASK);
+
+	/* start the timer */
+	cr = readl(TIMER_CR);
+	cr |= TIMER_1_CR_ENABLE;
+	writel(cr, TIMER_CR);
 
 	return 0;
 }
 
-static void gemini_timer_set_mode(enum clock_event_mode mode,
-				  struct clock_event_device *evt)
+static int gemini_timer_set_periodic(struct clock_event_device *evt)
 {
 	u32 period = DIV_ROUND_CLOSEST(tick_rate, HZ);
 	u32 cr;
 
-	switch (mode) {
-        case CLOCK_EVT_MODE_PERIODIC:
-		/* Start the timer */
-		writel(period,
-		       TIMER_COUNT(IO_ADDRESS(GEMINI_TIMER2_BASE)));
-		writel(period,
-		       TIMER_LOAD(IO_ADDRESS(GEMINI_TIMER2_BASE)));
-		cr = readl(TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
-		cr |= TIMER_2_CR_ENABLE;
-		cr |= TIMER_2_CR_INT;
-		writel(cr, TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-        case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		/*
-		 * Disable also for oneshot: the set_next() call will
-		 * arm the timer instead.
-		 */
-		cr = readl(TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
-		cr &= ~TIMER_2_CR_ENABLE;
-		cr &= ~TIMER_2_CR_INT;
-		writel(cr, TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
-		break;
-	default:
-                break;
-	}
+	/* Stop timer and interrupt */
+	cr = readl(TIMER_CR);
+	cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT);
+	writel(cr, TIMER_CR);
+
+	/* Setup timer to fire at 1/HT intervals. */
+	cr = 0xffffffff - (period - 1);
+	writel(cr, TIMER_COUNT(TIMER1_BASE));
+	writel(cr, TIMER_LOAD(TIMER1_BASE));
+
+	/* enable interrupt on overflow */
+	cr = readl(TIMER_INTR_MASK);
+	cr &= ~(TIMER_1_INT_MATCH1 | TIMER_1_INT_MATCH2);
+	cr |= TIMER_1_INT_OVERFLOW;
+	writel(cr, TIMER_INTR_MASK);
+
+	/* Start the timer */
+	cr = readl(TIMER_CR);
+	cr |= TIMER_1_CR_ENABLE;
+	cr |= TIMER_1_CR_INT;
+	writel(cr, TIMER_CR);
+
+	return 0;
 }
 
-/* Use TIMER2 as clock event */
+/* Use TIMER1 as clock event */
 static struct clock_event_device gemini_clockevent = {
-	.name		= "TIMER2",
-	.rating		= 300, /* Reasonably fast and accurate clock event */
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event	= gemini_timer_set_next_event,
-	.set_mode	= gemini_timer_set_mode,
+	.name			= "TIMER1",
+	/* Reasonably fast and accurate clock event */
+	.rating			= 300,
+	.shift                  = 32,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= gemini_timer_set_next_event,
+	.set_state_shutdown	= gemini_timer_shutdown,
+	.set_state_periodic	= gemini_timer_set_periodic,
+	.set_state_oneshot	= gemini_timer_shutdown,
+	.tick_resume		= gemini_timer_shutdown,
 };
 
 /*
@@ -151,20 +205,35 @@ void __init gemini_timer_init(void)
 	}
 
 	/*
-	 * Make irqs happen for the system timer
+	 * Reset the interrupt mask and status
 	 */
-	setup_irq(IRQ_TIMER2, &gemini_timer_irq);
-
-	/* Enable and use TIMER1 as clock source */
-	writel(0xffffffff, TIMER_COUNT(IO_ADDRESS(GEMINI_TIMER1_BASE)));
-	writel(0xffffffff, TIMER_LOAD(IO_ADDRESS(GEMINI_TIMER1_BASE)));
-	writel(TIMER_1_CR_ENABLE, TIMER_CR(IO_ADDRESS(GEMINI_TIMER_BASE)));
-	if (clocksource_mmio_init(TIMER_COUNT(IO_ADDRESS(GEMINI_TIMER1_BASE)),
-				  "TIMER1", tick_rate, 300, 32,
-				  clocksource_mmio_readl_up))
-		pr_err("timer: failed to initialize gemini clock source\n");
-
-	/* Configure and register the clockevent */
+	writel(TIMER_INT_ALL_MASK, TIMER_INTR_MASK);
+	writel(0, TIMER_INTR_STATE);
+	writel(TIMER_DEFAULT_FLAGS, TIMER_CR);
+
+	/*
+	 * Setup free-running clocksource timer (interrupts
+	 * disabled.)
+	 */
+	writel(0, TIMER_COUNT(TIMER3_BASE));
+	writel(0, TIMER_LOAD(TIMER3_BASE));
+	writel(0, TIMER_MATCH1(TIMER3_BASE));
+	writel(0, TIMER_MATCH2(TIMER3_BASE));
+	clocksource_mmio_init(TIMER_COUNT(TIMER3_BASE),
+			      "gemini_clocksource", tick_rate,
+			      300, 32, clocksource_mmio_readl_up);
+	sched_clock_register(gemini_read_sched_clock, 32, tick_rate);
+
+	/*
+	 * Setup clockevent timer (interrupt-driven.)
+	*/
+	writel(0, TIMER_COUNT(TIMER1_BASE));
+	writel(0, TIMER_LOAD(TIMER1_BASE));
+	writel(0, TIMER_MATCH1(TIMER1_BASE));
+	writel(0, TIMER_MATCH2(TIMER1_BASE));
+	setup_irq(IRQ_TIMER1, &gemini_timer_irq);
+	gemini_clockevent.cpumask = cpumask_of(0);
 	clockevents_config_and_register(&gemini_clockevent, tick_rate,
 					1, 0xffffffff);
+
 }
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 231fba0d03e5..6050a14faee6 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -28,8 +28,8 @@
 #include <linux/reboot.h>
 #include <linux/amba/bus.h>
 #include <linux/platform_device.h>
+#include <linux/psci.h>
 
-#include <asm/psci.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-highbank/pm.c b/arch/arm/mach-highbank/pm.c
index 7f2bd85eb935..400311695548 100644
--- a/arch/arm/mach-highbank/pm.c
+++ b/arch/arm/mach-highbank/pm.c
@@ -16,19 +16,21 @@
 
 #include <linux/cpu_pm.h>
 #include <linux/init.h>
+#include <linux/psci.h>
 #include <linux/suspend.h>
 
 #include <asm/suspend.h>
-#include <asm/psci.h>
+
+#include <uapi/linux/psci.h>
+
+#define HIGHBANK_SUSPEND_PARAM \
+	((0 << PSCI_0_2_POWER_STATE_ID_SHIFT) | \
+	 (1 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) | \
+	 (PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT))
 
 static int highbank_suspend_finish(unsigned long val)
 {
-	const struct psci_power_state ps = {
-		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
-		.affinity_level = 1,
-	};
-
-	return psci_ops.cpu_suspend(ps, __pa(cpu_resume));
+	return psci_ops.cpu_suspend(HIGHBANK_SUSPEND_PARAM, __pa(cpu_resume));
 }
 
 static int highbank_pm_enter(suspend_state_t state)
diff --git a/arch/arm/mach-hisi/hisilicon.c b/arch/arm/mach-hisi/hisilicon.c
index c6bd7c7bd4aa..8cc62150116a 100644
--- a/arch/arm/mach-hisi/hisilicon.c
+++ b/arch/arm/mach-hisi/hisilicon.c
@@ -11,7 +11,6 @@
  * published by the Free Software Foundation.
 */
 
-#include <linux/clk-provider.h>
 #include <linux/clocksource.h>
 #include <linux/irqchip.h>
 
diff --git a/arch/arm/mach-imx/3ds_debugboard.c b/arch/arm/mach-imx/3ds_debugboard.c
index 134377352966..45903be6e7b3 100644
--- a/arch/arm/mach-imx/3ds_debugboard.c
+++ b/arch/arm/mach-imx/3ds_debugboard.c
@@ -195,7 +195,7 @@ int __init mxc_expio_init(u32 base, u32 intr_gpio)
 
 	for (i = irq_base; i < irq_base + MXC_MAX_EXP_IO_LINES; i++) {
 		irq_set_chip_and_handler(i, &expio_irq_chip, handle_level_irq);
-		set_irq_flags(i, IRQF_VALID);
+		irq_clear_status_flags(i, IRQ_NOREQUEST);
 	}
 	irq_set_irq_type(p_irq, IRQF_TRIGGER_LOW);
 	irq_set_chained_handler(p_irq, mxc_expio_irq_handler);
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 573536f1bb73..8ceda2844c4f 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -548,6 +548,14 @@ config SOC_IMX6SX
 	help
 	  This enables support for Freescale i.MX6 SoloX processor.
 
+config SOC_IMX6UL
+	bool "i.MX6 UltraLite support"
+	select PINCTRL_IMX6UL
+	select SOC_IMX6
+
+	help
+	  This enables support for Freescale i.MX6 UltraLite processor.
+
 config SOC_IMX7D
 	bool "i.MX7 Dual support"
 	select PINCTRL_IMX7D
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 37c502ac9595..fb689d813b09 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -83,6 +83,7 @@ endif
 obj-$(CONFIG_SOC_IMX6Q) += mach-imx6q.o
 obj-$(CONFIG_SOC_IMX6SL) += mach-imx6sl.o
 obj-$(CONFIG_SOC_IMX6SX) += mach-imx6sx.o
+obj-$(CONFIG_SOC_IMX6UL) += mach-imx6ul.o
 obj-$(CONFIG_SOC_IMX7D) += mach-imx7d.o
 
 ifeq ($(CONFIG_SUSPEND),y)
diff --git a/arch/arm/mach-imx/cpu.c b/arch/arm/mach-imx/cpu.c
index a7fa92a7b1d7..5b0f752d5507 100644
--- a/arch/arm/mach-imx/cpu.c
+++ b/arch/arm/mach-imx/cpu.c
@@ -130,6 +130,9 @@ struct device * __init imx_soc_device_init(void)
 	case MXC_CPU_IMX6Q:
 		soc_id = "i.MX6Q";
 		break;
+	case MXC_CPU_IMX6UL:
+		soc_id = "i.MX6UL";
+		break;
 	case MXC_CPU_IMX7D:
 		soc_id = "i.MX7D";
 		break;
diff --git a/arch/arm/mach-imx/epit.c b/arch/arm/mach-imx/epit.c
index 074b1a81ba76..08ce20771bb3 100644
--- a/arch/arm/mach-imx/epit.c
+++ b/arch/arm/mach-imx/epit.c
@@ -57,7 +57,6 @@
 #include "hardware.h"
 
 static struct clock_event_device clockevent_epit;
-static enum clock_event_mode clockevent_mode = CLOCK_EVT_MODE_UNUSED;
 
 static void __iomem *timer_base;
 
@@ -106,8 +105,8 @@ static int epit_set_next_event(unsigned long evt,
 	return 0;
 }
 
-static void epit_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+/* Left event sources disabled, no more interrupts appear */
+static int epit_shutdown(struct clock_event_device *evt)
 {
 	unsigned long flags;
 
@@ -120,39 +119,41 @@ static void epit_set_mode(enum clock_event_mode mode,
 	/* Disable interrupt in GPT module */
 	epit_irq_disable();
 
-	if (mode != clockevent_mode) {
-		/* Set event time into far-far future */
-
-		/* Clear pending interrupt */
-		epit_irq_acknowledge();
-	}
+	/* Clear pending interrupt */
+	epit_irq_acknowledge();
 
-	/* Remember timer mode */
-	clockevent_mode = mode;
 	local_irq_restore(flags);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		printk(KERN_ERR "epit_set_mode: Periodic mode is not "
-				"supported for i.MX EPIT\n");
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
+	return 0;
+}
+
+static int epit_set_oneshot(struct clock_event_device *evt)
+{
+	unsigned long flags;
+
+	/*
+	 * The timer interrupt generation is disabled at least
+	 * for enough time to call epit_set_next_event()
+	 */
+	local_irq_save(flags);
+
+	/* Disable interrupt in GPT module */
+	epit_irq_disable();
+
+	/* Clear pending interrupt, only while switching mode */
+	if (!clockevent_state_oneshot(evt))
+		epit_irq_acknowledge();
+
 	/*
 	 * Do not put overhead of interrupt enable/disable into
 	 * epit_set_next_event(), the core has about 4 minutes
 	 * to call epit_set_next_event() or shutdown clock after
 	 * mode switching
 	 */
-		local_irq_save(flags);
-		epit_irq_enable();
-		local_irq_restore(flags);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		/* Left event sources disabled, no more interrupts appear */
-		break;
-	}
+	epit_irq_enable();
+	local_irq_restore(flags);
+
+	return 0;
 }
 
 /*
@@ -176,11 +177,13 @@ static struct irqaction epit_timer_irq = {
 };
 
 static struct clock_event_device clockevent_epit = {
-	.name		= "epit",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= epit_set_mode,
-	.set_next_event	= epit_set_next_event,
-	.rating		= 200,
+	.name			= "epit",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= epit_shutdown,
+	.tick_resume		= epit_shutdown,
+	.set_state_oneshot	= epit_set_oneshot,
+	.set_next_event		= epit_set_next_event,
+	.rating			= 200,
 };
 
 static int __init epit_clockevent_init(struct clk *timer_clk)
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 80bad29d609a..8c4467fad837 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -291,8 +291,6 @@ void __init imx_gpc_check_dt(void)
 	}
 }
 
-#ifdef CONFIG_PM_GENERIC_DOMAINS
-
 static void _imx6q_pm_pu_power_off(struct generic_pm_domain *genpd)
 {
 	int iso, iso2sw;
@@ -399,7 +397,6 @@ static struct genpd_onecell_data imx_gpc_onecell_data = {
 static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 {
 	struct clk *clk;
-	bool is_off;
 	int i;
 
 	imx6q_pu_domain.reg = pu_reg;
@@ -416,18 +413,13 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 	}
 	imx6q_pu_domain.num_clks = i;
 
-	is_off = IS_ENABLED(CONFIG_PM);
-	if (is_off) {
-		_imx6q_pm_pu_power_off(&imx6q_pu_domain.base);
-	} else {
-		/*
-		 * Enable power if compiled without CONFIG_PM in case the
-		 * bootloader disabled it.
-		 */
-		imx6q_pm_pu_power_on(&imx6q_pu_domain.base);
-	}
+	/* Enable power always in case bootloader disabled it. */
+	imx6q_pm_pu_power_on(&imx6q_pu_domain.base);
+
+	if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
+		return 0;
 
-	pm_genpd_init(&imx6q_pu_domain.base, NULL, is_off);
+	pm_genpd_init(&imx6q_pu_domain.base, NULL, false);
 	return of_genpd_add_provider_onecell(dev->of_node,
 					     &imx_gpc_onecell_data);
 
@@ -437,13 +429,6 @@ clk_err:
 	return -EINVAL;
 }
 
-#else
-static inline int imx_gpc_genpd_init(struct device *dev, struct regulator *reg)
-{
-	return 0;
-}
-#endif /* CONFIG_PM_GENERIC_DOMAINS */
-
 static int imx_gpc_probe(struct platform_device *pdev)
 {
 	struct regulator *pu_reg;
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
new file mode 100644
index 000000000000..1b97fe133cef
--- /dev/null
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -0,0 +1,88 @@
+/*
+ * Copyright (C) 2015 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/irqchip.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
+#include <linux/micrel_phy.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/regmap.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+
+#include "common.h"
+
+static void __init imx6ul_enet_clk_init(void)
+{
+	struct regmap *gpr;
+
+	gpr = syscon_regmap_lookup_by_compatible("fsl,imx6ul-iomuxc-gpr");
+	if (!IS_ERR(gpr))
+		regmap_update_bits(gpr, IOMUXC_GPR1, IMX6UL_GPR1_ENET_CLK_DIR,
+				   IMX6UL_GPR1_ENET_CLK_OUTPUT);
+	else
+		pr_err("failed to find fsl,imx6ul-iomux-gpr regmap\n");
+
+}
+
+static int ksz8081_phy_fixup(struct phy_device *dev)
+{
+	if (dev && dev->interface == PHY_INTERFACE_MODE_MII) {
+		phy_write(dev, 0x1f, 0x8110);
+		phy_write(dev, 0x16, 0x201);
+	} else if (dev && dev->interface == PHY_INTERFACE_MODE_RMII) {
+		phy_write(dev, 0x1f, 0x8190);
+		phy_write(dev, 0x16, 0x202);
+	}
+
+	return 0;
+}
+
+static void __init imx6ul_enet_phy_init(void)
+{
+	if (IS_BUILTIN(CONFIG_PHYLIB))
+		phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff,
+					   ksz8081_phy_fixup);
+}
+
+static inline void imx6ul_enet_init(void)
+{
+	imx6ul_enet_clk_init();
+	imx6ul_enet_phy_init();
+}
+
+static void __init imx6ul_init_machine(void)
+{
+	struct device *parent;
+
+	parent = imx_soc_device_init();
+	if (parent == NULL)
+		pr_warn("failed to initialize soc device\n");
+
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	imx6ul_enet_init();
+	imx_anatop_init();
+}
+
+static void __init imx6ul_init_irq(void)
+{
+	imx_init_revision_from_anatop();
+	imx_src_init();
+	irqchip_init();
+}
+
+static const char *imx6ul_dt_compat[] __initconst = {
+	"fsl,imx6ul",
+	NULL,
+};
+
+DT_MACHINE_START(IMX6UL, "Freescale i.MX6 Ultralite (Device Tree)")
+	.init_irq	= imx6ul_init_irq,
+	.init_machine	= imx6ul_init_machine,
+	.dt_compat	= imx6ul_dt_compat,
+MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx7d.c b/arch/arm/mach-imx/mach-imx7d.c
index 4d4a19099a43..62f3437257f1 100644
--- a/arch/arm/mach-imx/mach-imx7d.c
+++ b/arch/arm/mach-imx/mach-imx7d.c
@@ -31,7 +31,7 @@ static void __init imx7d_init_irq(void)
 	irqchip_init();
 }
 
-static const char *imx7d_dt_compat[] __initconst = {
+static const char *const imx7d_dt_compat[] __initconst = {
 	"fsl,imx7d",
 	NULL,
 };
diff --git a/arch/arm/mach-imx/mach-mx31ads.c b/arch/arm/mach-imx/mach-mx31ads.c
index d08c37c696f6..2c0853560bd2 100644
--- a/arch/arm/mach-imx/mach-mx31ads.c
+++ b/arch/arm/mach-imx/mach-mx31ads.c
@@ -238,7 +238,7 @@ static void __init mx31ads_init_expio(void)
 
 	for (i = irq_base; i < irq_base + MXC_MAX_EXP_IO_LINES; i++) {
 		irq_set_chip_and_handler(i, &expio_irq_chip, handle_level_irq);
-		set_irq_flags(i, IRQF_VALID);
+		irq_clear_status_flags(i, IRQ_NOREQUEST);
 	}
 	irq = gpio_to_irq(IOMUX_TO_GPIO(MX31_PIN_GPIO1_4));
 	irq_set_irq_type(irq, IRQ_TYPE_LEVEL_HIGH);
diff --git a/arch/arm/mach-imx/mxc.h b/arch/arm/mach-imx/mxc.h
index c4436d4fd6fd..a5b1af6d7441 100644
--- a/arch/arm/mach-imx/mxc.h
+++ b/arch/arm/mach-imx/mxc.h
@@ -38,6 +38,7 @@
 #define MXC_CPU_IMX6DL		0x61
 #define MXC_CPU_IMX6SX		0x62
 #define MXC_CPU_IMX6Q		0x63
+#define MXC_CPU_IMX6UL		0x64
 #define MXC_CPU_IMX7D		0x72
 
 #define IMX_DDR_TYPE_LPDDR2		1
@@ -165,6 +166,11 @@ static inline bool cpu_is_imx6sx(void)
 	return __mxc_cpu_type == MXC_CPU_IMX6SX;
 }
 
+static inline bool cpu_is_imx6ul(void)
+{
+	return __mxc_cpu_type == MXC_CPU_IMX6UL;
+}
+
 static inline bool cpu_is_imx6q(void)
 {
 	return __mxc_cpu_type == MXC_CPU_IMX6Q;
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index 1885676c23c0..532d4b08276d 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -297,7 +297,7 @@ static int __init imx_suspend_alloc_ocram(
 		goto put_node;
 	}
 
-	ocram_pool = gen_pool_get(&pdev->dev);
+	ocram_pool = gen_pool_get(&pdev->dev, NULL);
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 93ecf559d06d..8ff8fc0b261c 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -451,7 +451,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 		goto put_node;
 	}
 
-	ocram_pool = gen_pool_get(&pdev->dev);
+	ocram_pool = gen_pool_get(&pdev->dev, NULL);
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-iop13xx/irq.c b/arch/arm/mach-iop13xx/irq.c
index bc739701c301..623d85a4af2d 100644
--- a/arch/arm/mach-iop13xx/irq.c
+++ b/arch/arm/mach-iop13xx/irq.c
@@ -233,7 +233,7 @@ void __init iop13xx_init_irq(void)
 			irq_set_chip(i, &iop13xx_irqchip4);
 
 		irq_set_handler(i, handle_level_irq);
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(i, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	iop13xx_msi_init();
diff --git a/arch/arm/mach-iop32x/irq.c b/arch/arm/mach-iop32x/irq.c
index d7ee2789d890..2d1f69a68cbc 100644
--- a/arch/arm/mach-iop32x/irq.c
+++ b/arch/arm/mach-iop32x/irq.c
@@ -69,6 +69,6 @@ void __init iop32x_init_irq(void)
 
 	for (i = 0; i < NR_IRQS; i++) {
 		irq_set_chip_and_handler(i, &ext_chip, handle_level_irq);
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(i, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 }
diff --git a/arch/arm/mach-iop33x/irq.c b/arch/arm/mach-iop33x/irq.c
index f7f5d3e451c7..c99ec8d0d285 100644
--- a/arch/arm/mach-iop33x/irq.c
+++ b/arch/arm/mach-iop33x/irq.c
@@ -113,6 +113,6 @@ void __init iop33x_init_irq(void)
 		irq_set_chip_and_handler(i,
 					 (i < 32) ? &iop33x_irqchip1 : &iop33x_irqchip2,
 					 handle_level_irq);
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(i, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 }
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 8537d4c41e34..1cb6f2f02880 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -296,7 +296,7 @@ void __init ixp4xx_init_irq(void)
 	for(i = 0; i < NR_IRQS; i++) {
 		irq_set_chip_and_handler(i, &ixp4xx_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(i, IRQF_VALID);
+		irq_clear_status_flags(i, IRQ_NOREQUEST);
 	}
 }
 
@@ -521,43 +521,55 @@ static int ixp4xx_set_next_event(unsigned long evt,
 	return 0;
 }
 
-static void ixp4xx_set_mode(enum clock_event_mode mode,
-			    struct clock_event_device *evt)
+static int ixp4xx_shutdown(struct clock_event_device *evt)
 {
 	unsigned long opts = *IXP4XX_OSRT1 & IXP4XX_OST_RELOAD_MASK;
 	unsigned long osrt = *IXP4XX_OSRT1 & ~IXP4XX_OST_RELOAD_MASK;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		osrt = IXP4XX_LATCH & ~IXP4XX_OST_RELOAD_MASK;
- 		opts = IXP4XX_OST_ENABLE;
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* period set by 'set next_event' */
-		osrt = 0;
-		opts = IXP4XX_OST_ENABLE | IXP4XX_OST_ONE_SHOT;
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		opts &= ~IXP4XX_OST_ENABLE;
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		opts |= IXP4XX_OST_ENABLE;
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	default:
-		osrt = opts = 0;
-		break;
-	}
+	opts &= ~IXP4XX_OST_ENABLE;
+	*IXP4XX_OSRT1 = osrt | opts;
+	return 0;
+}
 
+static int ixp4xx_set_oneshot(struct clock_event_device *evt)
+{
+	unsigned long opts = IXP4XX_OST_ENABLE | IXP4XX_OST_ONE_SHOT;
+	unsigned long osrt = 0;
+
+	/* period set by 'set next_event' */
 	*IXP4XX_OSRT1 = osrt | opts;
+	return 0;
+}
+
+static int ixp4xx_set_periodic(struct clock_event_device *evt)
+{
+	unsigned long opts = IXP4XX_OST_ENABLE;
+	unsigned long osrt = IXP4XX_LATCH & ~IXP4XX_OST_RELOAD_MASK;
+
+	*IXP4XX_OSRT1 = osrt | opts;
+	return 0;
+}
+
+static int ixp4xx_resume(struct clock_event_device *evt)
+{
+	unsigned long opts = *IXP4XX_OSRT1 & IXP4XX_OST_RELOAD_MASK;
+	unsigned long osrt = *IXP4XX_OSRT1 & ~IXP4XX_OST_RELOAD_MASK;
+
+	opts |= IXP4XX_OST_ENABLE;
+	*IXP4XX_OSRT1 = osrt | opts;
+	return 0;
 }
 
 static struct clock_event_device clockevent_ixp4xx = {
-	.name		= "ixp4xx timer1",
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating         = 200,
-	.set_mode	= ixp4xx_set_mode,
-	.set_next_event	= ixp4xx_set_next_event,
+	.name			= "ixp4xx timer1",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_state_shutdown	= ixp4xx_shutdown,
+	.set_state_periodic	= ixp4xx_set_periodic,
+	.set_state_oneshot	= ixp4xx_set_oneshot,
+	.tick_resume		= ixp4xx_resume,
+	.set_next_event		= ixp4xx_set_next_event,
 };
 
 static void __init ixp4xx_clockevent_init(void)
diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c
index edea697e8253..e283939a216f 100644
--- a/arch/arm/mach-keystone/pm_domain.c
+++ b/arch/arm/mach-keystone/pm_domain.c
@@ -16,7 +16,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/pm_clock.h>
 #include <linux/platform_device.h>
-#include <linux/clk-provider.h>
 #include <linux/of.h>
 
 static struct dev_pm_domain keystone_pm_domain = {
diff --git a/arch/arm/mach-ks8695/irq.c b/arch/arm/mach-ks8695/irq.c
index 76802aac0f45..31439f2ee21e 100644
--- a/arch/arm/mach-ks8695/irq.c
+++ b/arch/arm/mach-ks8695/irq.c
@@ -172,6 +172,6 @@ void __init ks8695_init_irq(void)
 							 handle_edge_irq);
 		}
 
-		set_irq_flags(irq, IRQF_VALID);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
 	}
 }
diff --git a/arch/arm/mach-ks8695/time.c b/arch/arm/mach-ks8695/time.c
index a197874bf382..18eb0fbd8d82 100644
--- a/arch/arm/mach-ks8695/time.c
+++ b/arch/arm/mach-ks8695/time.c
@@ -54,28 +54,25 @@
 /* Timer0 Timeout Counter Register */
 #define T0TC_WATCHDOG		(0xff)		/* Enable watchdog mode */
 
-static void ks8695_set_mode(enum clock_event_mode mode,
-			    struct clock_event_device *evt)
+static int ks8695_set_periodic(struct clock_event_device *evt)
 {
+	u32 rate = DIV_ROUND_CLOSEST(KS8695_CLOCK_RATE, HZ);
+	u32 half = DIV_ROUND_CLOSEST(rate, 2);
 	u32 tmcon;
 
-	if (mode == CLOCK_EVT_FEAT_PERIODIC) {
-		u32 rate = DIV_ROUND_CLOSEST(KS8695_CLOCK_RATE, HZ);
-		u32 half = DIV_ROUND_CLOSEST(rate, 2);
-
-		/* Disable timer 1 */
-		tmcon = readl_relaxed(KS8695_TMR_VA + KS8695_TMCON);
-		tmcon &= ~TMCON_T1EN;
-		writel_relaxed(tmcon, KS8695_TMR_VA + KS8695_TMCON);
+	/* Disable timer 1 */
+	tmcon = readl_relaxed(KS8695_TMR_VA + KS8695_TMCON);
+	tmcon &= ~TMCON_T1EN;
+	writel_relaxed(tmcon, KS8695_TMR_VA + KS8695_TMCON);
 
-		/* Both registers need to count down */
-		writel_relaxed(half, KS8695_TMR_VA + KS8695_T1TC);
-		writel_relaxed(half, KS8695_TMR_VA + KS8695_T1PD);
+	/* Both registers need to count down */
+	writel_relaxed(half, KS8695_TMR_VA + KS8695_T1TC);
+	writel_relaxed(half, KS8695_TMR_VA + KS8695_T1PD);
 
-		/* Re-enable timer1 */
-		tmcon |= TMCON_T1EN;
-		writel_relaxed(tmcon, KS8695_TMR_VA + KS8695_TMCON);
-	}
+	/* Re-enable timer1 */
+	tmcon |= TMCON_T1EN;
+	writel_relaxed(tmcon, KS8695_TMR_VA + KS8695_TMCON);
+	return 0;
 }
 
 static int ks8695_set_next_event(unsigned long cycles,
@@ -102,11 +99,13 @@ static int ks8695_set_next_event(unsigned long cycles,
 }
 
 static struct clock_event_device clockevent_ks8695 = {
-	.name		= "ks8695_t1tc",
-	.rating		= 300, /* Reasonably fast and accurate clock event */
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.set_next_event	= ks8695_set_next_event,
-	.set_mode	= ks8695_set_mode,
+	.name			= "ks8695_t1tc",
+	/* Reasonably fast and accurate clock event */
+	.rating			= 300,
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.set_next_event		= ks8695_set_next_event,
+	.set_state_periodic	= ks8695_set_periodic,
 };
 
 /*
diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c
index d4f7dc87042b..cce4cef12b6e 100644
--- a/arch/arm/mach-lpc32xx/irq.c
+++ b/arch/arm/mach-lpc32xx/irq.c
@@ -283,25 +283,25 @@ static int lpc32xx_set_irq_type(struct irq_data *d, unsigned int type)
 	case IRQ_TYPE_EDGE_RISING:
 		/* Rising edge sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 1, 1);
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 		break;
 
 	case IRQ_TYPE_EDGE_FALLING:
 		/* Falling edge sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 0, 1);
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 		break;
 
 	case IRQ_TYPE_LEVEL_LOW:
 		/* Low level sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 0, 0);
-		__irq_set_handler_locked(d->irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 		break;
 
 	case IRQ_TYPE_LEVEL_HIGH:
 		/* High level sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 1, 0);
-		__irq_set_handler_locked(d->irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 		break;
 
 	/* Other modes are not supported */
@@ -434,7 +434,7 @@ void __init lpc32xx_init_irq(void)
 	for (i = 0; i < NR_IRQS; i++) {
 		irq_set_chip_and_handler(i, &lpc32xx_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(i, IRQF_VALID);
+		irq_clear_status_flags(i, IRQ_NOREQUEST);
 	}
 
 	/* Set default mappings */
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 7858d5b6f6ce..77d6b1bab278 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -212,7 +212,7 @@ static struct lpc32xx_mlc_platform_data lpc32xx_mlc_data = {
 	.dma_filter = pl08x_filter_id,
 };
 
-static const struct of_dev_auxdata lpc32xx_auxdata_lookup[] __initconst = {
+static const struct of_dev_auxdata const lpc32xx_auxdata_lookup[] __initconst = {
 	OF_DEV_AUXDATA("arm,pl022", 0x20084000, "dev:ssp0", NULL),
 	OF_DEV_AUXDATA("arm,pl022", 0x2008C000, "dev:ssp1", NULL),
 	OF_DEV_AUXDATA("arm,pl110", 0x31040000, "dev:clcd", &lpc32xx_clcd_data),
@@ -248,7 +248,7 @@ static void __init lpc3250_machine_init(void)
 			     lpc32xx_auxdata_lookup, NULL);
 }
 
-static char const *lpc32xx_dt_compat[] __initdata = {
+static const char *const lpc32xx_dt_compat[] __initconst = {
 	"nxp,lpc3220",
 	"nxp,lpc3230",
 	"nxp,lpc3240",
diff --git a/arch/arm/mach-lpc32xx/timer.c b/arch/arm/mach-lpc32xx/timer.c
index 4e5837299c04..ff3499d1fb1a 100644
--- a/arch/arm/mach-lpc32xx/timer.c
+++ b/arch/arm/mach-lpc32xx/timer.c
@@ -43,36 +43,24 @@ static int lpc32xx_clkevt_next_event(unsigned long delta,
 	return 0;
 }
 
-static void lpc32xx_clkevt_mode(enum clock_event_mode mode,
-    struct clock_event_device *dev)
+static int lpc32xx_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		WARN_ON(1);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/*
-		 * Disable the timer. When using oneshot, we must also
-		 * disable the timer to wait for the first call to
-		 * set_next_event().
-		 */
-		__raw_writel(0, LPC32XX_TIMER_TCR(LPC32XX_TIMER0_BASE));
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	/*
+	 * Disable the timer. When using oneshot, we must also
+	 * disable the timer to wait for the first call to
+	 * set_next_event().
+	 */
+	__raw_writel(0, LPC32XX_TIMER_TCR(LPC32XX_TIMER0_BASE));
+	return 0;
 }
 
 static struct clock_event_device lpc32xx_clkevt = {
-	.name		= "lpc32xx_clkevt",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 300,
-	.set_next_event	= lpc32xx_clkevt_next_event,
-	.set_mode	= lpc32xx_clkevt_mode,
+	.name			= "lpc32xx_clkevt",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 300,
+	.set_next_event		= lpc32xx_clkevt_next_event,
+	.set_state_shutdown	= lpc32xx_shutdown,
+	.set_state_oneshot	= lpc32xx_shutdown,
 };
 
 static irqreturn_t lpc32xx_timer_interrupt(int irq, void *dev_id)
diff --git a/arch/arm/mach-mediatek/Kconfig b/arch/arm/mach-mediatek/Kconfig
index 9f59e58da3a4..aeece17e5cea 100644
--- a/arch/arm/mach-mediatek/Kconfig
+++ b/arch/arm/mach-mediatek/Kconfig
@@ -3,6 +3,7 @@ menuconfig ARCH_MEDIATEK
 	select ARM_GIC
 	select PINCTRL
 	select MTK_TIMER
+	select MFD_SYSCON
 	help
 	  Support for Mediatek MT65xx & MT81xx SoCs
 
diff --git a/arch/arm/mach-mmp/mmp-dt.c b/arch/arm/mach-mmp/mmp-dt.c
index b2296c9309b8..6e155f03b83c 100644
--- a/arch/arm/mach-mmp/mmp-dt.c
+++ b/arch/arm/mach-mmp/mmp-dt.c
@@ -20,12 +20,12 @@
 
 extern void __init mmp_dt_init_timer(void);
 
-static const char *pxa168_dt_board_compat[] __initdata = {
+static const char *const pxa168_dt_board_compat[] __initconst = {
 	"mrvl,pxa168-aspenite",
 	NULL,
 };
 
-static const char *pxa910_dt_board_compat[] __initdata = {
+static const char *const pxa910_dt_board_compat[] __initconst = {
 	"mrvl,pxa910-dkb",
 	NULL,
 };
diff --git a/arch/arm/mach-mmp/mmp2-dt.c b/arch/arm/mach-mmp/mmp2-dt.c
index 998c0f533abc..0341359b24a4 100644
--- a/arch/arm/mach-mmp/mmp2-dt.c
+++ b/arch/arm/mach-mmp/mmp2-dt.c
@@ -30,7 +30,7 @@ static void __init mmp_init_time(void)
 	of_clk_init(NULL);
 }
 
-static const char *mmp2_dt_board_compat[] __initdata = {
+static const char *const mmp2_dt_board_compat[] __initconst = {
 	"mrvl,mmp2-brownstone",
 	NULL,
 };
diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c
index 04c9daf9f8d7..7db5870d127f 100644
--- a/arch/arm/mach-mmp/pm-pxa910.c
+++ b/arch/arm/mach-mmp/pm-pxa910.c
@@ -18,6 +18,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <asm/mach-types.h>
+#include <asm/outercache.h>
 #include <mach/hardware.h>
 #include <mach/cputype.h>
 #include <mach/addr-map.h>
diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c
index 10bfa03e58d4..dbc697b2fda1 100644
--- a/arch/arm/mach-mmp/time.c
+++ b/arch/arm/mach-mmp/time.c
@@ -124,32 +124,25 @@ static int timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void timer_set_mode(enum clock_event_mode mode,
-			   struct clock_event_device *dev)
+static int timer_set_shutdown(struct clock_event_device *evt)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/* disable the matching interrupt */
-		__raw_writel(0x00, mmp_timer_base + TMR_IER(0));
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		break;
-	}
+	/* disable the matching interrupt */
+	__raw_writel(0x00, mmp_timer_base + TMR_IER(0));
 	local_irq_restore(flags);
+
+	return 0;
 }
 
 static struct clock_event_device ckevt = {
-	.name		= "clockevent",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= timer_set_next_event,
-	.set_mode	= timer_set_mode,
+	.name			= "clockevent",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= timer_set_next_event,
+	.set_state_shutdown	= timer_set_shutdown,
+	.set_state_oneshot	= timer_set_shutdown,
 };
 
 static cycle_t clksrc_read(struct clocksource *cs)
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 97473168d6b6..c86a5a0aefac 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -96,6 +96,7 @@ config MACH_DOVE
 	select MACH_MVEBU_ANY
 	select ORION_IRQCHIP
 	select ORION_TIMER
+	select PM_GENERIC_DOMAINS if PM
 	select PINCTRL_DOVE
 	help
 	  Say 'Y' here if you want your kernel to support the
diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c
index afee9083ad92..9f739f3cad4c 100644
--- a/arch/arm/mach-mvebu/board-v7.c
+++ b/arch/arm/mach-mvebu/board-v7.c
@@ -14,7 +14,6 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index e46e9ea1e187..44eedf331ae7 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -65,18 +65,6 @@ static const struct of_device_id of_coherency_table[] = {
 int ll_enable_coherency(void);
 void ll_add_cpu_to_smp_group(void);
 
-int set_cpu_coherent(void)
-{
-	if (!coherency_base) {
-		pr_warn("Can't make current CPU cache coherent.\n");
-		pr_warn("Coherency fabric is not initialized\n");
-		return 1;
-	}
-
-	ll_add_cpu_to_smp_group();
-	return ll_enable_coherency();
-}
-
 static int mvebu_hwcc_notifier(struct notifier_block *nb,
 			       unsigned long event, void *__dev)
 {
@@ -206,6 +194,23 @@ static int coherency_type(void)
 	return type;
 }
 
+int set_cpu_coherent(void)
+{
+	int type = coherency_type();
+
+	if (type == COHERENCY_FABRIC_TYPE_ARMADA_370_XP) {
+		if (!coherency_base) {
+			pr_warn("Can't make current CPU cache coherent.\n");
+			pr_warn("Coherency fabric is not initialized\n");
+			return 1;
+		}
+		ll_add_cpu_to_smp_group();
+		return ll_enable_coherency();
+	}
+
+	return 0;
+}
+
 int coherency_available(void)
 {
 	return coherency_type() != COHERENCY_FABRIC_TYPE_NONE;
diff --git a/arch/arm/mach-mvebu/common.h b/arch/arm/mach-mvebu/common.h
index 3e0aca1f288a..6b775492cfad 100644
--- a/arch/arm/mach-mvebu/common.h
+++ b/arch/arm/mach-mvebu/common.h
@@ -25,6 +25,6 @@ int mvebu_system_controller_get_soc_id(u32 *dev, u32 *rev);
 
 void __iomem *mvebu_get_scu_base(void);
 
-int mvebu_pm_init(void (*board_pm_enter)(void __iomem *sdram_reg, u32 srcmd));
-
+int mvebu_pm_suspend_init(void (*board_pm_enter)(void __iomem *sdram_reg,
+							u32 srcmd));
 #endif
diff --git a/arch/arm/mach-mvebu/dove.c b/arch/arm/mach-mvebu/dove.c
index 5a1741500a30..1aebb82e3d7b 100644
--- a/arch/arm/mach-mvebu/dove.c
+++ b/arch/arm/mach-mvebu/dove.c
@@ -12,6 +12,7 @@
 #include <linux/mbus.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/soc/dove/pmu.h>
 #include <asm/hardware/cache-tauros2.h>
 #include <asm/mach/arch.h>
 #include "common.h"
@@ -24,6 +25,7 @@ static void __init dove_init(void)
 	tauros2_init(0);
 #endif
 	BUG_ON(mvebu_mbus_dt_init(false));
+	dove_init_pmu();
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
diff --git a/arch/arm/mach-mvebu/pm-board.c b/arch/arm/mach-mvebu/pm-board.c
index 301ab38d38ba..db17121d7d63 100644
--- a/arch/arm/mach-mvebu/pm-board.c
+++ b/arch/arm/mach-mvebu/pm-board.c
@@ -1,7 +1,7 @@
 /*
  * Board-level suspend/resume support.
  *
- * Copyright (C) 2014 Marvell
+ * Copyright (C) 2014-2015 Marvell
  *
  * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
  *
@@ -20,27 +20,27 @@
 #include <linux/slab.h>
 #include "common.h"
 
-#define ARMADA_XP_GP_PIC_NR_GPIOS 3
+#define ARMADA_PIC_NR_GPIOS 3
 
 static void __iomem *gpio_ctrl;
-static int pic_gpios[ARMADA_XP_GP_PIC_NR_GPIOS];
-static int pic_raw_gpios[ARMADA_XP_GP_PIC_NR_GPIOS];
+static int pic_gpios[ARMADA_PIC_NR_GPIOS];
+static int pic_raw_gpios[ARMADA_PIC_NR_GPIOS];
 
-static void mvebu_armada_xp_gp_pm_enter(void __iomem *sdram_reg, u32 srcmd)
+static void mvebu_armada_pm_enter(void __iomem *sdram_reg, u32 srcmd)
 {
 	u32 reg, ackcmd;
 	int i;
 
 	/* Put 001 as value on the GPIOs */
 	reg = readl(gpio_ctrl);
-	for (i = 0; i < ARMADA_XP_GP_PIC_NR_GPIOS; i++)
+	for (i = 0; i < ARMADA_PIC_NR_GPIOS; i++)
 		reg &= ~BIT(pic_raw_gpios[i]);
 	reg |= BIT(pic_raw_gpios[0]);
 	writel(reg, gpio_ctrl);
 
 	/* Prepare writing 111 to the GPIOs */
 	ackcmd = readl(gpio_ctrl);
-	for (i = 0; i < ARMADA_XP_GP_PIC_NR_GPIOS; i++)
+	for (i = 0; i < ARMADA_PIC_NR_GPIOS; i++)
 		ackcmd |= BIT(pic_raw_gpios[i]);
 
 	srcmd = cpu_to_le32(srcmd);
@@ -76,7 +76,7 @@ static void mvebu_armada_xp_gp_pm_enter(void __iomem *sdram_reg, u32 srcmd)
 		  [ackcmd] "r" (ackcmd), [gpio_ctrl] "r" (gpio_ctrl) : "r1");
 }
 
-static int mvebu_armada_xp_gp_pm_init(void)
+static int __init mvebu_armada_pm_init(void)
 {
 	struct device_node *np;
 	struct device_node *gpio_ctrl_np;
@@ -89,7 +89,7 @@ static int mvebu_armada_xp_gp_pm_init(void)
 	if (!np)
 		return -ENODEV;
 
-	for (i = 0; i < ARMADA_XP_GP_PIC_NR_GPIOS; i++) {
+	for (i = 0; i < ARMADA_PIC_NR_GPIOS; i++) {
 		char *name;
 		struct of_phandle_args args;
 
@@ -134,11 +134,19 @@ static int mvebu_armada_xp_gp_pm_init(void)
 	if (!gpio_ctrl)
 		return -ENOMEM;
 
-	mvebu_pm_init(mvebu_armada_xp_gp_pm_enter);
+	mvebu_pm_suspend_init(mvebu_armada_pm_enter);
 
 out:
 	of_node_put(np);
 	return ret;
 }
 
-late_initcall(mvebu_armada_xp_gp_pm_init);
+/*
+ * Registering the mvebu_board_pm_enter callback must be done before
+ * the platform_suspend_ops will be registered. In the same time we
+ * also need to have the gpio devices registered. That's why we use a
+ * device_initcall_sync which is called after all the device_initcall
+ * (used by the gpio device) but before the late_initcall (used to
+ * register the platform_suspend_ops)
+ */
+device_initcall_sync(mvebu_armada_pm_init);
diff --git a/arch/arm/mach-mvebu/pm.c b/arch/arm/mach-mvebu/pm.c
index 6573a8f11f70..8d32bf762b86 100644
--- a/arch/arm/mach-mvebu/pm.c
+++ b/arch/arm/mach-mvebu/pm.c
@@ -105,12 +105,10 @@ static phys_addr_t mvebu_internal_reg_base(void)
 	return of_translate_address(np, in_addr);
 }
 
-static void mvebu_pm_store_bootinfo(void)
+static void mvebu_pm_store_armadaxp_bootinfo(u32 *store_addr)
 {
-	u32 *store_addr;
 	phys_addr_t resume_pc;
 
-	store_addr = phys_to_virt(BOOT_INFO_ADDR);
 	resume_pc = virt_to_phys(armada_370_xp_cpu_resume);
 
 	/*
@@ -151,14 +149,30 @@ static void mvebu_pm_store_bootinfo(void)
 	writel(BOOT_MAGIC_LIST_END, store_addr);
 }
 
-static int mvebu_pm_enter(suspend_state_t state)
+static int mvebu_pm_store_bootinfo(void)
 {
-	if (state != PM_SUSPEND_MEM)
-		return -EINVAL;
+	u32 *store_addr;
+
+	store_addr = phys_to_virt(BOOT_INFO_ADDR);
+
+	if (of_machine_is_compatible("marvell,armadaxp"))
+		mvebu_pm_store_armadaxp_bootinfo(store_addr);
+	else
+		return -ENODEV;
+
+	return 0;
+}
+
+static int mvebu_enter_suspend(void)
+{
+	int ret;
+
+	ret = mvebu_pm_store_bootinfo();
+	if (ret)
+		return ret;
 
 	cpu_pm_enter();
 
-	mvebu_pm_store_bootinfo();
 	cpu_suspend(0, mvebu_pm_powerdown);
 
 	outer_resume();
@@ -168,23 +182,62 @@ static int mvebu_pm_enter(suspend_state_t state)
 	set_cpu_coherent();
 
 	cpu_pm_exit();
+	return 0;
+}
+
+static int mvebu_pm_enter(suspend_state_t state)
+{
+	switch (state) {
+	case PM_SUSPEND_STANDBY:
+		cpu_do_idle();
+		break;
+	case PM_SUSPEND_MEM:
+		pr_warn("Entering suspend to RAM. Only special wake-up sources will resume the system\n");
+		return mvebu_enter_suspend();
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int mvebu_pm_valid(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_STANDBY)
+		return 1;
+
+	if (state == PM_SUSPEND_MEM && mvebu_board_pm_enter != NULL)
+		return 1;
 
 	return 0;
 }
 
 static const struct platform_suspend_ops mvebu_pm_ops = {
 	.enter = mvebu_pm_enter,
-	.valid = suspend_valid_only_mem,
+	.valid = mvebu_pm_valid,
 };
 
-int mvebu_pm_init(void (*board_pm_enter)(void __iomem *sdram_reg, u32 srcmd))
+static int __init mvebu_pm_init(void)
+{
+	if (!of_machine_is_compatible("marvell,armadaxp") &&
+	    !of_machine_is_compatible("marvell,armada370") &&
+	    !of_machine_is_compatible("marvell,armada380") &&
+	    !of_machine_is_compatible("marvell,armada390"))
+		return -ENODEV;
+
+	suspend_set_ops(&mvebu_pm_ops);
+
+	return 0;
+}
+
+
+late_initcall(mvebu_pm_init);
+
+int __init mvebu_pm_suspend_init(void (*board_pm_enter)(void __iomem *sdram_reg,
+							u32 srcmd))
 {
 	struct device_node *np;
 	struct resource res;
 
-	if (!of_machine_is_compatible("marvell,armadaxp"))
-		return -ENODEV;
-
 	np = of_find_compatible_node(NULL, NULL,
 				     "marvell,armada-xp-sdram-controller");
 	if (!np)
@@ -212,7 +265,5 @@ int mvebu_pm_init(void (*board_pm_enter)(void __iomem *sdram_reg, u32 srcmd))
 
 	mvebu_board_pm_enter = board_pm_enter;
 
-	suspend_set_ops(&mvebu_pm_ops);
-
 	return 0;
 }
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index 4f4e22206ae5..e8fdb9ceedf0 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -415,7 +415,7 @@ static __init int armada_38x_cpuidle_init(void)
 	void __iomem *mpsoc_base;
 	u32 reg;
 
-	pr_warn("CPU idle is currently broken on Armada 38x: disabling");
+	pr_warn("CPU idle is currently broken on Armada 38x: disabling\n");
 	return 0;
 
 	np = of_find_compatible_node(NULL, NULL,
@@ -486,7 +486,7 @@ static int __init mvebu_v7_cpu_pm_init(void)
 	 */
 	if (of_machine_is_compatible("marvell,armada380")) {
 		cpu_hotplug_disable();
-		pr_warn("CPU hotplug support is currently broken on Armada 38x: disabling");
+		pr_warn("CPU hotplug support is currently broken on Armada 38x: disabling\n");
 	}
 
 	if (of_machine_is_compatible("marvell,armadaxp"))
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 2e7cec86e50e..f1ea4700efcf 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -282,7 +282,7 @@ static void __init apx4devkit_init(void)
 #define TX28_FEC_PHY_RESET	MXS_GPIO_NR(4, 13)
 #define TX28_FEC_nINT		MXS_GPIO_NR(4, 5)
 
-static const struct gpio tx28_gpios[] __initconst = {
+static const struct gpio const tx28_gpios[] __initconst = {
 	{ ENET0_MDC__GPIO_4_0, GPIOF_OUT_INIT_LOW, "GPIO_4_0" },
 	{ ENET0_MDIO__GPIO_4_1, GPIOF_OUT_INIT_LOW, "GPIO_4_1" },
 	{ ENET0_RX_EN__GPIO_4_2, GPIOF_OUT_INIT_LOW, "GPIO_4_2" },
@@ -528,7 +528,7 @@ static void mxs_restart(enum reboot_mode mode, const char *cmd)
 	soft_restart(0);
 }
 
-static const char *mxs_dt_compat[] __initdata = {
+static const char *const mxs_dt_compat[] __initconst = {
 	"fsl,imx28",
 	"fsl,imx23",
 	NULL,
diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c
index db25b0cef3a7..6373e2bff203 100644
--- a/arch/arm/mach-netx/generic.c
+++ b/arch/arm/mach-netx/generic.c
@@ -174,7 +174,7 @@ void __init netx_init_irq(void)
 	for (irq = NETX_IRQ_HIF_CHAINED(0); irq <= NETX_IRQ_HIF_LAST; irq++) {
 		irq_set_chip_and_handler(irq, &netx_hif_chip,
 					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
 	}
 
 	writel(NETX_DPMAS_INT_EN_GLB_EN, NETX_DPMAS_INT_EN);
diff --git a/arch/arm/mach-netx/time.c b/arch/arm/mach-netx/time.c
index 5fb2a590ec17..054a8a61e379 100644
--- a/arch/arm/mach-netx/time.c
+++ b/arch/arm/mach-netx/time.c
@@ -34,40 +34,40 @@
 #define TIMER_CLOCKEVENT 0
 #define TIMER_CLOCKSOURCE 1
 
-static void netx_set_mode(enum clock_event_mode mode,
-		struct clock_event_device *clk)
+static inline void timer_shutdown(struct clock_event_device *evt)
 {
-	u32 tmode;
-
 	/* disable timer */
 	writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT));
+}
+
+static int netx_shutdown(struct clock_event_device *evt)
+{
+	timer_shutdown(evt);
+
+	return 0;
+}
+
+static int netx_set_oneshot(struct clock_event_device *evt)
+{
+	u32 tmode = NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN;
+
+	timer_shutdown(evt);
+	writel(0, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT));
+	writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT));
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT));
-		tmode = NETX_GPIO_COUNTER_CTRL_RST_EN |
-			NETX_GPIO_COUNTER_CTRL_IRQ_EN |
-			NETX_GPIO_COUNTER_CTRL_RUN;
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		writel(0, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT));
-		tmode = NETX_GPIO_COUNTER_CTRL_IRQ_EN |
-			NETX_GPIO_COUNTER_CTRL_RUN;
-		break;
-
-	default:
-		WARN(1, "%s: unhandled mode %d\n", __func__, mode);
-		/* fall through */
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		tmode = 0;
-		break;
-	}
+	return 0;
+}
 
+static int netx_set_periodic(struct clock_event_device *evt)
+{
+	u32 tmode = NETX_GPIO_COUNTER_CTRL_RST_EN |
+		    NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN;
+
+	timer_shutdown(evt);
+	writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT));
 	writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT));
+
+	return 0;
 }
 
 static int netx_set_next_event(unsigned long evt,
@@ -81,7 +81,10 @@ static struct clock_event_device netx_clockevent = {
 	.name = "netx-timer" __stringify(TIMER_CLOCKEVENT),
 	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_next_event = netx_set_next_event,
-	.set_mode = netx_set_mode,
+	.set_state_shutdown = netx_shutdown,
+	.set_state_periodic = netx_set_periodic,
+	.set_state_oneshot = netx_set_oneshot,
+	.tick_resume = netx_shutdown,
 };
 
 /*
diff --git a/arch/arm/mach-nomadik/cpu-8815.c b/arch/arm/mach-nomadik/cpu-8815.c
index 9bda46f1fab7..0c612d95bd5c 100644
--- a/arch/arm/mach-nomadik/cpu-8815.c
+++ b/arch/arm/mach-nomadik/cpu-8815.c
@@ -26,10 +26,8 @@
 #include <linux/irq.h>
 #include <linux/dma-mapping.h>
 #include <linux/of_irq.h>
-#include <linux/of_gpio.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
-#include <linux/gpio.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -109,40 +107,6 @@ static void cpu8815_restart(enum reboot_mode mode, const char *cmd)
 	writel(1, srcbase + 0x18);
 }
 
-/*
- * This GPIO pin turns on a line that is used to detect card insertion
- * on this board.
- */
-static int __init cpu8815_mmcsd_init(void)
-{
-	struct device_node *cdbias;
-	int gpio, err;
-
-	cdbias = of_find_node_by_path("/usb-s8815/mmcsd-gpio");
-	if (!cdbias) {
-		pr_info("could not find MMC/SD card detect bias node\n");
-		return 0;
-	}
-	gpio = of_get_gpio(cdbias, 0);
-	if (gpio < 0) {
-		pr_info("could not obtain MMC/SD card detect bias GPIO\n");
-		return 0;
-	}
-	err = gpio_request(gpio, "card detect bias");
-	if (err) {
-		pr_info("failed to request card detect bias GPIO %d\n", gpio);
-		return -ENODEV;
-	}
-	err = gpio_direction_output(gpio, 0);
-	if (err){
-		pr_info("failed to set GPIO %d as output, low\n", gpio);
-		return err;
-	}
-	pr_info("enabled USB-S8815 CD bias GPIO %d, low\n", gpio);
-	return 0;
-}
-device_initcall(cpu8815_mmcsd_init);
-
 static const char * cpu8815_board_compat[] = {
 	"st,nomadik-nhk-15",
 	"calaosystems,usb-s8815",
@@ -150,9 +114,8 @@ static const char * cpu8815_board_compat[] = {
 };
 
 DT_MACHINE_START(NOMADIK_DT, "Nomadik STn8815")
-	/* At full speed latency must be >=2, so 0x249 in low bits */
-	.l2c_aux_val	= 0x00700249,
-	.l2c_aux_mask	= 0xfe0fefff,
+	.l2c_aux_val	= 0,
+	.l2c_aux_mask	= ~0,
 	.map_io		= cpu8815_map_io,
 	.restart	= cpu8815_restart,
 	.dt_compat      = cpu8815_board_compat,
diff --git a/arch/arm/mach-omap1/fpga.c b/arch/arm/mach-omap1/fpga.c
index 3c0e42219200..dfec671b1639 100644
--- a/arch/arm/mach-omap1/fpga.c
+++ b/arch/arm/mach-omap1/fpga.c
@@ -169,7 +169,7 @@ void omap1510_fpga_init_irq(void)
 		}
 
 		irq_set_handler(i, handle_edge_irq);
-		set_irq_flags(i, IRQF_VALID);
+		irq_clear_status_flags(i, IRQ_NOREQUEST);
 	}
 
 	/*
diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c
index f4d346fda9da..b11edc8a46f0 100644
--- a/arch/arm/mach-omap1/irq.c
+++ b/arch/arm/mach-omap1/irq.c
@@ -262,7 +262,7 @@ void __init omap1_init_irq(void)
 
 			irq_trigger = irq_banks[i].trigger_map >> IRQ_BIT(j);
 			omap_irq_set_cfg(j, 0, 0, irq_trigger);
-			set_irq_flags(j, IRQF_VALID);
+			irq_clear_status_flags(j, IRQ_NOREQUEST);
 		}
 		omap_alloc_gc(irq_banks[i].va, irq_base + i * 32, 32);
 	}
diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c
index a7588cfd0286..524977a31a49 100644
--- a/arch/arm/mach-omap1/time.c
+++ b/arch/arm/mach-omap1/time.c
@@ -124,29 +124,26 @@ static int omap_mpu_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void omap_mpu_set_mode(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int omap_mpu_set_oneshot(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		omap_mpu_set_autoreset(0);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		omap_mpu_timer_stop(0);
-		omap_mpu_remove_autoreset(0);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	omap_mpu_timer_stop(0);
+	omap_mpu_remove_autoreset(0);
+	return 0;
+}
+
+static int omap_mpu_set_periodic(struct clock_event_device *evt)
+{
+	omap_mpu_set_autoreset(0);
+	return 0;
 }
 
 static struct clock_event_device clockevent_mpu_timer1 = {
-	.name		= "mpu_timer1",
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event	= omap_mpu_set_next_event,
-	.set_mode	= omap_mpu_set_mode,
+	.name			= "mpu_timer1",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= omap_mpu_set_next_event,
+	.set_state_periodic	= omap_mpu_set_periodic,
+	.set_state_oneshot	= omap_mpu_set_oneshot,
 };
 
 static irqreturn_t omap_mpu_timer1_interrupt(int irq, void *dev_id)
diff --git a/arch/arm/mach-omap1/timer32k.c b/arch/arm/mach-omap1/timer32k.c
index 36bf174b3fac..0ae6c52a7d70 100644
--- a/arch/arm/mach-omap1/timer32k.c
+++ b/arch/arm/mach-omap1/timer32k.c
@@ -114,29 +114,28 @@ static int omap_32k_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void omap_32k_timer_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *evt)
+static int omap_32k_timer_shutdown(struct clock_event_device *evt)
 {
 	omap_32k_timer_stop();
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		omap_32k_timer_start(OMAP_32K_TIMER_TICK_PERIOD);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+static int omap_32k_timer_set_periodic(struct clock_event_device *evt)
+{
+	omap_32k_timer_stop();
+	omap_32k_timer_start(OMAP_32K_TIMER_TICK_PERIOD);
+	return 0;
 }
 
 static struct clock_event_device clockevent_32k_timer = {
-	.name		= "32k-timer",
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event	= omap_32k_timer_set_next_event,
-	.set_mode	= omap_32k_timer_set_mode,
+	.name			= "32k-timer",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= omap_32k_timer_set_next_event,
+	.set_state_shutdown	= omap_32k_timer_shutdown,
+	.set_state_periodic	= omap_32k_timer_set_periodic,
+	.set_state_oneshot	= omap_32k_timer_shutdown,
+	.tick_resume		= omap_32k_timer_shutdown,
 };
 
 static irqreturn_t omap_32k_timer_interrupt(int irq, void *dev_id)
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index ecc04ff13e95..07d2e100caab 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -29,6 +29,7 @@ config ARCH_OMAP4
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select OMAP_INTERCONNECT
+	select OMAP_INTERCONNECT_BARRIER
 	select PL310_ERRATA_588369 if CACHE_L2X0
 	select PL310_ERRATA_727915 if CACHE_L2X0
 	select PM_OPP if PM
@@ -46,6 +47,7 @@ config SOC_OMAP5
 	select HAVE_ARM_TWD if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT_BARRIER
 
 config SOC_AM33XX
 	bool "TI AM33XX"
@@ -60,6 +62,7 @@ config SOC_AM43XX
 	select ARM_GIC
 	select MACH_OMAP_GENERIC
 	select MIGHT_HAVE_CACHE_L2X0
+	select HAVE_ARM_SCU
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"
@@ -70,6 +73,7 @@ config SOC_DRA7XX
 	select HAVE_ARM_ARCH_TIMER
 	select IRQ_CROSSBAR
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT_BARRIER
 
 config ARCH_OMAP2PLUS
 	bool
@@ -91,6 +95,10 @@ config ARCH_OMAP2PLUS
 	help
 	  Systems based on OMAP2, OMAP3, OMAP4 or OMAP5
 
+config OMAP_INTERCONNECT_BARRIER
+	bool
+	select ARM_HEAVY_MB
+	
 
 if ARCH_OMAP2PLUS
 
@@ -177,26 +185,6 @@ config MACH_OMAP_LDP
 	default y
 	select OMAP_PACKAGE_CBB
 
-config MACH_OMAP3530_LV_SOM
-	bool "OMAP3 Logic 3530 LV SOM board"
-	depends on ARCH_OMAP3
-	default y
-	select OMAP_PACKAGE_CBB
-	help
-	 Support for the LogicPD OMAP3530 SOM Development kit
-	 for full description please see the products webpage at
-	 http://www.logicpd.com/products/development-kits/texas-instruments-zoom%E2%84%A2-omap35x-development-kit
-
-config MACH_OMAP3_TORPEDO
-	bool "OMAP3 Logic 35x Torpedo board"
-	depends on ARCH_OMAP3
-	default y
-	select OMAP_PACKAGE_CBB
-	help
-	 Support for the LogicPD OMAP35x Torpedo Development kit
-	 for full description please see the products webpage at
-	 http://www.logicpd.com/products/development-kits/zoom-omap35x-torpedo-development-kit
-
 config MACH_OMAP3517EVM
 	bool "OMAP3517/ AM3517 EVM board"
 	depends on ARCH_OMAP3
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 903c85be2897..935869698cbc 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -12,8 +12,7 @@ obj-y := id.o io.o control.o mux.o devices.o fb.o serial.o timer.o pm.o \
 
 hwmod-common				= omap_hwmod.o omap_hwmod_reset.o \
 					  omap_hwmod_common_data.o
-clock-common				= clock.o clock_common_data.o \
-					  clkt_dpll.o clkt_clksel.o
+clock-common				= clock.o
 secure-common				= omap-smc.o omap-secure.o
 
 obj-$(CONFIG_ARCH_OMAP2) += $(omap-2-3-common) $(hwmod-common)
@@ -182,24 +181,17 @@ obj-$(CONFIG_SOC_DRA7XX)		+= $(clockdomain-common)
 obj-$(CONFIG_SOC_DRA7XX)		+= clockdomains7xx_data.o
 
 # Clock framework
-obj-$(CONFIG_ARCH_OMAP2)		+= $(clock-common) clock2xxx.o
+obj-$(CONFIG_ARCH_OMAP2)		+= $(clock-common)
 obj-$(CONFIG_ARCH_OMAP2)		+= clkt2xxx_dpllcore.o
 obj-$(CONFIG_ARCH_OMAP2)		+= clkt2xxx_virt_prcm_set.o
-obj-$(CONFIG_ARCH_OMAP2)		+= clkt2xxx_dpll.o clkt_iclk.o
-obj-$(CONFIG_SOC_OMAP2430)		+= clock2430.o
-obj-$(CONFIG_ARCH_OMAP3)		+= $(clock-common) clock3xxx.o
-obj-$(CONFIG_ARCH_OMAP3)		+= clock34xx.o clkt34xx_dpll3m2.o
-obj-$(CONFIG_ARCH_OMAP3)		+= clock3517.o clock36xx.o
-obj-$(CONFIG_ARCH_OMAP3)		+= dpll3xxx.o
-obj-$(CONFIG_ARCH_OMAP3)		+= clkt_iclk.o
+obj-$(CONFIG_ARCH_OMAP2)		+= clkt2xxx_dpll.o
+obj-$(CONFIG_ARCH_OMAP3)		+= $(clock-common)
+obj-$(CONFIG_ARCH_OMAP3)		+= clkt34xx_dpll3m2.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(clock-common)
-obj-$(CONFIG_ARCH_OMAP4)		+= dpll3xxx.o dpll44xx.o
-obj-$(CONFIG_SOC_AM33XX)		+= $(clock-common) dpll3xxx.o
+obj-$(CONFIG_SOC_AM33XX)		+= $(clock-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(clock-common)
-obj-$(CONFIG_SOC_OMAP5)			+= dpll3xxx.o dpll44xx.o
 obj-$(CONFIG_SOC_DRA7XX)		+= $(clock-common)
-obj-$(CONFIG_SOC_DRA7XX)		+= dpll3xxx.o dpll44xx.o
-obj-$(CONFIG_SOC_AM43XX)		+= $(clock-common) dpll3xxx.o
+obj-$(CONFIG_SOC_AM43XX)		+= $(clock-common)
 
 # OMAP2 clock rate set data (old "OPP" data)
 obj-$(CONFIG_SOC_OMAP2420)		+= opp2420_data.o
@@ -234,8 +226,7 @@ obj-$(CONFIG_SOC_DRA7XX)		+= omap_hwmod_7xx_data.o
 # EMU peripherals
 obj-$(CONFIG_HW_PERF_EVENTS)		+= pmu.o
 
-iommu-$(CONFIG_OMAP_IOMMU)		:= omap-iommu.o
-obj-y					+= $(iommu-m) $(iommu-y)
+obj-$(CONFIG_OMAP_IOMMU)		+= omap-iommu.o
 
 # OMAP2420 MSDI controller integration support ("MMC")
 obj-$(CONFIG_SOC_OMAP2420)		+= msdi.o
@@ -243,9 +234,6 @@ obj-$(CONFIG_SOC_OMAP2420)		+= msdi.o
 # Specific board support
 obj-$(CONFIG_MACH_OMAP_GENERIC)		+= board-generic.o pdata-quirks.o
 obj-$(CONFIG_MACH_OMAP_LDP)		+= board-ldp.o
-obj-$(CONFIG_MACH_OMAP3530_LV_SOM)      += board-omap3logic.o
-obj-$(CONFIG_MACH_OMAP3_TORPEDO)        += board-omap3logic.o
-obj-$(CONFIG_MACH_OMAP3_PANDORA)	+= board-omap3pandora.o
 obj-$(CONFIG_MACH_NOKIA_N8X0)		+= board-n8x0.o
 obj-$(CONFIG_MACH_NOKIA_RX51)		+= board-rx51.o sdram-nokia.o
 obj-$(CONFIG_MACH_NOKIA_RX51)		+= board-rx51-peripherals.o
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 34ff14b7beab..24c9afc9e8a7 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -169,7 +169,7 @@ static const char *const ti814x_boards_compat[] __initconst = {
 	NULL,
 };
 
-DT_MACHINE_START(TI81XX_DT, "Generic ti814x (Flattened Device Tree)")
+DT_MACHINE_START(TI814X_DT, "Generic ti814x (Flattened Device Tree)")
 	.reserve	= omap_reserve,
 	.map_io		= ti81xx_map_io,
 	.init_early	= ti814x_init_early,
@@ -297,7 +297,7 @@ static const char *const dra74x_boards_compat[] __initconst = {
 DT_MACHINE_START(DRA74X_DT, "Generic DRA74X (Flattened Device Tree)")
 	.reserve	= omap_reserve,
 	.smp		= smp_ops(omap4_smp_ops),
-	.map_io		= omap5_map_io,
+	.map_io		= dra7xx_map_io,
 	.init_early	= dra7xx_init_early,
 	.init_late	= dra7xx_init_late,
 	.init_irq	= omap_gic_of_init,
@@ -316,7 +316,7 @@ static const char *const dra72x_boards_compat[] __initconst = {
 
 DT_MACHINE_START(DRA72X_DT, "Generic DRA72X (Flattened Device Tree)")
 	.reserve	= omap_reserve,
-	.map_io		= omap5_map_io,
+	.map_io		= dra7xx_map_io,
 	.init_early	= dra7xx_init_early,
 	.init_late	= dra7xx_init_late,
 	.init_irq	= omap_gic_of_init,
diff --git a/arch/arm/mach-omap2/board-omap3logic.c b/arch/arm/mach-omap2/board-omap3logic.c
deleted file mode 100644
index 6049f60a8813..000000000000
--- a/arch/arm/mach-omap2/board-omap3logic.c
+++ /dev/null
@@ -1,249 +0,0 @@
-/*
- * linux/arch/arm/mach-omap2/board-omap3logic.c
- *
- * Copyright (C) 2010 Li-Pro.Net
- * Stephan Linz <linz@li-pro.net>
- *
- * Copyright (C) 2010-2012 Logic Product Development, Inc.
- * Peter Barada <peter.barada@logicpd.com>
- * Ashwin BIhari <ashwin.bihari@logicpd.com>
- *
- * Modified from Beagle, EVM, and RX51
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/gpio.h>
-
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-
-#include <linux/i2c/twl.h>
-#include <linux/mmc/host.h>
-#include <linux/usb/phy.h>
-
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-
-#include "common.h"
-#include "mux.h"
-#include "hsmmc.h"
-#include "control.h"
-#include "common-board-devices.h"
-#include "gpmc.h"
-#include "gpmc-smsc911x.h"
-
-#define OMAP3LOGIC_SMSC911X_CS			1
-
-#define OMAP3530_LV_SOM_MMC_GPIO_CD		110
-#define OMAP3530_LV_SOM_MMC_GPIO_WP		126
-#define OMAP3530_LV_SOM_SMSC911X_GPIO_IRQ	152
-
-#define OMAP3_TORPEDO_MMC_GPIO_CD		127
-#define OMAP3_TORPEDO_SMSC911X_GPIO_IRQ		129
-
-static struct regulator_consumer_supply omap3logic_vmmc1_supply[] = {
-	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.0"),
-};
-
-/* VMMC1 for MMC1 pins CMD, CLK, DAT0..DAT3 (20 mA, plus card == max 220 mA) */
-static struct regulator_init_data omap3logic_vmmc1 = {
-	.constraints = {
-		.name			= "VMMC1",
-		.min_uV			= 1850000,
-		.max_uV			= 3150000,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_VOLTAGE
-					| REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(omap3logic_vmmc1_supply),
-	.consumer_supplies      = omap3logic_vmmc1_supply,
-};
-
-static struct twl4030_gpio_platform_data omap3logic_gpio_data = {
-	.use_leds	= true,
-	.pullups	= BIT(1),
-	.pulldowns	= BIT(2)  | BIT(6)  | BIT(7)  | BIT(8)
-			| BIT(13) | BIT(15) | BIT(16) | BIT(17),
-};
-
-static struct twl4030_usb_data omap3logic_usb_data = {
-	.usb_mode	= T2_USB_MODE_ULPI,
-};
-
-
-static struct twl4030_platform_data omap3logic_twldata = {
-	/* platform_data for children goes here */
-	.gpio		= &omap3logic_gpio_data,
-	.vmmc1		= &omap3logic_vmmc1,
-	.usb		= &omap3logic_usb_data,
-};
-
-static int __init omap3logic_i2c_init(void)
-{
-	omap3_pmic_init("twl4030", &omap3logic_twldata);
-	return 0;
-}
-
-static struct omap2_hsmmc_info __initdata board_mmc_info[] = {
-	{
-		.name		= "external",
-		.mmc		= 1,
-		.caps		= MMC_CAP_4_BIT_DATA,
-		.gpio_cd	= -EINVAL,
-		.gpio_wp	= -EINVAL,
-	},
-	{}      /* Terminator */
-};
-
-static void __init board_mmc_init(void)
-{
-	if (machine_is_omap3530_lv_som()) {
-		/* OMAP3530 LV SOM board */
-		board_mmc_info[0].gpio_cd = OMAP3530_LV_SOM_MMC_GPIO_CD;
-		board_mmc_info[0].gpio_wp = OMAP3530_LV_SOM_MMC_GPIO_WP;
-		omap_mux_init_signal("gpio_110", OMAP_PIN_OUTPUT);
-		omap_mux_init_signal("gpio_126", OMAP_PIN_OUTPUT);
-	} else if (machine_is_omap3_torpedo()) {
-		/* OMAP3 Torpedo board */
-		board_mmc_info[0].gpio_cd = OMAP3_TORPEDO_MMC_GPIO_CD;
-		omap_mux_init_signal("gpio_127", OMAP_PIN_OUTPUT);
-	} else {
-		/* unsupported board */
-		printk(KERN_ERR "%s(): unknown machine type\n", __func__);
-		return;
-	}
-
-	omap_hsmmc_init(board_mmc_info);
-}
-
-static struct omap_smsc911x_platform_data __initdata board_smsc911x_data = {
-	.cs             = OMAP3LOGIC_SMSC911X_CS,
-	.gpio_irq       = -EINVAL,
-	.gpio_reset     = -EINVAL,
-};
-
-/* TODO/FIXME (comment by Peter Barada, LogicPD):
- * Fix the PBIAS voltage for Torpedo MMC1 pins that
- * are used for other needs (IRQs, etc).            */
-static void omap3torpedo_fix_pbias_voltage(void)
-{
-	u16 control_pbias_offset = OMAP343X_CONTROL_PBIAS_LITE;
-	u32 reg;
-
-	if (machine_is_omap3_torpedo())
-	{
-		/* Set the bias for the pin */
-		reg = omap_ctrl_readl(control_pbias_offset);
-
-		reg &= ~OMAP343X_PBIASLITEPWRDNZ1;
-		omap_ctrl_writel(reg, control_pbias_offset);
-
-		/* 100ms delay required for PBIAS configuration */
-		msleep(100);
-
-		reg |= OMAP343X_PBIASLITEVMODE1;
-		reg |= OMAP343X_PBIASLITEPWRDNZ1;
-		omap_ctrl_writel(reg | 0x300, control_pbias_offset);
-	}
-}
-
-static inline void __init board_smsc911x_init(void)
-{
-	if (machine_is_omap3530_lv_som()) {
-		/* OMAP3530 LV SOM board */
-		board_smsc911x_data.gpio_irq =
-					OMAP3530_LV_SOM_SMSC911X_GPIO_IRQ;
-		omap_mux_init_signal("gpio_152", OMAP_PIN_INPUT);
-	} else if (machine_is_omap3_torpedo()) {
-		/* OMAP3 Torpedo board */
-		board_smsc911x_data.gpio_irq = OMAP3_TORPEDO_SMSC911X_GPIO_IRQ;
-		omap_mux_init_signal("gpio_129", OMAP_PIN_INPUT);
-	} else {
-		/* unsupported board */
-		printk(KERN_ERR "%s(): unknown machine type\n", __func__);
-		return;
-	}
-
-	gpmc_smsc911x_init(&board_smsc911x_data);
-}
-
-#ifdef CONFIG_OMAP_MUX
-static struct omap_board_mux board_mux[] __initdata = {
-	/* mUSB */
-	OMAP3_MUX(HSUSB0_CLK, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_STP, OMAP_MUX_MODE0 | OMAP_PIN_OUTPUT),
-	OMAP3_MUX(HSUSB0_DIR, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_NXT, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA0, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA1, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA2, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA3, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA4, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA5, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA6, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-	OMAP3_MUX(HSUSB0_DATA7, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
-
-	{ .reg_offset = OMAP_MUX_TERMINATOR },
-};
-#endif
-
-static struct regulator_consumer_supply dummy_supplies[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
-};
-
-static void __init omap3logic_init(void)
-{
-	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
-	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
-	omap3torpedo_fix_pbias_voltage();
-	omap3logic_i2c_init();
-	omap_serial_init();
-	omap_sdrc_init(NULL, NULL);
-	board_mmc_init();
-	board_smsc911x_init();
-
-	usb_bind_phy("musb-hdrc.0.auto", 0, "twl4030_usb");
-	usb_musb_init(NULL);
-
-	/* Ensure SDRC pins are mux'd for self-refresh */
-	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
-	omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT);
-}
-
-MACHINE_START(OMAP3_TORPEDO, "Logic OMAP3 Torpedo board")
-	.atag_offset	= 0x100,
-	.reserve	= omap_reserve,
-	.map_io		= omap3_map_io,
-	.init_early	= omap35xx_init_early,
-	.init_irq	= omap3_init_irq,
-	.init_machine	= omap3logic_init,
-	.init_late	= omap35xx_init_late,
-	.init_time	= omap3_sync32k_timer_init,
-	.restart	= omap3xxx_restart,
-MACHINE_END
-
-MACHINE_START(OMAP3530_LV_SOM, "OMAP Logic 3530 LV SOM board")
-	.atag_offset	= 0x100,
-	.reserve	= omap_reserve,
-	.map_io		= omap3_map_io,
-	.init_early	= omap35xx_init_early,
-	.init_irq	= omap3_init_irq,
-	.init_machine	= omap3logic_init,
-	.init_late	= omap35xx_init_late,
-	.init_time	= omap3_sync32k_timer_init,
-	.restart	= omap3xxx_restart,
-MACHINE_END
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
deleted file mode 100644
index 969e1003dd92..000000000000
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ /dev/null
@@ -1,633 +0,0 @@
-/*
- * board-omap3pandora.c (Pandora Handheld Console)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- *
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-
-#include <linux/spi/spi.h>
-#include <linux/regulator/machine.h>
-#include <linux/i2c/twl.h>
-#include <linux/omap-gpmc.h>
-#include <linux/wl12xx.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/nand.h>
-#include <linux/leds.h>
-#include <linux/input.h>
-#include <linux/input/matrix_keypad.h>
-#include <linux/gpio.h>
-#include <linux/gpio_keys.h>
-#include <linux/mmc/host.h>
-#include <linux/mmc/card.h>
-#include <linux/regulator/fixed.h>
-#include <linux/usb/phy.h>
-#include <linux/platform_data/spi-omap2-mcspi.h>
-
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-
-#include "common.h"
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
-#include <linux/platform_data/mtd-nand-omap2.h>
-
-#include "mux.h"
-#include "sdram-micron-mt46h32m32lf-6.h"
-#include "hsmmc.h"
-#include "common-board-devices.h"
-
-#define PANDORA_WIFI_IRQ_GPIO		21
-#define PANDORA_WIFI_NRESET_GPIO	23
-#define OMAP3_PANDORA_TS_GPIO		94
-
-static struct mtd_partition omap3pandora_nand_partitions[] = {
-	{
-		.name           = "xloader",
-		.offset         = 0,
-		.size           = 4 * NAND_BLOCK_SIZE,
-		.mask_flags     = MTD_WRITEABLE
-	}, {
-		.name           = "uboot",
-		.offset         = MTDPART_OFS_APPEND,
-		.size           = 15 * NAND_BLOCK_SIZE,
-	}, {
-		.name           = "uboot-env",
-		.offset         = MTDPART_OFS_APPEND,
-		.size           = 1 * NAND_BLOCK_SIZE,
-	}, {
-		.name           = "boot",
-		.offset         = MTDPART_OFS_APPEND,
-		.size           = 80 * NAND_BLOCK_SIZE,
-	}, {
-		.name           = "rootfs",
-		.offset         = MTDPART_OFS_APPEND,
-		.size           = MTDPART_SIZ_FULL,
-	},
-};
-
-static struct omap_nand_platform_data pandora_nand_data = {
-	.cs		= 0,
-	.devsize	= NAND_BUSWIDTH_16,
-	.xfer_type	= NAND_OMAP_PREFETCH_DMA,
-	.parts		= omap3pandora_nand_partitions,
-	.nr_parts	= ARRAY_SIZE(omap3pandora_nand_partitions),
-};
-
-static struct gpio_led pandora_gpio_leds[] = {
-	{
-		.name			= "pandora::sd1",
-		.default_trigger	= "mmc0",
-		.gpio			= 128,
-	}, {
-		.name			= "pandora::sd2",
-		.default_trigger	= "mmc1",
-		.gpio			= 129,
-	}, {
-		.name			= "pandora::bluetooth",
-		.gpio			= 158,
-	}, {
-		.name			= "pandora::wifi",
-		.gpio			= 159,
-	},
-};
-
-static struct gpio_led_platform_data pandora_gpio_led_data = {
-	.leds		= pandora_gpio_leds,
-	.num_leds	= ARRAY_SIZE(pandora_gpio_leds),
-};
-
-static struct platform_device pandora_leds_gpio = {
-	.name	= "leds-gpio",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &pandora_gpio_led_data,
-	},
-};
-
-static struct platform_device pandora_backlight = {
-	.name	= "pandora-backlight",
-	.id	= -1,
-};
-
-#define GPIO_BUTTON(gpio_num, ev_type, ev_code, act_low, descr)	\
-{								\
-	.gpio		= gpio_num,				\
-	.type		= ev_type,				\
-	.code		= ev_code,				\
-	.active_low	= act_low,				\
-	.debounce_interval = 4,					\
-	.desc		= "btn " descr,				\
-}
-
-#define GPIO_BUTTON_LOW(gpio_num, event_code, description)	\
-	GPIO_BUTTON(gpio_num, EV_KEY, event_code, 1, description)
-
-static struct gpio_keys_button pandora_gpio_keys[] = {
-	GPIO_BUTTON_LOW(110,	KEY_UP,		"up"),
-	GPIO_BUTTON_LOW(103,	KEY_DOWN,	"down"),
-	GPIO_BUTTON_LOW(96,	KEY_LEFT,	"left"),
-	GPIO_BUTTON_LOW(98,	KEY_RIGHT,	"right"),
-	GPIO_BUTTON_LOW(109,	KEY_PAGEUP,	"game 1"),
-	GPIO_BUTTON_LOW(111,	KEY_END,	"game 2"),
-	GPIO_BUTTON_LOW(106,	KEY_PAGEDOWN,	"game 3"),
-	GPIO_BUTTON_LOW(101,	KEY_HOME,	"game 4"),
-	GPIO_BUTTON_LOW(102,	KEY_RIGHTSHIFT,	"l"),
-	GPIO_BUTTON_LOW(97,	KEY_KPPLUS,	"l2"),
-	GPIO_BUTTON_LOW(105,	KEY_RIGHTCTRL,	"r"),
-	GPIO_BUTTON_LOW(107,	KEY_KPMINUS,	"r2"),
-	GPIO_BUTTON_LOW(104,	KEY_LEFTCTRL,	"ctrl"),
-	GPIO_BUTTON_LOW(99,	KEY_MENU,	"menu"),
-	GPIO_BUTTON_LOW(176,	KEY_COFFEE,	"hold"),
-	GPIO_BUTTON(100, EV_KEY, KEY_LEFTALT, 0, "alt"),
-	GPIO_BUTTON(108, EV_SW, SW_LID, 1, "lid"),
-};
-
-static struct gpio_keys_platform_data pandora_gpio_key_info = {
-	.buttons	= pandora_gpio_keys,
-	.nbuttons	= ARRAY_SIZE(pandora_gpio_keys),
-};
-
-static struct platform_device pandora_keys_gpio = {
-	.name	= "gpio-keys",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &pandora_gpio_key_info,
-	},
-};
-
-static const uint32_t board_keymap[] = {
-	/* row, col, code */
-	KEY(0, 0, KEY_9),
-	KEY(0, 1, KEY_8),
-	KEY(0, 2, KEY_I),
-	KEY(0, 3, KEY_J),
-	KEY(0, 4, KEY_N),
-	KEY(0, 5, KEY_M),
-	KEY(1, 0, KEY_0),
-	KEY(1, 1, KEY_7),
-	KEY(1, 2, KEY_U),
-	KEY(1, 3, KEY_H),
-	KEY(1, 4, KEY_B),
-	KEY(1, 5, KEY_SPACE),
-	KEY(2, 0, KEY_BACKSPACE),
-	KEY(2, 1, KEY_6),
-	KEY(2, 2, KEY_Y),
-	KEY(2, 3, KEY_G),
-	KEY(2, 4, KEY_V),
-	KEY(2, 5, KEY_FN),
-	KEY(3, 0, KEY_O),
-	KEY(3, 1, KEY_5),
-	KEY(3, 2, KEY_T),
-	KEY(3, 3, KEY_F),
-	KEY(3, 4, KEY_C),
-	KEY(4, 0, KEY_P),
-	KEY(4, 1, KEY_4),
-	KEY(4, 2, KEY_R),
-	KEY(4, 3, KEY_D),
-	KEY(4, 4, KEY_X),
-	KEY(5, 0, KEY_K),
-	KEY(5, 1, KEY_3),
-	KEY(5, 2, KEY_E),
-	KEY(5, 3, KEY_S),
-	KEY(5, 4, KEY_Z),
-	KEY(6, 0, KEY_L),
-	KEY(6, 1, KEY_2),
-	KEY(6, 2, KEY_W),
-	KEY(6, 3, KEY_A),
-	KEY(6, 4, KEY_DOT),
-	KEY(7, 0, KEY_ENTER),
-	KEY(7, 1, KEY_1),
-	KEY(7, 2, KEY_Q),
-	KEY(7, 3, KEY_LEFTSHIFT),
-	KEY(7, 4, KEY_COMMA),
-};
-
-static struct matrix_keymap_data board_map_data = {
-	.keymap			= board_keymap,
-	.keymap_size		= ARRAY_SIZE(board_keymap),
-};
-
-static struct twl4030_keypad_data pandora_kp_data = {
-	.keymap_data	= &board_map_data,
-	.rows		= 8,
-	.cols		= 6,
-	.rep		= 1,
-};
-
-static struct connector_atv_platform_data pandora_tv_pdata = {
-	.name = "tv",
-	.source = "venc.0",
-	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
-	.invert_polarity = false,
-};
-
-static struct platform_device pandora_tv_connector_device = {
-	.name                   = "connector-analog-tv",
-	.id                     = 0,
-	.dev.platform_data      = &pandora_tv_pdata,
-};
-
-static struct omap_dss_board_info pandora_dss_data = {
-	.default_display_name = "lcd",
-};
-
-static void pandora_wl1251_init_card(struct mmc_card *card)
-{
-	/*
-	 * We have TI wl1251 attached to MMC3. Pass this information to
-	 * SDIO core because it can't be probed by normal methods.
-	 */
-	if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) {
-		card->quirks |= MMC_QUIRK_NONSTD_SDIO;
-		card->cccr.wide_bus = 1;
-		card->cis.vendor = 0x104c;
-		card->cis.device = 0x9066;
-		card->cis.blksize = 512;
-		card->cis.max_dtr = 20000000;
-	}
-}
-
-static struct omap2_hsmmc_info omap3pandora_mmc[] = {
-	{
-		.mmc		= 1,
-		.caps		= MMC_CAP_4_BIT_DATA,
-		.gpio_cd	= -EINVAL,
-		.gpio_wp	= 126,
-		.ext_clock	= 0,
-		.deferred	= true,
-	},
-	{
-		.mmc		= 2,
-		.caps		= MMC_CAP_4_BIT_DATA,
-		.gpio_cd	= -EINVAL,
-		.gpio_wp	= 127,
-		.ext_clock	= 1,
-		.transceiver	= true,
-		.deferred	= true,
-	},
-	{
-		.mmc		= 3,
-		.caps		= MMC_CAP_4_BIT_DATA | MMC_CAP_POWER_OFF_CARD,
-		.gpio_cd	= -EINVAL,
-		.gpio_wp	= -EINVAL,
-		.init_card	= pandora_wl1251_init_card,
-	},
-	{}	/* Terminator */
-};
-
-static int omap3pandora_twl_gpio_setup(struct device *dev,
-		unsigned gpio, unsigned ngpio)
-{
-	int ret, gpio_32khz;
-
-	/* gpio + {0,1} is "mmc{0,1}_cd" (input/IRQ) */
-	omap3pandora_mmc[0].gpio_cd = gpio + 0;
-	omap3pandora_mmc[1].gpio_cd = gpio + 1;
-	omap_hsmmc_late_init(omap3pandora_mmc);
-
-	/* gpio + 13 drives 32kHz buffer for wifi module */
-	gpio_32khz = gpio + 13;
-	ret = gpio_request_one(gpio_32khz, GPIOF_OUT_INIT_HIGH, "wifi 32kHz");
-	if (ret < 0) {
-		pr_err("Cannot get GPIO line %d, ret=%d\n", gpio_32khz, ret);
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-static struct twl4030_gpio_platform_data omap3pandora_gpio_data = {
-	.setup		= omap3pandora_twl_gpio_setup,
-};
-
-static struct regulator_consumer_supply pandora_vmmc1_supply[] = {
-	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.0"),
-};
-
-static struct regulator_consumer_supply pandora_vmmc2_supply[] = {
-	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.1")
-};
-
-static struct regulator_consumer_supply pandora_vmmc3_supply[] = {
-	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.2"),
-};
-
-static struct regulator_consumer_supply pandora_vdds_supplies[] = {
-	REGULATOR_SUPPLY("vdds_sdi", "omapdss"),
-	REGULATOR_SUPPLY("vdds_dsi", "omapdss"),
-	REGULATOR_SUPPLY("vdds_dsi", "omapdss_dpi.0"),
-	REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.0"),
-};
-
-static struct regulator_consumer_supply pandora_vcc_lcd_supply[] = {
-	REGULATOR_SUPPLY("vcc", "spi1.1"),
-};
-
-static struct regulator_consumer_supply pandora_usb_phy_supply[] = {
-	REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"),	/* hsusb port 2 */
-};
-
-/* ads7846 on SPI and 2 nub controllers on I2C */
-static struct regulator_consumer_supply pandora_vaux4_supplies[] = {
-	REGULATOR_SUPPLY("vcc", "spi1.0"),
-	REGULATOR_SUPPLY("vcc", "3-0066"),
-	REGULATOR_SUPPLY("vcc", "3-0067"),
-};
-
-static struct regulator_consumer_supply pandora_adac_supply[] = {
-	REGULATOR_SUPPLY("vcc", "soc-audio"),
-};
-
-/* VMMC1 for MMC1 pins CMD, CLK, DAT0..DAT3 (20 mA, plus card == max 220 mA) */
-static struct regulator_init_data pandora_vmmc1 = {
-	.constraints = {
-		.min_uV			= 1850000,
-		.max_uV			= 3150000,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_VOLTAGE
-					| REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_vmmc1_supply),
-	.consumer_supplies	= pandora_vmmc1_supply,
-};
-
-/* VMMC2 for MMC2 pins CMD, CLK, DAT0..DAT3 (max 100 mA) */
-static struct regulator_init_data pandora_vmmc2 = {
-	.constraints = {
-		.min_uV			= 1850000,
-		.max_uV			= 3150000,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_VOLTAGE
-					| REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_vmmc2_supply),
-	.consumer_supplies	= pandora_vmmc2_supply,
-};
-
-/* VAUX1 for LCD */
-static struct regulator_init_data pandora_vaux1 = {
-	.constraints = {
-		.min_uV			= 3000000,
-		.max_uV			= 3000000,
-		.apply_uV		= true,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_vcc_lcd_supply),
-	.consumer_supplies	= pandora_vcc_lcd_supply,
-};
-
-/* VAUX2 for USB host PHY */
-static struct regulator_init_data pandora_vaux2 = {
-	.constraints = {
-		.min_uV			= 1800000,
-		.max_uV			= 1800000,
-		.apply_uV		= true,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_usb_phy_supply),
-	.consumer_supplies	= pandora_usb_phy_supply,
-};
-
-/* VAUX4 for ads7846 and nubs */
-static struct regulator_init_data pandora_vaux4 = {
-	.constraints = {
-		.min_uV			= 2800000,
-		.max_uV			= 2800000,
-		.apply_uV		= true,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_vaux4_supplies),
-	.consumer_supplies	= pandora_vaux4_supplies,
-};
-
-/* VSIM for audio DAC */
-static struct regulator_init_data pandora_vsim = {
-	.constraints = {
-		.min_uV			= 2800000,
-		.max_uV			= 2800000,
-		.apply_uV		= true,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_adac_supply),
-	.consumer_supplies	= pandora_adac_supply,
-};
-
-/* Fixed regulator internal to Wifi module */
-static struct regulator_init_data pandora_vmmc3 = {
-	.constraints = {
-		.valid_ops_mask		= REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_vmmc3_supply),
-	.consumer_supplies	= pandora_vmmc3_supply,
-};
-
-static struct fixed_voltage_config pandora_vwlan = {
-	.supply_name		= "vwlan",
-	.microvolts		= 1800000, /* 1.8V */
-	.gpio			= PANDORA_WIFI_NRESET_GPIO,
-	.startup_delay		= 50000, /* 50ms */
-	.enable_high		= 1,
-	.enabled_at_boot	= 0,
-	.init_data		= &pandora_vmmc3,
-};
-
-static struct platform_device pandora_vwlan_device = {
-	.name		= "reg-fixed-voltage",
-	.id		= 1,
-	.dev = {
-		.platform_data = &pandora_vwlan,
-	},
-};
-
-static struct twl4030_bci_platform_data pandora_bci_data;
-
-static struct twl4030_power_data pandora_power_data = {
-	.use_poweroff	= true,
-};
-
-static struct twl4030_platform_data omap3pandora_twldata = {
-	.gpio		= &omap3pandora_gpio_data,
-	.vmmc1		= &pandora_vmmc1,
-	.vmmc2		= &pandora_vmmc2,
-	.vaux1		= &pandora_vaux1,
-	.vaux2		= &pandora_vaux2,
-	.vaux4		= &pandora_vaux4,
-	.vsim		= &pandora_vsim,
-	.keypad		= &pandora_kp_data,
-	.bci		= &pandora_bci_data,
-	.power		= &pandora_power_data,
-};
-
-static struct i2c_board_info __initdata omap3pandora_i2c3_boardinfo[] = {
-	{
-		I2C_BOARD_INFO("bq27500", 0x55),
-		.flags = I2C_CLIENT_WAKE,
-	},
-};
-
-static int __init omap3pandora_i2c_init(void)
-{
-	omap3_pmic_get_config(&omap3pandora_twldata,
-			TWL_COMMON_PDATA_USB | TWL_COMMON_PDATA_AUDIO,
-			TWL_COMMON_REGULATOR_VDAC | TWL_COMMON_REGULATOR_VPLL2);
-
-	omap3pandora_twldata.vdac->constraints.apply_uV = true;
-
-	omap3pandora_twldata.vpll2->constraints.apply_uV = true;
-	omap3pandora_twldata.vpll2->num_consumer_supplies =
-					ARRAY_SIZE(pandora_vdds_supplies);
-	omap3pandora_twldata.vpll2->consumer_supplies = pandora_vdds_supplies;
-
-	omap3_pmic_init("tps65950", &omap3pandora_twldata);
-	/* i2c2 pins are not connected */
-	omap_register_i2c_bus(3, 100, omap3pandora_i2c3_boardinfo,
-			ARRAY_SIZE(omap3pandora_i2c3_boardinfo));
-	return 0;
-}
-
-static struct panel_tpo_td043mtea1_platform_data pandora_lcd_pdata = {
-	.name                   = "lcd",
-	.source                 = "dpi.0",
-
-	.data_lines		= 24,
-	.nreset_gpio		= 157,
-};
-
-static struct spi_board_info omap3pandora_spi_board_info[] __initdata = {
-	{
-		.modalias		= "panel-tpo-td043mtea1",
-		.bus_num		= 1,
-		.chip_select		= 1,
-		.max_speed_hz		= 375000,
-		.platform_data		= &pandora_lcd_pdata,
-	}
-};
-
-static void __init pandora_wl1251_init(void)
-{
-	struct wl1251_platform_data pandora_wl1251_pdata;
-	int ret;
-
-	memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata));
-
-	pandora_wl1251_pdata.power_gpio = -1;
-
-	ret = gpio_request_one(PANDORA_WIFI_IRQ_GPIO, GPIOF_IN, "wl1251 irq");
-	if (ret < 0)
-		goto fail;
-
-	pandora_wl1251_pdata.irq = gpio_to_irq(PANDORA_WIFI_IRQ_GPIO);
-	if (pandora_wl1251_pdata.irq < 0)
-		goto fail_irq;
-
-	pandora_wl1251_pdata.use_eeprom = true;
-	ret = wl1251_set_platform_data(&pandora_wl1251_pdata);
-	if (ret < 0)
-		goto fail_irq;
-
-	return;
-
-fail_irq:
-	gpio_free(PANDORA_WIFI_IRQ_GPIO);
-fail:
-	printk(KERN_ERR "wl1251 board initialisation failed\n");
-}
-
-static struct usbhs_phy_data phy_data[] __initdata = {
-	{
-		.port = 2,
-		.reset_gpio = 16,
-		.vcc_gpio = -EINVAL,
-	},
-};
-
-static struct platform_device *omap3pandora_devices[] __initdata = {
-	&pandora_leds_gpio,
-	&pandora_keys_gpio,
-	&pandora_vwlan_device,
-	&pandora_backlight,
-	&pandora_tv_connector_device,
-};
-
-static struct usbhs_omap_platform_data usbhs_bdata __initdata = {
-	.port_mode[1] = OMAP_EHCI_PORT_MODE_PHY,
-};
-
-#ifdef CONFIG_OMAP_MUX
-static struct omap_board_mux board_mux[] __initdata = {
-	{ .reg_offset = OMAP_MUX_TERMINATOR },
-};
-#endif
-
-static void __init omap3pandora_init(void)
-{
-	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
-	omap_hsmmc_init(omap3pandora_mmc);
-	omap3pandora_i2c_init();
-	pandora_wl1251_init();
-	platform_add_devices(omap3pandora_devices,
-			ARRAY_SIZE(omap3pandora_devices));
-	omap_display_init(&pandora_dss_data);
-	omap_serial_init();
-	omap_sdrc_init(mt46h32m32lf6_sdrc_params,
-				  mt46h32m32lf6_sdrc_params);
-	spi_register_board_info(omap3pandora_spi_board_info,
-			ARRAY_SIZE(omap3pandora_spi_board_info));
-	omap_ads7846_init(1, OMAP3_PANDORA_TS_GPIO, 0, NULL);
-
-	usbhs_init_phys(phy_data, ARRAY_SIZE(phy_data));
-	usbhs_init(&usbhs_bdata);
-
-	usb_bind_phy("musb-hdrc.0.auto", 0, "twl4030_usb");
-	usb_musb_init(NULL);
-	gpmc_nand_init(&pandora_nand_data, NULL);
-
-	/* Ensure SDRC pins are mux'd for self-refresh */
-	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
-	omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT);
-}
-
-MACHINE_START(OMAP3_PANDORA, "Pandora Handheld Console")
-	.atag_offset	= 0x100,
-	.reserve	= omap_reserve,
-	.map_io		= omap3_map_io,
-	.init_early	= omap35xx_init_early,
-	.init_irq	= omap3_init_irq,
-	.init_machine	= omap3pandora_init,
-	.init_late	= omap35xx_init_late,
-	.init_time	= omap3_sync32k_timer_init,
-	.restart	= omap3xxx_restart,
-MACHINE_END
diff --git a/arch/arm/mach-omap2/clkt34xx_dpll3m2.c b/arch/arm/mach-omap2/clkt34xx_dpll3m2.c
index eb69acf21014..3f6521313c93 100644
--- a/arch/arm/mach-omap2/clkt34xx_dpll3m2.c
+++ b/arch/arm/mach-omap2/clkt34xx_dpll3m2.c
@@ -23,12 +23,13 @@
 
 #include "clock.h"
 #include "clock3xxx.h"
-#include "clock34xx.h"
 #include "sdrc.h"
 #include "sram.h"
 
 #define CYCLES_PER_MHZ			1000000
 
+struct clk *sdrc_ick_p, *arm_fck_p;
+
 /*
  * CORE DPLL (DPLL3) M2 divider rate programming functions
  *
@@ -60,12 +61,14 @@ int omap3_core_dpll_m2_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!clk || !rate)
 		return -EINVAL;
 
-	validrate = omap2_clksel_round_rate_div(clk, rate, &new_div);
+	new_div = DIV_ROUND_UP(parent_rate, rate);
+	validrate = parent_rate / new_div;
+
 	if (validrate != rate)
 		return -EINVAL;
 
-	sdrcrate = __clk_get_rate(sdrc_ick_p);
-	clkrate = __clk_get_rate(hw->clk);
+	sdrcrate = clk_get_rate(sdrc_ick_p);
+	clkrate = clk_hw_get_rate(hw);
 	if (rate > clkrate)
 		sdrcrate <<= ((rate / clkrate) >> 1);
 	else
@@ -83,7 +86,7 @@ int omap3_core_dpll_m2_set_rate(struct clk_hw *hw, unsigned long rate,
 	/*
 	 * XXX This only needs to be done when the CPU frequency changes
 	 */
-	_mpurate = __clk_get_rate(arm_fck_p) / CYCLES_PER_MHZ;
+	_mpurate = clk_get_rate(arm_fck_p) / CYCLES_PER_MHZ;
 	c = (_mpurate << SDRC_MPURATE_SCALE) >> SDRC_MPURATE_BASE_SHIFT;
 	c += 1;  /* for safety */
 	c *= SDRC_MPURATE_LOOPS;
diff --git a/arch/arm/mach-omap2/clkt_clksel.c b/arch/arm/mach-omap2/clkt_clksel.c
deleted file mode 100644
index 7ee26108ac0d..000000000000
--- a/arch/arm/mach-omap2/clkt_clksel.c
+++ /dev/null
@@ -1,466 +0,0 @@
-/*
- * clkt_clksel.c - OMAP2/3/4 clksel clock functions
- *
- * Copyright (C) 2005-2008 Texas Instruments, Inc.
- * Copyright (C) 2004-2010 Nokia Corporation
- *
- * Contacts:
- * Richard Woodruff <r-woodruff2@ti.com>
- * Paul Walmsley
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *
- * clksel clocks are clocks that do not have a fixed parent, or that
- * can divide their parent's rate, or possibly both at the same time, based
- * on the contents of a hardware register bitfield.
- *
- * All of the various mux and divider settings can be encoded into
- * struct clksel* data structures, and then these can be autogenerated
- * from some hardware database for each new chip generation.  This
- * should avoid the need to write, review, and validate a lot of new
- * clock code for each new chip, since it can be exported from the SoC
- * design flow.  This is now done on OMAP4.
- *
- * The fusion of mux and divider clocks is a software creation.  In
- * hardware reality, the multiplexer (parent selection) and the
- * divider exist separately.  XXX At some point these clksel clocks
- * should be split into "divider" clocks and "mux" clocks to better
- * match the hardware.
- *
- * (The name "clksel" comes from the name of the corresponding
- * register field in the OMAP2/3 family of SoCs.)
- *
- * XXX Currently these clocks are only used in the OMAP2/3/4 code, but
- * many of the OMAP1 clocks should be convertible to use this
- * mechanism.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/clk-provider.h>
-#include <linux/io.h>
-#include <linux/bug.h>
-
-#include "clock.h"
-
-/* Private functions */
-
-/**
- * _get_clksel_by_parent() - return clksel struct for a given clk & parent
- * @clk: OMAP struct clk ptr to inspect
- * @src_clk: OMAP struct clk ptr of the parent clk to search for
- *
- * Scan the struct clksel array associated with the clock to find
- * the element associated with the supplied parent clock address.
- * Returns a pointer to the struct clksel on success or NULL on error.
- */
-static const struct clksel *_get_clksel_by_parent(struct clk_hw_omap *clk,
-						  struct clk *src_clk)
-{
-	const struct clksel *clks;
-
-	if (!src_clk)
-		return NULL;
-
-	for (clks = clk->clksel; clks->parent; clks++)
-		if (clks->parent == src_clk)
-			break; /* Found the requested parent */
-
-	if (!clks->parent) {
-		/* This indicates a data problem */
-		WARN(1, "clock: %s: could not find parent clock %s in clksel array\n",
-		     __clk_get_name(clk->hw.clk), __clk_get_name(src_clk));
-		return NULL;
-	}
-
-	return clks;
-}
-
-/**
- * _write_clksel_reg() - program a clock's clksel register in hardware
- * @clk: struct clk * to program
- * @v: clksel bitfield value to program (with LSB at bit 0)
- *
- * Shift the clksel register bitfield value @v to its appropriate
- * location in the clksel register and write it in.  This function
- * will ensure that the write to the clksel_reg reaches its
- * destination before returning -- important since PRM and CM register
- * accesses can be quite slow compared to ARM cycles -- but does not
- * take into account any time the hardware might take to switch the
- * clock source.
- */
-static void _write_clksel_reg(struct clk_hw_omap *clk, u32 field_val)
-{
-	u32 v;
-
-	v = omap2_clk_readl(clk, clk->clksel_reg);
-	v &= ~clk->clksel_mask;
-	v |= field_val << __ffs(clk->clksel_mask);
-	omap2_clk_writel(v, clk, clk->clksel_reg);
-
-	v = omap2_clk_readl(clk, clk->clksel_reg); /* OCP barrier */
-}
-
-/**
- * _clksel_to_divisor() - turn clksel field value into integer divider
- * @clk: OMAP struct clk to use
- * @field_val: register field value to find
- *
- * Given a struct clk of a rate-selectable clksel clock, and a register field
- * value to search for, find the corresponding clock divisor.  The register
- * field value should be pre-masked and shifted down so the LSB is at bit 0
- * before calling.  Returns 0 on error or returns the actual integer divisor
- * upon success.
- */
-static u32 _clksel_to_divisor(struct clk_hw_omap *clk, u32 field_val)
-{
-	const struct clksel *clks;
-	const struct clksel_rate *clkr;
-	struct clk *parent;
-
-	parent = __clk_get_parent(clk->hw.clk);
-
-	clks = _get_clksel_by_parent(clk, parent);
-	if (!clks)
-		return 0;
-
-	for (clkr = clks->rates; clkr->div; clkr++) {
-		if (!(clkr->flags & cpu_mask))
-			continue;
-
-		if (clkr->val == field_val)
-			break;
-	}
-
-	if (!clkr->div) {
-		/* This indicates a data error */
-		WARN(1, "clock: %s: could not find fieldval %d for parent %s\n",
-		     __clk_get_name(clk->hw.clk), field_val,
-		     __clk_get_name(parent));
-		return 0;
-	}
-
-	return clkr->div;
-}
-
-/**
- * _divisor_to_clksel() - turn clksel integer divisor into a field value
- * @clk: OMAP struct clk to use
- * @div: integer divisor to search for
- *
- * Given a struct clk of a rate-selectable clksel clock, and a clock
- * divisor, find the corresponding register field value.  Returns the
- * register field value _before_ left-shifting (i.e., LSB is at bit
- * 0); or returns 0xFFFFFFFF (~0) upon error.
- */
-static u32 _divisor_to_clksel(struct clk_hw_omap *clk, u32 div)
-{
-	const struct clksel *clks;
-	const struct clksel_rate *clkr;
-	struct clk *parent;
-
-	/* should never happen */
-	WARN_ON(div == 0);
-
-	parent = __clk_get_parent(clk->hw.clk);
-	clks = _get_clksel_by_parent(clk, parent);
-	if (!clks)
-		return ~0;
-
-	for (clkr = clks->rates; clkr->div; clkr++) {
-		if (!(clkr->flags & cpu_mask))
-			continue;
-
-		if (clkr->div == div)
-			break;
-	}
-
-	if (!clkr->div) {
-		pr_err("clock: %s: could not find divisor %d for parent %s\n",
-		       __clk_get_name(clk->hw.clk), div,
-		       __clk_get_name(parent));
-		return ~0;
-	}
-
-	return clkr->val;
-}
-
-/**
- * _read_divisor() - get current divisor applied to parent clock (from hdwr)
- * @clk: OMAP struct clk to use.
- *
- * Read the current divisor register value for @clk that is programmed
- * into the hardware, convert it into the actual divisor value, and
- * return it; or return 0 on error.
- */
-static u32 _read_divisor(struct clk_hw_omap *clk)
-{
-	u32 v;
-
-	if (!clk->clksel || !clk->clksel_mask)
-		return 0;
-
-	v = omap2_clk_readl(clk, clk->clksel_reg);
-	v &= clk->clksel_mask;
-	v >>= __ffs(clk->clksel_mask);
-
-	return _clksel_to_divisor(clk, v);
-}
-
-/* Public functions */
-
-/**
- * omap2_clksel_round_rate_div() - find divisor for the given clock and rate
- * @clk: OMAP struct clk to use
- * @target_rate: desired clock rate
- * @new_div: ptr to where we should store the divisor
- *
- * Finds 'best' divider value in an array based on the source and target
- * rates.  The divider array must be sorted with smallest divider first.
- * This function is also used by the DPLL3 M2 divider code.
- *
- * Returns the rounded clock rate or returns 0xffffffff on error.
- */
-u32 omap2_clksel_round_rate_div(struct clk_hw_omap *clk,
-						 unsigned long target_rate,
-				u32 *new_div)
-{
-	unsigned long test_rate;
-	const struct clksel *clks;
-	const struct clksel_rate *clkr;
-	u32 last_div = 0;
-	struct clk *parent;
-	unsigned long parent_rate;
-	const char *clk_name;
-
-	parent = __clk_get_parent(clk->hw.clk);
-	clk_name = __clk_get_name(clk->hw.clk);
-	parent_rate = __clk_get_rate(parent);
-
-	if (!clk->clksel || !clk->clksel_mask)
-		return ~0;
-
-	pr_debug("clock: clksel_round_rate_div: %s target_rate %ld\n",
-		 clk_name, target_rate);
-
-	*new_div = 1;
-
-	clks = _get_clksel_by_parent(clk, parent);
-	if (!clks)
-		return ~0;
-
-	for (clkr = clks->rates; clkr->div; clkr++) {
-		if (!(clkr->flags & cpu_mask))
-			continue;
-
-		/* Sanity check */
-		if (clkr->div <= last_div)
-			pr_err("clock: %s: clksel_rate table not sorted\n",
-			       clk_name);
-
-		last_div = clkr->div;
-
-		test_rate = parent_rate / clkr->div;
-
-		if (test_rate <= target_rate)
-			break; /* found it */
-	}
-
-	if (!clkr->div) {
-		pr_err("clock: %s: could not find divisor for target rate %ld for parent %s\n",
-		       clk_name, target_rate, __clk_get_name(parent));
-		return ~0;
-	}
-
-	*new_div = clkr->div;
-
-	pr_debug("clock: new_div = %d, new_rate = %ld\n", *new_div,
-		 (parent_rate / clkr->div));
-
-	return parent_rate / clkr->div;
-}
-
-/*
- * Clocktype interface functions to the OMAP clock code
- * (i.e., those used in struct clk field function pointers, etc.)
- */
-
-/**
- * omap2_clksel_find_parent_index() - return the array index of the current
- * hardware parent of @hw
- * @hw: struct clk_hw * to find the current hardware parent of
- *
- * Given a struct clk_hw pointer @hw to the 'hw' member of a struct
- * clk_hw_omap record representing a source-selectable hardware clock,
- * read the hardware register and determine what its parent is
- * currently set to.  Intended to be called only by the common clock
- * framework struct clk_hw_ops.get_parent function pointer.  Return
- * the array index of this parent clock upon success -- there is no
- * way to return an error, so if we encounter an error, just WARN()
- * and pretend that we know that we're doing.
- */
-u8 omap2_clksel_find_parent_index(struct clk_hw *hw)
-{
-	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
-	const struct clksel *clks;
-	const struct clksel_rate *clkr;
-	u32 r, found = 0;
-	struct clk *parent;
-	const char *clk_name;
-	int ret = 0, f = 0;
-
-	parent = __clk_get_parent(hw->clk);
-	clk_name = __clk_get_name(hw->clk);
-
-	/* XXX should be able to return an error */
-	WARN((!clk->clksel || !clk->clksel_mask),
-	     "clock: %s: attempt to call on a non-clksel clock", clk_name);
-
-	r = omap2_clk_readl(clk, clk->clksel_reg) & clk->clksel_mask;
-	r >>= __ffs(clk->clksel_mask);
-
-	for (clks = clk->clksel; clks->parent && !found; clks++) {
-		for (clkr = clks->rates; clkr->div && !found; clkr++) {
-			if (!(clkr->flags & cpu_mask))
-				continue;
-
-			if (clkr->val == r) {
-				found = 1;
-				ret = f;
-			}
-		}
-		f++;
-	}
-
-	/* This indicates a data error */
-	WARN(!found, "clock: %s: init parent: could not find regval %0x\n",
-	     clk_name, r);
-
-	return ret;
-}
-
-
-/**
- * omap2_clksel_recalc() - function ptr to pass via struct clk .recalc field
- * @clk: struct clk *
- *
- * This function is intended to be called only by the clock framework.
- * Each clksel clock should have its struct clk .recalc field set to this
- * function.  Returns the clock's current rate, based on its parent's rate
- * and its current divisor setting in the hardware.
- */
-unsigned long omap2_clksel_recalc(struct clk_hw *hw, unsigned long parent_rate)
-{
-	unsigned long rate;
-	u32 div = 0;
-	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
-
-	if (!parent_rate)
-		return 0;
-
-	div = _read_divisor(clk);
-	if (!div)
-		rate = parent_rate;
-	else
-		rate = parent_rate / div;
-
-	pr_debug("%s: recalc'd %s's rate to %lu (div %d)\n", __func__,
-		 __clk_get_name(hw->clk), rate, div);
-
-	return rate;
-}
-
-/**
- * omap2_clksel_round_rate() - find rounded rate for the given clock and rate
- * @clk: OMAP struct clk to use
- * @target_rate: desired clock rate
- *
- * This function is intended to be called only by the clock framework.
- * Finds best target rate based on the source clock and possible dividers.
- * rates. The divider array must be sorted with smallest divider first.
- *
- * Returns the rounded clock rate or returns 0xffffffff on error.
- */
-long omap2_clksel_round_rate(struct clk_hw *hw, unsigned long target_rate,
-			unsigned long *parent_rate)
-{
-	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
-	u32 new_div;
-
-	return omap2_clksel_round_rate_div(clk, target_rate, &new_div);
-}
-
-/**
- * omap2_clksel_set_rate() - program clock rate in hardware
- * @clk: struct clk * to program rate
- * @rate: target rate to program
- *
- * This function is intended to be called only by the clock framework.
- * Program @clk's rate to @rate in the hardware.  The clock can be
- * either enabled or disabled when this happens, although if the clock
- * is enabled, some downstream devices may glitch or behave
- * unpredictably when the clock rate is changed - this depends on the
- * hardware. This function does not currently check the usecount of
- * the clock, so if multiple drivers are using the clock, and the rate
- * is changed, they will all be affected without any notification.
- * Returns -EINVAL upon error, or 0 upon success.
- */
-int omap2_clksel_set_rate(struct clk_hw *hw, unsigned long rate,
-				unsigned long parent_rate)
-{
-	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
-	u32 field_val, validrate, new_div = 0;
-
-	if (!clk->clksel || !clk->clksel_mask)
-		return -EINVAL;
-
-	validrate = omap2_clksel_round_rate_div(clk, rate, &new_div);
-	if (validrate != rate)
-		return -EINVAL;
-
-	field_val = _divisor_to_clksel(clk, new_div);
-	if (field_val == ~0)
-		return -EINVAL;
-
-	_write_clksel_reg(clk, field_val);
-
-	pr_debug("clock: %s: set rate to %ld\n", __clk_get_name(hw->clk),
-		 __clk_get_rate(hw->clk));
-
-	return 0;
-}
-
-/*
- * Clksel parent setting function - not passed in struct clk function
- * pointer - instead, the OMAP clock code currently assumes that any
- * parent-setting clock is a clksel clock, and calls
- * omap2_clksel_set_parent() by default
- */
-
-/**
- * omap2_clksel_set_parent() - change a clock's parent clock
- * @clk: struct clk * of the child clock
- * @new_parent: struct clk * of the new parent clock
- *
- * This function is intended to be called only by the clock framework.
- * Change the parent clock of clock @clk to @new_parent.  This is
- * intended to be used while @clk is disabled.  This function does not
- * currently check the usecount of the clock, so if multiple drivers
- * are using the clock, and the parent is changed, they will all be
- * affected without any notification.  Returns -EINVAL upon error, or
- * 0 upon success.
- */
-int omap2_clksel_set_parent(struct clk_hw *hw, u8 field_val)
-{
-	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
-
-	if (!clk->clksel || !clk->clksel_mask)
-		return -EINVAL;
-
-	_write_clksel_reg(clk, field_val);
-	return 0;
-}
diff --git a/arch/arm/mach-omap2/clkt_iclk.c b/arch/arm/mach-omap2/clkt_iclk.c
deleted file mode 100644
index 55eb579aeae1..000000000000
--- a/arch/arm/mach-omap2/clkt_iclk.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * OMAP2/3 interface clock control
- *
- * Copyright (C) 2011 Nokia Corporation
- * Paul Walmsley
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/clk-provider.h>
-#include <linux/io.h>
-
-#include "clock.h"
-
-/* Register offsets */
-#define CM_AUTOIDLE			0x30
-#define CM_ICLKEN			0x10
-
-/* Private functions */
-
-/* XXX */
-void omap2_clkt_iclk_allow_idle(struct clk_hw_omap *clk)
-{
-	u32 v;
-	void __iomem *r;
-
-	r = (__force void __iomem *)
-		((__force u32)clk->enable_reg ^ (CM_AUTOIDLE ^ CM_ICLKEN));
-
-	v = omap2_clk_readl(clk, r);
-	v |= (1 << clk->enable_bit);
-	omap2_clk_writel(v, clk, r);
-}
-
-/* XXX */
-void omap2_clkt_iclk_deny_idle(struct clk_hw_omap *clk)
-{
-	u32 v;
-	void __iomem *r;
-
-	r = (__force void __iomem *)
-		((__force u32)clk->enable_reg ^ (CM_AUTOIDLE ^ CM_ICLKEN));
-
-	v = omap2_clk_readl(clk, r);
-	v &= ~(1 << clk->enable_bit);
-	omap2_clk_writel(v, clk, r);
-}
-
-/* Public data */
-
-const struct clk_hw_omap_ops clkhwops_iclk = {
-	.allow_idle	= omap2_clkt_iclk_allow_idle,
-	.deny_idle	= omap2_clkt_iclk_deny_idle,
-};
-
-const struct clk_hw_omap_ops clkhwops_iclk_wait = {
-	.allow_idle	= omap2_clkt_iclk_allow_idle,
-	.deny_idle	= omap2_clkt_iclk_deny_idle,
-	.find_idlest	= omap2_clk_dflt_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
-
-
-
diff --git a/arch/arm/mach-omap2/clock.c b/arch/arm/mach-omap2/clock.c
index a699d7169307..acb60ed17273 100644
--- a/arch/arm/mach-omap2/clock.c
+++ b/arch/arm/mach-omap2/clock.c
@@ -20,12 +20,11 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/delay.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/bitops.h>
-#include <linux/regmap.h>
 #include <linux/of_address.h>
-#include <linux/bootmem.h>
 #include <asm/cpu.h>
 
 #include <trace/events/power.h>
@@ -40,19 +39,8 @@
 #include "cm-regbits-34xx.h"
 #include "common.h"
 
-/*
- * MAX_MODULE_ENABLE_WAIT: maximum of number of microseconds to wait
- * for a module to indicate that it is no longer in idle
- */
-#define MAX_MODULE_ENABLE_WAIT		100000
-
 u16 cpu_mask;
 
-/*
- * Clock features setup. Used instead of CPU type checks.
- */
-struct ti_clk_features ti_clk_features;
-
 /* DPLL valid Fint frequency band limits - from 34xx TRM Section 4.7.6.2 */
 #define OMAP3430_DPLL_FINT_BAND1_MIN	750000
 #define OMAP3430_DPLL_FINT_BAND1_MAX	2100000
@@ -66,119 +54,24 @@ struct ti_clk_features ti_clk_features;
 #define OMAP3PLUS_DPLL_FINT_MIN		32000
 #define OMAP3PLUS_DPLL_FINT_MAX		52000000
 
-/*
- * clkdm_control: if true, then when a clock is enabled in the
- * hardware, its clockdomain will first be enabled; and when a clock
- * is disabled in the hardware, its clockdomain will be disabled
- * afterwards.
- */
-static bool clkdm_control = true;
-
-static LIST_HEAD(clk_hw_omap_clocks);
-
-struct clk_iomap {
-	struct regmap *regmap;
-	void __iomem *mem;
-};
-
-static struct clk_iomap *clk_memmaps[CLK_MAX_MEMMAPS];
-
-static void clk_memmap_writel(u32 val, void __iomem *reg)
-{
-	struct clk_omap_reg *r = (struct clk_omap_reg *)&reg;
-	struct clk_iomap *io = clk_memmaps[r->index];
-
-	if (io->regmap)
-		regmap_write(io->regmap, r->offset, val);
-	else
-		writel_relaxed(val, io->mem + r->offset);
-}
-
-static u32 clk_memmap_readl(void __iomem *reg)
-{
-	u32 val;
-	struct clk_omap_reg *r = (struct clk_omap_reg *)&reg;
-	struct clk_iomap *io = clk_memmaps[r->index];
-
-	if (io->regmap)
-		regmap_read(io->regmap, r->offset, &val);
-	else
-		val = readl_relaxed(io->mem + r->offset);
-
-	return val;
-}
-
-void omap2_clk_writel(u32 val, struct clk_hw_omap *clk, void __iomem *reg)
-{
-	if (WARN_ON_ONCE(!(clk->flags & MEMMAP_ADDRESSING)))
-		writel_relaxed(val, reg);
-	else
-		clk_memmap_writel(val, reg);
-}
-
-u32 omap2_clk_readl(struct clk_hw_omap *clk, void __iomem *reg)
-{
-	if (WARN_ON_ONCE(!(clk->flags & MEMMAP_ADDRESSING)))
-		return readl_relaxed(reg);
-	else
-		return clk_memmap_readl(reg);
-}
-
 static struct ti_clk_ll_ops omap_clk_ll_ops = {
-	.clk_readl = clk_memmap_readl,
-	.clk_writel = clk_memmap_writel,
+	.clkdm_clk_enable = clkdm_clk_enable,
+	.clkdm_clk_disable = clkdm_clk_disable,
+	.cm_wait_module_ready = omap_cm_wait_module_ready,
+	.cm_split_idlest_reg = cm_split_idlest_reg,
 };
 
 /**
- * omap2_clk_provider_init - initialize a clock provider
- * @match_table: DT device table to match for devices to init
- * @np: device node pointer for the this clock provider
- * @index: index for the clock provider
- + @syscon: syscon regmap pointer
- * @mem: iomem pointer for the clock provider memory area, only used if
- *	 syscon is not provided
+ * omap2_clk_setup_ll_ops - setup clock driver low-level ops
  *
- * Initializes a clock provider module (CM/PRM etc.), registering
- * the memory mapping at specified index and initializing the
- * low level driver infrastructure. Returns 0 in success.
+ * Sets up clock driver low-level platform ops. These are needed
+ * for register accesses and various other misc platform operations.
+ * Returns 0 on success, -EBUSY if low level ops have been registered
+ * already.
  */
-int __init omap2_clk_provider_init(struct device_node *np, int index,
-				   struct regmap *syscon, void __iomem *mem)
+int __init omap2_clk_setup_ll_ops(void)
 {
-	struct clk_iomap *io;
-
-	ti_clk_ll_ops = &omap_clk_ll_ops;
-
-	io = kzalloc(sizeof(*io), GFP_KERNEL);
-
-	io->regmap = syscon;
-	io->mem = mem;
-
-	clk_memmaps[index] = io;
-
-	ti_dt_clk_init_provider(np, index);
-
-	return 0;
-}
-
-/**
- * omap2_clk_legacy_provider_init - initialize a legacy clock provider
- * @index: index for the clock provider
- * @mem: iomem pointer for the clock provider memory area
- *
- * Initializes a legacy clock provider memory mapping.
- */
-void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem)
-{
-	struct clk_iomap *io;
-
-	ti_clk_ll_ops = &omap_clk_ll_ops;
-
-	io = memblock_virt_alloc(sizeof(*io), 0);
-
-	io->mem = mem;
-
-	clk_memmaps[index] = io;
+	return ti_clk_setup_ll_ops(&omap_clk_ll_ops);
 }
 
 /*
@@ -187,77 +80,6 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem)
 
 /* Private functions */
 
-
-/**
- * _wait_idlest_generic - wait for a module to leave the idle state
- * @clk: module clock to wait for (needed for register offsets)
- * @reg: virtual address of module IDLEST register
- * @mask: value to mask against to determine if the module is active
- * @idlest: idle state indicator (0 or 1) for the clock
- * @name: name of the clock (for printk)
- *
- * Wait for a module to leave idle, where its idle-status register is
- * not inside the CM module.  Returns 1 if the module left idle
- * promptly, or 0 if the module did not leave idle before the timeout
- * elapsed.  XXX Deprecated - should be moved into drivers for the
- * individual IP block that the IDLEST register exists in.
- */
-static int _wait_idlest_generic(struct clk_hw_omap *clk, void __iomem *reg,
-				u32 mask, u8 idlest, const char *name)
-{
-	int i = 0, ena = 0;
-
-	ena = (idlest) ? 0 : mask;
-
-	omap_test_timeout(((omap2_clk_readl(clk, reg) & mask) == ena),
-			  MAX_MODULE_ENABLE_WAIT, i);
-
-	if (i < MAX_MODULE_ENABLE_WAIT)
-		pr_debug("omap clock: module associated with clock %s ready after %d loops\n",
-			 name, i);
-	else
-		pr_err("omap clock: module associated with clock %s didn't enable in %d tries\n",
-		       name, MAX_MODULE_ENABLE_WAIT);
-
-	return (i < MAX_MODULE_ENABLE_WAIT) ? 1 : 0;
-};
-
-/**
- * _omap2_module_wait_ready - wait for an OMAP module to leave IDLE
- * @clk: struct clk * belonging to the module
- *
- * If the necessary clocks for the OMAP hardware IP block that
- * corresponds to clock @clk are enabled, then wait for the module to
- * indicate readiness (i.e., to leave IDLE).  This code does not
- * belong in the clock code and will be moved in the medium term to
- * module-dependent code.  No return value.
- */
-static void _omap2_module_wait_ready(struct clk_hw_omap *clk)
-{
-	void __iomem *companion_reg, *idlest_reg;
-	u8 other_bit, idlest_bit, idlest_val, idlest_reg_id;
-	s16 prcm_mod;
-	int r;
-
-	/* Not all modules have multiple clocks that their IDLEST depends on */
-	if (clk->ops->find_companion) {
-		clk->ops->find_companion(clk, &companion_reg, &other_bit);
-		if (!(omap2_clk_readl(clk, companion_reg) & (1 << other_bit)))
-			return;
-	}
-
-	clk->ops->find_idlest(clk, &idlest_reg, &idlest_bit, &idlest_val);
-	r = cm_split_idlest_reg(idlest_reg, &prcm_mod, &idlest_reg_id);
-	if (r) {
-		/* IDLEST register not in the CM module */
-		_wait_idlest_generic(clk, idlest_reg, (1 << idlest_bit),
-				     idlest_val, __clk_get_name(clk->hw.clk));
-	} else {
-		omap_cm_wait_module_ready(0, prcm_mod, idlest_reg_id,
-					  idlest_bit);
-	};
-}
-
 /* Public functions */
 
 /**
@@ -290,279 +112,6 @@ void omap2_init_clk_clkdm(struct clk_hw *hw)
 	}
 }
 
-/**
- * omap2_clk_disable_clkdm_control - disable clkdm control on clk enable/disable
- *
- * Prevent the OMAP clock code from calling into the clockdomain code
- * when a hardware clock in that clockdomain is enabled or disabled.
- * Intended to be called at init time from omap*_clk_init().  No
- * return value.
- */
-void __init omap2_clk_disable_clkdm_control(void)
-{
-	clkdm_control = false;
-}
-
-/**
- * omap2_clk_dflt_find_companion - find companion clock to @clk
- * @clk: struct clk * to find the companion clock of
- * @other_reg: void __iomem ** to return the companion clock CM_*CLKEN va in
- * @other_bit: u8 ** to return the companion clock bit shift in
- *
- * Note: We don't need special code here for INVERT_ENABLE for the
- * time being since INVERT_ENABLE only applies to clocks enabled by
- * CM_CLKEN_PLL
- *
- * Convert CM_ICLKEN* <-> CM_FCLKEN*.  This conversion assumes it's
- * just a matter of XORing the bits.
- *
- * Some clocks don't have companion clocks.  For example, modules with
- * only an interface clock (such as MAILBOXES) don't have a companion
- * clock.  Right now, this code relies on the hardware exporting a bit
- * in the correct companion register that indicates that the
- * nonexistent 'companion clock' is active.  Future patches will
- * associate this type of code with per-module data structures to
- * avoid this issue, and remove the casts.  No return value.
- */
-void omap2_clk_dflt_find_companion(struct clk_hw_omap *clk,
-			void __iomem **other_reg, u8 *other_bit)
-{
-	u32 r;
-
-	/*
-	 * Convert CM_ICLKEN* <-> CM_FCLKEN*.  This conversion assumes
-	 * it's just a matter of XORing the bits.
-	 */
-	r = ((__force u32)clk->enable_reg ^ (CM_FCLKEN ^ CM_ICLKEN));
-
-	*other_reg = (__force void __iomem *)r;
-	*other_bit = clk->enable_bit;
-}
-
-/**
- * omap2_clk_dflt_find_idlest - find CM_IDLEST reg va, bit shift for @clk
- * @clk: struct clk * to find IDLEST info for
- * @idlest_reg: void __iomem ** to return the CM_IDLEST va in
- * @idlest_bit: u8 * to return the CM_IDLEST bit shift in
- * @idlest_val: u8 * to return the idle status indicator
- *
- * Return the CM_IDLEST register address and bit shift corresponding
- * to the module that "owns" this clock.  This default code assumes
- * that the CM_IDLEST bit shift is the CM_*CLKEN bit shift, and that
- * the IDLEST register address ID corresponds to the CM_*CLKEN
- * register address ID (e.g., that CM_FCLKEN2 corresponds to
- * CM_IDLEST2).  This is not true for all modules.  No return value.
- */
-void omap2_clk_dflt_find_idlest(struct clk_hw_omap *clk,
-		void __iomem **idlest_reg, u8 *idlest_bit, u8 *idlest_val)
-{
-	u32 r;
-
-	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
-	*idlest_reg = (__force void __iomem *)r;
-	*idlest_bit = clk->enable_bit;
-
-	/*
-	 * 24xx uses 0 to indicate not ready, and 1 to indicate ready.
-	 * 34xx reverses this, just to keep us on our toes
-	 * AM35xx uses both, depending on the module.
-	 */
-	*idlest_val = ti_clk_features.cm_idlest_val;
-}
-
-/**
- * omap2_dflt_clk_enable - enable a clock in the hardware
- * @hw: struct clk_hw * of the clock to enable
- *
- * Enable the clock @hw in the hardware.  We first call into the OMAP
- * clockdomain code to "enable" the corresponding clockdomain if this
- * is the first enabled user of the clockdomain.  Then program the
- * hardware to enable the clock.  Then wait for the IP block that uses
- * this clock to leave idle (if applicable).  Returns the error value
- * from clkdm_clk_enable() if it terminated with an error, or -EINVAL
- * if @hw has a null clock enable_reg, or zero upon success.
- */
-int omap2_dflt_clk_enable(struct clk_hw *hw)
-{
-	struct clk_hw_omap *clk;
-	u32 v;
-	int ret = 0;
-
-	clk = to_clk_hw_omap(hw);
-
-	if (clkdm_control && clk->clkdm) {
-		ret = clkdm_clk_enable(clk->clkdm, hw->clk);
-		if (ret) {
-			WARN(1, "%s: could not enable %s's clockdomain %s: %d\n",
-			     __func__, __clk_get_name(hw->clk),
-			     clk->clkdm->name, ret);
-			return ret;
-		}
-	}
-
-	if (unlikely(clk->enable_reg == NULL)) {
-		pr_err("%s: %s missing enable_reg\n", __func__,
-		       __clk_get_name(hw->clk));
-		ret = -EINVAL;
-		goto err;
-	}
-
-	/* FIXME should not have INVERT_ENABLE bit here */
-	v = omap2_clk_readl(clk, clk->enable_reg);
-	if (clk->flags & INVERT_ENABLE)
-		v &= ~(1 << clk->enable_bit);
-	else
-		v |= (1 << clk->enable_bit);
-	omap2_clk_writel(v, clk, clk->enable_reg);
-	v = omap2_clk_readl(clk, clk->enable_reg); /* OCP barrier */
-
-	if (clk->ops && clk->ops->find_idlest)
-		_omap2_module_wait_ready(clk);
-
-	return 0;
-
-err:
-	if (clkdm_control && clk->clkdm)
-		clkdm_clk_disable(clk->clkdm, hw->clk);
-	return ret;
-}
-
-/**
- * omap2_dflt_clk_disable - disable a clock in the hardware
- * @hw: struct clk_hw * of the clock to disable
- *
- * Disable the clock @hw in the hardware, and call into the OMAP
- * clockdomain code to "disable" the corresponding clockdomain if all
- * clocks/hwmods in that clockdomain are now disabled.  No return
- * value.
- */
-void omap2_dflt_clk_disable(struct clk_hw *hw)
-{
-	struct clk_hw_omap *clk;
-	u32 v;
-
-	clk = to_clk_hw_omap(hw);
-	if (!clk->enable_reg) {
-		/*
-		 * 'independent' here refers to a clock which is not
-		 * controlled by its parent.
-		 */
-		pr_err("%s: independent clock %s has no enable_reg\n",
-		       __func__, __clk_get_name(hw->clk));
-		return;
-	}
-
-	v = omap2_clk_readl(clk, clk->enable_reg);
-	if (clk->flags & INVERT_ENABLE)
-		v |= (1 << clk->enable_bit);
-	else
-		v &= ~(1 << clk->enable_bit);
-	omap2_clk_writel(v, clk, clk->enable_reg);
-	/* No OCP barrier needed here since it is a disable operation */
-
-	if (clkdm_control && clk->clkdm)
-		clkdm_clk_disable(clk->clkdm, hw->clk);
-}
-
-/**
- * omap2_clkops_enable_clkdm - increment usecount on clkdm of @hw
- * @hw: struct clk_hw * of the clock being enabled
- *
- * Increment the usecount of the clockdomain of the clock pointed to
- * by @hw; if the usecount is 1, the clockdomain will be "enabled."
- * Only needed for clocks that don't use omap2_dflt_clk_enable() as
- * their enable function pointer.  Passes along the return value of
- * clkdm_clk_enable(), -EINVAL if @hw is not associated with a
- * clockdomain, or 0 if clock framework-based clockdomain control is
- * not implemented.
- */
-int omap2_clkops_enable_clkdm(struct clk_hw *hw)
-{
-	struct clk_hw_omap *clk;
-	int ret = 0;
-
-	clk = to_clk_hw_omap(hw);
-
-	if (unlikely(!clk->clkdm)) {
-		pr_err("%s: %s: no clkdm set ?!\n", __func__,
-		       __clk_get_name(hw->clk));
-		return -EINVAL;
-	}
-
-	if (unlikely(clk->enable_reg))
-		pr_err("%s: %s: should use dflt_clk_enable ?!\n", __func__,
-		       __clk_get_name(hw->clk));
-
-	if (!clkdm_control) {
-		pr_err("%s: %s: clkfw-based clockdomain control disabled ?!\n",
-		       __func__, __clk_get_name(hw->clk));
-		return 0;
-	}
-
-	ret = clkdm_clk_enable(clk->clkdm, hw->clk);
-	WARN(ret, "%s: could not enable %s's clockdomain %s: %d\n",
-	     __func__, __clk_get_name(hw->clk), clk->clkdm->name, ret);
-
-	return ret;
-}
-
-/**
- * omap2_clkops_disable_clkdm - decrement usecount on clkdm of @hw
- * @hw: struct clk_hw * of the clock being disabled
- *
- * Decrement the usecount of the clockdomain of the clock pointed to
- * by @hw; if the usecount is 0, the clockdomain will be "disabled."
- * Only needed for clocks that don't use omap2_dflt_clk_disable() as their
- * disable function pointer.  No return value.
- */
-void omap2_clkops_disable_clkdm(struct clk_hw *hw)
-{
-	struct clk_hw_omap *clk;
-
-	clk = to_clk_hw_omap(hw);
-
-	if (unlikely(!clk->clkdm)) {
-		pr_err("%s: %s: no clkdm set ?!\n", __func__,
-		       __clk_get_name(hw->clk));
-		return;
-	}
-
-	if (unlikely(clk->enable_reg))
-		pr_err("%s: %s: should use dflt_clk_disable ?!\n", __func__,
-		       __clk_get_name(hw->clk));
-
-	if (!clkdm_control) {
-		pr_err("%s: %s: clkfw-based clockdomain control disabled ?!\n",
-		       __func__, __clk_get_name(hw->clk));
-		return;
-	}
-
-	clkdm_clk_disable(clk->clkdm, hw->clk);
-}
-
-/**
- * omap2_dflt_clk_is_enabled - is clock enabled in the hardware?
- * @hw: struct clk_hw * to check
- *
- * Return 1 if the clock represented by @hw is enabled in the
- * hardware, or 0 otherwise.  Intended for use in the struct
- * clk_ops.is_enabled function pointer.
- */
-int omap2_dflt_clk_is_enabled(struct clk_hw *hw)
-{
-	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
-	u32 v;
-
-	v = omap2_clk_readl(clk, clk->enable_reg);
-
-	if (clk->flags & INVERT_ENABLE)
-		v ^= BIT(clk->enable_bit);
-
-	v &= BIT(clk->enable_bit);
-
-	return v ? 1 : 0;
-}
-
 static int __initdata mpurate;
 
 /*
@@ -584,178 +133,6 @@ static int __init omap_clk_setup(char *str)
 __setup("mpurate=", omap_clk_setup);
 
 /**
- * omap2_init_clk_hw_omap_clocks - initialize an OMAP clock
- * @clk: struct clk * to initialize
- *
- * Add an OMAP clock @clk to the internal list of OMAP clocks.  Used
- * temporarily for autoidle handling, until this support can be
- * integrated into the common clock framework code in some way.  No
- * return value.
- */
-void omap2_init_clk_hw_omap_clocks(struct clk *clk)
-{
-	struct clk_hw_omap *c;
-
-	if (__clk_get_flags(clk) & CLK_IS_BASIC)
-		return;
-
-	c = to_clk_hw_omap(__clk_get_hw(clk));
-	list_add(&c->node, &clk_hw_omap_clocks);
-}
-
-/**
- * omap2_clk_enable_autoidle_all - enable autoidle on all OMAP clocks that
- * support it
- *
- * Enable clock autoidle on all OMAP clocks that have allow_idle
- * function pointers associated with them.  This function is intended
- * to be temporary until support for this is added to the common clock
- * code.  Returns 0.
- */
-int omap2_clk_enable_autoidle_all(void)
-{
-	struct clk_hw_omap *c;
-
-	list_for_each_entry(c, &clk_hw_omap_clocks, node)
-		if (c->ops && c->ops->allow_idle)
-			c->ops->allow_idle(c);
-
-	of_ti_clk_allow_autoidle_all();
-
-	return 0;
-}
-
-/**
- * omap2_clk_disable_autoidle_all - disable autoidle on all OMAP clocks that
- * support it
- *
- * Disable clock autoidle on all OMAP clocks that have allow_idle
- * function pointers associated with them.  This function is intended
- * to be temporary until support for this is added to the common clock
- * code.  Returns 0.
- */
-int omap2_clk_disable_autoidle_all(void)
-{
-	struct clk_hw_omap *c;
-
-	list_for_each_entry(c, &clk_hw_omap_clocks, node)
-		if (c->ops && c->ops->deny_idle)
-			c->ops->deny_idle(c);
-
-	of_ti_clk_deny_autoidle_all();
-
-	return 0;
-}
-
-/**
- * omap2_clk_deny_idle - disable autoidle on an OMAP clock
- * @clk: struct clk * to disable autoidle for
- *
- * Disable autoidle on an OMAP clock.
- */
-int omap2_clk_deny_idle(struct clk *clk)
-{
-	struct clk_hw_omap *c;
-
-	if (__clk_get_flags(clk) & CLK_IS_BASIC)
-		return -EINVAL;
-
-	c = to_clk_hw_omap(__clk_get_hw(clk));
-	if (c->ops && c->ops->deny_idle)
-		c->ops->deny_idle(c);
-	return 0;
-}
-
-/**
- * omap2_clk_allow_idle - enable autoidle on an OMAP clock
- * @clk: struct clk * to enable autoidle for
- *
- * Enable autoidle on an OMAP clock.
- */
-int omap2_clk_allow_idle(struct clk *clk)
-{
-	struct clk_hw_omap *c;
-
-	if (__clk_get_flags(clk) & CLK_IS_BASIC)
-		return -EINVAL;
-
-	c = to_clk_hw_omap(__clk_get_hw(clk));
-	if (c->ops && c->ops->allow_idle)
-		c->ops->allow_idle(c);
-	return 0;
-}
-
-/**
- * omap2_clk_enable_init_clocks - prepare & enable a list of clocks
- * @clk_names: ptr to an array of strings of clock names to enable
- * @num_clocks: number of clock names in @clk_names
- *
- * Prepare and enable a list of clocks, named by @clk_names.  No
- * return value. XXX Deprecated; only needed until these clocks are
- * properly claimed and enabled by the drivers or core code that uses
- * them.  XXX What code disables & calls clk_put on these clocks?
- */
-void omap2_clk_enable_init_clocks(const char **clk_names, u8 num_clocks)
-{
-	struct clk *init_clk;
-	int i;
-
-	for (i = 0; i < num_clocks; i++) {
-		init_clk = clk_get(NULL, clk_names[i]);
-		if (WARN(IS_ERR(init_clk), "could not find init clock %s\n",
-				clk_names[i]))
-			continue;
-		clk_prepare_enable(init_clk);
-	}
-}
-
-const struct clk_hw_omap_ops clkhwops_wait = {
-	.find_idlest	= omap2_clk_dflt_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
-
-/**
- * omap2_clk_switch_mpurate_at_boot - switch ARM MPU rate by boot-time argument
- * @mpurate_ck_name: clk name of the clock to change rate
- *
- * Change the ARM MPU clock rate to the rate specified on the command
- * line, if one was specified.  @mpurate_ck_name should be
- * "virt_prcm_set" on OMAP2xxx and "dpll1_ck" on OMAP34xx/OMAP36xx.
- * XXX Does not handle voltage scaling - on OMAP2xxx this is currently
- * handled by the virt_prcm_set clock, but this should be handled by
- * the OPP layer.  XXX This is intended to be handled by the OPP layer
- * code in the near future and should be removed from the clock code.
- * Returns -EINVAL if 'mpurate' is zero or if clk_set_rate() rejects
- * the rate, -ENOENT if the struct clk referred to by @mpurate_ck_name
- * cannot be found, or 0 upon success.
- */
-int __init omap2_clk_switch_mpurate_at_boot(const char *mpurate_ck_name)
-{
-	struct clk *mpurate_ck;
-	int r;
-
-	if (!mpurate)
-		return -EINVAL;
-
-	mpurate_ck = clk_get(NULL, mpurate_ck_name);
-	if (WARN(IS_ERR(mpurate_ck), "Failed to get %s.\n", mpurate_ck_name))
-		return -ENOENT;
-
-	r = clk_set_rate(mpurate_ck, mpurate);
-	if (r < 0) {
-		WARN(1, "clock: %s: unable to set MPU rate to %d: %d\n",
-		     mpurate_ck_name, mpurate, r);
-		clk_put(mpurate_ck);
-		return -EINVAL;
-	}
-
-	calibrate_delay();
-	clk_put(mpurate_ck);
-
-	return 0;
-}
-
-/**
  * omap2_clk_print_new_rates - print summary of current clock tree rates
  * @hfclkin_ck_name: clk name for the off-chip HF oscillator
  * @core_ck_name: clk name for the on-chip CORE_CLK
@@ -801,29 +178,30 @@ void __init omap2_clk_print_new_rates(const char *hfclkin_ck_name,
  */
 void __init ti_clk_init_features(void)
 {
+	struct ti_clk_features features = { 0 };
 	/* Fint setup for DPLLs */
 	if (cpu_is_omap3430()) {
-		ti_clk_features.fint_min = OMAP3430_DPLL_FINT_BAND1_MIN;
-		ti_clk_features.fint_max = OMAP3430_DPLL_FINT_BAND2_MAX;
-		ti_clk_features.fint_band1_max = OMAP3430_DPLL_FINT_BAND1_MAX;
-		ti_clk_features.fint_band2_min = OMAP3430_DPLL_FINT_BAND2_MIN;
+		features.fint_min = OMAP3430_DPLL_FINT_BAND1_MIN;
+		features.fint_max = OMAP3430_DPLL_FINT_BAND2_MAX;
+		features.fint_band1_max = OMAP3430_DPLL_FINT_BAND1_MAX;
+		features.fint_band2_min = OMAP3430_DPLL_FINT_BAND2_MIN;
 	} else {
-		ti_clk_features.fint_min = OMAP3PLUS_DPLL_FINT_MIN;
-		ti_clk_features.fint_max = OMAP3PLUS_DPLL_FINT_MAX;
+		features.fint_min = OMAP3PLUS_DPLL_FINT_MIN;
+		features.fint_max = OMAP3PLUS_DPLL_FINT_MAX;
 	}
 
 	/* Bypass value setup for DPLLs */
 	if (cpu_is_omap24xx()) {
-		ti_clk_features.dpll_bypass_vals |=
+		features.dpll_bypass_vals |=
 			(1 << OMAP2XXX_EN_DPLL_LPBYPASS) |
 			(1 << OMAP2XXX_EN_DPLL_FRBYPASS);
 	} else if (cpu_is_omap34xx()) {
-		ti_clk_features.dpll_bypass_vals |=
+		features.dpll_bypass_vals |=
 			(1 << OMAP3XXX_EN_DPLL_LPBYPASS) |
 			(1 << OMAP3XXX_EN_DPLL_FRBYPASS);
 	} else if (soc_is_am33xx() || cpu_is_omap44xx() || soc_is_am43xx() ||
 		   soc_is_omap54xx() || soc_is_dra7xx()) {
-		ti_clk_features.dpll_bypass_vals |=
+		features.dpll_bypass_vals |=
 			(1 << OMAP4XXX_EN_DPLL_LPBYPASS) |
 			(1 << OMAP4XXX_EN_DPLL_FRBYPASS) |
 			(1 << OMAP4XXX_EN_DPLL_MNBYPASS);
@@ -831,7 +209,7 @@ void __init ti_clk_init_features(void)
 
 	/* Jitter correction only available on OMAP343X */
 	if (cpu_is_omap343x())
-		ti_clk_features.flags |= TI_CLK_DPLL_HAS_FREQSEL;
+		features.flags |= TI_CLK_DPLL_HAS_FREQSEL;
 
 	/* Idlest value for interface clocks.
 	 * 24xx uses 0 to indicate not ready, and 1 to indicate ready.
@@ -839,11 +217,13 @@ void __init ti_clk_init_features(void)
 	 * AM35xx uses both, depending on the module.
 	 */
 	if (cpu_is_omap24xx())
-		ti_clk_features.cm_idlest_val = OMAP24XX_CM_IDLEST_VAL;
+		features.cm_idlest_val = OMAP24XX_CM_IDLEST_VAL;
 	else if (cpu_is_omap34xx())
-		ti_clk_features.cm_idlest_val = OMAP34XX_CM_IDLEST_VAL;
+		features.cm_idlest_val = OMAP34XX_CM_IDLEST_VAL;
 
 	/* On OMAP3430 ES1.0, DPLL4 can't be re-programmed */
 	if (omap_rev() == OMAP3430_REV_ES1_0)
-		ti_clk_features.flags |= TI_CLK_DPLL4_DENY_REPROGRAM;
+		features.flags |= TI_CLK_DPLL4_DENY_REPROGRAM;
+
+	ti_clk_setup_features(&features);
 }
diff --git a/arch/arm/mach-omap2/clock.h b/arch/arm/mach-omap2/clock.h
index 652ed0ab86ec..67da640ba1c7 100644
--- a/arch/arm/mach-omap2/clock.h
+++ b/arch/arm/mach-omap2/clock.h
@@ -23,90 +23,6 @@
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 
-struct omap_clk {
-	u16				cpu;
-	struct clk_lookup		lk;
-};
-
-#define CLK(dev, con, ck)		\
-	{				\
-		.lk = {			\
-			.dev_id = dev,	\
-			.con_id = con,	\
-			.clk = ck,	\
-		},			\
-	}
-
-struct clockdomain;
-
-#define DEFINE_STRUCT_CLK(_name, _parent_array_name, _clkops_name)	\
-	static struct clk_core _name##_core = {			\
-		.name = #_name,					\
-		.hw = &_name##_hw.hw,				\
-		.parent_names = _parent_array_name,		\
-		.num_parents = ARRAY_SIZE(_parent_array_name),	\
-		.ops = &_clkops_name,				\
-	};							\
-	static struct clk _name = {				\
-		.core = &_name##_core,				\
-	};
-
-#define DEFINE_STRUCT_CLK_FLAGS(_name, _parent_array_name,	\
-				_clkops_name, _flags)		\
-	static struct clk_core _name##_core = {			\
-		.name = #_name,					\
-		.hw = &_name##_hw.hw,				\
-		.parent_names = _parent_array_name,		\
-		.num_parents = ARRAY_SIZE(_parent_array_name),	\
-		.ops = &_clkops_name,				\
-		.flags = _flags,				\
-	};							\
-	static struct clk _name = {				\
-		.core = &_name##_core,				\
-	};
-
-#define DEFINE_STRUCT_CLK_HW_OMAP(_name, _clkdm_name)		\
-	static struct clk_hw_omap _name##_hw = {		\
-		.hw = {						\
-			.clk = &_name,				\
-		},						\
-		.clkdm_name = _clkdm_name,			\
-	};
-
-#define DEFINE_CLK_OMAP_MUX(_name, _clkdm_name, _clksel,	\
-			    _clksel_reg, _clksel_mask,		\
-			    _parent_names, _ops)		\
-	static struct clk _name;				\
-	static struct clk_hw_omap _name##_hw = {		\
-		.hw = {						\
-			.clk = &_name,				\
-		},						\
-		.clksel		= _clksel,			\
-		.clksel_reg	= _clksel_reg,			\
-		.clksel_mask	= _clksel_mask,			\
-		.clkdm_name	= _clkdm_name,			\
-	};							\
-	DEFINE_STRUCT_CLK(_name, _parent_names, _ops);
-
-#define DEFINE_CLK_OMAP_MUX_GATE(_name, _clkdm_name, _clksel,	\
-				 _clksel_reg, _clksel_mask,	\
-				 _enable_reg, _enable_bit,	\
-				 _hwops, _parent_names, _ops)	\
-	static struct clk _name;				\
-	static struct clk_hw_omap _name##_hw = {		\
-		.hw = {						\
-			.clk = &_name,				\
-		},						\
-		.ops		= _hwops,			\
-		.enable_reg	= _enable_reg,			\
-		.enable_bit	= _enable_bit,			\
-		.clksel		= _clksel,			\
-		.clksel_reg	= _clksel_reg,			\
-		.clksel_mask	= _clksel_mask,			\
-		.clkdm_name	= _clkdm_name,			\
-	};							\
-	DEFINE_STRUCT_CLK(_name, _parent_names, _ops);
-
 /* struct clksel_rate.flags possibilities */
 #define RATE_IN_242X		(1 << 0)
 #define RATE_IN_243X		(1 << 1)
@@ -127,38 +43,6 @@ struct clockdomain;
 /* RATE_IN_3430ES2PLUS_36XX includes 34xx/35xx with ES >=2, and all 36xx/37xx */
 #define RATE_IN_3430ES2PLUS_36XX	(RATE_IN_3430ES2PLUS | RATE_IN_36XX)
 
-
-/**
- * struct clksel_rate - register bitfield values corresponding to clk divisors
- * @val: register bitfield value (shifted to bit 0)
- * @div: clock divisor corresponding to @val
- * @flags: (see "struct clksel_rate.flags possibilities" above)
- *
- * @val should match the value of a read from struct clk.clksel_reg
- * AND'ed with struct clk.clksel_mask, shifted right to bit 0.
- *
- * @div is the divisor that should be applied to the parent clock's rate
- * to produce the current clock's rate.
- */
-struct clksel_rate {
-	u32			val;
-	u8			div;
-	u16			flags;
-};
-
-/**
- * struct clksel - available parent clocks, and a pointer to their divisors
- * @parent: struct clk * to a possible parent clock
- * @rates: available divisors for this parent clock
- *
- * A struct clksel is always associated with one or more struct clks
- * and one or more struct clksel_rates.
- */
-struct clksel {
-	struct clk		 *parent;
-	const struct clksel_rate *rates;
-};
-
 /* CM_CLKSEL2_PLL.CORE_CLK_SRC bits (2XXX) */
 #define CORE_CLK_SRC_32K		0x0
 #define CORE_CLK_SRC_DPLL		0x1
@@ -180,105 +64,18 @@ struct clksel {
 #define OMAP4XXX_EN_DPLL_FRBYPASS		0x6
 #define OMAP4XXX_EN_DPLL_LOCKED			0x7
 
-u32 omap3_dpll_autoidle_read(struct clk_hw_omap *clk);
-void omap3_dpll_allow_idle(struct clk_hw_omap *clk);
-void omap3_dpll_deny_idle(struct clk_hw_omap *clk);
-void omap4_dpllmx_allow_gatectrl(struct clk_hw_omap *clk);
-void omap4_dpllmx_deny_gatectrl(struct clk_hw_omap *clk);
-
-void __init omap2_clk_disable_clkdm_control(void);
-
-/* clkt_clksel.c public functions */
-u32 omap2_clksel_round_rate_div(struct clk_hw_omap *clk,
-				unsigned long target_rate,
-				u32 *new_div);
-u8 omap2_clksel_find_parent_index(struct clk_hw *hw);
-unsigned long omap2_clksel_recalc(struct clk_hw *hw, unsigned long parent_rate);
-long omap2_clksel_round_rate(struct clk_hw *hw, unsigned long target_rate,
-				unsigned long *parent_rate);
-int omap2_clksel_set_rate(struct clk_hw *hw, unsigned long rate,
-				unsigned long parent_rate);
-int omap2_clksel_set_parent(struct clk_hw *hw, u8 field_val);
-
-/* clkt_iclk.c public functions */
-extern void omap2_clkt_iclk_allow_idle(struct clk_hw_omap *clk);
-extern void omap2_clkt_iclk_deny_idle(struct clk_hw_omap *clk);
-
-unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk);
-
-void omap2_clk_dflt_find_companion(struct clk_hw_omap *clk,
-				   void __iomem **other_reg,
-				   u8 *other_bit);
-void omap2_clk_dflt_find_idlest(struct clk_hw_omap *clk,
-				void __iomem **idlest_reg,
-				u8 *idlest_bit, u8 *idlest_val);
-int omap2_clk_enable_autoidle_all(void);
-int omap2_clk_allow_idle(struct clk *clk);
-int omap2_clk_deny_idle(struct clk *clk);
-int omap2_clk_switch_mpurate_at_boot(const char *mpurate_ck_name);
 void omap2_clk_print_new_rates(const char *hfclkin_ck_name,
 			       const char *core_ck_name,
 			       const char *mpu_ck_name);
 
-u32 omap2_clk_readl(struct clk_hw_omap *clk, void __iomem *reg);
-void omap2_clk_writel(u32 val, struct clk_hw_omap *clk, void __iomem *reg);
-
 extern u16 cpu_mask;
 
-/*
- * Clock features setup. Used instead of CPU type checks.
- */
-struct ti_clk_features {
-	u32 flags;
-	long fint_min;
-	long fint_max;
-	long fint_band1_max;
-	long fint_band2_min;
-	u8 dpll_bypass_vals;
-	u8 cm_idlest_val;
-};
-
-#define TI_CLK_DPLL_HAS_FREQSEL		(1 << 0)
-#define TI_CLK_DPLL4_DENY_REPROGRAM	(1 << 1)
-
-extern struct ti_clk_features ti_clk_features;
-
 extern const struct clkops clkops_omap2_dflt_wait;
 extern const struct clkops clkops_omap2_dflt;
 
 extern struct clk_functions omap2_clk_functions;
 
-extern const struct clksel_rate gpt_32k_rates[];
-extern const struct clksel_rate gpt_sys_rates[];
-extern const struct clksel_rate gfx_l3_rates[];
-extern const struct clksel_rate dsp_ick_rates[];
-
-extern const struct clk_hw_omap_ops clkhwops_iclk_wait;
-extern const struct clk_hw_omap_ops clkhwops_wait;
-extern const struct clk_hw_omap_ops clkhwops_omap3430es2_ssi_wait;
-extern const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait;
-extern const struct clk_hw_omap_ops clkhwops_omap3430es2_hsotgusb_wait;
-extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait;
-extern const struct clk_hw_omap_ops clkhwops_apll54;
-extern const struct clk_hw_omap_ops clkhwops_apll96;
-
-/* clksel_rate blocks shared between OMAP44xx and AM33xx */
-extern const struct clksel_rate div_1_0_rates[];
-extern const struct clksel_rate div3_1to4_rates[];
-extern const struct clksel_rate div_1_1_rates[];
-extern const struct clksel_rate div_1_2_rates[];
-extern const struct clksel_rate div_1_3_rates[];
-extern const struct clksel_rate div_1_4_rates[];
-extern const struct clksel_rate div31_1to31_rates[];
-
-extern int omap2_clkops_enable_clkdm(struct clk_hw *hw);
-extern void omap2_clkops_disable_clkdm(struct clk_hw *hw);
-
-struct regmap;
-
-int __init omap2_clk_provider_init(struct device_node *np, int index,
-				   struct regmap *syscon, void __iomem *mem);
-void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem);
+int __init omap2_clk_setup_ll_ops(void);
 
 void __init ti_clk_init_features(void);
 #endif
diff --git a/arch/arm/mach-omap2/clock2430.c b/arch/arm/mach-omap2/clock2430.c
deleted file mode 100644
index cef0c8d1de52..000000000000
--- a/arch/arm/mach-omap2/clock2430.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- * clock2430.c - OMAP2430-specific clock integration code
- *
- * Copyright (C) 2005-2008 Texas Instruments, Inc.
- * Copyright (C) 2004-2010 Nokia Corporation
- *
- * Contacts:
- * Richard Woodruff <r-woodruff2@ti.com>
- * Paul Walmsley
- *
- * Based on earlier work by Tuukka Tikkanen, Tony Lindgren,
- * Gordon McNutt and RidgeRun, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include "soc.h"
-#include "iomap.h"
-#include "clock.h"
-#include "clock2xxx.h"
-#include "cm2xxx.h"
-#include "cm-regbits-24xx.h"
-
-/**
- * omap2430_clk_i2chs_find_idlest - return CM_IDLEST info for 2430 I2CHS
- * @clk: struct clk * being enabled
- * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
- * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
- * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
- *
- * OMAP2430 I2CHS CM_IDLEST bits are in CM_IDLEST1_CORE, but the
- * CM_*CLKEN bits are in CM_{I,F}CLKEN2_CORE.  This custom function
- * passes back the correct CM_IDLEST register address for I2CHS
- * modules.  No return value.
- */
-static void omap2430_clk_i2chs_find_idlest(struct clk_hw_omap *clk,
-					   void __iomem **idlest_reg,
-					   u8 *idlest_bit,
-					   u8 *idlest_val)
-{
-	*idlest_reg = OMAP2430_CM_REGADDR(CORE_MOD, CM_IDLEST);
-	*idlest_bit = clk->enable_bit;
-	*idlest_val = OMAP24XX_CM_IDLEST_VAL;
-}
-
-/* 2430 I2CHS has non-standard IDLEST register */
-const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait = {
-	.find_idlest	= omap2430_clk_i2chs_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
diff --git a/arch/arm/mach-omap2/clock2xxx.c b/arch/arm/mach-omap2/clock2xxx.c
deleted file mode 100644
index b870f6a9e283..000000000000
--- a/arch/arm/mach-omap2/clock2xxx.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- * clock2xxx.c - OMAP2xxx-specific clock integration code
- *
- * Copyright (C) 2005-2008 Texas Instruments, Inc.
- * Copyright (C) 2004-2010 Nokia Corporation
- *
- * Contacts:
- * Richard Woodruff <r-woodruff2@ti.com>
- * Paul Walmsley
- *
- * Based on earlier work by Tuukka Tikkanen, Tony Lindgren,
- * Gordon McNutt and RidgeRun, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include "soc.h"
-#include "clock.h"
-#include "clock2xxx.h"
-#include "cm.h"
-#include "cm-regbits-24xx.h"
-
-struct clk_hw *dclk_hw;
-/*
- * Omap24xx specific clock functions
- */
-
-/*
- * Switch the MPU rate if specified on cmdline.  We cannot do this
- * early until cmdline is parsed.  XXX This should be removed from the
- * clock code and handled by the OPP layer code in the near future.
- */
-static int __init omap2xxx_clk_arch_init(void)
-{
-	int ret;
-
-	if (!cpu_is_omap24xx())
-		return 0;
-
-	ret = omap2_clk_switch_mpurate_at_boot("virt_prcm_set");
-	if (!ret)
-		omap2_clk_print_new_rates("sys_ck", "dpll_ck", "mpu_ck");
-
-	return ret;
-}
-
-omap_arch_initcall(omap2xxx_clk_arch_init);
-
-
diff --git a/arch/arm/mach-omap2/clock34xx.c b/arch/arm/mach-omap2/clock34xx.c
deleted file mode 100644
index 4596468e50ab..000000000000
--- a/arch/arm/mach-omap2/clock34xx.c
+++ /dev/null
@@ -1,138 +0,0 @@
-/*
- * OMAP3-specific clock framework functions
- *
- * Copyright (C) 2007-2008 Texas Instruments, Inc.
- * Copyright (C) 2007-2011 Nokia Corporation
- *
- * Paul Walmsley
- * Jouni Högander
- *
- * Parts of this code are based on code written by
- * Richard Woodruff, Tony Lindgren, Tuukka Tikkanen, Karthik Dasu,
- * Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include "clock.h"
-#include "clock34xx.h"
-#include "cm3xxx.h"
-#include "cm-regbits-34xx.h"
-
-/**
- * omap3430es2_clk_ssi_find_idlest - return CM_IDLEST info for SSI
- * @clk: struct clk * being enabled
- * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
- * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
- * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
- *
- * The OMAP3430ES2 SSI target CM_IDLEST bit is at a different shift
- * from the CM_{I,F}CLKEN bit.  Pass back the correct info via
- * @idlest_reg and @idlest_bit.  No return value.
- */
-static void omap3430es2_clk_ssi_find_idlest(struct clk_hw_omap *clk,
-					    void __iomem **idlest_reg,
-					    u8 *idlest_bit,
-					    u8 *idlest_val)
-{
-	u32 r;
-
-	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
-	*idlest_reg = (__force void __iomem *)r;
-	*idlest_bit = OMAP3430ES2_ST_SSI_IDLE_SHIFT;
-	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
-}
-const struct clk_hw_omap_ops clkhwops_omap3430es2_ssi_wait = {
-	.find_idlest	= omap3430es2_clk_ssi_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
-
-const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait = {
-	.allow_idle	= omap2_clkt_iclk_allow_idle,
-	.deny_idle	= omap2_clkt_iclk_deny_idle,
-	.find_idlest	= omap3430es2_clk_ssi_find_idlest,
-	.find_companion = omap2_clk_dflt_find_companion,
-};
-
-/**
- * omap3430es2_clk_dss_usbhost_find_idlest - CM_IDLEST info for DSS, USBHOST
- * @clk: struct clk * being enabled
- * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
- * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
- * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
- *
- * Some OMAP modules on OMAP3 ES2+ chips have both initiator and
- * target IDLEST bits.  For our purposes, we are concerned with the
- * target IDLEST bits, which exist at a different bit position than
- * the *CLKEN bit position for these modules (DSS and USBHOST) (The
- * default find_idlest code assumes that they are at the same
- * position.)  No return value.
- */
-static void omap3430es2_clk_dss_usbhost_find_idlest(struct clk_hw_omap *clk,
-						    void __iomem **idlest_reg,
-						    u8 *idlest_bit,
-						    u8 *idlest_val)
-{
-	u32 r;
-
-	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
-	*idlest_reg = (__force void __iomem *)r;
-	/* USBHOST_IDLE has same shift */
-	*idlest_bit = OMAP3430ES2_ST_DSS_IDLE_SHIFT;
-	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
-}
-
-const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait = {
-	.find_idlest	= omap3430es2_clk_dss_usbhost_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
-
-const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait = {
-	.allow_idle	= omap2_clkt_iclk_allow_idle,
-	.deny_idle	= omap2_clkt_iclk_deny_idle,
-	.find_idlest	= omap3430es2_clk_dss_usbhost_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
-
-/**
- * omap3430es2_clk_hsotgusb_find_idlest - return CM_IDLEST info for HSOTGUSB
- * @clk: struct clk * being enabled
- * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
- * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
- * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
- *
- * The OMAP3430ES2 HSOTGUSB target CM_IDLEST bit is at a different
- * shift from the CM_{I,F}CLKEN bit.  Pass back the correct info via
- * @idlest_reg and @idlest_bit.  No return value.
- */
-static void omap3430es2_clk_hsotgusb_find_idlest(struct clk_hw_omap *clk,
-						 void __iomem **idlest_reg,
-						 u8 *idlest_bit,
-						 u8 *idlest_val)
-{
-	u32 r;
-
-	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
-	*idlest_reg = (__force void __iomem *)r;
-	*idlest_bit = OMAP3430ES2_ST_HSOTGUSB_IDLE_SHIFT;
-	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
-}
-
-const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait = {
-	.allow_idle	= omap2_clkt_iclk_allow_idle,
-	.deny_idle	= omap2_clkt_iclk_deny_idle,
-	.find_idlest	= omap3430es2_clk_hsotgusb_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
-
-const struct clk_hw_omap_ops clkhwops_omap3430es2_hsotgusb_wait = {
-	.find_idlest	= omap3430es2_clk_hsotgusb_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
diff --git a/arch/arm/mach-omap2/clock34xx.h b/arch/arm/mach-omap2/clock34xx.h
deleted file mode 100644
index 084ba71b2b31..000000000000
--- a/arch/arm/mach-omap2/clock34xx.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * OMAP34xx clock function prototypes and macros
- *
- * Copyright (C) 2007-2010 Texas Instruments, Inc.
- * Copyright (C) 2007-2011 Nokia Corporation
- */
-
-#ifndef __ARCH_ARM_MACH_OMAP2_CLOCK34XX_H
-#define __ARCH_ARM_MACH_OMAP2_CLOCK34XX_H
-
-extern const struct clkops clkops_omap3430es2_ssi_wait;
-extern const struct clkops clkops_omap3430es2_iclk_ssi_wait;
-extern const struct clkops clkops_omap3430es2_hsotgusb_wait;
-extern const struct clkops clkops_omap3430es2_iclk_hsotgusb_wait;
-extern const struct clkops clkops_omap3430es2_dss_usbhost_wait;
-extern const struct clkops clkops_omap3430es2_iclk_dss_usbhost_wait;
-
-#endif
diff --git a/arch/arm/mach-omap2/clock3517.c b/arch/arm/mach-omap2/clock3517.c
deleted file mode 100644
index 4d79ae2c0241..000000000000
--- a/arch/arm/mach-omap2/clock3517.c
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- * OMAP3517/3505-specific clock framework functions
- *
- * Copyright (C) 2010 Texas Instruments, Inc.
- * Copyright (C) 2011 Nokia Corporation
- *
- * Ranjith Lohithakshan
- * Paul Walmsley
- *
- * Parts of this code are based on code written by
- * Richard Woodruff, Tony Lindgren, Tuukka Tikkanen, Karthik Dasu,
- * Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include "clock.h"
-#include "clock3517.h"
-#include "cm3xxx.h"
-#include "cm-regbits-34xx.h"
-
-/*
- * In AM35xx IPSS, the {ICK,FCK} enable bits for modules are exported
- * in the same register at a bit offset of 0x8. The EN_ACK for ICK is
- * at an offset of 4 from ICK enable bit.
- */
-#define AM35XX_IPSS_ICK_MASK			0xF
-#define AM35XX_IPSS_ICK_EN_ACK_OFFSET 		0x4
-#define AM35XX_IPSS_ICK_FCK_OFFSET		0x8
-#define AM35XX_IPSS_CLK_IDLEST_VAL		0
-
-/**
- * am35xx_clk_find_idlest - return clock ACK info for AM35XX IPSS
- * @clk: struct clk * being enabled
- * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
- * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
- * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
- *
- * The interface clocks on AM35xx IPSS reflects the clock idle status
- * in the enable register itsel at a bit offset of 4 from the enable
- * bit. A value of 1 indicates that clock is enabled.
- */
-static void am35xx_clk_find_idlest(struct clk_hw_omap *clk,
-					    void __iomem **idlest_reg,
-					    u8 *idlest_bit,
-					    u8 *idlest_val)
-{
-	*idlest_reg = (__force void __iomem *)(clk->enable_reg);
-	*idlest_bit = clk->enable_bit + AM35XX_IPSS_ICK_EN_ACK_OFFSET;
-	*idlest_val = AM35XX_IPSS_CLK_IDLEST_VAL;
-}
-
-/**
- * am35xx_clk_find_companion - find companion clock to @clk
- * @clk: struct clk * to find the companion clock of
- * @other_reg: void __iomem ** to return the companion clock CM_*CLKEN va in
- * @other_bit: u8 ** to return the companion clock bit shift in
- *
- * Some clocks don't have companion clocks.  For example, modules with
- * only an interface clock (such as HECC) don't have a companion
- * clock.  Right now, this code relies on the hardware exporting a bit
- * in the correct companion register that indicates that the
- * nonexistent 'companion clock' is active.  Future patches will
- * associate this type of code with per-module data structures to
- * avoid this issue, and remove the casts.  No return value.
- */
-static void am35xx_clk_find_companion(struct clk_hw_omap *clk,
-				      void __iomem **other_reg,
-				      u8 *other_bit)
-{
-	*other_reg = (__force void __iomem *)(clk->enable_reg);
-	if (clk->enable_bit & AM35XX_IPSS_ICK_MASK)
-		*other_bit = clk->enable_bit + AM35XX_IPSS_ICK_FCK_OFFSET;
-	else
-		*other_bit = clk->enable_bit - AM35XX_IPSS_ICK_FCK_OFFSET;
-}
-const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait = {
-	.find_idlest	= am35xx_clk_find_idlest,
-	.find_companion	= am35xx_clk_find_companion,
-};
-
-/**
- * am35xx_clk_ipss_find_idlest - return CM_IDLEST info for IPSS
- * @clk: struct clk * being enabled
- * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
- * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
- * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
- *
- * The IPSS target CM_IDLEST bit is at a different shift from the
- * CM_{I,F}CLKEN bit.  Pass back the correct info via @idlest_reg
- * and @idlest_bit.  No return value.
- */
-static void am35xx_clk_ipss_find_idlest(struct clk_hw_omap *clk,
-					    void __iomem **idlest_reg,
-					    u8 *idlest_bit,
-					    u8 *idlest_val)
-{
-	u32 r;
-
-	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
-	*idlest_reg = (__force void __iomem *)r;
-	*idlest_bit = AM35XX_ST_IPSS_SHIFT;
-	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
-}
-
-const struct clk_hw_omap_ops clkhwops_am35xx_ipss_wait = {
-	.allow_idle	= omap2_clkt_iclk_allow_idle,
-	.deny_idle	= omap2_clkt_iclk_deny_idle,
-	.find_idlest	= am35xx_clk_ipss_find_idlest,
-	.find_companion	= omap2_clk_dflt_find_companion,
-};
diff --git a/arch/arm/mach-omap2/clock3517.h b/arch/arm/mach-omap2/clock3517.h
deleted file mode 100644
index ca5e5a64c2e2..000000000000
--- a/arch/arm/mach-omap2/clock3517.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * OMAP3517/3505 clock function prototypes and macros
- *
- * Copyright (C) 2010 Texas Instruments, Inc.
- * Copyright (C) 2010 Nokia Corporation
- */
-
-#ifndef __ARCH_ARM_MACH_OMAP2_CLOCK3517_H
-#define __ARCH_ARM_MACH_OMAP2_CLOCK3517_H
-
-extern const struct clkops clkops_am35xx_ipss_module_wait;
-extern const struct clkops clkops_am35xx_ipss_wait;
-
-#endif
diff --git a/arch/arm/mach-omap2/clock36xx.c b/arch/arm/mach-omap2/clock36xx.c
deleted file mode 100644
index 91ccb962e09e..000000000000
--- a/arch/arm/mach-omap2/clock36xx.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * OMAP36xx-specific clkops
- *
- * Copyright (C) 2010 Texas Instruments, Inc.
- * Copyright (C) 2010 Nokia Corporation
- *
- * Mike Turquette
- * Vijaykumar GN
- * Paul Walmsley
- *
- * Parts of this code are based on code written by
- * Richard Woodruff, Tony Lindgren, Tuukka Tikkanen, Karthik Dasu,
- * Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/clk.h>
-#include <linux/clk-provider.h>
-#include <linux/io.h>
-
-#include "clock.h"
-#include "clock36xx.h"
-#define to_clk_divider(_hw) container_of(_hw, struct clk_divider, hw)
-
-/**
- * omap36xx_pwrdn_clk_enable_with_hsdiv_restore - enable clocks suffering
- *         from HSDivider PWRDN problem Implements Errata ID: i556.
- * @clk: DPLL output struct clk
- *
- * 3630 only: dpll3_m3_ck, dpll4_m2_ck, dpll4_m3_ck, dpll4_m4_ck,
- * dpll4_m5_ck & dpll4_m6_ck dividers gets loaded with reset
- * valueafter their respective PWRDN bits are set.  Any dummy write
- * (Any other value different from the Read value) to the
- * corresponding CM_CLKSEL register will refresh the dividers.
- */
-int omap36xx_pwrdn_clk_enable_with_hsdiv_restore(struct clk_hw *clk)
-{
-	struct clk_divider *parent;
-	struct clk_hw *parent_hw;
-	u32 dummy_v, orig_v;
-	struct clk_hw_omap *omap_clk = to_clk_hw_omap(clk);
-	int ret;
-
-	/* Clear PWRDN bit of HSDIVIDER */
-	ret = omap2_dflt_clk_enable(clk);
-
-	parent_hw = __clk_get_hw(__clk_get_parent(clk->clk));
-	parent = to_clk_divider(parent_hw);
-
-	/* Restore the dividers */
-	if (!ret) {
-		orig_v = omap2_clk_readl(omap_clk, parent->reg);
-		dummy_v = orig_v;
-
-		/* Write any other value different from the Read value */
-		dummy_v ^= (1 << parent->shift);
-		omap2_clk_writel(dummy_v, omap_clk, parent->reg);
-
-		/* Write the original divider */
-		omap2_clk_writel(orig_v, omap_clk, parent->reg);
-	}
-
-	return ret;
-}
diff --git a/arch/arm/mach-omap2/clock36xx.h b/arch/arm/mach-omap2/clock36xx.h
deleted file mode 100644
index 945bb7f083e9..000000000000
--- a/arch/arm/mach-omap2/clock36xx.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * OMAP36xx clock function prototypes and macros
- *
- * Copyright (C) 2010 Texas Instruments, Inc.
- * Copyright (C) 2010 Nokia Corporation
- */
-
-#ifndef __ARCH_ARM_MACH_OMAP2_CLOCK36XX_H
-#define __ARCH_ARM_MACH_OMAP2_CLOCK36XX_H
-
-extern int omap36xx_pwrdn_clk_enable_with_hsdiv_restore(struct clk_hw *hw);
-
-#endif
diff --git a/arch/arm/mach-omap2/clock3xxx.c b/arch/arm/mach-omap2/clock3xxx.c
deleted file mode 100644
index a9e86db5daf9..000000000000
--- a/arch/arm/mach-omap2/clock3xxx.c
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- * OMAP3-specific clock framework functions
- *
- * Copyright (C) 2007-2008 Texas Instruments, Inc.
- * Copyright (C) 2007-2010 Nokia Corporation
- *
- * Paul Walmsley
- * Jouni Högander
- *
- * Parts of this code are based on code written by
- * Richard Woodruff, Tony Lindgren, Tuukka Tikkanen, Karthik Dasu
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include "soc.h"
-#include "clock.h"
-#include "clock3xxx.h"
-#include "prm2xxx_3xxx.h"
-#include "prm-regbits-34xx.h"
-#include "cm2xxx_3xxx.h"
-#include "cm-regbits-34xx.h"
-
-/*
- * DPLL5_FREQ_FOR_USBHOST: USBHOST and USBTLL are the only clocks
- * that are sourced by DPLL5, and both of these require this clock
- * to be at 120 MHz for proper operation.
- */
-#define DPLL5_FREQ_FOR_USBHOST		120000000
-
-/* needed by omap3_core_dpll_m2_set_rate() */
-struct clk *sdrc_ick_p, *arm_fck_p;
-
-/**
- * omap3_dpll4_set_rate - set rate for omap3 per-dpll
- * @hw: clock to change
- * @rate: target rate for clock
- * @parent_rate: rate of the parent clock
- *
- * Check if the current SoC supports the per-dpll reprogram operation
- * or not, and then do the rate change if supported. Returns -EINVAL
- * if not supported, 0 for success, and potential error codes from the
- * clock rate change.
- */
-int omap3_dpll4_set_rate(struct clk_hw *hw, unsigned long rate,
-				unsigned long parent_rate)
-{
-	/*
-	 * According to the 12-5 CDP code from TI, "Limitation 2.5"
-	 * on 3430ES1 prevents us from changing DPLL multipliers or dividers
-	 * on DPLL4.
-	 */
-	if (ti_clk_features.flags & TI_CLK_DPLL4_DENY_REPROGRAM) {
-		pr_err("clock: DPLL4 cannot change rate due to silicon 'Limitation 2.5' on 3430ES1.\n");
-		return -EINVAL;
-	}
-
-	return omap3_noncore_dpll_set_rate(hw, rate, parent_rate);
-}
-
-/**
- * omap3_dpll4_set_rate_and_parent - set rate and parent for omap3 per-dpll
- * @hw: clock to change
- * @rate: target rate for clock
- * @parent_rate: rate of the parent clock
- * @index: parent index, 0 - reference clock, 1 - bypass clock
- *
- * Check if the current SoC support the per-dpll reprogram operation
- * or not, and then do the rate + parent change if supported. Returns
- * -EINVAL if not supported, 0 for success, and potential error codes
- * from the clock rate change.
- */
-int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
-				    unsigned long parent_rate, u8 index)
-{
-	if (ti_clk_features.flags & TI_CLK_DPLL4_DENY_REPROGRAM) {
-		pr_err("clock: DPLL4 cannot change rate due to silicon 'Limitation 2.5' on 3430ES1.\n");
-		return -EINVAL;
-	}
-
-	return omap3_noncore_dpll_set_rate_and_parent(hw, rate, parent_rate,
-						      index);
-}
-
-void __init omap3_clk_lock_dpll5(void)
-{
-	struct clk *dpll5_clk;
-	struct clk *dpll5_m2_clk;
-
-	dpll5_clk = clk_get(NULL, "dpll5_ck");
-	clk_set_rate(dpll5_clk, DPLL5_FREQ_FOR_USBHOST);
-	clk_prepare_enable(dpll5_clk);
-
-	/* Program dpll5_m2_clk divider for no division */
-	dpll5_m2_clk = clk_get(NULL, "dpll5_m2_ck");
-	clk_prepare_enable(dpll5_m2_clk);
-	clk_set_rate(dpll5_m2_clk, DPLL5_FREQ_FOR_USBHOST);
-
-	clk_disable_unprepare(dpll5_m2_clk);
-	clk_disable_unprepare(dpll5_clk);
-	return;
-}
-
-/* Common clock code */
-
-/*
- * Switch the MPU rate if specified on cmdline.  We cannot do this
- * early until cmdline is parsed.  XXX This should be removed from the
- * clock code and handled by the OPP layer code in the near future.
- */
-static int __init omap3xxx_clk_arch_init(void)
-{
-	int ret;
-
-	if (!cpu_is_omap34xx())
-		return 0;
-
-	ret = omap2_clk_switch_mpurate_at_boot("dpll1_ck");
-	if (!ret)
-		omap2_clk_print_new_rates("osc_sys_ck", "core_ck", "arm_fck");
-
-	return ret;
-}
-
-omap_arch_initcall(omap3xxx_clk_arch_init);
-
-
diff --git a/arch/arm/mach-omap2/clock44xx.h b/arch/arm/mach-omap2/clock44xx.h
deleted file mode 100644
index 287a46f78d97..000000000000
--- a/arch/arm/mach-omap2/clock44xx.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * OMAP4 clock function prototypes and macros
- *
- * Copyright (C) 2009 Texas Instruments, Inc.
- * Copyright (C) 2010 Nokia Corporation
- */
-
-#ifndef __ARCH_ARM_MACH_OMAP2_CLOCK44XX_H
-#define __ARCH_ARM_MACH_OMAP2_CLOCK44XX_H
-
-/*
- * OMAP4430_REGM4XEN_MULT: If the CM_CLKMODE_DPLL_ABE.DPLL_REGM4XEN bit is
- *    set, then the DPLL's lock frequency is multiplied by 4 (OMAP4430 TRM
- *    vV Section 3.6.3.3.1 "DPLLs Output Clocks Parameters")
- */
-#define OMAP4430_REGM4XEN_MULT	4
-
-int omap4xxx_clk_init(void);
-
-#endif
diff --git a/arch/arm/mach-omap2/clock_common_data.c b/arch/arm/mach-omap2/clock_common_data.c
deleted file mode 100644
index 61b60dfb14ce..000000000000
--- a/arch/arm/mach-omap2/clock_common_data.c
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- *  linux/arch/arm/mach-omap2/clock_common_data.c
- *
- *  Copyright (C) 2005-2009 Texas Instruments, Inc.
- *  Copyright (C) 2004-2009 Nokia Corporation
- *
- *  Contacts:
- *  Richard Woodruff <r-woodruff2@ti.com>
- *  Paul Walmsley
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This file contains clock data that is common to both the OMAP2xxx and
- * OMAP3xxx clock definition files.
- */
-
-#include "clock.h"
-
-/* clksel_rate data common to 24xx/343x */
-const struct clksel_rate gpt_32k_rates[] = {
-	 { .div = 1, .val = 0, .flags = RATE_IN_24XX | RATE_IN_3XXX },
-	 { .div = 0 }
-};
-
-const struct clksel_rate gpt_sys_rates[] = {
-	 { .div = 1, .val = 1, .flags = RATE_IN_24XX | RATE_IN_3XXX },
-	 { .div = 0 }
-};
-
-const struct clksel_rate gfx_l3_rates[] = {
-	{ .div = 1, .val = 1, .flags = RATE_IN_24XX | RATE_IN_3XXX },
-	{ .div = 2, .val = 2, .flags = RATE_IN_24XX | RATE_IN_3XXX },
-	{ .div = 3, .val = 3, .flags = RATE_IN_243X | RATE_IN_3XXX },
-	{ .div = 4, .val = 4, .flags = RATE_IN_243X | RATE_IN_3XXX },
-	{ .div = 0 }
-};
-
-const struct clksel_rate dsp_ick_rates[] = {
-	{ .div = 1, .val = 1, .flags = RATE_IN_24XX },
-	{ .div = 2, .val = 2, .flags = RATE_IN_24XX },
-	{ .div = 3, .val = 3, .flags = RATE_IN_243X },
-	{ .div = 0 },
-};
-
-
-/* clksel_rate blocks shared between OMAP44xx and AM33xx */
-
-const struct clksel_rate div_1_0_rates[] = {
-	{ .div = 1, .val = 0, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 0 },
-};
-
-const struct clksel_rate div3_1to4_rates[] = {
-	{ .div = 1, .val = 0, .flags = RATE_IN_4430 },
-	{ .div = 2, .val = 1, .flags = RATE_IN_4430 },
-	{ .div = 4, .val = 2, .flags = RATE_IN_4430 },
-	{ .div = 0 },
-};
-
-const struct clksel_rate div_1_1_rates[] = {
-	{ .div = 1, .val = 1, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 0 },
-};
-
-const struct clksel_rate div_1_2_rates[] = {
-	{ .div = 1, .val = 2, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 0 },
-};
-
-const struct clksel_rate div_1_3_rates[] = {
-	{ .div = 1, .val = 3, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 0 },
-};
-
-const struct clksel_rate div_1_4_rates[] = {
-	{ .div = 1, .val = 4, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 0 },
-};
-
-const struct clksel_rate div31_1to31_rates[] = {
-	{ .div = 1, .val = 1, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 2, .val = 2, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 3, .val = 3, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 4, .val = 4, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 5, .val = 5, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 6, .val = 6, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 7, .val = 7, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 8, .val = 8, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 9, .val = 9, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 10, .val = 10, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 11, .val = 11, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 12, .val = 12, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 13, .val = 13, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 14, .val = 14, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 15, .val = 15, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 16, .val = 16, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 17, .val = 17, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 18, .val = 18, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 19, .val = 19, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 20, .val = 20, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 21, .val = 21, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 22, .val = 22, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 23, .val = 23, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 24, .val = 24, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 25, .val = 25, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 26, .val = 26, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 27, .val = 27, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 28, .val = 28, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 29, .val = 29, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 30, .val = 30, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 31, .val = 31, .flags = RATE_IN_4430 | RATE_IN_AM33XX },
-	{ .div = 0 },
-};
diff --git a/arch/arm/mach-omap2/clockdomain.h b/arch/arm/mach-omap2/clockdomain.h
index 77bab5fb6814..2c398ce1a0f2 100644
--- a/arch/arm/mach-omap2/clockdomain.h
+++ b/arch/arm/mach-omap2/clockdomain.h
@@ -216,7 +216,8 @@ extern void __init omap242x_clockdomains_init(void);
 extern void __init omap243x_clockdomains_init(void);
 extern void __init omap3xxx_clockdomains_init(void);
 extern void __init am33xx_clockdomains_init(void);
-extern void __init ti81xx_clockdomains_init(void);
+extern void __init ti814x_clockdomains_init(void);
+extern void __init ti816x_clockdomains_init(void);
 extern void __init omap44xx_clockdomains_init(void);
 extern void __init omap54xx_clockdomains_init(void);
 extern void __init dra7xx_clockdomains_init(void);
diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c
index 57d5df0c1fbd..7581e036bda6 100644
--- a/arch/arm/mach-omap2/clockdomains7xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains7xx_data.c
@@ -331,7 +331,7 @@ static struct clockdomain l4per2_7xx_clkdm = {
 	.dep_bit	  = DRA7XX_L4PER2_STATDEP_SHIFT,
 	.wkdep_srcs	  = l4per2_wkup_sleep_deps,
 	.sleepdep_srcs	  = l4per2_wkup_sleep_deps,
-	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+	.flags		  = CLKDM_CAN_SWSUP,
 };
 
 static struct clockdomain mpu0_7xx_clkdm = {
diff --git a/arch/arm/mach-omap2/clockdomains81xx_data.c b/arch/arm/mach-omap2/clockdomains81xx_data.c
index ce2a82001d0d..53442c86a820 100644
--- a/arch/arm/mach-omap2/clockdomains81xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains81xx_data.c
@@ -165,7 +165,24 @@ static struct clockdomain default_l3_slow_816x_clkdm = {
 	.flags		= CLKDM_CAN_SWSUP,
 };
 
-static struct clockdomain *clockdomains_ti81xx[] __initdata = {
+static struct clockdomain *clockdomains_ti814x[] __initdata = {
+	&alwon_l3_slow_81xx_clkdm,
+	&alwon_l3_med_81xx_clkdm,
+	&alwon_l3_fast_81xx_clkdm,
+	&alwon_ethernet_81xx_clkdm,
+	&mmu_81xx_clkdm,
+	&mmu_cfg_81xx_clkdm,
+	NULL,
+};
+
+void __init ti814x_clockdomains_init(void)
+{
+	clkdm_register_platform_funcs(&am33xx_clkdm_operations);
+	clkdm_register_clkdms(clockdomains_ti814x);
+	clkdm_complete_init();
+}
+
+static struct clockdomain *clockdomains_ti816x[] __initdata = {
 	&alwon_mpu_816x_clkdm,
 	&alwon_l3_slow_81xx_clkdm,
 	&alwon_l3_med_81xx_clkdm,
@@ -185,10 +202,10 @@ static struct clockdomain *clockdomains_ti81xx[] __initdata = {
 	NULL,
 };
 
-void __init ti81xx_clockdomains_init(void)
+void __init ti816x_clockdomains_init(void)
 {
 	clkdm_register_platform_funcs(&am33xx_clkdm_operations);
-	clkdm_register_clkdms(clockdomains_ti81xx);
+	clkdm_register_clkdms(clockdomains_ti816x);
 	clkdm_complete_init();
 }
 #endif
diff --git a/arch/arm/mach-omap2/common.c b/arch/arm/mach-omap2/common.c
index eae6a0e87c90..484cdadfb187 100644
--- a/arch/arm/mach-omap2/common.c
+++ b/arch/arm/mach-omap2/common.c
@@ -30,4 +30,5 @@ int __weak omap_secure_ram_reserve_memblock(void)
 void __init omap_reserve(void)
 {
 	omap_secure_ram_reserve_memblock();
+	omap_barrier_reserve_memblock();
 }
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index cf3cf22ecd42..92e92cfc2775 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -189,6 +189,15 @@ static inline void omap44xx_restart(enum reboot_mode mode, const char *cmd)
 }
 #endif
 
+#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER
+void omap_barrier_reserve_memblock(void);
+void omap_barriers_init(void);
+#else
+static inline void omap_barrier_reserve_memblock(void)
+{
+}
+#endif
+
 /* This gets called from mach-omap2/io.c, do not call this */
 void __init omap2_set_globals_tap(u32 class, void __iomem *tap);
 
@@ -198,6 +207,7 @@ void __init omap3_map_io(void);
 void __init am33xx_map_io(void);
 void __init omap4_map_io(void);
 void __init omap5_map_io(void);
+void __init dra7xx_map_io(void);
 void __init ti81xx_map_io(void);
 
 /**
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index f008930277ed..cf5855174c93 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -652,6 +652,7 @@ static const struct of_device_id omap_scrm_dt_match_table[] = {
 	{ .compatible = "ti,am4-scm", .data = &ctrl_data },
 	{ .compatible = "ti,omap2-scm", .data = &omap2_ctrl_data },
 	{ .compatible = "ti,omap3-scm", .data = &omap2_ctrl_data },
+	{ .compatible = "ti,dm814-scm", .data = &ctrl_data },
 	{ .compatible = "ti,dm816-scrm", .data = &ctrl_data },
 	{ .compatible = "ti,omap4-scm-core", .data = &ctrl_data },
 	{ .compatible = "ti,omap5-scm-core", .data = &ctrl_data },
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index e1a56d87599e..1ed4be184a29 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -117,7 +117,6 @@ static void omap2_show_dma_caps(void)
 	u8 revision = dma_read(REVISION, 0) & 0xff;
 	printk(KERN_INFO "OMAP DMA hardware revision %d.%d\n",
 				revision >> 4, revision & 0xf);
-	return;
 }
 
 static unsigned configure_dma_errata(void)
diff --git a/arch/arm/mach-omap2/include/mach/barriers.h b/arch/arm/mach-omap2/include/mach/barriers.h
deleted file mode 100644
index 1c582a8592b9..000000000000
--- a/arch/arm/mach-omap2/include/mach/barriers.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * OMAP memory barrier header.
- *
- * Copyright (C) 2011 Texas Instruments, Inc.
- *  Santosh Shilimkar <santosh.shilimkar@ti.com>
- *  Richard Woodruff <r-woodruff2@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef __MACH_BARRIERS_H
-#define __MACH_BARRIERS_H
-
-#include <asm/outercache.h>
-
-extern void omap_bus_sync(void);
-
-#define rmb()		dsb()
-#define wmb()		do { dsb(); outer_sync(); omap_bus_sync(); } while (0)
-#define mb()		wmb()
-
-#endif	/* __MACH_BARRIERS_H */
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 820dde8b5b04..980c9372e6fd 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -37,7 +37,6 @@
 #include "clock.h"
 #include "clock2xxx.h"
 #include "clock3xxx.h"
-#include "clock44xx.h"
 #include "omap-pm.h"
 #include "sdrc.h"
 #include "control.h"
@@ -236,7 +235,7 @@ static struct map_desc omap44xx_io_desc[] __initdata = {
 };
 #endif
 
-#if defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX)
+#ifdef CONFIG_SOC_OMAP5
 static struct map_desc omap54xx_io_desc[] __initdata = {
 	{
 		.virtual	= L3_54XX_VIRT,
@@ -265,6 +264,53 @@ static struct map_desc omap54xx_io_desc[] __initdata = {
 };
 #endif
 
+#ifdef CONFIG_SOC_DRA7XX
+static struct map_desc dra7xx_io_desc[] __initdata = {
+	{
+		.virtual	= L4_CFG_MPU_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L4_CFG_MPU_DRA7XX_PHYS),
+		.length		= L4_CFG_MPU_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+	{
+		.virtual	= L3_MAIN_SN_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L3_MAIN_SN_DRA7XX_PHYS),
+		.length		= L3_MAIN_SN_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+	{
+		.virtual	= L4_PER1_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L4_PER1_DRA7XX_PHYS),
+		.length		= L4_PER1_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+	{
+		.virtual	= L4_PER2_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L4_PER2_DRA7XX_PHYS),
+		.length		= L4_PER2_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+	{
+		.virtual	= L4_PER3_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L4_PER3_DRA7XX_PHYS),
+		.length		= L4_PER3_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+	{
+		.virtual	= L4_CFG_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L4_CFG_DRA7XX_PHYS),
+		.length		= L4_CFG_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+	{
+		.virtual	= L4_WKUP_DRA7XX_VIRT,
+		.pfn		= __phys_to_pfn(L4_WKUP_DRA7XX_PHYS),
+		.length		= L4_WKUP_DRA7XX_SIZE,
+		.type		= MT_DEVICE,
+	},
+};
+#endif
+
 #ifdef CONFIG_SOC_OMAP2420
 void __init omap242x_map_io(void)
 {
@@ -306,13 +352,22 @@ void __init am33xx_map_io(void)
 void __init omap4_map_io(void)
 {
 	iotable_init(omap44xx_io_desc, ARRAY_SIZE(omap44xx_io_desc));
+	omap_barriers_init();
 }
 #endif
 
-#if defined(CONFIG_SOC_OMAP5) ||  defined(CONFIG_SOC_DRA7XX)
+#ifdef CONFIG_SOC_OMAP5
 void __init omap5_map_io(void)
 {
 	iotable_init(omap54xx_io_desc, ARRAY_SIZE(omap54xx_io_desc));
+	omap_barriers_init();
+}
+#endif
+
+#ifdef CONFIG_SOC_DRA7XX
+void __init dra7xx_map_io(void)
+{
+	iotable_init(dra7xx_io_desc, ARRAY_SIZE(dra7xx_io_desc));
 }
 #endif
 /*
@@ -554,11 +609,11 @@ void __init ti814x_init_early(void)
 	omap2_prcm_base_init();
 	omap3xxx_voltagedomains_init();
 	omap3xxx_powerdomains_init();
-	ti81xx_clockdomains_init();
-	ti81xx_hwmod_init();
+	ti814x_clockdomains_init();
+	dm814x_hwmod_init();
 	omap_hwmod_init_postsetup();
 	if (of_have_populated_dt())
-		omap_clk_soc_init = ti81xx_dt_clk_init;
+		omap_clk_soc_init = dm814x_dt_clk_init;
 }
 
 void __init ti816x_init_early(void)
@@ -571,11 +626,11 @@ void __init ti816x_init_early(void)
 	omap2_prcm_base_init();
 	omap3xxx_voltagedomains_init();
 	omap3xxx_powerdomains_init();
-	ti81xx_clockdomains_init();
-	ti81xx_hwmod_init();
+	ti816x_clockdomains_init();
+	dm816x_hwmod_init();
 	omap_hwmod_init_postsetup();
 	if (of_have_populated_dt())
-		omap_clk_soc_init = ti81xx_dt_clk_init;
+		omap_clk_soc_init = dm816x_dt_clk_init;
 }
 #endif
 
@@ -723,6 +778,8 @@ int __init omap_clk_init(void)
 
 	ti_clk_init_features();
 
+	omap2_clk_setup_ll_ops();
+
 	if (of_have_populated_dt()) {
 		ret = omap_control_init();
 		if (ret)
diff --git a/arch/arm/mach-omap2/iomap.h b/arch/arm/mach-omap2/iomap.h
index cce2b65039f1..6191d244438a 100644
--- a/arch/arm/mach-omap2/iomap.h
+++ b/arch/arm/mach-omap2/iomap.h
@@ -194,3 +194,66 @@
 #define L4_PER_54XX_PHYS	L4_PER_54XX_BASE /* 0x48000000 --> 0xfa000000 */
 #define L4_PER_54XX_VIRT	(L4_PER_54XX_PHYS + OMAP2_L4_IO_OFFSET)
 #define L4_PER_54XX_SIZE	SZ_4M
+
+/*
+ * ----------------------------------------------------------------------------
+ * DRA7xx specific IO mapping
+ * ----------------------------------------------------------------------------
+ */
+/*
+ * L3_MAIN_SN_DRA7XX_PHYS 0x44000000 --> 0xf8000000
+ * The overall space is 24MiB (0x4400_0000<->0x457F_FFFF), but mapping
+ * everything is just inefficient, since, there are too many address holes.
+ */
+#define L3_MAIN_SN_DRA7XX_PHYS		L3_MAIN_SN_DRA7XX_BASE
+#define L3_MAIN_SN_DRA7XX_VIRT		(L3_MAIN_SN_DRA7XX_PHYS + OMAP4_L3_IO_OFFSET)
+#define L3_MAIN_SN_DRA7XX_SIZE		SZ_1M
+
+/*
+ * L4_PER1_DRA7XX_PHYS	(0x4800_000<>0x480D_2FFF) -> 0.82MiB (alloc 1MiB)
+ *	(0x48000000<->0x48100000) <=> (0xFA000000<->0xFA100000)
+ */
+#define L4_PER1_DRA7XX_PHYS		L4_PER1_DRA7XX_BASE
+#define L4_PER1_DRA7XX_VIRT		(L4_PER1_DRA7XX_PHYS + OMAP2_L4_IO_OFFSET)
+#define L4_PER1_DRA7XX_SIZE		SZ_1M
+
+/*
+ * L4_CFG_MPU_DRA7XX_PHYS	(0x48210000<>0x482A_F2FF) -> 0.62MiB (alloc 1MiB)
+ *	(0x48210000<->0x48310000) <=> (0xFA210000<->0xFA310000)
+ * NOTE: This is a bit of an orphan memory map sitting isolated in TRM
+ */
+#define L4_CFG_MPU_DRA7XX_PHYS		L4_CFG_MPU_DRA7XX_BASE
+#define L4_CFG_MPU_DRA7XX_VIRT		(L4_CFG_MPU_DRA7XX_PHYS + OMAP2_L4_IO_OFFSET)
+#define L4_CFG_MPU_DRA7XX_SIZE		SZ_1M
+
+/*
+ * L4_PER2_DRA7XX_PHYS	(0x4840_0000<>0x4848_8FFF) -> .53MiB (alloc 1MiB)
+ *	(0x48400000<->0x48500000) <=> (0xFA400000<->0xFA500000)
+ */
+#define L4_PER2_DRA7XX_PHYS		L4_PER2_DRA7XX_BASE
+#define L4_PER2_DRA7XX_VIRT		(L4_PER2_DRA7XX_PHYS + OMAP2_L4_IO_OFFSET)
+#define L4_PER2_DRA7XX_SIZE		SZ_1M
+
+/*
+ * L4_PER3_DRA7XX_PHYS	(0x4880_0000<>0x489E_0FFF) -> 1.87MiB (alloc 2MiB)
+ *	(0x48800000<->0x48A00000) <=> (0xFA800000<->0xFAA00000)
+ */
+#define L4_PER3_DRA7XX_PHYS		L4_PER3_DRA7XX_BASE
+#define L4_PER3_DRA7XX_VIRT		(L4_PER3_DRA7XX_PHYS + OMAP2_L4_IO_OFFSET)
+#define L4_PER3_DRA7XX_SIZE		SZ_2M
+
+/*
+ * L4_CFG_DRA7XX_PHYS	(0x4A00_0000<>0x4A22_BFFF) ->2.17MiB (alloc 3MiB)?
+ *	(0x4A000000<->0x4A300000) <=> (0xFC000000<->0xFC300000)
+ */
+#define L4_CFG_DRA7XX_PHYS		L4_CFG_DRA7XX_BASE
+#define L4_CFG_DRA7XX_VIRT		(L4_CFG_DRA7XX_PHYS + OMAP2_L4_IO_OFFSET)
+#define L4_CFG_DRA7XX_SIZE		(SZ_1M + SZ_2M)
+
+/*
+ * L4_WKUP_DRA7XX_PHYS	(0x4AE0_0000<>0x4AE3_EFFF) -> .24 mb (alloc 1MiB)?
+ *	(0x4AE00000<->4AF00000)	<=> (0xFCE00000<->0xFCF00000)
+ */
+#define L4_WKUP_DRA7XX_PHYS		L4_WKUP_DRA7XX_BASE
+#define L4_WKUP_DRA7XX_VIRT		(L4_WKUP_DRA7XX_PHYS + OMAP2_L4_IO_OFFSET)
+#define L4_WKUP_DRA7XX_SIZE		SZ_1M
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index 4068350f9059..8867eb4025bf 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/of.h>
-#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -63,15 +62,5 @@ static int __init omap_iommu_init(void)
 
 	return omap_hwmod_for_each_by_class("mmu", omap_iommu_dev_init, NULL);
 }
-/* must be ready before omap3isp is probed */
 omap_subsys_initcall(omap_iommu_init);
-
-static void __exit omap_iommu_exit(void)
-{
-	/* Do nothing */
-}
-module_exit(omap_iommu_exit);
-
-MODULE_AUTHOR("Hiroshi DOYU");
-MODULE_DESCRIPTION("omap iommu: omap device registration");
-MODULE_LICENSE("GPL v2");
+/* must be ready before omap3isp is probed */
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 79f49d904a06..65024af169d3 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -105,7 +105,7 @@ static void dummy_cpu_resume(void)
 static void dummy_scu_prepare(unsigned int cpu_id, unsigned int cpu_state)
 {}
 
-struct cpu_pm_ops omap_pm_ops = {
+static struct cpu_pm_ops omap_pm_ops = {
 	.finish_suspend		= default_finish_suspend,
 	.resume			= dummy_cpu_resume,
 	.scu_prepare		= dummy_scu_prepare,
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 8e52621b5a6b..e1d2e991d17a 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -392,6 +392,7 @@ static struct irq_chip wakeupgen_chip = {
 	.irq_mask		= wakeupgen_mask,
 	.irq_unmask		= wakeupgen_unmask,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_type		= irq_chip_set_type_parent,
 	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
diff --git a/arch/arm/mach-omap2/omap3-restart.c b/arch/arm/mach-omap2/omap3-restart.c
index 103a49f68bcb..4bdd22edb96b 100644
--- a/arch/arm/mach-omap2/omap3-restart.c
+++ b/arch/arm/mach-omap2/omap3-restart.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/reboot.h>
 
+#include "common.h"
 #include "control.h"
 #include "prm.h"
 
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 16350eefa66c..949696b6f17b 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -51,6 +51,127 @@ static void __iomem *twd_base;
 
 #define IRQ_LOCALTIMER		29
 
+#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER
+
+/* Used to implement memory barrier on DRAM path */
+#define OMAP4_DRAM_BARRIER_VA			0xfe600000
+
+static void __iomem *dram_sync, *sram_sync;
+static phys_addr_t dram_sync_paddr;
+static u32 dram_sync_size;
+
+/*
+ * The OMAP4 bus structure contains asynchrnous bridges which can buffer
+ * data writes from the MPU. These asynchronous bridges can be found on
+ * paths between the MPU to EMIF, and the MPU to L3 interconnects.
+ *
+ * We need to be careful about re-ordering which can happen as a result
+ * of different accesses being performed via different paths, and
+ * therefore different asynchronous bridges.
+ */
+
+/*
+ * OMAP4 interconnect barrier which is called for each mb() and wmb().
+ * This is to ensure that normal paths to DRAM (normal memory, cacheable
+ * accesses) are properly synchronised with writes to DMA coherent memory
+ * (normal memory, uncacheable) and device writes.
+ *
+ * The mb() and wmb() barriers only operate only on the MPU->MA->EMIF
+ * path, as we need to ensure that data is visible to other system
+ * masters prior to writes to those system masters being seen.
+ *
+ * Note: the SRAM path is not synchronised via mb() and wmb().
+ */
+static void omap4_mb(void)
+{
+	if (dram_sync)
+		writel_relaxed(0, dram_sync);
+}
+
+/*
+ * OMAP4 Errata i688 - asynchronous bridge corruption when entering WFI.
+ *
+ * If a data is stalled inside asynchronous bridge because of back
+ * pressure, it may be accepted multiple times, creating pointer
+ * misalignment that will corrupt next transfers on that data path until
+ * next reset of the system. No recovery procedure once the issue is hit,
+ * the path remains consistently broken.
+ *
+ * Async bridges can be found on paths between MPU to EMIF and MPU to L3
+ * interconnects.
+ *
+ * This situation can happen only when the idle is initiated by a Master
+ * Request Disconnection (which is trigged by software when executing WFI
+ * on the CPU).
+ *
+ * The work-around for this errata needs all the initiators connected
+ * through an async bridge to ensure that data path is properly drained
+ * before issuing WFI. This condition will be met if one Strongly ordered
+ * access is performed to the target right before executing the WFI.
+ *
+ * In MPU case, L3 T2ASYNC FIFO and DDR T2ASYNC FIFO needs to be drained.
+ * IO barrier ensure that there is no synchronisation loss on initiators
+ * operating on both interconnect port simultaneously.
+ *
+ * This is a stronger version of the OMAP4 memory barrier below, and
+ * operates on both the MPU->MA->EMIF path but also the MPU->OCP path
+ * as well, and is necessary prior to executing a WFI.
+ */
+void omap_interconnect_sync(void)
+{
+	if (dram_sync && sram_sync) {
+		writel_relaxed(readl_relaxed(dram_sync), dram_sync);
+		writel_relaxed(readl_relaxed(sram_sync), sram_sync);
+		isb();
+	}
+}
+
+static int __init omap4_sram_init(void)
+{
+	struct device_node *np;
+	struct gen_pool *sram_pool;
+
+	np = of_find_compatible_node(NULL, NULL, "ti,omap4-mpu");
+	if (!np)
+		pr_warn("%s:Unable to allocate sram needed to handle errata I688\n",
+			__func__);
+	sram_pool = of_gen_pool_get(np, "sram", 0);
+	if (!sram_pool)
+		pr_warn("%s:Unable to get sram pool needed to handle errata I688\n",
+			__func__);
+	else
+		sram_sync = (void *)gen_pool_alloc(sram_pool, PAGE_SIZE);
+
+	return 0;
+}
+omap_arch_initcall(omap4_sram_init);
+
+/* Steal one page physical memory for barrier implementation */
+void __init omap_barrier_reserve_memblock(void)
+{
+	dram_sync_size = ALIGN(PAGE_SIZE, SZ_1M);
+	dram_sync_paddr = arm_memblock_steal(dram_sync_size, SZ_1M);
+}
+
+void __init omap_barriers_init(void)
+{
+	struct map_desc dram_io_desc[1];
+
+	dram_io_desc[0].virtual = OMAP4_DRAM_BARRIER_VA;
+	dram_io_desc[0].pfn = __phys_to_pfn(dram_sync_paddr);
+	dram_io_desc[0].length = dram_sync_size;
+	dram_io_desc[0].type = MT_MEMORY_RW_SO;
+	iotable_init(dram_io_desc, ARRAY_SIZE(dram_io_desc));
+	dram_sync = (void __iomem *) dram_io_desc[0].virtual;
+
+	pr_info("OMAP4: Map %pa to %p for dram barrier\n",
+		&dram_sync_paddr, dram_sync);
+
+	soc_mb = omap4_mb;
+}
+
+#endif
+
 void gic_dist_disable(void)
 {
 	if (gic_dist_base_addr)
diff --git a/arch/arm/mach-omap2/omap4-restart.c b/arch/arm/mach-omap2/omap4-restart.c
index a99e7f7fb5be..e17136a50e27 100644
--- a/arch/arm/mach-omap2/omap4-restart.c
+++ b/arch/arm/mach-omap2/omap4-restart.c
@@ -9,6 +9,7 @@
 
 #include <linux/types.h>
 #include <linux/reboot.h>
+#include "common.h"
 #include "prm.h"
 
 /**
diff --git a/arch/arm/mach-omap2/omap54xx.h b/arch/arm/mach-omap2/omap54xx.h
index 2d35c5709408..0ca8e938096b 100644
--- a/arch/arm/mach-omap2/omap54xx.h
+++ b/arch/arm/mach-omap2/omap54xx.h
@@ -30,6 +30,14 @@
 #define OMAP54XX_CTRL_BASE		0x4a002800
 #define OMAP54XX_SAR_RAM_BASE		0x4ae26000
 
+/* DRA7 specific base addresses */
+#define L3_MAIN_SN_DRA7XX_BASE		0x44000000
+#define L4_PER1_DRA7XX_BASE		0x48000000
+#define L4_CFG_MPU_DRA7XX_BASE		0x48210000
+#define L4_PER2_DRA7XX_BASE		0x48400000
+#define L4_PER3_DRA7XX_BASE		0x48800000
+#define L4_CFG_DRA7XX_BASE		0x4A000000
+#define L4_WKUP_DRA7XX_BASE		0x4ae00000
 #define DRA7XX_CM_CORE_AON_BASE		0x4a005000
 #define DRA7XX_CTRL_BASE		0x4a003400
 #define DRA7XX_TAP_BASE			0x4ae0c000
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index d78c12e7cb5e..cc8a987149e2 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -130,6 +130,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/io.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -299,7 +300,20 @@ static void _write_sysconfig(u32 v, struct omap_hwmod *oh)
 
 	/* Module might have lost context, always update cache and register */
 	oh->_sysc_cache = v;
+
+	/*
+	 * Some IP blocks (such as RTC) require unlocking of IP before
+	 * accessing its registers. If a function pointer is present
+	 * to unlock, then call it before accessing sysconfig and
+	 * call lock after writing sysconfig.
+	 */
+	if (oh->class->unlock)
+		oh->class->unlock(oh);
+
 	omap_hwmod_write(v, oh, oh->class->sysc->sysc_offs);
+
+	if (oh->class->lock)
+		oh->class->lock(oh);
 }
 
 /**
@@ -2373,6 +2387,9 @@ static int of_dev_hwmod_lookup(struct device_node *np,
  * registers.  This address is needed early so the OCP registers that
  * are part of the device's address space can be ioremapped properly.
  *
+ * If SYSC access is not needed, the registers will not be remapped
+ * and non-availability of MPU access is not treated as an error.
+ *
  * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and
  * -ENXIO on absent or invalid register target address space.
  */
@@ -2387,6 +2404,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data,
 
 	_save_mpu_port_index(oh);
 
+	/* if we don't need sysc access we don't need to ioremap */
+	if (!oh->class->sysc)
+		return 0;
+
+	/* we can't continue without MPU PORT if we need sysc access */
 	if (oh->_int_flags & _HWMOD_NO_MPU_PORT)
 		return -ENXIO;
 
@@ -2396,8 +2418,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data,
 			 oh->name);
 
 		/* Extract the IO space from device tree blob */
-		if (!np)
+		if (!np) {
+			pr_err("omap_hwmod: %s: no dt node\n", oh->name);
 			return -ENXIO;
+		}
 
 		va_start = of_iomap(np, index + oh->mpu_rt_idx);
 	} else {
@@ -2456,13 +2480,11 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 				oh->name, np->name);
 	}
 
-	if (oh->class->sysc) {
-		r = _init_mpu_rt_base(oh, NULL, index, np);
-		if (r < 0) {
-			WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
-			     oh->name);
-			return 0;
-		}
+	r = _init_mpu_rt_base(oh, NULL, index, np);
+	if (r < 0) {
+		WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
+		     oh->name);
+		return 0;
 	}
 
 	r = _init_clocks(oh, NULL);
@@ -3878,7 +3900,8 @@ void __init omap_hwmod_init(void)
 		soc_ops.init_clkdm = _init_clkdm;
 		soc_ops.update_context_lost = _omap4_update_context_lost;
 		soc_ops.get_context_lost = _omap4_get_context_lost;
-	} else if (cpu_is_ti816x() || soc_is_am33xx() || soc_is_am43xx()) {
+	} else if (cpu_is_ti814x() || cpu_is_ti816x() || soc_is_am33xx() ||
+		   soc_is_am43xx()) {
 		soc_ops.enable_module = _omap4_enable_module;
 		soc_ops.disable_module = _omap4_disable_module;
 		soc_ops.wait_target_ready = _omap4_wait_target_ready;
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index b5d27ec81610..ca6df1a73475 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -576,6 +576,8 @@ struct omap_hwmod_omap4_prcm {
  * @pre_shutdown: ptr to fn to be executed immediately prior to device shutdown
  * @reset: ptr to fn to be executed in place of the standard hwmod reset fn
  * @enable_preprogram:  ptr to fn to be executed during device enable
+ * @lock: ptr to fn to be executed to lock IP registers
+ * @unlock: ptr to fn to be executed to unlock IP registers
  *
  * Represent the class of a OMAP hardware "modules" (e.g. timer,
  * smartreflex, gpio, uart...)
@@ -600,6 +602,8 @@ struct omap_hwmod_class {
 	int					(*pre_shutdown)(struct omap_hwmod *oh);
 	int					(*reset)(struct omap_hwmod *oh);
 	int					(*enable_preprogram)(struct omap_hwmod *oh);
+	void					(*lock)(struct omap_hwmod *oh);
+	void					(*unlock)(struct omap_hwmod *oh);
 };
 
 /**
@@ -755,7 +759,8 @@ extern int omap3xxx_hwmod_init(void);
 extern int omap44xx_hwmod_init(void);
 extern int omap54xx_hwmod_init(void);
 extern int am33xx_hwmod_init(void);
-extern int ti81xx_hwmod_init(void);
+extern int dm814x_hwmod_init(void);
+extern int dm816x_hwmod_init(void);
 extern int dra7xx_hwmod_init(void);
 int am43xx_hwmod_init(void);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index 6dcfd03ced8f..36bcd2e75422 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -20,7 +20,7 @@
 #include "prm-regbits-24xx.h"
 #include "wd_timer.h"
 
-struct omap_hwmod_dma_info omap2xxx_dss_sdma_chs[] = {
+static struct omap_hwmod_dma_info omap2xxx_dss_sdma_chs[] = {
 	{ .name = "dispc", .dma_req = 5 },
 	{ .dma_req = -1, },
 };
diff --git a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
index 215d5efa0dba..e97a894b5f88 100644
--- a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
@@ -480,7 +480,7 @@ static struct omap_hwmod am43xx_dss_core_hwmod = {
 
 /* dispc */
 
-struct omap_dss_dispc_dev_attr am43xx_dss_dispc_dev_attr = {
+static struct omap_dss_dispc_dev_attr am43xx_dss_dispc_dev_attr = {
 	.manager_count		= 1,
 	.has_framedonetv_irq	= 0
 };
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 2606c6608bd8..562247bced49 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -827,8 +827,7 @@ static struct omap_hwmod_class_sysconfig dra7xx_gpmc_sysc = {
 	.syss_offs	= 0x0014,
 	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE |
 			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
@@ -844,7 +843,7 @@ static struct omap_hwmod dra7xx_gpmc_hwmod = {
 	.class		= &dra7xx_gpmc_hwmod_class,
 	.clkdm_name	= "l3main1_clkdm",
 	/* Skip reset for CONFIG_OMAP_GPMC_DEBUG for bootloader timings */
-	.flags		= HWMOD_SWSUP_SIDLE | DEBUG_OMAP_GPMC_HWMOD_FLAGS,
+	.flags		= DEBUG_OMAP_GPMC_HWMOD_FLAGS,
 	.main_clk	= "l3_iclk_div",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
index c92413769144..b1288f56d509 100644
--- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
@@ -32,21 +32,59 @@
  */
 
 /*
- * The alwon .clkctrl_offs field is offset from the CM_ALWON, that's
- * TRM 18.7.17 CM_ALWON device register values minus 0x1400.
+ * Common alwon .clkctrl_offs from dm814x TRM "Table 2-278. CM_ALWON REGISTERS"
+ * also dm816x TRM 18.7.17 CM_ALWON device register values minus 0x1400.
  */
+#define DM81XX_CM_ALWON_MCASP0_CLKCTRL		0x140
+#define DM81XX_CM_ALWON_MCASP1_CLKCTRL		0x144
+#define DM81XX_CM_ALWON_MCASP2_CLKCTRL		0x148
+#define DM81XX_CM_ALWON_MCBSP_CLKCTRL		0x14c
+#define DM81XX_CM_ALWON_UART_0_CLKCTRL		0x150
+#define DM81XX_CM_ALWON_UART_1_CLKCTRL		0x154
+#define DM81XX_CM_ALWON_UART_2_CLKCTRL		0x158
+#define DM81XX_CM_ALWON_GPIO_0_CLKCTRL		0x15c
+#define DM81XX_CM_ALWON_GPIO_1_CLKCTRL		0x160
+#define DM81XX_CM_ALWON_I2C_0_CLKCTRL		0x164
+#define DM81XX_CM_ALWON_I2C_1_CLKCTRL		0x168
+#define DM81XX_CM_ALWON_WDTIMER_CLKCTRL		0x18c
+#define DM81XX_CM_ALWON_SPI_CLKCTRL		0x190
+#define DM81XX_CM_ALWON_MAILBOX_CLKCTRL		0x194
+#define DM81XX_CM_ALWON_SPINBOX_CLKCTRL		0x198
+#define DM81XX_CM_ALWON_MMUDATA_CLKCTRL		0x19c
+#define DM81XX_CM_ALWON_MMUCFG_CLKCTRL		0x1a8
+#define DM81XX_CM_ALWON_CONTROL_CLKCTRL		0x1c4
+#define DM81XX_CM_ALWON_GPMC_CLKCTRL		0x1d0
+#define DM81XX_CM_ALWON_ETHERNET_0_CLKCTRL	0x1d4
+#define DM81XX_CM_ALWON_L3_CLKCTRL		0x1e4
+#define DM81XX_CM_ALWON_L4HS_CLKCTRL		0x1e8
+#define DM81XX_CM_ALWON_L4LS_CLKCTRL		0x1ec
+#define DM81XX_CM_ALWON_RTC_CLKCTRL		0x1f0
+#define DM81XX_CM_ALWON_TPCC_CLKCTRL		0x1f4
+#define DM81XX_CM_ALWON_TPTC0_CLKCTRL		0x1f8
+#define DM81XX_CM_ALWON_TPTC1_CLKCTRL		0x1fc
+#define DM81XX_CM_ALWON_TPTC2_CLKCTRL		0x200
+#define DM81XX_CM_ALWON_TPTC3_CLKCTRL		0x204
+
+/* Registers specific to dm814x */
+#define DM814X_CM_ALWON_MCASP_3_4_5_CLKCTRL	0x16c
+#define DM814X_CM_ALWON_ATL_CLKCTRL		0x170
+#define DM814X_CM_ALWON_MLB_CLKCTRL		0x174
+#define DM814X_CM_ALWON_PATA_CLKCTRL		0x178
+#define DM814X_CM_ALWON_UART_3_CLKCTRL		0x180
+#define DM814X_CM_ALWON_UART_4_CLKCTRL		0x184
+#define DM814X_CM_ALWON_UART_5_CLKCTRL		0x188
+#define DM814X_CM_ALWON_OCM_0_CLKCTRL		0x1b4
+#define DM814X_CM_ALWON_VCP_CLKCTRL		0x1b8
+#define DM814X_CM_ALWON_MPU_CLKCTRL		0x1dc
+#define DM814X_CM_ALWON_DEBUGSS_CLKCTRL		0x1e0
+#define DM814X_CM_ALWON_DCAN_0_1_CLKCTRL	0x218
+#define DM814X_CM_ALWON_MMCHS_0_CLKCTRL		0x21c
+#define DM814X_CM_ALWON_MMCHS_1_CLKCTRL		0x220
+#define DM814X_CM_ALWON_MMCHS_2_CLKCTRL		0x224
+#define DM814X_CM_ALWON_CUST_EFUSE_CLKCTRL	0x228
+
+/* Registers specific to dm816x */
 #define DM816X_DM_ALWON_BASE		0x1400
-#define DM816X_CM_ALWON_MCASP0_CLKCTRL	(0x1540 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_MCASP1_CLKCTRL	(0x1544 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_MCASP2_CLKCTRL	(0x1548 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_MCBSP_CLKCTRL	(0x154c - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_UART_0_CLKCTRL	(0x1550 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_UART_1_CLKCTRL	(0x1554 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_UART_2_CLKCTRL	(0x1558 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_GPIO_0_CLKCTRL	(0x155c - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_GPIO_1_CLKCTRL	(0x1560 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_I2C_0_CLKCTRL	(0x1564 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_I2C_1_CLKCTRL	(0x1568 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_TIMER_1_CLKCTRL	(0x1570 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_TIMER_2_CLKCTRL	(0x1574 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_TIMER_3_CLKCTRL	(0x1578 - DM816X_DM_ALWON_BASE)
@@ -54,29 +92,11 @@
 #define DM816X_CM_ALWON_TIMER_5_CLKCTRL	(0x1580 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_TIMER_6_CLKCTRL	(0x1584 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_TIMER_7_CLKCTRL	(0x1588 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_WDTIMER_CLKCTRL	(0x158c - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_SPI_CLKCTRL	(0x1590 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_MAILBOX_CLKCTRL	(0x1594 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_SPINBOX_CLKCTRL	(0x1598 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_MMUDATA_CLKCTRL	(0x159c - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_MMUCFG_CLKCTRL	(0x15a8 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_SDIO_CLKCTRL	(0x15b0 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_OCMC_0_CLKCTRL	(0x15b4 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_OCMC_1_CLKCTRL	(0x15b8 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_CONTRL_CLKCTRL	(0x15c4 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_GPMC_CLKCTRL	(0x15d0 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_ETHERNET_0_CLKCTRL (0x15d4 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_ETHERNET_1_CLKCTRL (0x15d8 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_MPU_CLKCTRL	(0x15dc - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_L3_CLKCTRL	(0x15e4 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_L4HS_CLKCTRL	(0x15e8 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_L4LS_CLKCTRL	(0x15ec - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_RTC_CLKCTRL	(0x15f0 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_TPCC_CLKCTRL	(0x15f4 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_TPTC0_CLKCTRL	(0x15f8 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_TPTC1_CLKCTRL	(0x15fc - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_TPTC2_CLKCTRL	(0x1600 - DM816X_DM_ALWON_BASE)
-#define DM816X_CM_ALWON_TPTC3_CLKCTRL	(0x1604 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_SR_0_CLKCTRL	(0x1608 - DM816X_DM_ALWON_BASE)
 #define DM816X_CM_ALWON_SR_1_CLKCTRL	(0x160c - DM816X_DM_ALWON_BASE)
 
@@ -88,28 +108,28 @@
 #define DM816X_CM_DEFAULT_USB_CLKCTRL	(0x558 - DM816X_CM_DEFAULT_OFFSET)
 
 /* L3 Interconnect entries clocked at 125, 250 and 500MHz */
-static struct omap_hwmod dm816x_alwon_l3_slow_hwmod = {
+static struct omap_hwmod dm81xx_alwon_l3_slow_hwmod = {
 	.name		= "alwon_l3_slow",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.class		= &l3_hwmod_class,
 	.flags		= HWMOD_NO_IDLEST,
 };
 
-static struct omap_hwmod dm816x_default_l3_slow_hwmod = {
+static struct omap_hwmod dm81xx_default_l3_slow_hwmod = {
 	.name		= "default_l3_slow",
 	.clkdm_name	= "default_l3_slow_clkdm",
 	.class		= &l3_hwmod_class,
 	.flags		= HWMOD_NO_IDLEST,
 };
 
-static struct omap_hwmod dm816x_alwon_l3_med_hwmod = {
+static struct omap_hwmod dm81xx_alwon_l3_med_hwmod = {
 	.name		= "l3_med",
 	.clkdm_name	= "alwon_l3_med_clkdm",
 	.class		= &l3_hwmod_class,
 	.flags		= HWMOD_NO_IDLEST,
 };
 
-static struct omap_hwmod dm816x_alwon_l3_fast_hwmod = {
+static struct omap_hwmod dm81xx_alwon_l3_fast_hwmod = {
 	.name		= "l3_fast",
 	.clkdm_name	= "alwon_l3_fast_clkdm",
 	.class		= &l3_hwmod_class,
@@ -120,7 +140,7 @@ static struct omap_hwmod dm816x_alwon_l3_fast_hwmod = {
  * L4 standard peripherals, see TRM table 1-12 for devices using this.
  * See TRM table 1-73 for devices using the 125MHz SYSCLK6 clock.
  */
-static struct omap_hwmod dm816x_l4_ls_hwmod = {
+static struct omap_hwmod dm81xx_l4_ls_hwmod = {
 	.name		= "l4_ls",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.class		= &l4_hwmod_class,
@@ -131,27 +151,54 @@ static struct omap_hwmod dm816x_l4_ls_hwmod = {
  * table 1-13. On dm816x, only EMAC, MDIO and SATA use this. See also TRM
  * table 1-73 for devices using 250MHz SYSCLK5 clock.
  */
-static struct omap_hwmod dm816x_l4_hs_hwmod = {
+static struct omap_hwmod dm81xx_l4_hs_hwmod = {
 	.name		= "l4_hs",
 	.clkdm_name	= "alwon_l3_med_clkdm",
 	.class		= &l4_hwmod_class,
 };
 
 /* L3 slow -> L4 ls peripheral interface running at 125MHz */
-static struct omap_hwmod_ocp_if dm816x_alwon_l3_slow__l4_ls = {
-	.master	= &dm816x_alwon_l3_slow_hwmod,
-	.slave	= &dm816x_l4_ls_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_slow__l4_ls = {
+	.master	= &dm81xx_alwon_l3_slow_hwmod,
+	.slave	= &dm81xx_l4_ls_hwmod,
 	.user	= OCP_USER_MPU,
 };
 
 /* L3 med -> L4 fast peripheral interface running at 250MHz */
-static struct omap_hwmod_ocp_if dm816x_alwon_l3_slow__l4_hs = {
-	.master	= &dm816x_alwon_l3_med_hwmod,
-	.slave	= &dm816x_l4_hs_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_slow__l4_hs = {
+	.master	= &dm81xx_alwon_l3_med_hwmod,
+	.slave	= &dm81xx_l4_hs_hwmod,
 	.user	= OCP_USER_MPU,
 };
 
 /* MPU */
+static struct omap_hwmod dm814x_mpu_hwmod = {
+	.name		= "mpu",
+	.clkdm_name	= "alwon_l3s_clkdm",
+	.class		= &mpu_hwmod_class,
+	.flags		= HWMOD_INIT_NO_IDLE,
+	.main_clk	= "mpu_ck",
+	.prcm		= {
+		.omap4 = {
+			.clkctrl_offs = DM814X_CM_ALWON_MPU_CLKCTRL,
+			.modulemode = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+static struct omap_hwmod_ocp_if dm814x_mpu__alwon_l3_slow = {
+	.master		= &dm814x_mpu_hwmod,
+	.slave		= &dm81xx_alwon_l3_slow_hwmod,
+	.user		= OCP_USER_MPU,
+};
+
+/* L3 med peripheral interface running at 200MHz */
+static struct omap_hwmod_ocp_if dm814x_mpu__alwon_l3_med = {
+	.master	= &dm814x_mpu_hwmod,
+	.slave	= &dm81xx_alwon_l3_med_hwmod,
+	.user	= OCP_USER_MPU,
+};
+
 static struct omap_hwmod dm816x_mpu_hwmod = {
 	.name		= "mpu",
 	.clkdm_name	= "alwon_mpu_clkdm",
@@ -168,14 +215,14 @@ static struct omap_hwmod dm816x_mpu_hwmod = {
 
 static struct omap_hwmod_ocp_if dm816x_mpu__alwon_l3_slow = {
 	.master		= &dm816x_mpu_hwmod,
-	.slave		= &dm816x_alwon_l3_slow_hwmod,
+	.slave		= &dm81xx_alwon_l3_slow_hwmod,
 	.user		= OCP_USER_MPU,
 };
 
 /* L3 med peripheral interface running at 250MHz */
 static struct omap_hwmod_ocp_if dm816x_mpu__alwon_l3_med = {
 	.master	= &dm816x_mpu_hwmod,
-	.slave	= &dm816x_alwon_l3_med_hwmod,
+	.slave	= &dm81xx_alwon_l3_med_hwmod,
 	.user	= OCP_USER_MPU,
 };
 
@@ -197,13 +244,13 @@ static struct omap_hwmod_class uart_class = {
 	.sysc = &uart_sysc,
 };
 
-static struct omap_hwmod dm816x_uart1_hwmod = {
+static struct omap_hwmod dm81xx_uart1_hwmod = {
 	.name		= "uart1",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk10_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_UART_0_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_UART_0_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -211,20 +258,20 @@ static struct omap_hwmod dm816x_uart1_hwmod = {
 	.flags		= DEBUG_TI81XXUART1_FLAGS,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__uart1 = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_uart1_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__uart1 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_uart1_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod dm816x_uart2_hwmod = {
+static struct omap_hwmod dm81xx_uart2_hwmod = {
 	.name		= "uart2",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk10_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_UART_1_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_UART_1_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -232,20 +279,20 @@ static struct omap_hwmod dm816x_uart2_hwmod = {
 	.flags		= DEBUG_TI81XXUART2_FLAGS,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__uart2 = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_uart2_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__uart2 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_uart2_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod dm816x_uart3_hwmod = {
+static struct omap_hwmod dm81xx_uart3_hwmod = {
 	.name		= "uart3",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk10_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_UART_2_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_UART_2_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -253,9 +300,9 @@ static struct omap_hwmod dm816x_uart3_hwmod = {
 	.flags		= DEBUG_TI81XXUART3_FLAGS,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__uart3 = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_uart3_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__uart3 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_uart3_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
@@ -276,23 +323,23 @@ static struct omap_hwmod_class wd_timer_class = {
 	.reset		= &omap2_wd_timer_reset,
 };
 
-static struct omap_hwmod dm816x_wd_timer_hwmod = {
+static struct omap_hwmod dm81xx_wd_timer_hwmod = {
 	.name		= "wd_timer",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk18_ck",
 	.flags		= HWMOD_NO_IDLEST,
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_WDTIMER_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_WDTIMER_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
 	.class		= &wd_timer_class,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__wd_timer1 = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_wd_timer_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__wd_timer1 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_wd_timer_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
@@ -320,27 +367,27 @@ static struct omap_hwmod dm81xx_i2c1_hwmod = {
 	.main_clk	= "sysclk10_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_I2C_0_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_I2C_0_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
 	.class		= &i2c_class,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__i2c1 = {
-	.master		= &dm816x_l4_ls_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__i2c1 = {
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm81xx_i2c1_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod dm816x_i2c2_hwmod = {
+static struct omap_hwmod dm81xx_i2c2_hwmod = {
 	.name		= "i2c2",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk10_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_I2C_1_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_I2C_1_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -358,9 +405,9 @@ static struct omap_hwmod_class_sysconfig dm81xx_elm_sysc = {
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__i2c2 = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_i2c2_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__i2c2 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_i2c2_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
@@ -378,7 +425,7 @@ static struct omap_hwmod dm81xx_elm_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm81xx_l4_ls__elm = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm81xx_elm_hwmod,
 	.user		= OCP_USER_MPU,
 };
@@ -417,7 +464,7 @@ static struct omap_hwmod dm81xx_gpio1_hwmod = {
 	.main_clk	= "sysclk6_ck",
 	.prcm = {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_GPIO_0_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_GPIO_0_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -427,7 +474,7 @@ static struct omap_hwmod dm81xx_gpio1_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm81xx_l4_ls__gpio1 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm81xx_gpio1_hwmod,
 	.user		= OCP_USER_MPU,
 };
@@ -443,7 +490,7 @@ static struct omap_hwmod dm81xx_gpio2_hwmod = {
 	.main_clk	= "sysclk6_ck",
 	.prcm = {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_GPIO_1_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_GPIO_1_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -453,7 +500,7 @@ static struct omap_hwmod dm81xx_gpio2_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm81xx_l4_ls__gpio2 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm81xx_gpio2_hwmod,
 	.user		= OCP_USER_MPU,
 };
@@ -482,14 +529,14 @@ static struct omap_hwmod dm81xx_gpmc_hwmod = {
 	.flags		= DEBUG_OMAP_GPMC_HWMOD_FLAGS,
 	.prcm = {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_GPMC_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_GPMC_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm81xx_alwon_l3_slow__gpmc = {
-	.master		= &dm816x_alwon_l3_slow_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_slow__gpmc = {
+	.master		= &dm81xx_alwon_l3_slow_hwmod,
 	.slave		= &dm81xx_gpmc_hwmod,
 	.user		= OCP_USER_MPU,
 };
@@ -522,7 +569,7 @@ static struct omap_hwmod dm81xx_usbss_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm81xx_default_l3_slow__usbss = {
-	.master		= &dm816x_default_l3_slow_hwmod,
+	.master		= &dm81xx_default_l3_slow_hwmod,
 	.slave		= &dm81xx_usbss_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -547,6 +594,22 @@ static struct omap_timer_capability_dev_attr capability_alwon_dev_attr = {
 	.timer_capability	= OMAP_TIMER_ALWON,
 };
 
+static struct omap_hwmod dm814x_timer1_hwmod = {
+	.name		= "timer1",
+	.clkdm_name	= "alwon_l3s_clkdm",
+	.main_clk	= "timer_sys_ck",
+	.dev_attr	= &capability_alwon_dev_attr,
+	.class		= &dm816x_timer_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
+};
+
+static struct omap_hwmod_ocp_if dm814x_l4_ls__timer1 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm814x_timer1_hwmod,
+	.clk		= "timer_sys_ck",
+	.user		= OCP_USER_MPU,
+};
+
 static struct omap_hwmod dm816x_timer1_hwmod = {
 	.name		= "timer1",
 	.clkdm_name	= "alwon_l3s_clkdm",
@@ -562,12 +625,28 @@ static struct omap_hwmod dm816x_timer1_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer1 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer1_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
 
+static struct omap_hwmod dm814x_timer2_hwmod = {
+	.name		= "timer2",
+	.clkdm_name	= "alwon_l3s_clkdm",
+	.main_clk	= "timer_sys_ck",
+	.dev_attr	= &capability_alwon_dev_attr,
+	.class		= &dm816x_timer_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
+};
+
+static struct omap_hwmod_ocp_if dm814x_l4_ls__timer2 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm814x_timer2_hwmod,
+	.clk		= "timer_sys_ck",
+	.user		= OCP_USER_MPU,
+};
+
 static struct omap_hwmod dm816x_timer2_hwmod = {
 	.name		= "timer2",
 	.clkdm_name	= "alwon_l3s_clkdm",
@@ -583,7 +662,7 @@ static struct omap_hwmod dm816x_timer2_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer2 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer2_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -604,7 +683,7 @@ static struct omap_hwmod dm816x_timer3_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer3 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer3_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -625,7 +704,7 @@ static struct omap_hwmod dm816x_timer4_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer4 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer4_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -646,7 +725,7 @@ static struct omap_hwmod dm816x_timer5_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer5 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer5_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -667,7 +746,7 @@ static struct omap_hwmod dm816x_timer6_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer6 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer6_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -688,12 +767,68 @@ static struct omap_hwmod dm816x_timer7_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__timer7 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_timer7_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
 
+/* CPSW on dm814x */
+static struct omap_hwmod_class_sysconfig dm814x_cpgmac_sysc = {
+	.rev_offs	= 0x0,
+	.sysc_offs	= 0x8,
+	.syss_offs	= 0x4,
+	.sysc_flags	= SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE |
+			  SYSS_HAS_RESET_STATUS,
+	.idlemodes	= SIDLE_FORCE | SIDLE_NO | MSTANDBY_FORCE |
+			  MSTANDBY_NO,
+	.sysc_fields	= &omap_hwmod_sysc_type3,
+};
+
+static struct omap_hwmod_class dm814x_cpgmac0_hwmod_class = {
+	.name		= "cpgmac0",
+	.sysc		= &dm814x_cpgmac_sysc,
+};
+
+static struct omap_hwmod dm814x_cpgmac0_hwmod = {
+	.name		= "cpgmac0",
+	.class		= &dm814x_cpgmac0_hwmod_class,
+	.clkdm_name	= "alwon_ethernet_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY,
+	.main_clk	= "cpsw_125mhz_gclk",
+	.prcm		= {
+		.omap4	= {
+			.clkctrl_offs = DM81XX_CM_ALWON_ETHERNET_0_CLKCTRL,
+			.modulemode = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+static struct omap_hwmod_class dm814x_mdio_hwmod_class = {
+	.name		= "davinci_mdio",
+};
+
+static struct omap_hwmod dm814x_mdio_hwmod = {
+	.name		= "davinci_mdio",
+	.class		= &dm814x_mdio_hwmod_class,
+	.clkdm_name	= "alwon_ethernet_clkdm",
+	.main_clk	= "cpsw_125mhz_gclk",
+};
+
+static struct omap_hwmod_ocp_if dm814x_l4_hs__cpgmac0 = {
+	.master		= &dm81xx_l4_hs_hwmod,
+	.slave		= &dm814x_cpgmac0_hwmod,
+	.clk		= "cpsw_125mhz_gclk",
+	.user		= OCP_USER_MPU,
+};
+
+static struct omap_hwmod_ocp_if dm814x_cpgmac0__mdio = {
+	.master		= &dm814x_cpgmac0_hwmod,
+	.slave		= &dm814x_mdio_hwmod,
+	.user		= OCP_USER_MPU,
+	.flags		= HWMOD_NO_IDLEST,
+};
+
 /* EMAC Ethernet */
 static struct omap_hwmod_class_sysconfig dm816x_emac_sysc = {
 	.rev_offs	= 0x0,
@@ -717,21 +852,21 @@ static struct omap_hwmod dm816x_emac0_hwmod = {
 	.class		= &dm816x_emac_hwmod_class,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_hs__emac0 = {
-	.master		= &dm816x_l4_hs_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_hs__emac0 = {
+	.master		= &dm81xx_l4_hs_hwmod,
 	.slave		= &dm816x_emac0_hwmod,
 	.clk		= "sysclk5_ck",
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_class dm816x_mdio_hwmod_class = {
+static struct omap_hwmod_class dm81xx_mdio_hwmod_class = {
 	.name		= "davinci_mdio",
 	.sysc		= &dm816x_emac_sysc,
 };
 
-struct omap_hwmod dm816x_emac0_mdio_hwmod = {
+static struct omap_hwmod dm81xx_emac0_mdio_hwmod = {
 	.name		= "davinci_mdio",
-	.class		= &dm816x_mdio_hwmod_class,
+	.class		= &dm81xx_mdio_hwmod_class,
 	.clkdm_name	= "alwon_ethernet_clkdm",
 	.main_clk	= "sysclk24_ck",
 	.flags		= HWMOD_NO_IDLEST,
@@ -741,15 +876,15 @@ struct omap_hwmod dm816x_emac0_mdio_hwmod = {
 	 */
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_ETHERNET_0_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_ETHERNET_0_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm816x_emac0__mdio = {
-	.master		= &dm816x_l4_hs_hwmod,
-	.slave		= &dm816x_emac0_mdio_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_emac0__mdio = {
+	.master		= &dm81xx_l4_hs_hwmod,
+	.slave		= &dm81xx_emac0_mdio_hwmod,
 	.user		= OCP_USER_MPU,
 };
 
@@ -768,7 +903,7 @@ static struct omap_hwmod dm816x_emac1_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_hs__emac1 = {
-	.master		= &dm816x_l4_hs_hwmod,
+	.master		= &dm81xx_l4_hs_hwmod,
 	.slave		= &dm816x_emac1_hwmod,
 	.clk		= "sysclk5_ck",
 	.user		= OCP_USER_MPU,
@@ -815,7 +950,7 @@ static struct omap_hwmod dm816x_mmc1_hwmod = {
 };
 
 static struct omap_hwmod_ocp_if dm816x_l4_ls__mmc1 = {
-	.master		= &dm816x_l4_ls_hwmod,
+	.master		= &dm81xx_l4_ls_hwmod,
 	.slave		= &dm816x_mmc1_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
@@ -843,13 +978,13 @@ static struct omap2_mcspi_dev_attr dm816x_mcspi1_dev_attr = {
 	.num_chipselect = 4,
 };
 
-static struct omap_hwmod dm816x_mcspi1_hwmod = {
+static struct omap_hwmod dm81xx_mcspi1_hwmod = {
 	.name		= "mcspi1",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk10_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_SPI_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_SPI_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
@@ -857,14 +992,14 @@ static struct omap_hwmod dm816x_mcspi1_hwmod = {
 	.dev_attr	= &dm816x_mcspi1_dev_attr,
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__mcspi1 = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_mcspi1_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__mcspi1 = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_mcspi1_hwmod,
 	.clk		= "sysclk6_ck",
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_class_sysconfig dm816x_mailbox_sysc = {
+static struct omap_hwmod_class_sysconfig dm81xx_mailbox_sysc = {
 	.rev_offs	= 0x000,
 	.sysc_offs	= 0x010,
 	.syss_offs	= 0x014,
@@ -874,55 +1009,55 @@ static struct omap_hwmod_class_sysconfig dm816x_mailbox_sysc = {
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
-static struct omap_hwmod_class dm816x_mailbox_hwmod_class = {
+static struct omap_hwmod_class dm81xx_mailbox_hwmod_class = {
 	.name = "mailbox",
-	.sysc = &dm816x_mailbox_sysc,
+	.sysc = &dm81xx_mailbox_sysc,
 };
 
-static struct omap_hwmod dm816x_mailbox_hwmod = {
+static struct omap_hwmod dm81xx_mailbox_hwmod = {
 	.name		= "mailbox",
 	.clkdm_name	= "alwon_l3s_clkdm",
-	.class		= &dm816x_mailbox_hwmod_class,
+	.class		= &dm81xx_mailbox_hwmod_class,
 	.main_clk	= "sysclk6_ck",
 	.prcm		= {
 		.omap4 = {
-			.clkctrl_offs = DM816X_CM_ALWON_MAILBOX_CLKCTRL,
+			.clkctrl_offs = DM81XX_CM_ALWON_MAILBOX_CLKCTRL,
 			.modulemode = MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-static struct omap_hwmod_ocp_if dm816x_l4_ls__mailbox = {
-	.master		= &dm816x_l4_ls_hwmod,
-	.slave		= &dm816x_mailbox_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_l4_ls__mailbox = {
+	.master		= &dm81xx_l4_ls_hwmod,
+	.slave		= &dm81xx_mailbox_hwmod,
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_class dm816x_tpcc_hwmod_class = {
+static struct omap_hwmod_class dm81xx_tpcc_hwmod_class = {
 	.name		= "tpcc",
 };
 
-struct omap_hwmod dm816x_tpcc_hwmod = {
+static struct omap_hwmod dm81xx_tpcc_hwmod = {
 	.name		= "tpcc",
-	.class		= &dm816x_tpcc_hwmod_class,
+	.class		= &dm81xx_tpcc_hwmod_class,
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk4_ck",
 	.prcm		= {
 		.omap4	= {
-			.clkctrl_offs	= DM816X_CM_ALWON_TPCC_CLKCTRL,
+			.clkctrl_offs	= DM81XX_CM_ALWON_TPCC_CLKCTRL,
 			.modulemode	= MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm816x_alwon_l3_fast__tpcc = {
-	.master		= &dm816x_alwon_l3_fast_hwmod,
-	.slave		= &dm816x_tpcc_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_fast__tpcc = {
+	.master		= &dm81xx_alwon_l3_fast_hwmod,
+	.slave		= &dm81xx_tpcc_hwmod,
 	.clk		= "sysclk4_ck",
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_addr_space dm816x_tptc0_addr_space[] = {
+static struct omap_hwmod_addr_space dm81xx_tptc0_addr_space[] = {
 	{
 		.pa_start	= 0x49800000,
 		.pa_end		= 0x49800000 + SZ_8K - 1,
@@ -931,40 +1066,40 @@ static struct omap_hwmod_addr_space dm816x_tptc0_addr_space[] = {
 	{ },
 };
 
-static struct omap_hwmod_class dm816x_tptc0_hwmod_class = {
+static struct omap_hwmod_class dm81xx_tptc0_hwmod_class = {
 	.name		= "tptc0",
 };
 
-struct omap_hwmod dm816x_tptc0_hwmod = {
+static struct omap_hwmod dm81xx_tptc0_hwmod = {
 	.name		= "tptc0",
-	.class		= &dm816x_tptc0_hwmod_class,
+	.class		= &dm81xx_tptc0_hwmod_class,
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk4_ck",
 	.prcm		= {
 		.omap4	= {
-			.clkctrl_offs	= DM816X_CM_ALWON_TPTC0_CLKCTRL,
+			.clkctrl_offs	= DM81XX_CM_ALWON_TPTC0_CLKCTRL,
 			.modulemode	= MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm816x_alwon_l3_fast__tptc0 = {
-	.master		= &dm816x_alwon_l3_fast_hwmod,
-	.slave		= &dm816x_tptc0_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_fast__tptc0 = {
+	.master		= &dm81xx_alwon_l3_fast_hwmod,
+	.slave		= &dm81xx_tptc0_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc0_addr_space,
+	.addr		= dm81xx_tptc0_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if dm816x_tptc0__alwon_l3_fast = {
-	.master		= &dm816x_tptc0_hwmod,
-	.slave		= &dm816x_alwon_l3_fast_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_tptc0__alwon_l3_fast = {
+	.master		= &dm81xx_tptc0_hwmod,
+	.slave		= &dm81xx_alwon_l3_fast_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc0_addr_space,
+	.addr		= dm81xx_tptc0_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_addr_space dm816x_tptc1_addr_space[] = {
+static struct omap_hwmod_addr_space dm81xx_tptc1_addr_space[] = {
 	{
 		.pa_start	= 0x49900000,
 		.pa_end		= 0x49900000 + SZ_8K - 1,
@@ -973,40 +1108,40 @@ static struct omap_hwmod_addr_space dm816x_tptc1_addr_space[] = {
 	{ },
 };
 
-static struct omap_hwmod_class dm816x_tptc1_hwmod_class = {
+static struct omap_hwmod_class dm81xx_tptc1_hwmod_class = {
 	.name		= "tptc1",
 };
 
-struct omap_hwmod dm816x_tptc1_hwmod = {
+static struct omap_hwmod dm81xx_tptc1_hwmod = {
 	.name		= "tptc1",
-	.class		= &dm816x_tptc1_hwmod_class,
+	.class		= &dm81xx_tptc1_hwmod_class,
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk4_ck",
 	.prcm		= {
 		.omap4	= {
-			.clkctrl_offs	= DM816X_CM_ALWON_TPTC1_CLKCTRL,
+			.clkctrl_offs	= DM81XX_CM_ALWON_TPTC1_CLKCTRL,
 			.modulemode	= MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm816x_alwon_l3_fast__tptc1 = {
-	.master		= &dm816x_alwon_l3_fast_hwmod,
-	.slave		= &dm816x_tptc1_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_fast__tptc1 = {
+	.master		= &dm81xx_alwon_l3_fast_hwmod,
+	.slave		= &dm81xx_tptc1_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc1_addr_space,
+	.addr		= dm81xx_tptc1_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if dm816x_tptc1__alwon_l3_fast = {
-	.master		= &dm816x_tptc1_hwmod,
-	.slave		= &dm816x_alwon_l3_fast_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_tptc1__alwon_l3_fast = {
+	.master		= &dm81xx_tptc1_hwmod,
+	.slave		= &dm81xx_alwon_l3_fast_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc1_addr_space,
+	.addr		= dm81xx_tptc1_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_addr_space dm816x_tptc2_addr_space[] = {
+static struct omap_hwmod_addr_space dm81xx_tptc2_addr_space[] = {
 	{
 		.pa_start	= 0x49a00000,
 		.pa_end		= 0x49a00000 + SZ_8K - 1,
@@ -1015,40 +1150,40 @@ static struct omap_hwmod_addr_space dm816x_tptc2_addr_space[] = {
 	{ },
 };
 
-static struct omap_hwmod_class dm816x_tptc2_hwmod_class = {
+static struct omap_hwmod_class dm81xx_tptc2_hwmod_class = {
 	.name		= "tptc2",
 };
 
-struct omap_hwmod dm816x_tptc2_hwmod = {
+static struct omap_hwmod dm81xx_tptc2_hwmod = {
 	.name		= "tptc2",
-	.class		= &dm816x_tptc2_hwmod_class,
+	.class		= &dm81xx_tptc2_hwmod_class,
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk4_ck",
 	.prcm		= {
 		.omap4	= {
-			.clkctrl_offs	= DM816X_CM_ALWON_TPTC2_CLKCTRL,
+			.clkctrl_offs	= DM81XX_CM_ALWON_TPTC2_CLKCTRL,
 			.modulemode	= MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm816x_alwon_l3_fast__tptc2 = {
-	.master		= &dm816x_alwon_l3_fast_hwmod,
-	.slave		= &dm816x_tptc2_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_fast__tptc2 = {
+	.master		= &dm81xx_alwon_l3_fast_hwmod,
+	.slave		= &dm81xx_tptc2_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc2_addr_space,
+	.addr		= dm81xx_tptc2_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if dm816x_tptc2__alwon_l3_fast = {
-	.master		= &dm816x_tptc2_hwmod,
-	.slave		= &dm816x_alwon_l3_fast_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_tptc2__alwon_l3_fast = {
+	.master		= &dm81xx_tptc2_hwmod,
+	.slave		= &dm81xx_alwon_l3_fast_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc2_addr_space,
+	.addr		= dm81xx_tptc2_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_addr_space dm816x_tptc3_addr_space[] = {
+static struct omap_hwmod_addr_space dm81xx_tptc3_addr_space[] = {
 	{
 		.pa_start	= 0x49b00000,
 		.pa_end		= 0x49b00000 + SZ_8K - 1,
@@ -1057,50 +1192,96 @@ static struct omap_hwmod_addr_space dm816x_tptc3_addr_space[] = {
 	{ },
 };
 
-static struct omap_hwmod_class dm816x_tptc3_hwmod_class = {
+static struct omap_hwmod_class dm81xx_tptc3_hwmod_class = {
 	.name		= "tptc3",
 };
 
-struct omap_hwmod dm816x_tptc3_hwmod = {
+static struct omap_hwmod dm81xx_tptc3_hwmod = {
 	.name		= "tptc3",
-	.class		= &dm816x_tptc3_hwmod_class,
+	.class		= &dm81xx_tptc3_hwmod_class,
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.main_clk	= "sysclk4_ck",
 	.prcm		= {
 		.omap4	= {
-			.clkctrl_offs	= DM816X_CM_ALWON_TPTC3_CLKCTRL,
+			.clkctrl_offs	= DM81XX_CM_ALWON_TPTC3_CLKCTRL,
 			.modulemode	= MODULEMODE_SWCTRL,
 		},
 	},
 };
 
-struct omap_hwmod_ocp_if dm816x_alwon_l3_fast__tptc3 = {
-	.master		= &dm816x_alwon_l3_fast_hwmod,
-	.slave		= &dm816x_tptc3_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_alwon_l3_fast__tptc3 = {
+	.master		= &dm81xx_alwon_l3_fast_hwmod,
+	.slave		= &dm81xx_tptc3_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc3_addr_space,
+	.addr		= dm81xx_tptc3_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if dm816x_tptc3__alwon_l3_fast = {
-	.master		= &dm816x_tptc3_hwmod,
-	.slave		= &dm816x_alwon_l3_fast_hwmod,
+static struct omap_hwmod_ocp_if dm81xx_tptc3__alwon_l3_fast = {
+	.master		= &dm81xx_tptc3_hwmod,
+	.slave		= &dm81xx_alwon_l3_fast_hwmod,
 	.clk		= "sysclk4_ck",
-	.addr		= dm816x_tptc3_addr_space,
+	.addr		= dm81xx_tptc3_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
+/*
+ * REVISIT: Test and enable the following once clocks work:
+ * dm81xx_l4_ls__gpio1
+ * dm81xx_l4_ls__gpio2
+ * dm81xx_l4_ls__mailbox
+ * dm81xx_alwon_l3_slow__gpmc
+ * dm81xx_default_l3_slow__usbss
+ *
+ * Also note that some devices share a single clkctrl_offs..
+ * For example, i2c1 and 3 share one, and i2c2 and 4 share one.
+ */
+static struct omap_hwmod_ocp_if *dm814x_hwmod_ocp_ifs[] __initdata = {
+	&dm814x_mpu__alwon_l3_slow,
+	&dm814x_mpu__alwon_l3_med,
+	&dm81xx_alwon_l3_slow__l4_ls,
+	&dm81xx_alwon_l3_slow__l4_hs,
+	&dm81xx_l4_ls__uart1,
+	&dm81xx_l4_ls__uart2,
+	&dm81xx_l4_ls__uart3,
+	&dm81xx_l4_ls__wd_timer1,
+	&dm81xx_l4_ls__i2c1,
+	&dm81xx_l4_ls__i2c2,
+	&dm81xx_l4_ls__elm,
+	&dm81xx_l4_ls__mcspi1,
+	&dm81xx_alwon_l3_fast__tpcc,
+	&dm81xx_alwon_l3_fast__tptc0,
+	&dm81xx_alwon_l3_fast__tptc1,
+	&dm81xx_alwon_l3_fast__tptc2,
+	&dm81xx_alwon_l3_fast__tptc3,
+	&dm81xx_tptc0__alwon_l3_fast,
+	&dm81xx_tptc1__alwon_l3_fast,
+	&dm81xx_tptc2__alwon_l3_fast,
+	&dm81xx_tptc3__alwon_l3_fast,
+	&dm814x_l4_ls__timer1,
+	&dm814x_l4_ls__timer2,
+	&dm814x_l4_hs__cpgmac0,
+	&dm814x_cpgmac0__mdio,
+	NULL,
+};
+
+int __init dm814x_hwmod_init(void)
+{
+	omap_hwmod_init();
+	return omap_hwmod_register_links(dm814x_hwmod_ocp_ifs);
+}
+
 static struct omap_hwmod_ocp_if *dm816x_hwmod_ocp_ifs[] __initdata = {
 	&dm816x_mpu__alwon_l3_slow,
 	&dm816x_mpu__alwon_l3_med,
-	&dm816x_alwon_l3_slow__l4_ls,
-	&dm816x_alwon_l3_slow__l4_hs,
-	&dm816x_l4_ls__uart1,
-	&dm816x_l4_ls__uart2,
-	&dm816x_l4_ls__uart3,
-	&dm816x_l4_ls__wd_timer1,
-	&dm816x_l4_ls__i2c1,
-	&dm816x_l4_ls__i2c2,
+	&dm81xx_alwon_l3_slow__l4_ls,
+	&dm81xx_alwon_l3_slow__l4_hs,
+	&dm81xx_l4_ls__uart1,
+	&dm81xx_l4_ls__uart2,
+	&dm81xx_l4_ls__uart3,
+	&dm81xx_l4_ls__wd_timer1,
+	&dm81xx_l4_ls__i2c1,
+	&dm81xx_l4_ls__i2c2,
 	&dm81xx_l4_ls__gpio1,
 	&dm81xx_l4_ls__gpio2,
 	&dm81xx_l4_ls__elm,
@@ -1112,26 +1293,26 @@ static struct omap_hwmod_ocp_if *dm816x_hwmod_ocp_ifs[] __initdata = {
 	&dm816x_l4_ls__timer5,
 	&dm816x_l4_ls__timer6,
 	&dm816x_l4_ls__timer7,
-	&dm816x_l4_ls__mcspi1,
-	&dm816x_l4_ls__mailbox,
-	&dm816x_l4_hs__emac0,
-	&dm816x_emac0__mdio,
+	&dm81xx_l4_ls__mcspi1,
+	&dm81xx_l4_ls__mailbox,
+	&dm81xx_l4_hs__emac0,
+	&dm81xx_emac0__mdio,
 	&dm816x_l4_hs__emac1,
-	&dm816x_alwon_l3_fast__tpcc,
-	&dm816x_alwon_l3_fast__tptc0,
-	&dm816x_alwon_l3_fast__tptc1,
-	&dm816x_alwon_l3_fast__tptc2,
-	&dm816x_alwon_l3_fast__tptc3,
-	&dm816x_tptc0__alwon_l3_fast,
-	&dm816x_tptc1__alwon_l3_fast,
-	&dm816x_tptc2__alwon_l3_fast,
-	&dm816x_tptc3__alwon_l3_fast,
+	&dm81xx_alwon_l3_fast__tpcc,
+	&dm81xx_alwon_l3_fast__tptc0,
+	&dm81xx_alwon_l3_fast__tptc1,
+	&dm81xx_alwon_l3_fast__tptc2,
+	&dm81xx_alwon_l3_fast__tptc3,
+	&dm81xx_tptc0__alwon_l3_fast,
+	&dm81xx_tptc1__alwon_l3_fast,
+	&dm81xx_tptc2__alwon_l3_fast,
+	&dm81xx_tptc3__alwon_l3_fast,
 	&dm81xx_alwon_l3_slow__gpmc,
 	&dm81xx_default_l3_slow__usbss,
 	NULL,
 };
 
-int __init ti81xx_hwmod_init(void)
+int __init dm816x_hwmod_init(void)
 {
 	omap_hwmod_init();
 	return omap_hwmod_register_links(dm816x_hwmod_ocp_ifs);
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 821171cf6b7d..ea56397599c2 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -14,9 +14,18 @@
 #include <linux/kernel.h>
 #include <linux/of_platform.h>
 #include <linux/ti_wilink_st.h>
+#include <linux/wl12xx.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/host.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 
 #include <linux/platform_data/pinctrl-single.h>
 #include <linux/platform_data/iommu-omap.h>
+#include <linux/platform_data/wkup_m3.h>
+
+#include <asm/siginfo.h>
+#include <asm/signal.h>
 
 #include "common.h"
 #include "common-board-devices.h"
@@ -25,13 +34,14 @@
 #include "omap_device.h"
 #include "omap-secure.h"
 #include "soc.h"
+#include "hsmmc.h"
 
 struct pdata_init {
 	const char *compatible;
 	void (*fn)(void);
 };
 
-struct of_dev_auxdata omap_auxdata_lookup[];
+static struct of_dev_auxdata omap_auxdata_lookup[];
 static struct twl4030_gpio_platform_data twl_gpio_auxdata;
 
 #ifdef CONFIG_MACH_NOKIA_N8X0
@@ -128,7 +138,7 @@ static void __init omap3_sbc_t3530_legacy_init(void)
 	omap3_sbc_t3x_usb_hub_init(167, "sb-t35 usb hub");
 }
 
-struct ti_st_plat_data wilink_pdata = {
+static struct ti_st_plat_data wilink_pdata = {
 	.nshutdown_gpio = 137,
 	.dev_name = "/dev/ttyO1",
 	.flow_cntrl = 1,
@@ -268,8 +278,136 @@ static void __init omap3_tao3530_legacy_init(void)
 {
 	hsmmc2_internal_input_clk();
 }
+
+/* omap3pandora legacy devices */
+#define PANDORA_WIFI_IRQ_GPIO		21
+#define PANDORA_WIFI_NRESET_GPIO	23
+
+static struct platform_device pandora_backlight = {
+	.name	= "pandora-backlight",
+	.id	= -1,
+};
+
+static struct regulator_consumer_supply pandora_vmmc3_supply[] = {
+	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.2"),
+};
+
+static struct regulator_init_data pandora_vmmc3 = {
+	.constraints = {
+		.valid_ops_mask		= REGULATOR_CHANGE_STATUS,
+	},
+	.num_consumer_supplies	= ARRAY_SIZE(pandora_vmmc3_supply),
+	.consumer_supplies	= pandora_vmmc3_supply,
+};
+
+static struct fixed_voltage_config pandora_vwlan = {
+	.supply_name		= "vwlan",
+	.microvolts		= 1800000, /* 1.8V */
+	.gpio			= PANDORA_WIFI_NRESET_GPIO,
+	.startup_delay		= 50000, /* 50ms */
+	.enable_high		= 1,
+	.init_data		= &pandora_vmmc3,
+};
+
+static struct platform_device pandora_vwlan_device = {
+	.name		= "reg-fixed-voltage",
+	.id		= 1,
+	.dev = {
+		.platform_data = &pandora_vwlan,
+	},
+};
+
+static void pandora_wl1251_init_card(struct mmc_card *card)
+{
+	/*
+	 * We have TI wl1251 attached to MMC3. Pass this information to
+	 * SDIO core because it can't be probed by normal methods.
+	 */
+	if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) {
+		card->quirks |= MMC_QUIRK_NONSTD_SDIO;
+		card->cccr.wide_bus = 1;
+		card->cis.vendor = 0x104c;
+		card->cis.device = 0x9066;
+		card->cis.blksize = 512;
+		card->cis.max_dtr = 24000000;
+		card->ocr = 0x80;
+	}
+}
+
+static struct omap2_hsmmc_info pandora_mmc3[] = {
+	{
+		.mmc		= 3,
+		.caps		= MMC_CAP_4_BIT_DATA | MMC_CAP_POWER_OFF_CARD,
+		.gpio_cd	= -EINVAL,
+		.gpio_wp	= -EINVAL,
+		.init_card	= pandora_wl1251_init_card,
+	},
+	{}	/* Terminator */
+};
+
+static void __init pandora_wl1251_init(void)
+{
+	struct wl1251_platform_data pandora_wl1251_pdata;
+	int ret;
+
+	memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata));
+
+	pandora_wl1251_pdata.power_gpio = -1;
+
+	ret = gpio_request_one(PANDORA_WIFI_IRQ_GPIO, GPIOF_IN, "wl1251 irq");
+	if (ret < 0)
+		goto fail;
+
+	pandora_wl1251_pdata.irq = gpio_to_irq(PANDORA_WIFI_IRQ_GPIO);
+	if (pandora_wl1251_pdata.irq < 0)
+		goto fail_irq;
+
+	pandora_wl1251_pdata.use_eeprom = true;
+	ret = wl1251_set_platform_data(&pandora_wl1251_pdata);
+	if (ret < 0)
+		goto fail_irq;
+
+	return;
+
+fail_irq:
+	gpio_free(PANDORA_WIFI_IRQ_GPIO);
+fail:
+	pr_err("wl1251 board initialisation failed\n");
+}
+
+static void __init omap3_pandora_legacy_init(void)
+{
+	platform_device_register(&pandora_backlight);
+	platform_device_register(&pandora_vwlan_device);
+	omap_hsmmc_init(pandora_mmc3);
+	omap_hsmmc_late_init(pandora_mmc3);
+	pandora_wl1251_init();
+}
 #endif /* CONFIG_ARCH_OMAP3 */
 
+#ifdef CONFIG_SOC_TI81XX
+static int fault_fixed_up;
+
+static int t410_abort_handler(unsigned long addr, unsigned int fsr,
+			      struct pt_regs *regs)
+{
+	if ((fsr == 0x406 || fsr == 0xc06) && !fault_fixed_up) {
+		pr_warn("External imprecise Data abort at addr=%#lx, fsr=%#x ignored.\n",
+			addr, fsr);
+		fault_fixed_up = 1;
+		return 0;
+	}
+
+	return 1;
+}
+
+static void __init t410_abort_init(void)
+{
+	hook_fault_code(16 + 6, t410_abort_handler, SIGBUS, BUS_OBJERR,
+			"imprecise external abort");
+}
+#endif
+
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
 static struct iommu_platform_data omap4_iommu_pdata = {
 	.reset_name = "mmu_cache",
@@ -278,6 +416,14 @@ static struct iommu_platform_data omap4_iommu_pdata = {
 };
 #endif
 
+#if defined(CONFIG_SOC_AM33XX) || defined(CONFIG_SOC_AM43XX)
+static struct wkup_m3_platform_data wkup_m3_data = {
+	.reset_name = "wkup_m3",
+	.assert_reset = omap_device_assert_hardreset,
+	.deassert_reset = omap_device_deassert_hardreset,
+};
+#endif
+
 #ifdef CONFIG_SOC_OMAP5
 static void __init omap5_uevm_legacy_init(void)
 {
@@ -323,7 +469,7 @@ static struct pdata_init auxdata_quirks[] __initdata = {
 	{ /* sentinel */ },
 };
 
-struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
+static struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 #ifdef CONFIG_MACH_NOKIA_N8X0
 	OF_DEV_AUXDATA("ti,omap2420-mmc", 0x4809c000, "mmci-omap.0", NULL),
 	OF_DEV_AUXDATA("menelaus", 0x72, "1-0072", &n8x0_menelaus_platform_data),
@@ -340,6 +486,10 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("ti,am3517-emac", 0x5c000000, "davinci_emac.0",
 		       &am35xx_emac_pdata),
 #endif
+#ifdef CONFIG_SOC_AM33XX
+	OF_DEV_AUXDATA("ti,am3352-wkup-m3", 0x44d00000, "44d00000.wkup_m3",
+		       &wkup_m3_data),
+#endif
 #ifdef CONFIG_ARCH_OMAP4
 	OF_DEV_AUXDATA("ti,omap4-padconf", 0x4a100040, "4a100040.pinmux", &pcs_pdata),
 	OF_DEV_AUXDATA("ti,omap4-padconf", 0x4a31e040, "4a31e040.pinmux", &pcs_pdata),
@@ -353,6 +503,8 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 #endif
 #ifdef CONFIG_SOC_AM43XX
 	OF_DEV_AUXDATA("ti,am437-padconf", 0x44e10800, "44e10800.pinmux", &pcs_pdata),
+	OF_DEV_AUXDATA("ti,am4372-wkup-m3", 0x44d00000, "44d00000.wkup_m3",
+		       &wkup_m3_data),
 #endif
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
 	OF_DEV_AUXDATA("ti,omap4-iommu", 0x4a066000, "4a066000.mmu",
@@ -381,6 +533,11 @@ static struct pdata_init pdata_quirks[] __initdata = {
 	{ "ti,omap3-evm-37xx", omap3_evm_legacy_init, },
 	{ "ti,am3517-evm", am3517_evm_legacy_init, },
 	{ "technexion,omap3-tao3530", omap3_tao3530_legacy_init, },
+	{ "openpandora,omap3-pandora-600mhz", omap3_pandora_legacy_init, },
+	{ "openpandora,omap3-pandora-1ghz", omap3_pandora_legacy_init, },
+#endif
+#ifdef CONFIG_SOC_TI81XX
+	{ "hp,t410", t410_abort_init, },
 #endif
 #ifdef CONFIG_SOC_OMAP5
 	{ "ti,omap5-uevm", omap5_uevm_legacy_init, },
diff --git a/arch/arm/mach-omap2/pm24xx.c b/arch/arm/mach-omap2/pm24xx.c
index b1aad7e1426c..2a1a4180d5d0 100644
--- a/arch/arm/mach-omap2/pm24xx.c
+++ b/arch/arm/mach-omap2/pm24xx.c
@@ -25,6 +25,7 @@
 #include <linux/sysfs.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/irq.h>
 #include <linux/time.h>
diff --git a/arch/arm/mach-omap2/powerdomains3xxx_data.c b/arch/arm/mach-omap2/powerdomains3xxx_data.c
index 70bc7066a4c2..d31c495175c1 100644
--- a/arch/arm/mach-omap2/powerdomains3xxx_data.c
+++ b/arch/arm/mach-omap2/powerdomains3xxx_data.c
@@ -349,6 +349,41 @@ static struct powerdomain device_81xx_pwrdm = {
 	.voltdm		  = { .name = "core" },
 };
 
+static struct powerdomain gem_814x_pwrdm = {
+	.name		= "gem_pwrdm",
+	.prcm_offs	= TI814X_PRM_DSP_MOD,
+	.pwrsts		= PWRSTS_OFF_ON,
+	.voltdm		= { .name = "dsp" },
+};
+
+static struct powerdomain ivahd_814x_pwrdm = {
+	.name		= "ivahd_pwrdm",
+	.prcm_offs	= TI814X_PRM_HDVICP_MOD,
+	.pwrsts		= PWRSTS_OFF_ON,
+	.voltdm		= { .name = "iva" },
+};
+
+static struct powerdomain hdvpss_814x_pwrdm = {
+	.name		= "hdvpss_pwrdm",
+	.prcm_offs	= TI814X_PRM_HDVPSS_MOD,
+	.pwrsts		= PWRSTS_OFF_ON,
+	.voltdm		= { .name = "dsp" },
+};
+
+static struct powerdomain sgx_814x_pwrdm = {
+	.name		= "sgx_pwrdm",
+	.prcm_offs	= TI814X_PRM_GFX_MOD,
+	.pwrsts		= PWRSTS_OFF_ON,
+	.voltdm		= { .name = "core" },
+};
+
+static struct powerdomain isp_814x_pwrdm = {
+	.name		= "isp_pwrdm",
+	.prcm_offs	= TI814X_PRM_ISP_MOD,
+	.pwrsts		= PWRSTS_OFF_ON,
+	.voltdm		= { .name = "core" },
+};
+
 static struct powerdomain active_816x_pwrdm = {
 	.name		  = "active_pwrdm",
 	.prcm_offs	  = TI816X_PRM_ACTIVE_MOD,
@@ -448,7 +483,18 @@ static struct powerdomain *powerdomains_am35x[] __initdata = {
 	NULL
 };
 
-static struct powerdomain *powerdomains_ti81xx[] __initdata = {
+static struct powerdomain *powerdomains_ti814x[] __initdata = {
+	&alwon_81xx_pwrdm,
+	&device_81xx_pwrdm,
+	&gem_814x_pwrdm,
+	&ivahd_814x_pwrdm,
+	&hdvpss_814x_pwrdm,
+	&sgx_814x_pwrdm,
+	&isp_814x_pwrdm,
+	NULL
+};
+
+static struct powerdomain *powerdomains_ti816x[] __initdata = {
 	&alwon_81xx_pwrdm,
 	&device_81xx_pwrdm,
 	&active_816x_pwrdm,
@@ -460,6 +506,73 @@ static struct powerdomain *powerdomains_ti81xx[] __initdata = {
 	NULL
 };
 
+/* TI81XX specific ops */
+#define TI81XX_PM_PWSTCTRL				0x0000
+#define TI81XX_RM_RSTCTRL				0x0010
+#define TI81XX_PM_PWSTST				0x0004
+
+static int ti81xx_pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
+{
+	omap2_prm_rmw_mod_reg_bits(OMAP_POWERSTATE_MASK,
+				   (pwrst << OMAP_POWERSTATE_SHIFT),
+				   pwrdm->prcm_offs, TI81XX_PM_PWSTCTRL);
+	return 0;
+}
+
+static int ti81xx_pwrdm_read_next_pwrst(struct powerdomain *pwrdm)
+{
+	return omap2_prm_read_mod_bits_shift(pwrdm->prcm_offs,
+					     TI81XX_PM_PWSTCTRL,
+					     OMAP_POWERSTATE_MASK);
+}
+
+static int ti81xx_pwrdm_read_pwrst(struct powerdomain *pwrdm)
+{
+	return omap2_prm_read_mod_bits_shift(pwrdm->prcm_offs,
+		(pwrdm->prcm_offs == TI814X_PRM_GFX_MOD) ? TI81XX_RM_RSTCTRL :
+					     TI81XX_PM_PWSTST,
+					     OMAP_POWERSTATEST_MASK);
+}
+
+static int ti81xx_pwrdm_read_logic_pwrst(struct powerdomain *pwrdm)
+{
+	return omap2_prm_read_mod_bits_shift(pwrdm->prcm_offs,
+		(pwrdm->prcm_offs == TI814X_PRM_GFX_MOD) ? TI81XX_RM_RSTCTRL :
+					     TI81XX_PM_PWSTST,
+					     OMAP3430_LOGICSTATEST_MASK);
+}
+
+static int ti81xx_pwrdm_wait_transition(struct powerdomain *pwrdm)
+{
+	u32 c = 0;
+
+	while ((omap2_prm_read_mod_reg(pwrdm->prcm_offs,
+		(pwrdm->prcm_offs == TI814X_PRM_GFX_MOD) ? TI81XX_RM_RSTCTRL :
+				       TI81XX_PM_PWSTST) &
+		OMAP_INTRANSITION_MASK) &&
+		(c++ < PWRDM_TRANSITION_BAILOUT))
+			udelay(1);
+
+	if (c > PWRDM_TRANSITION_BAILOUT) {
+		pr_err("powerdomain: %s timeout waiting for transition\n",
+		       pwrdm->name);
+		return -EAGAIN;
+	}
+
+	pr_debug("powerdomain: completed transition in %d loops\n", c);
+
+	return 0;
+}
+
+/* For dm814x we need to fix up fix GFX pwstst and rstctrl reg offsets */
+static struct pwrdm_ops ti81xx_pwrdm_operations = {
+	.pwrdm_set_next_pwrst	= ti81xx_pwrdm_set_next_pwrst,
+	.pwrdm_read_next_pwrst	= ti81xx_pwrdm_read_next_pwrst,
+	.pwrdm_read_pwrst	= ti81xx_pwrdm_read_pwrst,
+	.pwrdm_read_logic_pwrst	= ti81xx_pwrdm_read_logic_pwrst,
+	.pwrdm_wait_transition	= ti81xx_pwrdm_wait_transition,
+};
+
 void __init omap3xxx_powerdomains_init(void)
 {
 	unsigned int rev;
@@ -467,15 +580,22 @@ void __init omap3xxx_powerdomains_init(void)
 	if (!cpu_is_omap34xx() && !cpu_is_ti81xx())
 		return;
 
-	pwrdm_register_platform_funcs(&omap3_pwrdm_operations);
+	/* Only 81xx needs custom pwrdm_operations */
+	if (!cpu_is_ti81xx())
+		pwrdm_register_platform_funcs(&omap3_pwrdm_operations);;
 
 	rev = omap_rev();
 
 	if (rev == AM35XX_REV_ES1_0 || rev == AM35XX_REV_ES1_1) {
 		pwrdm_register_pwrdms(powerdomains_am35x);
+	} else if (rev == TI8148_REV_ES1_0 || rev == TI8148_REV_ES2_0 ||
+		   rev == TI8148_REV_ES2_1) {
+		pwrdm_register_platform_funcs(&ti81xx_pwrdm_operations);
+		pwrdm_register_pwrdms(powerdomains_ti814x);
 	} else if (rev == TI8168_REV_ES1_0 || rev == TI8168_REV_ES1_1
 			|| rev == TI8168_REV_ES2_0 || rev == TI8168_REV_ES2_1) {
-		pwrdm_register_pwrdms(powerdomains_ti81xx);
+		pwrdm_register_platform_funcs(&ti81xx_pwrdm_operations);
+		pwrdm_register_pwrdms(powerdomains_ti816x);
 	} else {
 		pwrdm_register_pwrdms(powerdomains_omap3430_common);
 
diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h
index 6ae0b3a1781e..c8f590b7c32d 100644
--- a/arch/arm/mach-omap2/prcm-common.h
+++ b/arch/arm/mach-omap2/prcm-common.h
@@ -51,6 +51,12 @@
 /*
  * TI81XX PRM module offsets
  */
+#define TI814X_PRM_DSP_MOD				0x0a00
+#define TI814X_PRM_HDVICP_MOD				0x0c00
+#define TI814X_PRM_ISP_MOD				0x0d00
+#define TI814X_PRM_HDVPSS_MOD				0x0e00
+#define TI814X_PRM_GFX_MOD				0x0f00
+
 #define TI81XX_PRM_DEVICE_MOD			0x0000
 #define TI816X_PRM_ACTIVE_MOD			0x0a00
 #define TI81XX_PRM_DEFAULT_MOD			0x0b00
@@ -472,6 +478,7 @@ struct omap_prcm_irq {
  * struct omap_prcm_irq_setup - PRCM interrupt controller details
  * @ack: PRM register offset for the first PRM_IRQSTATUS_MPU register
  * @mask: PRM register offset for the first PRM_IRQENABLE_MPU register
+ * @pm_ctrl: PRM register offset for the PRM_IO_PMCTRL register
  * @nr_regs: number of PRM_IRQ{STATUS,ENABLE}_MPU* registers
  * @nr_irqs: number of entries in the @irqs array
  * @irqs: ptr to an array of PRCM interrupt bits (see @nr_irqs)
@@ -494,6 +501,7 @@ struct omap_prcm_irq {
 struct omap_prcm_irq_setup {
 	u16 ack;
 	u16 mask;
+	u16 pm_ctrl;
 	u8 nr_regs;
 	u8 nr_irqs;
 	const struct omap_prcm_irq *irqs;
diff --git a/arch/arm/mach-omap2/prcm43xx.h b/arch/arm/mach-omap2/prcm43xx.h
index 7eebc27fa892..7c34c44eb0ae 100644
--- a/arch/arm/mach-omap2/prcm43xx.h
+++ b/arch/arm/mach-omap2/prcm43xx.h
@@ -25,6 +25,13 @@
 #define AM43XX_PRM_WKUP_INST				0x2000
 #define AM43XX_PRM_DEVICE_INST				0x4000
 
+/* PRM_IRQ offsets */
+#define AM43XX_PRM_IRQSTATUS_MPU_OFFSET			0x0004
+#define AM43XX_PRM_IRQENABLE_MPU_OFFSET			0x0008
+
+/* Other PRM offsets */
+#define AM43XX_PRM_IO_PMCTRL_OFFSET			0x0024
+
 /* RM RSTCTRL offsets */
 #define AM43XX_RM_PER_RSTCTRL_OFFSET			0x0010
 #define AM43XX_RM_GFX_RSTCTRL_OFFSET			0x0010
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 4541700f743a..30768003f854 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -18,13 +18,14 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/of_irq.h>
-
+#include <linux/of.h>
 
 #include "soc.h"
 #include "iomap.h"
 #include "common.h"
 #include "vp.h"
 #include "prm44xx.h"
+#include "prcm43xx.h"
 #include "prm-regbits-44xx.h"
 #include "prcm44xx.h"
 #include "prminst44xx.h"
@@ -45,6 +46,7 @@ static const struct omap_prcm_irq omap4_prcm_irqs[] = {
 static struct omap_prcm_irq_setup omap4_prcm_irq_setup = {
 	.ack			= OMAP4_PRM_IRQSTATUS_MPU_OFFSET,
 	.mask			= OMAP4_PRM_IRQENABLE_MPU_OFFSET,
+	.pm_ctrl		= OMAP4_PRM_IO_PMCTRL_OFFSET,
 	.nr_regs		= 2,
 	.irqs			= omap4_prcm_irqs,
 	.nr_irqs		= ARRAY_SIZE(omap4_prcm_irqs),
@@ -216,11 +218,11 @@ static inline u32 _read_pending_irq_reg(u16 irqen_offs, u16 irqst_offs)
  */
 static void omap44xx_prm_read_pending_irqs(unsigned long *events)
 {
-	events[0] = _read_pending_irq_reg(OMAP4_PRM_IRQENABLE_MPU_OFFSET,
-					  OMAP4_PRM_IRQSTATUS_MPU_OFFSET);
+	int i;
 
-	events[1] = _read_pending_irq_reg(OMAP4_PRM_IRQENABLE_MPU_2_OFFSET,
-					  OMAP4_PRM_IRQSTATUS_MPU_2_OFFSET);
+	for (i = 0; i < omap4_prcm_irq_setup.nr_regs; i++)
+		events[i] = _read_pending_irq_reg(omap4_prcm_irq_setup.mask +
+				i * 4, omap4_prcm_irq_setup.ack + i * 4);
 }
 
 /**
@@ -250,17 +252,17 @@ static void omap44xx_prm_ocp_barrier(void)
  */
 static void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask)
 {
-	saved_mask[0] =
-		omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
-					OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-	saved_mask[1] =
-		omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
-					OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
+	int i;
+	u16 reg;
+
+	for (i = 0; i < omap4_prcm_irq_setup.nr_regs; i++) {
+		reg = omap4_prcm_irq_setup.mask + i * 4;
 
-	omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
-				 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-	omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
-				 OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
+		saved_mask[i] =
+			omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
+						reg);
+		omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST, reg);
+	}
 
 	/* OCP barrier */
 	omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
@@ -279,10 +281,12 @@ static void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask)
  */
 static void omap44xx_prm_restore_irqen(u32 *saved_mask)
 {
-	omap4_prm_write_inst_reg(saved_mask[0], OMAP4430_PRM_OCP_SOCKET_INST,
-				 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-	omap4_prm_write_inst_reg(saved_mask[1], OMAP4430_PRM_OCP_SOCKET_INST,
-				 OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
+	int i;
+
+	for (i = 0; i < omap4_prcm_irq_setup.nr_regs; i++)
+		omap4_prm_write_inst_reg(saved_mask[i],
+					 OMAP4430_PRM_OCP_SOCKET_INST,
+					 omap4_prcm_irq_setup.mask + i * 4);
 }
 
 /**
@@ -306,10 +310,10 @@ static void omap44xx_prm_reconfigure_io_chain(void)
 	omap4_prm_rmw_inst_reg_bits(OMAP4430_WUCLK_CTRL_MASK,
 				    OMAP4430_WUCLK_CTRL_MASK,
 				    inst,
-				    OMAP4_PRM_IO_PMCTRL_OFFSET);
+				    omap4_prcm_irq_setup.pm_ctrl);
 	omap_test_timeout(
 		(((omap4_prm_read_inst_reg(inst,
-					   OMAP4_PRM_IO_PMCTRL_OFFSET) &
+					   omap4_prcm_irq_setup.pm_ctrl) &
 		   OMAP4430_WUCLK_STATUS_MASK) >>
 		  OMAP4430_WUCLK_STATUS_SHIFT) == 1),
 		MAX_IOPAD_LATCH_TIME, i);
@@ -319,10 +323,10 @@ static void omap44xx_prm_reconfigure_io_chain(void)
 	/* Trigger WUCLKIN disable */
 	omap4_prm_rmw_inst_reg_bits(OMAP4430_WUCLK_CTRL_MASK, 0x0,
 				    inst,
-				    OMAP4_PRM_IO_PMCTRL_OFFSET);
+				    omap4_prcm_irq_setup.pm_ctrl);
 	omap_test_timeout(
 		(((omap4_prm_read_inst_reg(inst,
-					   OMAP4_PRM_IO_PMCTRL_OFFSET) &
+					   omap4_prcm_irq_setup.pm_ctrl) &
 		   OMAP4430_WUCLK_STATUS_MASK) >>
 		  OMAP4430_WUCLK_STATUS_SHIFT) == 0),
 		MAX_IOPAD_LATCH_TIME, i);
@@ -350,7 +354,7 @@ static void __init omap44xx_prm_enable_io_wakeup(void)
 	omap4_prm_rmw_inst_reg_bits(OMAP4430_GLOBAL_WUEN_MASK,
 				    OMAP4430_GLOBAL_WUEN_MASK,
 				    inst,
-				    OMAP4_PRM_IO_PMCTRL_OFFSET);
+				    omap4_prcm_irq_setup.pm_ctrl);
 }
 
 /**
@@ -719,6 +723,15 @@ int __init omap44xx_prm_init(const struct omap_prcm_init_data *data)
 
 	omap4_prminst_set_prm_dev_inst(data->device_inst_offset);
 
+	/* Add AM437X specific differences */
+	if (of_device_is_compatible(data->np, "ti,am4-prcm")) {
+		omap4_prcm_irq_setup.nr_irqs = 1;
+		omap4_prcm_irq_setup.nr_regs = 1;
+		omap4_prcm_irq_setup.pm_ctrl = AM43XX_PRM_IO_PMCTRL_OFFSET;
+		omap4_prcm_irq_setup.ack = AM43XX_PRM_IRQSTATUS_MPU_OFFSET;
+		omap4_prcm_irq_setup.mask = AM43XX_PRM_IRQENABLE_MPU_OFFSET;
+	}
+
 	return prm_register(&omap44xx_prm_ll_data);
 }
 
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 7add7994dbfc..257e98c26618 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -696,6 +696,7 @@ static struct omap_prcm_init_data am4_prm_data __initdata = {
 	.index = TI_CLKM_PRM,
 	.init = omap44xx_prm_init,
 	.device_inst_offset = AM43XX_PRM_DEVICE_INST,
+	.flags = PRM_HAS_IO_WAKEUP,
 };
 #endif
 
@@ -705,7 +706,7 @@ static struct omap_prcm_init_data scrm_data __initdata = {
 };
 #endif
 
-static const struct of_device_id omap_prcm_dt_match_table[] __initconst = {
+static const struct of_device_id const omap_prcm_dt_match_table[] __initconst = {
 #ifdef CONFIG_SOC_AM33XX
 	{ .compatible = "ti,am3-prcm", .data = &am3_prm_data },
 #endif
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index ad1bb9431e94..9b09d85d811a 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -333,14 +333,12 @@ ENDPROC(omap4_cpu_resume)
 
 #endif	/* defined(CONFIG_SMP) && defined(CONFIG_PM) */
 
-ENTRY(omap_bus_sync)
-	ret	lr
-ENDPROC(omap_bus_sync)
-
 ENTRY(omap_do_wfi)
 	stmfd	sp!, {lr}
+#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER
 	/* Drain interconnect write buffers. */
-	bl omap_bus_sync
+	bl	omap_interconnect_sync
+#endif
 
 	/*
 	 * Execute an ISB instruction to ensure that all of the
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index cac46d852da1..e4d8701f99f9 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -102,38 +102,38 @@ static int omap2_gp_timer_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void omap2_gp_timer_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *evt)
+static int omap2_gp_timer_shutdown(struct clock_event_device *evt)
+{
+	__omap_dm_timer_stop(&clkev, OMAP_TIMER_POSTED, clkev.rate);
+	return 0;
+}
+
+static int omap2_gp_timer_set_periodic(struct clock_event_device *evt)
 {
 	u32 period;
 
 	__omap_dm_timer_stop(&clkev, OMAP_TIMER_POSTED, clkev.rate);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		period = clkev.rate / HZ;
-		period -= 1;
-		/* Looks like we need to first set the load value separately */
-		__omap_dm_timer_write(&clkev, OMAP_TIMER_LOAD_REG,
-				      0xffffffff - period, OMAP_TIMER_POSTED);
-		__omap_dm_timer_load_start(&clkev,
-					OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST,
-					0xffffffff - period, OMAP_TIMER_POSTED);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	period = clkev.rate / HZ;
+	period -= 1;
+	/* Looks like we need to first set the load value separately */
+	__omap_dm_timer_write(&clkev, OMAP_TIMER_LOAD_REG, 0xffffffff - period,
+			      OMAP_TIMER_POSTED);
+	__omap_dm_timer_load_start(&clkev,
+				   OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST,
+				   0xffffffff - period, OMAP_TIMER_POSTED);
+	return 0;
 }
 
 static struct clock_event_device clockevent_gpt = {
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 300,
-	.set_next_event	= omap2_gp_timer_set_next_event,
-	.set_mode	= omap2_gp_timer_set_mode,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 300,
+	.set_next_event		= omap2_gp_timer_set_next_event,
+	.set_state_shutdown	= omap2_gp_timer_shutdown,
+	.set_state_periodic	= omap2_gp_timer_set_periodic,
+	.set_state_oneshot	= omap2_gp_timer_shutdown,
+	.tick_resume		= omap2_gp_timer_shutdown,
 };
 
 static struct property device_disabled = {
@@ -208,8 +208,7 @@ static void __init omap_dmtimer_init(void)
 	/* If we are a secure device, remove any secure timer nodes */
 	if ((omap_type() != OMAP2_DEVICE_TYPE_GP)) {
 		np = omap_get_timer_dt(omap_timer_match, "ti,timer-secure");
-		if (np)
-			of_node_put(np);
+		of_node_put(np);
 	}
 }
 
@@ -649,23 +648,10 @@ static OMAP_SYS_32K_TIMER_INIT(4, 1, "timer_32k_ck", "ti,timer-alwon",
 
 #ifdef CONFIG_ARCH_OMAP4
 #ifdef CONFIG_HAVE_ARM_TWD
-static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, OMAP44XX_LOCAL_TWD_BASE, 29);
 void __init omap4_local_timer_init(void)
 {
 	omap4_sync32k_timer_init();
-	/* Local timers are not supprted on OMAP4430 ES1.0 */
-	if (omap_rev() != OMAP4430_REV_ES1_0) {
-		int err;
-
-		if (of_have_populated_dt()) {
-			clocksource_of_init();
-			return;
-		}
-
-		err = twd_local_timer_register(&twd_local_timer);
-		if (err)
-			pr_err("twd_local_timer_register failed %d\n", err);
-	}
+	clocksource_of_init();
 }
 #else
 void __init omap4_local_timer_init(void)
diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c
index 076fd20d7e5a..e5a35f6b83a7 100644
--- a/arch/arm/mach-omap2/vc.c
+++ b/arch/arm/mach-omap2/vc.c
@@ -563,7 +563,7 @@ struct i2c_init_data {
 	u8 hsscll_12;
 };
 
-static const __initdata struct i2c_init_data omap4_i2c_timing_data[] = {
+static const struct i2c_init_data const omap4_i2c_timing_data[] __initconst = {
 	{
 		.load = 50,
 		.loadbits = 0x3,
diff --git a/arch/arm/mach-omap2/voltagedomains3xxx_data.c b/arch/arm/mach-omap2/voltagedomains3xxx_data.c
index 261bb7cb4e60..307676d8c53c 100644
--- a/arch/arm/mach-omap2/voltagedomains3xxx_data.c
+++ b/arch/arm/mach-omap2/voltagedomains3xxx_data.c
@@ -95,7 +95,7 @@ static struct voltagedomain *voltagedomains_am35xx[] __initdata = {
 };
 
 
-static const char *sys_clk_name __initdata = "sys_ck";
+static const char *const sys_clk_name __initconst = "sys_ck";
 
 void __init omap3xxx_voltagedomains_init(void)
 {
diff --git a/arch/arm/mach-omap2/voltagedomains44xx_data.c b/arch/arm/mach-omap2/voltagedomains44xx_data.c
index 48b22a0a0c88..9b1f245b57d6 100644
--- a/arch/arm/mach-omap2/voltagedomains44xx_data.c
+++ b/arch/arm/mach-omap2/voltagedomains44xx_data.c
@@ -92,7 +92,7 @@ static struct voltagedomain *voltagedomains_omap4[] __initdata = {
 	NULL,
 };
 
-static const char *sys_clk_name __initdata = "sys_clkin_ck";
+static const char *const sys_clk_name __initconst = "sys_clkin_ck";
 
 void __init omap44xx_voltagedomains_init(void)
 {
diff --git a/arch/arm/mach-omap2/voltagedomains54xx_data.c b/arch/arm/mach-omap2/voltagedomains54xx_data.c
index 33d22b87252d..af5ff6496441 100644
--- a/arch/arm/mach-omap2/voltagedomains54xx_data.c
+++ b/arch/arm/mach-omap2/voltagedomains54xx_data.c
@@ -78,7 +78,7 @@ static struct voltagedomain *voltagedomains_omap5[] __initdata = {
 	NULL,
 };
 
-static const char *sys_clk_name __initdata = "sys_clkin";
+static const char *const sys_clk_name __initconst = "sys_clkin";
 
 void __init omap54xx_voltagedomains_init(void)
 {
diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig
index 2412efb6cdd9..08d2be2ea41f 100644
--- a/arch/arm/mach-orion5x/Kconfig
+++ b/arch/arm/mach-orion5x/Kconfig
@@ -78,11 +78,11 @@ config MACH_LINKSTATION_LSCHL
 	  Buffalo Linkstation Live v3 (LS-CHL) platform.
 
 config MACH_LINKSTATION_MINI
-	bool "Buffalo Linkstation Mini"
-	select I2C_BOARDINFO
+	bool "Buffalo Linkstation Mini (Flattened Device Tree)"
+	select ARCH_ORION5X_DT
 	help
 	  Say 'Y' here if you want your kernel to support the
-	  Buffalo Linkstation Mini platform.
+	  Buffalo Linkstation Mini (LS-WSGL) platform.
 
 config MACH_LINKSTATION_LS_HGL
 	bool "Buffalo Linkstation LS-HGL"
diff --git a/arch/arm/mach-orion5x/Makefile b/arch/arm/mach-orion5x/Makefile
index a40b5c9a58c4..a1e0fbe6a7a1 100644
--- a/arch/arm/mach-orion5x/Makefile
+++ b/arch/arm/mach-orion5x/Makefile
@@ -4,7 +4,6 @@ obj-$(CONFIG_MACH_RD88F5182)	+= rd88f5182-setup.o
 obj-$(CONFIG_MACH_KUROBOX_PRO)	+= kurobox_pro-setup.o
 obj-$(CONFIG_MACH_TERASTATION_PRO2)	+= terastation_pro2-setup.o
 obj-$(CONFIG_MACH_LINKSTATION_PRO) += kurobox_pro-setup.o
-obj-$(CONFIG_MACH_LINKSTATION_MINI) += lsmini-setup.o
 obj-$(CONFIG_MACH_LINKSTATION_LS_HGL) += ls_hgl-setup.o
 obj-$(CONFIG_MACH_DNS323)	+= dns323-setup.o
 obj-$(CONFIG_MACH_TS209)	+= ts209-setup.o tsx09-common.o
diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c
index 79f033b1ddff..d0871786dd8a 100644
--- a/arch/arm/mach-orion5x/board-dt.c
+++ b/arch/arm/mach-orion5x/board-dt.c
@@ -16,7 +16,6 @@
 #include <linux/of_platform.h>
 #include <linux/cpu.h>
 #include <linux/mbus.h>
-#include <linux/clk-provider.h>
 #include <linux/clocksource.h>
 #include <asm/system_misc.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index 09d2a26985da..f267e58a8283 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -236,9 +236,7 @@ static int __init dns323_read_mac_addr(void)
 	}
 
 	iounmap(mac_page);
-	printk("DNS-323: Found ethernet MAC address: ");
-	for (i = 0; i < 6; i++)
-		printk("%.2x%s", addr[i], (i < 5) ? ":" : ".\n");
+	printk("DNS-323: Found ethernet MAC address: %pM\n", addr);
 
 	memcpy(dns323_eth_data.mac_addr, addr, 6);
 
diff --git a/arch/arm/mach-orion5x/include/mach/irqs.h b/arch/arm/mach-orion5x/include/mach/irqs.h
index a6fa9d8f12d8..2431d9923427 100644
--- a/arch/arm/mach-orion5x/include/mach/irqs.h
+++ b/arch/arm/mach-orion5x/include/mach/irqs.h
@@ -16,42 +16,42 @@
 /*
  * Orion Main Interrupt Controller
  */
-#define IRQ_ORION5X_BRIDGE		0
-#define IRQ_ORION5X_DOORBELL_H2C	1
-#define IRQ_ORION5X_DOORBELL_C2H	2
-#define IRQ_ORION5X_UART0		3
-#define IRQ_ORION5X_UART1		4
-#define IRQ_ORION5X_I2C			5
-#define IRQ_ORION5X_GPIO_0_7		6
-#define IRQ_ORION5X_GPIO_8_15		7
-#define IRQ_ORION5X_GPIO_16_23		8
-#define IRQ_ORION5X_GPIO_24_31		9
-#define IRQ_ORION5X_PCIE0_ERR		10
-#define IRQ_ORION5X_PCIE0_INT		11
-#define IRQ_ORION5X_USB1_CTRL		12
-#define IRQ_ORION5X_DEV_BUS_ERR		14
-#define IRQ_ORION5X_PCI_ERR		15
-#define IRQ_ORION5X_USB_BR_ERR		16
-#define IRQ_ORION5X_USB0_CTRL		17
-#define IRQ_ORION5X_ETH_RX		18
-#define IRQ_ORION5X_ETH_TX		19
-#define IRQ_ORION5X_ETH_MISC		20
-#define IRQ_ORION5X_ETH_SUM		21
-#define IRQ_ORION5X_ETH_ERR		22
-#define IRQ_ORION5X_IDMA_ERR		23
-#define IRQ_ORION5X_IDMA_0		24
-#define IRQ_ORION5X_IDMA_1		25
-#define IRQ_ORION5X_IDMA_2		26
-#define IRQ_ORION5X_IDMA_3		27
-#define IRQ_ORION5X_CESA		28
-#define IRQ_ORION5X_SATA		29
-#define IRQ_ORION5X_XOR0		30
-#define IRQ_ORION5X_XOR1		31
+#define IRQ_ORION5X_BRIDGE		(1 + 0)
+#define IRQ_ORION5X_DOORBELL_H2C	(1 + 1)
+#define IRQ_ORION5X_DOORBELL_C2H	(1 + 2)
+#define IRQ_ORION5X_UART0		(1 + 3)
+#define IRQ_ORION5X_UART1		(1 + 4)
+#define IRQ_ORION5X_I2C			(1 + 5)
+#define IRQ_ORION5X_GPIO_0_7		(1 + 6)
+#define IRQ_ORION5X_GPIO_8_15		(1 + 7)
+#define IRQ_ORION5X_GPIO_16_23		(1 + 8)
+#define IRQ_ORION5X_GPIO_24_31		(1 + 9)
+#define IRQ_ORION5X_PCIE0_ERR		(1 + 10)
+#define IRQ_ORION5X_PCIE0_INT		(1 + 11)
+#define IRQ_ORION5X_USB1_CTRL		(1 + 12)
+#define IRQ_ORION5X_DEV_BUS_ERR		(1 + 14)
+#define IRQ_ORION5X_PCI_ERR		(1 + 15)
+#define IRQ_ORION5X_USB_BR_ERR		(1 + 16)
+#define IRQ_ORION5X_USB0_CTRL		(1 + 17)
+#define IRQ_ORION5X_ETH_RX		(1 + 18)
+#define IRQ_ORION5X_ETH_TX		(1 + 19)
+#define IRQ_ORION5X_ETH_MISC		(1 + 20)
+#define IRQ_ORION5X_ETH_SUM		(1 + 21)
+#define IRQ_ORION5X_ETH_ERR		(1 + 22)
+#define IRQ_ORION5X_IDMA_ERR		(1 + 23)
+#define IRQ_ORION5X_IDMA_0		(1 + 24)
+#define IRQ_ORION5X_IDMA_1		(1 + 25)
+#define IRQ_ORION5X_IDMA_2		(1 + 26)
+#define IRQ_ORION5X_IDMA_3		(1 + 27)
+#define IRQ_ORION5X_CESA		(1 + 28)
+#define IRQ_ORION5X_SATA		(1 + 29)
+#define IRQ_ORION5X_XOR0		(1 + 30)
+#define IRQ_ORION5X_XOR1		(1 + 31)
 
 /*
  * Orion General Purpose Pins
  */
-#define IRQ_ORION5X_GPIO_START	32
+#define IRQ_ORION5X_GPIO_START	33
 #define NR_GPIO_IRQS		32
 
 #define NR_IRQS			(IRQ_ORION5X_GPIO_START + NR_GPIO_IRQS)
diff --git a/arch/arm/mach-orion5x/irq.c b/arch/arm/mach-orion5x/irq.c
index cd4bac4d7e43..086ecb87d885 100644
--- a/arch/arm/mach-orion5x/irq.c
+++ b/arch/arm/mach-orion5x/irq.c
@@ -42,7 +42,7 @@ __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs)
 	stat = readl_relaxed(MAIN_IRQ_CAUSE);
 	stat &= readl_relaxed(MAIN_IRQ_MASK);
 	if (stat) {
-		unsigned int hwirq = __fls(stat);
+		unsigned int hwirq = 1 + __fls(stat);
 		handle_IRQ(hwirq, regs);
 		return;
 	}
@@ -51,7 +51,7 @@ __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs)
 
 void __init orion5x_init_irq(void)
 {
-	orion_irq_init(0, MAIN_IRQ_MASK);
+	orion_irq_init(1, MAIN_IRQ_MASK);
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	set_handle_irq(orion5x_legacy_handle_irq);
diff --git a/arch/arm/mach-orion5x/lsmini-setup.c b/arch/arm/mach-orion5x/lsmini-setup.c
deleted file mode 100644
index a6493e76f96d..000000000000
--- a/arch/arm/mach-orion5x/lsmini-setup.c
+++ /dev/null
@@ -1,280 +0,0 @@
-/*
- * arch/arm/mach-orion5x/lsmini-setup.c
- *
- * Maintainer: Alexey Kopytko <alexey@kopytko.ru>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/leds.h>
-#include <linux/gpio_keys.h>
-#include <linux/input.h>
-#include <linux/i2c.h>
-#include <linux/ata_platform.h>
-#include <linux/gpio.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/orion5x.h>
-#include "common.h"
-#include "mpp.h"
-
-/*****************************************************************************
- * Linkstation Mini Info
- ****************************************************************************/
-
-/*
- * 256K NOR flash Device bus boot chip select
- */
-
-#define LSMINI_NOR_BOOT_BASE	0xf4000000
-#define LSMINI_NOR_BOOT_SIZE	SZ_256K
-
-/*****************************************************************************
- * 256KB NOR Flash on BOOT Device
- ****************************************************************************/
-
-static struct physmap_flash_data lsmini_nor_flash_data = {
-	.width		= 1,
-};
-
-static struct resource lsmini_nor_flash_resource = {
-	.flags	= IORESOURCE_MEM,
-	.start	= LSMINI_NOR_BOOT_BASE,
-	.end	= LSMINI_NOR_BOOT_BASE + LSMINI_NOR_BOOT_SIZE - 1,
-};
-
-static struct platform_device lsmini_nor_flash = {
-	.name			= "physmap-flash",
-	.id			= 0,
-	.dev		= {
-		.platform_data	= &lsmini_nor_flash_data,
-	},
-	.num_resources		= 1,
-	.resource		= &lsmini_nor_flash_resource,
-};
-
-/*****************************************************************************
- * Ethernet
- ****************************************************************************/
-
-static struct mv643xx_eth_platform_data lsmini_eth_data = {
-	.phy_addr	= 8,
-};
-
-/*****************************************************************************
- * RTC 5C372a on I2C bus
- ****************************************************************************/
-
-static struct i2c_board_info __initdata lsmini_i2c_rtc = {
-	I2C_BOARD_INFO("rs5c372a", 0x32),
-};
-
-/*****************************************************************************
- * LEDs attached to GPIO
- ****************************************************************************/
-
-#define LSMINI_GPIO_LED_ALARM	2
-#define LSMINI_GPIO_LED_INFO	3
-#define LSMINI_GPIO_LED_FUNC	9
-#define LSMINI_GPIO_LED_PWR	14
-
-static struct gpio_led lsmini_led_pins[] = {
-	{
-		.name	   = "alarm:red",
-		.gpio	   = LSMINI_GPIO_LED_ALARM,
-		.active_low     = 1,
-	}, {
-		.name	   = "info:amber",
-		.gpio	   = LSMINI_GPIO_LED_INFO,
-		.active_low     = 1,
-	}, {
-		.name	   = "func:blue:top",
-		.gpio	   = LSMINI_GPIO_LED_FUNC,
-		.active_low     = 1,
-	}, {
-		.name	   = "power:blue:bottom",
-		.gpio	   = LSMINI_GPIO_LED_PWR,
-	},
-};
-
-static struct gpio_led_platform_data lsmini_led_data = {
-	.leds	   = lsmini_led_pins,
-	.num_leds       = ARRAY_SIZE(lsmini_led_pins),
-};
-
-static struct platform_device lsmini_leds = {
-	.name   = "leds-gpio",
-	.id     = -1,
-	.dev    = {
-		.platform_data  = &lsmini_led_data,
-	},
-};
-
-/****************************************************************************
- * GPIO Attached Keys
- ****************************************************************************/
-
-#define LSMINI_GPIO_KEY_FUNC       15
-#define LSMINI_GPIO_KEY_POWER	   18
-#define LSMINI_GPIO_KEY_AUTOPOWER 17
-
-#define LSMINI_SW_POWER		0x00
-#define LSMINI_SW_AUTOPOWER	0x01
-
-static struct gpio_keys_button lsmini_buttons[] = {
-	{
-		.code	   = KEY_OPTION,
-		.gpio	   = LSMINI_GPIO_KEY_FUNC,
-		.desc	   = "Function Button",
-		.active_low     = 1,
-	}, {
-		.type		= EV_SW,
-		.code	   = LSMINI_SW_POWER,
-		.gpio	   = LSMINI_GPIO_KEY_POWER,
-		.desc	   = "Power-on Switch",
-		.active_low     = 1,
-	}, {
-		.type		= EV_SW,
-		.code	   = LSMINI_SW_AUTOPOWER,
-		.gpio	   = LSMINI_GPIO_KEY_AUTOPOWER,
-		.desc	   = "Power-auto Switch",
-		.active_low     = 1,
-	},
-};
-
-static struct gpio_keys_platform_data lsmini_button_data = {
-	.buttons	= lsmini_buttons,
-	.nbuttons       = ARRAY_SIZE(lsmini_buttons),
-};
-
-static struct platform_device lsmini_button_device = {
-	.name	   = "gpio-keys",
-	.id	     = -1,
-	.num_resources  = 0,
-	.dev	    = {
-		.platform_data  = &lsmini_button_data,
-	},
-};
-
-
-/*****************************************************************************
- * SATA
- ****************************************************************************/
-static struct mv_sata_platform_data lsmini_sata_data = {
-	.n_ports	= 2,
-};
-
-
-/*****************************************************************************
- * Linkstation Mini specific power off method: reboot
- ****************************************************************************/
-/*
- * On the Linkstation Mini, the shutdown process is following:
- * - Userland monitors key events until the power switch goes to off position
- * - The board reboots
- * - U-boot starts and goes into an idle mode waiting for the user
- *   to move the switch to ON position
- */
-
-static void lsmini_power_off(void)
-{
-	orion5x_restart(REBOOT_HARD, NULL);
-}
-
-
-/*****************************************************************************
- * General Setup
- ****************************************************************************/
-
-#define LSMINI_GPIO_USB_POWER	16
-#define LSMINI_GPIO_AUTO_POWER	17
-#define LSMINI_GPIO_POWER	18
-
-#define LSMINI_GPIO_HDD_POWER0	1
-#define LSMINI_GPIO_HDD_POWER1	19
-
-static unsigned int lsmini_mpp_modes[] __initdata = {
-	MPP0_UNUSED, /* LED_RESERVE1 (unused) */
-	MPP1_GPIO, /* HDD_PWR */
-	MPP2_GPIO, /* LED_ALARM */
-	MPP3_GPIO, /* LED_INFO */
-	MPP4_UNUSED,
-	MPP5_UNUSED,
-	MPP6_UNUSED,
-	MPP7_UNUSED,
-	MPP8_UNUSED,
-	MPP9_GPIO, /* LED_FUNC */
-	MPP10_UNUSED,
-	MPP11_UNUSED, /* LED_ETH (dummy) */
-	MPP12_UNUSED,
-	MPP13_UNUSED,
-	MPP14_GPIO, /* LED_PWR */
-	MPP15_GPIO, /* FUNC */
-	MPP16_GPIO, /* USB_PWR */
-	MPP17_GPIO, /* AUTO_POWER */
-	MPP18_GPIO, /* POWER */
-	MPP19_GPIO, /* HDD_PWR1 */
-	0,
-};
-
-static void __init lsmini_init(void)
-{
-	/*
-	 * Setup basic Orion functions. Need to be called early.
-	 */
-	orion5x_init();
-
-	orion5x_mpp_conf(lsmini_mpp_modes);
-
-	/*
-	 * Configure peripherals.
-	 */
-	orion5x_ehci0_init();
-	orion5x_ehci1_init();
-	orion5x_eth_init(&lsmini_eth_data);
-	orion5x_i2c_init();
-	orion5x_sata_init(&lsmini_sata_data);
-	orion5x_uart0_init();
-	orion5x_xor_init();
-
-	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
-				    ORION_MBUS_DEVBUS_BOOT_ATTR,
-				    LSMINI_NOR_BOOT_BASE,
-				    LSMINI_NOR_BOOT_SIZE);
-	platform_device_register(&lsmini_nor_flash);
-
-	platform_device_register(&lsmini_button_device);
-
-	platform_device_register(&lsmini_leds);
-
-	i2c_register_board_info(0, &lsmini_i2c_rtc, 1);
-
-	/* enable USB power */
-	gpio_set_value(LSMINI_GPIO_USB_POWER, 1);
-
-	/* register power-off method */
-	pm_power_off = lsmini_power_off;
-
-	pr_info("%s: finished\n", __func__);
-}
-
-#ifdef CONFIG_MACH_LINKSTATION_MINI
-MACHINE_START(LINKSTATION_MINI, "Buffalo Linkstation Mini")
-	/* Maintainer: Alexey Kopytko <alexey@kopytko.ru> */
-	.atag_offset	= 0x100,
-	.init_machine	= lsmini_init,
-	.map_io		= orion5x_map_io,
-	.init_early	= orion5x_init_early,
-	.init_irq	= orion5x_init_irq,
-	.init_time	= orion5x_timer_init,
-	.fixup		= tag_fixup_mem32,
-	.restart	= orion5x_restart,
-MACHINE_END
-#endif
diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c
index 7189827d641d..24b2959719fa 100644
--- a/arch/arm/mach-orion5x/tsx09-common.c
+++ b/arch/arm/mach-orion5x/tsx09-common.c
@@ -101,9 +101,7 @@ static int __init qnap_tsx09_check_mac_addr(const char *addr_str)
 		addr[i] = byte;
 	}
 
-	printk(KERN_INFO "tsx09: found ethernet mac address ");
-	for (i = 0; i < 6; i++)
-		printk("%.2x%s", addr[i], (i < 5) ? ":" : ".\n");
+	printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr);
 
 	memcpy(qnap_tsx09_eth_data.mac_addr, addr, 6);
 
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index e03d8b5c9ad0..9ab8932403e5 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -4,6 +4,7 @@ menuconfig ARCH_SIRF
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
 	select NO_IOPORT_MAP
+	select REGMAP
 	select PINCTRL
 	select PINCTRL_SIRF
 	help
diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c
index d99d08eeb966..83e94c95e314 100644
--- a/arch/arm/mach-prima2/pm.c
+++ b/arch/arm/mach-prima2/pm.c
@@ -16,6 +16,7 @@
 #include <linux/of_platform.h>
 #include <linux/io.h>
 #include <linux/rtc/sirfsoc_rtciobrg.h>
+#include <asm/outercache.h>
 #include <asm/suspend.h>
 #include <asm/hardware/cache-l2x0.h>
 
diff --git a/arch/arm/mach-prima2/rtciobrg.c b/arch/arm/mach-prima2/rtciobrg.c
index 8f66d8f7ca75..d4852d24dc7d 100644
--- a/arch/arm/mach-prima2/rtciobrg.c
+++ b/arch/arm/mach-prima2/rtciobrg.c
@@ -1,5 +1,5 @@
 /*
- * RTC I/O Bridge interfaces for CSR SiRFprimaII
+ * RTC I/O Bridge interfaces for CSR SiRFprimaII/atlas7
  * ARM access the registers of SYSRTC, GPSRTC and PWRC through this module
  *
  * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/regmap.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
@@ -66,6 +67,7 @@ u32 sirfsoc_rtc_iobrg_readl(u32 addr)
 {
 	unsigned long flags, val;
 
+	/* TODO: add hwspinlock to sync with M3 */
 	spin_lock_irqsave(&rtciobrg_lock, flags);
 
 	val = __sirfsoc_rtc_iobrg_readl(addr);
@@ -90,6 +92,7 @@ void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr)
 {
 	unsigned long flags;
 
+	 /* TODO: add hwspinlock to sync with M3 */
 	spin_lock_irqsave(&rtciobrg_lock, flags);
 
 	sirfsoc_rtc_iobrg_pre_writel(val, addr);
@@ -102,6 +105,45 @@ void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr)
 }
 EXPORT_SYMBOL_GPL(sirfsoc_rtc_iobrg_writel);
 
+
+static int regmap_iobg_regwrite(void *context, unsigned int reg,
+				   unsigned int val)
+{
+	sirfsoc_rtc_iobrg_writel(val, reg);
+	return 0;
+}
+
+static int regmap_iobg_regread(void *context, unsigned int reg,
+				  unsigned int *val)
+{
+	*val = (u32)sirfsoc_rtc_iobrg_readl(reg);
+	return 0;
+}
+
+static struct regmap_bus regmap_iobg = {
+	.reg_write = regmap_iobg_regwrite,
+	.reg_read = regmap_iobg_regread,
+};
+
+/**
+ * devm_regmap_init_iobg(): Initialise managed register map
+ *
+ * @iobg: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_iobg(struct device *dev,
+				    const struct regmap_config *config)
+{
+	const struct regmap_bus *bus = &regmap_iobg;
+
+	return devm_regmap_init(dev, bus, dev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_iobg);
+
 static const struct of_device_id rtciobrg_ids[] = {
 	{ .compatible = "sirf,prima2-rtciobg" },
 	{}
@@ -132,7 +174,7 @@ static int __init sirfsoc_rtciobrg_init(void)
 }
 postcore_initcall(sirfsoc_rtciobrg_init);
 
-MODULE_AUTHOR("Zhiwu Song <zhiwu.song@csr.com>, "
-		"Barry Song <baohua.song@csr.com>");
+MODULE_AUTHOR("Zhiwu Song <zhiwu.song@csr.com>");
+MODULE_AUTHOR("Barry Song <baohua.song@csr.com>");
 MODULE_DESCRIPTION("CSR SiRFprimaII rtc io bridge");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index d897292712eb..70366b35d299 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -496,18 +496,18 @@ static struct irq_chip balloon3_irq_chip = {
 	.irq_unmask	= balloon3_unmask_irq,
 };
 
-static void balloon3_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void balloon3_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
 	unsigned long pending = __raw_readl(BALLOON3_INT_CONTROL_REG) &
 					balloon3_irq_enabled;
 	do {
-		/* clear useless edge notification */
-		if (desc->irq_data.chip->irq_ack) {
-			struct irq_data *d;
+		struct irq_data *d = irq_desc_get_irq_data(desc);
+		struct irq_chip *chip = irq_data_get_chip(d);
+		unsigned int irq;
 
-			d = irq_get_irq_data(BALLOON3_AUX_NIRQ);
-			desc->irq_data.chip->irq_ack(d);
-		}
+		/* clear useless edge notification */
+		if (chip->irq_ack)
+			chip->irq_ack(d);
 
 		while (pending) {
 			irq = BALLOON3_IRQ(0) + __ffs(pending);
@@ -528,7 +528,7 @@ static void __init balloon3_init_irq(void)
 	for (irq = BALLOON3_IRQ(0); irq <= BALLOON3_IRQ(7); irq++) {
 		irq_set_chip_and_handler(irq, &balloon3_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	irq_set_chained_handler(BALLOON3_AUX_NIRQ, balloon3_irq_handler);
diff --git a/arch/arm/mach-pxa/capc7117.c b/arch/arm/mach-pxa/capc7117.c
index c092730749b9..bf366b39fa61 100644
--- a/arch/arm/mach-pxa/capc7117.c
+++ b/arch/arm/mach-pxa/capc7117.c
@@ -24,6 +24,7 @@
 #include <linux/ata_platform.h>
 #include <linux/serial_8250.h>
 #include <linux/gpio.h>
+#include <linux/regulator/machine.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -144,6 +145,8 @@ static void __init capc7117_init(void)
 
 	capc7117_uarts_init();
 	capc7117_ide_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(CAPC7117,
diff --git a/arch/arm/mach-pxa/cm-x2xx-pci.c b/arch/arm/mach-pxa/cm-x2xx-pci.c
index d8f816c24a2f..1fa79f1f832d 100644
--- a/arch/arm/mach-pxa/cm-x2xx-pci.c
+++ b/arch/arm/mach-pxa/cm-x2xx-pci.c
@@ -29,8 +29,9 @@
 void __iomem *it8152_base_address;
 static int cmx2xx_it8152_irq_gpio;
 
-static void cmx2xx_it8152_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void cmx2xx_it8152_irq_demux(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	/* clear our parent irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
diff --git a/arch/arm/mach-pxa/cm-x2xx.c b/arch/arm/mach-pxa/cm-x2xx.c
index bb99f59a36d8..a17a91eb8e9a 100644
--- a/arch/arm/mach-pxa/cm-x2xx.c
+++ b/arch/arm/mach-pxa/cm-x2xx.c
@@ -13,6 +13,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
+#include <linux/regulator/machine.h>
 
 #include <linux/dm9000.h>
 #include <linux/leds.h>
@@ -466,6 +467,8 @@ static void __init cmx2xx_init(void)
 	cmx2xx_init_ac97();
 	cmx2xx_init_touchscreen();
 	cmx2xx_init_leds();
+
+	regulator_has_full_constraints();
 }
 
 static void __init cmx2xx_init_irq(void)
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 4d3588d26c2a..5851f4c254c1 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -835,6 +835,8 @@ static void __init cm_x300_init(void)
 	cm_x300_init_ac97();
 	cm_x300_init_wi2wi();
 	cm_x300_init_bl();
+
+	regulator_has_full_constraints();
 }
 
 static void __init cm_x300_fixup(struct tag *tags, char **cmdline)
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 5f9d9303b346..3503826333c7 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -18,6 +18,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/machine.h>
 #include <linux/ucb1400.h>
 
 #include <asm/mach/arch.h>
@@ -294,6 +295,8 @@ static void __init colibri_pxa270_init(void)
 		printk(KERN_ERR "Illegal colibri_pxa270_baseboard type %d\n",
 				colibri_pxa270_baseboard);
 	}
+
+	regulator_has_full_constraints();
 }
 
 /* The "Income s.r.o. SH-Dmaster PXA270 SBC" board can be booted either
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 35434662dc7c..e6ce669b54af 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -17,6 +17,7 @@
 #include <linux/platform_data/camera-pxa.h>
 #include <mach/audio.h>
 #include <mach/hardware.h>
+#include <linux/platform_data/mmp_dma.h>
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
 
 #include "devices.h"
@@ -1193,3 +1194,39 @@ void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info)
 	pd->dev.platform_data = info;
 	platform_device_add(pd);
 }
+
+static struct mmp_dma_platdata pxa_dma_pdata = {
+	.dma_channels	= 0,
+};
+
+static struct resource pxa_dma_resource[] = {
+	[0] = {
+		.start	= 0x40000000,
+		.end	= 0x4000ffff,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_DMA,
+		.end	= IRQ_DMA,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static u64 pxadma_dmamask = 0xffffffffUL;
+
+static struct platform_device pxa2xx_pxa_dma = {
+	.name		= "pxa-dma",
+	.id		= 0,
+	.dev		= {
+		.dma_mask = &pxadma_dmamask,
+		.coherent_dma_mask = 0xffffffff,
+	},
+	.num_resources	= ARRAY_SIZE(pxa_dma_resource),
+	.resource	= pxa_dma_resource,
+};
+
+void __init pxa2xx_set_dmac_info(int nb_channels)
+{
+	pxa_dma_pdata.dma_channels = nb_channels;
+	pxa_register_device(&pxa2xx_pxa_dma, &pxa_dma_pdata);
+}
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 51531ecffca8..9d7072b04045 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -1306,6 +1306,8 @@ static void __init em_x270_init(void)
 	em_x270_init_i2c();
 	em_x270_init_camera();
 	em_x270_userspace_consumers_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(EM_X270, "Compulab EM-X270")
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index c98511c5abd1..9b0eb0252af6 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -26,6 +26,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/can/platform/mcp251x.h>
+#include <linux/regulator/machine.h>
 
 #include "generic.h"
 
@@ -185,6 +186,8 @@ static void __init icontrol_init(void)
 	mxm_8x10_mmc_init();
 
 	icontrol_can_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 98608c5575cb..9c10248fadcc 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -133,7 +133,6 @@ static int pxa_irq_map(struct irq_domain *h, unsigned int virq,
 	irq_set_chip_and_handler(virq, &pxa_internal_irq_chip,
 				 handle_level_irq);
 	irq_set_chip_data(virq, base);
-	set_irq_flags(virq, IRQF_VALID);
 
 	return 0;
 }
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index eaee2c20b189..b070167deef2 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -120,8 +120,9 @@ static struct irq_chip lpd270_irq_chip = {
 	.irq_unmask	= lpd270_unmask_irq,
 };
 
-static void lpd270_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void lpd270_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq;
 	unsigned long pending;
 
 	pending = __raw_readw(LPD270_INT_STATUS) & lpd270_irq_enabled;
@@ -151,7 +152,7 @@ static void __init lpd270_init_irq(void)
 	for (irq = LPD270_IRQ(2); irq <= LPD270_IRQ(4); irq++) {
 		irq_set_chip_and_handler(irq, &lpd270_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 	irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), lpd270_irq_handler);
 	irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING);
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index 2897da2a5df6..9a0c8affdadb 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -284,8 +284,9 @@ static struct irq_chip pcm990_irq_chip = {
 	.irq_unmask	= pcm990_unmask_irq,
 };
 
-static void pcm990_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void pcm990_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq;
 	unsigned long pending;
 
 	pending = ~pcm990_cpld_readb(PCM990_CTRL_INTSETCLR);
@@ -311,7 +312,7 @@ static void __init pcm990_init_irq(void)
 	for (irq = PCM027_IRQ(0); irq <= PCM027_IRQ(3); irq++) {
 		irq_set_chip_and_handler(irq, &pcm990_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	/* disable all Interrupts */
diff --git a/arch/arm/mach-pxa/pxa-dt.c b/arch/arm/mach-pxa/pxa-dt.c
index 7e0e5bd0c9de..8e0e62ccdced 100644
--- a/arch/arm/mach-pxa/pxa-dt.c
+++ b/arch/arm/mach-pxa/pxa-dt.c
@@ -19,7 +19,7 @@
 #include "generic.h"
 
 #ifdef CONFIG_PXA3xx
-static const struct of_dev_auxdata pxa3xx_auxdata_lookup[] __initconst = {
+static const struct of_dev_auxdata const pxa3xx_auxdata_lookup[] __initconst = {
 	OF_DEV_AUXDATA("mrvl,pxa-uart",		0x40100000, "pxa2xx-uart.0", NULL),
 	OF_DEV_AUXDATA("mrvl,pxa-uart",		0x40200000, "pxa2xx-uart.1", NULL),
 	OF_DEV_AUXDATA("mrvl,pxa-uart",		0x40700000, "pxa2xx-uart.2", NULL),
@@ -39,7 +39,7 @@ static void __init pxa3xx_dt_init(void)
 			     pxa3xx_auxdata_lookup, NULL);
 }
 
-static const char *pxa3xx_dt_board_compat[] __initdata = {
+static const char *const pxa3xx_dt_board_compat[] __initconst = {
 	"marvell,pxa300",
 	"marvell,pxa310",
 	"marvell,pxa320",
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index 23a90c62ec11..1dc85ffc3e20 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -206,6 +206,7 @@ static int __init pxa25x_init(void)
 		register_syscore_ops(&pxa_irq_syscore_ops);
 		register_syscore_ops(&pxa2xx_mfp_syscore_ops);
 
+		pxa2xx_set_dmac_info(16);
 		pxa_register_device(&pxa25x_device_gpio, &pxa25x_gpio_info);
 		ret = platform_add_devices(pxa25x_devices,
 					   ARRAY_SIZE(pxa25x_devices));
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index b5abdeb5bb2d..e6aae9e8adfb 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -310,6 +310,7 @@ static int __init pxa27x_init(void)
 		if (!of_have_populated_dt()) {
 			pxa_register_device(&pxa27x_device_gpio,
 					    &pxa27x_gpio_info);
+			pxa2xx_set_dmac_info(32);
 			ret = platform_add_devices(devices,
 						   ARRAY_SIZE(devices));
 		}
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index bd4cbef15ccf..165638462a2f 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -325,7 +325,7 @@ static void __init pxa_init_ext_wakeup_irq(int (*fn)(struct irq_data *,
 	for (irq = IRQ_WAKEUP0; irq <= IRQ_WAKEUP1; irq++) {
 		irq_set_chip_and_handler(irq, &pxa_ext_wakeup_chip,
 					 handle_edge_irq);
-		set_irq_flags(irq, IRQF_VALID);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
 	}
 
 	pxa_ext_wakeup_chip.irq_set_wake = fn;
@@ -431,6 +431,7 @@ static int __init pxa3xx_init(void)
 		if (of_have_populated_dt())
 			return 0;
 
+		pxa2xx_set_dmac_info(32);
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 		if (ret)
 			return ret;
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 051a6555cbf9..bdc0c41bc4fd 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -841,11 +841,9 @@ static int sharpsl_pm_probe(struct platform_device *pdev)
 	sharpsl_pm.charge_mode = CHRG_OFF;
 	sharpsl_pm.flags = 0;
 
-	init_timer(&sharpsl_pm.ac_timer);
-	sharpsl_pm.ac_timer.function = sharpsl_ac_timer;
+	setup_timer(&sharpsl_pm.ac_timer, sharpsl_ac_timer, 0UL);
 
-	init_timer(&sharpsl_pm.chrg_full_timer);
-	sharpsl_pm.chrg_full_timer.function = sharpsl_chrg_full_timer;
+	setup_timer(&sharpsl_pm.chrg_full_timer, sharpsl_chrg_full_timer, 0UL);
 
 	led_trigger_register_simple("sharpsl-charge", &sharpsl_charge_led_trigger);
 
diff --git a/arch/arm/mach-pxa/tosa-bt.c b/arch/arm/mach-pxa/tosa-bt.c
index 685deff861d2..e0a53208880a 100644
--- a/arch/arm/mach-pxa/tosa-bt.c
+++ b/arch/arm/mach-pxa/tosa-bt.c
@@ -131,17 +131,4 @@ static struct platform_driver tosa_bt_driver = {
 		.name = "tosa-bt",
 	},
 };
-
-
-static int __init tosa_bt_init(void)
-{
-	return platform_driver_register(&tosa_bt_driver);
-}
-
-static void __exit tosa_bt_exit(void)
-{
-	platform_driver_unregister(&tosa_bt_driver);
-}
-
-module_init(tosa_bt_init);
-module_exit(tosa_bt_exit);
+module_platform_driver(tosa_bt_driver);
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 872dcb20e757..066e3a250ee0 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -26,6 +26,7 @@
 #include <linux/dm9000.h>
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/partitions.h>
+#include <linux/regulator/machine.h>
 #include <linux/i2c/pxa-i2c.h>
 
 #include <asm/types.h>
@@ -534,6 +535,8 @@ static void __init trizeps4_init(void)
 
 	BCR_writew(trizeps_conxs_bcr);
 	board_backlight_power(1);
+
+	regulator_has_full_constraints();
 }
 
 static void __init trizeps4_map_io(void)
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index de3b08073fe7..4841d6cefe76 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -276,8 +276,9 @@ static inline unsigned long viper_irq_pending(void)
 			viper_irq_enabled_mask;
 }
 
-static void viper_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void viper_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq;
 	unsigned long pending;
 
 	pending = viper_irq_pending();
@@ -313,7 +314,7 @@ static void __init viper_init_irq(void)
 		isa_irq = viper_bit_to_irq(level);
 		irq_set_chip_and_handler(isa_irq, &viper_irq_chip,
 					 handle_edge_irq);
-		set_irq_flags(isa_irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(isa_irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	irq_set_chained_handler(gpio_to_irq(VIPER_CPLD_GPIO),
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index aa89488f961e..54122a983ae3 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -24,6 +24,7 @@
 #include <linux/dm9000.h>
 #include <linux/ucb1400.h>
 #include <linux/ata_platform.h>
+#include <linux/regulator/machine.h>
 #include <linux/regulator/max1586.h>
 #include <linux/i2c/pxa-i2c.h>
 
@@ -711,6 +712,8 @@ static void __init vpac270_init(void)
 	vpac270_ts_init();
 	vpac270_rtc_init();
 	vpac270_ide_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(VPAC270, "Voipac PXA270")
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index ac2ae5c71ab4..6f94dd7b4dee 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -105,8 +105,9 @@ static inline unsigned long zeus_irq_pending(void)
 	return __raw_readw(ZEUS_CPLD_ISA_IRQ) & zeus_irq_enabled_mask;
 }
 
-static void zeus_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void zeus_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq;
 	unsigned long pending;
 
 	pending = zeus_irq_pending();
@@ -151,7 +152,7 @@ static void __init zeus_init_irq(void)
 		isa_irq = zeus_bit_to_irq(level);
 		irq_set_chip_and_handler(isa_irq, &zeus_irq_chip,
 					 handle_edge_irq);
-		set_irq_flags(isa_irq, IRQF_VALID | IRQF_PROBE);
+		irq_clear_status_flags(isa_irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	irq_set_irq_type(gpio_to_irq(ZEUS_ISA_GPIO), IRQ_TYPE_EDGE_RISING);
@@ -868,6 +869,8 @@ static void __init zeus_init(void)
 	i2c_register_board_info(0, ARRAY_AND_SIZE(zeus_i2c_devices));
 	pxa2xx_set_spi_info(3, &pxa2xx_spi_ssp3_master_info);
 	spi_register_board_info(zeus_spi_board_info, ARRAY_SIZE(zeus_spi_board_info));
+
+	regulator_has_full_constraints();
 }
 
 static struct map_desc zeus_io_desc[] __initdata = {
diff --git a/arch/arm/mach-realview/realview-dt.c b/arch/arm/mach-realview/realview-dt.c
index cc28b89dd48f..382cc1b90519 100644
--- a/arch/arm/mach-realview/realview-dt.c
+++ b/arch/arm/mach-realview/realview-dt.c
@@ -13,7 +13,7 @@
 #include <asm/hardware/cache-l2x0.h>
 #include "core.h"
 
-static const char *realview_dt_platform_compat[] __initconst = {
+static const char *const realview_dt_platform_compat[] __initconst = {
 	"arm,realview-eb",
 	"arm,realview-pb1176",
 	"arm,realview-pb11mp",
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index 8fcec1cc101e..3e7a4b761a95 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -72,29 +72,22 @@ static struct reset_control *rockchip_get_core_reset(int cpu)
 static int pmu_set_power_domain(int pd, bool on)
 {
 	u32 val = (on) ? 0 : BIT(pd);
+	struct reset_control *rstc = rockchip_get_core_reset(pd);
 	int ret;
 
+	if (IS_ERR(rstc) && read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) {
+		pr_err("%s: could not get reset control for core %d\n",
+		       __func__, pd);
+		return PTR_ERR(rstc);
+	}
+
 	/*
 	 * We need to soft reset the cpu when we turn off the cpu power domain,
 	 * or else the active processors might be stalled when the individual
 	 * processor is powered down.
 	 */
-	if (read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) {
-		struct reset_control *rstc = rockchip_get_core_reset(pd);
-
-		if (IS_ERR(rstc)) {
-			pr_err("%s: could not get reset control for core %d\n",
-			       __func__, pd);
-			return PTR_ERR(rstc);
-		}
-
-		if (on)
-			reset_control_deassert(rstc);
-		else
-			reset_control_assert(rstc);
-
-		reset_control_put(rstc);
-	}
+	if (!IS_ERR(rstc) && !on)
+		reset_control_assert(rstc);
 
 	ret = regmap_update_bits(pmu, PMU_PWRDN_CON, BIT(pd), val);
 	if (ret < 0) {
@@ -107,11 +100,17 @@ static int pmu_set_power_domain(int pd, bool on)
 		ret = pmu_power_domain_is_on(pd);
 		if (ret < 0) {
 			pr_err("%s: could not read power domain state\n",
-				 __func__);
+			       __func__);
 			return ret;
 		}
 	}
 
+	if (!IS_ERR(rstc)) {
+		if (on)
+			reset_control_deassert(rstc);
+		reset_control_put(rstc);
+	}
+
 	return 0;
 }
 
@@ -130,7 +129,7 @@ static int rockchip_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 	if (cpu >= ncores) {
 		pr_err("%s: cpu %d outside maximum number of cpus %d\n",
-							__func__, cpu, ncores);
+		       __func__, cpu, ncores);
 		return -ENXIO;
 	}
 
@@ -140,14 +139,19 @@ static int rockchip_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		return ret;
 
 	if (read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) {
-		/* We communicate with the bootrom to active the cpus other
+		/*
+		 * We communicate with the bootrom to active the cpus other
 		 * than cpu0, after a blob of initialize code, they will
 		 * stay at wfe state, once they are actived, they will check
 		 * the mailbox:
 		 * sram_base_addr + 4: 0xdeadbeaf
 		 * sram_base_addr + 8: start address for pc
-		 * */
-		udelay(10);
+		 * The cpu0 need to wait the other cpus other than cpu0 entering
+		 * the wfe state.The wait time is affected by many aspects.
+		 * (e.g: cpu frequency, bootrom frequency, sram frequency, ...)
+		 */
+		mdelay(1); /* ensure the cpus other than cpu0 to startup */
+
 		writel(virt_to_phys(secondary_startup), sram_base_addr + 8);
 		writel(0xDEADBEAF, sram_base_addr + 4);
 		dsb_sev();
@@ -317,6 +321,13 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
 #ifdef CONFIG_HOTPLUG_CPU
 static int rockchip_cpu_kill(unsigned int cpu)
 {
+	/*
+	 * We need a delay here to ensure that the dying CPU can finish
+	 * executing v7_coherency_exit() and reach the WFI/WFE state
+	 * prior to having the power domain disabled.
+	 */
+	mdelay(1);
+
 	pmu_set_power_domain(0 + cpu, false);
 	return 1;
 }
@@ -324,7 +335,7 @@ static int rockchip_cpu_kill(unsigned int cpu)
 static void rockchip_cpu_die(unsigned int cpu)
 {
 	v7_exit_coherency_flush(louis);
-	while(1)
+	while (1)
 		cpu_do_idle();
 }
 #endif
@@ -337,4 +348,5 @@ static struct smp_operations rockchip_smp_ops __initdata = {
 	.cpu_die		= rockchip_cpu_die,
 #endif
 };
+
 CPU_METHOD_OF_DECLARE(rk3066_smp, "rockchip,rk3066-smp", &rockchip_smp_ops);
diff --git a/arch/arm/mach-rockchip/pm.c b/arch/arm/mach-rockchip/pm.c
index b0dcbe28f78c..bee8c8051929 100644
--- a/arch/arm/mach-rockchip/pm.c
+++ b/arch/arm/mach-rockchip/pm.c
@@ -45,9 +45,11 @@ static phys_addr_t rk3288_bootram_phy;
 
 static struct regmap *pmu_regmap;
 static struct regmap *sgrf_regmap;
+static struct regmap *grf_regmap;
 
 static u32 rk3288_pmu_pwr_mode_con;
 static u32 rk3288_sgrf_soc_con0;
+static u32 rk3288_sgrf_cpu_con0;
 
 static inline u32 rk3288_l2_config(void)
 {
@@ -66,10 +68,37 @@ static void rk3288_config_bootdata(void)
 	rkpm_bootdata_l2ctlr = rk3288_l2_config();
 }
 
+#define GRF_UOC0_CON0			0x320
+#define GRF_UOC1_CON0			0x334
+#define GRF_UOC2_CON0			0x348
+#define GRF_SIDDQ			BIT(13)
+
+static bool rk3288_slp_disable_osc(void)
+{
+	static const u32 reg_offset[] = { GRF_UOC0_CON0, GRF_UOC1_CON0,
+					  GRF_UOC2_CON0 };
+	u32 reg, i;
+
+	/*
+	 * if any usb phy is still on(GRF_SIDDQ==0), that means we need the
+	 * function of usb wakeup, so do not switch to 32khz, since the usb phy
+	 * clk does not connect to 32khz osc
+	 */
+	for (i = 0; i < ARRAY_SIZE(reg_offset); i++) {
+		regmap_read(grf_regmap, reg_offset[i], &reg);
+		if (!(reg & GRF_SIDDQ))
+			return false;
+	}
+
+	return true;
+}
+
 static void rk3288_slp_mode_set(int level)
 {
 	u32 mode_set, mode_set1;
+	bool osc_disable = rk3288_slp_disable_osc();
 
+	regmap_read(sgrf_regmap, RK3288_SGRF_CPU_CON0, &rk3288_sgrf_cpu_con0);
 	regmap_read(sgrf_regmap, RK3288_SGRF_SOC_CON0, &rk3288_sgrf_soc_con0);
 
 	regmap_read(pmu_regmap, RK3288_PMU_PWRMODE_CON,
@@ -94,9 +123,6 @@ static void rk3288_slp_mode_set(int level)
 	regmap_write(sgrf_regmap, RK3288_SGRF_FAST_BOOT_ADDR,
 		     rk3288_bootram_phy);
 
-	regmap_write(pmu_regmap, RK3288_PMU_WAKEUP_CFG1,
-		     PMU_ARMINT_WAKEUP_EN);
-
 	mode_set = BIT(PMU_GLOBAL_INT_DISABLE) | BIT(PMU_L2FLUSH_EN) |
 		   BIT(PMU_SREF0_ENTER_EN) | BIT(PMU_SREF1_ENTER_EN) |
 		   BIT(PMU_DDR0_GATING_EN) | BIT(PMU_DDR1_GATING_EN) |
@@ -107,13 +133,31 @@ static void rk3288_slp_mode_set(int level)
 
 	if (level == ROCKCHIP_ARM_OFF_LOGIC_DEEP) {
 		/* arm off, logic deep sleep */
-		mode_set |= BIT(PMU_BUS_PD_EN) |
+		mode_set |= BIT(PMU_BUS_PD_EN) | BIT(PMU_PMU_USE_LF) |
 			    BIT(PMU_DDR1IO_RET_EN) | BIT(PMU_DDR0IO_RET_EN) |
-			    BIT(PMU_OSC_24M_DIS) | BIT(PMU_PMU_USE_LF) |
 			    BIT(PMU_ALIVE_USE_LF) | BIT(PMU_PLL_PD_EN);
 
+		if (osc_disable)
+			mode_set |= BIT(PMU_OSC_24M_DIS);
+
 		mode_set1 |= BIT(PMU_CLR_ALIVE) | BIT(PMU_CLR_BUS) |
 			     BIT(PMU_CLR_PERI) | BIT(PMU_CLR_DMA);
+
+		regmap_write(pmu_regmap, RK3288_PMU_WAKEUP_CFG1,
+			     PMU_ARMINT_WAKEUP_EN);
+
+		/*
+		 * In deep suspend we use PMU_PMU_USE_LF to let the rk3288
+		 * switch its main clock supply to the alternative 32kHz
+		 * source. Therefore set 30ms on a 32kHz clock for pmic
+		 * stabilization. Similar 30ms on 24MHz for the other
+		 * mode below.
+		 */
+		regmap_write(pmu_regmap, RK3288_PMU_STABL_CNT, 32 * 30);
+
+		/* only wait for stabilization, if we turned the osc off */
+		regmap_write(pmu_regmap, RK3288_PMU_OSC_CNT,
+					 osc_disable ? 32 * 30 : 0);
 	} else {
 		/*
 		 * arm off, logic normal
@@ -121,6 +165,15 @@ static void rk3288_slp_mode_set(int level)
 		 * wakeup will be error
 		 */
 		mode_set |= BIT(PMU_CLK_CORE_SRC_GATE_EN);
+
+		regmap_write(pmu_regmap, RK3288_PMU_WAKEUP_CFG1,
+			     PMU_ARMINT_WAKEUP_EN | PMU_GPIOINT_WAKEUP_EN);
+
+		/* 30ms on a 24MHz clock for pmic stabilization */
+		regmap_write(pmu_regmap, RK3288_PMU_STABL_CNT, 24000 * 30);
+
+		/* oscillator is still running, so no need to wait */
+		regmap_write(pmu_regmap, RK3288_PMU_OSC_CNT, 0);
 	}
 
 	regmap_write(pmu_regmap, RK3288_PMU_PWRMODE_CON, mode_set);
@@ -129,6 +182,9 @@ static void rk3288_slp_mode_set(int level)
 
 static void rk3288_slp_mode_set_resume(void)
 {
+	regmap_write(sgrf_regmap, RK3288_SGRF_CPU_CON0,
+		     rk3288_sgrf_cpu_con0 | SGRF_DAPDEVICEEN_WRITE);
+
 	regmap_write(pmu_regmap, RK3288_PMU_PWRMODE_CON,
 		     rk3288_pmu_pwr_mode_con);
 
@@ -190,7 +246,14 @@ static int rk3288_suspend_init(struct device_node *np)
 				"rockchip,rk3288-sgrf");
 	if (IS_ERR(sgrf_regmap)) {
 		pr_err("%s: could not find sgrf regmap\n", __func__);
-		return PTR_ERR(pmu_regmap);
+		return PTR_ERR(sgrf_regmap);
+	}
+
+	grf_regmap = syscon_regmap_lookup_by_compatible(
+				"rockchip,rk3288-grf");
+	if (IS_ERR(grf_regmap)) {
+		pr_err("%s: could not find grf regmap\n", __func__);
+		return PTR_ERR(grf_regmap);
 	}
 
 	sram_np = of_find_compatible_node(NULL, NULL,
@@ -221,9 +284,6 @@ static int rk3288_suspend_init(struct device_node *np)
 	memcpy(rk3288_bootram_base, rockchip_slp_cpu_resume,
 	       rk3288_bootram_sz);
 
-	regmap_write(pmu_regmap, RK3288_PMU_OSC_CNT, OSC_STABL_CNT_THRESH);
-	regmap_write(pmu_regmap, RK3288_PMU_STABL_CNT, PMU_STABL_CNT_THRESH);
-
 	return 0;
 }
 
diff --git a/arch/arm/mach-rockchip/pm.h b/arch/arm/mach-rockchip/pm.h
index 3e8d39c0c3d5..b5af26f8336e 100644
--- a/arch/arm/mach-rockchip/pm.h
+++ b/arch/arm/mach-rockchip/pm.h
@@ -59,19 +59,9 @@ static inline void rockchip_suspend_init(void)
 #define SGRF_DAPDEVICEEN		BIT(0)
 #define SGRF_DAPDEVICEEN_WRITE		BIT(16)
 
-#define RK3288_CRU_MODE_CON		0x50
-#define RK3288_CRU_SEL0_CON		0x60
-#define RK3288_CRU_SEL1_CON		0x64
-#define RK3288_CRU_SEL10_CON		0x88
-#define RK3288_CRU_SEL33_CON		0xe4
-#define RK3288_CRU_SEL37_CON		0xf4
-
 /* PMU_WAKEUP_CFG1 bits */
 #define PMU_ARMINT_WAKEUP_EN		BIT(0)
-
-/* wait 30ms for OSC stable and 30ms for pmic stable */
-#define OSC_STABL_CNT_THRESH	(32 * 30)
-#define PMU_STABL_CNT_THRESH	(32 * 30)
+#define PMU_GPIOINT_WAKEUP_EN		BIT(3)
 
 enum rk3288_pwr_mode_con {
 	PMU_PWR_MODE_EN = 0,
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index fcb1d59f7aec..f726d4c4e6dd 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -946,7 +946,7 @@ static int __init ecard_probe(int slot, unsigned irq, card_type_t type)
 		irq_set_chip_and_handler(ec->irq, &ecard_chip,
 					 handle_level_irq);
 		irq_set_chip_data(ec->irq, ec);
-		set_irq_flags(ec->irq, IRQF_VALID);
+		irq_clear_status_flags(ec->irq, IRQ_NOREQUEST);
 	}
 
 #ifdef CONFIG_ARCH_RPC
diff --git a/arch/arm/mach-rpc/irq.c b/arch/arm/mach-rpc/irq.c
index 3e4fa849c64d..66502e6207fe 100644
--- a/arch/arm/mach-rpc/irq.c
+++ b/arch/arm/mach-rpc/irq.c
@@ -117,7 +117,7 @@ extern unsigned char rpc_default_fiq_start, rpc_default_fiq_end;
 
 void __init rpc_init_irq(void)
 {
-	unsigned int irq, flags;
+	unsigned int irq, clr, set = 0;
 
 	iomd_writeb(0, IOMD_IRQMASKA);
 	iomd_writeb(0, IOMD_IRQMASKB);
@@ -128,37 +128,37 @@ void __init rpc_init_irq(void)
 		&rpc_default_fiq_end - &rpc_default_fiq_start);
 
 	for (irq = 0; irq < NR_IRQS; irq++) {
-		flags = IRQF_VALID;
+		clr = IRQ_NOREQUEST;
 
 		if (irq <= 6 || (irq >= 9 && irq <= 15))
-			flags |= IRQF_PROBE;
+			clr |= IRQ_NOPROBE;
 
 		if (irq == 21 || (irq >= 16 && irq <= 19) ||
 		    irq == IRQ_KEYBOARDTX)
-			flags |= IRQF_NOAUTOEN;
+			set |= IRQ_NOAUTOEN;
 
 		switch (irq) {
 		case 0 ... 7:
 			irq_set_chip_and_handler(irq, &iomd_a_chip,
 						 handle_level_irq);
-			set_irq_flags(irq, flags);
+			irq_modify_status(irq, clr, set);
 			break;
 
 		case 8 ... 15:
 			irq_set_chip_and_handler(irq, &iomd_b_chip,
 						 handle_level_irq);
-			set_irq_flags(irq, flags);
+			irq_modify_status(irq, clr, set);
 			break;
 
 		case 16 ... 21:
 			irq_set_chip_and_handler(irq, &iomd_dma_chip,
 						 handle_level_irq);
-			set_irq_flags(irq, flags);
+			irq_modify_status(irq, clr, set);
 			break;
 
 		case 64 ... 71:
 			irq_set_chip(irq, &iomd_fiq_chip);
-			set_irq_flags(irq, IRQF_VALID);
+			irq_modify_status(irq, clr, set);
 			break;
 		}
 	}
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index 23bec3a85b22..ef68ecb27396 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -124,6 +124,11 @@ config S3C24XX_PLL
 	  This also means that the PLL tables for the selected CPU(s) will
 	  be built which may increase the size of the kernel image.
 
+config S3C_SETUP_CAMIF
+	bool
+	help
+	  Compile in common setup code for S3C CAMIF devices
+
 # cpu frequency items common between s3c2410 and s3c2440/s3c2442
 
 config S3C2410_IOTIMING
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index 05920c8a5764..8ac2f58a3480 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -99,3 +99,4 @@ obj-$(CONFIG_S3C2416_SETUP_SDHCI_GPIO)	+= setup-sdhci-gpio.o
 obj-$(CONFIG_S3C2443_SETUP_SPI)		+= setup-spi.o
 obj-$(CONFIG_ARCH_S3C24XX)		+= setup-i2c.o
 obj-$(CONFIG_S3C24XX_SETUP_TS)		+= setup-ts.o
+obj-$(CONFIG_S3C_SETUP_CAMIF)		+= setup-camif.o
diff --git a/arch/arm/mach-s3c24xx/bast-irq.c b/arch/arm/mach-s3c24xx/bast-irq.c
index cb1b791954de..ced1ab86ac83 100644
--- a/arch/arm/mach-s3c24xx/bast-irq.c
+++ b/arch/arm/mach-s3c24xx/bast-irq.c
@@ -147,7 +147,7 @@ static __init int bast_irq_init(void)
 
 			irq_set_chip_and_handler(irqno, &bast_pc104_chip,
 						 handle_level_irq);
-			set_irq_flags(irqno, IRQF_VALID);
+			irq_clear_status_flags(irqno, IRQ_NOREQUEST);
 		}
 	}
 
diff --git a/arch/arm/plat-samsung/include/plat/fb-core.h b/arch/arm/mach-s3c24xx/fb-core.h
index bca383efcf6d..103bdbaddd55 100644
--- a/arch/arm/plat-samsung/include/plat/fb-core.h
+++ b/arch/arm/mach-s3c24xx/fb-core.h
@@ -1,6 +1,4 @@
 /*
- * arch/arm/plat-samsung/include/plat/fb-core.h
- *
  * Copyright 2010 Samsung Electronics Co., Ltd.
  *	Pawel Osciak <p.osciak@samsung.com>
  *
diff --git a/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c b/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
index f886478b88c5..5f028ff84cfe 100644
--- a/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
+++ b/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
@@ -39,7 +39,7 @@ static void __init s3c2416_dt_machine_init(void)
 	s3c_pm_init();
 }
 
-static char const *s3c2416_dt_compat[] __initdata = {
+static const char *const s3c2416_dt_compat[] __initconst = {
 	"samsung,s3c2416",
 	"samsung,s3c2450",
 	NULL
diff --git a/arch/arm/plat-samsung/include/plat/nand-core.h b/arch/arm/mach-s3c24xx/nand-core.h
index 6de20789a95e..7e811fe1cf41 100644
--- a/arch/arm/plat-samsung/include/plat/nand-core.h
+++ b/arch/arm/mach-s3c24xx/nand-core.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-samsung/include/plat/nand-core.h
- *
+/*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
diff --git a/arch/arm/mach-s3c24xx/s3c2412.c b/arch/arm/mach-s3c24xx/s3c2412.c
index 64a13605cfc3..fb5ee8d38913 100644
--- a/arch/arm/mach-s3c24xx/s3c2412.c
+++ b/arch/arm/mach-s3c24xx/s3c2412.c
@@ -40,11 +40,11 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq.h>
 #include <plat/devs.h>
-#include <plat/nand-core.h>
 #include <plat/pm.h>
 #include <plat/regs-spi.h>
 
 #include "common.h"
+#include "nand-core.h"
 #include "regs-dsc.h"
 #include "s3c2412-power.h"
 
diff --git a/arch/arm/mach-s3c24xx/s3c2416.c b/arch/arm/mach-s3c24xx/s3c2416.c
index 3f8ca2a3ef17..621b8648a7ef 100644
--- a/arch/arm/mach-s3c24xx/s3c2416.c
+++ b/arch/arm/mach-s3c24xx/s3c2416.c
@@ -59,12 +59,12 @@
 #include <plat/pm.h>
 
 #include <plat/iic-core.h>
-#include <plat/fb-core.h>
-#include <plat/nand-core.h>
 #include <plat/adc-core.h>
-#include <plat/spi-core.h>
 
 #include "common.h"
+#include "fb-core.h"
+#include "nand-core.h"
+#include "spi-core.h"
 
 static struct map_desc s3c2416_iodesc[] __initdata = {
 	IODESC_ENT(WATCHDOG),
diff --git a/arch/arm/mach-s3c24xx/s3c2443.c b/arch/arm/mach-s3c24xx/s3c2443.c
index 87b6b89d8ee7..b559d378cf43 100644
--- a/arch/arm/mach-s3c24xx/s3c2443.c
+++ b/arch/arm/mach-s3c24xx/s3c2443.c
@@ -41,10 +41,11 @@
 #include <plat/gpio-cfg-helpers.h>
 #include <plat/devs.h>
 #include <plat/cpu.h>
-#include <plat/fb-core.h>
-#include <plat/nand-core.h>
 #include <plat/adc-core.h>
-#include <plat/spi-core.h>
+
+#include "fb-core.h"
+#include "nand-core.h"
+#include "spi-core.h"
 
 static struct map_desc s3c2443_iodesc[] __initdata = {
 	IODESC_ENT(WATCHDOG),
diff --git a/arch/arm/mach-s3c24xx/s3c244x.c b/arch/arm/mach-s3c24xx/s3c244x.c
index b14119585dc7..31fd273269c2 100644
--- a/arch/arm/mach-s3c24xx/s3c244x.c
+++ b/arch/arm/mach-s3c24xx/s3c244x.c
@@ -41,9 +41,9 @@
 #include <plat/devs.h>
 #include <plat/cpu.h>
 #include <plat/pm.h>
-#include <plat/nand-core.h>
 
 #include "common.h"
+#include "nand-core.h"
 #include "regs-dsc.h"
 
 static struct map_desc s3c244x_iodesc[] __initdata = {
diff --git a/arch/arm/plat-samsung/setup-camif.c b/arch/arm/mach-s3c24xx/setup-camif.c
index 72d8edb8927a..72d8edb8927a 100644
--- a/arch/arm/plat-samsung/setup-camif.c
+++ b/arch/arm/mach-s3c24xx/setup-camif.c
diff --git a/arch/arm/plat-samsung/include/plat/spi-core.h b/arch/arm/mach-s3c24xx/spi-core.h
index 0b9428ab3fc3..0b9428ab3fc3 100644
--- a/arch/arm/plat-samsung/include/plat/spi-core.h
+++ b/arch/arm/mach-s3c24xx/spi-core.h
diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig
index eff95e950d81..28c7097e8506 100644
--- a/arch/arm/mach-s3c64xx/Kconfig
+++ b/arch/arm/mach-s3c64xx/Kconfig
@@ -34,6 +34,12 @@ config S3C64XX_DEV_ONENAND1
 	help
 	  Compile in platform device definition for OneNAND1 controller
 
+config SAMSUNG_DEV_BACKLIGHT
+	bool
+	depends on SAMSUNG_DEV_PWM
+	help
+	  Compile in platform device definition LCD backlight with PWM Timer
+
 # platform specific device setup
 
 config S3C64XX_SETUP_I2C0
diff --git a/arch/arm/mach-s3c64xx/Makefile b/arch/arm/mach-s3c64xx/Makefile
index 17f4b07ec763..bb233f342f31 100644
--- a/arch/arm/mach-s3c64xx/Makefile
+++ b/arch/arm/mach-s3c64xx/Makefile
@@ -40,6 +40,8 @@ obj-$(CONFIG_S3C64XX_SETUP_SDHCI_GPIO)	+= setup-sdhci-gpio.o
 obj-$(CONFIG_S3C64XX_SETUP_SPI)		+= setup-spi.o
 obj-$(CONFIG_S3C64XX_SETUP_USB_PHY) += setup-usb-phy.o
 
+obj-$(CONFIG_SAMSUNG_DEV_BACKLIGHT)	+= dev-backlight.o
+
 # Machine support
 
 obj-$(CONFIG_MACH_ANW6410)		+= mach-anw6410.o
diff --git a/arch/arm/plat-samsung/include/plat/ata-core.h b/arch/arm/mach-s3c64xx/ata-core.h
index f5a4ec7141b1..5951f24a9ec8 100644
--- a/arch/arm/plat-samsung/include/plat/ata-core.h
+++ b/arch/arm/mach-s3c64xx/ata-core.h
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-samsung/include/plat/ata-core.h
- *
+/*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
diff --git a/arch/arm/plat-samsung/include/plat/backlight.h b/arch/arm/mach-s3c64xx/backlight.h
index ad530c78fe8c..8dcacac523a2 100644
--- a/arch/arm/plat-samsung/include/plat/backlight.h
+++ b/arch/arm/mach-s3c64xx/backlight.h
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-samsung/include/plat/backlight.h
- *
+/*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *              http://www.samsung.com
  *
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index 16547f2641a3..fd63ecfb2f81 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -21,7 +21,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/clk-provider.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/serial_core.h>
@@ -48,12 +47,12 @@
 #include <plat/devs.h>
 #include <plat/pm.h>
 #include <plat/gpio-cfg.h>
-#include <plat/irq-uart.h>
 #include <plat/pwm-core.h>
 #include <plat/regs-irqtype.h>
-#include <plat/watchdog-reset.h>
 
 #include "common.h"
+#include "irq-uart.h"
+#include "watchdog-reset.h"
 
 /* External clock frequency */
 static unsigned long xtal_f = 12000000, xusbxti_f = 48000000;
@@ -420,7 +419,7 @@ static int __init s3c64xx_init_irq_eint(void)
 	for (irq = IRQ_EINT(0); irq <= IRQ_EINT(27); irq++) {
 		irq_set_chip_and_handler(irq, &s3c_irq_eint, handle_level_irq);
 		irq_set_chip_data(irq, (void *)eint_irq_to_bit(irq));
-		set_irq_flags(irq, IRQF_VALID);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
 	}
 
 	irq_set_chained_handler(IRQ_EINT0_3, s3c_irq_demux_eint0_3);
diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/mach-s3c64xx/dev-backlight.c
index 2157c5b539e6..38c323e68e3f 100644
--- a/arch/arm/plat-samsung/dev-backlight.c
+++ b/arch/arm/mach-s3c64xx/dev-backlight.c
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-samsung/dev-backlight.c
- *
+/*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *              http://www.samsung.com
  *
@@ -18,7 +17,8 @@
 
 #include <plat/devs.h>
 #include <plat/gpio-cfg.h>
-#include <plat/backlight.h>
+
+#include "backlight.h"
 
 struct samsung_bl_drvdata {
 	struct platform_pwm_backlight_data plat_data;
diff --git a/arch/arm/plat-samsung/include/plat/irq-uart.h b/arch/arm/mach-s3c64xx/irq-uart.h
index a9331e49bea3..4b296132962f 100644
--- a/arch/arm/plat-samsung/include/plat/irq-uart.h
+++ b/arch/arm/mach-s3c64xx/irq-uart.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-samsung/include/plat/irq-uart.h
- *
+/*
  * Copyright (c) 2010 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
diff --git a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
index 2fddf38192df..bbf74edd3dd9 100644
--- a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
+++ b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
@@ -15,11 +15,10 @@
 #include <asm/system_misc.h>
 
 #include <plat/cpu.h>
-#include <plat/watchdog-reset.h>
-
 #include <mach/map.h>
 
 #include "common.h"
+#include "watchdog-reset.h"
 
 /*
  * IO mapping for shared system controller IP.
@@ -61,7 +60,7 @@ static void s3c64xx_dt_restart(enum reboot_mode mode, const char *cmd)
 	soft_restart(0);
 }
 
-static char const *s3c64xx_dt_compat[] __initdata = {
+static const char *const s3c64xx_dt_compat[] __initconst = {
 	"samsung,s3c6400",
 	"samsung,s3c6410",
 	NULL
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index b7447a92276e..d590b88bd8a8 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -68,9 +68,9 @@
 #include <plat/adc.h>
 #include <linux/platform_data/touchscreen-s3c2410.h>
 #include <plat/keypad.h>
-#include <plat/backlight.h>
 #include <plat/samsung-time.h>
 
+#include "backlight.h"
 #include "common.h"
 #include "regs-modem.h"
 #include "regs-srom.h"
diff --git a/arch/arm/plat-samsung/include/plat/onenand-core.h b/arch/arm/mach-s3c64xx/onenand-core.h
index 7701cb7020c8..925eb13bbb60 100644
--- a/arch/arm/plat-samsung/include/plat/onenand-core.h
+++ b/arch/arm/mach-s3c64xx/onenand-core.h
@@ -1,6 +1,4 @@
 /*
- * linux/arch/arm/plat-samsung/onenand-core.h
- *
  *  Copyright (c) 2010 Samsung Electronics
  *  Kyungmin Park <kyungmin.park@samsung.com>
  *  Marek Szyprowski <m.szyprowski@samsung.com>
diff --git a/arch/arm/plat-samsung/include/plat/regs-usb-hsotg-phy.h b/arch/arm/mach-s3c64xx/regs-usb-hsotg-phy.h
index fcf279662067..eae3c311e590 100644
--- a/arch/arm/plat-samsung/include/plat/regs-usb-hsotg-phy.h
+++ b/arch/arm/mach-s3c64xx/regs-usb-hsotg-phy.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-s3c/include/plat/regs-usb-hsotg-phy.h
- *
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *      http://armlinux.simtec.co.uk/
diff --git a/arch/arm/mach-s3c64xx/s3c6400.c b/arch/arm/mach-s3c64xx/s3c6400.c
index 1ce48c54cd9c..33273abef669 100644
--- a/arch/arm/mach-s3c64xx/s3c6400.c
+++ b/arch/arm/mach-s3c64xx/s3c6400.c
@@ -41,9 +41,9 @@
 #include <plat/devs.h>
 #include <plat/sdhci.h>
 #include <plat/iic-core.h>
-#include <plat/onenand-core.h>
 
 #include "common.h"
+#include "onenand-core.h"
 
 void __init s3c6400_map_io(void)
 {
diff --git a/arch/arm/mach-s3c64xx/s3c6410.c b/arch/arm/mach-s3c64xx/s3c6410.c
index b2a7930548d9..eadc48dee0e4 100644
--- a/arch/arm/mach-s3c64xx/s3c6410.c
+++ b/arch/arm/mach-s3c64xx/s3c6410.c
@@ -41,12 +41,12 @@
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/sdhci.h>
-#include <plat/ata-core.h>
 #include <plat/adc-core.h>
 #include <plat/iic-core.h>
-#include <plat/onenand-core.h>
 
+#include "ata-core.h"
 #include "common.h"
+#include "onenand-core.h"
 
 void __init s3c6410_map_io(void)
 {
diff --git a/arch/arm/mach-s3c64xx/setup-usb-phy.c b/arch/arm/mach-s3c64xx/setup-usb-phy.c
index ca960bda02fd..2b17b7f5152f 100644
--- a/arch/arm/mach-s3c64xx/setup-usb-phy.c
+++ b/arch/arm/mach-s3c64xx/setup-usb-phy.c
@@ -16,10 +16,10 @@
 #include <linux/platform_device.h>
 #include <mach/map.h>
 #include <plat/cpu.h>
-#include <plat/regs-usb-hsotg-phy.h>
 #include <plat/usb-phy.h>
 
 #include "regs-sys.h"
+#include "regs-usb-hsotg-phy.h"
 
 static int s3c_usb_otgphy_init(struct platform_device *pdev)
 {
diff --git a/arch/arm/plat-samsung/include/plat/watchdog-reset.h b/arch/arm/mach-s3c64xx/watchdog-reset.h
index 0386b8f76623..42707dfbda9c 100644
--- a/arch/arm/plat-samsung/include/plat/watchdog-reset.h
+++ b/arch/arm/mach-s3c64xx/watchdog-reset.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-s3c/include/plat/watchdog-reset.h
- *
+/*
  * Copyright (c) 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 99d9a3b1bf34..6d237b4f7a8e 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -320,10 +320,10 @@ static int neponset_probe(struct platform_device *dev)
 
 	irq_set_chip_and_handler(d->irq_base + NEP_IRQ_SMC91X, &nochip,
 		handle_simple_irq);
-	set_irq_flags(d->irq_base + NEP_IRQ_SMC91X, IRQF_VALID | IRQF_PROBE);
+	irq_clear_status_flags(d->irq_base + NEP_IRQ_SMC91X, IRQ_NOREQUEST | IRQ_NOPROBE);
 	irq_set_chip_and_handler(d->irq_base + NEP_IRQ_USAR, &nochip,
 		handle_simple_irq);
-	set_irq_flags(d->irq_base + NEP_IRQ_USAR, IRQF_VALID | IRQF_PROBE);
+	irq_clear_status_flags(d->irq_base + NEP_IRQ_USAR, IRQ_NOREQUEST | IRQ_NOPROBE);
 	irq_set_chip(d->irq_base + NEP_IRQ_SA1111, &nochip);
 
 	irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 45006479d461..926e336d6aeb 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -4,6 +4,7 @@ config ARCH_SHMOBILE
 
 config PM_RCAR
 	bool
+	select PM_GENERIC_DOMAINS if PM
 
 config PM_RMOBILE
 	bool
@@ -50,6 +51,7 @@ config ARCH_EMEV2
 
 config ARCH_R7S72100
 	bool "RZ/A1H (R7S72100)"
+	select PM_GENERIC_DOMAINS if PM
 	select SYS_SUPPORTS_SH_MTU2
 
 config ARCH_R8A73A4
@@ -80,6 +82,11 @@ config ARCH_R8A7791
 	select ARCH_RCAR_GEN2
 	select I2C
 
+config ARCH_R8A7793
+	bool "R-Car M2-N (R8A7793)"
+	select ARCH_RCAR_GEN2
+	select I2C
+
 config ARCH_R8A7794
 	bool "R-Car E2 (R8A77940)"
 	select ARCH_RCAR_GEN2
@@ -89,13 +96,6 @@ config ARCH_SH73A0
 	select ARCH_RMOBILE
 	select RENESAS_INTC_IRQPIN
 
-comment "Renesas ARM SoCs Board Type"
-
-config MACH_MARZEN
-	bool "MARZEN board"
-	depends on ARCH_R8A7779
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
-
 comment "Renesas ARM SoCs System Configuration"
 endif
 
@@ -103,22 +103,6 @@ if ARCH_SHMOBILE_LEGACY
 
 comment "Renesas ARM SoCs System Type"
 
-config ARCH_SH73A0
-	bool "SH-Mobile AG5 (R8A73A00)"
-	select ARCH_RMOBILE
-	select ARCH_WANT_OPTIONAL_GPIOLIB
-	select ARM_GIC
-	select I2C
-	select SH_INTC
-	select RENESAS_INTC_IRQPIN
-
-config ARCH_R8A7740
-	bool "R-Mobile A1 (R8A77400)"
-	select ARCH_RMOBILE
-	select ARCH_WANT_OPTIONAL_GPIOLIB
-	select ARM_GIC
-	select RENESAS_INTC_IRQPIN
-
 config ARCH_R8A7778
 	bool "R-Car M1A (R8A77781)"
 	select ARCH_RCAR_GEN1
@@ -133,15 +117,6 @@ config ARCH_R8A7779
 
 comment "Renesas ARM SoCs Board Type"
 
-config MACH_ARMADILLO800EVA
-	bool "Armadillo-800 EVA board"
-	depends on ARCH_R8A7740
-	select ARCH_REQUIRE_GPIOLIB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
-	select SMSC_PHY if SH_ETH
-	select SND_SOC_WM8978 if SND_SIMPLE_CARD && I2C
-	select USE_OF
-
 config MACH_BOCKW
 	bool "BOCK-W platform"
 	depends on ARCH_R8A7778
@@ -164,21 +139,6 @@ config MACH_BOCKW_REFERENCE
 
 	   This is intended to aid developers
 
-config MACH_MARZEN
-	bool "MARZEN board"
-	depends on ARCH_R8A7779
-	select ARCH_REQUIRE_GPIOLIB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
-	select USE_OF
-
-config MACH_KZM9G
-	bool "KZM-A9-GT board"
-	depends on ARCH_SH73A0
-	select ARCH_REQUIRE_GPIOLIB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
-	select SND_SOC_AK4642 if SND_SIMPLE_CARD
-	select USE_OF
-
 comment "Renesas ARM SoCs System Configuration"
 
 config CPU_HAS_INTEVT
diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile
index 89e463de4479..476de30798d7 100644
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@@ -6,13 +6,14 @@
 obj-y				:= timer.o console.o
 
 # CPU objects
-obj-$(CONFIG_ARCH_SH73A0)	+= setup-sh73a0.o pm-sh73a0.o
+obj-$(CONFIG_ARCH_SH73A0)	+= setup-sh73a0.o
 obj-$(CONFIG_ARCH_R8A73A4)	+= setup-r8a73a4.o
-obj-$(CONFIG_ARCH_R8A7740)	+= setup-r8a7740.o pm-r8a7740.o
+obj-$(CONFIG_ARCH_R8A7740)	+= setup-r8a7740.o
 obj-$(CONFIG_ARCH_R8A7778)	+= setup-r8a7778.o
 obj-$(CONFIG_ARCH_R8A7779)	+= setup-r8a7779.o pm-r8a7779.o
 obj-$(CONFIG_ARCH_R8A7790)	+= setup-r8a7790.o
 obj-$(CONFIG_ARCH_R8A7791)	+= setup-r8a7791.o
+obj-$(CONFIG_ARCH_R8A7793)	+= setup-r8a7793.o
 obj-$(CONFIG_ARCH_R8A7794)	+= setup-r8a7794.o
 obj-$(CONFIG_ARCH_EMEV2)	+= setup-emev2.o
 obj-$(CONFIG_ARCH_R7S72100)	+= setup-r7s72100.o
@@ -20,10 +21,7 @@ obj-$(CONFIG_ARCH_R7S72100)	+= setup-r7s72100.o
 # Clock objects
 ifndef CONFIG_COMMON_CLK
 obj-y				+= clock.o
-obj-$(CONFIG_ARCH_SH73A0)	+= clock-sh73a0.o
-obj-$(CONFIG_ARCH_R8A7740)	+= clock-r8a7740.o
 obj-$(CONFIG_ARCH_R8A7778)	+= clock-r8a7778.o
-obj-$(CONFIG_ARCH_R8A7779)	+= clock-r8a7779.o
 endif
 
 # CPU reset vector handling objects
@@ -34,6 +32,7 @@ obj-$(CONFIG_ARCH_RCAR_GEN2)	+= setup-rcar-gen2.o platsmp-apmu.o $(cpu-y)
 CFLAGS_setup-rcar-gen2.o	+= -march=armv7-a
 obj-$(CONFIG_ARCH_R8A7790)	+= regulator-quirk-rcar-gen2.o
 obj-$(CONFIG_ARCH_R8A7791)	+= regulator-quirk-rcar-gen2.o
+obj-$(CONFIG_ARCH_R8A7793)	+= regulator-quirk-rcar-gen2.o
 
 # SMP objects
 smp-y				:= $(cpu-y)
@@ -51,14 +50,9 @@ obj-$(CONFIG_PM_RMOBILE)	+= pm-rmobile.o
 obj-$(CONFIG_ARCH_RCAR_GEN2)	+= pm-rcar-gen2.o
 
 # Board objects
-ifdef CONFIG_ARCH_SHMOBILE_MULTI
-obj-$(CONFIG_MACH_MARZEN)	+= board-marzen-reference.o
-else
+ifndef CONFIG_ARCH_SHMOBILE_MULTI
 obj-$(CONFIG_MACH_BOCKW)	+= board-bockw.o
 obj-$(CONFIG_MACH_BOCKW_REFERENCE)	+= board-bockw-reference.o
-obj-$(CONFIG_MACH_MARZEN)	+= board-marzen.o
-obj-$(CONFIG_MACH_ARMADILLO800EVA)	+= board-armadillo800eva.o
-obj-$(CONFIG_MACH_KZM9G)	+= board-kzm9g.o intc-sh73a0.o
 endif
 
 # Framework support
diff --git a/arch/arm/mach-shmobile/Makefile.boot b/arch/arm/mach-shmobile/Makefile.boot
index e1ef19cef89c..a489fe9a76cd 100644
--- a/arch/arm/mach-shmobile/Makefile.boot
+++ b/arch/arm/mach-shmobile/Makefile.boot
@@ -1,10 +1,7 @@
 # per-board load address for uImage
 loadaddr-y	:=
-loadaddr-$(CONFIG_MACH_ARMADILLO800EVA) += 0x40008000
 loadaddr-$(CONFIG_MACH_BOCKW) += 0x60008000
 loadaddr-$(CONFIG_MACH_BOCKW_REFERENCE) += 0x60008000
-loadaddr-$(CONFIG_MACH_KZM9G) += 0x41008000
-loadaddr-$(CONFIG_MACH_MARZEN) += 0x60008000
 
 __ZRELADDR	:= $(sort $(loadaddr-y))
    zreladdr-y   += $(__ZRELADDR)
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
deleted file mode 100644
index bf37e3c532f6..000000000000
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ /dev/null
@@ -1,1365 +0,0 @@
-/*
- * armadillo 800 eva board support
- *
- * Copyright (C) 2012 Renesas Solutions Corp.
- * Copyright (C) 2012 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/gpio.h>
-#include <linux/gpio_keys.h>
-#include <linux/i2c-gpio.h>
-#include <linux/input.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/mfd/tmio.h>
-#include <linux/mmc/host.h>
-#include <linux/mmc/sh_mmcif.h>
-#include <linux/mmc/sh_mobile_sdhi.h>
-#include <linux/pinctrl/machine.h>
-#include <linux/platform_data/st1232_pdata.h>
-#include <linux/platform_device.h>
-#include <linux/pwm.h>
-#include <linux/pwm_backlight.h>
-#include <linux/reboot.h>
-#include <linux/regulator/driver.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/gpio-regulator.h>
-#include <linux/regulator/machine.h>
-#include <linux/sh_eth.h>
-#include <linux/usb/renesas_usbhs.h>
-#include <linux/videodev2.h>
-
-#include <asm/hardware/cache-l2x0.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/mach/time.h>
-#include <asm/page.h>
-#include <media/mt9t112.h>
-#include <media/sh_mobile_ceu.h>
-#include <media/soc_camera.h>
-#include <sound/sh_fsi.h>
-#include <sound/simple_card.h>
-#include <video/sh_mobile_hdmi.h>
-#include <video/sh_mobile_lcdc.h>
-
-#include "common.h"
-#include "irqs.h"
-#include "pm-rmobile.h"
-#include "r8a7740.h"
-#include "sh-gpio.h"
-
-/*
- * CON1		Camera Module
- * CON2		Extension Bus
- * CON3		HDMI Output
- * CON4		Composite Video Output
- * CON5		H-UDI JTAG
- * CON6		ARM JTAG
- * CON7		SD1
- * CON8		SD2
- * CON9		RTC BackUp
- * CON10	Monaural Mic Input
- * CON11	Stereo Headphone Output
- * CON12	Audio Line Output(L)
- * CON13	Audio Line Output(R)
- * CON14	AWL13 Module
- * CON15	Extension
- * CON16	LCD1
- * CON17	LCD2
- * CON19	Power Input
- * CON20	USB1
- * CON21	USB2
- * CON22	Serial
- * CON23	LAN
- * CON24	USB3
- * LED1		Camera LED(Yellow)
- * LED2		Power LED (Green)
- * ED3-LED6	User LED(Yellow)
- * LED7		LAN link LED(Green)
- * LED8		LAN activity LED(Yellow)
- */
-
-/*
- * DipSwitch
- *
- *                    SW1
- *
- * -12345678-+---------------+----------------------------
- *  1        | boot          | hermit
- *  0        | boot          | OS auto boot
- * -12345678-+---------------+----------------------------
- *   00      | boot device   | eMMC
- *   10      | boot device   | SDHI0 (CON7)
- *   01      | boot device   | -
- *   11      | boot device   | Extension Buss (CS0)
- * -12345678-+---------------+----------------------------
- *     0     | Extension Bus | D8-D15 disable, eMMC enable
- *     1     | Extension Bus | D8-D15 enable,  eMMC disable
- * -12345678-+---------------+----------------------------
- *      0    | SDHI1         | COM8 disable, COM14 enable
- *      1    | SDHI1         | COM8 enable,  COM14 disable
- * -12345678-+---------------+----------------------------
- *       0   | USB0          | COM20 enable,  COM24 disable
- *       1   | USB0          | COM20 disable, COM24 enable
- * -12345678-+---------------+----------------------------
- *        00 | JTAG          | SH-X2
- *        10 | JTAG          | ARM
- *        01 | JTAG          | -
- *        11 | JTAG          | Boundary Scan
- *-----------+---------------+----------------------------
- */
-
-/*
- * FSI-WM8978
- *
- * this command is required when playback.
- *
- * # amixer set "Headphone" 50
- *
- * this command is required when capture.
- *
- * # amixer set "Input PGA" 15
- * # amixer set "Left Input Mixer MicP" on
- * # amixer set "Left Input Mixer MicN" on
- * # amixer set "Right Input Mixer MicN" on
- * # amixer set "Right Input Mixer MicP" on
- */
-
-/*
- * USB function
- *
- * When you use USB Function,
- * set SW1.6 ON, and connect cable to CN24.
- *
- * USBF needs workaround on R8A7740 chip.
- * These are a little bit complex.
- * see
- *	usbhsf_power_ctrl()
- */
-#define IRQ7		irq_pin(7)
-#define USBCR1		IOMEM(0xe605810a)
-#define USBH		0xC6700000
-#define USBH_USBCTR	0x10834
-
-struct usbhsf_private {
-	struct clk *phy;
-	struct clk *usb24;
-	struct clk *pci;
-	struct clk *func;
-	struct clk *host;
-	void __iomem *usbh_base;
-	struct renesas_usbhs_platform_info info;
-};
-
-#define usbhsf_get_priv(pdev)				\
-	container_of(renesas_usbhs_get_info(pdev),	\
-		     struct usbhsf_private, info)
-
-static int usbhsf_get_id(struct platform_device *pdev)
-{
-	return USBHS_GADGET;
-}
-
-static int usbhsf_power_ctrl(struct platform_device *pdev,
-			      void __iomem *base, int enable)
-{
-	struct usbhsf_private *priv = usbhsf_get_priv(pdev);
-
-	/*
-	 * Work around for USB Function.
-	 * It needs USB host clock, and settings
-	 */
-	if (enable) {
-		/*
-		 * enable all the related usb clocks
-		 * for usb workaround
-		 */
-		clk_enable(priv->usb24);
-		clk_enable(priv->pci);
-		clk_enable(priv->host);
-		clk_enable(priv->func);
-		clk_enable(priv->phy);
-
-		/*
-		 * set USBCR1
-		 *
-		 * Port1 is driven by USB function,
-		 * Port2 is driven by USB HOST
-		 * One HOST (Port1 or Port2 is HOST)
-		 * USB PLL input clock = 24MHz
-		 */
-		__raw_writew(0xd750, USBCR1);
-		mdelay(1);
-
-		/*
-		 * start USB Host
-		 */
-		__raw_writel(0x0000000c, priv->usbh_base + USBH_USBCTR);
-		__raw_writel(0x00000008, priv->usbh_base + USBH_USBCTR);
-		mdelay(10);
-
-		/*
-		 * USB PHY Power ON
-		 */
-		__raw_writew(0xd770, USBCR1);
-		__raw_writew(0x4000, base + 0x102); /* USBF :: SUSPMODE */
-
-	} else {
-		__raw_writel(0x0000010f, priv->usbh_base + USBH_USBCTR);
-		__raw_writew(0xd7c0, USBCR1); /* GPIO */
-
-		clk_disable(priv->phy);
-		clk_disable(priv->func);	/* usb work around */
-		clk_disable(priv->host);	/* usb work around */
-		clk_disable(priv->pci);		/* usb work around */
-		clk_disable(priv->usb24);	/* usb work around */
-	}
-
-	return 0;
-}
-
-static int usbhsf_get_vbus(struct platform_device *pdev)
-{
-	return gpio_get_value(209);
-}
-
-static irqreturn_t usbhsf_interrupt(int irq, void *data)
-{
-	struct platform_device *pdev = data;
-
-	renesas_usbhs_call_notify_hotplug(pdev);
-
-	return IRQ_HANDLED;
-}
-
-static int usbhsf_hardware_exit(struct platform_device *pdev)
-{
-	struct usbhsf_private *priv = usbhsf_get_priv(pdev);
-
-	if (!IS_ERR(priv->phy))
-		clk_put(priv->phy);
-	if (!IS_ERR(priv->usb24))
-		clk_put(priv->usb24);
-	if (!IS_ERR(priv->pci))
-		clk_put(priv->pci);
-	if (!IS_ERR(priv->host))
-		clk_put(priv->host);
-	if (!IS_ERR(priv->func))
-		clk_put(priv->func);
-	if (priv->usbh_base)
-		iounmap(priv->usbh_base);
-
-	priv->phy	= NULL;
-	priv->usb24	= NULL;
-	priv->pci	= NULL;
-	priv->host	= NULL;
-	priv->func	= NULL;
-	priv->usbh_base	= NULL;
-
-	free_irq(IRQ7, pdev);
-
-	return 0;
-}
-
-static int usbhsf_hardware_init(struct platform_device *pdev)
-{
-	struct usbhsf_private *priv = usbhsf_get_priv(pdev);
-	int ret;
-
-	priv->phy	= clk_get(&pdev->dev, "phy");
-	priv->usb24	= clk_get(&pdev->dev, "usb24");
-	priv->pci	= clk_get(&pdev->dev, "pci");
-	priv->func	= clk_get(&pdev->dev, "func");
-	priv->host	= clk_get(&pdev->dev, "host");
-	priv->usbh_base	= ioremap_nocache(USBH, 0x20000);
-
-	if (IS_ERR(priv->phy)		||
-	    IS_ERR(priv->usb24)		||
-	    IS_ERR(priv->pci)		||
-	    IS_ERR(priv->host)		||
-	    IS_ERR(priv->func)		||
-	    !priv->usbh_base) {
-		dev_err(&pdev->dev, "USB clock setting failed\n");
-		usbhsf_hardware_exit(pdev);
-		return -EIO;
-	}
-
-	ret = request_irq(IRQ7, usbhsf_interrupt, IRQF_TRIGGER_NONE,
-			  dev_name(&pdev->dev), pdev);
-	if (ret) {
-		dev_err(&pdev->dev, "request_irq err\n");
-		return ret;
-	}
-	irq_set_irq_type(IRQ7, IRQ_TYPE_EDGE_BOTH);
-
-	/* usb24 use 1/1 of parent clock (= usb24s = 24MHz) */
-	clk_set_rate(priv->usb24,
-		     clk_get_rate(clk_get_parent(priv->usb24)));
-
-	return 0;
-}
-
-static struct usbhsf_private usbhsf_private = {
-	.info = {
-		.platform_callback = {
-			.get_id		= usbhsf_get_id,
-			.get_vbus	= usbhsf_get_vbus,
-			.hardware_init	= usbhsf_hardware_init,
-			.hardware_exit	= usbhsf_hardware_exit,
-			.power_ctrl	= usbhsf_power_ctrl,
-		},
-		.driver_param = {
-			.buswait_bwait		= 5,
-			.detection_delay	= 5,
-			.d0_rx_id	= SHDMA_SLAVE_USBHS_RX,
-			.d1_tx_id	= SHDMA_SLAVE_USBHS_TX,
-		},
-	}
-};
-
-static struct resource usbhsf_resources[] = {
-	{
-		.name	= "USBHS",
-		.start	= 0xe6890000,
-		.end	= 0xe6890104 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		.start	= gic_spi(51),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device usbhsf_device = {
-	.name	= "renesas_usbhs",
-	.dev = {
-		.platform_data = &usbhsf_private.info,
-	},
-	.id = -1,
-	.num_resources	= ARRAY_SIZE(usbhsf_resources),
-	.resource	= usbhsf_resources,
-};
-
-/* Ether */
-static struct sh_eth_plat_data sh_eth_platdata = {
-	.phy			= 0x00, /* LAN8710A */
-	.edmac_endian		= EDMAC_LITTLE_ENDIAN,
-	.phy_interface		= PHY_INTERFACE_MODE_MII,
-};
-
-static struct resource sh_eth_resources[] = {
-	{
-		.start	= 0xe9a00000,
-		.end	= 0xe9a00800 - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= 0xe9a01800,
-		.end	= 0xe9a02000 - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= gic_spi(110),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sh_eth_device = {
-	.name = "r8a7740-gether",
-	.id = -1,
-	.dev = {
-		.platform_data = &sh_eth_platdata,
-		.dma_mask = &sh_eth_device.dev.coherent_dma_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-	},
-	.resource = sh_eth_resources,
-	.num_resources = ARRAY_SIZE(sh_eth_resources),
-};
-
-/* PWM */
-static struct resource pwm_resources[] = {
-	[0] = {
-		.start = 0xe6600000,
-		.end = 0xe66000ff,
-		.flags = IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device pwm_device = {
-	.name = "renesas-tpu-pwm",
-	.id = -1,
-	.num_resources = ARRAY_SIZE(pwm_resources),
-	.resource = pwm_resources,
-};
-
-static struct pwm_lookup pwm_lookup[] = {
-	PWM_LOOKUP("renesas-tpu-pwm", 2, "pwm-backlight.0", NULL,
-		   33333, PWM_POLARITY_INVERSED),
-};
-
-/* LCDC and backlight */
-static struct platform_pwm_backlight_data pwm_backlight_data = {
-	.lth_brightness = 50,
-	.max_brightness = 255,
-	.dft_brightness = 255,
-	.pwm_period_ns = 33333, /* 30kHz */
-	.enable_gpio = 61,
-};
-
-static struct platform_device pwm_backlight_device = {
-	.name = "pwm-backlight",
-	.dev = {
-		.platform_data = &pwm_backlight_data,
-	},
-};
-
-static struct fb_videomode lcdc0_mode = {
-	.name		= "AMPIER/AM-800480",
-	.xres		= 800,
-	.yres		= 480,
-	.left_margin	= 88,
-	.right_margin	= 40,
-	.hsync_len	= 128,
-	.upper_margin	= 20,
-	.lower_margin	= 5,
-	.vsync_len	= 5,
-	.sync		= 0,
-};
-
-static struct sh_mobile_lcdc_info lcdc0_info = {
-	.clock_source	= LCDC_CLK_BUS,
-	.ch[0] = {
-		.chan		= LCDC_CHAN_MAINLCD,
-		.fourcc		= V4L2_PIX_FMT_RGB565,
-		.interface_type	= RGB24,
-		.clock_divider	= 5,
-		.flags		= 0,
-		.lcd_modes	= &lcdc0_mode,
-		.num_modes	= 1,
-		.panel_cfg = {
-			.width	= 111,
-			.height = 68,
-		},
-	},
-};
-
-static struct resource lcdc0_resources[] = {
-	[0] = {
-		.name	= "LCD0",
-		.start	= 0xfe940000,
-		.end	= 0xfe943fff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(177),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device lcdc0_device = {
-	.name		= "sh_mobile_lcdc_fb",
-	.num_resources	= ARRAY_SIZE(lcdc0_resources),
-	.resource	= lcdc0_resources,
-	.id		= 0,
-	.dev	= {
-		.platform_data	= &lcdc0_info,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-	},
-};
-
-/*
- * LCDC1/HDMI
- */
-static struct sh_mobile_hdmi_info hdmi_info = {
-	.flags		= HDMI_OUTPUT_PUSH_PULL |
-			  HDMI_OUTPUT_POLARITY_HI |
-			  HDMI_32BIT_REG |
-			  HDMI_HAS_HTOP1 |
-			  HDMI_SND_SRC_SPDIF,
-};
-
-static struct resource hdmi_resources[] = {
-	[0] = {
-		.name	= "HDMI",
-		.start	= 0xe6be0000,
-		.end	= 0xe6be03ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(131),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.name	= "HDMI emma3pf",
-		.start	= 0xe6be4000,
-		.end	= 0xe6be43ff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device hdmi_device = {
-	.name		= "sh-mobile-hdmi",
-	.num_resources	= ARRAY_SIZE(hdmi_resources),
-	.resource	= hdmi_resources,
-	.id             = -1,
-	.dev	= {
-		.platform_data	= &hdmi_info,
-	},
-};
-
-static const struct fb_videomode lcdc1_mode = {
-	.name		= "HDMI 720p",
-	.xres		= 1280,
-	.yres		= 720,
-	.pixclock	= 13468,
-	.left_margin	= 220,
-	.right_margin	= 110,
-	.hsync_len	= 40,
-	.upper_margin	= 20,
-	.lower_margin	= 5,
-	.vsync_len	= 5,
-	.refresh	= 60,
-	.sync		= FB_SYNC_VERT_HIGH_ACT | FB_SYNC_HOR_HIGH_ACT,
-};
-
-static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
-	.clock_source	= LCDC_CLK_PERIPHERAL, /* HDMI clock */
-	.ch[0] = {
-		.chan			= LCDC_CHAN_MAINLCD,
-		.fourcc			= V4L2_PIX_FMT_RGB565,
-		.interface_type		= RGB24,
-		.clock_divider		= 1,
-		.flags			= LCDC_FLAGS_DWPOL,
-		.lcd_modes		= &lcdc1_mode,
-		.num_modes		= 1,
-		.tx_dev			= &hdmi_device,
-		.panel_cfg = {
-			.width	= 1280,
-			.height = 720,
-		},
-	},
-};
-
-static struct resource hdmi_lcdc_resources[] = {
-	[0] = {
-		.name	= "LCDC1",
-		.start	= 0xfe944000,
-		.end	= 0xfe948000 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(178),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device hdmi_lcdc_device = {
-	.name		= "sh_mobile_lcdc_fb",
-	.num_resources	= ARRAY_SIZE(hdmi_lcdc_resources),
-	.resource	= hdmi_lcdc_resources,
-	.id		= 1,
-	.dev	= {
-		.platform_data	= &hdmi_lcdc_info,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-	},
-};
-
-/* LEDS */
-static struct gpio_led gpio_leds[] = {
-	{
-		.name		= "LED3",
-		.gpio		= 102,
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	}, {
-		.name		= "LED4",
-		.gpio		= 111,
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	}, {
-		.name		= "LED5",
-		.gpio		= 110,
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	}, {
-		.name		= "LED6",
-		.gpio		= 177,
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	},
-};
-
-static struct gpio_led_platform_data leds_gpio_info = {
-	.leds		= gpio_leds,
-	.num_leds	= ARRAY_SIZE(gpio_leds),
-};
-
-static struct platform_device leds_gpio_device = {
-	.name   = "leds-gpio",
-	.id     = -1,
-	.dev    = {
-		.platform_data  = &leds_gpio_info,
-	},
-};
-
-/* GPIO KEY */
-#define GPIO_KEY(c, g, d, ...) \
-	{ .code = c, .gpio = g, .desc = d, .active_low = 1, __VA_ARGS__ }
-
-static struct gpio_keys_button gpio_buttons[] = {
-	GPIO_KEY(KEY_POWER,	99,	"SW3", .wakeup = 1),
-	GPIO_KEY(KEY_BACK,	100,	"SW4"),
-	GPIO_KEY(KEY_MENU,	97,	"SW5"),
-	GPIO_KEY(KEY_HOME,	98,	"SW6"),
-};
-
-static struct gpio_keys_platform_data gpio_key_info = {
-	.buttons	= gpio_buttons,
-	.nbuttons	= ARRAY_SIZE(gpio_buttons),
-};
-
-static struct platform_device gpio_keys_device = {
-	.name   = "gpio-keys",
-	.id     = -1,
-	.dev    = {
-		.platform_data  = &gpio_key_info,
-	},
-};
-
-/* Fixed 3.3V regulator to be used by SDHI1, MMCIF */
-static struct regulator_consumer_supply fixed3v3_power_consumers[] = {
-	REGULATOR_SUPPLY("vmmc", "sh_mmcif"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mmcif"),
-};
-
-/* Fixed 3.3V regulator used by LCD backlight */
-static struct regulator_consumer_supply fixed5v0_power_consumers[] = {
-	REGULATOR_SUPPLY("power", "pwm-backlight.0"),
-};
-
-/* Fixed 3.3V regulator to be used by SDHI0 */
-static struct regulator_consumer_supply vcc_sdhi0_consumers[] = {
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
-};
-
-static struct regulator_init_data vcc_sdhi0_init_data = {
-	.constraints = {
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(vcc_sdhi0_consumers),
-	.consumer_supplies      = vcc_sdhi0_consumers,
-};
-
-static struct fixed_voltage_config vcc_sdhi0_info = {
-	.supply_name = "SDHI0 Vcc",
-	.microvolts = 3300000,
-	.gpio = 75,
-	.enable_high = 1,
-	.init_data = &vcc_sdhi0_init_data,
-};
-
-static struct platform_device vcc_sdhi0 = {
-	.name = "reg-fixed-voltage",
-	.id   = 1,
-	.dev  = {
-		.platform_data = &vcc_sdhi0_info,
-	},
-};
-
-/* 1.8 / 3.3V SDHI0 VccQ regulator */
-static struct regulator_consumer_supply vccq_sdhi0_consumers[] = {
-	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
-};
-
-static struct regulator_init_data vccq_sdhi0_init_data = {
-	.constraints = {
-		.input_uV	= 3300000,
-		.min_uV		= 1800000,
-		.max_uV         = 3300000,
-		.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-				  REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(vccq_sdhi0_consumers),
-	.consumer_supplies      = vccq_sdhi0_consumers,
-};
-
-static struct gpio vccq_sdhi0_gpios[] = {
-	{17, GPIOF_OUT_INIT_LOW, "vccq-sdhi0" },
-};
-
-static struct gpio_regulator_state vccq_sdhi0_states[] = {
-	{ .value = 3300000, .gpios = (0 << 0) },
-	{ .value = 1800000, .gpios = (1 << 0) },
-};
-
-static struct gpio_regulator_config vccq_sdhi0_info = {
-	.supply_name = "vqmmc",
-
-	.enable_gpio = 74,
-	.enable_high = 1,
-	.enabled_at_boot = 0,
-
-	.gpios = vccq_sdhi0_gpios,
-	.nr_gpios = ARRAY_SIZE(vccq_sdhi0_gpios),
-
-	.states = vccq_sdhi0_states,
-	.nr_states = ARRAY_SIZE(vccq_sdhi0_states),
-
-	.type = REGULATOR_VOLTAGE,
-	.init_data = &vccq_sdhi0_init_data,
-};
-
-static struct platform_device vccq_sdhi0 = {
-	.name = "gpio-regulator",
-	.id   = -1,
-	.dev  = {
-		.platform_data = &vccq_sdhi0_info,
-	},
-};
-
-/* Fixed 3.3V regulator to be used by SDHI1 */
-static struct regulator_consumer_supply vcc_sdhi1_consumers[] = {
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
-};
-
-static struct regulator_init_data vcc_sdhi1_init_data = {
-	.constraints = {
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(vcc_sdhi1_consumers),
-	.consumer_supplies      = vcc_sdhi1_consumers,
-};
-
-static struct fixed_voltage_config vcc_sdhi1_info = {
-	.supply_name = "SDHI1 Vcc",
-	.microvolts = 3300000,
-	.gpio = 16,
-	.enable_high = 1,
-	.init_data = &vcc_sdhi1_init_data,
-};
-
-static struct platform_device vcc_sdhi1 = {
-	.name = "reg-fixed-voltage",
-	.id   = 2,
-	.dev  = {
-		.platform_data = &vcc_sdhi1_info,
-	},
-};
-
-/* SDHI0 */
-static struct tmio_mmc_data sdhi0_info = {
-	.chan_priv_tx	= (void *)SHDMA_SLAVE_SDHI0_TX,
-	.chan_priv_rx	= (void *)SHDMA_SLAVE_SDHI0_RX,
-	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
-			  MMC_CAP_POWER_OFF_CARD,
-	.flags		= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_USE_GPIO_CD,
-	.cd_gpio	= 167,
-};
-
-static struct resource sdhi0_resources[] = {
-	{
-		.name	= "SDHI0",
-		.start	= 0xe6850000,
-		.end	= 0xe6850100 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	/*
-	 * no SH_MOBILE_SDHI_IRQ_CARD_DETECT here
-	 */
-	{
-		.name	= SH_MOBILE_SDHI_IRQ_SDCARD,
-		.start	= gic_spi(118),
-		.flags	= IORESOURCE_IRQ,
-	},
-	{
-		.name	= SH_MOBILE_SDHI_IRQ_SDIO,
-		.start	= gic_spi(119),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi0_device = {
-	.name		= "sh_mobile_sdhi",
-	.id		= 0,
-	.dev		= {
-		.platform_data	= &sdhi0_info,
-	},
-	.num_resources	= ARRAY_SIZE(sdhi0_resources),
-	.resource	= sdhi0_resources,
-};
-
-/* SDHI1 */
-static struct tmio_mmc_data sdhi1_info = {
-	.chan_priv_tx	= (void *)SHDMA_SLAVE_SDHI1_TX,
-	.chan_priv_rx	= (void *)SHDMA_SLAVE_SDHI1_RX,
-	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
-			  MMC_CAP_POWER_OFF_CARD,
-	.flags		= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_USE_GPIO_CD,
-	/* Port72 cannot generate IRQs, will be used in polling mode. */
-	.cd_gpio	= 72,
-};
-
-static struct resource sdhi1_resources[] = {
-	[0] = {
-		.name	= "SDHI1",
-		.start	= 0xe6860000,
-		.end	= 0xe6860100 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(121),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start	= gic_spi(122),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= gic_spi(123),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi1_device = {
-	.name		= "sh_mobile_sdhi",
-	.id		= 1,
-	.dev		= {
-		.platform_data	= &sdhi1_info,
-	},
-	.num_resources	= ARRAY_SIZE(sdhi1_resources),
-	.resource	= sdhi1_resources,
-};
-
-static const struct pinctrl_map eva_sdhi1_pinctrl_map[] = {
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-r8a7740",
-				  "sdhi1_data4", "sdhi1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-r8a7740",
-				  "sdhi1_ctrl", "sdhi1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-r8a7740",
-				  "sdhi1_cd", "sdhi1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-r8a7740",
-				  "sdhi1_wp", "sdhi1"),
-};
-
-/* MMCIF */
-static struct sh_mmcif_plat_data sh_mmcif_plat = {
-	.sup_pclk	= 0,
-	.caps		= MMC_CAP_4_BIT_DATA |
-			  MMC_CAP_8_BIT_DATA |
-			  MMC_CAP_NONREMOVABLE,
-	.ccs_unsupported = true,
-	.slave_id_tx	= SHDMA_SLAVE_MMCIF_TX,
-	.slave_id_rx	= SHDMA_SLAVE_MMCIF_RX,
-};
-
-static struct resource sh_mmcif_resources[] = {
-	[0] = {
-		.name	= "MMCIF",
-		.start	= 0xe6bd0000,
-		.end	= 0xe6bd0100 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		/* MMC ERR */
-		.start	= gic_spi(56),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		/* MMC NOR */
-		.start	= gic_spi(57),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sh_mmcif_device = {
-	.name		= "sh_mmcif",
-	.id		= -1,
-	.dev		= {
-		.platform_data	= &sh_mmcif_plat,
-	},
-	.num_resources	= ARRAY_SIZE(sh_mmcif_resources),
-	.resource	= sh_mmcif_resources,
-};
-
-/* Camera */
-static int mt9t111_power(struct device *dev, int mode)
-{
-	struct clk *mclk = clk_get(NULL, "video1");
-
-	if (IS_ERR(mclk)) {
-		dev_err(dev, "can't get video1 clock\n");
-		return -EINVAL;
-	}
-
-	if (mode) {
-		/* video1 (= CON1 camera) expect 24MHz */
-		clk_set_rate(mclk, clk_round_rate(mclk, 24000000));
-		clk_enable(mclk);
-		gpio_set_value(158, 1);
-	} else {
-		gpio_set_value(158, 0);
-		clk_disable(mclk);
-	}
-
-	clk_put(mclk);
-
-	return 0;
-}
-
-static struct i2c_board_info i2c_camera_mt9t111 = {
-	I2C_BOARD_INFO("mt9t112", 0x3d),
-};
-
-static struct mt9t112_camera_info mt9t111_info = {
-	.divider = { 16, 0, 0, 7, 0, 10, 14, 7, 7 },
-};
-
-static struct soc_camera_link mt9t111_link = {
-	.i2c_adapter_id	= 0,
-	.bus_id		= 0,
-	.board_info	= &i2c_camera_mt9t111,
-	.power		= mt9t111_power,
-	.priv		= &mt9t111_info,
-};
-
-static struct platform_device camera_device = {
-	.name	= "soc-camera-pdrv",
-	.id	= 0,
-	.dev	= {
-		.platform_data = &mt9t111_link,
-	},
-};
-
-/* CEU0 */
-static struct sh_mobile_ceu_info sh_mobile_ceu0_info = {
-	.flags = SH_CEU_FLAG_LOWER_8BIT,
-};
-
-static struct resource ceu0_resources[] = {
-	[0] = {
-		.name	= "CEU",
-		.start	= 0xfe910000,
-		.end	= 0xfe91009f,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(160),
-		.flags  = IORESOURCE_IRQ,
-	},
-	[2] = {
-		/* place holder for contiguous memory */
-	},
-};
-
-static struct platform_device ceu0_device = {
-	.name		= "sh_mobile_ceu",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(ceu0_resources),
-	.resource	= ceu0_resources,
-	.dev	= {
-		.platform_data		= &sh_mobile_ceu0_info,
-		.coherent_dma_mask	= 0xffffffff,
-	},
-};
-
-/* FSI */
-static struct sh_fsi_platform_info fsi_info = {
-	/* FSI-WM8978 */
-	.port_a = {
-		.tx_id = SHDMA_SLAVE_FSIA_TX,
-	},
-	/* FSI-HDMI */
-	.port_b = {
-		.flags		= SH_FSI_FMT_SPDIF |
-				  SH_FSI_ENABLE_STREAM_MODE |
-				  SH_FSI_CLK_CPG,
-		.tx_id		= SHDMA_SLAVE_FSIB_TX,
-	}
-};
-
-static struct resource fsi_resources[] = {
-	[0] = {
-		.name	= "FSI",
-		.start	= 0xfe1f0000,
-		.end	= 0xfe1f0400 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(9),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device fsi_device = {
-	.name		= "sh_fsi2",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(fsi_resources),
-	.resource	= fsi_resources,
-	.dev	= {
-		.platform_data	= &fsi_info,
-	},
-};
-
-/* FSI-WM8978 */
-static struct asoc_simple_card_info fsi_wm8978_info = {
-	.name		= "wm8978",
-	.card		= "FSI2A-WM8978",
-	.codec		= "wm8978.0-001a",
-	.platform	= "sh_fsi2",
-	.daifmt		= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM,
-	.cpu_dai = {
-		.name	= "fsia-dai",
-	},
-	.codec_dai = {
-		.name	= "wm8978-hifi",
-		.sysclk	= 12288000,
-	},
-};
-
-static struct platform_device fsi_wm8978_device = {
-	.name	= "asoc-simple-card",
-	.id	= 0,
-	.dev	= {
-		.platform_data	= &fsi_wm8978_info,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-		.dma_mask = &fsi_wm8978_device.dev.coherent_dma_mask,
-	},
-};
-
-/* FSI-HDMI */
-static struct asoc_simple_card_info fsi2_hdmi_info = {
-	.name		= "HDMI",
-	.card		= "FSI2B-HDMI",
-	.codec		= "sh-mobile-hdmi",
-	.platform	= "sh_fsi2",
-	.daifmt		= SND_SOC_DAIFMT_CBS_CFS,
-	.cpu_dai = {
-		.name	= "fsib-dai",
-	},
-	.codec_dai = {
-		.name = "sh_mobile_hdmi-hifi",
-	},
-};
-
-static struct platform_device fsi_hdmi_device = {
-	.name	= "asoc-simple-card",
-	.id	= 1,
-	.dev	= {
-		.platform_data	= &fsi2_hdmi_info,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-		.dma_mask = &fsi_hdmi_device.dev.coherent_dma_mask,
-	},
-};
-
-/* RTC: RTC connects i2c-gpio. */
-static struct i2c_gpio_platform_data i2c_gpio_data = {
-	.sda_pin	= 208,
-	.scl_pin	= 91,
-	.udelay		= 5, /* 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
-	.name = "i2c-gpio",
-	.id = 2,
-	.dev = {
-		.platform_data = &i2c_gpio_data,
-	},
-};
-
-/* I2C */
-static struct st1232_pdata st1232_i2c0_pdata = {
-	.reset_gpio = 166,
-};
-
-static struct i2c_board_info i2c0_devices[] = {
-	{
-		I2C_BOARD_INFO("st1232-ts", 0x55),
-		.irq = irq_pin(10),
-		.platform_data = &st1232_i2c0_pdata,
-	},
-	{
-		I2C_BOARD_INFO("wm8978", 0x1a),
-	},
-};
-
-static struct i2c_board_info i2c2_devices[] = {
-	{
-		I2C_BOARD_INFO("s35390a", 0x30),
-		.type = "s35390a",
-	},
-};
-
-/*
- * board devices
- */
-static struct platform_device *eva_devices[] __initdata = {
-	&lcdc0_device,
-	&pwm_device,
-	&pwm_backlight_device,
-	&leds_gpio_device,
-	&gpio_keys_device,
-	&sh_eth_device,
-	&vcc_sdhi0,
-	&vccq_sdhi0,
-	&sdhi0_device,
-	&sh_mmcif_device,
-	&hdmi_device,
-	&hdmi_lcdc_device,
-	&camera_device,
-	&ceu0_device,
-	&fsi_device,
-	&fsi_wm8978_device,
-	&fsi_hdmi_device,
-	&i2c_gpio_device,
-};
-
-static const struct pinctrl_map eva_pinctrl_map[] = {
-	/* CEU0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_ceu.0", "pfc-r8a7740",
-				  "ceu0_data_0_7", "ceu0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_ceu.0", "pfc-r8a7740",
-				  "ceu0_clk_0", "ceu0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_ceu.0", "pfc-r8a7740",
-				  "ceu0_sync", "ceu0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_ceu.0", "pfc-r8a7740",
-				  "ceu0_field", "ceu0"),
-	/* FSIA */
-	PIN_MAP_MUX_GROUP_DEFAULT("asoc-simple-card.0", "pfc-r8a7740",
-				  "fsia_sclk_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("asoc-simple-card.0", "pfc-r8a7740",
-				  "fsia_mclk_out", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("asoc-simple-card.0", "pfc-r8a7740",
-				  "fsia_data_in_1", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("asoc-simple-card.0", "pfc-r8a7740",
-				  "fsia_data_out_0", "fsia"),
-	/* FSIB */
-	PIN_MAP_MUX_GROUP_DEFAULT("asoc-simple-card.1", "pfc-r8a7740",
-				  "fsib_mclk_in", "fsib"),
-	/* GETHER */
-	PIN_MAP_MUX_GROUP_DEFAULT("r8a7740-gether", "pfc-r8a7740",
-				  "gether_mii", "gether"),
-	PIN_MAP_MUX_GROUP_DEFAULT("r8a7740-gether", "pfc-r8a7740",
-				  "gether_int", "gether"),
-	/* HDMI */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-mobile-hdmi", "pfc-r8a7740",
-				  "hdmi", "hdmi"),
-	/* LCD0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_lcdc_fb.0", "pfc-r8a7740",
-				  "lcd0_data24_0", "lcd0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_lcdc_fb.0", "pfc-r8a7740",
-				  "lcd0_lclk_1", "lcd0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_lcdc_fb.0", "pfc-r8a7740",
-				  "lcd0_sync", "lcd0"),
-	/* MMCIF */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-r8a7740",
-				  "mmc0_data8_1", "mmc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-r8a7740",
-				  "mmc0_ctrl_1", "mmc0"),
-	/* SCIFA1 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.1", "pfc-r8a7740",
-				  "scifa1_data", "scifa1"),
-	/* SDHI0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7740",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7740",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7740",
-				  "sdhi0_wp", "sdhi0"),
-	/* ST1232 */
-	PIN_MAP_MUX_GROUP_DEFAULT("0-0055", "pfc-r8a7740",
-				  "intc_irq10", "intc"),
-	/* TPU0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("renesas-tpu-pwm", "pfc-r8a7740",
-				  "tpu0_to2_1", "tpu0"),
-	/* USBHS */
-	PIN_MAP_MUX_GROUP_DEFAULT("renesas_usbhs", "pfc-r8a7740",
-				  "intc_irq7_1", "intc"),
-};
-
-static void __init eva_clock_init(void)
-{
-	struct clk *system	= clk_get(NULL, "system_clk");
-	struct clk *xtal1	= clk_get(NULL, "extal1");
-	struct clk *usb24s	= clk_get(NULL, "usb24s");
-	struct clk *fsibck	= clk_get(NULL, "fsibck");
-
-	if (IS_ERR(system)	||
-	    IS_ERR(xtal1)	||
-	    IS_ERR(usb24s)	||
-	    IS_ERR(fsibck)) {
-		pr_err("armadillo800eva board clock init failed\n");
-		goto clock_error;
-	}
-
-	/* armadillo 800 eva extal1 is 24MHz */
-	clk_set_rate(xtal1, 24000000);
-
-	/* usb24s use extal1 (= system) clock (= 24MHz) */
-	clk_set_parent(usb24s, system);
-
-	/* FSIBCK is 12.288MHz, and it is parent of FSI-B */
-	clk_set_rate(fsibck, 12288000);
-
-clock_error:
-	if (!IS_ERR(system))
-		clk_put(system);
-	if (!IS_ERR(xtal1))
-		clk_put(xtal1);
-	if (!IS_ERR(usb24s))
-		clk_put(usb24s);
-	if (!IS_ERR(fsibck))
-		clk_put(fsibck);
-}
-
-/*
- * board init
- */
-#define GPIO_PORT7CR	IOMEM(0xe6050007)
-#define GPIO_PORT8CR	IOMEM(0xe6050008)
-static void __init eva_init(void)
-{
-	static struct pm_domain_device domain_devices[] __initdata = {
-		{ "A4LC", &lcdc0_device },
-		{ "A4LC", &hdmi_lcdc_device },
-		{ "A4MP", &hdmi_device },
-		{ "A4MP", &fsi_device },
-		{ "A4R",  &ceu0_device },
-		{ "A4S",  &sh_eth_device },
-		{ "A3SP", &pwm_device },
-		{ "A3SP", &sdhi0_device },
-		{ "A3SP", &sh_mmcif_device },
-	};
-	struct platform_device *usb = NULL, *sdhi1 = NULL;
-
-	regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
-				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
-	regulator_register_always_on(3, "fixed-5.0V", fixed5v0_power_consumers,
-				     ARRAY_SIZE(fixed5v0_power_consumers), 5000000);
-
-	pinctrl_register_mappings(eva_pinctrl_map, ARRAY_SIZE(eva_pinctrl_map));
-	pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
-
-	r8a7740_pinmux_init();
-	r8a7740_meram_workaround();
-
-	/* GETHER */
-	gpio_request_one(18, GPIOF_OUT_INIT_HIGH, NULL); /* PHY_RST */
-
-	/* USB */
-	gpio_request_one(159, GPIOF_IN, NULL); /* USB_DEVICE_MODE */
-
-	if (gpio_get_value(159)) {
-		/* USB Host */
-	} else {
-		/* USB Func */
-		/*
-		 * The USBHS interrupt handlers needs to read the IRQ pin value
-		 * (HI/LOW) to diffentiate USB connection and disconnection
-		 * events (usbhsf_get_vbus()). We thus need to select both the
-		 * intc_irq7_1 pin group and GPIO 209 here.
-		 */
-		gpio_request_one(209, GPIOF_IN, NULL);
-
-		platform_device_register(&usbhsf_device);
-		usb = &usbhsf_device;
-	}
-
-	/* CON1/CON15 Camera */
-	gpio_request_one(173, GPIOF_OUT_INIT_LOW, NULL);  /* STANDBY */
-	gpio_request_one(172, GPIOF_OUT_INIT_HIGH, NULL); /* RST */
-	/* see mt9t111_power() */
-	gpio_request_one(158, GPIOF_OUT_INIT_LOW, NULL);  /* CAM_PON */
-
-	/* FSI-WM8978 */
-	gpio_request(7, NULL);
-	gpio_request(8, NULL);
-	gpio_direction_none(GPIO_PORT7CR); /* FSIAOBT needs no direction */
-	gpio_direction_none(GPIO_PORT8CR); /* FSIAOLR needs no direction */
-
-	/*
-	 * CAUTION
-	 *
-	 * DBGMD/LCDC0/FSIA MUX
-	 * DBGMD_SELECT_B should be set after setting PFC Function.
-	 */
-	gpio_request_one(176, GPIOF_OUT_INIT_HIGH, NULL);
-
-	/*
-	 * We can switch CON8/CON14 by SW1.5,
-	 * but it needs after DBGMD_SELECT_B
-	 */
-	gpio_request_one(6, GPIOF_IN, NULL);
-	if (gpio_get_value(6)) {
-		/* CON14 enable */
-	} else {
-		/* CON8 (SDHI1) enable */
-		pinctrl_register_mappings(eva_sdhi1_pinctrl_map,
-					  ARRAY_SIZE(eva_sdhi1_pinctrl_map));
-
-		platform_device_register(&vcc_sdhi1);
-		platform_device_register(&sdhi1_device);
-		sdhi1 = &sdhi1_device;
-	}
-
-
-#ifdef CONFIG_CACHE_L2X0
-	/* Shared attribute override enable, 32K*8way */
-	l2x0_init(IOMEM(0xf0002000), 0x00400000, 0xc20f0fff);
-#endif
-
-	i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices));
-	i2c_register_board_info(2, i2c2_devices, ARRAY_SIZE(i2c2_devices));
-
-	r8a7740_add_standard_devices();
-
-	platform_add_devices(eva_devices,
-			     ARRAY_SIZE(eva_devices));
-
-	rmobile_add_devices_to_domains(domain_devices,
-				       ARRAY_SIZE(domain_devices));
-	if (usb)
-		rmobile_add_device_to_domain("A3SP", usb);
-	if (sdhi1)
-		rmobile_add_device_to_domain("A3SP", sdhi1);
-
-	r8a7740_pm_init();
-}
-
-static void __init eva_earlytimer_init(void)
-{
-	r8a7740_clock_init(MD_CK0 | MD_CK2);
-	shmobile_earlytimer_init();
-
-	/* the rate of extal1 clock must be set before late_time_init */
-	eva_clock_init();
-}
-
-#define RESCNT2 IOMEM(0xe6188020)
-static void eva_restart(enum reboot_mode mode, const char *cmd)
-{
-	/* Do soft power on reset */
-	writel((1 << 31), RESCNT2);
-}
-
-static const char *eva_boards_compat_dt[] __initdata = {
-	"renesas,armadillo800eva",
-	NULL,
-};
-
-DT_MACHINE_START(ARMADILLO800EVA_DT, "armadillo800eva")
-	.map_io		= r8a7740_map_io,
-	.init_early	= r8a7740_add_early_devices,
-	.init_irq	= r8a7740_init_irq_of,
-	.init_machine	= eva_init,
-	.init_late	= shmobile_init_late,
-	.init_time	= eva_earlytimer_init,
-	.dt_compat	= eva_boards_compat_dt,
-	.restart	= eva_restart,
-MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-bockw-reference.c b/arch/arm/mach-shmobile/board-bockw-reference.c
index 9a74efda3d18..4f78296f7d04 100644
--- a/arch/arm/mach-shmobile/board-bockw-reference.c
+++ b/arch/arm/mach-shmobile/board-bockw-reference.c
@@ -72,7 +72,7 @@ static void __init bockw_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static const char *bockw_boards_compat_dt[] __initdata = {
+static const char *const bockw_boards_compat_dt[] __initconst = {
 	"renesas,bockw-reference",
 	NULL,
 };
diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c
index 25558d1f417f..25a0e7233fe4 100644
--- a/arch/arm/mach-shmobile/board-bockw.c
+++ b/arch/arm/mach-shmobile/board-bockw.c
@@ -723,7 +723,7 @@ static void __init bockw_init_late(void)
 	ADD_USB_FUNC_DEVICE_IF_POSSIBLE();
 }
 
-static const char *bockw_boards_compat_dt[] __initdata = {
+static const char *const bockw_boards_compat_dt[] __initconst = {
 	"renesas,bockw",
 	NULL,
 };
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
deleted file mode 100644
index 260d8319fd82..000000000000
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ /dev/null
@@ -1,916 +0,0 @@
-/*
- * KZM-A9-GT board support
- *
- * Copyright (C) 2012	Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/delay.h>
-#include <linux/gpio.h>
-#include <linux/gpio_keys.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/i2c.h>
-#include <linux/i2c/pcf857x.h>
-#include <linux/input.h>
-#include <linux/irqchip/arm-gic.h>
-#include <linux/mmc/host.h>
-#include <linux/mmc/sh_mmcif.h>
-#include <linux/mmc/sh_mobile_sdhi.h>
-#include <linux/mfd/as3711.h>
-#include <linux/mfd/tmio.h>
-#include <linux/pinctrl/machine.h>
-#include <linux/pinctrl/pinconf-generic.h>
-#include <linux/platform_device.h>
-#include <linux/reboot.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/smsc911x.h>
-#include <linux/usb/r8a66597.h>
-#include <linux/usb/renesas_usbhs.h>
-#include <linux/videodev2.h>
-
-#include <sound/sh_fsi.h>
-#include <sound/simple_card.h>
-#include <asm/hardware/cache-l2x0.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <video/sh_mobile_lcdc.h>
-
-#include "common.h"
-#include "intc.h"
-#include "irqs.h"
-#include "sh73a0.h"
-
-/*
- * external GPIO
- */
-#define GPIO_PCF8575_BASE	(310)
-#define GPIO_PCF8575_PORT10	(GPIO_PCF8575_BASE + 8)
-#define GPIO_PCF8575_PORT11	(GPIO_PCF8575_BASE + 9)
-#define GPIO_PCF8575_PORT12	(GPIO_PCF8575_BASE + 10)
-#define GPIO_PCF8575_PORT13	(GPIO_PCF8575_BASE + 11)
-#define GPIO_PCF8575_PORT14	(GPIO_PCF8575_BASE + 12)
-#define GPIO_PCF8575_PORT15	(GPIO_PCF8575_BASE + 13)
-#define GPIO_PCF8575_PORT16	(GPIO_PCF8575_BASE + 14)
-
-/* Dummy supplies, where voltage doesn't matter */
-static struct regulator_consumer_supply dummy_supplies[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
-};
-
-/*
- * FSI-AK4648
- *
- * this command is required when playback.
- *
- * # amixer set "LINEOUT Mixer DACL" on
- */
-
-/* SMSC 9221 */
-static struct resource smsc9221_resources[] = {
-	[0] = {
-		.start	= 0x10000000, /* CS4 */
-		.end	= 0x100000ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= irq_pin(3), /* IRQ3 */
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct smsc911x_platform_config smsc9221_platdata = {
-	.flags		= SMSC911X_USE_32BIT | SMSC911X_SAVE_MAC_ADDRESS,
-	.phy_interface	= PHY_INTERFACE_MODE_MII,
-	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
-	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
-};
-
-static struct platform_device smsc_device = {
-	.name		= "smsc911x",
-	.dev  = {
-		.platform_data = &smsc9221_platdata,
-	},
-	.resource	= smsc9221_resources,
-	.num_resources	= ARRAY_SIZE(smsc9221_resources),
-};
-
-/* USB external chip */
-static struct r8a66597_platdata usb_host_data = {
-	.on_chip	= 0,
-	.xtal		= R8A66597_PLATDATA_XTAL_48MHZ,
-};
-
-static struct resource usb_resources[] = {
-	[0] = {
-		.start	= 0x10010000,
-		.end	= 0x1001ffff - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= irq_pin(1), /* IRQ1 */
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device usb_host_device = {
-	.name	= "r8a66597_hcd",
-	.dev = {
-		.platform_data		= &usb_host_data,
-		.dma_mask		= NULL,
-		.coherent_dma_mask	= 0xffffffff,
-	},
-	.num_resources	= ARRAY_SIZE(usb_resources),
-	.resource	= usb_resources,
-};
-
-/* USB Func CN17 */
-struct usbhs_private {
-	void __iomem *phy;
-	void __iomem *cr2;
-	struct renesas_usbhs_platform_info info;
-};
-
-#define IRQ15			irq_pin(15)
-#define USB_PHY_MODE		(1 << 4)
-#define USB_PHY_INT_EN		((1 << 3) | (1 << 2))
-#define USB_PHY_ON		(1 << 1)
-#define USB_PHY_OFF		(1 << 0)
-#define USB_PHY_INT_CLR		(USB_PHY_ON | USB_PHY_OFF)
-
-#define usbhs_get_priv(pdev) \
-	container_of(renesas_usbhs_get_info(pdev), struct usbhs_private, info)
-
-static int usbhs_get_vbus(struct platform_device *pdev)
-{
-	struct usbhs_private *priv = usbhs_get_priv(pdev);
-
-	return !((1 << 7) & __raw_readw(priv->cr2));
-}
-
-static int usbhs_phy_reset(struct platform_device *pdev)
-{
-	struct usbhs_private *priv = usbhs_get_priv(pdev);
-
-	/* init phy */
-	__raw_writew(0x8a0a, priv->cr2);
-
-	return 0;
-}
-
-static int usbhs_get_id(struct platform_device *pdev)
-{
-	return USBHS_GADGET;
-}
-
-static irqreturn_t usbhs_interrupt(int irq, void *data)
-{
-	struct platform_device *pdev = data;
-	struct usbhs_private *priv = usbhs_get_priv(pdev);
-
-	renesas_usbhs_call_notify_hotplug(pdev);
-
-	/* clear status */
-	__raw_writew(__raw_readw(priv->phy) | USB_PHY_INT_CLR, priv->phy);
-
-	return IRQ_HANDLED;
-}
-
-static int usbhs_hardware_init(struct platform_device *pdev)
-{
-	struct usbhs_private *priv = usbhs_get_priv(pdev);
-	int ret;
-
-	/* clear interrupt status */
-	__raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->phy);
-
-	ret = request_irq(IRQ15, usbhs_interrupt, IRQF_TRIGGER_HIGH,
-			  dev_name(&pdev->dev), pdev);
-	if (ret) {
-		dev_err(&pdev->dev, "request_irq err\n");
-		return ret;
-	}
-
-	/* enable USB phy interrupt */
-	__raw_writew(USB_PHY_MODE | USB_PHY_INT_EN, priv->phy);
-
-	return 0;
-}
-
-static int usbhs_hardware_exit(struct platform_device *pdev)
-{
-	struct usbhs_private *priv = usbhs_get_priv(pdev);
-
-	/* clear interrupt status */
-	__raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->phy);
-
-	free_irq(IRQ15, pdev);
-
-	return 0;
-}
-
-static u32 usbhs_pipe_cfg[] = {
-	USB_ENDPOINT_XFER_CONTROL,
-	USB_ENDPOINT_XFER_ISOC,
-	USB_ENDPOINT_XFER_ISOC,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_INT,
-	USB_ENDPOINT_XFER_INT,
-	USB_ENDPOINT_XFER_INT,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-	USB_ENDPOINT_XFER_BULK,
-};
-
-static struct usbhs_private usbhs_private = {
-	.phy	= IOMEM(0xe60781e0),		/* USBPHYINT */
-	.cr2	= IOMEM(0xe605810c),		/* USBCR2 */
-	.info = {
-		.platform_callback = {
-			.hardware_init	= usbhs_hardware_init,
-			.hardware_exit	= usbhs_hardware_exit,
-			.get_id		= usbhs_get_id,
-			.phy_reset	= usbhs_phy_reset,
-			.get_vbus	= usbhs_get_vbus,
-		},
-		.driver_param = {
-			.buswait_bwait	= 4,
-			.has_otg	= 1,
-			.pipe_type	= usbhs_pipe_cfg,
-			.pipe_size	= ARRAY_SIZE(usbhs_pipe_cfg),
-		},
-	},
-};
-
-static struct resource usbhs_resources[] = {
-	[0] = {
-		.start	= 0xE6890000,
-		.end	= 0xE68900e6 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(62),
-		.end	= gic_spi(62),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device usbhs_device = {
-	.name	= "renesas_usbhs",
-	.id	= -1,
-	.dev = {
-		.dma_mask		= NULL,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &usbhs_private.info,
-	},
-	.num_resources	= ARRAY_SIZE(usbhs_resources),
-	.resource	= usbhs_resources,
-};
-
-/* LCDC */
-static struct fb_videomode kzm_lcdc_mode = {
-	.name		= "WVGA Panel",
-	.xres		= 800,
-	.yres		= 480,
-	.left_margin	= 220,
-	.right_margin	= 110,
-	.hsync_len	= 70,
-	.upper_margin	= 20,
-	.lower_margin	= 5,
-	.vsync_len	= 5,
-	.sync		= 0,
-};
-
-static struct sh_mobile_lcdc_info lcdc_info = {
-	.clock_source = LCDC_CLK_BUS,
-	.ch[0] = {
-		.chan		= LCDC_CHAN_MAINLCD,
-		.fourcc		= V4L2_PIX_FMT_RGB565,
-		.interface_type	= RGB24,
-		.lcd_modes	= &kzm_lcdc_mode,
-		.num_modes	= 1,
-		.clock_divider	= 5,
-		.flags		= 0,
-		.panel_cfg = {
-			.width	= 152,
-			.height	= 91,
-		},
-	}
-};
-
-static struct resource lcdc_resources[] = {
-	[0] = {
-		.name	= "LCDC",
-		.start	= 0xfe940000,
-		.end	= 0xfe943fff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= intcs_evt2irq(0x580),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device lcdc_device = {
-	.name		= "sh_mobile_lcdc_fb",
-	.num_resources	= ARRAY_SIZE(lcdc_resources),
-	.resource	= lcdc_resources,
-	.dev	= {
-		.platform_data	= &lcdc_info,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-	},
-};
-
-/* Fixed 1.8V regulator to be used by MMCIF */
-static struct regulator_consumer_supply fixed1v8_power_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
-};
-
-/* MMCIF */
-static struct resource sh_mmcif_resources[] = {
-	[0] = {
-		.name	= "MMCIF",
-		.start	= 0xe6bd0000,
-		.end	= 0xe6bd00ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(140),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start	= gic_spi(141),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct sh_mmcif_plat_data sh_mmcif_platdata = {
-	.ocr		= MMC_VDD_165_195,
-	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
-	.ccs_unsupported = true,
-	.slave_id_tx	= SHDMA_SLAVE_MMCIF_TX,
-	.slave_id_rx	= SHDMA_SLAVE_MMCIF_RX,
-};
-
-static struct platform_device mmc_device = {
-	.name		= "sh_mmcif",
-	.dev		= {
-		.dma_mask		= NULL,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &sh_mmcif_platdata,
-	},
-	.num_resources	= ARRAY_SIZE(sh_mmcif_resources),
-	.resource	= sh_mmcif_resources,
-};
-
-/* Fixed 3.3V regulators to be used by SDHI0 */
-static struct regulator_consumer_supply vcc_sdhi0_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
-};
-
-static struct regulator_init_data vcc_sdhi0_init_data = {
-	.constraints = {
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(vcc_sdhi0_consumers),
-	.consumer_supplies      = vcc_sdhi0_consumers,
-};
-
-static struct fixed_voltage_config vcc_sdhi0_info = {
-	.supply_name = "SDHI0 Vcc",
-	.microvolts = 3300000,
-	.gpio = 15,
-	.enable_high = 1,
-	.init_data = &vcc_sdhi0_init_data,
-};
-
-static struct platform_device vcc_sdhi0 = {
-	.name = "reg-fixed-voltage",
-	.id   = 0,
-	.dev  = {
-		.platform_data = &vcc_sdhi0_info,
-	},
-};
-
-/* Fixed 3.3V regulators to be used by SDHI2 */
-static struct regulator_consumer_supply vcc_sdhi2_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.2"),
-};
-
-static struct regulator_init_data vcc_sdhi2_init_data = {
-	.constraints = {
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(vcc_sdhi2_consumers),
-	.consumer_supplies      = vcc_sdhi2_consumers,
-};
-
-static struct fixed_voltage_config vcc_sdhi2_info = {
-	.supply_name = "SDHI2 Vcc",
-	.microvolts = 3300000,
-	.gpio = 14,
-	.enable_high = 1,
-	.init_data = &vcc_sdhi2_init_data,
-};
-
-static struct platform_device vcc_sdhi2 = {
-	.name = "reg-fixed-voltage",
-	.id   = 1,
-	.dev  = {
-		.platform_data = &vcc_sdhi2_info,
-	},
-};
-
-/* SDHI */
-static struct tmio_mmc_data sdhi0_info = {
-	.chan_priv_tx	= (void *)SHDMA_SLAVE_SDHI0_TX,
-	.chan_priv_rx	= (void *)SHDMA_SLAVE_SDHI0_RX,
-	.flags		= TMIO_MMC_HAS_IDLE_WAIT,
-	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
-			  MMC_CAP_POWER_OFF_CARD,
-};
-
-static struct resource sdhi0_resources[] = {
-	[0] = {
-		.name	= "SDHI0",
-		.start	= 0xee100000,
-		.end	= 0xee1000ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= SH_MOBILE_SDHI_IRQ_CARD_DETECT,
-		.start	= gic_spi(83),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDCARD,
-		.start	= gic_spi(84),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDIO,
-		.start	= gic_spi(85),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi0_device = {
-	.name		= "sh_mobile_sdhi",
-	.num_resources	= ARRAY_SIZE(sdhi0_resources),
-	.resource	= sdhi0_resources,
-	.dev	= {
-		.platform_data	= &sdhi0_info,
-	},
-};
-
-/* Micro SD */
-static struct tmio_mmc_data sdhi2_info = {
-	.chan_priv_tx	= (void *)SHDMA_SLAVE_SDHI2_TX,
-	.chan_priv_rx	= (void *)SHDMA_SLAVE_SDHI2_RX,
-	.flags		= TMIO_MMC_HAS_IDLE_WAIT |
-			  TMIO_MMC_USE_GPIO_CD |
-			  TMIO_MMC_WRPROTECT_DISABLE,
-	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_POWER_OFF_CARD,
-	.cd_gpio	= 13,
-};
-
-static struct resource sdhi2_resources[] = {
-	[0] = {
-		.name	= "SDHI2",
-		.start	= 0xee140000,
-		.end	= 0xee1400ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= SH_MOBILE_SDHI_IRQ_CARD_DETECT,
-		.start	= gic_spi(103),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDCARD,
-		.start	= gic_spi(104),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDIO,
-		.start	= gic_spi(105),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi2_device = {
-	.name		= "sh_mobile_sdhi",
-	.id		= 2,
-	.num_resources	= ARRAY_SIZE(sdhi2_resources),
-	.resource	= sdhi2_resources,
-	.dev	= {
-		.platform_data	= &sdhi2_info,
-	},
-};
-
-/* KEY */
-#define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
-
-static struct gpio_keys_button gpio_buttons[] = {
-	GPIO_KEY(KEY_BACK,	GPIO_PCF8575_PORT10,	"SW3"),
-	GPIO_KEY(KEY_RIGHT,	GPIO_PCF8575_PORT11,	"SW2-R"),
-	GPIO_KEY(KEY_LEFT,	GPIO_PCF8575_PORT12,	"SW2-L"),
-	GPIO_KEY(KEY_ENTER,	GPIO_PCF8575_PORT13,	"SW2-P"),
-	GPIO_KEY(KEY_UP,	GPIO_PCF8575_PORT14,	"SW2-U"),
-	GPIO_KEY(KEY_DOWN,	GPIO_PCF8575_PORT15,	"SW2-D"),
-	GPIO_KEY(KEY_HOME,	GPIO_PCF8575_PORT16,	"SW1"),
-};
-
-static struct gpio_keys_platform_data gpio_key_info = {
-	.buttons	= gpio_buttons,
-	.nbuttons	= ARRAY_SIZE(gpio_buttons),
-};
-
-static struct platform_device gpio_keys_device = {
-	.name	= "gpio-keys",
-	.dev	= {
-		.platform_data  = &gpio_key_info,
-	},
-};
-
-/* FSI-AK4648 */
-static struct sh_fsi_platform_info fsi_info = {
-	.port_a = {
-		.tx_id = SHDMA_SLAVE_FSI2A_TX,
-	},
-};
-
-static struct resource fsi_resources[] = {
-	[0] = {
-		.name	= "FSI",
-		.start	= 0xEC230000,
-		.end	= 0xEC230400 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(146),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device fsi_device = {
-	.name		= "sh_fsi2",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(fsi_resources),
-	.resource	= fsi_resources,
-	.dev	= {
-		.platform_data	= &fsi_info,
-	},
-};
-
-static struct asoc_simple_card_info fsi2_ak4648_info = {
-	.name		= "AK4648",
-	.card		= "FSI2A-AK4648",
-	.codec		= "ak4642-codec.0-0012",
-	.platform	= "sh_fsi2",
-	.daifmt		= SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM,
-	.cpu_dai = {
-		.name	= "fsia-dai",
-	},
-	.codec_dai = {
-		.name	= "ak4642-hifi",
-		.sysclk	= 11289600,
-	},
-};
-
-static struct platform_device fsi_ak4648_device = {
-	.name	= "asoc-simple-card",
-	.dev	= {
-		.platform_data	= &fsi2_ak4648_info,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-		.dma_mask = &fsi_ak4648_device.dev.coherent_dma_mask,
-	},
-};
-
-/* I2C */
-
-/* StepDown1 is used to supply 1.315V to the CPU */
-static struct regulator_init_data as3711_sd1 = {
-	.constraints = {
-		.name = "1.315V CPU",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 1315000,
-		.max_uV = 1335000,
-	},
-};
-
-/* StepDown2 is used to supply 1.8V to the CPU and to the board */
-static struct regulator_init_data as3711_sd2 = {
-	.constraints = {
-		.name = "1.8V",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 1800000,
-		.max_uV = 1800000,
-	},
-};
-
-/*
- * StepDown3 is switched in parallel with StepDown2, seems to be off,
- * according to read-back pre-set register values
- */
-
-/* StepDown4 is used to supply 1.215V to the CPU and to the board */
-static struct regulator_init_data as3711_sd4 = {
-	.constraints = {
-		.name = "1.215V",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 1215000,
-		.max_uV = 1235000,
-	},
-};
-
-/* LDO1 is unused and unconnected */
-
-/* LDO2 is used to supply 2.8V to the CPU */
-static struct regulator_init_data as3711_ldo2 = {
-	.constraints = {
-		.name = "2.8V CPU",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 2800000,
-		.max_uV = 2800000,
-	},
-};
-
-/* LDO3 is used to supply 3.0V to the CPU */
-static struct regulator_init_data as3711_ldo3 = {
-	.constraints = {
-		.name = "3.0V CPU",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 3000000,
-		.max_uV = 3000000,
-	},
-};
-
-/* LDO4 is used to supply 2.8V to the board */
-static struct regulator_init_data as3711_ldo4 = {
-	.constraints = {
-		.name = "2.8V",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 2800000,
-		.max_uV = 2800000,
-	},
-};
-
-/* LDO5 is switched parallel to LDO4, also set to 2.8V */
-static struct regulator_init_data as3711_ldo5 = {
-	.constraints = {
-		.name = "2.8V #2",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 2800000,
-		.max_uV = 2800000,
-	},
-};
-
-/* LDO6 is unused and unconnected */
-
-/* LDO7 is used to supply 1.15V to the CPU */
-static struct regulator_init_data as3711_ldo7 = {
-	.constraints = {
-		.name = "1.15V CPU",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 1150000,
-		.max_uV = 1150000,
-	},
-};
-
-/* LDO8 is switched parallel to LDO7, also set to 1.15V */
-static struct regulator_init_data as3711_ldo8 = {
-	.constraints = {
-		.name = "1.15V CPU #2",
-		.boot_on = 1,
-		.always_on = 1,
-		.min_uV = 1150000,
-		.max_uV = 1150000,
-	},
-};
-
-static struct as3711_platform_data as3711_pdata = {
-	.regulator	= {
-		.init_data	= {
-			[AS3711_REGULATOR_SD_1] = &as3711_sd1,
-			[AS3711_REGULATOR_SD_2] = &as3711_sd2,
-			[AS3711_REGULATOR_SD_4] = &as3711_sd4,
-			[AS3711_REGULATOR_LDO_2] = &as3711_ldo2,
-			[AS3711_REGULATOR_LDO_3] = &as3711_ldo3,
-			[AS3711_REGULATOR_LDO_4] = &as3711_ldo4,
-			[AS3711_REGULATOR_LDO_5] = &as3711_ldo5,
-			[AS3711_REGULATOR_LDO_7] = &as3711_ldo7,
-			[AS3711_REGULATOR_LDO_8] = &as3711_ldo8,
-		},
-	},
-	.backlight	= {
-		.su2_fb = "sh_mobile_lcdc_fb.0",
-		.su2_max_uA = 36000,
-		.su2_feedback = AS3711_SU2_CURR_AUTO,
-		.su2_fbprot = AS3711_SU2_GPIO4,
-		.su2_auto_curr1 = true,
-		.su2_auto_curr2 = true,
-		.su2_auto_curr3 = true,
-	},
-};
-
-static struct pcf857x_platform_data pcf8575_pdata = {
-	.gpio_base	= GPIO_PCF8575_BASE,
-};
-
-static struct i2c_board_info i2c0_devices[] = {
-	{
-		I2C_BOARD_INFO("ak4648", 0x12),
-	},
-	{
-		I2C_BOARD_INFO("r2025sd", 0x32),
-	},
-	{
-		I2C_BOARD_INFO("ak8975", 0x0c),
-		.irq = irq_pin(28), /* IRQ28 */
-	},
-	{
-		I2C_BOARD_INFO("adxl34x", 0x1d),
-		.irq = irq_pin(26), /* IRQ26 */
-	},
-	{
-		I2C_BOARD_INFO("as3711", 0x40),
-		.irq = intcs_evt2irq(0x3300), /* IRQ24 */
-		.platform_data = &as3711_pdata,
-	},
-};
-
-static struct i2c_board_info i2c1_devices[] = {
-	{
-		I2C_BOARD_INFO("st1232-ts", 0x55),
-		.irq = irq_pin(8), /* IRQ8 */
-	},
-};
-
-static struct i2c_board_info i2c3_devices[] = {
-	{
-		I2C_BOARD_INFO("pcf8575", 0x20),
-		.irq = irq_pin(19), /* IRQ19 */
-		.platform_data = &pcf8575_pdata,
-	},
-};
-
-static struct platform_device *kzm_devices[] __initdata = {
-	&smsc_device,
-	&usb_host_device,
-	&usbhs_device,
-	&lcdc_device,
-	&mmc_device,
-	&vcc_sdhi0,
-	&vcc_sdhi2,
-	&sdhi0_device,
-	&sdhi2_device,
-	&gpio_keys_device,
-	&fsi_device,
-	&fsi_ak4648_device,
-};
-
-static unsigned long pin_pullup_conf[] = {
-	PIN_CONF_PACKED(PIN_CONFIG_BIAS_PULL_UP, 0),
-};
-
-static const struct pinctrl_map kzm_pinctrl_map[] = {
-	/* FSIA (AK4648) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2", "pfc-sh73a0",
-				  "fsia_mclk_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2", "pfc-sh73a0",
-				  "fsia_sclk_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2", "pfc-sh73a0",
-				  "fsia_data_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2", "pfc-sh73a0",
-				  "fsia_data_out", "fsia"),
-	/* I2C3 */
-	PIN_MAP_MUX_GROUP_DEFAULT("i2c-sh_mobile.3", "pfc-sh73a0",
-				  "i2c3_1", "i2c3"),
-	/* LCD */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_lcdc_fb.0", "pfc-sh73a0",
-				  "lcd_data24", "lcd"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_lcdc_fb.0", "pfc-sh73a0",
-				  "lcd_sync", "lcd"),
-	/* MMCIF */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				  "mmc0_data8_0", "mmc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				  "mmc0_ctrl_0", "mmc0"),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				    "PORT279", pin_pullup_conf),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				      "mmc0_data8_0", pin_pullup_conf),
-	/* SCIFA4 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-sh73a0",
-				  "scifa4_data", "scifa4"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-sh73a0",
-				  "scifa4_ctrl", "scifa4"),
-	/* SDHI0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_cd", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_wp", "sdhi0"),
-	/* SDHI2 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.2", "pfc-sh73a0",
-				  "sdhi2_data4", "sdhi2"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.2", "pfc-sh73a0",
-				  "sdhi2_ctrl", "sdhi2"),
-	/* SMSC */
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x.0", "pfc-sh73a0",
-				  "bsc_cs4", "bsc"),
-	/* USB */
-	PIN_MAP_MUX_GROUP_DEFAULT("renesas_usbhs", "pfc-sh73a0",
-				  "usb_vbus", "usb"),
-};
-
-static void __init kzm_init(void)
-{
-	regulator_register_always_on(2, "fixed-1.8V", fixed1v8_power_consumers,
-				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
-	regulator_register_fixed(3, dummy_supplies, ARRAY_SIZE(dummy_supplies));
-
-	pinctrl_register_mappings(kzm_pinctrl_map, ARRAY_SIZE(kzm_pinctrl_map));
-
-	sh73a0_pinmux_init();
-
-	/* SMSC */
-	gpio_request_one(224, GPIOF_IN, NULL); /* IRQ3 */
-
-	/* LCDC */
-	gpio_request_one(222, GPIOF_OUT_INIT_HIGH, NULL); /* LCDCDON */
-	gpio_request_one(226, GPIOF_OUT_INIT_HIGH, NULL); /* SC */
-
-	/* Touchscreen */
-	gpio_request_one(223, GPIOF_IN, NULL); /* IRQ8 */
-
-#ifdef CONFIG_CACHE_L2X0
-	/* Shared attribute override enable, 64K*8way */
-	l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff);
-#endif
-
-	i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices));
-	i2c_register_board_info(1, i2c1_devices, ARRAY_SIZE(i2c1_devices));
-	i2c_register_board_info(3, i2c3_devices, ARRAY_SIZE(i2c3_devices));
-
-	sh73a0_add_standard_devices();
-	platform_add_devices(kzm_devices, ARRAY_SIZE(kzm_devices));
-
-	sh73a0_pm_init();
-}
-
-static void kzm9g_restart(enum reboot_mode mode, const char *cmd)
-{
-#define RESCNT2 IOMEM(0xe6188020)
-	/* Do soft power on reset */
-	writel((1 << 31), RESCNT2);
-}
-
-static const char *kzm9g_boards_compat_dt[] __initdata = {
-	"renesas,kzm9g",
-	NULL,
-};
-
-DT_MACHINE_START(KZM9G_DT, "kzm9g")
-	.smp		= smp_ops(sh73a0_smp_ops),
-	.map_io		= sh73a0_map_io,
-	.init_early	= sh73a0_add_early_devices,
-	.init_irq	= sh73a0_init_irq,
-	.init_machine	= kzm_init,
-	.init_late	= shmobile_init_late,
-	.init_time	= sh73a0_earlytimer_init,
-	.restart	= kzm9g_restart,
-	.dt_compat	= kzm9g_boards_compat_dt,
-MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-marzen-reference.c b/arch/arm/mach-shmobile/board-marzen-reference.c
deleted file mode 100644
index b15eb923263f..000000000000
--- a/arch/arm/mach-shmobile/board-marzen-reference.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * marzen board support - Reference DT implementation
- *
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Magnus Damm
- * Copyright (C) 2013  Simon Horman
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/clk/shmobile.h>
-#include <linux/clocksource.h>
-#include <linux/of_platform.h>
-
-#include <asm/irq.h>
-#include <asm/mach/arch.h>
-
-#include "common.h"
-#include "irqs.h"
-#include "r8a7779.h"
-
-static void __init marzen_init_timer(void)
-{
-	r8a7779_clocks_init(r8a7779_read_mode_pins());
-	clocksource_of_init();
-}
-
-static void __init marzen_init(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-	r8a7779_init_irq_extpin_dt(1); /* IRQ1 as individual interrupt */
-}
-
-static const char *marzen_boards_compat_dt[] __initdata = {
-	"renesas,marzen",
-	"renesas,marzen-reference",
-	NULL,
-};
-
-DT_MACHINE_START(MARZEN, "marzen")
-	.smp		= smp_ops(r8a7779_smp_ops),
-	.map_io		= r8a7779_map_io,
-	.init_early	= shmobile_init_delay,
-	.init_time	= marzen_init_timer,
-	.init_irq	= r8a7779_init_irq_dt,
-	.init_machine	= marzen_init,
-	.init_late	= shmobile_init_late,
-	.dt_compat	= marzen_boards_compat_dt,
-MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
deleted file mode 100644
index 51db288f192a..000000000000
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ /dev/null
@@ -1,347 +0,0 @@
-/*
- * marzen board support
- *
- * Copyright (C) 2011, 2013  Renesas Solutions Corp.
- * Copyright (C) 2011  Magnus Damm
- * Copyright (C) 2013  Cogent Embedded, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/leds.h>
-#include <linux/dma-mapping.h>
-#include <linux/pinctrl/machine.h>
-#include <linux/platform_data/camera-rcar.h>
-#include <linux/platform_data/gpio-rcar.h>
-#include <linux/platform_data/usb-rcar-phy.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/smsc911x.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/sh_hspi.h>
-#include <linux/mmc/host.h>
-#include <linux/mmc/sh_mobile_sdhi.h>
-#include <linux/mfd/tmio.h>
-
-#include <media/soc_camera.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/traps.h>
-
-#include "common.h"
-#include "irqs.h"
-#include "r8a7779.h"
-
-/* Fixed 3.3V regulator to be used by SDHI0 */
-static struct regulator_consumer_supply fixed3v3_power_consumers[] = {
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
-};
-
-/* Dummy supplies, where voltage doesn't matter */
-static struct regulator_consumer_supply dummy_supplies[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
-};
-
-/* USB PHY */
-static struct resource usb_phy_resources[] = {
-	[0] = {
-		.start		= 0xffe70800,
-		.end		= 0xffe70900 - 1,
-		.flags		= IORESOURCE_MEM,
-	},
-};
-
-static struct rcar_phy_platform_data usb_phy_platform_data;
-
-static struct platform_device usb_phy = {
-	.name		= "rcar_usb_phy",
-	.id		= -1,
-	.dev  = {
-		.platform_data = &usb_phy_platform_data,
-	},
-	.resource	= usb_phy_resources,
-	.num_resources	= ARRAY_SIZE(usb_phy_resources),
-};
-
-/* SMSC LAN89218 */
-static struct resource smsc911x_resources[] = {
-	[0] = {
-		.start		= 0x18000000, /* ExCS0 */
-		.end		= 0x180000ff, /* A1->A7 */
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= irq_pin(1), /* IRQ 1 */
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct smsc911x_platform_config smsc911x_platdata = {
-	.flags		= SMSC911X_USE_32BIT, /* 32-bit SW on 16-bit HW bus */
-	.phy_interface	= PHY_INTERFACE_MODE_MII,
-	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
-	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
-};
-
-static struct platform_device eth_device = {
-	.name		= "smsc911x",
-	.id		= -1,
-	.dev  = {
-		.platform_data = &smsc911x_platdata,
-	},
-	.resource	= smsc911x_resources,
-	.num_resources	= ARRAY_SIZE(smsc911x_resources),
-};
-
-static struct resource sdhi0_resources[] = {
-	[0] = {
-		.name	= "sdhi0",
-		.start	= 0xffe4c000,
-		.end	= 0xffe4c0ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_iid(0x88),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct tmio_mmc_data sdhi0_platform_data = {
-	.chan_priv_tx = (void *)HPBDMA_SLAVE_SDHI0_TX,
-	.chan_priv_rx = (void *)HPBDMA_SLAVE_SDHI0_RX,
-	.flags        = TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT,
-	.capabilities = MMC_CAP_SD_HIGHSPEED,
-};
-
-static struct platform_device sdhi0_device = {
-	.name = "sh_mobile_sdhi",
-	.num_resources = ARRAY_SIZE(sdhi0_resources),
-	.resource = sdhi0_resources,
-	.id = 0,
-	.dev = {
-		.platform_data = &sdhi0_platform_data,
-	}
-};
-
-/* Thermal */
-static struct resource thermal_resources[] = {
-	[0] = {
-		.start		= 0xFFC48000,
-		.end		= 0xFFC48038 - 1,
-		.flags		= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device thermal_device = {
-	.name		= "rcar_thermal",
-	.resource	= thermal_resources,
-	.num_resources	= ARRAY_SIZE(thermal_resources),
-};
-
-/* HSPI */
-static struct resource hspi_resources[] = {
-	[0] = {
-		.start		= 0xFFFC7000,
-		.end		= 0xFFFC7018 - 1,
-		.flags		= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device hspi_device = {
-	.name	= "sh-hspi",
-	.id	= 0,
-	.resource	= hspi_resources,
-	.num_resources	= ARRAY_SIZE(hspi_resources),
-};
-
-/* LEDS */
-static struct gpio_led marzen_leds[] = {
-	{
-		.name		= "led2",
-		.gpio		= RCAR_GP_PIN(4, 29),
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	}, {
-		.name		= "led3",
-		.gpio		= RCAR_GP_PIN(4, 30),
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	}, {
-		.name		= "led4",
-		.gpio		= RCAR_GP_PIN(4, 31),
-		.default_state	= LEDS_GPIO_DEFSTATE_ON,
-	},
-};
-
-static struct gpio_led_platform_data marzen_leds_pdata = {
-	.leds		= marzen_leds,
-	.num_leds	= ARRAY_SIZE(marzen_leds),
-};
-
-static struct platform_device leds_device = {
-	.name	= "leds-gpio",
-	.id	= 0,
-	.dev	= {
-		.platform_data  = &marzen_leds_pdata,
-	},
-};
-
-/* VIN */
-static struct rcar_vin_platform_data vin_platform_data __initdata = {
-	.flags	= RCAR_VIN_BT656,
-};
-
-#define MARZEN_VIN(idx)						\
-static struct resource vin##idx##_resources[] __initdata = {	\
-	DEFINE_RES_MEM(0xffc50000 + 0x1000 * (idx), 0x1000),	\
-	DEFINE_RES_IRQ(gic_iid(0x5f + (idx))),			\
-};								\
-								\
-static struct platform_device_info vin##idx##_info __initdata = { \
-	.name		= "r8a7779-vin",			\
-	.id		= idx,					\
-	.res		= vin##idx##_resources,			\
-	.num_res	= ARRAY_SIZE(vin##idx##_resources),	\
-	.dma_mask	= DMA_BIT_MASK(32),			\
-	.data		= &vin_platform_data,			\
-	.size_data	= sizeof(vin_platform_data),		\
-}
-MARZEN_VIN(1);
-MARZEN_VIN(3);
-
-#define MARZEN_CAMERA(idx)					\
-static struct i2c_board_info camera##idx##_info = {		\
-	I2C_BOARD_INFO("adv7180", 0x20 + (idx)),		\
-};								\
-								\
-static struct soc_camera_link iclink##idx##_adv7180 = {		\
-	.bus_id		= 1 + 2 * (idx),			\
-	.i2c_adapter_id	= 0,					\
-	.board_info	= &camera##idx##_info,			\
-};								\
-								\
-static struct platform_device camera##idx##_device = {		\
-	.name	= "soc-camera-pdrv",				\
-	.id	= idx,						\
-	.dev	= {						\
-		.platform_data	= &iclink##idx##_adv7180,	\
-	},							\
-};
-
-MARZEN_CAMERA(0);
-MARZEN_CAMERA(1);
-
-static struct platform_device *marzen_devices[] __initdata = {
-	&eth_device,
-	&sdhi0_device,
-	&thermal_device,
-	&hspi_device,
-	&leds_device,
-	&usb_phy,
-	&camera0_device,
-	&camera1_device,
-};
-
-static const struct pinctrl_map marzen_pinctrl_map[] = {
-	/* DU (CN10: ARGB0, CN13: LVDS) */
-	PIN_MAP_MUX_GROUP_DEFAULT("rcar-du-r8a7779", "pfc-r8a7779",
-				  "du0_rgb888", "du0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("rcar-du-r8a7779", "pfc-r8a7779",
-				  "du0_sync_1", "du0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("rcar-du-r8a7779", "pfc-r8a7779",
-				  "du0_clk_out_0", "du0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("rcar-du-r8a7779", "pfc-r8a7779",
-				  "du1_rgb666", "du1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("rcar-du-r8a7779", "pfc-r8a7779",
-				  "du1_sync_1", "du1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("rcar-du-r8a7779", "pfc-r8a7779",
-				  "du1_clk_out", "du1"),
-	/* HSPI0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-hspi.0", "pfc-r8a7779",
-				  "hspi0", "hspi0"),
-	/* SCIF2 (CN18: DEBUG0) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.2", "pfc-r8a7779",
-				  "scif2_data_c", "scif2"),
-	/* SCIF4 (CN19: DEBUG1) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-r8a7779",
-				  "scif4_data", "scif4"),
-	/* SDHI0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_cd", "sdhi0"),
-	/* SMSC */
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x", "pfc-r8a7779",
-				  "intc_irq1_b", "intc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x", "pfc-r8a7779",
-				  "lbsc_ex_cs0", "lbsc"),
-	/* USB0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("ehci-platform.0", "pfc-r8a7779",
-				  "usb0", "usb0"),
-	/* USB1 */
-	PIN_MAP_MUX_GROUP_DEFAULT("ehci-platform.0", "pfc-r8a7779",
-				  "usb1", "usb1"),
-	/* USB2 */
-	PIN_MAP_MUX_GROUP_DEFAULT("ehci-platform.1", "pfc-r8a7779",
-				  "usb2", "usb2"),
-	/* VIN1 */
-	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.1", "pfc-r8a7779",
-				  "vin1_clk", "vin1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.1", "pfc-r8a7779",
-				  "vin1_data8", "vin1"),
-	/* VIN3 */
-	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.3", "pfc-r8a7779",
-				  "vin3_clk", "vin3"),
-	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.3", "pfc-r8a7779",
-				  "vin3_data8", "vin3"),
-};
-
-static void __init marzen_init(void)
-{
-	regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
-				ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
-	regulator_register_fixed(1, dummy_supplies,
-				ARRAY_SIZE(dummy_supplies));
-
-	pinctrl_register_mappings(marzen_pinctrl_map,
-				  ARRAY_SIZE(marzen_pinctrl_map));
-	r8a7779_pinmux_init();
-	r8a7779_init_irq_extpin(1); /* IRQ1 as individual interrupt */
-
-	r8a7779_add_standard_devices();
-	platform_device_register_full(&vin1_info);
-	platform_device_register_full(&vin3_info);
-	platform_add_devices(marzen_devices, ARRAY_SIZE(marzen_devices));
-}
-
-static const char *marzen_boards_compat_dt[] __initdata = {
-        "renesas,marzen",
-        NULL,
-};
-
-DT_MACHINE_START(MARZEN, "marzen")
-	.smp		= smp_ops(r8a7779_smp_ops),
-	.map_io		= r8a7779_map_io,
-	.init_early	= r8a7779_add_early_devices,
-	.init_irq	= r8a7779_init_irq_dt,
-	.init_machine	= marzen_init,
-	.init_late	= r8a7779_init_late,
-	.dt_compat	= marzen_boards_compat_dt,
-	.init_time	= r8a7779_earlytimer_init,
-MACHINE_END
diff --git a/arch/arm/mach-shmobile/clock-r8a7740.c b/arch/arm/mach-shmobile/clock-r8a7740.c
deleted file mode 100644
index 9cac8247c72b..000000000000
--- a/arch/arm/mach-shmobile/clock-r8a7740.c
+++ /dev/null
@@ -1,675 +0,0 @@
-/*
- * R8A7740 processor support
- *
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/io.h>
-#include <linux/sh_clk.h>
-#include <linux/clkdev.h>
-
-#include "clock.h"
-#include "common.h"
-#include "r8a7740.h"
-
-/*
- *        |  MDx  |  XTAL1/EXTAL1   |  System   | EXTALR |
- *  Clock |-------+-----------------+  clock    | 32.768 |   RCLK
- *  Mode  | 2/1/0 | src         MHz |  source   |  KHz   |  source
- * -------+-------+-----------------+-----------+--------+----------
- *    0   | 0 0 0 | External  20~50 | XTAL1     |    O   |  EXTALR
- *    1   | 0 0 1 | Crystal   20~30 | XTAL1     |    O   |  EXTALR
- *    2   | 0 1 0 | External  40~50 | XTAL1 / 2 |    O   |  EXTALR
- *    3   | 0 1 1 | Crystal   40~50 | XTAL1 / 2 |    O   |  EXTALR
- *    4   | 1 0 0 | External  20~50 | XTAL1     |    x   |  XTAL1 / 1024
- *    5   | 1 0 1 | Crystal   20~30 | XTAL1     |    x   |  XTAL1 / 1024
- *    6   | 1 1 0 | External  40~50 | XTAL1 / 2 |    x   |  XTAL1 / 2048
- *    7   | 1 1 1 | Crystal   40~50 | XTAL1 / 2 |    x   |  XTAL1 / 2048
- */
-
-/* CPG registers */
-#define FRQCRA		IOMEM(0xe6150000)
-#define FRQCRB		IOMEM(0xe6150004)
-#define VCLKCR1		IOMEM(0xE6150008)
-#define VCLKCR2		IOMEM(0xE615000c)
-#define FRQCRC		IOMEM(0xe61500e0)
-#define FSIACKCR	IOMEM(0xe6150018)
-#define PLLC01CR	IOMEM(0xe6150028)
-
-#define SUBCKCR		IOMEM(0xe6150080)
-#define USBCKCR		IOMEM(0xe615008c)
-
-#define MSTPSR0		IOMEM(0xe6150030)
-#define MSTPSR1		IOMEM(0xe6150038)
-#define MSTPSR2		IOMEM(0xe6150040)
-#define MSTPSR3		IOMEM(0xe6150048)
-#define MSTPSR4		IOMEM(0xe615004c)
-#define FSIBCKCR	IOMEM(0xe6150090)
-#define HDMICKCR	IOMEM(0xe6150094)
-#define SMSTPCR0	IOMEM(0xe6150130)
-#define SMSTPCR1	IOMEM(0xe6150134)
-#define SMSTPCR2	IOMEM(0xe6150138)
-#define SMSTPCR3	IOMEM(0xe615013c)
-#define SMSTPCR4	IOMEM(0xe6150140)
-
-#define FSIDIVA		IOMEM(0xFE1F8000)
-#define FSIDIVB		IOMEM(0xFE1F8008)
-
-/* Fixed 32 KHz root clock from EXTALR pin */
-static struct clk extalr_clk = {
-	.rate	= 32768,
-};
-
-/*
- * 25MHz default rate for the EXTAL1 root input clock.
- * If needed, reset this with clk_set_rate() from the platform code.
- */
-static struct clk extal1_clk = {
-	.rate	= 25000000,
-};
-
-/*
- * 48MHz default rate for the EXTAL2 root input clock.
- * If needed, reset this with clk_set_rate() from the platform code.
- */
-static struct clk extal2_clk = {
-	.rate	= 48000000,
-};
-
-/*
- * 27MHz default rate for the DV_CLKI root input clock.
- * If needed, reset this with clk_set_rate() from the platform code.
- */
-static struct clk dv_clk = {
-	.rate	= 27000000,
-};
-
-SH_CLK_RATIO(div2,	1, 2);
-SH_CLK_RATIO(div1k,	1, 1024);
-
-SH_FIXED_RATIO_CLK(extal1_div2_clk,	extal1_clk,		div2);
-SH_FIXED_RATIO_CLK(extal1_div1024_clk,	extal1_clk,		div1k);
-SH_FIXED_RATIO_CLK(extal1_div2048_clk,	extal1_div2_clk,	div1k);
-SH_FIXED_RATIO_CLK(extal2_div2_clk,	extal2_clk,		div2);
-
-static struct sh_clk_ops followparent_clk_ops = {
-	.recalc	= followparent_recalc,
-};
-
-/* Main clock */
-static struct clk system_clk = {
-	.ops	= &followparent_clk_ops,
-};
-
-SH_FIXED_RATIO_CLK(system_div2_clk, system_clk,	div2);
-
-/* r_clk */
-static struct clk r_clk = {
-	.ops	= &followparent_clk_ops,
-};
-
-/* PLLC0/PLLC1 */
-static unsigned long pllc01_recalc(struct clk *clk)
-{
-	unsigned long mult = 1;
-
-	if (__raw_readl(PLLC01CR) & (1 << 14))
-		mult = ((__raw_readl(clk->enable_reg) >> 24) & 0x7f) + 1;
-
-	return clk->parent->rate * mult;
-}
-
-static struct sh_clk_ops pllc01_clk_ops = {
-	.recalc		= pllc01_recalc,
-};
-
-static struct clk pllc0_clk = {
-	.ops		= &pllc01_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
-	.parent		= &system_clk,
-	.enable_reg	= (void __iomem *)FRQCRC,
-};
-
-static struct clk pllc1_clk = {
-	.ops		= &pllc01_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
-	.parent		= &system_div2_clk,
-	.enable_reg	= (void __iomem *)FRQCRA,
-};
-
-/* PLLC1 / 2 */
-SH_FIXED_RATIO_CLK(pllc1_div2_clk, pllc1_clk, div2);
-
-/* USB clock */
-/*
- * USBCKCR is controlling usb24 clock
- * bit[7] : parent clock
- * bit[6] : clock divide rate
- * And this bit[7] is used as a "usb24s" from other devices.
- * (Video clock / Sub clock / SPU clock)
- * You can controll this clock as a below.
- *
- * struct clk *usb24	= clk_get(dev,  "usb24");
- * struct clk *usb24s	= clk_get(NULL, "usb24s");
- * struct clk *system	= clk_get(NULL, "system_clk");
- * int rate = clk_get_rate(system);
- *
- * clk_set_parent(usb24s, system);  // for bit[7]
- * clk_set_rate(usb24, rate / 2);   // for bit[6]
- */
-static struct clk *usb24s_parents[] = {
-	[0] = &system_clk,
-	[1] = &extal2_clk
-};
-
-static int usb24s_enable(struct clk *clk)
-{
-	__raw_writel(__raw_readl(USBCKCR) & ~(1 << 8), USBCKCR);
-
-	return 0;
-}
-
-static void usb24s_disable(struct clk *clk)
-{
-	__raw_writel(__raw_readl(USBCKCR) | (1 << 8), USBCKCR);
-}
-
-static int usb24s_set_parent(struct clk *clk, struct clk *parent)
-{
-	int i, ret;
-	u32 val;
-
-	if (!clk->parent_table || !clk->parent_num)
-		return -EINVAL;
-
-	/* Search the parent */
-	for (i = 0; i < clk->parent_num; i++)
-		if (clk->parent_table[i] == parent)
-			break;
-
-	if (i == clk->parent_num)
-		return -ENODEV;
-
-	ret = clk_reparent(clk, parent);
-	if (ret < 0)
-		return ret;
-
-	val = __raw_readl(USBCKCR);
-	val &= ~(1 << 7);
-	val |= i << 7;
-	__raw_writel(val, USBCKCR);
-
-	return 0;
-}
-
-static struct sh_clk_ops usb24s_clk_ops = {
-	.recalc		= followparent_recalc,
-	.enable		= usb24s_enable,
-	.disable	= usb24s_disable,
-	.set_parent	= usb24s_set_parent,
-};
-
-static struct clk usb24s_clk = {
-	.ops		= &usb24s_clk_ops,
-	.parent_table	= usb24s_parents,
-	.parent_num	= ARRAY_SIZE(usb24s_parents),
-	.parent		= &system_clk,
-};
-
-static unsigned long usb24_recalc(struct clk *clk)
-{
-	return clk->parent->rate /
-		((__raw_readl(USBCKCR) & (1 << 6)) ? 1 : 2);
-};
-
-static int usb24_set_rate(struct clk *clk, unsigned long rate)
-{
-	u32 val;
-
-	/* closer to which ? parent->rate or parent->rate/2 */
-	val = __raw_readl(USBCKCR);
-	val &= ~(1 << 6);
-	val |= (rate > (clk->parent->rate / 4) * 3) << 6;
-	__raw_writel(val, USBCKCR);
-
-	return 0;
-}
-
-static struct sh_clk_ops usb24_clk_ops = {
-	.recalc		= usb24_recalc,
-	.set_rate	= usb24_set_rate,
-};
-
-static struct clk usb24_clk = {
-	.ops		= &usb24_clk_ops,
-	.parent		= &usb24s_clk,
-};
-
-/* External FSIACK/FSIBCK clock */
-static struct clk fsiack_clk = {
-};
-
-static struct clk fsibck_clk = {
-};
-
-static struct clk *main_clks[] = {
-	&extalr_clk,
-	&extal1_clk,
-	&extal2_clk,
-	&extal1_div2_clk,
-	&extal1_div1024_clk,
-	&extal1_div2048_clk,
-	&extal2_div2_clk,
-	&dv_clk,
-	&system_clk,
-	&system_div2_clk,
-	&r_clk,
-	&pllc0_clk,
-	&pllc1_clk,
-	&pllc1_div2_clk,
-	&usb24s_clk,
-	&usb24_clk,
-	&fsiack_clk,
-	&fsibck_clk,
-};
-
-/* DIV4 clocks */
-static void div4_kick(struct clk *clk)
-{
-	unsigned long value;
-
-	/* set KICK bit in FRQCRB to update hardware setting */
-	value = __raw_readl(FRQCRB);
-	value |= (1 << 31);
-	__raw_writel(value, FRQCRB);
-}
-
-static int divisors[] = { 2, 3, 4, 6, 8, 12, 16, 18,
-			  24, 32, 36, 48, 0, 72, 96, 0 };
-
-static struct clk_div_mult_table div4_div_mult_table = {
-	.divisors = divisors,
-	.nr_divisors = ARRAY_SIZE(divisors),
-};
-
-static struct clk_div4_table div4_table = {
-	.div_mult_table = &div4_div_mult_table,
-	.kick = div4_kick,
-};
-
-enum {
-	DIV4_I, DIV4_ZG, DIV4_B, DIV4_M1, DIV4_HP,
-	DIV4_HPP, DIV4_USBP, DIV4_S, DIV4_ZB, DIV4_M3, DIV4_CP,
-	DIV4_NR
-};
-
-static struct clk div4_clks[DIV4_NR] = {
-	[DIV4_I]	= SH_CLK_DIV4(&pllc1_clk, FRQCRA, 20, 0x6fff, CLK_ENABLE_ON_INIT),
-	[DIV4_ZG]	= SH_CLK_DIV4(&pllc1_clk, FRQCRA, 16, 0x6fff, CLK_ENABLE_ON_INIT),
-	[DIV4_B]	= SH_CLK_DIV4(&pllc1_clk, FRQCRA,  8, 0x6fff, CLK_ENABLE_ON_INIT),
-	[DIV4_M1]	= SH_CLK_DIV4(&pllc1_clk, FRQCRA,  4, 0x6fff, CLK_ENABLE_ON_INIT),
-	[DIV4_HP]	= SH_CLK_DIV4(&pllc1_clk, FRQCRB,  4, 0x6fff, 0),
-	[DIV4_HPP]	= SH_CLK_DIV4(&pllc1_clk, FRQCRC, 20, 0x6fff, 0),
-	[DIV4_USBP]	= SH_CLK_DIV4(&pllc1_clk, FRQCRC, 16, 0x6fff, 0),
-	[DIV4_S]	= SH_CLK_DIV4(&pllc1_clk, FRQCRC, 12, 0x6fff, 0),
-	[DIV4_ZB]	= SH_CLK_DIV4(&pllc1_clk, FRQCRC,  8, 0x6fff, 0),
-	[DIV4_M3]	= SH_CLK_DIV4(&pllc1_clk, FRQCRC,  4, 0x6fff, 0),
-	[DIV4_CP]	= SH_CLK_DIV4(&pllc1_clk, FRQCRC,  0, 0x6fff, 0),
-};
-
-/* DIV6 reparent */
-enum {
-	DIV6_HDMI,
-	DIV6_VCLK1, DIV6_VCLK2,
-	DIV6_FSIA, DIV6_FSIB,
-	DIV6_REPARENT_NR,
-};
-
-static struct clk *hdmi_parent[] = {
-	[0] = &pllc1_div2_clk,
-	[1] = &system_clk,
-	[2] = &dv_clk
-};
-
-static struct clk *vclk_parents[8] = {
-	[0] = &pllc1_div2_clk,
-	[2] = &dv_clk,
-	[3] = &usb24s_clk,
-	[4] = &extal1_div2_clk,
-	[5] = &extalr_clk,
-};
-
-static struct clk *fsia_parents[] = {
-	[0] = &pllc1_div2_clk,
-	[1] = &fsiack_clk, /* external clock */
-};
-
-static struct clk *fsib_parents[] = {
-	[0] = &pllc1_div2_clk,
-	[1] = &fsibck_clk, /* external clock */
-};
-
-static struct clk div6_reparent_clks[DIV6_REPARENT_NR] = {
-	[DIV6_HDMI] = SH_CLK_DIV6_EXT(HDMICKCR, 0,
-				      hdmi_parent, ARRAY_SIZE(hdmi_parent), 6, 2),
-	[DIV6_VCLK1] = SH_CLK_DIV6_EXT(VCLKCR1, 0,
-				       vclk_parents, ARRAY_SIZE(vclk_parents), 12, 3),
-	[DIV6_VCLK2] = SH_CLK_DIV6_EXT(VCLKCR2, 0,
-				       vclk_parents, ARRAY_SIZE(vclk_parents), 12, 3),
-	[DIV6_FSIA] = SH_CLK_DIV6_EXT(FSIACKCR, 0,
-				      fsia_parents, ARRAY_SIZE(fsia_parents), 6, 2),
-	[DIV6_FSIB] = SH_CLK_DIV6_EXT(FSIBCKCR, 0,
-				      fsib_parents, ARRAY_SIZE(fsib_parents), 6, 2),
-};
-
-/* DIV6 clocks */
-enum {
-	DIV6_SUB,
-	DIV6_NR
-};
-
-static struct clk div6_clks[DIV6_NR] = {
-	[DIV6_SUB]	= SH_CLK_DIV6(&pllc1_div2_clk, SUBCKCR, 0),
-};
-
-/* HDMI1/2 clock */
-static unsigned long hdmi12_recalc(struct clk *clk)
-{
-	u32 val = __raw_readl(HDMICKCR);
-	int shift = (int)clk->priv;
-
-	val >>= shift;
-	val &= 0x3;
-
-	return clk->parent->rate / (1 << val);
-};
-
-static int hdmi12_set_rate(struct clk *clk, unsigned long rate)
-{
-	u32 val, mask;
-	int i, shift;
-
-	for (i = 0; i < 3; i++)
-		if (rate == clk->parent->rate / (1 << i))
-			goto find;
-	return -ENODEV;
-
-find:
-	shift = (int)clk->priv;
-
-	val = __raw_readl(HDMICKCR);
-	mask = ~(0x3 << shift);
-	val = (val & mask) | i << shift;
-	__raw_writel(val, HDMICKCR);
-
-	return 0;
-};
-
-static struct sh_clk_ops hdmi12_clk_ops = {
-	.recalc		= hdmi12_recalc,
-	.set_rate	= hdmi12_set_rate,
-};
-
-static struct clk hdmi1_clk = {
-	.ops		= &hdmi12_clk_ops,
-	.priv		= (void *)9,
-	.parent		= &div6_reparent_clks[DIV6_HDMI],  /* late install */
-};
-
-static struct clk hdmi2_clk = {
-	.ops		= &hdmi12_clk_ops,
-	.priv		= (void *)11,
-	.parent		= &div6_reparent_clks[DIV6_HDMI], /* late install */
-};
-
-static struct clk *late_main_clks[] = {
-	&hdmi1_clk,
-	&hdmi2_clk,
-};
-
-/* FSI DIV */
-enum { FSIDIV_A, FSIDIV_B, FSIDIV_REPARENT_NR };
-
-static struct clk fsidivs[] = {
-	[FSIDIV_A] = SH_CLK_FSIDIV(FSIDIVA, &div6_reparent_clks[DIV6_FSIA]),
-	[FSIDIV_B] = SH_CLK_FSIDIV(FSIDIVB, &div6_reparent_clks[DIV6_FSIB]),
-};
-
-/* MSTP */
-enum {
-	MSTP128, MSTP127, MSTP125,
-	MSTP116, MSTP111, MSTP100, MSTP117,
-
-	MSTP230, MSTP229,
-	MSTP222,
-	MSTP218, MSTP217, MSTP216, MSTP214,
-	MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-
-	MSTP329, MSTP328, MSTP323, MSTP320,
-	MSTP314, MSTP313, MSTP312,
-	MSTP309, MSTP304,
-
-	MSTP416, MSTP415, MSTP407, MSTP406,
-
-	MSTP_NR
-};
-
-static struct clk mstp_clks[MSTP_NR] = {
-	[MSTP128] = SH_CLK_MSTP32(&div4_clks[DIV4_S],	SMSTPCR1, 28, 0), /* CEU21 */
-	[MSTP127] = SH_CLK_MSTP32(&div4_clks[DIV4_S],	SMSTPCR1, 27, 0), /* CEU20 */
-	[MSTP125] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR1, 25, 0), /* TMU0 */
-	[MSTP117] = SH_CLK_MSTP32(&div4_clks[DIV4_B],	SMSTPCR1, 17, 0), /* LCDC1 */
-	[MSTP116] = SH_CLK_MSTP32(&div4_clks[DIV4_HPP],	SMSTPCR1, 16, 0), /* IIC0 */
-	[MSTP111] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR1, 11, 0), /* TMU1 */
-	[MSTP100] = SH_CLK_MSTP32(&div4_clks[DIV4_B],	SMSTPCR1,  0, 0), /* LCDC0 */
-
-	[MSTP230] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2, 30, 0), /* SCIFA6 */
-	[MSTP229] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR2, 29, 0), /* INTCA */
-	[MSTP222] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2, 22, 0), /* SCIFA7 */
-	[MSTP218] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 18, 0), /* DMAC1 */
-	[MSTP217] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 17, 0), /* DMAC2 */
-	[MSTP216] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 16, 0), /* DMAC3 */
-	[MSTP214] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 14, 0), /* USBDMAC */
-	[MSTP207] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  7, 0), /* SCIFA5 */
-	[MSTP206] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  6, 0), /* SCIFB */
-	[MSTP204] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  4, 0), /* SCIFA0 */
-	[MSTP203] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  3, 0), /* SCIFA1 */
-	[MSTP202] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  2, 0), /* SCIFA2 */
-	[MSTP201] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  1, 0), /* SCIFA3 */
-	[MSTP200] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  0, 0), /* SCIFA4 */
-
-	[MSTP329] = SH_CLK_MSTP32(&r_clk,		SMSTPCR3, 29, 0), /* CMT10 */
-	[MSTP328] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 28, 0), /* FSI */
-	[MSTP323] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR3, 23, 0), /* IIC1 */
-	[MSTP320] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 20, 0), /* USBF */
-	[MSTP314] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 14, 0), /* SDHI0 */
-	[MSTP313] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 13, 0), /* SDHI1 */
-	[MSTP312] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 12, 0), /* MMC */
-	[MSTP309] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3,  9, 0), /* GEther */
-	[MSTP304] = SH_CLK_MSTP32(&div4_clks[DIV4_CP],	SMSTPCR3,  4, 0), /* TPU0 */
-
-	[MSTP416] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4, 16, 0), /* USBHOST */
-	[MSTP415] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4, 15, 0), /* SDHI2 */
-	[MSTP407] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4,  7, 0), /* USB-Func */
-	[MSTP406] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4,  6, 0), /* USB Phy */
-};
-
-static struct clk_lookup lookups[] = {
-	/* main clocks */
-	CLKDEV_CON_ID("extalr",			&extalr_clk),
-	CLKDEV_CON_ID("extal1",			&extal1_clk),
-	CLKDEV_CON_ID("extal2",			&extal2_clk),
-	CLKDEV_CON_ID("extal1_div2",		&extal1_div2_clk),
-	CLKDEV_CON_ID("extal1_div1024",		&extal1_div1024_clk),
-	CLKDEV_CON_ID("extal1_div2048",		&extal1_div2048_clk),
-	CLKDEV_CON_ID("extal2_div2",		&extal2_div2_clk),
-	CLKDEV_CON_ID("dv_clk",			&dv_clk),
-	CLKDEV_CON_ID("system_clk",		&system_clk),
-	CLKDEV_CON_ID("system_div2_clk",	&system_div2_clk),
-	CLKDEV_CON_ID("r_clk",			&r_clk),
-	CLKDEV_CON_ID("pllc0_clk",		&pllc0_clk),
-	CLKDEV_CON_ID("pllc1_clk",		&pllc1_clk),
-	CLKDEV_CON_ID("pllc1_div2_clk",		&pllc1_div2_clk),
-	CLKDEV_CON_ID("usb24s",			&usb24s_clk),
-	CLKDEV_CON_ID("hdmi1",			&hdmi1_clk),
-	CLKDEV_CON_ID("hdmi2",			&hdmi2_clk),
-	CLKDEV_CON_ID("video1",			&div6_reparent_clks[DIV6_VCLK1]),
-	CLKDEV_CON_ID("video2",			&div6_reparent_clks[DIV6_VCLK2]),
-	CLKDEV_CON_ID("fsiack",			&fsiack_clk),
-	CLKDEV_CON_ID("fsibck",			&fsibck_clk),
-
-	/* DIV4 clocks */
-	CLKDEV_CON_ID("i_clk",			&div4_clks[DIV4_I]),
-	CLKDEV_CON_ID("zg_clk",			&div4_clks[DIV4_ZG]),
-	CLKDEV_CON_ID("b_clk",			&div4_clks[DIV4_B]),
-	CLKDEV_CON_ID("m1_clk",			&div4_clks[DIV4_M1]),
-	CLKDEV_CON_ID("hp_clk",			&div4_clks[DIV4_HP]),
-	CLKDEV_CON_ID("hpp_clk",		&div4_clks[DIV4_HPP]),
-	CLKDEV_CON_ID("s_clk",			&div4_clks[DIV4_S]),
-	CLKDEV_CON_ID("zb_clk",			&div4_clks[DIV4_ZB]),
-	CLKDEV_CON_ID("m3_clk",			&div4_clks[DIV4_M3]),
-	CLKDEV_CON_ID("cp_clk",			&div4_clks[DIV4_CP]),
-
-	/* DIV6 clocks */
-	CLKDEV_CON_ID("sub_clk",		&div6_clks[DIV6_SUB]),
-
-	/* MSTP32 clocks */
-	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0",	&mstp_clks[MSTP100]),
-	CLKDEV_DEV_ID("i2c-sh_mobile.0",	&mstp_clks[MSTP116]),
-	CLKDEV_DEV_ID("fff20000.i2c",		&mstp_clks[MSTP116]),
-	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.1",	&mstp_clks[MSTP117]),
-	CLKDEV_DEV_ID("sh_mobile_ceu.0",	&mstp_clks[MSTP127]),
-	CLKDEV_DEV_ID("sh_mobile_ceu.1",	&mstp_clks[MSTP128]),
-
-	CLKDEV_DEV_ID("sh-sci.4",		&mstp_clks[MSTP200]),
-	CLKDEV_DEV_ID("e6c80000.serial",	&mstp_clks[MSTP200]),
-	CLKDEV_DEV_ID("sh-sci.3",		&mstp_clks[MSTP201]),
-	CLKDEV_DEV_ID("e6c70000.serial",	&mstp_clks[MSTP201]),
-	CLKDEV_DEV_ID("sh-sci.2",		&mstp_clks[MSTP202]),
-	CLKDEV_DEV_ID("e6c60000.serial",	&mstp_clks[MSTP202]),
-	CLKDEV_DEV_ID("sh-sci.1",		&mstp_clks[MSTP203]),
-	CLKDEV_DEV_ID("e6c50000.serial",	&mstp_clks[MSTP203]),
-	CLKDEV_DEV_ID("sh-sci.0",		&mstp_clks[MSTP204]),
-	CLKDEV_DEV_ID("e6c40000.serial",	&mstp_clks[MSTP204]),
-	CLKDEV_DEV_ID("sh-sci.8",		&mstp_clks[MSTP206]),
-	CLKDEV_DEV_ID("e6c30000.serial",	&mstp_clks[MSTP206]),
-	CLKDEV_DEV_ID("sh-sci.5",		&mstp_clks[MSTP207]),
-	CLKDEV_DEV_ID("e6cb0000.serial",	&mstp_clks[MSTP207]),
-	CLKDEV_DEV_ID("sh-dma-engine.3",	&mstp_clks[MSTP214]),
-	CLKDEV_DEV_ID("sh-dma-engine.2",	&mstp_clks[MSTP216]),
-	CLKDEV_DEV_ID("sh-dma-engine.1",	&mstp_clks[MSTP217]),
-	CLKDEV_DEV_ID("sh-dma-engine.0",	&mstp_clks[MSTP218]),
-	CLKDEV_DEV_ID("sh-sci.7",		&mstp_clks[MSTP222]),
-	CLKDEV_DEV_ID("e6cd0000.serial",	&mstp_clks[MSTP222]),
-	CLKDEV_DEV_ID("renesas_intc_irqpin.0",	&mstp_clks[MSTP229]),
-	CLKDEV_DEV_ID("renesas_intc_irqpin.1",	&mstp_clks[MSTP229]),
-	CLKDEV_DEV_ID("renesas_intc_irqpin.2",	&mstp_clks[MSTP229]),
-	CLKDEV_DEV_ID("renesas_intc_irqpin.3",	&mstp_clks[MSTP229]),
-	CLKDEV_DEV_ID("sh-sci.6",		&mstp_clks[MSTP230]),
-	CLKDEV_DEV_ID("e6cc0000.serial",	&mstp_clks[MSTP230]),
-
-	CLKDEV_DEV_ID("sh_fsi2",		&mstp_clks[MSTP328]),
-	CLKDEV_DEV_ID("fe1f0000.sound",		&mstp_clks[MSTP328]),
-	CLKDEV_DEV_ID("i2c-sh_mobile.1",	&mstp_clks[MSTP323]),
-	CLKDEV_DEV_ID("e6c20000.i2c",		&mstp_clks[MSTP323]),
-	CLKDEV_DEV_ID("renesas_usbhs",		&mstp_clks[MSTP320]),
-	CLKDEV_DEV_ID("sh_mobile_sdhi.0",	&mstp_clks[MSTP314]),
-	CLKDEV_DEV_ID("e6850000.sd",		&mstp_clks[MSTP314]),
-	CLKDEV_DEV_ID("sh_mobile_sdhi.1",	&mstp_clks[MSTP313]),
-	CLKDEV_DEV_ID("e6860000.sd",		&mstp_clks[MSTP313]),
-	CLKDEV_DEV_ID("sh_mmcif",		&mstp_clks[MSTP312]),
-	CLKDEV_DEV_ID("e6bd0000.mmc",		&mstp_clks[MSTP312]),
-	CLKDEV_DEV_ID("r8a7740-gether",		&mstp_clks[MSTP309]),
-	CLKDEV_DEV_ID("e9a00000.ethernet",	&mstp_clks[MSTP309]),
-	CLKDEV_DEV_ID("renesas-tpu-pwm",	&mstp_clks[MSTP304]),
-	CLKDEV_DEV_ID("e6600000.pwm",		&mstp_clks[MSTP304]),
-
-	CLKDEV_DEV_ID("sh_mobile_sdhi.2",	&mstp_clks[MSTP415]),
-	CLKDEV_DEV_ID("e6870000.sd",		&mstp_clks[MSTP415]),
-
-	/* ICK */
-	CLKDEV_ICK_ID("fck",	"sh-tmu.1",		&mstp_clks[MSTP111]),
-	CLKDEV_ICK_ID("fck",	"fff90000.timer",	&mstp_clks[MSTP111]),
-	CLKDEV_ICK_ID("fck",	"sh-tmu.0",		&mstp_clks[MSTP125]),
-	CLKDEV_ICK_ID("fck",	"fff80000.timer",	&mstp_clks[MSTP125]),
-	CLKDEV_ICK_ID("fck",	"sh-cmt-48.1",		&mstp_clks[MSTP329]),
-	CLKDEV_ICK_ID("fck",	"e6138000.timer",	&mstp_clks[MSTP329]),
-	CLKDEV_ICK_ID("host",	"renesas_usbhs",	&mstp_clks[MSTP416]),
-	CLKDEV_ICK_ID("func",	"renesas_usbhs",	&mstp_clks[MSTP407]),
-	CLKDEV_ICK_ID("phy",	"renesas_usbhs",	&mstp_clks[MSTP406]),
-	CLKDEV_ICK_ID("pci",	"renesas_usbhs",	&div4_clks[DIV4_USBP]),
-	CLKDEV_ICK_ID("usb24",	"renesas_usbhs",	&usb24_clk),
-	CLKDEV_ICK_ID("ick",	"sh-mobile-hdmi",	&div6_reparent_clks[DIV6_HDMI]),
-
-	CLKDEV_ICK_ID("icka", "sh_fsi2",	&div6_reparent_clks[DIV6_FSIA]),
-	CLKDEV_ICK_ID("ickb", "sh_fsi2",	&div6_reparent_clks[DIV6_FSIB]),
-	CLKDEV_ICK_ID("diva", "sh_fsi2",	&fsidivs[FSIDIV_A]),
-	CLKDEV_ICK_ID("divb", "sh_fsi2",	&fsidivs[FSIDIV_B]),
-	CLKDEV_ICK_ID("xcka", "sh_fsi2",	&fsiack_clk),
-	CLKDEV_ICK_ID("xckb", "sh_fsi2",	&fsibck_clk),
-};
-
-void __init r8a7740_clock_init(u8 md_ck)
-{
-	int k, ret = 0;
-
-	/* detect system clock parent */
-	if (md_ck & MD_CK1)
-		system_clk.parent = &extal1_div2_clk;
-	else
-		system_clk.parent = &extal1_clk;
-
-	/* detect RCLK parent */
-	switch (md_ck & (MD_CK2 | MD_CK1)) {
-	case MD_CK2 | MD_CK1:
-		r_clk.parent = &extal1_div2048_clk;
-		break;
-	case MD_CK2:
-		r_clk.parent = &extal1_div1024_clk;
-		break;
-	case MD_CK1:
-	default:
-		r_clk.parent = &extalr_clk;
-		break;
-	}
-
-	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
-		ret = clk_register(main_clks[k]);
-
-	if (!ret)
-		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
-
-	if (!ret)
-		ret = sh_clk_div6_register(div6_clks, DIV6_NR);
-
-	if (!ret)
-		ret = sh_clk_div6_reparent_register(div6_reparent_clks,
-						    DIV6_REPARENT_NR);
-
-	if (!ret)
-		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
-
-	for (k = 0; !ret && (k < ARRAY_SIZE(late_main_clks)); k++)
-		ret = clk_register(late_main_clks[k]);
-
-	if (!ret)
-		ret = sh_clk_fsidiv_register(fsidivs, FSIDIV_REPARENT_NR);
-
-	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
-
-	if (!ret)
-		shmobile_clk_init();
-	else
-		panic("failed to setup r8a7740 clocks\n");
-}
diff --git a/arch/arm/mach-shmobile/clock-r8a7779.c b/arch/arm/mach-shmobile/clock-r8a7779.c
deleted file mode 100644
index fa8ab2cc9187..000000000000
--- a/arch/arm/mach-shmobile/clock-r8a7779.c
+++ /dev/null
@@ -1,271 +0,0 @@
-/*
- * r8a7779 clock framework support
- *
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/bitops.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/io.h>
-#include <linux/sh_clk.h>
-#include <linux/clkdev.h>
-#include <linux/sh_timer.h>
-
-#include "clock.h"
-#include "common.h"
-#include "r8a7779.h"
-
-/*
- *		MD1 = 1			MD1 = 0
- *		(PLLA = 1500)		(PLLA = 1600)
- *		(MHz)			(MHz)
- *------------------------------------------------+--------------------
- * clkz		1000   (2/3)		800   (1/2)
- * clkzs	 250   (1/6)		200   (1/8)
- * clki		 750   (1/2)		800   (1/2)
- * clks		 250   (1/6)		200   (1/8)
- * clks1	 125   (1/12)		100   (1/16)
- * clks3	 187.5 (1/8)		200   (1/8)
- * clks4	  93.7 (1/16)		100   (1/16)
- * clkp		  62.5 (1/24)		 50   (1/32)
- * clkg		  62.5 (1/24)		 66.6 (1/24)
- * clkb, CLKOUT
- * (MD2 = 0)	  62.5 (1/24)		 66.6 (1/24)
- * (MD2 = 1)	  41.6 (1/36)		 50   (1/32)
-*/
-
-#define MD(nr)	BIT(nr)
-
-#define MSTPCR0		IOMEM(0xffc80030)
-#define MSTPCR1		IOMEM(0xffc80034)
-#define MSTPCR3		IOMEM(0xffc8003c)
-#define MSTPSR1		IOMEM(0xffc80044)
-
-/* ioremap() through clock mapping mandatory to avoid
- * collision with ARM coherent DMA virtual memory range.
- */
-
-static struct clk_mapping cpg_mapping = {
-	.phys	= 0xffc80000,
-	.len	= 0x80,
-};
-
-/*
- * Default rate for the root input clock, reset this with clk_set_rate()
- * from the platform code.
- */
-static struct clk plla_clk = {
-	/* .rate will be updated on r8a7779_clock_init() */
-	.mapping	= &cpg_mapping,
-};
-
-/*
- * clock ratio of these clock will be updated
- * on r8a7779_clock_init()
- */
-SH_FIXED_RATIO_CLK_SET(clkz_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clkzs_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clki_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clks_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clks1_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clks3_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clks4_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clkb_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clkout_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clkp_clk,	plla_clk, 1, 1);
-SH_FIXED_RATIO_CLK_SET(clkg_clk,	plla_clk, 1, 1);
-
-static struct clk *main_clks[] = {
-	&plla_clk,
-	&clkz_clk,
-	&clkzs_clk,
-	&clki_clk,
-	&clks_clk,
-	&clks1_clk,
-	&clks3_clk,
-	&clks4_clk,
-	&clkb_clk,
-	&clkout_clk,
-	&clkp_clk,
-	&clkg_clk,
-};
-
-enum { MSTP323, MSTP322, MSTP321, MSTP320,
-	MSTP120,
-	MSTP116, MSTP115, MSTP114,
-	MSTP110, MSTP109, MSTP108,
-	MSTP103, MSTP101, MSTP100,
-	MSTP030,
-	MSTP029, MSTP028, MSTP027, MSTP026, MSTP025, MSTP024, MSTP023, MSTP022, MSTP021,
-	MSTP016, MSTP015, MSTP014,
-	MSTP007,
-	MSTP_NR };
-
-static struct clk mstp_clks[MSTP_NR] = {
-	[MSTP323] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 23, 0), /* SDHI0 */
-	[MSTP322] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 22, 0), /* SDHI1 */
-	[MSTP321] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 21, 0), /* SDHI2 */
-	[MSTP320] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 20, 0), /* SDHI3 */
-	[MSTP120] = SH_CLK_MSTP32_STS(&clks_clk, MSTPCR1, 20, MSTPSR1, 0), /* VIN3 */
-	[MSTP116] = SH_CLK_MSTP32_STS(&clkp_clk, MSTPCR1, 16, MSTPSR1, 0), /* PCIe */
-	[MSTP115] = SH_CLK_MSTP32_STS(&clkp_clk, MSTPCR1, 15, MSTPSR1, 0), /* SATA */
-	[MSTP114] = SH_CLK_MSTP32_STS(&clkp_clk, MSTPCR1, 14, MSTPSR1, 0), /* Ether */
-	[MSTP110] = SH_CLK_MSTP32_STS(&clks_clk, MSTPCR1, 10, MSTPSR1, 0), /* VIN0 */
-	[MSTP109] = SH_CLK_MSTP32_STS(&clks_clk, MSTPCR1,  9, MSTPSR1, 0), /* VIN1 */
-	[MSTP108] = SH_CLK_MSTP32_STS(&clks_clk, MSTPCR1,  8, MSTPSR1, 0), /* VIN2 */
-	[MSTP103] = SH_CLK_MSTP32_STS(&clks_clk, MSTPCR1,  3, MSTPSR1, 0), /* DU */
-	[MSTP101] = SH_CLK_MSTP32_STS(&clkp_clk, MSTPCR1,  1, MSTPSR1, 0), /* USB2 */
-	[MSTP100] = SH_CLK_MSTP32_STS(&clkp_clk, MSTPCR1,  0, MSTPSR1, 0), /* USB0/1 */
-	[MSTP030] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 30, 0), /* I2C0 */
-	[MSTP029] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 29, 0), /* I2C1 */
-	[MSTP028] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 28, 0), /* I2C2 */
-	[MSTP027] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 27, 0), /* I2C3 */
-	[MSTP026] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 26, 0), /* SCIF0 */
-	[MSTP025] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 25, 0), /* SCIF1 */
-	[MSTP024] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 24, 0), /* SCIF2 */
-	[MSTP023] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 23, 0), /* SCIF3 */
-	[MSTP022] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 22, 0), /* SCIF4 */
-	[MSTP021] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 21, 0), /* SCIF5 */
-	[MSTP016] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 16, 0), /* TMU0 */
-	[MSTP015] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 15, 0), /* TMU1 */
-	[MSTP014] = SH_CLK_MSTP32(&clkp_clk, MSTPCR0, 14, 0), /* TMU2 */
-	[MSTP007] = SH_CLK_MSTP32(&clks_clk, MSTPCR0,  7, 0), /* HSPI */
-};
-
-static struct clk_lookup lookups[] = {
-	/* main clocks */
-	CLKDEV_CON_ID("plla_clk", &plla_clk),
-	CLKDEV_CON_ID("clkz_clk", &clkz_clk),
-	CLKDEV_CON_ID("clkzs_clk", &clkzs_clk),
-
-	/* DIV4 clocks */
-	CLKDEV_CON_ID("shyway_clk",	&clks_clk),
-	CLKDEV_CON_ID("bus_clk",	&clkout_clk),
-	CLKDEV_CON_ID("shyway4_clk",	&clks4_clk),
-	CLKDEV_CON_ID("shyway3_clk",	&clks3_clk),
-	CLKDEV_CON_ID("shyway1_clk",	&clks1_clk),
-	CLKDEV_CON_ID("peripheral_clk",	&clkp_clk),
-
-	/* MSTP32 clocks */
-	CLKDEV_DEV_ID("r8a7779-vin.3", &mstp_clks[MSTP120]), /* VIN3 */
-	CLKDEV_DEV_ID("rcar-pcie", &mstp_clks[MSTP116]), /* PCIe */
-	CLKDEV_DEV_ID("sata_rcar", &mstp_clks[MSTP115]), /* SATA */
-	CLKDEV_DEV_ID("fc600000.sata", &mstp_clks[MSTP115]), /* SATA w/DT */
-	CLKDEV_DEV_ID("r8a777x-ether", &mstp_clks[MSTP114]), /* Ether */
-	CLKDEV_DEV_ID("r8a7779-vin.0", &mstp_clks[MSTP110]), /* VIN0 */
-	CLKDEV_DEV_ID("r8a7779-vin.1", &mstp_clks[MSTP109]), /* VIN1 */
-	CLKDEV_DEV_ID("r8a7779-vin.2", &mstp_clks[MSTP108]), /* VIN2 */
-	CLKDEV_DEV_ID("ehci-platform.1", &mstp_clks[MSTP101]), /* USB EHCI port2 */
-	CLKDEV_DEV_ID("ohci-platform.1", &mstp_clks[MSTP101]), /* USB OHCI port2 */
-	CLKDEV_DEV_ID("ehci-platform.0", &mstp_clks[MSTP100]), /* USB EHCI port0/1 */
-	CLKDEV_DEV_ID("ohci-platform.0", &mstp_clks[MSTP100]), /* USB OHCI port0/1 */
-	CLKDEV_ICK_ID("fck", "sh-tmu.0", &mstp_clks[MSTP016]), /* TMU0 */
-	CLKDEV_DEV_ID("i2c-rcar.0", &mstp_clks[MSTP030]), /* I2C0 */
-	CLKDEV_DEV_ID("ffc70000.i2c", &mstp_clks[MSTP030]), /* I2C0 */
-	CLKDEV_DEV_ID("i2c-rcar.1", &mstp_clks[MSTP029]), /* I2C1 */
-	CLKDEV_DEV_ID("ffc71000.i2c", &mstp_clks[MSTP029]), /* I2C1 */
-	CLKDEV_DEV_ID("i2c-rcar.2", &mstp_clks[MSTP028]), /* I2C2 */
-	CLKDEV_DEV_ID("ffc72000.i2c", &mstp_clks[MSTP028]), /* I2C2 */
-	CLKDEV_DEV_ID("i2c-rcar.3", &mstp_clks[MSTP027]), /* I2C3 */
-	CLKDEV_DEV_ID("ffc73000.i2c", &mstp_clks[MSTP027]), /* I2C3 */
-	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP026]), /* SCIF0 */
-	CLKDEV_DEV_ID("sh-sci.1", &mstp_clks[MSTP025]), /* SCIF1 */
-	CLKDEV_DEV_ID("sh-sci.2", &mstp_clks[MSTP024]), /* SCIF2 */
-	CLKDEV_DEV_ID("sh-sci.3", &mstp_clks[MSTP023]), /* SCIF3 */
-	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP022]), /* SCIF4 */
-	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP021]), /* SCIF6 */
-	CLKDEV_DEV_ID("sh-hspi.0", &mstp_clks[MSTP007]), /* HSPI0 */
-	CLKDEV_DEV_ID("fffc7000.spi", &mstp_clks[MSTP007]), /* HSPI0 */
-	CLKDEV_DEV_ID("sh-hspi.1", &mstp_clks[MSTP007]), /* HSPI1 */
-	CLKDEV_DEV_ID("fffc8000.spi", &mstp_clks[MSTP007]), /* HSPI1 */
-	CLKDEV_DEV_ID("sh-hspi.2", &mstp_clks[MSTP007]), /* HSPI2 */
-	CLKDEV_DEV_ID("fffc6000.spi", &mstp_clks[MSTP007]), /* HSPI2 */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP323]), /* SDHI0 */
-	CLKDEV_DEV_ID("ffe4c000.sd", &mstp_clks[MSTP323]), /* SDHI0 */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP322]), /* SDHI1 */
-	CLKDEV_DEV_ID("ffe4d000.sd", &mstp_clks[MSTP322]), /* SDHI1 */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP321]), /* SDHI2 */
-	CLKDEV_DEV_ID("ffe4e000.sd", &mstp_clks[MSTP321]), /* SDHI2 */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.3", &mstp_clks[MSTP320]), /* SDHI3 */
-	CLKDEV_DEV_ID("ffe4f000.sd", &mstp_clks[MSTP320]), /* SDHI3 */
-	CLKDEV_DEV_ID("rcar-du-r8a7779", &mstp_clks[MSTP103]), /* DU */
-};
-
-void __init r8a7779_clock_init(void)
-{
-	u32 mode = r8a7779_read_mode_pins();
-	int k, ret = 0;
-
-	if (mode & MD(1)) {
-		plla_clk.rate = 1500000000;
-
-		SH_CLK_SET_RATIO(&clkz_clk_ratio,	2, 3);
-		SH_CLK_SET_RATIO(&clkzs_clk_ratio,	1, 6);
-		SH_CLK_SET_RATIO(&clki_clk_ratio,	1, 2);
-		SH_CLK_SET_RATIO(&clks_clk_ratio,	1, 6);
-		SH_CLK_SET_RATIO(&clks1_clk_ratio,	1, 12);
-		SH_CLK_SET_RATIO(&clks3_clk_ratio,	1, 8);
-		SH_CLK_SET_RATIO(&clks4_clk_ratio,	1, 16);
-		SH_CLK_SET_RATIO(&clkp_clk_ratio,	1, 24);
-		SH_CLK_SET_RATIO(&clkg_clk_ratio,	1, 24);
-		if (mode & MD(2)) {
-			SH_CLK_SET_RATIO(&clkb_clk_ratio,	1, 36);
-			SH_CLK_SET_RATIO(&clkout_clk_ratio,	1, 36);
-		} else {
-			SH_CLK_SET_RATIO(&clkb_clk_ratio,	1, 24);
-			SH_CLK_SET_RATIO(&clkout_clk_ratio,	1, 24);
-		}
-	} else {
-		plla_clk.rate = 1600000000;
-
-		SH_CLK_SET_RATIO(&clkz_clk_ratio,	1, 2);
-		SH_CLK_SET_RATIO(&clkzs_clk_ratio,	1, 8);
-		SH_CLK_SET_RATIO(&clki_clk_ratio,	1, 2);
-		SH_CLK_SET_RATIO(&clks_clk_ratio,	1, 8);
-		SH_CLK_SET_RATIO(&clks1_clk_ratio,	1, 16);
-		SH_CLK_SET_RATIO(&clks3_clk_ratio,	1, 8);
-		SH_CLK_SET_RATIO(&clks4_clk_ratio,	1, 16);
-		SH_CLK_SET_RATIO(&clkp_clk_ratio,	1, 32);
-		SH_CLK_SET_RATIO(&clkg_clk_ratio,	1, 24);
-		if (mode & MD(2)) {
-			SH_CLK_SET_RATIO(&clkb_clk_ratio,	1, 32);
-			SH_CLK_SET_RATIO(&clkout_clk_ratio,	1, 32);
-		} else {
-			SH_CLK_SET_RATIO(&clkb_clk_ratio,	1, 24);
-			SH_CLK_SET_RATIO(&clkout_clk_ratio,	1, 24);
-		}
-	}
-
-	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
-		ret = clk_register(main_clks[k]);
-
-	if (!ret)
-		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
-
-	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
-
-	if (!ret)
-		shmobile_clk_init();
-	else
-		panic("failed to setup r8a7779 clocks\n");
-}
-
-/* do nothing for !CONFIG_SMP or !CONFIG_HAVE_TWD */
-void __init __weak r8a7779_register_twd(void) { }
-
-void __init r8a7779_earlytimer_init(void)
-{
-	r8a7779_clock_init();
-	r8a7779_register_twd();
-	shmobile_earlytimer_init();
-}
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
deleted file mode 100644
index 3855fb024fdb..000000000000
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ /dev/null
@@ -1,752 +0,0 @@
-/*
- * sh73a0 clock framework support
- *
- * Copyright (C) 2010 Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/io.h>
-#include <linux/sh_clk.h>
-#include <linux/clkdev.h>
-#include <asm/processor.h>
-#include "clock.h"
-#include "common.h"
-
-#define FRQCRA		IOMEM(0xe6150000)
-#define FRQCRB		IOMEM(0xe6150004)
-#define FRQCRD		IOMEM(0xe61500e4)
-#define VCLKCR1		IOMEM(0xe6150008)
-#define VCLKCR2		IOMEM(0xe615000C)
-#define VCLKCR3		IOMEM(0xe615001C)
-#define ZBCKCR		IOMEM(0xe6150010)
-#define FLCKCR		IOMEM(0xe6150014)
-#define SD0CKCR		IOMEM(0xe6150074)
-#define SD1CKCR		IOMEM(0xe6150078)
-#define SD2CKCR		IOMEM(0xe615007C)
-#define FSIACKCR	IOMEM(0xe6150018)
-#define FSIBCKCR	IOMEM(0xe6150090)
-#define SUBCKCR		IOMEM(0xe6150080)
-#define SPUACKCR	IOMEM(0xe6150084)
-#define SPUVCKCR	IOMEM(0xe6150094)
-#define MSUCKCR		IOMEM(0xe6150088)
-#define HSICKCR		IOMEM(0xe615008C)
-#define MFCK1CR		IOMEM(0xe6150098)
-#define MFCK2CR		IOMEM(0xe615009C)
-#define DSITCKCR	IOMEM(0xe6150060)
-#define DSI0PCKCR	IOMEM(0xe6150064)
-#define DSI1PCKCR	IOMEM(0xe6150068)
-#define DSI0PHYCR	0xe615006C
-#define DSI1PHYCR	0xe6150070
-#define PLLECR		IOMEM(0xe61500d0)
-#define PLL0CR		IOMEM(0xe61500d8)
-#define PLL1CR		IOMEM(0xe6150028)
-#define PLL2CR		IOMEM(0xe615002c)
-#define PLL3CR		IOMEM(0xe61500dc)
-#define SMSTPCR0	IOMEM(0xe6150130)
-#define SMSTPCR1	IOMEM(0xe6150134)
-#define SMSTPCR2	IOMEM(0xe6150138)
-#define SMSTPCR3	IOMEM(0xe615013c)
-#define SMSTPCR4	IOMEM(0xe6150140)
-#define SMSTPCR5	IOMEM(0xe6150144)
-#define CKSCR		IOMEM(0xe61500c0)
-
-/* Fixed 32 KHz root clock from EXTALR pin */
-static struct clk r_clk = {
-	.rate           = 32768,
-};
-
-/*
- * 26MHz default rate for the EXTAL1 root input clock.
- * If needed, reset this with clk_set_rate() from the platform code.
- */
-struct clk sh73a0_extal1_clk = {
-	.rate		= 26000000,
-};
-
-/*
- * 48MHz default rate for the EXTAL2 root input clock.
- * If needed, reset this with clk_set_rate() from the platform code.
- */
-struct clk sh73a0_extal2_clk = {
-	.rate		= 48000000,
-};
-
-static struct sh_clk_ops main_clk_ops = {
-	.recalc		= followparent_recalc,
-};
-
-/* Main clock */
-static struct clk main_clk = {
-	/* .parent wll be set on sh73a0_clock_init() */
-	.ops		= &main_clk_ops,
-};
-
-/* PLL0, PLL1, PLL2, PLL3 */
-static unsigned long pll_recalc(struct clk *clk)
-{
-	unsigned long mult = 1;
-
-	if (__raw_readl(PLLECR) & (1 << clk->enable_bit)) {
-		mult = (((__raw_readl(clk->enable_reg) >> 24) & 0x3f) + 1);
-		/* handle CFG bit for PLL1 and PLL2 */
-		switch (clk->enable_bit) {
-		case 1:
-		case 2:
-			if (__raw_readl(clk->enable_reg) & (1 << 20))
-				mult *= 2;
-		}
-	}
-
-	return clk->parent->rate * mult;
-}
-
-static struct sh_clk_ops pll_clk_ops = {
-	.recalc		= pll_recalc,
-};
-
-static struct clk pll0_clk = {
-	.ops		= &pll_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
-	.parent		= &main_clk,
-	.enable_reg	= (void __iomem *)PLL0CR,
-	.enable_bit	= 0,
-};
-
-static struct clk pll1_clk = {
-	.ops		= &pll_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
-	.parent		= &main_clk,
-	.enable_reg	= (void __iomem *)PLL1CR,
-	.enable_bit	= 1,
-};
-
-static struct clk pll2_clk = {
-	.ops		= &pll_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
-	.parent		= &main_clk,
-	.enable_reg	= (void __iomem *)PLL2CR,
-	.enable_bit	= 2,
-};
-
-static struct clk pll3_clk = {
-	.ops		= &pll_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
-	.parent		= &main_clk,
-	.enable_reg	= (void __iomem *)PLL3CR,
-	.enable_bit	= 3,
-};
-
-/* A fixed divide block */
-SH_CLK_RATIO(div2,  1, 2);
-SH_CLK_RATIO(div7,  1, 7);
-SH_CLK_RATIO(div13, 1, 13);
-
-SH_FIXED_RATIO_CLK(extal1_div2_clk,	sh73a0_extal1_clk,	div2);
-SH_FIXED_RATIO_CLK(extal2_div2_clk,	sh73a0_extal2_clk,	div2);
-SH_FIXED_RATIO_CLK(main_div2_clk,	main_clk,		div2);
-SH_FIXED_RATIO_CLK(pll1_div2_clk,	pll1_clk,		div2);
-SH_FIXED_RATIO_CLK(pll1_div7_clk,	pll1_clk,		div7);
-SH_FIXED_RATIO_CLK(pll1_div13_clk,	pll1_clk,		div13);
-
-/* External input clock */
-struct clk sh73a0_extcki_clk = {
-};
-
-struct clk sh73a0_extalr_clk = {
-};
-
-static struct clk *main_clks[] = {
-	&r_clk,
-	&sh73a0_extal1_clk,
-	&sh73a0_extal2_clk,
-	&extal1_div2_clk,
-	&extal2_div2_clk,
-	&main_clk,
-	&main_div2_clk,
-	&pll0_clk,
-	&pll1_clk,
-	&pll2_clk,
-	&pll3_clk,
-	&pll1_div2_clk,
-	&pll1_div7_clk,
-	&pll1_div13_clk,
-	&sh73a0_extcki_clk,
-	&sh73a0_extalr_clk,
-};
-
-static int frqcr_kick(void)
-{
-	int i;
-
-	/* set KICK bit in FRQCRB to update hardware setting, check success */
-	__raw_writel(__raw_readl(FRQCRB) | (1 << 31), FRQCRB);
-	for (i = 1000; i; i--)
-		if (__raw_readl(FRQCRB) & (1 << 31))
-			cpu_relax();
-		else
-			return i;
-
-	return -ETIMEDOUT;
-}
-
-static void div4_kick(struct clk *clk)
-{
-	frqcr_kick();
-}
-
-static int divisors[] = { 2, 3, 4, 6, 8, 12, 16, 18,
-			  24, 0, 36, 48, 7 };
-
-static struct clk_div_mult_table div4_div_mult_table = {
-	.divisors = divisors,
-	.nr_divisors = ARRAY_SIZE(divisors),
-};
-
-static struct clk_div4_table div4_table = {
-	.div_mult_table = &div4_div_mult_table,
-	.kick = div4_kick,
-};
-
-enum { DIV4_I, DIV4_ZG, DIV4_M3, DIV4_B, DIV4_M1, DIV4_M2,
-	DIV4_Z, DIV4_ZX, DIV4_HP, DIV4_NR };
-
-#define DIV4(_reg, _bit, _mask, _flags) \
-	SH_CLK_DIV4(&pll1_clk, _reg, _bit, _mask, _flags)
-
-static struct clk div4_clks[DIV4_NR] = {
-	[DIV4_I] = DIV4(FRQCRA, 20, 0xdff, CLK_ENABLE_ON_INIT),
-	/*
-	 * ZG clock is dividing PLL0 frequency to supply SGX. Make sure not to
-	 * exceed maximum frequencies of 201.5MHz for VDD_DVFS=1.175 and
-	 * 239.2MHz for VDD_DVFS=1.315V.
-	 */
-	[DIV4_ZG] = SH_CLK_DIV4(&pll0_clk, FRQCRA, 16, 0xd7f, CLK_ENABLE_ON_INIT),
-	[DIV4_M3] = DIV4(FRQCRA, 12, 0x1dff, CLK_ENABLE_ON_INIT),
-	[DIV4_B] = DIV4(FRQCRA, 8, 0xdff, CLK_ENABLE_ON_INIT),
-	[DIV4_M1] = DIV4(FRQCRA, 4, 0x1dff, 0),
-	[DIV4_M2] = DIV4(FRQCRA, 0, 0x1dff, 0),
-	[DIV4_Z] = SH_CLK_DIV4(&pll0_clk, FRQCRB, 24, 0x97f, 0),
-	[DIV4_ZX] = DIV4(FRQCRB, 12, 0xdff, 0),
-	[DIV4_HP] = DIV4(FRQCRB, 4, 0xdff, 0),
-};
-
-static unsigned long twd_recalc(struct clk *clk)
-{
-	return clk_get_rate(clk->parent) / 4;
-}
-
-static struct sh_clk_ops twd_clk_ops = {
-	.recalc = twd_recalc,
-};
-
-static struct clk twd_clk = {
-	.parent = &div4_clks[DIV4_Z],
-	.ops = &twd_clk_ops,
-};
-
-static struct sh_clk_ops zclk_ops, kicker_ops;
-static const struct sh_clk_ops *div4_clk_ops;
-
-static int zclk_set_rate(struct clk *clk, unsigned long rate)
-{
-	int ret;
-
-	if (!clk->parent || !__clk_get(clk->parent))
-		return -ENODEV;
-
-	if (readl(FRQCRB) & (1 << 31))
-		return -EBUSY;
-
-	if (rate == clk_get_rate(clk->parent)) {
-		/* 1:1 - switch off divider */
-		__raw_writel(__raw_readl(FRQCRB) & ~(1 << 28), FRQCRB);
-		/* nullify the divider to prepare for the next time */
-		ret = div4_clk_ops->set_rate(clk, rate / 2);
-		if (!ret)
-			ret = frqcr_kick();
-		if (ret > 0)
-			ret = 0;
-	} else {
-		/* Enable the divider */
-		__raw_writel(__raw_readl(FRQCRB) | (1 << 28), FRQCRB);
-
-		ret = frqcr_kick();
-		if (ret >= 0)
-			/*
-			 * set the divider - call the DIV4 method, it will kick
-			 * FRQCRB too
-			 */
-			ret = div4_clk_ops->set_rate(clk, rate);
-		if (ret < 0)
-			goto esetrate;
-	}
-
-esetrate:
-	__clk_put(clk->parent);
-	return ret;
-}
-
-static long zclk_round_rate(struct clk *clk, unsigned long rate)
-{
-	unsigned long div_freq = div4_clk_ops->round_rate(clk, rate),
-		parent_freq = clk_get_rate(clk->parent);
-
-	if (rate > div_freq && abs(parent_freq - rate) < rate - div_freq)
-		return parent_freq;
-
-	return div_freq;
-}
-
-static unsigned long zclk_recalc(struct clk *clk)
-{
-	/*
-	 * Must recalculate frequencies in case PLL0 has been changed, even if
-	 * the divisor is unused ATM!
-	 */
-	unsigned long div_freq = div4_clk_ops->recalc(clk);
-
-	if (__raw_readl(FRQCRB) & (1 << 28))
-		return div_freq;
-
-	return clk_get_rate(clk->parent);
-}
-
-static int kicker_set_rate(struct clk *clk, unsigned long rate)
-{
-	if (__raw_readl(FRQCRB) & (1 << 31))
-		return -EBUSY;
-
-	return div4_clk_ops->set_rate(clk, rate);
-}
-
-static void div4_clk_extend(void)
-{
-	int i;
-
-	div4_clk_ops = div4_clks[0].ops;
-
-	/* Add a kicker-busy check before changing the rate */
-	kicker_ops = *div4_clk_ops;
-	/* We extend the DIV4 clock with a 1:1 pass-through case */
-	zclk_ops = *div4_clk_ops;
-
-	kicker_ops.set_rate = kicker_set_rate;
-	zclk_ops.set_rate = zclk_set_rate;
-	zclk_ops.round_rate = zclk_round_rate;
-	zclk_ops.recalc = zclk_recalc;
-
-	for (i = 0; i < DIV4_NR; i++)
-		div4_clks[i].ops = i == DIV4_Z ? &zclk_ops : &kicker_ops;
-}
-
-enum { DIV6_VCK1, DIV6_VCK2, DIV6_VCK3, DIV6_ZB1,
-	DIV6_FLCTL, DIV6_SDHI0, DIV6_SDHI1, DIV6_SDHI2,
-	DIV6_FSIA, DIV6_FSIB, DIV6_SUB,
-	DIV6_SPUA, DIV6_SPUV, DIV6_MSU,
-	DIV6_HSI,  DIV6_MFG1, DIV6_MFG2,
-	DIV6_DSIT, DIV6_DSI0P, DIV6_DSI1P,
-	DIV6_NR };
-
-static struct clk *vck_parent[8] = {
-	[0] = &pll1_div2_clk,
-	[1] = &pll2_clk,
-	[2] = &sh73a0_extcki_clk,
-	[3] = &sh73a0_extal2_clk,
-	[4] = &main_div2_clk,
-	[5] = &sh73a0_extalr_clk,
-	[6] = &main_clk,
-};
-
-static struct clk *pll_parent[4] = {
-	[0] = &pll1_div2_clk,
-	[1] = &pll2_clk,
-	[2] = &pll1_div13_clk,
-};
-
-static struct clk *hsi_parent[4] = {
-	[0] = &pll1_div2_clk,
-	[1] = &pll2_clk,
-	[2] = &pll1_div7_clk,
-};
-
-static struct clk *pll_extal2_parent[] = {
-	[0] = &pll1_div2_clk,
-	[1] = &pll2_clk,
-	[2] = &sh73a0_extal2_clk,
-	[3] = &sh73a0_extal2_clk,
-};
-
-static struct clk *dsi_parent[8] = {
-	[0] = &pll1_div2_clk,
-	[1] = &pll2_clk,
-	[2] = &main_clk,
-	[3] = &sh73a0_extal2_clk,
-	[4] = &sh73a0_extcki_clk,
-};
-
-static struct clk div6_clks[DIV6_NR] = {
-	[DIV6_VCK1] = SH_CLK_DIV6_EXT(VCLKCR1, 0,
-			vck_parent, ARRAY_SIZE(vck_parent), 12, 3),
-	[DIV6_VCK2] = SH_CLK_DIV6_EXT(VCLKCR2, 0,
-			vck_parent, ARRAY_SIZE(vck_parent), 12, 3),
-	[DIV6_VCK3] = SH_CLK_DIV6_EXT(VCLKCR3, 0,
-			vck_parent, ARRAY_SIZE(vck_parent), 12, 3),
-	[DIV6_ZB1] = SH_CLK_DIV6_EXT(ZBCKCR, CLK_ENABLE_ON_INIT,
-			pll_parent, ARRAY_SIZE(pll_parent), 7, 1),
-	[DIV6_FLCTL] = SH_CLK_DIV6_EXT(FLCKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 7, 1),
-	[DIV6_SDHI0] = SH_CLK_DIV6_EXT(SD0CKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 6, 2),
-	[DIV6_SDHI1] = SH_CLK_DIV6_EXT(SD1CKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 6, 2),
-	[DIV6_SDHI2] = SH_CLK_DIV6_EXT(SD2CKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 6, 2),
-	[DIV6_FSIA] = SH_CLK_DIV6_EXT(FSIACKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 6, 1),
-	[DIV6_FSIB] = SH_CLK_DIV6_EXT(FSIBCKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 6, 1),
-	[DIV6_SUB] = SH_CLK_DIV6_EXT(SUBCKCR, 0,
-			pll_extal2_parent, ARRAY_SIZE(pll_extal2_parent), 6, 2),
-	[DIV6_SPUA] = SH_CLK_DIV6_EXT(SPUACKCR, 0,
-			pll_extal2_parent, ARRAY_SIZE(pll_extal2_parent), 6, 2),
-	[DIV6_SPUV] = SH_CLK_DIV6_EXT(SPUVCKCR, 0,
-			pll_extal2_parent, ARRAY_SIZE(pll_extal2_parent), 6, 2),
-	[DIV6_MSU] = SH_CLK_DIV6_EXT(MSUCKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 7, 1),
-	[DIV6_HSI] = SH_CLK_DIV6_EXT(HSICKCR, 0,
-			hsi_parent, ARRAY_SIZE(hsi_parent), 6, 2),
-	[DIV6_MFG1] = SH_CLK_DIV6_EXT(MFCK1CR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 7, 1),
-	[DIV6_MFG2] = SH_CLK_DIV6_EXT(MFCK2CR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 7, 1),
-	[DIV6_DSIT] = SH_CLK_DIV6_EXT(DSITCKCR, 0,
-			pll_parent, ARRAY_SIZE(pll_parent), 7, 1),
-	[DIV6_DSI0P] = SH_CLK_DIV6_EXT(DSI0PCKCR, 0,
-			dsi_parent, ARRAY_SIZE(dsi_parent), 12, 3),
-	[DIV6_DSI1P] = SH_CLK_DIV6_EXT(DSI1PCKCR, 0,
-			dsi_parent, ARRAY_SIZE(dsi_parent), 12, 3),
-};
-
-/* DSI DIV */
-static unsigned long dsiphy_recalc(struct clk *clk)
-{
-	u32 value;
-
-	value = __raw_readl(clk->mapping->base);
-
-	/* FIXME */
-	if (!(value & 0x000B8000))
-		return clk->parent->rate;
-
-	value &= 0x3f;
-	value += 1;
-
-	if ((value < 12) ||
-	    (value > 33)) {
-		pr_err("DSIPHY has wrong value (%d)", value);
-		return 0;
-	}
-
-	return clk->parent->rate / value;
-}
-
-static long dsiphy_round_rate(struct clk *clk, unsigned long rate)
-{
-	return clk_rate_mult_range_round(clk, 12, 33, rate);
-}
-
-static void dsiphy_disable(struct clk *clk)
-{
-	u32 value;
-
-	value = __raw_readl(clk->mapping->base);
-	value &= ~0x000B8000;
-
-	__raw_writel(value , clk->mapping->base);
-}
-
-static int dsiphy_enable(struct clk *clk)
-{
-	u32 value;
-	int multi;
-
-	value = __raw_readl(clk->mapping->base);
-	multi = (value & 0x3f) + 1;
-
-	if ((multi < 12) || (multi > 33))
-		return -EIO;
-
-	__raw_writel(value | 0x000B8000, clk->mapping->base);
-
-	return 0;
-}
-
-static int dsiphy_set_rate(struct clk *clk, unsigned long rate)
-{
-	u32 value;
-	int idx;
-
-	idx = rate / clk->parent->rate;
-	if ((idx < 12) || (idx > 33))
-		return -EINVAL;
-
-	idx += -1;
-
-	value = __raw_readl(clk->mapping->base);
-	value = (value & ~0x3f) + idx;
-
-	__raw_writel(value, clk->mapping->base);
-
-	return 0;
-}
-
-static struct sh_clk_ops dsiphy_clk_ops = {
-	.recalc		= dsiphy_recalc,
-	.round_rate	= dsiphy_round_rate,
-	.set_rate	= dsiphy_set_rate,
-	.enable		= dsiphy_enable,
-	.disable	= dsiphy_disable,
-};
-
-static struct clk_mapping dsi0phy_clk_mapping = {
-	.phys	= DSI0PHYCR,
-	.len	= 4,
-};
-
-static struct clk_mapping dsi1phy_clk_mapping = {
-	.phys	= DSI1PHYCR,
-	.len	= 4,
-};
-
-static struct clk dsi0phy_clk = {
-	.ops		= &dsiphy_clk_ops,
-	.parent		= &div6_clks[DIV6_DSI0P], /* late install */
-	.mapping	= &dsi0phy_clk_mapping,
-};
-
-static struct clk dsi1phy_clk = {
-	.ops		= &dsiphy_clk_ops,
-	.parent		= &div6_clks[DIV6_DSI1P], /* late install */
-	.mapping	= &dsi1phy_clk_mapping,
-};
-
-static struct clk *late_main_clks[] = {
-	&dsi0phy_clk,
-	&dsi1phy_clk,
-	&twd_clk,
-};
-
-enum { MSTP001,
-	MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP112, MSTP100,
-	MSTP219, MSTP218, MSTP217,
-	MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-	MSTP331, MSTP329, MSTP328, MSTP325, MSTP323, MSTP322,
-	MSTP314, MSTP313, MSTP312, MSTP311,
-	MSTP304, MSTP303, MSTP302, MSTP301, MSTP300,
-	MSTP411, MSTP410, MSTP403,
-	MSTP508,
-	MSTP_NR };
-
-#define MSTP(_parent, _reg, _bit, _flags) \
-	SH_CLK_MSTP32(_parent, _reg, _bit, _flags)
-
-static struct clk mstp_clks[MSTP_NR] = {
-	[MSTP001] = MSTP(&div4_clks[DIV4_HP], SMSTPCR0, 1, 0), /* IIC2 */
-	[MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* CEU1 */
-	[MSTP128] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 28, 0), /* CSI2-RX1 */
-	[MSTP127] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 27, 0), /* CEU0 */
-	[MSTP126] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 26, 0), /* CSI2-RX0 */
-	[MSTP125] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 25, 0), /* TMU0 */
-	[MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX0 */
-	[MSTP116] = MSTP(&div4_clks[DIV4_HP], SMSTPCR1, 16, 0), /* IIC0 */
-	[MSTP112] = MSTP(&div4_clks[DIV4_ZG], SMSTPCR1, 12, 0), /* SGX */
-	[MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
-	[MSTP219] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 19, 0), /* SCIFA7 */
-	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* SY-DMAC */
-	[MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* MP-DMAC */
-	[MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
-	[MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
-	[MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
-	[MSTP203] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 3, 0), /* SCIFA1 */
-	[MSTP202] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 2, 0), /* SCIFA2 */
-	[MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */
-	[MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */
-	[MSTP331] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 31, 0), /* SCIFA6 */
-	[MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
-	[MSTP328] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 28, 0), /*FSI*/
-	[MSTP325] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 25, 0), /* IrDA */
-	[MSTP323] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 23, 0), /* IIC1 */
-	[MSTP322] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 22, 0), /* USB */
-	[MSTP314] = MSTP(&div6_clks[DIV6_SDHI0], SMSTPCR3, 14, 0), /* SDHI0 */
-	[MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */
-	[MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */
-	[MSTP311] = MSTP(&div6_clks[DIV6_SDHI2], SMSTPCR3, 11, 0), /* SDHI2 */
-	[MSTP304] = MSTP(&main_div2_clk, SMSTPCR3, 4, 0), /* TPU0 */
-	[MSTP303] = MSTP(&main_div2_clk, SMSTPCR3, 3, 0), /* TPU1 */
-	[MSTP302] = MSTP(&main_div2_clk, SMSTPCR3, 2, 0), /* TPU2 */
-	[MSTP301] = MSTP(&main_div2_clk, SMSTPCR3, 1, 0), /* TPU3 */
-	[MSTP300] = MSTP(&main_div2_clk, SMSTPCR3, 0, 0), /* TPU4 */
-	[MSTP411] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 11, 0), /* IIC3 */
-	[MSTP410] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 10, 0), /* IIC4 */
-	[MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */
-	[MSTP508] = MSTP(&div4_clks[DIV4_HP], SMSTPCR5, 8, 0), /* INTCA0 */
-};
-
-/* The lookups structure below includes duplicate entries for some clocks
- * with alternate names.
- * - The traditional name used when a device is initialised with platform data
- * - The name used when a device is initialised using device tree
- * The longer-term aim is to remove these duplicates, and indeed the
- * lookups table entirely, by describing clocks using device tree.
- */
-static struct clk_lookup lookups[] = {
-	/* main clocks */
-	CLKDEV_CON_ID("r_clk", &r_clk),
-	CLKDEV_DEV_ID("smp_twd", &twd_clk), /* smp_twd */
-
-	/* DIV4 clocks */
-	CLKDEV_DEV_ID("cpu0", &div4_clks[DIV4_Z]),
-
-	/* DIV6 clocks */
-	CLKDEV_CON_ID("vck1_clk", &div6_clks[DIV6_VCK1]),
-	CLKDEV_CON_ID("vck2_clk", &div6_clks[DIV6_VCK2]),
-	CLKDEV_CON_ID("vck3_clk", &div6_clks[DIV6_VCK3]),
-	CLKDEV_CON_ID("sdhi0_clk", &div6_clks[DIV6_SDHI0]),
-	CLKDEV_CON_ID("sdhi1_clk", &div6_clks[DIV6_SDHI1]),
-	CLKDEV_CON_ID("sdhi2_clk", &div6_clks[DIV6_SDHI2]),
-
-	/* MSTP32 clocks */
-	CLKDEV_DEV_ID("i2c-sh_mobile.2", &mstp_clks[MSTP001]), /* I2C2 */
-	CLKDEV_DEV_ID("e6824000.i2c", &mstp_clks[MSTP001]), /* I2C2 */
-	CLKDEV_DEV_ID("sh_mobile_ceu.1", &mstp_clks[MSTP129]), /* CEU1 */
-	CLKDEV_DEV_ID("sh-mobile-csi2.1", &mstp_clks[MSTP128]), /* CSI2-RX1 */
-	CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[MSTP127]), /* CEU0 */
-	CLKDEV_DEV_ID("sh-mobile-csi2.0", &mstp_clks[MSTP126]), /* CSI2-RX0 */
-	CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX */
-	CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* I2C0 */
-	CLKDEV_DEV_ID("e6820000.i2c", &mstp_clks[MSTP116]), /* I2C0 */
-	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
-	CLKDEV_DEV_ID("sh-sci.7", &mstp_clks[MSTP219]), /* SCIFA7 */
-	CLKDEV_DEV_ID("e6cd0000.serial", &mstp_clks[MSTP219]), /* SCIFA7 */
-	CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* SY-DMAC */
-	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* MP-DMAC */
-	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
-	CLKDEV_DEV_ID("e6cb0000.serial", &mstp_clks[MSTP207]), /* SCIFA5 */
-	CLKDEV_DEV_ID("sh-sci.8", &mstp_clks[MSTP206]), /* SCIFB */
-	CLKDEV_DEV_ID("e6c3000.serial", &mstp_clks[MSTP206]), /* SCIFB */
-	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
-	CLKDEV_DEV_ID("e6c40000.serial", &mstp_clks[MSTP204]), /* SCIFA0 */
-	CLKDEV_DEV_ID("sh-sci.1", &mstp_clks[MSTP203]), /* SCIFA1 */
-	CLKDEV_DEV_ID("e6c50000.serial", &mstp_clks[MSTP203]), /* SCIFA1 */
-	CLKDEV_DEV_ID("sh-sci.2", &mstp_clks[MSTP202]), /* SCIFA2 */
-	CLKDEV_DEV_ID("e6c60000.serial", &mstp_clks[MSTP202]), /* SCIFA2 */
-	CLKDEV_DEV_ID("sh-sci.3", &mstp_clks[MSTP201]), /* SCIFA3 */
-	CLKDEV_DEV_ID("e6c70000.serial", &mstp_clks[MSTP201]), /* SCIFA3 */
-	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP200]), /* SCIFA4 */
-	CLKDEV_DEV_ID("e6c80000.serial", &mstp_clks[MSTP200]), /* SCIFA4 */
-	CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP331]), /* SCIFA6 */
-	CLKDEV_DEV_ID("e6cc0000.serial", &mstp_clks[MSTP331]), /* SCIFA6 */
-	CLKDEV_DEV_ID("sh_fsi2", &mstp_clks[MSTP328]), /* FSI */
-	CLKDEV_DEV_ID("ec230000.sound", &mstp_clks[MSTP328]), /* FSI */
-	CLKDEV_DEV_ID("sh_irda.0", &mstp_clks[MSTP325]), /* IrDA */
-	CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* I2C1 */
-	CLKDEV_DEV_ID("e6822000.i2c", &mstp_clks[MSTP323]), /* I2C1 */
-	CLKDEV_DEV_ID("renesas_usbhs", &mstp_clks[MSTP322]), /* USB */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */
-	CLKDEV_DEV_ID("ee100000.sd", &mstp_clks[MSTP314]), /* SDHI0 */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
-	CLKDEV_DEV_ID("ee120000.sd", &mstp_clks[MSTP313]), /* SDHI1 */
-	CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */
-	CLKDEV_DEV_ID("e6bd0000.mmc", &mstp_clks[MSTP312]), /* MMCIF0 */
-	CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP311]), /* SDHI2 */
-	CLKDEV_DEV_ID("ee140000.sd", &mstp_clks[MSTP311]), /* SDHI2 */
-	CLKDEV_DEV_ID("renesas-tpu-pwm.0", &mstp_clks[MSTP304]), /* TPU0 */
-	CLKDEV_DEV_ID("renesas-tpu-pwm.1", &mstp_clks[MSTP303]), /* TPU1 */
-	CLKDEV_DEV_ID("renesas-tpu-pwm.2", &mstp_clks[MSTP302]), /* TPU2 */
-	CLKDEV_DEV_ID("renesas-tpu-pwm.3", &mstp_clks[MSTP301]), /* TPU3 */
-	CLKDEV_DEV_ID("renesas-tpu-pwm.4", &mstp_clks[MSTP300]), /* TPU4 */
-	CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* I2C3 */
-	CLKDEV_DEV_ID("e6826000.i2c", &mstp_clks[MSTP411]), /* I2C3 */
-	CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* I2C4 */
-	CLKDEV_DEV_ID("e6828000.i2c", &mstp_clks[MSTP410]), /* I2C4 */
-	CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
-	CLKDEV_DEV_ID("renesas_intc_irqpin.0",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("e6900000.irqpin",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("renesas_intc_irqpin.1",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("e6900004.irqpin",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("renesas_intc_irqpin.2",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("e6900008.irqpin",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("renesas_intc_irqpin.3",	&mstp_clks[MSTP508]), /* INTCA0 */
-	CLKDEV_DEV_ID("e690000c.irqpin",	&mstp_clks[MSTP508]), /* INTCA0 */
-
-	/* ICK */
-	CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSIT]),
-	CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.1", &div6_clks[DIV6_DSIT]),
-	CLKDEV_ICK_ID("dsip_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSI0P]),
-	CLKDEV_ICK_ID("dsip_clk", "sh-mipi-dsi.1", &div6_clks[DIV6_DSI1P]),
-	CLKDEV_ICK_ID("dsiphy_clk", "sh-mipi-dsi.0", &dsi0phy_clk),
-	CLKDEV_ICK_ID("dsiphy_clk", "sh-mipi-dsi.1", &dsi1phy_clk),
-	CLKDEV_ICK_ID("fck", "sh-cmt-48.1", &mstp_clks[MSTP329]), /* CMT1 */
-	CLKDEV_ICK_ID("fck", "e6138000.timer", &mstp_clks[MSTP329]), /* CMT1 */
-	CLKDEV_ICK_ID("fck", "sh-tmu.0", &mstp_clks[MSTP125]), /* TMU0 */
-};
-
-void __init sh73a0_clock_init(void)
-{
-	int k, ret = 0;
-
-	/* Set SDHI clocks to a known state */
-	__raw_writel(0x108, SD0CKCR);
-	__raw_writel(0x108, SD1CKCR);
-	__raw_writel(0x108, SD2CKCR);
-
-	/* detect main clock parent */
-	switch ((__raw_readl(CKSCR) >> 28) & 0x03) {
-	case 0:
-		main_clk.parent = &sh73a0_extal1_clk;
-		break;
-	case 1:
-		main_clk.parent = &extal1_div2_clk;
-		break;
-	case 2:
-		main_clk.parent = &sh73a0_extal2_clk;
-		break;
-	case 3:
-		main_clk.parent = &extal2_div2_clk;
-		break;
-	}
-
-	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
-		ret = clk_register(main_clks[k]);
-
-	if (!ret) {
-		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
-		if (!ret)
-			div4_clk_extend();
-	}
-
-	if (!ret)
-		ret = sh_clk_div6_reparent_register(div6_clks, DIV6_NR);
-
-	if (!ret)
-		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
-
-	for (k = 0; !ret && (k < ARRAY_SIZE(late_main_clks)); k++)
-		ret = clk_register(late_main_clks[k]);
-
-	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
-
-	if (!ret)
-		shmobile_clk_init();
-	else
-		panic("failed to setup sh73a0 clocks\n");
-}
diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h
index 476092b86c6e..8d27ec546a35 100644
--- a/arch/arm/mach-shmobile/common.h
+++ b/arch/arm/mach-shmobile/common.h
@@ -13,7 +13,7 @@ extern void shmobile_smp_boot(void);
 extern void shmobile_smp_sleep(void);
 extern void shmobile_smp_hook(unsigned int cpu, unsigned long fn,
 			      unsigned long arg);
-extern int shmobile_smp_cpu_disable(unsigned int cpu);
+extern bool shmobile_smp_cpu_can_disable(unsigned int cpu);
 extern void shmobile_boot_scu(void);
 extern void shmobile_smp_scu_prepare_cpus(unsigned int max_cpus);
 extern void shmobile_smp_scu_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-shmobile/dma-register.h b/arch/arm/mach-shmobile/dma-register.h
deleted file mode 100644
index 52a2f66e600f..000000000000
--- a/arch/arm/mach-shmobile/dma-register.h
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * SH-ARM CPU-specific DMA definitions, used by both DMA drivers
- *
- * Copyright (C) 2012 Renesas Solutions Corp
- *
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on arch/sh/include/cpu-sh4/cpu/dma-register.h
- * Copyright (C) 2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef DMA_REGISTER_H
-#define DMA_REGISTER_H
-
-/*
- *		Direct Memory Access Controller
- */
-
-/* Transmit sizes and respective CHCR register values */
-enum {
-	XMIT_SZ_8BIT		= 0,
-	XMIT_SZ_16BIT		= 1,
-	XMIT_SZ_32BIT		= 2,
-	XMIT_SZ_64BIT		= 7,
-	XMIT_SZ_128BIT		= 3,
-	XMIT_SZ_256BIT		= 4,
-	XMIT_SZ_512BIT		= 5,
-};
-
-/* log2(size / 8) - used to calculate number of transfers */
-static const unsigned int dma_ts_shift[] = {
-	[XMIT_SZ_8BIT]		= 0,
-	[XMIT_SZ_16BIT]		= 1,
-	[XMIT_SZ_32BIT]		= 2,
-	[XMIT_SZ_64BIT]		= 3,
-	[XMIT_SZ_128BIT]	= 4,
-	[XMIT_SZ_256BIT]	= 5,
-	[XMIT_SZ_512BIT]	= 6,
-};
-
-#define TS_LOW_BIT	0x3 /* --xx */
-#define TS_HI_BIT	0xc /* xx-- */
-
-#define TS_LOW_SHIFT	(3)
-#define TS_HI_SHIFT	(20 - 2)	/* 2 bits for shifted low TS */
-
-#define TS_INDEX2VAL(i) \
-	((((i) & TS_LOW_BIT) << TS_LOW_SHIFT) |\
-	 (((i) & TS_HI_BIT)  << TS_HI_SHIFT))
-
-#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | RS_ERS | TS_INDEX2VAL((xmit_sz)))
-#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | RS_ERS | TS_INDEX2VAL((xmit_sz)))
-
-
-/*
- *		USB High-Speed DMAC
- */
-/* Transmit sizes and respective CHCR register values */
-enum {
-	USBTS_XMIT_SZ_8BYTE		= 0,
-	USBTS_XMIT_SZ_16BYTE		= 1,
-	USBTS_XMIT_SZ_32BYTE		= 2,
-};
-
-/* log2(size / 8) - used to calculate number of transfers */
-static const unsigned int dma_usbts_shift[] = {
-	[USBTS_XMIT_SZ_8BYTE]	= 3,
-	[USBTS_XMIT_SZ_16BYTE]	= 4,
-	[USBTS_XMIT_SZ_32BYTE]	= 5,
-};
-
-#define USBTS_LOW_BIT	0x3 /* --xx */
-#define USBTS_HI_BIT	0x0 /* ---- */
-
-#define USBTS_LOW_SHIFT	6
-#define USBTS_HI_SHIFT	0
-
-#define USBTS_INDEX2VAL(i) (((i) & 3) << 6)
-
-#endif /* DMA_REGISTER_H */
diff --git a/arch/arm/mach-shmobile/include/mach/head-kzm9g.txt b/arch/arm/mach-shmobile/include/mach/head-kzm9g.txt
deleted file mode 100644
index 9531f46a822a..000000000000
--- a/arch/arm/mach-shmobile/include/mach/head-kzm9g.txt
+++ /dev/null
@@ -1,410 +0,0 @@
-LIST "KZM9G low-level initialization routine."
-LIST "Adapted from u-boot KZM9G support code."
-
-LIST "Copyright (C) 2013 Ulrich Hecht"
-
-LIST "This program is free software; you can redistribute it and/or modify"
-LIST "it under the terms of the GNU General Public License version 2 as"
-LIST "published by the Free Software Foundation."
-
-LIST "This program is distributed in the hope that it will be useful,"
-LIST "but WITHOUT ANY WARRANTY; without even the implied warranty of"
-LIST "MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the"
-LIST "GNU General Public License for more details."
-
-
-LIST "Register definitions:"
-
-LIST "Secure control register"
-#define LIFEC_SEC_SRC (0xE6110008)
-
-LIST "RWDT"
-#define RWDT_BASE   (0xE6020000)
-#define RWTCSRA0 (RWDT_BASE + 0x04)
-
-LIST "HPB Semaphore Control Registers"
-#define HPBSCR_BASE (0xE6000000)
-#define HPBCTRL6 (HPBSCR_BASE + 0x1030)
-
-#define SBSC1_BASE  (0xFE400000)
-#define SDCR0A		(SBSC1_BASE + 0x0008)
-#define SDCR1A		(SBSC1_BASE + 0x000C)
-#define SDPCRA		(SBSC1_BASE + 0x0010)
-#define SDCR0SA		(SBSC1_BASE + 0x0018)
-#define SDCR1SA		(SBSC1_BASE + 0x001C)
-#define RTCSRA		(SBSC1_BASE + 0x0020)
-#define RTCORA		(SBSC1_BASE + 0x0028)
-#define RTCORHA		(SBSC1_BASE + 0x002C)
-#define SDWCRC0A	(SBSC1_BASE + 0x0040)
-#define SDWCRC1A	(SBSC1_BASE + 0x0044)
-#define SDWCR00A	(SBSC1_BASE + 0x0048)
-#define SDWCR01A	(SBSC1_BASE + 0x004C)
-#define SDWCR10A	(SBSC1_BASE + 0x0050)
-#define SDWCR11A	(SBSC1_BASE + 0x0054)
-#define SDWCR2A		(SBSC1_BASE + 0x0060)
-#define SDWCRC2A	(SBSC1_BASE + 0x0064)
-#define ZQCCRA		(SBSC1_BASE + 0x0068)
-#define SDMRACR0A	(SBSC1_BASE + 0x0084)
-#define SDMRTMPCRA	(SBSC1_BASE + 0x008C)
-#define SDMRTMPMSKA	(SBSC1_BASE + 0x0094)
-#define SDGENCNTA	(SBSC1_BASE + 0x009C)
-#define SDDRVCR0A	(SBSC1_BASE + 0x00B4)
-#define DLLCNT0A	(SBSC1_BASE + 0x0354)
-
-#define SDMRA1  (0xFE500000)
-#define SDMRA2  (0xFE5C0000)
-#define SDMRA3  (0xFE504000)
-
-#define SBSC2_BASE  (0xFB400000)
-#define SDCR0B		(SBSC2_BASE + 0x0008)
-#define SDCR1B		(SBSC2_BASE + 0x000C)
-#define SDPCRB		(SBSC2_BASE + 0x0010)
-#define SDCR0SB		(SBSC2_BASE + 0x0018)
-#define SDCR1SB		(SBSC2_BASE + 0x001C)
-#define RTCSRB		(SBSC2_BASE + 0x0020)
-#define RTCORB		(SBSC2_BASE + 0x0028)
-#define RTCORHB		(SBSC2_BASE + 0x002C)
-#define SDWCRC0B	(SBSC2_BASE + 0x0040)
-#define SDWCRC1B	(SBSC2_BASE + 0x0044)
-#define SDWCR00B	(SBSC2_BASE + 0x0048)
-#define SDWCR01B	(SBSC2_BASE + 0x004C)
-#define SDWCR10B	(SBSC2_BASE + 0x0050)
-#define SDWCR11B	(SBSC2_BASE + 0x0054)
-#define SDPDCR0B	(SBSC2_BASE + 0x0058)
-#define SDWCR2B		(SBSC2_BASE + 0x0060)
-#define SDWCRC2B	(SBSC2_BASE + 0x0064)
-#define ZQCCRB		(SBSC2_BASE + 0x0068)
-#define SDMRACR0B	(SBSC2_BASE + 0x0084)
-#define SDMRTMPCRB	(SBSC2_BASE + 0x008C)
-#define SDMRTMPMSKB	(SBSC2_BASE + 0x0094)
-#define SDGENCNTB	(SBSC2_BASE + 0x009C)
-#define DPHYCNT0B	(SBSC2_BASE + 0x00A0)
-#define DPHYCNT1B	(SBSC2_BASE + 0x00A4)
-#define DPHYCNT2B	(SBSC2_BASE + 0x00A8)
-#define SDDRVCR0B	(SBSC2_BASE + 0x00B4)
-#define DLLCNT0B	(SBSC2_BASE + 0x0354)
-
-#define SDMRB1  (0xFB500000)
-#define SDMRB2  (0xFB5C0000)
-#define SDMRB3  (0xFB504000)
-
-#define CPG_BASE   (0xE6150000)
-#define FRQCRA		(CPG_BASE + 0x0000)
-#define FRQCRB		(CPG_BASE + 0x0004)
-#define FRQCRD		(CPG_BASE + 0x00E4)
-#define VCLKCR1		(CPG_BASE + 0x0008)
-#define VCLKCR2		(CPG_BASE + 0x000C)
-#define VCLKCR3		(CPG_BASE + 0x001C)
-#define ZBCKCR		(CPG_BASE + 0x0010)
-#define FLCKCR		(CPG_BASE + 0x0014)
-#define SD0CKCR		(CPG_BASE + 0x0074)
-#define SD1CKCR		(CPG_BASE + 0x0078)
-#define SD2CKCR		(CPG_BASE + 0x007C)
-#define FSIACKCR	(CPG_BASE + 0x0018)
-#define SUBCKCR		(CPG_BASE + 0x0080)
-#define SPUACKCR	(CPG_BASE + 0x0084)
-#define SPUVCKCR	(CPG_BASE + 0x0094)
-#define MSUCKCR		(CPG_BASE + 0x0088)
-#define HSICKCR		(CPG_BASE + 0x008C)
-#define FSIBCKCR	(CPG_BASE + 0x0090)
-#define MFCK1CR		(CPG_BASE + 0x0098)
-#define MFCK2CR		(CPG_BASE + 0x009C)
-#define DSITCKCR	(CPG_BASE + 0x0060)
-#define DSI0PCKCR	(CPG_BASE + 0x0064)
-#define DSI1PCKCR	(CPG_BASE + 0x0068)
-#define DSI0PHYCR	(CPG_BASE + 0x006C)
-#define DVFSCR3		(CPG_BASE + 0x0174)
-#define DVFSCR4		(CPG_BASE + 0x0178)
-#define DVFSCR5		(CPG_BASE + 0x017C)
-#define MPMODE		(CPG_BASE + 0x00CC)
-
-#define PLLECR		(CPG_BASE + 0x00D0)
-#define PLL0CR		(CPG_BASE + 0x00D8)
-#define PLL1CR		(CPG_BASE + 0x0028)
-#define PLL2CR		(CPG_BASE + 0x002C)
-#define PLL3CR		(CPG_BASE + 0x00DC)
-#define PLL0STPCR	(CPG_BASE + 0x00F0)
-#define PLL1STPCR	(CPG_BASE + 0x00C8)
-#define PLL2STPCR	(CPG_BASE + 0x00F8)
-#define PLL3STPCR	(CPG_BASE + 0x00FC)
-#define RMSTPCR0	(CPG_BASE + 0x0110)
-#define RMSTPCR1	(CPG_BASE + 0x0114)
-#define RMSTPCR2	(CPG_BASE + 0x0118)
-#define RMSTPCR3	(CPG_BASE + 0x011C)
-#define RMSTPCR4	(CPG_BASE + 0x0120)
-#define RMSTPCR5	(CPG_BASE + 0x0124)
-#define SMSTPCR0	(CPG_BASE + 0x0130)
-#define SMSTPCR2	(CPG_BASE + 0x0138)
-#define SMSTPCR3	(CPG_BASE + 0x013C)
-#define CPGXXCR4	(CPG_BASE + 0x0150)
-#define SRCR0		(CPG_BASE + 0x80A0)
-#define SRCR2		(CPG_BASE + 0x80B0)
-#define SRCR3		(CPG_BASE + 0x80A8)
-#define VREFCR		(CPG_BASE + 0x00EC)
-#define PCLKCR		(CPG_BASE + 0x1020)
-
-#define PORT32CR (0xE6051020)
-#define PORT33CR (0xE6051021)
-#define PORT34CR (0xE6051022)
-#define PORT35CR (0xE6051023)
-
-LIST "DRAM initialization code:"
-
-EW RWTCSRA0, 0xA507
-
-ED_AND LIFEC_SEC_SRC, 0xFFFF7FFF
-
-ED_AND SMSTPCR3,0xFFFF7FFF
-ED_AND SRCR3, 0xFFFF7FFF
-ED_AND SMSTPCR2,0xFFFBFFFF
-ED_AND SRCR2, 0xFFFBFFFF
-ED PLLECR, 0x00000000
-
-WAIT_MASK PLLECR, 0x00000F00, 0x00000000
-WAIT_MASK FRQCRB, 0x80000000, 0x00000000
-
-ED PLL0CR, 0x2D000000
-ED PLL1CR, 0x17100000
-ED FRQCRB, 0x96235880
-WAIT_MASK FRQCRB, 0x80000000, 0x00000000
-
-ED FLCKCR, 0x0000000B
-ED_AND SMSTPCR0, 0xFFFFFFFD
-
-ED_AND SRCR0, 0xFFFFFFFD
-ED 0xE6001628, 0x514
-ED 0xE6001648, 0x514
-ED 0xE6001658, 0x514
-ED 0xE6001678, 0x514
-
-ED DVFSCR4, 0x00092000
-ED DVFSCR5, 0x000000DC
-ED PLLECR, 0x00000000
-WAIT_MASK PLLECR, 0x00000F00, 0x00000000
-
-ED FRQCRA, 0x0012453C
-ED FRQCRB, 0x80431350
-WAIT_MASK FRQCRB, 0x80000000, 0x00000000
-ED FRQCRD, 0x00000B0B
-WAIT_MASK FRQCRD, 0x80000000, 0x00000000
-
-ED PCLKCR, 0x00000003
-ED VCLKCR1, 0x0000012F
-ED VCLKCR2, 0x00000119
-ED VCLKCR3, 0x00000119
-ED ZBCKCR, 0x00000002
-ED FLCKCR, 0x00000005
-ED SD0CKCR, 0x00000080
-ED SD1CKCR, 0x00000080
-ED SD2CKCR, 0x00000080
-ED FSIACKCR, 0x0000003F
-ED FSIBCKCR, 0x0000003F
-ED SUBCKCR, 0x00000080
-ED SPUACKCR, 0x0000000B
-ED SPUVCKCR, 0x0000000B
-ED MSUCKCR, 0x0000013F
-ED HSICKCR, 0x00000080
-ED MFCK1CR, 0x0000003F
-ED MFCK2CR, 0x0000003F
-ED DSITCKCR, 0x00000107
-ED DSI0PCKCR, 0x00000313
-ED DSI1PCKCR, 0x0000130D
-ED DSI0PHYCR, 0x2A800E0E
-ED PLL0CR, 0x1E000000
-ED PLL0CR, 0x2D000000
-ED PLL1CR, 0x17100000
-ED PLL2CR, 0x27000080
-ED PLL3CR, 0x1D000000
-ED PLL0STPCR, 0x00080000
-ED PLL1STPCR, 0x000120C0
-ED PLL2STPCR, 0x00012000
-ED PLL3STPCR, 0x00000030
-ED PLLECR, 0x0000000B
-WAIT_MASK PLLECR, 0x00000B00, 0x00000B00
-
-ED DVFSCR3, 0x000120F0
-ED MPMODE, 0x00000020
-ED VREFCR, 0x0000028A
-ED RMSTPCR0, 0xE4628087
-ED RMSTPCR1, 0xFFFFFFFF
-ED RMSTPCR2, 0x53FFFFFF
-ED RMSTPCR3, 0xFFFFFFFF
-ED RMSTPCR4, 0x00800D3D
-ED RMSTPCR5, 0xFFFFF3FF
-ED SMSTPCR2, 0x00000000
-ED SRCR2,  0x00040000
-ED_AND PLLECR, 0xFFFFFFF7
-WAIT_MASK PLLECR, 0x00000800, 0x00000000
-
-LIST "set SBSC operational"
-ED HPBCTRL6, 0x00000001
-WAIT_MASK HPBCTRL6, 0x00000001, 0x00000001
-
-LIST "set SBSC operating frequency"
-ED FRQCRD, 0x00001414
-WAIT_MASK FRQCRD, 0x80000000, 0x00000000
-ED PLL3CR, 0x1D000000
-ED_OR PLLECR, 0x00000008
-WAIT_MASK PLLECR, 0x00000800, 0x00000800
-
-LIST "enable DLL oscillation in DDRPHY"
-ED_OR DLLCNT0A, 0x00000002
-
-LIST "wait >= 100 ns"
-ED SDGENCNTA, 0x00000005
-WAIT_MASK SDGENCNTA, 0xFFFFFFFF, 0x00000000
-
-LIST "target LPDDR2 device settings"
-ED SDCR0A, 0xACC90159
-ED SDCR1A, 0x00010059
-ED SDWCRC0A, 0x50874114
-ED SDWCRC1A, 0x33199B37
-ED SDWCRC2A, 0x008F2313
-ED SDWCR00A, 0x31020707
-ED SDWCR01A, 0x0017040A
-ED SDWCR10A, 0x31020707
-ED SDWCR11A, 0x0017040A
-
-ED SDDRVCR0A, 0x055557ff
-
-ED SDWCR2A, 0x30000000
-
-LIST "drive CKE high"
-ED_OR SDPCRA, 0x00000080
-WAIT_MASK SDPCRA, 0x00000080, 0x00000080
-
-LIST "wait >= 200 us"
-ED SDGENCNTA, 0x00002710
-WAIT_MASK SDGENCNTA, 0xFFFFFFFF, 0x00000000
-
-LIST "issue reset command to LPDDR2 device"
-ED SDMRACR0A, 0x0000003F
-ED SDMRA1, 0x00000000
-
-LIST "wait >= 10 (or 1) us (docs inconsistent)"
-ED SDGENCNTA, 0x000001F4
-WAIT_MASK SDGENCNTA, 0xFFFFFFFF, 0x00000000
-
-LIST "MRW ZS initialization calibration command"
-ED SDMRACR0A, 0x0000FF0A
-ED SDMRA3, 0x00000000
-
-LIST "wait >= 1 us"
-ED SDGENCNTA, 0x00000032
-WAIT_MASK SDGENCNTA, 0xFFFFFFFF, 0x00000000
-
-LIST "specify operating mode in LPDDR2"
-ED SDMRACR0A, 0x00002201
-ED SDMRA1, 0x00000000
-ED SDMRACR0A, 0x00000402
-ED SDMRA1, 0x00000000
-ED SDMRACR0A, 0x00000203
-ED SDMRA1, 0x00000000
-
-LIST "initialize DDR interface"
-ED SDMRA2, 0x00000000
-
-LIST "temperature sensor control"
-ED SDMRTMPCRA, 0x88800004
-ED SDMRTMPMSKA,0x00000004
-
-LIST "auto-refreshing control"
-ED RTCORA, 0xA55A0032
-ED RTCORHA, 0xA55A000C
-ED RTCSRA, 0xA55A2048
-
-ED_OR SDCR0A, 0x00000800
-ED_OR SDCR1A, 0x00000400
-
-LIST "auto ZQ calibration control"
-ED ZQCCRA, 0xFFF20000
-
-ED_OR DLLCNT0B, 0x00000002
-ED SDGENCNTB, 0x00000005
-WAIT_MASK SDGENCNTB, 0xFFFFFFFF, 0x00000000
-
-ED SDCR0B, 0xACC90159
-ED SDCR1B, 0x00010059
-ED SDWCRC0B, 0x50874114
-ED SDWCRC1B, 0x33199B37
-ED SDWCRC2B, 0x008F2313
-ED SDWCR00B, 0x31020707
-ED SDWCR01B, 0x0017040A
-ED SDWCR10B, 0x31020707
-ED SDWCR11B, 0x0017040A
-ED SDDRVCR0B, 0x055557ff
-ED SDWCR2B, 0x30000000
-ED_OR SDPCRB, 0x00000080
-WAIT_MASK SDPCRB, 0x00000080, 0x00000080
-
-ED SDGENCNTB, 0x00002710
-WAIT_MASK SDGENCNTB, 0xFFFFFFFF, 0x00000000
-ED SDMRACR0B, 0x0000003F
-
-LIST "upstream u-boot writes to SDMRA1A for both SBSC 1 and 2, which does"
-LIST "not seem to make a lot of sense..."
-ED SDMRB1, 0x00000000
-
-ED SDGENCNTB, 0x000001F4
-WAIT_MASK SDGENCNTB, 0xFFFFFFFF, 0x00000000
-
-ED SDMRACR0B, 0x0000FF0A
-ED SDMRB3, 0x00000000
-ED SDGENCNTB, 0x00000032
-WAIT_MASK SDGENCNTB, 0xFFFFFFFF, 0x00000000
-
-ED SDMRACR0B, 0x00002201
-ED SDMRB1, 0x00000000
-ED SDMRACR0B, 0x00000402
-ED SDMRB1, 0x00000000
-ED SDMRACR0B, 0x00000203
-ED SDMRB1, 0x00000000
-ED SDMRB2, 0x00000000
-ED SDMRTMPCRB, 0x88800004
-ED SDMRTMPMSKB, 0x00000004
-ED RTCORB,  0xA55A0032
-ED RTCORHB, 0xA55A000C
-ED RTCSRB,  0xA55A2048
-ED_OR SDCR0B, 0x00000800
-ED_OR SDCR1B, 0x00000400
-ED ZQCCRB, 0xFFF20000
-ED_OR SDPDCR0B, 0x00030000
-ED DPHYCNT1B, 0xA5390000
-ED DPHYCNT0B, 0x00001200
-ED DPHYCNT1B, 0x07CE0000
-ED DPHYCNT0B, 0x00001247
-WAIT_MASK DPHYCNT2B, 0xFFFFFFFF, 0x07CE0000
-
-ED_AND SDPDCR0B, 0xFFFCFFFF
-
-ED FRQCRD, 0x00000B0B
-WAIT_MASK FRQCRD, 0x80000000, 0x00000000
-
-ED CPGXXCR4, 0xfffffffc
-
-LIST "Setup SCIF4 / workaround"
-EB PORT32CR, 0x12
-EB PORT33CR, 0x22
-EB PORT34CR, 0x12
-EB PORT35CR, 0x22
-
-EW 0xE6C80000, 0
-EB 0xE6C80004, 0x19
-EW 0xE6C80008, 0x0030
-EW 0xE6C80018, 0
-EW 0xE6C80030, 0x0014
-
-LIST "Magic to avoid hangs and corruption on DRAM writes."
-
-LIST "It has been observed that the system would most often hang while"
-LIST "decompressing the kernel, and if it didn't it would always write"
-LIST "a corrupt image to DRAM."
-LIST "This problem does not occur in u-boot, and the reason is that"
-LIST "u-boot performs an additional cache invalidation after setting up"
-LIST "the DRAM controller. Such an invalidation should not be necessary at"
-LIST "this point, and attempts at removing parts of the routine to arrive"
-LIST "at the minimal snippet of code necessary to avoid the DRAM stability"
-LIST "problem yielded the following:"
-
-MRC p15, 0, r0, c1, c0, 0
-MCR p15, 0, r0, c1, c0, 0
diff --git a/arch/arm/mach-shmobile/include/mach/zboot.h b/arch/arm/mach-shmobile/include/mach/zboot.h
deleted file mode 100644
index 175ee05465da..000000000000
--- a/arch/arm/mach-shmobile/include/mach/zboot.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef ZBOOT_H
-#define ZBOOT_H
-
-#include <mach/zboot_macros.h>
-
-/**************************************************
- *
- *		board specific settings
- *
- **************************************************/
-
-#ifdef CONFIG_MACH_KZM9G
-#define MEMORY_START	0x43000000
-#include "mach/head-kzm9g.txt"
-#else
-#error "unsupported board."
-#endif
-
-#endif /* ZBOOT_H */
diff --git a/arch/arm/mach-shmobile/include/mach/zboot_macros.h b/arch/arm/mach-shmobile/include/mach/zboot_macros.h
deleted file mode 100644
index 14fd3d538e9a..000000000000
--- a/arch/arm/mach-shmobile/include/mach/zboot_macros.h
+++ /dev/null
@@ -1,108 +0,0 @@
-#ifndef __ZBOOT_MACRO_H
-#define __ZBOOT_MACRO_H
-
-/* The LIST command is used to include comments in the script */
-.macro	LIST comment
-.endm
-
-/* The ED command is used to write a 32-bit word */
-.macro ED, addr, data
-	LDR	r0, 1f
-	LDR	r1, 2f
-	STR	r1, [r0]
-	B	3f
-1 :	.long	\addr
-2 :	.long	\data
-3 :
-.endm
-
-/* The EW command is used to write a 16-bit word */
-.macro EW, addr, data
-	LDR	r0, 1f
-	LDR	r1, 2f
-	STRH	r1, [r0]
-	B	3f
-1 :	.long	\addr
-2 :	.long	\data
-3 :
-.endm
-
-/* The EB command is used to write an 8-bit word */
-.macro EB, addr, data
-	LDR	r0, 1f
-	LDR	r1, 2f
-	STRB	r1, [r0]
-	B	3f
-1 :	.long	\addr
-2 :	.long	\data
-3 :
-.endm
-
-/* The WAIT command is used to delay the execution */
-.macro  WAIT, time, reg
-	LDR	r1, 1f
-	LDR	r0, 2f
-	STR	r0, [r1]
-10 :
-	LDR	r0, [r1]
-	CMP	r0, #0x00000000
-	BNE	10b
-	NOP
-	B	3f
-1 :	.long	\reg
-2 :	.long	\time * 100
-3 :
-.endm
-
-/* The DD command is used to read a 32-bit word */
-.macro  DD, start, end
-	LDR	r1, 1f
-	B	2f
-1 :	.long	\start
-2 :
-.endm
-
-/* loop until a given value has been read (with mask) */
-.macro WAIT_MASK, addr, data, cmp
-	LDR	r0, 2f
-	LDR	r1, 3f
-	LDR	r2, 4f
-1:
-	LDR	r3, [r0, #0]
-	AND	r3, r1, r3
-	CMP	r2, r3
-	BNE	1b
-	B	5f
-2:	.long	\addr
-3:	.long	\data
-4:	.long	\cmp
-5:
-.endm
-
-/* read 32-bit value from addr, "or" an immediate and write back */
-.macro ED_OR, addr, data
-	LDR r4, 1f
-	LDR r5, 2f
-	LDR r6, [r4]
-	ORR r5, r6, r5
-	STR r5, [r4]
-	B	3f
-1:	.long	\addr
-2:	.long	\data
-3:
-.endm
-
-/* read 32-bit value from addr, "and" an immediate and write back */
-.macro ED_AND, addr, data
-	LDR r4, 1f
-	LDR r5, 2f
-	LDR r6, [r4]
-	AND r5, r6, r5
-	STR r5, [r4]
-	B	3f
-1:	.long \addr
-2:	.long \data
-3:
-.endm
-
-#endif /* __ZBOOT_MACRO_H */
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
deleted file mode 100644
index fd63ae6532fc..000000000000
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ /dev/null
@@ -1,337 +0,0 @@
-/*
- * sh73a0 processor support - INTC hardware block
- *
- * Copyright (C) 2010  Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/arm-gic.h>
-
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-
-#include "intc.h"
-#include "irqs.h"
-#include "sh73a0.h"
-
-enum {
-	UNUSED = 0,
-
-	/* interrupt sources INTCS */
-	PINTCS_PINT1, PINTCS_PINT2,
-	RTDMAC_0_DEI0, RTDMAC_0_DEI1, RTDMAC_0_DEI2, RTDMAC_0_DEI3,
-	CEU, MFI, BBIF2, VPU, TSIF1, _3DG_SGX543, _2DDMAC_2DDM0,
-	RTDMAC_1_DEI4, RTDMAC_1_DEI5, RTDMAC_1_DADERR,
-	KEYSC_KEY, VINT, MSIOF,
-	TMU0_TUNI00, TMU0_TUNI01, TMU0_TUNI02,
-	CMT0, TSIF0, CMT2, LMB, MSUG, MSU_MSU, MSU_MSU2,
-	CTI, RWDT0, ICB, PEP, ASA, JPU_JPEG, LCDC, LCRC,
-	RTDMAC_2_DEI6, RTDMAC_2_DEI7, RTDMAC_2_DEI8, RTDMAC_2_DEI9,
-	RTDMAC_3_DEI10, RTDMAC_3_DEI11,
-	FRC, GCU, LCDC1, CSIRX,
-	DSITX0_DSITX00, DSITX0_DSITX01,
-	SPU2_SPU0, SPU2_SPU1, FSI,
-	TMU1_TUNI10, TMU1_TUNI11, TMU1_TUNI12,
-	TSIF2, CMT4, MFIS2, CPORTS2R, TSG, DMASCH1, SCUW,
-	VIO60, VIO61, CEU21, CSI21, DSITX1_DSITX10, DSITX1_DSITX11,
-	DISP, DSRV, EMUX2_EMUX20I, EMUX2_EMUX21I,
-	MSTIF0_MST00I, MSTIF0_MST01I, MSTIF1_MST10I, MSTIF1_MST11I,
-	SPUV,
-
-	/* interrupt groups INTCS */
-	RTDMAC_0, RTDMAC_1, RTDMAC_2, RTDMAC_3,
-	DSITX0, SPU2, TMU1, MSU,
-};
-
-static struct intc_vect intcs_vectors[] = {
-	INTCS_VECT(PINTCS_PINT1, 0x0600), INTCS_VECT(PINTCS_PINT2, 0x0620),
-	INTCS_VECT(RTDMAC_0_DEI0, 0x0800), INTCS_VECT(RTDMAC_0_DEI1, 0x0820),
-	INTCS_VECT(RTDMAC_0_DEI2, 0x0840), INTCS_VECT(RTDMAC_0_DEI3, 0x0860),
-	INTCS_VECT(CEU, 0x0880), INTCS_VECT(MFI, 0x0900),
-	INTCS_VECT(BBIF2, 0x0960), INTCS_VECT(VPU, 0x0980),
-	INTCS_VECT(TSIF1, 0x09a0), INTCS_VECT(_3DG_SGX543, 0x09e0),
-	INTCS_VECT(_2DDMAC_2DDM0, 0x0a00),
-	INTCS_VECT(RTDMAC_1_DEI4, 0x0b80), INTCS_VECT(RTDMAC_1_DEI5, 0x0ba0),
-	INTCS_VECT(RTDMAC_1_DADERR, 0x0bc0),
-	INTCS_VECT(KEYSC_KEY, 0x0be0), INTCS_VECT(VINT, 0x0c80),
-	INTCS_VECT(MSIOF, 0x0d20),
-	INTCS_VECT(TMU0_TUNI00, 0x0e80), INTCS_VECT(TMU0_TUNI01, 0x0ea0),
-	INTCS_VECT(TMU0_TUNI02, 0x0ec0),
-	INTCS_VECT(CMT0, 0x0f00), INTCS_VECT(TSIF0, 0x0f20),
-	INTCS_VECT(CMT2, 0x0f40), INTCS_VECT(LMB, 0x0f60),
-	INTCS_VECT(MSUG, 0x0f80),
-	INTCS_VECT(MSU_MSU, 0x0fa0), INTCS_VECT(MSU_MSU2, 0x0fc0),
-	INTCS_VECT(CTI, 0x0400), INTCS_VECT(RWDT0, 0x0440),
-	INTCS_VECT(ICB, 0x0480), INTCS_VECT(PEP, 0x04a0),
-	INTCS_VECT(ASA, 0x04c0), INTCS_VECT(JPU_JPEG, 0x0560),
-	INTCS_VECT(LCDC, 0x0580), INTCS_VECT(LCRC, 0x05a0),
-	INTCS_VECT(RTDMAC_2_DEI6, 0x1300), INTCS_VECT(RTDMAC_2_DEI7, 0x1320),
-	INTCS_VECT(RTDMAC_2_DEI8, 0x1340), INTCS_VECT(RTDMAC_2_DEI9, 0x1360),
-	INTCS_VECT(RTDMAC_3_DEI10, 0x1380), INTCS_VECT(RTDMAC_3_DEI11, 0x13a0),
-	INTCS_VECT(FRC, 0x1700), INTCS_VECT(GCU, 0x1760),
-	INTCS_VECT(LCDC1, 0x1780), INTCS_VECT(CSIRX, 0x17a0),
-	INTCS_VECT(DSITX0_DSITX00, 0x17c0), INTCS_VECT(DSITX0_DSITX01, 0x17e0),
-	INTCS_VECT(SPU2_SPU0, 0x1800), INTCS_VECT(SPU2_SPU1, 0x1820),
-	INTCS_VECT(FSI, 0x1840),
-	INTCS_VECT(TMU1_TUNI10, 0x1900), INTCS_VECT(TMU1_TUNI11, 0x1920),
-	INTCS_VECT(TMU1_TUNI12, 0x1940),
-	INTCS_VECT(TSIF2, 0x1960), INTCS_VECT(CMT4, 0x1980),
-	INTCS_VECT(MFIS2, 0x1a00), INTCS_VECT(CPORTS2R, 0x1a20),
-	INTCS_VECT(TSG, 0x1ae0), INTCS_VECT(DMASCH1, 0x1b00),
-	INTCS_VECT(SCUW, 0x1b40),
-	INTCS_VECT(VIO60, 0x1b60), INTCS_VECT(VIO61, 0x1b80),
-	INTCS_VECT(CEU21, 0x1ba0), INTCS_VECT(CSI21, 0x1be0),
-	INTCS_VECT(DSITX1_DSITX10, 0x1c00), INTCS_VECT(DSITX1_DSITX11, 0x1c20),
-	INTCS_VECT(DISP, 0x1c40), INTCS_VECT(DSRV, 0x1c60),
-	INTCS_VECT(EMUX2_EMUX20I, 0x1c80), INTCS_VECT(EMUX2_EMUX21I, 0x1ca0),
-	INTCS_VECT(MSTIF0_MST00I, 0x1cc0), INTCS_VECT(MSTIF0_MST01I, 0x1ce0),
-	INTCS_VECT(MSTIF1_MST10I, 0x1d00), INTCS_VECT(MSTIF1_MST11I, 0x1d20),
-	INTCS_VECT(SPUV, 0x2300),
-};
-
-static struct intc_group intcs_groups[] __initdata = {
-	INTC_GROUP(RTDMAC_0, RTDMAC_0_DEI0, RTDMAC_0_DEI1,
-		   RTDMAC_0_DEI2, RTDMAC_0_DEI3),
-	INTC_GROUP(RTDMAC_1, RTDMAC_1_DEI4, RTDMAC_1_DEI5, RTDMAC_1_DADERR),
-	INTC_GROUP(RTDMAC_2, RTDMAC_2_DEI6, RTDMAC_2_DEI7,
-		   RTDMAC_2_DEI8, RTDMAC_2_DEI9),
-	INTC_GROUP(RTDMAC_3, RTDMAC_3_DEI10, RTDMAC_3_DEI11),
-	INTC_GROUP(TMU1, TMU1_TUNI12, TMU1_TUNI11, TMU1_TUNI10),
-	INTC_GROUP(DSITX0, DSITX0_DSITX00, DSITX0_DSITX01),
-	INTC_GROUP(SPU2, SPU2_SPU0, SPU2_SPU1),
-	INTC_GROUP(MSU, MSU_MSU, MSU_MSU2),
-};
-
-static struct intc_mask_reg intcs_mask_registers[] = {
-	{ 0xffd20184, 0xffd201c4, 8, /* IMR1SA / IMCR1SA */
-	  { 0, 0, 0, CEU,
-	    0, 0, 0, 0 } },
-	{ 0xffd20188, 0xffd201c8, 8, /* IMR2SA / IMCR2SA */
-	  { 0, 0, 0, VPU,
-	    BBIF2, 0, 0, MFI } },
-	{ 0xffd2018c, 0xffd201cc, 8, /* IMR3SA / IMCR3SA */
-	  { 0, 0, 0, _2DDMAC_2DDM0,
-	    0, ASA, PEP, ICB } },
-	{ 0xffd20190, 0xffd201d0, 8, /* IMR4SA / IMCR4SA */
-	  { 0, 0, 0, CTI,
-	    JPU_JPEG, 0, LCRC, LCDC } },
-	{ 0xffd20194, 0xffd201d4, 8, /* IMR5SA / IMCR5SA */
-	  { KEYSC_KEY, RTDMAC_1_DADERR, RTDMAC_1_DEI5, RTDMAC_1_DEI4,
-	    RTDMAC_0_DEI3, RTDMAC_0_DEI2, RTDMAC_0_DEI1, RTDMAC_0_DEI0 } },
-	{ 0xffd20198, 0xffd201d8, 8, /* IMR6SA / IMCR6SA */
-	  { 0, 0, MSIOF, 0,
-	    _3DG_SGX543, 0, 0, 0 } },
-	{ 0xffd2019c, 0xffd201dc, 8, /* IMR7SA / IMCR7SA */
-	  { 0, TMU0_TUNI02, TMU0_TUNI01, TMU0_TUNI00,
-	    0, 0, 0, 0 } },
-	{ 0xffd201a0, 0xffd201e0, 8, /* IMR8SA / IMCR8SA */
-	  { 0, 0, 0, 0,
-	    0, MSU_MSU, MSU_MSU2, MSUG } },
-	{ 0xffd201a4, 0xffd201e4, 8, /* IMR9SA / IMCR9SA */
-	  { 0, RWDT0, CMT2, CMT0,
-	    0, 0, 0, 0 } },
-	{ 0xffd201ac, 0xffd201ec, 8, /* IMR11SA / IMCR11SA */
-	  { 0, 0, 0, 0,
-	    0, TSIF1, LMB, TSIF0 } },
-	{ 0xffd201b0, 0xffd201f0, 8, /* IMR12SA / IMCR12SA */
-	  { 0, 0, 0, 0,
-	    0, 0, PINTCS_PINT2, PINTCS_PINT1 } },
-	{ 0xffd50180, 0xffd501c0, 8, /* IMR0SA3 / IMCR0SA3 */
-	  { RTDMAC_2_DEI6, RTDMAC_2_DEI7, RTDMAC_2_DEI8, RTDMAC_2_DEI9,
-	    RTDMAC_3_DEI10, RTDMAC_3_DEI11, 0, 0 } },
-	{ 0xffd50190, 0xffd501d0, 8, /* IMR4SA3 / IMCR4SA3 */
-	  { FRC, 0, 0, GCU,
-	    LCDC1, CSIRX, DSITX0_DSITX00, DSITX0_DSITX01 } },
-	{ 0xffd50194, 0xffd501d4, 8, /* IMR5SA3 / IMCR5SA3 */
-	  { SPU2_SPU0, SPU2_SPU1, FSI, 0,
-	    0, 0, 0, 0 } },
-	{ 0xffd50198, 0xffd501d8, 8, /* IMR6SA3 / IMCR6SA3 */
-	  { TMU1_TUNI10, TMU1_TUNI11, TMU1_TUNI12, 0,
-	    TSIF2, CMT4, 0, 0 } },
-	{ 0xffd5019c, 0xffd501dc, 8, /* IMR7SA3 / IMCR7SA3 */
-	  { MFIS2, CPORTS2R, 0, 0,
-	    0, 0, 0, TSG } },
-	{ 0xffd501a0, 0xffd501e0, 8, /* IMR8SA3 / IMCR8SA3 */
-	  { DMASCH1, 0, SCUW, VIO60,
-	    VIO61, CEU21, 0, CSI21 } },
-	{ 0xffd501a4, 0xffd501e4, 8, /* IMR9SA3 / IMCR9SA3 */
-	  { DSITX1_DSITX10, DSITX1_DSITX11, DISP, DSRV,
-	    EMUX2_EMUX20I, EMUX2_EMUX21I, MSTIF0_MST00I, MSTIF0_MST01I } },
-	{ 0xffd501a8, 0xffd501e8, 8, /* IMR10SA3 / IMCR10SA3 */
-	  { MSTIF0_MST00I, MSTIF0_MST01I, 0, 0,
-	    0, 0, 0, 0  } },
-	{ 0xffd60180, 0xffd601c0, 8, /* IMR0SA4 / IMCR0SA4 */
-	  { SPUV, 0, 0, 0,
-	    0, 0, 0, 0  } },
-};
-
-/* Priority is needed for INTCA to receive the INTCS interrupt */
-static struct intc_prio_reg intcs_prio_registers[] = {
-	{ 0xffd20000, 0, 16, 4, /* IPRAS */ { CTI, 0, _2DDMAC_2DDM0, ICB } },
-	{ 0xffd20004, 0, 16, 4, /* IPRBS */ { JPU_JPEG, LCDC, 0, LCRC } },
-	{ 0xffd20008, 0, 16, 4, /* IPRCS */ { BBIF2, 0, 0, 0 } },
-	{ 0xffd2000c, 0, 16, 4, /* IPRDS */ { PINTCS_PINT1, PINTCS_PINT2,
-					      0, 0 } },
-	{ 0xffd20010, 0, 16, 4, /* IPRES */ { RTDMAC_0, CEU, MFI, VPU } },
-	{ 0xffd20014, 0, 16, 4, /* IPRFS */ { KEYSC_KEY, RTDMAC_1,
-					      CMT2, CMT0 } },
-	{ 0xffd20018, 0, 16, 4, /* IPRGS */ { TMU0_TUNI00, TMU0_TUNI01,
-					      TMU0_TUNI02, TSIF1 } },
-	{ 0xffd2001c, 0, 16, 4, /* IPRHS */ { VINT, 0, 0, 0 } },
-	{ 0xffd20020, 0, 16, 4, /* IPRIS */ { 0, MSIOF, TSIF0, 0 } },
-	{ 0xffd20024, 0, 16, 4, /* IPRJS */ { 0, _3DG_SGX543, MSUG, MSU } },
-	{ 0xffd20028, 0, 16, 4, /* IPRKS */ { 0, ASA, LMB, PEP } },
-	{ 0xffd20030, 0, 16, 4, /* IPRMS */ { 0, 0, 0, RWDT0 } },
-	{ 0xffd50000, 0, 16, 4, /* IPRAS3 */ { RTDMAC_2, 0, 0, 0 } },
-	{ 0xffd50004, 0, 16, 4, /* IPRBS3 */ { RTDMAC_3, 0, 0, 0 } },
-	{ 0xffd50020, 0, 16, 4, /* IPRIS3 */ { FRC, 0, 0, 0 } },
-	{ 0xffd50024, 0, 16, 4, /* IPRJS3 */ { LCDC1, CSIRX, DSITX0, 0 } },
-	{ 0xffd50028, 0, 16, 4, /* IPRKS3 */ { SPU2, 0, FSI, 0 } },
-	{ 0xffd50030, 0, 16, 4, /* IPRMS3 */ { TMU1, 0, 0, TSIF2 } },
-	{ 0xffd50034, 0, 16, 4, /* IPRNS3 */ { CMT4, 0, 0, 0 } },
-	{ 0xffd50038, 0, 16, 4, /* IPROS3 */ { MFIS2, CPORTS2R, 0, 0 } },
-	{ 0xffd50040, 0, 16, 4, /* IPRQS3 */ { DMASCH1, 0, SCUW, VIO60 } },
-	{ 0xffd50044, 0, 16, 4, /* IPRRS3 */ { VIO61, CEU21, 0, CSI21 } },
-	{ 0xffd50048, 0, 16, 4, /* IPRSS3 */ { DSITX1_DSITX10, DSITX1_DSITX11,
-					       DISP, DSRV } },
-	{ 0xffd5004c, 0, 16, 4, /* IPRTS3 */ { EMUX2_EMUX20I, EMUX2_EMUX21I,
-					       MSTIF0_MST00I, MSTIF0_MST01I } },
-	{ 0xffd50050, 0, 16, 4, /* IPRUS3 */ { MSTIF1_MST10I, MSTIF1_MST11I,
-					       0, 0 } },
-	{ 0xffd60000, 0, 16, 4, /* IPRAS4 */ { SPUV, 0, 0, 0 } },
-};
-
-static struct resource intcs_resources[] __initdata = {
-	[0] = {
-		.start	= 0xffd20000,
-		.end	= 0xffd201ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= 0xffd50000,
-		.end	= 0xffd501ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= 0xffd60000,
-		.end	= 0xffd601ff,
-		.flags	= IORESOURCE_MEM,
-	}
-};
-
-static struct intc_desc intcs_desc __initdata = {
-	.name = "sh73a0-intcs",
-	.resource = intcs_resources,
-	.num_resources = ARRAY_SIZE(intcs_resources),
-	.hw = INTC_HW_DESC(intcs_vectors, intcs_groups, intcs_mask_registers,
-			   intcs_prio_registers, NULL, NULL),
-};
-
-static struct irqaction sh73a0_intcs_cascade;
-
-static irqreturn_t sh73a0_intcs_demux(int irq, void *dev_id)
-{
-	unsigned int evtcodeas = ioread32((void __iomem *)dev_id);
-
-	generic_handle_irq(intcs_evt2irq(evtcodeas));
-
-	return IRQ_HANDLED;
-}
-
-#define PINTER0_PHYS 0xe69000a0
-#define PINTER1_PHYS 0xe69000a4
-#define PINTER0_VIRT IOMEM(0xe69000a0)
-#define PINTER1_VIRT IOMEM(0xe69000a4)
-#define PINTRR0 IOMEM(0xe69000d0)
-#define PINTRR1 IOMEM(0xe69000d4)
-
-#define PINT0A_IRQ(n, irq) INTC_IRQ((n), SH73A0_PINT0_IRQ(irq))
-#define PINT0B_IRQ(n, irq) INTC_IRQ((n), SH73A0_PINT0_IRQ(irq + 8))
-#define PINT0C_IRQ(n, irq) INTC_IRQ((n), SH73A0_PINT0_IRQ(irq + 16))
-#define PINT0D_IRQ(n, irq) INTC_IRQ((n), SH73A0_PINT0_IRQ(irq + 24))
-#define PINT1E_IRQ(n, irq) INTC_IRQ((n), SH73A0_PINT1_IRQ(irq))
-
-INTC_PINT(intc_pint0, PINTER0_PHYS, 0xe69000b0, "sh73a0-pint0",		\
-  INTC_PINT_E(A), INTC_PINT_E(B), INTC_PINT_E(C), INTC_PINT_E(D),	\
-  INTC_PINT_V(A, PINT0A_IRQ), INTC_PINT_V(B, PINT0B_IRQ),		\
-  INTC_PINT_V(C, PINT0C_IRQ), INTC_PINT_V(D, PINT0D_IRQ),		\
-  INTC_PINT_E(A), INTC_PINT_E(B), INTC_PINT_E(C), INTC_PINT_E(D),	\
-  INTC_PINT_E(A), INTC_PINT_E(B), INTC_PINT_E(C), INTC_PINT_E(D));
-
-INTC_PINT(intc_pint1, PINTER1_PHYS, 0xe69000c0, "sh73a0-pint1",		\
-  INTC_PINT_E(E), INTC_PINT_E_EMPTY, INTC_PINT_E_EMPTY, INTC_PINT_E_EMPTY, \
-  INTC_PINT_V(E, PINT1E_IRQ), INTC_PINT_V_NONE,				\
-  INTC_PINT_V_NONE, INTC_PINT_V_NONE,					\
-  INTC_PINT_E_NONE, INTC_PINT_E_NONE, INTC_PINT_E_NONE, INTC_PINT_E(E), \
-  INTC_PINT_E(E), INTC_PINT_E_NONE, INTC_PINT_E_NONE, INTC_PINT_E_NONE);
-
-static struct irqaction sh73a0_pint0_cascade;
-static struct irqaction sh73a0_pint1_cascade;
-
-static void pint_demux(void __iomem *rr, void __iomem *er, int base_irq)
-{
-	unsigned long value =  ioread32(rr) & ioread32(er);
-	int k;
-
-	for (k = 0; k < 32; k++) {
-		if (value & (1 << (31 - k))) {
-			generic_handle_irq(base_irq + k);
-			iowrite32(~(1 << (31 - k)), rr);
-		}
-	}
-}
-
-static irqreturn_t sh73a0_pint0_demux(int irq, void *dev_id)
-{
-	pint_demux(PINTRR0, PINTER0_VIRT, SH73A0_PINT0_IRQ(0));
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t sh73a0_pint1_demux(int irq, void *dev_id)
-{
-	pint_demux(PINTRR1, PINTER1_VIRT, SH73A0_PINT1_IRQ(0));
-	return IRQ_HANDLED;
-}
-
-void __init sh73a0_init_irq(void)
-{
-	void __iomem *gic_dist_base = IOMEM(0xf0001000);
-	void __iomem *gic_cpu_base = IOMEM(0xf0000100);
-	void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE);
-
-	gic_set_irqchip_flags(IRQCHIP_SKIP_SET_WAKE);
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-
-	register_intc_controller(&intcs_desc);
-	register_intc_controller(&intc_pint0_desc);
-	register_intc_controller(&intc_pint1_desc);
-
-	/* demux using INTEVTSA */
-	sh73a0_intcs_cascade.name = "INTCS cascade";
-	sh73a0_intcs_cascade.handler = sh73a0_intcs_demux;
-	sh73a0_intcs_cascade.dev_id = intevtsa;
-	setup_irq(gic_spi(50), &sh73a0_intcs_cascade);
-
-	/* PINT pins are sanely tied to the GIC as SPI */
-	sh73a0_pint0_cascade.name = "PINT0 cascade";
-	sh73a0_pint0_cascade.handler = sh73a0_pint0_demux;
-	setup_irq(gic_spi(33), &sh73a0_pint0_cascade);
-
-	sh73a0_pint1_cascade.name = "PINT1 cascade";
-	sh73a0_pint1_cascade.handler = sh73a0_pint1_demux;
-	setup_irq(gic_spi(34), &sh73a0_pint1_cascade);
-}
diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c
index b0790fc32282..4e54512bee30 100644
--- a/arch/arm/mach-shmobile/platsmp-apmu.c
+++ b/arch/arm/mach-shmobile/platsmp-apmu.c
@@ -46,7 +46,7 @@ static int __maybe_unused apmu_power_on(void __iomem *p, int bit)
 	return 0;
 }
 
-static int apmu_power_off(void __iomem *p, int bit)
+static int __maybe_unused apmu_power_off(void __iomem *p, int bit)
 {
 	/* request Core Standby for next WFI */
 	writel_relaxed(3, p + CPUNCR_OFFS(bit));
@@ -67,7 +67,7 @@ static int __maybe_unused apmu_power_off_poll(void __iomem *p, int bit)
 	return 0;
 }
 
-static int apmu_wrap(int cpu, int (*fn)(void __iomem *p, int cpu))
+static int __maybe_unused apmu_wrap(int cpu, int (*fn)(void __iomem *p, int cpu))
 {
 	void __iomem *p = apmu_cpus[cpu].iomem;
 
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index 3923e09e966d..b23378f3d7e1 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -31,8 +31,8 @@ void shmobile_smp_hook(unsigned int cpu, unsigned long fn, unsigned long arg)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int shmobile_smp_cpu_disable(unsigned int cpu)
+bool shmobile_smp_cpu_can_disable(unsigned int cpu)
 {
-	return 0; /* Hotplug of any CPU is supported */
+	return true; /* Hotplug of any CPU is supported */
 }
 #endif
diff --git a/arch/arm/mach-shmobile/pm-r8a7740.c b/arch/arm/mach-shmobile/pm-r8a7740.c
deleted file mode 100644
index 34608fcf0648..000000000000
--- a/arch/arm/mach-shmobile/pm-r8a7740.c
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * r8a7740 power management support
- *
- * Copyright (C) 2012  Renesas Solutions Corp.
- * Copyright (C) 2012  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/console.h>
-#include <linux/io.h>
-#include <linux/suspend.h>
-
-#include "common.h"
-#include "pm-rmobile.h"
-
-#define SYSC_BASE	IOMEM(0xe6180000)
-
-#if defined(CONFIG_PM) && !defined(CONFIG_ARCH_MULTIPLATFORM)
-static int r8a7740_pd_a3sm_suspend(void)
-{
-	/*
-	 * The A3SM domain contains the CPU core and therefore it should
-	 * only be turned off if the CPU is not in use.
-	 */
-	return -EBUSY;
-}
-
-static int r8a7740_pd_a3sp_suspend(void)
-{
-	/*
-	 * Serial consoles make use of SCIF hardware located in A3SP,
-	 * keep such power domain on if "no_console_suspend" is set.
-	 */
-	return console_suspend_enabled ? 0 : -EBUSY;
-}
-
-static int r8a7740_pd_d4_suspend(void)
-{
-	/*
-	 * The D4 domain contains the Coresight-ETM hardware block and
-	 * therefore it should only be turned off if the debug module is
-	 * not in use.
-	 */
-	return -EBUSY;
-}
-
-static struct rmobile_pm_domain r8a7740_pm_domains[] = {
-	{
-		.genpd.name	= "A4LC",
-		.base		= SYSC_BASE,
-		.bit_shift	= 1,
-	}, {
-		.genpd.name	= "A4MP",
-		.base		= SYSC_BASE,
-		.bit_shift	= 2,
-	}, {
-		.genpd.name	= "D4",
-		.base		= SYSC_BASE,
-		.bit_shift	= 3,
-		.gov		= &pm_domain_always_on_gov,
-		.suspend	= r8a7740_pd_d4_suspend,
-	}, {
-		.genpd.name	= "A4R",
-		.base		= SYSC_BASE,
-		.bit_shift	= 5,
-	}, {
-		.genpd.name	= "A3RV",
-		.base		= SYSC_BASE,
-		.bit_shift	= 6,
-	}, {
-		.genpd.name	= "A4S",
-		.base		= SYSC_BASE,
-		.bit_shift	= 10,
-		.no_debug	= true,
-	}, {
-		.genpd.name	= "A3SP",
-		.base		= SYSC_BASE,
-		.bit_shift	= 11,
-		.gov		= &pm_domain_always_on_gov,
-		.no_debug	= true,
-		.suspend	= r8a7740_pd_a3sp_suspend,
-	}, {
-		.genpd.name	= "A3SM",
-		.base		= SYSC_BASE,
-		.bit_shift	= 12,
-		.gov		= &pm_domain_always_on_gov,
-		.suspend	= r8a7740_pd_a3sm_suspend,
-	}, {
-		.genpd.name	= "A3SG",
-		.base		= SYSC_BASE,
-		.bit_shift	= 13,
-	}, {
-		.genpd.name	= "A4SU",
-		.base		= SYSC_BASE,
-		.bit_shift	= 20,
-	},
-};
-
-void __init r8a7740_init_pm_domains(void)
-{
-	rmobile_init_domains(r8a7740_pm_domains, ARRAY_SIZE(r8a7740_pm_domains));
-	pm_genpd_add_subdomain_names("A4R", "A3RV");
-	pm_genpd_add_subdomain_names("A4S", "A3SP");
-	pm_genpd_add_subdomain_names("A4S", "A3SM");
-	pm_genpd_add_subdomain_names("A4S", "A3SG");
-}
-#endif /* CONFIG_PM && !CONFIG_ARCH_MULTIPLATFORM */
-
-#ifdef CONFIG_SUSPEND
-static int r8a7740_enter_suspend(suspend_state_t suspend_state)
-{
-	cpu_do_idle();
-	return 0;
-}
-
-static void r8a7740_suspend_init(void)
-{
-	shmobile_suspend_ops.enter = r8a7740_enter_suspend;
-}
-#else
-static void r8a7740_suspend_init(void) {}
-#endif
-
-void __init r8a7740_pm_init(void)
-{
-	r8a7740_suspend_init();
-}
diff --git a/arch/arm/mach-shmobile/pm-r8a7779.c b/arch/arm/mach-shmobile/pm-r8a7779.c
index 44a74c4c5a01..47a862e7f8ba 100644
--- a/arch/arm/mach-shmobile/pm-r8a7779.c
+++ b/arch/arm/mach-shmobile/pm-r8a7779.c
@@ -35,7 +35,8 @@ struct r8a7779_pm_domain {
 	struct rcar_sysc_ch ch;
 };
 
-static inline struct rcar_sysc_ch *to_r8a7779_ch(struct generic_pm_domain *d)
+static inline
+const struct rcar_sysc_ch *to_r8a7779_ch(struct generic_pm_domain *d)
 {
 	return &container_of(d, struct r8a7779_pm_domain, genpd)->ch;
 }
@@ -83,7 +84,6 @@ static void r8a7779_init_pm_domain(struct r8a7779_pm_domain *r8a7779_pd)
 {
 	struct generic_pm_domain *genpd = &r8a7779_pd->genpd;
 
-	genpd->flags = GENPD_FLAG_PM_CLK;
 	pm_genpd_init(genpd, NULL, false);
 	genpd->dev_ops.active_wakeup = pd_active_wakeup;
 	genpd->power_off = pd_power_down;
diff --git a/arch/arm/mach-shmobile/pm-rcar.c b/arch/arm/mach-shmobile/pm-rcar.c
index 00022ee56f80..4092ad16e0a4 100644
--- a/arch/arm/mach-shmobile/pm-rcar.c
+++ b/arch/arm/mach-shmobile/pm-rcar.c
@@ -15,32 +15,58 @@
 #include <asm/io.h>
 #include "pm-rcar.h"
 
-/* SYSC */
-#define SYSCSR 0x00
-#define SYSCISR 0x04
-#define SYSCISCR 0x08
+/* SYSC Common */
+#define SYSCSR			0x00	/* SYSC Status Register */
+#define SYSCISR			0x04	/* Interrupt Status Register */
+#define SYSCISCR		0x08	/* Interrupt Status Clear Register */
+#define SYSCIER			0x0c	/* Interrupt Enable Register */
+#define SYSCIMR			0x10	/* Interrupt Mask Register */
 
-#define PWRSR_OFFS 0x00
-#define PWROFFCR_OFFS 0x04
-#define PWRONCR_OFFS 0x0c
-#define PWRER_OFFS 0x14
+/* SYSC Status Register */
+#define SYSCSR_PONENB		1	/* Ready for power resume requests */
+#define SYSCSR_POFFENB		0	/* Ready for power shutoff requests */
 
-#define SYSCSR_RETRIES 100
-#define SYSCSR_DELAY_US 1
+/*
+ * Power Control Register Offsets inside the register block for each domain
+ * Note: The "CR" registers for ARM cores exist on H1 only
+ *       Use WFI to power off, CPG/APMU to resume ARM cores on R-Car Gen2
+ */
+#define PWRSR_OFFS		0x00	/* Power Status Register */
+#define PWROFFCR_OFFS		0x04	/* Power Shutoff Control Register */
+#define PWROFFSR_OFFS		0x08	/* Power Shutoff Status Register */
+#define PWRONCR_OFFS		0x0c	/* Power Resume Control Register */
+#define PWRONSR_OFFS		0x10	/* Power Resume Status Register */
+#define PWRER_OFFS		0x14	/* Power Shutoff/Resume Error */
+
+
+#define SYSCSR_RETRIES		100
+#define SYSCSR_DELAY_US		1
+
+#define PWRER_RETRIES		100
+#define PWRER_DELAY_US		1
 
-#define SYSCISR_RETRIES 1000
-#define SYSCISR_DELAY_US 1
+#define SYSCISR_RETRIES		1000
+#define SYSCISR_DELAY_US	1
 
 static void __iomem *rcar_sysc_base;
 static DEFINE_SPINLOCK(rcar_sysc_lock); /* SMP CPUs + I/O devices */
 
-static int rcar_sysc_pwr_on_off(struct rcar_sysc_ch *sysc_ch,
-				int sr_bit, int reg_offs)
+static int rcar_sysc_pwr_on_off(const struct rcar_sysc_ch *sysc_ch, bool on)
 {
+	unsigned int sr_bit, reg_offs;
 	int k;
 
+	if (on) {
+		sr_bit = SYSCSR_PONENB;
+		reg_offs = PWRONCR_OFFS;
+	} else {
+		sr_bit = SYSCSR_POFFENB;
+		reg_offs = PWROFFCR_OFFS;
+	}
+
+	/* Wait until SYSC is ready to accept a power request */
 	for (k = 0; k < SYSCSR_RETRIES; k++) {
-		if (ioread32(rcar_sysc_base + SYSCSR) & (1 << sr_bit))
+		if (ioread32(rcar_sysc_base + SYSCSR) & BIT(sr_bit))
 			break;
 		udelay(SYSCSR_DELAY_US);
 	}
@@ -48,27 +74,17 @@ static int rcar_sysc_pwr_on_off(struct rcar_sysc_ch *sysc_ch,
 	if (k == SYSCSR_RETRIES)
 		return -EAGAIN;
 
-	iowrite32(1 << sysc_ch->chan_bit,
+	/* Submit power shutoff or power resume request */
+	iowrite32(BIT(sysc_ch->chan_bit),
 		  rcar_sysc_base + sysc_ch->chan_offs + reg_offs);
 
 	return 0;
 }
 
-static int rcar_sysc_pwr_off(struct rcar_sysc_ch *sysc_ch)
-{
-	return rcar_sysc_pwr_on_off(sysc_ch, 0, PWROFFCR_OFFS);
-}
-
-static int rcar_sysc_pwr_on(struct rcar_sysc_ch *sysc_ch)
+static int rcar_sysc_power(const struct rcar_sysc_ch *sysc_ch, bool on)
 {
-	return rcar_sysc_pwr_on_off(sysc_ch, 1, PWRONCR_OFFS);
-}
-
-static int rcar_sysc_update(struct rcar_sysc_ch *sysc_ch,
-			    int (*on_off_fn)(struct rcar_sysc_ch *))
-{
-	unsigned int isr_mask = 1 << sysc_ch->isr_bit;
-	unsigned int chan_mask = 1 << sysc_ch->chan_bit;
+	unsigned int isr_mask = BIT(sysc_ch->isr_bit);
+	unsigned int chan_mask = BIT(sysc_ch->chan_bit);
 	unsigned int status;
 	unsigned long flags;
 	int ret = 0;
@@ -78,15 +94,26 @@ static int rcar_sysc_update(struct rcar_sysc_ch *sysc_ch,
 
 	iowrite32(isr_mask, rcar_sysc_base + SYSCISCR);
 
-	do {
-		ret = on_off_fn(sysc_ch);
+	/* Submit power shutoff or resume request until it was accepted */
+	for (k = 0; k < PWRER_RETRIES; k++) {
+		ret = rcar_sysc_pwr_on_off(sysc_ch, on);
 		if (ret)
 			goto out;
 
 		status = ioread32(rcar_sysc_base +
 				  sysc_ch->chan_offs + PWRER_OFFS);
-	} while (status & chan_mask);
+		if (!(status & chan_mask))
+			break;
+
+		udelay(PWRER_DELAY_US);
+	}
+
+	if (k == PWRER_RETRIES) {
+		ret = -EIO;
+		goto out;
+	}
 
+	/* Wait until the power shutoff or resume request has completed * */
 	for (k = 0; k < SYSCISR_RETRIES; k++) {
 		if (ioread32(rcar_sysc_base + SYSCISR) & isr_mask)
 			break;
@@ -106,22 +133,22 @@ static int rcar_sysc_update(struct rcar_sysc_ch *sysc_ch,
 	return ret;
 }
 
-int rcar_sysc_power_down(struct rcar_sysc_ch *sysc_ch)
+int rcar_sysc_power_down(const struct rcar_sysc_ch *sysc_ch)
 {
-	return rcar_sysc_update(sysc_ch, rcar_sysc_pwr_off);
+	return rcar_sysc_power(sysc_ch, false);
 }
 
-int rcar_sysc_power_up(struct rcar_sysc_ch *sysc_ch)
+int rcar_sysc_power_up(const struct rcar_sysc_ch *sysc_ch)
 {
-	return rcar_sysc_update(sysc_ch, rcar_sysc_pwr_on);
+	return rcar_sysc_power(sysc_ch, true);
 }
 
-bool rcar_sysc_power_is_off(struct rcar_sysc_ch *sysc_ch)
+bool rcar_sysc_power_is_off(const struct rcar_sysc_ch *sysc_ch)
 {
 	unsigned int st;
 
 	st = ioread32(rcar_sysc_base + sysc_ch->chan_offs + PWRSR_OFFS);
-	if (st & (1 << sysc_ch->chan_bit))
+	if (st & BIT(sysc_ch->chan_bit))
 		return true;
 
 	return false;
diff --git a/arch/arm/mach-shmobile/pm-rcar.h b/arch/arm/mach-shmobile/pm-rcar.h
index ef3a1ef628f1..1b901db4a24c 100644
--- a/arch/arm/mach-shmobile/pm-rcar.h
+++ b/arch/arm/mach-shmobile/pm-rcar.h
@@ -2,14 +2,14 @@
 #define PM_RCAR_H
 
 struct rcar_sysc_ch {
-	unsigned long chan_offs;
-	unsigned int chan_bit;
-	unsigned int isr_bit;
+	u16 chan_offs;
+	u8 chan_bit;
+	u8 isr_bit;
 };
 
-int rcar_sysc_power_down(struct rcar_sysc_ch *sysc_ch);
-int rcar_sysc_power_up(struct rcar_sysc_ch *sysc_ch);
-bool rcar_sysc_power_is_off(struct rcar_sysc_ch *sysc_ch);
+int rcar_sysc_power_down(const struct rcar_sysc_ch *sysc_ch);
+int rcar_sysc_power_up(const struct rcar_sysc_ch *sysc_ch);
+bool rcar_sysc_power_is_off(const struct rcar_sysc_ch *sysc_ch);
 void __iomem *rcar_sysc_init(phys_addr_t base);
 
 #endif /* PM_RCAR_H */
diff --git a/arch/arm/mach-shmobile/pm-rmobile.c b/arch/arm/mach-shmobile/pm-rmobile.c
index 95018209ff0b..a5b96b990aea 100644
--- a/arch/arm/mach-shmobile/pm-rmobile.c
+++ b/arch/arm/mach-shmobile/pm-rmobile.c
@@ -34,6 +34,12 @@
 #define PSTR_RETRIES	100
 #define PSTR_DELAY_US	10
 
+static inline
+struct rmobile_pm_domain *to_rmobile_pd(struct generic_pm_domain *d)
+{
+	return container_of(d, struct rmobile_pm_domain, genpd);
+}
+
 static int rmobile_pd_power_down(struct generic_pm_domain *genpd)
 {
 	struct rmobile_pm_domain *rmobile_pd = to_rmobile_pd(genpd);
@@ -42,7 +48,7 @@ static int rmobile_pd_power_down(struct generic_pm_domain *genpd)
 	if (rmobile_pd->bit_shift == ~0)
 		return -EBUSY;
 
-	mask = 1 << rmobile_pd->bit_shift;
+	mask = BIT(rmobile_pd->bit_shift);
 	if (rmobile_pd->suspend) {
 		int ret = rmobile_pd->suspend();
 
@@ -79,7 +85,7 @@ static int __rmobile_pd_power_up(struct rmobile_pm_domain *rmobile_pd,
 	if (rmobile_pd->bit_shift == ~0)
 		return 0;
 
-	mask = 1 << rmobile_pd->bit_shift;
+	mask = BIT(rmobile_pd->bit_shift);
 	if (__raw_readl(rmobile_pd->base + PSTR) & mask)
 		goto out;
 
@@ -163,43 +169,6 @@ static void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd)
 	__rmobile_pd_power_up(rmobile_pd, false);
 }
 
-#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
-
-void rmobile_init_domains(struct rmobile_pm_domain domains[], int num)
-{
-	int j;
-
-	for (j = 0; j < num; j++)
-		rmobile_init_pm_domain(&domains[j]);
-}
-
-void rmobile_add_device_to_domain_td(const char *domain_name,
-				     struct platform_device *pdev,
-				     struct gpd_timing_data *td)
-{
-	struct device *dev = &pdev->dev;
-
-	__pm_genpd_name_add_device(domain_name, dev, td);
-}
-
-void rmobile_add_devices_to_domains(struct pm_domain_device data[],
-				    int size)
-{
-	struct gpd_timing_data latencies = {
-		.stop_latency_ns = DEFAULT_DEV_LATENCY_NS,
-		.start_latency_ns = DEFAULT_DEV_LATENCY_NS,
-		.save_state_latency_ns = DEFAULT_DEV_LATENCY_NS,
-		.restore_state_latency_ns = DEFAULT_DEV_LATENCY_NS,
-	};
-	int j;
-
-	for (j = 0; j < size; j++)
-		rmobile_add_device_to_domain_td(data[j].domain_name,
-						data[j].pdev, &latencies);
-}
-
-#else /* !CONFIG_ARCH_SHMOBILE_LEGACY */
-
 static int rmobile_pd_suspend_busy(void)
 {
 	/*
@@ -430,5 +399,3 @@ static int __init rmobile_init_pm_domains(void)
 }
 
 core_initcall(rmobile_init_pm_domains);
-
-#endif /* !CONFIG_ARCH_SHMOBILE_LEGACY */
diff --git a/arch/arm/mach-shmobile/pm-rmobile.h b/arch/arm/mach-shmobile/pm-rmobile.h
index 53219786f539..30a4a421ee31 100644
--- a/arch/arm/mach-shmobile/pm-rmobile.h
+++ b/arch/arm/mach-shmobile/pm-rmobile.h
@@ -26,39 +26,9 @@ struct rmobile_pm_domain {
 	bool no_debug;
 };
 
-static inline
-struct rmobile_pm_domain *to_rmobile_pd(struct generic_pm_domain *d)
-{
-	return container_of(d, struct rmobile_pm_domain, genpd);
-}
-
 struct pm_domain_device {
 	const char *domain_name;
 	struct platform_device *pdev;
 };
 
-#if defined(CONFIG_PM_RMOBILE) && defined(CONFIG_ARCH_SHMOBILE_LEGACY)
-extern void rmobile_init_domains(struct rmobile_pm_domain domains[], int num);
-extern void rmobile_add_device_to_domain_td(const char *domain_name,
-					    struct platform_device *pdev,
-					    struct gpd_timing_data *td);
-
-static inline void rmobile_add_device_to_domain(const char *domain_name,
-						struct platform_device *pdev)
-{
-	rmobile_add_device_to_domain_td(domain_name, pdev, NULL);
-}
-
-extern void rmobile_add_devices_to_domains(struct pm_domain_device data[],
-					   int size);
-#else
-
-#define rmobile_init_domains(domains, num) do { } while (0)
-#define rmobile_add_device_to_domain_td(name, pdev, td) do { } while (0)
-#define rmobile_add_device_to_domain(name, pdev) do { } while (0)
-
-static inline void rmobile_add_devices_to_domains(struct pm_domain_device d[],
-						  int size) {}
-#endif /* CONFIG_PM_RMOBILE */
-
 #endif /* PM_RMOBILE_H */
diff --git a/arch/arm/mach-shmobile/pm-sh73a0.c b/arch/arm/mach-shmobile/pm-sh73a0.c
deleted file mode 100644
index a7e466817965..000000000000
--- a/arch/arm/mach-shmobile/pm-sh73a0.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * sh73a0 Power management support
- *
- *  Copyright (C) 2012 Bastian Hecht <hechtb+renesas@gmail.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/suspend.h>
-#include "common.h"
-
-#ifdef CONFIG_SUSPEND
-static int sh73a0_enter_suspend(suspend_state_t suspend_state)
-{
-	cpu_do_idle();
-	return 0;
-}
-
-static void sh73a0_suspend_init(void)
-{
-	shmobile_suspend_ops.enter = sh73a0_enter_suspend;
-}
-#else
-static void sh73a0_suspend_init(void) {}
-#endif
-
-void __init sh73a0_pm_init(void)
-{
-	sh73a0_suspend_init();
-}
diff --git a/arch/arm/mach-shmobile/r8a7740.h b/arch/arm/mach-shmobile/r8a7740.h
deleted file mode 100644
index ca7805ad7ea3..000000000000
--- a/arch/arm/mach-shmobile/r8a7740.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __ASM_R8A7740_H__
-#define __ASM_R8A7740_H__
-
-/*
- * MD_CKx pin
- */
-#define MD_CK2	(1 << 2)
-#define MD_CK1	(1 << 1)
-#define MD_CK0	(1 << 0)
-
-/* DMA slave IDs */
-enum {
-	SHDMA_SLAVE_INVALID,
-	SHDMA_SLAVE_SDHI0_RX,
-	SHDMA_SLAVE_SDHI0_TX,
-	SHDMA_SLAVE_SDHI1_RX,
-	SHDMA_SLAVE_SDHI1_TX,
-	SHDMA_SLAVE_SDHI2_RX,
-	SHDMA_SLAVE_SDHI2_TX,
-	SHDMA_SLAVE_FSIA_RX,
-	SHDMA_SLAVE_FSIA_TX,
-	SHDMA_SLAVE_FSIB_TX,
-	SHDMA_SLAVE_USBHS_TX,
-	SHDMA_SLAVE_USBHS_RX,
-	SHDMA_SLAVE_MMCIF_TX,
-	SHDMA_SLAVE_MMCIF_RX,
-};
-
-extern void r8a7740_meram_workaround(void);
-extern void r8a7740_init_irq_of(void);
-extern void r8a7740_map_io(void);
-extern void r8a7740_add_early_devices(void);
-extern void r8a7740_add_standard_devices(void);
-extern void r8a7740_clock_init(u8 md_ck);
-extern void r8a7740_pinmux_init(void);
-extern void r8a7740_pm_init(void);
-
-#if defined(CONFIG_PM) && !defined(CONFIG_ARCH_MULTIPLATFORM)
-extern void __init r8a7740_init_pm_domains(void);
-#else
-static inline void r8a7740_init_pm_domains(void) {}
-#endif /* CONFIG_PM && !CONFIG_ARCH_MULTIPLATFORM */
-
-#endif /* __ASM_R8A7740_H__ */
diff --git a/arch/arm/mach-shmobile/r8a7779.h b/arch/arm/mach-shmobile/r8a7779.h
index 19f97046dd70..db303f76704e 100644
--- a/arch/arm/mach-shmobile/r8a7779.h
+++ b/arch/arm/mach-shmobile/r8a7779.h
@@ -3,26 +3,7 @@
 
 #include <linux/sh_clk.h>
 
-/* HPB-DMA slave IDs */
-enum {
-	HPBDMA_SLAVE_DUMMY,
-	HPBDMA_SLAVE_SDHI0_TX,
-	HPBDMA_SLAVE_SDHI0_RX,
-};
-
-extern void r8a7779_init_irq_extpin(int irlm);
-extern void r8a7779_init_irq_extpin_dt(int irlm);
-extern void r8a7779_init_irq_dt(void);
-extern void r8a7779_map_io(void);
-extern void r8a7779_earlytimer_init(void);
-extern void r8a7779_add_early_devices(void);
-extern void r8a7779_add_standard_devices(void);
-extern void r8a7779_init_late(void);
-extern u32 r8a7779_read_mode_pins(void);
-extern void r8a7779_clock_init(void);
-extern void r8a7779_pinmux_init(void);
 extern void r8a7779_pm_init(void);
-extern void r8a7779_register_twd(void);
 
 #ifdef CONFIG_PM
 extern void __init r8a7779_init_pm_domains(void);
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 384e6e934b87..62437b57813e 100644
--- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -123,7 +123,8 @@ static int __init rcar_gen2_regulator_quirk(void)
 	u32 mon;
 
 	if (!of_machine_is_compatible("renesas,koelsch") &&
-	    !of_machine_is_compatible("renesas,lager"))
+	    !of_machine_is_compatible("renesas,lager") &&
+	    !of_machine_is_compatible("renesas,gose"))
 		return -ENODEV;
 
 	irqc = ioremap(IRQC_BASE, PAGE_SIZE);
diff --git a/arch/arm/mach-shmobile/setup-r7s72100.c b/arch/arm/mach-shmobile/setup-r7s72100.c
index 171174777b6f..d46639fc6849 100644
--- a/arch/arm/mach-shmobile/setup-r7s72100.c
+++ b/arch/arm/mach-shmobile/setup-r7s72100.c
@@ -20,7 +20,7 @@
 
 #include "common.h"
 
-static const char *r7s72100_boards_compat_dt[] __initdata = {
+static const char *const r7s72100_boards_compat_dt[] __initconst = {
 	"renesas,r7s72100",
 	NULL,
 };
diff --git a/arch/arm/mach-shmobile/setup-r8a73a4.c b/arch/arm/mach-shmobile/setup-r8a73a4.c
index 446cee611902..20173c4f415d 100644
--- a/arch/arm/mach-shmobile/setup-r8a73a4.c
+++ b/arch/arm/mach-shmobile/setup-r8a73a4.c
@@ -20,7 +20,7 @@
 
 #include "common.h"
 
-static const char *r8a73a4_boards_compat_dt[] __initdata = {
+static const char *const r8a73a4_boards_compat_dt[] __initconst = {
 	"renesas,r8a73a4",
 	NULL,
 };
diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c
index 00291cc1772d..0c8f80c5b04d 100644
--- a/arch/arm/mach-shmobile/setup-r8a7740.c
+++ b/arch/arm/mach-shmobile/setup-r8a7740.c
@@ -13,31 +13,19 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  */
-#include <linux/dma-mapping.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
-#include <linux/platform_data/irq-renesas-intc-irqpin.h>
-#include <linux/platform_device.h>
 #include <linux/of_platform.h>
-#include <linux/serial_sci.h>
-#include <linux/sh_dma.h>
-#include <linux/sh_timer.h>
-#include <linux/platform_data/sh_ipmmu.h>
 
-#include <asm/mach-types.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 #include <asm/hardware/cache-l2x0.h>
 
 #include "common.h"
-#include "dma-register.h"
-#include "irqs.h"
-#include "pm-rmobile.h"
-#include "r8a7740.h"
 
 static struct map_desc r8a7740_io_desc[] __initdata = {
 	 /*
@@ -64,613 +52,12 @@ static struct map_desc r8a7740_io_desc[] __initdata = {
 #endif
 };
 
-void __init r8a7740_map_io(void)
+static void __init r8a7740_map_io(void)
 {
 	debug_ll_io_init();
 	iotable_init(r8a7740_io_desc, ARRAY_SIZE(r8a7740_io_desc));
 }
 
-/* PFC */
-static const struct resource pfc_resources[] = {
-	DEFINE_RES_MEM(0xe6050000, 0x8000),
-	DEFINE_RES_MEM(0xe605800c, 0x0020),
-};
-
-void __init r8a7740_pinmux_init(void)
-{
-	platform_device_register_simple("pfc-r8a7740", -1, pfc_resources,
-					ARRAY_SIZE(pfc_resources));
-}
-
-static struct renesas_intc_irqpin_config irqpin0_platform_data = {
-	.irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */
-};
-
-static struct resource irqpin0_resources[] = {
-	DEFINE_RES_MEM(0xe6900000, 4), /* ICR1A */
-	DEFINE_RES_MEM(0xe6900010, 4), /* INTPRI00A */
-	DEFINE_RES_MEM(0xe6900020, 1), /* INTREQ00A */
-	DEFINE_RES_MEM(0xe6900040, 1), /* INTMSK00A */
-	DEFINE_RES_MEM(0xe6900060, 1), /* INTMSKCLR00A */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ0 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ1 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ2 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ3 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ4 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ5 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ6 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ7 */
-};
-
-static struct platform_device irqpin0_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 0,
-	.resource	= irqpin0_resources,
-	.num_resources	= ARRAY_SIZE(irqpin0_resources),
-	.dev		= {
-		.platform_data  = &irqpin0_platform_data,
-	},
-};
-
-static struct renesas_intc_irqpin_config irqpin1_platform_data = {
-	.irq_base = irq_pin(8), /* IRQ8 -> IRQ15 */
-};
-
-static struct resource irqpin1_resources[] = {
-	DEFINE_RES_MEM(0xe6900004, 4), /* ICR2A */
-	DEFINE_RES_MEM(0xe6900014, 4), /* INTPRI10A */
-	DEFINE_RES_MEM(0xe6900024, 1), /* INTREQ10A */
-	DEFINE_RES_MEM(0xe6900044, 1), /* INTMSK10A */
-	DEFINE_RES_MEM(0xe6900064, 1), /* INTMSKCLR10A */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ8 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ9 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ10 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ11 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ12 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ13 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ14 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ15 */
-};
-
-static struct platform_device irqpin1_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 1,
-	.resource	= irqpin1_resources,
-	.num_resources	= ARRAY_SIZE(irqpin1_resources),
-	.dev		= {
-		.platform_data  = &irqpin1_platform_data,
-	},
-};
-
-static struct renesas_intc_irqpin_config irqpin2_platform_data = {
-	.irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */
-};
-
-static struct resource irqpin2_resources[] = {
-	DEFINE_RES_MEM(0xe6900008, 4), /* ICR3A */
-	DEFINE_RES_MEM(0xe6900018, 4), /* INTPRI30A */
-	DEFINE_RES_MEM(0xe6900028, 1), /* INTREQ30A */
-	DEFINE_RES_MEM(0xe6900048, 1), /* INTMSK30A */
-	DEFINE_RES_MEM(0xe6900068, 1), /* INTMSKCLR30A */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ16 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ17 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ18 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ19 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ20 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ21 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ22 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ23 */
-};
-
-static struct platform_device irqpin2_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 2,
-	.resource	= irqpin2_resources,
-	.num_resources	= ARRAY_SIZE(irqpin2_resources),
-	.dev		= {
-		.platform_data  = &irqpin2_platform_data,
-	},
-};
-
-static struct renesas_intc_irqpin_config irqpin3_platform_data = {
-	.irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */
-};
-
-static struct resource irqpin3_resources[] = {
-	DEFINE_RES_MEM(0xe690000c, 4), /* ICR3A */
-	DEFINE_RES_MEM(0xe690001c, 4), /* INTPRI30A */
-	DEFINE_RES_MEM(0xe690002c, 1), /* INTREQ30A */
-	DEFINE_RES_MEM(0xe690004c, 1), /* INTMSK30A */
-	DEFINE_RES_MEM(0xe690006c, 1), /* INTMSKCLR30A */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ24 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ25 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ26 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ27 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ28 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ29 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ30 */
-	DEFINE_RES_IRQ(gic_spi(149)), /* IRQ31 */
-};
-
-static struct platform_device irqpin3_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 3,
-	.resource	= irqpin3_resources,
-	.num_resources	= ARRAY_SIZE(irqpin3_resources),
-	.dev		= {
-		.platform_data  = &irqpin3_platform_data,
-	},
-};
-
-/* SCIF */
-#define R8A7740_SCIF(scif_type, index, baseaddr, irq)		\
-static struct plat_sci_port scif##index##_platform_data = {	\
-	.type		= scif_type,				\
-	.flags		= UPF_BOOT_AUTOCONF,			\
-	.scscr		= SCSCR_RE | SCSCR_TE,			\
-};								\
-								\
-static struct resource scif##index##_resources[] = {		\
-	DEFINE_RES_MEM(baseaddr, 0x100),			\
-	DEFINE_RES_IRQ(irq),					\
-};								\
-								\
-static struct platform_device scif##index##_device = {		\
-	.name		= "sh-sci",				\
-	.id		= index,				\
-	.resource	= scif##index##_resources,		\
-	.num_resources	= ARRAY_SIZE(scif##index##_resources),	\
-	.dev		= {					\
-		.platform_data	= &scif##index##_platform_data,	\
-	},							\
-}
-
-R8A7740_SCIF(PORT_SCIFA, 0, 0xe6c40000, gic_spi(100));
-R8A7740_SCIF(PORT_SCIFA, 1, 0xe6c50000, gic_spi(101));
-R8A7740_SCIF(PORT_SCIFA, 2, 0xe6c60000, gic_spi(102));
-R8A7740_SCIF(PORT_SCIFA, 3, 0xe6c70000, gic_spi(103));
-R8A7740_SCIF(PORT_SCIFA, 4, 0xe6c80000, gic_spi(104));
-R8A7740_SCIF(PORT_SCIFA, 5, 0xe6cb0000, gic_spi(105));
-R8A7740_SCIF(PORT_SCIFA, 6, 0xe6cc0000, gic_spi(106));
-R8A7740_SCIF(PORT_SCIFA, 7, 0xe6cd0000, gic_spi(107));
-R8A7740_SCIF(PORT_SCIFB, 8, 0xe6c30000, gic_spi(108));
-
-/* CMT */
-static struct sh_timer_config cmt1_platform_data = {
-	.channels_mask = 0x3f,
-};
-
-static struct resource cmt1_resources[] = {
-	DEFINE_RES_MEM(0xe6138000, 0x170),
-	DEFINE_RES_IRQ(gic_spi(58)),
-};
-
-static struct platform_device cmt1_device = {
-	.name		= "sh-cmt-48",
-	.id		= 1,
-	.dev = {
-		.platform_data	= &cmt1_platform_data,
-	},
-	.resource	= cmt1_resources,
-	.num_resources	= ARRAY_SIZE(cmt1_resources),
-};
-
-/* TMU */
-static struct sh_timer_config tmu0_platform_data = {
-	.channels_mask = 7,
-};
-
-static struct resource tmu0_resources[] = {
-	DEFINE_RES_MEM(0xfff80000, 0x2c),
-	DEFINE_RES_IRQ(gic_spi(198)),
-	DEFINE_RES_IRQ(gic_spi(199)),
-	DEFINE_RES_IRQ(gic_spi(200)),
-};
-
-static struct platform_device tmu0_device = {
-	.name		= "sh-tmu",
-	.id		= 0,
-	.dev = {
-		.platform_data	= &tmu0_platform_data,
-	},
-	.resource	= tmu0_resources,
-	.num_resources	= ARRAY_SIZE(tmu0_resources),
-};
-
-/* IPMMUI (an IPMMU module for ICB/LMB) */
-static struct resource ipmmu_resources[] = {
-	[0] = {
-		.name	= "IPMMUI",
-		.start	= 0xfe951000,
-		.end	= 0xfe9510ff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static const char * const ipmmu_dev_names[] = {
-	"sh_mobile_lcdc_fb.0",
-	"sh_mobile_lcdc_fb.1",
-	"sh_mobile_ceu.0",
-};
-
-static struct shmobile_ipmmu_platform_data ipmmu_platform_data = {
-	.dev_names = ipmmu_dev_names,
-	.num_dev_names = ARRAY_SIZE(ipmmu_dev_names),
-};
-
-static struct platform_device ipmmu_device = {
-	.name           = "ipmmu",
-	.id             = -1,
-	.dev = {
-		.platform_data = &ipmmu_platform_data,
-	},
-	.resource       = ipmmu_resources,
-	.num_resources  = ARRAY_SIZE(ipmmu_resources),
-};
-
-static struct platform_device *r8a7740_early_devices[] __initdata = {
-	&scif0_device,
-	&scif1_device,
-	&scif2_device,
-	&scif3_device,
-	&scif4_device,
-	&scif5_device,
-	&scif6_device,
-	&scif7_device,
-	&scif8_device,
-	&irqpin0_device,
-	&irqpin1_device,
-	&irqpin2_device,
-	&irqpin3_device,
-	&tmu0_device,
-	&ipmmu_device,
-	&cmt1_device,
-};
-
-/* DMA */
-static const struct sh_dmae_slave_config r8a7740_dmae_slaves[] = {
-	{
-		.slave_id	= SHDMA_SLAVE_SDHI0_TX,
-		.addr		= 0xe6850030,
-		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xc1,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI0_RX,
-		.addr		= 0xe6850030,
-		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xc2,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI1_TX,
-		.addr		= 0xe6860030,
-		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xc9,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI1_RX,
-		.addr		= 0xe6860030,
-		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xca,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI2_TX,
-		.addr		= 0xe6870030,
-		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xcd,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI2_RX,
-		.addr		= 0xe6870030,
-		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xce,
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSIA_TX,
-		.addr		= 0xfe1f0024,
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xb1,
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSIA_RX,
-		.addr		= 0xfe1f0020,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xb2,
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSIB_TX,
-		.addr		= 0xfe1f0064,
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xb5,
-	}, {
-		.slave_id	= SHDMA_SLAVE_MMCIF_TX,
-		.addr		= 0xe6bd0034,
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd1,
-	}, {
-		.slave_id	= SHDMA_SLAVE_MMCIF_RX,
-		.addr		= 0xe6bd0034,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd2,
-	},
-};
-
-#define DMA_CHANNEL(a, b, c)			\
-{						\
-	.offset		= a,			\
-	.dmars		= b,			\
-	.dmars_bit	= c,			\
-	.chclr_offset	= (0x220 - 0x20) + a	\
-}
-
-static const struct sh_dmae_channel r8a7740_dmae_channels[] = {
-	DMA_CHANNEL(0x00, 0, 0),
-	DMA_CHANNEL(0x10, 0, 8),
-	DMA_CHANNEL(0x20, 4, 0),
-	DMA_CHANNEL(0x30, 4, 8),
-	DMA_CHANNEL(0x50, 8, 0),
-	DMA_CHANNEL(0x60, 8, 8),
-};
-
-static struct sh_dmae_pdata dma_platform_data = {
-	.slave		= r8a7740_dmae_slaves,
-	.slave_num	= ARRAY_SIZE(r8a7740_dmae_slaves),
-	.channel	= r8a7740_dmae_channels,
-	.channel_num	= ARRAY_SIZE(r8a7740_dmae_channels),
-	.ts_low_shift	= TS_LOW_SHIFT,
-	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
-	.ts_high_shift	= TS_HI_SHIFT,
-	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
-	.ts_shift	= dma_ts_shift,
-	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
-	.dmaor_init	= DMAOR_DME,
-	.chclr_present	= 1,
-};
-
-/* Resource order important! */
-static struct resource r8a7740_dmae0_resources[] = {
-	{
-		/* Channel registers and DMAOR */
-		.start	= 0xfe008020,
-		.end	= 0xfe00828f,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		/* DMARSx */
-		.start	= 0xfe009000,
-		.end	= 0xfe00900b,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		.name	= "error_irq",
-		.start	= gic_spi(34),
-		.end	= gic_spi(34),
-		.flags	= IORESOURCE_IRQ,
-	},
-	{
-		/* IRQ for channels 0-5 */
-		.start	= gic_spi(28),
-		.end	= gic_spi(33),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-/* Resource order important! */
-static struct resource r8a7740_dmae1_resources[] = {
-	{
-		/* Channel registers and DMAOR */
-		.start	= 0xfe018020,
-		.end	= 0xfe01828f,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		/* DMARSx */
-		.start	= 0xfe019000,
-		.end	= 0xfe01900b,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		.name	= "error_irq",
-		.start	= gic_spi(41),
-		.end	= gic_spi(41),
-		.flags	= IORESOURCE_IRQ,
-	},
-	{
-		/* IRQ for channels 0-5 */
-		.start	= gic_spi(35),
-		.end	= gic_spi(40),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-/* Resource order important! */
-static struct resource r8a7740_dmae2_resources[] = {
-	{
-		/* Channel registers and DMAOR */
-		.start	= 0xfe028020,
-		.end	= 0xfe02828f,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		/* DMARSx */
-		.start	= 0xfe029000,
-		.end	= 0xfe02900b,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		.name	= "error_irq",
-		.start	= gic_spi(48),
-		.end	= gic_spi(48),
-		.flags	= IORESOURCE_IRQ,
-	},
-	{
-		/* IRQ for channels 0-5 */
-		.start	= gic_spi(42),
-		.end	= gic_spi(47),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device dma0_device = {
-	.name		= "sh-dma-engine",
-	.id		= 0,
-	.resource	= r8a7740_dmae0_resources,
-	.num_resources	= ARRAY_SIZE(r8a7740_dmae0_resources),
-	.dev		= {
-		.platform_data	= &dma_platform_data,
-	},
-};
-
-static struct platform_device dma1_device = {
-	.name		= "sh-dma-engine",
-	.id		= 1,
-	.resource	= r8a7740_dmae1_resources,
-	.num_resources	= ARRAY_SIZE(r8a7740_dmae1_resources),
-	.dev		= {
-		.platform_data	= &dma_platform_data,
-	},
-};
-
-static struct platform_device dma2_device = {
-	.name		= "sh-dma-engine",
-	.id		= 2,
-	.resource	= r8a7740_dmae2_resources,
-	.num_resources	= ARRAY_SIZE(r8a7740_dmae2_resources),
-	.dev		= {
-		.platform_data	= &dma_platform_data,
-	},
-};
-
-/* USB-DMAC */
-static const struct sh_dmae_channel r8a7740_usb_dma_channels[] = {
-	{
-		.offset = 0,
-	}, {
-		.offset = 0x20,
-	},
-};
-
-static const struct sh_dmae_slave_config r8a7740_usb_dma_slaves[] = {
-	{
-		.slave_id	= SHDMA_SLAVE_USBHS_TX,
-		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
-	}, {
-		.slave_id	= SHDMA_SLAVE_USBHS_RX,
-		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
-	},
-};
-
-static struct sh_dmae_pdata usb_dma_platform_data = {
-	.slave		= r8a7740_usb_dma_slaves,
-	.slave_num	= ARRAY_SIZE(r8a7740_usb_dma_slaves),
-	.channel	= r8a7740_usb_dma_channels,
-	.channel_num	= ARRAY_SIZE(r8a7740_usb_dma_channels),
-	.ts_low_shift	= USBTS_LOW_SHIFT,
-	.ts_low_mask	= USBTS_LOW_BIT << USBTS_LOW_SHIFT,
-	.ts_high_shift	= USBTS_HI_SHIFT,
-	.ts_high_mask	= USBTS_HI_BIT << USBTS_HI_SHIFT,
-	.ts_shift	= dma_usbts_shift,
-	.ts_shift_num	= ARRAY_SIZE(dma_usbts_shift),
-	.dmaor_init	= DMAOR_DME,
-	.chcr_offset	= 0x14,
-	.chcr_ie_bit	= 1 << 5,
-	.dmaor_is_32bit	= 1,
-	.needs_tend_set	= 1,
-	.no_dmars	= 1,
-	.slave_only	= 1,
-};
-
-static struct resource r8a7740_usb_dma_resources[] = {
-	{
-		/* Channel registers and DMAOR */
-		.start	= 0xe68a0020,
-		.end	= 0xe68a0064 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		/* VCR/SWR/DMICR */
-		.start	= 0xe68a0000,
-		.end	= 0xe68a0014 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		/* IRQ for channels */
-		.start	= gic_spi(49),
-		.end	= gic_spi(49),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device usb_dma_device = {
-	.name		= "sh-dma-engine",
-	.id		= 3,
-	.resource	= r8a7740_usb_dma_resources,
-	.num_resources	= ARRAY_SIZE(r8a7740_usb_dma_resources),
-	.dev		= {
-		.platform_data	= &usb_dma_platform_data,
-	},
-};
-
-/* I2C */
-static struct resource i2c0_resources[] = {
-	[0] = {
-		.name	= "IIC0",
-		.start	= 0xfff20000,
-		.end	= 0xfff20425 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(201),
-		.end	= gic_spi(204),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource i2c1_resources[] = {
-	[0] = {
-		.name	= "IIC1",
-		.start	= 0xe6c20000,
-		.end	= 0xe6c20425 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(70), /* IIC1_ALI1 */
-		.end    = gic_spi(73), /* IIC1_DTEI1 */
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device i2c0_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 0,
-	.resource	= i2c0_resources,
-	.num_resources	= ARRAY_SIZE(i2c0_resources),
-};
-
-static struct platform_device i2c1_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 1,
-	.resource	= i2c1_resources,
-	.num_resources	= ARRAY_SIZE(i2c1_resources),
-};
-
-static struct resource pmu_resources[] = {
-	[0] = {
-		.start	= gic_spi(83),
-		.end	= gic_spi(83),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device pmu_device = {
-	.name	= "armv7-pmu",
-	.id	= -1,
-	.num_resources = ARRAY_SIZE(pmu_resources),
-	.resource = pmu_resources,
-};
-
-static struct platform_device *r8a7740_late_devices[] __initdata = {
-	&i2c0_device,
-	&i2c1_device,
-	&dma0_device,
-	&dma1_device,
-	&dma2_device,
-	&usb_dma_device,
-	&pmu_device,
-};
-
 /*
  * r8a7740 chip has lasting errata on MERAM buffer.
  * this is work-around for it.
@@ -678,7 +65,7 @@ static struct platform_device *r8a7740_late_devices[] __initdata = {
  *	"Media RAM (MERAM)" on r8a7740 documentation
  */
 #define MEBUFCNTR	0xFE950098
-void __init r8a7740_meram_workaround(void)
+static void __init r8a7740_meram_workaround(void)
 {
 	void __iomem *reg;
 
@@ -689,70 +76,13 @@ void __init r8a7740_meram_workaround(void)
 	}
 }
 
-void __init r8a7740_add_standard_devices(void)
-{
-	static struct pm_domain_device domain_devices[] __initdata = {
-		{ "A4R",  &tmu0_device },
-		{ "A4R",  &i2c0_device },
-		{ "A4S",  &irqpin0_device },
-		{ "A4S",  &irqpin1_device },
-		{ "A4S",  &irqpin2_device },
-		{ "A4S",  &irqpin3_device },
-		{ "A3SP", &scif0_device },
-		{ "A3SP", &scif1_device },
-		{ "A3SP", &scif2_device },
-		{ "A3SP", &scif3_device },
-		{ "A3SP", &scif4_device },
-		{ "A3SP", &scif5_device },
-		{ "A3SP", &scif6_device },
-		{ "A3SP", &scif7_device },
-		{ "A3SP", &scif8_device },
-		{ "A3SP", &i2c1_device },
-		{ "A3SP", &ipmmu_device },
-		{ "A3SP", &dma0_device },
-		{ "A3SP", &dma1_device },
-		{ "A3SP", &dma2_device },
-		{ "A3SP", &usb_dma_device },
-	};
-
-	r8a7740_init_pm_domains();
-
-	/* add devices */
-	platform_add_devices(r8a7740_early_devices,
-			    ARRAY_SIZE(r8a7740_early_devices));
-	platform_add_devices(r8a7740_late_devices,
-			     ARRAY_SIZE(r8a7740_late_devices));
-
-	/* add devices to PM domain  */
-	rmobile_add_devices_to_domains(domain_devices,
-				       ARRAY_SIZE(domain_devices));
-}
-
-void __init r8a7740_add_early_devices(void)
-{
-	early_platform_add_devices(r8a7740_early_devices,
-				   ARRAY_SIZE(r8a7740_early_devices));
-
-	/* setup early console here as well */
-	shmobile_setup_console();
-}
-
-#ifdef CONFIG_USE_OF
-
-void __init r8a7740_init_irq_of(void)
+static void __init r8a7740_init_irq_of(void)
 {
 	void __iomem *intc_prio_base = ioremap_nocache(0xe6900010, 0x10);
 	void __iomem *intc_msk_base = ioremap_nocache(0xe6900040, 0x10);
 	void __iomem *pfc_inta_ctrl = ioremap_nocache(0xe605807c, 0x4);
 
-#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
-	void __iomem *gic_dist_base = ioremap_nocache(0xc2800000, 0x1000);
-	void __iomem *gic_cpu_base = ioremap_nocache(0xc2000000, 0x1000);
-
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-#else
 	irqchip_init();
-#endif
 
 	/* route signals to GIC */
 	iowrite32(0x0, pfc_inta_ctrl);
@@ -787,7 +117,7 @@ static void __init r8a7740_generic_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static const char *r8a7740_boards_compat_dt[] __initdata = {
+static const char *const r8a7740_boards_compat_dt[] __initconst = {
 	"renesas,r8a7740",
 	NULL,
 };
@@ -800,5 +130,3 @@ DT_MACHINE_START(R8A7740_DT, "Generic R8A7740 (Flattened Device Tree)")
 	.init_late	= shmobile_init_late,
 	.dt_compat	= r8a7740_boards_compat_dt,
 MACHINE_END
-
-#endif /* CONFIG_USE_OF */
diff --git a/arch/arm/mach-shmobile/setup-r8a7778.c b/arch/arm/mach-shmobile/setup-r8a7778.c
index c49aa094fe17..b9116c81e54b 100644
--- a/arch/arm/mach-shmobile/setup-r8a7778.c
+++ b/arch/arm/mach-shmobile/setup-r8a7778.c
@@ -615,7 +615,7 @@ void __init r8a7778_init_irq_dt(void)
 	iounmap(base);
 }
 
-static const char *r8a7778_compat_dt[] __initdata = {
+static const char *const r8a7778_compat_dt[] __initconst = {
 	"renesas,r8a7778",
 	NULL,
 };
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index c03e562be12b..6bfa6407a27c 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -14,37 +14,17 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  */
-#include <linux/kernel.h>
+#include <linux/clk/shmobile.h>
+#include <linux/clocksource.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
-#include <linux/of_platform.h>
-#include <linux/platform_data/dma-rcar-hpbdma.h>
-#include <linux/platform_data/gpio-rcar.h>
-#include <linux/platform_data/irq-renesas-intc-irqpin.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/input.h>
-#include <linux/io.h>
-#include <linux/serial_sci.h>
-#include <linux/sh_timer.h>
-#include <linux/dma-mapping.h>
-#include <linux/usb/otg.h>
-#include <linux/usb/hcd.h>
-#include <linux/usb/ehci_pdriver.h>
-#include <linux/usb/ohci_pdriver.h>
-#include <linux/pm_runtime.h>
 
-#include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/mach/time.h>
 #include <asm/mach/map.h>
-#include <asm/hardware/cache-l2x0.h>
 
 #include "common.h"
-#include "irqs.h"
 #include "r8a7779.h"
 
 static struct map_desc r8a7779_io_desc[] __initdata = {
@@ -64,7 +44,7 @@ static struct map_desc r8a7779_io_desc[] __initdata = {
 	},
 };
 
-void __init r8a7779_map_io(void)
+static void __init r8a7779_map_io(void)
 {
 	debug_ll_io_init();
 	iotable_init(r8a7779_io_desc, ARRAY_SIZE(r8a7779_io_desc));
@@ -80,652 +60,10 @@ void __init r8a7779_map_io(void)
 #define INT2NTSR0 IOMEM(0xfe700060)
 #define INT2NTSR1 IOMEM(0xfe700064)
 
-static struct renesas_intc_irqpin_config irqpin0_platform_data __initdata = {
-	.irq_base = irq_pin(0), /* IRQ0 -> IRQ3 */
-	.sense_bitfield_width = 2,
-};
-
-static struct resource irqpin0_resources[] __initdata = {
-	DEFINE_RES_MEM(0xfe78001c, 4), /* ICR1 */
-	DEFINE_RES_MEM(0xfe780010, 4), /* INTPRI */
-	DEFINE_RES_MEM(0xfe780024, 4), /* INTREQ */
-	DEFINE_RES_MEM(0xfe780044, 4), /* INTMSK0 */
-	DEFINE_RES_MEM(0xfe780064, 4), /* INTMSKCLR0 */
-	DEFINE_RES_IRQ(gic_spi(27)), /* IRQ0 */
-	DEFINE_RES_IRQ(gic_spi(28)), /* IRQ1 */
-	DEFINE_RES_IRQ(gic_spi(29)), /* IRQ2 */
-	DEFINE_RES_IRQ(gic_spi(30)), /* IRQ3 */
-};
-
-void __init r8a7779_init_irq_extpin_dt(int irlm)
-{
-	void __iomem *icr0 = ioremap_nocache(0xfe780000, PAGE_SIZE);
-	u32 tmp;
-
-	if (!icr0) {
-		pr_warn("r8a7779: unable to setup external irq pin mode\n");
-		return;
-	}
-
-	tmp = ioread32(icr0);
-	if (irlm)
-		tmp |= 1 << 23; /* IRQ0 -> IRQ3 as individual pins */
-	else
-		tmp &= ~(1 << 23); /* IRL mode - not supported */
-	tmp |= (1 << 21); /* LVLMODE = 1 */
-	iowrite32(tmp, icr0);
-	iounmap(icr0);
-}
-
-void __init r8a7779_init_irq_extpin(int irlm)
-{
-	r8a7779_init_irq_extpin_dt(irlm);
-	if (irlm)
-		platform_device_register_resndata(
-			NULL, "renesas_intc_irqpin", -1,
-			irqpin0_resources, ARRAY_SIZE(irqpin0_resources),
-			&irqpin0_platform_data, sizeof(irqpin0_platform_data));
-}
-
-/* PFC/GPIO */
-static struct resource r8a7779_pfc_resources[] = {
-	DEFINE_RES_MEM(0xfffc0000, 0x023c),
-};
-
-static struct platform_device r8a7779_pfc_device = {
-	.name		= "pfc-r8a7779",
-	.id		= -1,
-	.resource	= r8a7779_pfc_resources,
-	.num_resources	= ARRAY_SIZE(r8a7779_pfc_resources),
-};
-
-#define R8A7779_GPIO(idx, npins) \
-static struct resource r8a7779_gpio##idx##_resources[] = {		\
-	DEFINE_RES_MEM(0xffc40000 + (0x1000 * (idx)), 0x002c),		\
-	DEFINE_RES_IRQ(gic_iid(0xad + (idx))),				\
-};									\
-									\
-static struct gpio_rcar_config r8a7779_gpio##idx##_platform_data = {	\
-	.gpio_base	= 32 * (idx),					\
-	.irq_base	= 0,						\
-	.number_of_pins	= npins,					\
-	.pctl_name	= "pfc-r8a7779",				\
-};									\
-									\
-static struct platform_device r8a7779_gpio##idx##_device = {		\
-	.name		= "gpio_rcar",					\
-	.id		= idx,						\
-	.resource	= r8a7779_gpio##idx##_resources,		\
-	.num_resources	= ARRAY_SIZE(r8a7779_gpio##idx##_resources),	\
-	.dev		= {						\
-		.platform_data	= &r8a7779_gpio##idx##_platform_data,	\
-	},								\
-}
-
-R8A7779_GPIO(0, 32);
-R8A7779_GPIO(1, 32);
-R8A7779_GPIO(2, 32);
-R8A7779_GPIO(3, 32);
-R8A7779_GPIO(4, 32);
-R8A7779_GPIO(5, 32);
-R8A7779_GPIO(6, 9);
-
-static struct platform_device *r8a7779_pinctrl_devices[] __initdata = {
-	&r8a7779_pfc_device,
-	&r8a7779_gpio0_device,
-	&r8a7779_gpio1_device,
-	&r8a7779_gpio2_device,
-	&r8a7779_gpio3_device,
-	&r8a7779_gpio4_device,
-	&r8a7779_gpio5_device,
-	&r8a7779_gpio6_device,
-};
-
-void __init r8a7779_pinmux_init(void)
-{
-	platform_add_devices(r8a7779_pinctrl_devices,
-			    ARRAY_SIZE(r8a7779_pinctrl_devices));
-}
-
-/* SCIF */
-#define R8A7779_SCIF(index, baseaddr, irq)			\
-static struct plat_sci_port scif##index##_platform_data = {	\
-	.type		= PORT_SCIF,				\
-	.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,	\
-	.scscr		= SCSCR_RE | SCSCR_TE | SCSCR_CKE1,	\
-};								\
-								\
-static struct resource scif##index##_resources[] = {		\
-	DEFINE_RES_MEM(baseaddr, 0x100),			\
-	DEFINE_RES_IRQ(irq),					\
-};								\
-								\
-static struct platform_device scif##index##_device = {		\
-	.name		= "sh-sci",				\
-	.id		= index,				\
-	.resource	= scif##index##_resources,		\
-	.num_resources	= ARRAY_SIZE(scif##index##_resources),	\
-	.dev		= {					\
-		.platform_data	= &scif##index##_platform_data,	\
-	},							\
-}
-
-R8A7779_SCIF(0, 0xffe40000, gic_iid(0x78));
-R8A7779_SCIF(1, 0xffe41000, gic_iid(0x79));
-R8A7779_SCIF(2, 0xffe42000, gic_iid(0x7a));
-R8A7779_SCIF(3, 0xffe43000, gic_iid(0x7b));
-R8A7779_SCIF(4, 0xffe44000, gic_iid(0x7c));
-R8A7779_SCIF(5, 0xffe45000, gic_iid(0x7d));
-
-/* TMU */
-static struct sh_timer_config tmu0_platform_data = {
-	.channels_mask = 7,
-};
-
-static struct resource tmu0_resources[] = {
-	DEFINE_RES_MEM(0xffd80000, 0x30),
-	DEFINE_RES_IRQ(gic_iid(0x40)),
-	DEFINE_RES_IRQ(gic_iid(0x41)),
-	DEFINE_RES_IRQ(gic_iid(0x42)),
-};
-
-static struct platform_device tmu0_device = {
-	.name		= "sh-tmu",
-	.id		= 0,
-	.dev = {
-		.platform_data	= &tmu0_platform_data,
-	},
-	.resource	= tmu0_resources,
-	.num_resources	= ARRAY_SIZE(tmu0_resources),
-};
-
-/* I2C */
-static struct resource rcar_i2c0_res[] = {
-	{
-		.start  = 0xffc70000,
-		.end    = 0xffc70fff,
-		.flags  = IORESOURCE_MEM,
-	}, {
-		.start  = gic_iid(0x6f),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device i2c0_device = {
-	.name		= "i2c-rcar",
-	.id		= 0,
-	.resource	= rcar_i2c0_res,
-	.num_resources	= ARRAY_SIZE(rcar_i2c0_res),
-};
-
-static struct resource rcar_i2c1_res[] = {
-	{
-		.start  = 0xffc71000,
-		.end    = 0xffc71fff,
-		.flags  = IORESOURCE_MEM,
-	}, {
-		.start  = gic_iid(0x72),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device i2c1_device = {
-	.name		= "i2c-rcar",
-	.id		= 1,
-	.resource	= rcar_i2c1_res,
-	.num_resources	= ARRAY_SIZE(rcar_i2c1_res),
-};
-
-static struct resource rcar_i2c2_res[] = {
-	{
-		.start  = 0xffc72000,
-		.end    = 0xffc72fff,
-		.flags  = IORESOURCE_MEM,
-	}, {
-		.start  = gic_iid(0x70),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device i2c2_device = {
-	.name		= "i2c-rcar",
-	.id		= 2,
-	.resource	= rcar_i2c2_res,
-	.num_resources	= ARRAY_SIZE(rcar_i2c2_res),
-};
-
-static struct resource rcar_i2c3_res[] = {
-	{
-		.start  = 0xffc73000,
-		.end    = 0xffc73fff,
-		.flags  = IORESOURCE_MEM,
-	}, {
-		.start  = gic_iid(0x71),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device i2c3_device = {
-	.name		= "i2c-rcar",
-	.id		= 3,
-	.resource	= rcar_i2c3_res,
-	.num_resources	= ARRAY_SIZE(rcar_i2c3_res),
-};
-
-static struct resource sata_resources[] = {
-	[0] = {
-		.name	= "rcar-sata",
-		.start	= 0xfc600000,
-		.end	= 0xfc601fff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_iid(0x84),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sata_device = {
-	.name		= "sata_rcar",
-	.id		= -1,
-	.resource	= sata_resources,
-	.num_resources	= ARRAY_SIZE(sata_resources),
-	.dev		= {
-		.dma_mask		= &sata_device.dev.coherent_dma_mask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-	},
-};
-
-/* USB */
-static struct usb_phy *phy;
-
-static int usb_power_on(struct platform_device *pdev)
-{
-	if (IS_ERR(phy))
-		return PTR_ERR(phy);
-
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
-
-	usb_phy_init(phy);
-
-	return 0;
-}
-
-static void usb_power_off(struct platform_device *pdev)
-{
-	if (IS_ERR(phy))
-		return;
-
-	usb_phy_shutdown(phy);
-
-	pm_runtime_put_sync(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
-}
-
-static int ehci_init_internal_buffer(struct usb_hcd *hcd)
+static void __init r8a7779_init_irq_dt(void)
 {
-	/*
-	 * Below are recommended values from the datasheet;
-	 * see [USB :: Setting of EHCI Internal Buffer].
-	 */
-	/* EHCI IP internal buffer setting */
-	iowrite32(0x00ff0040, hcd->regs + 0x0094);
-	/* EHCI IP internal buffer enable */
-	iowrite32(0x00000001, hcd->regs + 0x009C);
-
-	return 0;
-}
-
-static struct usb_ehci_pdata ehcix_pdata = {
-	.power_on	= usb_power_on,
-	.power_off	= usb_power_off,
-	.power_suspend	= usb_power_off,
-	.pre_setup	= ehci_init_internal_buffer,
-};
-
-static struct resource ehci0_resources[] = {
-	[0] = {
-		.start	= 0xffe70000,
-		.end	= 0xffe70400 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_iid(0x4c),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device ehci0_device = {
-	.name	= "ehci-platform",
-	.id	= 0,
-	.dev	= {
-		.dma_mask		= &ehci0_device.dev.coherent_dma_mask,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &ehcix_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(ehci0_resources),
-	.resource	= ehci0_resources,
-};
-
-static struct resource ehci1_resources[] = {
-	[0] = {
-		.start	= 0xfff70000,
-		.end	= 0xfff70400 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_iid(0x4d),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device ehci1_device = {
-	.name	= "ehci-platform",
-	.id	= 1,
-	.dev	= {
-		.dma_mask		= &ehci1_device.dev.coherent_dma_mask,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &ehcix_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(ehci1_resources),
-	.resource	= ehci1_resources,
-};
-
-static struct usb_ohci_pdata ohcix_pdata = {
-	.power_on	= usb_power_on,
-	.power_off	= usb_power_off,
-	.power_suspend	= usb_power_off,
-};
-
-static struct resource ohci0_resources[] = {
-	[0] = {
-		.start	= 0xffe70400,
-		.end	= 0xffe70800 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_iid(0x4c),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device ohci0_device = {
-	.name	= "ohci-platform",
-	.id	= 0,
-	.dev	= {
-		.dma_mask		= &ohci0_device.dev.coherent_dma_mask,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &ohcix_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(ohci0_resources),
-	.resource	= ohci0_resources,
-};
-
-static struct resource ohci1_resources[] = {
-	[0] = {
-		.start	= 0xfff70400,
-		.end	= 0xfff70800 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_iid(0x4d),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device ohci1_device = {
-	.name	= "ohci-platform",
-	.id	= 1,
-	.dev	= {
-		.dma_mask		= &ohci1_device.dev.coherent_dma_mask,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &ohcix_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(ohci1_resources),
-	.resource	= ohci1_resources,
-};
-
-/* HPB-DMA */
-
-/* Asynchronous mode register bits */
-#define HPB_DMAE_ASYNCMDR_ASMD43_MASK		BIT(23)	/* MMC1 */
-#define HPB_DMAE_ASYNCMDR_ASMD43_SINGLE		BIT(23)	/* MMC1 */
-#define HPB_DMAE_ASYNCMDR_ASMD43_MULTI		0	/* MMC1 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD43_MASK		BIT(22)	/* MMC1 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD43_BURST	BIT(22)	/* MMC1 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD43_NBURST	0	/* MMC1 */
-#define HPB_DMAE_ASYNCMDR_ASMD24_MASK		BIT(21)	/* MMC0 */
-#define HPB_DMAE_ASYNCMDR_ASMD24_SINGLE		BIT(21)	/* MMC0 */
-#define HPB_DMAE_ASYNCMDR_ASMD24_MULTI		0	/* MMC0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD24_MASK		BIT(20)	/* MMC0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD24_BURST	BIT(20)	/* MMC0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD24_NBURST	0	/* MMC0 */
-#define HPB_DMAE_ASYNCMDR_ASMD41_MASK		BIT(19)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD41_SINGLE		BIT(19)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD41_MULTI		0	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD41_MASK		BIT(18)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD41_BURST	BIT(18)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD41_NBURST	0	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD40_MASK		BIT(17)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD40_SINGLE		BIT(17)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD40_MULTI		0	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD40_MASK		BIT(16)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD40_BURST	BIT(16)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD40_NBURST	0	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD39_MASK		BIT(15)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD39_SINGLE		BIT(15)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD39_MULTI		0	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD39_MASK		BIT(14)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD39_BURST	BIT(14)	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD39_NBURST	0	/* SDHI3 */
-#define HPB_DMAE_ASYNCMDR_ASMD27_MASK		BIT(13)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD27_SINGLE		BIT(13)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD27_MULTI		0	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD27_MASK		BIT(12)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD27_BURST	BIT(12)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD27_NBURST	0	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD26_MASK		BIT(11)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD26_SINGLE		BIT(11)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD26_MULTI		0	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD26_MASK		BIT(10)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD26_BURST	BIT(10)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD26_NBURST	0	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD25_MASK		BIT(9)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD25_SINGLE		BIT(9)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD25_MULTI		0	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD25_MASK		BIT(8)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD25_BURST	BIT(8)	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD25_NBURST	0	/* SDHI2 */
-#define HPB_DMAE_ASYNCMDR_ASMD23_MASK		BIT(7)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD23_SINGLE		BIT(7)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD23_MULTI		0	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD23_MASK		BIT(6)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD23_BURST	BIT(6)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD23_NBURST	0	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD22_MASK		BIT(5)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD22_SINGLE		BIT(5)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD22_MULTI		0	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD22_MASK		BIT(4)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD22_BURST	BIT(4)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD22_NBURST	0	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD21_MASK		BIT(3)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD21_SINGLE		BIT(3)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD21_MULTI		0	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD21_MASK		BIT(2)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD21_BURST	BIT(2)	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD21_NBURST	0	/* SDHI0 */
-#define HPB_DMAE_ASYNCMDR_ASMD20_MASK		BIT(1)	/* SDHI1 */
-#define HPB_DMAE_ASYNCMDR_ASMD20_SINGLE		BIT(1)	/* SDHI1 */
-#define HPB_DMAE_ASYNCMDR_ASMD20_MULTI		0	/* SDHI1 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD20_MASK		BIT(0)	/* SDHI1 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD20_BURST	BIT(0)	/* SDHI1 */
-#define HPB_DMAE_ASYNCMDR_ASBTMD20_NBURST	0	/* SDHI1 */
-
-static const struct hpb_dmae_slave_config hpb_dmae_slaves[] = {
-	{
-		.id	= HPBDMA_SLAVE_SDHI0_TX,
-		.addr	= 0xffe4c000 + 0x30,
-		.dcr	= HPB_DMAE_DCR_SPDS_16BIT |
-			  HPB_DMAE_DCR_DMDL |
-			  HPB_DMAE_DCR_DPDS_16BIT,
-		.rstr	= HPB_DMAE_ASYNCRSTR_ASRST21 |
-			  HPB_DMAE_ASYNCRSTR_ASRST22 |
-			  HPB_DMAE_ASYNCRSTR_ASRST23,
-		.mdr	= HPB_DMAE_ASYNCMDR_ASMD21_SINGLE |
-			  HPB_DMAE_ASYNCMDR_ASBTMD21_NBURST,
-		.mdm	= HPB_DMAE_ASYNCMDR_ASMD21_MASK |
-			  HPB_DMAE_ASYNCMDR_ASBTMD21_MASK,
-		.port	= 0x0D0C,
-		.flags	= HPB_DMAE_SET_ASYNC_RESET | HPB_DMAE_SET_ASYNC_MODE,
-		.dma_ch	= 21,
-	}, {
-		.id	= HPBDMA_SLAVE_SDHI0_RX,
-		.addr	= 0xffe4c000 + 0x30,
-		.dcr	= HPB_DMAE_DCR_SMDL |
-			  HPB_DMAE_DCR_SPDS_16BIT |
-			  HPB_DMAE_DCR_DPDS_16BIT,
-		.rstr	= HPB_DMAE_ASYNCRSTR_ASRST21 |
-			  HPB_DMAE_ASYNCRSTR_ASRST22 |
-			  HPB_DMAE_ASYNCRSTR_ASRST23,
-		.mdr	= HPB_DMAE_ASYNCMDR_ASMD22_SINGLE |
-			  HPB_DMAE_ASYNCMDR_ASBTMD22_NBURST,
-		.mdm	= HPB_DMAE_ASYNCMDR_ASMD22_MASK |
-			  HPB_DMAE_ASYNCMDR_ASBTMD22_MASK,
-		.port	= 0x0D0C,
-		.flags	= HPB_DMAE_SET_ASYNC_RESET | HPB_DMAE_SET_ASYNC_MODE,
-		.dma_ch	= 22,
-	},
-};
-
-static const struct hpb_dmae_channel hpb_dmae_channels[] = {
-	HPB_DMAE_CHANNEL(0x93, HPBDMA_SLAVE_SDHI0_TX), /* ch. 21 */
-	HPB_DMAE_CHANNEL(0x93, HPBDMA_SLAVE_SDHI0_RX), /* ch. 22 */
-};
-
-static struct hpb_dmae_pdata dma_platform_data __initdata = {
-	.slaves			= hpb_dmae_slaves,
-	.num_slaves		= ARRAY_SIZE(hpb_dmae_slaves),
-	.channels		= hpb_dmae_channels,
-	.num_channels		= ARRAY_SIZE(hpb_dmae_channels),
-	.ts_shift		= {
-		[XMIT_SZ_8BIT]	= 0,
-		[XMIT_SZ_16BIT]	= 1,
-		[XMIT_SZ_32BIT]	= 2,
-	},
-	.num_hw_channels	= 44,
-};
-
-static struct resource hpb_dmae_resources[] __initdata = {
-	/* Channel registers */
-	DEFINE_RES_MEM(0xffc08000, 0x1000),
-	/* Common registers */
-	DEFINE_RES_MEM(0xffc09000, 0x170),
-	/* Asynchronous reset registers */
-	DEFINE_RES_MEM(0xffc00300, 4),
-	/* Asynchronous mode registers */
-	DEFINE_RES_MEM(0xffc00400, 4),
-	/* IRQ for DMA channels */
-	DEFINE_RES_NAMED(gic_iid(0x8e), 12, NULL, IORESOURCE_IRQ),
-};
-
-static void __init r8a7779_register_hpb_dmae(void)
-{
-	platform_device_register_resndata(NULL, "hpb-dma-engine",
-					  -1, hpb_dmae_resources,
-					  ARRAY_SIZE(hpb_dmae_resources),
-					  &dma_platform_data,
-					  sizeof(dma_platform_data));
-}
-
-static struct platform_device *r8a7779_early_devices[] __initdata = {
-	&tmu0_device,
-};
-
-static struct platform_device *r8a7779_standard_devices[] __initdata = {
-	&scif0_device,
-	&scif1_device,
-	&scif2_device,
-	&scif3_device,
-	&scif4_device,
-	&scif5_device,
-	&i2c0_device,
-	&i2c1_device,
-	&i2c2_device,
-	&i2c3_device,
-	&sata_device,
-};
-
-void __init r8a7779_add_standard_devices(void)
-{
-#ifdef CONFIG_CACHE_L2X0
-	/* Shared attribute override enable, 64K*16way */
-	l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff);
-#endif
-	r8a7779_pm_init();
-
-	r8a7779_init_pm_domains();
-
-	platform_add_devices(r8a7779_early_devices,
-			    ARRAY_SIZE(r8a7779_early_devices));
-	platform_add_devices(r8a7779_standard_devices,
-			    ARRAY_SIZE(r8a7779_standard_devices));
-	r8a7779_register_hpb_dmae();
-}
-
-void __init r8a7779_add_early_devices(void)
-{
-	early_platform_add_devices(r8a7779_early_devices,
-				   ARRAY_SIZE(r8a7779_early_devices));
-
-	/* Early serial console setup is not included here due to
-	 * memory map collisions. The SCIF serial ports in r8a7779
-	 * are difficult to identity map 1:1 due to collision with the
-	 * virtual memory range used by the coherent DMA code on ARM.
-	 *
-	 * Anyone wanting to debug early can remove UPF_IOREMAP from
-	 * the sh-sci serial console platform data, adjust mapbase
-	 * to a static M:N virt:phys mapping that needs to be added to
-	 * the mappings passed with iotable_init() above.
-	 *
-	 * Then add a call to shmobile_setup_console() from this function.
-	 *
-	 * As a final step pass earlyprint=sh-sci.2,115200 on the kernel
-	 * command line in case of the marzen board.
-	 */
-}
-
-static struct platform_device *r8a7779_late_devices[] __initdata = {
-	&ehci0_device,
-	&ehci1_device,
-	&ohci0_device,
-	&ohci1_device,
-};
-
-void __init r8a7779_init_late(void)
-{
-	/* get USB PHY */
-	phy = usb_get_phy(USB_PHY_TYPE_USB2);
-
-	shmobile_init_late();
-	platform_add_devices(r8a7779_late_devices,
-			     ARRAY_SIZE(r8a7779_late_devices));
-}
-
-#ifdef CONFIG_USE_OF
-void __init r8a7779_init_irq_dt(void)
-{
-#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
-	void __iomem *gic_dist_base = ioremap_nocache(0xf0001000, 0x1000);
-	void __iomem *gic_cpu_base = ioremap_nocache(0xf0000100, 0x1000);
-#endif
-	gic_set_irqchip_flags(IRQCHIP_SKIP_SET_WAKE);
-
-#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-#else
 	irqchip_init();
-#endif
+
 	/* route all interrupts to ARM */
 	__raw_writel(0xffffffff, INT2NTSR0);
 	__raw_writel(0x3fffffff, INT2NTSR1);
@@ -740,7 +78,7 @@ void __init r8a7779_init_irq_dt(void)
 
 #define MODEMR		0xffcc0020
 
-u32 __init r8a7779_read_mode_pins(void)
+static u32 __init r8a7779_read_mode_pins(void)
 {
 	static u32 mode;
 	static bool mode_valid;
@@ -756,16 +94,23 @@ u32 __init r8a7779_read_mode_pins(void)
 	return mode;
 }
 
-static const char *r8a7779_compat_dt[] __initdata = {
+static void __init r8a7779_init_time(void)
+{
+	r8a7779_clocks_init(r8a7779_read_mode_pins());
+	clocksource_of_init();
+}
+
+static const char *const r8a7779_compat_dt[] __initconst = {
 	"renesas,r8a7779",
 	NULL,
 };
 
 DT_MACHINE_START(R8A7779_DT, "Generic R8A7779 (Flattened Device Tree)")
+	.smp		= smp_ops(r8a7779_smp_ops),
 	.map_io		= r8a7779_map_io,
 	.init_early	= shmobile_init_delay,
+	.init_time	= r8a7779_init_time,
 	.init_irq	= r8a7779_init_irq_dt,
 	.init_late	= shmobile_init_late,
 	.dt_compat	= r8a7779_compat_dt,
 MACHINE_END
-#endif /* CONFIG_USE_OF */
diff --git a/arch/arm/mach-shmobile/setup-r8a7791.c b/arch/arm/mach-shmobile/setup-r8a7791.c
index ef8eb3af586d..3b8dbaf07777 100644
--- a/arch/arm/mach-shmobile/setup-r8a7791.c
+++ b/arch/arm/mach-shmobile/setup-r8a7791.c
@@ -23,7 +23,7 @@
 #include "r8a7791.h"
 #include "rcar-gen2.h"
 
-static const char *r8a7791_boards_compat_dt[] __initdata = {
+static const char *const r8a7791_boards_compat_dt[] __initconst = {
 	"renesas,r8a7791",
 	NULL,
 };
diff --git a/arch/arm/mach-shmobile/setup-r8a7793.c b/arch/arm/mach-shmobile/setup-r8a7793.c
new file mode 100644
index 000000000000..1d2825cb7a65
--- /dev/null
+++ b/arch/arm/mach-shmobile/setup-r8a7793.c
@@ -0,0 +1,33 @@
+/*
+ * r8a7793 processor support
+ *
+ * Copyright (C) 2015  Ulrich Hecht
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <asm/mach/arch.h>
+
+#include "common.h"
+#include "rcar-gen2.h"
+
+static const char *r8a7793_boards_compat_dt[] __initconst = {
+	"renesas,r8a7793",
+	NULL,
+};
+
+DT_MACHINE_START(R8A7793_DT, "Generic R8A7793 (Flattened Device Tree)")
+	.init_early	= shmobile_init_delay,
+	.init_time	= rcar_gen2_timer_init,
+	.init_late	= shmobile_init_late,
+	.reserve	= rcar_gen2_reserve,
+	.dt_compat	= r8a7793_boards_compat_dt,
+MACHINE_END
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index 5d13595aa027..aa3339258d9c 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -128,9 +128,7 @@ void __init rcar_gen2_timer_init(void)
 #endif /* CONFIG_ARM_ARCH_TIMER */
 
 	rcar_gen2_clocks_init(mode);
-#ifdef CONFIG_ARCH_SHMOBILE_MULTI
 	clocksource_of_init();
-#endif
 }
 
 struct memory_reserve_config {
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index fb2ab7590af8..99a2004cac76 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -18,28 +18,17 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/platform_device.h>
 #include <linux/of_platform.h>
 #include <linux/delay.h>
 #include <linux/input.h>
-#include <linux/i2c/i2c-sh_mobile.h>
 #include <linux/io.h>
-#include <linux/serial_sci.h>
-#include <linux/sh_dma.h>
-#include <linux/sh_timer.h>
-#include <linux/platform_data/sh_ipmmu.h>
-#include <linux/platform_data/irq-renesas-intc-irqpin.h>
 
 #include <asm/hardware/cache-l2x0.h>
-#include <asm/mach-types.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
 #include "common.h"
-#include "dma-register.h"
-#include "intc.h"
-#include "irqs.h"
 #include "sh73a0.h"
 
 static struct map_desc sh73a0_io_desc[] __initdata = {
@@ -54,737 +43,12 @@ static struct map_desc sh73a0_io_desc[] __initdata = {
 	},
 };
 
-void __init sh73a0_map_io(void)
+static void __init sh73a0_map_io(void)
 {
 	debug_ll_io_init();
 	iotable_init(sh73a0_io_desc, ARRAY_SIZE(sh73a0_io_desc));
 }
 
-/* PFC */
-static struct resource pfc_resources[] __initdata = {
-	DEFINE_RES_MEM(0xe6050000, 0x8000),
-	DEFINE_RES_MEM(0xe605801c, 0x000c),
-};
-
-void __init sh73a0_pinmux_init(void)
-{
-	platform_device_register_simple("pfc-sh73a0", -1, pfc_resources,
-					ARRAY_SIZE(pfc_resources));
-}
-
-/* SCIF */
-#define SH73A0_SCIF(scif_type, index, baseaddr, irq)		\
-static struct plat_sci_port scif##index##_platform_data = {	\
-	.type		= scif_type,				\
-	.flags		= UPF_BOOT_AUTOCONF,			\
-	.scscr		= SCSCR_RE | SCSCR_TE,			\
-};								\
-								\
-static struct resource scif##index##_resources[] = {		\
-	DEFINE_RES_MEM(baseaddr, 0x100),			\
-	DEFINE_RES_IRQ(irq),					\
-};								\
-								\
-static struct platform_device scif##index##_device = {		\
-	.name		= "sh-sci",				\
-	.id		= index,				\
-	.resource	= scif##index##_resources,		\
-	.num_resources	= ARRAY_SIZE(scif##index##_resources),	\
-	.dev		= {					\
-		.platform_data	= &scif##index##_platform_data,	\
-	},							\
-}
-
-SH73A0_SCIF(PORT_SCIFA, 0, 0xe6c40000, gic_spi(72));
-SH73A0_SCIF(PORT_SCIFA, 1, 0xe6c50000, gic_spi(73));
-SH73A0_SCIF(PORT_SCIFA, 2, 0xe6c60000, gic_spi(74));
-SH73A0_SCIF(PORT_SCIFA, 3, 0xe6c70000, gic_spi(75));
-SH73A0_SCIF(PORT_SCIFA, 4, 0xe6c80000, gic_spi(78));
-SH73A0_SCIF(PORT_SCIFA, 5, 0xe6cb0000, gic_spi(79));
-SH73A0_SCIF(PORT_SCIFA, 6, 0xe6cc0000, gic_spi(156));
-SH73A0_SCIF(PORT_SCIFA, 7, 0xe6cd0000, gic_spi(143));
-SH73A0_SCIF(PORT_SCIFB, 8, 0xe6c30000, gic_spi(80));
-
-static struct sh_timer_config cmt1_platform_data = {
-	.channels_mask = 0x3f,
-};
-
-static struct resource cmt1_resources[] = {
-	DEFINE_RES_MEM(0xe6138000, 0x200),
-	DEFINE_RES_IRQ(gic_spi(65)),
-};
-
-static struct platform_device cmt1_device = {
-	.name		= "sh-cmt-48",
-	.id		= 1,
-	.dev = {
-		.platform_data	= &cmt1_platform_data,
-	},
-	.resource	= cmt1_resources,
-	.num_resources	= ARRAY_SIZE(cmt1_resources),
-};
-
-/* TMU */
-static struct sh_timer_config tmu0_platform_data = {
-	.channels_mask = 7,
-};
-
-static struct resource tmu0_resources[] = {
-	DEFINE_RES_MEM(0xfff60000, 0x2c),
-	DEFINE_RES_IRQ(intcs_evt2irq(0xe80)),
-	DEFINE_RES_IRQ(intcs_evt2irq(0xea0)),
-	DEFINE_RES_IRQ(intcs_evt2irq(0xec0)),
-};
-
-static struct platform_device tmu0_device = {
-	.name		= "sh-tmu",
-	.id		= 0,
-	.dev = {
-		.platform_data	= &tmu0_platform_data,
-	},
-	.resource	= tmu0_resources,
-	.num_resources	= ARRAY_SIZE(tmu0_resources),
-};
-
-static struct resource i2c0_resources[] = {
-	[0] = DEFINE_RES_MEM(0xe6820000, 0x426),
-	[1] = {
-		.start	= gic_spi(167),
-		.end	= gic_spi(170),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource i2c1_resources[] = {
-	[0] = DEFINE_RES_MEM(0xe6822000, 0x426),
-	[1] = {
-		.start	= gic_spi(51),
-		.end	= gic_spi(54),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource i2c2_resources[] = {
-	[0] = DEFINE_RES_MEM(0xe6824000, 0x426),
-	[1] = {
-		.start	= gic_spi(171),
-		.end	= gic_spi(174),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource i2c3_resources[] = {
-	[0] = DEFINE_RES_MEM(0xe6826000, 0x426),
-	[1] = {
-		.start	= gic_spi(183),
-		.end	= gic_spi(186),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource i2c4_resources[] = {
-	[0] = DEFINE_RES_MEM(0xe6828000, 0x426),
-	[1] = {
-		.start	= gic_spi(187),
-		.end	= gic_spi(190),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct i2c_sh_mobile_platform_data i2c_platform_data = {
-	.clks_per_count	= 2,
-};
-
-static struct platform_device i2c0_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 0,
-	.resource	= i2c0_resources,
-	.num_resources	= ARRAY_SIZE(i2c0_resources),
-	.dev		= {
-		.platform_data	= &i2c_platform_data,
-	},
-};
-
-static struct platform_device i2c1_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 1,
-	.resource	= i2c1_resources,
-	.num_resources	= ARRAY_SIZE(i2c1_resources),
-	.dev		= {
-		.platform_data	= &i2c_platform_data,
-	},
-};
-
-static struct platform_device i2c2_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 2,
-	.resource	= i2c2_resources,
-	.num_resources	= ARRAY_SIZE(i2c2_resources),
-	.dev		= {
-		.platform_data	= &i2c_platform_data,
-	},
-};
-
-static struct platform_device i2c3_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 3,
-	.resource	= i2c3_resources,
-	.num_resources	= ARRAY_SIZE(i2c3_resources),
-	.dev		= {
-		.platform_data	= &i2c_platform_data,
-	},
-};
-
-static struct platform_device i2c4_device = {
-	.name		= "i2c-sh_mobile",
-	.id		= 4,
-	.resource	= i2c4_resources,
-	.num_resources	= ARRAY_SIZE(i2c4_resources),
-	.dev		= {
-		.platform_data	= &i2c_platform_data,
-	},
-};
-
-static const struct sh_dmae_slave_config sh73a0_dmae_slaves[] = {
-	{
-		.slave_id	= SHDMA_SLAVE_SCIF0_TX,
-		.addr		= 0xe6c40020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x21,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF0_RX,
-		.addr		= 0xe6c40024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x22,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF1_TX,
-		.addr		= 0xe6c50020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x25,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF1_RX,
-		.addr		= 0xe6c50024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x26,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF2_TX,
-		.addr		= 0xe6c60020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x29,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF2_RX,
-		.addr		= 0xe6c60024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x2a,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF3_TX,
-		.addr		= 0xe6c70020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x2d,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF3_RX,
-		.addr		= 0xe6c70024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x2e,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF4_TX,
-		.addr		= 0xe6c80020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x39,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF4_RX,
-		.addr		= 0xe6c80024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x3a,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF5_TX,
-		.addr		= 0xe6cb0020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x35,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF5_RX,
-		.addr		= 0xe6cb0024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x36,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF6_TX,
-		.addr		= 0xe6cc0020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x1d,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF6_RX,
-		.addr		= 0xe6cc0024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x1e,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF7_TX,
-		.addr		= 0xe6cd0020,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x19,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF7_RX,
-		.addr		= 0xe6cd0024,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x1a,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF8_TX,
-		.addr		= 0xe6c30040,
-		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x3d,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SCIF8_RX,
-		.addr		= 0xe6c30060,
-		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
-		.mid_rid	= 0x3e,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI0_TX,
-		.addr		= 0xee100030,
-		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xc1,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI0_RX,
-		.addr		= 0xee100030,
-		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xc2,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI1_TX,
-		.addr		= 0xee120030,
-		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xc9,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI1_RX,
-		.addr		= 0xee120030,
-		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xca,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI2_TX,
-		.addr		= 0xee140030,
-		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xcd,
-	}, {
-		.slave_id	= SHDMA_SLAVE_SDHI2_RX,
-		.addr		= 0xee140030,
-		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
-		.mid_rid	= 0xce,
-	}, {
-		.slave_id	= SHDMA_SLAVE_MMCIF_TX,
-		.addr		= 0xe6bd0034,
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd1,
-	}, {
-		.slave_id	= SHDMA_SLAVE_MMCIF_RX,
-		.addr		= 0xe6bd0034,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd2,
-	},
-};
-
-#define DMAE_CHANNEL(_offset)					\
-	{							\
-		.offset         = _offset - 0x20,		\
-		.dmars          = _offset - 0x20 + 0x40,	\
-	}
-
-static const struct sh_dmae_channel sh73a0_dmae_channels[] = {
-	DMAE_CHANNEL(0x8000),
-	DMAE_CHANNEL(0x8080),
-	DMAE_CHANNEL(0x8100),
-	DMAE_CHANNEL(0x8180),
-	DMAE_CHANNEL(0x8200),
-	DMAE_CHANNEL(0x8280),
-	DMAE_CHANNEL(0x8300),
-	DMAE_CHANNEL(0x8380),
-	DMAE_CHANNEL(0x8400),
-	DMAE_CHANNEL(0x8480),
-	DMAE_CHANNEL(0x8500),
-	DMAE_CHANNEL(0x8580),
-	DMAE_CHANNEL(0x8600),
-	DMAE_CHANNEL(0x8680),
-	DMAE_CHANNEL(0x8700),
-	DMAE_CHANNEL(0x8780),
-	DMAE_CHANNEL(0x8800),
-	DMAE_CHANNEL(0x8880),
-	DMAE_CHANNEL(0x8900),
-	DMAE_CHANNEL(0x8980),
-};
-
-static struct sh_dmae_pdata sh73a0_dmae_platform_data = {
-	.slave          = sh73a0_dmae_slaves,
-	.slave_num      = ARRAY_SIZE(sh73a0_dmae_slaves),
-	.channel        = sh73a0_dmae_channels,
-	.channel_num    = ARRAY_SIZE(sh73a0_dmae_channels),
-	.ts_low_shift   = TS_LOW_SHIFT,
-	.ts_low_mask    = TS_LOW_BIT << TS_LOW_SHIFT,
-	.ts_high_shift  = TS_HI_SHIFT,
-	.ts_high_mask   = TS_HI_BIT << TS_HI_SHIFT,
-	.ts_shift       = dma_ts_shift,
-	.ts_shift_num   = ARRAY_SIZE(dma_ts_shift),
-	.dmaor_init     = DMAOR_DME,
-};
-
-static struct resource sh73a0_dmae_resources[] = {
-	DEFINE_RES_MEM(0xfe000020, 0x89e0),
-	{
-		.name	= "error_irq",
-		.start  = gic_spi(129),
-		.end    = gic_spi(129),
-		.flags  = IORESOURCE_IRQ,
-	},
-	{
-		/* IRQ for channels 0-19 */
-		.start  = gic_spi(109),
-		.end    = gic_spi(128),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device dma0_device = {
-	.name		= "sh-dma-engine",
-	.id		= 0,
-	.resource	= sh73a0_dmae_resources,
-	.num_resources	= ARRAY_SIZE(sh73a0_dmae_resources),
-	.dev		= {
-		.platform_data	= &sh73a0_dmae_platform_data,
-	},
-};
-
-/* MPDMAC */
-static const struct sh_dmae_slave_config sh73a0_mpdma_slaves[] = {
-	{
-		.slave_id	= SHDMA_SLAVE_FSI2A_RX,
-		.addr		= 0xec230020,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd6, /* CHECK ME */
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSI2A_TX,
-		.addr		= 0xec230024,
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd5, /* CHECK ME */
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSI2C_RX,
-		.addr		= 0xec230060,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xda, /* CHECK ME */
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSI2C_TX,
-		.addr		= 0xec230064,
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd9, /* CHECK ME */
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSI2B_RX,
-		.addr		= 0xec240020,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0x8e, /* CHECK ME */
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSI2B_TX,
-		.addr		= 0xec240024,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0x8d, /* CHECK ME */
-	}, {
-		.slave_id	= SHDMA_SLAVE_FSI2D_RX,
-		.addr		=  0xec240060,
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0x9a, /* CHECK ME */
-	},
-};
-
-#define MPDMA_CHANNEL(a, b, c)			\
-{						\
-	.offset		= a,			\
-	.dmars		= b,			\
-	.dmars_bit	= c,			\
-	.chclr_offset	= (0x220 - 0x20) + a	\
-}
-
-static const struct sh_dmae_channel sh73a0_mpdma_channels[] = {
-	MPDMA_CHANNEL(0x00, 0, 0),
-	MPDMA_CHANNEL(0x10, 0, 8),
-	MPDMA_CHANNEL(0x20, 4, 0),
-	MPDMA_CHANNEL(0x30, 4, 8),
-	MPDMA_CHANNEL(0x50, 8, 0),
-	MPDMA_CHANNEL(0x70, 8, 8),
-};
-
-static struct sh_dmae_pdata sh73a0_mpdma_platform_data = {
-	.slave		= sh73a0_mpdma_slaves,
-	.slave_num	= ARRAY_SIZE(sh73a0_mpdma_slaves),
-	.channel	= sh73a0_mpdma_channels,
-	.channel_num	= ARRAY_SIZE(sh73a0_mpdma_channels),
-	.ts_low_shift	= TS_LOW_SHIFT,
-	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
-	.ts_high_shift	= TS_HI_SHIFT,
-	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
-	.ts_shift	= dma_ts_shift,
-	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
-	.dmaor_init	= DMAOR_DME,
-	.chclr_present	= 1,
-};
-
-/* Resource order important! */
-static struct resource sh73a0_mpdma_resources[] = {
-	/* Channel registers and DMAOR */
-	DEFINE_RES_MEM(0xec618020, 0x270),
-	/* DMARSx */
-	DEFINE_RES_MEM(0xec619000, 0xc),
-	{
-		.name	= "error_irq",
-		.start	= gic_spi(181),
-		.end	= gic_spi(181),
-		.flags	= IORESOURCE_IRQ,
-	},
-	{
-		/* IRQ for channels 0-5 */
-		.start	= gic_spi(175),
-		.end	= gic_spi(180),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device mpdma0_device = {
-	.name		= "sh-dma-engine",
-	.id		= 1,
-	.resource	= sh73a0_mpdma_resources,
-	.num_resources	= ARRAY_SIZE(sh73a0_mpdma_resources),
-	.dev		= {
-		.platform_data	= &sh73a0_mpdma_platform_data,
-	},
-};
-
-static struct resource pmu_resources[] = {
-	[0] = {
-		.start	= gic_spi(55),
-		.end	= gic_spi(55),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[1] = {
-		.start	= gic_spi(56),
-		.end	= gic_spi(56),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device pmu_device = {
-	.name		= "armv7-pmu",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(pmu_resources),
-	.resource	= pmu_resources,
-};
-
-/* an IPMMU module for ICB */
-static struct resource ipmmu_resources[] = {
-	DEFINE_RES_MEM(0xfe951000, 0x100),
-};
-
-static const char * const ipmmu_dev_names[] = {
-	"sh_mobile_lcdc_fb.0",
-};
-
-static struct shmobile_ipmmu_platform_data ipmmu_platform_data = {
-	.dev_names = ipmmu_dev_names,
-	.num_dev_names = ARRAY_SIZE(ipmmu_dev_names),
-};
-
-static struct platform_device ipmmu_device = {
-	.name           = "ipmmu",
-	.id             = -1,
-	.dev = {
-		.platform_data = &ipmmu_platform_data,
-	},
-	.resource       = ipmmu_resources,
-	.num_resources  = ARRAY_SIZE(ipmmu_resources),
-};
-
-static struct renesas_intc_irqpin_config irqpin0_platform_data = {
-	.irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */
-	.control_parent = true,
-};
-
-static struct resource irqpin0_resources[] = {
-	DEFINE_RES_MEM(0xe6900000, 4), /* ICR1A */
-	DEFINE_RES_MEM(0xe6900010, 4), /* INTPRI00A */
-	DEFINE_RES_MEM(0xe6900020, 1), /* INTREQ00A */
-	DEFINE_RES_MEM(0xe6900040, 1), /* INTMSK00A */
-	DEFINE_RES_MEM(0xe6900060, 1), /* INTMSKCLR00A */
-	DEFINE_RES_IRQ(gic_spi(1)), /* IRQ0 */
-	DEFINE_RES_IRQ(gic_spi(2)), /* IRQ1 */
-	DEFINE_RES_IRQ(gic_spi(3)), /* IRQ2 */
-	DEFINE_RES_IRQ(gic_spi(4)), /* IRQ3 */
-	DEFINE_RES_IRQ(gic_spi(5)), /* IRQ4 */
-	DEFINE_RES_IRQ(gic_spi(6)), /* IRQ5 */
-	DEFINE_RES_IRQ(gic_spi(7)), /* IRQ6 */
-	DEFINE_RES_IRQ(gic_spi(8)), /* IRQ7 */
-};
-
-static struct platform_device irqpin0_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 0,
-	.resource	= irqpin0_resources,
-	.num_resources	= ARRAY_SIZE(irqpin0_resources),
-	.dev		= {
-		.platform_data	= &irqpin0_platform_data,
-	},
-};
-
-static struct renesas_intc_irqpin_config irqpin1_platform_data = {
-	.irq_base = irq_pin(8), /* IRQ8 -> IRQ15 */
-	.control_parent = true, /* Disable spurious IRQ10 */
-};
-
-static struct resource irqpin1_resources[] = {
-	DEFINE_RES_MEM(0xe6900004, 4), /* ICR2A */
-	DEFINE_RES_MEM(0xe6900014, 4), /* INTPRI10A */
-	DEFINE_RES_MEM(0xe6900024, 1), /* INTREQ10A */
-	DEFINE_RES_MEM(0xe6900044, 1), /* INTMSK10A */
-	DEFINE_RES_MEM(0xe6900064, 1), /* INTMSKCLR10A */
-	DEFINE_RES_IRQ(gic_spi(9)), /* IRQ8 */
-	DEFINE_RES_IRQ(gic_spi(10)), /* IRQ9 */
-	DEFINE_RES_IRQ(gic_spi(11)), /* IRQ10 */
-	DEFINE_RES_IRQ(gic_spi(12)), /* IRQ11 */
-	DEFINE_RES_IRQ(gic_spi(13)), /* IRQ12 */
-	DEFINE_RES_IRQ(gic_spi(14)), /* IRQ13 */
-	DEFINE_RES_IRQ(gic_spi(15)), /* IRQ14 */
-	DEFINE_RES_IRQ(gic_spi(16)), /* IRQ15 */
-};
-
-static struct platform_device irqpin1_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 1,
-	.resource	= irqpin1_resources,
-	.num_resources	= ARRAY_SIZE(irqpin1_resources),
-	.dev		= {
-		.platform_data	= &irqpin1_platform_data,
-	},
-};
-
-static struct renesas_intc_irqpin_config irqpin2_platform_data = {
-	.irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */
-	.control_parent = true,
-};
-
-static struct resource irqpin2_resources[] = {
-	DEFINE_RES_MEM(0xe6900008, 4), /* ICR3A */
-	DEFINE_RES_MEM(0xe6900018, 4), /* INTPRI20A */
-	DEFINE_RES_MEM(0xe6900028, 1), /* INTREQ20A */
-	DEFINE_RES_MEM(0xe6900048, 1), /* INTMSK20A */
-	DEFINE_RES_MEM(0xe6900068, 1), /* INTMSKCLR20A */
-	DEFINE_RES_IRQ(gic_spi(17)), /* IRQ16 */
-	DEFINE_RES_IRQ(gic_spi(18)), /* IRQ17 */
-	DEFINE_RES_IRQ(gic_spi(19)), /* IRQ18 */
-	DEFINE_RES_IRQ(gic_spi(20)), /* IRQ19 */
-	DEFINE_RES_IRQ(gic_spi(21)), /* IRQ20 */
-	DEFINE_RES_IRQ(gic_spi(22)), /* IRQ21 */
-	DEFINE_RES_IRQ(gic_spi(23)), /* IRQ22 */
-	DEFINE_RES_IRQ(gic_spi(24)), /* IRQ23 */
-};
-
-static struct platform_device irqpin2_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 2,
-	.resource	= irqpin2_resources,
-	.num_resources	= ARRAY_SIZE(irqpin2_resources),
-	.dev		= {
-		.platform_data	= &irqpin2_platform_data,
-	},
-};
-
-static struct renesas_intc_irqpin_config irqpin3_platform_data = {
-	.irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */
-	.control_parent = true,
-};
-
-static struct resource irqpin3_resources[] = {
-	DEFINE_RES_MEM(0xe690000c, 4), /* ICR4A */
-	DEFINE_RES_MEM(0xe690001c, 4), /* INTPRI30A */
-	DEFINE_RES_MEM(0xe690002c, 1), /* INTREQ30A */
-	DEFINE_RES_MEM(0xe690004c, 1), /* INTMSK30A */
-	DEFINE_RES_MEM(0xe690006c, 1), /* INTMSKCLR30A */
-	DEFINE_RES_IRQ(gic_spi(25)), /* IRQ24 */
-	DEFINE_RES_IRQ(gic_spi(26)), /* IRQ25 */
-	DEFINE_RES_IRQ(gic_spi(27)), /* IRQ26 */
-	DEFINE_RES_IRQ(gic_spi(28)), /* IRQ27 */
-	DEFINE_RES_IRQ(gic_spi(29)), /* IRQ28 */
-	DEFINE_RES_IRQ(gic_spi(30)), /* IRQ29 */
-	DEFINE_RES_IRQ(gic_spi(31)), /* IRQ30 */
-	DEFINE_RES_IRQ(gic_spi(32)), /* IRQ31 */
-};
-
-static struct platform_device irqpin3_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 3,
-	.resource	= irqpin3_resources,
-	.num_resources	= ARRAY_SIZE(irqpin3_resources),
-	.dev		= {
-		.platform_data	= &irqpin3_platform_data,
-	},
-};
-
-static struct platform_device *sh73a0_early_devices[] __initdata = {
-	&scif0_device,
-	&scif1_device,
-	&scif2_device,
-	&scif3_device,
-	&scif4_device,
-	&scif5_device,
-	&scif6_device,
-	&scif7_device,
-	&scif8_device,
-	&tmu0_device,
-	&ipmmu_device,
-	&cmt1_device,
-};
-
-static struct platform_device *sh73a0_late_devices[] __initdata = {
-	&i2c0_device,
-	&i2c1_device,
-	&i2c2_device,
-	&i2c3_device,
-	&i2c4_device,
-	&dma0_device,
-	&mpdma0_device,
-	&pmu_device,
-	&irqpin0_device,
-	&irqpin1_device,
-	&irqpin2_device,
-	&irqpin3_device,
-};
-
-#define SRCR2          IOMEM(0xe61580b0)
-
-void __init sh73a0_add_standard_devices(void)
-{
-	/* Clear software reset bit on SY-DMAC module */
-	__raw_writel(__raw_readl(SRCR2) & ~(1 << 18), SRCR2);
-
-	platform_add_devices(sh73a0_early_devices,
-			    ARRAY_SIZE(sh73a0_early_devices));
-	platform_add_devices(sh73a0_late_devices,
-			    ARRAY_SIZE(sh73a0_late_devices));
-}
-
-/* do nothing for !CONFIG_SMP or !CONFIG_HAVE_TWD */
-void __init __weak sh73a0_register_twd(void) { }
-
-void __init sh73a0_earlytimer_init(void)
-{
-	shmobile_init_delay();
-#ifndef CONFIG_COMMON_CLK
-	sh73a0_clock_init();
-#endif
-	shmobile_earlytimer_init();
-	sh73a0_register_twd();
-}
-
-void __init sh73a0_add_early_devices(void)
-{
-	early_platform_add_devices(sh73a0_early_devices,
-				   ARRAY_SIZE(sh73a0_early_devices));
-
-	/* setup early console here as well */
-	shmobile_setup_console();
-}
-
-#ifdef CONFIG_USE_OF
-
 static void __init sh73a0_generic_init(void)
 {
 #ifdef CONFIG_CACHE_L2X0
@@ -794,7 +58,7 @@ static void __init sh73a0_generic_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static const char *sh73a0_boards_compat_dt[] __initdata = {
+static const char *const sh73a0_boards_compat_dt[] __initconst = {
 	"renesas,sh73a0",
 	NULL,
 };
@@ -807,4 +71,3 @@ DT_MACHINE_START(SH73A0_DT, "Generic SH73A0 (Flattened Device Tree)")
 	.init_late	= shmobile_init_late,
 	.dt_compat	= sh73a0_boards_compat_dt,
 MACHINE_END
-#endif /* CONFIG_USE_OF */
diff --git a/arch/arm/mach-shmobile/sh73a0.h b/arch/arm/mach-shmobile/sh73a0.h
index 5a80f18b4fa0..39646806cf64 100644
--- a/arch/arm/mach-shmobile/sh73a0.h
+++ b/arch/arm/mach-shmobile/sh73a0.h
@@ -1,89 +1,6 @@
 #ifndef __ASM_SH73A0_H__
 #define __ASM_SH73A0_H__
 
-/* DMA slave IDs */
-enum {
-	SHDMA_SLAVE_INVALID,
-	SHDMA_SLAVE_SCIF0_TX,
-	SHDMA_SLAVE_SCIF0_RX,
-	SHDMA_SLAVE_SCIF1_TX,
-	SHDMA_SLAVE_SCIF1_RX,
-	SHDMA_SLAVE_SCIF2_TX,
-	SHDMA_SLAVE_SCIF2_RX,
-	SHDMA_SLAVE_SCIF3_TX,
-	SHDMA_SLAVE_SCIF3_RX,
-	SHDMA_SLAVE_SCIF4_TX,
-	SHDMA_SLAVE_SCIF4_RX,
-	SHDMA_SLAVE_SCIF5_TX,
-	SHDMA_SLAVE_SCIF5_RX,
-	SHDMA_SLAVE_SCIF6_TX,
-	SHDMA_SLAVE_SCIF6_RX,
-	SHDMA_SLAVE_SCIF7_TX,
-	SHDMA_SLAVE_SCIF7_RX,
-	SHDMA_SLAVE_SCIF8_TX,
-	SHDMA_SLAVE_SCIF8_RX,
-	SHDMA_SLAVE_SDHI0_TX,
-	SHDMA_SLAVE_SDHI0_RX,
-	SHDMA_SLAVE_SDHI1_TX,
-	SHDMA_SLAVE_SDHI1_RX,
-	SHDMA_SLAVE_SDHI2_TX,
-	SHDMA_SLAVE_SDHI2_RX,
-	SHDMA_SLAVE_MMCIF_TX,
-	SHDMA_SLAVE_MMCIF_RX,
-	SHDMA_SLAVE_FSI2A_TX,
-	SHDMA_SLAVE_FSI2A_RX,
-	SHDMA_SLAVE_FSI2B_TX,
-	SHDMA_SLAVE_FSI2B_RX,
-	SHDMA_SLAVE_FSI2C_TX,
-	SHDMA_SLAVE_FSI2C_RX,
-	SHDMA_SLAVE_FSI2D_RX,
-};
-
-/*
- *		SH73A0 IRQ LOCATION TABLE
- *
- * 416	-----------------------------------------
- *		IRQ0-IRQ15
- * 431	-----------------------------------------
- * ...
- * 448	-----------------------------------------
- *		sh73a0-intcs
- *		sh73a0-intca-irq-pins
- * 680	-----------------------------------------
- * ...
- * 700	-----------------------------------------
- *		sh73a0-pint0
- * 731	-----------------------------------------
- * 732	-----------------------------------------
- *		sh73a0-pint1
- * 739	-----------------------------------------
- * ...
- * 800	-----------------------------------------
- *		IRQ16-IRQ31
- * 815	-----------------------------------------
- * ...
- * 928	-----------------------------------------
- *		sh73a0-intca-irq-pins
- * 943	-----------------------------------------
- */
-
-/* PINT interrupts are located at Linux IRQ 700 and up */
-#define SH73A0_PINT0_IRQ(irq) ((irq) + 700)
-#define SH73A0_PINT1_IRQ(irq) ((irq) + 732)
-
-extern void sh73a0_init_irq(void);
-extern void sh73a0_init_irq_dt(void);
-extern void sh73a0_map_io(void);
-extern void sh73a0_earlytimer_init(void);
-extern void sh73a0_add_early_devices(void);
-extern void sh73a0_add_standard_devices(void);
-extern void sh73a0_clock_init(void);
-extern void sh73a0_pinmux_init(void);
-extern void sh73a0_pm_init(void);
-extern struct clk sh73a0_extal1_clk;
-extern struct clk sh73a0_extal2_clk;
-extern struct clk sh73a0_extcki_clk;
-extern struct clk sh73a0_extalr_clk;
 extern struct smp_operations sh73a0_smp_ops;
 
 #endif /* __ASM_SH73A0_H__ */
diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c
index 01f792fcb220..353562b8a5ee 100644
--- a/arch/arm/mach-shmobile/smp-r8a7779.c
+++ b/arch/arm/mach-shmobile/smp-r8a7779.c
@@ -23,7 +23,6 @@
 #include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 #include <asm/smp_scu.h>
-#include <asm/smp_twd.h>
 
 #include "common.h"
 #include "pm-rcar.h"
@@ -32,41 +31,33 @@
 #define AVECR IOMEM(0xfe700040)
 #define R8A7779_SCU_BASE 0xf0000000
 
-static struct rcar_sysc_ch r8a7779_ch_cpu1 = {
+static const struct rcar_sysc_ch r8a7779_ch_cpu1 = {
 	.chan_offs = 0x40, /* PWRSR0 .. PWRER0 */
 	.chan_bit = 1, /* ARM1 */
 	.isr_bit = 1, /* ARM1 */
 };
 
-static struct rcar_sysc_ch r8a7779_ch_cpu2 = {
+static const struct rcar_sysc_ch r8a7779_ch_cpu2 = {
 	.chan_offs = 0x40, /* PWRSR0 .. PWRER0 */
 	.chan_bit = 2, /* ARM2 */
 	.isr_bit = 2, /* ARM2 */
 };
 
-static struct rcar_sysc_ch r8a7779_ch_cpu3 = {
+static const struct rcar_sysc_ch r8a7779_ch_cpu3 = {
 	.chan_offs = 0x40, /* PWRSR0 .. PWRER0 */
 	.chan_bit = 3, /* ARM3 */
 	.isr_bit = 3, /* ARM3 */
 };
 
-static struct rcar_sysc_ch *r8a7779_ch_cpu[4] = {
+static const struct rcar_sysc_ch * const r8a7779_ch_cpu[4] = {
 	[1] = &r8a7779_ch_cpu1,
 	[2] = &r8a7779_ch_cpu2,
 	[3] = &r8a7779_ch_cpu3,
 };
 
-#if defined(CONFIG_HAVE_ARM_TWD) && !defined(CONFIG_ARCH_MULTIPLATFORM)
-static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, R8A7779_SCU_BASE + 0x600, 29);
-void __init r8a7779_register_twd(void)
-{
-	twd_local_timer_register(&twd_local_timer);
-}
-#endif
-
 static int r8a7779_platform_cpu_kill(unsigned int cpu)
 {
-	struct rcar_sysc_ch *ch = NULL;
+	const struct rcar_sysc_ch *ch = NULL;
 	int ret = -EIO;
 
 	cpu = cpu_logical_map(cpu);
@@ -82,7 +73,7 @@ static int r8a7779_platform_cpu_kill(unsigned int cpu)
 
 static int r8a7779_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	struct rcar_sysc_ch *ch = NULL;
+	const struct rcar_sysc_ch *ch = NULL;
 	unsigned int lcpu = cpu_logical_map(cpu);
 	int ret;
 
diff --git a/arch/arm/mach-shmobile/smp-r8a7790.c b/arch/arm/mach-shmobile/smp-r8a7790.c
index 930f45cbc08a..4b33d432a364 100644
--- a/arch/arm/mach-shmobile/smp-r8a7790.c
+++ b/arch/arm/mach-shmobile/smp-r8a7790.c
@@ -26,12 +26,12 @@
 #include "rcar-gen2.h"
 #include "r8a7790.h"
 
-static struct rcar_sysc_ch r8a7790_ca15_scu = {
+static const struct rcar_sysc_ch r8a7790_ca15_scu = {
 	.chan_offs = 0x180, /* PWRSR5 .. PWRER5 */
 	.isr_bit = 12, /* CA15-SCU */
 };
 
-static struct rcar_sysc_ch r8a7790_ca7_scu = {
+static const struct rcar_sysc_ch r8a7790_ca7_scu = {
 	.chan_offs = 0x100, /* PWRSR3 .. PWRER3 */
 	.isr_bit = 21, /* CA7-SCU */
 };
@@ -64,7 +64,7 @@ struct smp_operations r8a7790_smp_ops __initdata = {
 	.smp_prepare_cpus	= r8a7790_smp_prepare_cpus,
 	.smp_boot_secondary	= shmobile_smp_apmu_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_apmu_cpu_die,
 	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/smp-r8a7791.c b/arch/arm/mach-shmobile/smp-r8a7791.c
index 5e2d1db79afa..b2508c0d276b 100644
--- a/arch/arm/mach-shmobile/smp-r8a7791.c
+++ b/arch/arm/mach-shmobile/smp-r8a7791.c
@@ -58,7 +58,7 @@ struct smp_operations r8a7791_smp_ops __initdata = {
 	.smp_prepare_cpus	= r8a7791_smp_prepare_cpus,
 	.smp_boot_secondary	= r8a7791_smp_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_apmu_cpu_die,
 	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index 2106d6b76a06..bc2824a036e1 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -33,14 +33,6 @@
 
 #define SH73A0_SCU_BASE 0xf0000000
 
-#if defined(CONFIG_HAVE_ARM_TWD) && !defined(CONFIG_ARCH_MULTIPLATFORM)
-static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, SH73A0_SCU_BASE + 0x600, 29);
-void __init sh73a0_register_twd(void)
-{
-	twd_local_timer_register(&twd_local_timer);
-}
-#endif
-
 static int sh73a0_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	unsigned int lcpu = cpu_logical_map(cpu);
@@ -68,7 +60,7 @@ struct smp_operations sh73a0_smp_ops __initdata = {
 	.smp_prepare_cpus	= sh73a0_smp_prepare_cpus,
 	.smp_boot_secondary	= sh73a0_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_scu_cpu_die,
 	.cpu_kill		= shmobile_smp_scu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/timer.c b/arch/arm/mach-shmobile/timer.c
index 0edf2a6d2bbe..f1d027aa7a81 100644
--- a/arch/arm/mach-shmobile/timer.c
+++ b/arch/arm/mach-shmobile/timer.c
@@ -70,18 +70,6 @@ void __init shmobile_init_delay(void)
 	if (!max_freq)
 		return;
 
-#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
-	/* Non-multiplatform r8a73a4 SoC cannot use arch timer due
-	 * to GIC being initialized from C and arch timer via DT */
-	if (of_machine_is_compatible("renesas,r8a73a4"))
-		has_arch_timer = false;
-
-	/* Non-multiplatform r8a7790 SoC cannot use arch timer due
-	 * to GIC being initialized from C and arch timer via DT */
-	if (of_machine_is_compatible("renesas,r8a7790"))
-		has_arch_timer = false;
-#endif
-
 	if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) {
 		if (is_a7_a8_a9)
 			shmobile_setup_delay_hz(max_freq, 1, 3);
diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h
index 7259c3732702..5bc6ea87cdf7 100644
--- a/arch/arm/mach-socfpga/core.h
+++ b/arch/arm/mach-socfpga/core.h
@@ -25,6 +25,7 @@
 #define SOCFPGA_RSTMGR_MODPERRST	0x14
 #define SOCFPGA_RSTMGR_BRGMODRST	0x1c
 
+#define SOCFPGA_A10_RSTMGR_CTRL		0xC
 #define SOCFPGA_A10_RSTMGR_MODMPURST	0x20
 
 /* System Manager bits */
diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c
index c6f1df89f9af..15c8ce8965f4 100644
--- a/arch/arm/mach-socfpga/platsmp.c
+++ b/arch/arm/mach-socfpga/platsmp.c
@@ -106,11 +106,23 @@ static void socfpga_cpu_die(unsigned int cpu)
 		cpu_do_idle();
 }
 
+/*
+ * We need a dummy function so that platform_can_cpu_hotplug() knows
+ * we support CPU hotplug. However, the function does not need to do
+ * anything, because CPUs going offline just do WFI. We could reset
+ * the CPUs but it would increase power consumption.
+ */
+static int socfpga_cpu_kill(unsigned int cpu)
+{
+	return 1;
+}
+
 static struct smp_operations socfpga_smp_ops __initdata = {
 	.smp_prepare_cpus	= socfpga_smp_prepare_cpus,
 	.smp_boot_secondary	= socfpga_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= socfpga_cpu_die,
+	.cpu_kill		= socfpga_cpu_kill,
 #endif
 };
 
@@ -119,6 +131,7 @@ static struct smp_operations socfpga_a10_smp_ops __initdata = {
 	.smp_boot_secondary	= socfpga_a10_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= socfpga_cpu_die,
+	.cpu_kill		= socfpga_cpu_kill,
 #endif
 };
 
diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c
index 6a4199f2bffb..c378ab0c2431 100644
--- a/arch/arm/mach-socfpga/pm.c
+++ b/arch/arm/mach-socfpga/pm.c
@@ -56,7 +56,7 @@ static int socfpga_setup_ocram_self_refresh(void)
 		goto put_node;
 	}
 
-	ocram_pool = gen_pool_get(&pdev->dev);
+	ocram_pool = gen_pool_get(&pdev->dev, NULL);
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c
index 19643a756c48..a1c0efaa8794 100644
--- a/arch/arm/mach-socfpga/socfpga.c
+++ b/arch/arm/mach-socfpga/socfpga.c
@@ -74,6 +74,19 @@ static void socfpga_cyclone5_restart(enum reboot_mode mode, const char *cmd)
 	writel(temp, rst_manager_base_addr + SOCFPGA_RSTMGR_CTRL);
 }
 
+static void socfpga_arria10_restart(enum reboot_mode mode, const char *cmd)
+{
+	u32 temp;
+
+	temp = readl(rst_manager_base_addr + SOCFPGA_A10_RSTMGR_CTRL);
+
+	if (mode == REBOOT_HARD)
+		temp |= RSTMGR_CTRL_SWCOLDRSTREQ;
+	else
+		temp |= RSTMGR_CTRL_SWWARMRSTREQ;
+	writel(temp, rst_manager_base_addr + SOCFPGA_A10_RSTMGR_CTRL);
+}
+
 static const char *altera_dt_match[] = {
 	"altr,socfpga",
 	NULL
@@ -86,3 +99,16 @@ DT_MACHINE_START(SOCFPGA, "Altera SOCFPGA")
 	.restart	= socfpga_cyclone5_restart,
 	.dt_compat	= altera_dt_match,
 MACHINE_END
+
+static const char *altera_a10_dt_match[] = {
+	"altr,socfpga-arria10",
+	NULL
+};
+
+DT_MACHINE_START(SOCFPGA_A10, "Altera SOCFPGA Arria10")
+	.l2c_aux_val	= 0,
+	.l2c_aux_mask	= ~0,
+	.init_irq	= socfpga_init_irq,
+	.restart	= socfpga_arria10_restart,
+	.dt_compat	= altera_a10_dt_match,
+MACHINE_END
diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h
index a99d90a4d09c..06640914d9a0 100644
--- a/arch/arm/mach-spear/generic.h
+++ b/arch/arm/mach-spear/generic.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2009-2012 ST Microelectronics
  * Rajeev Kumar <rajeev-dlh.kumar@st.com>
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/irqs.h b/arch/arm/mach-spear/include/mach/irqs.h
index 92da0a8c6bce..7058720c5278 100644
--- a/arch/arm/mach-spear/include/mach/irqs.h
+++ b/arch/arm/mach-spear/include/mach/irqs.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2009-2012 ST Microelectronics
  * Rajeev Kumar <rajeev-dlh.kumar@st.com>
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/misc_regs.h b/arch/arm/mach-spear/include/mach/misc_regs.h
index 935639ce59ba..cfaf7c665b58 100644
--- a/arch/arm/mach-spear/include/mach/misc_regs.h
+++ b/arch/arm/mach-spear/include/mach/misc_regs.h
@@ -4,7 +4,7 @@
  * Miscellaneous registers definitions for SPEAr3xx machine family
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/spear.h b/arch/arm/mach-spear/include/mach/spear.h
index f2d6a0176575..5ed841ccf8a3 100644
--- a/arch/arm/mach-spear/include/mach/spear.h
+++ b/arch/arm/mach-spear/include/mach/spear.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2009,2012 ST Microelectronics
  * Rajeev Kumar<rajeev-dlh.kumar@st.com>
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/uncompress.h b/arch/arm/mach-spear/include/mach/uncompress.h
index 51b2dc93e4da..8439b9c12edb 100644
--- a/arch/arm/mach-spear/include/mach/uncompress.h
+++ b/arch/arm/mach-spear/include/mach/uncompress.h
@@ -4,7 +4,7 @@
  * Serial port stubs for kernel decompress status messages
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/pl080.c b/arch/arm/mach-spear/pl080.c
index cfa1199d0f4a..b4529f3e0ee9 100644
--- a/arch/arm/mach-spear/pl080.c
+++ b/arch/arm/mach-spear/pl080.c
@@ -4,7 +4,7 @@
  * DMAC pl080 definitions for SPEAr platform
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/pl080.h b/arch/arm/mach-spear/pl080.h
index eb6590ded40d..608dec6725ae 100644
--- a/arch/arm/mach-spear/pl080.h
+++ b/arch/arm/mach-spear/pl080.h
@@ -4,7 +4,7 @@
  * DMAC pl080 definitions for SPEAr platform
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/restart.c b/arch/arm/mach-spear/restart.c
index ce5e098c4888..b4342155a783 100644
--- a/arch/arm/mach-spear/restart.c
+++ b/arch/arm/mach-spear/restart.c
@@ -4,7 +4,7 @@
  * SPEAr platform specific restart functions
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear1310.c b/arch/arm/mach-spear/spear1310.c
index d9ce4d8000f0..cd5d375d91f0 100644
--- a/arch/arm/mach-spear/spear1310.c
+++ b/arch/arm/mach-spear/spear1310.c
@@ -4,7 +4,7 @@
  * SPEAr1310 machine source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear1340.c b/arch/arm/mach-spear/spear1340.c
index 3f3c0f124bd3..94594d5a446c 100644
--- a/arch/arm/mach-spear/spear1340.c
+++ b/arch/arm/mach-spear/spear1340.c
@@ -4,7 +4,7 @@
  * SPEAr1340 machine source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear13xx.c b/arch/arm/mach-spear/spear13xx.c
index 2e463a93468d..b7afce6795f4 100644
--- a/arch/arm/mach-spear/spear13xx.c
+++ b/arch/arm/mach-spear/spear13xx.c
@@ -4,7 +4,7 @@
  * SPEAr13XX machines common source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear300.c b/arch/arm/mach-spear/spear300.c
index b52e48f342f4..5b32edda2276 100644
--- a/arch/arm/mach-spear/spear300.c
+++ b/arch/arm/mach-spear/spear300.c
@@ -4,7 +4,7 @@
  * SPEAr300 machine source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear310.c b/arch/arm/mach-spear/spear310.c
index ed2029db391f..86a44ac7ff67 100644
--- a/arch/arm/mach-spear/spear310.c
+++ b/arch/arm/mach-spear/spear310.c
@@ -4,7 +4,7 @@
  * SPEAr310 machine source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear320.c b/arch/arm/mach-spear/spear320.c
index bf634b32a930..d45d751926c5 100644
--- a/arch/arm/mach-spear/spear320.c
+++ b/arch/arm/mach-spear/spear320.c
@@ -4,7 +4,7 @@
  * SPEAr320 machine source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c
index bf3b1fd8cb23..23394ac76cf2 100644
--- a/arch/arm/mach-spear/spear3xx.c
+++ b/arch/arm/mach-spear/spear3xx.c
@@ -4,7 +4,7 @@
  * SPEAr3XX machines common source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/time.c b/arch/arm/mach-spear/time.c
index 26fda4ed4d51..9ccffc1d0f28 100644
--- a/arch/arm/mach-spear/time.c
+++ b/arch/arm/mach-spear/time.c
@@ -66,8 +66,6 @@
 static __iomem void *gpt_base;
 static struct clk *gpt_clk;
 
-static void clockevent_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *clk_event_dev);
 static int clockevent_next_event(unsigned long evt,
 				 struct clock_event_device *clk_event_dev);
 
@@ -95,54 +93,67 @@ static void __init spear_clocksource_init(void)
 		200, 16, clocksource_mmio_readw_up);
 }
 
-static struct clock_event_device clkevt = {
-	.name = "tmr0",
-	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = clockevent_set_mode,
-	.set_next_event = clockevent_next_event,
-	.shift = 0,	/* to be computed */
-};
+static inline void timer_shutdown(struct clock_event_device *evt)
+{
+	u16 val = readw(gpt_base + CR(CLKEVT));
+
+	/* stop the timer */
+	val &= ~CTRL_ENABLE;
+	writew(val, gpt_base + CR(CLKEVT));
+}
+
+static int spear_shutdown(struct clock_event_device *evt)
+{
+	timer_shutdown(evt);
+
+	return 0;
+}
+
+static int spear_set_oneshot(struct clock_event_device *evt)
+{
+	u16 val;
 
-static void clockevent_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *clk_event_dev)
+	/* stop the timer */
+	timer_shutdown(evt);
+
+	val = readw(gpt_base + CR(CLKEVT));
+	val |= CTRL_ONE_SHOT;
+	writew(val, gpt_base + CR(CLKEVT));
+
+	return 0;
+}
+
+static int spear_set_periodic(struct clock_event_device *evt)
 {
 	u32 period;
 	u16 val;
 
 	/* stop the timer */
+	timer_shutdown(evt);
+
+	period = clk_get_rate(gpt_clk) / HZ;
+	period >>= CTRL_PRESCALER16;
+	writew(period, gpt_base + LOAD(CLKEVT));
+
 	val = readw(gpt_base + CR(CLKEVT));
-	val &= ~CTRL_ENABLE;
+	val &= ~CTRL_ONE_SHOT;
+	val |= CTRL_ENABLE | CTRL_INT_ENABLE;
 	writew(val, gpt_base + CR(CLKEVT));
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		period = clk_get_rate(gpt_clk) / HZ;
-		period >>= CTRL_PRESCALER16;
-		writew(period, gpt_base + LOAD(CLKEVT));
-
-		val = readw(gpt_base + CR(CLKEVT));
-		val &= ~CTRL_ONE_SHOT;
-		val |= CTRL_ENABLE | CTRL_INT_ENABLE;
-		writew(val, gpt_base + CR(CLKEVT));
-
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		val = readw(gpt_base + CR(CLKEVT));
-		val |= CTRL_ONE_SHOT;
-		writew(val, gpt_base + CR(CLKEVT));
-
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-
-		break;
-	default:
-		pr_err("Invalid mode requested\n");
-		break;
-	}
+	return 0;
 }
 
+static struct clock_event_device clkevt = {
+	.name = "tmr0",
+	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown = spear_shutdown,
+	.set_state_periodic = spear_set_periodic,
+	.set_state_oneshot = spear_set_oneshot,
+	.tick_resume = spear_shutdown,
+	.set_next_event = clockevent_next_event,
+	.shift = 0,	/* to be computed */
+};
+
 static int clockevent_next_event(unsigned long cycles,
 				 struct clock_event_device *clk_event_dev)
 {
@@ -193,7 +204,7 @@ static void __init spear_clockevent_init(int irq)
 	setup_irq(irq, &spear_timer_irq);
 }
 
-const static struct of_device_id timer_of_match[] __initconst = {
+static const struct of_device_id const timer_of_match[] __initconst = {
 	{ .compatible = "st,spear-timer", },
 	{ },
 };
diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c
index b373acade338..ae10fb280a78 100644
--- a/arch/arm/mach-sti/board-dt.c
+++ b/arch/arm/mach-sti/board-dt.c
@@ -14,7 +14,7 @@
 
 #include "smp.h"
 
-static const char *stih41x_dt_match[] __initdata = {
+static const char *const stih41x_dt_match[] __initconst = {
 	"st,stih415",
 	"st,stih416",
 	"st,stih407",
diff --git a/arch/arm/mach-sti/headsmp.S b/arch/arm/mach-sti/headsmp.S
index 4c09bae86edf..e0ad451700d5 100644
--- a/arch/arm/mach-sti/headsmp.S
+++ b/arch/arm/mach-sti/headsmp.S
@@ -37,6 +37,7 @@ pen:	ldr	r7, [r6]
 	 * should now contain the SVC stack for this core
 	 */
 	b	secondary_startup
+ENDPROC(sti_secondary_startup)
 
 1:	.long	.
 	.long	pen_release
diff --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c
index d4b624f8dfcb..c4ad6eae67fa 100644
--- a/arch/arm/mach-sti/platsmp.c
+++ b/arch/arm/mach-sti/platsmp.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
@@ -38,8 +39,6 @@ static DEFINE_SPINLOCK(boot_lock);
 
 static void sti_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
@@ -99,14 +98,62 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 static void __init sti_smp_prepare_cpus(unsigned int max_cpus)
 {
-	void __iomem *scu_base = NULL;
-	struct device_node *np = of_find_compatible_node(
-					NULL, NULL, "arm,cortex-a9-scu");
+	struct device_node *np;
+	void __iomem *scu_base;
+	u32 __iomem *cpu_strt_ptr;
+	u32 release_phys;
+	int cpu;
+	unsigned long entry_pa = virt_to_phys(sti_secondary_startup);
+
+	np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-scu");
+
 	if (np) {
 		scu_base = of_iomap(np, 0);
 		scu_enable(scu_base);
 		of_node_put(np);
 	}
+
+	if (max_cpus <= 1)
+		return;
+
+	for_each_possible_cpu(cpu) {
+
+		np = of_get_cpu_node(cpu, NULL);
+
+		if (!np)
+			continue;
+
+		if (of_property_read_u32(np, "cpu-release-addr",
+						&release_phys)) {
+			pr_err("CPU %d: missing or invalid cpu-release-addr "
+				"property\n", cpu);
+			continue;
+		}
+
+		/*
+		 * holding pen is usually configured in SBC DMEM but can also be
+		 * in RAM.
+		 */
+
+		if (!memblock_is_memory(release_phys))
+			cpu_strt_ptr =
+				ioremap(release_phys, sizeof(release_phys));
+		else
+			cpu_strt_ptr =
+				(u32 __iomem *)phys_to_virt(release_phys);
+
+		__raw_writel(entry_pa, cpu_strt_ptr);
+
+		/*
+		 * wmb so that data is actually written
+		 * before cache flush is done
+		 */
+		smp_wmb();
+		sync_cache_w(cpu_strt_ptr);
+
+		if (!memblock_is_memory(release_phys))
+			iounmap(cpu_strt_ptr);
+	}
 }
 
 struct smp_operations __initdata sti_smp_ops = {
diff --git a/arch/arm/mach-sti/smp.h b/arch/arm/mach-sti/smp.h
index 1871b72b1a7e..ae22707d301f 100644
--- a/arch/arm/mach-sti/smp.h
+++ b/arch/arm/mach-sti/smp.h
@@ -14,4 +14,6 @@
 
 extern struct smp_operations	sti_smp_ops;
 
+void sti_secondary_startup(void);
+
 #endif
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index 81502b90dd91..4efe2d43a126 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -35,7 +35,7 @@ config MACH_SUN7I
 	select SUN5I_HSTIMER
 
 config MACH_SUN8I
-	bool "Allwinner A23 (sun8i) SoCs support"
+	bool "Allwinner sun8i Family SoCs support"
 	default ARCH_SUNXI
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c
index 1bc811a74a9f..65bab2876343 100644
--- a/arch/arm/mach-sunxi/sunxi.c
+++ b/arch/arm/mach-sunxi/sunxi.c
@@ -67,10 +67,13 @@ MACHINE_END
 
 static const char * const sun8i_board_dt_compat[] = {
 	"allwinner,sun8i-a23",
+	"allwinner,sun8i-a33",
+	"allwinner,sun8i-h3",
 	NULL,
 };
 
-DT_MACHINE_START(SUN8I_DT, "Allwinner sun8i (A23) Family")
+DT_MACHINE_START(SUN8I_DT, "Allwinner sun8i Family")
+	.init_time	= sun6i_timer_init,
 	.dt_compat	= sun8i_board_dt_compat,
 	.init_late	= sunxi_dt_cpufreq_init,
 MACHINE_END
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 5d1a318f1302..0fa4c5f8b1be 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -8,6 +8,7 @@ menuconfig ARCH_TEGRA
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select PINCTRL
+	select PM_OPP
 	select ARCH_HAS_RESET_CONTROLLER
 	select RESET_CONTROLLER
 	select SOC_BUS
diff --git a/arch/arm/mach-tegra/cpuidle-tegra114.c b/arch/arm/mach-tegra/cpuidle-tegra114.c
index 155807fa6fdd..9157546fe68c 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra114.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra114.c
@@ -24,6 +24,7 @@
 #include <asm/cpuidle.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
+#include <asm/psci.h>
 
 #include "pm.h"
 #include "sleep.h"
@@ -44,16 +45,12 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev,
 	tegra_set_cpu_in_lp2();
 	cpu_pm_enter();
 
-	tick_broadcast_enter();
-
 	call_firmware_op(prepare_idle);
 
 	/* Do suspend by ourselves if the firmware does not implement it */
 	if (call_firmware_op(do_idle, 0) == -ENOSYS)
 		cpu_suspend(0, tegra30_sleep_cpu_secondary_finish);
 
-	tick_broadcast_exit();
-
 	cpu_pm_exit();
 	tegra_clear_cpu_in_lp2();
 
@@ -61,6 +58,13 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev,
 
 	return index;
 }
+
+static void tegra114_idle_enter_freeze(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv,
+				       int index)
+{
+       tegra114_idle_power_down(dev, drv, index);
+}
 #endif
 
 static struct cpuidle_driver tegra_idle_driver = {
@@ -72,8 +76,10 @@ static struct cpuidle_driver tegra_idle_driver = {
 #ifdef CONFIG_PM_SLEEP
 		[1] = {
 			.enter			= tegra114_idle_power_down,
+			.enter_freeze		= tegra114_idle_enter_freeze,
 			.exit_latency		= 500,
 			.target_residency	= 1000,
+			.flags			= CPUIDLE_FLAG_TIMER_STOP,
 			.power_usage		= 0,
 			.name			= "powered-down",
 			.desc			= "CPU power gated",
@@ -84,5 +90,8 @@ static struct cpuidle_driver tegra_idle_driver = {
 
 int __init tegra114_cpuidle_init(void)
 {
-	return cpuidle_register(&tegra_idle_driver, NULL);
+	if (!psci_smp_available())
+		return cpuidle_register(&tegra_idle_driver, NULL);
+
+	return 0;
 }
diff --git a/arch/arm/mach-tegra/iomap.h b/arch/arm/mach-tegra/iomap.h
index 81dc950b4881..9e5b2f869fc8 100644
--- a/arch/arm/mach-tegra/iomap.h
+++ b/arch/arm/mach-tegra/iomap.h
@@ -82,9 +82,6 @@
 #define TEGRA_EMC_BASE			0x7000F400
 #define TEGRA_EMC_SIZE			SZ_1K
 
-#define TEGRA_FUSE_BASE			0x7000F800
-#define TEGRA_FUSE_SIZE			SZ_1K
-
 #define TEGRA_EMC0_BASE			0x7001A000
 #define TEGRA_EMC0_SIZE			SZ_2K
 
diff --git a/arch/arm/mach-uniphier/platsmp.c b/arch/arm/mach-uniphier/platsmp.c
index 5943e1cb7fe1..4b784f721135 100644
--- a/arch/arm/mach-uniphier/platsmp.c
+++ b/arch/arm/mach-uniphier/platsmp.c
@@ -60,12 +60,6 @@ err:
 	sbcm_regmap = NULL;
 }
 
-static void __naked uniphier_secondary_startup(void)
-{
-	asm("bl		v7_invalidate_l1\n"
-	    "b		secondary_startup\n");
-};
-
 static int uniphier_boot_secondary(unsigned int cpu,
 				   struct task_struct *idle)
 {
@@ -75,7 +69,7 @@ static int uniphier_boot_secondary(unsigned int cpu,
 		return -ENODEV;
 
 	ret = regmap_write(sbcm_regmap, 0x1208,
-			   virt_to_phys(uniphier_secondary_startup));
+			   virt_to_phys(secondary_startup));
 	if (!ret)
 		asm("sev"); /* wake up secondary CPU */
 
diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index 4418a5078833..c8643ac5db71 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o
 obj-$(CONFIG_UX500_SOC_DB8500)	+= cpu-db8500.o
 obj-$(CONFIG_MACH_MOP500)	+= board-mop500-regulators.o \
 				board-mop500-audio.o
-obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o
+obj-$(CONFIG_SMP)		+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS) += pm_domains.o
 
diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
index 7557bede7ae6..780bd13cd7e3 100644
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ b/arch/arm/mach-ux500/cache-l2x0.c
@@ -8,6 +8,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 
+#include <asm/outercache.h>
 #include <asm/hardware/cache-l2x0.h>
 
 #include "db8500-regs.h"
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 16913800bbf9..f80560318c58 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -20,10 +20,10 @@
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/regulator/machine.h>
 #include <linux/random.h>
 
-#include <asm/pmu.h>
 #include <asm/mach/map.h>
 
 #include "setup.h"
@@ -154,7 +154,6 @@ static const char * stericsson_dt_platform_compat[] = {
 };
 
 DT_MACHINE_START(U8500_DT, "ST-Ericsson Ux5x0 platform (Device Tree Support)")
-	.smp            = smp_ops(ux500_smp_ops),
 	.map_io		= u8500_map_io,
 	.init_irq	= ux500_init_irq,
 	/* we re-use nomadik timer here */
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
index e31d3d61c998..41b81c4fbe63 100644
--- a/arch/arm/mach-ux500/cpu.c
+++ b/arch/arm/mach-ux500/cpu.c
@@ -56,7 +56,6 @@ void __init ux500_init_irq(void)
 	struct device_node *np;
 	struct resource r;
 
-	gic_set_irqchip_flags(IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND);
 	irqchip_init();
 	np = of_find_compatible_node(NULL, NULL, "stericsson,db8500-prcmu");
 	of_address_to_resource(np, 0, &r);
@@ -72,21 +71,12 @@ void __init ux500_init_irq(void)
 	 * Init clocks here so that they are available for system timer
 	 * initialization.
 	 */
-	if (cpu_is_u8500_family()) {
-		u8500_of_clk_init(U8500_CLKRST1_BASE,
-				  U8500_CLKRST2_BASE,
-				  U8500_CLKRST3_BASE,
-				  U8500_CLKRST5_BASE,
-				  U8500_CLKRST6_BASE);
-	} else if (cpu_is_u9540()) {
-		u9540_clk_init(U8500_CLKRST1_BASE, U8500_CLKRST2_BASE,
-			       U8500_CLKRST3_BASE, U8500_CLKRST5_BASE,
-			       U8500_CLKRST6_BASE);
-	} else if (cpu_is_u8540()) {
-		u8540_clk_init(U8500_CLKRST1_BASE, U8500_CLKRST2_BASE,
-			       U8500_CLKRST3_BASE, U8500_CLKRST5_BASE,
-			       U8500_CLKRST6_BASE);
-	}
+	if (cpu_is_u8500_family())
+		u8500_clk_init();
+	else if (cpu_is_u9540())
+		u9540_clk_init();
+	else if (cpu_is_u8540())
+		u8540_clk_init();
 }
 
 static const char * __init ux500_get_machine(void)
diff --git a/arch/arm/mach-ux500/headsmp.S b/arch/arm/mach-ux500/headsmp.S
deleted file mode 100644
index 9cdea049485d..000000000000
--- a/arch/arm/mach-ux500/headsmp.S
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- *  Copyright (c) 2009 ST-Ericsson
- *	This file is based  ARM Realview platform
- *  Copyright (c) 2003 ARM Limited
- *  All Rights Reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-
-/*
- * U8500 specific entry point for secondary CPUs.
- */
-ENTRY(u8500_secondary_startup)
-	mrc	p15, 0, r0, c0, c0, 5
-	and	r0, r0, #15
-	adr	r4, 1f
-	ldmia	r4, {r5, r6}
-	sub	r4, r4, r5
-	add	r6, r6, r4
-pen:	ldr	r7, [r6]
-	cmp	r7, r0
-	bne	pen
-
-	/*
-	 * we've been released from the holding pen: secondary_stack
-	 * should now contain the SVC stack for this core
-	 */
-	b	secondary_startup
-ENDPROC(u8500_secondary_startup)
-
-	.align 2
-1:	.long	.
-	.long	pen_release
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index 62b1de922bd8..70766b963758 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -28,135 +28,81 @@
 #include "db8500-regs.h"
 #include "id.h"
 
-static void __iomem *scu_base;
-static void __iomem *backupram;
-
-/* This is called from headsmp.S to wakeup the secondary core */
-extern void u8500_secondary_startup(void);
-
-/*
- * Write pen_release in a way that is guaranteed to be visible to all
- * observers, irrespective of whether they're taking part in coherency
- * or not.  This is necessary for the hotplug code to work reliably.
- */
-static void write_pen_release(int val)
-{
-	pen_release = val;
-	smp_wmb();
-	sync_cache_w(&pen_release);
-}
-
-static DEFINE_SPINLOCK(boot_lock);
-
-static void ux500_secondary_init(unsigned int cpu)
-{
-	/*
-	 * let the primary processor know we're out of the
-	 * pen, then head off into the C entry point
-	 */
-	write_pen_release(-1);
-
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
-}
+/* Magic triggers in backup RAM */
+#define UX500_CPU1_JUMPADDR_OFFSET 0x1FF4
+#define UX500_CPU1_WAKEMAGIC_OFFSET 0x1FF0
 
-static int ux500_boot_secondary(unsigned int cpu, struct task_struct *idle)
+static void wakeup_secondary(void)
 {
-	unsigned long timeout;
-
-	/*
-	 * set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	spin_lock(&boot_lock);
-
-	/*
-	 * The secondary processor is waiting to be released from
-	 * the holding pen - release it, then wait for it to flag
-	 * that it has been released by resetting pen_release.
-	 */
-	write_pen_release(cpu_logical_map(cpu));
-
-	arch_send_wakeup_ipi_mask(cpumask_of(cpu));
+	struct device_node *np;
+	static void __iomem *backupram;
 
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (pen_release == -1)
-			break;
+	np = of_find_compatible_node(NULL, NULL, "ste,dbx500-backupram");
+	if (!np) {
+		pr_err("No backupram base address\n");
+		return;
+	}
+	backupram = of_iomap(np, 0);
+	of_node_put(np);
+	if (!backupram) {
+		pr_err("No backupram remap\n");
+		return;
 	}
 
 	/*
-	 * now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	spin_unlock(&boot_lock);
-
-	return pen_release != -1 ? -ENOSYS : 0;
-}
-
-static void __init wakeup_secondary(void)
-{
-	/*
 	 * write the address of secondary startup into the backup ram register
 	 * at offset 0x1FF4, then write the magic number 0xA1FEED01 to the
 	 * backup ram register at offset 0x1FF0, which is what boot rom code
-	 * is waiting for. This would wake up the secondary core from WFE
+	 * is waiting for. This will wake up the secondary core from WFE.
 	 */
-#define UX500_CPU1_JUMPADDR_OFFSET 0x1FF4
-	__raw_writel(virt_to_phys(u8500_secondary_startup),
-		     backupram + UX500_CPU1_JUMPADDR_OFFSET);
-
-#define UX500_CPU1_WAKEMAGIC_OFFSET 0x1FF0
-	__raw_writel(0xA1FEED01,
-		     backupram + UX500_CPU1_WAKEMAGIC_OFFSET);
+	writel(virt_to_phys(secondary_startup),
+	       backupram + UX500_CPU1_JUMPADDR_OFFSET);
+	writel(0xA1FEED01,
+	       backupram + UX500_CPU1_WAKEMAGIC_OFFSET);
 
 	/* make sure write buffer is drained */
 	mb();
+	iounmap(backupram);
 }
 
-/*
- * Initialise the CPU possible map early - this describes the CPUs
- * which may be present or become present in the system.
- */
-static void __init ux500_smp_init_cpus(void)
+static void __init ux500_smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int i, ncores;
 	struct device_node *np;
+	static void __iomem *scu_base;
+	unsigned int ncores;
+	int i;
 
 	np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-scu");
+	if (!np) {
+		pr_err("No SCU base address\n");
+		return;
+	}
 	scu_base = of_iomap(np, 0);
 	of_node_put(np);
-	if (!scu_base)
+	if (!scu_base) {
+		pr_err("No SCU remap\n");
 		return;
-	backupram = ioremap(U8500_BACKUPRAM0_BASE, SZ_8K);
-	ncores = scu_get_core_count(scu_base);
-
-	/* sanity check */
-	if (ncores > nr_cpu_ids) {
-		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
-			ncores, nr_cpu_ids);
-		ncores = nr_cpu_ids;
 	}
 
+	scu_enable(scu_base);
+	ncores = scu_get_core_count(scu_base);
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
+	iounmap(scu_base);
 }
 
-static void __init ux500_smp_prepare_cpus(unsigned int max_cpus)
+static int ux500_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	scu_enable(scu_base);
 	wakeup_secondary();
+	arch_send_wakeup_ipi_mask(cpumask_of(cpu));
+	return 0;
 }
 
 struct smp_operations ux500_smp_ops __initdata = {
-	.smp_init_cpus		= ux500_smp_init_cpus,
 	.smp_prepare_cpus	= ux500_smp_prepare_cpus,
-	.smp_secondary_init	= ux500_secondary_init,
 	.smp_boot_secondary	= ux500_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= ux500_cpu_die,
 #endif
 };
+CPU_METHOD_OF_DECLARE(ux500_smp, "ste,dbx500-smp", &ux500_smp_ops);
diff --git a/arch/arm/mach-ux500/setup.h b/arch/arm/mach-ux500/setup.h
index 1fb6ad2789f1..65876eac0761 100644
--- a/arch/arm/mach-ux500/setup.h
+++ b/arch/arm/mach-ux500/setup.h
@@ -26,7 +26,6 @@ extern struct device *ux500_soc_device_init(const char *soc_id);
 
 extern void ux500_timer_init(void);
 
-extern struct smp_operations ux500_smp_ops;
 extern void ux500_cpu_die(unsigned int cpu);
 
 #endif /*  __ASM_ARCH_SETUP_H */
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index b3328cd46c33..1aa4ccece69f 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -80,7 +80,7 @@ static void tc2_pm_cpu_powerdown_prepare(unsigned int cpu, unsigned int cluster)
 	 * to the CPU by disabling the GIC CPU IF to prevent wfi
 	 * from completing execution behind power controller back
 	 */
-	gic_cpu_if_down();
+	gic_cpu_if_down(0);
 }
 
 static void tc2_pm_cluster_powerdown_prepare(unsigned int cluster)
diff --git a/arch/arm/mach-w90x900/irq.c b/arch/arm/mach-w90x900/irq.c
index d66d43ae8df5..491b317daffa 100644
--- a/arch/arm/mach-w90x900/irq.c
+++ b/arch/arm/mach-w90x900/irq.c
@@ -211,6 +211,6 @@ void __init nuc900_init_irq(void)
 	for (irqno = IRQ_WDT; irqno <= IRQ_ADC; irqno++) {
 		irq_set_chip_and_handler(irqno, &nuc900_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(irqno, IRQF_VALID);
+		irq_clear_status_flags(irqno, IRQ_NOREQUEST);
 	}
 }
diff --git a/arch/arm/mach-w90x900/time.c b/arch/arm/mach-w90x900/time.c
index 9230d3725599..cd1966ec9143 100644
--- a/arch/arm/mach-w90x900/time.c
+++ b/arch/arm/mach-w90x900/time.c
@@ -48,31 +48,32 @@
 
 static unsigned int timer0_load;
 
-static void nuc900_clockevent_setmode(enum clock_event_mode mode,
-		struct clock_event_device *clk)
+static int nuc900_clockevent_shutdown(struct clock_event_device *evt)
 {
-	unsigned int val;
+	unsigned int val = __raw_readl(REG_TCSR0) & ~(0x03 << 27);
 
-	val = __raw_readl(REG_TCSR0);
-	val &= ~(0x03 << 27);
+	__raw_writel(val, REG_TCSR0);
+	return 0;
+}
+
+static int nuc900_clockevent_set_oneshot(struct clock_event_device *evt)
+{
+	unsigned int val = __raw_readl(REG_TCSR0) & ~(0x03 << 27);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		__raw_writel(timer0_load, REG_TICR0);
-		val |= (PERIOD | COUNTEN | INTEN | PRESCALE);
-		break;
+	val |= (ONESHOT | COUNTEN | INTEN | PRESCALE);
 
-	case CLOCK_EVT_MODE_ONESHOT:
-		val |= (ONESHOT | COUNTEN | INTEN | PRESCALE);
-		break;
+	__raw_writel(val, REG_TCSR0);
+	return 0;
+}
 
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+static int nuc900_clockevent_set_periodic(struct clock_event_device *evt)
+{
+	unsigned int val = __raw_readl(REG_TCSR0) & ~(0x03 << 27);
 
+	__raw_writel(timer0_load, REG_TICR0);
+	val |= (PERIOD | COUNTEN | INTEN | PRESCALE);
 	__raw_writel(val, REG_TCSR0);
+	return 0;
 }
 
 static int nuc900_clockevent_setnextevent(unsigned long evt,
@@ -90,11 +91,15 @@ static int nuc900_clockevent_setnextevent(unsigned long evt,
 }
 
 static struct clock_event_device nuc900_clockevent_device = {
-	.name		= "nuc900-timer0",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= nuc900_clockevent_setmode,
-	.set_next_event	= nuc900_clockevent_setnextevent,
-	.rating		= 300,
+	.name			= "nuc900-timer0",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= nuc900_clockevent_shutdown,
+	.set_state_periodic	= nuc900_clockevent_set_periodic,
+	.set_state_oneshot	= nuc900_clockevent_set_oneshot,
+	.tick_resume		= nuc900_clockevent_shutdown,
+	.set_next_event		= nuc900_clockevent_setnextevent,
+	.rating			= 300,
 };
 
 /*IRQ handler for the timer*/
diff --git a/arch/arm/mach-zx/Kconfig b/arch/arm/mach-zx/Kconfig
index 2a910dc0d15e..7fdc5bf24f9b 100644
--- a/arch/arm/mach-zx/Kconfig
+++ b/arch/arm/mach-zx/Kconfig
@@ -13,6 +13,7 @@ config SOC_ZX296702
 	select ARM_GLOBAL_TIMER
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
+	select PM_GENERIC_DOMAINS
 	help
 	  Support for ZTE ZX296702 SoC which is a dual core CortexA9MP
 endif
diff --git a/arch/arm/mach-zx/Makefile b/arch/arm/mach-zx/Makefile
index 7c2edf6e5f8b..a4b486433209 100644
--- a/arch/arm/mach-zx/Makefile
+++ b/arch/arm/mach-zx/Makefile
@@ -1,2 +1,2 @@
-obj-$(CONFIG_SOC_ZX296702) += zx296702.o
+obj-$(CONFIG_SOC_ZX296702) += zx296702.o zx296702-pm-domain.o
 obj-$(CONFIG_SMP) += headsmp.o platsmp.o
diff --git a/arch/arm/mach-zx/zx296702-pm-domain.c b/arch/arm/mach-zx/zx296702-pm-domain.c
new file mode 100644
index 000000000000..e08574d4e2ca
--- /dev/null
+++ b/arch/arm/mach-zx/zx296702-pm-domain.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd.
+ *
+ * Author: Jun Nie <jun.nie@linaro.org>
+ * License terms: GNU General Public License (GPL) version 2
+ */
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/slab.h>
+
+#define PCU_DM_CLKEN        0x18
+#define PCU_DM_RSTEN        0x1C
+#define PCU_DM_ISOEN        0x20
+#define PCU_DM_PWRDN        0x24
+#define PCU_DM_ACK_SYNC     0x28
+
+enum {
+	PCU_DM_NEON0 = 0,
+	PCU_DM_NEON1,
+	PCU_DM_GPU,
+	PCU_DM_DECPPU,
+	PCU_DM_VOU,
+	PCU_DM_R2D,
+	PCU_DM_TOP,
+};
+
+static void __iomem *pcubase;
+
+struct zx_pm_domain {
+	struct generic_pm_domain dm;
+	unsigned int bit;
+};
+
+static int normal_power_off(struct generic_pm_domain *domain)
+{
+	struct zx_pm_domain *zpd = (struct zx_pm_domain *)domain;
+	unsigned long loop = 1000;
+	u32 tmp;
+
+	tmp = readl_relaxed(pcubase + PCU_DM_CLKEN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp, pcubase + PCU_DM_CLKEN);
+	udelay(5);
+
+	tmp = readl_relaxed(pcubase + PCU_DM_ISOEN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp | BIT(zpd->bit), pcubase + PCU_DM_ISOEN);
+	udelay(5);
+
+	tmp = readl_relaxed(pcubase + PCU_DM_RSTEN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp, pcubase + PCU_DM_RSTEN);
+	udelay(5);
+
+	tmp = readl_relaxed(pcubase + PCU_DM_PWRDN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp | BIT(zpd->bit), pcubase + PCU_DM_PWRDN);
+	do {
+		tmp = readl_relaxed(pcubase + PCU_DM_ACK_SYNC) & BIT(zpd->bit);
+	} while (--loop && !tmp);
+
+	if (!loop) {
+		pr_err("Error: %s %s fail\n", __func__, domain->name);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int normal_power_on(struct generic_pm_domain *domain)
+{
+	struct zx_pm_domain *zpd = (struct zx_pm_domain *)domain;
+	unsigned long loop = 10000;
+	u32 tmp;
+
+	tmp = readl_relaxed(pcubase + PCU_DM_PWRDN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp, pcubase + PCU_DM_PWRDN);
+	do {
+		tmp = readl_relaxed(pcubase + PCU_DM_ACK_SYNC) & BIT(zpd->bit);
+	} while (--loop && tmp);
+
+	if (!loop) {
+		pr_err("Error: %s %s fail\n", __func__, domain->name);
+		return -EIO;
+	}
+
+	tmp = readl_relaxed(pcubase + PCU_DM_RSTEN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp | BIT(zpd->bit), pcubase + PCU_DM_RSTEN);
+	udelay(5);
+
+	tmp = readl_relaxed(pcubase + PCU_DM_ISOEN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp, pcubase + PCU_DM_ISOEN);
+	udelay(5);
+
+	tmp = readl_relaxed(pcubase + PCU_DM_CLKEN);
+	tmp &= ~BIT(zpd->bit);
+	writel_relaxed(tmp | BIT(zpd->bit), pcubase + PCU_DM_CLKEN);
+	udelay(5);
+	return 0;
+}
+
+static struct zx_pm_domain gpu_domain = {
+	.dm = {
+		.name		= "gpu_domain",
+		.power_off	= normal_power_off,
+		.power_on	= normal_power_on,
+	},
+	.bit = PCU_DM_GPU,
+};
+
+static struct zx_pm_domain decppu_domain = {
+	.dm = {
+		.name		= "decppu_domain",
+		.power_off	= normal_power_off,
+		.power_on	= normal_power_on,
+	},
+	.bit = PCU_DM_DECPPU,
+};
+
+static struct zx_pm_domain vou_domain = {
+	.dm = {
+		.name		= "vou_domain",
+		.power_off	= normal_power_off,
+		.power_on	= normal_power_on,
+	},
+	.bit = PCU_DM_VOU,
+};
+
+static struct zx_pm_domain r2d_domain = {
+	.dm = {
+		.name		= "r2d_domain",
+		.power_off	= normal_power_off,
+		.power_on	= normal_power_on,
+	},
+	.bit = PCU_DM_R2D,
+};
+
+static struct generic_pm_domain *zx296702_pm_domains[] = {
+	&vou_domain.dm,
+	&gpu_domain.dm,
+	&decppu_domain.dm,
+	&r2d_domain.dm,
+};
+
+static int zx296702_pd_probe(struct platform_device *pdev)
+{
+	struct genpd_onecell_data *genpd_data;
+	struct resource *res;
+	int i;
+
+	genpd_data = devm_kzalloc(&pdev->dev, sizeof(*genpd_data), GFP_KERNEL);
+	if (!genpd_data)
+		return -ENOMEM;
+
+	genpd_data->domains = zx296702_pm_domains;
+	genpd_data->num_domains = ARRAY_SIZE(zx296702_pm_domains);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "no memory resource defined\n");
+		return -ENODEV;
+	}
+
+	pcubase = devm_ioremap_resource(&pdev->dev, res);
+	if (!pcubase) {
+		dev_err(&pdev->dev, "ioremap fail.\n");
+		return -EIO;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(zx296702_pm_domains); ++i)
+		pm_genpd_init(zx296702_pm_domains[i], NULL, false);
+
+	of_genpd_add_provider_onecell(pdev->dev.of_node, genpd_data);
+	return 0;
+}
+
+static const struct of_device_id zx296702_pm_domain_matches[] __initconst = {
+	{ .compatible = "zte,zx296702-pcu", },
+	{ },
+};
+
+static struct platform_driver zx296702_pd_driver __initdata = {
+	.driver = {
+		.name = "zx-powerdomain",
+		.owner = THIS_MODULE,
+		.of_match_table = zx296702_pm_domain_matches,
+	},
+	.probe = zx296702_pd_probe,
+};
+
+static int __init zx296702_pd_init(void)
+{
+	return platform_driver_register(&zx296702_pd_driver);
+}
+subsys_initcall(zx296702_pd_init);
diff --git a/arch/arm/mach-zx/zx296702.c b/arch/arm/mach-zx/zx296702.c
index 60bb1a8e1bf1..a041e13ab0ac 100644
--- a/arch/arm/mach-zx/zx296702.c
+++ b/arch/arm/mach-zx/zx296702.c
@@ -13,7 +13,7 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 
-static const char *zx296702_dt_compat[] __initconst = {
+static const char *const zx296702_dt_compat[] __initconst = {
 	"zte,zx296702",
 	NULL,
 };
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 616d5840fc2e..5a6e4e20ca0a 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -186,7 +186,6 @@ static void __init zynq_map_io(void)
 
 static void __init zynq_irq_init(void)
 {
-	gic_set_irqchip_flags(IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND);
 	irqchip_init();
 }
 
@@ -197,8 +196,8 @@ static const char * const zynq_dt_match[] = {
 
 DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform")
 	/* 64KB way size, 8-way associativity, parity disabled */
-	.l2c_aux_val	= 0x00000000,
-	.l2c_aux_mask	= 0xffffffff,
+	.l2c_aux_val    = 0x00400000,
+	.l2c_aux_mask	= 0xffbfffff,
 	.smp		= smp_ops(zynq_smp_ops),
 	.map_io		= zynq_map_io,
 	.init_irq	= zynq_irq_init,
diff --git a/arch/arm/mach-zynq/headsmp.S b/arch/arm/mach-zynq/headsmp.S
index 045c72720a4d..f6d5de073e34 100644
--- a/arch/arm/mach-zynq/headsmp.S
+++ b/arch/arm/mach-zynq/headsmp.S
@@ -18,7 +18,7 @@ ARM_BE8(rev	r0, r0)
 .globl zynq_secondary_trampoline_jump
 zynq_secondary_trampoline_jump:
 	/* Space for jumping address */
-	.word	/* cpu 1 */
+	.word	0	/* cpu 1 */
 .globl zynq_secondary_trampoline_end
 zynq_secondary_trampoline_end:
 ENDPROC(zynq_secondary_trampoline)
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7c6b976ab8d3..df7537f12469 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -883,6 +883,7 @@ config OUTER_CACHE
 
 config OUTER_CACHE_SYNC
 	bool
+	select ARM_HEAVY_MB
 	help
 	  The outer cache has a outer_cache_fns.sync function pointer
 	  that can be used to drain the write buffer of the outer cache.
@@ -1031,6 +1032,9 @@ config ARCH_HAS_BARRIERS
 	  This option allows the use of custom mandatory barriers
 	  included via the mach/barriers.h file.
 
+config ARM_HEAVY_MB
+	bool
+
 config ARCH_SUPPORTS_BIG_ENDIAN
 	bool
 	help
diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S
index 54473cd4aba9..b3b31e30cadd 100644
--- a/arch/arm/mm/abort-ev4.S
+++ b/arch/arm/mm/abort-ev4.S
@@ -19,6 +19,7 @@ ENTRY(v4_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	ldr	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable userspace access
 	bic	r1, r1, #1 << 11 | 1 << 10	@ clear bits 11 and 10 of FSR
 	tst	r3, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S
index a0908d4653a3..a6a381a6caa5 100644
--- a/arch/arm/mm/abort-ev5t.S
+++ b/arch/arm/mm/abort-ev5t.S
@@ -21,8 +21,10 @@ ENTRY(v5t_early_abort)
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable user access
 	bic	r1, r1, #1 << 11		@ clear bits 11 of FSR
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ check write
 	orreq	r1, r1, #1 << 11
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S
index 4006b7a61264..00ab011bef58 100644
--- a/arch/arm/mm/abort-ev5tj.S
+++ b/arch/arm/mm/abort-ev5tj.S
@@ -24,7 +24,9 @@ ENTRY(v5tj_early_abort)
 	bne	do_DataAbort
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
-	do_ldrd_abort tmp=ip, insn=r3
+	uaccess_disable ip			@ disable userspace access
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8c48c5c22a33..8801a15aa105 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,16 +26,18 @@ ENTRY(v6_early_abort)
 	ldr	ip, =0x4107b36
 	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
 	teq	ip, r3, lsr #4			@ r0 ARM1136?
-	bne	do_DataAbort
+	bne	1f
 	tst	r5, #PSR_J_BIT			@ Java?
 	tsteq	r5, #PSR_T_BIT			@ Thumb?
-	bne	do_DataAbort
+	bne	1f
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
  ARM_BE8(rev	r3, r3)
 
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	1f				@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 #endif
+1:	uaccess_disable ip			@ disable userspace access
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 4812ad054214..e8d0e08c227f 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -15,6 +15,7 @@
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
+	uaccess_disable ip			@ disable userspace access
 
 	/*
 	 * V6 code adjusts the returned DFSR.
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index f3982580c273..6d8e8e3365d1 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -26,6 +26,7 @@ ENTRY(v4t_late_abort)
 #endif
 	bne	.data_thumb_abort
 	ldr	r8, [r4]			@ read arm instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
 	and	r7, r8, #15 << 24
@@ -155,6 +156,7 @@ ENTRY(v4t_late_abort)
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 11			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 8			@ yes
 	and	r7, r8, #15 << 12
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 2cbf68ef0e83..4509bee4e081 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -13,6 +13,7 @@
 	tst	\psr, #PSR_T_BIT
 	beq	not_thumb
 	ldrh	\tmp, [\pc]			@ Read aborted Thumb instruction
+	uaccess_disable ip			@ disable userspace access
 	and	\tmp, \tmp, # 0xfe00		@ Mask opcode field
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes
@@ -29,12 +30,9 @@ not_thumb:
  *   [7:4] == 1101
  *    [20] == 0
  */
-	.macro	do_ldrd_abort, tmp, insn
-	tst	\insn, #0x0e100000		@ [27:25,20] == 0
-	bne	not_ldrd
-	and	\tmp, \insn, #0x000000f0	@ [7:4] == 1101
-	cmp	\tmp, #0x000000d0
-	beq	do_DataAbort
-not_ldrd:
+	.macro	teq_ldrd, tmp, insn
+	mov	\tmp, #0x0e100000
+	orr	\tmp, #0x000000f0
+	and	\tmp, \insn, \tmp
+	teq	\tmp, #0x000000d0
 	.endm
-
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 097181e08c25..5c1b7a7b9af6 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -368,7 +368,6 @@ int __init feroceon_of_init(void)
 	struct device_node *node;
 	void __iomem *base;
 	bool l2_wt_override = false;
-	struct resource res;
 
 #if defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH)
 	l2_wt_override = true;
@@ -376,10 +375,7 @@ int __init feroceon_of_init(void)
 
 	node = of_find_matching_node(NULL, feroceon_ids);
 	if (node && of_device_is_compatible(node, "marvell,kirkwood-cache")) {
-		if (of_address_to_resource(node, 0, &res))
-			return -ENODEV;
-
-		base = ioremap(res.start, resource_size(&res));
+		base = of_iomap(node, 0);
 		if (!base)
 			return -ENOMEM;
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 71b3d3309024..493692d838c6 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1171,6 +1171,11 @@ static void __init l2c310_of_parse(const struct device_node *np,
 		}
 	}
 
+	if (of_property_read_bool(np, "arm,shared-override")) {
+		*aux_val |= L2C_AUX_CTRL_SHARED_OVERRIDE;
+		*aux_mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
+	}
+
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
 
 	ret = of_property_read_u32(np, "arm,double-linefill", &val);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1ced8a0f7a52..bf35abcc7d59 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -39,6 +39,7 @@
 #include <asm/system_info.h>
 #include <asm/dma-contiguous.h>
 
+#include "dma.h"
 #include "mm.h"
 
 /*
@@ -648,14 +649,18 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	size = PAGE_ALIGN(size);
 	want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs);
 
-	if (is_coherent || nommu())
+	if (nommu())
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT))
+		addr = __alloc_from_contiguous(dev, size, prot, &page,
+					       caller, want_vaddr);
+	else if (is_coherent)
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!dev_get_cma_area(dev))
-		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller, want_vaddr);
 	else
-		addr = __alloc_from_contiguous(dev, size, prot, &page, caller, want_vaddr);
+		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page,
+					    caller, want_vaddr);
 
 	if (page)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
@@ -683,13 +688,12 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
 		return memory;
 
-	return __dma_alloc(dev, size, handle, gfp, prot, true,
+	return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true,
 			   attrs, __builtin_return_address(0));
 }
 
@@ -753,12 +757,12 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 
 	size = PAGE_ALIGN(size);
 
-	if (is_coherent || nommu()) {
+	if (nommu()) {
 		__dma_free_buffer(page, size);
-	} else if (__free_from_pool(cpu_addr, size)) {
+	} else if (!is_coherent && __free_from_pool(cpu_addr, size)) {
 		return;
 	} else if (!dev_get_cma_area(dev)) {
-		if (want_vaddr)
+		if (want_vaddr && !is_coherent)
 			__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
@@ -1520,7 +1524,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
-		phys_addr_t phys = page_to_phys(sg_page(s));
+		phys_addr_t phys = sg_phys(s) & PAGE_MASK;
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
 		if (!is_coherent &&
@@ -1971,7 +1975,7 @@ static int extend_iommu_mapping(struct dma_iommu_mapping *mapping)
 {
 	int next_bitmap;
 
-	if (mapping->nr_bitmaps > mapping->extensions)
+	if (mapping->nr_bitmaps >= mapping->extensions)
 		return -EINVAL;
 
 	next_bitmap = mapping->nr_bitmaps;
diff --git a/arch/arm/mm/dma.h b/arch/arm/mm/dma.h
new file mode 100644
index 000000000000..70ea6852f94e
--- /dev/null
+++ b/arch/arm/mm/dma.h
@@ -0,0 +1,32 @@
+#ifndef DMA_H
+#define DMA_H
+
+#include <asm/glue-cache.h>
+
+#ifndef MULTI_CACHE
+#define dmac_map_area			__glue(_CACHE,_dma_map_area)
+#define dmac_unmap_area 		__glue(_CACHE,_dma_unmap_area)
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+extern void dmac_map_area(const void *, size_t, int);
+extern void dmac_unmap_area(const void *, size_t, int);
+
+#else
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+#define dmac_map_area			cpu_cache.dma_map_area
+#define dmac_unmap_area 		cpu_cache.dma_unmap_area
+
+#endif
+
+#endif
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 34b66af516ea..1ec8e7590fc6 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -21,6 +21,21 @@
 
 #include "mm.h"
 
+#ifdef CONFIG_ARM_HEAVY_MB
+void (*soc_mb)(void);
+
+void arm_heavy_mb(void)
+{
+#ifdef CONFIG_OUTER_CACHE_SYNC
+	if (outer_cache.sync)
+		outer_cache.sync();
+#endif
+	if (soc_mb)
+		soc_mb();
+}
+EXPORT_SYMBOL(arm_heavy_mb);
+#endif
+
 #ifdef CONFIG_CPU_CACHE_VIPT
 
 static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index ee8dfa793989..9df5f09585ca 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -79,7 +79,7 @@ void *kmap_atomic(struct page *page)
 
 	type = kmap_atomic_idx_push();
 
-	idx = type + KM_TYPE_NR * smp_processor_id();
+	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
@@ -106,7 +106,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (kvaddr >= (void *)FIXADDR_START) {
 		type = kmap_atomic_idx();
-		idx = type + KM_TYPE_NR * smp_processor_id();
+		idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
@@ -138,7 +138,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 		return page_address(page);
 
 	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR * smp_processor_id();
+	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index d1e5ad7ab3bc..0c81056c1dd7 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -255,7 +255,7 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 }
 #endif
 
-void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
+static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	unsigned long offset, size_t size, unsigned int mtype, void *caller)
 {
 	const struct mem_type *type;
@@ -363,7 +363,7 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
 		  unsigned int mtype)
 {
 	return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
-			__builtin_return_address(0));
+					__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
@@ -371,13 +371,26 @@ void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 				      unsigned int, void *) =
 	__arm_ioremap_caller;
 
-void __iomem *
-__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
 {
-	return arch_ioremap_caller(phys_addr, size, mtype,
-		__builtin_return_address(0));
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				   __builtin_return_address(0));
 }
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap_wc);
 
 /*
  * Remap an arbitrary physical address space into the kernel virtual
@@ -431,11 +444,11 @@ void __iounmap(volatile void __iomem *io_addr)
 
 void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
 
-void __arm_iounmap(volatile void __iomem *io_addr)
+void iounmap(volatile void __iomem *cookie)
 {
-	arch_iounmap(io_addr);
+	arch_iounmap(cookie);
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
 
 #ifdef CONFIG_PCI
 static int pci_ioremap_mem_type = MT_DEVICE;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6ca7d9aa896f..7cd15143a507 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -291,13 +291,13 @@ static struct mem_type mem_types[] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_HIGH_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_USER | L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_MEMORY_RWX] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
@@ -357,6 +357,47 @@ const struct mem_type *get_mem_type(unsigned int type)
 }
 EXPORT_SYMBOL(get_mem_type);
 
+static pte_t *(*pte_offset_fixmap)(pmd_t *dir, unsigned long addr);
+
+static pte_t bm_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+	__aligned(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE) __initdata;
+
+static pte_t * __init pte_offset_early_fixmap(pmd_t *dir, unsigned long addr)
+{
+	return &bm_pte[pte_index(addr)];
+}
+
+static pte_t *pte_offset_late_fixmap(pmd_t *dir, unsigned long addr)
+{
+	return pte_offset_kernel(dir, addr);
+}
+
+static inline pmd_t * __init fixmap_pmd(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	pud_t *pud = pud_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
+
+	return pmd;
+}
+
+void __init early_fixmap_init(void)
+{
+	pmd_t *pmd;
+
+	/*
+	 * The early fixmap range spans multiple pmds, for which
+	 * we are not prepared:
+	 */
+	BUILD_BUG_ON((__fix_to_virt(__end_of_permanent_fixed_addresses) >> PMD_SHIFT)
+		     != FIXADDR_TOP >> PMD_SHIFT);
+
+	pmd = fixmap_pmd(FIXADDR_TOP);
+	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+
+	pte_offset_fixmap = pte_offset_early_fixmap;
+}
+
 /*
  * To avoid TLB flush broadcasts, this uses local_flush_tlb_kernel_range().
  * As a result, this can only be called with preemption disabled, as under
@@ -365,7 +406,7 @@ EXPORT_SYMBOL(get_mem_type);
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
-	pte_t *pte = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+	pte_t *pte = pte_offset_fixmap(pmd_off_k(vaddr), vaddr);
 
 	/* Make sure fixmap region does not exceed available allocation. */
 	BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) >
@@ -855,7 +896,7 @@ static void __init create_mapping(struct map_desc *md)
 	}
 
 	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET &&
+	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
 	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
 		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
 			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
@@ -1072,6 +1113,7 @@ void __init sanity_check_meminfo(void)
 	int highmem = 0;
 	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
 	struct memblock_region *reg;
+	bool should_use_highmem = false;
 
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
@@ -1090,6 +1132,7 @@ void __init sanity_check_meminfo(void)
 				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
 					  &block_start, &block_end);
 				memblock_remove(reg->base, reg->size);
+				should_use_highmem = true;
 				continue;
 			}
 
@@ -1100,6 +1143,7 @@ void __init sanity_check_meminfo(void)
 					  &block_start, &block_end, &vmalloc_limit);
 				memblock_remove(vmalloc_limit, overlap_size);
 				block_end = vmalloc_limit;
+				should_use_highmem = true;
 			}
 		}
 
@@ -1134,6 +1178,9 @@ void __init sanity_check_meminfo(void)
 		}
 	}
 
+	if (should_use_highmem)
+		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
@@ -1213,10 +1260,10 @@ void __init arm_mm_memblock_reserve(void)
 
 /*
  * Set up the device mappings.  Since we clear out the page tables for all
- * mappings above VMALLOC_START, we will remove any debug device mappings.
- * This means you have to be careful how you debug this function, or any
- * called function.  This means you can't use any function or debugging
- * method which may touch any device, otherwise the kernel _will_ crash.
+ * mappings above VMALLOC_START, except early fixmap, we might remove debug
+ * device mappings.  This means earlycon can be used to debug this function
+ * Any other function or debugging method which may touch any device _will_
+ * crash the kernel.
  */
 static void __init devicemaps_init(const struct machine_desc *mdesc)
 {
@@ -1231,7 +1278,10 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 
 	early_trap_init(vectors);
 
-	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
+	/*
+	 * Clear page table except top pmd used by early fixmaps
+	 */
+	for (addr = VMALLOC_START; addr < (FIXADDR_TOP & PMD_MASK); addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
@@ -1483,6 +1533,35 @@ void __init early_paging_init(const struct machine_desc *mdesc)
 
 #endif
 
+static void __init early_fixmap_shutdown(void)
+{
+	int i;
+	unsigned long va = fix_to_virt(__end_of_permanent_fixed_addresses - 1);
+
+	pte_offset_fixmap = pte_offset_late_fixmap;
+	pmd_clear(fixmap_pmd(va));
+	local_flush_tlb_kernel_page(va);
+
+	for (i = 0; i < __end_of_permanent_fixed_addresses; i++) {
+		pte_t *pte;
+		struct map_desc map;
+
+		map.virtual = fix_to_virt(i);
+		pte = pte_offset_early_fixmap(pmd_off_k(map.virtual), map.virtual);
+
+		/* Only i/o device mappings are supported ATM */
+		if (pte_none(*pte) ||
+		    (pte_val(*pte) & L_PTE_MT_MASK) != L_PTE_MT_DEV_SHARED)
+			continue;
+
+		map.pfn = pte_pfn(*pte);
+		map.type = MT_DEVICE;
+		map.length = PAGE_SIZE;
+
+		create_mapping(&map);
+	}
+}
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
@@ -1494,7 +1573,9 @@ void __init paging_init(const struct machine_desc *mdesc)
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	memblock_set_current_limit(arm_lowmem_limit);
 	dma_contiguous_remap();
+	early_fixmap_shutdown();
 	devicemaps_init(mdesc);
 	kmap_init();
 	tcm_init();
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index afd7e05d95f1..1dd10936d68d 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -351,30 +351,43 @@ void __iomem *__arm_ioremap_pfn(unsigned long pfn, unsigned long offset,
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
-			   size_t size, unsigned int mtype, void *caller)
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
+				   unsigned int mtype, void *caller)
 {
-	return __arm_ioremap_pfn(pfn, offset, size, mtype);
+	return (void __iomem *)phys_addr;
 }
 
-void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
-			    unsigned int mtype)
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
 {
-	return (void __iomem *)phys_addr;
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE,
+				    __builtin_return_address(0));
 }
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap);
 
-void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
 
-void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
-				   unsigned int mtype, void *caller)
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iounmap(volatile void __iomem *addr)
 {
-	return __arm_ioremap(phys_addr, size, mtype);
 }
+EXPORT_SYMBOL(__iounmap);
 
 void (*arch_iounmap)(volatile void __iomem *);
 
-void __arm_iounmap(volatile void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index a3681f11dd9f..e683db1b90a3 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -84,6 +84,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		if (!new_pte)
 			goto no_pte;
 
+#ifndef CONFIG_ARM_LPAE
+		/*
+		 * Modify the PTE pointer to have the correct domain.  This
+		 * needs to be the vectors domain to avoid the low vectors
+		 * being unmapped.
+		 */
+		pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK;
+		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
+#endif
+
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 0716bbe19872..de2b246fed38 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -274,7 +274,10 @@ __v7_ca15mp_setup:
 __v7_b15mp_setup:
 __v7_ca17mp_setup:
 	mov	r10, #0
-1:
+1:	adr	r12, __v7_setup_stack		@ the local stack
+	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+	bl      v7_invalidate_l1
+	ldmia	r12, {r0-r5, lr}
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
 	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
@@ -283,7 +286,7 @@ __v7_ca17mp_setup:
 	orreq	r0, r0, r10			@ Enable CPU-specific SMP bits
 	mcreq	p15, 0, r0, c1, c0, 1
 #endif
-	b	__v7_setup
+	b	__v7_setup_cont
 
 /*
  * Errata:
@@ -413,10 +416,11 @@ __v7_pj4b_setup:
 
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, r7, r9, r11, lr}
+	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, r7, r9, r11, lr}
+	ldmia	r12, {r0-r5, lr}
 
+__v7_setup_cont:
 	and	r0, r9, #0xff000000		@ ARM?
 	teq	r0, #0x41000000
 	bne	__errata_finish
@@ -480,7 +484,7 @@ ENDPROC(__v7_setup)
 
 	.align	2
 __v7_setup_stack:
-	.space	4 * 11				@ 11 registers
+	.space	4 * 7				@ 12 registers
 
 	__INITDATA
 
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 4550d247e308..876060bcceeb 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -74,32 +74,52 @@ struct jit_ctx {
 
 int bpf_jit_enable __read_mostly;
 
-static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+static inline int call_neg_helper(struct sk_buff *skb, int offset, void *ret,
+		      unsigned int size)
+{
+	void *ptr = bpf_internal_load_pointer_neg_helper(skb, offset, size);
+
+	if (!ptr)
+		return -EFAULT;
+	memcpy(ret, ptr, size);
+	return 0;
+}
+
+static u64 jit_get_skb_b(struct sk_buff *skb, int offset)
 {
 	u8 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 1);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 1);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 1);
 
 	return (u64)err << 32 | ret;
 }
 
-static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+static u64 jit_get_skb_h(struct sk_buff *skb, int offset)
 {
 	u16 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 2);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 2);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 2);
 
 	return (u64)err << 32 | ntohs(ret);
 }
 
-static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+static u64 jit_get_skb_w(struct sk_buff *skb, int offset)
 {
 	u32 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 4);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 4);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 4);
 
 	return (u64)err << 32 | ntohl(ret);
 }
@@ -536,9 +556,6 @@ static int build_body(struct jit_ctx *ctx)
 		case BPF_LD | BPF_B | BPF_ABS:
 			load_order = 0;
 load:
-			/* the interpreter will deal with the negative K */
-			if ((int)k < 0)
-				return -ENOTSUPP;
 			emit_mov_i(r_off, k, ctx);
 load_common:
 			ctx->seen |= SEEN_DATA | SEEN_CALL;
@@ -547,12 +564,24 @@ load_common:
 				emit(ARM_SUB_I(r_scratch, r_skb_hl,
 					       1 << load_order), ctx);
 				emit(ARM_CMP_R(r_scratch, r_off), ctx);
-				condt = ARM_COND_HS;
+				condt = ARM_COND_GE;
 			} else {
 				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
 				condt = ARM_COND_HI;
 			}
 
+			/*
+			 * test for negative offset, only if we are
+			 * currently scheduled to take the fast
+			 * path. this will update the flags so that
+			 * the slowpath instruction are ignored if the
+			 * offset is negative.
+			 *
+			 * for loard_order == 0 the HI condition will
+			 * make loads at offset 0 take the slow path too.
+			 */
+			_emit(condt, ARM_CMP_I(r_off, 0), ctx);
+
 			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
 			      ctx);
 
@@ -828,7 +857,9 @@ b_epilogue:
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
 		case BPF_ANC | SKF_AD_IFINDEX:
+		case BPF_ANC | SKF_AD_HATYPE:
 			/* A = skb->dev->ifindex */
+			/* A = skb->dev->type */
 			ctx->seen |= SEEN_SKB;
 			off = offsetof(struct sk_buff, dev);
 			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
@@ -838,8 +869,24 @@ b_epilogue:
 
 			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
 						  ifindex) != 4);
-			off = offsetof(struct net_device, ifindex);
-			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  type) != 2);
+
+			if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
+				off = offsetof(struct net_device, ifindex);
+				emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			} else {
+				/*
+				 * offset of field "type" in "struct
+				 * net_device" is above what can be
+				 * used in the ldrh rd, [rn, #imm]
+				 * instruction, so load the offset in
+				 * a register and use ldrh rd, [rn, rm]
+				 */
+				off = offsetof(struct net_device, type);
+				emit_mov_i(ARM_R3, off, ctx);
+				emit(ARM_LDRH_R(r_A, r_scratch, ARM_R3), ctx);
+			}
 			break;
 		case BPF_ANC | SKF_AD_MARK:
 			ctx->seen |= SEEN_SKB;
@@ -860,9 +907,22 @@ b_epilogue:
 			off = offsetof(struct sk_buff, vlan_tci);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
-				OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx);
-			else
-				OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx);
+				OP_IMM3(ARM_AND, r_A, r_A, ~VLAN_TAG_PRESENT, ctx);
+			else {
+				OP_IMM3(ARM_LSR, r_A, r_A, 12, ctx);
+				OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx);
+			}
+			break;
+		case BPF_ANC | SKF_AD_PKTTYPE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  __pkt_type_offset[0]) != 1);
+			off = PKT_TYPE_OFFSET();
+			emit(ARM_LDRB_I(r_A, r_skb, off), ctx);
+			emit(ARM_AND_I(r_A, r_A, PKT_TYPE_MAX), ctx);
+#ifdef __BIG_ENDIAN_BITFIELD
+			emit(ARM_LSR_I(r_A, r_A, 5), ctx);
+#endif
 			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
@@ -873,6 +933,14 @@ b_epilogue:
 			off = offsetof(struct sk_buff, queue_mapping);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			break;
+		case BPF_ANC | SKF_AD_PAY_OFFSET:
+			ctx->seen |= SEEN_SKB | SEEN_CALL;
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			emit_mov_i(ARM_R3, (unsigned int)skb_get_poff, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
 		case BPF_LDX | BPF_W | BPF_ABS:
 			/*
 			 * load a 32bit word from struct seccomp_data.
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index b2d7d92859d3..4b17d5ab652a 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -74,6 +74,7 @@
 #define ARM_INST_LDRB_I		0x05d00000
 #define ARM_INST_LDRB_R		0x07d00000
 #define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDRH_R		0x019000b0
 #define ARM_INST_LDR_I		0x05900000
 
 #define ARM_INST_LDM		0x08900000
@@ -160,6 +161,8 @@
 				 | (rm))
 #define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
 				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
+#define ARM_LDRH_R(rt, rn, rm)	(ARM_INST_LDRH_R | (rt) << 12 | (rn) << 16 \
+				 | (rm))
 
 #define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
 
diff --git a/arch/arm/plat-iop/time.c b/arch/arm/plat-iop/time.c
index 6ad65d8ae237..101e8f2c7abe 100644
--- a/arch/arm/plat-iop/time.c
+++ b/arch/arm/plat-iop/time.c
@@ -77,41 +77,57 @@ static int iop_set_next_event(unsigned long delta,
 
 static unsigned long ticks_per_jiffy;
 
-static void iop_set_mode(enum clock_event_mode mode,
-			 struct clock_event_device *unused)
+static int iop_set_periodic(struct clock_event_device *evt)
 {
 	u32 tmr = read_tmr0();
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		write_tmr0(tmr & ~IOP_TMR_EN);
-		write_tcr0(ticks_per_jiffy - 1);
-		write_trr0(ticks_per_jiffy - 1);
-		tmr |= (IOP_TMR_RELOAD | IOP_TMR_EN);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* ->set_next_event sets period and enables timer */
-		tmr &= ~(IOP_TMR_RELOAD | IOP_TMR_EN);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		tmr |= IOP_TMR_EN;
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	default:
-		tmr &= ~IOP_TMR_EN;
-		break;
-	}
+	write_tmr0(tmr & ~IOP_TMR_EN);
+	write_tcr0(ticks_per_jiffy - 1);
+	write_trr0(ticks_per_jiffy - 1);
+	tmr |= (IOP_TMR_RELOAD | IOP_TMR_EN);
 
 	write_tmr0(tmr);
+	return 0;
+}
+
+static int iop_set_oneshot(struct clock_event_device *evt)
+{
+	u32 tmr = read_tmr0();
+
+	/* ->set_next_event sets period and enables timer */
+	tmr &= ~(IOP_TMR_RELOAD | IOP_TMR_EN);
+	write_tmr0(tmr);
+	return 0;
+}
+
+static int iop_shutdown(struct clock_event_device *evt)
+{
+	u32 tmr = read_tmr0();
+
+	tmr &= ~IOP_TMR_EN;
+	write_tmr0(tmr);
+	return 0;
+}
+
+static int iop_resume(struct clock_event_device *evt)
+{
+	u32 tmr = read_tmr0();
+
+	tmr |= IOP_TMR_EN;
+	write_tmr0(tmr);
+	return 0;
 }
 
 static struct clock_event_device iop_clockevent = {
-	.name		= "iop_timer0",
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating         = 300,
-	.set_next_event	= iop_set_next_event,
-	.set_mode	= iop_set_mode,
+	.name			= "iop_timer0",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 300,
+	.set_next_event		= iop_set_next_event,
+	.set_state_shutdown	= iop_shutdown,
+	.set_state_periodic	= iop_set_periodic,
+	.tick_resume		= iop_resume,
+	.set_state_oneshot	= iop_set_oneshot,
 };
 
 static irqreturn_t
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index 5168a52a17f9..79c33eca09a3 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -407,9 +407,9 @@ static int gpio_irq_set_type(struct irq_data *d, u32 type)
 	return 0;
 }
 
-static void gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void gpio_irq_handler(unsigned __irq, struct irq_desc *desc)
 {
-	struct orion_gpio_chip *ochip = irq_get_handler_data(irq);
+	struct orion_gpio_chip *ochip = irq_desc_get_handler_data(desc);
 	u32 cause, type;
 	int i;
 
@@ -582,8 +582,9 @@ void __init orion_gpio_init(struct device_node *np,
 
 	for (i = 0; i < 4; i++) {
 		if (irqs[i]) {
-			irq_set_handler_data(irqs[i], ochip);
-			irq_set_chained_handler(irqs[i], gpio_irq_handler);
+			irq_set_chained_handler_and_data(irqs[i],
+							 gpio_irq_handler,
+							 ochip);
 		}
 	}
 
diff --git a/arch/arm/plat-orion/time.c b/arch/arm/plat-orion/time.c
index 261258f717fc..8085a8aac812 100644
--- a/arch/arm/plat-orion/time.c
+++ b/arch/arm/plat-orion/time.c
@@ -106,60 +106,63 @@ orion_clkevt_next_event(unsigned long delta, struct clock_event_device *dev)
 	return 0;
 }
 
-static void
-orion_clkevt_mode(enum clock_event_mode mode, struct clock_event_device *dev)
+static int orion_clkevt_shutdown(struct clock_event_device *evt)
 {
 	unsigned long flags;
 	u32 u;
 
 	local_irq_save(flags);
-	if (mode == CLOCK_EVT_MODE_PERIODIC) {
-		/*
-		 * Setup timer to fire at 1/HZ intervals.
-		 */
-		writel(ticks_per_jiffy - 1, timer_base + TIMER1_RELOAD_OFF);
-		writel(ticks_per_jiffy - 1, timer_base + TIMER1_VAL_OFF);
-
-		/*
-		 * Enable timer interrupt.
-		 */
-		u = readl(bridge_base + BRIDGE_MASK_OFF);
-		writel(u | BRIDGE_INT_TIMER1, bridge_base + BRIDGE_MASK_OFF);
-
-		/*
-		 * Enable timer.
-		 */
-		u = readl(timer_base + TIMER_CTRL_OFF);
-		writel(u | TIMER1_EN | TIMER1_RELOAD_EN,
-		       timer_base + TIMER_CTRL_OFF);
-	} else {
-		/*
-		 * Disable timer.
-		 */
-		u = readl(timer_base + TIMER_CTRL_OFF);
-		writel(u & ~TIMER1_EN, timer_base + TIMER_CTRL_OFF);
-
-		/*
-		 * Disable timer interrupt.
-		 */
-		u = readl(bridge_base + BRIDGE_MASK_OFF);
-		writel(u & ~BRIDGE_INT_TIMER1, bridge_base + BRIDGE_MASK_OFF);
-
-		/*
-		 * ACK pending timer interrupt.
-		 */
-		writel(bridge_timer1_clr_mask, bridge_base + BRIDGE_CAUSE_OFF);
-
-	}
+
+	/* Disable timer */
+	u = readl(timer_base + TIMER_CTRL_OFF);
+	writel(u & ~TIMER1_EN, timer_base + TIMER_CTRL_OFF);
+
+	/* Disable timer interrupt */
+	u = readl(bridge_base + BRIDGE_MASK_OFF);
+	writel(u & ~BRIDGE_INT_TIMER1, bridge_base + BRIDGE_MASK_OFF);
+
+	/* ACK pending timer interrupt */
+	writel(bridge_timer1_clr_mask, bridge_base + BRIDGE_CAUSE_OFF);
+
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+static int orion_clkevt_set_periodic(struct clock_event_device *evt)
+{
+	unsigned long flags;
+	u32 u;
+
+	local_irq_save(flags);
+
+	/* Setup timer to fire at 1/HZ intervals */
+	writel(ticks_per_jiffy - 1, timer_base + TIMER1_RELOAD_OFF);
+	writel(ticks_per_jiffy - 1, timer_base + TIMER1_VAL_OFF);
+
+	/* Enable timer interrupt */
+	u = readl(bridge_base + BRIDGE_MASK_OFF);
+	writel(u | BRIDGE_INT_TIMER1, bridge_base + BRIDGE_MASK_OFF);
+
+	/* Enable timer */
+	u = readl(timer_base + TIMER_CTRL_OFF);
+	writel(u | TIMER1_EN | TIMER1_RELOAD_EN, timer_base + TIMER_CTRL_OFF);
+
 	local_irq_restore(flags);
+
+	return 0;
 }
 
 static struct clock_event_device orion_clkevt = {
-	.name		= "orion_tick",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.rating		= 300,
-	.set_next_event	= orion_clkevt_next_event,
-	.set_mode	= orion_clkevt_mode,
+	.name			= "orion_tick",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 300,
+	.set_next_event		= orion_clkevt_next_event,
+	.set_state_shutdown	= orion_clkevt_shutdown,
+	.set_state_periodic	= orion_clkevt_set_periodic,
+	.set_state_oneshot	= orion_clkevt_shutdown,
+	.tick_resume		= orion_clkevt_shutdown,
 };
 
 static irqreturn_t orion_timer_interrupt(int irq, void *dev_id)
diff --git a/arch/arm/plat-pxa/dma.c b/arch/arm/plat-pxa/dma.c
index d92f07f6ecfb..de2b061889ec 100644
--- a/arch/arm/plat-pxa/dma.c
+++ b/arch/arm/plat-pxa/dma.c
@@ -289,7 +289,8 @@ int pxa_request_dma (char *name, pxa_dma_prio prio,
 		/* try grabbing a DMA channel with the requested priority */
 		for (i = 0; i < num_dma_channels; i++) {
 			if ((dma_channels[i].prio == prio) &&
-			    !dma_channels[i].name) {
+			    !dma_channels[i].name &&
+			    !pxad_toggle_reserved_channel(i)) {
 				found = 1;
 				break;
 			}
@@ -326,13 +327,14 @@ void pxa_free_dma (int dma_ch)
 	local_irq_save(flags);
 	DCSR(dma_ch) = DCSR_STARTINTR|DCSR_ENDINTR|DCSR_BUSERR;
 	dma_channels[dma_ch].name = NULL;
+	pxad_toggle_reserved_channel(dma_ch);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(pxa_free_dma);
 
 static irqreturn_t dma_irq_handler(int irq, void *dev_id)
 {
-	int i, dint = DINT;
+	int i, dint = DINT, done = 0;
 	struct dma_channel *channel;
 
 	while (dint) {
@@ -341,16 +343,13 @@ static irqreturn_t dma_irq_handler(int irq, void *dev_id)
 		channel = &dma_channels[i];
 		if (channel->name && channel->irq_handler) {
 			channel->irq_handler(i, channel->data);
-		} else {
-			/*
-			 * IRQ for an unregistered DMA channel:
-			 * let's clear the interrupts and disable it.
-			 */
-			printk (KERN_WARNING "spurious IRQ for DMA channel %d\n", i);
-			DCSR(i) = DCSR_STARTINTR|DCSR_ENDINTR|DCSR_BUSERR;
+			done++;
 		}
 	}
-	return IRQ_HANDLED;
+	if (done)
+		return IRQ_HANDLED;
+	else
+		return IRQ_NONE;
 }
 
 int __init pxa_init_dma(int irq, int num_ch)
@@ -372,7 +371,8 @@ int __init pxa_init_dma(int irq, int num_ch)
 		spin_lock_init(&dma_channels[i].lock);
 	}
 
-	ret = request_irq(irq, dma_irq_handler, 0, "DMA", NULL);
+	ret = request_irq(irq, dma_irq_handler, IRQF_SHARED, "DMA",
+			  dma_channels);
 	if (ret) {
 		printk (KERN_CRIT "Wow!  Can't register IRQ for DMA\n");
 		kfree(dma_channels);
diff --git a/arch/arm/plat-pxa/include/plat/dma.h b/arch/arm/plat-pxa/include/plat/dma.h
index a7b91dc06852..28848b344e2d 100644
--- a/arch/arm/plat-pxa/include/plat/dma.h
+++ b/arch/arm/plat-pxa/include/plat/dma.h
@@ -82,4 +82,19 @@ int pxa_request_dma (char *name,
 
 void pxa_free_dma (int dma_ch);
 
+/*
+ * Cooperation with pxa_dma + dmaengine while there remains at least one pxa
+ * driver not converted to dmaengine.
+ */
+#if defined(CONFIG_PXA_DMA)
+extern int pxad_toggle_reserved_channel(int legacy_channel);
+#else
+static inline int pxad_toggle_reserved_channel(int legacy_channel)
+{
+	return 0;
+}
+#endif
+
+extern void __init pxa2xx_set_dmac_info(int nb_channels);
+
 #endif /* __PLAT_DMA_H */
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index cb8e3d655d1a..57729b915003 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -217,12 +217,6 @@ config SAMSUNG_DEV_PWM
 	help
 	  Compile in platform device definition for PWM Timer
 
-config SAMSUNG_DEV_BACKLIGHT
-	bool
-	depends on SAMSUNG_DEV_PWM
-	help
-	  Compile in platform device definition LCD backlight with PWM Timer
-
 config S3C24XX_PWM
 	bool "PWM device support"
 	select PWM
@@ -231,25 +225,14 @@ config S3C24XX_PWM
 	  Support for exporting the PWM timer blocks via the pwm device
 	  system
 
-config S3C_SETUP_CAMIF
-	bool
-	help
-	  Compile in common setup code for S3C CAMIF devices
-
 config SAMSUNG_PM_GPIO
 	bool
 	default y if GPIO_SAMSUNG && PM
 	help
 	  Include legacy GPIO power management code for platforms not using
 	  pinctrl-samsung driver.
-
 endif
 
-config S5P_DEV_MFC
-	bool
-	help
-	  Compile in setup memory (init) code for MFC
-
 comment "Power management"
 
 config SAMSUNG_PM_DEBUG
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index 1a29ab1f446d..8c911760f55f 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -20,11 +20,6 @@ obj-$(CONFIG_SAMSUNG_ATAGS)	+= platformdata.o
 
 obj-$(CONFIG_SAMSUNG_ATAGS)	+= devs.o
 obj-$(CONFIG_SAMSUNG_ATAGS)	+= dev-uart.o
-obj-$(CONFIG_S5P_DEV_MFC)	+= s5p-dev-mfc.o
-
-obj-$(CONFIG_SAMSUNG_DEV_BACKLIGHT)	+= dev-backlight.o
-
-obj-$(CONFIG_S3C_SETUP_CAMIF)	+= setup-camif.o
 
 # PM support
 
diff --git a/arch/arm/plat-samsung/include/plat/keypad-core.h b/arch/arm/plat-samsung/include/plat/keypad-core.h
deleted file mode 100644
index d513e1b3a31e..000000000000
--- a/arch/arm/plat-samsung/include/plat/keypad-core.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * linux/arch/arm/plat-samsung/include/plat/keypad-core.h
- *
- * Copyright (C) 2010 Samsung Electronics Co.Ltd
- * Author: Joonyoung Shim <jy0922.shim@samsung.com>
- *
- * Samsung keypad controller core function
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
-
-#ifndef __ASM_ARCH_KEYPAD_CORE_H
-#define __ASM_ARCH_KEYPAD_CORE_H
-
-/* These function are only for use with the core support code, such as
- * the cpu specific initialisation code
- */
-
-/* re-define device name depending on support. */
-static inline void samsung_keypad_setname(char *name)
-{
-#ifdef CONFIG_SAMSUNG_DEV_KEYPAD
-	samsung_device_keypad.name = name;
-#endif
-}
-
-#endif /* __ASM_ARCH_KEYPAD_CORE_H */
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 9d259d94e429..1160434eece0 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -14,7 +14,7 @@ VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 VDSO_LDFLAGS += -nostdlib -shared
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id)
-VDSO_LDFLAGS += $(call cc-option, -fuse-ld=bfd)
+VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd)
 
 obj-$(CONFIG_VDSO) += vdso.o
 extra-$(CONFIG_VDSO) += vdso.lds
diff --git a/arch/arm/vdso/vdsomunge.c b/arch/arm/vdso/vdsomunge.c
index 9005b07296c8..aedec81d1198 100644
--- a/arch/arm/vdso/vdsomunge.c
+++ b/arch/arm/vdso/vdsomunge.c
@@ -45,13 +45,11 @@
  * it does.
  */
 
-#define _GNU_SOURCE
-
 #include <byteswap.h>
 #include <elf.h>
 #include <errno.h>
-#include <error.h>
 #include <fcntl.h>
+#include <stdarg.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -82,11 +80,25 @@
 #define EF_ARM_ABI_FLOAT_HARD 0x400
 #endif
 
+static int failed;
+static const char *argv0;
 static const char *outfile;
 
+static void fail(const char *fmt, ...)
+{
+	va_list ap;
+
+	failed = 1;
+	fprintf(stderr, "%s: ", argv0);
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
 static void cleanup(void)
 {
-	if (error_message_count > 0 && outfile != NULL)
+	if (failed && outfile != NULL)
 		unlink(outfile);
 }
 
@@ -119,68 +131,66 @@ int main(int argc, char **argv)
 	int infd;
 
 	atexit(cleanup);
+	argv0 = argv[0];
 
 	if (argc != 3)
-		error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]);
+		fail("Usage: %s [infile] [outfile]\n", argv[0]);
 
 	infile = argv[1];
 	outfile = argv[2];
 
 	infd = open(infile, O_RDONLY);
 	if (infd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", infile);
+		fail("Cannot open %s: %s\n", infile, strerror(errno));
 
 	if (fstat(infd, &stat) != 0)
-		error(EXIT_FAILURE, errno, "Failed stat for %s", infile);
+		fail("Failed stat for %s: %s\n", infile, strerror(errno));
 
 	inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0);
 	if (inbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", infile);
+		fail("Failed to map %s: %s\n", infile, strerror(errno));
 
 	close(infd);
 
 	inhdr = inbuf;
 
 	if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0)
-		error(EXIT_FAILURE, 0, "Not an ELF file");
+		fail("Not an ELF file\n");
 
 	if (inhdr->e_ident[EI_CLASS] != ELFCLASS32)
-		error(EXIT_FAILURE, 0, "Unsupported ELF class");
+		fail("Unsupported ELF class\n");
 
 	swap = inhdr->e_ident[EI_DATA] != HOST_ORDER;
 
 	if (read_elf_half(inhdr->e_type, swap) != ET_DYN)
-		error(EXIT_FAILURE, 0, "Not a shared object");
+		fail("Not a shared object\n");
 
-	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) {
-		error(EXIT_FAILURE, 0, "Unsupported architecture %#x",
-		      inhdr->e_machine);
-	}
+	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM)
+		fail("Unsupported architecture %#x\n", inhdr->e_machine);
 
 	e_flags = read_elf_word(inhdr->e_flags, swap);
 
 	if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) {
-		error(EXIT_FAILURE, 0, "Unsupported EABI version %#x",
-		      EF_ARM_EABI_VERSION(e_flags));
+		fail("Unsupported EABI version %#x\n",
+		     EF_ARM_EABI_VERSION(e_flags));
 	}
 
 	if (e_flags & EF_ARM_ABI_FLOAT_HARD)
-		error(EXIT_FAILURE, 0,
-		      "Unexpected hard-float flag set in e_flags");
+		fail("Unexpected hard-float flag set in e_flags\n");
 
 	clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT);
 
 	outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
 	if (outfd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", outfile);
+		fail("Cannot open %s: %s\n", outfile, strerror(errno));
 
 	if (ftruncate(outfd, stat.st_size) != 0)
-		error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile);
+		fail("Cannot truncate %s: %s\n", outfile, strerror(errno));
 
 	outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED,
 		      outfd, 0);
 	if (outbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", outfile);
+		fail("Failed to map %s: %s\n", outfile, strerror(errno));
 
 	close(outfd);
 
@@ -195,7 +205,7 @@ int main(int argc, char **argv)
 	}
 
 	if (msync(outbuf, stat.st_size, MS_SYNC) != 0)
-		error(EXIT_FAILURE, errno, "Failed to sync %s", outfile);
+		fail("Failed to sync %s: %s\n", outfile, strerror(errno));
 
 	return EXIT_SUCCESS;
 }
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 6c09cc440a2b..c50c8d33f874 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -45,13 +45,6 @@ static struct vcpu_info __percpu *xen_vcpu_info;
 unsigned long xen_released_pages;
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
-/* TODO: to be removed */
-__read_mostly int xen_have_vector_callback;
-EXPORT_SYMBOL_GPL(xen_have_vector_callback);
-
-int xen_platform_pci_unplug = XEN_UNPLUG_ALL;
-EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
-
 static __read_mostly unsigned int xen_events_irq;
 
 static __initdata struct device_node *xen_node;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0f6edb14b7e4..7d95663c0160 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -20,15 +20,16 @@ config ARM64
 	select ARM_GIC_V2M if PCI_MSI
 	select ARM_GIC_V3
 	select ARM_GIC_V3_ITS if PCI_MSI
+	select ARM_PSCI_FW
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select EDAC_SUPPORT
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
+	select EDAC_SUPPORT
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
-	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IRQ_PROBE
@@ -53,6 +54,7 @@ config ARM64
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
+	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -104,6 +106,10 @@ config NO_IOPORT_MAP
 config STACKTRACE_SUPPORT
 	def_bool y
 
+config ILLEGAL_POINTER_VALUE
+	hex
+	default 0xdead000000000000
+
 config LOCKDEP_SUPPORT
 	def_bool y
 
@@ -113,6 +119,14 @@ config TRACE_IRQFLAGS_SUPPORT
 config RWSEM_XCHGADD_ALGORITHM
 	def_bool y
 
+config GENERIC_BUG
+	def_bool y
+	depends on BUG
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	def_bool y
+	depends on GENERIC_BUG
+
 config GENERIC_HWEIGHT
 	def_bool y
 
@@ -137,6 +151,9 @@ config NEED_DMA_MAP_STATE
 config NEED_SG_DMA_LENGTH
 	def_bool y
 
+config SMP
+	def_bool y
+
 config SWIOTLB
 	def_bool y
 
@@ -160,110 +177,7 @@ source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
 
-menu "Platform selection"
-
-config ARCH_EXYNOS
-	bool
-	help
-	  This enables support for Samsung Exynos SoC family
-
-config ARCH_EXYNOS7
-	bool "ARMv8 based Samsung Exynos7"
-	select ARCH_EXYNOS
-	select COMMON_CLK_SAMSUNG
-	select HAVE_S3C2410_WATCHDOG if WATCHDOG
-	select HAVE_S3C_RTC if RTC_CLASS
-	select PINCTRL
-	select PINCTRL_EXYNOS
-
-	help
-	  This enables support for Samsung Exynos7 SoC family
-
-config ARCH_FSL_LS2085A
-	bool "Freescale LS2085A SOC"
-	help
-	  This enables support for Freescale LS2085A SOC.
-
-config ARCH_HISI
-	bool "Hisilicon SoC Family"
-	help
-	  This enables support for Hisilicon ARMv8 SoC family
-
-config ARCH_MEDIATEK
-	bool "Mediatek MT65xx & MT81xx ARMv8 SoC"
-	select ARM_GIC
-	select PINCTRL
-	help
-	  Support for Mediatek MT65xx & MT81xx ARMv8 SoCs
-
-config ARCH_QCOM
-	bool "Qualcomm Platforms"
-	select PINCTRL
-	help
-	  This enables support for the ARMv8 based Qualcomm chipsets.
-
-config ARCH_SEATTLE
-	bool "AMD Seattle SoC Family"
-	help
-	  This enables support for AMD Seattle SOC Family
-
-config ARCH_TEGRA
-	bool "NVIDIA Tegra SoC Family"
-	select ARCH_HAS_RESET_CONTROLLER
-	select ARCH_REQUIRE_GPIOLIB
-	select CLKDEV_LOOKUP
-	select CLKSRC_MMIO
-	select CLKSRC_OF
-	select GENERIC_CLOCKEVENTS
-	select HAVE_CLK
-	select PINCTRL
-	select RESET_CONTROLLER
-	help
-	  This enables support for the NVIDIA Tegra SoC family.
-
-config ARCH_TEGRA_132_SOC
-	bool "NVIDIA Tegra132 SoC"
-	depends on ARCH_TEGRA
-	select PINCTRL_TEGRA124
-	select USB_ULPI if USB_PHY
-	select USB_ULPI_VIEWPORT if USB_PHY
-	help
-	  Enable support for NVIDIA Tegra132 SoC, based on the Denver
-	  ARMv8 CPU.  The Tegra132 SoC is similar to the Tegra124 SoC,
-	  but contains an NVIDIA Denver CPU complex in place of
-	  Tegra124's "4+1" Cortex-A15 CPU complex.
-
-config ARCH_SPRD
-	bool "Spreadtrum SoC platform"
-	help
-	  Support for Spreadtrum ARM based SoCs
-
-config ARCH_THUNDER
-	bool "Cavium Inc. Thunder SoC Family"
-	help
-	  This enables support for Cavium's Thunder Family of SoCs.
-
-config ARCH_VEXPRESS
-	bool "ARMv8 software model (Versatile Express)"
-	select ARCH_REQUIRE_GPIOLIB
-	select COMMON_CLK_VERSATILE
-	select POWER_RESET_VEXPRESS
-	select VEXPRESS_CONFIG
-	help
-	  This enables support for the ARMv8 software model (Versatile
-	  Express).
-
-config ARCH_XGENE
-	bool "AppliedMicro X-Gene SOC Family"
-	help
-	  This enables support for AppliedMicro X-Gene SOC Family
-
-config ARCH_ZYNQMP
-	bool "Xilinx ZynqMP Family"
-	help
-	  This enables support for Xilinx ZynqMP Family
-
-endmenu
+source "arch/arm64/Kconfig.platforms"
 
 menu "Bus support"
 
@@ -474,22 +388,8 @@ config CPU_BIG_ENDIAN
        help
          Say Y if you plan on running a kernel in big-endian mode.
 
-config SMP
-	bool "Symmetric Multi-Processing"
-	help
-	  This enables support for systems with more than one CPU.  If
-	  you say N here, the kernel will run on single and
-	  multiprocessor machines, but will use only one CPU of a
-	  multiprocessor machine. If you say Y here, the kernel will run
-	  on many, but not all, single processor machines. On a single
-	  processor machine, the kernel will run faster if you say N
-	  here.
-
-	  If you don't know what to do here, say N.
-
 config SCHED_MC
 	bool "Multi-core scheduler support"
-	depends on SMP
 	help
 	  Multi-core scheduler support improves the CPU scheduler's decision
 	  making when dealing with multi-core CPU chips at a cost of slightly
@@ -497,7 +397,6 @@ config SCHED_MC
 
 config SCHED_SMT
 	bool "SMT scheduler support"
-	depends on SMP
 	help
 	  Improves the CPU scheduler's decision making when dealing with
 	  MultiThreading at a cost of slightly increased overhead in some
@@ -506,23 +405,17 @@ config SCHED_SMT
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
-	depends on SMP
 	# These have to remain sorted largest to smallest
 	default "64"
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
-	depends on SMP
 	help
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
 
 source kernel/Kconfig.preempt
 
-config UP_LATE_INIT
-       def_bool y
-       depends on !SMP
-
 config HZ
 	int
 	default 100
@@ -664,6 +557,53 @@ config SETEND_EMULATION
 	  If unsure, say Y
 endif
 
+menu "ARMv8.1 architectural features"
+
+config ARM64_HW_AFDBM
+	bool "Support for hardware updates of the Access and Dirty page flags"
+	default y
+	help
+	  The ARMv8.1 architecture extensions introduce support for
+	  hardware updates of the access and dirty information in page
+	  table entries. When enabled in TCR_EL1 (HA and HD bits) on
+	  capable processors, accesses to pages with PTE_AF cleared will
+	  set this bit instead of raising an access flag fault.
+	  Similarly, writes to read-only pages with the DBM bit set will
+	  clear the read-only bit (AP[2]) instead of raising a
+	  permission fault.
+
+	  Kernels built with this configuration option enabled continue
+	  to work on pre-ARMv8.1 hardware and the performance impact is
+	  minimal. If unsure, say Y.
+
+config ARM64_PAN
+	bool "Enable support for Privileged Access Never (PAN)"
+	default y
+	help
+	 Privileged Access Never (PAN; part of the ARMv8.1 Extensions)
+	 prevents the kernel or hypervisor from accessing user-space (EL0)
+	 memory directly.
+
+	 Choosing this option will cause any unprotected (not using
+	 copy_to_user et al) memory access to fail with a permission fault.
+
+	 The feature is detected at runtime, and will remain as a 'nop'
+	 instruction if the cpu does not implement the feature.
+
+config ARM64_LSE_ATOMICS
+	bool "Atomic instructions"
+	help
+	  As part of the Large System Extensions, ARMv8.1 introduces new
+	  atomic instructions that are designed specifically to scale in
+	  very large systems.
+
+	  Say Y here to make use of these instructions for the in-kernel
+	  atomic routines. This incurs a small overhead on CPUs that do
+	  not support these instructions and requires the kernel to be
+	  built with binutils >= 2.25.
+
+endmenu
+
 endmenu
 
 menu "Boot options"
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
new file mode 100644
index 000000000000..23800a19a7bc
--- /dev/null
+++ b/arch/arm64/Kconfig.platforms
@@ -0,0 +1,125 @@
+menu "Platform selection"
+
+config ARCH_BCM_IPROC
+	bool "Broadcom iProc SoC Family"
+	help
+	  This enables support for Broadcom iProc based SoCs
+
+config ARCH_BERLIN
+	bool "Marvell Berlin SoC Family"
+	select DW_APB_ICTL
+	help
+	  This enables support for Marvell Berlin SoC Family
+
+config ARCH_EXYNOS
+	bool
+	help
+	  This enables support for Samsung Exynos SoC family
+
+config ARCH_EXYNOS7
+	bool "ARMv8 based Samsung Exynos7"
+	select ARCH_EXYNOS
+	select COMMON_CLK_SAMSUNG
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
+	select HAVE_S3C_RTC if RTC_CLASS
+	select PINCTRL
+	select PINCTRL_EXYNOS
+
+	help
+	  This enables support for Samsung Exynos7 SoC family
+
+config ARCH_FSL_LS2085A
+	bool "Freescale LS2085A SOC"
+	help
+	  This enables support for Freescale LS2085A SOC.
+
+config ARCH_HISI
+	bool "Hisilicon SoC Family"
+	help
+	  This enables support for Hisilicon ARMv8 SoC family
+
+config ARCH_MEDIATEK
+	bool "Mediatek MT65xx & MT81xx ARMv8 SoC"
+	select ARM_GIC
+	select PINCTRL
+	help
+	  Support for Mediatek MT65xx & MT81xx ARMv8 SoCs
+
+config ARCH_QCOM
+	bool "Qualcomm Platforms"
+	select PINCTRL
+	help
+	  This enables support for the ARMv8 based Qualcomm chipsets.
+
+config ARCH_ROCKCHIP
+	bool "Rockchip Platforms"
+	select ARCH_HAS_RESET_CONTROLLER
+	select ARCH_REQUIRE_GPIOLIB
+	select PINCTRL
+	select PINCTRL_ROCKCHIP
+	help
+	  This enables support for the ARMv8 based Rockchip chipsets,
+	  like the RK3368.
+
+config ARCH_SEATTLE
+	bool "AMD Seattle SoC Family"
+	help
+	  This enables support for AMD Seattle SOC Family
+
+config ARCH_TEGRA
+	bool "NVIDIA Tegra SoC Family"
+	select ARCH_HAS_RESET_CONTROLLER
+	select ARCH_REQUIRE_GPIOLIB
+	select CLKDEV_LOOKUP
+	select CLKSRC_MMIO
+	select CLKSRC_OF
+	select GENERIC_CLOCKEVENTS
+	select HAVE_CLK
+	select PINCTRL
+	select RESET_CONTROLLER
+	help
+	  This enables support for the NVIDIA Tegra SoC family.
+
+config ARCH_TEGRA_132_SOC
+	bool "NVIDIA Tegra132 SoC"
+	depends on ARCH_TEGRA
+	select PINCTRL_TEGRA124
+	select USB_ULPI if USB_PHY
+	select USB_ULPI_VIEWPORT if USB_PHY
+	help
+	  Enable support for NVIDIA Tegra132 SoC, based on the Denver
+	  ARMv8 CPU.  The Tegra132 SoC is similar to the Tegra124 SoC,
+	  but contains an NVIDIA Denver CPU complex in place of
+	  Tegra124's "4+1" Cortex-A15 CPU complex.
+
+config ARCH_SPRD
+	bool "Spreadtrum SoC platform"
+	help
+	  Support for Spreadtrum ARM based SoCs
+
+config ARCH_THUNDER
+	bool "Cavium Inc. Thunder SoC Family"
+	help
+	  This enables support for Cavium's Thunder Family of SoCs.
+
+config ARCH_VEXPRESS
+	bool "ARMv8 software model (Versatile Express)"
+	select ARCH_REQUIRE_GPIOLIB
+	select COMMON_CLK_VERSATILE
+	select POWER_RESET_VEXPRESS
+	select VEXPRESS_CONFIG
+	help
+	  This enables support for the ARMv8 software model (Versatile
+	  Express).
+
+config ARCH_XGENE
+	bool "AppliedMicro X-Gene SOC Family"
+	help
+	  This enables support for AppliedMicro X-Gene SOC Family
+
+config ARCH_ZYNQMP
+	bool "Xilinx ZynqMP Family"
+	help
+	  This enables support for Xilinx ZynqMP Family
+
+endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 4d2a925998f9..15ff5b4156fd 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -17,7 +17,18 @@ GZFLAGS		:=-9
 
 KBUILD_DEFCONFIG := defconfig
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only
+# Check for binutils support for specific extensions
+lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1)
+
+ifeq ($(CONFIG_ARM64_LSE_ATOMICS), y)
+  ifeq ($(lseinstr),)
+$(warning LSE atomics not supported by binutils)
+  endif
+endif
+
+KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+KBUILD_AFLAGS	+= $(lseinstr)
+
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 AS		+= -EB
@@ -58,7 +69,10 @@ all:	$(KBUILD_IMAGE) $(KBUILD_DTBS)
 
 boot := arch/arm64/boot
 
-Image Image.gz: vmlinux
+Image: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+Image.%: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zinstall install: vmlinux
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index 5a0e3ab854a5..abcbba2f01ba 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -19,9 +19,21 @@ targets := Image Image.gz
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+$(obj)/Image.bz2: $(obj)/Image FORCE
+	$(call if_changed,bzip2)
+
 $(obj)/Image.gz: $(obj)/Image FORCE
 	$(call if_changed,gzip)
 
+$(obj)/Image.lz4: $(obj)/Image FORCE
+	$(call if_changed,lz4)
+
+$(obj)/Image.lzma: $(obj)/Image FORCE
+	$(call if_changed,lzma)
+
+$(obj)/Image.lzo: $(obj)/Image FORCE
+	$(call if_changed,lzo)
+
 install: $(obj)/Image
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 38913be23695..d9f88330e7b0 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,12 +1,15 @@
 dts-dirs += amd
 dts-dirs += apm
 dts-dirs += arm
+dts-dirs += broadcom
 dts-dirs += cavium
 dts-dirs += exynos
 dts-dirs += freescale
 dts-dirs += hisilicon
+dts-dirs += marvell
 dts-dirs += mediatek
 dts-dirs += qcom
+dts-dirs += rockchip
 dts-dirs += sprd
 dts-dirs += xilinx
 
diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts
index 83578e766b94..4c55833d8a41 100644
--- a/arch/arm64/boot/dts/apm/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm/apm-mustang.dts
@@ -23,6 +23,16 @@
 		device_type = "memory";
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		button@1 {
+			label = "POWER";
+			linux,code = <116>;
+			linux,input-type = <0x1>;
+			interrupts = <0x0 0x2d 0x1>;
+		};
+	};
 };
 
 &pcie0clk {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 0689c3fb56e3..d831bc2ac204 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -490,7 +490,8 @@
 				0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */
 			reg-names = "csr", "cfg";
 			ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000   /* io */
-				  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */
+				  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000   /* mem */
+				  0x43000000 0xf0 0x00000000 0xf0 0x00000000 0x10 0x00000000>; /* mem */
 			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
 				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
@@ -513,8 +514,9 @@
 			reg = < 0x00 0x1f2c0000 0x0 0x00010000   /* Controller registers */
 				0xd0 0xd0000000 0x0 0x00040000>; /* PCI config space */
 			reg-names = "csr", "cfg";
-			ranges = <0x01000000 0x0 0x00000000 0xd0 0x10000000 0x00 0x00010000   /* io  */
-				  0x02000000 0x0 0x80000000 0xd1 0x80000000 0x00 0x80000000>; /* mem */
+			ranges = <0x01000000 0x00 0x00000000 0xd0 0x10000000 0x00 0x00010000   /* io  */
+				  0x02000000 0x00 0x80000000 0xd1 0x80000000 0x00 0x80000000   /* mem */
+				  0x43000000 0xd8 0x00000000 0xd8 0x00000000 0x08 0x00000000>; /* mem */
 			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
 				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
@@ -537,8 +539,9 @@
 			reg =  < 0x00 0x1f2d0000 0x0 0x00010000   /* Controller registers */
 				 0x90 0xd0000000 0x0 0x00040000>; /* PCI config space */
 			reg-names = "csr", "cfg";
-			ranges = <0x01000000 0x0 0x00000000 0x90 0x10000000 0x0 0x00010000   /* io  */
-				  0x02000000 0x0 0x80000000 0x91 0x80000000 0x0 0x80000000>; /* mem */
+			ranges = <0x01000000 0x00 0x00000000 0x90 0x10000000 0x00 0x00010000   /* io  */
+				  0x02000000 0x00 0x80000000 0x91 0x80000000 0x00 0x80000000   /* mem */
+				  0x43000000 0x94 0x00000000 0x94 0x00000000 0x04 0x00000000>; /* mem */
 			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
 				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
@@ -561,8 +564,9 @@
 			reg = < 0x00 0x1f500000 0x0 0x00010000   /* Controller registers */
 				0xa0 0xd0000000 0x0 0x00040000>; /* PCI config space */
 			reg-names = "csr", "cfg";
-			ranges = <0x01000000 0x0 0x00000000 0xa0 0x10000000 0x0 0x00010000   /* io   */
-				  0x02000000 0x0 0x80000000 0xa1 0x80000000 0x0 0x80000000>; /* mem  */
+			ranges = <0x01000000 0x00 0x00000000 0xa0 0x10000000 0x00 0x00010000   /* io  */
+				  0x02000000 0x00 0x80000000 0xa1 0x80000000 0x00 0x80000000   /* mem */
+				  0x43000000 0xb0 0x00000000 0xb0 0x00000000 0x10 0x00000000>; /* mem */
 			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
 				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
@@ -585,8 +589,9 @@
 			reg = < 0x00 0x1f510000 0x0 0x00010000   /* Controller registers */
 				0xc0 0xd0000000 0x0 0x00200000>; /* PCI config space */
 			reg-names = "csr", "cfg";
-			ranges = <0x01000000 0x0 0x00000000 0xc0 0x10000000 0x0 0x00010000   /* io  */
-				  0x02000000 0x0 0x80000000 0xc1 0x80000000 0x0 0x80000000>; /* mem */
+			ranges = <0x01000000 0x00 0x00000000 0xc0 0x10000000 0x00 0x00010000   /* io  */
+				  0x02000000 0x00 0x80000000 0xc1 0x80000000 0x00 0x80000000   /* mem */
+				  0x43000000 0xc8 0x00000000 0xc8 0x00000000 0x08 0x00000000>; /* mem */
 			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
 				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
@@ -823,7 +828,7 @@
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/arch/arm64/boot/dts/arm/Makefile b/arch/arm64/boot/dts/arm/Makefile
index c5c98b91514e..bb3c07209676 100644
--- a/arch/arm64/boot/dts/arm/Makefile
+++ b/arch/arm64/boot/dts/arm/Makefile
@@ -1,6 +1,7 @@
 dtb-$(CONFIG_ARCH_VEXPRESS) += foundation-v8.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb juno-r1.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2f-1xv7-ca53x2.dtb
 
 always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
index 021e0f40f419..637e046f0e36 100644
--- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -136,6 +136,8 @@
 					clock-names = "refclk", "timclk", "apb_pclk";
 					#clock-cells = <1>;
 					clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+					assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>;
+					assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>;
 				};
 
 				apbregs@010000 {
diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
index c46cbb29f3c6..88a7583ed7a7 100644
--- a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
@@ -74,6 +74,8 @@
 				clock-names = "refclk", "timclk", "apb_pclk";
 				#clock-cells = <1>;
 				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+				assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>;
+				assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>;
 			};
 
 			aaci@040000 {
diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts
new file mode 100644
index 000000000000..5b1d0181023b
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts
@@ -0,0 +1,191 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ * LogicTile Express 20MG
+ * V2F-1XV7
+ *
+ * Cortex-A53 (2 cores) Soft Macrocell Model
+ *
+ * HBI-0247C
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "V2F-1XV7 Cortex-A53x2 SMM";
+	arm,hbi = <0x247>;
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,vexpress,v2f-1xv7,ca53x2", "arm,vexpress,v2f-1xv7", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen {
+		stdout-path = "serial0:38400n8";
+	};
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+		i2c0 = &v2m_i2c_dvi;
+		i2c1 = &v2m_i2c_pcie;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0 0>;
+			next-level-cache = <&L2_0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0 1>;
+			next-level-cache = <&L2_0>;
+		};
+
+		L2_0: l2-cache0 {
+			compatible = "cache";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>; /* 2GB @ 2GB */
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,gic-400";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x2000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		smbclk: osc@4 {
+			/* SMC clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 4>;
+			freq-range = <40000000 40000000>;
+			#clock-cells = <0>;
+			clock-output-names = "smclk";
+		};
+
+		volt@0 {
+			/* VIO to expansion board above */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 0>;
+			regulator-name = "VIO_UP";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+		};
+
+		volt@1 {
+			/* 12V from power connector J6 */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 1>;
+			regulator-name = "12";
+			regulator-always-on;
+		};
+
+		temp@0 {
+			/* FPGA temperature */
+			compatible = "arm,vexpress-temp";
+			arm,vexpress-sysreg,func = <4 0>;
+			label = "FPGA";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic GIC_SPI  0 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  1 &gic GIC_SPI  1 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  2 &gic GIC_SPI  2 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  3 &gic GIC_SPI  3 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  4 &gic GIC_SPI  4 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  5 &gic GIC_SPI  5 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  6 &gic GIC_SPI  6 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  7 &gic GIC_SPI  7 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  8 &gic GIC_SPI  8 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  9 &gic GIC_SPI  9 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+
+		/include/ "../../../../arm/boot/dts/vexpress-v2m-rs1.dtsi"
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/Makefile b/arch/arm64/boot/dts/broadcom/Makefile
new file mode 100644
index 000000000000..e21fe66f1837
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/Makefile
@@ -0,0 +1,5 @@
+dtb-$(CONFIG_ARCH_BCM_IPROC) += ns2-svk.dtb
+
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
+clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
new file mode 100644
index 000000000000..244baf879dc9
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -0,0 +1,59 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2015 Broadcom Corporation.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+#include "ns2.dtsi"
+
+/ {
+	model = "Broadcom NS2 SVK";
+	compatible = "brcm,ns2-svk", "brcm,ns2";
+
+	aliases {
+		serial0 = &uart3;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x000000000 0x80000000 0x00000000 0x40000000>;
+	};
+
+	soc: soc {
+		uart3: serial@66130000 {
+			status = "ok";
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
new file mode 100644
index 000000000000..3c92d92278e5
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -0,0 +1,118 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2015 Broadcom Corporation.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/memreserve/ 0x84b00000 0x00000008;
+
+/ {
+	compatible = "brcm,ns2";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0 0>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x84b00000>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0 1>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x84b00000>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0 2>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x84b00000>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0 3>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x84b00000>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0xff) |
+			      IRQ_TYPE_EDGE_RISING)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_RAW(0xff) |
+			      IRQ_TYPE_EDGE_RISING)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_RAW(0xff) |
+			      IRQ_TYPE_EDGE_RISING)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_RAW(0xff) |
+			      IRQ_TYPE_EDGE_RISING)>;
+	};
+
+	soc: soc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0xffffffff>;
+
+		gic: interrupt-controller@65210000 {
+			compatible = "arm,gic-400";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg = <0x65210000 0x1000>,
+			      <0x65220000 0x1000>,
+			      <0x65240000 0x2000>,
+			      <0x65260000 0x1000>;
+		};
+
+		uart3: serial@66130000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x66130000 0x100>;
+			interrupts = <GIC_SPI 393 IRQ_TYPE_LEVEL_HIGH>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clock-frequency = <23961600>;
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index d8c0bdc51882..9cb7cf94284a 100644
--- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
@@ -376,10 +376,19 @@
 		gic0: interrupt-controller@8010,00000000 {
 			compatible = "arm,gic-v3";
 			#interrupt-cells = <3>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
 			interrupt-controller;
 			reg = <0x8010 0x00000000 0x0 0x010000>, /* GICD */
 			      <0x8010 0x80000000 0x0 0x600000>; /* GICR */
 			interrupts = <1 9 0xf04>;
+
+			its: gic-its@8010,00020000 {
+				compatible = "arm,gic-v3-its";
+				msi-controller;
+				reg = <0x8010 0x20000 0x0 0x200000>;
+			};
 		};
 
 		uaa0: serial@87e0,24000000 {
diff --git a/arch/arm64/boot/dts/marvell/Makefile b/arch/arm64/boot/dts/marvell/Makefile
new file mode 100644
index 000000000000..e2f6afa7f849
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/Makefile
@@ -0,0 +1,5 @@
+dtb-$(CONFIG_ARCH_BERLIN) += berlin4ct-dmp.dtb
+
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
+clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts b/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts
new file mode 100644
index 000000000000..0d70d39fa8d2
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts
@@ -0,0 +1,66 @@
+/*
+ * Copyright (C) 2015 Marvell Technology Group Ltd.
+ *
+ * Author: Jisheng Zhang <jszhang@marvell.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPLv2 or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include "berlin4ct.dtsi"
+
+/ {
+	model = "Marvell BG4CT DMP board";
+	compatible = "marvell,berlin4ct-dmp", "marvell,berlin4ct", "marvell,berlin";
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		device_type = "memory";
+		/* the first 16MB is for firmwares' usage */
+		reg = <0 0x01000000 0 0x7f000000>;
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/marvell/berlin4ct.dtsi b/arch/arm64/boot/dts/marvell/berlin4ct.dtsi
new file mode 100644
index 000000000000..dd4a10d605d9
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/berlin4ct.dtsi
@@ -0,0 +1,164 @@
+/*
+ * Copyright (C) 2015 Marvell Technology Group Ltd.
+ *
+ * Author: Jisheng Zhang <jszhang@marvell.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPLv2 or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	compatible = "marvell,berlin4ct", "marvell,berlin";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a53", "arm,armv8";
+			device_type = "cpu";
+			reg = <0x0>;
+			enable-method = "psci";
+		};
+
+		cpu1: cpu@1 {
+			compatible = "arm,cortex-a53", "arm,armv8";
+			device_type = "cpu";
+			reg = <0x1>;
+			enable-method = "psci";
+		};
+
+		cpu2: cpu@2 {
+			compatible = "arm,cortex-a53", "arm,armv8";
+			device_type = "cpu";
+			reg = <0x2>;
+			enable-method = "psci";
+		};
+
+		cpu3: cpu@3 {
+			compatible = "arm,cortex-a53", "arm,armv8";
+			device_type = "cpu";
+			reg = <0x3>;
+			enable-method = "psci";
+		};
+	};
+
+	osc: osc {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <25000000>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>,
+				     <&cpu2>,
+				     <&cpu3>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0 0xf7000000 0x1000000>;
+
+		gic: interrupt-controller@901000 {
+			compatible = "arm,gic-400";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg = <0x901000 0x1000>,
+			      <0x902000 0x2000>,
+			      <0x904000 0x2000>,
+			      <0x906000 0x2000>;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
+		};
+
+		apb@fc0000 {
+			compatible = "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0xfc0000 0x10000>;
+			interrupt-parent = <&sic>;
+
+			sic: interrupt-controller@1000 {
+				compatible = "snps,dw-apb-ictl";
+				reg = <0x1000 0x30>;
+				interrupt-controller;
+				#interrupt-cells = <1>;
+				interrupt-parent = <&gic>;
+				interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			uart0: uart@d000 {
+				compatible = "snps,dw-apb-uart";
+				reg = <0xd000 0x100>;
+				interrupts = <8>;
+				clocks = <&osc>;
+				reg-shift = <2>;
+				status = "disabled";
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile
index 3ce24622b231..e0a4bff2fc17 100644
--- a/arch/arm64/boot/dts/mediatek/Makefile
+++ b/arch/arm64/boot/dts/mediatek/Makefile
@@ -1,3 +1,4 @@
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt6795-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-evb.dtb
 
 always		:= $(dtb-y)
diff --git a/arch/arm64/boot/dts/mediatek/mt6795-evb.dts b/arch/arm64/boot/dts/mediatek/mt6795-evb.dts
new file mode 100644
index 000000000000..ad665f5835f0
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt6795-evb.dts
@@ -0,0 +1,41 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Mars.C <mars.cheng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/dts-v1/;
+#include "mt6795.dtsi"
+
+/ {
+	model = "MediaTek MT6795 Evaluation Board";
+	compatible = "mediatek,mt6795-evb", "mediatek,mt6795";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x1e800000>;
+	};
+
+	chosen {
+		stdout-path = "serial0:921600n8";
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt6795.dtsi b/arch/arm64/boot/dts/mediatek/mt6795.dtsi
new file mode 100644
index 000000000000..c85659d0ff5d
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt6795.dtsi
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Mars.C <mars.cheng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	compatible = "mediatek,mt6795";
+	interrupt-parent = <&sysirq>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x001>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x002>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x003>;
+		};
+
+		cpu4: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x100>;
+		};
+
+		cpu5: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x101>;
+		};
+
+		cpu6: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x102>;
+		};
+
+		cpu7: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x103>;
+		};
+	};
+
+	system_clk: dummy13m {
+		compatible = "fixed-clock";
+		clock-frequency = <13000000>;
+		#clock-cells = <0>;
+	};
+
+	rtc_clk: dummy32k {
+		compatible = "fixed-clock";
+		clock-frequency = <32000>;
+		#clock-cells = <0>;
+	};
+
+	uart_clk: dummy26m {
+		compatible = "fixed-clock";
+		clock-frequency = <26000000>;
+		#clock-cells = <0>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	sysirq: intpol-controller@10200620 {
+		compatible = "mediatek,mt6795-sysirq",
+			     "mediatek,mt6577-sysirq";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		interrupt-parent = <&gic>;
+		reg = <0 0x10200620 0 0x20>;
+	};
+
+	gic: interrupt-controller@10221000 {
+		compatible = "arm,gic-400";
+		#interrupt-cells = <3>;
+		interrupt-parent = <&gic>;
+		interrupt-controller;
+		reg = <0 0x10221000 0 0x1000>,
+		      <0 0x10222000 0 0x2000>,
+		      <0 0x10224000 0 0x2000>,
+		      <0 0x10226000 0 0x2000>;
+	};
+
+	uart0: serial@11002000 {
+		compatible = "mediatek,mt6795-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0 0x11002000 0 0x400>;
+		interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+
+	uart1: serial@11003000 {
+		compatible = "mediatek,mt6795-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0 0x11003000 0 0x400>;
+		interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+
+	uart2: serial@11004000 {
+		compatible = "mediatek,mt6795-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0 0x11004000 0 0x400>;
+		interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+
+	uart3: serial@11005000 {
+		compatible = "mediatek,mt6795-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0 0x11005000 0 0x400>;
+		interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index d0ab012fa379..4be66cadbc7c 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -34,6 +34,359 @@
 	chosen { };
 };
 
+&i2c1 {
+	status = "okay";
+
+	buck: da9211@68 {
+		compatible = "dlg,da9211";
+		reg = <0x68>;
+
+		regulators {
+			da9211_vcpu_reg: BUCKA {
+				regulator-name = "VBUCKA";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1310000>;
+				regulator-min-microamp	= <2000000>;
+				regulator-max-microamp	= <4400000>;
+				regulator-ramp-delay = <10000>;
+				regulator-always-on;
+			};
+
+			da9211_vgpu_reg: BUCKB {
+				regulator-name = "VBUCKB";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1310000>;
+				regulator-min-microamp	= <2000000>;
+				regulator-max-microamp	= <3000000>;
+				regulator-ramp-delay = <10000>;
+			};
+		};
+	};
+};
+
+&mmc0 {
+	status = "okay";
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_pins_default>;
+	pinctrl-1 = <&mmc0_pins_uhs>;
+	bus-width = <8>;
+	max-frequency = <50000000>;
+	cap-mmc-highspeed;
+	vmmc-supply = <&mt6397_vemc_3v3_reg>;
+	vqmmc-supply = <&mt6397_vio18_reg>;
+	non-removable;
+};
+
+&mmc1 {
+	status = "okay";
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc1_pins_default>;
+	pinctrl-1 = <&mmc1_pins_uhs>;
+	bus-width = <4>;
+	max-frequency = <50000000>;
+	cap-sd-highspeed;
+	sd-uhs-sdr25;
+	cd-gpios = <&pio 132 0>;
+	vmmc-supply = <&mt6397_vmch_reg>;
+	vqmmc-supply = <&mt6397_vmc_reg>;
+};
+
+&pio {
+	mmc0_pins_default: mmc0default {
+		pins_cmd_dat {
+			pinmux = <MT8173_PIN_57_MSDC0_DAT0__FUNC_MSDC0_DAT0>,
+				 <MT8173_PIN_58_MSDC0_DAT1__FUNC_MSDC0_DAT1>,
+				 <MT8173_PIN_59_MSDC0_DAT2__FUNC_MSDC0_DAT2>,
+				 <MT8173_PIN_60_MSDC0_DAT3__FUNC_MSDC0_DAT3>,
+				 <MT8173_PIN_61_MSDC0_DAT4__FUNC_MSDC0_DAT4>,
+				 <MT8173_PIN_62_MSDC0_DAT5__FUNC_MSDC0_DAT5>,
+				 <MT8173_PIN_63_MSDC0_DAT6__FUNC_MSDC0_DAT6>,
+				 <MT8173_PIN_64_MSDC0_DAT7__FUNC_MSDC0_DAT7>,
+				 <MT8173_PIN_66_MSDC0_CMD__FUNC_MSDC0_CMD>;
+			input-enable;
+			bias-pull-up;
+		};
+
+		pins_clk {
+			pinmux = <MT8173_PIN_65_MSDC0_CLK__FUNC_MSDC0_CLK>;
+			bias-pull-down;
+		};
+
+		pins_rst {
+			pinmux = <MT8173_PIN_68_MSDC0_RST___FUNC_MSDC0_RSTB>;
+			bias-pull-up;
+		};
+	};
+
+	mmc1_pins_default: mmc1default {
+		pins_cmd_dat {
+			pinmux = <MT8173_PIN_73_MSDC1_DAT0__FUNC_MSDC1_DAT0>,
+				 <MT8173_PIN_74_MSDC1_DAT1__FUNC_MSDC1_DAT1>,
+				 <MT8173_PIN_75_MSDC1_DAT2__FUNC_MSDC1_DAT2>,
+				 <MT8173_PIN_76_MSDC1_DAT3__FUNC_MSDC1_DAT3>,
+				 <MT8173_PIN_78_MSDC1_CMD__FUNC_MSDC1_CMD>;
+			input-enable;
+			drive-strength = <MTK_DRIVE_4mA>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins_clk {
+			pinmux = <MT8173_PIN_77_MSDC1_CLK__FUNC_MSDC1_CLK>;
+			bias-pull-down;
+			drive-strength = <MTK_DRIVE_4mA>;
+		};
+
+		pins_insert {
+			pinmux = <MT8173_PIN_132_I2S0_DATA1__FUNC_GPIO132>;
+			bias-pull-up;
+		};
+	};
+
+	mmc0_pins_uhs: mmc0 {
+		pins_cmd_dat {
+			pinmux = <MT8173_PIN_57_MSDC0_DAT0__FUNC_MSDC0_DAT0>,
+				 <MT8173_PIN_58_MSDC0_DAT1__FUNC_MSDC0_DAT1>,
+				 <MT8173_PIN_59_MSDC0_DAT2__FUNC_MSDC0_DAT2>,
+				 <MT8173_PIN_60_MSDC0_DAT3__FUNC_MSDC0_DAT3>,
+				 <MT8173_PIN_61_MSDC0_DAT4__FUNC_MSDC0_DAT4>,
+				 <MT8173_PIN_62_MSDC0_DAT5__FUNC_MSDC0_DAT5>,
+				 <MT8173_PIN_63_MSDC0_DAT6__FUNC_MSDC0_DAT6>,
+				 <MT8173_PIN_64_MSDC0_DAT7__FUNC_MSDC0_DAT7>,
+				 <MT8173_PIN_66_MSDC0_CMD__FUNC_MSDC0_CMD>;
+			input-enable;
+			drive-strength = <MTK_DRIVE_2mA>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins_clk {
+			pinmux = <MT8173_PIN_65_MSDC0_CLK__FUNC_MSDC0_CLK>;
+			drive-strength = <MTK_DRIVE_2mA>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins_rst {
+			pinmux = <MT8173_PIN_68_MSDC0_RST___FUNC_MSDC0_RSTB>;
+			bias-pull-up;
+		};
+	};
+
+	mmc1_pins_uhs: mmc1 {
+		pins_cmd_dat {
+			pinmux = <MT8173_PIN_73_MSDC1_DAT0__FUNC_MSDC1_DAT0>,
+				 <MT8173_PIN_74_MSDC1_DAT1__FUNC_MSDC1_DAT1>,
+				 <MT8173_PIN_75_MSDC1_DAT2__FUNC_MSDC1_DAT2>,
+				 <MT8173_PIN_76_MSDC1_DAT3__FUNC_MSDC1_DAT3>,
+				 <MT8173_PIN_78_MSDC1_CMD__FUNC_MSDC1_CMD>;
+			input-enable;
+			drive-strength = <MTK_DRIVE_4mA>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins_clk {
+			pinmux = <MT8173_PIN_77_MSDC1_CLK__FUNC_MSDC1_CLK>;
+			drive-strength = <MTK_DRIVE_4mA>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+	};
+};
+
+&pwrap {
+	pmic: mt6397 {
+		compatible = "mediatek,mt6397";
+		interrupt-parent = <&pio>;
+		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+
+		mt6397regulator: mt6397regulator {
+			compatible = "mediatek,mt6397-regulator";
+
+			mt6397_vpca15_reg: buck_vpca15 {
+				regulator-compatible = "buck_vpca15";
+				regulator-name = "vpca15";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vpca7_reg: buck_vpca7 {
+				regulator-compatible = "buck_vpca7";
+				regulator-name = "vpca7";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+			};
+
+			mt6397_vsramca15_reg: buck_vsramca15 {
+				regulator-compatible = "buck_vsramca15";
+				regulator-name = "vsramca15";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vsramca7_reg: buck_vsramca7 {
+				regulator-compatible = "buck_vsramca7";
+				regulator-name = "vsramca7";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vcore_reg: buck_vcore {
+				regulator-compatible = "buck_vcore";
+				regulator-name = "vcore";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vgpu_reg: buck_vgpu {
+				regulator-compatible = "buck_vgpu";
+				regulator-name = "vgpu";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+			};
+
+			mt6397_vdrm_reg: buck_vdrm {
+				regulator-compatible = "buck_vdrm";
+				regulator-name = "vdrm";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vio18_reg: buck_vio18 {
+				regulator-compatible = "buck_vio18";
+				regulator-name = "vio18";
+				regulator-min-microvolt = <1620000>;
+				regulator-max-microvolt = <1980000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+			};
+
+			mt6397_vtcxo_reg: ldo_vtcxo {
+				regulator-compatible = "ldo_vtcxo";
+				regulator-name = "vtcxo";
+				regulator-always-on;
+			};
+
+			mt6397_va28_reg: ldo_va28 {
+				regulator-compatible = "ldo_va28";
+				regulator-name = "va28";
+				regulator-always-on;
+			};
+
+			mt6397_vcama_reg: ldo_vcama {
+				regulator-compatible = "ldo_vcama";
+				regulator-name = "vcama";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vio28_reg: ldo_vio28 {
+				regulator-compatible = "ldo_vio28";
+				regulator-name = "vio28";
+				regulator-always-on;
+			};
+
+			mt6397_vusb_reg: ldo_vusb {
+				regulator-compatible = "ldo_vusb";
+				regulator-name = "vusb";
+			};
+
+			mt6397_vmc_reg: ldo_vmc {
+				regulator-compatible = "ldo_vmc";
+				regulator-name = "vmc";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vmch_reg: ldo_vmch {
+				regulator-compatible = "ldo_vmch";
+				regulator-name = "vmch";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vemc_3v3_reg: ldo_vemc3v3 {
+				regulator-compatible = "ldo_vemc3v3";
+				regulator-name = "vemc_3v3";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp1_reg: ldo_vgp1 {
+				regulator-compatible = "ldo_vgp1";
+				regulator-name = "vcamd";
+				regulator-min-microvolt = <1220000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <240>;
+			};
+
+			mt6397_vgp2_reg: ldo_vgp2 {
+				regulator-compatible = "ldo_vgp2";
+				regulator-name = "vcamio";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp3_reg: ldo_vgp3 {
+				regulator-compatible = "ldo_vgp3";
+				regulator-name = "vcamaf";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp4_reg: ldo_vgp4 {
+				regulator-compatible = "ldo_vgp4";
+				regulator-name = "vgp4";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp5_reg: ldo_vgp5 {
+				regulator-compatible = "ldo_vgp5";
+				regulator-name = "vgp5";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp6_reg: ldo_vgp6 {
+				regulator-compatible = "ldo_vgp6";
+				regulator-name = "vgp6";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vibr_reg: ldo_vibr {
+				regulator-compatible = "ldo_vibr";
+				regulator-name = "vibr";
+				regulator-min-microvolt = <1300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+		};
+	};
+};
+
 &uart0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 27237a1c1a87..d18ee4259ee5 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -11,8 +11,11 @@
  * GNU General Public License for more details.
  */
 
+#include <dt-bindings/clock/mt8173-clk.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/mt8173-power.h>
+#include <dt-bindings/reset-controller/mt8173-resets.h>
 #include "mt8173-pinfunc.h"
 
 / {
@@ -49,6 +52,8 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
 			reg = <0x000>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
 		};
 
 		cpu1: cpu@1 {
@@ -56,6 +61,7 @@
 			compatible = "arm,cortex-a53";
 			reg = <0x001>;
 			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
 		};
 
 		cpu2: cpu@100 {
@@ -63,6 +69,7 @@
 			compatible = "arm,cortex-a57";
 			reg = <0x100>;
 			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
 		};
 
 		cpu3: cpu@101 {
@@ -70,6 +77,20 @@
 			compatible = "arm,cortex-a57";
 			reg = <0x101>;
 			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+
+		idle-states {
+			entry-method = "arm,psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				local-timer-stop;
+				entry-latency-us = <639>;
+				exit-latency-us = <680>;
+				min-residency-us = <1088>;
+				arm,psci-suspend-param = <0x0010000>;
+			};
 		};
 	};
 
@@ -81,10 +102,18 @@
 		cpu_on	      = <0x84000003>;
 	};
 
-	uart_clk: dummy26m {
+	clk26m: oscillator@0 {
 		compatible = "fixed-clock";
+		#clock-cells = <0>;
 		clock-frequency = <26000000>;
+		clock-output-names = "clk26m";
+	};
+
+	clk32k: oscillator@1 {
+		compatible = "fixed-clock";
 		#clock-cells = <0>;
+		clock-frequency = <32000>;
+		clock-output-names = "clk32k";
 	};
 
 	timer {
@@ -106,11 +135,32 @@
 		compatible = "simple-bus";
 		ranges;
 
-		/*
-		 * Pinctrl access register at 0x10005000 through regmap.
-		 * Register 0x1000b000 is used by EINT.
-		 */
-		pio: pinctrl@10005000 {
+		topckgen: clock-controller@10000000 {
+			compatible = "mediatek,mt8173-topckgen";
+			reg = <0 0x10000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		infracfg: power-controller@10001000 {
+			compatible = "mediatek,mt8173-infracfg", "syscon";
+			reg = <0 0x10001000 0 0x1000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
+		pericfg: power-controller@10003000 {
+			compatible = "mediatek,mt8173-pericfg", "syscon";
+			reg = <0 0x10003000 0 0x1000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
+		syscfg_pctl_a: syscfg_pctl_a@10005000 {
+			compatible = "mediatek,mt8173-pctl-a-syscfg", "syscon";
+			reg = <0 0x10005000 0 0x1000>;
+		};
+
+		pio: pinctrl@0x10005000 {
 			compatible = "mediatek,mt8173-pinctrl";
 			reg = <0 0x1000b000 0 0x1000>;
 			mediatek,pctl-regmap = <&syscfg_pctl_a>;
@@ -122,11 +172,81 @@
 			interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+
+			i2c0_pins_a: i2c0 {
+				pins1 {
+					pinmux = <MT8173_PIN_45_SDA0__FUNC_SDA0>,
+						 <MT8173_PIN_46_SCL0__FUNC_SCL0>;
+					bias-disable;
+				};
+			};
+
+			i2c1_pins_a: i2c1 {
+				pins1 {
+					pinmux = <MT8173_PIN_125_SDA1__FUNC_SDA1>,
+						 <MT8173_PIN_126_SCL1__FUNC_SCL1>;
+					bias-disable;
+				};
+			};
+
+			i2c2_pins_a: i2c2 {
+				pins1 {
+					pinmux = <MT8173_PIN_43_SDA2__FUNC_SDA2>,
+						 <MT8173_PIN_44_SCL2__FUNC_SCL2>;
+					bias-disable;
+				};
+			};
+
+			i2c3_pins_a: i2c3 {
+				pins1 {
+					pinmux = <MT8173_PIN_106_SDA3__FUNC_SDA3>,
+						 <MT8173_PIN_107_SCL3__FUNC_SCL3>;
+					bias-disable;
+				};
+			};
+
+			i2c4_pins_a: i2c4 {
+				pins1 {
+					pinmux = <MT8173_PIN_133_SDA4__FUNC_SDA4>,
+						 <MT8173_PIN_134_SCL4__FUNC_SCL4>;
+					bias-disable;
+				};
+			};
+
+			i2c6_pins_a: i2c6 {
+				pins1 {
+					pinmux = <MT8173_PIN_100_MSDC2_DAT0__FUNC_SDA5>,
+						 <MT8173_PIN_101_MSDC2_DAT1__FUNC_SCL5>;
+					bias-disable;
+				};
+			};
 		};
 
-		syscfg_pctl_a: syscfg_pctl_a@10005000 {
-			compatible = "mediatek,mt8173-pctl-a-syscfg", "syscon";
-			reg = <0 0x10005000 0 0x1000>;
+		scpsys: scpsys@10006000 {
+			compatible = "mediatek,mt8173-scpsys";
+			#power-domain-cells = <1>;
+			reg = <0 0x10006000 0 0x1000>;
+			clocks = <&clk26m>,
+				 <&topckgen CLK_TOP_MM_SEL>;
+			clock-names = "mfg", "mm";
+			infracfg = <&infracfg>;
+		};
+
+		watchdog: watchdog@10007000 {
+			compatible = "mediatek,mt8173-wdt",
+				     "mediatek,mt6589-wdt";
+			reg = <0 0x10007000 0 0x100>;
+		};
+
+		pwrap: pwrap@1000d000 {
+			compatible = "mediatek,mt8173-pwrap";
+			reg = <0 0x1000d000 0 0x1000>;
+			reg-names = "pwrap";
+			interrupts = <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
+			resets = <&infracfg MT8173_INFRA_PMIC_WRAP_RST>;
+			reset-names = "pwrap";
+			clocks = <&infracfg CLK_INFRA_PMICSPI>, <&infracfg CLK_INFRA_PMICWRAP>;
+			clock-names = "spi", "wrap";
 		};
 
 		sysirq: intpol-controller@10200620 {
@@ -138,6 +258,12 @@
 			reg = <0 0x10200620 0 0x20>;
 		};
 
+		apmixedsys: clock-controller@10209000 {
+			compatible = "mediatek,mt8173-apmixedsys";
+			reg = <0 0x10209000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
 		gic: interrupt-controller@10220000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
@@ -156,7 +282,8 @@
 				     "mediatek,mt6577-uart";
 			reg = <0 0x11002000 0 0x400>;
 			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART0_SEL>, <&pericfg CLK_PERI_UART0>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
@@ -165,7 +292,8 @@
 				     "mediatek,mt6577-uart";
 			reg = <0 0x11003000 0 0x400>;
 			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART1_SEL>, <&pericfg CLK_PERI_UART1>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
@@ -174,7 +302,8 @@
 				     "mediatek,mt6577-uart";
 			reg = <0 0x11004000 0 0x400>;
 			interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART2_SEL>, <&pericfg CLK_PERI_UART2>;
+			clock-names = "baud", "bus";
 			status = "disabled";
 		};
 
@@ -183,7 +312,179 @@
 				     "mediatek,mt6577-uart";
 			reg = <0 0x11005000 0 0x400>;
 			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&uart_clk>;
+			clocks = <&pericfg CLK_PERI_UART3_SEL>, <&pericfg CLK_PERI_UART3>;
+			clock-names = "baud", "bus";
+			status = "disabled";
+		};
+
+		i2c0: i2c@11007000 {
+			compatible = "mediatek,mt8173-i2c";
+			reg = <0 0x11007000 0 0x70>,
+			      <0 0x11000100 0 0x80>;
+			interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_LOW>;
+			clock-div = <16>;
+			clocks = <&pericfg CLK_PERI_I2C0>,
+				 <&pericfg CLK_PERI_AP_DMA>;
+			clock-names = "main", "dma";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c0_pins_a>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@11008000 {
+			compatible = "mediatek,mt8173-i2c";
+			reg = <0 0x11008000 0 0x70>,
+			      <0 0x11000180 0 0x80>;
+			interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_LOW>;
+			clock-div = <16>;
+			clocks = <&pericfg CLK_PERI_I2C1>,
+				 <&pericfg CLK_PERI_AP_DMA>;
+			clock-names = "main", "dma";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c1_pins_a>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c2: i2c@11009000 {
+			compatible = "mediatek,mt8173-i2c";
+			reg = <0 0x11009000 0 0x70>,
+			      <0 0x11000200 0 0x80>;
+			interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_LOW>;
+			clock-div = <16>;
+			clocks = <&pericfg CLK_PERI_I2C2>,
+				 <&pericfg CLK_PERI_AP_DMA>;
+			clock-names = "main", "dma";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c2_pins_a>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c3: i2c3@11010000 {
+			compatible = "mediatek,mt8173-i2c";
+			reg = <0 0x11010000 0 0x70>,
+			      <0 0x11000280 0 0x80>;
+			interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_LOW>;
+			clock-div = <16>;
+			clocks = <&pericfg CLK_PERI_I2C3>,
+				 <&pericfg CLK_PERI_AP_DMA>;
+			clock-names = "main", "dma";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c3_pins_a>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c4: i2c4@11011000 {
+			compatible = "mediatek,mt8173-i2c";
+			reg = <0 0x11011000 0 0x70>,
+			      <0 0x11000300 0 0x80>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_LOW>;
+			clock-div = <16>;
+			clocks = <&pericfg CLK_PERI_I2C4>,
+				 <&pericfg CLK_PERI_AP_DMA>;
+			clock-names = "main", "dma";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c4_pins_a>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c6: i2c6@11013000 {
+			compatible = "mediatek,mt8173-i2c";
+			reg = <0 0x11013000 0 0x70>,
+			      <0 0x11000080 0 0x80>;
+			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_LOW>;
+			clock-div = <16>;
+			clocks = <&pericfg CLK_PERI_I2C6>,
+				 <&pericfg CLK_PERI_AP_DMA>;
+			clock-names = "main", "dma";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c6_pins_a>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		afe: audio-controller@11220000  {
+			compatible = "mediatek,mt8173-afe-pcm";
+			reg = <0 0x11220000 0 0x1000>;
+			interrupts = <GIC_SPI 134 IRQ_TYPE_EDGE_FALLING>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_AUDIO>;
+			clocks = <&infracfg CLK_INFRA_AUDIO>,
+				 <&topckgen CLK_TOP_AUDIO_SEL>,
+				 <&topckgen CLK_TOP_AUD_INTBUS_SEL>,
+				 <&topckgen CLK_TOP_APLL1_DIV0>,
+				 <&topckgen CLK_TOP_APLL2_DIV0>,
+				 <&topckgen CLK_TOP_I2S0_M_SEL>,
+				 <&topckgen CLK_TOP_I2S1_M_SEL>,
+				 <&topckgen CLK_TOP_I2S2_M_SEL>,
+				 <&topckgen CLK_TOP_I2S3_M_SEL>,
+				 <&topckgen CLK_TOP_I2S3_B_SEL>;
+			clock-names = "infra_sys_audio_clk",
+				      "top_pdn_audio",
+				      "top_pdn_aud_intbus",
+				      "bck0",
+				      "bck1",
+				      "i2s0_m",
+				      "i2s1_m",
+				      "i2s2_m",
+				      "i2s3_m",
+				      "i2s3_b";
+			assigned-clocks = <&topckgen CLK_TOP_AUD_1_SEL>,
+					  <&topckgen CLK_TOP_AUD_2_SEL>;
+			assigned-clock-parents = <&topckgen CLK_TOP_APLL1>,
+						 <&topckgen CLK_TOP_APLL2>;
+		};
+
+		mmc0: mmc@11230000 {
+			compatible = "mediatek,mt8173-mmc",
+				     "mediatek,mt8135-mmc";
+			reg = <0 0x11230000 0 0x1000>;
+			interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&pericfg CLK_PERI_MSDC30_0>,
+				 <&topckgen CLK_TOP_MSDC50_0_H_SEL>;
+			clock-names = "source", "hclk";
+			status = "disabled";
+		};
+
+		mmc1: mmc@11240000 {
+			compatible = "mediatek,mt8173-mmc",
+				     "mediatek,mt8135-mmc";
+			reg = <0 0x11240000 0 0x1000>;
+			interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&pericfg CLK_PERI_MSDC30_1>,
+				 <&topckgen CLK_TOP_AXI_SEL>;
+			clock-names = "source", "hclk";
+			status = "disabled";
+		};
+
+		mmc2: mmc@11250000 {
+			compatible = "mediatek,mt8173-mmc",
+				     "mediatek,mt8135-mmc";
+			reg = <0 0x11250000 0 0x1000>;
+			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&pericfg CLK_PERI_MSDC30_2>,
+				 <&topckgen CLK_TOP_AXI_SEL>;
+			clock-names = "source", "hclk";
+			status = "disabled";
+		};
+
+		mmc3: mmc@11260000 {
+			compatible = "mediatek,mt8173-mmc",
+				     "mediatek,mt8135-mmc";
+			reg = <0 0x11260000 0 0x1000>;
+			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&pericfg CLK_PERI_MSDC30_3>,
+				 <&topckgen CLK_TOP_MSDC50_2_H_SEL>;
+			clock-names = "source", "hclk";
 			status = "disabled";
 		};
 	};
diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi b/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi
index 535532b9287f..e03c11d9d834 100644
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi
@@ -2,27 +2,37 @@
 
 &pm8916_gpios {
 
-	pinctrl-names = "default";
-	pinctrl-0 = <&pm8916_gpios_default>;
-
-	pm8916_gpios_default: default {
-		usb_hub_reset_pm {
-			pins = "gpio1";
+	usb_hub_reset_pm: usb_hub_reset_pm {
+		pinconf {
+			pins = "gpio3";
 			function = PMIC_GPIO_FUNC_NORMAL;
 			output-low;
 		};
-		usb_sw_sel_pm {
-			pins = "gpio2";
+	};
+
+	usb_sw_sel_pm: usb_sw_sel_pm {
+		pinconf {
+			pins = "gpio4";
 			function = PMIC_GPIO_FUNC_NORMAL;
+			power-source = <PM8916_GPIO_VPH>;
 			input-disable;
 		};
-		usr_led_3_ctrl {
-			pins = "gpio3";
+	};
+
+	pm8916_gpios_leds: pm8916_gpios_leds {
+		pinconf {
+			pins = "gpio1", "gpio2";
 			function = PMIC_GPIO_FUNC_NORMAL;
 			output-low;
 		};
-		usr_led_4_ctrl {
-			pins = "gpio4";
+	};
+};
+
+&pm8916_mpps {
+
+	pm8916_mpps_leds: pm8916_mpps_leds {
+		pinconf {
+			pins = "mpp2", "mpp3";
 			function = PMIC_GPIO_FUNC_NORMAL;
 			output-low;
 		};
diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi b/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi
index 5f7023f90df7..cbeee0bcdf52 100644
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi
@@ -3,17 +3,9 @@
 
 &msmgpio {
 
-	pinctrl-names = "default";
-	pinctrl-0 = <&soc_gpios_default>;
-
-	soc_gpios_default: default {
-		usr_led_1_ctrl_default: usr_led_1_ctrl_default {
-			pins = "gpio21";
-			function = "gpio";
-			output-low;
-		};
-		usr_led_2_ctrl_default: usr_led_2_ctrl_default {
-			pins = "gpio120";
+	msmgpio_leds: msmgpio_leds {
+		pinconf {
+			pins = "gpio21", "gpio120";
 			function = "gpio";
 			output-low;
 		};
diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
index 98abece6b233..66804ffbc6d2 100644
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
@@ -32,5 +32,56 @@
 			pinctrl-0 = <&blsp1_uart2_default>;
 			pinctrl-1 = <&blsp1_uart2_sleep>;
 		};
+
+		leds {
+			pinctrl-names = "default";
+			pinctrl-0 = <&msmgpio_leds>,
+				    <&pm8916_gpios_leds>,
+				    <&pm8916_mpps_leds>;
+
+			compatible = "gpio-leds";
+
+			led@1 {
+				label = "apq8016-sbc:green:user1";
+				gpios = <&msmgpio 21 GPIO_ACTIVE_HIGH>;
+				linux,default-trigger = "heartbeat";
+				default-state = "off";
+			};
+
+			led@2 {
+				label = "apq8016-sbc:green:user2";
+				gpios = <&msmgpio 120 GPIO_ACTIVE_HIGH>;
+				linux,default-trigger = "mmc0";
+				default-state = "off";
+			};
+
+			led@3 {
+				label = "apq8016-sbc:green:user3";
+				gpios = <&pm8916_gpios 1 GPIO_ACTIVE_HIGH>;
+				linux,default-trigger = "mmc1";
+				default-state = "off";
+			};
+
+			led@4 {
+				label = "apq8016-sbc:green:user4";
+				gpios = <&pm8916_gpios 2 GPIO_ACTIVE_HIGH>;
+				linux,default-trigger = "none";
+				default-state = "off";
+			};
+
+			led@5 {
+				label = "apq8016-sbc:yellow:wlan";
+				gpios = <&pm8916_mpps 2 GPIO_ACTIVE_HIGH>;
+				linux,default-trigger = "wlan";
+				default-state = "off";
+			};
+
+			led@6 {
+				label = "apq8016-sbc:blue:bt";
+				gpios = <&pm8916_mpps 3 GPIO_ACTIVE_HIGH>;
+				linux,default-trigger = "bt";
+				default-state = "off";
+			};
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
new file mode 100644
index 000000000000..568956859088
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
@@ -0,0 +1,430 @@
+/*
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+&msmgpio {
+
+	blsp1_uart2_default: blsp1_uart2_default {
+		pinmux {
+			function = "blsp_uart2";
+			pins = "gpio4", "gpio5";
+		};
+		pinconf {
+			pins = "gpio4", "gpio5";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp1_uart2_sleep: blsp1_uart2_sleep {
+		pinmux {
+			function = "blsp_uart2";
+			pins = "gpio4", "gpio5";
+		};
+		pinconf {
+			pins = "gpio4", "gpio5";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	spi1_default: spi1_default {
+		pinmux {
+			function = "blsp_spi1";
+			pins = "gpio0", "gpio1", "gpio3";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio2";
+		};
+		pinconf {
+			pins = "gpio0", "gpio1", "gpio3";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio2";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	spi1_sleep: spi1_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio0", "gpio1", "gpio2", "gpio3";
+		};
+		pinconf {
+			pins = "gpio0", "gpio1", "gpio2", "gpio3";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	spi2_default: spi2_default {
+		pinmux {
+			function = "blsp_spi2";
+			pins = "gpio4", "gpio5", "gpio7";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio6";
+		};
+		pinconf {
+			pins = "gpio4", "gpio5", "gpio6", "gpio7";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio6";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	spi2_sleep: spi2_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio4", "gpio5", "gpio6", "gpio7";
+		};
+		pinconf {
+			pins = "gpio4", "gpio5", "gpio6", "gpio7";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	spi3_default: spi3_default {
+		pinmux {
+			function = "blsp_spi3";
+			pins = "gpio8", "gpio9", "gpio11";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio10";
+		};
+		pinconf {
+			pins = "gpio8", "gpio9", "gpio10", "gpio11";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio10";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	spi3_sleep: spi3_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio8", "gpio9", "gpio10", "gpio11";
+		};
+		pinconf {
+			pins = "gpio8", "gpio9", "gpio10", "gpio11";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	spi4_default: spi4_default {
+		pinmux {
+			function = "blsp_spi4";
+			pins = "gpio12", "gpio13", "gpio15";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio14";
+		};
+		pinconf {
+			pins = "gpio12", "gpio13", "gpio14", "gpio15";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio14";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	spi4_sleep: spi4_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio12", "gpio13", "gpio14", "gpio15";
+		};
+		pinconf {
+			pins = "gpio12", "gpio13", "gpio14", "gpio15";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	spi5_default: spi5_default {
+		pinmux {
+			function = "blsp_spi5";
+			pins = "gpio16", "gpio17", "gpio19";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio18";
+		};
+		pinconf {
+			pins = "gpio16", "gpio17", "gpio18", "gpio19";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio18";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	spi5_sleep: spi5_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio16", "gpio17", "gpio18", "gpio19";
+		};
+		pinconf {
+			pins = "gpio16", "gpio17", "gpio18", "gpio19";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	spi6_default: spi6_default {
+		pinmux {
+			function = "blsp_spi6";
+			pins = "gpio20", "gpio21", "gpio23";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio22";
+		};
+		pinconf {
+			pins = "gpio20", "gpio21", "gpio22", "gpio23";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio22";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	spi6_sleep: spi6_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio20", "gpio21", "gpio22", "gpio23";
+		};
+		pinconf {
+			pins = "gpio20", "gpio21", "gpio22", "gpio23";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	i2c4_default: i2c4_default {
+		pinmux {
+			function = "blsp_i2c4";
+			pins = "gpio14", "gpio15";
+		};
+		pinconf {
+			pins = "gpio14", "gpio15";
+			drive-strength = <2>;
+			bias-disable = <0>;
+		};
+	};
+
+	i2c4_sleep: i2c4_sleep {
+		pinmux {
+			function = "blsp_i2c4";
+			pins = "gpio14", "gpio15";
+		};
+		pinconf {
+			pins = "gpio14", "gpio15";
+			drive-strength = <2>;
+			bias-disable = <0>;
+		};
+	};
+
+	sdhc2_cd_pin {
+		sdc2_cd_on: cd_on {
+			pinmux {
+				function = "gpio";
+				pins = "gpio38";
+			};
+			pinconf {
+				pins = "gpio38";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+		};
+		sdc2_cd_off: cd_off {
+			pinmux {
+				function = "gpio";
+				pins = "gpio38";
+			};
+			pinconf {
+				pins = "gpio38";
+				drive-strength = <2>;
+				bias-disable;
+			};
+		};
+	};
+
+	pmx_sdc1_clk {
+		sdc1_clk_on: clk_on {
+			pinmux {
+				pins = "sdc1_clk";
+			};
+			pinconf {
+				pins = "sdc1_clk";
+				bias-disable;
+				drive-strength = <16>;
+			};
+		};
+		sdc1_clk_off: clk_off {
+			pinmux {
+				pins = "sdc1_clk";
+			};
+			pinconf {
+				pins = "sdc1_clk";
+				bias-disable;
+				drive-strength = <2>;
+			};
+		};
+	};
+
+	pmx_sdc1_cmd {
+		sdc1_cmd_on: cmd_on {
+			pinmux {
+				pins = "sdc1_cmd";
+			};
+			pinconf {
+				pins = "sdc1_cmd";
+				bias-pull-up;
+				drive-strength = <10>;
+			};
+		};
+		sdc1_cmd_off: cmd_off {
+			pinmux {
+				pins = "sdc1_cmd";
+			};
+			pinconf {
+				pins = "sdc1_cmd";
+				bias-pull-up;
+				drive-strength = <2>;
+			};
+		};
+	};
+
+	pmx_sdc1_data {
+		sdc1_data_on: data_on {
+			pinmux {
+				pins = "sdc1_data";
+			};
+			pinconf {
+				pins = "sdc1_data";
+				bias-pull-up;
+				drive-strength = <10>;
+			};
+		};
+		sdc1_data_off: data_off {
+			pinmux {
+				pins = "sdc1_data";
+			};
+			pinconf {
+				pins = "sdc1_data";
+				bias-pull-up;
+				drive-strength = <2>;
+			};
+		};
+	};
+
+	pmx_sdc2_clk {
+		sdc2_clk_on: clk_on {
+			pinmux {
+				pins = "sdc2_clk";
+			};
+			pinconf {
+				pins = "sdc2_clk";
+				bias-disable;
+				drive-strength = <16>;
+			};
+		};
+		sdc2_clk_off: clk_off {
+			pinmux {
+				pins = "sdc2_clk";
+			};
+			pinconf {
+				pins = "sdc2_clk";
+				bias-disable;
+				drive-strength = <2>;
+			};
+		};
+	};
+
+	pmx_sdc2_cmd {
+		sdc2_cmd_on: cmd_on {
+			pinmux {
+				pins = "sdc2_cmd";
+			};
+			pinconf {
+				pins = "sdc2_cmd";
+				bias-pull-up;
+				drive-strength = <10>;
+			};
+		};
+		sdc2_cmd_off: cmd_off {
+			pinmux {
+				pins = "sdc2_cmd";
+			};
+			pinconf {
+				pins = "sdc2_cmd";
+				bias-pull-up;
+				drive-strength = <2>;
+			};
+		};
+	};
+
+	pmx_sdc2_data {
+		sdc2_data_on: data_on {
+			pinmux {
+				pins = "sdc2_data";
+			};
+			pinconf {
+				pins = "sdc2_data";
+				bias-pull-up;
+				drive-strength = <10>;
+			};
+		};
+		sdc2_data_off: data_off {
+			pinmux {
+				pins = "sdc2_data";
+			};
+			pinconf {
+				pins = "sdc2_data";
+				bias-pull-up;
+				drive-strength = <2>;
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 0f49ebd0aa8b..5911de008dd5 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -24,7 +24,10 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
-	aliases { };
+	aliases {
+		sdhc1 = &sdhc_1; /* SDC1 eMMC slot */
+		sdhc2 = &sdhc_2; /* SDC2 SD card slot */
+	};
 
 	chosen { };
 
@@ -90,30 +93,6 @@
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
-
-			blsp1_uart2_default: blsp1_uart2_default {
-				pinmux {
-					function = "blsp_uart2";
-					pins = "gpio4", "gpio5";
-				};
-				pinconf {
-					pins = "gpio4", "gpio5";
-					drive-strength = <16>;
-					bias-disable;
-				};
-			};
-
-			blsp1_uart2_sleep: blsp1_uart2_sleep {
-				pinmux {
-					function = "blsp_uart2";
-					pins = "gpio4", "gpio5";
-				};
-				pinconf {
-					pins = "gpio4", "gpio5";
-					drive-strength = <2>;
-					bias-pull-down;
-				};
-			};
 		};
 
 		gcc: qcom,gcc@1800000 {
@@ -132,6 +111,202 @@
 			status = "disabled";
 		};
 
+		blsp_dma: dma@7884000 {
+			compatible = "qcom,bam-v1.7.0";
+			reg = <0x07884000 0x23000>;
+			interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "bam_clk";
+			#dma-cells = <1>;
+			qcom,ee = <0>;
+			status = "disabled";
+		};
+
+		blsp_spi1: spi@78b5000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078b5000 0x600>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 5>, <&blsp_dma 4>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi1_default>;
+			pinctrl-1 = <&spi1_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp_spi2: spi@78b6000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078b6000 0x600>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 7>, <&blsp_dma 6>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi2_default>;
+			pinctrl-1 = <&spi2_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp_spi3: spi@78b7000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078b7000 0x600>;
+			interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP3_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 9>, <&blsp_dma 8>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi3_default>;
+			pinctrl-1 = <&spi3_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp_spi4: spi@78b8000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078b8000 0x600>;
+			interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP4_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 11>, <&blsp_dma 10>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi4_default>;
+			pinctrl-1 = <&spi4_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp_spi5: spi@78b9000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078b9000 0x600>;
+			interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP5_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 13>, <&blsp_dma 12>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi5_default>;
+			pinctrl-1 = <&spi5_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp_spi6: spi@78ba000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078ba000 0x600>;
+			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP6_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 15>, <&blsp_dma 14>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi6_default>;
+			pinctrl-1 = <&spi6_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp_i2c4: i2c@78b8000 {
+			compatible = "qcom,i2c-qup-v2.2.1";
+			reg = <0x78b8000 0x1000>;
+			interrupts = <GIC_SPI 98 0>;
+			clocks = <&gcc GCC_BLSP1_AHB_CLK>,
+				<&gcc GCC_BLSP1_QUP4_I2C_APPS_CLK>;
+			clock-names = "iface", "core";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&i2c4_default>;
+			pinctrl-1 = <&i2c4_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		sdhc_1: sdhci@07824000 {
+			compatible = "qcom,sdhci-msm-v4";
+			reg = <0x07824900 0x11c>, <0x07824000 0x800>;
+			reg-names = "hc_mem", "core_mem";
+
+			interrupts = <0 123 0>, <0 138 0>;
+			interrupt-names = "hc_irq", "pwr_irq";
+			clocks = <&gcc GCC_SDCC1_APPS_CLK>,
+				 <&gcc GCC_SDCC1_AHB_CLK>;
+			clock-names = "core", "iface";
+			bus-width = <8>;
+			non-removable;
+			status = "disabled";
+		};
+
+		sdhc_2: sdhci@07864000 {
+			compatible = "qcom,sdhci-msm-v4";
+			reg = <0x07864900 0x11c>, <0x07864000 0x800>;
+			reg-names = "hc_mem", "core_mem";
+
+			interrupts = <0 125 0>, <0 221 0>;
+			interrupt-names = "hc_irq", "pwr_irq";
+			clocks = <&gcc GCC_SDCC2_APPS_CLK>,
+				 <&gcc GCC_SDCC2_AHB_CLK>;
+			clock-names = "core", "iface";
+			bus-width = <4>;
+			status = "disabled";
+		};
+
+		usb_dev: usb@78d9000 {
+			compatible = "qcom,ci-hdrc";
+			reg = <0x78d9000 0x400>;
+			dr_mode = "peripheral";
+			interrupts = <GIC_SPI 134 IRQ_TYPE_NONE>;
+			usb-phy = <&usb_otg>;
+			status = "disabled";
+		};
+
+		usb_host: ehci@78d9000 {
+			compatible = "qcom,ehci-host";
+			reg = <0x78d9000 0x400>;
+			interrupts = <GIC_SPI 134 IRQ_TYPE_NONE>;
+			usb-phy = <&usb_otg>;
+			status = "disabled";
+		};
+
+		usb_otg: phy@78d9000 {
+			compatible = "qcom,usb-otg-snps";
+			reg = <0x78d9000 0x400>;
+			interrupts = <GIC_SPI 134 IRQ_TYPE_EDGE_BOTH>,
+				     <GIC_SPI 140 IRQ_TYPE_EDGE_RISING>;
+
+			qcom,vdd-levels = <1 5 7>;
+			qcom,phy-init-sequence = <0x44 0x6B 0x24 0x13>;
+			dr_mode = "peripheral";
+			qcom,otg-control = <2>; // PMIC
+
+			clocks = <&gcc GCC_USB_HS_AHB_CLK>,
+				 <&gcc GCC_USB_HS_SYSTEM_CLK>,
+				 <&gcc GCC_USB2A_PHY_SLEEP_CLK>;
+			clock-names = "iface", "core", "sleep";
+
+			resets = <&gcc GCC_USB2A_PHY_BCR>,
+				 <&gcc GCC_USB_HS_BCR>;
+			reset-names = "phy", "link";
+			status = "disabled";
+		};
+
 		intc: interrupt-controller@b000000 {
 			compatible = "qcom,msm-qgic2";
 			interrupt-controller;
@@ -217,3 +392,5 @@
 		};
 	};
 };
+
+#include "msm8916-pins.dtsi"
diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile
new file mode 100644
index 000000000000..601e6a236c1d
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/Makefile
@@ -0,0 +1,5 @@
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3368-r88.dtb
+
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
+clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
new file mode 100644
index 000000000000..401a81231eb9
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
@@ -0,0 +1,354 @@
+/*
+ * Copyright (c) 2015 Heiko Stuebner <heiko@sntech.de>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "rk3368.dtsi"
+
+/ {
+	model = "Rockchip R88";
+	compatible = "rockchip,r88", "rockchip,rk3368";
+
+	chosen {
+		stdout-path = "serial2:115200n8";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x0 0x0 0x40000000>;
+	};
+
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		pinctrl-0 = <&emmc_reset>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>;
+	};
+
+	keys: gpio-keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pwr_key>;
+
+		button@0 {
+			gpio-key,wakeup = <1>;
+			gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
+			label = "GPIO Power";
+			linux,code = <116>;
+		};
+	};
+
+	leds: gpio-leds {
+		compatible = "gpio-leds";
+
+		work {
+			gpios = <&gpio3 29 GPIO_ACTIVE_HIGH>;
+			label = "r88:green:led";
+			pinctrl-names = "default";
+			pinctrl-0 = <&led_ctl>;
+		};
+	};
+
+	ir: ir-receiver {
+		compatible = "gpio-ir-receiver";
+		gpios = <&gpio3 30 GPIO_ACTIVE_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ir_int>;
+	};
+
+	sdio_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&hym8563>;
+		clock-names = "ext_clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_rst>, <&wifi_reg_on>;
+
+		reset-gpios =
+			/* BT_RST_N */
+			<&gpio3 5 GPIO_ACTIVE_LOW>,
+
+			/* WL_REG_ON */
+			<&gpio3 4 GPIO_ACTIVE_LOW>;
+	};
+
+	vcc_18: vcc18-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_18";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+
+	/* supplies both host and otg */
+	vcc_host: vcc-host-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 4 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&host_vbus_drv>;
+		regulator-name = "vcc_host";
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+
+	vcc_io: vcc-io-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_io";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+
+	vcc_lan: vcc-lan-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_lan";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_io>;
+	};
+
+	vcc_sys: vcc-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_sys";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vccio_wl: vccio-wl-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vccio_wl";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_io>;
+	};
+
+	vdd_10: vdd-10-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_10";
+		regulator-min-microvolt = <1000000>;
+		regulator-max-microvolt = <1000000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+};
+
+&emmc {
+	broken-cd;
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	disable-wp;
+	mmc-pwrseq = <&emmc_pwrseq>;
+	non-removable;
+	num-slots = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>;
+	status = "okay";
+};
+
+&gmac {
+	phy-supply = <&vcc_lan>;
+	phy-mode = "rmii";
+	clock_in_out = "output";
+	snps,reset-gpio = <&gpio3 12 0>;
+	snps,reset-active-low;
+	snps,reset-delays-us = <0 10000 1000000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&rmii_pins>;
+	tx_delay = <0x30>;
+	rx_delay = <0x10>;
+	status = "ok";
+};
+
+&i2c0 {
+	status = "okay";
+
+	vdd_cpu: syr827@40 {
+		compatible = "silergy,syr827";
+		reg = <0x40>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu";
+		regulator-enable-ramp-delay = <300>;
+		regulator-min-microvolt = <712500>;
+		regulator-max-microvolt = <1500000>;
+		regulator-ramp-delay = <8000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+	};
+
+	hym8563: hym8563@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "xin32k";
+		/* rtc_int is not connected */
+	};
+};
+
+&sdio0 {
+	assigned-clocks = <&cru SCLK_SDIO0>;
+	assigned-clock-parents = <&cru PLL_CPLL>;
+	broken-cd;
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&sdio_pwrseq>;
+	non-removable;
+	num-slots = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdio0_clk &sdio0_cmd &sdio0_bus4>;
+	vmmc-supply = <&vcc_io>;
+	vqmmc-supply = <&vccio_wl>;
+	status = "okay";
+};
+
+&pinctrl {
+	pcfg_pull_none_drv_8ma: pcfg-pull-none-drv-8ma {
+		bias-disable;
+		drive-strength = <8>;
+	};
+
+	pcfg_pull_up_drv_8ma: pcfg-pull-up-drv-8ma {
+		bias-pull-up;
+		drive-strength = <8>;
+	};
+
+	emmc {
+		emmc_bus8: emmc-bus8 {
+			rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 19 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 20 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 21 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 22 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 23 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 24 RK_FUNC_2 &pcfg_pull_up_drv_8ma>,
+					<1 25 RK_FUNC_2 &pcfg_pull_up_drv_8ma>;
+		};
+
+		emmc-clk {
+			rockchip,pins = <2 4 RK_FUNC_2 &pcfg_pull_none_drv_8ma>;
+		};
+
+		emmc-cmd {
+			rockchip,pins = <1 26 RK_FUNC_2 &pcfg_pull_up_drv_8ma>;
+		};
+
+		emmc_reset: emmc-reset {
+			rockchip,pins = <2 3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	ir {
+		ir_int: ir-int {
+			rockchip,pins = <3 30 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	keys {
+		pwr_key: pwr-key {
+			rockchip,pins = <0 2 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	leds {
+		stby_pwren: stby-pwren {
+			rockchip,pins = <0 12 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		led_ctl: led-ctl {
+			rockchip,pins = <3 29 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	sdio {
+		wifi_reg_on: wifi-reg-on {
+			rockchip,pins = <3 4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		bt_rst: bt-rst {
+			rockchip,pins = <3 5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		host_vbus_drv: host-vbus-drv {
+			rockchip,pins = <0 4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&saradc {
+	vref-supply = <&vcc_18>;
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&wdt {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
new file mode 100644
index 000000000000..a712bea3bf2c
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -0,0 +1,900 @@
+/*
+ * Copyright (c) 2015 Heiko Stuebner <heiko@sntech.de>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/clock/rk3368-cru.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+/ {
+	compatible = "rockchip,rk3368";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
+		i2c5 = &i2c5;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+		serial4 = &uart4;
+		spi0 = &spi0;
+		spi1 = &spi1;
+		spi2 = &spi2;
+	};
+
+	cpus {
+		#address-cells = <0x2>;
+		#size-cells = <0x0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu_b0>;
+				};
+				core1 {
+					cpu = <&cpu_b1>;
+				};
+				core2 {
+					cpu = <&cpu_b2>;
+				};
+				core3 {
+					cpu = <&cpu_b3>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&cpu_l0>;
+				};
+				core1 {
+					cpu = <&cpu_l1>;
+				};
+				core2 {
+					cpu = <&cpu_l2>;
+				};
+				core3 {
+					cpu = <&cpu_l3>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "arm,psci";
+
+			cpu_sleep: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x1010000>;
+				entry-latency-us = <0x3fffffff>;
+				exit-latency-us = <0x40000000>;
+				min-residency-us = <0xffffffff>;
+			};
+		};
+
+		cpu_l0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x0>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_l1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x1>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_l2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x2>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_l3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x3>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_b0: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x100>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_b1: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x101>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_b2: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x102>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+
+		cpu_b3: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x103>;
+			cpu-idle-states = <&cpu_sleep>;
+			enable-method = "psci";
+		};
+	};
+
+	arm-pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu_l0>, <&cpu_l1>, <&cpu_l2>,
+				     <&cpu_l3>, <&cpu_b0>, <&cpu_b1>,
+				     <&cpu_b2>, <&cpu_b3>;
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13
+			(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>,
+			     <GIC_PPI 14
+			(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>,
+			     <GIC_PPI 11
+			(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>,
+			     <GIC_PPI 10
+			(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	xin24m: oscillator {
+		compatible = "fixed-clock";
+		clock-frequency = <24000000>;
+		clock-output-names = "xin24m";
+		#clock-cells = <0>;
+	};
+
+	sdmmc: dwmmc@ff0c0000 {
+		compatible = "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc";
+		reg = <0x0 0xff0c0000 0x0 0x4000>;
+		clock-freq-min-max = <400000 150000000>;
+		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>;
+		clock-names = "biu", "ciu";
+		fifo-depth = <0x100>;
+		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+		status = "disabled";
+	};
+
+	sdio0: dwmmc@ff0d0000 {
+		compatible = "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc";
+		reg = <0x0 0xff0d0000 0x0 0x4000>;
+		clock-freq-min-max = <400000 150000000>;
+		clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>,
+			 <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>;
+		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		fifo-depth = <0x100>;
+		interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+		status = "disabled";
+	};
+
+	emmc: dwmmc@ff0f0000 {
+		compatible = "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc";
+		reg = <0x0 0xff0f0000 0x0 0x4000>;
+		clock-freq-min-max = <400000 150000000>;
+		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>;
+		clock-names = "biu", "ciu";
+		fifo-depth = <0x100>;
+		interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+		status = "disabled";
+	};
+
+	saradc: saradc@ff100000 {
+		compatible = "rockchip,saradc";
+		reg = <0x0 0xff100000 0x0 0x100>;
+		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
+		#io-channel-cells = <1>;
+		clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
+		clock-names = "saradc", "apb_pclk";
+		status = "disabled";
+	};
+
+	spi0: spi@ff110000 {
+		compatible = "rockchip,rk3368-spi", "rockchip,rk3066-spi";
+		reg = <0x0 0xff110000 0x0 0x1000>;
+		clocks = <&cru SCLK_SPI0>, <&cru PCLK_SPI0>;
+		clock-names = "spiclk", "apb_pclk";
+		interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi0_clk &spi0_tx &spi0_rx &spi0_cs0>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	spi1: spi@ff120000 {
+		compatible = "rockchip,rk3368-spi", "rockchip,rk3066-spi";
+		reg = <0x0 0xff120000 0x0 0x1000>;
+		clocks = <&cru SCLK_SPI1>, <&cru PCLK_SPI1>;
+		clock-names = "spiclk", "apb_pclk";
+		interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi1_clk &spi1_tx &spi1_rx &spi1_cs0>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	spi2: spi@ff130000 {
+		compatible = "rockchip,rk3368-spi", "rockchip,rk3066-spi";
+		reg = <0x0 0xff130000 0x0 0x1000>;
+		clocks = <&cru SCLK_SPI2>, <&cru PCLK_SPI2>;
+		clock-names = "spiclk", "apb_pclk";
+		interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi2_clk &spi2_tx &spi2_rx &spi2_cs0>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c1: i2c@ff140000 {
+		compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c";
+		reg = <0x0 0xff140000 0x0 0x1000>;
+		interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2c";
+		clocks = <&cru PCLK_I2C1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c1_xfer>;
+		status = "disabled";
+	};
+
+	i2c3: i2c@ff150000 {
+		compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c";
+		reg = <0x0 0xff150000 0x0 0x1000>;
+		interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2c";
+		clocks = <&cru PCLK_I2C3>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c3_xfer>;
+		status = "disabled";
+	};
+
+	i2c4: i2c@ff160000 {
+		compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c";
+		reg = <0x0 0xff160000 0x0 0x1000>;
+		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2c";
+		clocks = <&cru PCLK_I2C4>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c4_xfer>;
+		status = "disabled";
+	};
+
+	i2c5: i2c@ff170000 {
+		compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c";
+		reg = <0x0 0xff170000 0x0 0x1000>;
+		interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2c";
+		clocks = <&cru PCLK_I2C5>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c5_xfer>;
+		status = "disabled";
+	};
+
+	uart0: serial@ff180000 {
+		compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart";
+		reg = <0x0 0xff180000 0x0 0x100>;
+		clock-frequency = <24000000>;
+		clocks = <&cru SCLK_UART0>, <&cru PCLK_UART0>;
+		clock-names = "baudclk", "apb_pclk";
+		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	uart1: serial@ff190000 {
+		compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart";
+		reg = <0x0 0xff190000 0x0 0x100>;
+		clock-frequency = <24000000>;
+		clocks = <&cru SCLK_UART1>, <&cru PCLK_UART1>;
+		clock-names = "baudclk", "apb_pclk";
+		interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	uart3: serial@ff1b0000 {
+		compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart";
+		reg = <0x0 0xff1b0000 0x0 0x100>;
+		clock-frequency = <24000000>;
+		clocks = <&cru SCLK_UART3>, <&cru PCLK_UART3>;
+		clock-names = "baudclk", "apb_pclk";
+		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	uart4: serial@ff1c0000 {
+		compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart";
+		reg = <0x0 0xff1c0000 0x0 0x100>;
+		clock-frequency = <24000000>;
+		clocks = <&cru SCLK_UART4>, <&cru PCLK_UART4>;
+		clock-names = "baudclk", "apb_pclk";
+		interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	gmac: ethernet@ff290000 {
+		compatible = "rockchip,rk3368-gmac";
+		reg = <0x0 0xff290000 0x0 0x10000>;
+		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq";
+		rockchip,grf = <&grf>;
+		clocks = <&cru SCLK_MAC>,
+			<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
+			<&cru SCLK_MACREF>, <&cru SCLK_MACREF_OUT>,
+			<&cru ACLK_GMAC>, <&cru PCLK_GMAC>;
+		clock-names = "stmmaceth",
+			"mac_clk_rx", "mac_clk_tx",
+			"clk_mac_ref", "clk_mac_refout",
+			"aclk_mac", "pclk_mac";
+		status = "disabled";
+	};
+
+	usb_host0_ehci: usb@ff500000 {
+		compatible = "generic-ehci";
+		reg = <0x0 0xff500000 0x0 0x100>;
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru HCLK_HOST0>;
+		clock-names = "usbhost";
+		status = "disabled";
+	};
+
+	usb_otg: usb@ff580000 {
+		compatible = "rockchip,rk3368-usb", "rockchip,rk3066-usb",
+				"snps,dwc2";
+		reg = <0x0 0xff580000 0x0 0x40000>;
+		interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru HCLK_OTG0>;
+		clock-names = "otg";
+		dr_mode = "otg";
+		g-np-tx-fifo-size = <16>;
+		g-rx-fifo-size = <275>;
+		g-tx-fifo-size = <256 128 128 64 64 32>;
+		g-use-dma;
+		status = "disabled";
+	};
+
+	i2c0: i2c@ff650000 {
+		compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c";
+		reg = <0x0 0xff650000 0x0 0x1000>;
+		clocks = <&cru PCLK_I2C0>;
+		clock-names = "i2c";
+		interrupts = <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c0_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c2: i2c@ff660000 {
+		compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c";
+		reg = <0x0 0xff660000 0x0 0x1000>;
+		interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2c";
+		clocks = <&cru PCLK_I2C2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c2_xfer>;
+		status = "disabled";
+	};
+
+	uart2: serial@ff690000 {
+		compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart";
+		reg = <0x0 0xff690000 0x0 0x100>;
+		clocks = <&cru SCLK_UART2>, <&cru PCLK_UART2>;
+		clock-names = "baudclk", "apb_pclk";
+		interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&uart2_xfer>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	pmugrf: syscon@ff738000 {
+		compatible = "rockchip,rk3368-pmugrf", "syscon";
+		reg = <0x0 0xff738000 0x0 0x1000>;
+	};
+
+	cru: clock-controller@ff760000 {
+		compatible = "rockchip,rk3368-cru";
+		reg = <0x0 0xff760000 0x0 0x1000>;
+		rockchip,grf = <&grf>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+	grf: syscon@ff770000 {
+		compatible = "rockchip,rk3368-grf", "syscon";
+		reg = <0x0 0xff770000 0x0 0x1000>;
+	};
+
+	wdt: watchdog@ff800000 {
+		compatible = "rockchip,rk3368-wdt", "snps,dw-wdt";
+		reg = <0x0 0xff800000 0x0 0x100>;
+		clocks = <&cru PCLK_WDT>;
+		interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
+		status = "disabled";
+	};
+
+	gic: interrupt-controller@ffb71000 {
+		compatible = "arm,gic-400";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+
+		reg = <0x0 0xffb71000 0x0 0x1000>,
+		      <0x0 0xffb72000 0x0 0x1000>,
+		      <0x0 0xffb74000 0x0 0x2000>,
+		      <0x0 0xffb76000 0x0 0x2000>;
+		interrupts = <GIC_PPI 9
+		      (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	pinctrl: pinctrl {
+		compatible = "rockchip,rk3368-pinctrl";
+		rockchip,grf = <&grf>;
+		rockchip,pmu = <&pmugrf>;
+		#address-cells = <0x2>;
+		#size-cells = <0x2>;
+		ranges;
+
+		gpio0: gpio0@ff750000 {
+			compatible = "rockchip,gpio-bank";
+			reg = <0x0 0xff750000 0x0 0x100>;
+			clocks = <&cru PCLK_GPIO0>;
+			interrupts = <GIC_SPI 0x51 IRQ_TYPE_LEVEL_HIGH>;
+
+			gpio-controller;
+			#gpio-cells = <0x2>;
+
+			interrupt-controller;
+			#interrupt-cells = <0x2>;
+		};
+
+		gpio1: gpio1@ff780000 {
+			compatible = "rockchip,gpio-bank";
+			reg = <0x0 0xff780000 0x0 0x100>;
+			clocks = <&cru PCLK_GPIO1>;
+			interrupts = <GIC_SPI 0x52 IRQ_TYPE_LEVEL_HIGH>;
+
+			gpio-controller;
+			#gpio-cells = <0x2>;
+
+			interrupt-controller;
+			#interrupt-cells = <0x2>;
+		};
+
+		gpio2: gpio2@ff790000 {
+			compatible = "rockchip,gpio-bank";
+			reg = <0x0 0xff790000 0x0 0x100>;
+			clocks = <&cru PCLK_GPIO2>;
+			interrupts = <GIC_SPI 0x53 IRQ_TYPE_LEVEL_HIGH>;
+
+			gpio-controller;
+			#gpio-cells = <0x2>;
+
+			interrupt-controller;
+			#interrupt-cells = <0x2>;
+		};
+
+		gpio3: gpio3@ff7a0000 {
+			compatible = "rockchip,gpio-bank";
+			reg = <0x0 0xff7a0000 0x0 0x100>;
+			clocks = <&cru PCLK_GPIO3>;
+			interrupts = <GIC_SPI 0x54 IRQ_TYPE_LEVEL_HIGH>;
+
+			gpio-controller;
+			#gpio-cells = <0x2>;
+
+			interrupt-controller;
+			#interrupt-cells = <0x2>;
+		};
+
+		pcfg_pull_up: pcfg-pull-up {
+			bias-pull-up;
+		};
+
+		pcfg_pull_down: pcfg-pull-down {
+			bias-pull-down;
+		};
+
+		pcfg_pull_none: pcfg-pull-none {
+			bias-disable;
+		};
+
+		pcfg_pull_none_12ma: pcfg-pull-none-12ma {
+			bias-disable;
+			drive-strength = <12>;
+		};
+
+		emmc {
+			emmc_clk: emmc-clk {
+				rockchip,pins = <2 4 RK_FUNC_2 &pcfg_pull_none>;
+			};
+
+			emmc_cmd: emmc-cmd {
+				rockchip,pins = <1 26 RK_FUNC_2 &pcfg_pull_up>;
+			};
+
+			emmc_pwr: emmc-pwr {
+				rockchip,pins = <1 27 RK_FUNC_2 &pcfg_pull_up>;
+			};
+
+			emmc_bus1: emmc-bus1 {
+				rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>;
+			};
+
+			emmc_bus4: emmc-bus4 {
+				rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>,
+						<1 19 RK_FUNC_2 &pcfg_pull_up>,
+						<1 20 RK_FUNC_2 &pcfg_pull_up>,
+						<1 21 RK_FUNC_2 &pcfg_pull_up>;
+			};
+
+			emmc_bus8: emmc-bus8 {
+				rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>,
+						<1 19 RK_FUNC_2 &pcfg_pull_up>,
+						<1 20 RK_FUNC_2 &pcfg_pull_up>,
+						<1 21 RK_FUNC_2 &pcfg_pull_up>,
+						<1 22 RK_FUNC_2 &pcfg_pull_up>,
+						<1 23 RK_FUNC_2 &pcfg_pull_up>,
+						<1 24 RK_FUNC_2 &pcfg_pull_up>,
+						<1 25 RK_FUNC_2 &pcfg_pull_up>;
+			};
+		};
+
+		gmac {
+			rgmii_pins: rgmii-pins {
+				rockchip,pins =	<3 22 RK_FUNC_1 &pcfg_pull_none>,
+						<3 24 RK_FUNC_1 &pcfg_pull_none>,
+						<3 19 RK_FUNC_1 &pcfg_pull_none>,
+						<3 8 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 9 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 10 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 14 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 28 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 13 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 15 RK_FUNC_1 &pcfg_pull_none>,
+						<3 16 RK_FUNC_1 &pcfg_pull_none>,
+						<3 17 RK_FUNC_1 &pcfg_pull_none>,
+						<3 18 RK_FUNC_1 &pcfg_pull_none>,
+						<3 25 RK_FUNC_1 &pcfg_pull_none>,
+						<3 20 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			rmii_pins: rmii-pins {
+				rockchip,pins =	<3 22 RK_FUNC_1 &pcfg_pull_none>,
+						<3 24 RK_FUNC_1 &pcfg_pull_none>,
+						<3 19 RK_FUNC_1 &pcfg_pull_none>,
+						<3 8 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 9 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 13 RK_FUNC_1 &pcfg_pull_none_12ma>,
+						<3 15 RK_FUNC_1 &pcfg_pull_none>,
+						<3 16 RK_FUNC_1 &pcfg_pull_none>,
+						<3 20 RK_FUNC_1 &pcfg_pull_none>,
+						<3 21 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
+		i2c0 {
+			i2c0_xfer: i2c0-xfer {
+				rockchip,pins = <0 6 RK_FUNC_1 &pcfg_pull_none>,
+						<0 7 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
+		i2c1 {
+			i2c1_xfer: i2c1-xfer {
+				rockchip,pins = <2 21 RK_FUNC_1 &pcfg_pull_none>,
+						<2 22 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
+		i2c2 {
+			i2c2_xfer: i2c2-xfer {
+				rockchip,pins = <0 9 RK_FUNC_2 &pcfg_pull_none>,
+						<3 31 RK_FUNC_2 &pcfg_pull_none>;
+			};
+		};
+
+		i2c3 {
+			i2c3_xfer: i2c3-xfer {
+				rockchip,pins = <1 16 RK_FUNC_1 &pcfg_pull_none>,
+						<1 17 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
+		i2c4 {
+			i2c4_xfer: i2c4-xfer {
+				rockchip,pins = <3 24 RK_FUNC_2 &pcfg_pull_none>,
+						<3 25 RK_FUNC_2 &pcfg_pull_none>;
+			};
+		};
+
+		i2c5 {
+			i2c5_xfer: i2c5-xfer {
+				rockchip,pins = <3 26 RK_FUNC_2 &pcfg_pull_none>,
+						<3 27 RK_FUNC_2 &pcfg_pull_none>;
+			};
+		};
+
+		sdio0 {
+			sdio0_bus1: sdio0-bus1 {
+				rockchip,pins = <2 28 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_bus4: sdio0-bus4 {
+				rockchip,pins = <2 28 RK_FUNC_1 &pcfg_pull_up>,
+						<2 29 RK_FUNC_1 &pcfg_pull_up>,
+						<2 30 RK_FUNC_1 &pcfg_pull_up>,
+						<2 31 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_cmd: sdio0-cmd {
+				rockchip,pins = <3 0 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_clk: sdio0-clk {
+				rockchip,pins = <3 1 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			sdio0_cd: sdio0-cd {
+				rockchip,pins = <3 2 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_wp: sdio0-wp {
+				rockchip,pins = <3 3 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_pwr: sdio0-pwr {
+				rockchip,pins = <3 4 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_bkpwr: sdio0-bkpwr {
+				rockchip,pins = <3 5 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdio0_int: sdio0-int {
+				rockchip,pins = <3 6 RK_FUNC_1 &pcfg_pull_up>;
+			};
+		};
+
+		sdmmc {
+			sdmmc_clk: sdmmc-clk {
+				rockchip,pins = <2 9 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			sdmmc_cmd: sdmmc-cmd {
+				rockchip,pins = <2 10 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdmmc_cd: sdmcc-cd {
+				rockchip,pins = <2 11 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdmmc_bus1: sdmmc-bus1 {
+				rockchip,pins = <2 5 RK_FUNC_1 &pcfg_pull_up>;
+			};
+
+			sdmmc_bus4: sdmmc-bus4 {
+				rockchip,pins = <2 5 RK_FUNC_1 &pcfg_pull_up>,
+						<2 6 RK_FUNC_1 &pcfg_pull_up>,
+						<2 7 RK_FUNC_1 &pcfg_pull_up>,
+						<2 8 RK_FUNC_1 &pcfg_pull_up>;
+			};
+		};
+
+		spi0 {
+			spi0_clk: spi0-clk {
+				rockchip,pins = <1 29 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi0_cs0: spi0-cs0 {
+				rockchip,pins = <1 24 RK_FUNC_3 &pcfg_pull_up>;
+			};
+			spi0_cs1: spi0-cs1 {
+				rockchip,pins = <1 25 RK_FUNC_3 &pcfg_pull_up>;
+			};
+			spi0_tx: spi0-tx {
+				rockchip,pins = <1 23 RK_FUNC_3 &pcfg_pull_up>;
+			};
+			spi0_rx: spi0-rx {
+				rockchip,pins = <1 22 RK_FUNC_3 &pcfg_pull_up>;
+			};
+		};
+
+		spi1 {
+			spi1_clk: spi1-clk {
+				rockchip,pins = <1 14 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi1_cs0: spi1-cs0 {
+				rockchip,pins = <1 15 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi1_cs1: spi1-cs1 {
+				rockchip,pins = <3 28 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi1_rx: spi1-rx {
+				rockchip,pins = <1 16 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi1_tx: spi1-tx {
+				rockchip,pins = <1 17 RK_FUNC_2 &pcfg_pull_up>;
+			};
+		};
+
+		spi2 {
+			spi2_clk: spi2-clk {
+				rockchip,pins = <0 12 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi2_cs0: spi2-cs0 {
+				rockchip,pins = <0 13 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi2_rx: spi2-rx {
+				rockchip,pins = <0 10 RK_FUNC_2 &pcfg_pull_up>;
+			};
+			spi2_tx: spi2-tx {
+				rockchip,pins = <0 11 RK_FUNC_2 &pcfg_pull_up>;
+			};
+		};
+
+		uart0 {
+			uart0_xfer: uart0-xfer {
+				rockchip,pins = <2 24 RK_FUNC_1 &pcfg_pull_up>,
+						<2 25 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			uart0_cts: uart0-cts {
+				rockchip,pins = <2 26 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			uart0_rts: uart0-rts {
+				rockchip,pins = <2 27 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
+		uart1 {
+			uart1_xfer: uart1-xfer {
+				rockchip,pins = <0 20 RK_FUNC_3 &pcfg_pull_up>,
+						<0 21 RK_FUNC_3 &pcfg_pull_none>;
+			};
+
+			uart1_cts: uart1-cts {
+				rockchip,pins = <0 22 RK_FUNC_3 &pcfg_pull_none>;
+			};
+
+			uart1_rts: uart1-rts {
+				rockchip,pins = <0 23 RK_FUNC_3 &pcfg_pull_none>;
+			};
+		};
+
+		uart2 {
+			uart2_xfer: uart2-xfer {
+				rockchip,pins = <2 6 RK_FUNC_2 &pcfg_pull_up>,
+						<2 5 RK_FUNC_2 &pcfg_pull_none>;
+			};
+			/* no rts / cts for uart2 */
+		};
+
+		uart3 {
+			uart3_xfer: uart3-xfer {
+				rockchip,pins = <3 29 RK_FUNC_2 &pcfg_pull_up>,
+						<3 30 RK_FUNC_3 &pcfg_pull_none>;
+			};
+
+			uart3_cts: uart3-cts {
+				rockchip,pins = <3 16 RK_FUNC_2 &pcfg_pull_none>;
+			};
+
+			uart3_rts: uart3-rts {
+				rockchip,pins = <3 17 RK_FUNC_2 &pcfg_pull_none>;
+			};
+		};
+
+		uart4 {
+			uart4_xfer: uart4-xfer {
+				rockchip,pins = <0 27 RK_FUNC_3 &pcfg_pull_up>,
+						<0 26 RK_FUNC_3 &pcfg_pull_none>;
+			};
+
+			uart4_cts: uart4-cts {
+				rockchip,pins = <0 24 RK_FUNC_3 &pcfg_pull_none>;
+			};
+
+			uart4_rts: uart4-rts {
+				rockchip,pins = <0 25 RK_FUNC_3 &pcfg_pull_none>;
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/sprd/sc9836.dtsi b/arch/arm64/boot/dts/sprd/sc9836.dtsi
index ee34e1a36e03..63894c456969 100644
--- a/arch/arm64/boot/dts/sprd/sc9836.dtsi
+++ b/arch/arm64/boot/dts/sprd/sc9836.dtsi
@@ -16,28 +16,28 @@
 		#address-cells = <2>;
 		#size-cells = <0>;
 
-		cpu@0 {
+		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x0>;
 			enable-method = "psci";
 		};
 
-		cpu@1 {
+		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x1>;
 			enable-method = "psci";
 		};
 
-		cpu@2 {
+		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x2>;
 			enable-method = "psci";
 		};
 
-		cpu@3 {
+		cpu3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0 0x3>;
@@ -75,14 +75,103 @@
 				};
 			};
 
-			/* funnel input port 0~3 is reserved for ETMs */
+			/* funnel input port 0-4 */
 			port@1 {
+				reg = <0>;
+				funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm1_out>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm2_out>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm3_out>;
+				};
+			};
+
+			port@5 {
 				reg = <4>;
 				funnel_in_port4: endpoint {
 					slave-mode;
 					remote-endpoint = <&stm_out>;
 				};
 			};
+			/* Other input ports aren't connected to anyone */
+		};
+	};
+
+	etm@10440000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x10440000 0 0x1000>;
+
+		cpu = <&cpu0>;
+		clocks = <&clk26mhz>;
+		clock-names = "apb_pclk";
+		port {
+			etm0_out: endpoint {
+				remote-endpoint = <&funnel_in_port0>;
+			};
+		};
+	};
+
+	etm@10540000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x10540000 0 0x1000>;
+
+		cpu = <&cpu1>;
+		clocks = <&clk26mhz>;
+		clock-names = "apb_pclk";
+		port {
+			etm1_out: endpoint {
+				remote-endpoint = <&funnel_in_port1>;
+			};
+		};
+	};
+
+	etm@10640000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x10640000 0 0x1000>;
+
+		cpu = <&cpu2>;
+		clocks = <&clk26mhz>;
+		clock-names = "apb_pclk";
+		port {
+			etm2_out: endpoint {
+				remote-endpoint = <&funnel_in_port2>;
+			};
+		};
+	};
+
+	etm@10740000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x10740000 0 0x1000>;
+
+		cpu = <&cpu3>;
+		clocks = <&clk26mhz>;
+		clock-names = "apb_pclk";
+		port {
+			etm3_out: endpoint {
+				remote-endpoint = <&funnel_in_port3>;
+			};
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
index 0a3f40ecd06d..ce5d848251fa 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
@@ -32,6 +32,10 @@
 	};
 };
 
+&can0 {
+	status = "okay";
+};
+
 &gem0 {
 	status = "okay";
 	phy-handle = <&phy0>;
@@ -42,6 +46,91 @@
 	};
 };
 
+&gpio {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+	clock-frequency = <400000>;
+	eeprom@54 {
+		compatible = "at,24c64";
+		reg = <0x54>;
+	};
+};
+
+&i2c1 {
+	status = "okay";
+	clock-frequency = <400000>;
+	eeprom@55 {
+		compatible = "at,24c64";
+		reg = <0x55>;
+	};
+};
+
+&sata {
+	status = "okay";
+	ceva,broken-gen2;
+};
+
+&sdhci0 {
+	status = "okay";
+};
+
+&sdhci1 {
+	status = "okay";
+};
+
+&spi0 {
+	status = "okay";
+	num-cs = <1>;
+	spi0_flash0: spi0_flash0@0 {
+		compatible = "m25p80";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <50000000>;
+		reg = <0>;
+
+		spi0_flash0@00000000 {
+			label = "spi0_flash0";
+			reg = <0x0 0x100000>;
+		};
+	};
+};
+
+&spi1 {
+	status = "okay";
+	num-cs = <1>;
+	spi1_flash0: spi1_flash0@0 {
+		compatible = "m25p80";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <50000000>;
+		reg = <0>;
+
+		spi1_flash0@00000000 {
+			label = "spi1_flash0";
+			reg = <0x0 0x100000>;
+		};
+	};
+};
+
 &uart0 {
 	status = "okay";
 };
+
+&usb0 {
+	status = "okay";
+	dr_mode = "peripheral";
+	maximum-speed = "high-speed";
+};
+
+&usb1 {
+	status = "okay";
+	dr_mode = "host";
+	maximum-speed = "high-speed";
+};
+
+&watchdog0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 11e0b00045cf..857eda5c7217 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -96,74 +96,38 @@
 		#size-cells = <1>;
 		ranges;
 
-		misc_clk: misc_clk {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <25000000>;
-		};
-
-		ttc0: timer@ff110000 {
-			compatible = "cdns,ttc";
-			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 36 4>, <0 37 4>, <0 38 4>;
-			reg = <0x0 0xff110000 0x1000>;
-			clocks = <&misc_clk>;
-			timer-width = <32>;
-		};
-
-		ttc1: timer@ff120000 {
-			compatible = "cdns,ttc";
-			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 39 4>, <0 40 4>, <0 41 4>;
-			reg = <0x0 0xff120000 0x1000>;
-			clocks = <&misc_clk>;
-			timer-width = <32>;
-		};
-
-		ttc2: timer@ff130000 {
-			compatible = "cdns,ttc";
-			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 42 4>, <0 43 4>, <0 44 4>;
-			reg = <0x0 0xff130000 0x1000>;
-			clocks = <&misc_clk>;
-			timer-width = <32>;
-		};
-
-		ttc3: timer@ff140000 {
-			compatible = "cdns,ttc";
+		can0: can@ff060000 {
+			compatible = "xlnx,zynq-can-1.0";
 			status = "disabled";
+			clocks = <&misc_clk &misc_clk>;
+			clock-names = "can_clk", "pclk";
+			reg = <0x0 0xff060000 0x1000>;
+			interrupts = <0 23 4>;
 			interrupt-parent = <&gic>;
-			interrupts = <0 45 4>, <0 46 4>, <0 47 4>;
-			reg = <0x0 0xff140000 0x1000>;
-			clocks = <&misc_clk>;
-			timer-width = <32>;
+			tx-fifo-depth = <0x40>;
+			rx-fifo-depth = <0x40>;
 		};
 
-		uart0: serial@ff000000 {
-			compatible = "cdns,uart-r1p8";
+		can1: can@ff070000 {
+			compatible = "xlnx,zynq-can-1.0";
 			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 21 4>;
-			reg = <0x0 0xff000000 0x1000>;
-			clock-names = "uart_clk", "pclk";
 			clocks = <&misc_clk &misc_clk>;
+			clock-names = "can_clk", "pclk";
+			reg = <0x0 0xff070000 0x1000>;
+			interrupts = <0 24 4>;
+			interrupt-parent = <&gic>;
+			tx-fifo-depth = <0x40>;
+			rx-fifo-depth = <0x40>;
 		};
 
-		uart1: serial@ff010000 {
-			compatible = "cdns,uart-r1p8";
-			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 22 4>;
-			reg = <0x0 0xff010000 0x1000>;
-			clock-names = "uart_clk", "pclk";
-			clocks = <&misc_clk &misc_clk>;
+		misc_clk: misc_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <25000000>;
 		};
 
 		gpio: gpio@ff0a0000 {
-			compatible = "xlnx,zynq-gpio-1.0";
+			compatible = "xlnx,zynqmp-gpio-1.0";
 			status = "disabled";
 			#gpio-cells = <0x2>;
 			clocks = <&misc_clk>;
@@ -220,30 +184,6 @@
 			#size-cells = <0>;
 		};
 
-		spi0: spi@ff040000 {
-			compatible = "cdns,spi-r1p6";
-			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 19 4>;
-			reg = <0x0 0xff040000 0x1000>;
-			clock-names = "ref_clk", "pclk";
-			clocks = <&misc_clk &misc_clk>;
-			#address-cells = <1>;
-			#size-cells = <0>;
-		};
-
-		spi1: spi@ff050000 {
-			compatible = "cdns,spi-r1p6";
-			status = "disabled";
-			interrupt-parent = <&gic>;
-			interrupts = <0 20 4>;
-			reg = <0x0 0xff050000 0x1000>;
-			clock-names = "ref_clk", "pclk";
-			clocks = <&misc_clk &misc_clk>;
-			#address-cells = <1>;
-			#size-cells = <0>;
-		};
-
 		i2c_clk: i2c_clk {
 			compatible = "fixed-clock";
 			#clock-cells = <0x0>;
@@ -272,6 +212,21 @@
 			#size-cells = <0>;
 		};
 
+		sata_clk: sata_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <75000000>;
+		};
+
+		sata: ahci@fd0c0000 {
+			compatible = "ceva,ahci-1v84";
+			status = "disabled";
+			reg = <0x0 0xfd0c0000 0x2000>;
+			interrupt-parent = <&gic>;
+			interrupts = <0 133 4>;
+			clocks = <&sata_clk>;
+		};
+
 		sdhci0: sdhci@ff160000 {
 			compatible = "arasan,sdhci-8.9a";
 			status = "disabled";
@@ -292,6 +247,122 @@
 			clocks = <&misc_clk>, <&misc_clk>;
 		};
 
+		smmu: smmu@fd800000 {
+			compatible = "arm,mmu-500";
+			reg = <0x0 0xfd800000 0x20000>;
+			#global-interrupts = <1>;
+			interrupt-parent = <&gic>;
+			interrupts = <0 157 4>,
+				<0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>,
+				<0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>,
+				<0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>,
+				<0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>;
+		};
+
+		spi0: spi@ff040000 {
+			compatible = "cdns,spi-r1p6";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 19 4>;
+			reg = <0x0 0xff040000 0x1000>;
+			clock-names = "ref_clk", "pclk";
+			clocks = <&misc_clk &misc_clk>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		spi1: spi@ff050000 {
+			compatible = "cdns,spi-r1p6";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 20 4>;
+			reg = <0x0 0xff050000 0x1000>;
+			clock-names = "ref_clk", "pclk";
+			clocks = <&misc_clk &misc_clk>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		ttc0: timer@ff110000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 36 4>, <0 37 4>, <0 38 4>;
+			reg = <0x0 0xff110000 0x1000>;
+			clocks = <&misc_clk>;
+			timer-width = <32>;
+		};
+
+		ttc1: timer@ff120000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 39 4>, <0 40 4>, <0 41 4>;
+			reg = <0x0 0xff120000 0x1000>;
+			clocks = <&misc_clk>;
+			timer-width = <32>;
+		};
+
+		ttc2: timer@ff130000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 42 4>, <0 43 4>, <0 44 4>;
+			reg = <0x0 0xff130000 0x1000>;
+			clocks = <&misc_clk>;
+			timer-width = <32>;
+		};
+
+		ttc3: timer@ff140000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 45 4>, <0 46 4>, <0 47 4>;
+			reg = <0x0 0xff140000 0x1000>;
+			clocks = <&misc_clk>;
+			timer-width = <32>;
+		};
+
+		uart0: serial@ff000000 {
+			compatible = "cdns,uart-r1p8";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 21 4>;
+			reg = <0x0 0xff000000 0x1000>;
+			clock-names = "uart_clk", "pclk";
+			clocks = <&misc_clk &misc_clk>;
+		};
+
+		uart1: serial@ff010000 {
+			compatible = "cdns,uart-r1p8";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 22 4>;
+			reg = <0x0 0xff010000 0x1000>;
+			clock-names = "uart_clk", "pclk";
+			clocks = <&misc_clk &misc_clk>;
+		};
+
+		usb0: usb@fe200000 {
+			compatible = "snps,dwc3";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 65 4>;
+			reg = <0x0 0xfe200000 0x40000>;
+			clock-names = "clk_xin", "clk_ahb";
+			clocks = <&misc_clk>, <&misc_clk>;
+		};
+
+		usb1: usb@fe300000 {
+			compatible = "snps,dwc3";
+			status = "disabled";
+			interrupt-parent = <&gic>;
+			interrupts = <0 70 4>;
+			reg = <0x0 0xfe300000 0x40000>;
+			clock-names = "clk_xin", "clk_ahb";
+			clocks = <&misc_clk>, <&misc_clk>;
+		};
+
 		watchdog0: watchdog@fd4d0000 {
 			compatible = "cdns,wdt-r1p2";
 			status = "disabled";
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f38c94f1d898..34d71dd86781 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -31,10 +31,13 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_ARCH_BCM_IPROC=y
+CONFIG_ARCH_BERLIN=y
 CONFIG_ARCH_EXYNOS7=y
 CONFIG_ARCH_FSL_LS2085A=y
 CONFIG_ARCH_HISI=y
 CONFIG_ARCH_MEDIATEK=y
+CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SEATTLE=y
 CONFIG_ARCH_TEGRA=y
 CONFIG_ARCH_TEGRA_132_SOC=y
@@ -83,6 +86,7 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_CEVA=y
 CONFIG_AHCI_XGENE=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
@@ -101,6 +105,7 @@ CONFIG_SERIO_AMBAKMI=y
 CONFIG_LEGACY_PTY_COUNT=16
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_8250_MT6577=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 3303e8a7b837..f4bf2f2a014c 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -124,7 +124,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 
 	ce_aes_ccm_auth_data(mac, (u8 *)&ltag, ltag.len, &macp, ctx->key_enc,
 			     num_rounds(ctx));
-	scatterwalk_start(&walk, req->assoc);
+	scatterwalk_start(&walk, req->src);
 
 	do {
 		u32 n = scatterwalk_clamp(&walk, len);
@@ -151,6 +151,10 @@ static int ccm_encrypt(struct aead_request *req)
 	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
 	struct blkcipher_desc desc = { .info = req->iv };
 	struct blkcipher_walk walk;
+	struct scatterlist srcbuf[2];
+	struct scatterlist dstbuf[2];
+	struct scatterlist *src;
+	struct scatterlist *dst;
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
 	u8 buf[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen;
@@ -168,7 +172,12 @@ static int ccm_encrypt(struct aead_request *req)
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
-	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	src = scatterwalk_ffwd(srcbuf, req->src, req->assoclen);
+	dst = src;
+	if (req->src != req->dst)
+		dst = scatterwalk_ffwd(dstbuf, req->dst, req->assoclen);
+
+	blkcipher_walk_init(&walk, dst, src, len);
 	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
 					     AES_BLOCK_SIZE);
 
@@ -194,7 +203,7 @@ static int ccm_encrypt(struct aead_request *req)
 		return err;
 
 	/* copy authtag to end of dst */
-	scatterwalk_map_and_copy(mac, req->dst, req->cryptlen,
+	scatterwalk_map_and_copy(mac, dst, req->cryptlen,
 				 crypto_aead_authsize(aead), 1);
 
 	return 0;
@@ -207,6 +216,10 @@ static int ccm_decrypt(struct aead_request *req)
 	unsigned int authsize = crypto_aead_authsize(aead);
 	struct blkcipher_desc desc = { .info = req->iv };
 	struct blkcipher_walk walk;
+	struct scatterlist srcbuf[2];
+	struct scatterlist dstbuf[2];
+	struct scatterlist *src;
+	struct scatterlist *dst;
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
 	u8 buf[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen - authsize;
@@ -224,7 +237,12 @@ static int ccm_decrypt(struct aead_request *req)
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
-	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	src = scatterwalk_ffwd(srcbuf, req->src, req->assoclen);
+	dst = src;
+	if (req->src != req->dst)
+		dst = scatterwalk_ffwd(dstbuf, req->dst, req->assoclen);
+
+	blkcipher_walk_init(&walk, dst, src, len);
 	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
 					     AES_BLOCK_SIZE);
 
@@ -250,44 +268,42 @@ static int ccm_decrypt(struct aead_request *req)
 		return err;
 
 	/* compare calculated auth tag with the stored one */
-	scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize,
+	scatterwalk_map_and_copy(buf, src, req->cryptlen - authsize,
 				 authsize, 0);
 
-	if (memcmp(mac, buf, authsize))
+	if (crypto_memneq(mac, buf, authsize))
 		return -EBADMSG;
 	return 0;
 }
 
-static struct crypto_alg ccm_aes_alg = {
-	.cra_name		= "ccm(aes)",
-	.cra_driver_name	= "ccm-aes-ce",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_AEAD,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-	.cra_alignmask		= 7,
-	.cra_type		= &crypto_aead_type,
-	.cra_module		= THIS_MODULE,
-	.cra_aead = {
-		.ivsize		= AES_BLOCK_SIZE,
-		.maxauthsize	= AES_BLOCK_SIZE,
-		.setkey		= ccm_setkey,
-		.setauthsize	= ccm_setauthsize,
-		.encrypt	= ccm_encrypt,
-		.decrypt	= ccm_decrypt,
-	}
+static struct aead_alg ccm_aes_alg = {
+	.base = {
+		.cra_name		= "ccm(aes)",
+		.cra_driver_name	= "ccm-aes-ce",
+		.cra_priority		= 300,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_alignmask		= 7,
+		.cra_module		= THIS_MODULE,
+	},
+	.ivsize		= AES_BLOCK_SIZE,
+	.maxauthsize	= AES_BLOCK_SIZE,
+	.setkey		= ccm_setkey,
+	.setauthsize	= ccm_setauthsize,
+	.encrypt	= ccm_encrypt,
+	.decrypt	= ccm_decrypt,
 };
 
 static int __init aes_mod_init(void)
 {
 	if (!(elf_hwcap & HWCAP_AES))
 		return -ENODEV;
-	return crypto_register_alg(&ccm_aes_alg);
+	return crypto_register_aead(&ccm_aes_alg);
 }
 
 static void __exit aes_mod_exit(void)
 {
-	crypto_unregister_alg(&ccm_aes_alg);
+	crypto_unregister_aead(&ccm_aes_alg);
 }
 
 module_init(aes_mod_init);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index b112a39834d0..70fd9ffb58cf 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -25,6 +25,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += msi.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 39248d3adf5d..208cec08a74f 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,13 +12,21 @@
 #ifndef _ASM_ACPI_H
 #define _ASM_ACPI_H
 
-#include <linux/mm.h>
 #include <linux/irqchip/arm-gic-acpi.h>
+#include <linux/mm.h>
+#include <linux/psci.h>
 
 #include <asm/cputype.h>
-#include <asm/psci.h>
 #include <asm/smp_plat.h>
 
+/* Macros for consistency checks of the GICC subtable of MADT */
+#define ACPI_MADT_GICC_LENGTH	\
+	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
+
+#define BAD_MADT_GICC_ENTRY(entry, end)						\
+	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
+	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
 /* ACPI table mapping after acpi_gbl_permanent_mmap is set */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index c385a0c4057f..d56ec0715157 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -3,6 +3,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/init.h>
+#include <linux/kconfig.h>
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
@@ -15,7 +17,7 @@ struct alt_instr {
 	u8  alt_len;		/* size of new instruction(s), <= orig_len */
 };
 
-void apply_alternatives_all(void);
+void __init apply_alternatives_all(void);
 void apply_alternatives(void *start, size_t length);
 void free_alternatives_memory(void);
 
@@ -40,7 +42,8 @@ void free_alternatives_memory(void);
  * be fixed in a binutils release posterior to 2.25.51.0.2 (anything
  * containing commit 4e4d08cf7399b606 or c1baaddf8861).
  */
-#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled)	\
+	".if "__stringify(cfg_enabled)" == 1\n"				\
 	"661:\n\t"							\
 	oldinstr "\n"							\
 	"662:\n"							\
@@ -53,7 +56,11 @@ void free_alternatives_memory(void);
 	"664:\n\t"							\
 	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"
+	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".endif\n"
+
+#define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...)	\
+	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg))
 
 #else
 
@@ -65,7 +72,8 @@ void free_alternatives_memory(void);
 	.byte \alt_len
 .endm
 
-.macro alternative_insn insn1 insn2 cap
+.macro alternative_insn insn1, insn2, cap, enable = 1
+	.if \enable
 661:	\insn1
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
@@ -75,8 +83,70 @@ void free_alternatives_memory(void);
 664:	.popsection
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
+	.endif
+.endm
+
+/*
+ * Begin an alternative code sequence.
+ *
+ * The code that follows this macro will be assembled and linked as
+ * normal. There are no restrictions on this code.
+ */
+.macro alternative_if_not cap, enable = 1
+	.if \enable
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
+	.popsection
+661:
+	.endif
+.endm
+
+/*
+ * Provide the alternative code sequence.
+ *
+ * The code that follows this macro is assembled into a special
+ * section to be used for dynamic patching. Code that follows this
+ * macro must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ *    sequence.
+ *
+ * 2. Not contain a branch target that is used outside of the
+ *    alternative sequence it is defined in (branches into an
+ *    alternative sequence are not fixed up).
+ */
+.macro alternative_else, enable = 1
+	.if \enable
+662:	.pushsection .altinstr_replacement, "ax"
+663:
+	.endif
 .endm
 
+/*
+ * Complete an alternative code sequence.
+ */
+.macro alternative_endif, enable = 1
+	.if \enable
+664:	.popsection
+	.org	. - (664b-663b) + (662b-661b)
+	.org	. - (662b-661b) + (664b-663b)
+	.endif
+.endm
+
+#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
+	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
+
+
 #endif  /*  __ASSEMBLY__  */
 
+/*
+ * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature));
+ *
+ * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature, CONFIG_FOO));
+ * N.B. If CONFIG_FOO is specified, but not selected, the whole block
+ *      will be omitted, including oldinstr.
+ */
+#define ALTERNATIVE(oldinstr, newinstr, ...)   \
+	_ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1)
+
 #endif /* __ASM_ALTERNATIVE_H */
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 144b64ad96c3..b51f2cc22ca9 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -50,18 +50,6 @@
 	.endm
 
 /*
- * Save/disable and restore interrupts.
- */
-	.macro	save_and_disable_irqs, olddaif
-	mrs	\olddaif, daif
-	disable_irq
-	.endm
-
-	.macro	restore_irqs, olddaif
-	msr	daif, \olddaif
-	.endm
-
-/*
  * Enable and disable debug exceptions.
  */
 	.macro	disable_dbg
@@ -103,9 +91,7 @@
  * SMP data memory barrier
  */
 	.macro	smp_dmb, opt
-#ifdef CONFIG_SMP
 	dmb	\opt
-#endif
 	.endm
 
 #define USER(l, x...)				\
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 7047051ded40..35a67783cfa0 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -24,233 +24,72 @@
 #include <linux/types.h>
 
 #include <asm/barrier.h>
-#include <asm/cmpxchg.h>
-
-#define ATOMIC_INIT(i)	{ (i) }
+#include <asm/lse.h>
 
 #ifdef __KERNEL__
 
-/*
- * On ARM, ordinary assignment (str instruction) doesn't clear the local
- * strex/ldrex monitor on some implementations. The reason we can use it for
- * atomic_set() is the clrex or dummy strex done on every exception return.
- */
-#define atomic_read(v)	ACCESS_ONCE((v)->counter)
-#define atomic_set(v,i)	(((v)->counter) = (i))
-
-/*
- * AArch64 UP and SMP safe atomic ops.  We use load exclusive and
- * store exclusive to ensure that these are atomic.  We may loop
- * to ensure that the update happens.
- */
-
-#define ATOMIC_OP(op, asm_op)						\
-static inline void atomic_##op(int i, atomic_t *v)			\
-{									\
-	unsigned long tmp;						\
-	int result;							\
-									\
-	asm volatile("// atomic_" #op "\n"				\
-"1:	ldxr	%w0, %2\n"						\
-"	" #asm_op "	%w0, %w0, %w3\n"				\
-"	stxr	%w1, %w0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
-}									\
+#define __ARM64_IN_ATOMIC_IMPL
 
-#define ATOMIC_OP_RETURN(op, asm_op)					\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
-{									\
-	unsigned long tmp;						\
-	int result;							\
-									\
-	asm volatile("// atomic_" #op "_return\n"			\
-"1:	ldxr	%w0, %2\n"						\
-"	" #asm_op "	%w0, %w0, %w3\n"				\
-"	stlxr	%w1, %w0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
-	: "memory");							\
-									\
-	smp_mb();							\
-	return result;							\
-}
-
-#define ATOMIC_OPS(op, asm_op)						\
-	ATOMIC_OP(op, asm_op)						\
-	ATOMIC_OP_RETURN(op, asm_op)
-
-ATOMIC_OPS(add, add)
-ATOMIC_OPS(sub, sub)
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
-
-static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
-{
-	unsigned long tmp;
-	int oldval;
-
-	smp_mb();
-
-	asm volatile("// atomic_cmpxchg\n"
-"1:	ldxr	%w1, %2\n"
-"	cmp	%w1, %w3\n"
-"	b.ne	2f\n"
-"	stxr	%w0, %w4, %2\n"
-"	cbnz	%w0, 1b\n"
-"2:"
-	: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
-	: "Ir" (old), "r" (new)
-	: "cc");
-
-	smp_mb();
-	return oldval;
-}
-
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+#if defined(CONFIG_ARM64_LSE_ATOMICS) && defined(CONFIG_AS_LSE)
+#include <asm/atomic_lse.h>
+#else
+#include <asm/atomic_ll_sc.h>
+#endif
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
+#undef __ARM64_IN_ATOMIC_IMPL
 
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
-		c = old;
-	return c;
-}
+#include <asm/cmpxchg.h>
 
-#define atomic_inc(v)		atomic_add(1, v)
-#define atomic_dec(v)		atomic_sub(1, v)
+#define ___atomic_add_unless(v, a, u, sfx)				\
+({									\
+	typeof((v)->counter) c, old;					\
+									\
+	c = atomic##sfx##_read(v);					\
+	while (c != (u) &&						\
+	      (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c)	\
+		c = old;						\
+	c;								\
+ })
 
-#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)    (atomic_add_return(1, v))
-#define atomic_dec_return(v)    (atomic_sub_return(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
+#define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
+#define atomic_read(v)			READ_ONCE((v)->counter)
+#define atomic_set(v, i)		(((v)->counter) = (i))
+#define atomic_xchg(v, new)		xchg(&((v)->counter), (new))
+#define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
+
+#define atomic_inc(v)			atomic_add(1, (v))
+#define atomic_dec(v)			atomic_sub(1, (v))
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
+#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
+#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
+#define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
+#define __atomic_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
+#define atomic_andnot			atomic_andnot
 
 /*
  * 64-bit atomic operations.
  */
-#define ATOMIC64_INIT(i) { (i) }
-
-#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
-#define atomic64_set(v,i)	(((v)->counter) = (i))
-
-#define ATOMIC64_OP(op, asm_op)						\
-static inline void atomic64_##op(long i, atomic64_t *v)			\
-{									\
-	long result;							\
-	unsigned long tmp;						\
-									\
-	asm volatile("// atomic64_" #op "\n"				\
-"1:	ldxr	%0, %2\n"						\
-"	" #asm_op "	%0, %0, %3\n"					\
-"	stxr	%w1, %0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
-}									\
-
-#define ATOMIC64_OP_RETURN(op, asm_op)					\
-static inline long atomic64_##op##_return(long i, atomic64_t *v)	\
-{									\
-	long result;							\
-	unsigned long tmp;						\
-									\
-	asm volatile("// atomic64_" #op "_return\n"			\
-"1:	ldxr	%0, %2\n"						\
-"	" #asm_op "	%0, %0, %3\n"					\
-"	stlxr	%w1, %0, %2\n"						\
-"	cbnz	%w1, 1b"						\
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
-	: "memory");							\
-									\
-	smp_mb();							\
-	return result;							\
-}
-
-#define ATOMIC64_OPS(op, asm_op)					\
-	ATOMIC64_OP(op, asm_op)						\
-	ATOMIC64_OP_RETURN(op, asm_op)
-
-ATOMIC64_OPS(add, add)
-ATOMIC64_OPS(sub, sub)
-
-#undef ATOMIC64_OPS
-#undef ATOMIC64_OP_RETURN
-#undef ATOMIC64_OP
-
-static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
-{
-	long oldval;
-	unsigned long res;
-
-	smp_mb();
-
-	asm volatile("// atomic64_cmpxchg\n"
-"1:	ldxr	%1, %2\n"
-"	cmp	%1, %3\n"
-"	b.ne	2f\n"
-"	stxr	%w0, %4, %2\n"
-"	cbnz	%w0, 1b\n"
-"2:"
-	: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
-	: "Ir" (old), "r" (new)
-	: "cc");
-
-	smp_mb();
-	return oldval;
-}
-
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_dec_if_positive\n"
-"1:	ldxr	%0, %2\n"
-"	subs	%0, %0, #1\n"
-"	b.mi	2f\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b\n"
-"	dmb	ish\n"
-"2:"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	:
-	: "cc", "memory");
-
-	return result;
-}
-
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-
-	c = atomic64_read(v);
-	while (c != u && (old = atomic64_cmpxchg((v), c, c + a)) != c)
-		c = old;
-
-	return c != u;
-}
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define ATOMIC64_INIT			ATOMIC_INIT
+#define atomic64_read			atomic_read
+#define atomic64_set			atomic_set
+#define atomic64_xchg			atomic_xchg
+#define atomic64_cmpxchg		atomic_cmpxchg
+
+#define atomic64_inc(v)			atomic64_add(1, (v))
+#define atomic64_dec(v)			atomic64_sub(1, (v))
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
+#define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
+#define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
+#define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
+#define atomic64_andnot			atomic64_andnot
+
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #endif
 #endif
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
new file mode 100644
index 000000000000..b3b5c4ae3800
--- /dev/null
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -0,0 +1,247 @@
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_ATOMIC_LL_SC_H
+#define __ASM_ATOMIC_LL_SC_H
+
+#ifndef __ARM64_IN_ATOMIC_IMPL
+#error "please don't include this file directly"
+#endif
+
+/*
+ * AArch64 UP and SMP safe atomic ops.  We use load exclusive and
+ * store exclusive to ensure that these are atomic.  We may loop
+ * to ensure that the update happens.
+ *
+ * NOTE: these functions do *not* follow the PCS and must explicitly
+ * save any clobbered registers other than x0 (regardless of return
+ * value).  This is achieved through -fcall-saved-* compiler flags for
+ * this file, which unfortunately don't work on a per-function basis
+ * (the optimize attribute silently ignores these options).
+ */
+
+#define ATOMIC_OP(op, asm_op)						\
+__LL_SC_INLINE void							\
+__LL_SC_PREFIX(atomic_##op(int i, atomic_t *v))				\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "\n"				\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+__LL_SC_EXPORT(atomic_##op);
+
+#define ATOMIC_OP_RETURN(op, asm_op)					\
+__LL_SC_INLINE int							\
+__LL_SC_PREFIX(atomic_##op##_return(int i, atomic_t *v))		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "_return\n"			\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stlxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic_##op##_return);
+
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_OP_RETURN(op, asm_op)
+
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
+
+ATOMIC_OP(and, and)
+ATOMIC_OP(andnot, bic)
+ATOMIC_OP(or, orr)
+ATOMIC_OP(xor, eor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#define ATOMIC64_OP(op, asm_op)						\
+__LL_SC_INLINE void							\
+__LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v))			\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "\n"				\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+__LL_SC_EXPORT(atomic64_##op);
+
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
+__LL_SC_INLINE long							\
+__LL_SC_PREFIX(atomic64_##op##_return(long i, atomic64_t *v))		\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "_return\n"			\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stlxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic64_##op##_return);
+
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN(op, asm_op)
+
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
+
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(andnot, bic)
+ATOMIC64_OP(or, orr)
+ATOMIC64_OP(xor, eor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+__LL_SC_INLINE long
+__LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v))
+{
+	long result;
+	unsigned long tmp;
+
+	asm volatile("// atomic64_dec_if_positive\n"
+"	prfm	pstl1strm, %2\n"
+"1:	ldxr	%0, %2\n"
+"	subs	%0, %0, #1\n"
+"	b.lt	2f\n"
+"	stlxr	%w1, %0, %2\n"
+"	cbnz	%w1, 1b\n"
+"	dmb	ish\n"
+"2:"
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+	:
+	: "cc", "memory");
+
+	return result;
+}
+__LL_SC_EXPORT(atomic64_dec_if_positive);
+
+#define __CMPXCHG_CASE(w, sz, name, mb, rel, cl)			\
+__LL_SC_INLINE unsigned long						\
+__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr,		\
+				     unsigned long old,			\
+				     unsigned long new))		\
+{									\
+	unsigned long tmp, oldval;					\
+									\
+	asm volatile(							\
+	"	prfm	pstl1strm, %[v]\n"				\
+	"1:	ldxr" #sz "\t%" #w "[oldval], %[v]\n"			\
+	"	eor	%" #w "[tmp], %" #w "[oldval], %" #w "[old]\n"	\
+	"	cbnz	%" #w "[tmp], 2f\n"				\
+	"	st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n"	\
+	"	cbnz	%w[tmp], 1b\n"					\
+	"	" #mb "\n"						\
+	"	mov	%" #w "[oldval], %" #w "[old]\n"		\
+	"2:"								\
+	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
+	  [v] "+Q" (*(unsigned long *)ptr)				\
+	: [old] "Lr" (old), [new] "r" (new)				\
+	: cl);								\
+									\
+	return oldval;							\
+}									\
+__LL_SC_EXPORT(__cmpxchg_case_##name);
+
+__CMPXCHG_CASE(w, b,    1,        ,  ,         )
+__CMPXCHG_CASE(w, h,    2,        ,  ,         )
+__CMPXCHG_CASE(w,  ,    4,        ,  ,         )
+__CMPXCHG_CASE( ,  ,    8,        ,  ,         )
+__CMPXCHG_CASE(w, b, mb_1, dmb ish, l, "memory")
+__CMPXCHG_CASE(w, h, mb_2, dmb ish, l, "memory")
+__CMPXCHG_CASE(w,  , mb_4, dmb ish, l, "memory")
+__CMPXCHG_CASE( ,  , mb_8, dmb ish, l, "memory")
+
+#undef __CMPXCHG_CASE
+
+#define __CMPXCHG_DBL(name, mb, rel, cl)				\
+__LL_SC_INLINE int							\
+__LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1,		\
+				      unsigned long old2,		\
+				      unsigned long new1,		\
+				      unsigned long new2,		\
+				      volatile void *ptr))		\
+{									\
+	unsigned long tmp, ret;						\
+									\
+	asm volatile("// __cmpxchg_double" #name "\n"			\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxp	%0, %1, %2\n"					\
+	"	eor	%0, %0, %3\n"					\
+	"	eor	%1, %1, %4\n"					\
+	"	orr	%1, %0, %1\n"					\
+	"	cbnz	%1, 2f\n"					\
+	"	st" #rel "xp	%w0, %5, %6, %2\n"			\
+	"	cbnz	%w0, 1b\n"					\
+	"	" #mb "\n"						\
+	"2:"								\
+	: "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr)	\
+	: "r" (old1), "r" (old2), "r" (new1), "r" (new2)		\
+	: cl);								\
+									\
+	return ret;							\
+}									\
+__LL_SC_EXPORT(__cmpxchg_double##name);
+
+__CMPXCHG_DBL(   ,        ,  ,         )
+__CMPXCHG_DBL(_mb, dmb ish, l, "memory")
+
+#undef __CMPXCHG_DBL
+
+#endif	/* __ASM_ATOMIC_LL_SC_H */
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
new file mode 100644
index 000000000000..55d740e63459
--- /dev/null
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -0,0 +1,391 @@
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_ATOMIC_LSE_H
+#define __ASM_ATOMIC_LSE_H
+
+#ifndef __ARM64_IN_ATOMIC_IMPL
+#error "please don't include this file directly"
+#endif
+
+#define __LL_SC_ATOMIC(op)	__LL_SC_CALL(atomic_##op)
+
+static inline void atomic_andnot(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(andnot),
+	"	stclr	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_or(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(or),
+	"	stset	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_xor(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(xor),
+	"	steor	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(add),
+	"	stadd	%w[i], %[v]\n")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(add_return),
+	/* LSE atomics */
+	"	ldaddal	%w[i], w30, %[v]\n"
+	"	add	%w[i], %w[i], w30")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return w0;
+}
+
+static inline void atomic_and(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(and),
+	/* LSE atomics */
+	"	mvn	%w[i], %w[i]\n"
+	"	stclr	%w[i], %[v]")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(sub),
+	/* LSE atomics */
+	"	neg	%w[i], %w[i]\n"
+	"	stadd	%w[i], %[v]")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	register int w0 asm ("w0") = i;
+	register atomic_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC(sub_return)
+	"	nop",
+	/* LSE atomics */
+	"	neg	%w[i], %w[i]\n"
+	"	ldaddal	%w[i], w30, %[v]\n"
+	"	add	%w[i], %w[i], w30")
+	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return w0;
+}
+
+#undef __LL_SC_ATOMIC
+
+#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
+
+static inline void atomic64_andnot(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(andnot),
+	"	stclr	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_or(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(or),
+	"	stset	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_xor(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(xor),
+	"	steor	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_add(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(add),
+	"	stadd	%[i], %[v]\n")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline long atomic64_add_return(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(add_return),
+	/* LSE atomics */
+	"	ldaddal	%[i], x30, %[v]\n"
+	"	add	%[i], %[i], x30")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return x0;
+}
+
+static inline void atomic64_and(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(and),
+	/* LSE atomics */
+	"	mvn	%[i], %[i]\n"
+	"	stclr	%[i], %[v]")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline void atomic64_sub(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(sub),
+	/* LSE atomics */
+	"	neg	%[i], %[i]\n"
+	"	stadd	%[i], %[v]")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30");
+}
+
+static inline long atomic64_sub_return(long i, atomic64_t *v)
+{
+	register long x0 asm ("x0") = i;
+	register atomic64_t *x1 asm ("x1") = v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(sub_return)
+	"	nop",
+	/* LSE atomics */
+	"	neg	%[i], %[i]\n"
+	"	ldaddal	%[i], x30, %[v]\n"
+	"	add	%[i], %[i], x30")
+	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: "r" (x1)
+	: "x30", "memory");
+
+	return x0;
+}
+
+static inline long atomic64_dec_if_positive(atomic64_t *v)
+{
+	register long x0 asm ("x0") = (long)v;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	nop\n"
+	__LL_SC_ATOMIC64(dec_if_positive)
+	"	nop\n"
+	"	nop\n"
+	"	nop\n"
+	"	nop\n"
+	"	nop",
+	/* LSE atomics */
+	"1:	ldr	x30, %[v]\n"
+	"	subs	%[ret], x30, #1\n"
+	"	b.lt	2f\n"
+	"	casal	x30, %[ret], %[v]\n"
+	"	sub	x30, x30, #1\n"
+	"	sub	x30, x30, %[ret]\n"
+	"	cbnz	x30, 1b\n"
+	"2:")
+	: [ret] "+&r" (x0), [v] "+Q" (v->counter)
+	:
+	: "x30", "cc", "memory");
+
+	return x0;
+}
+
+#undef __LL_SC_ATOMIC64
+
+#define __LL_SC_CMPXCHG(op)	__LL_SC_CALL(__cmpxchg_case_##op)
+
+#define __CMPXCHG_CASE(w, sz, name, mb, cl...)				\
+static inline unsigned long __cmpxchg_case_##name(volatile void *ptr,	\
+						  unsigned long old,	\
+						  unsigned long new)	\
+{									\
+	register unsigned long x0 asm ("x0") = (unsigned long)ptr;	\
+	register unsigned long x1 asm ("x1") = old;			\
+	register unsigned long x2 asm ("x2") = new;			\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+		__LL_SC_CMPXCHG(name)					\
+	"	nop",							\
+	/* LSE atomics */						\
+	"	mov	" #w "30, %" #w "[old]\n"			\
+	"	cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n"		\
+	"	mov	%" #w "[ret], " #w "30")			\
+	: [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr)		\
+	: [old] "r" (x1), [new] "r" (x2)				\
+	: "x30" , ##cl);						\
+									\
+	return x0;							\
+}
+
+__CMPXCHG_CASE(w, b,    1,   )
+__CMPXCHG_CASE(w, h,    2,   )
+__CMPXCHG_CASE(w,  ,    4,   )
+__CMPXCHG_CASE(x,  ,    8,   )
+__CMPXCHG_CASE(w, b, mb_1, al, "memory")
+__CMPXCHG_CASE(w, h, mb_2, al, "memory")
+__CMPXCHG_CASE(w,  , mb_4, al, "memory")
+__CMPXCHG_CASE(x,  , mb_8, al, "memory")
+
+#undef __LL_SC_CMPXCHG
+#undef __CMPXCHG_CASE
+
+#define __LL_SC_CMPXCHG_DBL(op)	__LL_SC_CALL(__cmpxchg_double##op)
+
+#define __CMPXCHG_DBL(name, mb, cl...)					\
+static inline int __cmpxchg_double##name(unsigned long old1,		\
+					 unsigned long old2,		\
+					 unsigned long new1,		\
+					 unsigned long new2,		\
+					 volatile void *ptr)		\
+{									\
+	unsigned long oldval1 = old1;					\
+	unsigned long oldval2 = old2;					\
+	register unsigned long x0 asm ("x0") = old1;			\
+	register unsigned long x1 asm ("x1") = old2;			\
+	register unsigned long x2 asm ("x2") = new1;			\
+	register unsigned long x3 asm ("x3") = new2;			\
+	register unsigned long x4 asm ("x4") = (unsigned long)ptr;	\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	"	nop\n"							\
+	"	nop\n"							\
+	__LL_SC_CMPXCHG_DBL(name),					\
+	/* LSE atomics */						\
+	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
+	"	eor	%[old1], %[old1], %[oldval1]\n"			\
+	"	eor	%[old2], %[old2], %[oldval2]\n"			\
+	"	orr	%[old1], %[old1], %[old2]")			\
+	: [old1] "+r" (x0), [old2] "+r" (x1),				\
+	  [v] "+Q" (*(unsigned long *)ptr)				\
+	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
+	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
+	: "x30" , ##cl);						\
+									\
+	return x0;							\
+}
+
+__CMPXCHG_DBL(   ,   )
+__CMPXCHG_DBL(_mb, al, "memory")
+
+#undef __LL_SC_CMPXCHG_DBL
+#undef __CMPXCHG_DBL
+
+#endif	/* __ASM_ATOMIC_LSE_H */
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 0fa47c4275cb..624f9679f4b0 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -35,28 +35,6 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
-#ifndef CONFIG_SMP
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-
-#define smp_store_release(p, v)						\
-do {									\
-	compiletime_assert_atomic_type(*p);				\
-	barrier();							\
-	ACCESS_ONCE(*p) = (v);						\
-} while (0)
-
-#define smp_load_acquire(p)						\
-({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
-	compiletime_assert_atomic_type(*p);				\
-	barrier();							\
-	___p1;								\
-})
-
-#else
-
 #define smp_mb()	dmb(ish)
 #define smp_rmb()	dmb(ishld)
 #define smp_wmb()	dmb(ishst)
@@ -109,8 +87,6 @@ do {									\
 	___p1;								\
 })
 
-#endif
-
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
new file mode 100644
index 000000000000..4a748ce9ba1a
--- /dev/null
+++ b/arch/arm64/include/asm/bug.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2015  ARM Limited
+ * Author: Dave Martin <Dave.Martin@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ARCH_ARM64_ASM_BUG_H
+#define _ARCH_ARM64_ASM_BUG_H
+
+#include <asm/debug-monitors.h>
+
+#ifdef CONFIG_GENERIC_BUG
+#define HAVE_ARCH_BUG
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
+#define __BUGVERBOSE_LOCATION(file, line)				\
+		".pushsection .rodata.str,\"aMS\",@progbits,1\n"	\
+	"2:	.string \"" file "\"\n\t"				\
+		".popsection\n\t"					\
+									\
+		".long 2b - 0b\n\t"					\
+		".short " #line "\n\t"
+#else
+#define _BUGVERBOSE_LOCATION(file, line)
+#endif
+
+#define _BUG_FLAGS(flags) __BUG_FLAGS(flags)
+
+#define __BUG_FLAGS(flags) asm volatile (		\
+		".pushsection __bug_table,\"a\"\n\t"	\
+		".align 2\n\t"				\
+	"0:	.long 1f - 0b\n\t"			\
+_BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
+		".short " #flags "\n\t"			\
+		".popsection\n"				\
+							\
+	"1:	brk %[imm]"				\
+		:: [imm] "i" (BUG_BRK_IMM)		\
+)
+
+#define BUG() do {				\
+	_BUG_FLAGS(0);				\
+	unreachable();				\
+} while (0)
+
+#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint))
+
+#endif /* ! CONFIG_GENERIC_BUG */
+
+#include <asm-generic/bug.h>
+
+#endif /* ! _ARCH_ARM64_ASM_BUG_H */
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index d8c25b7b18fb..899e9f1d19e4 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -21,7 +21,9 @@
 #include <linux/bug.h>
 #include <linux/mmdebug.h>
 
+#include <asm/atomic.h>
 #include <asm/barrier.h>
+#include <asm/lse.h>
 
 static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
 {
@@ -29,37 +31,73 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 
 	switch (size) {
 	case 1:
-		asm volatile("//	__xchg1\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxrb	%w0, %2\n"
 		"	stlxrb	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpalb	%w3, %w0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
 			: "r" (x)
 			: "memory");
 		break;
 	case 2:
-		asm volatile("//	__xchg2\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxrh	%w0, %2\n"
 		"	stlxrh	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpalh	%w3, %w0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
 			: "r" (x)
 			: "memory");
 		break;
 	case 4:
-		asm volatile("//	__xchg4\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxr	%w0, %2\n"
 		"	stlxr	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpal	%w3, %w0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
 			: "r" (x)
 			: "memory");
 		break;
 	case 8:
-		asm volatile("//	__xchg8\n"
+		asm volatile(ARM64_LSE_ATOMIC_INSN(
+		/* LL/SC */
+		"	prfm	pstl1strm, %2\n"
 		"1:	ldxr	%0, %2\n"
 		"	stlxr	%w1, %3, %2\n"
 		"	cbnz	%w1, 1b\n"
+		"	dmb	ish",
+		/* LSE atomics */
+		"	nop\n"
+		"	nop\n"
+		"	swpal	%3, %0, %2\n"
+		"	nop\n"
+		"	nop")
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
 			: "r" (x)
 			: "memory");
@@ -68,7 +106,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		BUILD_BUG();
 	}
 
-	smp_mb();
 	return ret;
 }
 
@@ -83,131 +120,39 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
 {
-	unsigned long oldval = 0, res;
-
 	switch (size) {
 	case 1:
-		do {
-			asm volatile("// __cmpxchg1\n"
-			"	ldxrb	%w1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%w1, %w3\n"
-			"	b.ne	1f\n"
-			"	stxrb	%w0, %w4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u8 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
+		return __cmpxchg_case_1(ptr, (u8)old, new);
 	case 2:
-		do {
-			asm volatile("// __cmpxchg2\n"
-			"	ldxrh	%w1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%w1, %w3\n"
-			"	b.ne	1f\n"
-			"	stxrh	%w0, %w4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u16 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
+		return __cmpxchg_case_2(ptr, (u16)old, new);
 	case 4:
-		do {
-			asm volatile("// __cmpxchg4\n"
-			"	ldxr	%w1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%w1, %w3\n"
-			"	b.ne	1f\n"
-			"	stxr	%w0, %w4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u32 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
+		return __cmpxchg_case_4(ptr, old, new);
 	case 8:
-		do {
-			asm volatile("// __cmpxchg8\n"
-			"	ldxr	%1, %2\n"
-			"	mov	%w0, #0\n"
-			"	cmp	%1, %3\n"
-			"	b.ne	1f\n"
-			"	stxr	%w0, %4, %2\n"
-			"1:\n"
-				: "=&r" (res), "=&r" (oldval), "+Q" (*(u64 *)ptr)
-				: "Ir" (old), "r" (new)
-				: "cc");
-		} while (res);
-		break;
-
+		return __cmpxchg_case_8(ptr, old, new);
 	default:
 		BUILD_BUG();
 	}
 
-	return oldval;
+	unreachable();
 }
 
-#define system_has_cmpxchg_double()     1
-
-static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2,
-		unsigned long old1, unsigned long old2,
-		unsigned long new1, unsigned long new2, int size)
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+					 unsigned long new, int size)
 {
-	unsigned long loop, lost;
-
 	switch (size) {
+	case 1:
+		return __cmpxchg_case_mb_1(ptr, (u8)old, new);
+	case 2:
+		return __cmpxchg_case_mb_2(ptr, (u16)old, new);
+	case 4:
+		return __cmpxchg_case_mb_4(ptr, old, new);
 	case 8:
-		VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1);
-		do {
-			asm volatile("// __cmpxchg_double8\n"
-			"	ldxp	%0, %1, %2\n"
-			"	eor	%0, %0, %3\n"
-			"	eor	%1, %1, %4\n"
-			"	orr	%1, %0, %1\n"
-			"	mov	%w0, #0\n"
-			"	cbnz	%1, 1f\n"
-			"	stxp	%w0, %5, %6, %2\n"
-			"1:\n"
-				: "=&r"(loop), "=&r"(lost), "+Q" (*(u64 *)ptr1)
-				: "r" (old1), "r"(old2), "r"(new1), "r"(new2));
-		} while (loop);
-		break;
+		return __cmpxchg_case_mb_8(ptr, old, new);
 	default:
 		BUILD_BUG();
 	}
 
-	return !lost;
-}
-
-static inline int __cmpxchg_double_mb(volatile void *ptr1, volatile void *ptr2,
-			unsigned long old1, unsigned long old2,
-			unsigned long new1, unsigned long new2, int size)
-{
-	int ret;
-
-	smp_mb();
-	ret = __cmpxchg_double(ptr1, ptr2, old1, old2, new1, new2, size);
-	smp_mb();
-
-	return ret;
-}
-
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
-					 unsigned long new, int size)
-{
-	unsigned long ret;
-
-	smp_mb();
-	ret = __cmpxchg(ptr, old, new, size);
-	smp_mb();
-
-	return ret;
+	unreachable();
 }
 
 #define cmpxchg(ptr, o, n) \
@@ -228,21 +173,32 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
+#define system_has_cmpxchg_double()     1
+
+#define __cmpxchg_double_check(ptr1, ptr2)					\
+({										\
+	if (sizeof(*(ptr1)) != 8)						\
+		BUILD_BUG();							\
+	VM_BUG_ON((unsigned long *)(ptr2) - (unsigned long *)(ptr1) != 1);	\
+})
+
 #define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \
 ({\
 	int __ret;\
-	__ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \
-			(unsigned long)(o2), (unsigned long)(n1), \
-			(unsigned long)(n2), sizeof(*(ptr1)));\
+	__cmpxchg_double_check(ptr1, ptr2); \
+	__ret = !__cmpxchg_double_mb((unsigned long)(o1), (unsigned long)(o2), \
+				     (unsigned long)(n1), (unsigned long)(n2), \
+				     ptr1); \
 	__ret; \
 })
 
 #define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \
 ({\
 	int __ret;\
-	__ret = __cmpxchg_double((ptr1), (ptr2), (unsigned long)(o1), \
-			(unsigned long)(o2), (unsigned long)(n1), \
-			(unsigned long)(n2), sizeof(*(ptr1)));\
+	__cmpxchg_double_check(ptr1, ptr2); \
+	__ret = !__cmpxchg_double((unsigned long)(o1), (unsigned long)(o2), \
+				  (unsigned long)(n1), (unsigned long)(n2), \
+				  ptr1); \
 	__ret; \
 })
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index c1044218a63a..171570702bb8 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -25,15 +25,20 @@
 #define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
 #define ARM64_WORKAROUND_845719			2
 #define ARM64_HAS_SYSREG_GIC_CPUIF		3
+#define ARM64_HAS_PAN				4
+#define ARM64_HAS_LSE_ATOMICS			5
 
-#define ARM64_NCAPS				4
+#define ARM64_NCAPS				6
 
 #ifndef __ASSEMBLY__
 
+#include <linux/kernel.h>
+
 struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
 	bool (*matches)(const struct arm64_cpu_capabilities *);
+	void (*enable)(void);
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;
@@ -41,8 +46,8 @@ struct arm64_cpu_capabilities {
 		};
 
 		struct {	/* Feature register checking */
-			u64 register_mask;
-			u64 register_value;
+			int field_pos;
+			int min_field_value;
 		};
 	};
 };
@@ -70,6 +75,13 @@ static inline void cpus_set_cap(unsigned int num)
 		__set_bit(num, cpu_hwcaps);
 }
 
+static inline int __attribute_const__ cpuid_feature_extract_field(u64 features,
+								  int field)
+{
+	return (s64)(features << (64 - 4 - field)) >> (64 - 4);
+}
+
+
 void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void check_local_cpu_errata(void);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index a84ec605bed8..ee6403df9fe4 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -81,9 +81,6 @@
 #define ID_AA64MMFR0_BIGEND(mmfr0)	\
 	(((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT)
 
-#define SCTLR_EL1_CP15BEN	(0x1 << 5)
-#define SCTLR_EL1_SED		(0x1 << 8)
-
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 40ec68aa6870..279c85b5ec09 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -18,6 +18,12 @@
 
 #ifdef __KERNEL__
 
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <asm/esr.h>
+#include <asm/insn.h>
+#include <asm/ptrace.h>
+
 /* Low-level stepping controls. */
 #define DBG_MDSCR_SS		(1 << 0)
 #define DBG_SPSR_SS		(1 << 21)
@@ -38,12 +44,7 @@
 /*
  * Break point instruction encoding
  */
-#define BREAK_INSTR_SIZE		4
-
-/*
- * ESR values expected for dynamic and compile time BRK instruction
- */
-#define DBG_ESR_VAL_BRK(x)	(0xf2000000 | ((x) & 0xfffff))
+#define BREAK_INSTR_SIZE		AARCH64_INSN_SIZE
 
 /*
  * #imm16 values used for BRK instruction generation
@@ -51,10 +52,12 @@
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
  * 0x401: for compile time BRK instruction
+ * 0x800: kernel-mode BUG() and WARN() traps
  */
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
+#define BUG_BRK_IMM			0x800
 
 /*
  * BRK instruction encoding
@@ -68,25 +71,10 @@
  */
 #define AARCH64_BREAK_FAULT	(AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5))
 
-/*
- * Extract byte from BRK instruction
- */
-#define KGDB_DYN_DBG_BRK_INS_BYTE(x) \
-	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
-
-/*
- * Extract byte from BRK #imm16
- */
-#define KGBD_DYN_DBG_BRK_IMM_BYTE(x) \
-	(((((KGDB_DYN_DBG_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
-
-#define KGDB_DYN_DBG_BRK_BYTE(x) \
-	(KGDB_DYN_DBG_BRK_INS_BYTE(x) | KGBD_DYN_DBG_BRK_IMM_BYTE(x))
-
-#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DBG_BRK_BYTE(0)
-#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DBG_BRK_BYTE(1)
-#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DBG_BRK_BYTE(2)
-#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DBG_BRK_BYTE(3)
+#define AARCH64_BREAK_KGDB_DYN_DBG	\
+	(AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5))
+#define KGDB_DYN_BRK_INS_BYTE(x)	\
+	((AARCH64_BREAK_KGDB_DYN_DBG >> (8 * (x))) & 0xff)
 
 #define CACHE_FLUSH_IS_SAFE		1
 
@@ -127,13 +115,13 @@ void unregister_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
-enum debug_el {
+enum dbg_active_el {
 	DBG_ACTIVE_EL0 = 0,
 	DBG_ACTIVE_EL1,
 };
 
-void enable_debug_monitors(enum debug_el el);
-void disable_debug_monitors(enum debug_el el);
+void enable_debug_monitors(enum dbg_active_el el);
+void disable_debug_monitors(enum dbg_active_el el);
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 70522450ca23..77eeb2cc648f 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -18,6 +18,8 @@
 #ifndef __ASM_ESR_H
 #define __ASM_ESR_H
 
+#include <asm/memory.h>
+
 #define ESR_ELx_EC_UNKNOWN	(0x00)
 #define ESR_ELx_EC_WFx		(0x01)
 /* Unallocated EC: 0x02 */
@@ -99,6 +101,13 @@
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
 #define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
 
+/* ESR value templates for specific events */
+
+/* BRK instruction trap from AArch64 state */
+#define ESR_ELx_VAL_BRK64(imm)					\
+	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
+	 ((imm) & 0xffff))
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 0303705fcad6..6cb7e1a6bc02 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -18,7 +18,13 @@
 #ifndef __ASM_EXCEPTION_H
 #define __ASM_EXCEPTION_H
 
+#include <linux/ftrace.h>
+
 #define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
 #define __exception_irq_entry	__exception
+#endif
 
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index c0739187a920..8b9884c726ad 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -8,7 +8,7 @@
  * Copyright (C) 1998 Ingo Molnar
  * Copyright (C) 2013 Mark Salter <msalter@redhat.com>
  *
- * Adapted from arch/x86_64 version.
+ * Adapted from arch/x86 version.
  *
  */
 
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 74069b3bd919..007a69fc4f40 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -20,10 +20,17 @@
 
 #include <linux/futex.h>
 #include <linux/uaccess.h>
+
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/errno.h>
+#include <asm/sysreg.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 	asm volatile(							\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,		\
+		    CONFIG_ARM64_PAN)					\
+"	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w3, %w0, %2\n"						\
@@ -39,6 +46,8 @@
 "	.align	3\n"							\
 "	.quad	1b, 4b, 2b, 4b\n"					\
 "	.popsection\n"							\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,		\
+		    CONFIG_ARM64_PAN)					\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
 	: "memory")
@@ -112,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+"	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
 "	cbnz	%w3, 3f\n"
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 6aae421f4d73..2bb7009bdac7 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -24,9 +24,7 @@
 
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_SMP
 	unsigned int ipi_irqs[NR_IPI];
-#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
@@ -34,10 +32,8 @@ typedef struct {
 #define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
 #define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
 
-#ifdef CONFIG_SMP
 u64 smp_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu	smp_irq_stat_cpu
-#endif
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 2fd9b14ca295..bb4052e85dba 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -13,10 +13,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef __ASM_HUGETLB_H
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
index b4f6b19a8a68..8e24ef3f7c82 100644
--- a/arch/arm64/include/asm/irq_work.h
+++ b/arch/arm64/include/asm/irq_work.h
@@ -1,8 +1,6 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-#ifdef CONFIG_SMP
-
 #include <asm/smp.h>
 
 static inline bool arch_irq_work_has_interrupt(void)
@@ -10,13 +8,4 @@ static inline bool arch_irq_work_has_interrupt(void)
 	return !!__smp_cross_call;
 }
 
-#else
-
-static inline bool arch_irq_work_has_interrupt(void)
-{
-	return false;
-}
-
-#endif
-
 #endif /* __ASM_IRQ_WORK_H */
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index c0e5165c2f76..1b5e0e843c3a 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -26,14 +26,28 @@
 
 #define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm goto("1: nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align 3\n\t"
 		 ".quad 1b, %l[l_yes], %c0\n\t"
 		 ".popsection\n\t"
-		 :  :  "i"(key) :  : l_yes);
+		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm goto("1: b %l[l_yes]\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align 3\n\t"
+		 ".quad 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
 
 	return false;
 l_yes:
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
new file mode 100644
index 000000000000..3de42d68611d
--- /dev/null
+++ b/arch/arm64/include/asm/lse.h
@@ -0,0 +1,53 @@
+#ifndef __ASM_LSE_H
+#define __ASM_LSE_H
+
+#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
+
+#include <linux/stringify.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+
+#ifdef __ASSEMBLER__
+
+.arch_extension	lse
+
+.macro alt_lse, llsc, lse
+	alternative_insn "\llsc", "\lse", ARM64_HAS_LSE_ATOMICS
+.endm
+
+#else	/* __ASSEMBLER__ */
+
+__asm__(".arch_extension	lse");
+
+/* Move the ll/sc atomics out-of-line */
+#define __LL_SC_INLINE
+#define __LL_SC_PREFIX(x)	__ll_sc_##x
+#define __LL_SC_EXPORT(x)	EXPORT_SYMBOL(__LL_SC_PREFIX(x))
+
+/* Macro for constructing calls to out-of-line ll/sc atomics */
+#define __LL_SC_CALL(op)	"bl\t" __stringify(__LL_SC_PREFIX(op)) "\n"
+
+/* In-line patching at runtime */
+#define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
+	ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
+
+#endif	/* __ASSEMBLER__ */
+#else	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+
+#ifdef __ASSEMBLER__
+
+.macro alt_lse, llsc, lse
+	\llsc
+.endm
+
+#else	/* __ASSEMBLER__ */
+
+#define __LL_SC_INLINE		static inline
+#define __LL_SC_PREFIX(x)	x
+#define __LL_SC_EXPORT(x)
+
+#define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc
+
+#endif	/* __ASSEMBLER__ */
+#endif	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+#endif	/* __ASM_LSE_H */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index f800d45ea226..44a59c20e773 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -114,6 +114,14 @@ extern phys_addr_t		memstart_addr;
 #define PHYS_OFFSET		({ memstart_addr; })
 
 /*
+ * The maximum physical address that the linear direct mapping
+ * of system RAM can cover. (PAGE_OFFSET can be interpreted as
+ * a 2's complement signed quantity and negated to derive the
+ * maximum size of the linear mapping.)
+ */
+#define MAX_MEMBLOCK_ADDR	({ memstart_addr - PAGE_OFFSET - 1; })
+
+/*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
  *
diff --git a/arch/arm64/include/asm/mm-arch-hooks.h b/arch/arm64/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 562b655f5ba9..000000000000
--- a/arch/arm64/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ARM64_MM_ARCH_HOOKS_H
-#define _ASM_ARM64_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ARM64_MM_ARCH_HOOKS_H */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 79fcfb048884..030208767185 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -28,7 +28,6 @@ typedef struct {
 #define ASID(mm)	((mm)->context.id & 0xffff)
 
 extern void paging_init(void);
-extern void setup_mm_for_reboot(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 4fde8c1df97f..0a456bef8c79 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,8 +16,6 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
-#ifdef CONFIG_SMP
-
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -38,12 +36,6 @@ static inline unsigned long __my_cpu_offset(void)
 }
 #define __my_cpu_offset __my_cpu_offset()
 
-#else	/* !CONFIG_SMP */
-
-#define set_my_cpu_offset(x)	do { } while (0)
-
-#endif /* CONFIG_SMP */
-
 #define PERCPU_OP(op, asm_op)						\
 static inline unsigned long __percpu_##op(void *ptr,			\
 			unsigned long val, int size)			\
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 6471773db6fd..7bd3cdb533ea 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -17,7 +17,7 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
-#ifdef CONFIG_HW_PERF_EVENTS
+#ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 59bfae75dc98..24154b055835 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -104,6 +104,7 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
 #define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
 
@@ -168,5 +169,7 @@
 #define TCR_TG1_64K		(UL(3) << 30)
 #define TCR_ASID16		(UL(1) << 36)
 #define TCR_TBI0		(UL(1) << 37)
+#define TCR_HA			(UL(1) << 39)
+#define TCR_HD			(UL(1) << 40)
 
 #endif
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 56283f8a675c..6900b2d95371 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -16,6 +16,7 @@
 #ifndef __ASM_PGTABLE_H
 #define __ASM_PGTABLE_H
 
+#include <asm/bug.h>
 #include <asm/proc-fns.h>
 
 #include <asm/memory.h>
@@ -27,7 +28,11 @@
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
+#ifdef CONFIG_ARM64_HW_AFDBM
+#define PTE_WRITE		(PTE_DBM)		 /* same as DBM */
+#else
 #define PTE_WRITE		(_AT(pteval_t, 1) << 57)
+#endif
 #define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
 /*
@@ -48,18 +53,16 @@
 #define FIRST_USER_ADDRESS	0UL
 
 #ifndef __ASSEMBLY__
+
+#include <linux/mmdebug.h>
+
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
-#ifdef CONFIG_SMP
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
-#else
-#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF)
-#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
-#endif
 
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
@@ -137,12 +140,20 @@ extern struct page *empty_zero_page;
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
 #define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
-#define pte_dirty(pte)		(!!(pte_val(pte) & PTE_DIRTY))
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+#define pte_hw_dirty(pte)	(!(pte_val(pte) & PTE_RDONLY))
+#else
+#define pte_hw_dirty(pte)	(0)
+#endif
+#define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
+#define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
+
+#define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
@@ -209,20 +220,49 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	}
 }
 
+struct mm_struct;
+struct vm_area_struct;
+
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 
+/*
+ * PTE bits configuration in the presence of hardware Dirty Bit Management
+ * (PTE_WRITE == PTE_DBM):
+ *
+ * Dirty  Writable | PTE_RDONLY  PTE_WRITE  PTE_DIRTY (sw)
+ *   0      0      |   1           0          0
+ *   0      1      |   1           1          0
+ *   1      0      |   1           0          1
+ *   1      1      |   0           1          x
+ *
+ * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
+ * the page fault mechanism. Checking the dirty status of a pte becomes:
+ *
+ *   PTE_DIRTY || !PTE_RDONLY
+ */
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
 	if (pte_valid_user(pte)) {
 		if (!pte_special(pte) && pte_exec(pte))
 			__sync_icache_dcache(pte, addr);
-		if (pte_dirty(pte) && pte_write(pte))
+		if (pte_sw_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
 	}
 
+	/*
+	 * If the existing pte is valid, check for potential race with
+	 * hardware updates of the pte (ptep_set_access_flags safely changes
+	 * valid ptes without going through an invalid entry).
+	 */
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	    pte_valid(*ptep)) {
+		BUG_ON(!pte_young(pte));
+		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+	}
+
 	set_pte(ptep, pte);
 }
 
@@ -461,6 +501,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
 			      PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK;
+	/* preserve the hardware dirty information */
+	if (pte_hw_dirty(pte))
+		newprot |= PTE_DIRTY;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
@@ -470,6 +513,101 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
 }
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * Atomic pte/pmd modifications.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pte_t *ptep)
+{
+	pteval_t pteval;
+	unsigned int tmp, res;
+
+	asm volatile("//	ptep_test_and_clear_young\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	ubfx	%w3, %w0, %5, #1	// extract PTE_AF (young)\n"
+	"	and	%0, %0, %4		// clear PTE_AF\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res)
+	: "L" (~PTE_AF), "I" (ilog2(PTE_AF)));
+
+	return res;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pmd_t *pmdp)
+{
+	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	pteval_t old_pteval;
+	unsigned int tmp;
+
+	asm volatile("//	ptep_get_and_clear\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	stxr	%w1, xzr, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)));
+
+	return __pte(old_pteval);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pmd_t *pmdp)
+{
+	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * ptep_set_wrprotect - mark read-only while trasferring potential hardware
+ * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
+ */
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
+{
+	pteval_t pteval;
+	unsigned long tmp;
+
+	asm volatile("//	ptep_set_wrprotect\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	tst	%0, %4			// check for hw dirty (!PTE_RDONLY)\n"
+	"	csel	%1, %3, xzr, eq		// set PTE_DIRTY|PTE_RDONLY if dirty\n"
+	"	orr	%0, %0, %1		// if !dirty, PTE_RDONLY is already set\n"
+	"	and	%0, %0, %5		// clear PTE_WRITE/PTE_DBM\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+	: "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE)
+	: "cc");
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pmd_t *pmdp)
+{
+	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
+}
+#endif
+#endif	/* CONFIG_ARM64_HW_AFDBM */
+
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
@@ -505,6 +643,21 @@ extern int kern_addr_valid(unsigned long addr);
 
 #define pgtable_cache_init() do { } while (0)
 
+/*
+ * On AArch64, the cache coherency is handled via the set_pte_at() function.
+ */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+	/*
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
+	 */
+	dsb(ishst);
+}
+
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e4c893e54f01..98f32355dc97 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -186,4 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #endif
 
+void cpu_enable_pan(void);
+
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index d6dd9fdbc3be..536274ed292e 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -183,11 +183,7 @@ static inline int valid_user_regs(struct user_pt_regs *regs)
 
 #define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
-#ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
 
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index db02be81b90a..d9c3d6a6100a 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -20,10 +20,6 @@
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
 
-#ifndef CONFIG_SMP
-# error "<asm/smp.h> included in non-SMP build"
-#endif
-
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
 struct seq_file;
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
index 7abf7570c00f..af58dcdefb21 100644
--- a/arch/arm64/include/asm/smp_plat.h
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -56,6 +56,4 @@ static inline int get_logical_index(u64 mpidr)
 	return -EINVAL;
 }
 
-void __init do_post_cpus_up_work(void);
-
 #endif /* __ASM_SMP_PLAT_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index cee128732435..c85e96d174a5 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -16,6 +16,7 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
+#include <asm/lse.h>
 #include <asm/spinlock_types.h>
 #include <asm/processor.h>
 
@@ -38,11 +39,21 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 
 	asm volatile(
 	/* Atomically increment the next ticket. */
+	ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 "	prfm	pstl1strm, %3\n"
 "1:	ldaxr	%w0, %3\n"
 "	add	%w1, %w0, %w5\n"
 "	stxr	%w2, %w1, %3\n"
-"	cbnz	%w2, 1b\n"
+"	cbnz	%w2, 1b\n",
+	/* LSE atomics */
+"	mov	%w2, %w5\n"
+"	ldadda	%w2, %w0, %3\n"
+"	nop\n"
+"	nop\n"
+"	nop\n"
+	)
+
 	/* Did we get the lock? */
 "	eor	%w1, %w0, %w0, ror #16\n"
 "	cbz	%w1, 3f\n"
@@ -67,15 +78,25 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	unsigned int tmp;
 	arch_spinlock_t lockval;
 
-	asm volatile(
-"	prfm	pstl1strm, %2\n"
-"1:	ldaxr	%w0, %2\n"
-"	eor	%w1, %w0, %w0, ror #16\n"
-"	cbnz	%w1, 2f\n"
-"	add	%w0, %w0, %3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b\n"
-"2:"
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldaxr	%w0, %2\n"
+	"	eor	%w1, %w0, %w0, ror #16\n"
+	"	cbnz	%w1, 2f\n"
+	"	add	%w0, %w0, %3\n"
+	"	stxr	%w1, %w0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	"2:",
+	/* LSE atomics */
+	"	ldr	%w0, %2\n"
+	"	eor	%w1, %w0, %w0, ror #16\n"
+	"	cbnz	%w1, 1f\n"
+	"	add	%w1, %w0, %3\n"
+	"	casa	%w0, %w1, %2\n"
+	"	and	%w1, %w1, #0xffff\n"
+	"	eor	%w1, %w1, %w0, lsr #16\n"
+	"1:")
 	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
 	: "I" (1 << TICKET_SHIFT)
 	: "memory");
@@ -85,10 +106,19 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	asm volatile(
-"	stlrh	%w1, %0\n"
-	: "=Q" (lock->owner)
-	: "r" (lock->owner + 1)
+	unsigned long tmp;
+
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	ldrh	%w1, %0\n"
+	"	add	%w1, %w1, #1\n"
+	"	stlrh	%w1, %0",
+	/* LSE atomics */
+	"	mov	%w1, #1\n"
+	"	nop\n"
+	"	staddlh	%w1, %0")
+	: "=Q" (lock->owner), "=&r" (tmp)
+	:
 	: "memory");
 }
 
@@ -123,13 +153,24 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned int tmp;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 	"	sevl\n"
 	"1:	wfe\n"
 	"2:	ldaxr	%w0, %1\n"
 	"	cbnz	%w0, 1b\n"
 	"	stxr	%w0, %w2, %1\n"
 	"	cbnz	%w0, 2b\n"
+	"	nop",
+	/* LSE atomics */
+	"1:	mov	%w0, wzr\n"
+	"2:	casa	%w0, %w2, %1\n"
+	"	cbz	%w0, 3f\n"
+	"	ldxr	%w0, %1\n"
+	"	cbz	%w0, 2b\n"
+	"	wfe\n"
+	"	b	1b\n"
+	"3:")
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -139,11 +180,18 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned int tmp;
 
-	asm volatile(
-	"	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1f\n"
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"1:	ldaxr	%w0, %1\n"
+	"	cbnz	%w0, 2f\n"
 	"	stxr	%w0, %w2, %1\n"
-	"1:\n"
+	"	cbnz	%w0, 1b\n"
+	"2:",
+	/* LSE atomics */
+	"	mov	%w0, wzr\n"
+	"	casa	%w0, %w2, %1\n"
+	"	nop\n"
+	"	nop")
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -153,9 +201,10 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
-	asm volatile(
-	"	stlr	%w1, %0\n"
-	: "=Q" (rw->lock) : "r" (0) : "memory");
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	"	stlr	wzr, %0",
+	"	swpl	wzr, wzr, %0")
+	: "=Q" (rw->lock) :: "memory");
 }
 
 /* write_can_lock - would write_trylock() succeed? */
@@ -172,6 +221,10 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
  *
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
+ *
+ * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC
+ * and LSE implementations may exhibit different behaviour (although this
+ * will have no effect on lockdep).
  */
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
@@ -179,26 +232,43 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 
 	asm volatile(
 	"	sevl\n"
+	ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 	"1:	wfe\n"
 	"2:	ldaxr	%w0, %2\n"
 	"	add	%w0, %w0, #1\n"
 	"	tbnz	%w0, #31, 1b\n"
 	"	stxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 2b\n"
+	"	nop\n"
+	"	cbnz	%w1, 2b",
+	/* LSE atomics */
+	"1:	wfe\n"
+	"2:	ldxr	%w0, %2\n"
+	"	adds	%w1, %w0, #1\n"
+	"	tbnz	%w1, #31, 1b\n"
+	"	casa	%w0, %w1, %2\n"
+	"	sbc	%w0, %w1, %w0\n"
+	"	cbnz	%w0, 2b")
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "memory");
+	: "cc", "memory");
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	unsigned int tmp, tmp2;
 
-	asm volatile(
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
 	"1:	ldxr	%w0, %2\n"
 	"	sub	%w0, %w0, #1\n"
 	"	stlxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 1b\n"
+	"	cbnz	%w1, 1b",
+	/* LSE atomics */
+	"	movn	%w0, #0\n"
+	"	nop\n"
+	"	nop\n"
+	"	staddl	%w0, %2")
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
 	: "memory");
@@ -206,17 +276,28 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned int tmp, tmp2 = 1;
+	unsigned int tmp, tmp2;
 
-	asm volatile(
-	"	ldaxr	%w0, %2\n"
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+	"	mov	%w1, #1\n"
+	"1:	ldaxr	%w0, %2\n"
 	"	add	%w0, %w0, #1\n"
-	"	tbnz	%w0, #31, 1f\n"
+	"	tbnz	%w0, #31, 2f\n"
 	"	stxr	%w1, %w0, %2\n"
-	"1:\n"
-	: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
+	"	cbnz	%w1, 1b\n"
+	"2:",
+	/* LSE atomics */
+	"	ldr	%w0, %2\n"
+	"	adds	%w1, %w0, #1\n"
+	"	tbnz	%w1, #31, 1f\n"
+	"	casa	%w0, %w1, %2\n"
+	"	sbc	%w1, %w1, %w0\n"
+	"	nop\n"
+	"1:")
+	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "memory");
+	: "cc", "memory");
 
 	return !tmp2;
 }
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index b8d383665f56..55be59a35e3f 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,6 +20,8 @@
 # error "please don't include this file directly"
 #endif
 
+#include <linux/types.h>
+
 #define TICKET_SHIFT	16
 
 typedef struct {
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5c89df0acbcb..a7f3d4b2514d 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -20,8 +20,29 @@
 #ifndef __ASM_SYSREG_H
 #define __ASM_SYSREG_H
 
+#include <asm/opcodes.h>
+
+#define SCTLR_EL1_CP15BEN	(0x1 << 5)
+#define SCTLR_EL1_SED		(0x1 << 8)
+
+/*
+ * ARMv8 ARM reserves the following encoding for system registers:
+ * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
+ *  C5.2, version:ARM DDI 0487A.f)
+ *	[20-19] : Op0
+ *	[18-16] : Op1
+ *	[15-12] : CRn
+ *	[11-8]  : CRm
+ *	[7-5]   : Op2
+ */
 #define sys_reg(op0, op1, crn, crm, op2) \
-	((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+	((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#define REG_PSTATE_PAN_IMM                     sys_reg(0, 0, 4, 0, 4)
+#define SCTLR_EL1_SPAN                         (1 << 23)
+
+#define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\
+				     (!!x)<<8 | 0x1f)
 
 #ifdef __ASSEMBLY__
 
@@ -31,11 +52,11 @@
 	.equ	__reg_num_xzr, 31
 
 	.macro	mrs_s, rt, sreg
-	.inst	0xd5300000|(\sreg)|(__reg_num_\rt)
+	.inst	0xd5200000|(\sreg)|(__reg_num_\rt)
 	.endm
 
 	.macro	msr_s, sreg, rt
-	.inst	0xd5100000|(\sreg)|(__reg_num_\rt)
+	.inst	0xd5000000|(\sreg)|(__reg_num_\rt)
 	.endm
 
 #else
@@ -47,14 +68,23 @@ asm(
 "	.equ	__reg_num_xzr, 31\n"
 "\n"
 "	.macro	mrs_s, rt, sreg\n"
-"	.inst	0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.inst	0xd5200000|(\\sreg)|(__reg_num_\\rt)\n"
 "	.endm\n"
 "\n"
 "	.macro	msr_s, sreg, rt\n"
-"	.inst	0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.inst	0xd5000000|(\\sreg)|(__reg_num_\\rt)\n"
 "	.endm\n"
 );
 
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+	u32 val;
+
+	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
+	val &= ~clear;
+	val |= set;
+	asm volatile("msr sctlr_el1, %0" : : "r" (val));
+}
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 3a0242c7eb8d..d6e6b6660380 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -41,7 +41,12 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		flush_tlb_mm(tlb->mm);
 	} else {
 		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
-		flush_tlb_range(&vma, tlb->start, tlb->end);
+		/*
+		 * The intermediate page table levels are already handled by
+		 * the __(pte|pmd|pud)_free_tlb() functions, so last level
+		 * TLBI is sufficient here.
+		 */
+		__flush_tlb_range(&vma, tlb->start, tlb->end, true);
 	}
 }
 
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 934815d45eda..7bd2da021658 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -87,27 +87,56 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 		((unsigned long)ASID(vma->vm_mm) << 48);
 
 	dsb(ishst);
-	asm("tlbi	vae1is, %0" : : "r" (addr));
+	asm("tlbi	vale1is, %0" : : "r" (addr));
 	dsb(ish);
 }
 
+/*
+ * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
+ * necessarily a performance improvement.
+ */
+#define MAX_TLB_RANGE	(1024UL << PAGE_SHIFT)
+
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
-				     unsigned long start, unsigned long end)
+				     unsigned long start, unsigned long end,
+				     bool last_level)
 {
 	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
 	unsigned long addr;
+
+	if ((end - start) > MAX_TLB_RANGE) {
+		flush_tlb_mm(vma->vm_mm);
+		return;
+	}
+
 	start = asid | (start >> 12);
 	end = asid | (end >> 12);
 
 	dsb(ishst);
-	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
-		asm("tlbi vae1is, %0" : : "r"(addr));
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
+		if (last_level)
+			asm("tlbi vale1is, %0" : : "r"(addr));
+		else
+			asm("tlbi vae1is, %0" : : "r"(addr));
+	}
 	dsb(ish);
 }
 
-static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long end)
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	__flush_tlb_range(vma, start, end, false);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
+
+	if ((end - start) > MAX_TLB_RANGE) {
+		flush_tlb_all();
+		return;
+	}
+
 	start >>= 12;
 	end >>= 12;
 
@@ -119,29 +148,6 @@ static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long e
 }
 
 /*
- * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
- * necessarily a performance improvement.
- */
-#define MAX_TLB_RANGE	(1024UL << PAGE_SHIFT)
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	if ((end - start) <= MAX_TLB_RANGE)
-		__flush_tlb_range(vma, start, end);
-	else
-		flush_tlb_mm(vma->vm_mm);
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	if ((end - start) <= MAX_TLB_RANGE)
-		__flush_tlb_kernel_range(start, end);
-	else
-		flush_tlb_all();
-}
-
-/*
  * Used to invalidate the TLB (walk caches) corresponding to intermediate page
  * table levels (pgd/pud/pmd).
  */
@@ -154,20 +160,6 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 	asm("tlbi	vae1is, %0" : : "r" (addr));
 	dsb(ish);
 }
-/*
- * On AArch64, the cache coherency is handled via the set_pte_at() function.
- */
-static inline void update_mmu_cache(struct vm_area_struct *vma,
-				    unsigned long addr, pte_t *ptep)
-{
-	/*
-	 * set_pte() does not have a DSB for user mappings, so make sure that
-	 * the page table write is visible.
-	 */
-	dsb(ishst);
-}
-
-#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
 #endif
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 225ec3524fbf..a3e9d6fdbf21 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -1,8 +1,6 @@
 #ifndef __ASM_TOPOLOGY_H
 #define __ASM_TOPOLOGY_H
 
-#ifdef CONFIG_SMP
-
 #include <linux/cpumask.h>
 
 struct cpu_topology {
@@ -24,13 +22,6 @@ void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#else
-
-static inline void init_cpu_topology(void) { }
-static inline void store_cpu_topology(unsigned int cpuid) { }
-
-#endif
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 232e4ba5d314..0cc2f29bf9da 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -34,13 +34,32 @@ struct undef_hook {
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	extern char __irqentry_text_start[];
+	extern char __irqentry_text_end[];
+
+	return ptr >= (unsigned long)&__irqentry_text_start &&
+	       ptr < (unsigned long)&__irqentry_text_end;
+}
+#else
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	return 0;
+}
+#endif
+
 static inline int in_exception_text(unsigned long ptr)
 {
 	extern char __exception_text_start[];
 	extern char __exception_text_end[];
+	int in;
+
+	in = ptr >= (unsigned long)&__exception_text_start &&
+	     ptr < (unsigned long)&__exception_text_end;
 
-	return ptr >= (unsigned long)&__exception_text_start &&
-	       ptr < (unsigned long)&__exception_text_end;
+	return in ? : __in_irqentry_text(ptr);
 }
 
 #endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 07e1ba449bf1..b2ede967fe7d 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -24,7 +24,10 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/ptrace.h>
+#include <asm/sysreg.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
@@ -131,6 +134,8 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_asm("ldrb", "%w", __gu_val, (ptr), (err));	\
@@ -148,6 +153,8 @@ do {									\
 		BUILD_BUG();						\
 	}								\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __get_user(x, ptr)						\
@@ -194,6 +201,8 @@ do {									\
 do {									\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__put_user_asm("strb", "%w", __pu_val, (ptr), (err));	\
@@ -210,6 +219,8 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
+			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __put_user(x, ptr)						\
diff --git a/arch/arm64/include/asm/xen/events.h b/arch/arm64/include/asm/xen/events.h
index 86553213c132..4318866d053c 100644
--- a/arch/arm64/include/asm/xen/events.h
+++ b/arch/arm64/include/asm/xen/events.h
@@ -18,4 +18,10 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
+/* Rebind event channel is supported by default */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return true;
+}
+
 #endif /* _ASM_ARM64_XEN_EVENTS_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 73cf0f54d57c..361c8a8ef55f 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -27,5 +27,6 @@
 #define HWCAP_SHA1		(1 << 5)
 #define HWCAP_SHA2		(1 << 6)
 #define HWCAP_CRC32		(1 << 7)
+#define HWCAP_ATOMICS		(1 << 8)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 6913643bbe54..208db3df135a 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -44,6 +44,7 @@
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
 #define PSR_D_BIT	0x00000200
+#define PSR_PAN_BIT	0x00400000
 #define PSR_Q_BIT	0x08000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 426d0763c81b..22dc9bc781be 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -17,15 +17,15 @@ arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
 			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
-			   cpufeature.o alternative.o cacheinfo.o
+			   cpufeature.o alternative.o cacheinfo.o		\
+			   smp.o smp_spin_table.o topology.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o entry32.o		\
 					   ../../arm/kernel/opcodes.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o topology.o
-arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
+arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_CPU_PM)		+= sleep.o suspend.o
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 221b98312f0c..ab9db0e9818c 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -85,7 +85,7 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
 	return insn;
 }
 
-static int __apply_alternatives(void *alt_region)
+static void __apply_alternatives(void *alt_region)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
@@ -114,19 +114,39 @@ static int __apply_alternatives(void *alt_region)
 		flush_icache_range((uintptr_t)origptr,
 				   (uintptr_t)(origptr + nr_inst));
 	}
-
-	return 0;
 }
 
-void apply_alternatives_all(void)
+/*
+ * We might be patching the stop_machine state machine, so implement a
+ * really simple polling protocol here.
+ */
+static int __apply_alternatives_multi_stop(void *unused)
 {
+	static int patched = 0;
 	struct alt_region region = {
 		.begin	= __alt_instructions,
 		.end	= __alt_instructions_end,
 	};
 
+	/* We always have a CPU 0 at this point (__init) */
+	if (smp_processor_id()) {
+		while (!READ_ONCE(patched))
+			cpu_relax();
+		isb();
+	} else {
+		BUG_ON(patched);
+		__apply_alternatives(&region);
+		/* Barriers provided by the cache flushing */
+		WRITE_ONCE(patched, 1);
+	}
+
+	return 0;
+}
+
+void __init apply_alternatives_all(void)
+{
 	/* better not try code patching on a live SMP system */
-	stop_machine(__apply_alternatives, &region, NULL);
+	stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
 }
 
 void apply_alternatives(void *start, size_t length)
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 7922c2e710ca..bcee7abac68e 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -14,8 +14,11 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/insn.h>
 #include <asm/opcodes.h>
+#include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -279,6 +282,8 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
+		    CONFIG_ARM64_PAN)				\
 	"	mov		%w2, %w1\n"			\
 	"0:	ldxr"B"		%w1, [%3]\n"			\
 	"1:	stxr"B"		%w0, %w2, [%3]\n"		\
@@ -294,7 +299,9 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
 	"	.align		3\n"				\
 	"	.quad		0b, 3b\n"			\
 	"	.quad		1b, 3b\n"			\
-	"	.popsection"					\
+	"	.popsection\n"					\
+	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
+		CONFIG_ARM64_PAN)				\
 	: "=&r" (res), "+r" (data), "=&r" (temp)		\
 	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
 	: "memory")
@@ -504,16 +511,6 @@ ret:
 	return 0;
 }
 
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
-	u32 val;
-
-	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
-	val &= ~clear;
-	val |= set;
-	asm volatile("msr sctlr_el1, %0" : : "r" (val));
-}
-
 static int cp15_barrier_set_hw_mode(bool enable)
 {
 	if (enable)
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index 5ea337dd2f15..b6bd7d447768 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -30,9 +30,7 @@ extern const struct cpu_operations cpu_psci_ops;
 const struct cpu_operations *cpu_ops[NR_CPUS];
 
 static const struct cpu_operations *supported_cpu_ops[] __initconst = {
-#ifdef CONFIG_SMP
 	&smp_spin_table_ops,
-#endif
 	&cpu_psci_ops,
 	NULL,
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 5ad86ceac010..3c9aed32f70b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -21,24 +21,57 @@
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
+#include <asm/processor.h>
 
 static bool
-has_id_aa64pfr0_feature(const struct arm64_cpu_capabilities *entry)
+feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 {
-	u64 val;
+	int val = cpuid_feature_extract_field(reg, entry->field_pos);
 
-	val = read_cpuid(id_aa64pfr0_el1);
-	return (val & entry->register_mask) == entry->register_value;
+	return val >= entry->min_field_value;
 }
 
+#define __ID_FEAT_CHK(reg)						\
+static bool __maybe_unused						\
+has_##reg##_feature(const struct arm64_cpu_capabilities *entry)		\
+{									\
+	u64 val;							\
+									\
+	val = read_cpuid(reg##_el1);					\
+	return feature_matches(val, entry);				\
+}
+
+__ID_FEAT_CHK(id_aa64pfr0);
+__ID_FEAT_CHK(id_aa64mmfr1);
+__ID_FEAT_CHK(id_aa64isar0);
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
 		.matches = has_id_aa64pfr0_feature,
-		.register_mask = (0xf << 24),
-		.register_value = (1 << 24),
+		.field_pos = 24,
+		.min_field_value = 1,
+	},
+#ifdef CONFIG_ARM64_PAN
+	{
+		.desc = "Privileged Access Never",
+		.capability = ARM64_HAS_PAN,
+		.matches = has_id_aa64mmfr1_feature,
+		.field_pos = 20,
+		.min_field_value = 1,
+		.enable = cpu_enable_pan,
 	},
+#endif /* CONFIG_ARM64_PAN */
+#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
+	{
+		.desc = "LSE atomic instructions",
+		.capability = ARM64_HAS_LSE_ATOMICS,
+		.matches = has_id_aa64isar0_feature,
+		.field_pos = 20,
+		.min_field_value = 2,
+	},
+#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
 	{},
 };
 
@@ -55,9 +88,15 @@ void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			pr_info("%s %s\n", info, caps[i].desc);
 		cpus_set_cap(caps[i].capability);
 	}
+
+	/* second pass allows enable() to consider interacting capabilities */
+	for (i = 0; caps[i].desc; i++) {
+		if (cpus_have_cap(caps[i].capability) && caps[i].enable)
+			caps[i].enable();
+	}
 }
 
 void check_local_cpu_features(void)
 {
-	check_cpu_capabilities(arm64_features, "detected feature");
+	check_cpu_capabilities(arm64_features, "detected feature:");
 }
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index b056369fd47d..9b3b62ac9c24 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -82,7 +82,7 @@ early_param("nodebugmon", early_debug_disable);
 static DEFINE_PER_CPU(int, mde_ref_count);
 static DEFINE_PER_CPU(int, kde_ref_count);
 
-void enable_debug_monitors(enum debug_el el)
+void enable_debug_monitors(enum dbg_active_el el)
 {
 	u32 mdscr, enable = 0;
 
@@ -102,7 +102,7 @@ void enable_debug_monitors(enum debug_el el)
 	}
 }
 
-void disable_debug_monitors(enum debug_el el)
+void disable_debug_monitors(enum dbg_active_el el)
 {
 	u32 mdscr, disable = 0;
 
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
index f5374065ad53..816120ece6bc 100644
--- a/arch/arm64/kernel/efi-stub.c
+++ b/arch/arm64/kernel/efi-stub.c
@@ -13,7 +13,7 @@
 #include <asm/efi.h>
 #include <asm/sections.h>
 
-efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table,
+efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg,
 					unsigned long *image_addr,
 					unsigned long *image_size,
 					unsigned long *reserve_addr,
@@ -23,21 +23,44 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table,
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_memsize = 0;
+	unsigned long nr_pages;
+	void *old_image_addr = (void *)*image_addr;
 
 	/* Relocate the image, if required. */
 	kernel_size = _edata - _text;
 	if (*image_addr != (dram_base + TEXT_OFFSET)) {
 		kernel_memsize = kernel_size + (_end - _edata);
-		status = efi_low_alloc(sys_table, kernel_memsize + TEXT_OFFSET,
-				       SZ_2M, reserve_addr);
+
+		/*
+		 * First, try a straight allocation at the preferred offset.
+		 * This will work around the issue where, if dram_base == 0x0,
+		 * efi_low_alloc() refuses to allocate at 0x0 (to prevent the
+		 * address of the allocation to be mistaken for a FAIL return
+		 * value or a NULL pointer). It will also ensure that, on
+		 * platforms where the [dram_base, dram_base + TEXT_OFFSET)
+		 * interval is partially occupied by the firmware (like on APM
+		 * Mustang), we can still place the kernel at the address
+		 * 'dram_base + TEXT_OFFSET'.
+		 */
+		*image_addr = *reserve_addr = dram_base + TEXT_OFFSET;
+		nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) /
+			   EFI_PAGE_SIZE;
+		status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS,
+					EFI_LOADER_DATA, nr_pages,
+					(efi_physical_addr_t *)reserve_addr);
 		if (status != EFI_SUCCESS) {
-			pr_efi_err(sys_table, "Failed to relocate kernel\n");
-			return status;
+			kernel_memsize += TEXT_OFFSET;
+			status = efi_low_alloc(sys_table_arg, kernel_memsize,
+					       SZ_2M, reserve_addr);
+
+			if (status != EFI_SUCCESS) {
+				pr_efi_err(sys_table_arg, "Failed to relocate kernel\n");
+				return status;
+			}
+			*image_addr = *reserve_addr + TEXT_OFFSET;
 		}
-		memcpy((void *)*reserve_addr + TEXT_OFFSET, (void *)*image_addr,
-		       kernel_size);
-		*image_addr = *reserve_addr + TEXT_OFFSET;
-		*reserve_size = kernel_memsize + TEXT_OFFSET;
+		memcpy((void *)*image_addr, old_image_addr, kernel_size);
+		*reserve_size = kernel_memsize;
 	}
 
 
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 9d4aa18f2a82..e8ca6eaedd02 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -122,12 +122,12 @@ static int __init uefi_init(void)
 
 	/* Show what we know for posterity */
 	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor));
+			     sizeof(vendor) * sizeof(efi_char16_t));
 	if (c16) {
 		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = c16[i];
 		vendor[i] = '\0';
-		early_memunmap(c16, sizeof(vendor));
+		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
 	}
 
 	pr_info("EFI v%u.%.02u by %s\n",
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a7691a378668..4306c937b1ff 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -116,41 +116,34 @@
 	*/
 	.endm
 
-	.macro	kernel_exit, el, ret = 0
+	.macro	kernel_exit, el
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	msr	sp_el0, x23
-
 #ifdef CONFIG_ARM64_ERRATUM_845719
-
-#undef SEQUENCE_ORG
-#undef SEQUENCE_ALT
-
+alternative_if_not ARM64_WORKAROUND_845719
+	nop
+	nop
 #ifdef CONFIG_PID_IN_CONTEXTIDR
-
-#define SEQUENCE_ORG	"nop ; nop ; nop"
-#define SEQUENCE_ALT	"tbz x22, #4, 1f ; mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:"
-
+	nop
+#endif
+alternative_else
+	tbz	x22, #4, 1f
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+	mrs	x29, contextidr_el1
+	msr	contextidr_el1, x29
 #else
-
-#define SEQUENCE_ORG	"nop ; nop"
-#define SEQUENCE_ALT	"tbz x22, #4, 1f ; msr contextidr_el1, xzr; 1:"
-
+	msr contextidr_el1, xzr
 #endif
-
-	alternative_insn SEQUENCE_ORG, SEQUENCE_ALT, ARM64_WORKAROUND_845719
-
+1:
+alternative_endif
 #endif
 	.endif
 	msr	elr_el1, x21			// set up the return data
 	msr	spsr_el1, x22
-	.if	\ret
-	ldr	x1, [sp, #S_X1]			// preserve x0 (syscall return)
-	.else
 	ldp	x0, x1, [sp, #16 * 0]
-	.endif
 	ldp	x2, x3, [sp, #16 * 1]
 	ldp	x4, x5, [sp, #16 * 2]
 	ldp	x6, x7, [sp, #16 * 3]
@@ -352,8 +345,8 @@ el1_inv:
 	// TODO: add support for undefined instructions in kernel mode
 	enable_dbg
 	mov	x0, sp
+	mov	x2, x1
 	mov	x1, #BAD_SYNC
-	mrs	x2, esr_el1
 	b	bad_mode
 ENDPROC(el1_sync)
 
@@ -553,7 +546,7 @@ el0_inv:
 	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
-	mrs	x2, esr_el1
+	mov	x2, x25
 	bl	bad_mode
 	b	ret_to_user
 ENDPROC(el0_sync)
@@ -585,7 +578,8 @@ ENDPROC(el0_irq)
  *
  */
 ENTRY(cpu_switch_to)
-	add	x8, x0, #THREAD_CPU_CONTEXT
+	mov	x10, #THREAD_CPU_CONTEXT
+	add	x8, x0, x10
 	mov	x9, sp
 	stp	x19, x20, [x8], #16		// store callee-saved registers
 	stp	x21, x22, [x8], #16
@@ -594,7 +588,7 @@ ENTRY(cpu_switch_to)
 	stp	x27, x28, [x8], #16
 	stp	x29, x9, [x8], #16
 	str	lr, [x8]
-	add	x8, x1, #THREAD_CPU_CONTEXT
+	add	x8, x1, x10
 	ldp	x19, x20, [x8], #16		// restore callee-saved registers
 	ldp	x21, x22, [x8], #16
 	ldp	x23, x24, [x8], #16
@@ -612,22 +606,21 @@ ENDPROC(cpu_switch_to)
  */
 ret_fast_syscall:
 	disable_irq				// disable interrupts
+	str	x0, [sp, #S_X0]			// returned x0
 	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
 	cbnz	x2, ret_fast_syscall_trace
 	and	x2, x1, #_TIF_WORK_MASK
-	cbnz	x2, fast_work_pending
+	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
-	kernel_exit 0, ret = 1
+	kernel_exit 0
 ret_fast_syscall_trace:
 	enable_irq				// enable interrupts
-	b	__sys_trace_return
+	b	__sys_trace_return_skipped	// we already saved x0
 
 /*
  * Ok, we need to do extra processing, enter the slow path.
  */
-fast_work_pending:
-	str	x0, [sp, #S_X0]			// returned x0
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
 	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
@@ -651,7 +644,7 @@ ret_to_user:
 	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
 no_work_pending:
-	kernel_exit 0, ret = 0
+	kernel_exit 0
 ENDPROC(ret_to_user)
 
 /*
diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S
index bd9bfaa9269b..f332d5d1f6b4 100644
--- a/arch/arm64/kernel/entry32.S
+++ b/arch/arm64/kernel/entry32.S
@@ -32,13 +32,11 @@
 
 ENTRY(compat_sys_sigreturn_wrapper)
 	mov	x0, sp
-	mov	x27, #0		// prevent syscall restart handling (why)
 	b	compat_sys_sigreturn
 ENDPROC(compat_sys_sigreturn_wrapper)
 
 ENTRY(compat_sys_rt_sigreturn_wrapper)
 	mov	x0, sp
-	mov	x27, #0		// prevent syscall restart handling (why)
 	b	compat_sys_rt_sigreturn
 ENDPROC(compat_sys_rt_sigreturn_wrapper)
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 44d6f7545505..c56956a16d3f 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -158,6 +158,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 void fpsimd_flush_thread(void)
 {
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
+	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index c0ff3ce4299e..a055be6125cf 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -62,13 +62,8 @@
 /*
  * Initial memory map attributes.
  */
-#ifndef CONFIG_SMP
-#define PTE_FLAGS	PTE_TYPE_PAGE | PTE_AF
-#define PMD_FLAGS	PMD_TYPE_SECT | PMD_SECT_AF
-#else
 #define PTE_FLAGS	PTE_TYPE_PAGE | PTE_AF | PTE_SHARED
 #define PMD_FLAGS	PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S
-#endif
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define MM_MMUFLAGS	PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS
@@ -574,7 +569,6 @@ ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL1
 	.popsection
 
-#ifdef CONFIG_SMP
 	/*
 	 * This provides a "holding pen" for platforms to hold all secondary
 	 * cores are held until we're ready for them to initialise.
@@ -622,7 +616,6 @@ ENTRY(__secondary_switched)
 	mov	x29, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
-#endif	/* CONFIG_SMP */
 
 /*
  * Enable the MMU.
@@ -641,5 +634,13 @@ __enable_mmu:
 	isb
 	msr	sctlr_el1, x0
 	isb
+	/*
+	 * Invalidate the local I-cache so that any instructions fetched
+	 * speculatively from the PoC are discarded, since they may have
+	 * been dynamically patched at the PoU.
+	 */
+	ic	iallu
+	dsb	nsh
+	isb
 	br	x27
 ENDPROC(__enable_mmu)
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 7a1a5da6c8c1..003bc3d50636 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -156,7 +156,7 @@ static void write_wb_reg(int reg, int n, u64 val)
  * Convert a breakpoint privilege level to the corresponding exception
  * level.
  */
-static enum debug_el debug_exception_level(int privilege)
+static enum dbg_active_el debug_exception_level(int privilege)
 {
 	switch (privilege) {
 	case AARCH64_BREAKPOINT_EL0:
@@ -230,7 +230,7 @@ static int hw_breakpoint_control(struct perf_event *bp,
 	struct perf_event **slots;
 	struct debug_info *debug_info = &current->thread.debug;
 	int i, max_slots, ctrl_reg, val_reg, reg_enable;
-	enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege);
+	enum dbg_active_el dbg_el = debug_exception_level(info->ctrl.privilege);
 	u32 ctrl;
 
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
@@ -537,7 +537,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
  * exception level at the register level.
  * This is used when single-stepping after a breakpoint exception.
  */
-static void toggle_bp_registers(int reg, enum debug_el el, int enable)
+static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable)
 {
 	int i, max_slots, privilege;
 	u32 ctrl;
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index dd9671cd0bb2..f341866aa810 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -101,9 +101,8 @@ static void __kprobes *patch_map(void *addr, int fixmap)
 		return addr;
 
 	BUG_ON(!page);
-	set_fixmap(fixmap, page_to_phys(page));
-
-	return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK));
+	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+			(uintaddr & ~PAGE_MASK));
 }
 
 static void __kprobes patch_unmap(int fixmap)
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 240b75c0e94f..11dc3fd47853 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -33,9 +33,7 @@ unsigned long irq_err_count;
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
-#ifdef CONFIG_SMP
 	show_ipi_list(p, prec);
-#endif
 	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	return 0;
 }
@@ -61,7 +59,7 @@ void __init init_IRQ(void)
 static bool migrate_one_irq(struct irq_desc *desc)
 {
 	struct irq_data *d = irq_desc_get_irq_data(desc);
-	const struct cpumask *affinity = d->affinity;
+	const struct cpumask *affinity = irq_data_get_affinity_mask(d);
 	struct irq_chip *c;
 	bool ret = false;
 
@@ -81,7 +79,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
-		cpumask_copy(d->affinity, affinity);
+		cpumask_copy(irq_data_get_affinity_mask(d), affinity);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
index 4f1fec7a46db..c2dd1ad3e648 100644
--- a/arch/arm64/kernel/jump_label.c
+++ b/arch/arm64/kernel/jump_label.c
@@ -28,7 +28,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	void *addr = (void *)entry->code;
 	u32 insn;
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		insn = aarch64_insn_gen_branch_imm(entry->code,
 						   entry->target,
 						   AARCH64_INSN_BRANCH_NOLINK);
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index a0d10c55f307..bcac81e600b9 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -235,13 +235,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 
 static struct break_hook kgdb_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
-	.esr_val	= DBG_ESR_VAL_BRK(KGDB_DYN_DBG_BRK_IMM),
+	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM),
 	.fn		= kgdb_brk_fn
 };
 
 static struct break_hook kgdb_compiled_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
-	.esr_val	= DBG_ESR_VAL_BRK(KGDB_COMPILED_DBG_BRK_IMM),
+	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM),
 	.fn		= kgdb_compiled_brk_fn
 };
 
@@ -328,9 +328,9 @@ void kgdb_arch_exit(void)
  */
 struct kgdb_arch arch_kgdb_ops = {
 	.gdb_bpt_instr = {
-		KGDB_DYN_BRK_INS_BYTE0,
-		KGDB_DYN_BRK_INS_BYTE1,
-		KGDB_DYN_BRK_INS_BYTE2,
-		KGDB_DYN_BRK_INS_BYTE3,
+		KGDB_DYN_BRK_INS_BYTE(0),
+		KGDB_DYN_BRK_INS_BYTE(1),
+		KGDB_DYN_BRK_INS_BYTE(2),
+		KGDB_DYN_BRK_INS_BYTE(3),
 	}
 };
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 4095379dc069..b3d098bd34aa 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -38,6 +38,19 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 	return res->start;
 }
 
+/**
+ * pcibios_enable_device - Enable I/O and memory.
+ * @dev: PCI device to be enabled
+ * @mask: bitmask of BARs to enable
+ */
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+	if (pci_has_flag(PCI_PROBE_ONLY))
+		return 0;
+
+	return pci_enable_resources(dev, mask);
+}
+
 /*
  * Try to assign the IRQ number from DT when adding a new device
  */
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
new file mode 100644
index 000000000000..3aa74830cc69
--- /dev/null
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -0,0 +1,196 @@
+/*
+ * arm64 callchain support
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+struct frame_tail {
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail __user *
+user_backtrace(struct frame_tail __user *tail,
+	       struct perf_callchain_entry *entry)
+{
+	struct frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail >= buftail.fp)
+		return NULL;
+
+	return buftail.fp;
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+		      struct perf_callchain_entry *entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs)
+{
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->pc);
+
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+
+		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		       tail && !((unsigned long)tail & 0xf))
+			tail = user_backtrace(tail, entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+			tail && !((unsigned long)tail & 0x3))
+			tail = compat_user_backtrace(tail, entry);
+#endif
+	}
+}
+
+/*
+ * Gets called by walk_stackframe() for every stackframe. This will be called
+ * whist unwinding the stackframe and is like a subroutine return so we use
+ * the PC.
+ */
+static int callchain_trace(struct stackframe *frame, void *data)
+{
+	struct perf_callchain_entry *entry = data;
+	perf_callchain_store(entry, frame->pc);
+	return 0;
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
+{
+	struct stackframe frame;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	frame.fp = regs->regs[29];
+	frame.sp = regs->sp;
+	frame.pc = regs->pc;
+
+	walk_stackframe(&frame, callchain_trace, entry);
+}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+		return perf_guest_cbs->get_guest_ip();
+
+	return instruction_pointer(regs);
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	int misc = 0;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		if (perf_guest_cbs->is_user_mode())
+			misc |= PERF_RECORD_MISC_GUEST_USER;
+		else
+			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (user_mode(regs))
+			misc |= PERF_RECORD_MISC_USER;
+		else
+			misc |= PERF_RECORD_MISC_KERNEL;
+	}
+
+	return misc;
+}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index b31e9a4b6275..f9a74d4fff3b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -25,7 +25,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -36,7 +36,6 @@
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
-#include <asm/stacktrace.h>
 
 /*
  * ARMv8 supports a maximum of 32 events.
@@ -78,6 +77,16 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 
 #define CACHE_OP_UNSUPPORTED		0xFFFF
 
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
+	},								\
+}
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -435,10 +444,8 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 	unsigned int i, irqs;
 	struct platform_device *pmu_device = armpmu->plat_device;
 
-	if (!pmu_device) {
-		pr_err("no PMU device registered\n");
+	if (!pmu_device)
 		return -ENODEV;
-	}
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 	if (!irqs) {
@@ -703,118 +710,28 @@ enum armv8_pmuv3_perf_types {
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 						[PERF_COUNT_HW_CACHE_OP_MAX]
 						[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
@@ -1337,7 +1254,7 @@ static int armpmu_device_probe(struct platform_device *pdev)
 		}
 
 		for_each_possible_cpu(cpu)
-			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
+			if (dn == of_cpu_device_node_get(cpu))
 				break;
 
 		if (cpu >= nr_cpu_ids) {
@@ -1415,180 +1332,3 @@ static int __init init_hw_perf_events(void)
 }
 early_initcall(init_hw_perf_events);
 
-/*
- * Callchain handling code.
- */
-struct frame_tail {
-	struct frame_tail	__user *fp;
-	unsigned long		lr;
-} __attribute__((packed));
-
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry *entry)
-{
-	struct frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail >= buftail.fp)
-		return NULL;
-
-	return buftail.fp;
-}
-
-#ifdef CONFIG_COMPAT
-/*
- * The registers we're interested in are at the end of the variable
- * length saved register structure. The fp points at the end of this
- * structure so the address of this struct is:
- * (struct compat_frame_tail *)(xxx->fp)-1
- *
- * This code has been adapted from the ARM OProfile support.
- */
-struct compat_frame_tail {
-	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
-	u32		sp;
-	u32		lr;
-} __attribute__((packed));
-
-static struct compat_frame_tail __user *
-compat_user_backtrace(struct compat_frame_tail __user *tail,
-		      struct perf_callchain_entry *entry)
-{
-	struct compat_frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail + 1 >= (struct compat_frame_tail __user *)
-			compat_ptr(buftail.fp))
-		return NULL;
-
-	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
-}
-#endif /* CONFIG_COMPAT */
-
-void perf_callchain_user(struct perf_callchain_entry *entry,
-			 struct pt_regs *regs)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
-	perf_callchain_store(entry, regs->pc);
-
-	if (!compat_user_mode(regs)) {
-		/* AARCH64 mode */
-		struct frame_tail __user *tail;
-
-		tail = (struct frame_tail __user *)regs->regs[29];
-
-		while (entry->nr < PERF_MAX_STACK_DEPTH &&
-		       tail && !((unsigned long)tail & 0xf))
-			tail = user_backtrace(tail, entry);
-	} else {
-#ifdef CONFIG_COMPAT
-		/* AARCH32 compat mode */
-		struct compat_frame_tail __user *tail;
-
-		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
-
-		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
-			tail && !((unsigned long)tail & 0x3))
-			tail = compat_user_backtrace(tail, entry);
-#endif
-	}
-}
-
-/*
- * Gets called by walk_stackframe() for every stackframe. This will be called
- * whist unwinding the stackframe and is like a subroutine return so we use
- * the PC.
- */
-static int callchain_trace(struct stackframe *frame, void *data)
-{
-	struct perf_callchain_entry *entry = data;
-	perf_callchain_store(entry, frame->pc);
-	return 0;
-}
-
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
-			   struct pt_regs *regs)
-{
-	struct stackframe frame;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
-	frame.fp = regs->regs[29];
-	frame.sp = regs->sp;
-	frame.pc = regs->pc;
-
-	walk_stackframe(&frame, callchain_trace, entry);
-}
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
-
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
-	int misc = 0;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
-
-	return misc;
-}
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 869f202748e8..aa94a88f6279 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -18,23 +18,17 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
-#include <linux/reboot.h>
-#include <linux/pm.h>
 #include <linux/delay.h>
+#include <linux/psci.h>
 #include <linux/slab.h>
+
 #include <uapi/linux/psci.h>
 
 #include <asm/compiler.h>
-#include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/errno.h>
-#include <asm/psci.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
-#include <asm/system_misc.h>
-
-#define PSCI_POWER_STATE_TYPE_STANDBY		0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
 
 static bool psci_power_state_loses_context(u32 state)
 {
@@ -50,122 +44,8 @@ static bool psci_power_state_is_valid(u32 state)
 	return !(state & ~valid_mask);
 }
 
-/*
- * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF
- * calls to its resident CPU, so we must avoid issuing those. We never migrate
- * a Trusted OS even if it claims to be capable of migration -- doing so will
- * require cooperation with a Trusted OS driver.
- */
-static int resident_cpu = -1;
-
-struct psci_operations {
-	int (*cpu_suspend)(u32 state, unsigned long entry_point);
-	int (*cpu_off)(u32 state);
-	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-	int (*migrate)(unsigned long cpuid);
-	int (*affinity_info)(unsigned long target_affinity,
-			unsigned long lowest_affinity_level);
-	int (*migrate_info_type)(void);
-};
-
-static struct psci_operations psci_ops;
-
-typedef unsigned long (psci_fn)(unsigned long, unsigned long,
-				unsigned long, unsigned long);
-asmlinkage psci_fn __invoke_psci_fn_hvc;
-asmlinkage psci_fn __invoke_psci_fn_smc;
-static psci_fn *invoke_psci_fn;
-
-enum psci_function {
-	PSCI_FN_CPU_SUSPEND,
-	PSCI_FN_CPU_ON,
-	PSCI_FN_CPU_OFF,
-	PSCI_FN_MIGRATE,
-	PSCI_FN_MAX,
-};
-
 static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
 
-static u32 psci_function_id[PSCI_FN_MAX];
-
-static int psci_to_linux_errno(int errno)
-{
-	switch (errno) {
-	case PSCI_RET_SUCCESS:
-		return 0;
-	case PSCI_RET_NOT_SUPPORTED:
-		return -EOPNOTSUPP;
-	case PSCI_RET_INVALID_PARAMS:
-		return -EINVAL;
-	case PSCI_RET_DENIED:
-		return -EPERM;
-	};
-
-	return -EINVAL;
-}
-
-static u32 psci_get_version(void)
-{
-	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
-}
-
-static int psci_cpu_suspend(u32 state, unsigned long entry_point)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
-	err = invoke_psci_fn(fn, state, entry_point, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_cpu_off(u32 state)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_CPU_OFF];
-	err = invoke_psci_fn(fn, state, 0, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_CPU_ON];
-	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_migrate(unsigned long cpuid)
-{
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_MIGRATE];
-	err = invoke_psci_fn(fn, cpuid, 0, 0);
-	return psci_to_linux_errno(err);
-}
-
-static int psci_affinity_info(unsigned long target_affinity,
-		unsigned long lowest_affinity_level)
-{
-	return invoke_psci_fn(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity,
-			      lowest_affinity_level, 0);
-}
-
-static int psci_migrate_info_type(void)
-{
-	return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0);
-}
-
-static unsigned long psci_migrate_info_up_cpu(void)
-{
-	return invoke_psci_fn(PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU, 0, 0, 0);
-}
-
 static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu)
 {
 	int i, ret, count = 0;
@@ -230,240 +110,6 @@ free_mem:
 	return ret;
 }
 
-static int get_set_conduit_method(struct device_node *np)
-{
-	const char *method;
-
-	pr_info("probing for conduit method from DT.\n");
-
-	if (of_property_read_string(np, "method", &method)) {
-		pr_warn("missing \"method\" property\n");
-		return -ENXIO;
-	}
-
-	if (!strcmp("hvc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_hvc;
-	} else if (!strcmp("smc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_smc;
-	} else {
-		pr_warn("invalid \"method\" property: %s\n", method);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
-{
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
-}
-
-static void psci_sys_poweroff(void)
-{
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
-}
-
-/*
- * Detect the presence of a resident Trusted OS which may cause CPU_OFF to
- * return DENIED (which would be fatal).
- */
-static void __init psci_init_migrate(void)
-{
-	unsigned long cpuid;
-	int type, cpu;
-
-	type = psci_ops.migrate_info_type();
-
-	if (type == PSCI_0_2_TOS_MP) {
-		pr_info("Trusted OS migration not required\n");
-		return;
-	}
-
-	if (type == PSCI_RET_NOT_SUPPORTED) {
-		pr_info("MIGRATE_INFO_TYPE not supported.\n");
-		return;
-	}
-
-	if (type != PSCI_0_2_TOS_UP_MIGRATE &&
-	    type != PSCI_0_2_TOS_UP_NO_MIGRATE) {
-		pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type);
-		return;
-	}
-
-	cpuid = psci_migrate_info_up_cpu();
-	if (cpuid & ~MPIDR_HWID_BITMASK) {
-		pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n",
-			cpuid);
-		return;
-	}
-
-	cpu = get_logical_index(cpuid);
-	resident_cpu = cpu >= 0 ? cpu : -1;
-
-	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
-}
-
-static void __init psci_0_2_set_functions(void)
-{
-	pr_info("Using standard PSCI v0.2 function IDs\n");
-	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN64_CPU_SUSPEND;
-	psci_ops.cpu_suspend = psci_cpu_suspend;
-
-	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
-	psci_ops.cpu_off = psci_cpu_off;
-
-	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN64_CPU_ON;
-	psci_ops.cpu_on = psci_cpu_on;
-
-	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE;
-	psci_ops.migrate = psci_migrate;
-
-	psci_ops.affinity_info = psci_affinity_info;
-
-	psci_ops.migrate_info_type = psci_migrate_info_type;
-
-	arm_pm_restart = psci_sys_reset;
-
-	pm_power_off = psci_sys_poweroff;
-}
-
-/*
- * Probe function for PSCI firmware versions >= 0.2
- */
-static int __init psci_probe(void)
-{
-	u32 ver = psci_get_version();
-
-	pr_info("PSCIv%d.%d detected in firmware.\n",
-			PSCI_VERSION_MAJOR(ver),
-			PSCI_VERSION_MINOR(ver));
-
-	if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) {
-		pr_err("Conflicting PSCI version detected.\n");
-		return -EINVAL;
-	}
-
-	psci_0_2_set_functions();
-
-	psci_init_migrate();
-
-	return 0;
-}
-
-typedef int (*psci_initcall_t)(const struct device_node *);
-
-/*
- * PSCI init function for PSCI versions >=0.2
- *
- * Probe based on PSCI PSCI_VERSION function
- */
-static int __init psci_0_2_init(struct device_node *np)
-{
-	int err;
-
-	err = get_set_conduit_method(np);
-
-	if (err)
-		goto out_put_node;
-	/*
-	 * Starting with v0.2, the PSCI specification introduced a call
-	 * (PSCI_VERSION) that allows probing the firmware version, so
-	 * that PSCI function IDs and version specific initialization
-	 * can be carried out according to the specific version reported
-	 * by firmware
-	 */
-	err = psci_probe();
-
-out_put_node:
-	of_node_put(np);
-	return err;
-}
-
-/*
- * PSCI < v0.2 get PSCI Function IDs via DT.
- */
-static int __init psci_0_1_init(struct device_node *np)
-{
-	u32 id;
-	int err;
-
-	err = get_set_conduit_method(np);
-
-	if (err)
-		goto out_put_node;
-
-	pr_info("Using PSCI v0.1 Function IDs from DT\n");
-
-	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
-		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
-		psci_ops.cpu_suspend = psci_cpu_suspend;
-	}
-
-	if (!of_property_read_u32(np, "cpu_off", &id)) {
-		psci_function_id[PSCI_FN_CPU_OFF] = id;
-		psci_ops.cpu_off = psci_cpu_off;
-	}
-
-	if (!of_property_read_u32(np, "cpu_on", &id)) {
-		psci_function_id[PSCI_FN_CPU_ON] = id;
-		psci_ops.cpu_on = psci_cpu_on;
-	}
-
-	if (!of_property_read_u32(np, "migrate", &id)) {
-		psci_function_id[PSCI_FN_MIGRATE] = id;
-		psci_ops.migrate = psci_migrate;
-	}
-
-out_put_node:
-	of_node_put(np);
-	return err;
-}
-
-static const struct of_device_id psci_of_match[] __initconst = {
-	{ .compatible = "arm,psci",	.data = psci_0_1_init},
-	{ .compatible = "arm,psci-0.2",	.data = psci_0_2_init},
-	{},
-};
-
-int __init psci_dt_init(void)
-{
-	struct device_node *np;
-	const struct of_device_id *matched_np;
-	psci_initcall_t init_fn;
-
-	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
-
-	if (!np)
-		return -ENODEV;
-
-	init_fn = (psci_initcall_t)matched_np->data;
-	return init_fn(np);
-}
-
-#ifdef CONFIG_ACPI
-/*
- * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's
- * explicitly clarified in SBBR
- */
-int __init psci_acpi_init(void)
-{
-	if (!acpi_psci_present()) {
-		pr_info("is not implemented in ACPI.\n");
-		return -EOPNOTSUPP;
-	}
-
-	pr_info("probing for conduit method from ACPI.\n");
-
-	if (acpi_psci_use_hvc())
-		invoke_psci_fn = __invoke_psci_fn_hvc;
-	else
-		invoke_psci_fn = __invoke_psci_fn_smc;
-
-	return psci_probe();
-}
-#endif
-
-#ifdef CONFIG_SMP
-
 static int __init cpu_psci_cpu_init(unsigned int cpu)
 {
 	return 0;
@@ -489,11 +135,6 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static bool psci_tos_resident_on(int cpu)
-{
-	return cpu == resident_cpu;
-}
-
 static int cpu_psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
@@ -550,7 +191,6 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	return -ETIMEDOUT;
 }
 #endif
-#endif
 
 static int psci_suspend_finisher(unsigned long index)
 {
@@ -585,7 +225,6 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_init_idle	= cpu_psci_cpu_init_idle,
 	.cpu_suspend	= cpu_psci_cpu_suspend,
 #endif
-#ifdef CONFIG_SMP
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
@@ -594,6 +233,5 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_die	= cpu_psci_cpu_die,
 	.cpu_kill	= cpu_psci_cpu_kill,
 #endif
-#endif
 };
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index d882b833dbdb..1971f491bb90 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -826,6 +826,30 @@ static int compat_vfp_set(struct task_struct *target,
 	return ret;
 }
 
+static int compat_tls_get(struct task_struct *target,
+			  const struct user_regset *regset, unsigned int pos,
+			  unsigned int count, void *kbuf, void __user *ubuf)
+{
+	compat_ulong_t tls = (compat_ulong_t)target->thread.tp_value;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
+}
+
+static int compat_tls_set(struct task_struct *target,
+			  const struct user_regset *regset, unsigned int pos,
+			  unsigned int count, const void *kbuf,
+			  const void __user *ubuf)
+{
+	int ret;
+	compat_ulong_t tls;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
+	if (ret)
+		return ret;
+
+	target->thread.tp_value = tls;
+	return ret;
+}
+
 static const struct user_regset aarch32_regsets[] = {
 	[REGSET_COMPAT_GPR] = {
 		.core_note_type = NT_PRSTATUS,
@@ -850,6 +874,64 @@ static const struct user_regset_view user_aarch32_view = {
 	.regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets)
 };
 
+static const struct user_regset aarch32_ptrace_regsets[] = {
+	[REGSET_GPR] = {
+		.core_note_type = NT_PRSTATUS,
+		.n = COMPAT_ELF_NGREG,
+		.size = sizeof(compat_elf_greg_t),
+		.align = sizeof(compat_elf_greg_t),
+		.get = compat_gpr_get,
+		.set = compat_gpr_set
+	},
+	[REGSET_FPR] = {
+		.core_note_type = NT_ARM_VFP,
+		.n = VFP_STATE_SIZE / sizeof(compat_ulong_t),
+		.size = sizeof(compat_ulong_t),
+		.align = sizeof(compat_ulong_t),
+		.get = compat_vfp_get,
+		.set = compat_vfp_set
+	},
+	[REGSET_TLS] = {
+		.core_note_type = NT_ARM_TLS,
+		.n = 1,
+		.size = sizeof(compat_ulong_t),
+		.align = sizeof(compat_ulong_t),
+		.get = compat_tls_get,
+		.set = compat_tls_set,
+	},
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	[REGSET_HW_BREAK] = {
+		.core_note_type = NT_ARM_HW_BREAK,
+		.n = sizeof(struct user_hwdebug_state) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.get = hw_break_get,
+		.set = hw_break_set,
+	},
+	[REGSET_HW_WATCH] = {
+		.core_note_type = NT_ARM_HW_WATCH,
+		.n = sizeof(struct user_hwdebug_state) / sizeof(u32),
+		.size = sizeof(u32),
+		.align = sizeof(u32),
+		.get = hw_break_get,
+		.set = hw_break_set,
+	},
+#endif
+	[REGSET_SYSTEM_CALL] = {
+		.core_note_type = NT_ARM_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(int),
+		.align = sizeof(int),
+		.get = system_call_get,
+		.set = system_call_set,
+	},
+};
+
+static const struct user_regset_view user_aarch32_ptrace_view = {
+	.name = "aarch32", .e_machine = EM_ARM,
+	.regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets)
+};
+
 static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off,
 				   compat_ulong_t __user *ret)
 {
@@ -1109,8 +1191,16 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_COMPAT
-	if (is_compat_thread(task_thread_info(task)))
+	/*
+	 * Core dumping of 32-bit tasks or compat ptrace requests must use the
+	 * user_aarch32_view compatible with arm32. Native ptrace requests on
+	 * 32-bit children use an extended user_aarch32_ptrace_view to allow
+	 * access to the TLS register.
+	 */
+	if (is_compat_task())
 		return &user_aarch32_view;
+	else if (is_compat_thread(task_thread_info(task)))
+		return &user_aarch32_ptrace_view;
 #endif
 	return &user_aarch64_view;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f3067d4d4e35..888478881243 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -34,7 +34,6 @@
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
 #include <linux/root_dev.h>
-#include <linux/clk-provider.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
 #include <linux/smp.h>
@@ -46,6 +45,7 @@
 #include <linux/of_platform.h>
 #include <linux/efi.h>
 #include <linux/personality.h>
+#include <linux/psci.h>
 
 #include <asm/acpi.h>
 #include <asm/fixmap.h>
@@ -61,9 +61,7 @@
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 #include <asm/memblock.h>
-#include <asm/psci.h>
 #include <asm/efi.h>
-#include <asm/virt.h>
 #include <asm/xen/hypervisor.h>
 
 unsigned long elf_hwcap __read_mostly;
@@ -131,7 +129,6 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 }
 
 struct mpidr_hash mpidr_hash;
-#ifdef CONFIG_SMP
 /**
  * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
  *			  level in order to build a linear index from an
@@ -197,35 +194,11 @@ static void __init smp_build_mpidr_hash(void)
 		pr_warn("Large number of MPIDR hash buckets detected\n");
 	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
 }
-#endif
-
-static void __init hyp_mode_check(void)
-{
-	if (is_hyp_mode_available())
-		pr_info("CPU: All CPU(s) started at EL2\n");
-	else if (is_hyp_mode_mismatched())
-		WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC,
-			   "CPU: CPUs started in inconsistent modes");
-	else
-		pr_info("CPU: All CPU(s) started at EL1\n");
-}
-
-void __init do_post_cpus_up_work(void)
-{
-	hyp_mode_check();
-	apply_alternatives_all();
-}
-
-#ifdef CONFIG_UP_LATE_INIT
-void __init up_late_init(void)
-{
-	do_post_cpus_up_work();
-}
-#endif /* CONFIG_UP_LATE_INIT */
 
 static void __init setup_processor(void)
 {
-	u64 features, block;
+	u64 features;
+	s64 block;
 	u32 cwg;
 	int cls;
 
@@ -255,8 +228,8 @@ static void __init setup_processor(void)
 	 * for non-negative values. Negative values are reserved.
 	 */
 	features = read_cpuid(ID_AA64ISAR0_EL1);
-	block = (features >> 4) & 0xf;
-	if (!(block & 0x8)) {
+	block = cpuid_feature_extract_field(features, 4);
+	if (block > 0) {
 		switch (block) {
 		default:
 		case 2:
@@ -268,26 +241,36 @@ static void __init setup_processor(void)
 		}
 	}
 
-	block = (features >> 8) & 0xf;
-	if (block && !(block & 0x8))
+	if (cpuid_feature_extract_field(features, 8) > 0)
 		elf_hwcap |= HWCAP_SHA1;
 
-	block = (features >> 12) & 0xf;
-	if (block && !(block & 0x8))
+	if (cpuid_feature_extract_field(features, 12) > 0)
 		elf_hwcap |= HWCAP_SHA2;
 
-	block = (features >> 16) & 0xf;
-	if (block && !(block & 0x8))
+	if (cpuid_feature_extract_field(features, 16) > 0)
 		elf_hwcap |= HWCAP_CRC32;
 
+	block = cpuid_feature_extract_field(features, 20);
+	if (block > 0) {
+		switch (block) {
+		default:
+		case 2:
+			elf_hwcap |= HWCAP_ATOMICS;
+		case 1:
+			/* RESERVED */
+		case 0:
+			break;
+		}
+	}
+
 #ifdef CONFIG_COMPAT
 	/*
 	 * ID_ISAR5_EL1 carries similar information as above, but pertaining to
-	 * the Aarch32 32-bit execution state.
+	 * the AArch32 32-bit execution state.
 	 */
 	features = read_cpuid(ID_ISAR5_EL1);
-	block = (features >> 4) & 0xf;
-	if (!(block & 0x8)) {
+	block = cpuid_feature_extract_field(features, 4);
+	if (block > 0) {
 		switch (block) {
 		default:
 		case 2:
@@ -299,16 +282,13 @@ static void __init setup_processor(void)
 		}
 	}
 
-	block = (features >> 8) & 0xf;
-	if (block && !(block & 0x8))
+	if (cpuid_feature_extract_field(features, 8) > 0)
 		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
 
-	block = (features >> 12) & 0xf;
-	if (block && !(block & 0x8))
+	if (cpuid_feature_extract_field(features, 12) > 0)
 		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
 
-	block = (features >> 16) & 0xf;
-	if (block && !(block & 0x8))
+	if (cpuid_feature_extract_field(features, 16) > 0)
 		compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
 #endif
 }
@@ -405,10 +385,8 @@ void __init setup_arch(char **cmdline_p)
 	xen_early_init();
 
 	cpu_read_bootcpu_ops();
-#ifdef CONFIG_SMP
 	smp_init_cpus();
 	smp_build_mpidr_hash();
-#endif
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
@@ -427,8 +405,13 @@ void __init setup_arch(char **cmdline_p)
 
 static int __init arm64_device_init(void)
 {
-	of_iommu_init();
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	if (of_have_populated_dt()) {
+		of_iommu_init();
+		of_platform_populate(NULL, of_default_bus_match_table,
+				     NULL, NULL);
+	} else if (acpi_disabled) {
+		pr_crit("Device tree not populated\n");
+	}
 	return 0;
 }
 arch_initcall_sync(arm64_device_init);
@@ -456,6 +439,7 @@ static const char *hwcap_str[] = {
 	"sha1",
 	"sha2",
 	"crc32",
+	"atomics",
 	NULL
 };
 
@@ -508,9 +492,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * online processors, looking for lines beginning with
 		 * "processor".  Give glibc what it expects.
 		 */
-#ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
-#endif
 
 		/*
 		 * Dump out the common processor features in a single line.
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 1670f15ef69e..948f0ad2de23 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitely for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -201,8 +202,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE))
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 803cfea41962..f586f7c875e2 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -82,7 +82,6 @@ ENTRY(__cpu_suspend_enter)
 	str	x2, [x0, #CPU_CTX_SP]
 	ldr	x1, =sleep_save_sp
 	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
-#ifdef CONFIG_SMP
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
 	ldr	x10, [x9, #MPIDR_HASH_MASK]
@@ -94,7 +93,6 @@ ENTRY(__cpu_suspend_enter)
 	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
 	add	x1, x1, x8, lsl #3
-#endif
 	bl	__cpu_suspend_save
 	/*
 	 * Grab suspend finisher in x20 and its argument in x19
@@ -135,6 +133,14 @@ ENTRY(cpu_resume_mmu)
 	ldr	x3, =cpu_resume_after_mmu
 	msr	sctlr_el1, x0		// restore sctlr_el1
 	isb
+	/*
+	 * Invalidate the local I-cache so that any instructions fetched
+	 * speculatively from the PoC are discarded, since they may have
+	 * been dynamically patched at the PoU.
+	 */
+	ic	iallu
+	dsb	nsh
+	isb
 	br	x3			// global jump to virtual address
 ENDPROC(cpu_resume_mmu)
 	.popsection
@@ -151,7 +157,6 @@ ENDPROC(cpu_resume_after_mmu)
 
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
-#ifdef CONFIG_SMP
 	mrs	x1, mpidr_el1
 	adrp	x8, mpidr_hash
 	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
@@ -161,9 +166,6 @@ ENTRY(cpu_resume)
 	ldp	w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
         /* x7 contains hash index, let's use it to grab context pointer */
-#else
-	mov	x7, xzr
-#endif
 	ldr_l	x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 695801a54ca5..dbdaacddd9a5 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -52,6 +52,7 @@
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
+#include <asm/virt.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
@@ -310,10 +311,22 @@ void cpu_die(void)
 }
 #endif
 
+static void __init hyp_mode_check(void)
+{
+	if (is_hyp_mode_available())
+		pr_info("CPU: All CPU(s) started at EL2\n");
+	else if (is_hyp_mode_mismatched())
+		WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC,
+			   "CPU: CPUs started in inconsistent modes");
+	else
+		pr_info("CPU: All CPU(s) started at EL1\n");
+}
+
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
-	do_post_cpus_up_work();
+	hyp_mode_check();
+	apply_alternatives_all();
 }
 
 void __init smp_prepare_boot_cpu(void)
@@ -438,7 +451,7 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
 	struct acpi_madt_generic_interrupt *processor;
 
 	processor = (struct acpi_madt_generic_interrupt *)header;
-	if (BAD_MADT_ENTRY(processor, end))
+	if (BAD_MADT_GICC_ENTRY(processor, end))
 		return -EINVAL;
 
 	acpi_table_print_madt_entry(header);
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 42f9195cf2f8..149151fb42bb 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -42,7 +42,6 @@
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
 
-#ifdef CONFIG_SMP
 unsigned long profile_pc(struct pt_regs *regs)
 {
 	struct stackframe frame;
@@ -62,7 +61,6 @@ unsigned long profile_pc(struct pt_regs *regs)
 	return frame.pc;
 }
 EXPORT_SYMBOL(profile_pc);
-#endif
 
 void __init time_init(void)
 {
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index fcb8f7b42271..694f6deedbab 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -300,6 +300,6 @@ void __init init_cpu_topology(void)
 	 * Discard anything that was parsed if we hit an error so we
 	 * don't use partial information.
 	 */
-	if (parse_dt_topology())
+	if (of_have_populated_dt() && parse_dt_topology())
 		reset_cpu_topology();
 }
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 566bc4c35040..f93aae5e4307 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bug.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
@@ -32,8 +33,10 @@
 #include <linux/syscalls.h>
 
 #include <asm/atomic.h>
+#include <asm/bug.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
+#include <asm/insn.h>
 #include <asm/traps.h>
 #include <asm/stacktrace.h>
 #include <asm/exception.h>
@@ -52,11 +55,12 @@ int show_unhandled_signals = 1;
  * Dump out the contents of some memory nicely...
  */
 static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
-		     unsigned long top)
+		     unsigned long top, bool compat)
 {
 	unsigned long first;
 	mm_segment_t fs;
 	int i;
+	unsigned int width = compat ? 4 : 8;
 
 	/*
 	 * We need to switch to kernel mode so that we can use __get_user
@@ -75,13 +79,22 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 		memset(str, ' ', sizeof(str));
 		str[sizeof(str) - 1] = '\0';
 
-		for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
+		for (p = first, i = 0; i < (32 / width)
+					&& p < top; i++, p += width) {
 			if (p >= bottom && p < top) {
-				unsigned int val;
-				if (__get_user(val, (unsigned int *)p) == 0)
-					sprintf(str + i * 9, " %08x", val);
-				else
-					sprintf(str + i * 9, " ????????");
+				unsigned long val;
+
+				if (width == 8) {
+					if (__get_user(val, (unsigned long *)p) == 0)
+						sprintf(str + i * 17, " %016lx", val);
+					else
+						sprintf(str + i * 17, " ????????????????");
+				} else {
+					if (__get_user(val, (unsigned int *)p) == 0)
+						sprintf(str + i * 9, " %08lx", val);
+					else
+						sprintf(str + i * 9, " ????????");
+				}
 			}
 		}
 		printk("%s%04lx:%s\n", lvl, first & 0xffff, str);
@@ -95,7 +108,7 @@ static void dump_backtrace_entry(unsigned long where, unsigned long stack)
 	print_ip_sym(where);
 	if (in_exception_text(where))
 		dump_mem("", "Exception stack", stack,
-			 stack + sizeof(struct pt_regs));
+			 stack + sizeof(struct pt_regs), false);
 }
 
 static void dump_instr(const char *lvl, struct pt_regs *regs)
@@ -179,11 +192,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #else
 #define S_PREEMPT ""
 #endif
-#ifdef CONFIG_SMP
 #define S_SMP " SMP"
-#else
-#define S_SMP ""
-#endif
 
 static int __die(const char *str, int err, struct thread_info *thread,
 		 struct pt_regs *regs)
@@ -207,7 +216,8 @@ static int __die(const char *str, int err, struct thread_info *thread,
 
 	if (!user_mode(regs) || in_interrupt()) {
 		dump_mem(KERN_EMERG, "Stack: ", regs->sp,
-			 THREAD_SIZE + (unsigned long)task_stack_page(tsk));
+			 THREAD_SIZE + (unsigned long)task_stack_page(tsk),
+			 compat_user_mode(regs));
 		dump_backtrace(regs, tsk);
 		dump_instr(KERN_EMERG, regs);
 	}
@@ -459,7 +469,63 @@ void __pgd_error(const char *file, int line, unsigned long val)
 	pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val);
 }
 
+/* GENERIC_BUG traps */
+
+int is_valid_bugaddr(unsigned long addr)
+{
+	/*
+	 * bug_handler() only called for BRK #BUG_BRK_IMM.
+	 * So the answer is trivial -- any spurious instances with no
+	 * bug table entry will be rejected by report_bug() and passed
+	 * back to the debug-monitors code and handled as a fatal
+	 * unexpected debug exception.
+	 */
+	return 1;
+}
+
+static int bug_handler(struct pt_regs *regs, unsigned int esr)
+{
+	if (user_mode(regs))
+		return DBG_HOOK_ERROR;
+
+	switch (report_bug(regs->pc, regs)) {
+	case BUG_TRAP_TYPE_BUG:
+		die("Oops - BUG", regs, 0);
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		/* Ideally, report_bug() should backtrace for us... but no. */
+		dump_backtrace(regs, NULL);
+		break;
+
+	default:
+		/* unknown/unrecognised bug trap type */
+		return DBG_HOOK_ERROR;
+	}
+
+	/* If thread survives, skip over the BUG instruction and continue: */
+	regs->pc += AARCH64_INSN_SIZE;	/* skip BRK and resume */
+	return DBG_HOOK_HANDLED;
+}
+
+static struct break_hook bug_break_hook = {
+	.esr_val = 0xf2000000 | BUG_BRK_IMM,
+	.esr_mask = 0xffffffff,
+	.fn = bug_handler,
+};
+
+/*
+ * Initial handler for AArch64 BRK exceptions
+ * This handler only used until debug_traps_init().
+ */
+int __init early_brk64(unsigned long addr, unsigned int esr,
+		struct pt_regs *regs)
+{
+	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
+}
+
+/* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
-	return;
+	register_break_hook(&bug_break_hook);
 }
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index ec37ab3f524f..97bc68f4c689 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -199,16 +199,15 @@ up_fail:
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->use_syscall			= use_syscall;
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift;
 	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 17a8fb14f428..10915aaf0b01 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -810,7 +810,11 @@
  * Call into the vgic backend for state saving
  */
 .macro save_vgic_state
-	alternative_insn "bl __save_vgic_v2_state", "bl __save_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+	bl	__save_vgic_v2_state
+alternative_else
+	bl	__save_vgic_v3_state
+alternative_endif
 	mrs	x24, hcr_el2
 	mov	x25, #HCR_INT_OVERRIDE
 	neg	x25, x25
@@ -827,7 +831,11 @@
 	orr	x24, x24, #HCR_INT_OVERRIDE
 	orr	x24, x24, x25
 	msr	hcr_el2, x24
-	alternative_insn "bl __restore_vgic_v2_state", "bl __restore_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+	bl	__restore_vgic_v2_state
+alternative_else
+	bl	__restore_vgic_v3_state
+alternative_endif
 .endm
 
 .macro save_timer_state
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index f02530e726f6..85c57158dcd9 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -168,8 +168,8 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
 		inject_abt32(vcpu, false, addr);
-
-	inject_abt64(vcpu, false, addr);
+	else
+		inject_abt64(vcpu, false, addr);
 }
 
 /**
@@ -184,8 +184,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
 		inject_abt32(vcpu, true, addr);
-
-	inject_abt64(vcpu, true, addr);
+	else
+		inject_abt64(vcpu, true, addr);
 }
 
 /**
@@ -198,6 +198,6 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
 		inject_undef32(vcpu);
-
-	inject_undef64(vcpu);
+	else
+		inject_undef64(vcpu);
 }
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index d98d3e39879e..1a811ecf71da 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -3,3 +3,16 @@ lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
 		   strchr.o strrchr.o
+
+# Tell the compiler to treat all general purpose registers as
+# callee-saved, which allows for efficient runtime patching of the bl
+# instruction in the caller with an atomic instruction when supported by
+# the CPU. Result and argument registers are handled correctly, based on
+# the function prototype.
+lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
+CFLAGS_atomic_ll_sc.o	:= -fcall-used-x0 -ffixed-x1 -ffixed-x2		\
+		   -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6		\
+		   -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9		\
+		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\
+		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
+		   -fcall-saved-x16 -fcall-saved-x17 -fcall-saved-x18
diff --git a/arch/arm64/lib/atomic_ll_sc.c b/arch/arm64/lib/atomic_ll_sc.c
new file mode 100644
index 000000000000..b0c538b0da28
--- /dev/null
+++ b/arch/arm64/lib/atomic_ll_sc.c
@@ -0,0 +1,3 @@
+#include <asm/atomic.h>
+#define __ARM64_IN_ATOMIC_IMPL
+#include <asm/atomic_ll_sc.h>
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
index 7dac371cc9a2..43ac736baa5b 100644
--- a/arch/arm64/lib/bitops.S
+++ b/arch/arm64/lib/bitops.S
@@ -18,52 +18,59 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/lse.h>
 
 /*
  * x0: bits 5:0  bit offset
  *     bits 31:6 word offset
  * x1: address
  */
-	.macro	bitop, name, instr
+	.macro	bitop, name, llsc, lse
 ENTRY(	\name	)
 	and	w3, w0, #63		// Get bit offset
 	eor	w0, w0, w3		// Clear low bits
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
+alt_lse "	prfm	pstl1strm, [x1]",	"nop"
 	lsl	x3, x2, x3		// Create mask
-1:	ldxr	x2, [x1]
-	\instr	x2, x2, x3
-	stxr	w0, x2, [x1]
-	cbnz	w0, 1b
+
+alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
+alt_lse	"	\llsc	x2, x2, x3",		"nop"
+alt_lse	"	stxr	w0, x2, [x1]",		"nop"
+alt_lse	"	cbnz	w0, 1b",		"nop"
+
 	ret
 ENDPROC(\name	)
 	.endm
 
-	.macro	testop, name, instr
+	.macro	testop, name, llsc, lse
 ENTRY(	\name	)
 	and	w3, w0, #63		// Get bit offset
 	eor	w0, w0, w3		// Clear low bits
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
+alt_lse "	prfm	pstl1strm, [x1]",	"nop"
 	lsl	x4, x2, x3		// Create mask
-1:	ldxr	x2, [x1]
-	lsr	x0, x2, x3		// Save old value of bit
-	\instr	x2, x2, x4		// toggle bit
-	stlxr	w5, x2, [x1]
-	cbnz	w5, 1b
-	dmb	ish
+
+alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"
+	lsr	x0, x2, x3
+alt_lse	"	\llsc	x2, x2, x4",		"nop"
+alt_lse	"	stlxr	w5, x2, [x1]",		"nop"
+alt_lse	"	cbnz	w5, 1b",		"nop"
+alt_lse	"	dmb	ish",			"nop"
+
 	and	x0, x0, #1
-3:	ret
+	ret
 ENDPROC(\name	)
 	.endm
 
 /*
  * Atomic bit operations.
  */
-	bitop	change_bit, eor
-	bitop	clear_bit, bic
-	bitop	set_bit, orr
+	bitop	change_bit, eor, steor
+	bitop	clear_bit, bic, stclr
+	bitop	set_bit, orr, stset
 
-	testop	test_and_change_bit, eor
-	testop	test_and_clear_bit, bic
-	testop	test_and_set_bit, orr
+	testop	test_and_change_bit, eor, ldeoral
+	testop	test_and_clear_bit, bic, ldclral
+	testop	test_and_set_bit, orr, ldsetal
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index c17967fdf5f6..a9723c71c52b 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -16,7 +16,11 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 	.text
 
@@ -29,6 +33,8 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__clear_user)
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -48,6 +54,8 @@ USER(9f, strh	wzr, [x0], #2	)
 	b.mi	5f
 USER(9f, strb	wzr, [x0]	)
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__clear_user)
 
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 5e27add9d362..1be9ef27be97 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -15,7 +15,11 @@
  */
 
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
@@ -28,14 +32,21 @@
  *	x0 - bytes not copied
  */
 ENTRY(__copy_from_user)
-	add	x4, x1, x2			// upper user buffer boundary
-	subs	x2, x2, #8
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
+	add	x5, x1, x2			// upper user buffer boundary
+	subs	x2, x2, #16
+	b.mi	1f
+0:
+USER(9f, ldp	x3, x4, [x1], #16)
+	subs	x2, x2, #16
+	stp	x3, x4, [x0], #16
+	b.pl	0b
+1:	adds	x2, x2, #8
 	b.mi	2f
-1:
 USER(9f, ldr	x3, [x1], #8	)
-	subs	x2, x2, #8
+	sub	x2, x2, #8
 	str	x3, [x0], #8
-	b.pl	1b
 2:	adds	x2, x2, #4
 	b.mi	3f
 USER(9f, ldr	w3, [x1], #4	)
@@ -51,12 +62,14 @@ USER(9f, ldrh	w3, [x1], #2	)
 USER(9f, ldrb	w3, [x1]	)
 	strb	w3, [x0]
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__copy_from_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x2, x4, x1
+9:	sub	x2, x5, x1
 	mov	x3, x2
 10:	strb	wzr, [x0], #1			// zero remaining buffer space
 	subs	x3, x3, #1
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 84b6c9bb9b93..1b94661e22b3 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -17,7 +17,11 @@
  */
 
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
@@ -30,14 +34,21 @@
  *	x0 - bytes not copied
  */
 ENTRY(__copy_in_user)
-	add	x4, x0, x2			// upper user buffer boundary
-	subs	x2, x2, #8
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
+	add	x5, x0, x2			// upper user buffer boundary
+	subs	x2, x2, #16
+	b.mi	1f
+0:
+USER(9f, ldp	x3, x4, [x1], #16)
+	subs	x2, x2, #16
+USER(9f, stp	x3, x4, [x0], #16)
+	b.pl	0b
+1:	adds	x2, x2, #8
 	b.mi	2f
-1:
 USER(9f, ldr	x3, [x1], #8	)
-	subs	x2, x2, #8
+	sub	x2, x2, #8
 USER(9f, str	x3, [x0], #8	)
-	b.pl	1b
 2:	adds	x2, x2, #4
 	b.mi	3f
 USER(9f, ldr	w3, [x1], #4	)
@@ -53,11 +64,13 @@ USER(9f, strh	w3, [x0], #2	)
 USER(9f, ldrb	w3, [x1]	)
 USER(9f, strb	w3, [x0]	)
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__copy_in_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x0, x4, x0			// bytes not copied
+9:	sub	x0, x5, x0			// bytes not copied
 	ret
 	.previous
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index a0aeeb9b7a28..a257b47e2dc4 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -15,7 +15,11 @@
  */
 
 #include <linux/linkage.h>
+
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
@@ -28,14 +32,21 @@
  *	x0 - bytes not copied
  */
 ENTRY(__copy_to_user)
-	add	x4, x0, x2			// upper user buffer boundary
-	subs	x2, x2, #8
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
+	add	x5, x0, x2			// upper user buffer boundary
+	subs	x2, x2, #16
+	b.mi	1f
+0:
+	ldp	x3, x4, [x1], #16
+	subs	x2, x2, #16
+USER(9f, stp	x3, x4, [x0], #16)
+	b.pl	0b
+1:	adds	x2, x2, #8
 	b.mi	2f
-1:
 	ldr	x3, [x1], #8
-	subs	x2, x2, #8
+	sub	x2, x2, #8
 USER(9f, str	x3, [x0], #8	)
-	b.pl	1b
 2:	adds	x2, x2, #4
 	b.mi	3f
 	ldr	w3, [x1], #4
@@ -51,11 +62,13 @@ USER(9f, strh	w3, [x0], #2	)
 	ldrb	w3, [x1]
 USER(9f, strb	w3, [x0]	)
 5:	mov	x0, #0
+ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
+	    CONFIG_ARM64_PAN)
 	ret
 ENDPROC(__copy_to_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	sub	x0, x4, x0			// bytes not copied
+9:	sub	x0, x5, x0			// bytes not copied
 	ret
 	.previous
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 9d84feb41a16..773d37a14039 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,5 +4,3 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
-
-CFLAGS_mmu.o			:= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index bdeb5d38c2dd..eb48d5df4a0f 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -143,7 +143,12 @@ __dma_clean_range:
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x0, x0, x3
-1:	alternative_insn "dc cvac, x0", "dc civac, x0", ARM64_WORKAROUND_CLEAN_CACHE
+1:
+alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
+	dc	cvac, x0
+alternative_else
+	dc	civac, x0
+alternative_endif
 	add	x0, x0, x2
 	cmp	x0, x1
 	b.lo	1b
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 76c1e6cd36fc..d70ff14dbdbd 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -53,8 +53,6 @@ static void flush_context(void)
 		__flush_icache_all();
 }
 
-#ifdef CONFIG_SMP
-
 static void set_mm_context(struct mm_struct *mm, unsigned int asid)
 {
 	unsigned long flags;
@@ -110,23 +108,12 @@ static void reset_context(void *info)
 	cpu_switch_mm(mm->pgd, mm);
 }
 
-#else
-
-static inline void set_mm_context(struct mm_struct *mm, unsigned int asid)
-{
-	mm->context.id = asid;
-	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
-}
-
-#endif
-
 void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 	unsigned int bits = asid_bits();
 
 	raw_spin_lock(&cpu_asid_lock);
-#ifdef CONFIG_SMP
 	/*
 	 * Check the ASID again, in case the change was broadcast from another
 	 * CPU before we acquired the lock.
@@ -136,7 +123,6 @@ void __new_context(struct mm_struct *mm)
 		raw_spin_unlock(&cpu_asid_lock);
 		return;
 	}
-#endif
 	/*
 	 * At this point, it is guaranteed that the current mm (with an old
 	 * ASID) isn't active on any other CPU since the ASIDs are changed
@@ -155,10 +141,8 @@ void __new_context(struct mm_struct *mm)
 			cpu_last_asid = ASID_FIRST_VERSION;
 		asid = cpu_last_asid + smp_processor_id();
 		flush_context();
-#ifdef CONFIG_SMP
 		smp_wmb();
 		smp_call_function(reset_context, NULL, 1);
-#endif
 		cpu_last_asid += NR_CPUS - 1;
 	}
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index d16a1cead23f..0bcc4bc94b4a 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -144,6 +144,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	struct page *page;
 	void *ptr, *coherent_ptr;
 	bool coherent = is_device_dma_coherent(dev);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);
 
 	size = PAGE_ALIGN(size);
 
@@ -171,9 +172,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
 	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
-				__get_dma_pgprot(attrs,
-					__pgprot(PROT_NORMAL_NC), false),
-					NULL);
+						   prot, NULL);
 	if (!coherent_ptr)
 		goto no_map;
 
@@ -303,9 +302,10 @@ static void __swiotlb_sync_sg_for_device(struct device *dev,
 				       sg->length, dir);
 }
 
-/* vma->vm_page_prot must be set appropriately before calling this function */
-static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			     void *cpu_addr, dma_addr_t dma_addr, size_t size)
+static int __swiotlb_mmap(struct device *dev,
+			  struct vm_area_struct *vma,
+			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			  struct dma_attrs *attrs)
 {
 	int ret = -ENXIO;
 	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
@@ -314,6 +314,9 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+					     is_device_dma_coherent(dev));
+
 	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
@@ -327,20 +330,24 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
-static int __swiotlb_mmap(struct device *dev,
-			  struct vm_area_struct *vma,
-			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			  struct dma_attrs *attrs)
+static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+				 void *cpu_addr, dma_addr_t handle, size_t size,
+				 struct dma_attrs *attrs)
 {
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
-					     is_device_dma_coherent(dev));
-	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+	int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+
+	if (!ret)
+		sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)),
+			    PAGE_ALIGN(size), 0);
+
+	return ret;
 }
 
 static struct dma_map_ops swiotlb_dma_ops = {
 	.alloc = __dma_alloc,
 	.free = __dma_free,
 	.mmap = __swiotlb_mmap,
+	.get_sgtable = __swiotlb_get_sgtable,
 	.map_page = __swiotlb_map_page,
 	.unmap_page = __swiotlb_unmap_page,
 	.map_sg = __swiotlb_map_sg_attrs,
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 94d98cd1aad8..aba9ead1384c 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -30,9 +30,11 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
+#include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
+#include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -224,6 +226,13 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	}
 
 	/*
+	 * PAN bit set implies the fault happened in kernel space, but not
+	 * in the arch's user access functions.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT))
+		goto no_context;
+
+	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
 	 * we can bug out early if this is from code which shouldn't.
@@ -492,14 +501,22 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
 }
 
-static struct fault_info debug_fault_info[] = {
+int __init early_brk64(unsigned long addr, unsigned int esr,
+		       struct pt_regs *regs);
+
+/*
+ * __refdata because early_brk64 is __init, but the reference to it is
+ * clobbered at arch_initcall time.
+ * See traps.c and debug-monitors.c:debug_traps_init().
+ */
+static struct fault_info __refdata debug_fault_info[] = {
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
 	{ do_bad,	SIGBUS,		0,		"unknown 3"		},
 	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
 	{ do_bad,	SIGTRAP,	0,		"aarch32 vector catch"	},
-	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
+	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
 	{ do_bad,	SIGBUS,		0,		"unknown 7"		},
 };
 
@@ -536,3 +553,10 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 
 	return 0;
 }
+
+#ifdef CONFIG_ARM64_PAN
+void cpu_enable_pan(void)
+{
+	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+}
+#endif /* CONFIG_ARM64_PAN */
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 4dfa3975ce5b..c26b804015e8 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -60,14 +60,10 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long uaddr, void *dst, const void *src,
 		       unsigned long len)
 {
-#ifdef CONFIG_SMP
 	preempt_disable();
-#endif
 	memcpy(dst, src, len);
 	flush_ptrace_access(vma, page, uaddr, dst, len);
-#ifdef CONFIG_SMP
 	preempt_enable();
-#endif
 }
 
 void __sync_icache_dcache(pte_t pte, unsigned long addr)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 831ec534d449..383b03ff38f8 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -13,10 +13,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #include <linux/init.h>
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index ad87ce826cce..f5c0680d17d9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -358,9 +358,9 @@ void free_initmem(void)
 
 #ifdef CONFIG_BLK_DEV_INITRD
 
-static int keep_initrd;
+static int keep_initrd __initdata;
 
-void free_initrd_mem(unsigned long start, unsigned long end)
+void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd)
 		free_reserved_area((void *)start, (void *)end, 0, "initrd");
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a4ede4e2ddd1..9211b8527f25 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -267,7 +267,7 @@ static void *late_alloc(unsigned long size)
 	return ptr;
 }
 
-static void __ref create_mapping(phys_addr_t phys, unsigned long virt,
+static void __init create_mapping(phys_addr_t phys, unsigned long virt,
 				  phys_addr_t size, pgprot_t prot)
 {
 	if (virt < VMALLOC_START) {
@@ -461,17 +461,6 @@ void __init paging_init(void)
 }
 
 /*
- * Enable the identity mapping to allow the MMU disabling.
- */
-void setup_mm_for_reboot(void)
-{
-	cpu_set_reserved_ttbr0();
-	flush_tlb_all();
-	cpu_set_idmap_tcr_t0sz();
-	cpu_switch_mm(idmap_pg_dir, &init_mm);
-}
-
-/*
  * Check whether a kernel address is valid (derived from arch/x86/).
  */
 int kern_addr_valid(unsigned long addr)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 39139a3aa16d..e4ee7bd8830a 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -34,11 +34,7 @@
 #define TCR_TG_FLAGS	TCR_TG0_4K | TCR_TG1_4K
 #endif
 
-#ifdef CONFIG_SMP
 #define TCR_SMP_FLAGS	TCR_SHARED
-#else
-#define TCR_SMP_FLAGS	0
-#endif
 
 /* PTWs cacheable, inner/outer WBWA */
 #define TCR_CACHE_FLAGS	TCR_IRGN_WBWA | TCR_ORGN_WBWA
@@ -150,13 +146,13 @@ ENDPROC(cpu_do_switch_mm)
  *	value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-	ic	iallu				// I+BTB cache invalidate
 	tlbi	vmalle1is			// invalidate I + D TLBs
 	dsb	ish
 
 	mov	x0, #3 << 20
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
-	msr	mdscr_el1, xzr			// Reset mdscr_el1
+	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
+	msr	mdscr_el1, x0			// access to the DCC from EL0
 	/*
 	 * Memory region attributes for LPAE:
 	 *
@@ -196,6 +192,19 @@ ENTRY(__cpu_setup)
 	 */
 	mrs	x9, ID_AA64MMFR0_EL1
 	bfi	x10, x9, #32, #3
+#ifdef CONFIG_ARM64_HW_AFDBM
+	/*
+	 * Hardware update of the Access and Dirty bits.
+	 */
+	mrs	x9, ID_AA64MMFR1_EL1
+	and	x9, x9, #0xf
+	cbz	x9, 2f
+	cmp	x9, #2
+	b.lt	1f
+	orr	x10, x10, #TCR_HD		// hardware Dirty flag update
+1:	orr	x10, x10, #TCR_HA		// hardware Access flag update
+2:
+#endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
 	ret					// return to head.S
 ENDPROC(__cpu_setup)
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 1d66afdfac07..f61f2dd67464 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index 2d07ce1c5327..97c9bdf83409 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -44,6 +44,18 @@ static inline int __atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OP_RETURN(sub, sub, rKs21)
 ATOMIC_OP_RETURN(add, add, r)
 
+#define ATOMIC_OP(op, asm_op)						\
+ATOMIC_OP_RETURN(op, asm_op, r)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	(void)__atomic_##op##_return(i, v);				\
+}
+
+ATOMIC_OP(and, and)
+ATOMIC_OP(or, or)
+ATOMIC_OP(xor, eor)
+
+#undef ATOMIC_OP
 #undef ATOMIC_OP_RETURN
 
 /*
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index e998ff5d8e1a..f855646e0db7 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -297,6 +297,7 @@ extern void __iounmap(void __iomem *addr);
 
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 #define cached(addr) P1SEGADDR(addr)
 #define uncached(addr) P2SEGADDR(addr)
diff --git a/arch/avr32/include/asm/mm-arch-hooks.h b/arch/avr32/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 145452ffbdad..000000000000
--- a/arch/avr32/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_AVR32_MM_ARCH_HOOKS_H
-#define _ASM_AVR32_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_AVR32_MM_ARCH_HOOKS_H */
diff --git a/arch/avr32/include/asm/switch_to.h b/arch/avr32/include/asm/switch_to.h
index 9a8e9d5208d4..6f00581c3d4f 100644
--- a/arch/avr32/include/asm/switch_to.h
+++ b/arch/avr32/include/asm/switch_to.h
@@ -15,11 +15,13 @@
  */
 #ifdef CONFIG_OWNERSHIP_TRACE
 #include <asm/ocd.h>
-#define finish_arch_switch(prev)			\
+#define ocd_switch(prev, next)				\
 	do {						\
 		ocd_write(PID, prev->pid);		\
-		ocd_write(PID, current->pid);		\
+		ocd_write(PID, next->pid);		\
 	} while(0)
+#else
+#define ocd_switch(prev, next)
 #endif
 
 /*
@@ -38,6 +40,7 @@ extern struct task_struct *__switch_to(struct task_struct *,
 				       struct cpu_context *);
 #define switch_to(prev, next, last)					\
 	do {								\
+		ocd_switch(prev, next);					\
 		last = __switch_to(prev, &prev->thread.cpu_context + 1,	\
 				   &next->thread.cpu_context);		\
 	} while (0)
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index d0f771be9e96..a124c55733db 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -18,6 +18,7 @@
 
 #include <mach/pm.h>
 
+static bool disable_cpu_idle_poll;
 
 static cycle_t read_cycle_count(struct clocksource *cs)
 {
@@ -80,45 +81,45 @@ static int comparator_next_event(unsigned long delta,
 	return 0;
 }
 
-static void comparator_mode(enum clock_event_mode mode,
-		struct clock_event_device *evdev)
+static int comparator_shutdown(struct clock_event_device *evdev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		pr_debug("%s: start\n", evdev->name);
-		/* FALLTHROUGH */
-	case CLOCK_EVT_MODE_RESUME:
+	pr_debug("%s: %s\n", __func__, evdev->name);
+	sysreg_write(COMPARE, 0);
+
+	if (disable_cpu_idle_poll) {
+		disable_cpu_idle_poll = false;
 		/*
-		 * If we're using the COUNT and COMPARE registers we
-		 * need to force idle poll.
+		 * Only disable idle poll if we have forced that
+		 * in a previous call.
 		 */
-		cpu_idle_poll_ctrl(true);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		sysreg_write(COMPARE, 0);
-		pr_debug("%s: stop\n", evdev->name);
-		if (evdev->mode == CLOCK_EVT_MODE_ONESHOT ||
-		    evdev->mode == CLOCK_EVT_MODE_RESUME) {
-			/*
-			 * Only disable idle poll if we have forced that
-			 * in a previous call.
-			 */
-			cpu_idle_poll_ctrl(false);
-		}
-		break;
-	default:
-		BUG();
+		cpu_idle_poll_ctrl(false);
 	}
+	return 0;
+}
+
+static int comparator_set_oneshot(struct clock_event_device *evdev)
+{
+	pr_debug("%s: %s\n", __func__, evdev->name);
+
+	disable_cpu_idle_poll = true;
+	/*
+	 * If we're using the COUNT and COMPARE registers we
+	 * need to force idle poll.
+	 */
+	cpu_idle_poll_ctrl(true);
+
+	return 0;
 }
 
 static struct clock_event_device comparator = {
-	.name		= "avr32_comparator",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.shift		= 16,
-	.rating		= 50,
-	.set_next_event	= comparator_next_event,
-	.set_mode	= comparator_mode,
+	.name			= "avr32_comparator",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.shift			= 16,
+	.rating			= 50,
+	.set_next_event		= comparator_next_event,
+	.set_state_shutdown	= comparator_shutdown,
+	.set_state_oneshot	= comparator_set_oneshot,
+	.tick_resume		= comparator_set_oneshot,
 };
 
 void read_persistent_clock(struct timespec *ts)
diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c
index 23b1a97fae7a..52c179bec0cc 100644
--- a/arch/avr32/mach-at32ap/clock.c
+++ b/arch/avr32/mach-at32ap/clock.c
@@ -80,6 +80,9 @@ int clk_enable(struct clk *clk)
 {
 	unsigned long flags;
 
+	if (!clk)
+		return 0;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	__clk_enable(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -106,6 +109,9 @@ void clk_disable(struct clk *clk)
 {
 	unsigned long flags;
 
+	if (IS_ERR_OR_NULL(clk))
+		return;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	__clk_disable(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -117,6 +123,9 @@ unsigned long clk_get_rate(struct clk *clk)
 	unsigned long flags;
 	unsigned long rate;
 
+	if (!clk)
+		return 0;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	rate = clk->get_rate(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -129,6 +138,9 @@ long clk_round_rate(struct clk *clk, unsigned long rate)
 {
 	unsigned long flags, actual_rate;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_rate)
 		return -ENOSYS;
 
@@ -145,6 +157,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 	unsigned long flags;
 	long ret;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_rate)
 		return -ENOSYS;
 
@@ -161,6 +176,9 @@ int clk_set_parent(struct clk *clk, struct clk *parent)
 	unsigned long flags;
 	int ret;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_parent)
 		return -ENOSYS;
 
@@ -174,7 +192,7 @@ EXPORT_SYMBOL(clk_set_parent);
 
 struct clk *clk_get_parent(struct clk *clk)
 {
-	return clk->parent;
+	return !clk ? NULL : clk->parent;
 }
 EXPORT_SYMBOL(clk_get_parent);
 
diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c
index 2d48b6a46166..d51ff8f1c541 100644
--- a/arch/avr32/mach-at32ap/extint.c
+++ b/arch/avr32/mach-at32ap/extint.c
@@ -128,9 +128,9 @@ static int eic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 
 	irqd_set_trigger_type(d, flow_type);
 	if (flow_type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
-		__irq_set_handler_locked(irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 	else
-		__irq_set_handler_locked(irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 
 	return IRQ_SET_MASK_OK_NOCOPY;
 }
diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c
index 903c7d81d0d5..157a5e0e789f 100644
--- a/arch/avr32/mach-at32ap/pio.c
+++ b/arch/avr32/mach-at32ap/pio.c
@@ -286,7 +286,7 @@ static void gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 	struct pio_device	*pio = irq_desc_get_chip_data(desc);
 	unsigned		gpio_irq;
 
-	gpio_irq = (unsigned) irq_get_handler_data(irq);
+	gpio_irq = (unsigned) irq_desc_get_handler_data(desc);
 	for (;;) {
 		u32		isr;
 
@@ -312,7 +312,6 @@ gpio_irq_setup(struct pio_device *pio, int irq, int gpio_irq)
 	unsigned	i;
 
 	irq_set_chip_data(irq, pio);
-	irq_set_handler_data(irq, (void *)gpio_irq);
 
 	for (i = 0; i < 32; i++, gpio_irq++) {
 		irq_set_chip_data(gpio_irq, pio);
@@ -320,7 +319,8 @@ gpio_irq_setup(struct pio_device *pio, int irq, int gpio_irq)
 					 handle_simple_irq);
 	}
 
-	irq_set_chained_handler(irq, gpio_irq_handler);
+	irq_set_chained_handler_and_data(irq, gpio_irq_handler,
+					 (void *)gpio_irq);
 }
 
 /*--------------------------------------------------------------------------*/
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 07051a63415d..61cd1e786a14 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -21,6 +21,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
diff --git a/arch/blackfin/include/asm/atomic.h b/arch/blackfin/include/asm/atomic.h
index a107a98e9978..1c1c42330c99 100644
--- a/arch/blackfin/include/asm/atomic.h
+++ b/arch/blackfin/include/asm/atomic.h
@@ -16,19 +16,21 @@
 #include <linux/types.h>
 
 asmlinkage int __raw_uncached_fetch_asm(const volatile int *ptr);
-asmlinkage int __raw_atomic_update_asm(volatile int *ptr, int value);
-asmlinkage int __raw_atomic_clear_asm(volatile int *ptr, int value);
-asmlinkage int __raw_atomic_set_asm(volatile int *ptr, int value);
+asmlinkage int __raw_atomic_add_asm(volatile int *ptr, int value);
+
+asmlinkage int __raw_atomic_and_asm(volatile int *ptr, int value);
+asmlinkage int __raw_atomic_or_asm(volatile int *ptr, int value);
 asmlinkage int __raw_atomic_xor_asm(volatile int *ptr, int value);
 asmlinkage int __raw_atomic_test_asm(const volatile int *ptr, int value);
 
 #define atomic_read(v) __raw_uncached_fetch_asm(&(v)->counter)
 
-#define atomic_add_return(i, v) __raw_atomic_update_asm(&(v)->counter, i)
-#define atomic_sub_return(i, v) __raw_atomic_update_asm(&(v)->counter, -(i))
+#define atomic_add_return(i, v) __raw_atomic_add_asm(&(v)->counter, i)
+#define atomic_sub_return(i, v) __raw_atomic_add_asm(&(v)->counter, -(i))
 
-#define atomic_clear_mask(m, v) __raw_atomic_clear_asm(&(v)->counter, m)
-#define atomic_set_mask(m, v)   __raw_atomic_set_asm(&(v)->counter, m)
+#define atomic_or(i, v)  (void)__raw_atomic_or_asm(&(v)->counter, i)
+#define atomic_and(i, v) (void)__raw_atomic_and_asm(&(v)->counter, i)
+#define atomic_xor(i, v) (void)__raw_atomic_xor_asm(&(v)->counter, i)
 
 #endif
 
diff --git a/arch/blackfin/include/asm/mm-arch-hooks.h b/arch/blackfin/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 1c5211ec338f..000000000000
--- a/arch/blackfin/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_BLACKFIN_MM_ARCH_HOOKS_H
-#define _ASM_BLACKFIN_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_BLACKFIN_MM_ARCH_HOOKS_H */
diff --git a/arch/blackfin/kernel/bfin_ksyms.c b/arch/blackfin/kernel/bfin_ksyms.c
index c446591b961d..a401c27b69b4 100644
--- a/arch/blackfin/kernel/bfin_ksyms.c
+++ b/arch/blackfin/kernel/bfin_ksyms.c
@@ -83,11 +83,12 @@ EXPORT_SYMBOL(insl);
 EXPORT_SYMBOL(insl_16);
 
 #ifdef CONFIG_SMP
-EXPORT_SYMBOL(__raw_atomic_update_asm);
-EXPORT_SYMBOL(__raw_atomic_clear_asm);
-EXPORT_SYMBOL(__raw_atomic_set_asm);
+EXPORT_SYMBOL(__raw_atomic_add_asm);
+EXPORT_SYMBOL(__raw_atomic_and_asm);
+EXPORT_SYMBOL(__raw_atomic_or_asm);
 EXPORT_SYMBOL(__raw_atomic_xor_asm);
 EXPORT_SYMBOL(__raw_atomic_test_asm);
+
 EXPORT_SYMBOL(__raw_xchg_1_asm);
 EXPORT_SYMBOL(__raw_xchg_2_asm);
 EXPORT_SYMBOL(__raw_xchg_4_asm);
diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c
index cb0a4845339e..fb9e95f1b719 100644
--- a/arch/blackfin/kernel/time-ts.c
+++ b/arch/blackfin/kernel/time-ts.c
@@ -136,44 +136,44 @@ static int bfin_gptmr0_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void bfin_gptmr0_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int bfin_gptmr0_set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC: {
 #ifndef CONFIG_BF60x
-		set_gptimer_config(TIMER0_id, \
-			TIMER_OUT_DIS | TIMER_IRQ_ENA | \
-			TIMER_PERIOD_CNT | TIMER_MODE_PWM);
+	set_gptimer_config(TIMER0_id,
+			   TIMER_OUT_DIS | TIMER_IRQ_ENA |
+			   TIMER_PERIOD_CNT | TIMER_MODE_PWM);
 #else
-		set_gptimer_config(TIMER0_id,  TIMER_OUT_DIS
-			| TIMER_MODE_PWM_CONT | TIMER_PULSE_HI | TIMER_IRQ_PER);
+	set_gptimer_config(TIMER0_id,
+			   TIMER_OUT_DIS | TIMER_MODE_PWM_CONT |
+			   TIMER_PULSE_HI | TIMER_IRQ_PER);
 #endif
 
-		set_gptimer_period(TIMER0_id, get_sclk() / HZ);
-		set_gptimer_pwidth(TIMER0_id, get_sclk() / HZ - 1);
-		enable_gptimers(TIMER0bit);
-		break;
-	}
-	case CLOCK_EVT_MODE_ONESHOT:
-		disable_gptimers(TIMER0bit);
+	set_gptimer_period(TIMER0_id, get_sclk() / HZ);
+	set_gptimer_pwidth(TIMER0_id, get_sclk() / HZ - 1);
+	enable_gptimers(TIMER0bit);
+	return 0;
+}
+
+static int bfin_gptmr0_set_oneshot(struct clock_event_device *evt)
+{
+	disable_gptimers(TIMER0bit);
 #ifndef CONFIG_BF60x
-		set_gptimer_config(TIMER0_id, \
-			TIMER_OUT_DIS | TIMER_IRQ_ENA | TIMER_MODE_PWM);
+	set_gptimer_config(TIMER0_id,
+			   TIMER_OUT_DIS | TIMER_IRQ_ENA | TIMER_MODE_PWM);
 #else
-		set_gptimer_config(TIMER0_id, TIMER_OUT_DIS | TIMER_MODE_PWM
-			| TIMER_PULSE_HI | TIMER_IRQ_WID_DLY);
+	set_gptimer_config(TIMER0_id,
+			   TIMER_OUT_DIS | TIMER_MODE_PWM | TIMER_PULSE_HI |
+			   TIMER_IRQ_WID_DLY);
 #endif
 
-		set_gptimer_period(TIMER0_id, 0);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		disable_gptimers(TIMER0bit);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	set_gptimer_period(TIMER0_id, 0);
+	return 0;
+}
+
+static int bfin_gptmr0_shutdown(struct clock_event_device *evt)
+{
+	disable_gptimers(TIMER0bit);
+	return 0;
 }
 
 static void bfin_gptmr0_ack(void)
@@ -211,13 +211,16 @@ static struct irqaction gptmr0_irq = {
 };
 
 static struct clock_event_device clockevent_gptmr0 = {
-	.name		= "bfin_gptimer0",
-	.rating		= 300,
-	.irq		= IRQ_TIMER0,
-	.shift		= 32,
-	.features 	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event = bfin_gptmr0_set_next_event,
-	.set_mode	= bfin_gptmr0_set_mode,
+	.name			= "bfin_gptimer0",
+	.rating			= 300,
+	.irq			= IRQ_TIMER0,
+	.shift			= 32,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= bfin_gptmr0_set_next_event,
+	.set_state_shutdown	= bfin_gptmr0_shutdown,
+	.set_state_periodic	= bfin_gptmr0_set_periodic,
+	.set_state_oneshot	= bfin_gptmr0_set_oneshot,
 };
 
 static void __init bfin_gptmr0_clockevent_init(struct clock_event_device *evt)
@@ -250,36 +253,35 @@ static int bfin_coretmr_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void bfin_coretmr_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int bfin_coretmr_set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC: {
-		unsigned long tcount = ((get_cclk() / (HZ * TIME_SCALE)) - 1);
-		bfin_write_TCNTL(TMPWR);
-		CSYNC();
-		bfin_write_TSCALE(TIME_SCALE - 1);
-		bfin_write_TPERIOD(tcount);
-		bfin_write_TCOUNT(tcount);
-		CSYNC();
-		bfin_write_TCNTL(TMPWR | TMREN | TAUTORLD);
-		break;
-	}
-	case CLOCK_EVT_MODE_ONESHOT:
-		bfin_write_TCNTL(TMPWR);
-		CSYNC();
-		bfin_write_TSCALE(TIME_SCALE - 1);
-		bfin_write_TPERIOD(0);
-		bfin_write_TCOUNT(0);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		bfin_write_TCNTL(0);
-		CSYNC();
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	unsigned long tcount = ((get_cclk() / (HZ * TIME_SCALE)) - 1);
+
+	bfin_write_TCNTL(TMPWR);
+	CSYNC();
+	bfin_write_TSCALE(TIME_SCALE - 1);
+	bfin_write_TPERIOD(tcount);
+	bfin_write_TCOUNT(tcount);
+	CSYNC();
+	bfin_write_TCNTL(TMPWR | TMREN | TAUTORLD);
+	return 0;
+}
+
+static int bfin_coretmr_set_oneshot(struct clock_event_device *evt)
+{
+	bfin_write_TCNTL(TMPWR);
+	CSYNC();
+	bfin_write_TSCALE(TIME_SCALE - 1);
+	bfin_write_TPERIOD(0);
+	bfin_write_TCOUNT(0);
+	return 0;
+}
+
+static int bfin_coretmr_shutdown(struct clock_event_device *evt)
+{
+	bfin_write_TCNTL(0);
+	CSYNC();
+	return 0;
 }
 
 void bfin_coretmr_init(void)
@@ -335,7 +337,9 @@ void bfin_coretmr_clockevent_init(void)
 	evt->shift = 32;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->set_next_event = bfin_coretmr_set_next_event;
-	evt->set_mode = bfin_coretmr_set_mode;
+	evt->set_state_shutdown = bfin_coretmr_shutdown;
+	evt->set_state_periodic = bfin_coretmr_set_periodic;
+	evt->set_state_oneshot = bfin_coretmr_set_oneshot;
 
 	clock_tick = get_cclk() / TIME_SCALE;
 	evt->mult = div_sc(clock_tick, NSEC_PER_SEC, evt->shift);
diff --git a/arch/blackfin/mach-bf537/ints-priority.c b/arch/blackfin/mach-bf537/ints-priority.c
index 2137a209a22b..14b2f74554dc 100644
--- a/arch/blackfin/mach-bf537/ints-priority.c
+++ b/arch/blackfin/mach-bf537/ints-priority.c
@@ -182,9 +182,11 @@ static struct irq_chip bf537_mac_rx_irqchip = {
 	.irq_unmask = bf537_mac_rx_unmask_irq,
 };
 
-static void bf537_demux_mac_rx_irq(unsigned int int_irq,
+static void bf537_demux_mac_rx_irq(unsigned int __int_irq,
 				   struct irq_desc *desc)
 {
+	unsigned int int_irq = irq_desc_get_irq(desc);
+
 	if (bfin_read_DMA1_IRQ_STATUS() & (DMA_DONE | DMA_ERR))
 		bfin_handle_irq(IRQ_MAC_RX);
 	else
diff --git a/arch/blackfin/mach-bf561/atomic.S b/arch/blackfin/mach-bf561/atomic.S
index 2a08df8e8c4c..26fccb5568b9 100644
--- a/arch/blackfin/mach-bf561/atomic.S
+++ b/arch/blackfin/mach-bf561/atomic.S
@@ -587,10 +587,10 @@ ENDPROC(___raw_write_unlock_asm)
  * r0 = ptr
  * r1 = value
  *
- * Add a signed value to a 32bit word and return the new value atomically.
+ * ADD a signed value to a 32bit word and return the new value atomically.
  * Clobbers: r3:0, p1:0
  */
-ENTRY(___raw_atomic_update_asm)
+ENTRY(___raw_atomic_add_asm)
 	p1 = r0;
 	r3 = r1;
 	[--sp] = rets;
@@ -603,19 +603,19 @@ ENTRY(___raw_atomic_update_asm)
 	r0 = r3;
 	rets = [sp++];
 	rts;
-ENDPROC(___raw_atomic_update_asm)
+ENDPROC(___raw_atomic_add_asm)
 
 /*
  * r0 = ptr
  * r1 = mask
  *
- * Clear the mask bits from a 32bit word and return the old 32bit value
+ * AND the mask bits from a 32bit word and return the old 32bit value
  * atomically.
  * Clobbers: r3:0, p1:0
  */
-ENTRY(___raw_atomic_clear_asm)
+ENTRY(___raw_atomic_and_asm)
 	p1 = r0;
-	r3 = ~r1;
+	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
 	r2 = [p1];
@@ -627,17 +627,17 @@ ENTRY(___raw_atomic_clear_asm)
 	r0 = r3;
 	rets = [sp++];
 	rts;
-ENDPROC(___raw_atomic_clear_asm)
+ENDPROC(___raw_atomic_and_asm)
 
 /*
  * r0 = ptr
  * r1 = mask
  *
- * Set the mask bits into a 32bit word and return the old 32bit value
+ * OR the mask bits into a 32bit word and return the old 32bit value
  * atomically.
  * Clobbers: r3:0, p1:0
  */
-ENTRY(___raw_atomic_set_asm)
+ENTRY(___raw_atomic_or_asm)
 	p1 = r0;
 	r3 = r1;
 	[--sp] = rets;
@@ -651,7 +651,7 @@ ENTRY(___raw_atomic_set_asm)
 	r0 = r3;
 	rets = [sp++];
 	rts;
-ENDPROC(___raw_atomic_set_asm)
+ENDPROC(___raw_atomic_or_asm)
 
 /*
  * r0 = ptr
@@ -787,7 +787,7 @@ ENTRY(___raw_bit_set_asm)
 	r2 = r1;
 	r1 = 1;
 	r1 <<= r2;
-	jump ___raw_atomic_set_asm
+	jump ___raw_atomic_or_asm
 ENDPROC(___raw_bit_set_asm)
 
 /*
@@ -798,10 +798,10 @@ ENDPROC(___raw_bit_set_asm)
  * Clobbers: r3:0, p1:0
  */
 ENTRY(___raw_bit_clear_asm)
-	r2 = r1;
-	r1 = 1;
-	r1 <<= r2;
-	jump ___raw_atomic_clear_asm
+	r2 = 1;
+	r2 <<= r1;
+	r1 = ~r2;
+	jump ___raw_atomic_and_asm
 ENDPROC(___raw_bit_clear_asm)
 
 /*
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 7236bdfc71e6..a6d1b03cdf36 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -194,7 +194,8 @@ void bfin_internal_unmask_irq(unsigned int irq)
 #ifdef CONFIG_SMP
 static void bfin_internal_unmask_irq_chip(struct irq_data *d)
 {
-	bfin_internal_unmask_irq_affinity(d->irq, d->affinity);
+	bfin_internal_unmask_irq_affinity(d->irq,
+					  irq_data_get_affinity_mask(d));
 }
 
 static int bfin_internal_set_affinity(struct irq_data *d,
@@ -685,12 +686,12 @@ void bfin_demux_mac_status_irq(unsigned int int_err_irq,
 }
 #endif
 
-static inline void bfin_set_irq_handler(unsigned irq, irq_flow_handler_t handle)
+static inline void bfin_set_irq_handler(struct irq_data *d, irq_flow_handler_t handle)
 {
 #ifdef CONFIG_IPIPE
 	handle = handle_level_irq;
 #endif
-	__irq_set_handler_locked(irq, handle);
+	irq_set_handler_locked(d, handle);
 }
 
 #ifdef CONFIG_GPIO_ADI
@@ -802,9 +803,9 @@ static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type)
 	}
 
 	if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING))
-		bfin_set_irq_handler(irq, handle_edge_irq);
+		bfin_set_irq_handler(d, handle_edge_irq);
 	else
-		bfin_set_irq_handler(irq, handle_level_irq);
+		bfin_set_irq_handler(d, handle_level_irq);
 
 	return 0;
 }
@@ -824,9 +825,9 @@ static void bfin_demux_gpio_block(unsigned int irq)
 	}
 }
 
-void bfin_demux_gpio_irq(unsigned int inta_irq,
-			struct irq_desc *desc)
+void bfin_demux_gpio_irq(unsigned int __inta_irq, struct irq_desc *desc)
 {
+	unsigned int inta_irq = irq_desc_get_irq(desc);
 	unsigned int irq;
 
 	switch (inta_irq) {
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 1c7259597395..0030e21cfceb 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -195,7 +195,7 @@ void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg)
 	local_irq_save(flags);
 	for_each_cpu(cpu, cpumask) {
 		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
-		atomic_set_mask((1 << msg), &bfin_ipi_data->bits);
+		atomic_or((1 << msg), &bfin_ipi_data->bits);
 		atomic_inc(&bfin_ipi_data->count);
 	}
 	local_irq_restore(flags);
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 7aeb32272975..f17c4dc6050c 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -26,6 +26,7 @@ generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += mmu.h
 generic-y += mmu_context.h
diff --git a/arch/c6x/include/asm/mm-arch-hooks.h b/arch/c6x/include/asm/mm-arch-hooks.h
deleted file mode 100644
index bb3c4a6ce8e9..000000000000
--- a/arch/c6x/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_C6X_MM_ARCH_HOOKS_H
-#define _ASM_C6X_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_C6X_MM_ARCH_HOOKS_H */
diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c
index 74e3371eb824..d487698e978a 100644
--- a/arch/c6x/platforms/megamod-pic.c
+++ b/arch/c6x/platforms/megamod-pic.c
@@ -93,10 +93,11 @@ static struct irq_chip megamod_chip = {
 	.irq_unmask	= unmask_megamod,
 };
 
-static void megamod_irq_cascade(unsigned int irq, struct irq_desc *desc)
+static void megamod_irq_cascade(unsigned int __irq, struct irq_desc *desc)
 {
 	struct megamod_cascade_data *cascade;
 	struct megamod_pic *pic;
+	unsigned int irq;
 	u32 events;
 	int n, idx;
 
@@ -282,8 +283,8 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np)
 		soc_writel(~0, &pic->regs->evtmask[i]);
 		soc_writel(~0, &pic->regs->evtclr[i]);
 
-		irq_set_handler_data(irq, &cascade_data[i]);
-		irq_set_chained_handler(irq, megamod_irq_cascade);
+		irq_set_chained_handler_and_data(irq, megamod_irq_cascade,
+						 &cascade_data[i]);
 	}
 
 	/* Finally, set up the MUX registers */
diff --git a/arch/c6x/platforms/timer64.c b/arch/c6x/platforms/timer64.c
index 3c73d74a4674..c19901e5f055 100644
--- a/arch/c6x/platforms/timer64.c
+++ b/arch/c6x/platforms/timer64.c
@@ -126,35 +126,37 @@ static int next_event(unsigned long delta,
 	return 0;
 }
 
-static void set_clock_mode(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
+static int set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		timer64_enable();
-		timer64_mode = TIMER64_MODE_PERIODIC;
-		timer64_config(TIMER64_RATE / HZ);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		timer64_enable();
-		timer64_mode = TIMER64_MODE_ONE_SHOT;
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		timer64_mode = TIMER64_MODE_DISABLED;
-		timer64_disable();
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	timer64_enable();
+	timer64_mode = TIMER64_MODE_PERIODIC;
+	timer64_config(TIMER64_RATE / HZ);
+	return 0;
+}
+
+static int set_oneshot(struct clock_event_device *evt)
+{
+	timer64_enable();
+	timer64_mode = TIMER64_MODE_ONE_SHOT;
+	return 0;
+}
+
+static int shutdown(struct clock_event_device *evt)
+{
+	timer64_mode = TIMER64_MODE_DISABLED;
+	timer64_disable();
+	return 0;
 }
 
 static struct clock_event_device t64_clockevent_device = {
-	.name		= "TIMER64_EVT32_TIMER",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.rating		= 200,
-	.set_mode	= set_clock_mode,
-	.set_next_event	= next_event,
+	.name			= "TIMER64_EVT32_TIMER",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 200,
+	.set_state_shutdown	= shutdown,
+	.set_state_periodic	= set_periodic,
+	.set_state_oneshot	= set_oneshot,
+	.set_next_event		= next_event,
 };
 
 static irqreturn_t timer_interrupt(int irq, void *dev_id)
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index 4dda9bd6b8fb..e989cee77414 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -1464,7 +1464,7 @@ static inline void handle_rx_packet(struct sync_port *port)
 		if (port->write_ts_idx == NBR_IN_DESCR)
 			port->write_ts_idx = 0;
 		idx = port->write_ts_idx++;
-		do_posix_clock_monotonic_gettime(&port->timestamp[idx]);
+		ktime_get_ts(&port->timestamp[idx]);
 		port->in_buffer_len += port->inbufchunk;
 	}
 	spin_unlock_irqrestore(&port->lock, flags);
diff --git a/arch/cris/arch-v32/kernel/time.c b/arch/cris/arch-v32/kernel/time.c
index 4fce9f1f7cc0..d2a84407654a 100644
--- a/arch/cris/arch-v32/kernel/time.c
+++ b/arch/cris/arch-v32/kernel/time.c
@@ -172,8 +172,7 @@ void handle_watchdog_bite(struct pt_regs *regs)
 extern void cris_profile_sample(struct pt_regs *regs);
 static void __iomem *timer_base;
 
-static void crisv32_clkevt_mode(enum clock_event_mode mode,
-				struct clock_event_device *dev)
+static int crisv32_clkevt_switch_state(struct clock_event_device *dev)
 {
 	reg_timer_rw_tmr0_ctrl ctrl = {
 		.op = regk_timer_hold,
@@ -181,6 +180,7 @@ static void crisv32_clkevt_mode(enum clock_event_mode mode,
 	};
 
 	REG_WR(timer, timer_base, rw_tmr0_ctrl, ctrl);
+	return 0;
 }
 
 static int crisv32_clkevt_next_event(unsigned long evt,
@@ -231,7 +231,9 @@ static struct clock_event_device crisv32_clockevent = {
 	.name = "crisv32-timer",
 	.rating = 300,
 	.features = CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = crisv32_clkevt_mode,
+	.set_state_oneshot = crisv32_clkevt_switch_state,
+	.set_state_shutdown = crisv32_clkevt_switch_state,
+	.tick_resume = crisv32_clkevt_switch_state,
 	.set_next_event = crisv32_clkevt_next_event,
 };
 
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index d294f6aaff1d..ad2244f35bca 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -18,6 +18,7 @@ generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/cris/include/asm/mm-arch-hooks.h b/arch/cris/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 314f774db2b0..000000000000
--- a/arch/cris/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_CRIS_MM_ARCH_HOOKS_H
-#define _ASM_CRIS_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_CRIS_MM_ARCH_HOOKS_H */
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 30edce31e5c2..8e47b832cc76 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -4,5 +4,6 @@ generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += trace_clock.h
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 102190a61d65..0da689def4cc 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -15,7 +15,6 @@
 #define _ASM_ATOMIC_H
 
 #include <linux/types.h>
-#include <asm/spr-regs.h>
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
@@ -23,6 +22,8 @@
 #error not SMP safe
 #endif
 
+#include <asm/atomic_defs.h>
+
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
@@ -34,56 +35,26 @@
 #define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = (i))
 
-#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-static inline int atomic_add_return(int i, atomic_t *v)
+static inline int atomic_inc_return(atomic_t *v)
 {
-	unsigned long val;
+	return __atomic_add_return(1, &v->counter);
+}
 
-	asm("0:						\n"
-	    "	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-	    "	ckeq		icc3,cc7		\n"
-	    "	ld.p		%M0,%1			\n"	/* LD.P/ORCR must be atomic */
-	    "	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-	    "	add%I2		%1,%2,%1		\n"
-	    "	cst.p		%1,%M0		,cc3,#1	\n"
-	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* clear ICC3.Z if store happens */
-	    "	beq		icc3,#0,0b		\n"
-	    : "+U"(v->counter), "=&r"(val)
-	    : "NPr"(i)
-	    : "memory", "cc7", "cc3", "icc3"
-	    );
+static inline int atomic_dec_return(atomic_t *v)
+{
+	return __atomic_sub_return(1, &v->counter);
+}
 
-	return val;
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	return __atomic_add_return(i, &v->counter);
 }
 
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
-	unsigned long val;
-
-	asm("0:						\n"
-	    "	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-	    "	ckeq		icc3,cc7		\n"
-	    "	ld.p		%M0,%1			\n"	/* LD.P/ORCR must be atomic */
-	    "	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-	    "	sub%I2		%1,%2,%1		\n"
-	    "	cst.p		%1,%M0		,cc3,#1	\n"
-	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* clear ICC3.Z if store happens */
-	    "	beq		icc3,#0,0b		\n"
-	    : "+U"(v->counter), "=&r"(val)
-	    : "NPr"(i)
-	    : "memory", "cc7", "cc3", "icc3"
-	    );
-
-	return val;
+	return __atomic_sub_return(i, &v->counter);
 }
 
-#else
-
-extern int atomic_add_return(int i, atomic_t *v);
-extern int atomic_sub_return(int i, atomic_t *v);
-
-#endif
-
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	return atomic_add_return(i, v) < 0;
@@ -101,17 +72,14 @@ static inline void atomic_sub(int i, atomic_t *v)
 
 static inline void atomic_inc(atomic_t *v)
 {
-	atomic_add_return(1, v);
+	atomic_inc_return(v);
 }
 
 static inline void atomic_dec(atomic_t *v)
 {
-	atomic_sub_return(1, v);
+	atomic_dec_return(v);
 }
 
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
 #define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
 #define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
@@ -120,18 +88,19 @@ static inline void atomic_dec(atomic_t *v)
  * 64-bit atomic ops
  */
 typedef struct {
-	volatile long long counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-static inline long long atomic64_read(atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
 	long long counter;
 
 	asm("ldd%I1 %M1,%0"
 	    : "=e"(counter)
 	    : "m"(v->counter));
+
 	return counter;
 }
 
@@ -142,10 +111,25 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 		     : "e"(i));
 }
 
-extern long long atomic64_inc_return(atomic64_t *v);
-extern long long atomic64_dec_return(atomic64_t *v);
-extern long long atomic64_add_return(long long i, atomic64_t *v);
-extern long long atomic64_sub_return(long long i, atomic64_t *v);
+static inline long long atomic64_inc_return(atomic64_t *v)
+{
+	return __atomic64_add_return(1, &v->counter);
+}
+
+static inline long long atomic64_dec_return(atomic64_t *v)
+{
+	return __atomic64_sub_return(1, &v->counter);
+}
+
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
+{
+	return __atomic64_add_return(i, &v->counter);
+}
+
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+{
+	return __atomic64_sub_return(i, &v->counter);
+}
 
 static inline long long atomic64_add_negative(long long i, atomic64_t *v)
 {
@@ -176,6 +160,7 @@ static inline void atomic64_dec(atomic64_t *v)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_inc_return((v)) == 0)
 
+
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&(v)->counter, old, new))
 #define atomic_xchg(v, new)		(xchg(&(v)->counter, new))
 #define atomic64_cmpxchg(v, old, new)	(__cmpxchg_64(old, new, &(v)->counter))
@@ -196,5 +181,21 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	(void)__atomic32_fetch_##op(i, &v->counter);			\
+}									\
+									\
+static inline void atomic64_##op(long long i, atomic64_t *v)		\
+{									\
+	(void)__atomic64_fetch_##op(i, &v->counter);			\
+}
+
+ATOMIC_OP(or)
+ATOMIC_OP(and)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/frv/include/asm/atomic_defs.h b/arch/frv/include/asm/atomic_defs.h
new file mode 100644
index 000000000000..36e126d2f801
--- /dev/null
+++ b/arch/frv/include/asm/atomic_defs.h
@@ -0,0 +1,172 @@
+
+#include <asm/spr-regs.h>
+
+#ifdef __ATOMIC_LIB__
+
+#ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
+
+#define ATOMIC_QUALS
+#define ATOMIC_EXPORT(x)	EXPORT_SYMBOL(x)
+
+#else /* !OUTOFLINE && LIB */
+
+#define ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)
+
+#endif /* OUTOFLINE */
+
+#else /* !__ATOMIC_LIB__ */
+
+#define ATOMIC_EXPORT(x)
+
+#ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
+
+#define ATOMIC_OP_RETURN(op)						\
+extern int __atomic_##op##_return(int i, int *v);			\
+extern long long __atomic64_##op##_return(long long i, long long *v);
+
+#define ATOMIC_FETCH_OP(op)						\
+extern int __atomic32_fetch_##op(int i, int *v);			\
+extern long long __atomic64_fetch_##op(long long i, long long *v);
+
+#else /* !OUTOFLINE && !LIB */
+
+#define ATOMIC_QUALS	static inline
+
+#endif /* OUTOFLINE */
+#endif /* __ATOMIC_LIB__ */
+
+
+/*
+ * Note on the 64 bit inline asm variants...
+ *
+ * CSTD is a conditional instruction and needs a constrained memory reference.
+ * Normally 'U' provides the correct constraints for conditional instructions
+ * and this is used for the 32 bit version, however 'U' does not appear to work
+ * for 64 bit values (gcc-4.9)
+ *
+ * The exact constraint is that conditional instructions cannot deal with an
+ * immediate displacement in the memory reference, so what we do is we read the
+ * address through a volatile cast into a local variable in order to insure we
+ * _have_ to compute the correct address without displacement. This allows us
+ * to use the regular 'm' for the memory address.
+ *
+ * Furthermore, the %Ln operand, which prints the low word register (r+1),
+ * really only works for registers, this means we cannot allow immediate values
+ * for the 64 bit versions -- like we do for the 32 bit ones.
+ *
+ */
+
+#ifndef ATOMIC_OP_RETURN
+#define ATOMIC_OP_RETURN(op)						\
+ATOMIC_QUALS int __atomic_##op##_return(int i, int *v)			\
+{									\
+	int val;							\
+									\
+	asm volatile(							\
+	    "0:						\n"		\
+	    "	orcc		gr0,gr0,gr0,icc3	\n"		\
+	    "	ckeq		icc3,cc7		\n"		\
+	    "	ld.p		%M0,%1			\n"		\
+	    "	orcr		cc7,cc7,cc3		\n"		\
+	    "   "#op"%I2	%1,%2,%1		\n"		\
+	    "	cst.p		%1,%M0		,cc3,#1	\n"		\
+	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"		\
+	    "	beq		icc3,#0,0b		\n"		\
+	    : "+U"(*v), "=&r"(val)					\
+	    : "NPr"(i)							\
+	    : "memory", "cc7", "cc3", "icc3"				\
+	    );								\
+									\
+	return val;							\
+}									\
+ATOMIC_EXPORT(__atomic_##op##_return);					\
+									\
+ATOMIC_QUALS long long __atomic64_##op##_return(long long i, long long *v)	\
+{									\
+	long long *__v = READ_ONCE(v);					\
+	long long val;							\
+									\
+	asm volatile(							\
+	    "0:						\n"		\
+	    "	orcc		gr0,gr0,gr0,icc3	\n"		\
+	    "	ckeq		icc3,cc7		\n"		\
+	    "	ldd.p		%M0,%1			\n"		\
+	    "	orcr		cc7,cc7,cc3		\n"		\
+	    "   "#op"cc		%L1,%L2,%L1,icc0	\n"		\
+	    "   "#op"x		%1,%2,%1,icc0		\n"		\
+	    "	cstd.p		%1,%M0		,cc3,#1	\n"		\
+	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"		\
+	    "	beq		icc3,#0,0b		\n"		\
+	    : "+m"(*__v), "=&e"(val)					\
+	    : "e"(i)							\
+	    : "memory", "cc7", "cc3", "icc0", "icc3"			\
+	    );								\
+									\
+	return val;							\
+}									\
+ATOMIC_EXPORT(__atomic64_##op##_return);
+#endif
+
+#ifndef ATOMIC_FETCH_OP
+#define ATOMIC_FETCH_OP(op)						\
+ATOMIC_QUALS int __atomic32_fetch_##op(int i, int *v)			\
+{									\
+	int old, tmp;							\
+									\
+	asm volatile(							\
+		"0:						\n"	\
+		"	orcc		gr0,gr0,gr0,icc3	\n"	\
+		"	ckeq		icc3,cc7		\n"	\
+		"	ld.p		%M0,%1			\n"	\
+		"	orcr		cc7,cc7,cc3		\n"	\
+		"	"#op"%I3	%1,%3,%2		\n"	\
+		"	cst.p		%2,%M0		,cc3,#1	\n"	\
+		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	\
+		"	beq		icc3,#0,0b		\n"	\
+		: "+U"(*v), "=&r"(old), "=r"(tmp)			\
+		: "NPr"(i)						\
+		: "memory", "cc7", "cc3", "icc3"			\
+		);							\
+									\
+	return old;							\
+}									\
+ATOMIC_EXPORT(__atomic32_fetch_##op);					\
+									\
+ATOMIC_QUALS long long __atomic64_fetch_##op(long long i, long long *v)	\
+{									\
+	long long *__v = READ_ONCE(v);					\
+	long long old, tmp;						\
+									\
+	asm volatile(							\
+		"0:						\n"	\
+		"	orcc		gr0,gr0,gr0,icc3	\n"	\
+		"	ckeq		icc3,cc7		\n"	\
+		"	ldd.p		%M0,%1			\n"	\
+		"	orcr		cc7,cc7,cc3		\n"	\
+		"	"#op"		%L1,%L3,%L2		\n"	\
+		"	"#op"		%1,%3,%2		\n"	\
+		"	cstd.p		%2,%M0		,cc3,#1	\n"	\
+		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	\
+		"	beq		icc3,#0,0b		\n"	\
+		: "+m"(*__v), "=&e"(old), "=e"(tmp)			\
+		: "e"(i)						\
+		: "memory", "cc7", "cc3", "icc3"			\
+		);							\
+									\
+	return old;							\
+}									\
+ATOMIC_EXPORT(__atomic64_fetch_##op);
+#endif
+
+ATOMIC_FETCH_OP(or)
+ATOMIC_FETCH_OP(and)
+ATOMIC_FETCH_OP(xor)
+
+ATOMIC_OP_RETURN(add)
+ATOMIC_OP_RETURN(sub)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_QUALS
+#undef ATOMIC_EXPORT
diff --git a/arch/frv/include/asm/bitops.h b/arch/frv/include/asm/bitops.h
index 96de220ef131..0df8e95e3715 100644
--- a/arch/frv/include/asm/bitops.h
+++ b/arch/frv/include/asm/bitops.h
@@ -25,109 +25,30 @@
 
 #include <asm-generic/bitops/ffz.h>
 
-#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-static inline
-unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v)
-{
-	unsigned long old, tmp;
-
-	asm volatile(
-		"0:						\n"
-		"	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-		"	ckeq		icc3,cc7		\n"
-		"	ld.p		%M0,%1			\n"	/* LD.P/ORCR are atomic */
-		"	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-		"	and%I3		%1,%3,%2		\n"
-		"	cst.p		%2,%M0		,cc3,#1	\n"	/* if store happens... */
-		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* ... clear ICC3.Z */
-		"	beq		icc3,#0,0b		\n"
-		: "+U"(*v), "=&r"(old), "=r"(tmp)
-		: "NPr"(~mask)
-		: "memory", "cc7", "cc3", "icc3"
-		);
-
-	return old;
-}
-
-static inline
-unsigned long atomic_test_and_OR_mask(unsigned long mask, volatile unsigned long *v)
-{
-	unsigned long old, tmp;
-
-	asm volatile(
-		"0:						\n"
-		"	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-		"	ckeq		icc3,cc7		\n"
-		"	ld.p		%M0,%1			\n"	/* LD.P/ORCR are atomic */
-		"	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-		"	or%I3		%1,%3,%2		\n"
-		"	cst.p		%2,%M0		,cc3,#1	\n"	/* if store happens... */
-		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* ... clear ICC3.Z */
-		"	beq		icc3,#0,0b		\n"
-		: "+U"(*v), "=&r"(old), "=r"(tmp)
-		: "NPr"(mask)
-		: "memory", "cc7", "cc3", "icc3"
-		);
-
-	return old;
-}
-
-static inline
-unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsigned long *v)
-{
-	unsigned long old, tmp;
-
-	asm volatile(
-		"0:						\n"
-		"	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-		"	ckeq		icc3,cc7		\n"
-		"	ld.p		%M0,%1			\n"	/* LD.P/ORCR are atomic */
-		"	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-		"	xor%I3		%1,%3,%2		\n"
-		"	cst.p		%2,%M0		,cc3,#1	\n"	/* if store happens... */
-		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* ... clear ICC3.Z */
-		"	beq		icc3,#0,0b		\n"
-		: "+U"(*v), "=&r"(old), "=r"(tmp)
-		: "NPr"(mask)
-		: "memory", "cc7", "cc3", "icc3"
-		);
-
-	return old;
-}
-
-#else
-
-extern unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v);
-extern unsigned long atomic_test_and_OR_mask(unsigned long mask, volatile unsigned long *v);
-extern unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsigned long *v);
-
-#endif
-
-#define atomic_clear_mask(mask, v)	atomic_test_and_ANDNOT_mask((mask), (v))
-#define atomic_set_mask(mask, v)	atomic_test_and_OR_mask((mask), (v))
+#include <asm/atomic.h>
 
 static inline int test_and_clear_bit(unsigned long nr, volatile void *addr)
 {
-	volatile unsigned long *ptr = addr;
-	unsigned long mask = 1UL << (nr & 31);
+	unsigned int *ptr = (void *)addr;
+	unsigned int mask = 1UL << (nr & 31);
 	ptr += nr >> 5;
-	return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0;
+	return (__atomic32_fetch_and(~mask, ptr) & mask) != 0;
 }
 
 static inline int test_and_set_bit(unsigned long nr, volatile void *addr)
 {
-	volatile unsigned long *ptr = addr;
-	unsigned long mask = 1UL << (nr & 31);
+	unsigned int *ptr = (void *)addr;
+	unsigned int mask = 1UL << (nr & 31);
 	ptr += nr >> 5;
-	return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0;
+	return (__atomic32_fetch_or(mask, ptr) & mask) != 0;
 }
 
 static inline int test_and_change_bit(unsigned long nr, volatile void *addr)
 {
-	volatile unsigned long *ptr = addr;
-	unsigned long mask = 1UL << (nr & 31);
+	unsigned int *ptr = (void *)addr;
+	unsigned int mask = 1UL << (nr & 31);
 	ptr += nr >> 5;
-	return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0;
+	return (__atomic32_fetch_xor(mask, ptr) & mask) != 0;
 }
 
 static inline void clear_bit(unsigned long nr, volatile void *addr)
diff --git a/arch/frv/include/asm/io.h b/arch/frv/include/asm/io.h
index a31b63ec4930..70dfbea8c8d7 100644
--- a/arch/frv/include/asm/io.h
+++ b/arch/frv/include/asm/io.h
@@ -278,6 +278,7 @@ static inline void __iomem *ioremap_fullcache(unsigned long physaddr, unsigned l
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 extern void iounmap(void volatile __iomem *addr);
 
diff --git a/arch/frv/include/asm/mm-arch-hooks.h b/arch/frv/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 51d13a870404..000000000000
--- a/arch/frv/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_FRV_MM_ARCH_HOOKS_H
-#define _ASM_FRV_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_FRV_MM_ARCH_HOOKS_H */
diff --git a/arch/frv/kernel/dma.c b/arch/frv/kernel/dma.c
index 156184e17e57..370dc9fa0b11 100644
--- a/arch/frv/kernel/dma.c
+++ b/arch/frv/kernel/dma.c
@@ -109,13 +109,13 @@ static struct frv_dma_channel frv_dma_channels[FRV_DMA_NCHANS] = {
 
 static DEFINE_RWLOCK(frv_dma_channels_lock);
 
-unsigned long frv_dma_inprogress;
+unsigned int frv_dma_inprogress;
 
 #define frv_clear_dma_inprogress(channel) \
-	atomic_clear_mask(1 << (channel), &frv_dma_inprogress);
+	(void)__atomic32_fetch_and(~(1 << (channel)), &frv_dma_inprogress);
 
 #define frv_set_dma_inprogress(channel) \
-	atomic_set_mask(1 << (channel), &frv_dma_inprogress);
+	(void)__atomic32_fetch_or(1 << (channel), &frv_dma_inprogress);
 
 /*****************************************************************************/
 /*
diff --git a/arch/frv/kernel/frv_ksyms.c b/arch/frv/kernel/frv_ksyms.c
index 86c516d96dcd..cdb4ce9960eb 100644
--- a/arch/frv/kernel/frv_ksyms.c
+++ b/arch/frv/kernel/frv_ksyms.c
@@ -58,11 +58,6 @@ EXPORT_SYMBOL(__outsl_ns);
 EXPORT_SYMBOL(__insl_ns);
 
 #ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-EXPORT_SYMBOL(atomic_test_and_ANDNOT_mask);
-EXPORT_SYMBOL(atomic_test_and_OR_mask);
-EXPORT_SYMBOL(atomic_test_and_XOR_mask);
-EXPORT_SYMBOL(atomic_add_return);
-EXPORT_SYMBOL(atomic_sub_return);
 EXPORT_SYMBOL(__xchg_32);
 EXPORT_SYMBOL(__cmpxchg_32);
 #endif
diff --git a/arch/frv/lib/Makefile b/arch/frv/lib/Makefile
index 4ff2fb1e6b16..970e8b4f1a02 100644
--- a/arch/frv/lib/Makefile
+++ b/arch/frv/lib/Makefile
@@ -5,4 +5,4 @@
 lib-y := \
 	__ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o __ucmpdi2.o \
 	checksum.o memcpy.o memset.o atomic-ops.o atomic64-ops.o \
-	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o
+	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o atomic-lib.o
diff --git a/arch/frv/lib/atomic-lib.c b/arch/frv/lib/atomic-lib.c
new file mode 100644
index 000000000000..4d1b887c248b
--- /dev/null
+++ b/arch/frv/lib/atomic-lib.c
@@ -0,0 +1,7 @@
+
+#include <linux/export.h>
+#include <asm/atomic.h>
+
+#define __ATOMIC_LIB__
+
+#include <asm/atomic_defs.h>
diff --git a/arch/frv/lib/atomic-ops.S b/arch/frv/lib/atomic-ops.S
index 5e9e6ab5dd0e..b7439a960b5b 100644
--- a/arch/frv/lib/atomic-ops.S
+++ b/arch/frv/lib/atomic-ops.S
@@ -19,116 +19,6 @@
 
 ###############################################################################
 #
-# unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v);
-#
-###############################################################################
-	.globl		atomic_test_and_ANDNOT_mask
-        .type		atomic_test_and_ANDNOT_mask,@function
-atomic_test_and_ANDNOT_mask:
-	not.p		gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	and		gr8,gr10,gr11
-	cst.p		gr11,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_test_and_ANDNOT_mask, .-atomic_test_and_ANDNOT_mask
-
-###############################################################################
-#
-# unsigned long atomic_test_and_OR_mask(unsigned long mask, volatile unsigned long *v);
-#
-###############################################################################
-	.globl		atomic_test_and_OR_mask
-        .type		atomic_test_and_OR_mask,@function
-atomic_test_and_OR_mask:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	or		gr8,gr10,gr11
-	cst.p		gr11,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_test_and_OR_mask, .-atomic_test_and_OR_mask
-
-###############################################################################
-#
-# unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsigned long *v);
-#
-###############################################################################
-	.globl		atomic_test_and_XOR_mask
-        .type		atomic_test_and_XOR_mask,@function
-atomic_test_and_XOR_mask:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	xor		gr8,gr10,gr11
-	cst.p		gr11,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_test_and_XOR_mask, .-atomic_test_and_XOR_mask
-
-###############################################################################
-#
-# int atomic_add_return(int i, atomic_t *v)
-#
-###############################################################################
-	.globl		atomic_add_return
-        .type		atomic_add_return,@function
-atomic_add_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	add		gr8,gr10,gr8
-	cst.p		gr8,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_add_return, .-atomic_add_return
-
-###############################################################################
-#
-# int atomic_sub_return(int i, atomic_t *v)
-#
-###############################################################################
-	.globl		atomic_sub_return
-        .type		atomic_sub_return,@function
-atomic_sub_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	sub		gr8,gr10,gr8
-	cst.p		gr8,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_sub_return, .-atomic_sub_return
-
-###############################################################################
-#
 # uint32_t __xchg_32(uint32_t i, uint32_t *v)
 #
 ###############################################################################
diff --git a/arch/frv/lib/atomic64-ops.S b/arch/frv/lib/atomic64-ops.S
index b6194eeac127..c4c472308a33 100644
--- a/arch/frv/lib/atomic64-ops.S
+++ b/arch/frv/lib/atomic64-ops.S
@@ -20,100 +20,6 @@
 
 ###############################################################################
 #
-# long long atomic64_inc_return(atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_inc_return
-        .type		atomic64_inc_return,@function
-atomic64_inc_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	addicc		gr9,#1,gr9,icc0
-	addxi		gr8,#0,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_inc_return, .-atomic64_inc_return
-
-###############################################################################
-#
-# long long atomic64_dec_return(atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_dec_return
-        .type		atomic64_dec_return,@function
-atomic64_dec_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	subicc		gr9,#1,gr9,icc0
-	subxi		gr8,#0,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_dec_return, .-atomic64_dec_return
-
-###############################################################################
-#
-# long long atomic64_add_return(long long i, atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_add_return
-        .type		atomic64_add_return,@function
-atomic64_add_return:
-	or.p		gr8,gr8,gr4
-	or		gr9,gr9,gr5
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	addcc		gr9,gr5,gr9,icc0
-	addx		gr8,gr4,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_add_return, .-atomic64_add_return
-
-###############################################################################
-#
-# long long atomic64_sub_return(long long i, atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_sub_return
-        .type		atomic64_sub_return,@function
-atomic64_sub_return:
-	or.p		gr8,gr8,gr4
-	or		gr9,gr9,gr5
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	subcc		gr9,gr5,gr9,icc0
-	subx		gr8,gr4,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_sub_return, .-atomic64_sub_return
-
-###############################################################################
-#
 # uint64_t __xchg_64(uint64_t i, uint64_t *v)
 #
 ###############################################################################
diff --git a/arch/frv/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c
index 0635bd6c2af3..34bb4b13e079 100644
--- a/arch/frv/mb93090-mb00/pci-frv.c
+++ b/arch/frv/mb93090-mb00/pci-frv.c
@@ -175,14 +175,6 @@ static void __init pcibios_assign_resources(void)
 			if (!r->start && r->end)
 				pci_assign_resource(dev, idx);
 		}
-
-		if (pci_probe & PCI_ASSIGN_ROMS) {
-			r = &dev->resource[PCI_ROM_RESOURCE];
-			r->end -= r->start;
-			r->start = 0;
-			if (r->end)
-				pci_assign_resource(dev, PCI_ROM_RESOURCE);
-		}
 	}
 }
 
diff --git a/arch/frv/mb93090-mb00/pci-frv.h b/arch/frv/mb93090-mb00/pci-frv.h
index a7e487fe76ed..d51992ff5a61 100644
--- a/arch/frv/mb93090-mb00/pci-frv.h
+++ b/arch/frv/mb93090-mb00/pci-frv.h
@@ -14,14 +14,6 @@
 #define DBG(x...)
 #endif
 
-#define PCI_PROBE_BIOS		0x0001
-#define PCI_PROBE_CONF1		0x0002
-#define PCI_PROBE_CONF2		0x0004
-#define PCI_NO_CHECKS		0x0400
-#define PCI_ASSIGN_ROMS		0x1000
-#define PCI_BIOS_IRQ_SCAN	0x2000
-#define PCI_ASSIGN_ALL_BUSSES	0x4000
-
 extern unsigned int __nongpreldata pci_probe;
 
 /* pci-frv.c */
diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c
index f211839e2cae..f9c86c475bbd 100644
--- a/arch/frv/mb93090-mb00/pci-vdk.c
+++ b/arch/frv/mb93090-mb00/pci-vdk.c
@@ -294,8 +294,6 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	printk("### PCIBIOS_FIXUP_BUS(%d)\n",bus->number);
 #endif
 
-	pci_read_bridge_bases(bus);
-
 	if (bus->number == 0) {
 		struct pci_dev *dev;
 		list_for_each_entry(dev, &bus->devices, bus_list) {
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 00379d64f707..70e6ae1e7006 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -33,6 +33,7 @@ generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += mmu.h
 generic-y += mmu_context.h
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 7ca73f8546cc..702ee539f87d 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -16,83 +16,52 @@
 
 #include <linux/kernel.h>
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
-
-	flags = arch_local_irq_save();
-	ret = v->counter += i;
-	arch_local_irq_restore(flags);
-	return ret;
+#define ATOMIC_OP_RETURN(op, c_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)	\
+{								\
+	h8300flags flags;					\
+	int ret;						\
+								\
+	flags = arch_local_irq_save();				\
+	ret = v->counter c_op i;				\
+	arch_local_irq_restore(flags);				\
+	return ret;						\
 }
 
-#define atomic_add(i, v) atomic_add_return(i, v)
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
-
-	flags = arch_local_irq_save();
-	ret = v->counter -= i;
-	arch_local_irq_restore(flags);
-	return ret;
+#define ATOMIC_OP(op, c_op)					\
+static inline void atomic_##op(int i, atomic_t *v)		\
+{								\
+	h8300flags flags;					\
+								\
+	flags = arch_local_irq_save();				\
+	v->counter c_op i;					\
+	arch_local_irq_restore(flags);				\
 }
 
-#define atomic_sub(i, v) atomic_sub_return(i, v)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
+ATOMIC_OP_RETURN(add, +=)
+ATOMIC_OP_RETURN(sub, -=)
 
-static inline int atomic_inc_return(atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or,  |=)
+ATOMIC_OP(xor, ^=)
 
-	flags = arch_local_irq_save();
-	v->counter++;
-	ret = v->counter;
-	arch_local_irq_restore(flags);
-	return ret;
-}
-
-#define atomic_inc(v) atomic_inc_return(v)
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
+#define atomic_add(i, v)		(void)atomic_add_return(i, v)
+#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
-static inline int atomic_dec_return(atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
+#define atomic_sub(i, v)		(void)atomic_sub_return(i, v)
+#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
 
-	flags = arch_local_irq_save();
-	--v->counter;
-	ret = v->counter;
-	arch_local_irq_restore(flags);
-	return ret;
-}
+#define atomic_inc_return(v)		atomic_add_return(1, v)
+#define atomic_dec_return(v)		atomic_sub_return(1, v)
 
-#define atomic_dec(v) atomic_dec_return(v)
+#define atomic_inc(v)			(void)atomic_inc_return(v)
+#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
 
-static inline int atomic_dec_and_test(atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
-
-	flags = arch_local_irq_save();
-	--v->counter;
-	ret = v->counter;
-	arch_local_irq_restore(flags);
-	return ret == 0;
-}
+#define atomic_dec(v)			(void)atomic_dec_return(v)
+#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
@@ -120,40 +89,4 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return ret;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *v)
-{
-	unsigned char ccr;
-	unsigned long tmp;
-
-	__asm__ __volatile__("stc ccr,%w3\n\t"
-			     "orc #0x80,ccr\n\t"
-			     "mov.l %0,%1\n\t"
-			     "and.l %2,%1\n\t"
-			     "mov.l %1,%0\n\t"
-			     "ldc %w3,ccr"
-			     : "=m"(*v), "=r"(tmp)
-			     : "g"(~(mask)), "r"(ccr));
-}
-
-static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
-{
-	unsigned char ccr;
-	unsigned long tmp;
-
-	__asm__ __volatile__("stc ccr,%w3\n\t"
-			     "orc #0x80,ccr\n\t"
-			     "mov.l %0,%1\n\t"
-			     "or.l %2,%1\n\t"
-			     "mov.l %1,%0\n\t"
-			     "ldc %w3,ccr"
-			     : "=m"(*v), "=r"(tmp)
-			     : "g"(~(mask)), "r"(ccr));
-}
-
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()    barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc()    barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
 #endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 5ade4a163558..daee37bd0999 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -28,6 +28,7 @@ generic-y += kmap_types.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += pci.h
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 93d07025f183..811d61f6422d 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -132,6 +132,10 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
diff --git a/arch/hexagon/include/asm/mm-arch-hooks.h b/arch/hexagon/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 05e8b939e416..000000000000
--- a/arch/hexagon/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_HEXAGON_MM_ARCH_HOOKS_H
-#define _ASM_HEXAGON_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_HEXAGON_MM_ARCH_HOOKS_H */
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index ccff13d33fa2..9de3ba12f6b9 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += exec.h
 generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += trace_clock.h
 generic-y += vtime.h
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 0bf03501fe5c..be4beeb77d57 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -45,8 +45,6 @@ ia64_atomic_##op (int i, atomic_t *v)					\
 ATOMIC_OP(add, +)
 ATOMIC_OP(sub, -)
 
-#undef ATOMIC_OP
-
 #define atomic_add_return(i,v)						\
 ({									\
 	int __ia64_aar_i = (i);						\
@@ -71,6 +69,16 @@ ATOMIC_OP(sub, -)
 		: ia64_atomic_sub(__ia64_asr_i, v);			\
 })
 
+ATOMIC_OP(and, &)
+ATOMIC_OP(or, |)
+ATOMIC_OP(xor, ^)
+
+#define atomic_and(i,v)	(void)ia64_atomic_and(i,v)
+#define atomic_or(i,v)	(void)ia64_atomic_or(i,v)
+#define atomic_xor(i,v)	(void)ia64_atomic_xor(i,v)
+
+#undef ATOMIC_OP
+
 #define ATOMIC64_OP(op, c_op)						\
 static __inline__ long							\
 ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
@@ -89,8 +97,6 @@ ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
 ATOMIC64_OP(add, +)
 ATOMIC64_OP(sub, -)
 
-#undef ATOMIC64_OP
-
 #define atomic64_add_return(i,v)					\
 ({									\
 	long __ia64_aar_i = (i);					\
@@ -115,6 +121,16 @@ ATOMIC64_OP(sub, -)
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
 
+ATOMIC64_OP(and, &)
+ATOMIC64_OP(or, |)
+ATOMIC64_OP(xor, ^)
+
+#define atomic64_and(i,v)	(void)ia64_atomic64_and(i,v)
+#define atomic64_or(i,v)	(void)ia64_atomic64_or(i,v)
+#define atomic64_xor(i,v)	(void)ia64_atomic64_xor(i,v)
+
+#undef ATOMIC64_OP
+
 #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index 843ba435e43b..df896a1c41d3 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -66,12 +66,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	___p1;								\
diff --git a/arch/ia64/include/asm/mm-arch-hooks.h b/arch/ia64/include/asm/mm-arch-hooks.h
deleted file mode 100644
index ab4b5c698322..000000000000
--- a/arch/ia64/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_IA64_MM_ARCH_HOOKS_H
-#define _ASM_IA64_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_IA64_MM_ARCH_HOOKS_H */
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index bc9501e36e77..d2fae054d988 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -610,9 +610,9 @@ register_intr (unsigned int gsi, int irq, unsigned char delivery,
 			       chip->name, irq_type->name);
 		chip = irq_type;
 	}
-	__irq_set_chip_handler_name_locked(irq, chip, trigger == IOSAPIC_EDGE ?
-					   handle_edge_irq : handle_level_irq,
-					   NULL);
+	irq_set_chip_handler_name_locked(irq_get_irq_data(irq), chip,
+		trigger == IOSAPIC_EDGE ? handle_edge_irq : handle_level_irq,
+		NULL);
 	return 0;
 }
 
@@ -838,7 +838,7 @@ iosapic_unregister_intr (unsigned int gsi)
 	if (iosapic_intr_info[irq].count == 0) {
 #ifdef CONFIG_SMP
 		/* Clear affinity */
-		cpumask_setall(irq_get_irq_data(irq)->affinity);
+		cpumask_setall(irq_get_affinity_mask(irq));
 #endif
 		/* Clear the interrupt information */
 		iosapic_intr_info[irq].dest = 0;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 812a1e6b3179..de4fc00dea98 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -67,7 +67,7 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 };
 void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 {
 	if (irq < NR_IRQS) {
-		cpumask_copy(irq_get_irq_data(irq)->affinity,
+		cpumask_copy(irq_get_affinity_mask(irq),
 			     cpumask_of(cpu_logical_id(hwid)));
 		irq_redir[irq] = (char) (redir & 0xff);
 	}
@@ -119,8 +119,8 @@ static void migrate_irqs(void)
 		if (irqd_is_per_cpu(data))
 			continue;
 
-		if (cpumask_any_and(data->affinity, cpu_online_mask)
-		    >= nr_cpu_ids) {
+		if (cpumask_any_and(irq_data_get_affinity_mask(data),
+				    cpu_online_mask) >= nr_cpu_ids) {
 			/*
 			 * Save it for phase 2 processing
 			 */
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index d70bf15c690a..af4eaec0f7c3 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -23,7 +23,7 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata,
 	if (irq_prepare_move(irq, cpu))
 		return -1;
 
-	__get_cached_msi_msg(idata->msi_desc, &msg);
+	__get_cached_msi_msg(irq_data_get_msi_desc(idata), &msg);
 
 	addr = msg.address_lo;
 	addr &= MSI_ADDR_DEST_ID_MASK;
@@ -36,7 +36,7 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata,
 	msg.data = data;
 
 	pci_write_msi_msg(irq, &msg);
-	cpumask_copy(idata->affinity, cpumask_of(cpu));
+	cpumask_copy(irq_data_get_affinity_mask(idata), cpumask_of(cpu));
 
 	return 0;
 }
@@ -148,7 +148,7 @@ static int dmar_msi_set_affinity(struct irq_data *data,
 	msg.address_lo |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu));
 
 	dmar_msi_write(irq, &msg);
-	cpumask_copy(data->affinity, mask);
+	cpumask_copy(irq_data_get_affinity_mask(data), mask);
 
 	return 0;
 }
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index ed6129768681..46ecc5d948aa 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -444,7 +444,7 @@ int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size)
 			if (p->pte & 0x1)
 				if (is_tr_overlap(p, va, log_size)) {
 					printk(KERN_DEBUG "Overlapped Entry"
-						"Inserted for TR Reigster!!\n");
+						"Inserted for TR Register!!\n");
 					goto out;
 			}
 		}
@@ -456,7 +456,7 @@ int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size)
 			if (p->pte & 0x1)
 				if (is_tr_overlap(p, va, log_size)) {
 					printk(KERN_DEBUG "Overlapped Entry"
-						"Inserted for TR Reigster!!\n");
+						"Inserted for TR Register!!\n");
 					goto out;
 				}
 		}
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 7cc3be9fa7c6..d89b6013c941 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -533,10 +533,9 @@ void pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
-	if (b->self) {
-		pci_read_bridge_bases(b);
+	if (b->self)
 		pcibios_fixup_bridge_resources(b->self);
-	}
+
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 	platform_pci_fixup_bus(b);
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index a0eb27b66d13..fb25065b22c6 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -175,7 +175,7 @@ static int sn_set_msi_irq_affinity(struct irq_data *data,
 	 * Release XIO resources for the old MSI PCI address
 	 */
 
-	__get_cached_msi_msg(data->msi_desc, &msg);
+	__get_cached_msi_msg(irq_data_get_msi_desc(data), &msg);
 	sn_pdev = (struct pcidev_info *)sn_irq_info->irq_pciioinfo;
 	pdev = sn_pdev->pdi_linux_pcidev;
 	provider = SN_PCIDEV_BUSPROVIDER(pdev);
@@ -206,7 +206,7 @@ static int sn_set_msi_irq_affinity(struct irq_data *data,
 	msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff);
 
 	pci_write_msi_msg(irq, &msg);
-	cpumask_copy(data->affinity, cpu_mask);
+	cpumask_copy(irq_data_get_affinity_mask(data), cpu_mask);
 
 	return 0;
 }
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index ba1cdc018731..e0eb704ca1fa 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += preempt.h
 generic-y += sections.h
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index 31bb74adba08..025e2a170493 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -94,6 +94,10 @@ static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -239,45 +243,4 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
-static __inline__ void atomic_clear_mask(unsigned long  mask, atomic_t *addr)
-{
-	unsigned long flags;
-	unsigned long tmp;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-		"# atomic_clear_mask		\n\t"
-		DCACHE_CLEAR("%0", "r5", "%1")
-		M32R_LOCK" %0, @%1;		\n\t"
-		"and	%0, %2;			\n\t"
-		M32R_UNLOCK" %0, @%1;		\n\t"
-		: "=&r" (tmp)
-		: "r" (addr), "r" (~mask)
-		: "memory"
-		__ATOMIC_CLOBBER
-	);
-	local_irq_restore(flags);
-}
-
-static __inline__ void atomic_set_mask(unsigned long  mask, atomic_t *addr)
-{
-	unsigned long flags;
-	unsigned long tmp;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-		"# atomic_set_mask		\n\t"
-		DCACHE_CLEAR("%0", "r5", "%1")
-		M32R_LOCK" %0, @%1;		\n\t"
-		"or	%0, %2;			\n\t"
-		M32R_UNLOCK" %0, @%1;		\n\t"
-		: "=&r" (tmp)
-		: "r" (addr), "r" (mask)
-		: "memory"
-		__ATOMIC_CLOBBER
-	);
-	local_irq_restore(flags);
-}
-
 #endif	/* _ASM_M32R_ATOMIC_H */
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 0c3f25ee3381..61b8931bc192 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -69,6 +69,7 @@ extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(off,size) ioremap(off,size)
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 /*
  * IO bus memory addresses are also 1:1 with the physical address
@@ -174,6 +175,11 @@ static inline void _writel(unsigned long l, unsigned long addr)
 #define iowrite16 writew
 #define iowrite32 writel
 
+#define ioread16be(addr)	be16_to_cpu(readw(addr))
+#define ioread32be(addr)	be32_to_cpu(readl(addr))
+#define iowrite16be(v, addr)	writew(cpu_to_be16(v), (addr))
+#define iowrite32be(v, addr)	writel(cpu_to_be32(v), (addr))
+
 #define mmiowb()
 
 #define flush_write_buffers() do { } while (0)  /* M32R_FIXME */
diff --git a/arch/m32r/include/asm/mm-arch-hooks.h b/arch/m32r/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 6d60b4750f41..000000000000
--- a/arch/m32r/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_M32R_MM_ARCH_HOOKS_H
-#define _ASM_M32R_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_M32R_MM_ARCH_HOOKS_H */
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index c18ddc74ef9a..62d6961e7f2b 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -156,7 +156,7 @@ void smp_flush_cache_all(void)
 	cpumask_clear_cpu(smp_processor_id(), &cpumask);
 	spin_lock(&flushcache_lock);
 	mask=cpumask_bits(&cpumask);
-	atomic_set_mask(*mask, (atomic_t *)&flushcache_cpumask);
+	atomic_or(*mask, (atomic_t *)&flushcache_cpumask);
 	send_IPI_mask(&cpumask, INVALIDATE_CACHE_IPI, 0);
 	_flush_cache_copyback_all();
 	while (flushcache_cpumask)
@@ -407,7 +407,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	flush_vma = vma;
 	flush_va = va;
 	mask=cpumask_bits(&cpumask);
-	atomic_set_mask(*mask, (atomic_t *)&flush_cpumask);
+	atomic_or(*mask, (atomic_t *)&flush_cpumask);
 
 	/*
 	 * We have to send the IPI only to
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 33013dfcd3e1..c496d48a8c8d 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -125,6 +125,13 @@ endif # M68KCLASSIC
 
 if COLDFIRE
 
+choice
+	prompt "ColdFire SoC type"
+	default M520x
+	help
+	  Select the type of ColdFire System-on-Chip (SoC) that you want
+	  to build for.
+
 config M5206
 	bool "MCF5206"
 	depends on !MMU
@@ -174,9 +181,6 @@ config M525x
 	help
 	  Freescale (Motorola) Coldfire 5251/5253 processor support.
 
-config M527x
-	bool
-
 config M5271
 	bool "MCF5271"
 	depends on !MMU
@@ -223,9 +227,6 @@ config M5307
 	help
 	  Motorola ColdFire 5307 processor support.
 
-config M53xx
-	bool
-
 config M532x
 	bool "MCF532x"
 	depends on !MMU
@@ -251,9 +252,6 @@ config M5407
 	help
 	  Motorola ColdFire 5407 processor support.
 
-config M54xx
-	bool
-
 config M547x
 	bool "MCF547x"
 	select M54xx
@@ -280,6 +278,17 @@ config M5441x
 	help
 	  Freescale Coldfire 54410/54415/54416/54417/54418 processor support.
 
+endchoice
+
+config M527x
+	bool
+
+config M53xx
+	bool
+
+config M54xx
+	bool
+
 endif # COLDFIRE
 
 
@@ -416,22 +425,18 @@ config HAVE_MBAR
 config HAVE_IPSBAR
 	bool
 
-config CLOCK_SET
-	bool "Enable setting the CPU clock frequency"
-	depends on COLDFIRE
-	default n
-	help
-	  On some CPU's you do not need to know what the core CPU clock
-	  frequency is. On these you can disable clock setting. On some
-	  traditional 68K parts, and on all ColdFire parts you need to set
-	  the appropriate CPU clock frequency. On these devices many of the
-	  onboard peripherals derive their timing from the master CPU clock
-	  frequency.
-
 config CLOCK_FREQ
 	int "Set the core clock frequency"
+	default "25000000" if M5206
+	default "54000000" if M5206e
+	default "166666666" if M520x
+	default "140000000" if M5249
+	default "150000000" if M527x || M523x
+	default "90000000" if M5307
+	default "50000000" if M5407
+	default "266000000" if M54xx
 	default "66666666"
-	depends on CLOCK_SET
+	depends on COLDFIRE
 	help
 	  Define the CPU clock frequency in use. This is the core clock
 	  frequency, it may or may not be the same as the external clock
diff --git a/arch/m68k/coldfire/intc-5272.c b/arch/m68k/coldfire/intc-5272.c
index d1e2fbad327c..47371de60427 100644
--- a/arch/m68k/coldfire/intc-5272.c
+++ b/arch/m68k/coldfire/intc-5272.c
@@ -143,8 +143,10 @@ static int intc_irq_set_type(struct irq_data *d, unsigned int type)
  * We need to be careful with the masking/acking due to the side effects
  * of masking an interrupt.
  */
-static void intc_external_irq(unsigned int irq, struct irq_desc *desc)
+static void intc_external_irq(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
+
 	irq_desc_get_chip(desc)->irq_ack(&desc->irq_data);
 	handle_simple_irq(irq, desc);
 }
diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c
index b15219ed22bf..c525e4c08f84 100644
--- a/arch/m68k/coldfire/m5272.c
+++ b/arch/m68k/coldfire/m5272.c
@@ -126,7 +126,7 @@ static struct fixed_phy_status nettel_fixed_phy_status __initdata = {
 static int __init init_BSP(void)
 {
 	m5272_uarts_init();
-	fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status);
+	fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status, -1);
 	return 0;
 }
 
diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c
index 075aaabd1360..f7836c6a6b60 100644
--- a/arch/m68k/coldfire/m54xx.c
+++ b/arch/m68k/coldfire/m54xx.c
@@ -25,6 +25,7 @@
 #include <asm/m54xxgpt.h>
 #ifdef CONFIG_MMU
 #include <asm/mmu_context.h>
+#include <linux/pfn.h>
 #endif
 
 /***************************************************************************/
@@ -91,13 +92,13 @@ static void __init mcf54xx_bootmem_alloc(void)
 	m68k_memory[0].size = _ramend - _rambase;
 
 	/* compute total pages in system */
-	num_pages = (_ramend - _rambase) >> PAGE_SHIFT;
+	num_pages = PFN_DOWN(_ramend - _rambase);
 
 	/* page numbers */
 	memstart = PAGE_ALIGN(_ramstart);
-	min_low_pfn = _rambase >> PAGE_SHIFT;
-	start_pfn = memstart >> PAGE_SHIFT;
-	max_low_pfn = _ramend >> PAGE_SHIFT;
+	min_low_pfn = PFN_DOWN(_rambase);
+	start_pfn = PFN_DOWN(memstart);
+	max_low_pfn = PFN_DOWN(_ramend);
 	high_memory = (void *)_ramend;
 
 	m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6;
diff --git a/arch/m68k/coldfire/pit.c b/arch/m68k/coldfire/pit.c
index 493b3111d4c1..d86a9ffb3f13 100644
--- a/arch/m68k/coldfire/pit.c
+++ b/arch/m68k/coldfire/pit.c
@@ -42,37 +42,28 @@ static u32 pit_cnt;
  * This is also called after resume to bring the PIT into operation again.
  */
 
-static void init_cf_pit_timer(enum clock_event_mode mode,
-                             struct clock_event_device *evt)
+static int cf_pit_set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-
-		__raw_writew(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
-		__raw_writew(PIT_CYCLES_PER_JIFFY, TA(MCFPIT_PMR));
-		__raw_writew(MCFPIT_PCSR_EN | MCFPIT_PCSR_PIE | \
-				MCFPIT_PCSR_OVW | MCFPIT_PCSR_RLD | \
-				MCFPIT_PCSR_CLK64, TA(MCFPIT_PCSR));
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-
-		__raw_writew(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-
-		__raw_writew(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
-		__raw_writew(MCFPIT_PCSR_EN | MCFPIT_PCSR_PIE | \
-				MCFPIT_PCSR_OVW | MCFPIT_PCSR_CLK64, \
-				TA(MCFPIT_PCSR));
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
+	__raw_writew(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
+	__raw_writew(PIT_CYCLES_PER_JIFFY, TA(MCFPIT_PMR));
+	__raw_writew(MCFPIT_PCSR_EN | MCFPIT_PCSR_PIE |
+		     MCFPIT_PCSR_OVW | MCFPIT_PCSR_RLD |
+		     MCFPIT_PCSR_CLK64, TA(MCFPIT_PCSR));
+	return 0;
+}
+
+static int cf_pit_set_oneshot(struct clock_event_device *evt)
+{
+	__raw_writew(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
+	__raw_writew(MCFPIT_PCSR_EN | MCFPIT_PCSR_PIE |
+		     MCFPIT_PCSR_OVW | MCFPIT_PCSR_CLK64, TA(MCFPIT_PCSR));
+	return 0;
+}
+
+static int cf_pit_shutdown(struct clock_event_device *evt)
+{
+	__raw_writew(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
+	return 0;
 }
 
 /*
@@ -88,12 +79,15 @@ static int cf_pit_next_event(unsigned long delta,
 }
 
 struct clock_event_device cf_pit_clockevent = {
-	.name		= "pit",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= init_cf_pit_timer,
-	.set_next_event	= cf_pit_next_event,
-	.shift		= 32,
-	.irq		= MCF_IRQ_PIT1,
+	.name			= "pit",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= cf_pit_shutdown,
+	.set_state_periodic	= cf_pit_set_periodic,
+	.set_state_oneshot	= cf_pit_set_oneshot,
+	.set_next_event		= cf_pit_next_event,
+	.shift			= 32,
+	.irq			= MCF_IRQ_PIT1,
 };
 
 
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 753a6237f99a..0b6b40d37b95 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -57,7 +57,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -91,6 +91,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -287,7 +288,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -320,7 +320,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -345,6 +344,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -355,6 +355,7 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -363,6 +364,7 @@ CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -448,6 +450,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -536,6 +539,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -543,6 +547,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -571,14 +576,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 1f93dcaf02e5..eeb3a8991fc4 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -55,7 +55,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -89,6 +89,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -279,7 +280,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -302,7 +302,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -327,17 +326,20 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -406,6 +408,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -494,6 +497,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -501,6 +505,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -529,14 +534,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 831b8b8b92ad..3a7006654ce9 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -55,7 +55,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -89,6 +89,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -283,7 +284,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -311,7 +311,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -336,6 +335,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -343,11 +343,13 @@ CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -428,6 +430,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -516,6 +519,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -523,6 +527,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -551,14 +556,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 91fd187c16d5..0586b323a673 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -53,7 +53,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -87,6 +87,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -277,7 +278,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -301,7 +301,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -326,17 +325,20 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -399,6 +401,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -487,6 +490,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -494,6 +498,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -522,14 +527,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 9d4934f1d2c3..ad1dbce07aa4 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -55,7 +55,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -89,6 +89,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -279,7 +280,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -302,7 +302,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -327,6 +326,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -334,11 +334,13 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -408,6 +410,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -496,6 +499,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -503,6 +507,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -531,14 +536,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/m5208evb_defconfig b/arch/m68k/configs/m5208evb_defconfig
index e7292f460af4..4c7b7938d53a 100644
--- a/arch/m68k/configs/m5208evb_defconfig
+++ b/arch/m68k/configs/m5208evb_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,17 +12,12 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_M520x=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=166666666
-CONFIG_CLOCK_DIV=2
-CONFIG_M5208EVB=y
+# CONFIG_MMU is not set
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x40000000
 CONFIG_RAMSIZE=0x2000000
 CONFIG_VECTORBASE=0x40000000
 CONFIG_KERNELBASE=0x40020000
-CONFIG_RAM16BIT=y
 CONFIG_BINFMT_FLAT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -40,24 +31,19 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_BAUDRATE=115200
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
@@ -68,8 +54,6 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_FULLDEBUG=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
+CONFIG_FULLDEBUG=y
diff --git a/arch/m68k/configs/m5249evb_defconfig b/arch/m68k/configs/m5249evb_defconfig
index 0cd4b39f325b..a782f368650f 100644
--- a/arch/m68k/configs/m5249evb_defconfig
+++ b/arch/m68k/configs/m5249evb_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,10 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5249=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=140000000
-CONFIG_CLOCK_DIV=2
 CONFIG_M5249C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -38,23 +32,18 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -62,7 +51,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
diff --git a/arch/m68k/configs/m5272c3_defconfig b/arch/m68k/configs/m5272c3_defconfig
index a60cb3509135..6f5fb92f5cbf 100644
--- a/arch/m68k/configs/m5272c3_defconfig
+++ b/arch/m68k/configs/m5272c3_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,8 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5272=y
-CONFIG_CLOCK_SET=y
 CONFIG_M5272C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -36,23 +32,18 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -61,6 +52,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
diff --git a/arch/m68k/configs/m5275evb_defconfig b/arch/m68k/configs/m5275evb_defconfig
index e6502ab7cb2f..b5d7cd1ce856 100644
--- a/arch/m68k/configs/m5275evb_defconfig
+++ b/arch/m68k/configs/m5275evb_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,11 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5275=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=150000000
-CONFIG_CLOCK_DIV=2
-CONFIG_M5275EVB=y
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00000000
@@ -39,24 +32,19 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -65,8 +53,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
diff --git a/arch/m68k/configs/m5307c3_defconfig b/arch/m68k/configs/m5307c3_defconfig
index 023812abd2e6..1b4c09461c40 100644
--- a/arch/m68k/configs/m5307c3_defconfig
+++ b/arch/m68k/configs/m5307c3_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,10 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5307=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=90000000
-CONFIG_CLOCK_DIV=2
 CONFIG_M5307C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -38,16 +32,11 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 CONFIG_SLIP=y
 CONFIG_SLIP_COMPRESSED=y
@@ -56,21 +45,17 @@ CONFIG_SLIP_COMPRESSED=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_LEGACY_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_FULLDEBUG=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
+CONFIG_FULLDEBUG=y
diff --git a/arch/m68k/configs/m5407c3_defconfig b/arch/m68k/configs/m5407c3_defconfig
index 557b39f3be90..275ad543d4bc 100644
--- a/arch/m68k/configs/m5407c3_defconfig
+++ b/arch/m68k/configs/m5407c3_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -17,9 +13,8 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5407=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=50000000
 CONFIG_M5407C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00000000
@@ -38,22 +33,17 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
@@ -63,8 +53,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
diff --git a/arch/m68k/configs/m5475evb_defconfig b/arch/m68k/configs/m5475evb_defconfig
index c5018a68819b..4f4ccd13c11b 100644
--- a/arch/m68k/configs/m5475evb_defconfig
+++ b/arch/m68k/configs/m5475evb_defconfig
@@ -1,11 +1,7 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_SYSCTL_SYSCALL=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -20,19 +16,16 @@ CONFIG_MODULES=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_COLDFIRE=y
-CONFIG_M547x=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=266000000
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x0
 CONFIG_RAMSIZE=0x2000000
 CONFIG_VECTORBASE=0x0
 CONFIG_MBAR=0xff000000
 CONFIG_KERNELBASE=0x20000
+CONFIG_PCI=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_JEDECPROBE=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 72bc187ca995..b44acacaecf4 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -54,7 +54,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -88,6 +88,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -282,7 +283,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -311,7 +311,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -343,6 +342,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -351,12 +351,14 @@ CONFIG_MACMACE=y
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
 CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -430,6 +432,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -518,6 +521,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -525,6 +529,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -553,14 +558,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 8fb65535597f..8afca3753db1 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -64,7 +64,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -98,6 +98,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -301,7 +302,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -344,7 +344,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -376,6 +375,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -391,6 +391,7 @@ CONFIG_MACMACE=y
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HP is not set
 CONFIG_BVME6000_NET=y
 CONFIG_MVME16x_NET=y
@@ -403,6 +404,7 @@ CONFIG_NE2000=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -510,6 +512,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -598,6 +601,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -605,6 +609,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -633,14 +638,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index f34491ec0126..ef00875994d9 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -52,7 +52,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -86,6 +86,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -276,7 +277,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -300,7 +300,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -325,6 +324,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -332,11 +332,13 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -399,6 +401,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -487,6 +490,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -494,6 +498,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -522,14 +527,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 3d3614d1b041..387c2bd90ff1 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -53,7 +53,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -87,6 +87,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -277,7 +278,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -301,7 +301,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -326,17 +325,20 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -399,6 +401,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -487,6 +490,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -494,6 +498,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -522,14 +527,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 643e9c93bea7..35355c1bc714 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -53,7 +53,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -87,6 +87,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -280,7 +281,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -307,7 +307,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -332,6 +331,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -341,12 +341,14 @@ CONFIG_VETH=m
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -421,6 +423,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -509,6 +512,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -516,6 +520,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -544,14 +549,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 8fecc5aa166c..8442d267b877 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -50,7 +50,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -84,6 +84,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -274,7 +275,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -298,7 +298,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -323,17 +322,20 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -400,6 +402,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -487,6 +490,7 @@ CONFIG_TEST_BPF=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -494,6 +498,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -522,14 +527,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 9902c5bfbdc8..0e1b542e1555 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -50,7 +50,7 @@ CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
 CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE=m
+CONFIG_GENEVE_CORE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -84,6 +84,7 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=m
+CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -274,7 +275,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -298,7 +298,6 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_CACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -323,6 +322,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
+CONFIG_GENEVE=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
@@ -330,11 +330,13 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
@@ -400,6 +402,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -488,6 +491,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -495,6 +499,7 @@ CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -523,14 +528,15 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DRBG_MENU=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 2d75ae246167..f2a00c591bf7 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -76,7 +76,7 @@ static void nfhd_make_request(struct request_queue *queue, struct bio *bio)
 				bvec_to_phys(&bvec));
 		sec += len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 1555bc189c7d..eb85bd9c6180 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -18,6 +18,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += mutex.h
 generic-y += percpu.h
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index e85f047fb072..039fac120cc0 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -77,6 +77,10 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, eor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -170,16 +174,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 	return c != 0;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *v)
-{
-	__asm__ __volatile__("andl %1,%0" : "+m" (*v) : ASM_DI (~(mask)));
-}
-
-static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
-{
-	__asm__ __volatile__("orl %1,%0" : "+m" (*v) : ASM_DI (mask));
-}
-
 static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
diff --git a/arch/m68k/include/asm/coldfire.h b/arch/m68k/include/asm/coldfire.h
index c94557b91448..50aa4dac9ca2 100644
--- a/arch/m68k/include/asm/coldfire.h
+++ b/arch/m68k/include/asm/coldfire.h
@@ -19,7 +19,7 @@
  *	in any case new boards come along from time to time that have yet
  *	another different clocking frequency.
  */
-#ifdef CONFIG_CLOCK_SET
+#ifdef CONFIG_CLOCK_FREQ
 #define	MCF_CLK		CONFIG_CLOCK_FREQ
 #else
 #error "Don't know what your ColdFire CPU clock frequency is??"
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 618c85d3c786..c98ac81582ac 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -413,7 +413,8 @@ static inline void isa_delay(void)
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
+#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) && \
+    !(defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE))
 /*
  * We need to define dummy functions for GENERIC_IOMAP support.
  */
@@ -467,6 +468,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
+#define ioremap_uc ioremap_nocache
 static inline void __iomem *ioremap_wt(unsigned long physaddr,
 					 unsigned long size)
 {
diff --git a/arch/m68k/include/asm/mm-arch-hooks.h b/arch/m68k/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 7e8709bc90ae..000000000000
--- a/arch/m68k/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_M68K_MM_ARCH_HOOKS_H
-#define _ASM_M68K_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_M68K_MM_ARCH_HOOKS_H */
diff --git a/arch/m68k/kernel/bootinfo_proc.c b/arch/m68k/kernel/bootinfo_proc.c
index 7ee853e1432b..2a33a9645ad8 100644
--- a/arch/m68k/kernel/bootinfo_proc.c
+++ b/arch/m68k/kernel/bootinfo_proc.c
@@ -62,12 +62,10 @@ static int __init init_bootinfo_procfs(void)
 	if (!bootinfo_size)
 		return -EINVAL;
 
-	bootinfo_copy = kmalloc(bootinfo_size, GFP_KERNEL);
+	bootinfo_copy = kmemdup(bootinfo_tmp, bootinfo_size, GFP_KERNEL);
 	if (!bootinfo_copy)
 		return -ENOMEM;
 
-	memcpy(bootinfo_copy, bootinfo_tmp, bootinfo_size);
-
 	pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_fops, NULL);
 	if (!pde) {
 		kfree(bootinfo_copy);
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index bb11dceed7ed..191610d97689 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -63,13 +63,15 @@ void __init oss_nubus_init(void)
  * Handle miscellaneous OSS interrupts.
  */
 
-static void oss_irq(unsigned int irq, struct irq_desc *desc)
+static void oss_irq(unsigned int __irq, struct irq_desc *desc)
 {
 	int events = oss->irq_pending &
-	             (OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM);
+		(OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM);
 
 #ifdef DEBUG_IRQS
 	if ((console_loglevel == 10) && !(events & OSS_IP_SCSI)) {
+		unsigned int irq = irq_desc_get_irq(desc);
+
 		printk("oss_irq: irq %u events = 0x%04X\n", irq,
 			(int) oss->irq_pending);
 	}
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index 272dde481d17..3b9e302e7a37 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -113,9 +113,10 @@ void __init psc_init(void)
  * PSC interrupt handler. It's a lot like the VIA interrupt handler.
  */
 
-static void psc_irq(unsigned int irq, struct irq_desc *desc)
+static void psc_irq(unsigned int __irq, struct irq_desc *desc)
 {
 	unsigned int offset = (unsigned int)irq_desc_get_handler_data(desc);
+	unsigned int irq = irq_desc_get_irq(desc);
 	int pIFR	= pIFRbase + offset;
 	int pIER	= pIERbase + offset;
 	int irq_num;
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 199320f3c345..df31353fd200 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -25,6 +25,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index 948d8688643c..21c4c268b86c 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -74,44 +74,14 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	int temp;
-
-	asm volatile (
-		"1:	LNKGETD %0, [%1]\n"
-		"	AND	%0, %0, %2\n"
-		"	LNKSETD	[%1] %0\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ	1b\n"
-		: "=&d" (temp)
-		: "da" (&v->counter), "bd" (~mask)
-		: "cc");
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	int temp;
-
-	asm volatile (
-		"1:	LNKGETD %0, [%1]\n"
-		"	OR	%0, %0, %2\n"
-		"	LNKSETD	[%1], %0\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ	1b\n"
-		: "=&d" (temp)
-		: "da" (&v->counter), "bd" (mask)
-		: "cc");
-}
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int result, temp;
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index f5d5898c1020..f8efe380fe8b 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -68,31 +68,14 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	__global_lock1(flags);
-	fence();
-	v->counter &= ~mask;
-	__global_unlock1(flags);
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	__global_lock1(flags);
-	fence();
-	v->counter |= mask;
-	__global_unlock1(flags);
-}
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index 5a696e507930..172b7e5efc53 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -90,12 +90,12 @@ static inline void fence(void)
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
diff --git a/arch/metag/include/asm/elf.h b/arch/metag/include/asm/elf.h
index d2baf6961794..87b0cf1e0acb 100644
--- a/arch/metag/include/asm/elf.h
+++ b/arch/metag/include/asm/elf.h
@@ -11,7 +11,7 @@
 #define R_METAG_RELBRANCH                4
 #define R_METAG_GETSETOFF                5
 
-/* Backward compatability */
+/* Backward compatibility */
 #define R_METAG_REG32OP1                 6
 #define R_METAG_REG32OP2                 7
 #define R_METAG_REG32OP3                 8
diff --git a/arch/metag/include/asm/ftrace.h b/arch/metag/include/asm/ftrace.h
index 2901f0f7d944..a2269d60a945 100644
--- a/arch/metag/include/asm/ftrace.h
+++ b/arch/metag/include/asm/ftrace.h
@@ -6,7 +6,7 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount_wrapper(void);
-#define MCOUNT_ADDR		((long)(mcount_wrapper))
+#define MCOUNT_ADDR		((unsigned long)(mcount_wrapper))
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
diff --git a/arch/metag/include/asm/mm-arch-hooks.h b/arch/metag/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b0072b2eb0de..000000000000
--- a/arch/metag/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_METAG_MM_ARCH_HOOKS_H
-#define _ASM_METAG_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_METAG_MM_ARCH_HOOKS_H */
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 9989ddb169ca..2f222f355c4b 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += device.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += syscalls.h
 generic-y += trace_clock.h
diff --git a/arch/microblaze/include/asm/ftrace.h b/arch/microblaze/include/asm/ftrace.h
index fd2fa2eca62f..da0144f40d99 100644
--- a/arch/microblaze/include/asm/ftrace.h
+++ b/arch/microblaze/include/asm/ftrace.h
@@ -3,7 +3,7 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-#define MCOUNT_ADDR		((long)(_mcount))
+#define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	8 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/microblaze/include/asm/mm-arch-hooks.h b/arch/microblaze/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 5c4065911bda..000000000000
--- a/arch/microblaze/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
-#define _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_MICROBLAZE_MM_ARCH_HOOKS_H */
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index bf4dec229437..c89da6312954 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -61,8 +61,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	/* FIXME this part of code is untested */
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		__dma_sync(page_to_phys(sg_page(sg)) + sg->offset,
-							sg->length, direction);
+		__dma_sync(sg_phys(sg), sg->length, direction);
 	}
 
 	return nents;
diff --git a/arch/microblaze/kernel/intc.c b/arch/microblaze/kernel/intc.c
index 719feee1e043..90bec7d71f85 100644
--- a/arch/microblaze/kernel/intc.c
+++ b/arch/microblaze/kernel/intc.c
@@ -11,12 +11,11 @@
 
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
+#include <linux/irqchip.h>
 #include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/bug.h>
 
-#include "../../drivers/irqchip/irqchip.h"
-
 static void __iomem *intc_baseaddr;
 
 /* No one else should require these constants, so define them locally here. */
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index c8977450e28c..67e2ef48d2d0 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -122,37 +122,29 @@ static int xilinx_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void xilinx_timer_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int xilinx_timer_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		pr_info("%s: periodic\n", __func__);
-		xilinx_timer0_start_periodic(freq_div_hz);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		pr_info("%s: oneshot\n", __func__);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-		pr_info("%s: unused\n", __func__);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		pr_info("%s: shutdown\n", __func__);
-		xilinx_timer0_stop();
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		pr_info("%s: resume\n", __func__);
-		break;
-	}
+	pr_info("%s\n", __func__);
+	xilinx_timer0_stop();
+	return 0;
+}
+
+static int xilinx_timer_set_periodic(struct clock_event_device *evt)
+{
+	pr_info("%s\n", __func__);
+	xilinx_timer0_start_periodic(freq_div_hz);
+	return 0;
 }
 
 static struct clock_event_device clockevent_xilinx_timer = {
-	.name		= "xilinx_clockevent",
-	.features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.shift		= 8,
-	.rating		= 300,
-	.set_next_event	= xilinx_timer_set_next_event,
-	.set_mode	= xilinx_timer_set_mode,
+	.name			= "xilinx_clockevent",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.shift			= 8,
+	.rating			= 300,
+	.set_next_event		= xilinx_timer_set_next_event,
+	.set_state_shutdown	= xilinx_timer_shutdown,
+	.set_state_periodic	= xilinx_timer_set_periodic,
 };
 
 static inline void timer_ack(void)
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index ae838ed5fcf2..6b8b75266801 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -863,14 +863,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	/* When called from the generic PCI probe, read PCI<->PCI bridge
-	 * bases. This is -not- called when generating the PCI tree from
-	 * the OF device-tree.
-	 */
-	if (bus->self != NULL)
-		pci_read_bridge_bases(bus);
-
-	/* Now fixup the bus bus */
+	/* Fixup the bus */
 	pcibios_setup_bus_self(bus);
 
 	/* Now fixup devices on that bus */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2a14585c90d2..752acca8de1f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1,8 +1,10 @@
 config MIPS
 	bool
 	default y
+	select ARCH_SUPPORTS_UPROBES
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_IDE
@@ -13,7 +15,6 @@ config MIPS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_BPF_JIT if !CPU_MICROMIPS
-	select ARCH_HAVE_CUSTOM_GPIO_H
 	select HAVE_FUNCTION_TRACER
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
@@ -118,6 +119,7 @@ config ATH25
 
 config ATH79
 	bool "Atheros AR71XX/AR724X/AR913X based boards"
+	select ARCH_HAS_RESET_CONTROLLER
 	select ARCH_REQUIRE_GPIOLIB
 	select BOOT_RAW
 	select CEVT_R4K
@@ -151,7 +153,6 @@ config BMIPS_GENERIC
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
 	select IRQ_MIPS_CPU
-	select RAW_IRQ_ACCESSORS
 	select DMA_NONCOHERENT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -409,6 +410,7 @@ config MIPS_MALTA
 	select CEVT_R4K
 	select CSRC_R4K
 	select CLKSRC_MIPS_GIC
+	select COMMON_CLK
 	select DMA_MAYBE_COHERENT
 	select GENERIC_ISA_DMA
 	select HAVE_PCSPKR_PLATFORM
@@ -459,6 +461,7 @@ config MIPS_SEAD3
 	select CEVT_R4K
 	select CSRC_R4K
 	select CLKSRC_MIPS_GIC
+	select COMMON_CLK
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select DMA_NONCOHERENT
@@ -899,6 +902,7 @@ config NLM_XLP_BOARD
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select ARCH_PHYS_ADDR_T_64BIT
+	select ARCH_REQUIRE_GPIOLIB
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
@@ -948,6 +952,7 @@ source "arch/mips/jazz/Kconfig"
 source "arch/mips/jz4740/Kconfig"
 source "arch/mips/lantiq/Kconfig"
 source "arch/mips/lasat/Kconfig"
+source "arch/mips/pistachio/Kconfig"
 source "arch/mips/pmcs-msp71xx/Kconfig"
 source "arch/mips/ralink/Kconfig"
 source "arch/mips/sgi-ip27/Kconfig"
@@ -1041,6 +1046,9 @@ config FW_CFE
 config ARCH_DMA_ADDR_T_64BIT
 	def_bool (HIGHMEM && ARCH_PHYS_ADDR_T_64BIT) || 64BIT
 
+config ARCH_SUPPORTS_UPROBES
+	bool
+
 config DMA_MAYBE_COHERENT
 	select DMA_NONCOHERENT
 	bool
@@ -1071,10 +1079,6 @@ config HOTPLUG_CPU
 config SYS_SUPPORTS_HOTPLUG_CPU
 	bool
 
-config I8259
-	bool
-	select IRQ_DOMAIN
-
 config MIPS_BONITO64
 	bool
 
@@ -1368,7 +1372,7 @@ config CPU_MIPS32_R2
 	  otherwise CPU_MIPS32_R1 is a safe bet for any MIPS32 system.
 
 config CPU_MIPS32_R6
-	bool "MIPS32 Release 6 (EXPERIMENTAL)"
+	bool "MIPS32 Release 6"
 	depends on SYS_HAS_CPU_MIPS32_R6
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_32BIT_KERNEL
@@ -1419,7 +1423,7 @@ config CPU_MIPS64_R2
 	  otherwise CPU_MIPS64_R1 is a safe bet for any MIPS64 system.
 
 config CPU_MIPS64_R6
-	bool "MIPS64 Release 6 (EXPERIMENTAL)"
+	bool "MIPS64 Release 6"
 	depends on SYS_HAS_CPU_MIPS64_R6
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_32BIT_KERNEL
@@ -1427,6 +1431,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
+	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
 	help
 	  Choose this option to build a kernel for release 6 or later of the
 	  MIPS64 architecture.  New MIPS processors, starting with the Warrior
@@ -1968,6 +1973,7 @@ config 32BIT
 	select TRAD_SIGNALS
 	help
 	  Select this option if you want to build a 32-bit kernel.
+
 config 64BIT
 	bool "64-bit kernel"
 	depends on CPU_SUPPORTS_64BIT_KERNEL && SYS_SUPPORTS_64BIT_KERNEL
@@ -2113,7 +2119,7 @@ config CPU_R4K_CACHE_TLB
 
 config MIPS_MT_SMP
 	bool "MIPS MT SMP support (1 TC on each available VPE)"
-	depends on SYS_SUPPORTS_MULTITHREADING
+	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select SYNC_R4K
@@ -2214,7 +2220,7 @@ config MIPS_VPE_APSP_API_MT
 
 config MIPS_CMP
 	bool "MIPS CMP framework support (DEPRECATED)"
-	depends on SYS_SUPPORTS_MIPS_CMP
+	depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6
 	select MIPS_GIC_IPI
 	select SMP
 	select SYNC_R4K
@@ -2231,7 +2237,7 @@ config MIPS_CMP
 
 config MIPS_CPS
 	bool "MIPS Coherent Processing System support"
-	depends on SYS_SUPPORTS_MIPS_CPS && !64BIT
+	depends on SYS_SUPPORTS_MIPS_CPS && !CPU_MIPSR6
 	select MIPS_CM
 	select MIPS_CPC
 	select MIPS_CPS_PM if HOTPLUG_CPU
@@ -2262,11 +2268,6 @@ config MIPS_CM
 config MIPS_CPC
 	bool
 
-config SB1_PASS_1_WORKAROUNDS
-	bool
-	depends on CPU_SB1_PASS_1
-	default y
-
 config SB1_PASS_2_WORKAROUNDS
 	bool
 	depends on CPU_SB1 && (CPU_SB1_PASS_2_2 || CPU_SB1_PASS_2)
@@ -2311,7 +2312,7 @@ config CPU_MICROMIPS
 endchoice
 
 config CPU_HAS_MSA
-	bool "Support for the MIPS SIMD Architecture (EXPERIMENTAL)"
+	bool "Support for the MIPS SIMD Architecture"
 	depends on CPU_SUPPORTS_MSA
 	depends on 64BIT || MIPS_O32_FP64_SUPPORT
 	help
@@ -2651,7 +2652,7 @@ config SECCOMP
 	  If unsure, say Y. Only embedded should say N here.
 
 config MIPS_O32_FP64_SUPPORT
-	bool "Support for O32 binaries using 64-bit FP (EXPERIMENTAL)"
+	bool "Support for O32 binaries using 64-bit FP"
 	depends on 32BIT || MIPS32_O32
 	help
 	  When this is enabled, the kernel will support use of 64-bit floating
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 3a2b775e8458..e250524021ac 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -87,15 +87,6 @@ config SB1XXX_CORELIS
 	  Select compile flags that produce code that can be processed by the
 	  Corelis mksym utility and UDB Emulator.
 
-config RUNTIME_DEBUG
-	bool "Enable run-time debugging"
-	depends on DEBUG_KERNEL
-	help
-	  If you say Y here, some debugging macros will do run-time checking.
-	  If you say N here, those macros will mostly turn to no-ops.  See
-	  arch/mips/include/asm/debug.h for debugging macros.
-	  If unsure, say N.
-
 config DEBUG_ZBOOT
 	bool "Enable compressed kernel support debugging"
 	depends on DEBUG_KERNEL && SYS_SUPPORTS_ZBOOT
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index ae2dd59050f7..252e347958f3 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -181,13 +181,6 @@ cflags-$(CONFIG_CPU_R4000_WORKAROUNDS)	+= $(call cc-option,-mfix-r4000,)
 cflags-$(CONFIG_CPU_R4400_WORKAROUNDS)	+= $(call cc-option,-mfix-r4400,)
 cflags-$(CONFIG_CPU_DADDI_WORKAROUNDS)	+= $(call cc-option,-mno-daddi,)
 
-ifdef CONFIG_CPU_SB1
-ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-KBUILD_AFLAGS_MODULE += -msb1-pass1-workarounds
-KBUILD_CFLAGS_MODULE += -msb1-pass1-workarounds
-endif
-endif
-
 # For smartmips configurations, there are hundreds of warnings due to ISA overrides
 # in assembly and header files. smartmips is only supported for MIPS32r1 onwards
 # and there is no support for 64-bit. Various '.set mips2' or '.set mips3' or
diff --git a/arch/mips/alchemy/Kconfig b/arch/mips/alchemy/Kconfig
index b9628983d620..7fa24881b708 100644
--- a/arch/mips/alchemy/Kconfig
+++ b/arch/mips/alchemy/Kconfig
@@ -6,13 +6,6 @@ config ALCHEMY_GPIOINT_AU1000
 config ALCHEMY_GPIOINT_AU1300
 	bool
 
-# select this in your board config if you don't want to use the gpio
-# namespace as documented in the manuals.  In this case however you need
-# to create the necessary gpio_* functions in your board code/headers!
-# see arch/mips/include/asm/mach-au1x00/gpio.h   for more information.
-config ALCHEMY_GPIO_INDIRECT
-	def_bool n
-
 choice
 	prompt "Machine type"
 	depends on MIPS_ALCHEMY
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index acf9a2a37f5a..79efe4c6e636 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -34,6 +34,7 @@
 #include <asm/idle.h>
 #include <asm/reboot.h>
 #include <asm/mach-au1x00/au1000.h>
+#include <asm/mach-au1x00/gpio-au1000.h>
 #include <prom.h>
 
 const char *get_system_type(void)
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 1e3b102389ef..85bb75669b0d 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -32,6 +32,7 @@
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
 #include <asm/mach-au1x00/au1000.h>
+#include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-au1x00/au1xxx_eth.h>
 #include <prom.h>
 
diff --git a/arch/mips/alchemy/common/Makefile b/arch/mips/alchemy/common/Makefile
index f64744f3b59f..23800b8e67e5 100644
--- a/arch/mips/alchemy/common/Makefile
+++ b/arch/mips/alchemy/common/Makefile
@@ -5,10 +5,5 @@
 # Makefile for the Alchemy Au1xx0 CPUs, generic files.
 #
 
-obj-y += prom.o time.o clock.o platform.o power.o \
+obj-y += prom.o time.o clock.o platform.o power.o gpiolib.o \
 	 setup.o sleeper.o dma.o dbdma.o vss.o irq.o usb.o
-
-# optional gpiolib support
-ifeq ($(CONFIG_ALCHEMY_GPIO_INDIRECT),)
- obj-$(CONFIG_GPIOLIB) += gpiolib.o
-endif
diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c
index 6e46abe0dac6..bd34f4093cd9 100644
--- a/arch/mips/alchemy/common/clock.c
+++ b/arch/mips/alchemy/common/clock.c
@@ -35,6 +35,7 @@
 
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/slab.h>
@@ -389,12 +390,11 @@ static long alchemy_calc_div(unsigned long rate, unsigned long prate,
 	return div1;
 }
 
-static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_clk,
-					int scale, int maxdiv)
+static int alchemy_clk_fgcs_detr(struct clk_hw *hw,
+				 struct clk_rate_request *req,
+				 int scale, int maxdiv)
 {
-	struct clk *pc, *bpc, *free;
+	struct clk_hw *pc, *bpc, *free;
 	long tdv, tpr, pr, nr, br, bpr, diff, lastdiff;
 	int j;
 
@@ -408,7 +408,7 @@ static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
 	 * the one that gets closest to but not over the requested rate.
 	 */
 	for (j = 0; j < 7; j++) {
-		pc = clk_get_parent_by_index(hw->clk, j);
+		pc = clk_hw_get_parent_by_index(hw, j);
 		if (!pc)
 			break;
 
@@ -416,20 +416,20 @@ static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
 		 * XXX: we would actually want clk_has_active_children()
 		 * but this is a good-enough approximation for now.
 		 */
-		if (!__clk_is_prepared(pc)) {
+		if (!clk_hw_is_prepared(pc)) {
 			if (!free)
 				free = pc;
 		}
 
-		pr = clk_get_rate(pc);
-		if (pr < rate)
+		pr = clk_hw_get_rate(pc);
+		if (pr < req->rate)
 			continue;
 
 		/* what can hardware actually provide */
-		tdv = alchemy_calc_div(rate, pr, scale, maxdiv, NULL);
+		tdv = alchemy_calc_div(req->rate, pr, scale, maxdiv, NULL);
 		nr = pr / tdv;
-		diff = rate - nr;
-		if (nr > rate)
+		diff = req->rate - nr;
+		if (nr > req->rate)
 			continue;
 
 		if (diff < lastdiff) {
@@ -448,15 +448,16 @@ static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
 	 */
 	if (lastdiff && free) {
 		for (j = (maxdiv == 4) ? 1 : scale; j <= maxdiv; j += scale) {
-			tpr = rate * j;
+			tpr = req->rate * j;
 			if (tpr < 0)
 				break;
-			pr = clk_round_rate(free, tpr);
+			pr = clk_hw_round_rate(free, tpr);
 
-			tdv = alchemy_calc_div(rate, pr, scale, maxdiv, NULL);
+			tdv = alchemy_calc_div(req->rate, pr, scale, maxdiv,
+					       NULL);
 			nr = pr / tdv;
-			diff = rate - nr;
-			if (nr > rate)
+			diff = req->rate - nr;
+			if (nr > req->rate)
 				continue;
 			if (diff < lastdiff) {
 				lastdiff = diff;
@@ -469,9 +470,14 @@ static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
 		}
 	}
 
-	*best_parent_rate = bpr;
-	*best_parent_clk = __clk_get_hw(bpc);
-	return br;
+	if (br < 0)
+		return br;
+
+	req->best_parent_rate = bpr;
+	req->best_parent_hw = bpc;
+	req->rate = br;
+
+	return 0;
 }
 
 static int alchemy_clk_fgv1_en(struct clk_hw *hw)
@@ -562,14 +568,10 @@ static unsigned long alchemy_clk_fgv1_recalc(struct clk_hw *hw,
 	return parent_rate / v;
 }
 
-static long alchemy_clk_fgv1_detr(struct clk_hw *hw, unsigned long rate,
-					unsigned long min_rate,
-					unsigned long max_rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_clk)
+static int alchemy_clk_fgv1_detr(struct clk_hw *hw,
+				 struct clk_rate_request *req)
 {
-	return alchemy_clk_fgcs_detr(hw, rate, best_parent_rate,
-				     best_parent_clk, 2, 512);
+	return alchemy_clk_fgcs_detr(hw, req, 2, 512);
 }
 
 /* Au1000, Au1100, Au15x0, Au12x0 */
@@ -696,11 +698,8 @@ static unsigned long alchemy_clk_fgv2_recalc(struct clk_hw *hw,
 	return t;
 }
 
-static long alchemy_clk_fgv2_detr(struct clk_hw *hw, unsigned long rate,
-					unsigned long min_rate,
-					unsigned long max_rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_clk)
+static int alchemy_clk_fgv2_detr(struct clk_hw *hw,
+				 struct clk_rate_request *req)
 {
 	struct alchemy_fgcs_clk *c = to_fgcs_clk(hw);
 	int scale, maxdiv;
@@ -713,8 +712,7 @@ static long alchemy_clk_fgv2_detr(struct clk_hw *hw, unsigned long rate,
 		maxdiv = 512;
 	}
 
-	return alchemy_clk_fgcs_detr(hw, rate, best_parent_rate,
-				     best_parent_clk, scale, maxdiv);
+	return alchemy_clk_fgcs_detr(hw, req, scale, maxdiv);
 }
 
 /* Au1300 larger input mux, no separate disable bit, flexible divider */
@@ -917,17 +915,13 @@ static int alchemy_clk_csrc_setr(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
-static long alchemy_clk_csrc_detr(struct clk_hw *hw, unsigned long rate,
-					unsigned long min_rate,
-					unsigned long max_rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_clk)
+static int alchemy_clk_csrc_detr(struct clk_hw *hw,
+				 struct clk_rate_request *req)
 {
 	struct alchemy_fgcs_clk *c = to_fgcs_clk(hw);
 	int scale = c->dt[2] == 3 ? 1 : 2; /* au1300 check */
 
-	return alchemy_clk_fgcs_detr(hw, rate, best_parent_rate,
-				     best_parent_clk, scale, 4);
+	return alchemy_clk_fgcs_detr(hw, req, scale, 4);
 }
 
 static struct clk_ops alchemy_clkops_csrc = {
diff --git a/arch/mips/alchemy/common/irq.c b/arch/mips/alchemy/common/irq.c
index 6cb60abfdcc9..4c496c50edf6 100644
--- a/arch/mips/alchemy/common/irq.c
+++ b/arch/mips/alchemy/common/irq.c
@@ -491,7 +491,7 @@ static int au1x_ic_settype(struct irq_data *d, unsigned int flow_type)
 	default:
 		ret = -EINVAL;
 	}
-	__irq_set_chip_handler_name_locked(d->irq, chip, handler, name);
+	irq_set_chip_handler_name_locked(d, chip, handler, name);
 
 	wmb();
 
@@ -703,7 +703,7 @@ static int au1300_gpic_settype(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	__irq_set_chip_handler_name_locked(d->irq, &au1300_gpic, hdl, name);
+	irq_set_chip_handler_name_locked(d, &au1300_gpic, hdl, name);
 
 	au1300_gpic_chgcfg(d->irq - ALCHEMY_GPIC_INT_BASE, GPIC_CFG_IC_MASK, s);
 
diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c
index 50e17e13c18b..f99d3ec17a45 100644
--- a/arch/mips/alchemy/common/time.c
+++ b/arch/mips/alchemy/common/time.c
@@ -69,11 +69,6 @@ static int au1x_rtcmatch2_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void au1x_rtcmatch2_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *cd)
-{
-}
-
 static irqreturn_t au1x_rtcmatch2_irq(int irq, void *dev_id)
 {
 	struct clock_event_device *cd = dev_id;
@@ -86,7 +81,6 @@ static struct clock_event_device au1x_rtcmatch2_clockdev = {
 	.features	= CLOCK_EVT_FEAT_ONESHOT,
 	.rating		= 1500,
 	.set_next_event = au1x_rtcmatch2_set_next_event,
-	.set_mode	= au1x_rtcmatch2_set_mode,
 	.cpumask	= cpu_all_mask,
 };
 
diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c
index c98c9ea3372c..324ad72d7c36 100644
--- a/arch/mips/alchemy/devboards/bcsr.c
+++ b/arch/mips/alchemy/devboards/bcsr.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/interrupt.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/irq.h>
@@ -88,10 +89,11 @@ EXPORT_SYMBOL_GPL(bcsr_mod);
 static void bcsr_csc_handler(unsigned int irq, struct irq_desc *d)
 {
 	unsigned short bisr = __raw_readw(bcsr_virt + BCSR_REG_INTSTAT);
+	struct irq_chip *chip = irq_desc_get_chip(d);
 
-	disable_irq_nosync(irq);
+	chained_irq_enter(chip, d);
 	generic_handle_irq(bcsr_csc_base + __ffs(bisr));
-	enable_irq(irq);
+	chained_irq_exit(chip, d);
 }
 
 static void bcsr_irq_mask(struct irq_data *d)
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 001102e197f1..bdeed9d13c6f 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -33,6 +33,7 @@
 #include <linux/spi/spi_gpio.h>
 #include <linux/spi/ads7846.h>
 #include <asm/mach-au1x00/au1000.h>
+#include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-au1x00/au1000_dma.h>
 #include <asm/mach-au1x00/au1100_mmc.h>
 #include <asm/mach-db1x00/bcsr.h>
diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index 1c64fdbe4c81..b58077008a53 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -24,6 +24,7 @@
 #include <linux/wm97xx.h>
 
 #include <asm/mach-au1x00/au1000.h>
+#include <asm/mach-au1x00/gpio-au1300.h>
 #include <asm/mach-au1x00/au1100_mmc.h>
 #include <asm/mach-au1x00/au1200fb.h>
 #include <asm/mach-au1x00/au1xxx_dbdma.h>
diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index 0fd5177e35ab..5740bcfdfc7f 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -20,6 +20,7 @@
 #include <linux/spi/flash.h>
 #include <asm/bootinfo.h>
 #include <asm/mach-au1x00/au1000.h>
+#include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-au1x00/au1xxx_eth.h>
 #include <asm/mach-au1x00/au1xxx_dbdma.h>
 #include <asm/mach-au1x00/au1xxx_psc.h>
diff --git a/arch/mips/alchemy/devboards/pm.c b/arch/mips/alchemy/devboards/pm.c
index bfeb8f3c0be6..93024dc6b314 100644
--- a/arch/mips/alchemy/devboards/pm.c
+++ b/arch/mips/alchemy/devboards/pm.c
@@ -9,7 +9,7 @@
 #include <linux/suspend.h>
 #include <linux/sysfs.h>
 #include <asm/mach-au1x00/au1000.h>
-#include <asm/mach-au1x00/gpio.h>
+#include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
 
 /*
diff --git a/arch/mips/ar7/gpio.c b/arch/mips/ar7/gpio.c
index d8dbd8f0c1d2..f4930456eb8e 100644
--- a/arch/mips/ar7/gpio.c
+++ b/arch/mips/ar7/gpio.c
@@ -21,7 +21,10 @@
 #include <linux/module.h>
 #include <linux/gpio.h>
 
-#include <asm/mach-ar7/gpio.h>
+#include <asm/mach-ar7/ar7.h>
+
+#define AR7_GPIO_MAX 32
+#define TITAN_GPIO_MAX 51
 
 struct ar7_gpio_chip {
 	void __iomem		*regs;
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index be9ff1673ded..58fca9ad5fcc 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -39,7 +39,6 @@
 
 #include <asm/addrspace.h>
 #include <asm/mach-ar7/ar7.h>
-#include <asm/mach-ar7/gpio.h>
 #include <asm/mach-ar7/prom.h>
 
 /*****************************************************************************
@@ -679,7 +678,8 @@ static int __init ar7_register_devices(void)
 	}
 
 	if (ar7_has_high_cpmac()) {
-		res = fixed_phy_add(PHY_POLL, cpmac_high.id, &fixed_phy_status);
+		res = fixed_phy_add(PHY_POLL, cpmac_high.id,
+				    &fixed_phy_status, -1);
 		if (!res) {
 			cpmac_get_mac(1, cpmac_high_data.dev_addr);
 
@@ -692,7 +692,7 @@ static int __init ar7_register_devices(void)
 	} else
 		cpmac_low_data.phy_mask = 0xffffffff;
 
-	res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status);
+	res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status, -1);
 	if (!res) {
 		cpmac_get_mac(0, cpmac_low_data.dev_addr);
 		res = platform_device_register(&cpmac_low);
diff --git a/arch/mips/ar7/setup.c b/arch/mips/ar7/setup.c
index 820b7a313d9b..7bb9a670bb73 100644
--- a/arch/mips/ar7/setup.c
+++ b/arch/mips/ar7/setup.c
@@ -23,7 +23,6 @@
 #include <asm/reboot.h>
 #include <asm/mach-ar7/ar7.h>
 #include <asm/mach-ar7/prom.h>
-#include <asm/mach-ar7/gpio.h>
 
 static void ar7_machine_restart(char *command)
 {
diff --git a/arch/mips/ath79/Makefile b/arch/mips/ath79/Makefile
index 5c9ff692ff3c..fcc382cfc770 100644
--- a/arch/mips/ath79/Makefile
+++ b/arch/mips/ath79/Makefile
@@ -8,7 +8,7 @@
 # under the terms of the GNU General Public License version 2 as published
 # by the Free Software Foundation.
 
-obj-y	:= prom.o setup.o irq.o common.o clock.o gpio.o
+obj-y	:= prom.o setup.o irq.o common.o clock.o
 
 obj-$(CONFIG_EARLY_PRINTK)		+= early_printk.o
 obj-$(CONFIG_PCI)			+= pci.o
diff --git a/arch/mips/ath79/common.h b/arch/mips/ath79/common.h
index e5ea71277f0c..ca7cc19adfea 100644
--- a/arch/mips/ath79/common.h
+++ b/arch/mips/ath79/common.h
@@ -25,9 +25,6 @@ unsigned long ath79_get_sys_clk_rate(const char *id);
 void ath79_ddr_ctrl_init(void);
 void ath79_ddr_wb_flush(unsigned int reg);
 
-void ath79_gpio_function_enable(u32 mask);
-void ath79_gpio_function_disable(u32 mask);
-void ath79_gpio_function_setup(u32 set, u32 clear);
 void ath79_gpio_init(void);
 
 #endif /* __ATH79_COMMON_H */
diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c
index afb009603f7f..807132b838b2 100644
--- a/arch/mips/ath79/irq.c
+++ b/arch/mips/ath79/irq.c
@@ -17,7 +17,6 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip.h>
 #include <linux/of_irq.h>
-#include "../../../drivers/irqchip/irqchip.h"
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
@@ -124,8 +123,6 @@ static void ar934x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 {
 	u32 status;
 
-	disable_irq_nosync(irq);
-
 	status = ath79_reset_rr(AR934X_RESET_REG_PCIE_WMAC_INT_STATUS);
 
 	if (status & AR934X_PCIE_WMAC_INT_PCIE_ALL) {
@@ -137,8 +134,6 @@ static void ar934x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 	} else {
 		spurious_interrupt();
 	}
-
-	enable_irq(irq);
 }
 
 static void ar934x_ip2_irq_init(void)
@@ -157,14 +152,12 @@ static void qca955x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 {
 	u32 status;
 
-	disable_irq_nosync(irq);
-
 	status = ath79_reset_rr(QCA955X_RESET_REG_EXT_INT_STATUS);
 	status &= QCA955X_EXT_INT_PCIE_RC1_ALL | QCA955X_EXT_INT_WMAC_ALL;
 
 	if (status == 0) {
 		spurious_interrupt();
-		goto enable;
+		return;
 	}
 
 	if (status & QCA955X_EXT_INT_PCIE_RC1_ALL) {
@@ -176,17 +169,12 @@ static void qca955x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 		/* TODO: flush DDR? */
 		generic_handle_irq(ATH79_IP2_IRQ(1));
 	}
-
-enable:
-	enable_irq(irq);
 }
 
 static void qca955x_ip3_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 {
 	u32 status;
 
-	disable_irq_nosync(irq);
-
 	status = ath79_reset_rr(QCA955X_RESET_REG_EXT_INT_STATUS);
 	status &= QCA955X_EXT_INT_PCIE_RC2_ALL |
 		  QCA955X_EXT_INT_USB1 |
@@ -194,7 +182,7 @@ static void qca955x_ip3_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 
 	if (status == 0) {
 		spurious_interrupt();
-		goto enable;
+		return;
 	}
 
 	if (status & QCA955X_EXT_INT_USB1) {
@@ -211,9 +199,6 @@ static void qca955x_ip3_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 		/* TODO: flush DDR? */
 		generic_handle_irq(ATH79_IP3_IRQ(2));
 	}
-
-enable:
-	enable_irq(irq);
 }
 
 static void qca955x_irq_init(void)
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 01a644f174dd..1ba21204ebe0 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -190,6 +190,7 @@ int get_c0_perfcount_int(void)
 {
 	return ATH79_MISC_IRQ(5);
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/bcm47xx/buttons.c b/arch/mips/bcm47xx/buttons.c
index 08a4abf09a33..52caa75bfe4e 100644
--- a/arch/mips/bcm47xx/buttons.c
+++ b/arch/mips/bcm47xx/buttons.c
@@ -396,10 +396,9 @@ static int __init bcm47xx_buttons_copy(const struct gpio_keys_button *buttons,
 {
 	size_t size = nbuttons * sizeof(*buttons);
 
-	bcm47xx_button_pdata.buttons = kmalloc(size, GFP_KERNEL);
+	bcm47xx_button_pdata.buttons = kmemdup(buttons, size, GFP_KERNEL);
 	if (!bcm47xx_button_pdata.buttons)
 		return -ENOMEM;
-	memcpy(bcm47xx_button_pdata.buttons, buttons, size);
 	bcm47xx_button_pdata.nbuttons = nbuttons;
 
 	return 0;
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 98c075f81795..17503a05938e 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -263,7 +263,7 @@ static int __init bcm47xx_register_bus_complete(void)
 	bcm47xx_leds_register();
 	bcm47xx_workarounds();
 
-	fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status);
+	fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status, -1);
 	return 0;
 }
 device_initcall(bcm47xx_register_bus_complete);
diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c
index e3e808a6c542..1a47ec2a0906 100644
--- a/arch/mips/bcm63xx/irq.c
+++ b/arch/mips/bcm63xx/irq.c
@@ -60,7 +60,7 @@ static inline int enable_irq_for_cpu(int cpu, struct irq_data *d,
 	if (m)
 		enable &= cpumask_test_cpu(cpu, m);
 	else if (irqd_affinity_was_set(d))
-		enable &= cpumask_test_cpu(cpu, d->affinity);
+		enable &= cpumask_test_cpu(cpu, irq_data_get_affinity_mask(d));
 #endif
 	return enable;
 }
@@ -365,9 +365,9 @@ static int bcm63xx_external_irq_set_type(struct irq_data *d,
 
 	irqd_set_trigger_type(d, flow_type);
 	if (flow_type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
-		__irq_set_handler_locked(d->irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 	else
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 
 	return IRQ_SET_MASK_OK_NOCOPY;
 }
diff --git a/arch/mips/bmips/irq.c b/arch/mips/bmips/irq.c
index 14552e58ff7e..e7fc6f9348ba 100644
--- a/arch/mips/bmips/irq.c
+++ b/arch/mips/bmips/irq.c
@@ -34,5 +34,5 @@ void __init arch_init_irq(void)
 	irqchip_init();
 }
 
-OF_DECLARE_2(irqchip, mips_cpu_intc, "mti,cpu-interrupt-controller",
+IRQCHIP_DECLARE(mips_cpu_intc, "mti,cpu-interrupt-controller",
 	     mips_cpu_irq_of_init);
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index dc91bde10d62..d5bdee115f22 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -78,7 +78,7 @@ endif
 
 vmlinuzobjs-y += $(obj)/piggy.o
 
-quiet_cmd_zld = LD	$@
+quiet_cmd_zld = LD      $@
       cmd_zld = $(LD) $(LDFLAGS) -Ttext $(VMLINUZ_LOAD_ADDRESS) -T $< $(vmlinuzobjs-y) -o $@
 quiet_cmd_strip = STRIP	  $@
       cmd_strip = $(STRIP) -s $@
diff --git a/arch/mips/boot/dts/netlogic/xlp_evp.dts b/arch/mips/boot/dts/netlogic/xlp_evp.dts
index 89ad04808c02..ec16ec2d8d02 100644
--- a/arch/mips/boot/dts/netlogic/xlp_evp.dts
+++ b/arch/mips/boot/dts/netlogic/xlp_evp.dts
@@ -110,6 +110,18 @@
 				read-only;
 			};
 		};
+
+		gpio: xlp_gpio@34100 {
+			compatible = "netlogic,xlp832-gpio";
+			reg = <0 0x34100 0x1000>;
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			#interrupt-cells = <2>;
+			interrupt-parent = <&pic>;
+			interrupts = <39>;
+			interrupt-controller;
+		};
 	};
 
 	chosen {
diff --git a/arch/mips/boot/dts/netlogic/xlp_fvp.dts b/arch/mips/boot/dts/netlogic/xlp_fvp.dts
index 63e62b7bd758..4bcebe641d8e 100644
--- a/arch/mips/boot/dts/netlogic/xlp_fvp.dts
+++ b/arch/mips/boot/dts/netlogic/xlp_fvp.dts
@@ -110,6 +110,18 @@
 				read-only;
 			};
 		};
+
+		gpio: xlp_gpio@34100 {
+			compatible = "netlogic,xlp208-gpio";
+			reg = <0 0x34100 0x1000>;
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			#interrupt-cells = <2>;
+			interrupt-parent = <&pic>;
+			interrupts = <39>;
+			interrupt-controller;
+		};
 	};
 
 	chosen {
diff --git a/arch/mips/boot/dts/netlogic/xlp_gvp.dts b/arch/mips/boot/dts/netlogic/xlp_gvp.dts
index bb4ecd1d47fc..b3ccb82ad7e4 100644
--- a/arch/mips/boot/dts/netlogic/xlp_gvp.dts
+++ b/arch/mips/boot/dts/netlogic/xlp_gvp.dts
@@ -69,6 +69,17 @@
 			};
 		};
 
+		gpio: xlp_gpio@114100 {
+			compatible = "netlogic,xlp980-gpio";
+			reg = <0 0x114100 0x1000>;
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			#interrupt-cells = <2>;
+			interrupt-parent = <&pic>;
+			interrupts = <39>;
+			interrupt-controller;
+		};
 	};
 
 	chosen {
diff --git a/arch/mips/boot/dts/netlogic/xlp_rvp.dts b/arch/mips/boot/dts/netlogic/xlp_rvp.dts
index 7188aed2ea2e..3783639a318a 100644
--- a/arch/mips/boot/dts/netlogic/xlp_rvp.dts
+++ b/arch/mips/boot/dts/netlogic/xlp_rvp.dts
@@ -69,6 +69,17 @@
 			};
 		};
 
+		gpio: xlp_gpio@114100 {
+			compatible = "netlogic,xlp532-gpio";
+			reg = <0 0x114100 0x1000>;
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			#interrupt-cells = <2>;
+			interrupt-parent = <&pic>;
+			interrupts = <39>;
+			interrupt-controller;
+		};
 	};
 
 	chosen {
diff --git a/arch/mips/boot/dts/netlogic/xlp_svp.dts b/arch/mips/boot/dts/netlogic/xlp_svp.dts
index 1ebd00edaacc..44d6640c1441 100644
--- a/arch/mips/boot/dts/netlogic/xlp_svp.dts
+++ b/arch/mips/boot/dts/netlogic/xlp_svp.dts
@@ -110,6 +110,18 @@
 				read-only;
 			};
 		};
+
+		gpio: xlp_gpio@34100 {
+			compatible = "netlogic,xlp316-gpio";
+			reg = <0 0x34100 0x1000>;
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			#interrupt-cells = <2>;
+			interrupt-parent = <&pic>;
+			interrupts = <39>;
+			interrupt-controller;
+		};
 	};
 
 	chosen {
diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi
index 4759cff814d1..fb7734eadbf0 100644
--- a/arch/mips/boot/dts/qca/ar9132.dtsi
+++ b/arch/mips/boot/dts/qca/ar9132.dtsi
@@ -115,6 +115,14 @@
 				interrupt-controller;
 				#interrupt-cells = <1>;
 			};
+
+			rst: reset-controller@1806001c {
+				compatible = "qca,ar9132-reset",
+						"qca,ar7100-reset";
+				reg = <0x1806001c 0x4>;
+
+				#reset-cells = <1>;
+			};
 		};
 
 		spi@1f000000 {
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
index 9eb0feef4417..36e30d65ba05 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
@@ -195,6 +195,12 @@ int cvmx_helper_board_get_mii_address(int ipd_port)
 			return 8;
 		else
 			return -1;
+	case CVMX_BOARD_TYPE_KONTRON_S1901:
+		if (ipd_port == CVMX_HELPER_BOARD_MGMT_IPD_PORT)
+			return 1;
+		else
+			return -1;
+
 	}
 
 	/* Some unknown board. Somebody forgot to update this function... */
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-util.c b/arch/mips/cavium-octeon/executive/cvmx-helper-util.c
index 453d7f66459a..b45b2975746d 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-util.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-util.c
@@ -95,9 +95,9 @@ int cvmx_helper_dump_packet(cvmx_wqe_t *work)
 	uint8_t *data_address;
 	uint8_t *end_of_data;
 
-	cvmx_dprintf("Packet Length:   %u\n", work->len);
-	cvmx_dprintf("	  Input Port:  %u\n", work->ipprt);
-	cvmx_dprintf("	  QoS:	       %u\n", work->qos);
+	cvmx_dprintf("Packet Length:   %u\n", work->word1.len);
+	cvmx_dprintf("	  Input Port:  %u\n", cvmx_wqe_get_port(work));
+	cvmx_dprintf("	  QoS:	       %u\n", cvmx_wqe_get_qos(work));
 	cvmx_dprintf("	  Buffers:     %u\n", work->word2.s.bufs);
 
 	if (work->word2.s.bufs == 0) {
@@ -127,7 +127,7 @@ int cvmx_helper_dump_packet(cvmx_wqe_t *work)
 		}
 	} else
 		buffer_ptr = work->packet_ptr;
-	remaining_bytes = work->len;
+	remaining_bytes = work->word1.len;
 
 	while (remaining_bytes) {
 		start_of_buffer =
@@ -382,6 +382,10 @@ int cvmx_helper_get_ipd_port(int interface, int port)
 		return port + 32;
 	case 3:
 		return port + 36;
+	case 4:
+		return port + 40;
+	case 5:
+		return port + 44;
 	}
 	return -1;
 }
@@ -404,6 +408,10 @@ int cvmx_helper_get_interface_num(int ipd_port)
 		return 2;
 	else if (ipd_port < 40)
 		return 3;
+	else if (ipd_port < 44)
+		return 4;
+	else if (ipd_port < 48)
+		return 5;
 	else
 		cvmx_dprintf("cvmx_helper_get_interface_num: Illegal IPD "
 			     "port number\n");
@@ -428,6 +436,10 @@ int cvmx_helper_get_interface_index_num(int ipd_port)
 		return ipd_port & 3;
 	else if (ipd_port < 40)
 		return ipd_port & 3;
+	else if (ipd_port < 44)
+		return ipd_port & 3;
+	else if (ipd_port < 48)
+		return ipd_port & 3;
 	else
 		cvmx_dprintf("cvmx_helper_get_interface_index_num: "
 			     "Illegal IPD port number\n");
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
index 7653b7e92197..a56ee590de1f 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
@@ -124,6 +124,13 @@ int __cvmx_helper_xaui_enable(int interface)
 	union cvmx_gmxx_tx_int_en gmx_tx_int_en;
 	union cvmx_pcsxx_int_en_reg pcsx_int_en_reg;
 
+	/* Setup PKND */
+	if (octeon_has_feature(OCTEON_FEATURE_PKND)) {
+		gmx_cfg.u64 = cvmx_read_csr(CVMX_GMXX_PRTX_CFG(0, interface));
+		gmx_cfg.s.pknd = cvmx_helper_get_ipd_port(interface, 0);
+		cvmx_write_csr(CVMX_GMXX_PRTX_CFG(0, interface), gmx_cfg.u64);
+	}
+
 	/* (1) Interface has already been enabled. */
 
 	/* (2) Disable GMX. */
@@ -151,7 +158,12 @@ int __cvmx_helper_xaui_enable(int interface)
 	/* (4)c Aply reset sequence */
 	xauiCtl.u64 = cvmx_read_csr(CVMX_PCSXX_CONTROL1_REG(interface));
 	xauiCtl.s.lo_pwr = 0;
-	xauiCtl.s.reset = 1;
+
+	/* Issuing a reset here seems to hang some CN68XX chips. */
+	if (!OCTEON_IS_MODEL(OCTEON_CN68XX_PASS1_X) &&
+	    !OCTEON_IS_MODEL(OCTEON_CN68XX_PASS2_X))
+		xauiCtl.s.reset = 1;
+
 	cvmx_write_csr(CVMX_PCSXX_CONTROL1_REG(interface), xauiCtl.u64);
 
 	/* Wait for PCS to come out of reset */
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c
index 7e5cf7a5e2f3..376701f41cc2 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c
@@ -83,6 +83,8 @@ static cvmx_helper_link_info_t
  */
 int cvmx_helper_get_number_of_interfaces(void)
 {
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX))
+		return 9;
 	if (OCTEON_IS_MODEL(OCTEON_CN56XX) || OCTEON_IS_MODEL(OCTEON_CN52XX))
 		return 4;
 	else
@@ -656,6 +658,21 @@ static int __cvmx_helper_global_setup_pko(void)
 	fau_to.s.tout_val = 0xfff;
 	fau_to.s.tout_enb = 0;
 	cvmx_write_csr(CVMX_IOB_FAU_TIMEOUT, fau_to.u64);
+
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX)) {
+		union cvmx_pko_reg_min_pkt min_pkt;
+
+		min_pkt.u64 = 0;
+		min_pkt.s.size1 = 59;
+		min_pkt.s.size2 = 59;
+		min_pkt.s.size3 = 59;
+		min_pkt.s.size4 = 59;
+		min_pkt.s.size5 = 59;
+		min_pkt.s.size6 = 59;
+		min_pkt.s.size7 = 59;
+		cvmx_write_csr(CVMX_PKO_REG_MIN_PKT, min_pkt.u64);
+	}
+
 	return 0;
 }
 
diff --git a/arch/mips/cavium-octeon/executive/cvmx-pko.c b/arch/mips/cavium-octeon/executive/cvmx-pko.c
index 008b881cdf64..87be167a7a6a 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-pko.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-pko.c
@@ -39,6 +39,143 @@
  * Internal state of packet output
  */
 
+static int __cvmx_pko_int(int interface, int index)
+{
+	switch (interface) {
+	case 0:
+		return index;
+	case 1:
+		return 4;
+	case 2:
+		return index + 0x08;
+	case 3:
+		return index + 0x0c;
+	case 4:
+		return index + 0x10;
+	case 5:
+		return 0x1c;
+	case 6:
+		return 0x1d;
+	case 7:
+		return 0x1e;
+	case 8:
+		return 0x1f;
+	default:
+		return -1;
+	}
+}
+
+static void __cvmx_pko_iport_config(int pko_port)
+{
+	int queue;
+	const int num_queues = 1;
+	const int base_queue = pko_port;
+	const int static_priority_end = 1;
+	const int static_priority_base = 1;
+
+	for (queue = 0; queue < num_queues; queue++) {
+		union cvmx_pko_mem_iqueue_ptrs config;
+		cvmx_cmd_queue_result_t cmd_res;
+		uint64_t *buf_ptr;
+
+		config.u64		= 0;
+		config.s.index		= queue;
+		config.s.qid		= base_queue + queue;
+		config.s.ipid		= pko_port;
+		config.s.tail		= (queue == (num_queues - 1));
+		config.s.s_tail		= (queue == static_priority_end);
+		config.s.static_p	= (static_priority_base >= 0);
+		config.s.static_q	= (queue <= static_priority_end);
+		config.s.qos_mask	= 0xff;
+
+		cmd_res = cvmx_cmd_queue_initialize(
+				CVMX_CMD_QUEUE_PKO(base_queue + queue),
+				CVMX_PKO_MAX_QUEUE_DEPTH,
+				CVMX_FPA_OUTPUT_BUFFER_POOL,
+				(CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE -
+				 CVMX_PKO_COMMAND_BUFFER_SIZE_ADJUST * 8));
+
+		WARN(cmd_res,
+		     "%s: cmd_res=%d pko_port=%d base_queue=%d num_queues=%d queue=%d\n",
+			__func__, (int)cmd_res, pko_port, base_queue,
+			num_queues, queue);
+
+		buf_ptr = (uint64_t *)cvmx_cmd_queue_buffer(
+				CVMX_CMD_QUEUE_PKO(base_queue + queue));
+		config.s.buf_ptr = cvmx_ptr_to_phys(buf_ptr) >> 7;
+		CVMX_SYNCWS;
+		cvmx_write_csr(CVMX_PKO_MEM_IQUEUE_PTRS, config.u64);
+	}
+}
+
+static void __cvmx_pko_queue_alloc_o68(void)
+{
+	int port;
+
+	for (port = 0; port < 48; port++)
+		__cvmx_pko_iport_config(port);
+}
+
+static void __cvmx_pko_port_map_o68(void)
+{
+	int port;
+	int interface, index;
+	cvmx_helper_interface_mode_t mode;
+	union cvmx_pko_mem_iport_ptrs config;
+
+	/*
+	 * Initialize every iport with the invalid eid.
+	 */
+	config.u64 = 0;
+	config.s.eid = 31; /* Invalid */
+	for (port = 0; port < 128; port++) {
+		config.s.ipid = port;
+		cvmx_write_csr(CVMX_PKO_MEM_IPORT_PTRS, config.u64);
+	}
+
+	/*
+	 * Set up PKO_MEM_IPORT_PTRS
+	 */
+	for (port = 0; port < 48; port++) {
+		interface = cvmx_helper_get_interface_num(port);
+		index = cvmx_helper_get_interface_index_num(port);
+		mode = cvmx_helper_interface_get_mode(interface);
+		if (mode == CVMX_HELPER_INTERFACE_MODE_DISABLED)
+			continue;
+
+		config.s.ipid = port;
+		config.s.qos_mask = 0xff;
+		config.s.crc = 1;
+		config.s.min_pkt = 1;
+		config.s.intr = __cvmx_pko_int(interface, index);
+		config.s.eid = config.s.intr;
+		config.s.pipe = (mode == CVMX_HELPER_INTERFACE_MODE_LOOP) ?
+			index : port;
+		cvmx_write_csr(CVMX_PKO_MEM_IPORT_PTRS, config.u64);
+	}
+}
+
+static void __cvmx_pko_chip_init(void)
+{
+	int i;
+
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX)) {
+		__cvmx_pko_port_map_o68();
+		__cvmx_pko_queue_alloc_o68();
+		return;
+	}
+
+	/*
+	 * Initialize queues
+	 */
+	for (i = 0; i < CVMX_PKO_MAX_OUTPUT_QUEUES; i++) {
+		const uint64_t priority = 8;
+
+		cvmx_pko_config_port(CVMX_PKO_MEM_QUEUE_PTRS_ILLEGAL_PID, i, 1,
+				     &priority);
+	}
+}
+
 /**
  * Call before any other calls to initialize the packet
  * output system.  This does chip global config, and should only be
@@ -47,8 +184,6 @@
 
 void cvmx_pko_initialize_global(void)
 {
-	int i;
-	uint64_t priority = 8;
 	union cvmx_pko_reg_cmd_buf config;
 
 	/*
@@ -62,9 +197,10 @@ void cvmx_pko_initialize_global(void)
 
 	cvmx_write_csr(CVMX_PKO_REG_CMD_BUF, config.u64);
 
-	for (i = 0; i < CVMX_PKO_MAX_OUTPUT_QUEUES; i++)
-		cvmx_pko_config_port(CVMX_PKO_MEM_QUEUE_PTRS_ILLEGAL_PID, i, 1,
-				     &priority);
+	/*
+	 * Chip-specific setup.
+	 */
+	__cvmx_pko_chip_init();
 
 	/*
 	 * If we aren't using all of the queues optimize PKO's
@@ -212,6 +348,9 @@ cvmx_pko_status_t cvmx_pko_config_port(uint64_t port, uint64_t base_queue,
 	int static_priority_base = -1;
 	int static_priority_end = -1;
 
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX))
+		return CVMX_PKO_SUCCESS;
+
 	if ((port >= CVMX_PKO_NUM_OUTPUT_PORTS)
 	    && (port != CVMX_PKO_MEM_QUEUE_PTRS_ILLEGAL_PID)) {
 		cvmx_dprintf("ERROR: cvmx_pko_config_port: Invalid port %llu\n",
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index d8124a3c5a85..f26c3c661cca 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -225,13 +225,14 @@ static int next_cpu_for_irq(struct irq_data *data)
 
 #ifdef CONFIG_SMP
 	int cpu;
-	int weight = cpumask_weight(data->affinity);
+	struct cpumask *mask = irq_data_get_affinity_mask(data);
+	int weight = cpumask_weight(mask);
 	struct octeon_ciu_chip_data *cd = irq_data_get_irq_chip_data(data);
 
 	if (weight > 1) {
 		cpu = cd->current_cpu;
 		for (;;) {
-			cpu = cpumask_next(cpu, data->affinity);
+			cpu = cpumask_next(cpu, mask);
 			if (cpu >= nr_cpu_ids) {
 				cpu = -1;
 				continue;
@@ -240,7 +241,7 @@ static int next_cpu_for_irq(struct irq_data *data)
 			}
 		}
 	} else if (weight == 1) {
-		cpu = cpumask_first(data->affinity);
+		cpu = cpumask_first(mask);
 	} else {
 		cpu = smp_processor_id();
 	}
@@ -662,6 +663,11 @@ static int octeon_irq_ciu_gpio_set_type(struct irq_data *data, unsigned int t)
 	irqd_set_trigger_type(data, t);
 	octeon_irq_gpio_setup(data);
 
+	if (irqd_get_trigger_type(data) & IRQ_TYPE_EDGE_BOTH)
+		irq_set_handler_locked(data, handle_edge_irq);
+	else
+		irq_set_handler_locked(data, handle_level_irq);
+
 	return IRQ_SET_MASK_OK;
 }
 
@@ -696,32 +702,23 @@ static void octeon_irq_ciu_gpio_ack(struct irq_data *data)
 	cvmx_write_csr(CVMX_GPIO_INT_CLR, mask);
 }
 
-static void octeon_irq_handle_trigger(unsigned int irq, struct irq_desc *desc)
-{
-	struct irq_data *data = irq_desc_get_irq_data(desc);
-
-	if (irqd_get_trigger_type(data) & IRQ_TYPE_EDGE_BOTH)
-		handle_edge_irq(irq, desc);
-	else
-		handle_level_irq(irq, desc);
-}
-
 #ifdef CONFIG_SMP
 
 static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
 {
 	int cpu = smp_processor_id();
 	cpumask_t new_affinity;
+	struct cpumask *mask = irq_data_get_affinity_mask(data);
 
-	if (!cpumask_test_cpu(cpu, data->affinity))
+	if (!cpumask_test_cpu(cpu, mask))
 		return;
 
-	if (cpumask_weight(data->affinity) > 1) {
+	if (cpumask_weight(mask) > 1) {
 		/*
 		 * It has multi CPU affinity, just remove this CPU
 		 * from the affinity set.
 		 */
-		cpumask_copy(&new_affinity, data->affinity);
+		cpumask_copy(&new_affinity, mask);
 		cpumask_clear_cpu(cpu, &new_affinity);
 	} else {
 		/* Otherwise, put it on lowest numbered online CPU. */
@@ -1227,8 +1224,13 @@ static int octeon_irq_gpio_map(struct irq_domain *d,
 		octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 
+	/*
+	 * Default to handle_level_irq. If the DT contains a different
+	 * trigger type, it will call the irq_set_type callback and
+	 * the handler gets updated.
+	 */
 	r = octeon_irq_set_ciu_mapping(virq, line, bit, hw,
-		octeon_irq_gpio_chip, octeon_irq_handle_trigger);
+				       octeon_irq_gpio_chip, handle_level_irq);
 	return r;
 }
 
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 56f5d080ef9d..b7fa9ae28c36 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -42,7 +42,7 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id)
 	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(coreid), action);
 
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
diff --git a/arch/mips/configs/pistachio_defconfig b/arch/mips/configs/pistachio_defconfig
index 1646cce032c3..642b50946943 100644
--- a/arch/mips/configs/pistachio_defconfig
+++ b/arch/mips/configs/pistachio_defconfig
@@ -320,7 +320,6 @@ CONFIG_KEYS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_YAMA=y
-CONFIG_SECURITY_YAMA_STACKED=y
 CONFIG_DEFAULT_SECURITY_DAC=y
 CONFIG_CRYPTO_AUTHENC=y
 CONFIG_CRYPTO_HMAC=y
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 7fe5c61a3cb8..40ec4ca3f946 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += emergency-restart.h
 generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += parport.h
 generic-y += percpu.h
@@ -15,6 +16,5 @@ generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
 generic-y += trace_clock.h
-generic-y += ucontext.h
 generic-y += user.h
 generic-y += xor.h
diff --git a/arch/mips/include/asm/abi.h b/arch/mips/include/asm/abi.h
index 7186bb51b89b..37f84078e78a 100644
--- a/arch/mips/include/asm/abi.h
+++ b/arch/mips/include/asm/abi.h
@@ -20,6 +20,10 @@ struct mips_abi {
 				     struct pt_regs *regs, sigset_t *set);
 	const unsigned long	rt_signal_return_offset;
 	const unsigned long	restart;
+
+	unsigned	off_sc_fpregs;
+	unsigned	off_sc_fpc_csr;
+	unsigned	off_sc_used_math;
 };
 
 #endif /* _ASM_ABI_H */
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 76317a70200d..867f924b05c7 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -232,6 +232,30 @@
 	.set	pop
 	.endm
 
+	.macro	ld_b	wd, off, base
+	.set	push
+	.set	mips32r2
+	.set	msa
+	ld.b	$w\wd, \off(\base)
+	.set	pop
+	.endm
+
+	.macro	ld_h	wd, off, base
+	.set	push
+	.set	mips32r2
+	.set	msa
+	ld.h	$w\wd, \off(\base)
+	.set	pop
+	.endm
+
+	.macro	ld_w	wd, off, base
+	.set	push
+	.set	mips32r2
+	.set	msa
+	ld.w	$w\wd, \off(\base)
+	.set	pop
+	.endm
+
 	.macro	ld_d	wd, off, base
 	.set	push
 	.set	mips32r2
@@ -241,6 +265,30 @@
 	.set	pop
 	.endm
 
+	.macro	st_b	wd, off, base
+	.set	push
+	.set	mips32r2
+	.set	msa
+	st.b	$w\wd, \off(\base)
+	.set	pop
+	.endm
+
+	.macro	st_h	wd, off, base
+	.set	push
+	.set	mips32r2
+	.set	msa
+	st.h	$w\wd, \off(\base)
+	.set	pop
+	.endm
+
+	.macro	st_w	wd, off, base
+	.set	push
+	.set	mips32r2
+	.set	msa
+	st.w	$w\wd, \off(\base)
+	.set	pop
+	.endm
+
 	.macro	st_d	wd, off, base
 	.set	push
 	.set	mips32r2
@@ -290,7 +338,13 @@
 #ifdef CONFIG_CPU_MICROMIPS
 #define CFC_MSA_INSN		0x587e0056
 #define CTC_MSA_INSN		0x583e0816
+#define LDB_MSA_INSN		0x58000807
+#define LDH_MSA_INSN		0x58000817
+#define LDW_MSA_INSN		0x58000827
 #define LDD_MSA_INSN		0x58000837
+#define STB_MSA_INSN		0x5800080f
+#define STH_MSA_INSN		0x5800081f
+#define STW_MSA_INSN		0x5800082f
 #define STD_MSA_INSN		0x5800083f
 #define COPY_UW_MSA_INSN	0x58f00056
 #define COPY_UD_MSA_INSN	0x58f80056
@@ -299,7 +353,13 @@
 #else
 #define CFC_MSA_INSN		0x787e0059
 #define CTC_MSA_INSN		0x783e0819
+#define LDB_MSA_INSN		0x78000820
+#define LDH_MSA_INSN		0x78000821
+#define LDW_MSA_INSN		0x78000822
 #define LDD_MSA_INSN		0x78000823
+#define STB_MSA_INSN		0x78000824
+#define STH_MSA_INSN		0x78000825
+#define STW_MSA_INSN		0x78000826
 #define STD_MSA_INSN		0x78000827
 #define COPY_UW_MSA_INSN	0x78f00059
 #define COPY_UD_MSA_INSN	0x78f80059
@@ -329,6 +389,33 @@
 	.set	pop
 	.endm
 
+	.macro	ld_b	wd, off, base
+	.set	push
+	.set	noat
+	SET_HARDFLOAT
+	addu	$1, \base, \off
+	.word	LDB_MSA_INSN | (\wd << 6)
+	.set	pop
+	.endm
+
+	.macro	ld_h	wd, off, base
+	.set	push
+	.set	noat
+	SET_HARDFLOAT
+	addu	$1, \base, \off
+	.word	LDH_MSA_INSN | (\wd << 6)
+	.set	pop
+	.endm
+
+	.macro	ld_w	wd, off, base
+	.set	push
+	.set	noat
+	SET_HARDFLOAT
+	addu	$1, \base, \off
+	.word	LDW_MSA_INSN | (\wd << 6)
+	.set	pop
+	.endm
+
 	.macro	ld_d	wd, off, base
 	.set	push
 	.set	noat
@@ -338,6 +425,33 @@
 	.set	pop
 	.endm
 
+	.macro	st_b	wd, off, base
+	.set	push
+	.set	noat
+	SET_HARDFLOAT
+	addu	$1, \base, \off
+	.word	STB_MSA_INSN | (\wd << 6)
+	.set	pop
+	.endm
+
+	.macro	st_h	wd, off, base
+	.set	push
+	.set	noat
+	SET_HARDFLOAT
+	addu	$1, \base, \off
+	.word	STH_MSA_INSN | (\wd << 6)
+	.set	pop
+	.endm
+
+	.macro	st_w	wd, off, base
+	.set	push
+	.set	noat
+	SET_HARDFLOAT
+	addu	$1, \base, \off
+	.word	STW_MSA_INSN | (\wd << 6)
+	.set	pop
+	.endm
+
 	.macro	st_d	wd, off, base
 	.set	push
 	.set	noat
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 26d436336f2e..4c42fd9af777 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -137,6 +137,10 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 ATOMIC_OPS(add, +=, addu)
 ATOMIC_OPS(sub, -=, subu)
 
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -416,6 +420,9 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 
 ATOMIC64_OPS(add, +=, daddu)
 ATOMIC64_OPS(sub, -=, dsubu)
+ATOMIC64_OP(and, &=, and)
+ATOMIC64_OP(or, |=, or)
+ATOMIC64_OP(xor, ^=, xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 7ecba84656d4..752e0b86c171 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -133,12 +133,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
diff --git a/arch/mips/include/asm/cdmm.h b/arch/mips/include/asm/cdmm.h
index 16e22ce9719f..bece2064cc8c 100644
--- a/arch/mips/include/asm/cdmm.h
+++ b/arch/mips/include/asm/cdmm.h
@@ -53,7 +53,7 @@ struct mips_cdmm_driver {
  * mips_cdmm_phys_base() - Choose a physical base address for CDMM region.
  *
  * Picking a suitable physical address at which to map the CDMM region is
- * platform specific, so this weak function can be defined by platform code to
+ * platform specific, so this function can be defined by platform code to
  * pick a suitable value if none is configured by the bootloader.
  *
  * This address must be 32kB aligned, and the region occupies a maximum of 32kB
@@ -61,7 +61,7 @@ struct mips_cdmm_driver {
  *
  * Returns:	Physical base address for CDMM region, or 0 on failure.
  */
-phys_addr_t __weak mips_cdmm_phys_base(void);
+phys_addr_t mips_cdmm_phys_base(void);
 
 extern struct bus_type mips_cdmm_bustype;
 void __iomem *mips_cdmm_early_probe(unsigned int dev_type);
diff --git a/arch/mips/include/asm/cevt-r4k.h b/arch/mips/include/asm/cevt-r4k.h
index f0edf6fcd002..2e13a038d260 100644
--- a/arch/mips/include/asm/cevt-r4k.h
+++ b/arch/mips/include/asm/cevt-r4k.h
@@ -21,7 +21,6 @@ DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 
 void mips_event_handler(struct clock_event_device *dev);
 int c0_compare_int_usable(void);
-void mips_set_clock_mode(enum clock_event_mode, struct clock_event_device *);
 irqreturn_t c0_compare_interrupt(int, void *);
 
 extern struct irqaction c0_compare_irqaction;
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index f25de771f7ed..9801ac982655 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -411,4 +411,8 @@
 # define cpu_has_cdmm		(cpu_data[0].options & MIPS_CPU_CDMM)
 #endif
 
+#ifndef cpu_has_small_pages
+# define cpu_has_small_pages	(cpu_data[0].options & MIPS_CPU_SP)
+#endif
+
 #endif /* __ASM_CPU_FEATURES_H */
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index d41e8e284825..abee2bfd10dc 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -77,6 +77,10 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	 */
 #endif
 
+#ifdef CONFIG_SYS_HAS_CPU_MIPS64_R6
+	case CPU_I6400:
+#endif
+
 #ifdef CONFIG_SYS_HAS_CPU_R3000
 	case CPU_R2000:
 	case CPU_R3000:
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index e46e40602af3..cd89e9855775 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -120,6 +120,7 @@
 #define PRID_IMP_PROAPTIV_MP	0xa300
 #define PRID_IMP_M5150		0xa700
 #define PRID_IMP_P5600		0xa800
+#define PRID_IMP_I6400		0xa900
 
 /*
  * These are the PRID's for when 23:16 == PRID_COMP_SIBYTE
@@ -307,6 +308,7 @@ enum cpu_type_enum {
 	CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350,
 	CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, CPU_LOONGSON1, CPU_M14KC,
 	CPU_M14KEC, CPU_INTERAPTIV, CPU_P5600, CPU_PROAPTIV, CPU_1074K, CPU_M5150,
+	CPU_I6400,
 
 	/*
 	 * MIPS64 class processors
@@ -382,6 +384,7 @@ enum cpu_type_enum {
 #define MIPS_CPU_XPA		0x2000000000ull /* CPU supports Extended Physical Addressing */
 #define MIPS_CPU_CDMM		0x4000000000ull	/* CPU has Common Device Memory Map */
 #define MIPS_CPU_BP_GHIST	0x8000000000ull /* R12K+ Branch Prediction Global History */
+#define MIPS_CPU_SP		0x10000000000ull /* Small (1KB) page support */
 
 /*
  * CPU ASE encodings
diff --git a/arch/mips/include/asm/debug.h b/arch/mips/include/asm/debug.h
deleted file mode 100644
index 1fd5a2b39445..000000000000
--- a/arch/mips/include/asm/debug.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * Debug macros for run-time debugging.
- * Turned on/off with CONFIG_RUNTIME_DEBUG option.
- *
- * Copyright (C) 2001 MontaVista Software Inc.
- * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- */
-
-#ifndef _ASM_DEBUG_H
-#define _ASM_DEBUG_H
-
-
-/*
- * run-time macros for catching spurious errors.  Eable CONFIG_RUNTIME_DEBUG in
- * kernel hacking config menu to use them.
- *
- * Use them as run-time debugging aid.  NEVER USE THEM AS ERROR HANDLING CODE!!!
- */
-
-#ifdef CONFIG_RUNTIME_DEBUG
-
-#include <linux/kernel.h>
-
-#define db_assert(x)  if (!(x)) { \
-	panic("assertion failed at %s:%d: %s", __FILE__, __LINE__, #x); }
-#define db_warn(x)  if (!(x)) { \
-	printk(KERN_WARNING "warning at %s:%d: %s", __FILE__, __LINE__, #x); }
-#define db_verify(x, y) db_assert(x y)
-#define db_verify_warn(x, y) db_warn(x y)
-#define db_run(x)  do { x; } while (0)
-
-#else
-
-#define db_assert(x)
-#define db_warn(x)
-#define db_verify(x, y) x
-#define db_verify_warn(x, y) x
-#define db_run(x)
-
-#endif
-
-#endif /* _ASM_DEBUG_H */
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index f19e890b99d2..53b26933b12c 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -382,7 +382,9 @@ do {									\
    instruction set this cpu supports.  This could be done in userspace,
    but it's not easy, and we've already done it here.  */
 
-#define ELF_HWCAP	(0)
+#define ELF_HWCAP	(elf_hwcap)
+extern unsigned int elf_hwcap;
+#include <asm/hwcap.h>
 
 /*
  * This yields a string that ld.so will use to load implementation
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 084780b355aa..9cbf383b8834 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -74,7 +74,7 @@ static inline int __enable_fpu(enum fpu_mode mode)
 		goto fr_common;
 
 	case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6) \
+#if !(defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) \
       || defined(CONFIG_64BIT))
 		/* we only have a 32-bit FPU */
 		return SIGFPE;
@@ -164,25 +164,30 @@ static inline int own_fpu(int restore)
 	return ret;
 }
 
-static inline void lose_fpu(int save)
+static inline void lose_fpu_inatomic(int save, struct task_struct *tsk)
 {
-	preempt_disable();
 	if (is_msa_enabled()) {
 		if (save) {
-			save_msa(current);
-			current->thread.fpu.fcr31 =
+			save_msa(tsk);
+			tsk->thread.fpu.fcr31 =
 					read_32bit_cp1_register(CP1_STATUS);
 		}
 		disable_msa();
-		clear_thread_flag(TIF_USEDMSA);
+		clear_tsk_thread_flag(tsk, TIF_USEDMSA);
 		__disable_fpu();
 	} else if (is_fpu_owner()) {
 		if (save)
-			_save_fp(current);
+			_save_fp(tsk);
 		__disable_fpu();
 	}
-	KSTK_STATUS(current) &= ~ST0_CU1;
-	clear_thread_flag(TIF_USEDFPU);
+	KSTK_STATUS(tsk) &= ~ST0_CU1;
+	clear_tsk_thread_flag(tsk, TIF_USEDFPU);
+}
+
+static inline void lose_fpu(int save)
+{
+	preempt_disable();
+	lose_fpu_inatomic(save, current);
 	preempt_enable();
 }
 
diff --git a/arch/mips/include/asm/gpio.h b/arch/mips/include/asm/gpio.h
deleted file mode 100644
index 06e46faf862d..000000000000
--- a/arch/mips/include/asm/gpio.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_MIPS_GPIO_H
-#define __ASM_MIPS_GPIO_H
-
-#include <gpio.h>
-
-#endif /* __ASM_MIPS_GPIO_H */
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index f0db99f8defe..15e0fecbc300 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -49,7 +49,7 @@ extern int cp0_compare_irq_shift;
 extern int cp0_perfcount_irq;
 extern int cp0_fdc_irq;
 
-extern int __weak get_c0_fdc_int(void);
+extern int get_c0_fdc_int(void);
 
 void arch_trigger_all_cpu_backtrace(bool);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 608aa57799c8..e77672539e8e 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -26,14 +26,29 @@
 #define NOP_INSN "nop"
 #endif
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\t" NOP_INSN "\n\t"
 		"nop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
-		: :  "i" (key) : : l_yes);
+		: :  "i" (&((char *)key)[branch]) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\tj %l[l_yes]\n\t"
+		"nop\n\t"
+		".pushsection __jump_table,  \"aw\"\n\t"
+		WORD_INSN " 1b, %l[l_yes], %0\n\t"
+		".popsection\n\t"
+		: :  "i" (&((char *)key)[branch]) : : l_yes);
+
 	return false;
 l_yes:
 	return true;
diff --git a/arch/mips/include/asm/kdebug.h b/arch/mips/include/asm/kdebug.h
index cba22ab7ad4d..8e3d08e739c1 100644
--- a/arch/mips/include/asm/kdebug.h
+++ b/arch/mips/include/asm/kdebug.h
@@ -11,7 +11,9 @@ enum die_val {
 	DIE_PAGE_FAULT,
 	DIE_BREAK,
 	DIE_SSTEPBP,
-	DIE_MSAFP
+	DIE_MSAFP,
+	DIE_UPROBE,
+	DIE_UPROBE_XOL,
 };
 
 #endif /* _ASM_MIPS_KDEBUG_H */
diff --git a/arch/mips/include/asm/linkage.h b/arch/mips/include/asm/linkage.h
index 2767dda9e309..99651b0ea7c7 100644
--- a/arch/mips/include/asm/linkage.h
+++ b/arch/mips/include/asm/linkage.h
@@ -5,7 +5,6 @@
 #include <asm/asm.h>
 #endif
 
-#define __weak __attribute__((weak))
 #define cond_syscall(x) asm(".weak\t" #x "\n" #x "\t=\tsys_ni_syscall")
 #define SYSCALL_ALIAS(alias, name)					\
 	asm ( #alias " = " #name "\n\t.globl " #alias)
diff --git a/arch/mips/include/asm/maar.h b/arch/mips/include/asm/maar.h
index 6c62b0f899c0..b02891f9caaf 100644
--- a/arch/mips/include/asm/maar.h
+++ b/arch/mips/include/asm/maar.h
@@ -26,7 +26,7 @@
  *
  * Return:	The number of MAAR pairs configured.
  */
-unsigned __weak platform_maar_init(unsigned num_pairs);
+unsigned platform_maar_init(unsigned num_pairs);
 
 /**
  * write_maar_pair() - write to a pair of MAARs
diff --git a/arch/mips/include/asm/mach-ar7/ar7.h b/arch/mips/include/asm/mach-ar7/ar7.h
index a47ea0c85248..468cbd61b906 100644
--- a/arch/mips/include/asm/mach-ar7/ar7.h
+++ b/arch/mips/include/asm/mach-ar7/ar7.h
@@ -203,4 +203,8 @@ static inline void ar7_device_off(u32 bit)
 int __init ar7_gpio_init(void);
 void __init ar7_init_clocks(void);
 
+/* Board specific GPIO functions */
+int ar7_gpio_enable(unsigned gpio);
+int ar7_gpio_disable(unsigned gpio);
+
 #endif /* __AR7_H__ */
diff --git a/arch/mips/include/asm/mach-ath25/gpio.h b/arch/mips/include/asm/mach-ath25/gpio.h
deleted file mode 100644
index 713564b8e8ef..000000000000
--- a/arch/mips/include/asm/mach-ath25/gpio.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __ASM_MACH_ATH25_GPIO_H
-#define __ASM_MACH_ATH25_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#define gpio_get_value __gpio_get_value
-#define gpio_set_value __gpio_set_value
-#define gpio_cansleep __gpio_cansleep
-#define gpio_to_irq __gpio_to_irq
-
-static inline int irq_to_gpio(unsigned irq)
-{
-	return -EINVAL;
-}
-
-#endif	/* __ASM_MACH_ATH25_GPIO_H */
diff --git a/arch/mips/include/asm/mach-ath79/gpio.h b/arch/mips/include/asm/mach-ath79/gpio.h
deleted file mode 100644
index 60dcb62785b4..000000000000
--- a/arch/mips/include/asm/mach-ath79/gpio.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  Atheros AR71XX/AR724X/AR913X GPIO API definitions
- *
- *  Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org>
- *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms of the GNU General Public License version 2 as published
- *  by the Free Software Foundation.
- *
- */
-
-#ifndef __ASM_MACH_ATH79_GPIO_H
-#define __ASM_MACH_ATH79_GPIO_H
-
-#define ARCH_NR_GPIOS	64
-#include <asm-generic/gpio.h>
-
-int gpio_to_irq(unsigned gpio);
-int irq_to_gpio(unsigned irq);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-
-#define gpio_cansleep	__gpio_cansleep
-
-#endif /* __ASM_MACH_ATH79_GPIO_H */
diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
index 9785e4ebb450..adde1fa5097e 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
@@ -266,6 +266,17 @@ static inline int alchemy_gpio1_to_irq(int gpio)
 	return -ENXIO;
 }
 
+/* On Au1000, Au1500 and Au1100 GPIOs won't work as inputs before
+ * SYS_PININPUTEN is written to at least once.  On Au1550/Au1200/Au1300 this
+ * register enables use of GPIOs as wake source.
+ */
+static inline void alchemy_gpio1_input_enable(void)
+{
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
+	__raw_writel(0, base + 0x110);		/* the write op is key */
+	wmb();
+}
+
 /*
  * GPIO2 block macros for common linux GPIO functions. The 'gpio'
  * parameter must be in range of ALCHEMY_GPIO2_BASE..ALCHEMY_GPIO2_MAX.
@@ -518,141 +529,4 @@ static inline int alchemy_irq_to_gpio(int irq)
 	return -ENXIO;
 }
 
-/**********************************************************************/
-
-/* Linux gpio framework integration.
- *
- * 4 use cases of Au1000-Au1200 GPIOS:
- *(1) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=y:
- *	Board must register gpiochips.
- *(2) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=n:
- *	2 (1 for Au1000) gpio_chips are registered.
- *
- *(3) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=y:
- *	the boards' gpio.h must provide the linux gpio wrapper functions,
- *
- *(4) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=n:
- *	inlinable gpio functions are provided which enable access to the
- *	Au1000 gpios only by using the numbers straight out of the data-
- *	sheets.
-
- * Cases 1 and 3 are intended for boards which want to provide their own
- * GPIO namespace and -operations (i.e. for example you have 8 GPIOs
- * which are in part provided by spare Au1000 GPIO pins and in part by
- * an external FPGA but you still want them to be accssible in linux
- * as gpio0-7. The board can of course use the alchemy_gpioX_* functions
- * as required).
- */
-
-#ifndef CONFIG_GPIOLIB
-
-#ifdef CONFIG_ALCHEMY_GPIOINT_AU1000
-
-#ifndef CONFIG_ALCHEMY_GPIO_INDIRECT	/* case (4) */
-
-static inline int gpio_direction_input(int gpio)
-{
-	return alchemy_gpio_direction_input(gpio);
-}
-
-static inline int gpio_direction_output(int gpio, int v)
-{
-	return alchemy_gpio_direction_output(gpio, v);
-}
-
-static inline int gpio_get_value(int gpio)
-{
-	return alchemy_gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(int gpio, int v)
-{
-	alchemy_gpio_set_value(gpio, v);
-}
-
-static inline int gpio_get_value_cansleep(unsigned gpio)
-{
-	return gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value_cansleep(unsigned gpio, int value)
-{
-	gpio_set_value(gpio, value);
-}
-
-static inline int gpio_is_valid(int gpio)
-{
-	return alchemy_gpio_is_valid(gpio);
-}
-
-static inline int gpio_cansleep(int gpio)
-{
-	return alchemy_gpio_cansleep(gpio);
-}
-
-static inline int gpio_to_irq(int gpio)
-{
-	return alchemy_gpio_to_irq(gpio);
-}
-
-static inline int irq_to_gpio(int irq)
-{
-	return alchemy_irq_to_gpio(irq);
-}
-
-static inline int gpio_request(unsigned gpio, const char *label)
-{
-	return 0;
-}
-
-static inline int gpio_request_one(unsigned gpio,
-					unsigned long flags, const char *label)
-{
-	return 0;
-}
-
-static inline int gpio_request_array(struct gpio *array, size_t num)
-{
-	return 0;
-}
-
-static inline void gpio_free(unsigned gpio)
-{
-}
-
-static inline void gpio_free_array(struct gpio *array, size_t num)
-{
-}
-
-static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
-{
-	return -ENOSYS;
-}
-
-static inline int gpio_export(unsigned gpio, bool direction_may_change)
-{
-	return -ENOSYS;
-}
-
-static inline int gpio_export_link(struct device *dev, const char *name,
-				   unsigned gpio)
-{
-	return -ENOSYS;
-}
-
-static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
-{
-	return -ENOSYS;
-}
-
-static inline void gpio_unexport(unsigned gpio)
-{
-}
-
-#endif	/* !CONFIG_ALCHEMY_GPIO_INDIRECT */
-
-#endif	/* CONFIG_ALCHEMY_GPIOINT_AU1000 */
-
-#endif	/* !CONFIG_GPIOLIB */
-
 #endif /* _ALCHEMY_GPIO_AU1000_H_ */
diff --git a/arch/mips/include/asm/mach-au1x00/gpio.h b/arch/mips/include/asm/mach-au1x00/gpio.h
deleted file mode 100644
index 22e7ff17fc48..000000000000
--- a/arch/mips/include/asm/mach-au1x00/gpio.h
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- * Alchemy GPIO support.
- *
- * With CONFIG_GPIOLIB=y different types of on-chip GPIO can be supported within
- *  the same kernel image.
- * With CONFIG_GPIOLIB=n, your board must select ALCHEMY_GPIOINT_AU1XXX for the
- *  appropriate CPU type (AU1000 currently).
- */
-
-#ifndef _ALCHEMY_GPIO_H_
-#define _ALCHEMY_GPIO_H_
-
-#include <asm/mach-au1x00/au1000.h>
-#include <asm/mach-au1x00/gpio-au1000.h>
-#include <asm/mach-au1x00/gpio-au1300.h>
-
-/* On Au1000, Au1500 and Au1100 GPIOs won't work as inputs before
- * SYS_PININPUTEN is written to at least once.  On Au1550/Au1200/Au1300 this
- * register enables use of GPIOs as wake source.
- */
-static inline void alchemy_gpio1_input_enable(void)
-{
-	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
-	__raw_writel(0, base + 0x110);		/* the write op is key */
-	wmb();
-}
-
-
-/* Linux gpio framework integration.
-*
-* 4 use cases of Alchemy GPIOS:
-*(1) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=y:
-*	Board must register gpiochips.
-*(2) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=n:
-*	A gpiochip for the 75 GPIOs is registered.
-*
-*(3) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=y:
-*	the boards' gpio.h must provide	the linux gpio wrapper functions,
-*
-*(4) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=n:
-*	inlinable gpio functions are provided which enable access to the
-*	Au1300 gpios only by using the numbers straight out of the data-
-*	sheets.
-
-* Cases 1 and 3 are intended for boards which want to provide their own
-* GPIO namespace and -operations (i.e. for example you have 8 GPIOs
-* which are in part provided by spare Au1300 GPIO pins and in part by
-* an external FPGA but you still want them to be accssible in linux
-* as gpio0-7. The board can of course use the alchemy_gpioX_* functions
-* as required).
-*/
-
-#ifdef CONFIG_GPIOLIB
-
-/* wraps the cpu-dependent irq_to_gpio functions */
-/* FIXME: gpiolib needs an irq_to_gpio hook */
-static inline int __au_irq_to_gpio(unsigned int irq)
-{
-	switch (alchemy_get_cputype()) {
-	case ALCHEMY_CPU_AU1000...ALCHEMY_CPU_AU1200:
-		return alchemy_irq_to_gpio(irq);
-	case ALCHEMY_CPU_AU1300:
-		return au1300_irq_to_gpio(irq);
-	}
-	return -EINVAL;
-}
-
-
-/* using gpiolib to provide up to 2 gpio_chips for on-chip gpios */
-#ifndef CONFIG_ALCHEMY_GPIO_INDIRECT	/* case (2) */
-
-/* get everything through gpiolib */
-#define gpio_to_irq	__gpio_to_irq
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-#define irq_to_gpio	__au_irq_to_gpio
-
-#include <asm-generic/gpio.h>
-
-#endif	/* !CONFIG_ALCHEMY_GPIO_INDIRECT */
-
-
-#endif	/* CONFIG_GPIOLIB */
-
-#endif	/* _ALCHEMY_GPIO_H_ */
diff --git a/arch/mips/include/asm/mach-bcm47xx/gpio.h b/arch/mips/include/asm/mach-bcm47xx/gpio.h
deleted file mode 100644
index 90daefa24a4d..000000000000
--- a/arch/mips/include/asm/mach-bcm47xx/gpio.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef __ASM_MIPS_MACH_BCM47XX_GPIO_H
-#define __ASM_MIPS_MACH_BCM47XX_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#define gpio_get_value __gpio_get_value
-#define gpio_set_value __gpio_set_value
-
-#define gpio_cansleep __gpio_cansleep
-#define gpio_to_irq __gpio_to_irq
-
-static inline int irq_to_gpio(unsigned int irq)
-{
-	return -EINVAL;
-}
-
-#endif
diff --git a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h b/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
deleted file mode 100644
index 11d3b572b1b3..000000000000
--- a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#include <asm/mach-generic/dma-coherence.h>
-
-#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-bcm63xx/gpio.h b/arch/mips/include/asm/mach-bcm63xx/gpio.h
deleted file mode 100644
index 1eb534de8e3b..000000000000
--- a/arch/mips/include/asm/mach-bcm63xx/gpio.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef __ASM_MIPS_MACH_BCM63XX_GPIO_H
-#define __ASM_MIPS_MACH_BCM63XX_GPIO_H
-
-#include <bcm63xx_gpio.h>
-
-#define gpio_to_irq(gpio)	-1
-
-#define gpio_get_value __gpio_get_value
-#define gpio_set_value __gpio_set_value
-
-#define gpio_cansleep __gpio_cansleep
-
-#include <asm-generic/gpio.h>
-
-#endif /* __ASM_MIPS_MACH_BCM63XX_GPIO_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/gpio.h b/arch/mips/include/asm/mach-cavium-octeon/gpio.h
deleted file mode 100644
index 34e9f7aabab4..000000000000
--- a/arch/mips/include/asm/mach-cavium-octeon/gpio.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __ASM_MACH_CAVIUM_OCTEON_GPIO_H
-#define __ASM_MACH_CAVIUM_OCTEON_GPIO_H
-
-#ifdef CONFIG_GPIOLIB
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-#else
-int gpio_request(unsigned gpio, const char *label);
-void gpio_free(unsigned gpio);
-int gpio_direction_input(unsigned gpio);
-int gpio_direction_output(unsigned gpio, int value);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-#endif
-
-#include <asm-generic/gpio.h>
-
-#define gpio_to_irq	__gpio_to_irq
-
-#endif /* __ASM_MACH_GENERIC_GPIO_H */
diff --git a/arch/mips/include/asm/mach-generic/gpio.h b/arch/mips/include/asm/mach-generic/gpio.h
deleted file mode 100644
index b4e70208da64..000000000000
--- a/arch/mips/include/asm/mach-generic/gpio.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __ASM_MACH_GENERIC_GPIO_H
-#define __ASM_MACH_GENERIC_GPIO_H
-
-#ifdef CONFIG_GPIOLIB
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-#else
-int gpio_request(unsigned gpio, const char *label);
-void gpio_free(unsigned gpio);
-int gpio_direction_input(unsigned gpio);
-int gpio_direction_output(unsigned gpio, int value);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-#endif
-int gpio_to_irq(unsigned gpio);
-int irq_to_gpio(unsigned irq);
-
-#include <asm-generic/gpio.h>		/* cansleep wrappers */
-
-#endif /* __ASM_MACH_GENERIC_GPIO_H */
diff --git a/arch/mips/include/asm/mach-jz4740/gpio.h b/arch/mips/include/asm/mach-jz4740/gpio.h
index eaacba79cf18..bf8c3e1860e7 100644
--- a/arch/mips/include/asm/mach-jz4740/gpio.h
+++ b/arch/mips/include/asm/mach-jz4740/gpio.h
@@ -73,8 +73,6 @@ int jz_gpio_port_direction_output(int port, uint32_t mask);
 void jz_gpio_port_set_value(int port, uint32_t value, uint32_t mask);
 uint32_t jz_gpio_port_get_value(int port, uint32_t mask);
 
-#include <asm/mach-generic/gpio.h>
-
 #define JZ_GPIO_PORTA(x) ((x) + 32 * 0)
 #define JZ_GPIO_PORTB(x) ((x) + 32 * 1)
 #define JZ_GPIO_PORTC(x) ((x) + 32 * 2)
diff --git a/arch/mips/include/asm/mach-lantiq/gpio.h b/arch/mips/include/asm/mach-lantiq/gpio.h
deleted file mode 100644
index 9ba1caebca5f..000000000000
--- a/arch/mips/include/asm/mach-lantiq/gpio.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_MIPS_MACH_LANTIQ_GPIO_H
-#define __ASM_MIPS_MACH_LANTIQ_GPIO_H
-
-#define gpio_to_irq __gpio_to_irq
-
-#define gpio_get_value __gpio_get_value
-#define gpio_set_value __gpio_set_value
-
-#define gpio_cansleep __gpio_cansleep
-
-#include <asm-generic/gpio.h>
-
-#endif
diff --git a/arch/mips/include/asm/mach-loongson64/gpio.h b/arch/mips/include/asm/mach-loongson64/gpio.h
deleted file mode 100644
index b3b216904a9a..000000000000
--- a/arch/mips/include/asm/mach-loongson64/gpio.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Loongson GPIO Support
- *
- * Copyright (c) 2008  Richard Liu, STMicroelectronics <richard.liu@st.com>
- * Copyright (c) 2008-2010  Arnaud Patard <apatard@mandriva.com>
- * Copyright (c) 2014  Huacai Chen <chenhc@lemote.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __LOONGSON_GPIO_H
-#define __LOONGSON_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#define gpio_get_value __gpio_get_value
-#define gpio_set_value __gpio_set_value
-#define gpio_cansleep __gpio_cansleep
-
-/* The chip can do interrupt
- * but it has not been tested and doc not clear
- */
-static inline int gpio_to_irq(int gpio)
-{
-	return -EINVAL;
-}
-
-static inline int irq_to_gpio(int gpio)
-{
-	return -EINVAL;
-}
-
-#endif	/* __LOONGSON_GPIO_H */
diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h
index 37c08a27b4f0..c9f7e231e66b 100644
--- a/arch/mips/include/asm/mach-loongson64/mmzone.h
+++ b/arch/mips/include/asm/mach-loongson64/mmzone.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
- *                    Insititute of Computing Technology
+ *                    Institute of Computing Technology
  * Author:  Xiang Gao, gaoxiang@ict.ac.cn
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
diff --git a/arch/mips/include/asm/mach-pistachio/gpio.h b/arch/mips/include/asm/mach-pistachio/gpio.h
deleted file mode 100644
index 6c1649c27b8d..000000000000
--- a/arch/mips/include/asm/mach-pistachio/gpio.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Pistachio IRQ setup
- *
- * Copyright (C) 2014 Google, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- */
-
-#ifndef __ASM_MACH_PISTACHIO_GPIO_H
-#define __ASM_MACH_PISTACHIO_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-#define gpio_to_irq	__gpio_to_irq
-
-#endif /* __ASM_MACH_PISTACHIO_GPIO_H */
diff --git a/arch/mips/include/asm/mach-rc32434/gpio.h b/arch/mips/include/asm/mach-rc32434/gpio.h
index 4dee0a34250c..db211212ce79 100644
--- a/arch/mips/include/asm/mach-rc32434/gpio.h
+++ b/arch/mips/include/asm/mach-rc32434/gpio.h
@@ -13,18 +13,6 @@
 #ifndef _RC32434_GPIO_H_
 #define _RC32434_GPIO_H_
 
-#include <linux/types.h>
-#include <asm-generic/gpio.h>
-
-#define NR_BUILTIN_GPIO		32
-
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-
-#define gpio_to_irq(gpio)	(8 + 4 * 32 + gpio)
-#define irq_to_gpio(irq)	(irq - (8 + 4 * 32))
-
 struct rb532_gpio_reg {
 	u32   gpiofunc;	  /* GPIO Function Register
 			   * gpiofunc[x]==0 bit = gpio
diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h
index 0a227d426b9c..520f8fc2c806 100644
--- a/arch/mips/include/asm/mach-sibyte/war.h
+++ b/arch/mips/include/asm/mach-sibyte/war.h
@@ -13,8 +13,7 @@
 #define R4600_V2_HIT_CACHEOP_WAR	0
 #define R5432_CP0_INTERRUPT_WAR		0
 
-#if defined(CONFIG_SB1_PASS_1_WORKAROUNDS) || \
-    defined(CONFIG_SB1_PASS_2_WORKAROUNDS)
+#if defined(CONFIG_SB1_PASS_2_WORKAROUNDS)
 
 #ifndef __ASSEMBLY__
 extern int sb1250_m3_workaround_needed(void);
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index edc7ee95269e..d75b75e78ebb 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -33,6 +33,29 @@ extern void __iomem *mips_cm_l2sync_base;
  */
 extern phys_addr_t __mips_cm_phys_base(void);
 
+/*
+ * mips_cm_is64 - determine CM register width
+ *
+ * The CM register width is processor and CM specific. A 64-bit processor
+ * usually has a 64-bit CM and a 32-bit one has a 32-bit CM but a 64-bit
+ * processor could come with a 32-bit CM. Moreover, accesses on 64-bit CMs
+ * can be done either using regular 64-bit load/store instructions, or 32-bit
+ * load/store instruction on 32-bit register pairs. We opt for using 64-bit
+ * accesses on 64-bit CMs and kernels and 32-bit in any other case.
+ *
+ * It's set to 0 for 32-bit accesses and 1 for 64-bit accesses.
+ */
+extern int mips_cm_is64;
+
+/**
+ * mips_cm_error_report - Report CM cache errors
+ */
+#ifdef CONFIG_MIPS_CM
+extern void mips_cm_error_report(void);
+#else
+static inline void mips_cm_error_report(void) {}
+#endif
+
 /**
  * mips_cm_probe - probe for a Coherence Manager
  *
@@ -90,20 +113,46 @@ static inline bool mips_cm_has_l2sync(void)
 
 /* Macros to ease the creation of register access functions */
 #define BUILD_CM_R_(name, off)					\
-static inline u32 __iomem *addr_gcr_##name(void)		\
+static inline unsigned long __iomem *addr_gcr_##name(void)	\
 {								\
-	return (u32 __iomem *)(mips_cm_base + (off));		\
+	return (unsigned long __iomem *)(mips_cm_base + (off));	\
 }								\
 								\
-static inline u32 read_gcr_##name(void)				\
+static inline u32 read32_gcr_##name(void)			\
 {								\
 	return __raw_readl(addr_gcr_##name());			\
+}								\
+								\
+static inline u64 read64_gcr_##name(void)			\
+{								\
+	return __raw_readq(addr_gcr_##name());			\
+}								\
+								\
+static inline unsigned long read_gcr_##name(void)		\
+{								\
+	if (mips_cm_is64)					\
+		return read64_gcr_##name();			\
+	else							\
+		return read32_gcr_##name();			\
 }
 
 #define BUILD_CM__W(name, off)					\
-static inline void write_gcr_##name(u32 value)			\
+static inline void write32_gcr_##name(u32 value)		\
 {								\
 	__raw_writel(value, addr_gcr_##name());			\
+}								\
+								\
+static inline void write64_gcr_##name(u64 value)		\
+{								\
+	__raw_writeq(value, addr_gcr_##name());			\
+}								\
+								\
+static inline void write_gcr_##name(unsigned long value)	\
+{								\
+	if (mips_cm_is64)					\
+		write64_gcr_##name(value);			\
+	else							\
+		write32_gcr_##name(value);			\
 }
 
 #define BUILD_CM_RW(name, off)					\
@@ -144,6 +193,7 @@ BUILD_CM_RW(reg3_base,		MIPS_CM_GCB_OFS + 0xc0)
 BUILD_CM_RW(reg3_mask,		MIPS_CM_GCB_OFS + 0xc8)
 BUILD_CM_R_(gic_status,		MIPS_CM_GCB_OFS + 0xd0)
 BUILD_CM_R_(cpc_status,		MIPS_CM_GCB_OFS + 0xf0)
+BUILD_CM_RW(l2_config,		MIPS_CM_GCB_OFS + 0x130)
 
 /* Core Local & Core Other register accessor functions */
 BUILD_CM_Cx_RW(reset_release,	0x00)
@@ -189,6 +239,13 @@ BUILD_CM_Cx_R_(tcid_8_priority,	0x80)
 #define CM_GCR_REV_MINOR_SHF			0
 #define CM_GCR_REV_MINOR_MSK			(_ULCAST_(0xff) << 0)
 
+#define CM_ENCODE_REV(major, minor) \
+		(((major) << CM_GCR_REV_MAJOR_SHF) | \
+		 ((minor) << CM_GCR_REV_MINOR_SHF))
+
+#define CM_REV_CM2				CM_ENCODE_REV(6, 0)
+#define CM_REV_CM3				CM_ENCODE_REV(8, 0)
+
 /* GCR_ERROR_CAUSE register fields */
 #define CM_GCR_ERROR_CAUSE_ERRTYPE_SHF		27
 #define CM_GCR_ERROR_CAUSE_ERRTYPE_MSK		(_ULCAST_(0x1f) << 27)
@@ -249,6 +306,16 @@ BUILD_CM_Cx_R_(tcid_8_priority,	0x80)
 #define CM_GCR_CPC_STATUS_EX_SHF		0
 #define CM_GCR_CPC_STATUS_EX_MSK		(_ULCAST_(0x1) << 0)
 
+/* GCR_L2_CONFIG register fields */
+#define CM_GCR_L2_CONFIG_BYPASS_SHF		20
+#define CM_GCR_L2_CONFIG_BYPASS_MSK		(_ULCAST_(0x1) << 20)
+#define CM_GCR_L2_CONFIG_SET_SIZE_SHF		12
+#define CM_GCR_L2_CONFIG_SET_SIZE_MSK		(_ULCAST_(0xf) << 12)
+#define CM_GCR_L2_CONFIG_LINE_SIZE_SHF		8
+#define CM_GCR_L2_CONFIG_LINE_SIZE_MSK		(_ULCAST_(0xf) << 8)
+#define CM_GCR_L2_CONFIG_ASSOC_SHF		0
+#define CM_GCR_L2_CONFIG_ASSOC_MSK		(_ULCAST_(0xff) << 0)
+
 /* GCR_Cx_COHERENCE register fields */
 #define CM_GCR_Cx_COHERENCE_COHDOMAINEN_SHF	0
 #define CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK	(_ULCAST_(0xff) << 0)
@@ -324,4 +391,18 @@ static inline int mips_cm_l2sync(void)
 	return 0;
 }
 
+/**
+ * mips_cm_revision() - return CM revision
+ *
+ * Return: The revision of the CM, from GCR_REV, or 0 if no CM is present. The
+ * return value should be checked against the CM_REV_* macros.
+ */
+static inline int mips_cm_revision(void)
+{
+	if (!mips_cm_present())
+		return 0;
+
+	return read_gcr_rev();
+}
+
 #endif /* __MIPS_ASM_MIPS_CM_H__ */
diff --git a/arch/mips/include/asm/mips-cpc.h b/arch/mips/include/asm/mips-cpc.h
index 1cebe8c79051..f386f32702f1 100644
--- a/arch/mips/include/asm/mips-cpc.h
+++ b/arch/mips/include/asm/mips-cpc.h
@@ -28,16 +28,6 @@ extern void __iomem *mips_cpc_base;
 extern phys_addr_t mips_cpc_default_phys_base(void);
 
 /**
- * mips_cpc_phys_base - retrieve the physical base address of the CPC
- *
- * This function returns the physical base address of the Cluster Power
- * Controller memory mapped registers, or 0 if no Cluster Power Controller
- * is present. It may be overriden by individual platforms which determine
- * this address in a different way.
- */
-extern phys_addr_t __weak mips_cpc_phys_base(void);
-
-/**
  * mips_cpc_probe - probe for a Cluster Power Controller
  *
  * Attempt to detect the presence of a Cluster Power Controller. Returns 0 if
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index c5b0956a8530..d3cd8eac81e3 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -112,6 +112,30 @@
 #define CP0_TX39_CACHE	$7
 
 
+/* Generic EntryLo bit definitions */
+#define ENTRYLO_G		(_ULCAST_(1) << 0)
+#define ENTRYLO_V		(_ULCAST_(1) << 1)
+#define ENTRYLO_D		(_ULCAST_(1) << 2)
+#define ENTRYLO_C_SHIFT		3
+#define ENTRYLO_C		(_ULCAST_(7) << ENTRYLO_C_SHIFT)
+
+/* R3000 EntryLo bit definitions */
+#define R3K_ENTRYLO_G		(_ULCAST_(1) << 8)
+#define R3K_ENTRYLO_V		(_ULCAST_(1) << 9)
+#define R3K_ENTRYLO_D		(_ULCAST_(1) << 10)
+#define R3K_ENTRYLO_N		(_ULCAST_(1) << 11)
+
+/* MIPS32/64 EntryLo bit definitions */
+#ifdef CONFIG_64BIT
+/* as read by dmfc0 */
+#define MIPS_ENTRYLO_XI		(_ULCAST_(1) << 62)
+#define MIPS_ENTRYLO_RI		(_ULCAST_(1) << 63)
+#else
+/* as read by mfc0 */
+#define MIPS_ENTRYLO_XI		(_ULCAST_(1) << 30)
+#define MIPS_ENTRYLO_RI		(_ULCAST_(1) << 31)
+#endif
+
 /*
  * Values for PageMask register
  */
@@ -203,6 +227,9 @@
 #define PG_ESP		(_ULCAST_(1) <<	 28)
 #define PG_IEC		(_ULCAST_(1) <<  27)
 
+/* MIPS32/64 EntryHI bit definitions */
+#define MIPS_ENTRYHI_EHINV	(_ULCAST_(1) << 10)
+
 /*
  * R4x00 interrupt enable / cause bits
  */
@@ -579,6 +606,8 @@
 
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
+/* FTLB probability bits for R6 */
+#define MIPS_CONF7_FTLBP_SHIFT	(18)
 
 /* MAAR bit definitions */
 #define MIPS_MAAR_ADDR		((BIT_ULL(BITS_PER_LONG - 12) - 1) << 12)
@@ -586,31 +615,6 @@
 #define MIPS_MAAR_S		(_ULCAST_(1) << 1)
 #define MIPS_MAAR_V		(_ULCAST_(1) << 0)
 
-/*  EntryHI bit definition */
-#define MIPS_ENTRYHI_EHINV	(_ULCAST_(1) << 10)
-
-/* R3000 EntryLo bit definitions */
-#define R3K_ENTRYLO_G		(_ULCAST_(1) << 8)
-#define R3K_ENTRYLO_V		(_ULCAST_(1) << 9)
-#define R3K_ENTRYLO_D		(_ULCAST_(1) << 10)
-#define R3K_ENTRYLO_N		(_ULCAST_(1) << 11)
-
-/* R4000 compatible EntryLo bit definitions */
-#define MIPS_ENTRYLO_G		(_ULCAST_(1) << 0)
-#define MIPS_ENTRYLO_V		(_ULCAST_(1) << 1)
-#define MIPS_ENTRYLO_D		(_ULCAST_(1) << 2)
-#define MIPS_ENTRYLO_C_SHIFT	3
-#define MIPS_ENTRYLO_C		(_ULCAST_(7) << MIPS_ENTRYLO_C_SHIFT)
-#ifdef CONFIG_64BIT
-/* as read by dmfc0 */
-#define MIPS_ENTRYLO_XI		(_ULCAST_(1) << 62)
-#define MIPS_ENTRYLO_RI		(_ULCAST_(1) << 63)
-#else
-/* as read by mfc0 */
-#define MIPS_ENTRYLO_XI		(_ULCAST_(1) << 30)
-#define MIPS_ENTRYLO_RI		(_ULCAST_(1) << 31)
-#endif
-
 /* CMGCRBase bit definitions */
 #define MIPS_CMGCRB_BASE	11
 #define MIPS_CMGCRF_BASE	(~_ULCAST_((1 << MIPS_CMGCRB_BASE) - 1))
@@ -932,7 +936,7 @@ do {								\
  */
 
 #define __read_32bit_c0_register(source, sel)				\
-({ int __res;								\
+({ unsigned int __res;							\
 	if (sel == 0)							\
 		__asm__ __volatile__(					\
 			"mfc0\t%0, " #source "\n\t"			\
@@ -1014,7 +1018,7 @@ do {									\
  * On RM7000/RM9000 these are uses to access cop0 set 1 registers
  */
 #define __read_32bit_c0_ctrl_register(source)				\
-({ int __res;								\
+({ unsigned int __res;							\
 	__asm__ __volatile__(						\
 		"cfc0\t%0, " #source "\n\t"				\
 		: "=r" (__res));					\
@@ -1471,7 +1475,7 @@ do {									\
  */
 #define _read_32bit_cp1_register(source, gas_hardfloat)			\
 ({									\
-	int __res;							\
+	unsigned int __res;						\
 									\
 	__asm__ __volatile__(						\
 	"	.set	push					\n"	\
diff --git a/arch/mips/include/asm/mm-arch-hooks.h b/arch/mips/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b5609fe8e475..000000000000
--- a/arch/mips/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_MIPS_MM_ARCH_HOOKS_H
-#define _ASM_MIPS_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_MIPS_MM_ARCH_HOOKS_H */
diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h
index af5638b12c75..bbb85fe21642 100644
--- a/arch/mips/include/asm/msa.h
+++ b/arch/mips/include/asm/msa.h
@@ -14,10 +14,90 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/inst.h>
+
 extern void _save_msa(struct task_struct *);
 extern void _restore_msa(struct task_struct *);
 extern void _init_msa_upper(void);
 
+extern void read_msa_wr_b(unsigned idx, union fpureg *to);
+extern void read_msa_wr_h(unsigned idx, union fpureg *to);
+extern void read_msa_wr_w(unsigned idx, union fpureg *to);
+extern void read_msa_wr_d(unsigned idx, union fpureg *to);
+
+/**
+ * read_msa_wr() - Read a single MSA vector register
+ * @idx:	The index of the vector register to read
+ * @to:		The FPU register union to store the registers value in
+ * @fmt:	The format of the data in the vector register
+ *
+ * Read the value of MSA vector register idx into the FPU register
+ * union to, using the format fmt.
+ */
+static inline void read_msa_wr(unsigned idx, union fpureg *to,
+			       enum msa_2b_fmt fmt)
+{
+	switch (fmt) {
+	case msa_fmt_b:
+		read_msa_wr_b(idx, to);
+		break;
+
+	case msa_fmt_h:
+		read_msa_wr_h(idx, to);
+		break;
+
+	case msa_fmt_w:
+		read_msa_wr_w(idx, to);
+		break;
+
+	case msa_fmt_d:
+		read_msa_wr_d(idx, to);
+		break;
+
+	default:
+		BUG();
+	}
+}
+
+extern void write_msa_wr_b(unsigned idx, union fpureg *from);
+extern void write_msa_wr_h(unsigned idx, union fpureg *from);
+extern void write_msa_wr_w(unsigned idx, union fpureg *from);
+extern void write_msa_wr_d(unsigned idx, union fpureg *from);
+
+/**
+ * write_msa_wr() - Write a single MSA vector register
+ * @idx:	The index of the vector register to write
+ * @from:	The FPU register union to take the registers value from
+ * @fmt:	The format of the data in the vector register
+ *
+ * Write the value from the FPU register union from into MSA vector
+ * register idx, using the format fmt.
+ */
+static inline void write_msa_wr(unsigned idx, union fpureg *from,
+				enum msa_2b_fmt fmt)
+{
+	switch (fmt) {
+	case msa_fmt_b:
+		write_msa_wr_b(idx, from);
+		break;
+
+	case msa_fmt_h:
+		write_msa_wr_h(idx, from);
+		break;
+
+	case msa_fmt_w:
+		write_msa_wr_w(idx, from);
+		break;
+
+	case msa_fmt_d:
+		write_msa_wr_d(idx, from);
+		break;
+
+	default:
+		BUG();
+	}
+}
+
 static inline void enable_msa(void)
 {
 	if (cpu_has_msa) {
diff --git a/arch/mips/include/asm/octeon/cvmx-bootinfo.h b/arch/mips/include/asm/octeon/cvmx-bootinfo.h
index c373d95b5e2c..d92cf59bdae6 100644
--- a/arch/mips/include/asm/octeon/cvmx-bootinfo.h
+++ b/arch/mips/include/asm/octeon/cvmx-bootinfo.h
@@ -284,6 +284,7 @@ enum cvmx_board_types_enum {
 	CVMX_BOARD_TYPE_CUST_PRIVATE_MIN = 20001,
 	CVMX_BOARD_TYPE_UBNT_E100 = 20002,
 	CVMX_BOARD_TYPE_CUST_DSR1000N = 20006,
+	CVMX_BOARD_TYPE_KONTRON_S1901 = 21901,
 	CVMX_BOARD_TYPE_CUST_PRIVATE_MAX = 30000,
 
 	/* The remaining range is reserved for future use. */
@@ -384,6 +385,7 @@ static inline const char *cvmx_board_type_to_string(enum
 		ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_CUST_PRIVATE_MIN)
 		ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_UBNT_E100)
 		ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_CUST_DSR1000N)
+		ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_KONTRON_S1901)
 		ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_CUST_PRIVATE_MAX)
 	}
 	return "Unsupported Board";
diff --git a/arch/mips/include/asm/octeon/cvmx-pip.h b/arch/mips/include/asm/octeon/cvmx-pip.h
index df69bfd2b006..c210154ad941 100644
--- a/arch/mips/include/asm/octeon/cvmx-pip.h
+++ b/arch/mips/include/asm/octeon/cvmx-pip.h
@@ -37,7 +37,7 @@
 #include <asm/octeon/cvmx-fpa.h>
 #include <asm/octeon/cvmx-pip-defs.h>
 
-#define CVMX_PIP_NUM_INPUT_PORTS		40
+#define CVMX_PIP_NUM_INPUT_PORTS		48
 #define CVMX_PIP_NUM_WATCHERS			4
 
 /*
diff --git a/arch/mips/include/asm/octeon/cvmx-pko.h b/arch/mips/include/asm/octeon/cvmx-pko.h
index 3da59bb8ce24..5f47f76ed510 100644
--- a/arch/mips/include/asm/octeon/cvmx-pko.h
+++ b/arch/mips/include/asm/octeon/cvmx-pko.h
@@ -542,6 +542,9 @@ static inline int cvmx_pko_get_base_queue_per_core(int port, int core)
  */
 static inline int cvmx_pko_get_base_queue(int port)
 {
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX))
+		return port;
+
 	return cvmx_pko_get_base_queue_per_core(port, 0);
 }
 
diff --git a/arch/mips/include/asm/octeon/cvmx-pow-defs.h b/arch/mips/include/asm/octeon/cvmx-pow-defs.h
index 9020ef443736..6a3db4b068ff 100644
--- a/arch/mips/include/asm/octeon/cvmx-pow-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pow-defs.h
@@ -52,6 +52,12 @@
 #define CVMX_POW_WQ_INT_THRX(offset) (CVMX_ADD_IO_SEG(0x0001670000000080ull) + ((offset) & 15) * 8)
 #define CVMX_POW_WS_PCX(offset) (CVMX_ADD_IO_SEG(0x0001670000000280ull) + ((offset) & 15) * 8)
 
+#define CVMX_SSO_WQ_INT (CVMX_ADD_IO_SEG(0x0001670000001000ull))
+#define CVMX_SSO_WQ_IQ_DIS (CVMX_ADD_IO_SEG(0x0001670000001010ull))
+#define CVMX_SSO_WQ_INT_PC (CVMX_ADD_IO_SEG(0x0001670000001020ull))
+#define CVMX_SSO_PPX_GRP_MSK(offset) (CVMX_ADD_IO_SEG(0x0001670000006000ull) + ((offset) & 31) * 8)
+#define CVMX_SSO_WQ_INT_THRX(offset) (CVMX_ADD_IO_SEG(0x0001670000007000ull) + ((offset) & 63) * 8)
+
 union cvmx_pow_bist_stat {
 	uint64_t u64;
 	struct cvmx_pow_bist_stat_s {
@@ -1286,4 +1292,27 @@ union cvmx_pow_ws_pcx {
 	struct cvmx_pow_ws_pcx_s cnf71xx;
 };
 
+union cvmx_sso_wq_int_thrx {
+	uint64_t u64;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_33_63:31;
+		uint64_t tc_en:1;
+		uint64_t tc_thr:4;
+		uint64_t reserved_26_27:2;
+		uint64_t ds_thr:12;
+		uint64_t reserved_12_13:2;
+		uint64_t iq_thr:12;
+#else
+		uint64_t iq_thr:12;
+		uint64_t reserved_12_13:2;
+		uint64_t ds_thr:12;
+		uint64_t reserved_26_27:2;
+		uint64_t tc_thr:4;
+		uint64_t tc_en:1;
+		uint64_t reserved_33_63:31;
+#endif
+	} s;
+};
+
 #endif
diff --git a/arch/mips/include/asm/octeon/cvmx-pow.h b/arch/mips/include/asm/octeon/cvmx-pow.h
index d5565d758ddd..51531563f8dc 100644
--- a/arch/mips/include/asm/octeon/cvmx-pow.h
+++ b/arch/mips/include/asm/octeon/cvmx-pow.h
@@ -1810,10 +1810,11 @@ static inline void cvmx_pow_work_submit(cvmx_wqe_t *wqp, uint32_t tag,
 	cvmx_addr_t ptr;
 	cvmx_pow_tag_req_t tag_req;
 
-	wqp->qos = qos;
-	wqp->tag = tag;
-	wqp->tag_type = tag_type;
-	wqp->grp = grp;
+	wqp->word1.tag = tag;
+	wqp->word1.tag_type = tag_type;
+
+	cvmx_wqe_set_qos(wqp, qos);
+	cvmx_wqe_set_grp(wqp, grp);
 
 	tag_req.u64 = 0;
 	tag_req.s.op = CVMX_POW_TAG_OP_ADDWQ;
diff --git a/arch/mips/include/asm/octeon/cvmx-wqe.h b/arch/mips/include/asm/octeon/cvmx-wqe.h
index 2d6d0c7127a7..0d697aa786d4 100644
--- a/arch/mips/include/asm/octeon/cvmx-wqe.h
+++ b/arch/mips/include/asm/octeon/cvmx-wqe.h
@@ -193,6 +193,53 @@ typedef union {
 	        uint64_t bufs:8;
 #endif
 	} s;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t bufs:8;
+		uint64_t ip_offset:8;
+		uint64_t vlan_valid:1;
+		uint64_t vlan_stacked:1;
+		uint64_t unassigned:1;
+		uint64_t vlan_cfi:1;
+		uint64_t vlan_id:12;
+		uint64_t port:12;		/* MAC/PIP port number. */
+		uint64_t dec_ipcomp:1;
+		uint64_t tcp_or_udp:1;
+		uint64_t dec_ipsec:1;
+		uint64_t is_v6:1;
+		uint64_t software:1;
+		uint64_t L4_error:1;
+		uint64_t is_frag:1;
+		uint64_t IP_exc:1;
+		uint64_t is_bcast:1;
+		uint64_t is_mcast:1;
+		uint64_t not_IP:1;
+		uint64_t rcv_error:1;
+		uint64_t err_code:8;
+#else
+		uint64_t err_code:8;
+		uint64_t rcv_error:1;
+		uint64_t not_IP:1;
+		uint64_t is_mcast:1;
+		uint64_t is_bcast:1;
+		uint64_t IP_exc:1;
+		uint64_t is_frag:1;
+		uint64_t L4_error:1;
+		uint64_t software:1;
+		uint64_t is_v6:1;
+		uint64_t dec_ipsec:1;
+		uint64_t tcp_or_udp:1;
+		uint64_t dec_ipcomp:1;
+		uint64_t port:12;
+		uint64_t vlan_id:12;
+		uint64_t vlan_cfi:1;
+		uint64_t unassigned:1;
+		uint64_t vlan_stacked:1;
+		uint64_t vlan_valid:1;
+		uint64_t ip_offset:8;
+		uint64_t bufs:8;
+#endif
+	} s_cn68xx;
 
 	/* use this to get at the 16 vlan bits */
 	struct {
@@ -355,6 +402,146 @@ typedef union {
 
 } cvmx_pip_wqe_word2;
 
+union cvmx_pip_wqe_word0 {
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		/**
+		 * raw chksum result generated by the HW
+		 */
+		uint16_t hw_chksum;
+		/**
+		 * Field unused by hardware - available for software
+		 */
+		uint8_t unused;
+		/**
+		 * Next pointer used by hardware for list maintenance.
+		 * May be written/read by HW before the work queue
+		 * entry is scheduled to a PP (Only 36 bits used in
+		 * Octeon 1)
+		 */
+		uint64_t next_ptr:40;
+#else
+		uint64_t next_ptr:40;
+		uint8_t unused;
+		uint16_t hw_chksum;
+#endif
+	} cn38xx;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t l4ptr:8;       /* 56..63 */
+		uint64_t unused0:8;     /* 48..55 */
+		uint64_t l3ptr:8;       /* 40..47 */
+		uint64_t l2ptr:8;       /* 32..39 */
+		uint64_t unused1:18;    /* 14..31 */
+		uint64_t bpid:6;        /* 8..13 */
+		uint64_t unused2:2;     /* 6..7 */
+		uint64_t pknd:6;        /* 0..5 */
+#else
+		uint64_t pknd:6;        /* 0..5 */
+		uint64_t unused2:2;     /* 6..7 */
+		uint64_t bpid:6;        /* 8..13 */
+		uint64_t unused1:18;    /* 14..31 */
+		uint64_t l2ptr:8;       /* 32..39 */
+		uint64_t l3ptr:8;       /* 40..47 */
+		uint64_t unused0:8;     /* 48..55 */
+		uint64_t l4ptr:8;       /* 56..63 */
+#endif
+	} cn68xx;
+};
+
+union cvmx_wqe_word0 {
+	uint64_t u64;
+	union cvmx_pip_wqe_word0 pip;
+};
+
+union cvmx_wqe_word1 {
+	uint64_t u64;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t len:16;
+		uint64_t varies:14;
+		/**
+		 * the type of the tag (ORDERED, ATOMIC, NULL)
+		 */
+		uint64_t tag_type:2;
+		uint64_t tag:32;
+#else
+		uint64_t tag:32;
+		uint64_t tag_type:2;
+		uint64_t varies:14;
+		uint64_t len:16;
+#endif
+	};
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t len:16;
+		uint64_t zero_0:1;
+		/**
+		 * HW sets this to what it thought the priority of
+		 * the input packet was
+		 */
+		uint64_t qos:3;
+
+		uint64_t zero_1:1;
+		/**
+		 * the group that the work queue entry will be scheduled to
+		 */
+		uint64_t grp:6;
+		uint64_t zero_2:3;
+		uint64_t tag_type:2;
+		uint64_t tag:32;
+#else
+		uint64_t tag:32;
+		uint64_t tag_type:2;
+		uint64_t zero_2:3;
+		uint64_t grp:6;
+		uint64_t zero_1:1;
+		uint64_t qos:3;
+		uint64_t zero_0:1;
+		uint64_t len:16;
+#endif
+	} cn68xx;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		/**
+		 * HW sets to the total number of bytes in the packet
+		 */
+		uint64_t len:16;
+		/**
+		 * HW sets this to input physical port
+		 */
+		uint64_t ipprt:6;
+
+		/**
+		 * HW sets this to what it thought the priority of
+		 * the input packet was
+		 */
+		uint64_t qos:3;
+
+		/**
+		 * the group that the work queue entry will be scheduled to
+		 */
+		uint64_t grp:4;
+		/**
+		 * the type of the tag (ORDERED, ATOMIC, NULL)
+		 */
+		uint64_t tag_type:3;
+		/**
+		 * the synchronization/ordering tag
+		 */
+		uint64_t tag:32;
+#else
+		uint64_t tag:32;
+		uint64_t tag_type:2;
+		uint64_t zero_2:1;
+		uint64_t grp:4;
+		uint64_t qos:3;
+		uint64_t ipprt:6;
+		uint64_t len:16;
+#endif
+	} cn38xx;
+};
+
 /**
  * Work queue entry format
  *
@@ -366,70 +553,13 @@ typedef struct {
      * WORD 0
      *	HW WRITE: the following 64 bits are filled by HW when a packet arrives
      */
-
-#ifdef __BIG_ENDIAN_BITFIELD
-    /**
-     * raw chksum result generated by the HW
-     */
-	uint16_t hw_chksum;
-    /**
-     * Field unused by hardware - available for software
-     */
-	uint8_t unused;
-    /**
-     * Next pointer used by hardware for list maintenance.
-     * May be written/read by HW before the work queue
-     *		 entry is scheduled to a PP
-     * (Only 36 bits used in Octeon 1)
-     */
-	uint64_t next_ptr:40;
-#else
-	uint64_t next_ptr:40;
-	uint8_t unused;
-	uint16_t hw_chksum;
-#endif
+	union cvmx_wqe_word0 word0;
 
     /*****************************************************************
      * WORD 1
      *	HW WRITE: the following 64 bits are filled by HW when a packet arrives
      */
-
-#ifdef __BIG_ENDIAN_BITFIELD
-    /**
-     * HW sets to the total number of bytes in the packet
-     */
-	uint64_t len:16;
-    /**
-     * HW sets this to input physical port
-     */
-	uint64_t ipprt:6;
-
-    /**
-     * HW sets this to what it thought the priority of the input packet was
-     */
-	uint64_t qos:3;
-
-    /**
-     * the group that the work queue entry will be scheduled to
-     */
-	uint64_t grp:4;
-    /**
-     * the type of the tag (ORDERED, ATOMIC, NULL)
-     */
-	uint64_t tag_type:3;
-    /**
-     * the synchronization/ordering tag
-     */
-	uint64_t tag:32;
-#else
-	uint64_t tag:32;
-	uint64_t tag_type:2;
-	uint64_t zero_2:1;
-	uint64_t grp:4;
-	uint64_t qos:3;
-	uint64_t ipprt:6;
-	uint64_t len:16;
-#endif
+	union cvmx_wqe_word1 word1;
 
     /**
      * WORD 2 HW WRITE: the following 64-bits are filled in by
@@ -465,4 +595,64 @@ typedef struct {
 
 } CVMX_CACHE_LINE_ALIGNED cvmx_wqe_t;
 
+static inline int cvmx_wqe_get_port(cvmx_wqe_t *work)
+{
+	int port;
+
+	if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE))
+		port = work->word2.s_cn68xx.port;
+	else
+		port = work->word1.cn38xx.ipprt;
+
+	return port;
+}
+
+static inline void cvmx_wqe_set_port(cvmx_wqe_t *work, int port)
+{
+	if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE))
+		work->word2.s_cn68xx.port = port;
+	else
+		work->word1.cn38xx.ipprt = port;
+}
+
+static inline int cvmx_wqe_get_grp(cvmx_wqe_t *work)
+{
+	int grp;
+
+	if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE))
+		grp = work->word1.cn68xx.grp;
+	else
+		grp = work->word1.cn38xx.grp;
+
+	return grp;
+}
+
+static inline void cvmx_wqe_set_grp(cvmx_wqe_t *work, int grp)
+{
+	if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE))
+		work->word1.cn68xx.grp = grp;
+	else
+		work->word1.cn38xx.grp = grp;
+}
+
+static inline int cvmx_wqe_get_qos(cvmx_wqe_t *work)
+{
+	int qos;
+
+	if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE))
+		qos = work->word1.cn68xx.qos;
+	else
+		qos = work->word1.cn38xx.qos;
+
+	return qos;
+}
+
+static inline void cvmx_wqe_set_qos(cvmx_wqe_t *work, int qos)
+{
+	if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE))
+		work->word1.cn68xx.qos = qos;
+	else
+		work->word1.cn38xx.qos = qos;
+}
+
 #endif /* __CVMX_WQE_H__ */
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index c28a8499aec7..ff7ad91c85db 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -133,20 +133,13 @@
 #define _PAGE_HUGE		(1 << _PAGE_HUGE_SHIFT)
 #define _PAGE_SPLITTING_SHIFT	(_PAGE_HUGE_SHIFT + 1)
 #define _PAGE_SPLITTING		(1 << _PAGE_SPLITTING_SHIFT)
-
-/* Only R2 or newer cores have the XI bit */
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
-#define _PAGE_NO_EXEC_SHIFT	(_PAGE_SPLITTING_SHIFT + 1)
-#else
-#define _PAGE_GLOBAL_SHIFT	(_PAGE_SPLITTING_SHIFT + 1)
-#define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
-#endif	/* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
-
 #endif	/* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */
 
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 /* XI - page cannot be executed */
-#ifndef _PAGE_NO_EXEC_SHIFT
+#ifdef _PAGE_SPLITTING_SHIFT
+#define _PAGE_NO_EXEC_SHIFT	(_PAGE_SPLITTING_SHIFT + 1)
+#else
 #define _PAGE_NO_EXEC_SHIFT	(_PAGE_MODIFIED_SHIFT + 1)
 #endif
 #define _PAGE_NO_EXEC		(cpu_has_rixi ? (1 << _PAGE_NO_EXEC_SHIFT) : 0)
@@ -156,14 +149,16 @@
 #define _PAGE_READ		(cpu_has_rixi ? 0 : (1 << _PAGE_READ_SHIFT))
 #define _PAGE_NO_READ_SHIFT	_PAGE_READ_SHIFT
 #define _PAGE_NO_READ		(cpu_has_rixi ? (1 << _PAGE_READ_SHIFT) : 0)
+#endif	/* defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) */
 
+#if defined(_PAGE_NO_READ_SHIFT)
 #define _PAGE_GLOBAL_SHIFT	(_PAGE_NO_READ_SHIFT + 1)
-#define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
-
-#else	/* !CONFIG_CPU_MIPSR2 && !CONFIG_CPU_MIPSR6 */
+#elif defined(_PAGE_SPLITTING_SHIFT)
+#define _PAGE_GLOBAL_SHIFT	(_PAGE_SPLITTING_SHIFT + 1)
+#else
 #define _PAGE_GLOBAL_SHIFT	(_PAGE_MODIFIED_SHIFT + 1)
+#endif
 #define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
-#endif	/* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 
 #define _PAGE_VALID_SHIFT	(_PAGE_GLOBAL_SHIFT + 1)
 #define _PAGE_VALID		(1 << _PAGE_VALID_SHIFT)
@@ -249,7 +244,7 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val)
 #define _CACHE_CACHABLE_NONCOHERENT (3<<_CACHE_SHIFT)  /* LOONGSON       */
 #define _CACHE_CACHABLE_COHERENT    (3<<_CACHE_SHIFT)  /* LOONGSON-3     */
 
-#elif defined(CONFIG_MACH_JZ4740)
+#elif defined(CONFIG_MACH_INGENIC)
 
 /* Ingenic uses the WA bit to achieve write-combine memory writes */
 #define _CACHE_UNCACHED_ACCELERATED (1<<_CACHE_SHIFT)
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 9d8106758142..8957f15e21ec 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -182,8 +182,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+#ifdef CONFIG_SMP
+		/*
+		 * For SMP, multiple CPUs can race, so we need to do
+		 * this atomically.
+		 */
+#ifdef CONFIG_64BIT
+#define LL_INSN "lld"
+#define SC_INSN "scd"
+#else /* CONFIG_32BIT */
+#define LL_INSN "ll"
+#define SC_INSN "sc"
+#endif
+		unsigned long page_global = _PAGE_GLOBAL;
+		unsigned long tmp;
+
+		__asm__ __volatile__ (
+			"	.set	push\n"
+			"	.set	noreorder\n"
+			"1:	" LL_INSN "	%[tmp], %[buddy]\n"
+			"	bnez	%[tmp], 2f\n"
+			"	 or	%[tmp], %[tmp], %[global]\n"
+			"	" SC_INSN "	%[tmp], %[buddy]\n"
+			"	beqz	%[tmp], 1b\n"
+			"	 nop\n"
+			"2:\n"
+			"	.set pop"
+			: [buddy] "+m" (buddy->pte),
+			  [tmp] "=&r" (tmp)
+			: [global] "r" (page_global));
+#else /* !CONFIG_SMP */
 		if (pte_none(*buddy))
 			pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
 	}
 #endif
 }
@@ -362,6 +393,8 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
+#define pgprot_writecombine pgprot_writecombine
+
 static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
 {
 	unsigned long prot = pgprot_val(_prot);
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 9b3b48e21c22..59ee6dcf6eed 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -275,6 +275,7 @@ struct thread_struct {
 	unsigned long cp0_badvaddr;	/* Last user fault */
 	unsigned long cp0_baduaddr;	/* Last kernel fault accessing USEG */
 	unsigned long error_code;
+	unsigned long trap_nr;
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	struct octeon_cop2_state cp2 __attribute__ ((__aligned__(128)));
 	struct octeon_cvmseg_state cvmseg __attribute__ ((__aligned__(128)));
@@ -341,6 +342,7 @@ struct thread_struct {
 	.cp0_badvaddr		= 0,				\
 	.cp0_baduaddr		= 0,				\
 	.error_code		= 0,				\
+	.trap_nr		= 0,				\
 	/*							\
 	 * Platform specific cop2 registers(null if no COP2)	\
 	 */							\
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index ffc320389f40..f6fc6aac5496 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -14,11 +14,16 @@
 #include <linux/linkage.h>
 #include <linux/types.h>
 #include <asm/isadep.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
 #include <uapi/asm/ptrace.h>
 
 /*
  * This struct defines the way the registers are stored on the stack during a
  * system call/exception. As usual the registers k0/k1 aren't being saved.
+ *
+ * If you add a register here, also add it to regoffset_table[] in
+ * arch/mips/kernel/ptrace.c.
  */
 struct pt_regs {
 #ifdef CONFIG_32BIT
@@ -43,8 +48,83 @@ struct pt_regs {
 	unsigned long long mpl[6];        /* MTM{0-5} */
 	unsigned long long mtp[6];        /* MTP{0-5} */
 #endif
+	unsigned long __last[0];
 } __aligned(8);
 
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->regs[31];
+}
+
+/*
+ * Don't use asm-generic/ptrace.h it defines FP accessors that don't make
+ * sense on MIPS.  We rather want an error if they get invoked.
+ */
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+                                           unsigned long val)
+{
+	regs->cp0_epc = val;
+}
+
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:       pt_regs from which register value is gotten.
+ * @offset:     offset number of the register.
+ *
+ * regs_get_register returns the value of a register. The @offset is the
+ * offset of the register in struct pt_regs address which specified by @regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+                                              unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:       pt_regs which contains kernel stack pointer.
+ * @addr:       address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static inline int regs_within_kernel_stack(struct pt_regs *regs,
+                                           unsigned long addr)
+{
+	return ((addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:       pt_regs which contains kernel stack pointer.
+ * @n:          stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+                                                      unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
 struct task_struct;
 
 extern int ptrace_getregs(struct task_struct *child,
diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h
index 8efe5a9e2c3e..003e273eff4c 100644
--- a/arch/mips/include/asm/signal.h
+++ b/arch/mips/include/asm/signal.h
@@ -23,4 +23,7 @@
 
 #define __ARCH_HAS_IRIX_SIGACTION
 
+extern int protected_save_fp_context(void __user *sc);
+extern int protected_restore_fp_context(void __user *sc);
+
 #endif /* _ASM_SIGNAL_H */
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 2b25d1ba1ea0..03722d4326a1 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -23,6 +23,7 @@
 extern int smp_num_siblings;
 extern cpumask_t cpu_sibling_map[];
 extern cpumask_t cpu_core_map[];
+extern cpumask_t cpu_foreign_map;
 
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
@@ -82,8 +83,6 @@ static inline void __cpu_die(unsigned int cpu)
 extern void play_dead(void);
 #endif
 
-extern asmlinkage void smp_call_function_interrupt(void);
-
 static inline void arch_send_call_function_single_ipi(int cpu)
 {
 	extern struct plat_smp_ops *mp_ops;	/* private */
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index 9de4ba43dcd1..40196bebe849 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -42,6 +42,11 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 	return ((counters >> 16) ^ counters) & 0xffff;
 }
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.h.serving_now == lock.h.ticket;
+}
+
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_spin_unlock_wait(x) \
 	while (arch_spin_is_locked(x)) { cpu_relax(); }
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index 28d6d9364bd1..a71da576883c 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -152,6 +152,31 @@
 		.set	noreorder
 		bltz	k0, 8f
 		 move	k1, sp
+#ifdef CONFIG_EVA
+		/*
+		 * Flush interAptiv's Return Prediction Stack (RPS) by writing
+		 * EntryHi. Toggling Config7.RPS is slower and less portable.
+		 *
+		 * The RPS isn't automatically flushed when exceptions are
+		 * taken, which can result in kernel mode speculative accesses
+		 * to user addresses if the RPS mispredicts. That's harmless
+		 * when user and kernel share the same address space, but with
+		 * EVA the same user segments may be unmapped to kernel mode,
+		 * even containing sensitive MMIO regions or invalid memory.
+		 *
+		 * This can happen when the kernel sets the return address to
+		 * ret_from_* and jr's to the exception handler, which looks
+		 * more like a tail call than a function call. If nested calls
+		 * don't evict the last user address in the RPS, it will
+		 * mispredict the return and fetch from a user controlled
+		 * address into the icache.
+		 *
+		 * More recent EVA-capable cores with MAAR to restrict
+		 * speculative accesses aren't affected.
+		 */
+		MFC0	k0, CP0_ENTRYHI
+		MTC0	k0, CP0_ENTRYHI
+#endif
 		.set	reorder
 		/* Called from user mode, new stack. */
 		get_saved_sp
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index 7163cd7fdd69..28b5d84a5022 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -16,29 +16,21 @@
 #include <asm/watch.h>
 #include <asm/dsp.h>
 #include <asm/cop2.h>
-#include <asm/msa.h>
+#include <asm/fpu.h>
 
 struct task_struct;
 
-enum {
-	FP_SAVE_NONE	= 0,
-	FP_SAVE_VECTOR	= -1,
-	FP_SAVE_SCALAR	= 1,
-};
-
 /**
  * resume - resume execution of a task
  * @prev:	The task previously executed.
  * @next:	The task to begin executing.
  * @next_ti:	task_thread_info(next).
- * @fp_save:	Which, if any, FP context to save for prev.
  *
  * This function is used whilst scheduling to save the context of prev & load
  * the context of next. Returns prev.
  */
 extern asmlinkage struct task_struct *resume(struct task_struct *prev,
-		struct task_struct *next, struct thread_info *next_ti,
-		s32 fp_save);
+		struct task_struct *next, struct thread_info *next_ti);
 
 extern unsigned int ll_bit;
 extern struct task_struct *ll_task;
@@ -83,45 +75,38 @@ do {	if (cpu_has_rw_llb) {						\
 	}								\
 } while (0)
 
+/*
+ * For newly created kernel threads switch_to() will return to
+ * ret_from_kernel_thread, newly created user threads to ret_from_fork.
+ * That is, everything following resume() will be skipped for new threads.
+ * So everything that matters to new threads should be placed before resume().
+ */
 #define switch_to(prev, next, last)					\
 do {									\
-	u32 __c0_stat;							\
-	s32 __fpsave = FP_SAVE_NONE;					\
 	__mips_mt_fpaff_switch_to(prev);				\
-	if (cpu_has_dsp)						\
+	lose_fpu_inatomic(1, prev);					\
+	if (cpu_has_dsp) {						\
 		__save_dsp(prev);					\
-	if (cop2_present && (KSTK_STATUS(prev) & ST0_CU2)) {		\
-		if (cop2_lazy_restore)					\
-			KSTK_STATUS(prev) &= ~ST0_CU2;			\
-		__c0_stat = read_c0_status();				\
-		write_c0_status(__c0_stat | ST0_CU2);			\
-		cop2_save(prev);					\
-		write_c0_status(__c0_stat & ~ST0_CU2);			\
+		__restore_dsp(next);					\
 	}								\
-	__clear_software_ll_bit();					\
-	if (test_and_clear_tsk_thread_flag(prev, TIF_USEDFPU))		\
-		__fpsave = FP_SAVE_SCALAR;				\
-	if (test_and_clear_tsk_thread_flag(prev, TIF_USEDMSA))		\
-		__fpsave = FP_SAVE_VECTOR;				\
-	(last) = resume(prev, next, task_thread_info(next), __fpsave);	\
-} while (0)
-
-#define finish_arch_switch(prev)					\
-do {									\
-	u32 __c0_stat;							\
-	if (cop2_present && !cop2_lazy_restore &&			\
-			(KSTK_STATUS(current) & ST0_CU2)) {		\
-		__c0_stat = read_c0_status();				\
-		write_c0_status(__c0_stat | ST0_CU2);			\
-		cop2_restore(current);					\
-		write_c0_status(__c0_stat & ~ST0_CU2);			\
+	if (cop2_present) {						\
+		set_c0_status(ST0_CU2);					\
+		if ((KSTK_STATUS(prev) & ST0_CU2)) {			\
+			if (cop2_lazy_restore)				\
+				KSTK_STATUS(prev) &= ~ST0_CU2;		\
+			cop2_save(prev);				\
+		}							\
+		if (KSTK_STATUS(next) & ST0_CU2 &&			\
+		    !cop2_lazy_restore) {				\
+			cop2_restore(next);				\
+		}							\
+		clear_c0_status(ST0_CU2);				\
 	}								\
-	if (cpu_has_dsp)						\
-		__restore_dsp(current);					\
+	__clear_software_ll_bit();					\
 	if (cpu_has_userlocal)						\
-		write_c0_userlocal(current_thread_info()->tp_value);	\
+		write_c0_userlocal(task_thread_info(next)->tp_value);	\
 	__restore_watch();						\
-	disable_msa();							\
+	(last) = resume(prev, next, task_thread_info(next));		\
 } while (0)
 
 #endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 9c0014e87c17..e309d8fcb516 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -99,6 +99,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	3	/* syscall auditing active */
 #define TIF_SECCOMP		4	/* secure computing */
 #define TIF_NOTIFY_RESUME	5	/* callback before returning to user */
+#define TIF_UPROBE		6	/* breakpointed or singlestepping */
 #define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal() */
 #define TIF_USEDFPU		16	/* FPU was used by this task this quantum (SMP) */
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
@@ -122,6 +123,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
+#define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_USEDFPU		(1<<TIF_USEDFPU)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_FIXADE		(1<<TIF_FIXADE)
@@ -146,7 +148,8 @@ static inline struct thread_info *current_thread_info(void)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK		\
-	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_NOTIFY_RESUME)
+	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_NOTIFY_RESUME |	\
+	 _TIF_UPROBE)
 /* work to do on any return to u-space */
 #define _TIF_ALLWORK_MASK	(_TIF_NOHZ | _TIF_WORK_MASK |		\
 				 _TIF_WORK_SYSCALL_EXIT |		\
diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
index 8ab2874225c4..17d4cd20f18c 100644
--- a/arch/mips/include/asm/time.h
+++ b/arch/mips/include/asm/time.h
@@ -51,7 +51,7 @@ extern int __weak get_c0_perfcount_int(void);
 /*
  * Initialize the calling CPU's compare interrupt as clockevent device
  */
-extern unsigned int __weak get_c0_compare_int(void);
+extern unsigned int get_c0_compare_int(void);
 extern int r4k_clockevent_init(void);
 
 static inline int mips_clockevent_init(void)
diff --git a/arch/mips/include/asm/tlbdebug.h b/arch/mips/include/asm/tlbdebug.h
index bb8f5c29c3d9..3a25a8780ac7 100644
--- a/arch/mips/include/asm/tlbdebug.h
+++ b/arch/mips/include/asm/tlbdebug.h
@@ -11,6 +11,7 @@
 /*
  * TLB debugging functions:
  */
+extern void dump_tlb_regs(void);
 extern void dump_tlb_all(void);
 
 #endif /* __ASM_TLBDEBUG_H */
diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h
new file mode 100644
index 000000000000..34c325c674c4
--- /dev/null
+++ b/arch/mips/include/asm/uprobes.h
@@ -0,0 +1,58 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_UPROBES_H
+#define __ASM_UPROBES_H
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+#include <asm/break.h>
+#include <asm/inst.h>
+
+/*
+ * We want this to be defined as union mips_instruction but that makes the
+ * generic code blow up.
+ */
+typedef u32 uprobe_opcode_t;
+
+/*
+ * Classic MIPS (note this implementation doesn't consider microMIPS yet)
+ * instructions are always 4 bytes but in order to deal with branches and
+ * their delay slots, we treat instructions as having 8 bytes maximum.
+ */
+#define MAX_UINSN_BYTES			8
+#define UPROBE_XOL_SLOT_BYTES		128	/* Max. cache line size */
+
+#define UPROBE_BRK_UPROBE		0x000d000d	/* break 13 */
+#define UPROBE_BRK_UPROBE_XOL		0x000e000d	/* break 14 */
+
+#define UPROBE_SWBP_INSN		UPROBE_BRK_UPROBE
+#define UPROBE_SWBP_INSN_SIZE		4
+
+struct arch_uprobe {
+	unsigned long	resume_epc;
+	u32	insn[2];
+	u32	ixol[2];
+	union	mips_instruction orig_inst[MAX_UINSN_BYTES / 4];
+};
+
+struct arch_uprobe_task {
+	unsigned long saved_trap_nr;
+};
+
+extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup,
+	struct mm_struct *mm, unsigned long addr);
+extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
+extern int arch_uprobe_exception_notify(struct notifier_block *self,
+	unsigned long val, void *data);
+extern void arch_uprobe_abort_xol(struct arch_uprobe *aup,
+	struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(
+	unsigned long trampoline_vaddr, struct pt_regs *regs);
+
+#endif /* __ASM_UPROBES_H */
diff --git a/arch/mips/include/asm/vpe.h b/arch/mips/include/asm/vpe.h
index 7849f3978fea..80e70dbd1f64 100644
--- a/arch/mips/include/asm/vpe.h
+++ b/arch/mips/include/asm/vpe.h
@@ -122,7 +122,7 @@ void release_vpe(struct vpe *v);
 void *alloc_progmem(unsigned long len);
 void release_progmem(void *ptr);
 
-int __weak vpe_run(struct vpe *v);
+int vpe_run(struct vpe *v);
 void cleanup_tc(struct tc *tc);
 
 int __init vpe_module_init(void);
diff --git a/arch/mips/include/uapi/asm/break.h b/arch/mips/include/uapi/asm/break.h
index 002c39ea20c3..9c4265cbf151 100644
--- a/arch/mips/include/uapi/asm/break.h
+++ b/arch/mips/include/uapi/asm/break.h
@@ -21,6 +21,8 @@
 #define BRK_DIVZERO	7	/* Divide by zero check */
 #define BRK_RANGE	8	/* Range error check */
 #define BRK_BUG		12	/* Used by BUG() */
+#define BRK_UPROBE	13	/* See <asm/uprobes.h> */
+#define BRK_UPROBE_XOL	14	/* See <asm/uprobes.h> */
 #define BRK_MEMU	514	/* Used by FPU emulator */
 #define BRK_KPROBE_BP	515	/* Kprobe break */
 #define BRK_KPROBE_SSTEPBP 516	/* Kprobe single step software implementation */
diff --git a/arch/mips/include/uapi/asm/hwcap.h b/arch/mips/include/uapi/asm/hwcap.h
new file mode 100644
index 000000000000..c7484a7ca686
--- /dev/null
+++ b/arch/mips/include/uapi/asm/hwcap.h
@@ -0,0 +1,8 @@
+#ifndef _UAPI_ASM_HWCAP_H
+#define _UAPI_ASM_HWCAP_H
+
+/* HWCAP flags */
+#define HWCAP_MIPS_R6		(1 << 0)
+#define HWCAP_MIPS_MSA		(1 << 1)
+
+#endif /* _UAPI_ASM_HWCAP_H */
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index fc0cf5ac0cf7..9b44d5a816fa 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -26,7 +26,7 @@ enum major_op {
 	cop0_op, cop1_op, cop2_op, cop1x_op,
 	beql_op, bnel_op, blezl_op, bgtzl_op,
 	daddi_op, cbcond1_op = daddi_op, daddiu_op, ldl_op, ldr_op,
-	spec2_op, jalx_op, mdmx_op, spec3_op,
+	spec2_op, jalx_op, mdmx_op, msa_op = mdmx_op, spec3_op,
 	lb_op, lh_op, lwl_op, lw_op,
 	lbu_op, lhu_op, lwr_op, lwu_op,
 	sb_op, sh_op, swl_op, sw_op,
@@ -167,8 +167,13 @@ enum cop1_sdw_func {
 	fround_op    =	0x0c, ftrunc_op	   =  0x0d,
 	fceil_op     =	0x0e, ffloor_op	   =  0x0f,
 	fmovc_op     =	0x11, fmovz_op	   =  0x12,
-	fmovn_op     =	0x13, frecip_op	   =  0x15,
-	frsqrt_op    =	0x16, fcvts_op	   =  0x20,
+	fmovn_op     =	0x13, fseleqz_op   =  0x14,
+	frecip_op    =  0x15, frsqrt_op    =  0x16,
+	fselnez_op   =  0x17, fmaddf_op    =  0x18,
+	fmsubf_op    =  0x19, frint_op     =  0x1a,
+	fclass_op    =  0x1b, fmin_op      =  0x1c,
+	fmina_op     =  0x1d, fmax_op      =  0x1e,
+	fmaxa_op     =  0x1f, fcvts_op     =  0x20,
 	fcvtd_op     =	0x21, fcvte_op	   =  0x22,
 	fcvtw_op     =	0x24, fcvtl_op	   =  0x25,
 	fcmp_op	     =	0x30
@@ -221,6 +226,24 @@ enum bshfl_func {
 };
 
 /*
+ * func field for MSA MI10 format.
+ */
+enum msa_mi10_func {
+	msa_ld_op = 8,
+	msa_st_op = 9,
+};
+
+/*
+ * MSA 2 bit format fields.
+ */
+enum msa_2b_fmt {
+	msa_fmt_b = 0,
+	msa_fmt_h = 1,
+	msa_fmt_w = 2,
+	msa_fmt_d = 3,
+};
+
+/*
  * (microMIPS) Major opcodes.
  */
 enum mm_major_op {
@@ -611,6 +634,16 @@ struct v_format {				/* MDMX vector format */
 	;)))))))
 };
 
+struct msa_mi10_format {		/* MSA MI10 */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(signed int s10 : 10,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int wd : 5,
+	__BITFIELD_FIELD(unsigned int func : 4,
+	__BITFIELD_FIELD(unsigned int df : 2,
+	;))))))
+};
+
 struct spec3_format {   /* SPEC3 */
 	__BITFIELD_FIELD(unsigned int opcode:6,
 	__BITFIELD_FIELD(unsigned int rs:5,
@@ -888,6 +921,7 @@ union mips_instruction {
 	struct p_format p_format;
 	struct f_format f_format;
 	struct ma_format ma_format;
+	struct msa_mi10_format msa_mi10_format;
 	struct b_format b_format;
 	struct ps_format ps_format;
 	struct v_format v_format;
diff --git a/arch/mips/include/uapi/asm/sigcontext.h b/arch/mips/include/uapi/asm/sigcontext.h
index 6c9906f59c6e..5cbd9ae6421f 100644
--- a/arch/mips/include/uapi/asm/sigcontext.h
+++ b/arch/mips/include/uapi/asm/sigcontext.h
@@ -12,11 +12,23 @@
 #include <linux/types.h>
 #include <asm/sgidefs.h>
 
+/* scalar FP context was used */
+#define USED_FP			(1 << 0)
+
+/* the value of Status.FR when context was saved */
+#define USED_FR1		(1 << 1)
+
+/* FR=1, but with odd singles in bits 63:32 of preceding even double */
+#define USED_HYBRID_FPRS	(1 << 2)
+
+/* extended context was used, see struct extcontext for details */
+#define USED_EXTCONTEXT		(1 << 3)
+
 #if _MIPS_SIM == _MIPS_SIM_ABI32
 
 /*
  * Keep this struct definition in sync with the sigcontext fragment
- * in arch/mips/tools/offset.c
+ * in arch/mips/kernel/asm-offsets.c
  */
 struct sigcontext {
 	unsigned int		sc_regmask;	/* Unused */
@@ -46,7 +58,7 @@ struct sigcontext {
 #include <linux/posix_types.h>
 /*
  * Keep this struct definition in sync with the sigcontext fragment
- * in arch/mips/tools/offset.c
+ * in arch/mips/kernel/asm-offsets.c
  *
  * Warning: this structure illdefined with sc_badvaddr being just an unsigned
  * int so it was changed to unsigned long in 2.6.0-test1.  This may break
diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h
index 8f2d184dbe9f..c4ddc4f0d2dc 100644
--- a/arch/mips/include/uapi/asm/swab.h
+++ b/arch/mips/include/uapi/asm/swab.h
@@ -16,11 +16,13 @@
 #if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||		\
     defined(_MIPS_ARCH_LOONGSON3A)
 
-static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
+static inline __attribute__((nomips16)) __attribute_const__
+		__u16 __arch_swab16(__u16 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips32r2		\n"
+	"	.set	nomips16		\n"
 	"	wsbh	%0, %1			\n"
 	"	.set	pop			\n"
 	: "=r" (x)
@@ -30,11 +32,13 @@ static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 }
 #define __arch_swab16 __arch_swab16
 
-static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
+static inline __attribute__((nomips16)) __attribute_const__
+		__u32 __arch_swab32(__u32 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips32r2		\n"
+	"	.set	nomips16		\n"
 	"	wsbh	%0, %1			\n"
 	"	rotr	%0, %0, 16		\n"
 	"	.set	pop			\n"
@@ -50,11 +54,13 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
  * 64-bit kernel on r2 CPUs.
  */
 #ifdef __mips64
-static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
+static inline __attribute__((nomips16)) __attribute_const__
+		__u64 __arch_swab64(__u64 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips64r2		\n"
+	"	.set	nomips16		\n"
 	"	dsbh	%0, %1			\n"
 	"	dshd	%0, %0			\n"
 	"	.set	pop			\n"
diff --git a/arch/mips/include/uapi/asm/ucontext.h b/arch/mips/include/uapi/asm/ucontext.h
new file mode 100644
index 000000000000..2320144ce858
--- /dev/null
+++ b/arch/mips/include/uapi/asm/ucontext.h
@@ -0,0 +1,65 @@
+#ifndef __MIPS_UAPI_ASM_UCONTEXT_H
+#define __MIPS_UAPI_ASM_UCONTEXT_H
+
+/**
+ * struct extcontext - extended context header structure
+ * @magic:	magic value identifying the type of extended context
+ * @size:	the size in bytes of the enclosing structure
+ *
+ * Extended context structures provide context which does not fit within struct
+ * sigcontext. They are placed sequentially in memory at the end of struct
+ * ucontext and struct sigframe, with each extended context structure beginning
+ * with a header defined by this struct. The type of context represented is
+ * indicated by the magic field. Userland may check each extended context
+ * structure against magic values that it recognises. The size field allows any
+ * unrecognised context to be skipped, allowing for future expansion. The end
+ * of the extended context data is indicated by the magic value
+ * END_EXTCONTEXT_MAGIC.
+ */
+struct extcontext {
+	unsigned int		magic;
+	unsigned int		size;
+};
+
+/**
+ * struct msa_extcontext - MSA extended context structure
+ * @ext:	the extended context header, with magic == MSA_EXTCONTEXT_MAGIC
+ * @wr:		the most significant 64 bits of each MSA vector register
+ * @csr:	the value of the MSA control & status register
+ *
+ * If MSA context is live for a task at the time a signal is delivered to it,
+ * this structure will hold the MSA context of the task as it was prior to the
+ * signal delivery.
+ */
+struct msa_extcontext {
+	struct extcontext	ext;
+#define MSA_EXTCONTEXT_MAGIC	0x784d5341	/* xMSA */
+
+	unsigned long long	wr[32];
+	unsigned int		csr;
+};
+
+#define END_EXTCONTEXT_MAGIC	0x78454e44	/* xEND */
+
+/**
+ * struct ucontext - user context structure
+ * @uc_flags:
+ * @uc_link:
+ * @uc_stack:
+ * @uc_mcontext:	holds basic processor state
+ * @uc_sigmask:
+ * @uc_extcontext:	holds extended processor state
+ */
+struct ucontext {
+	/* Historic fields matching asm-generic */
+	unsigned long		uc_flags;
+	struct ucontext		*uc_link;
+	stack_t			uc_stack;
+	struct sigcontext	uc_mcontext;
+	sigset_t		uc_sigmask;
+
+	/* Extended context structures may follow ucontext */
+	unsigned long long	uc_extcontext[0];
+};
+
+#endif /* __MIPS_UAPI_ASM_UCONTEXT_H */
diff --git a/arch/mips/jazz/irq.c b/arch/mips/jazz/irq.c
index e1ea4f625f7a..5d6828b2a750 100644
--- a/arch/mips/jazz/irq.c
+++ b/arch/mips/jazz/irq.c
@@ -110,18 +110,11 @@ asmlinkage void plat_irq_dispatch(void)
 	}
 }
 
-static void r4030_set_mode(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
-{
-	/* Nothing to do ...  */
-}
-
 struct clock_event_device r4030_clockevent = {
 	.name		= "r4030",
 	.features	= CLOCK_EVT_FEAT_PERIODIC,
 	.rating		= 300,
 	.irq		= JAZZ_TIMER_IRQ,
-	.set_mode	= r4030_set_mode,
 };
 
 static irqreturn_t r4030_timer_interrupt(int irq, void *dev_id)
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index 54c80d42a88d..6cd69fdaa1c5 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -231,6 +231,13 @@ static int jz_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
 	return 0;
 }
 
+static int jz_gpio_to_irq(struct gpio_chip *chip, unsigned gpio)
+{
+	struct jz_gpio_chip *jz_gpio = gpio_chip_to_jz_gpio_chip(chip);
+
+	return jz_gpio->irq_base + gpio;
+}
+
 int jz_gpio_port_direction_input(int port, uint32_t mask)
 {
 	writel(mask, GPIO_TO_REG(port, JZ_REG_GPIO_DIRECTION_CLEAR));
@@ -262,18 +269,6 @@ uint32_t jz_gpio_port_get_value(int port, uint32_t mask)
 }
 EXPORT_SYMBOL(jz_gpio_port_get_value);
 
-int gpio_to_irq(unsigned gpio)
-{
-	return JZ4740_IRQ_GPIO(0) + gpio;
-}
-EXPORT_SYMBOL_GPL(gpio_to_irq);
-
-int irq_to_gpio(unsigned irq)
-{
-	return irq - JZ4740_IRQ_GPIO(0);
-}
-EXPORT_SYMBOL_GPL(irq_to_gpio);
-
 #define IRQ_TO_BIT(irq) BIT(irq_to_gpio(irq) & 0x1f)
 
 static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq)
@@ -403,6 +398,7 @@ static int jz_gpio_irq_set_wake(struct irq_data *data, unsigned int on)
 		.get = jz_gpio_get_value, \
 		.direction_output = jz_gpio_direction_output, \
 		.direction_input = jz_gpio_direction_input, \
+		.to_irq = jz_gpio_to_irq, \
 		.base = JZ4740_GPIO_BASE_ ## _bank, \
 		.ngpio = JZ4740_GPIO_NUM_ ## _bank, \
 	}, \
@@ -423,8 +419,8 @@ static void jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id)
 	chip->base = ioremap(JZ4740_GPIO_BASE_ADDR + (id * 0x100), 0x100);
 
 	chip->irq = JZ4740_IRQ_INTC_GPIO(id);
-	irq_set_handler_data(chip->irq, chip);
-	irq_set_chained_handler(chip->irq, jz_gpio_irq_demux_handler);
+	irq_set_chained_handler_and_data(chip->irq,
+					 jz_gpio_irq_demux_handler, chip);
 
 	gc = irq_alloc_generic_chip(chip->gpio_chip.label, 1, chip->irq_base,
 		chip->base, handle_level_irq);
diff --git a/arch/mips/jz4740/time.c b/arch/mips/jz4740/time.c
index 7ab47fee1be8..1f7ca2c9f262 100644
--- a/arch/mips/jz4740/time.c
+++ b/arch/mips/jz4740/time.c
@@ -58,7 +58,7 @@ static irqreturn_t jz4740_clockevent_irq(int irq, void *devid)
 
 	jz4740_timer_ack_full(TIMER_CLOCKEVENT);
 
-	if (cd->mode != CLOCK_EVT_MODE_PERIODIC)
+	if (!clockevent_state_periodic(cd))
 		jz4740_timer_disable(TIMER_CLOCKEVENT);
 
 	cd->event_handler(cd);
@@ -66,24 +66,29 @@ static irqreturn_t jz4740_clockevent_irq(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
-static void jz4740_clockevent_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *cd)
+static int jz4740_clockevent_set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		jz4740_timer_set_count(TIMER_CLOCKEVENT, 0);
-		jz4740_timer_set_period(TIMER_CLOCKEVENT, jz4740_jiffies_per_tick);
-	case CLOCK_EVT_MODE_RESUME:
-		jz4740_timer_irq_full_enable(TIMER_CLOCKEVENT);
-		jz4740_timer_enable(TIMER_CLOCKEVENT);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		jz4740_timer_disable(TIMER_CLOCKEVENT);
-		break;
-	default:
-		break;
-	}
+	jz4740_timer_set_count(TIMER_CLOCKEVENT, 0);
+	jz4740_timer_set_period(TIMER_CLOCKEVENT, jz4740_jiffies_per_tick);
+	jz4740_timer_irq_full_enable(TIMER_CLOCKEVENT);
+	jz4740_timer_enable(TIMER_CLOCKEVENT);
+
+	return 0;
+}
+
+static int jz4740_clockevent_resume(struct clock_event_device *evt)
+{
+	jz4740_timer_irq_full_enable(TIMER_CLOCKEVENT);
+	jz4740_timer_enable(TIMER_CLOCKEVENT);
+
+	return 0;
+}
+
+static int jz4740_clockevent_shutdown(struct clock_event_device *evt)
+{
+	jz4740_timer_disable(TIMER_CLOCKEVENT);
+
+	return 0;
 }
 
 static int jz4740_clockevent_set_next(unsigned long evt,
@@ -100,7 +105,10 @@ static struct clock_event_device jz4740_clockevent = {
 	.name = "jz4740-timer",
 	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_next_event = jz4740_clockevent_set_next,
-	.set_mode = jz4740_clockevent_set_mode,
+	.set_state_shutdown = jz4740_clockevent_shutdown,
+	.set_state_periodic = jz4740_clockevent_set_periodic,
+	.set_state_oneshot = jz4740_clockevent_shutdown,
+	.tick_resume = jz4740_clockevent_resume,
 	.rating = 200,
 #ifdef CONFIG_MACH_JZ4740
 	.irq = JZ4740_IRQ_TCU0,
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 3f5cf8aff6f3..d982be1ea1c3 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -61,7 +61,6 @@ obj-$(CONFIG_MIPS_VPE_APSP_API) += rtlx.o
 obj-$(CONFIG_MIPS_VPE_APSP_API_CMP) += rtlx-cmp.o
 obj-$(CONFIG_MIPS_VPE_APSP_API_MT) += rtlx-mt.o
 
-obj-$(CONFIG_I8259)		+= i8259.o
 obj-$(CONFIG_IRQ_CPU_RM7K)	+= irq-rm7000.o
 obj-$(CONFIG_MIPS_MSC)		+= irq-msc01.o
 obj-$(CONFIG_IRQ_TXX9)		+= irq_txx9.o
@@ -100,6 +99,7 @@ obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_mipsxx.o
 
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o
 
 obj-$(CONFIG_MIPS_CM)		+= mips-cm.o
 obj-$(CONFIG_MIPS_CPC)		+= mips-cpc.o
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index beabe19ff8e5..154e2039ea5e 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -1,5 +1,5 @@
 /*
- * offset.c: Calculate pt_regs and task_struct offsets.
+ * asm-offsets.c: Calculate pt_regs and task_struct offsets.
  *
  * Copyright (C) 1996 David S. Miller
  * Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003 Ralf Baechle
@@ -128,6 +128,7 @@ void output_thread_defines(void)
 	       thread.cp0_baduaddr);
 	OFFSET(THREAD_ECODE, task_struct, \
 	       thread.error_code);
+	OFFSET(THREAD_TRAPNO, task_struct, thread.trap_nr);
 	BLANK();
 }
 
@@ -245,17 +246,6 @@ void output_sc_defines(void)
 }
 #endif
 
-#ifdef CONFIG_MIPS32_COMPAT
-void output_sc32_defines(void)
-{
-	COMMENT("Linux 32-bit sigcontext offsets.");
-	OFFSET(SC32_FPREGS, sigcontext32, sc_fpregs);
-	OFFSET(SC32_FPC_CSR, sigcontext32, sc_fpc_csr);
-	OFFSET(SC32_FPC_EIR, sigcontext32, sc_fpc_eir);
-	BLANK();
-}
-#endif
-
 void output_signal_defined(void)
 {
 	COMMENT("Linux signal numbers.");
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index c0c5e5972256..d8f9b357b222 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -600,7 +600,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		break;
 
 	case blezl_op: /* not really i_format */
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			goto sigill_r6;
 	case blez_op:
 		/*
@@ -635,7 +635,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		break;
 
 	case bgtzl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			goto sigill_r6;
 	case bgtz_op:
 		/*
diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c
index 7976457184b1..940ac00e9129 100644
--- a/arch/mips/kernel/cevt-bcm1480.c
+++ b/arch/mips/kernel/cevt-bcm1480.c
@@ -40,8 +40,8 @@
  * The general purpose timer ticks at 1MHz independent if
  * the rest of the system
  */
-static void sibyte_set_mode(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
+
+static int sibyte_set_periodic(struct clock_event_device *evt)
 {
 	unsigned int cpu = smp_processor_id();
 	void __iomem *cfg, *init;
@@ -49,24 +49,22 @@ static void sibyte_set_mode(enum clock_event_mode mode,
 	cfg = IOADDR(A_SCD_TIMER_REGISTER(cpu, R_SCD_TIMER_CFG));
 	init = IOADDR(A_SCD_TIMER_REGISTER(cpu, R_SCD_TIMER_INIT));
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		__raw_writeq(0, cfg);
-		__raw_writeq((V_SCD_TIMER_FREQ / HZ) - 1, init);
-		__raw_writeq(M_SCD_TIMER_ENABLE | M_SCD_TIMER_MODE_CONTINUOUS,
-			     cfg);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Stop the timer until we actually program a shot */
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		__raw_writeq(0, cfg);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:	/* shuddup gcc */
-	case CLOCK_EVT_MODE_RESUME:
-		;
-	}
+	__raw_writeq(0, cfg);
+	__raw_writeq((V_SCD_TIMER_FREQ / HZ) - 1, init);
+	__raw_writeq(M_SCD_TIMER_ENABLE | M_SCD_TIMER_MODE_CONTINUOUS, cfg);
+	return 0;
+}
+
+static int sibyte_shutdown(struct clock_event_device *evt)
+{
+	unsigned int cpu = smp_processor_id();
+	void __iomem *cfg;
+
+	cfg = IOADDR(A_SCD_TIMER_REGISTER(cpu, R_SCD_TIMER_CFG));
+
+	/* Stop the timer until we actually program a shot */
+	__raw_writeq(0, cfg);
+	return 0;
 }
 
 static int sibyte_next_event(unsigned long delta, struct clock_event_device *cd)
@@ -91,7 +89,7 @@ static irqreturn_t sibyte_counter_handler(int irq, void *dev_id)
 	void __iomem *cfg;
 	unsigned long tmode;
 
-	if (cd->mode == CLOCK_EVT_MODE_PERIODIC)
+	if (clockevent_state_periodic(cd))
 		tmode = M_SCD_TIMER_ENABLE | M_SCD_TIMER_MODE_CONTINUOUS;
 	else
 		tmode = 0;
@@ -130,7 +128,9 @@ void sb1480_clockevent_init(void)
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= sibyte_next_event;
-	cd->set_mode		= sibyte_set_mode;
+	cd->set_state_shutdown	= sibyte_shutdown;
+	cd->set_state_periodic	= sibyte_set_periodic;
+	cd->set_state_oneshot	= sibyte_shutdown;
 	clockevents_register_device(cd);
 
 	bcm1480_mask_irq(cpu, irq);
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
index ff1f01b72270..77a5ddf53f57 100644
--- a/arch/mips/kernel/cevt-ds1287.c
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -59,27 +59,32 @@ static int ds1287_set_next_event(unsigned long delta,
 	return -EINVAL;
 }
 
-static void ds1287_set_mode(enum clock_event_mode mode,
-			    struct clock_event_device *evt)
+static int ds1287_shutdown(struct clock_event_device *evt)
 {
 	u8 val;
 
 	spin_lock(&rtc_lock);
 
 	val = CMOS_READ(RTC_REG_B);
+	val &= ~RTC_PIE;
+	CMOS_WRITE(val, RTC_REG_B);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		val |= RTC_PIE;
-		break;
-	default:
-		val &= ~RTC_PIE;
-		break;
-	}
+	spin_unlock(&rtc_lock);
+	return 0;
+}
 
+static int ds1287_set_periodic(struct clock_event_device *evt)
+{
+	u8 val;
+
+	spin_lock(&rtc_lock);
+
+	val = CMOS_READ(RTC_REG_B);
+	val |= RTC_PIE;
 	CMOS_WRITE(val, RTC_REG_B);
 
 	spin_unlock(&rtc_lock);
+	return 0;
 }
 
 static void ds1287_event_handler(struct clock_event_device *dev)
@@ -87,11 +92,13 @@ static void ds1287_event_handler(struct clock_event_device *dev)
 }
 
 static struct clock_event_device ds1287_clockevent = {
-	.name		= "ds1287",
-	.features	= CLOCK_EVT_FEAT_PERIODIC,
-	.set_next_event = ds1287_set_next_event,
-	.set_mode	= ds1287_set_mode,
-	.event_handler	= ds1287_event_handler,
+	.name			= "ds1287",
+	.features		= CLOCK_EVT_FEAT_PERIODIC,
+	.set_next_event		= ds1287_set_next_event,
+	.set_state_shutdown	= ds1287_shutdown,
+	.set_state_periodic	= ds1287_set_periodic,
+	.tick_resume		= ds1287_shutdown,
+	.event_handler		= ds1287_event_handler,
 };
 
 static irqreturn_t ds1287_interrupt(int irq, void *dev_id)
diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c
index f069460751ab..66040051151d 100644
--- a/arch/mips/kernel/cevt-gt641xx.c
+++ b/arch/mips/kernel/cevt-gt641xx.c
@@ -64,8 +64,7 @@ static int gt641xx_timer0_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void gt641xx_timer0_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *evt)
+static int gt641xx_timer0_shutdown(struct clock_event_device *evt)
 {
 	u32 ctrl;
 
@@ -73,21 +72,39 @@ static void gt641xx_timer0_set_mode(enum clock_event_mode mode,
 
 	ctrl = GT_READ(GT_TC_CONTROL_OFS);
 	ctrl &= ~(GT_TC_CONTROL_ENTC0_MSK | GT_TC_CONTROL_SELTC0_MSK);
+	GT_WRITE(GT_TC_CONTROL_OFS, ctrl);
+
+	raw_spin_unlock(&gt641xx_timer_lock);
+	return 0;
+}
+
+static int gt641xx_timer0_set_oneshot(struct clock_event_device *evt)
+{
+	u32 ctrl;
+
+	raw_spin_lock(&gt641xx_timer_lock);
+
+	ctrl = GT_READ(GT_TC_CONTROL_OFS);
+	ctrl &= ~GT_TC_CONTROL_SELTC0_MSK;
+	ctrl |= GT_TC_CONTROL_ENTC0_MSK;
+	GT_WRITE(GT_TC_CONTROL_OFS, ctrl);
+
+	raw_spin_unlock(&gt641xx_timer_lock);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		ctrl |= GT_TC_CONTROL_ENTC0_MSK | GT_TC_CONTROL_SELTC0_MSK;
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		ctrl |= GT_TC_CONTROL_ENTC0_MSK;
-		break;
-	default:
-		break;
-	}
+static int gt641xx_timer0_set_periodic(struct clock_event_device *evt)
+{
+	u32 ctrl;
+
+	raw_spin_lock(&gt641xx_timer_lock);
 
+	ctrl = GT_READ(GT_TC_CONTROL_OFS);
+	ctrl |= GT_TC_CONTROL_ENTC0_MSK | GT_TC_CONTROL_SELTC0_MSK;
 	GT_WRITE(GT_TC_CONTROL_OFS, ctrl);
 
 	raw_spin_unlock(&gt641xx_timer_lock);
+	return 0;
 }
 
 static void gt641xx_timer0_event_handler(struct clock_event_device *dev)
@@ -95,12 +112,16 @@ static void gt641xx_timer0_event_handler(struct clock_event_device *dev)
 }
 
 static struct clock_event_device gt641xx_timer0_clockevent = {
-	.name		= "gt641xx-timer0",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.irq		= GT641XX_TIMER0_IRQ,
-	.set_next_event = gt641xx_timer0_set_next_event,
-	.set_mode	= gt641xx_timer0_set_mode,
-	.event_handler	= gt641xx_timer0_event_handler,
+	.name			= "gt641xx-timer0",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.irq			= GT641XX_TIMER0_IRQ,
+	.set_next_event		= gt641xx_timer0_set_next_event,
+	.set_state_shutdown	= gt641xx_timer0_shutdown,
+	.set_state_periodic	= gt641xx_timer0_set_periodic,
+	.set_state_oneshot	= gt641xx_timer0_set_oneshot,
+	.tick_resume		= gt641xx_timer0_shutdown,
+	.event_handler		= gt641xx_timer0_event_handler,
 };
 
 static irqreturn_t gt641xx_timer0_interrupt(int irq, void *dev_id)
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index d70c4d893219..8dfe6a6e1480 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -28,12 +28,6 @@ static int mips_next_event(unsigned long delta,
 	return res;
 }
 
-void mips_set_clock_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
-{
-	/* Nothing to do ...  */
-}
-
 DEFINE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 int cp0_timer_irq_installed;
 
@@ -174,6 +168,11 @@ int c0_compare_int_usable(void)
 	return 1;
 }
 
+unsigned int __weak get_c0_compare_int(void)
+{
+	return MIPS_CPU_IRQ_BASE + cp0_compare_irq;
+}
+
 int r4k_clockevent_init(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -189,11 +188,9 @@ int r4k_clockevent_init(void)
 	/*
 	 * With vectored interrupts things are getting platform specific.
 	 * get_c0_compare_int is a hook to allow a platform to return the
-	 * interrupt number of it's liking.
+	 * interrupt number of its liking.
 	 */
-	irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq;
-	if (get_c0_compare_int)
-		irq = get_c0_compare_int();
+	irq = get_c0_compare_int();
 
 	cd = &per_cpu(mips_clockevent_device, cpu);
 
@@ -212,7 +209,6 @@ int r4k_clockevent_init(void)
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= mips_next_event;
-	cd->set_mode		= mips_set_clock_mode;
 	cd->event_handler	= mips_event_handler;
 
 	clockevents_register_device(cd);
diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c
index 5ea6d6b1de15..3d860efd63b9 100644
--- a/arch/mips/kernel/cevt-sb1250.c
+++ b/arch/mips/kernel/cevt-sb1250.c
@@ -38,8 +38,20 @@
  * The general purpose timer ticks at 1MHz independent if
  * the rest of the system
  */
-static void sibyte_set_mode(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
+
+static int sibyte_shutdown(struct clock_event_device *evt)
+{
+	void __iomem *cfg;
+
+	cfg = IOADDR(A_SCD_TIMER_REGISTER(smp_processor_id(), R_SCD_TIMER_CFG));
+
+	/* Stop the timer until we actually program a shot */
+	__raw_writeq(0, cfg);
+
+	return 0;
+}
+
+static int sibyte_set_periodic(struct clock_event_device *evt)
 {
 	unsigned int cpu = smp_processor_id();
 	void __iomem *cfg, *init;
@@ -47,24 +59,11 @@ static void sibyte_set_mode(enum clock_event_mode mode,
 	cfg = IOADDR(A_SCD_TIMER_REGISTER(cpu, R_SCD_TIMER_CFG));
 	init = IOADDR(A_SCD_TIMER_REGISTER(cpu, R_SCD_TIMER_INIT));
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		__raw_writeq(0, cfg);
-		__raw_writeq((V_SCD_TIMER_FREQ / HZ) - 1, init);
-		__raw_writeq(M_SCD_TIMER_ENABLE | M_SCD_TIMER_MODE_CONTINUOUS,
-			     cfg);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Stop the timer until we actually program a shot */
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		__raw_writeq(0, cfg);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:	/* shuddup gcc */
-	case CLOCK_EVT_MODE_RESUME:
-		;
-	}
+	__raw_writeq(0, cfg);
+	__raw_writeq((V_SCD_TIMER_FREQ / HZ) - 1, init);
+	__raw_writeq(M_SCD_TIMER_ENABLE | M_SCD_TIMER_MODE_CONTINUOUS, cfg);
+
+	return 0;
 }
 
 static int sibyte_next_event(unsigned long delta, struct clock_event_device *cd)
@@ -89,7 +88,7 @@ static irqreturn_t sibyte_counter_handler(int irq, void *dev_id)
 	void __iomem *cfg;
 	unsigned long tmode;
 
-	if (cd->mode == CLOCK_EVT_MODE_PERIODIC)
+	if (clockevent_state_periodic(cd))
 		tmode = M_SCD_TIMER_ENABLE | M_SCD_TIMER_MODE_CONTINUOUS;
 	else
 		tmode = 0;
@@ -129,7 +128,9 @@ void sb1250_clockevent_init(void)
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= sibyte_next_event;
-	cd->set_mode		= sibyte_set_mode;
+	cd->set_state_shutdown	= sibyte_shutdown;
+	cd->set_state_periodic	= sibyte_set_periodic;
+	cd->set_state_oneshot	= sibyte_shutdown;
 	clockevents_register_device(cd);
 
 	sb1250_mask_irq(cpu, irq);
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index 723932441ecc..537eefdf838f 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -85,36 +85,54 @@ static void txx9tmr_stop_and_clear(struct txx9_tmr_reg __iomem *tmrptr)
 	__raw_writel(0, &tmrptr->tisr);
 }
 
-static void txx9tmr_set_mode(enum clock_event_mode mode,
-			     struct clock_event_device *evt)
+static int txx9tmr_set_state_periodic(struct clock_event_device *evt)
 {
 	struct txx9_clock_event_device *txx9_cd =
 		container_of(evt, struct txx9_clock_event_device, cd);
 	struct txx9_tmr_reg __iomem *tmrptr = txx9_cd->tmrptr;
 
 	txx9tmr_stop_and_clear(tmrptr);
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		__raw_writel(TXx9_TMITMR_TIIE | TXx9_TMITMR_TZCE,
-			     &tmrptr->itmr);
-		/* start timer */
-		__raw_writel(((u64)(NSEC_PER_SEC / HZ) * evt->mult) >>
-			     evt->shift,
-			     &tmrptr->cpra);
-		__raw_writel(TCR_BASE | TXx9_TMTCR_TCE, &tmrptr->tcr);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		__raw_writel(0, &tmrptr->itmr);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		__raw_writel(TXx9_TMITMR_TIIE, &tmrptr->itmr);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		__raw_writel(TIMER_CCD, &tmrptr->ccdr);
-		__raw_writel(0, &tmrptr->itmr);
-		break;
-	}
+
+	__raw_writel(TXx9_TMITMR_TIIE | TXx9_TMITMR_TZCE, &tmrptr->itmr);
+	/* start timer */
+	__raw_writel(((u64)(NSEC_PER_SEC / HZ) * evt->mult) >> evt->shift,
+		     &tmrptr->cpra);
+	__raw_writel(TCR_BASE | TXx9_TMTCR_TCE, &tmrptr->tcr);
+	return 0;
+}
+
+static int txx9tmr_set_state_oneshot(struct clock_event_device *evt)
+{
+	struct txx9_clock_event_device *txx9_cd =
+		container_of(evt, struct txx9_clock_event_device, cd);
+	struct txx9_tmr_reg __iomem *tmrptr = txx9_cd->tmrptr;
+
+	txx9tmr_stop_and_clear(tmrptr);
+	__raw_writel(TXx9_TMITMR_TIIE, &tmrptr->itmr);
+	return 0;
+}
+
+static int txx9tmr_set_state_shutdown(struct clock_event_device *evt)
+{
+	struct txx9_clock_event_device *txx9_cd =
+		container_of(evt, struct txx9_clock_event_device, cd);
+	struct txx9_tmr_reg __iomem *tmrptr = txx9_cd->tmrptr;
+
+	txx9tmr_stop_and_clear(tmrptr);
+	__raw_writel(0, &tmrptr->itmr);
+	return 0;
+}
+
+static int txx9tmr_tick_resume(struct clock_event_device *evt)
+{
+	struct txx9_clock_event_device *txx9_cd =
+		container_of(evt, struct txx9_clock_event_device, cd);
+	struct txx9_tmr_reg __iomem *tmrptr = txx9_cd->tmrptr;
+
+	txx9tmr_stop_and_clear(tmrptr);
+	__raw_writel(TIMER_CCD, &tmrptr->ccdr);
+	__raw_writel(0, &tmrptr->itmr);
+	return 0;
 }
 
 static int txx9tmr_set_next_event(unsigned long delta,
@@ -133,12 +151,15 @@ static int txx9tmr_set_next_event(unsigned long delta,
 
 static struct txx9_clock_event_device txx9_clock_event_device = {
 	.cd = {
-		.name		= "TXx9",
-		.features	= CLOCK_EVT_FEAT_PERIODIC |
-				  CLOCK_EVT_FEAT_ONESHOT,
-		.rating		= 200,
-		.set_mode	= txx9tmr_set_mode,
-		.set_next_event = txx9tmr_set_next_event,
+		.name			= "TXx9",
+		.features		= CLOCK_EVT_FEAT_PERIODIC |
+					  CLOCK_EVT_FEAT_ONESHOT,
+		.rating			= 200,
+		.set_state_shutdown	= txx9tmr_set_state_shutdown,
+		.set_state_periodic	= txx9tmr_set_state_periodic,
+		.set_state_oneshot	= txx9tmr_set_state_oneshot,
+		.tick_resume		= txx9tmr_tick_resume,
+		.set_next_event		= txx9tmr_set_next_event,
 	},
 };
 
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 55b759a0019e..9f71c06aebf6 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -60,7 +60,7 @@ LEAF(mips_cps_core_entry)
 	 nop
 
 	/* This is an NMI */
-	la	k0, nmi_handler
+	PTR_LA	k0, nmi_handler
 	jr	k0
 	 nop
 
@@ -107,10 +107,10 @@ not_nmi:
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
-	li	a0, KSEG0
-	add	a1, a0, t1
+	li	a0, CKSEG0
+	PTR_ADD	a1, a0, t1
 1:	cache	Index_Store_Tag_I, 0(a0)
-	add	a0, a0, t0
+	PTR_ADD	a0, a0, t0
 	bne	a0, a1, 1b
 	 nop
 icache_done:
@@ -134,12 +134,12 @@ icache_done:
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
-	li	a0, KSEG0
-	addu	a1, a0, t1
-	subu	a1, a1, t0
+	li	a0, CKSEG0
+	PTR_ADDU a1, a0, t1
+	PTR_SUBU a1, a1, t0
 1:	cache	Index_Store_Tag_D, 0(a0)
 	bne	a0, a1, 1b
-	 add	a0, a0, t0
+	 PTR_ADD a0, a0, t0
 dcache_done:
 
 	/* Set Kseg0 CCA to that in s0 */
@@ -156,7 +156,7 @@ dcache_done:
 	ehb
 
 	/* Jump to kseg0 */
-	la	t0, 1f
+	PTR_LA	t0, 1f
 	jr	t0
 	 nop
 
@@ -178,9 +178,9 @@ dcache_done:
 	 nop
 
 	/* Off we go! */
-	lw	t1, VPEBOOTCFG_PC(v0)
-	lw	gp, VPEBOOTCFG_GP(v0)
-	lw	sp, VPEBOOTCFG_SP(v0)
+	PTR_L	t1, VPEBOOTCFG_PC(v0)
+	PTR_L	gp, VPEBOOTCFG_GP(v0)
+	PTR_L	sp, VPEBOOTCFG_SP(v0)
 	jr	t1
 	 nop
 	END(mips_cps_core_entry)
@@ -217,7 +217,7 @@ LEAF(excep_intex)
 
 .org 0x480
 LEAF(excep_ejtag)
-	la	k0, ejtag_debug_handler
+	PTR_LA	k0, ejtag_debug_handler
 	jr	k0
 	 nop
 	END(excep_ejtag)
@@ -229,7 +229,7 @@ LEAF(mips_cps_core_init)
 	 nop
 
 	.set	push
-	.set	mips32r2
+	.set	mips64r2
 	.set	mt
 
 	/* Only allow 1 TC per VPE to execute... */
@@ -237,7 +237,7 @@ LEAF(mips_cps_core_init)
 
 	/* ...and for the moment only 1 VPE */
 	dvpe
-	la	t1, 1f
+	PTR_LA	t1, 1f
 	jr.hb	t1
 	 nop
 
@@ -250,25 +250,25 @@ LEAF(mips_cps_core_init)
 	mfc0	t0, CP0_MVPCONF0
 	srl	t0, t0, MVPCONF0_PVPE_SHIFT
 	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
-	addiu	t7, t0, 1
+	addiu	ta3, t0, 1
 
 	/* If there's only 1, we're done */
 	beqz	t0, 2f
 	 nop
 
 	/* Loop through each VPE within this core */
-	li	t5, 1
+	li	ta1, 1
 
 1:	/* Operate on the appropriate TC */
-	mtc0	t5, CP0_VPECONTROL
+	mtc0	ta1, CP0_VPECONTROL
 	ehb
 
 	/* Bind TC to VPE (1:1 TC:VPE mapping) */
-	mttc0	t5, CP0_TCBIND
+	mttc0	ta1, CP0_TCBIND
 
 	/* Set exclusive TC, non-active, master */
 	li	t0, VPECONF0_MVP
-	sll	t1, t5, VPECONF0_XTC_SHIFT
+	sll	t1, ta1, VPECONF0_XTC_SHIFT
 	or	t0, t0, t1
 	mttc0	t0, CP0_VPECONF0
 
@@ -280,8 +280,8 @@ LEAF(mips_cps_core_init)
 	mttc0	t0, CP0_TCHALT
 
 	/* Next VPE */
-	addiu	t5, t5, 1
-	slt	t0, t5, t7
+	addiu	ta1, ta1, 1
+	slt	t0, ta1, ta3
 	bnez	t0, 1b
 	 nop
 
@@ -298,19 +298,19 @@ LEAF(mips_cps_core_init)
 
 LEAF(mips_cps_boot_vpes)
 	/* Retrieve CM base address */
-	la	t0, mips_cm_base
-	lw	t0, 0(t0)
+	PTR_LA	t0, mips_cm_base
+	PTR_L	t0, 0(t0)
 
 	/* Calculate a pointer to this cores struct core_boot_config */
 	lw	t0, GCR_CL_ID_OFS(t0)
 	li	t1, COREBOOTCFG_SIZE
 	mul	t0, t0, t1
-	la	t1, mips_cps_core_bootcfg
-	lw	t1, 0(t1)
-	addu	t0, t0, t1
+	PTR_LA	t1, mips_cps_core_bootcfg
+	PTR_L	t1, 0(t1)
+	PTR_ADDU t0, t0, t1
 
 	/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
-	has_mt	t6, 1f
+	has_mt	ta2, 1f
 	 li	t9, 0
 
 	/* Find the number of VPEs present in the core */
@@ -334,24 +334,24 @@ LEAF(mips_cps_boot_vpes)
 1:	/* Calculate a pointer to this VPEs struct vpe_boot_config */
 	li	t1, VPEBOOTCFG_SIZE
 	mul	v0, t9, t1
-	lw	t7, COREBOOTCFG_VPECONFIG(t0)
-	addu	v0, v0, t7
+	PTR_L	ta3, COREBOOTCFG_VPECONFIG(t0)
+	PTR_ADDU v0, v0, ta3
 
 #ifdef CONFIG_MIPS_MT
 
 	/* If the core doesn't support MT then return */
-	bnez	t6, 1f
+	bnez	ta2, 1f
 	 nop
 	jr	ra
 	 nop
 
 	.set	push
-	.set	mips32r2
+	.set	mips64r2
 	.set	mt
 
 1:	/* Enter VPE configuration state */
 	dvpe
-	la	t1, 1f
+	PTR_LA	t1, 1f
 	jr.hb	t1
 	 nop
 1:	mfc0	t1, CP0_MVPCONTROL
@@ -360,12 +360,12 @@ LEAF(mips_cps_boot_vpes)
 	ehb
 
 	/* Loop through each VPE */
-	lw	t6, COREBOOTCFG_VPEMASK(t0)
-	move	t8, t6
-	li	t5, 0
+	PTR_L	ta2, COREBOOTCFG_VPEMASK(t0)
+	move	t8, ta2
+	li	ta1, 0
 
 	/* Check whether the VPE should be running. If not, skip it */
-1:	andi	t0, t6, 1
+1:	andi	t0, ta2, 1
 	beqz	t0, 2f
 	 nop
 
@@ -373,7 +373,7 @@ LEAF(mips_cps_boot_vpes)
 	mfc0	t0, CP0_VPECONTROL
 	ori	t0, t0, VPECONTROL_TARGTC
 	xori	t0, t0, VPECONTROL_TARGTC
-	or	t0, t0, t5
+	or	t0, t0, ta1
 	mtc0	t0, CP0_VPECONTROL
 	ehb
 
@@ -384,8 +384,8 @@ LEAF(mips_cps_boot_vpes)
 
 	/* Calculate a pointer to the VPEs struct vpe_boot_config */
 	li	t0, VPEBOOTCFG_SIZE
-	mul	t0, t0, t5
-	addu	t0, t0, t7
+	mul	t0, t0, ta1
+	addu	t0, t0, ta3
 
 	/* Set the TC restart PC */
 	lw	t1, VPEBOOTCFG_PC(t0)
@@ -423,9 +423,9 @@ LEAF(mips_cps_boot_vpes)
 	mttc0	t0, CP0_VPECONF0
 
 	/* Next VPE */
-2:	srl	t6, t6, 1
-	addiu	t5, t5, 1
-	bnez	t6, 1b
+2:	srl	ta2, ta2, 1
+	addiu	ta1, ta1, 1
+	bnez	ta2, 1b
 	 nop
 
 	/* Leave VPE configuration state */
@@ -445,7 +445,7 @@ LEAF(mips_cps_boot_vpes)
 	/* This VPE should be offline, halt the TC */
 	li	t0, TCHALT_H
 	mtc0	t0, CP0_TCHALT
-	la	t0, 1f
+	PTR_LA	t0, 1f
 1:	jr.hb	t0
 	 nop
 
@@ -466,10 +466,10 @@ LEAF(mips_cps_boot_vpes)
 	.set	noat
 	lw	$1, TI_CPU(gp)
 	sll	$1, $1, LONGLOG
-	la	\dest, __per_cpu_offset
+	PTR_LA	\dest, __per_cpu_offset
 	addu	$1, $1, \dest
 	lw	$1, 0($1)
-	la	\dest, cps_cpu_state
+	PTR_LA	\dest, cps_cpu_state
 	addu	\dest, \dest, $1
 	.set	pop
 	.endm
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index dbe0792fc9c1..571a8e6ea5bd 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -32,6 +32,9 @@
 #include <asm/spram.h>
 #include <asm/uaccess.h>
 
+/* Hardware capabilities */
+unsigned int elf_hwcap __read_mostly;
+
 /*
  * Get the FPU Implementation/Revision.
  */
@@ -188,7 +191,7 @@ __setup("nohtw", htw_disable);
 static int mips_ftlb_disabled;
 static int mips_has_ftlb_configured;
 
-static void set_ftlb_enable(struct cpuinfo_mips *c, int enable);
+static int set_ftlb_enable(struct cpuinfo_mips *c, int enable);
 
 static int __init ftlb_disable(char *s)
 {
@@ -202,7 +205,10 @@ static int __init ftlb_disable(char *s)
 		return 1;
 
 	/* Disable it in the boot cpu */
-	set_ftlb_enable(&cpu_data[0], 0);
+	if (set_ftlb_enable(&cpu_data[0], 0)) {
+		pr_warn("Can't turn FTLB off\n");
+		return 1;
+	}
 
 	back_to_back_c0_hazard();
 
@@ -364,30 +370,41 @@ static unsigned int calculate_ftlb_probability(struct cpuinfo_mips *c)
 		return 3;
 }
 
-static void set_ftlb_enable(struct cpuinfo_mips *c, int enable)
+static int set_ftlb_enable(struct cpuinfo_mips *c, int enable)
 {
-	unsigned int config6;
+	unsigned int config;
 
 	/* It's implementation dependent how the FTLB can be enabled */
 	switch (c->cputype) {
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 		/* proAptiv & related cores use Config6 to enable the FTLB */
-		config6 = read_c0_config6();
+		config = read_c0_config6();
 		/* Clear the old probability value */
-		config6 &= ~(3 << MIPS_CONF6_FTLBP_SHIFT);
+		config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT);
 		if (enable)
 			/* Enable FTLB */
-			write_c0_config6(config6 |
+			write_c0_config6(config |
 					 (calculate_ftlb_probability(c)
 					  << MIPS_CONF6_FTLBP_SHIFT)
 					 | MIPS_CONF6_FTLBEN);
 		else
 			/* Disable FTLB */
-			write_c0_config6(config6 &  ~MIPS_CONF6_FTLBEN);
-		back_to_back_c0_hazard();
+			write_c0_config6(config &  ~MIPS_CONF6_FTLBEN);
 		break;
+	case CPU_I6400:
+		/* I6400 & related cores use Config7 to configure FTLB */
+		config = read_c0_config7();
+		/* Clear the old probability value */
+		config &= ~(3 << MIPS_CONF7_FTLBP_SHIFT);
+		write_c0_config7(config | (calculate_ftlb_probability(c)
+					   << MIPS_CONF7_FTLBP_SHIFT));
+		break;
+	default:
+		return 1;
 	}
+
+	return 0;
 }
 
 static inline unsigned int decode_config0(struct cpuinfo_mips *c)
@@ -524,6 +541,8 @@ static inline unsigned int decode_config3(struct cpuinfo_mips *c)
 	}
 	if (config3 & MIPS_CONF3_CDMM)
 		c->options |= MIPS_CPU_CDMM;
+	if (config3 & MIPS_CONF3_SP)
+		c->options |= MIPS_CPU_SP;
 
 	return config3 & MIPS_CONF_M;
 }
@@ -540,7 +559,16 @@ static inline unsigned int decode_config4(struct cpuinfo_mips *c)
 	if (cpu_has_tlb) {
 		if (((config4 & MIPS_CONF4_IE) >> 29) == 2)
 			c->options |= MIPS_CPU_TLBINV;
-		mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+		/*
+		 * This is a bit ugly. R6 has dropped that field from
+		 * config4 and the only valid configuration is VTLB+FTLB so
+		 * set a good value for mmuextdef for that case.
+		 */
+		if (cpu_has_mips_r6)
+			mmuextdef = MIPS_CONF4_MMUEXTDEF_VTLBSIZEEXT;
+		else
+			mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+
 		switch (mmuextdef) {
 		case MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT:
 			c->tlbsize += (config4 & MIPS_CONF4_MMUSIZEEXT) * 0x40;
@@ -1121,6 +1149,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 		c->cputype = CPU_P5600;
 		__cpu_name[cpu] = "MIPS P5600";
 		break;
+	case PRID_IMP_I6400:
+		c->cputype = CPU_I6400;
+		__cpu_name[cpu] = "MIPS I6400";
+		break;
 	case PRID_IMP_M5150:
 		c->cputype = CPU_M5150;
 		__cpu_name[cpu] = "MIPS M5150";
@@ -1492,10 +1524,14 @@ void cpu_probe(void)
 	else
 		c->srsets = 1;
 
+	if (cpu_has_mips_r6)
+		elf_hwcap |= HWCAP_MIPS_R6;
+
 	if (cpu_has_msa) {
 		c->msa_id = cpu_get_msa_id();
 		WARN(c->msa_id & MSA_IR_WRPF,
 		     "Vector register partitioning unimplemented!");
+		elf_hwcap |= HWCAP_MIPS_MSA;
 	}
 
 	cpu_probe_vmbits(c);
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index af42e7003f12..baa7b6fc0a60 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -407,7 +407,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	noat
 	SAVE_ALL
 	FEXPORT(handle_\exception\ext)
-	__BUILD_clear_\clear
+	__build_clear_\clear
 	.set	at
 	__BUILD_\verbose \exception
 	move	a0, sp
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index e4f62b7875d2..ab1478d5a4db 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -196,6 +196,7 @@ void __init check_wait(void)
 	case CPU_INTERAPTIV:
 	case CPU_M5150:
 	case CPU_QEMU_GENERIC:
+	case CPU_I6400:
 		cpu_wait = r4k_wait;
 		if (read_c0_config7() & MIPS_CONF7_WII)
 			cpu_wait = r4k_wait_irqoff;
diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c
index dda800e9e731..3e586daa3a32 100644
--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@@ -51,7 +51,7 @@ void arch_jump_label_transform(struct jump_entry *e,
 	/* Target must have the right alignment and ISA must be preserved. */
 	BUG_ON((e->target & J_ALIGN_MASK) != J_ISA_BIT);
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		insn.j_format.opcode = J_ISA_BIT ? mm_j32_op : j_op;
 		insn.j_format.target = e->target >> J_RANGE_SHIFT;
 	} else {
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 85bbe9b96759..b8ceee576cdf 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -15,11 +15,131 @@
 
 void __iomem *mips_cm_base;
 void __iomem *mips_cm_l2sync_base;
+int mips_cm_is64;
+
+static char *cm2_tr[8] = {
+	"mem",	"gcr",	"gic",	"mmio",
+	"0x04", "cpc", "0x06", "0x07"
+};
+
+/* CM3 Tag ECC transation type */
+static char *cm3_tr[16] = {
+	[0x0] = "ReqNoData",
+	[0x1] = "0x1",
+	[0x2] = "ReqWData",
+	[0x3] = "0x3",
+	[0x4] = "IReqNoResp",
+	[0x5] = "IReqWResp",
+	[0x6] = "IReqNoRespDat",
+	[0x7] = "IReqWRespDat",
+	[0x8] = "RespNoData",
+	[0x9] = "RespDataFol",
+	[0xa] = "RespWData",
+	[0xb] = "RespDataOnly",
+	[0xc] = "IRespNoData",
+	[0xd] = "IRespDataFol",
+	[0xe] = "IRespWData",
+	[0xf] = "IRespDataOnly"
+};
+
+static char *cm2_cmd[32] = {
+	[0x00] = "0x00",
+	[0x01] = "Legacy Write",
+	[0x02] = "Legacy Read",
+	[0x03] = "0x03",
+	[0x04] = "0x04",
+	[0x05] = "0x05",
+	[0x06] = "0x06",
+	[0x07] = "0x07",
+	[0x08] = "Coherent Read Own",
+	[0x09] = "Coherent Read Share",
+	[0x0a] = "Coherent Read Discard",
+	[0x0b] = "Coherent Ready Share Always",
+	[0x0c] = "Coherent Upgrade",
+	[0x0d] = "Coherent Writeback",
+	[0x0e] = "0x0e",
+	[0x0f] = "0x0f",
+	[0x10] = "Coherent Copyback",
+	[0x11] = "Coherent Copyback Invalidate",
+	[0x12] = "Coherent Invalidate",
+	[0x13] = "Coherent Write Invalidate",
+	[0x14] = "Coherent Completion Sync",
+	[0x15] = "0x15",
+	[0x16] = "0x16",
+	[0x17] = "0x17",
+	[0x18] = "0x18",
+	[0x19] = "0x19",
+	[0x1a] = "0x1a",
+	[0x1b] = "0x1b",
+	[0x1c] = "0x1c",
+	[0x1d] = "0x1d",
+	[0x1e] = "0x1e",
+	[0x1f] = "0x1f"
+};
+
+/* CM3 Tag ECC command type */
+static char *cm3_cmd[16] = {
+	[0x0] = "Legacy Read",
+	[0x1] = "Legacy Write",
+	[0x2] = "Coherent Read Own",
+	[0x3] = "Coherent Read Share",
+	[0x4] = "Coherent Read Discard",
+	[0x5] = "Coherent Evicted",
+	[0x6] = "Coherent Upgrade",
+	[0x7] = "Coherent Upgrade for Store Conditional",
+	[0x8] = "Coherent Writeback",
+	[0x9] = "Coherent Write Invalidate",
+	[0xa] = "0xa",
+	[0xb] = "0xb",
+	[0xc] = "0xc",
+	[0xd] = "0xd",
+	[0xe] = "0xe",
+	[0xf] = "0xf"
+};
+
+/* CM3 Tag ECC command group */
+static char *cm3_cmd_group[8] = {
+	[0x0] = "Normal",
+	[0x1] = "Registers",
+	[0x2] = "TLB",
+	[0x3] = "0x3",
+	[0x4] = "L1I",
+	[0x5] = "L1D",
+	[0x6] = "L3",
+	[0x7] = "L2"
+};
+
+static char *cm2_core[8] = {
+	"Invalid/OK",	"Invalid/Data",
+	"Shared/OK",	"Shared/Data",
+	"Modified/OK",	"Modified/Data",
+	"Exclusive/OK", "Exclusive/Data"
+};
+
+static char *cm2_causes[32] = {
+	"None", "GC_WR_ERR", "GC_RD_ERR", "COH_WR_ERR",
+	"COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07",
+	"0x08", "0x09", "0x0a", "0x0b",
+	"0x0c", "0x0d", "0x0e", "0x0f",
+	"0x10", "0x11", "0x12", "0x13",
+	"0x14", "0x15", "0x16", "INTVN_WR_ERR",
+	"INTVN_RD_ERR", "0x19", "0x1a", "0x1b",
+	"0x1c", "0x1d", "0x1e", "0x1f"
+};
+
+static char *cm3_causes[32] = {
+	"0x0", "MP_CORRECTABLE_ECC_ERR", "MP_REQUEST_DECODE_ERR",
+	"MP_UNCORRECTABLE_ECC_ERR", "MP_PARITY_ERR", "MP_COHERENCE_ERR",
+	"CMBIU_REQUEST_DECODE_ERR", "CMBIU_PARITY_ERR", "CMBIU_AXI_RESP_ERR",
+	"0x9", "RBI_BUS_ERR", "0xb", "0xc", "0xd", "0xe", "0xf", "0x10",
+	"0x11", "0x12", "0x13", "0x14", "0x15", "0x16", "0x17", "0x18",
+	"0x19", "0x1a", "0x1b", "0x1c", "0x1d", "0x1e", "0x1f"
+};
 
 phys_addr_t __mips_cm_phys_base(void)
 {
 	u32 config3 = read_c0_config3();
-	u32 cmgcr;
+	unsigned long cmgcr;
 
 	/* Check the CMGCRBase register is implemented */
 	if (!(config3 & MIPS_CONF3_CMGCR))
@@ -81,6 +201,13 @@ int mips_cm_probe(void)
 	phys_addr_t addr;
 	u32 base_reg;
 
+	/*
+	 * No need to probe again if we have already been
+	 * here before.
+	 */
+	if (mips_cm_base)
+		return 0;
+
 	addr = mips_cm_phys_base();
 	BUG_ON((addr & CM_GCR_BASE_GCRBASE_MSK) != addr);
 	if (!addr)
@@ -117,5 +244,133 @@ int mips_cm_probe(void)
 	/* probe for an L2-only sync region */
 	mips_cm_probe_l2sync();
 
+	/* determine register width for this CM */
+	mips_cm_is64 = config_enabled(CONFIG_64BIT) && (mips_cm_revision() >= CM_REV_CM3);
+
 	return 0;
 }
+
+void mips_cm_error_report(void)
+{
+	unsigned long revision = mips_cm_revision();
+	/*
+	 * CM3 has a 64-bit Error cause register with 0:57 containing the error
+	 * info and 63:58 the error type. For old CMs, everything is contained
+	 * in a single 32-bit register (0:26 and 31:27 respectively). Even
+	 * though the cm_error is u64, we will simply ignore the upper word
+	 * for CM2.
+	 */
+	u64 cm_error = read_gcr_error_cause();
+	int cm_error_cause_sft = CM_GCR_ERROR_CAUSE_ERRTYPE_SHF +
+				 ((revision >= CM_REV_CM3) ? 31 : 0);
+	unsigned long cm_addr = read_gcr_error_addr();
+	unsigned long cm_other = read_gcr_error_mult();
+	int ocause, cause;
+	char buf[256];
+
+	if (!mips_cm_present())
+		return;
+
+	cause = cm_error >> cm_error_cause_sft;
+
+	if (!cause)
+		/* All good */
+		return;
+
+	ocause = cm_other >> CM_GCR_ERROR_MULT_ERR2ND_SHF;
+	if (revision < CM_REV_CM3) { /* CM2 */
+		if (cause < 16) {
+			unsigned long cca_bits = (cm_error >> 15) & 7;
+			unsigned long tr_bits = (cm_error >> 12) & 7;
+			unsigned long cmd_bits = (cm_error >> 7) & 0x1f;
+			unsigned long stag_bits = (cm_error >> 3) & 15;
+			unsigned long sport_bits = (cm_error >> 0) & 7;
+
+			snprintf(buf, sizeof(buf),
+				 "CCA=%lu TR=%s MCmd=%s STag=%lu "
+				 "SPort=%lu\n", cca_bits, cm2_tr[tr_bits],
+				 cm2_cmd[cmd_bits], stag_bits, sport_bits);
+		} else {
+			/* glob state & sresp together */
+			unsigned long c3_bits = (cm_error >> 18) & 7;
+			unsigned long c2_bits = (cm_error >> 15) & 7;
+			unsigned long c1_bits = (cm_error >> 12) & 7;
+			unsigned long c0_bits = (cm_error >> 9) & 7;
+			unsigned long sc_bit = (cm_error >> 8) & 1;
+			unsigned long cmd_bits = (cm_error >> 3) & 0x1f;
+			unsigned long sport_bits = (cm_error >> 0) & 7;
+
+			snprintf(buf, sizeof(buf),
+				 "C3=%s C2=%s C1=%s C0=%s SC=%s "
+				 "MCmd=%s SPort=%lu\n",
+				 cm2_core[c3_bits], cm2_core[c2_bits],
+				 cm2_core[c1_bits], cm2_core[c0_bits],
+				 sc_bit ? "True" : "False",
+				 cm2_cmd[cmd_bits], sport_bits);
+		}
+			pr_err("CM_ERROR=%08llx %s <%s>\n", cm_error,
+			       cm2_causes[cause], buf);
+		pr_err("CM_ADDR =%08lx\n", cm_addr);
+		pr_err("CM_OTHER=%08lx %s\n", cm_other, cm2_causes[ocause]);
+	} else { /* CM3 */
+	/* Used by cause == {1,2,3} */
+		unsigned long core_id_bits = (cm_error >> 22) & 0xf;
+		unsigned long vp_id_bits = (cm_error >> 18) & 0xf;
+		unsigned long cmd_bits = (cm_error >> 14) & 0xf;
+		unsigned long cmd_group_bits = (cm_error >> 11) & 0xf;
+		unsigned long cm3_cca_bits = (cm_error >> 8) & 7;
+		unsigned long mcp_bits = (cm_error >> 5) & 0xf;
+		unsigned long cm3_tr_bits = (cm_error >> 1) & 0xf;
+		unsigned long sched_bit = cm_error & 0x1;
+
+		if (cause == 1 || cause == 3) { /* Tag ECC */
+			unsigned long tag_ecc = (cm_error >> 57) & 0x1;
+			unsigned long tag_way_bits = (cm_error >> 29) & 0xffff;
+			unsigned long dword_bits = (cm_error >> 49) & 0xff;
+			unsigned long data_way_bits = (cm_error >> 45) & 0xf;
+			unsigned long data_sets_bits = (cm_error >> 29) & 0xfff;
+			unsigned long bank_bit = (cm_error >> 28) & 0x1;
+			snprintf(buf, sizeof(buf),
+				 "%s ECC Error: Way=%lu (DWORD=%lu, Sets=%lu)"
+				 "Bank=%lu CoreID=%lu VPID=%lu Command=%s"
+				 "Command Group=%s CCA=%lu MCP=%d"
+				 "Transaction type=%s Scheduler=%lu\n",
+				 tag_ecc ? "TAG" : "DATA",
+				 tag_ecc ? (unsigned long)ffs(tag_way_bits) - 1 :
+				 data_way_bits, bank_bit, dword_bits,
+				 data_sets_bits,
+				 core_id_bits, vp_id_bits,
+				 cm3_cmd[cmd_bits],
+				 cm3_cmd_group[cmd_group_bits],
+				 cm3_cca_bits, 1 << mcp_bits,
+				 cm3_tr[cm3_tr_bits], sched_bit);
+		} else if (cause == 2) {
+			unsigned long data_error_type = (cm_error >> 41) & 0xfff;
+			unsigned long data_decode_cmd = (cm_error >> 37) & 0xf;
+			unsigned long data_decode_group = (cm_error >> 34) & 0x7;
+			unsigned long data_decode_destination_id = (cm_error >> 28) & 0x3f;
+
+			snprintf(buf, sizeof(buf),
+				 "Decode Request Error: Type=%lu, Command=%lu"
+				 "Command Group=%lu Destination ID=%lu"
+				 "CoreID=%lu VPID=%lu Command=%s"
+				 "Command Group=%s CCA=%lu MCP=%d"
+				 "Transaction type=%s Scheduler=%lu\n",
+				 data_error_type, data_decode_cmd,
+				 data_decode_group, data_decode_destination_id,
+				 core_id_bits, vp_id_bits,
+				 cm3_cmd[cmd_bits],
+				 cm3_cmd_group[cmd_group_bits],
+				 cm3_cca_bits, 1 << mcp_bits,
+				 cm3_tr[cm3_tr_bits], sched_bit);
+		}
+
+		pr_err("CM_ERROR=%llx %s <%s>\n", cm_error,
+		       cm3_causes[cause], buf);
+		pr_err("CM_ADDR =%lx\n", cm_addr);
+		pr_err("CM_OTHER=%lx %s\n", cm_other, cm3_causes[ocause]);
+	}
+
+	/* reprime cause register */
+	write_gcr_error_cause(0);
+}
diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c
index 11964501c4b0..8af4d627b68b 100644
--- a/arch/mips/kernel/mips-cpc.c
+++ b/arch/mips/kernel/mips-cpc.c
@@ -21,9 +21,16 @@ static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock);
 
 static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags);
 
-phys_addr_t __weak mips_cpc_phys_base(void)
+/**
+ * mips_cpc_phys_base - retrieve the physical base address of the CPC
+ *
+ * This function returns the physical base address of the Cluster Power
+ * Controller memory mapped registers, or 0 if no Cluster Power Controller
+ * is present.
+ */
+static phys_addr_t mips_cpc_phys_base(void)
 {
-	u32 cpc_base;
+	unsigned long cpc_base;
 
 	if (!mips_cm_present())
 		return 0;
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 3e4491aa6d6b..789d7bf4fef3 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 				      unsigned long __user *user_mask_ptr)
 {
 	unsigned int real_len;
-	cpumask_t mask;
+	cpumask_t allowed, mask;
 	int retval;
 	struct task_struct *p;
 
@@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 	if (retval)
 		goto out_unlock;
 
-	cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
+	cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+	cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index cc1b6fadf089..d7b8dd43147a 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1556,6 +1556,7 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 #endif
 		break;
 	case CPU_P5600:
+	case CPU_I6400:
 		/* 8-bit event numbers */
 		raw_id = config & 0x1ff;
 		base_id = raw_id & 0xff;
@@ -1717,6 +1718,11 @@ init_hw_perf_events(void)
 		mipspmu.general_event_map = &mipsxxcore_event_map2;
 		mipspmu.cache_event_map = &mipsxxcore_cache_map2;
 		break;
+	case CPU_I6400:
+		mipspmu.name = "mips/I6400";
+		mipspmu.general_event_map = &mipsxxcore_event_map2;
+		mipspmu.cache_event_map = &mipsxxcore_cache_map2;
+		break;
 	case CPU_1004K:
 		mipspmu.name = "mips/1004K";
 		mipspmu.general_event_map = &mipsxxcore_event_map;
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 06147179a175..f63a289977cc 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -267,6 +267,7 @@ static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
 
 	/* CPUs which do not require the workaround */
 	case CPU_P5600:
+	case CPU_I6400:
 		return 0;
 
 	default:
@@ -671,6 +672,7 @@ static int __init cps_pm_init(void)
 	case CPU_PROAPTIV:
 	case CPU_M5150:
 	case CPU_P5600:
+	case CPU_I6400:
 		stype_intervention = 0x2;
 		stype_memory = 0x3;
 		stype_ordering = 0x10;
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index b130033838ba..5fcec3032f38 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -38,7 +38,7 @@ char *mips_get_machine_name(void)
 	return mips_machine_name;
 }
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	return add_memory_region(base, size, BOOT_MEM_RAM);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index e933a309f2ea..4f0ac78d17f1 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -25,6 +25,7 @@
 #include <linux/regset.h>
 #include <linux/smp.h>
 #include <linux/security.h>
+#include <linux/stddef.h>
 #include <linux/tracehook.h>
 #include <linux/audit.h>
 #include <linux/seccomp.h>
@@ -490,6 +491,93 @@ enum mips_regset {
 	REGSET_FPR,
 };
 
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(reg, r) {					\
+	.name = #reg,							\
+	.offset = offsetof(struct pt_regs, r)				\
+}
+
+#define REG_OFFSET_END {						\
+	.name = NULL,							\
+	.offset = 0							\
+}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(r0, regs[0]),
+	REG_OFFSET_NAME(r1, regs[1]),
+	REG_OFFSET_NAME(r2, regs[2]),
+	REG_OFFSET_NAME(r3, regs[3]),
+	REG_OFFSET_NAME(r4, regs[4]),
+	REG_OFFSET_NAME(r5, regs[5]),
+	REG_OFFSET_NAME(r6, regs[6]),
+	REG_OFFSET_NAME(r7, regs[7]),
+	REG_OFFSET_NAME(r8, regs[8]),
+	REG_OFFSET_NAME(r9, regs[9]),
+	REG_OFFSET_NAME(r10, regs[10]),
+	REG_OFFSET_NAME(r11, regs[11]),
+	REG_OFFSET_NAME(r12, regs[12]),
+	REG_OFFSET_NAME(r13, regs[13]),
+	REG_OFFSET_NAME(r14, regs[14]),
+	REG_OFFSET_NAME(r15, regs[15]),
+	REG_OFFSET_NAME(r16, regs[16]),
+	REG_OFFSET_NAME(r17, regs[17]),
+	REG_OFFSET_NAME(r18, regs[18]),
+	REG_OFFSET_NAME(r19, regs[19]),
+	REG_OFFSET_NAME(r20, regs[20]),
+	REG_OFFSET_NAME(r21, regs[21]),
+	REG_OFFSET_NAME(r22, regs[22]),
+	REG_OFFSET_NAME(r23, regs[23]),
+	REG_OFFSET_NAME(r24, regs[24]),
+	REG_OFFSET_NAME(r25, regs[25]),
+	REG_OFFSET_NAME(r26, regs[26]),
+	REG_OFFSET_NAME(r27, regs[27]),
+	REG_OFFSET_NAME(r28, regs[28]),
+	REG_OFFSET_NAME(r29, regs[29]),
+	REG_OFFSET_NAME(r30, regs[30]),
+	REG_OFFSET_NAME(r31, regs[31]),
+	REG_OFFSET_NAME(c0_status, cp0_status),
+	REG_OFFSET_NAME(hi, hi),
+	REG_OFFSET_NAME(lo, lo),
+#ifdef CONFIG_CPU_HAS_SMARTMIPS
+	REG_OFFSET_NAME(acx, acx),
+#endif
+	REG_OFFSET_NAME(c0_badvaddr, cp0_badvaddr),
+	REG_OFFSET_NAME(c0_cause, cp0_cause),
+	REG_OFFSET_NAME(c0_epc, cp0_epc),
+#ifdef CONFIG_MIPS_MT_SMTC
+	REG_OFFSET_NAME(c0_tcstatus, cp0_tcstatus),
+#endif
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+	REG_OFFSET_NAME(mpl0, mpl[0]),
+	REG_OFFSET_NAME(mpl1, mpl[1]),
+	REG_OFFSET_NAME(mpl2, mpl[2]),
+	REG_OFFSET_NAME(mtp0, mtp[0]),
+	REG_OFFSET_NAME(mtp1, mtp[1]),
+	REG_OFFSET_NAME(mtp2, mtp[2]),
+#endif
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:       the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+        const struct pt_regs_offset *roff;
+        for (roff = regoffset_table; roff->name != NULL; roff++)
+                if (!strcmp(roff->name, name))
+                        return roff->offset;
+        return -EINVAL;
+}
+
 #if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
 
 static const struct user_regset mips_regsets[] = {
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 1d88af26ba82..f09546ee2cdc 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -13,6 +13,7 @@
  * Copyright (C) 1999, 2001 Silicon Graphics, Inc.
  */
 #include <asm/asm.h>
+#include <asm/asmmacro.h>
 #include <asm/errno.h>
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
@@ -35,6 +36,14 @@
 
 	.set	noreorder
 
+/**
+ * _save_fp_context() - save FP context from the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
+ *
+ * Save FP context, including the 32 FP data registers and the FP
+ * control & status register, from the FPU to signal context.
+ */
 LEAF(_save_fp_context)
 	.set	push
 	SET_HARDFLOAT
@@ -54,117 +63,60 @@ LEAF(_save_fp_context)
 	 nop
 #endif
 	/* Store the 16 odd double precision registers */
-	EX	sdc1 $f1, SC_FPREGS+8(a0)
-	EX	sdc1 $f3, SC_FPREGS+24(a0)
-	EX	sdc1 $f5, SC_FPREGS+40(a0)
-	EX	sdc1 $f7, SC_FPREGS+56(a0)
-	EX	sdc1 $f9, SC_FPREGS+72(a0)
-	EX	sdc1 $f11, SC_FPREGS+88(a0)
-	EX	sdc1 $f13, SC_FPREGS+104(a0)
-	EX	sdc1 $f15, SC_FPREGS+120(a0)
-	EX	sdc1 $f17, SC_FPREGS+136(a0)
-	EX	sdc1 $f19, SC_FPREGS+152(a0)
-	EX	sdc1 $f21, SC_FPREGS+168(a0)
-	EX	sdc1 $f23, SC_FPREGS+184(a0)
-	EX	sdc1 $f25, SC_FPREGS+200(a0)
-	EX	sdc1 $f27, SC_FPREGS+216(a0)
-	EX	sdc1 $f29, SC_FPREGS+232(a0)
-	EX	sdc1 $f31, SC_FPREGS+248(a0)
+	EX	sdc1 $f1, 8(a0)
+	EX	sdc1 $f3, 24(a0)
+	EX	sdc1 $f5, 40(a0)
+	EX	sdc1 $f7, 56(a0)
+	EX	sdc1 $f9, 72(a0)
+	EX	sdc1 $f11, 88(a0)
+	EX	sdc1 $f13, 104(a0)
+	EX	sdc1 $f15, 120(a0)
+	EX	sdc1 $f17, 136(a0)
+	EX	sdc1 $f19, 152(a0)
+	EX	sdc1 $f21, 168(a0)
+	EX	sdc1 $f23, 184(a0)
+	EX	sdc1 $f25, 200(a0)
+	EX	sdc1 $f27, 216(a0)
+	EX	sdc1 $f29, 232(a0)
+	EX	sdc1 $f31, 248(a0)
 1:	.set	pop
 #endif
 
 	.set push
 	SET_HARDFLOAT
 	/* Store the 16 even double precision registers */
-	EX	sdc1 $f0, SC_FPREGS+0(a0)
-	EX	sdc1 $f2, SC_FPREGS+16(a0)
-	EX	sdc1 $f4, SC_FPREGS+32(a0)
-	EX	sdc1 $f6, SC_FPREGS+48(a0)
-	EX	sdc1 $f8, SC_FPREGS+64(a0)
-	EX	sdc1 $f10, SC_FPREGS+80(a0)
-	EX	sdc1 $f12, SC_FPREGS+96(a0)
-	EX	sdc1 $f14, SC_FPREGS+112(a0)
-	EX	sdc1 $f16, SC_FPREGS+128(a0)
-	EX	sdc1 $f18, SC_FPREGS+144(a0)
-	EX	sdc1 $f20, SC_FPREGS+160(a0)
-	EX	sdc1 $f22, SC_FPREGS+176(a0)
-	EX	sdc1 $f24, SC_FPREGS+192(a0)
-	EX	sdc1 $f26, SC_FPREGS+208(a0)
-	EX	sdc1 $f28, SC_FPREGS+224(a0)
-	EX	sdc1 $f30, SC_FPREGS+240(a0)
-	EX	sw t1, SC_FPC_CSR(a0)
+	EX	sdc1 $f0, 0(a0)
+	EX	sdc1 $f2, 16(a0)
+	EX	sdc1 $f4, 32(a0)
+	EX	sdc1 $f6, 48(a0)
+	EX	sdc1 $f8, 64(a0)
+	EX	sdc1 $f10, 80(a0)
+	EX	sdc1 $f12, 96(a0)
+	EX	sdc1 $f14, 112(a0)
+	EX	sdc1 $f16, 128(a0)
+	EX	sdc1 $f18, 144(a0)
+	EX	sdc1 $f20, 160(a0)
+	EX	sdc1 $f22, 176(a0)
+	EX	sdc1 $f24, 192(a0)
+	EX	sdc1 $f26, 208(a0)
+	EX	sdc1 $f28, 224(a0)
+	EX	sdc1 $f30, 240(a0)
+	EX	sw t1, 0(a1)
 	jr	ra
 	 li	v0, 0					# success
 	.set pop
 	END(_save_fp_context)
 
-#ifdef CONFIG_MIPS32_COMPAT
-	/* Save 32-bit process floating point context */
-LEAF(_save_fp_context32)
-	.set push
-	.set MIPS_ISA_ARCH_LEVEL_RAW
-	SET_HARDFLOAT
-	cfc1	t1, fcr31
-
-#ifndef CONFIG_CPU_MIPS64_R6
-	mfc0	t0, CP0_STATUS
-	sll	t0, t0, 5
-	bgez	t0, 1f			# skip storing odd if FR=0
-	 nop
-#endif
-
-	/* Store the 16 odd double precision registers */
-	EX      sdc1 $f1, SC32_FPREGS+8(a0)
-	EX      sdc1 $f3, SC32_FPREGS+24(a0)
-	EX      sdc1 $f5, SC32_FPREGS+40(a0)
-	EX      sdc1 $f7, SC32_FPREGS+56(a0)
-	EX      sdc1 $f9, SC32_FPREGS+72(a0)
-	EX      sdc1 $f11, SC32_FPREGS+88(a0)
-	EX      sdc1 $f13, SC32_FPREGS+104(a0)
-	EX      sdc1 $f15, SC32_FPREGS+120(a0)
-	EX      sdc1 $f17, SC32_FPREGS+136(a0)
-	EX      sdc1 $f19, SC32_FPREGS+152(a0)
-	EX      sdc1 $f21, SC32_FPREGS+168(a0)
-	EX      sdc1 $f23, SC32_FPREGS+184(a0)
-	EX      sdc1 $f25, SC32_FPREGS+200(a0)
-	EX      sdc1 $f27, SC32_FPREGS+216(a0)
-	EX      sdc1 $f29, SC32_FPREGS+232(a0)
-	EX      sdc1 $f31, SC32_FPREGS+248(a0)
-
-	/* Store the 16 even double precision registers */
-1:	EX	sdc1 $f0, SC32_FPREGS+0(a0)
-	EX	sdc1 $f2, SC32_FPREGS+16(a0)
-	EX	sdc1 $f4, SC32_FPREGS+32(a0)
-	EX	sdc1 $f6, SC32_FPREGS+48(a0)
-	EX	sdc1 $f8, SC32_FPREGS+64(a0)
-	EX	sdc1 $f10, SC32_FPREGS+80(a0)
-	EX	sdc1 $f12, SC32_FPREGS+96(a0)
-	EX	sdc1 $f14, SC32_FPREGS+112(a0)
-	EX	sdc1 $f16, SC32_FPREGS+128(a0)
-	EX	sdc1 $f18, SC32_FPREGS+144(a0)
-	EX	sdc1 $f20, SC32_FPREGS+160(a0)
-	EX	sdc1 $f22, SC32_FPREGS+176(a0)
-	EX	sdc1 $f24, SC32_FPREGS+192(a0)
-	EX	sdc1 $f26, SC32_FPREGS+208(a0)
-	EX	sdc1 $f28, SC32_FPREGS+224(a0)
-	EX	sdc1 $f30, SC32_FPREGS+240(a0)
-	EX	sw t1, SC32_FPC_CSR(a0)
-	cfc1	t0, $0				# implementation/version
-	EX	sw t0, SC32_FPC_EIR(a0)
-	.set pop
-
-	jr	ra
-	 li	v0, 0					# success
-	END(_save_fp_context32)
-#endif
-
-/*
- * Restore FPU state:
- *  - fp gp registers
- *  - cp1 status/control register
+/**
+ * _restore_fp_context() - restore FP context to the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
+ *
+ * Restore FP context, including the 32 FP data registers and the FP
+ * control & status register, from signal context to the FPU.
  */
 LEAF(_restore_fp_context)
-	EX	lw t1, SC_FPC_CSR(a0)
+	EX	lw t1, 0(a1)
 
 #if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)  || \
 		defined(CONFIG_CPU_MIPS32_R6)
@@ -178,101 +130,231 @@ LEAF(_restore_fp_context)
 	bgez	t0, 1f			# skip loading odd if FR=0
 	 nop
 #endif
-	EX	ldc1 $f1, SC_FPREGS+8(a0)
-	EX	ldc1 $f3, SC_FPREGS+24(a0)
-	EX	ldc1 $f5, SC_FPREGS+40(a0)
-	EX	ldc1 $f7, SC_FPREGS+56(a0)
-	EX	ldc1 $f9, SC_FPREGS+72(a0)
-	EX	ldc1 $f11, SC_FPREGS+88(a0)
-	EX	ldc1 $f13, SC_FPREGS+104(a0)
-	EX	ldc1 $f15, SC_FPREGS+120(a0)
-	EX	ldc1 $f17, SC_FPREGS+136(a0)
-	EX	ldc1 $f19, SC_FPREGS+152(a0)
-	EX	ldc1 $f21, SC_FPREGS+168(a0)
-	EX	ldc1 $f23, SC_FPREGS+184(a0)
-	EX	ldc1 $f25, SC_FPREGS+200(a0)
-	EX	ldc1 $f27, SC_FPREGS+216(a0)
-	EX	ldc1 $f29, SC_FPREGS+232(a0)
-	EX	ldc1 $f31, SC_FPREGS+248(a0)
+	EX	ldc1 $f1, 8(a0)
+	EX	ldc1 $f3, 24(a0)
+	EX	ldc1 $f5, 40(a0)
+	EX	ldc1 $f7, 56(a0)
+	EX	ldc1 $f9, 72(a0)
+	EX	ldc1 $f11, 88(a0)
+	EX	ldc1 $f13, 104(a0)
+	EX	ldc1 $f15, 120(a0)
+	EX	ldc1 $f17, 136(a0)
+	EX	ldc1 $f19, 152(a0)
+	EX	ldc1 $f21, 168(a0)
+	EX	ldc1 $f23, 184(a0)
+	EX	ldc1 $f25, 200(a0)
+	EX	ldc1 $f27, 216(a0)
+	EX	ldc1 $f29, 232(a0)
+	EX	ldc1 $f31, 248(a0)
 1:	.set pop
 #endif
 	.set push
 	SET_HARDFLOAT
-	EX	ldc1 $f0, SC_FPREGS+0(a0)
-	EX	ldc1 $f2, SC_FPREGS+16(a0)
-	EX	ldc1 $f4, SC_FPREGS+32(a0)
-	EX	ldc1 $f6, SC_FPREGS+48(a0)
-	EX	ldc1 $f8, SC_FPREGS+64(a0)
-	EX	ldc1 $f10, SC_FPREGS+80(a0)
-	EX	ldc1 $f12, SC_FPREGS+96(a0)
-	EX	ldc1 $f14, SC_FPREGS+112(a0)
-	EX	ldc1 $f16, SC_FPREGS+128(a0)
-	EX	ldc1 $f18, SC_FPREGS+144(a0)
-	EX	ldc1 $f20, SC_FPREGS+160(a0)
-	EX	ldc1 $f22, SC_FPREGS+176(a0)
-	EX	ldc1 $f24, SC_FPREGS+192(a0)
-	EX	ldc1 $f26, SC_FPREGS+208(a0)
-	EX	ldc1 $f28, SC_FPREGS+224(a0)
-	EX	ldc1 $f30, SC_FPREGS+240(a0)
+	EX	ldc1 $f0, 0(a0)
+	EX	ldc1 $f2, 16(a0)
+	EX	ldc1 $f4, 32(a0)
+	EX	ldc1 $f6, 48(a0)
+	EX	ldc1 $f8, 64(a0)
+	EX	ldc1 $f10, 80(a0)
+	EX	ldc1 $f12, 96(a0)
+	EX	ldc1 $f14, 112(a0)
+	EX	ldc1 $f16, 128(a0)
+	EX	ldc1 $f18, 144(a0)
+	EX	ldc1 $f20, 160(a0)
+	EX	ldc1 $f22, 176(a0)
+	EX	ldc1 $f24, 192(a0)
+	EX	ldc1 $f26, 208(a0)
+	EX	ldc1 $f28, 224(a0)
+	EX	ldc1 $f30, 240(a0)
 	ctc1	t1, fcr31
 	.set pop
 	jr	ra
 	 li	v0, 0					# success
 	END(_restore_fp_context)
 
-#ifdef CONFIG_MIPS32_COMPAT
-LEAF(_restore_fp_context32)
-	/* Restore an o32 sigcontext.  */
-	.set push
-	SET_HARDFLOAT
-	EX	lw t1, SC32_FPC_CSR(a0)
+#ifdef CONFIG_CPU_HAS_MSA
 
-#ifndef CONFIG_CPU_MIPS64_R6
-	mfc0	t0, CP0_STATUS
-	sll	t0, t0, 5
-	bgez	t0, 1f			# skip loading odd if FR=0
+	.macro	op_one_wr	op, idx, base
+	.align	4
+\idx:	\op	\idx, 0, \base
+	jr	ra
 	 nop
-#endif
+	.endm
 
-	EX      ldc1 $f1, SC32_FPREGS+8(a0)
-	EX      ldc1 $f3, SC32_FPREGS+24(a0)
-	EX      ldc1 $f5, SC32_FPREGS+40(a0)
-	EX      ldc1 $f7, SC32_FPREGS+56(a0)
-	EX      ldc1 $f9, SC32_FPREGS+72(a0)
-	EX      ldc1 $f11, SC32_FPREGS+88(a0)
-	EX      ldc1 $f13, SC32_FPREGS+104(a0)
-	EX      ldc1 $f15, SC32_FPREGS+120(a0)
-	EX      ldc1 $f17, SC32_FPREGS+136(a0)
-	EX      ldc1 $f19, SC32_FPREGS+152(a0)
-	EX      ldc1 $f21, SC32_FPREGS+168(a0)
-	EX      ldc1 $f23, SC32_FPREGS+184(a0)
-	EX      ldc1 $f25, SC32_FPREGS+200(a0)
-	EX      ldc1 $f27, SC32_FPREGS+216(a0)
-	EX      ldc1 $f29, SC32_FPREGS+232(a0)
-	EX      ldc1 $f31, SC32_FPREGS+248(a0)
+	.macro	op_msa_wr	name, op
+LEAF(\name)
+	.set		push
+	.set		noreorder
+	sll		t0, a0, 4
+	PTR_LA		t1, 0f
+	PTR_ADDU	t0, t0, t1
+	jr		t0
+	  nop
+	op_one_wr	\op, 0, a1
+	op_one_wr	\op, 1, a1
+	op_one_wr	\op, 2, a1
+	op_one_wr	\op, 3, a1
+	op_one_wr	\op, 4, a1
+	op_one_wr	\op, 5, a1
+	op_one_wr	\op, 6, a1
+	op_one_wr	\op, 7, a1
+	op_one_wr	\op, 8, a1
+	op_one_wr	\op, 9, a1
+	op_one_wr	\op, 10, a1
+	op_one_wr	\op, 11, a1
+	op_one_wr	\op, 12, a1
+	op_one_wr	\op, 13, a1
+	op_one_wr	\op, 14, a1
+	op_one_wr	\op, 15, a1
+	op_one_wr	\op, 16, a1
+	op_one_wr	\op, 17, a1
+	op_one_wr	\op, 18, a1
+	op_one_wr	\op, 19, a1
+	op_one_wr	\op, 20, a1
+	op_one_wr	\op, 21, a1
+	op_one_wr	\op, 22, a1
+	op_one_wr	\op, 23, a1
+	op_one_wr	\op, 24, a1
+	op_one_wr	\op, 25, a1
+	op_one_wr	\op, 26, a1
+	op_one_wr	\op, 27, a1
+	op_one_wr	\op, 28, a1
+	op_one_wr	\op, 29, a1
+	op_one_wr	\op, 30, a1
+	op_one_wr	\op, 31, a1
+	.set		pop
+	END(\name)
+	.endm
 
-1:	EX	ldc1 $f0, SC32_FPREGS+0(a0)
-	EX	ldc1 $f2, SC32_FPREGS+16(a0)
-	EX	ldc1 $f4, SC32_FPREGS+32(a0)
-	EX	ldc1 $f6, SC32_FPREGS+48(a0)
-	EX	ldc1 $f8, SC32_FPREGS+64(a0)
-	EX	ldc1 $f10, SC32_FPREGS+80(a0)
-	EX	ldc1 $f12, SC32_FPREGS+96(a0)
-	EX	ldc1 $f14, SC32_FPREGS+112(a0)
-	EX	ldc1 $f16, SC32_FPREGS+128(a0)
-	EX	ldc1 $f18, SC32_FPREGS+144(a0)
-	EX	ldc1 $f20, SC32_FPREGS+160(a0)
-	EX	ldc1 $f22, SC32_FPREGS+176(a0)
-	EX	ldc1 $f24, SC32_FPREGS+192(a0)
-	EX	ldc1 $f26, SC32_FPREGS+208(a0)
-	EX	ldc1 $f28, SC32_FPREGS+224(a0)
-	EX	ldc1 $f30, SC32_FPREGS+240(a0)
-	ctc1	t1, fcr31
+	op_msa_wr	read_msa_wr_b, st_b
+	op_msa_wr	read_msa_wr_h, st_h
+	op_msa_wr	read_msa_wr_w, st_w
+	op_msa_wr	read_msa_wr_d, st_d
+
+	op_msa_wr	write_msa_wr_b, ld_b
+	op_msa_wr	write_msa_wr_h, ld_h
+	op_msa_wr	write_msa_wr_w, ld_w
+	op_msa_wr	write_msa_wr_d, ld_d
+
+#endif /* CONFIG_CPU_HAS_MSA */
+
+#ifdef CONFIG_CPU_HAS_MSA
+
+	.macro	save_msa_upper	wr, off, base
+	.set	push
+	.set	noat
+#ifdef CONFIG_64BIT
+	copy_u_d \wr, 1
+	EX sd	$1, \off(\base)
+#elif defined(CONFIG_CPU_LITTLE_ENDIAN)
+	copy_u_w \wr, 2
+	EX sw	$1, \off(\base)
+	copy_u_w \wr, 3
+	EX sw	$1, (\off+4)(\base)
+#else /* CONFIG_CPU_BIG_ENDIAN */
+	copy_u_w \wr, 2
+	EX sw	$1, (\off+4)(\base)
+	copy_u_w \wr, 3
+	EX sw	$1, \off(\base)
+#endif
+	.set	pop
+	.endm
+
+LEAF(_save_msa_all_upper)
+	save_msa_upper	0, 0x00, a0
+	save_msa_upper	1, 0x08, a0
+	save_msa_upper	2, 0x10, a0
+	save_msa_upper	3, 0x18, a0
+	save_msa_upper	4, 0x20, a0
+	save_msa_upper	5, 0x28, a0
+	save_msa_upper	6, 0x30, a0
+	save_msa_upper	7, 0x38, a0
+	save_msa_upper	8, 0x40, a0
+	save_msa_upper	9, 0x48, a0
+	save_msa_upper	10, 0x50, a0
+	save_msa_upper	11, 0x58, a0
+	save_msa_upper	12, 0x60, a0
+	save_msa_upper	13, 0x68, a0
+	save_msa_upper	14, 0x70, a0
+	save_msa_upper	15, 0x78, a0
+	save_msa_upper	16, 0x80, a0
+	save_msa_upper	17, 0x88, a0
+	save_msa_upper	18, 0x90, a0
+	save_msa_upper	19, 0x98, a0
+	save_msa_upper	20, 0xa0, a0
+	save_msa_upper	21, 0xa8, a0
+	save_msa_upper	22, 0xb0, a0
+	save_msa_upper	23, 0xb8, a0
+	save_msa_upper	24, 0xc0, a0
+	save_msa_upper	25, 0xc8, a0
+	save_msa_upper	26, 0xd0, a0
+	save_msa_upper	27, 0xd8, a0
+	save_msa_upper	28, 0xe0, a0
+	save_msa_upper	29, 0xe8, a0
+	save_msa_upper	30, 0xf0, a0
+	save_msa_upper	31, 0xf8, a0
 	jr	ra
-	 li	v0, 0					# success
-	.set pop
-	END(_restore_fp_context32)
+	 li	v0, 0
+	END(_save_msa_all_upper)
+
+	.macro	restore_msa_upper	wr, off, base
+	.set	push
+	.set	noat
+#ifdef CONFIG_64BIT
+	EX ld	$1, \off(\base)
+	insert_d \wr, 1
+#elif defined(CONFIG_CPU_LITTLE_ENDIAN)
+	EX lw	$1, \off(\base)
+	insert_w \wr, 2
+	EX lw	$1, (\off+4)(\base)
+	insert_w \wr, 3
+#else /* CONFIG_CPU_BIG_ENDIAN */
+	EX lw	$1, (\off+4)(\base)
+	insert_w \wr, 2
+	EX lw	$1, \off(\base)
+	insert_w \wr, 3
 #endif
+	.set	pop
+	.endm
+
+LEAF(_restore_msa_all_upper)
+	restore_msa_upper	0, 0x00, a0
+	restore_msa_upper	1, 0x08, a0
+	restore_msa_upper	2, 0x10, a0
+	restore_msa_upper	3, 0x18, a0
+	restore_msa_upper	4, 0x20, a0
+	restore_msa_upper	5, 0x28, a0
+	restore_msa_upper	6, 0x30, a0
+	restore_msa_upper	7, 0x38, a0
+	restore_msa_upper	8, 0x40, a0
+	restore_msa_upper	9, 0x48, a0
+	restore_msa_upper	10, 0x50, a0
+	restore_msa_upper	11, 0x58, a0
+	restore_msa_upper	12, 0x60, a0
+	restore_msa_upper	13, 0x68, a0
+	restore_msa_upper	14, 0x70, a0
+	restore_msa_upper	15, 0x78, a0
+	restore_msa_upper	16, 0x80, a0
+	restore_msa_upper	17, 0x88, a0
+	restore_msa_upper	18, 0x90, a0
+	restore_msa_upper	19, 0x98, a0
+	restore_msa_upper	20, 0xa0, a0
+	restore_msa_upper	21, 0xa8, a0
+	restore_msa_upper	22, 0xb0, a0
+	restore_msa_upper	23, 0xb8, a0
+	restore_msa_upper	24, 0xc0, a0
+	restore_msa_upper	25, 0xc8, a0
+	restore_msa_upper	26, 0xd0, a0
+	restore_msa_upper	27, 0xd8, a0
+	restore_msa_upper	28, 0xe0, a0
+	restore_msa_upper	29, 0xe8, a0
+	restore_msa_upper	30, 0xf0, a0
+	restore_msa_upper	31, 0xf8, a0
+	jr	ra
+	 li	v0, 0
+	END(_restore_msa_all_upper)
+
+#endif /* CONFIG_CPU_HAS_MSA */
 
 	.set	reorder
 
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 04cbbde3521b..92cd0516ecf5 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -34,7 +34,7 @@
 #ifndef USE_ALTERNATE_RESUME_IMPL
 /*
  * task_struct *resume(task_struct *prev, task_struct *next,
- *		       struct thread_info *next_ti, s32 fp_save)
+ *		       struct thread_info *next_ti)
  */
 	.align	5
 	LEAF(resume)
@@ -43,45 +43,6 @@
 	cpu_save_nonscratch a0
 	LONG_S	ra, THREAD_REG31(a0)
 
-	/*
-	 * Check whether we need to save any FP context. FP context is saved
-	 * iff the process has used the context with the scalar FPU or the MSA
-	 * ASE in the current time slice, as indicated by _TIF_USEDFPU and
-	 * _TIF_USEDMSA respectively. switch_to will have set fp_save
-	 * accordingly to an FP_SAVE_ enum value.
-	 */
-	beqz	a3, 2f
-
-	/*
-	 * We do. Clear the saved CU1 bit for prev, such that next time it is
-	 * scheduled it will start in userland with the FPU disabled. If the
-	 * task uses the FPU then it will be enabled again via the do_cpu trap.
-	 * This allows us to lazily restore the FP context.
-	 */
-	PTR_L	t3, TASK_THREAD_INFO(a0)
-	LONG_L	t0, ST_OFF(t3)
-	li	t1, ~ST0_CU1
-	and	t0, t0, t1
-	LONG_S	t0, ST_OFF(t3)
-
-	/* Check whether we're saving scalar or vector context. */
-	bgtz	a3, 1f
-
-	/* Save 128b MSA vector context + scalar FP control & status. */
-	.set push
-	SET_HARDFLOAT
-	cfc1	t1, fcr31
-	msa_save_all	a0
-	.set pop	/* SET_HARDFLOAT */
-
-	sw	t1, THREAD_FCR31(a0)
-	b	2f
-
-1:	/* Save 32b/64b scalar FP context. */
-	fpu_save_double a0 t0 t1		# c0_status passed in t0
-						# clobbers t1
-2:
-
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
 	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 74bab9ddd0e1..c6bbf2165051 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -24,7 +24,7 @@ LEAF(relocate_new_kernel)
 
 process_entry:
 	PTR_L		s2, (s0)
-	PTR_ADD		s0, s0, SZREG
+	PTR_ADDIU	s0, s0, SZREG
 
 	/*
 	 * In case of a kdump/crash kernel, the indirection page is not
@@ -61,9 +61,9 @@ copy_word:
 	/* copy page word by word */
 	REG_L		s5, (s2)
 	REG_S		s5, (s4)
-	PTR_ADD		s4, s4, SZREG
-	PTR_ADD		s2, s2, SZREG
-	LONG_SUB	s6, s6, 1
+	PTR_ADDIU	s4, s4, SZREG
+	PTR_ADDIU	s2, s2, SZREG
+	LONG_ADDIU	s6, s6, -1
 	beq		s6, zero, process_entry
 	b		copy_word
 	b		process_entry
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 6e8de80bb446..4cc13508d967 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -73,10 +73,11 @@ NESTED(handle_sys, PT_SIZE, sp)
 	.set    noreorder
 	.set	nomacro
 
-1:	user_lw(t5, 16(t0))		# argument #5 from usp
-4:	user_lw(t6, 20(t0))		# argument #6 from usp
-3:	user_lw(t7, 24(t0))		# argument #7 from usp
-2:	user_lw(t8, 28(t0))		# argument #8 from usp
+load_a4: user_lw(t5, 16(t0))		# argument #5 from usp
+load_a5: user_lw(t6, 20(t0))		# argument #6 from usp
+load_a6: user_lw(t7, 24(t0))		# argument #7 from usp
+load_a7: user_lw(t8, 28(t0))		# argument #8 from usp
+loads_done:
 
 	sw	t5, 16(sp)		# argument #5 to ksp
 	sw	t6, 20(sp)		# argument #6 to ksp
@@ -85,10 +86,10 @@ NESTED(handle_sys, PT_SIZE, sp)
 	.set	pop
 
 	.section __ex_table,"a"
-	PTR	1b,bad_stack
-	PTR	2b,bad_stack
-	PTR	3b,bad_stack
-	PTR	4b,bad_stack
+	PTR	load_a4, bad_stack_a4
+	PTR	load_a5, bad_stack_a5
+	PTR	load_a6, bad_stack_a6
+	PTR	load_a7, bad_stack_a7
 	.previous
 
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
@@ -153,8 +154,8 @@ syscall_trace_entry:
 /* ------------------------------------------------------------------------ */
 
 	/*
-	 * The stackpointer for a call with more than 4 arguments is bad.
-	 * We probably should handle this case a bit more drastic.
+	 * Our open-coded access area sanity test for the stack pointer
+	 * failed. We probably should handle this case a bit more drastic.
 	 */
 bad_stack:
 	li	v0, EFAULT
@@ -163,6 +164,22 @@ bad_stack:
 	sw	t0, PT_R7(sp)
 	j	o32_syscall_exit
 
+bad_stack_a4:
+	li	t5, 0
+	b	load_a5
+
+bad_stack_a5:
+	li	t6, 0
+	b	load_a6
+
+bad_stack_a6:
+	li	t7, 0
+	b	load_a7
+
+bad_stack_a7:
+	li	t8, 0
+	b	loads_done
+
 	/*
 	 * The system call does not exist in this kernel
 	 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index ad4d44635c76..a6f6b762c47a 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -80,7 +80,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	daddiu	a1, v0, __NR_64_Linux
+	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 446cc654da56..4b2010654c46 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -72,7 +72,7 @@ n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	daddiu	a1, v0, __NR_N32_Linux
+	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index d07b210fbeff..f543ff4feef9 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -69,16 +69,17 @@ NESTED(handle_sys, PT_SIZE, sp)
 	daddu	t1, t0, 32
 	bltz	t1, bad_stack
 
-1:	lw	a4, 16(t0)		# argument #5 from usp
-2:	lw	a5, 20(t0)		# argument #6 from usp
-3:	lw	a6, 24(t0)		# argument #7 from usp
-4:	lw	a7, 28(t0)		# argument #8 from usp (for indirect syscalls)
+load_a4: lw	a4, 16(t0)		# argument #5 from usp
+load_a5: lw	a5, 20(t0)		# argument #6 from usp
+load_a6: lw	a6, 24(t0)		# argument #7 from usp
+load_a7: lw	a7, 28(t0)		# argument #8 from usp
+loads_done:
 
 	.section __ex_table,"a"
-	PTR	1b, bad_stack
-	PTR	2b, bad_stack
-	PTR	3b, bad_stack
-	PTR	4b, bad_stack
+	PTR	load_a4, bad_stack_a4
+	PTR	load_a5, bad_stack_a5
+	PTR	load_a6, bad_stack_a6
+	PTR	load_a7, bad_stack_a7
 	.previous
 
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
@@ -167,6 +168,22 @@ bad_stack:
 	sd	t0, PT_R7(sp)
 	j	o32_syscall_exit
 
+bad_stack_a4:
+	li	a4, 0
+	b	load_a5
+
+bad_stack_a5:
+	li	a5, 0
+	b	load_a6
+
+bad_stack_a6:
+	li	a6, 0
+	b	load_a7
+
+bad_stack_a7:
+	li	a7, 0
+	b	loads_done
+
 not_o32_scall:
 	/*
 	 * This is not an o32 compatibility syscall, pass it on
@@ -383,7 +400,7 @@ EXPORT(sys32_call_table)
 	PTR	sys_connect			/* 4170 */
 	PTR	sys_getpeername
 	PTR	sys_getsockname
-	PTR	sys_getsockopt
+	PTR	compat_sys_getsockopt
 	PTR	sys_listen
 	PTR	compat_sys_recv			/* 4175 */
 	PTR	compat_sys_recvfrom
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index be73c491182b..35b8316002f8 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -337,6 +337,11 @@ static void __init bootmem_init(void)
 			min_low_pfn = start;
 		if (end <= reserved_end)
 			continue;
+#ifdef CONFIG_BLK_DEV_INITRD
+		/* mapstart should be after initrd_end */
+		if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
+			continue;
+#endif
 		if (start >= mapstart)
 			continue;
 		mapstart = max(reserved_end, start);
@@ -366,14 +371,6 @@ static void __init bootmem_init(void)
 		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 	}
 
-#ifdef CONFIG_BLK_DEV_INITRD
-	/*
-	 * mapstart should be after initrd_end
-	 */
-	if (initrd_end)
-		mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
-#endif
-
 	/*
 	 * Initialize the boot-time allocator with low memory only.
 	 */
@@ -479,7 +476,7 @@ static void __init bootmem_init(void)
  *  o bootmem_init()
  *  o sparse_init()
  *  o paging_init()
- *  o dma_continguous_reserve()
+ *  o dma_contiguous_reserve()
  *
  * At this stage the bootmem allocator is ready to use.
  *
diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h
index 0b85f827cd18..f50d48435c68 100644
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@@ -31,4 +31,13 @@ extern int fpcsr_pending(unsigned int __user *fpcsr);
 #define lock_fpu_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_fpu_owner()	({ pagefault_enable(); preempt_enable(); })
 
+/* Assembly functions to move context to/from the FPU */
+extern asmlinkage int
+_save_fp_context(void __user *fpregs, void __user *csr);
+extern asmlinkage int
+_restore_fp_context(void __user *fpregs, void __user *csr);
+
+extern asmlinkage int _save_msa_all_upper(void __user *buf);
+extern asmlinkage int _restore_msa_all_upper(void __user *buf);
+
 #endif	/* __SIGNAL_COMMON_H */
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 6a28c792d862..2fec67bfc457 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -21,6 +21,7 @@
 #include <linux/wait.h>
 #include <linux/ptrace.h>
 #include <linux/unistd.h>
+#include <linux/uprobes.h>
 #include <linux/compiler.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
@@ -38,20 +39,21 @@
 #include <asm/vdso.h>
 #include <asm/dsp.h>
 #include <asm/inst.h>
+#include <asm/msa.h>
 
 #include "signal-common.h"
 
-static int (*save_fp_context)(struct sigcontext __user *sc);
-static int (*restore_fp_context)(struct sigcontext __user *sc);
-
-extern asmlinkage int _save_fp_context(struct sigcontext __user *sc);
-extern asmlinkage int _restore_fp_context(struct sigcontext __user *sc);
+static int (*save_fp_context)(void __user *sc);
+static int (*restore_fp_context)(void __user *sc);
 
 struct sigframe {
 	u32 sf_ass[4];		/* argument save space for o32 */
 	u32 sf_pad[2];		/* Was: signal trampoline */
+
+	/* Matches struct ucontext from its uc_mcontext field onwards */
 	struct sigcontext sf_sc;
 	sigset_t sf_mask;
+	unsigned long long sf_extcontext[0];
 };
 
 struct rt_sigframe {
@@ -65,43 +67,255 @@ struct rt_sigframe {
  * Thread saved context copy to/from a signal context presumed to be on the
  * user stack, and therefore accessed with appropriate macros from uaccess.h.
  */
-static int copy_fp_to_sigcontext(struct sigcontext __user *sc)
+static int copy_fp_to_sigcontext(void __user *sc)
 {
+	struct mips_abi *abi = current->thread.abi;
+	uint64_t __user *fpregs = sc + abi->off_sc_fpregs;
+	uint32_t __user *csr = sc + abi->off_sc_fpc_csr;
 	int i;
 	int err = 0;
+	int inc = test_thread_flag(TIF_32BIT_FPREGS) ? 2 : 1;
 
-	for (i = 0; i < NUM_FPU_REGS; i++) {
+	for (i = 0; i < NUM_FPU_REGS; i += inc) {
 		err |=
 		    __put_user(get_fpr64(&current->thread.fpu.fpr[i], 0),
-			       &sc->sc_fpregs[i]);
+			       &fpregs[i]);
 	}
-	err |= __put_user(current->thread.fpu.fcr31, &sc->sc_fpc_csr);
+	err |= __put_user(current->thread.fpu.fcr31, csr);
 
 	return err;
 }
 
-static int copy_fp_from_sigcontext(struct sigcontext __user *sc)
+static int copy_fp_from_sigcontext(void __user *sc)
 {
+	struct mips_abi *abi = current->thread.abi;
+	uint64_t __user *fpregs = sc + abi->off_sc_fpregs;
+	uint32_t __user *csr = sc + abi->off_sc_fpc_csr;
 	int i;
 	int err = 0;
+	int inc = test_thread_flag(TIF_32BIT_FPREGS) ? 2 : 1;
 	u64 fpr_val;
 
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		err |= __get_user(fpr_val, &sc->sc_fpregs[i]);
+	for (i = 0; i < NUM_FPU_REGS; i += inc) {
+		err |= __get_user(fpr_val, &fpregs[i]);
 		set_fpr64(&current->thread.fpu.fpr[i], 0, fpr_val);
 	}
-	err |= __get_user(current->thread.fpu.fcr31, &sc->sc_fpc_csr);
+	err |= __get_user(current->thread.fpu.fcr31, csr);
 
 	return err;
 }
 
 /*
+ * Wrappers for the assembly _{save,restore}_fp_context functions.
+ */
+static int save_hw_fp_context(void __user *sc)
+{
+	struct mips_abi *abi = current->thread.abi;
+	uint64_t __user *fpregs = sc + abi->off_sc_fpregs;
+	uint32_t __user *csr = sc + abi->off_sc_fpc_csr;
+
+	return _save_fp_context(fpregs, csr);
+}
+
+static int restore_hw_fp_context(void __user *sc)
+{
+	struct mips_abi *abi = current->thread.abi;
+	uint64_t __user *fpregs = sc + abi->off_sc_fpregs;
+	uint32_t __user *csr = sc + abi->off_sc_fpc_csr;
+
+	return _restore_fp_context(fpregs, csr);
+}
+
+/*
+ * Extended context handling.
+ */
+
+static inline void __user *sc_to_extcontext(void __user *sc)
+{
+	struct ucontext __user *uc;
+
+	/*
+	 * We can just pretend the sigcontext is always embedded in a struct
+	 * ucontext here, because the offset from sigcontext to extended
+	 * context is the same in the struct sigframe case.
+	 */
+	uc = container_of(sc, struct ucontext, uc_mcontext);
+	return &uc->uc_extcontext;
+}
+
+static int save_msa_extcontext(void __user *buf)
+{
+	struct msa_extcontext __user *msa = buf;
+	uint64_t val;
+	int i, err;
+
+	if (!thread_msa_context_live())
+		return 0;
+
+	/*
+	 * Ensure that we can't lose the live MSA context between checking
+	 * for it & writing it to memory.
+	 */
+	preempt_disable();
+
+	if (is_msa_enabled()) {
+		/*
+		 * There are no EVA versions of the vector register load/store
+		 * instructions, so MSA context has to be saved to kernel memory
+		 * and then copied to user memory. The save to kernel memory
+		 * should already have been done when handling scalar FP
+		 * context.
+		 */
+		BUG_ON(config_enabled(CONFIG_EVA));
+
+		err = __put_user(read_msa_csr(), &msa->csr);
+		err |= _save_msa_all_upper(&msa->wr);
+
+		preempt_enable();
+	} else {
+		preempt_enable();
+
+		err = __put_user(current->thread.fpu.msacsr, &msa->csr);
+
+		for (i = 0; i < NUM_FPU_REGS; i++) {
+			val = get_fpr64(&current->thread.fpu.fpr[i], 1);
+			err |= __put_user(val, &msa->wr[i]);
+		}
+	}
+
+	err |= __put_user(MSA_EXTCONTEXT_MAGIC, &msa->ext.magic);
+	err |= __put_user(sizeof(*msa), &msa->ext.size);
+
+	return err ? -EFAULT : sizeof(*msa);
+}
+
+static int restore_msa_extcontext(void __user *buf, unsigned int size)
+{
+	struct msa_extcontext __user *msa = buf;
+	unsigned long long val;
+	unsigned int csr;
+	int i, err;
+
+	if (size != sizeof(*msa))
+		return -EINVAL;
+
+	err = get_user(csr, &msa->csr);
+	if (err)
+		return err;
+
+	preempt_disable();
+
+	if (is_msa_enabled()) {
+		/*
+		 * There are no EVA versions of the vector register load/store
+		 * instructions, so MSA context has to be copied to kernel
+		 * memory and later loaded to registers. The same is true of
+		 * scalar FP context, so FPU & MSA should have already been
+		 * disabled whilst handling scalar FP context.
+		 */
+		BUG_ON(config_enabled(CONFIG_EVA));
+
+		write_msa_csr(csr);
+		err |= _restore_msa_all_upper(&msa->wr);
+		preempt_enable();
+	} else {
+		preempt_enable();
+
+		current->thread.fpu.msacsr = csr;
+
+		for (i = 0; i < NUM_FPU_REGS; i++) {
+			err |= __get_user(val, &msa->wr[i]);
+			set_fpr64(&current->thread.fpu.fpr[i], 1, val);
+		}
+	}
+
+	return err;
+}
+
+static int save_extcontext(void __user *buf)
+{
+	int sz;
+
+	sz = save_msa_extcontext(buf);
+	if (sz < 0)
+		return sz;
+	buf += sz;
+
+	/* If no context was saved then trivially return */
+	if (!sz)
+		return 0;
+
+	/* Write the end marker */
+	if (__put_user(END_EXTCONTEXT_MAGIC, (u32 *)buf))
+		return -EFAULT;
+
+	sz += sizeof(((struct extcontext *)NULL)->magic);
+	return sz;
+}
+
+static int restore_extcontext(void __user *buf)
+{
+	struct extcontext ext;
+	int err;
+
+	while (1) {
+		err = __get_user(ext.magic, (unsigned int *)buf);
+		if (err)
+			return err;
+
+		if (ext.magic == END_EXTCONTEXT_MAGIC)
+			return 0;
+
+		err = __get_user(ext.size, (unsigned int *)(buf
+			+ offsetof(struct extcontext, size)));
+		if (err)
+			return err;
+
+		switch (ext.magic) {
+		case MSA_EXTCONTEXT_MAGIC:
+			err = restore_msa_extcontext(buf, ext.size);
+			break;
+
+		default:
+			err = -EINVAL;
+			break;
+		}
+
+		if (err)
+			return err;
+
+		buf += ext.size;
+	}
+}
+
+/*
  * Helper routines
  */
-static int protected_save_fp_context(struct sigcontext __user *sc)
+int protected_save_fp_context(void __user *sc)
 {
+	struct mips_abi *abi = current->thread.abi;
+	uint64_t __user *fpregs = sc + abi->off_sc_fpregs;
+	uint32_t __user *csr = sc + abi->off_sc_fpc_csr;
+	uint32_t __user *used_math = sc + abi->off_sc_used_math;
+	unsigned int used, ext_sz;
 	int err;
-#ifndef CONFIG_EVA
+
+	used = used_math() ? USED_FP : 0;
+	if (!used)
+		goto fp_done;
+
+	if (!test_thread_flag(TIF_32BIT_FPREGS))
+		used |= USED_FR1;
+	if (test_thread_flag(TIF_HYBRID_FPREGS))
+		used |= USED_HYBRID_FPRS;
+
+	/*
+	 * EVA does not have userland equivalents of ldc1 or sdc1, so
+	 * save to the kernel FP context & copy that to userland below.
+	 */
+	if (config_enabled(CONFIG_EVA))
+		lose_fpu(1);
+
 	while (1) {
 		lock_fpu_owner();
 		if (is_fpu_owner()) {
@@ -114,27 +328,57 @@ static int protected_save_fp_context(struct sigcontext __user *sc)
 		if (likely(!err))
 			break;
 		/* touch the sigcontext and try again */
-		err = __put_user(0, &sc->sc_fpregs[0]) |
-			__put_user(0, &sc->sc_fpregs[31]) |
-			__put_user(0, &sc->sc_fpc_csr);
+		err = __put_user(0, &fpregs[0]) |
+			__put_user(0, &fpregs[31]) |
+			__put_user(0, csr);
 		if (err)
-			break;	/* really bad sigcontext */
+			return err;	/* really bad sigcontext */
 	}
-#else
-	/*
-	 * EVA does not have FPU EVA instructions so saving fpu context directly
-	 * does not work.
-	 */
-	lose_fpu(1);
-	err = save_fp_context(sc); /* this might fail */
-#endif
-	return err;
+
+fp_done:
+	ext_sz = err = save_extcontext(sc_to_extcontext(sc));
+	if (err < 0)
+		return err;
+	used |= ext_sz ? USED_EXTCONTEXT : 0;
+
+	return __put_user(used, used_math);
 }
 
-static int protected_restore_fp_context(struct sigcontext __user *sc)
+int protected_restore_fp_context(void __user *sc)
 {
-	int err, tmp __maybe_unused;
-#ifndef CONFIG_EVA
+	struct mips_abi *abi = current->thread.abi;
+	uint64_t __user *fpregs = sc + abi->off_sc_fpregs;
+	uint32_t __user *csr = sc + abi->off_sc_fpc_csr;
+	uint32_t __user *used_math = sc + abi->off_sc_used_math;
+	unsigned int used;
+	int err, sig = 0, tmp __maybe_unused;
+
+	err = __get_user(used, used_math);
+	conditional_used_math(used & USED_FP);
+
+	/*
+	 * The signal handler may have used FPU; give it up if the program
+	 * doesn't want it following sigreturn.
+	 */
+	if (err || !(used & USED_FP))
+		lose_fpu(0);
+	if (err)
+		return err;
+	if (!(used & USED_FP))
+		goto fp_done;
+
+	err = sig = fpcsr_pending(csr);
+	if (err < 0)
+		return err;
+
+	/*
+	 * EVA does not have userland equivalents of ldc1 or sdc1, so we
+	 * disable the FPU here such that the code below simply copies to
+	 * the kernel FP context.
+	 */
+	if (config_enabled(CONFIG_EVA))
+		lose_fpu(0);
+
 	while (1) {
 		lock_fpu_owner();
 		if (is_fpu_owner()) {
@@ -147,28 +391,24 @@ static int protected_restore_fp_context(struct sigcontext __user *sc)
 		if (likely(!err))
 			break;
 		/* touch the sigcontext and try again */
-		err = __get_user(tmp, &sc->sc_fpregs[0]) |
-			__get_user(tmp, &sc->sc_fpregs[31]) |
-			__get_user(tmp, &sc->sc_fpc_csr);
+		err = __get_user(tmp, &fpregs[0]) |
+			__get_user(tmp, &fpregs[31]) |
+			__get_user(tmp, csr);
 		if (err)
 			break;	/* really bad sigcontext */
 	}
-#else
-	/*
-	 * EVA does not have FPU EVA instructions so restoring fpu context
-	 * directly does not work.
-	 */
-	lose_fpu(0);
-	err = restore_fp_context(sc); /* this might fail */
-#endif
-	return err;
+
+fp_done:
+	if (used & USED_EXTCONTEXT)
+		err |= restore_extcontext(sc_to_extcontext(sc));
+
+	return err ?: sig;
 }
 
 int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 {
 	int err = 0;
 	int i;
-	unsigned int used_math;
 
 	err |= __put_user(regs->cp0_epc, &sc->sc_pc);
 
@@ -191,19 +431,38 @@ int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp);
 	}
 
-	used_math = !!used_math();
-	err |= __put_user(used_math, &sc->sc_used_math);
 
-	if (used_math) {
-		/*
-		 * Save FPU state to signal context. Signal handler
-		 * will "inherit" current FPU state.
-		 */
-		err |= protected_save_fp_context(sc);
-	}
+	/*
+	 * Save FPU state to signal context. Signal handler
+	 * will "inherit" current FPU state.
+	 */
+	err |= protected_save_fp_context(sc);
+
 	return err;
 }
 
+static size_t extcontext_max_size(void)
+{
+	size_t sz = 0;
+
+	/*
+	 * The assumption here is that between this point & the point at which
+	 * the extended context is saved the size of the context should only
+	 * ever be able to shrink (if the task is preempted), but never grow.
+	 * That is, what this function returns is an upper bound on the size of
+	 * the extended context for the current task at the current time.
+	 */
+
+	if (thread_msa_context_live())
+		sz += sizeof(struct msa_extcontext);
+
+	/* If any context is saved then we'll append the end marker */
+	if (sz)
+		sz += sizeof(((struct extcontext *)NULL)->magic);
+
+	return sz;
+}
+
 int fpcsr_pending(unsigned int __user *fpcsr)
 {
 	int err, sig = 0;
@@ -223,21 +482,8 @@ int fpcsr_pending(unsigned int __user *fpcsr)
 	return err ?: sig;
 }
 
-static int
-check_and_restore_fp_context(struct sigcontext __user *sc)
-{
-	int err, sig;
-
-	err = sig = fpcsr_pending(&sc->sc_fpc_csr);
-	if (err > 0)
-		err = 0;
-	err |= protected_restore_fp_context(sc);
-	return err ?: sig;
-}
-
 int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 {
-	unsigned int used_math;
 	unsigned long treg;
 	int err = 0;
 	int i;
@@ -265,19 +511,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	for (i = 1; i < 32; i++)
 		err |= __get_user(regs->regs[i], &sc->sc_regs[i]);
 
-	err |= __get_user(used_math, &sc->sc_used_math);
-	conditional_used_math(used_math);
-
-	if (used_math) {
-		/* restore fpu context if we have used it before */
-		if (!err)
-			err = check_and_restore_fp_context(sc);
-	} else {
-		/* signal handler may have used FPU.  Give it up. */
-		lose_fpu(0);
-	}
-
-	return err;
+	return err ?: protected_restore_fp_context(sc);
 }
 
 void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
@@ -285,6 +519,9 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 {
 	unsigned long sp;
 
+	/* Leave space for potential extended context */
+	frame_size += extcontext_max_size();
+
 	/* Default to using normal stack */
 	sp = regs->regs[29];
 
@@ -520,7 +757,11 @@ struct mips_abi mips_abi = {
 	.setup_rt_frame = setup_rt_frame,
 	.rt_signal_return_offset =
 		offsetof(struct mips_vdso, rt_signal_trampoline),
-	.restart	= __NR_restart_syscall
+	.restart	= __NR_restart_syscall,
+
+	.off_sc_fpregs = offsetof(struct sigcontext, sc_fpregs),
+	.off_sc_fpc_csr = offsetof(struct sigcontext, sc_fpc_csr),
+	.off_sc_used_math = offsetof(struct sigcontext, sc_used_math),
 };
 
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
@@ -616,6 +857,9 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 
 	user_exit();
 
+	if (thread_info_flags & _TIF_UPROBE)
+		uprobe_notify_resume(regs);
+
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
@@ -629,43 +873,46 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 }
 
 #ifdef CONFIG_SMP
-#ifndef CONFIG_EVA
-static int smp_save_fp_context(struct sigcontext __user *sc)
+static int smp_save_fp_context(void __user *sc)
 {
 	return raw_cpu_has_fpu
-	       ? _save_fp_context(sc)
+	       ? save_hw_fp_context(sc)
 	       : copy_fp_to_sigcontext(sc);
 }
 
-static int smp_restore_fp_context(struct sigcontext __user *sc)
+static int smp_restore_fp_context(void __user *sc)
 {
 	return raw_cpu_has_fpu
-	       ? _restore_fp_context(sc)
+	       ? restore_hw_fp_context(sc)
 	       : copy_fp_from_sigcontext(sc);
 }
-#endif /* CONFIG_EVA */
 #endif
 
 static int signal_setup(void)
 {
-#ifndef CONFIG_EVA
+	/*
+	 * The offset from sigcontext to extended context should be the same
+	 * regardless of the type of signal, such that userland can always know
+	 * where to look if it wishes to find the extended context structures.
+	 */
+	BUILD_BUG_ON((offsetof(struct sigframe, sf_extcontext) -
+		      offsetof(struct sigframe, sf_sc)) !=
+		     (offsetof(struct rt_sigframe, rs_uc.uc_extcontext) -
+		      offsetof(struct rt_sigframe, rs_uc.uc_mcontext)));
+
 #ifdef CONFIG_SMP
 	/* For now just do the cpu_has_fpu check when the functions are invoked */
 	save_fp_context = smp_save_fp_context;
 	restore_fp_context = smp_restore_fp_context;
 #else
 	if (cpu_has_fpu) {
-		save_fp_context = _save_fp_context;
-		restore_fp_context = _restore_fp_context;
+		save_fp_context = save_hw_fp_context;
+		restore_fp_context = restore_hw_fp_context;
 	} else {
 		save_fp_context = copy_fp_to_sigcontext;
 		restore_fp_context = copy_fp_from_sigcontext;
 	}
 #endif /* CONFIG_SMP */
-#else
-	save_fp_context = copy_fp_to_sigcontext;
-	restore_fp_context = copy_fp_from_sigcontext;
-#endif
 
 	return 0;
 }
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 19a7705f2a01..f7e89524e316 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -36,12 +36,6 @@
 
 #include "signal-common.h"
 
-static int (*save_fp_context32)(struct sigcontext32 __user *sc);
-static int (*restore_fp_context32)(struct sigcontext32 __user *sc);
-
-extern asmlinkage int _save_fp_context32(struct sigcontext32 __user *sc);
-extern asmlinkage int _restore_fp_context32(struct sigcontext32 __user *sc);
-
 /*
  * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
  */
@@ -74,99 +68,11 @@ struct rt_sigframe32 {
 	struct ucontext32 rs_uc;
 };
 
-/*
- * Thread saved context copy to/from a signal context presumed to be on the
- * user stack, and therefore accessed with appropriate macros from uaccess.h.
- */
-static int copy_fp_to_sigcontext32(struct sigcontext32 __user *sc)
-{
-	int i;
-	int err = 0;
-	int inc = test_thread_flag(TIF_32BIT_FPREGS) ? 2 : 1;
-
-	for (i = 0; i < NUM_FPU_REGS; i += inc) {
-		err |=
-		    __put_user(get_fpr64(&current->thread.fpu.fpr[i], 0),
-			       &sc->sc_fpregs[i]);
-	}
-	err |= __put_user(current->thread.fpu.fcr31, &sc->sc_fpc_csr);
-
-	return err;
-}
-
-static int copy_fp_from_sigcontext32(struct sigcontext32 __user *sc)
-{
-	int i;
-	int err = 0;
-	int inc = test_thread_flag(TIF_32BIT_FPREGS) ? 2 : 1;
-	u64 fpr_val;
-
-	for (i = 0; i < NUM_FPU_REGS; i += inc) {
-		err |= __get_user(fpr_val, &sc->sc_fpregs[i]);
-		set_fpr64(&current->thread.fpu.fpr[i], 0, fpr_val);
-	}
-	err |= __get_user(current->thread.fpu.fcr31, &sc->sc_fpc_csr);
-
-	return err;
-}
-
-/*
- * sigcontext handlers
- */
-static int protected_save_fp_context32(struct sigcontext32 __user *sc)
-{
-	int err;
-	while (1) {
-		lock_fpu_owner();
-		if (is_fpu_owner()) {
-			err = save_fp_context32(sc);
-			unlock_fpu_owner();
-		} else {
-			unlock_fpu_owner();
-			err = copy_fp_to_sigcontext32(sc);
-		}
-		if (likely(!err))
-			break;
-		/* touch the sigcontext and try again */
-		err = __put_user(0, &sc->sc_fpregs[0]) |
-			__put_user(0, &sc->sc_fpregs[31]) |
-			__put_user(0, &sc->sc_fpc_csr);
-		if (err)
-			break;	/* really bad sigcontext */
-	}
-	return err;
-}
-
-static int protected_restore_fp_context32(struct sigcontext32 __user *sc)
-{
-	int err, tmp __maybe_unused;
-	while (1) {
-		lock_fpu_owner();
-		if (is_fpu_owner()) {
-			err = restore_fp_context32(sc);
-			unlock_fpu_owner();
-		} else {
-			unlock_fpu_owner();
-			err = copy_fp_from_sigcontext32(sc);
-		}
-		if (likely(!err))
-			break;
-		/* touch the sigcontext and try again */
-		err = __get_user(tmp, &sc->sc_fpregs[0]) |
-			__get_user(tmp, &sc->sc_fpregs[31]) |
-			__get_user(tmp, &sc->sc_fpc_csr);
-		if (err)
-			break;	/* really bad sigcontext */
-	}
-	return err;
-}
-
 static int setup_sigcontext32(struct pt_regs *regs,
 			      struct sigcontext32 __user *sc)
 {
 	int err = 0;
 	int i;
-	u32 used_math;
 
 	err |= __put_user(regs->cp0_epc, &sc->sc_pc);
 
@@ -186,35 +92,18 @@ static int setup_sigcontext32(struct pt_regs *regs,
 		err |= __put_user(mflo3(), &sc->sc_lo3);
 	}
 
-	used_math = !!used_math();
-	err |= __put_user(used_math, &sc->sc_used_math);
+	/*
+	 * Save FPU state to signal context.  Signal handler
+	 * will "inherit" current FPU state.
+	 */
+	err |= protected_save_fp_context(sc);
 
-	if (used_math) {
-		/*
-		 * Save FPU state to signal context.  Signal handler
-		 * will "inherit" current FPU state.
-		 */
-		err |= protected_save_fp_context32(sc);
-	}
 	return err;
 }
 
-static int
-check_and_restore_fp_context32(struct sigcontext32 __user *sc)
-{
-	int err, sig;
-
-	err = sig = fpcsr_pending(&sc->sc_fpc_csr);
-	if (err > 0)
-		err = 0;
-	err |= protected_restore_fp_context32(sc);
-	return err ?: sig;
-}
-
 static int restore_sigcontext32(struct pt_regs *regs,
 				struct sigcontext32 __user *sc)
 {
-	u32 used_math;
 	int err = 0;
 	s32 treg;
 	int i;
@@ -238,70 +127,7 @@ static int restore_sigcontext32(struct pt_regs *regs,
 	for (i = 1; i < 32; i++)
 		err |= __get_user(regs->regs[i], &sc->sc_regs[i]);
 
-	err |= __get_user(used_math, &sc->sc_used_math);
-	conditional_used_math(used_math);
-
-	if (used_math) {
-		/* restore fpu context if we have used it before */
-		if (!err)
-			err = check_and_restore_fp_context32(sc);
-	} else {
-		/* signal handler may have used FPU.  Give it up. */
-		lose_fpu(0);
-	}
-
-	return err;
-}
-
-/*
- *
- */
-extern void __put_sigset_unknown_nsig(void);
-extern void __get_sigset_unknown_nsig(void);
-
-static inline int put_sigset(const sigset_t *kbuf, compat_sigset_t __user *ubuf)
-{
-	int err = 0;
-
-	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)))
-		return -EFAULT;
-
-	switch (_NSIG_WORDS) {
-	default:
-		__put_sigset_unknown_nsig();
-	case 2:
-		err |= __put_user(kbuf->sig[1] >> 32, &ubuf->sig[3]);
-		err |= __put_user(kbuf->sig[1] & 0xffffffff, &ubuf->sig[2]);
-	case 1:
-		err |= __put_user(kbuf->sig[0] >> 32, &ubuf->sig[1]);
-		err |= __put_user(kbuf->sig[0] & 0xffffffff, &ubuf->sig[0]);
-	}
-
-	return err;
-}
-
-static inline int get_sigset(sigset_t *kbuf, const compat_sigset_t __user *ubuf)
-{
-	int err = 0;
-	unsigned long sig[4];
-
-	if (!access_ok(VERIFY_READ, ubuf, sizeof(*ubuf)))
-		return -EFAULT;
-
-	switch (_NSIG_WORDS) {
-	default:
-		__get_sigset_unknown_nsig();
-	case 2:
-		err |= __get_user(sig[3], &ubuf->sig[3]);
-		err |= __get_user(sig[2], &ubuf->sig[2]);
-		kbuf->sig[1] = sig[2] | (sig[3] << 32);
-	case 1:
-		err |= __get_user(sig[1], &ubuf->sig[1]);
-		err |= __get_user(sig[0], &ubuf->sig[0]);
-		kbuf->sig[0] = sig[0] | (sig[1] << 32);
-	}
-
-	return err;
+	return err ?: protected_restore_fp_context(sc);
 }
 
 /*
@@ -409,8 +235,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
@@ -587,20 +411,9 @@ struct mips_abi mips_abi_32 = {
 	.setup_rt_frame = setup_rt_frame_32,
 	.rt_signal_return_offset =
 		offsetof(struct mips_vdso, o32_rt_signal_trampoline),
-	.restart	= __NR_O32_restart_syscall
-};
-
-static int signal32_init(void)
-{
-	if (cpu_has_fpu) {
-		save_fp_context32 = _save_fp_context32;
-		restore_fp_context32 = _restore_fp_context32;
-	} else {
-		save_fp_context32 = copy_fp_to_sigcontext32;
-		restore_fp_context32 = copy_fp_from_sigcontext32;
-	}
+	.restart	= __NR_O32_restart_syscall,
 
-	return 0;
-}
-
-arch_initcall(signal32_init);
+	.off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs),
+	.off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr),
+	.off_sc_used_math = offsetof(struct sigcontext32, sc_used_math),
+};
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index f1d4751eead0..0d017fdcaf07 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -153,5 +153,9 @@ struct mips_abi mips_abi_n32 = {
 	.setup_rt_frame = setup_rt_frame_n32,
 	.rt_signal_return_offset =
 		offsetof(struct mips_vdso, n32_rt_signal_trampoline),
-	.restart	= __NR_N32_restart_syscall
+	.restart	= __NR_N32_restart_syscall,
+
+	.off_sc_fpregs = offsetof(struct sigcontext, sc_fpregs),
+	.off_sc_fpc_csr = offsetof(struct sigcontext, sc_fpc_csr),
+	.off_sc_used_math = offsetof(struct sigcontext, sc_used_math),
 };
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 336708ae5c5b..78cf8c2f1de0 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -284,7 +284,7 @@ static irqreturn_t bmips5000_ipi_interrupt(int irq, void *dev_id)
 	if (action == 0)
 		scheduler_ipi();
 	else
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
@@ -336,7 +336,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 4251d390b5b6..c88937745b4e 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -133,7 +133,7 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
 	/*
 	 * Patch the start of mips_cps_core_entry to provide:
 	 *
-	 * v0 = CM base address
+	 * v1 = CM base address
 	 * s0 = kseg0 CCA
 	 */
 	entry_code = (u32 *)&mips_cps_core_entry;
@@ -369,7 +369,7 @@ void play_dead(void)
 
 static void wait_for_sibling_halt(void *ptr_cpu)
 {
-	unsigned cpu = (unsigned)ptr_cpu;
+	unsigned cpu = (unsigned long)ptr_cpu;
 	unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	unsigned halted;
 	unsigned long flags;
@@ -430,7 +430,7 @@ static void cps_cpu_die(unsigned int cpu)
 		 */
 		err = smp_call_function_single(cpu_death_sibling,
 					       wait_for_sibling_halt,
-					       (void *)cpu, 1);
+					       (void *)(unsigned long)cpu, 1);
 		if (err)
 			panic("Failed to call remote sibling CPU\n");
 	}
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index faa46ebd9dda..a31896c33716 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -63,6 +63,13 @@ EXPORT_SYMBOL(cpu_sibling_map);
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
+/*
+ * A logcal cpu mask containing only one VPE per core to
+ * reduce the number of IPIs on large MT systems.
+ */
+cpumask_t cpu_foreign_map __read_mostly;
+EXPORT_SYMBOL(cpu_foreign_map);
+
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
@@ -103,6 +110,29 @@ static inline void set_cpu_core_map(int cpu)
 	}
 }
 
+/*
+ * Calculate a new cpu_foreign_map mask whenever a
+ * new cpu appears or disappears.
+ */
+static inline void calculate_cpu_foreign_map(void)
+{
+	int i, k, core_present;
+	cpumask_t temp_foreign_map;
+
+	/* Re-calculate the mask */
+	for_each_online_cpu(i) {
+		core_present = 0;
+		for_each_cpu(k, &temp_foreign_map)
+			if (cpu_data[i].package == cpu_data[k].package &&
+			    cpu_data[i].core == cpu_data[k].core)
+				core_present = 1;
+		if (!core_present)
+			cpumask_set_cpu(i, &temp_foreign_map);
+	}
+
+	cpumask_copy(&cpu_foreign_map, &temp_foreign_map);
+}
+
 struct plat_smp_ops *mp_ops;
 EXPORT_SYMBOL(mp_ops);
 
@@ -146,6 +176,8 @@ asmlinkage void start_secondary(void)
 	set_cpu_sibling_map(cpu);
 	set_cpu_core_map(cpu);
 
+	calculate_cpu_foreign_map();
+
 	cpumask_set_cpu(cpu, &cpu_callin_map);
 
 	synchronise_count_slave(cpu);
@@ -160,22 +192,21 @@ asmlinkage void start_secondary(void)
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-/*
- * Call into both interrupt handlers, as we share the IPI for them
- */
-void __irq_entry smp_call_function_interrupt(void)
-{
-	irq_enter();
-	generic_smp_call_function_interrupt();
-	irq_exit();
-}
-
 static void stop_this_cpu(void *dummy)
 {
 	/*
-	 * Remove this CPU:
+	 * Remove this CPU. Be a bit slow here and
+	 * set the bits for every online CPU so we don't miss
+	 * any IPI whilst taking this VPE down.
 	 */
+
+	cpumask_copy(&cpu_foreign_map, cpu_online_mask);
+
+	/* Make it visible to every other CPU */
+	smp_mb();
+
 	set_cpu_online(smp_processor_id(), false);
+	calculate_cpu_foreign_map();
 	local_irq_disable();
 	while (1);
 }
@@ -197,6 +228,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	mp_ops->prepare_cpus(max_cpus);
 	set_cpu_sibling_map(0);
 	set_cpu_core_map(0);
+	calculate_cpu_foreign_map();
 #ifndef CONFIG_HOTPLUG_CPU
 	init_cpu_present(cpu_possible_mask);
 #endif
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
index d1168d7c31e8..8489c88f9932 100644
--- a/arch/mips/kernel/spram.c
+++ b/arch/mips/kernel/spram.c
@@ -209,6 +209,7 @@ void spram_config(void)
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 	case CPU_QEMU_GENERIC:
+	case CPU_I6400:
 		config0 = read_c0_config();
 		/* FIXME: addresses are Malta specific */
 		if (config0 & (1<<24)) {
diff --git a/arch/mips/kernel/sysrq.c b/arch/mips/kernel/sysrq.c
index 5b539f5fc9d9..5f055393092d 100644
--- a/arch/mips/kernel/sysrq.c
+++ b/arch/mips/kernel/sysrq.c
@@ -21,24 +21,12 @@ static DEFINE_SPINLOCK(show_lock);
 
 static void sysrq_tlbdump_single(void *dummy)
 {
-	const int field = 2 * sizeof(unsigned long);
 	unsigned long flags;
 
 	spin_lock_irqsave(&show_lock, flags);
 
 	pr_info("CPU%d:\n", smp_processor_id());
-	pr_info("Index	: %0x\n", read_c0_index());
-	pr_info("Pagemask: %0x\n", read_c0_pagemask());
-	pr_info("EntryHi : %0*lx\n", field, read_c0_entryhi());
-	pr_info("EntryLo0: %0*lx\n", field, read_c0_entrylo0());
-	pr_info("EntryLo1: %0*lx\n", field, read_c0_entrylo1());
-	pr_info("Wired   : %0x\n", read_c0_wired());
-	pr_info("Pagegrain: %0x\n", read_c0_pagegrain());
-	if (cpu_has_htw) {
-		pr_info("PWField : %0*lx\n", field, read_c0_pwfield());
-		pr_info("PWSize  : %0*lx\n", field, read_c0_pwsize());
-		pr_info("PWCtl   : %0x\n", read_c0_pwctl());
-	}
+	dump_tlb_regs();
 	pr_info("\n");
 	dump_tlb_all();
 	pr_info("\n");
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 2a7b38ed23f0..fdb392b27e81 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -192,6 +192,7 @@ static void show_stacktrace(struct task_struct *task,
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
+	mm_segment_t old_fs = get_fs();
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
@@ -210,7 +211,13 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 			prepare_frametrace(&regs);
 		}
 	}
+	/*
+	 * show_stack() deals exclusively with kernel mode, so be sure to access
+	 * the stack in the kernel (not user) address space.
+	 */
+	set_fs(KERNEL_DS);
 	show_stacktrace(task, &regs);
+	set_fs(old_fs);
 }
 
 static void show_code(unsigned int __user *pc)
@@ -363,11 +370,6 @@ void show_registers(struct pt_regs *regs)
 	set_fs(old_fs);
 }
 
-static int regs_to_trapnr(struct pt_regs *regs)
-{
-	return (regs->cp0_cause >> 2) & 0x1f;
-}
-
 static DEFINE_RAW_SPINLOCK(die_lock);
 
 void __noreturn die(const char *str, struct pt_regs *regs)
@@ -377,7 +379,7 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 
 	oops_enter();
 
-	if (notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs),
+	if (notify_die(DIE_OOPS, str, regs, 0, current->thread.trap_nr,
 		       SIGSEGV) == NOTIFY_STOP)
 		sig = 0;
 
@@ -463,7 +465,7 @@ asmlinkage void do_be(struct pt_regs *regs)
 	printk(KERN_ALERT "%s bus error, epc == %0*lx, ra == %0*lx\n",
 	       data ? "Data" : "Instruction",
 	       field, regs->cp0_epc, field, regs->regs[31]);
-	if (notify_die(DIE_OOPS, "bus error", regs, 0, regs_to_trapnr(regs),
+	if (notify_die(DIE_OOPS, "bus error", regs, 0, current->thread.trap_nr,
 		       SIGBUS) == NOTIFY_STOP)
 		goto out;
 
@@ -819,7 +821,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 	int sig;
 
 	prev_state = exception_enter();
-	if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs),
+	if (notify_die(DIE_FP, "FP exception", regs, 0, current->thread.trap_nr,
 		       SIGFPE) == NOTIFY_STOP)
 		goto out;
 
@@ -875,11 +877,12 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 	char b[40];
 
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
-	if (kgdb_ll_trap(DIE_TRAP, str, regs, code, regs_to_trapnr(regs), SIGTRAP) == NOTIFY_STOP)
+	if (kgdb_ll_trap(DIE_TRAP, str, regs, code, current->thread.trap_nr,
+			 SIGTRAP) == NOTIFY_STOP)
 		return;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
-	if (notify_die(DIE_TRAP, str, regs, code, regs_to_trapnr(regs),
+	if (notify_die(DIE_TRAP, str, regs, code, current->thread.trap_nr,
 		       SIGTRAP) == NOTIFY_STOP)
 		return;
 
@@ -941,6 +944,7 @@ asmlinkage void do_bp(struct pt_regs *regs)
 		set_fs(KERNEL_DS);
 
 	prev_state = exception_enter();
+	current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 	if (get_isa16_mode(regs->cp0_epc)) {
 		u16 instr[2];
 
@@ -980,15 +984,27 @@ asmlinkage void do_bp(struct pt_regs *regs)
 	 * pertain to them.
 	 */
 	switch (bcode) {
+	case BRK_UPROBE:
+		if (notify_die(DIE_UPROBE, "uprobe", regs, bcode,
+			       current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP)
+			goto out;
+		else
+			break;
+	case BRK_UPROBE_XOL:
+		if (notify_die(DIE_UPROBE_XOL, "uprobe_xol", regs, bcode,
+			       current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP)
+			goto out;
+		else
+			break;
 	case BRK_KPROBE_BP:
 		if (notify_die(DIE_BREAK, "debug", regs, bcode,
-			       regs_to_trapnr(regs), SIGTRAP) == NOTIFY_STOP)
+			       current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP)
 			goto out;
 		else
 			break;
 	case BRK_KPROBE_SSTEPBP:
 		if (notify_die(DIE_SSTEPBP, "single_step", regs, bcode,
-			       regs_to_trapnr(regs), SIGTRAP) == NOTIFY_STOP)
+			       current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP)
 			goto out;
 		else
 			break;
@@ -1021,6 +1037,7 @@ asmlinkage void do_tr(struct pt_regs *regs)
 		set_fs(get_ds());
 
 	prev_state = exception_enter();
+	current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 	if (get_isa16_mode(regs->cp0_epc)) {
 		if (__get_user(instr[0], (u16 __user *)(epc + 0)) ||
 		    __get_user(instr[1], (u16 __user *)(epc + 2)))
@@ -1087,8 +1104,9 @@ asmlinkage void do_ri(struct pt_regs *regs)
 no_r2_instr:
 
 	prev_state = exception_enter();
+	current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 
-	if (notify_die(DIE_RI, "RI Fault", regs, 0, regs_to_trapnr(regs),
+	if (notify_die(DIE_RI, "RI Fault", regs, 0, current->thread.trap_nr,
 		       SIGILL) == NOTIFY_STOP)
 		goto out;
 
@@ -1437,8 +1455,9 @@ asmlinkage void do_msa_fpe(struct pt_regs *regs, unsigned int msacsr)
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 	if (notify_die(DIE_MSAFP, "MSA FP exception", regs, 0,
-		       regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP)
+		       current->thread.trap_nr, SIGFPE) == NOTIFY_STOP)
 		goto out;
 
 	/* Clear MSACSR.Cause before enabling interrupts */
@@ -1516,32 +1535,26 @@ asmlinkage void do_watch(struct pt_regs *regs)
 
 asmlinkage void do_mcheck(struct pt_regs *regs)
 {
-	const int field = 2 * sizeof(unsigned long);
 	int multi_match = regs->cp0_status & ST0_TS;
 	enum ctx_state prev_state;
+	mm_segment_t old_fs = get_fs();
 
 	prev_state = exception_enter();
 	show_regs(regs);
 
 	if (multi_match) {
-		pr_err("Index	: %0x\n", read_c0_index());
-		pr_err("Pagemask: %0x\n", read_c0_pagemask());
-		pr_err("EntryHi : %0*lx\n", field, read_c0_entryhi());
-		pr_err("EntryLo0: %0*lx\n", field, read_c0_entrylo0());
-		pr_err("EntryLo1: %0*lx\n", field, read_c0_entrylo1());
-		pr_err("Wired   : %0x\n", read_c0_wired());
-		pr_err("Pagegrain: %0x\n", read_c0_pagegrain());
-		if (cpu_has_htw) {
-			pr_err("PWField : %0*lx\n", field, read_c0_pwfield());
-			pr_err("PWSize  : %0*lx\n", field, read_c0_pwsize());
-			pr_err("PWCtl   : %0x\n", read_c0_pwctl());
-		}
-		pr_err("\n");
+		dump_tlb_regs();
+		pr_info("\n");
 		dump_tlb_all();
 	}
 
+	if (!user_mode(regs))
+		set_fs(KERNEL_DS);
+
 	show_code((unsigned int __user *) regs->cp0_epc);
 
+	set_fs(old_fs);
+
 	/*
 	 * Some chips may have other causes of machine check (e.g. SB1
 	 * graduation timer)
@@ -1638,6 +1651,7 @@ static inline void parity_protection_init(void)
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 	case CPU_QEMU_GENERIC:
+	case CPU_I6400:
 		{
 #define ERRCTL_PE	0x80000000
 #define ERRCTL_L2P	0x00800000
@@ -2130,10 +2144,10 @@ void per_cpu_trap_init(bool is_boot_cpu)
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
 
-		/* Boot CPU's cache setup in setup_arch(). */
-		if (!is_boot_cpu)
-			cpu_cache_init();
-		tlb_init();
+	/* Boot CPU's cache setup in setup_arch(). */
+	if (!is_boot_cpu)
+		cpu_cache_init();
+	tlb_init();
 	TLBMISS_HANDLER_SETUP();
 }
 
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index af84bef0c90d..990354dd6bde 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -438,7 +438,7 @@ do {                                                        \
 		: "memory");                                \
 } while(0)
 
-#define     StoreDW(addr, value, res) \
+#define     _StoreDW(addr, value, res) \
 do {                                                        \
 		__asm__ __volatile__ (                      \
 			".set\tpush\n\t"		    \
@@ -891,6 +891,9 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 #ifdef	CONFIG_EVA
 	mm_segment_t seg;
 #endif
+	union fpureg *fpr;
+	enum msa_2b_fmt df;
+	unsigned int wd;
 	origpc = (unsigned long)pc;
 	orig31 = regs->regs[31];
 
@@ -1202,6 +1205,75 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			break;
 		return;
 
+	case msa_op:
+		if (!cpu_has_msa)
+			goto sigill;
+
+		/*
+		 * If we've reached this point then userland should have taken
+		 * the MSA disabled exception & initialised vector context at
+		 * some point in the past.
+		 */
+		BUG_ON(!thread_msa_context_live());
+
+		df = insn.msa_mi10_format.df;
+		wd = insn.msa_mi10_format.wd;
+		fpr = &current->thread.fpu.fpr[wd];
+
+		switch (insn.msa_mi10_format.func) {
+		case msa_ld_op:
+			if (!access_ok(VERIFY_READ, addr, sizeof(*fpr)))
+				goto sigbus;
+
+			/*
+			 * Disable preemption to avoid a race between copying
+			 * state from userland, migrating to another CPU and
+			 * updating the hardware vector register below.
+			 */
+			preempt_disable();
+
+			res = __copy_from_user_inatomic(fpr, addr,
+							sizeof(*fpr));
+			if (res)
+				goto fault;
+
+			/*
+			 * Update the hardware register if it is in use by the
+			 * task in this quantum, in order to avoid having to
+			 * save & restore the whole vector context.
+			 */
+			if (test_thread_flag(TIF_USEDMSA))
+				write_msa_wr(wd, fpr, df);
+
+			preempt_enable();
+			break;
+
+		case msa_st_op:
+			if (!access_ok(VERIFY_WRITE, addr, sizeof(*fpr)))
+				goto sigbus;
+
+			/*
+			 * Update from the hardware register if it is in use by
+			 * the task in this quantum, in order to avoid having to
+			 * save & restore the whole vector context.
+			 */
+			preempt_disable();
+			if (test_thread_flag(TIF_USEDMSA))
+				read_msa_wr(wd, fpr, df);
+			preempt_enable();
+
+			res = __copy_to_user_inatomic(addr, fpr, sizeof(*fpr));
+			if (res)
+				goto fault;
+			break;
+
+		default:
+			goto sigbus;
+		}
+
+		compute_return_epc(regs);
+		break;
+
 #ifndef CONFIG_CPU_MIPSR6
 	/*
 	 * COP2 is available to implementor for application specific use.
@@ -2240,5 +2312,5 @@ static int __init debugfs_unaligned(void)
 		return -ENOMEM;
 	return 0;
 }
-__initcall(debugfs_unaligned);
+arch_initcall(debugfs_unaligned);
 #endif
diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c
new file mode 100644
index 000000000000..8452d933a645
--- /dev/null
+++ b/arch/mips/kernel/uprobes.c
@@ -0,0 +1,341 @@
+#include <linux/highmem.h>
+#include <linux/kdebug.h>
+#include <linux/types.h>
+#include <linux/notifier.h>
+#include <linux/sched.h>
+#include <linux/uprobes.h>
+
+#include <asm/branch.h>
+#include <asm/cpu-features.h>
+#include <asm/ptrace.h>
+#include <asm/inst.h>
+
+static inline int insn_has_delay_slot(const union mips_instruction insn)
+{
+	switch (insn.i_format.opcode) {
+	/*
+	 * jr and jalr are in r_format format.
+	 */
+	case spec_op:
+		switch (insn.r_format.func) {
+		case jalr_op:
+		case jr_op:
+			return 1;
+		}
+		break;
+
+	/*
+	 * This group contains:
+	 * bltz_op, bgez_op, bltzl_op, bgezl_op,
+	 * bltzal_op, bgezal_op, bltzall_op, bgezall_op.
+	 */
+	case bcond_op:
+		switch (insn.i_format.rt) {
+		case bltz_op:
+		case bltzl_op:
+		case bgez_op:
+		case bgezl_op:
+		case bltzal_op:
+		case bltzall_op:
+		case bgezal_op:
+		case bgezall_op:
+		case bposge32_op:
+			return 1;
+		}
+		break;
+
+	/*
+	 * These are unconditional and in j_format.
+	 */
+	case jal_op:
+	case j_op:
+	case beq_op:
+	case beql_op:
+	case bne_op:
+	case bnel_op:
+	case blez_op: /* not really i_format */
+	case blezl_op:
+	case bgtz_op:
+	case bgtzl_op:
+		return 1;
+
+	/*
+	 * And now the FPA/cp1 branch instructions.
+	 */
+	case cop1_op:
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+	case lwc2_op: /* This is bbit0 on Octeon */
+	case ldc2_op: /* This is bbit032 on Octeon */
+	case swc2_op: /* This is bbit1 on Octeon */
+	case sdc2_op: /* This is bbit132 on Octeon */
+#endif
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * arch_uprobe_analyze_insn - instruction analysis including validity and fixups.
+ * @mm: the probed address space.
+ * @arch_uprobe: the probepoint information.
+ * @addr: virtual address at which to install the probepoint
+ * Return 0 on success or a -ve number on error.
+ */
+int arch_uprobe_analyze_insn(struct arch_uprobe *aup,
+	struct mm_struct *mm, unsigned long addr)
+{
+	union mips_instruction inst;
+
+	/*
+	 * For the time being this also blocks attempts to use uprobes with
+	 * MIPS16 and microMIPS.
+	 */
+	if (addr & 0x03)
+		return -EINVAL;
+
+	inst.word = aup->insn[0];
+	aup->ixol[0] = aup->insn[insn_has_delay_slot(inst)];
+	aup->ixol[1] = UPROBE_BRK_UPROBE_XOL;		/* NOP  */
+
+	return 0;
+}
+
+/**
+ * is_trap_insn - check if the instruction is a trap variant
+ * @insn: instruction to be checked.
+ * Returns true if @insn is a trap variant.
+ *
+ * This definition overrides the weak definition in kernel/events/uprobes.c.
+ * and is needed for the case where an architecture has multiple trap
+ * instructions (like PowerPC or MIPS).  We treat BREAK just like the more
+ * modern conditional trap instructions.
+ */
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+	union mips_instruction inst;
+
+	inst.word = *insn;
+
+	switch (inst.i_format.opcode) {
+	case spec_op:
+		switch (inst.r_format.func) {
+		case break_op:
+		case teq_op:
+		case tge_op:
+		case tgeu_op:
+		case tlt_op:
+		case tltu_op:
+		case tne_op:
+			return 1;
+		}
+		break;
+
+	case bcond_op:	/* Yes, really ...  */
+		switch (inst.u_format.rt) {
+		case teqi_op:
+		case tgei_op:
+		case tgeiu_op:
+		case tlti_op:
+		case tltiu_op:
+		case tnei_op:
+			return 1;
+		}
+		break;
+	}
+
+	return 0;
+}
+
+#define UPROBE_TRAP_NR	ULONG_MAX
+
+/*
+ * arch_uprobe_pre_xol - prepare to execute out of line.
+ * @auprobe: the probepoint information.
+ * @regs: reflects the saved user state of current task.
+ */
+int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+	union mips_instruction insn;
+
+	/*
+	 * Now find the EPC where to resume after the breakpoint has been
+	 * dealt with.  This may require emulation of a branch.
+	 */
+	aup->resume_epc = regs->cp0_epc + 4;
+	if (insn_has_delay_slot((union mips_instruction) aup->insn[0])) {
+		unsigned long epc;
+
+		epc = regs->cp0_epc;
+		__compute_return_epc_for_insn(regs, insn);
+		aup->resume_epc = regs->cp0_epc;
+	}
+
+	utask->autask.saved_trap_nr = current->thread.trap_nr;
+	current->thread.trap_nr = UPROBE_TRAP_NR;
+	regs->cp0_epc = current->utask->xol_vaddr;
+
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	current->thread.trap_nr = utask->autask.saved_trap_nr;
+	regs->cp0_epc = aup->resume_epc;
+
+	return 0;
+}
+
+/*
+ * If xol insn itself traps and generates a signal(Say,
+ * SIGILL/SIGSEGV/etc), then detect the case where a singlestepped
+ * instruction jumps back to its own address. It is assumed that anything
+ * like do_page_fault/do_trap/etc sets thread.trap_nr != -1.
+ *
+ * arch_uprobe_pre_xol/arch_uprobe_post_xol save/restore thread.trap_nr,
+ * arch_uprobe_xol_was_trapped() simply checks that ->trap_nr is not equal to
+ * UPROBE_TRAP_NR == -1 set by arch_uprobe_pre_xol().
+ */
+bool arch_uprobe_xol_was_trapped(struct task_struct *tsk)
+{
+	if (tsk->thread.trap_nr != UPROBE_TRAP_NR)
+		return true;
+
+	return false;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+	unsigned long val, void *data)
+{
+	struct die_args *args = data;
+	struct pt_regs *regs = args->regs;
+
+	/* regs == NULL is a kernel bug */
+	if (WARN_ON(!regs))
+		return NOTIFY_DONE;
+
+	/* We are only interested in userspace traps */
+	if (!user_mode(regs))
+		return NOTIFY_DONE;
+
+	switch (val) {
+	case DIE_BREAK:
+		if (uprobe_pre_sstep_notifier(regs))
+			return NOTIFY_STOP;
+		break;
+	case DIE_UPROBE_XOL:
+		if (uprobe_post_sstep_notifier(regs))
+			return NOTIFY_STOP;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/*
+ * This function gets called when XOL instruction either gets trapped or
+ * the thread has a fatal signal. Reset the instruction pointer to its
+ * probed address for the potential restart or for post mortem analysis.
+ */
+void arch_uprobe_abort_xol(struct arch_uprobe *aup,
+	struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	instruction_pointer_set(regs, utask->vaddr);
+}
+
+unsigned long arch_uretprobe_hijack_return_addr(
+	unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+	unsigned long ra;
+
+	ra = regs->regs[31];
+
+	/* Replace the return address with the trampoline address */
+	regs->regs[31] = ra;
+
+	return ra;
+}
+
+/**
+ * set_swbp - store breakpoint at a given address.
+ * @auprobe: arch specific probepoint information.
+ * @mm: the probed process address space.
+ * @vaddr: the virtual address to insert the opcode.
+ *
+ * For mm @mm, store the breakpoint instruction at @vaddr.
+ * Return 0 (success) or a negative errno.
+ *
+ * This version overrides the weak version in kernel/events/uprobes.c.
+ * It is required to handle MIPS16 and microMIPS.
+ */
+int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
+	unsigned long vaddr)
+{
+	return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
+}
+
+/**
+ * set_orig_insn - Restore the original instruction.
+ * @mm: the probed process address space.
+ * @auprobe: arch specific probepoint information.
+ * @vaddr: the virtual address to insert the opcode.
+ *
+ * For mm @mm, restore the original opcode (opcode) at @vaddr.
+ * Return 0 (success) or a negative errno.
+ *
+ * This overrides the weak version in kernel/events/uprobes.c.
+ */
+int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+		 unsigned long vaddr)
+{
+	return uprobe_write_opcode(mm, vaddr,
+			*(uprobe_opcode_t *)&auprobe->orig_inst[0].word);
+}
+
+void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+				  void *src, unsigned long len)
+{
+	void *kaddr;
+
+	/* Initialize the slot */
+	kaddr = kmap_atomic(page);
+	memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len);
+	kunmap_atomic(kaddr);
+
+	/*
+	 * The MIPS version of flush_icache_range will operate safely on
+	 * user space addresses and more importantly, it doesn't require a
+	 * VMA argument.
+	 */
+	flush_icache_range(vaddr, vaddr + len);
+}
+
+/**
+ * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
+ * @regs: Reflects the saved state of the task after it has hit a breakpoint
+ * instruction.
+ * Return the address of the breakpoint instruction.
+ *
+ * This overrides the weak version in kernel/events/uprobes.c.
+ */
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+/*
+ * See if the instruction can be emulated.
+ * Returns true if instruction was emulated, false otherwise.
+ *
+ * For now we always emulate so this function just returns 0.
+ */
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	return 0;
+}
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 11da314565cc..9067b651c7a2 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -817,6 +817,7 @@ static int vpe_open(struct inode *inode, struct file *filp)
 
 static int vpe_release(struct inode *inode, struct file *filp)
 {
+#if defined(CONFIG_MIPS_VPE_LOADER_MT) || defined(CONFIG_MIPS_VPE_LOADER_CMP)
 	struct vpe *v;
 	Elf_Ehdr *hdr;
 	int ret = 0;
@@ -827,7 +828,7 @@ static int vpe_release(struct inode *inode, struct file *filp)
 
 	hdr = (Elf_Ehdr *) v->pbuffer;
 	if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) == 0) {
-		if ((vpe_elfload(v) >= 0) && vpe_run) {
+		if (vpe_elfload(v) >= 0) {
 			vpe_run(v);
 		} else {
 			pr_warn("VPE loader: ELF load failed.\n");
@@ -850,6 +851,10 @@ static int vpe_release(struct inode *inode, struct file *filp)
 	v->plen = 0;
 
 	return ret;
+#else
+	pr_warn("VPE loader: ELF load failed.\n");
+	return -ENOEXEC;
+#endif
 }
 
 static ssize_t vpe_write(struct file *file, const char __user *buffer,
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 6ab10573490d..2c218c3bbca5 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -293,7 +293,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
@@ -466,6 +466,7 @@ int get_c0_perfcount_int(void)
 {
 	return ltq_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c
index a57959e648a6..c710d969938d 100644
--- a/arch/mips/lasat/sysctl.c
+++ b/arch/mips/lasat/sysctl.c
@@ -270,4 +270,4 @@ static int __init lasat_register_sysctl(void)
 	return 0;
 }
 
-__initcall(lasat_register_sysctl);
+arch_initcall(lasat_register_sysctl);
diff --git a/arch/mips/lib/dump_tlb.c b/arch/mips/lib/dump_tlb.c
index 167f35634709..92a37319efbe 100644
--- a/arch/mips/lib/dump_tlb.c
+++ b/arch/mips/lib/dump_tlb.c
@@ -13,6 +13,33 @@
 #include <asm/pgtable.h>
 #include <asm/tlbdebug.h>
 
+void dump_tlb_regs(void)
+{
+	const int field = 2 * sizeof(unsigned long);
+
+	pr_info("Index    : %0x\n", read_c0_index());
+	pr_info("PageMask : %0x\n", read_c0_pagemask());
+	pr_info("EntryHi  : %0*lx\n", field, read_c0_entryhi());
+	pr_info("EntryLo0 : %0*lx\n", field, read_c0_entrylo0());
+	pr_info("EntryLo1 : %0*lx\n", field, read_c0_entrylo1());
+	pr_info("Wired    : %0x\n", read_c0_wired());
+	switch (current_cpu_type()) {
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_R14000:
+	case CPU_R16000:
+		pr_info("FrameMask: %0x\n", read_c0_framemask());
+		break;
+	}
+	if (cpu_has_small_pages || cpu_has_rixi || cpu_has_xpa)
+		pr_info("PageGrain: %0x\n", read_c0_pagegrain());
+	if (cpu_has_htw) {
+		pr_info("PWField  : %0*lx\n", field, read_c0_pwfield());
+		pr_info("PWSize   : %0*lx\n", field, read_c0_pwsize());
+		pr_info("PWCtl    : %0x\n", read_c0_pwctl());
+	}
+}
+
 static inline const char *msk2str(unsigned int mask)
 {
 	switch (mask) {
@@ -87,7 +114,7 @@ static void dump_tlb(int first, int last)
 		 * leave only a single G bit set after a machine check exception
 		 * due to duplicate TLB entry.
 		 */
-		if (!((entrylo0 | entrylo1) & MIPS_ENTRYLO_G) &&
+		if (!((entrylo0 | entrylo1) & ENTRYLO_G) &&
 		    (entryhi & 0xff) != asid)
 			continue;
 
@@ -96,8 +123,8 @@ static void dump_tlb(int first, int last)
 		 */
 		printk("Index: %2d pgmask=%s ", i, msk2str(pagemask));
 
-		c0 = (entrylo0 & MIPS_ENTRYLO_C) >> MIPS_ENTRYLO_C_SHIFT;
-		c1 = (entrylo1 & MIPS_ENTRYLO_C) >> MIPS_ENTRYLO_C_SHIFT;
+		c0 = (entrylo0 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
+		c1 = (entrylo1 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
 
 		printk("va=%0*lx asid=%02lx\n",
 		       vwidth, (entryhi & ~0x1fffUL),
@@ -114,9 +141,9 @@ static void dump_tlb(int first, int last)
 			       (entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0);
 		printk("pa=%0*llx c=%d d=%d v=%d g=%d] [",
 		       pwidth, pa, c0,
-		       (entrylo0 & MIPS_ENTRYLO_D) ? 1 : 0,
-		       (entrylo0 & MIPS_ENTRYLO_V) ? 1 : 0,
-		       (entrylo0 & MIPS_ENTRYLO_G) ? 1 : 0);
+		       (entrylo0 & ENTRYLO_D) ? 1 : 0,
+		       (entrylo0 & ENTRYLO_V) ? 1 : 0,
+		       (entrylo0 & ENTRYLO_G) ? 1 : 0);
 		/* RI/XI are in awkward places, so mask them off separately */
 		pa = entrylo1 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI);
 		if (xpa)
@@ -128,9 +155,9 @@ static void dump_tlb(int first, int last)
 			       (entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0);
 		printk("pa=%0*llx c=%d d=%d v=%d g=%d]\n",
 		       pwidth, pa, c1,
-		       (entrylo1 & MIPS_ENTRYLO_D) ? 1 : 0,
-		       (entrylo1 & MIPS_ENTRYLO_V) ? 1 : 0,
-		       (entrylo1 & MIPS_ENTRYLO_G) ? 1 : 0);
+		       (entrylo1 & ENTRYLO_D) ? 1 : 0,
+		       (entrylo1 & ENTRYLO_V) ? 1 : 0,
+		       (entrylo1 & ENTRYLO_G) ? 1 : 0);
 	}
 	printk("\n");
 
diff --git a/arch/mips/lib/r3k_dump_tlb.c b/arch/mips/lib/r3k_dump_tlb.c
index 8e0d3cff8ae4..cfcbb5218b59 100644
--- a/arch/mips/lib/r3k_dump_tlb.c
+++ b/arch/mips/lib/r3k_dump_tlb.c
@@ -14,6 +14,17 @@
 #include <asm/pgtable.h>
 #include <asm/tlbdebug.h>
 
+extern int r3k_have_wired_reg;
+
+void dump_tlb_regs(void)
+{
+	pr_info("Index    : %0x\n", read_c0_index());
+	pr_info("EntryHi  : %0lx\n", read_c0_entryhi());
+	pr_info("EntryLo  : %0lx\n", read_c0_entrylo0());
+	if (r3k_have_wired_reg)
+		pr_info("Wired    : %0x\n", read_c0_wired());
+}
+
 static void dump_tlb(int first, int last)
 {
 	int	i;
diff --git a/arch/mips/loongson32/common/time.c b/arch/mips/loongson32/common/time.c
index df0f850d6a5f..0996b025eeef 100644
--- a/arch/mips/loongson32/common/time.c
+++ b/arch/mips/loongson32/common/time.c
@@ -126,26 +126,34 @@ static irqreturn_t ls1x_clockevent_isr(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
-static void ls1x_clockevent_set_mode(enum clock_event_mode mode,
-				     struct clock_event_device *cd)
+static int ls1x_clockevent_set_state_periodic(struct clock_event_device *cd)
 {
 	raw_spin_lock(&ls1x_timer_lock);
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		ls1x_pwmtimer_set_period(ls1x_jiffies_per_tick);
-		ls1x_pwmtimer_restart();
-	case CLOCK_EVT_MODE_RESUME:
-		__raw_writel(INT_EN | CNT_EN, timer_base + PWM_CTRL);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		__raw_writel(__raw_readl(timer_base + PWM_CTRL) & ~CNT_EN,
-			     timer_base + PWM_CTRL);
-		break;
-	default:
-		break;
-	}
+	ls1x_pwmtimer_set_period(ls1x_jiffies_per_tick);
+	ls1x_pwmtimer_restart();
+	__raw_writel(INT_EN | CNT_EN, timer_base + PWM_CTRL);
 	raw_spin_unlock(&ls1x_timer_lock);
+
+	return 0;
+}
+
+static int ls1x_clockevent_tick_resume(struct clock_event_device *cd)
+{
+	raw_spin_lock(&ls1x_timer_lock);
+	__raw_writel(INT_EN | CNT_EN, timer_base + PWM_CTRL);
+	raw_spin_unlock(&ls1x_timer_lock);
+
+	return 0;
+}
+
+static int ls1x_clockevent_set_state_shutdown(struct clock_event_device *cd)
+{
+	raw_spin_lock(&ls1x_timer_lock);
+	__raw_writel(__raw_readl(timer_base + PWM_CTRL) & ~CNT_EN,
+		     timer_base + PWM_CTRL);
+	raw_spin_unlock(&ls1x_timer_lock);
+
+	return 0;
 }
 
 static int ls1x_clockevent_set_next(unsigned long evt,
@@ -160,12 +168,15 @@ static int ls1x_clockevent_set_next(unsigned long evt,
 }
 
 static struct clock_event_device ls1x_clockevent = {
-	.name		= "ls1x-pwmtimer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC,
-	.rating		= 300,
-	.irq		= LS1X_TIMER_IRQ,
-	.set_next_event	= ls1x_clockevent_set_next,
-	.set_mode	= ls1x_clockevent_set_mode,
+	.name			= "ls1x-pwmtimer",
+	.features		= CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 300,
+	.irq			= LS1X_TIMER_IRQ,
+	.set_next_event		= ls1x_clockevent_set_next,
+	.set_state_shutdown	= ls1x_clockevent_set_state_shutdown,
+	.set_state_periodic	= ls1x_clockevent_set_state_periodic,
+	.set_state_oneshot	= ls1x_clockevent_set_state_shutdown,
+	.tick_resume		= ls1x_clockevent_tick_resume,
 };
 
 static struct irqaction ls1x_pwmtimer_irqaction = {
diff --git a/arch/mips/loongson64/common/bonito-irq.c b/arch/mips/loongson64/common/bonito-irq.c
index cc0e4fd548e6..4e116d23bab3 100644
--- a/arch/mips/loongson64/common/bonito-irq.c
+++ b/arch/mips/loongson64/common/bonito-irq.c
@@ -3,7 +3,7 @@
  * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net
  * Copyright (C) 2000, 2001 Ralf Baechle (ralf@gnu.org)
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/common/cmdline.c b/arch/mips/loongson64/common/cmdline.c
index 72fed003a536..01fbed137028 100644
--- a/arch/mips/loongson64/common/cmdline.c
+++ b/arch/mips/loongson64/common/cmdline.c
@@ -6,7 +6,7 @@
  * Copyright 2003 ICT CAS
  * Author: Michael Guo <guoyi@ict.ac.cn>
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
index 12c75db23420..da77d412514c 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
@@ -1,7 +1,7 @@
 /*
  * CS5536 General timer functions
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
@@ -51,40 +51,36 @@ void enable_mfgpt0_counter(void)
 }
 EXPORT_SYMBOL(enable_mfgpt0_counter);
 
-static void init_mfgpt_timer(enum clock_event_mode mode,
-			     struct clock_event_device *evt)
+static int mfgpt_timer_set_periodic(struct clock_event_device *evt)
 {
 	raw_spin_lock(&mfgpt_lock);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		outw(COMPARE, MFGPT0_CMP2);	/* set comparator2 */
-		outw(0, MFGPT0_CNT);	/* set counter to 0 */
-		enable_mfgpt0_counter();
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		if (evt->mode == CLOCK_EVT_MODE_PERIODIC ||
-		    evt->mode == CLOCK_EVT_MODE_ONESHOT)
-			disable_mfgpt0_counter();
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* The oneshot mode have very high deviation, Not use it! */
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
+	outw(COMPARE, MFGPT0_CMP2);	/* set comparator2 */
+	outw(0, MFGPT0_CNT);		/* set counter to 0 */
+	enable_mfgpt0_counter();
+
 	raw_spin_unlock(&mfgpt_lock);
+	return 0;
+}
+
+static int mfgpt_timer_shutdown(struct clock_event_device *evt)
+{
+	if (clockevent_state_periodic(evt) || clockevent_state_oneshot(evt)) {
+		raw_spin_lock(&mfgpt_lock);
+		disable_mfgpt0_counter();
+		raw_spin_unlock(&mfgpt_lock);
+	}
+
+	return 0;
 }
 
 static struct clock_event_device mfgpt_clockevent = {
 	.name = "mfgpt",
 	.features = CLOCK_EVT_FEAT_PERIODIC,
-	.set_mode = init_mfgpt_timer,
+
+	/* The oneshot mode have very high deviation, don't use it! */
+	.set_state_shutdown = mfgpt_timer_shutdown,
+	.set_state_periodic = mfgpt_timer_set_periodic,
 	.irq = CS5536_MFGPT_INTR,
 };
 
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index 22f04ca2ff3e..f6c44dd332e2 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -6,7 +6,7 @@
  * Copyright 2003 ICT CAS
  * Author: Michael Guo <guoyi@ict.ac.cn>
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/irq.c b/arch/mips/loongson64/common/irq.c
index 687003b19b45..d36d969a4a87 100644
--- a/arch/mips/loongson64/common/irq.c
+++ b/arch/mips/loongson64/common/irq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/common/setup.c b/arch/mips/loongson64/common/setup.c
index d477dd6bb326..2dc5122f0e09 100644
--- a/arch/mips/loongson64/common/setup.c
+++ b/arch/mips/loongson64/common/setup.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/fuloong-2e/irq.c b/arch/mips/loongson64/fuloong-2e/irq.c
index ef5ec8f3de5f..892963f860b7 100644
--- a/arch/mips/loongson64/fuloong-2e/irq.c
+++ b/arch/mips/loongson64/fuloong-2e/irq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/lemote-2f/clock.c b/arch/mips/loongson64/lemote-2f/clock.c
index 462e34d46b4a..a78fb657068c 100644
--- a/arch/mips/loongson64/lemote-2f/clock.c
+++ b/arch/mips/loongson64/lemote-2f/clock.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -15,7 +15,7 @@
 #include <linux/spinlock.h>
 
 #include <asm/clock.h>
-#include <asm/mach-loongson/loongson.h>
+#include <asm/mach-loongson64/loongson.h>
 
 static LIST_HEAD(clock_list);
 static DEFINE_SPINLOCK(clock_lock);
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index 5c21cd3bd339..bf9f1a77f0e5 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -78,55 +78,77 @@ static void hpet_enable_legacy_int(void)
 	/* Do nothing on Loongson-3 */
 }
 
-static void hpet_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int hpet_set_state_periodic(struct clock_event_device *evt)
 {
-	int cfg = 0;
+	int cfg;
 
 	spin_lock(&hpet_lock);
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		pr_info("set clock event to periodic mode!\n");
-		/* stop counter */
-		hpet_stop_counter();
-
-		/* enables the timer0 to generate a periodic interrupt */
-		cfg = hpet_read(HPET_T0_CFG);
-		cfg &= ~HPET_TN_LEVEL;
-		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
-				HPET_TN_SETVAL | HPET_TN_32BIT;
-		hpet_write(HPET_T0_CFG, cfg);
-
-		/* set the comparator */
-		hpet_write(HPET_T0_CMP, HPET_COMPARE_VAL);
-		udelay(1);
-		hpet_write(HPET_T0_CMP, HPET_COMPARE_VAL);
-
-		/* start counter */
-		hpet_start_counter();
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		cfg = hpet_read(HPET_T0_CFG);
-		cfg &= ~HPET_TN_ENABLE;
-		hpet_write(HPET_T0_CFG, cfg);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		pr_info("set clock event to one shot mode!\n");
-		cfg = hpet_read(HPET_T0_CFG);
-		/* set timer0 type
-		 * 1 : periodic interrupt
-		 * 0 : non-periodic(oneshot) interrupt
-		 */
-		cfg &= ~HPET_TN_PERIODIC;
-		cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
-		hpet_write(HPET_T0_CFG, cfg);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		hpet_enable_legacy_int();
-		break;
-	}
+
+	pr_info("set clock event to periodic mode!\n");
+	/* stop counter */
+	hpet_stop_counter();
+
+	/* enables the timer0 to generate a periodic interrupt */
+	cfg = hpet_read(HPET_T0_CFG);
+	cfg &= ~HPET_TN_LEVEL;
+	cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
+		HPET_TN_32BIT;
+	hpet_write(HPET_T0_CFG, cfg);
+
+	/* set the comparator */
+	hpet_write(HPET_T0_CMP, HPET_COMPARE_VAL);
+	udelay(1);
+	hpet_write(HPET_T0_CMP, HPET_COMPARE_VAL);
+
+	/* start counter */
+	hpet_start_counter();
+
+	spin_unlock(&hpet_lock);
+	return 0;
+}
+
+static int hpet_set_state_shutdown(struct clock_event_device *evt)
+{
+	int cfg;
+
+	spin_lock(&hpet_lock);
+
+	cfg = hpet_read(HPET_T0_CFG);
+	cfg &= ~HPET_TN_ENABLE;
+	hpet_write(HPET_T0_CFG, cfg);
+
 	spin_unlock(&hpet_lock);
+	return 0;
+}
+
+static int hpet_set_state_oneshot(struct clock_event_device *evt)
+{
+	int cfg;
+
+	spin_lock(&hpet_lock);
+
+	pr_info("set clock event to one shot mode!\n");
+	cfg = hpet_read(HPET_T0_CFG);
+	/*
+	 * set timer0 type
+	 * 1 : periodic interrupt
+	 * 0 : non-periodic(oneshot) interrupt
+	 */
+	cfg &= ~HPET_TN_PERIODIC;
+	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+	hpet_write(HPET_T0_CFG, cfg);
+
+	spin_unlock(&hpet_lock);
+	return 0;
+}
+
+static int hpet_tick_resume(struct clock_event_device *evt)
+{
+	spin_lock(&hpet_lock);
+	hpet_enable_legacy_int();
+	spin_unlock(&hpet_lock);
+
+	return 0;
 }
 
 static int hpet_next_event(unsigned long delta,
@@ -206,7 +228,10 @@ void __init setup_hpet_timer(void)
 	cd->name = "hpet";
 	cd->rating = 320;
 	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	cd->set_mode = hpet_set_mode;
+	cd->set_state_shutdown = hpet_set_state_shutdown;
+	cd->set_state_periodic = hpet_set_state_periodic;
+	cd->set_state_oneshot = hpet_set_state_oneshot;
+	cd->tick_resume = hpet_tick_resume;
 	cd->set_next_event = hpet_next_event;
 	cd->irq = HPET_T0_IRQ;
 	cd->cpumask = cpumask_of(cpu);
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 12d14ed48778..6f9e010cec4d 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
- *                    Insititute of Computing Technology
+ *                    Institute of Computing Technology
  * Author:  Xiang Gao, gaoxiang@ict.ac.cn
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 509877c6e9d9..1a4738a8f2d3 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -266,8 +266,11 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 
 	if (action & SMP_ASK_C0COUNT) {
 		BUG_ON(cpu != 0);
diff --git a/arch/mips/math-emu/Makefile b/arch/mips/math-emu/Makefile
index 2e5f96275c38..a19641d3ac23 100644
--- a/arch/mips/math-emu/Makefile
+++ b/arch/mips/math-emu/Makefile
@@ -4,9 +4,9 @@
 
 obj-y	+= cp1emu.o ieee754dp.o ieee754sp.o ieee754.o \
 	   dp_div.o dp_mul.o dp_sub.o dp_add.o dp_fsp.o dp_cmp.o dp_simple.o \
-	   dp_tint.o dp_fint.o \
+	   dp_tint.o dp_fint.o dp_maddf.o dp_msubf.o dp_2008class.o dp_fmin.o dp_fmax.o \
 	   sp_div.o sp_mul.o sp_sub.o sp_add.o sp_fdp.o sp_cmp.o sp_simple.o \
-	   sp_tint.o sp_fint.o \
+	   sp_tint.o sp_fint.o sp_maddf.o sp_msubf.o sp_2008class.o sp_fmin.o sp_fmax.o \
 	   dsemul.o
 
 lib-y	+= ieee754d.o \
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 22b9b2cb9219..32f0e19a0d7f 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -451,7 +451,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 			/* Fall through */
 		case jr_op:
 			/* For R6, JR already emulated in jalr_op */
-			if (NO_R6EMU && insn.r_format.opcode == jr_op)
+			if (NO_R6EMU && insn.r_format.func == jr_op)
 				break;
 			*contpc = regs->regs[insn.r_format.rs];
 			return 1;
@@ -551,7 +551,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.next_pc_inc;
 		return 1;
 	case blezl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			break;
 	case blez_op:
 
@@ -588,7 +588,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.next_pc_inc;
 		return 1;
 	case bgtzl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			break;
 	case bgtz_op:
 		/*
@@ -1137,7 +1137,7 @@ emul:
 			break;
 
 		case mfhc_op:
-			if (!cpu_has_mips_r2)
+			if (!cpu_has_mips_r2_r6)
 				goto sigill;
 
 			/* copregister rd -> gpr[rt] */
@@ -1148,7 +1148,7 @@ emul:
 			break;
 
 		case mthc_op:
-			if (!cpu_has_mips_r2)
+			if (!cpu_has_mips_r2_r6)
 				goto sigill;
 
 			/* copregister rd <- gpr[rt] */
@@ -1181,6 +1181,24 @@ emul:
 			}
 			break;
 
+		case bc1eqz_op:
+		case bc1nez_op:
+			if (!cpu_has_mips_r6 || delay_slot(xcp))
+				return SIGILL;
+
+			cond = likely = 0;
+			switch (MIPSInst_RS(ir)) {
+			case bc1eqz_op:
+				if (get_fpr32(&current->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1)
+				    cond = 1;
+				break;
+			case bc1nez_op:
+				if (!(get_fpr32(&current->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1))
+				    cond = 1;
+				break;
+			}
+			goto branch_common;
+
 		case bc_op:
 			if (delay_slot(xcp))
 				return SIGILL;
@@ -1207,7 +1225,7 @@ emul:
 			case bct_op:
 				break;
 			}
-
+branch_common:
 			set_delay_slot(xcp);
 			if (cond) {
 				/*
@@ -1376,6 +1394,14 @@ static const unsigned char cmptab[8] = {
 	IEEE754_CLT | IEEE754_CEQ | IEEE754_CUN,	/* cmp_ule (sig) cmp_ngt */
 };
 
+static const unsigned char negative_cmptab[8] = {
+	0, /* Reserved */
+	IEEE754_CLT | IEEE754_CGT | IEEE754_CEQ,
+	IEEE754_CLT | IEEE754_CGT | IEEE754_CUN,
+	IEEE754_CLT | IEEE754_CGT,
+	/* Reserved */
+};
+
 
 /*
  * Additional MIPS4 instructions
@@ -1717,6 +1743,126 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(rv.s, MIPSInst_FS(ir));
 			break;
 
+		case fseleqz_op:
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(rv.s, MIPSInst_FT(ir));
+			if (rv.w & 0x1)
+				rv.w = 0;
+			else
+				SPFROMREG(rv.s, MIPSInst_FS(ir));
+			break;
+
+		case fselnez_op:
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(rv.s, MIPSInst_FT(ir));
+			if (rv.w & 0x1)
+				SPFROMREG(rv.s, MIPSInst_FS(ir));
+			else
+				rv.w = 0;
+			break;
+
+		case fmaddf_op: {
+			union ieee754sp ft, fs, fd;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(ft, MIPSInst_FT(ir));
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			SPFROMREG(fd, MIPSInst_FD(ir));
+			rv.s = ieee754sp_maddf(fd, fs, ft);
+			break;
+		}
+
+		case fmsubf_op: {
+			union ieee754sp ft, fs, fd;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(ft, MIPSInst_FT(ir));
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			SPFROMREG(fd, MIPSInst_FD(ir));
+			rv.s = ieee754sp_msubf(fd, fs, ft);
+			break;
+		}
+
+		case frint_op: {
+			union ieee754sp fs;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.l = ieee754sp_tlong(fs);
+			rv.s = ieee754sp_flong(rv.l);
+			goto copcsr;
+		}
+
+		case fclass_op: {
+			union ieee754sp fs;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.w = ieee754sp_2008class(fs);
+			rfmt = w_fmt;
+			break;
+		}
+
+		case fmin_op: {
+			union ieee754sp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(ft, MIPSInst_FT(ir));
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.s = ieee754sp_fmin(fs, ft);
+			break;
+		}
+
+		case fmina_op: {
+			union ieee754sp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(ft, MIPSInst_FT(ir));
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.s = ieee754sp_fmina(fs, ft);
+			break;
+		}
+
+		case fmax_op: {
+			union ieee754sp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(ft, MIPSInst_FT(ir));
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.s = ieee754sp_fmax(fs, ft);
+			break;
+		}
+
+		case fmaxa_op: {
+			union ieee754sp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(ft, MIPSInst_FT(ir));
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.s = ieee754sp_fmaxa(fs, ft);
+			break;
+		}
+
 		case fabs_op:
 			handler.u = ieee754sp_abs;
 			goto scopuop;
@@ -1820,7 +1966,7 @@ copcsr:
 			goto copcsr;
 
 		default:
-			if (MIPSInst_FUNC(ir) >= fcmp_op) {
+			if (!NO_R6EMU && MIPSInst_FUNC(ir) >= fcmp_op) {
 				unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op;
 				union ieee754sp fs, ft;
 
@@ -1914,6 +2060,127 @@ copcsr:
 				return 0;
 			DPFROMREG(rv.d, MIPSInst_FS(ir));
 			break;
+
+		case fseleqz_op:
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(rv.d, MIPSInst_FT(ir));
+			if (rv.l & 0x1)
+				rv.l = 0;
+			else
+				DPFROMREG(rv.d, MIPSInst_FS(ir));
+			break;
+
+		case fselnez_op:
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(rv.d, MIPSInst_FT(ir));
+			if (rv.l & 0x1)
+				DPFROMREG(rv.d, MIPSInst_FS(ir));
+			else
+				rv.l = 0;
+			break;
+
+		case fmaddf_op: {
+			union ieee754dp ft, fs, fd;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(ft, MIPSInst_FT(ir));
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			DPFROMREG(fd, MIPSInst_FD(ir));
+			rv.d = ieee754dp_maddf(fd, fs, ft);
+			break;
+		}
+
+		case fmsubf_op: {
+			union ieee754dp ft, fs, fd;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(ft, MIPSInst_FT(ir));
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			DPFROMREG(fd, MIPSInst_FD(ir));
+			rv.d = ieee754dp_msubf(fd, fs, ft);
+			break;
+		}
+
+		case frint_op: {
+			union ieee754dp fs;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.l = ieee754dp_tlong(fs);
+			rv.d = ieee754dp_flong(rv.l);
+			goto copcsr;
+		}
+
+		case fclass_op: {
+			union ieee754dp fs;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.w = ieee754dp_2008class(fs);
+			rfmt = w_fmt;
+			break;
+		}
+
+		case fmin_op: {
+			union ieee754dp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(ft, MIPSInst_FT(ir));
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.d = ieee754dp_fmin(fs, ft);
+			break;
+		}
+
+		case fmina_op: {
+			union ieee754dp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(ft, MIPSInst_FT(ir));
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.d = ieee754dp_fmina(fs, ft);
+			break;
+		}
+
+		case fmax_op: {
+			union ieee754dp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(ft, MIPSInst_FT(ir));
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.d = ieee754dp_fmax(fs, ft);
+			break;
+		}
+
+		case fmaxa_op: {
+			union ieee754dp fs, ft;
+
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(ft, MIPSInst_FT(ir));
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.d = ieee754dp_fmaxa(fs, ft);
+			break;
+		}
+
 		case fabs_op:
 			handler.u = ieee754dp_abs;
 			goto dcopuop;
@@ -1997,7 +2264,7 @@ dcopuop:
 			goto copcsr;
 
 		default:
-			if (MIPSInst_FUNC(ir) >= fcmp_op) {
+			if (!NO_R6EMU && MIPSInst_FUNC(ir) >= fcmp_op) {
 				unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op;
 				union ieee754dp fs, ft;
 
@@ -2021,8 +2288,11 @@ dcopuop:
 			break;
 		}
 		break;
+	}
+
+	case w_fmt: {
+		union ieee754dp fs;
 
-	case w_fmt:
 		switch (MIPSInst_FUNC(ir)) {
 		case fcvts_op:
 			/* convert word to single precision real */
@@ -2036,10 +2306,65 @@ dcopuop:
 			rv.d = ieee754dp_fint(fs.bits);
 			rfmt = d_fmt;
 			goto copcsr;
-		default:
-			return SIGILL;
+		default: {
+			/* Emulating the new CMP.condn.fmt R6 instruction */
+#define CMPOP_MASK	0x7
+#define SIGN_BIT	(0x1 << 3)
+#define PREDICATE_BIT	(0x1 << 4)
+
+			int cmpop = MIPSInst_FUNC(ir) & CMPOP_MASK;
+			int sig = MIPSInst_FUNC(ir) & SIGN_BIT;
+			union ieee754sp fs, ft;
+
+			/* This is an R6 only instruction */
+			if (!cpu_has_mips_r6 ||
+			    (MIPSInst_FUNC(ir) & 0x20))
+				return SIGILL;
+
+			/* fmt is w_fmt for single precision so fix it */
+			rfmt = s_fmt;
+			/* default to false */
+			rv.w = 0;
+
+			/* CMP.condn.S */
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			SPFROMREG(ft, MIPSInst_FT(ir));
+
+			/* positive predicates */
+			if (!(MIPSInst_FUNC(ir) & PREDICATE_BIT)) {
+				if (ieee754sp_cmp(fs, ft, cmptab[cmpop],
+						  sig))
+				    rv.w = -1; /* true, all 1s */
+				if ((sig) &&
+				    ieee754_cxtest(IEEE754_INVALID_OPERATION))
+					rcsr = FPU_CSR_INV_X | FPU_CSR_INV_S;
+				else
+					goto copcsr;
+			} else {
+				/* negative predicates */
+				switch (cmpop) {
+				case 1:
+				case 2:
+				case 3:
+					if (ieee754sp_cmp(fs, ft,
+							  negative_cmptab[cmpop],
+							  sig))
+						rv.w = -1; /* true, all 1s */
+					if (sig &&
+					    ieee754_cxtest(IEEE754_INVALID_OPERATION))
+						rcsr = FPU_CSR_INV_X | FPU_CSR_INV_S;
+					else
+						goto copcsr;
+					break;
+				default:
+					/* Reserved R6 ops */
+					pr_err("Reserved MIPS R6 CMP.condn.S operation\n");
+					return SIGILL;
+				}
+			}
+			break;
+			}
 		}
-		break;
 	}
 
 	case l_fmt:
@@ -2060,11 +2385,60 @@ dcopuop:
 			rv.d = ieee754dp_flong(bits);
 			rfmt = d_fmt;
 			goto copcsr;
-		default:
-			return SIGILL;
-		}
-		break;
+		default: {
+			/* Emulating the new CMP.condn.fmt R6 instruction */
+			int cmpop = MIPSInst_FUNC(ir) & CMPOP_MASK;
+			int sig = MIPSInst_FUNC(ir) & SIGN_BIT;
+			union ieee754dp fs, ft;
+
+			if (!cpu_has_mips_r6 ||
+			    (MIPSInst_FUNC(ir) & 0x20))
+				return SIGILL;
+
+			/* fmt is l_fmt for double precision so fix it */
+			rfmt = d_fmt;
+			/* default to false */
+			rv.l = 0;
 
+			/* CMP.condn.D */
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			DPFROMREG(ft, MIPSInst_FT(ir));
+
+			/* positive predicates */
+			if (!(MIPSInst_FUNC(ir) & PREDICATE_BIT)) {
+				if (ieee754dp_cmp(fs, ft,
+						  cmptab[cmpop], sig))
+				    rv.l = -1LL; /* true, all 1s */
+				if (sig &&
+				    ieee754_cxtest(IEEE754_INVALID_OPERATION))
+					rcsr = FPU_CSR_INV_X | FPU_CSR_INV_S;
+				else
+					goto copcsr;
+			} else {
+				/* negative predicates */
+				switch (cmpop) {
+				case 1:
+				case 2:
+				case 3:
+					if (ieee754dp_cmp(fs, ft,
+							  negative_cmptab[cmpop],
+							  sig))
+						rv.l = -1LL; /* true, all 1s */
+					if (sig &&
+					    ieee754_cxtest(IEEE754_INVALID_OPERATION))
+						rcsr = FPU_CSR_INV_X | FPU_CSR_INV_S;
+					else
+						goto copcsr;
+					break;
+				default:
+					/* Reserved R6 ops */
+					pr_err("Reserved MIPS R6 CMP.condn.D operation\n");
+					return SIGILL;
+				}
+			}
+			break;
+			}
+		}
 	default:
 		return SIGILL;
 	}
diff --git a/arch/mips/math-emu/dp_2008class.c b/arch/mips/math-emu/dp_2008class.c
new file mode 100644
index 000000000000..9dc39fc4835e
--- /dev/null
+++ b/arch/mips/math-emu/dp_2008class.c
@@ -0,0 +1,55 @@
+/*
+ * IEEE754 floating point arithmetic
+ * double precision: CLASS.f
+ * FPR[fd] = class(FPR[fs])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754dp.h"
+
+int ieee754dp_2008class(union ieee754dp x)
+{
+	COMPXDP;
+
+	EXPLODEXDP;
+
+	/*
+	 * 10 bit mask as follows:
+	 *
+	 * bit0 = SNAN
+	 * bit1 = QNAN
+	 * bit2 = -INF
+	 * bit3 = -NORM
+	 * bit4 = -DNORM
+	 * bit5 = -ZERO
+	 * bit6 = INF
+	 * bit7 = NORM
+	 * bit8 = DNORM
+	 * bit9 = ZERO
+	 */
+
+	switch(xc) {
+	case IEEE754_CLASS_SNAN:
+		return 0x01;
+	case IEEE754_CLASS_QNAN:
+		return 0x02;
+	case IEEE754_CLASS_INF:
+		return 0x04 << (xs ? 0 : 4);
+	case IEEE754_CLASS_NORM:
+		return 0x08 << (xs ? 0 : 4);
+	case IEEE754_CLASS_DNORM:
+		return 0x10 << (xs ? 0 : 4);
+	case IEEE754_CLASS_ZERO:
+		return 0x20 << (xs ? 0 : 4);
+	default:
+		pr_err("Unknown class: %d\n", xc);
+		return 0;
+	}
+}
diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c
new file mode 100644
index 000000000000..fd71b8daaaf2
--- /dev/null
+++ b/arch/mips/math-emu/dp_fmax.c
@@ -0,0 +1,213 @@
+/*
+ * IEEE754 floating point arithmetic
+ * double precision: MIN{,A}.f
+ * MIN : Scalar Floating-Point Minimum
+ * MINA: Scalar Floating-Point argument with Minimum Absolute Value
+ *
+ * MIN.D : FPR[fd] = minNum(FPR[fs],FPR[ft])
+ * MINA.D: FPR[fd] = maxNumMag(FPR[fs],FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754dp.h"
+
+union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
+{
+	COMPXDP;
+	COMPYDP;
+
+	EXPLODEXDP;
+	EXPLODEYDP;
+
+	FLUSHXDP;
+	FLUSHYDP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754dp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return xs ? y : x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return ys ? x : y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754dp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		DPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		DPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		DPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & DP_HIDDEN_BIT);
+	assert(ym & DP_HIDDEN_BIT);
+
+	/* Compare signs */
+	if (xs > ys)
+		return y;
+	else if (xs < ys)
+		return x;
+
+	/* Compare exponent */
+	if (xe > ye)
+		return x;
+	else if (xe < ye)
+		return y;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return y;
+	return x;
+}
+
+union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
+{
+	COMPXDP;
+	COMPYDP;
+
+	EXPLODEXDP;
+	EXPLODEYDP;
+
+	FLUSHXDP;
+	FLUSHYDP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754dp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754dp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		DPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		DPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		DPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & DP_HIDDEN_BIT);
+	assert(ym & DP_HIDDEN_BIT);
+
+	/* Compare exponent */
+	if (xe > ye)
+		return x;
+	else if (xe < ye)
+		return y;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return y;
+	return x;
+}
diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c
new file mode 100644
index 000000000000..c1072b0dfb95
--- /dev/null
+++ b/arch/mips/math-emu/dp_fmin.c
@@ -0,0 +1,213 @@
+/*
+ * IEEE754 floating point arithmetic
+ * double precision: MIN{,A}.f
+ * MIN : Scalar Floating-Point Minimum
+ * MINA: Scalar Floating-Point argument with Minimum Absolute Value
+ *
+ * MIN.D : FPR[fd] = minNum(FPR[fs],FPR[ft])
+ * MINA.D: FPR[fd] = maxNumMag(FPR[fs],FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754dp.h"
+
+union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
+{
+	COMPXDP;
+	COMPYDP;
+
+	EXPLODEXDP;
+	EXPLODEYDP;
+
+	FLUSHXDP;
+	FLUSHYDP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754dp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return xs ? x : y;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return ys ? y : x;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754dp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		DPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		DPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		DPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & DP_HIDDEN_BIT);
+	assert(ym & DP_HIDDEN_BIT);
+
+	/* Compare signs */
+	if (xs > ys)
+		return x;
+	else if (xs < ys)
+		return y;
+
+	/* Compare exponent */
+	if (xe > ye)
+		return y;
+	else if (xe < ye)
+		return x;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return x;
+	return y;
+}
+
+union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
+{
+	COMPXDP;
+	COMPYDP;
+
+	EXPLODEXDP;
+	EXPLODEYDP;
+
+	FLUSHXDP;
+	FLUSHYDP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754dp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754dp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		DPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		DPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		DPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & DP_HIDDEN_BIT);
+	assert(ym & DP_HIDDEN_BIT);
+
+	/* Compare exponent */
+	if (xe > ye)
+		return y;
+	else if (xe < ye)
+		return x;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return x;
+	return y;
+}
diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c
new file mode 100644
index 000000000000..119eda9fa1ea
--- /dev/null
+++ b/arch/mips/math-emu/dp_maddf.c
@@ -0,0 +1,265 @@
+/*
+ * IEEE754 floating point arithmetic
+ * double precision: MADDF.f (Fused Multiply Add)
+ * MADDF.fmt: FPR[fd] = FPR[fd] + (FPR[fs] x FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754dp.h"
+
+union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	int re;
+	int rs;
+	u64 rm;
+	unsigned lxm;
+	unsigned hxm;
+	unsigned lym;
+	unsigned hym;
+	u64 lrm;
+	u64 hrm;
+	u64 t;
+	u64 at;
+	int s;
+
+	COMPXDP;
+	COMPYDP;
+
+	u64 zm; int ze; int zs __maybe_unused; int zc;
+
+	EXPLODEXDP;
+	EXPLODEYDP;
+	EXPLODEDP(z, zc, zs, ze, zm)
+
+	FLUSHXDP;
+	FLUSHYDP;
+	FLUSHDP(z, zc, zs, ze, zm);
+
+	ieee754_clearcx();
+
+	switch (zc) {
+	case IEEE754_CLASS_SNAN:
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(z);
+	case IEEE754_CLASS_DNORM:
+		DPDNORMx(zm, ze);
+	/* QNAN is handled separately below */
+	}
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754dp_nanxcpt(x);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return x;
+
+
+	/*
+	 * Infinity handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		return ieee754dp_inf(xs ^ ys);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		/* Multiplication is 0 so just return z */
+		return z;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		DPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		DPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		DPDNORMX;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		/* fall through to real computations */
+	}
+
+	/* Finally get to do some computation */
+
+	/*
+	 * Do the multiplication bit first
+	 *
+	 * rm = xm * ym, re = xe + ye basically
+	 *
+	 * At this point xm and ym should have been normalized.
+	 */
+	assert(xm & DP_HIDDEN_BIT);
+	assert(ym & DP_HIDDEN_BIT);
+
+	re = xe + ye;
+	rs = xs ^ ys;
+
+	/* shunt to top of word */
+	xm <<= 64 - (DP_FBITS + 1);
+	ym <<= 64 - (DP_FBITS + 1);
+
+	/*
+	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 */
+
+	/* 32 * 32 => 64 */
+#define DPXMULT(x, y)	((u64)(x) * (u64)y)
+
+	lxm = xm;
+	hxm = xm >> 32;
+	lym = ym;
+	hym = ym >> 32;
+
+	lrm = DPXMULT(lxm, lym);
+	hrm = DPXMULT(hxm, hym);
+
+	t = DPXMULT(lxm, hym);
+
+	at = lrm + (t << 32);
+	hrm += at < lrm;
+	lrm = at;
+
+	hrm = hrm + (t >> 32);
+
+	t = DPXMULT(hxm, lym);
+
+	at = lrm + (t << 32);
+	hrm += at < lrm;
+	lrm = at;
+
+	hrm = hrm + (t >> 32);
+
+	rm = hrm | (lrm != 0);
+
+	/*
+	 * Sticky shift down to normal rounding precision.
+	 */
+	if ((s64) rm < 0) {
+		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
+		     ((rm << (DP_FBITS + 1 + 3)) != 0);
+			re++;
+	} else {
+		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
+		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
+	}
+	assert(rm & (DP_HIDDEN_BIT << 3));
+
+	/* And now the addition */
+	assert(zm & DP_HIDDEN_BIT);
+
+	/*
+	 * Provide guard,round and stick bit space.
+	 */
+	zm <<= 3;
+
+	if (ze > re) {
+		/*
+		 * Have to shift y fraction right to align.
+		 */
+		s = ze - re;
+		rm = XDPSRS(rm, s);
+		re += s;
+	} else if (re > ze) {
+		/*
+		 * Have to shift x fraction right to align.
+		 */
+		s = re - ze;
+		zm = XDPSRS(zm, s);
+		ze += s;
+	}
+	assert(ze == re);
+	assert(ze <= DP_EMAX);
+
+	if (zs == rs) {
+		/*
+		 * Generate 28 bit result of adding two 27 bit numbers
+		 * leaving result in xm, xs and xe.
+		 */
+		zm = zm + rm;
+
+		if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */
+			zm = XDPSRS1(zm);
+			ze++;
+		}
+	} else {
+		if (zm >= rm) {
+			zm = zm - rm;
+		} else {
+			zm = rm - zm;
+			zs = rs;
+		}
+		if (zm == 0)
+			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
+
+		/*
+		 * Normalize to rounding precision.
+		 */
+		while ((zm >> (DP_FBITS + 3)) == 0) {
+			zm <<= 1;
+			ze--;
+		}
+	}
+
+	return ieee754dp_format(zs, ze, zm);
+}
diff --git a/arch/mips/math-emu/dp_msubf.c b/arch/mips/math-emu/dp_msubf.c
new file mode 100644
index 000000000000..12241262f856
--- /dev/null
+++ b/arch/mips/math-emu/dp_msubf.c
@@ -0,0 +1,269 @@
+/*
+ * IEEE754 floating point arithmetic
+ * double precision: MSUB.f (Fused Multiply Subtract)
+ * MSUBF.fmt: FPR[fd] = FPR[fd] - (FPR[fs] x FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754dp.h"
+
+union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	int re;
+	int rs;
+	u64 rm;
+	unsigned lxm;
+	unsigned hxm;
+	unsigned lym;
+	unsigned hym;
+	u64 lrm;
+	u64 hrm;
+	u64 t;
+	u64 at;
+	int s;
+
+	COMPXDP;
+	COMPYDP;
+
+	u64 zm; int ze; int zs __maybe_unused; int zc;
+
+	EXPLODEXDP;
+	EXPLODEYDP;
+	EXPLODEDP(z, zc, zs, ze, zm)
+
+	FLUSHXDP;
+	FLUSHYDP;
+	FLUSHDP(z, zc, zs, ze, zm);
+
+	ieee754_clearcx();
+
+	switch (zc) {
+	case IEEE754_CLASS_SNAN:
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(z);
+	case IEEE754_CLASS_DNORM:
+		DPDNORMx(zm, ze);
+	/* QNAN is handled separately below */
+	}
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754dp_nanxcpt(x);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return x;
+
+
+	/*
+	 * Infinity handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		return ieee754dp_inf(xs ^ ys);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		/* Multiplication is 0 so just return z */
+		return z;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		DPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		DPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		DPDNORMX;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754dp_inf(zs);
+		/* fall through to real computations */
+	}
+
+	/* Finally get to do some computation */
+
+	/*
+	 * Do the multiplication bit first
+	 *
+	 * rm = xm * ym, re = xe + ye basically
+	 *
+	 * At this point xm and ym should have been normalized.
+	 */
+	assert(xm & DP_HIDDEN_BIT);
+	assert(ym & DP_HIDDEN_BIT);
+
+	re = xe + ye;
+	rs = xs ^ ys;
+
+	/* shunt to top of word */
+	xm <<= 64 - (DP_FBITS + 1);
+	ym <<= 64 - (DP_FBITS + 1);
+
+	/*
+	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 */
+
+	/* 32 * 32 => 64 */
+#define DPXMULT(x, y)	((u64)(x) * (u64)y)
+
+	lxm = xm;
+	hxm = xm >> 32;
+	lym = ym;
+	hym = ym >> 32;
+
+	lrm = DPXMULT(lxm, lym);
+	hrm = DPXMULT(hxm, hym);
+
+	t = DPXMULT(lxm, hym);
+
+	at = lrm + (t << 32);
+	hrm += at < lrm;
+	lrm = at;
+
+	hrm = hrm + (t >> 32);
+
+	t = DPXMULT(hxm, lym);
+
+	at = lrm + (t << 32);
+	hrm += at < lrm;
+	lrm = at;
+
+	hrm = hrm + (t >> 32);
+
+	rm = hrm | (lrm != 0);
+
+	/*
+	 * Sticky shift down to normal rounding precision.
+	 */
+	if ((s64) rm < 0) {
+		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
+		     ((rm << (DP_FBITS + 1 + 3)) != 0);
+			re++;
+	} else {
+		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
+		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
+	}
+	assert(rm & (DP_HIDDEN_BIT << 3));
+
+	/* And now the subtraction */
+
+	/* flip sign of r and handle as add */
+	rs ^= 1;
+
+	assert(zm & DP_HIDDEN_BIT);
+
+	/*
+	 * Provide guard,round and stick bit space.
+	 */
+	zm <<= 3;
+
+	if (ze > re) {
+		/*
+		 * Have to shift y fraction right to align.
+		 */
+		s = ze - re;
+		rm = XDPSRS(rm, s);
+		re += s;
+	} else if (re > ze) {
+		/*
+		 * Have to shift x fraction right to align.
+		 */
+		s = re - ze;
+		zm = XDPSRS(zm, s);
+		ze += s;
+	}
+	assert(ze == re);
+	assert(ze <= DP_EMAX);
+
+	if (zs == rs) {
+		/*
+		 * Generate 28 bit result of adding two 27 bit numbers
+		 * leaving result in xm, xs and xe.
+		 */
+		zm = zm + rm;
+
+		if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */
+			zm = XDPSRS1(zm);
+			ze++;
+		}
+	} else {
+		if (zm >= rm) {
+			zm = zm - rm;
+		} else {
+			zm = rm - zm;
+			zs = rs;
+		}
+		if (zm == 0)
+			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
+
+		/*
+		 * Normalize to rounding precision.
+		 */
+		while ((zm >> (DP_FBITS + 3)) == 0) {
+			zm <<= 1;
+			ze--;
+		}
+	}
+
+	return ieee754dp_format(zs, ze, zm);
+}
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index e0b5cc27d78b..cbb36c14b155 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -33,7 +33,6 @@ struct emuframe {
 
 int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc)
 {
-	extern asmlinkage void handle_dsemulret(void);
 	struct emuframe __user *fr;
 	int err;
 
diff --git a/arch/mips/math-emu/ieee754.h b/arch/mips/math-emu/ieee754.h
index a5ca108ce467..df94720714c7 100644
--- a/arch/mips/math-emu/ieee754.h
+++ b/arch/mips/math-emu/ieee754.h
@@ -75,6 +75,16 @@ int ieee754sp_cmp(union ieee754sp x, union ieee754sp y, int cop, int sig);
 
 union ieee754sp ieee754sp_sqrt(union ieee754sp x);
 
+union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y);
+union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y);
+int ieee754sp_2008class(union ieee754sp x);
+union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y);
+union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y);
+union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y);
+union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y);
+
 /*
  * double precision (often aka double)
 */
@@ -99,6 +109,15 @@ int ieee754dp_cmp(union ieee754dp x, union ieee754dp y, int cop, int sig);
 
 union ieee754dp ieee754dp_sqrt(union ieee754dp x);
 
+union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y);
+union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y);
+int ieee754dp_2008class(union ieee754dp x);
+union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y);
+union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y);
+union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y);
+union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y);
 
 
 /* 5 types of floating point number
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index 05389d5e3a93..6383e2c5c1ad 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -65,8 +65,8 @@ static inline int ieee754_class_nan(int xc)
 			vc = IEEE754_CLASS_INF;				\
 		else if (vm & SP_MBIT(SP_FBITS-1))			\
 			vc = IEEE754_CLASS_SNAN;			\
-	else								\
-		vc = IEEE754_CLASS_QNAN;				\
+		else							\
+			vc = IEEE754_CLASS_QNAN;			\
 	} else if (ve == SP_EMIN-1+SP_EBIAS) {				\
 		if (vm) {						\
 			ve = SP_EMIN;					\
@@ -105,8 +105,8 @@ static inline int ieee754_class_nan(int xc)
 		if (vm) {						\
 			ve = DP_EMIN;					\
 			vc = IEEE754_CLASS_DNORM;			\
-	} else								\
-		vc = IEEE754_CLASS_ZERO;				\
+		} else							\
+			vc = IEEE754_CLASS_ZERO;			\
 	} else {							\
 		ve -= DP_EBIAS;						\
 		vm |= DP_HIDDEN_BIT;					\
diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c
index f308e0f05fc5..506a67a98cdf 100644
--- a/arch/mips/math-emu/me-debugfs.c
+++ b/arch/mips/math-emu/me-debugfs.c
@@ -65,4 +65,4 @@ do {									\
 
 	return 0;
 }
-__initcall(debugfs_fpuemu);
+arch_initcall(debugfs_fpuemu);
diff --git a/arch/mips/math-emu/sp_2008class.c b/arch/mips/math-emu/sp_2008class.c
new file mode 100644
index 000000000000..ff62606a1465
--- /dev/null
+++ b/arch/mips/math-emu/sp_2008class.c
@@ -0,0 +1,55 @@
+/*
+ * IEEE754 floating point arithmetic
+ * single precision: CLASS.f
+ * FPR[fd] = class(FPR[fs])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754sp.h"
+
+int ieee754sp_2008class(union ieee754sp x)
+{
+	COMPXSP;
+
+	EXPLODEXSP;
+
+	/*
+	 * 10 bit mask as follows:
+	 *
+	 * bit0 = SNAN
+	 * bit1 = QNAN
+	 * bit2 = -INF
+	 * bit3 = -NORM
+	 * bit4 = -DNORM
+	 * bit5 = -ZERO
+	 * bit6 = INF
+	 * bit7 = NORM
+	 * bit8 = DNORM
+	 * bit9 = ZERO
+	 */
+
+	switch(xc) {
+	case IEEE754_CLASS_SNAN:
+		return 0x01;
+	case IEEE754_CLASS_QNAN:
+		return 0x02;
+	case IEEE754_CLASS_INF:
+		return 0x04 << (xs ? 0 : 4);
+	case IEEE754_CLASS_NORM:
+		return 0x08 << (xs ? 0 : 4);
+	case IEEE754_CLASS_DNORM:
+		return 0x10 << (xs ? 0 : 4);
+	case IEEE754_CLASS_ZERO:
+		return 0x20 << (xs ? 0 : 4);
+	default:
+		pr_err("Unknown class: %d\n", xc);
+		return 0;
+	}
+}
diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c
new file mode 100644
index 000000000000..4d000844e48e
--- /dev/null
+++ b/arch/mips/math-emu/sp_fmax.c
@@ -0,0 +1,213 @@
+/*
+ * IEEE754 floating point arithmetic
+ * single precision: MAX{,A}.f
+ * MAX : Scalar Floating-Point Maximum
+ * MAXA: Scalar Floating-Point argument with Maximum Absolute Value
+ *
+ * MAX.S : FPR[fd] = maxNum(FPR[fs],FPR[ft])
+ * MAXA.S: FPR[fd] = maxNumMag(FPR[fs],FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754sp.h"
+
+union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
+{
+	COMPXSP;
+	COMPYSP;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+
+	FLUSHXSP;
+	FLUSHYSP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return xs ? y : x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return ys ? x : y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754sp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		SPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	/* Compare signs */
+	if (xs > ys)
+		return y;
+	else if (xs < ys)
+		return x;
+
+	/* Compare exponent */
+	if (xe > ye)
+		return x;
+	else if (xe < ye)
+		return y;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return y;
+	return x;
+}
+
+union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
+{
+	COMPXSP;
+	COMPYSP;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+
+	FLUSHXSP;
+	FLUSHYSP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754sp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		SPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	/* Compare exponent */
+	if (xe > ye)
+		return x;
+	else if (xe < ye)
+		return y;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return y;
+	return x;
+}
diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c
new file mode 100644
index 000000000000..4eb1bb9e9dec
--- /dev/null
+++ b/arch/mips/math-emu/sp_fmin.c
@@ -0,0 +1,213 @@
+/*
+ * IEEE754 floating point arithmetic
+ * single precision: MIN{,A}.f
+ * MIN : Scalar Floating-Point Minimum
+ * MINA: Scalar Floating-Point argument with Minimum Absolute Value
+ *
+ * MIN.S : FPR[fd] = minNum(FPR[fs],FPR[ft])
+ * MINA.S: FPR[fd] = maxNumMag(FPR[fs],FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754sp.h"
+
+union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
+{
+	COMPXSP;
+	COMPYSP;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+
+	FLUSHXSP;
+	FLUSHYSP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return xs ? x : y;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return ys ? y : x;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754sp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		SPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	/* Compare signs */
+	if (xs > ys)
+		return x;
+	else if (xs < ys)
+		return y;
+
+	/* Compare exponent */
+	if (xe > ye)
+		return y;
+	else if (xe < ye)
+		return x;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return x;
+	return y;
+}
+
+union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
+{
+	COMPXSP;
+	COMPYSP;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+
+	FLUSHXSP;
+	FLUSHYSP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754sp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		SPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	/* Compare exponent */
+	if (xe > ye)
+		return y;
+	else if (xe < ye)
+		return x;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return x;
+	return y;
+}
diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c
new file mode 100644
index 000000000000..dd1dd83e34eb
--- /dev/null
+++ b/arch/mips/math-emu/sp_maddf.c
@@ -0,0 +1,255 @@
+/*
+ * IEEE754 floating point arithmetic
+ * single precision: MADDF.f (Fused Multiply Add)
+ * MADDF.fmt: FPR[fd] = FPR[fd] + (FPR[fs] x FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754sp.h"
+
+union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	int re;
+	int rs;
+	unsigned rm;
+	unsigned short lxm;
+	unsigned short hxm;
+	unsigned short lym;
+	unsigned short hym;
+	unsigned lrm;
+	unsigned hrm;
+	unsigned t;
+	unsigned at;
+	int s;
+
+	COMPXSP;
+	COMPYSP;
+	u32 zm; int ze; int zs __maybe_unused; int zc;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+	EXPLODESP(z, zc, zs, ze, zm)
+
+	FLUSHXSP;
+	FLUSHYSP;
+	FLUSHSP(z, zc, zs, ze, zm);
+
+	ieee754_clearcx();
+
+	switch (zc) {
+	case IEEE754_CLASS_SNAN:
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(z);
+	case IEEE754_CLASS_DNORM:
+		SPDNORMx(zm, ze);
+	/* QNAN is handled separately below */
+	}
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return x;
+
+	/*
+	 * Infinity handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		return ieee754sp_inf(xs ^ ys);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		/* Multiplication is 0 so just return z */
+		return z;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		SPDNORMX;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		/* fall through to real computations */
+	}
+
+	/* Finally get to do some computation */
+
+	/*
+	 * Do the multiplication bit first
+	 *
+	 * rm = xm * ym, re = xe + ye basically
+	 *
+	 * At this point xm and ym should have been normalized.
+	 */
+
+	/* rm = xm * ym, re = xe+ye basically */
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	re = xe + ye;
+	rs = xs ^ ys;
+
+	/* shunt to top of word */
+	xm <<= 32 - (SP_FBITS + 1);
+	ym <<= 32 - (SP_FBITS + 1);
+
+	/*
+	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 */
+	lxm = xm & 0xffff;
+	hxm = xm >> 16;
+	lym = ym & 0xffff;
+	hym = ym >> 16;
+
+	lrm = lxm * lym;	/* 16 * 16 => 32 */
+	hrm = hxm * hym;	/* 16 * 16 => 32 */
+
+	t = lxm * hym; /* 16 * 16 => 32 */
+	at = lrm + (t << 16);
+	hrm += at < lrm;
+	lrm = at;
+	hrm = hrm + (t >> 16);
+
+	t = hxm * lym; /* 16 * 16 => 32 */
+	at = lrm + (t << 16);
+	hrm += at < lrm;
+	lrm = at;
+	hrm = hrm + (t >> 16);
+
+	rm = hrm | (lrm != 0);
+
+	/*
+	 * Sticky shift down to normal rounding precision.
+	 */
+	if ((int) rm < 0) {
+		rm = (rm >> (32 - (SP_FBITS + 1 + 3))) |
+		    ((rm << (SP_FBITS + 1 + 3)) != 0);
+		re++;
+	} else {
+		rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
+		     ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
+	}
+	assert(rm & (SP_HIDDEN_BIT << 3));
+
+	/* And now the addition */
+
+	assert(zm & SP_HIDDEN_BIT);
+
+	/*
+	 * Provide guard,round and stick bit space.
+	 */
+	zm <<= 3;
+
+	if (ze > re) {
+		/*
+		 * Have to shift y fraction right to align.
+		 */
+		s = ze - re;
+		SPXSRSYn(s);
+	} else if (re > ze) {
+		/*
+		 * Have to shift x fraction right to align.
+		 */
+		s = re - ze;
+		SPXSRSYn(s);
+	}
+	assert(ze == re);
+	assert(ze <= SP_EMAX);
+
+	if (zs == rs) {
+		/*
+		 * Generate 28 bit result of adding two 27 bit numbers
+		 * leaving result in zm, zs and ze.
+		 */
+		zm = zm + rm;
+
+		if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */
+			SPXSRSX1();
+		}
+	} else {
+		if (zm >= rm) {
+			zm = zm - rm;
+		} else {
+			zm = rm - zm;
+			zs = rs;
+		}
+		if (zm == 0)
+			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
+
+		/*
+		 * Normalize in extended single precision
+		 */
+		while ((zm >> (SP_MBITS + 3)) == 0) {
+			zm <<= 1;
+			ze--;
+		}
+
+	}
+	return ieee754sp_format(zs, ze, zm);
+}
diff --git a/arch/mips/math-emu/sp_msubf.c b/arch/mips/math-emu/sp_msubf.c
new file mode 100644
index 000000000000..81c38b980d69
--- /dev/null
+++ b/arch/mips/math-emu/sp_msubf.c
@@ -0,0 +1,258 @@
+/*
+ * IEEE754 floating point arithmetic
+ * single precision: MSUB.f (Fused Multiply Subtract)
+ * MSUBF.fmt: FPR[fd] = FPR[fd] - (FPR[fs] x FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754sp.h"
+
+union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	int re;
+	int rs;
+	unsigned rm;
+	unsigned short lxm;
+	unsigned short hxm;
+	unsigned short lym;
+	unsigned short hym;
+	unsigned lrm;
+	unsigned hrm;
+	unsigned t;
+	unsigned at;
+	int s;
+
+	COMPXSP;
+	COMPYSP;
+	u32 zm; int ze; int zs __maybe_unused; int zc;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+	EXPLODESP(z, zc, zs, ze, zm)
+
+	FLUSHXSP;
+	FLUSHYSP;
+	FLUSHSP(z, zc, zs, ze, zm);
+
+	ieee754_clearcx();
+
+	switch (zc) {
+	case IEEE754_CLASS_SNAN:
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(z);
+	case IEEE754_CLASS_DNORM:
+		SPDNORMx(zm, ze);
+	/* QNAN is handled separately below */
+	}
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return x;
+
+	/*
+	 * Infinity handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		return ieee754sp_inf(xs ^ ys);
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		/* Multiplication is 0 so just return z */
+		return z;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		SPDNORMX;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
+		if (zc == IEEE754_CLASS_QNAN)
+			return z;
+		else if (zc == IEEE754_CLASS_INF)
+			return ieee754sp_inf(zs);
+		/* fall through to real compuation */
+	}
+
+	/* Finally get to do some computation */
+
+	/*
+	 * Do the multiplication bit first
+	 *
+	 * rm = xm * ym, re = xe + ye basically
+	 *
+	 * At this point xm and ym should have been normalized.
+	 */
+
+	/* rm = xm * ym, re = xe+ye basically */
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	re = xe + ye;
+	rs = xs ^ ys;
+
+	/* shunt to top of word */
+	xm <<= 32 - (SP_FBITS + 1);
+	ym <<= 32 - (SP_FBITS + 1);
+
+	/*
+	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 */
+	lxm = xm & 0xffff;
+	hxm = xm >> 16;
+	lym = ym & 0xffff;
+	hym = ym >> 16;
+
+	lrm = lxm * lym;	/* 16 * 16 => 32 */
+	hrm = hxm * hym;	/* 16 * 16 => 32 */
+
+	t = lxm * hym; /* 16 * 16 => 32 */
+	at = lrm + (t << 16);
+	hrm += at < lrm;
+	lrm = at;
+	hrm = hrm + (t >> 16);
+
+	t = hxm * lym; /* 16 * 16 => 32 */
+	at = lrm + (t << 16);
+	hrm += at < lrm;
+	lrm = at;
+	hrm = hrm + (t >> 16);
+
+	rm = hrm | (lrm != 0);
+
+	/*
+	 * Sticky shift down to normal rounding precision.
+	 */
+	if ((int) rm < 0) {
+		rm = (rm >> (32 - (SP_FBITS + 1 + 3))) |
+		    ((rm << (SP_FBITS + 1 + 3)) != 0);
+		re++;
+	} else {
+		rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
+		     ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
+	}
+	assert(rm & (SP_HIDDEN_BIT << 3));
+
+	/* And now the subtraction */
+
+	/* Flip sign of r and handle as add */
+	rs ^= 1;
+
+	assert(zm & SP_HIDDEN_BIT);
+
+	/*
+	 * Provide guard,round and stick bit space.
+	 */
+	zm <<= 3;
+
+	if (ze > re) {
+		/*
+		 * Have to shift y fraction right to align.
+		 */
+		s = ze - re;
+		SPXSRSYn(s);
+	} else if (re > ze) {
+		/*
+		 * Have to shift x fraction right to align.
+		 */
+		s = re - ze;
+		SPXSRSYn(s);
+	}
+	assert(ze == re);
+	assert(ze <= SP_EMAX);
+
+	if (zs == rs) {
+		/*
+		 * Generate 28 bit result of adding two 27 bit numbers
+		 * leaving result in zm, zs and ze.
+		 */
+		zm = zm + rm;
+
+		if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */
+			SPXSRSX1(); /* shift preserving sticky */
+		}
+	} else {
+		if (zm >= rm) {
+			zm = zm - rm;
+		} else {
+			zm = rm - zm;
+			zs = rs;
+		}
+		if (zm == 0)
+			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
+
+		/*
+		 * Normalize in extended single precision
+		 */
+		while ((zm >> (SP_MBITS + 3)) == 0) {
+			zm <<= 1;
+			ze--;
+		}
+
+	}
+	return ieee754sp_format(zs, ze, zm);
+}
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 7f660dc67596..5d3a25e1cfae 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -37,6 +37,7 @@
 #include <asm/cacheflush.h> /* for run_uncached() */
 #include <asm/traps.h>
 #include <asm/dma-coherence.h>
+#include <asm/mips-cm.h>
 
 /*
  * Special Variant of smp_call_function for use by cache functions:
@@ -51,9 +52,16 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info)
 {
 	preempt_disable();
 
-#ifndef CONFIG_MIPS_MT_SMP
-	smp_call_function(func, info, 1);
-#endif
+	/*
+	 * The Coherent Manager propagates address-based cache ops to other
+	 * cores but not index-based ops. However, r4k_on_each_cpu is used
+	 * in both cases so there is no easy way to tell what kind of op is
+	 * executed to the other cores. The best we can probably do is
+	 * to restrict that call when a CM is not present because both
+	 * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops.
+	 */
+	if (!mips_cm_present())
+		smp_call_function_many(&cpu_foreign_map, func, info, 1);
 	func(info);
 	preempt_enable();
 }
@@ -937,7 +945,9 @@ static void b5k_instruction_hazard(void)
 }
 
 static char *way_string[] = { NULL, "direct mapped", "2-way",
-	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way"
+	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way",
+	"9-way", "10-way", "11-way", "12-way",
+	"13-way", "14-way", "15-way", "16-way",
 };
 
 static void probe_pcache(void)
@@ -1266,6 +1276,7 @@ static void probe_pcache(void)
 	case CPU_PROAPTIV:
 	case CPU_M5150:
 	case CPU_QEMU_GENERIC:
+	case CPU_I6400:
 		if (!(read_c0_config7() & MIPS_CONF7_IAR) &&
 		    (c->icache.waysize > PAGE_SIZE))
 			c->icache.flags |= MIPS_CACHE_ALIASES;
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 77d96db8253c..aab218c36e0d 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -160,18 +160,18 @@ static inline void setup_protection_map(void)
 		protection_map[1]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[2]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[3]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
-		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[5]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[7]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 
 		protection_map[8]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[9]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ);
 		protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE  | _PAGE_NO_READ);
+		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 		protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 
 	} else {
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index eeaf0245c3b1..8f23cf08f4ba 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -194,6 +194,40 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 		__free_pages(page, get_order(size));
 }
 
+static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+	void *cpu_addr, dma_addr_t dma_addr, size_t size,
+	struct dma_attrs *attrs)
+{
+	unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)cpu_addr;
+	unsigned long off = vma->vm_pgoff;
+	unsigned long pfn;
+	int ret = -ENXIO;
+
+	if (!plat_device_is_coherent(dev) && !hw_coherentio)
+		addr = CAC_ADDR(addr);
+
+	pfn = page_to_pfn(virt_to_page((void *)addr));
+
+	if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
 static inline void __dma_sync_virtual(void *addr, size_t size,
 	enum dma_data_direction direction)
 {
@@ -380,6 +414,7 @@ EXPORT_SYMBOL(dma_cache_sync);
 static struct dma_map_ops mips_default_dma_map_ops = {
 	.alloc = mips_dma_alloc_coherent,
 	.free = mips_dma_free_coherent,
+	.mmap = mips_dma_mmap,
 	.map_page = mips_dma_map_page,
 	.unmap_page = mips_dma_unmap_page,
 	.map_sg = mips_dma_map_sg,
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 36c0f26fac6b..4b88fa031891 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -57,12 +57,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 
 #ifdef CONFIG_KPROBES
 	/*
-	 * This is to notify the fault handler of the kprobes.	The
-	 * exception code is redundant as it is also carried in REGS,
-	 * but we pass it anyhow.
+	 * This is to notify the fault handler of the kprobes.
 	 */
 	if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
-		       (regs->cp0_cause >> 2) & 0x1f, SIGSEGV) == NOTIFY_STOP)
+		       current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
 		return;
 #endif
 
@@ -133,7 +131,8 @@ good_area:
 #endif
 				goto bad_area;
 			}
-			if (!(vma->vm_flags & VM_READ)) {
+			if (!(vma->vm_flags & VM_READ) &&
+			    exception_epc(regs) != address) {
 #if 0
 				pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
 					  raw_smp_processor_id(),
@@ -223,6 +222,7 @@ bad_area_nosemaphore:
 			print_vma_addr(" ", regs->regs[31]);
 			pr_info("\n");
 		}
+		current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 		info.si_signo = SIGSEGV;
 		info.si_errno = 0;
 		/* info.si_code has been set above */
@@ -281,6 +281,7 @@ do_sigbus:
 		       field, (unsigned long) regs->cp0_epc,
 		       field, (unsigned long) regs->regs[31]);
 #endif
+	current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 	tsk->thread.cp0_badvaddr = address;
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 198a3147dd7d..66d0f49c5bec 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -37,6 +37,7 @@
 #include <asm/cpu.h>
 #include <asm/dma.h>
 #include <asm/kmap_types.h>
+#include <asm/maar.h>
 #include <asm/mmu_context.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -333,9 +334,40 @@ static inline void mem_init_free_highmem(void)
 #endif
 }
 
-unsigned __weak platform_maar_init(unsigned num_maars)
+unsigned __weak platform_maar_init(unsigned num_pairs)
 {
-	return 0;
+	struct maar_config cfg[BOOT_MEM_MAP_MAX];
+	unsigned i, num_configured, num_cfg = 0;
+	phys_addr_t skip;
+
+	for (i = 0; i < boot_mem_map.nr_map; i++) {
+		switch (boot_mem_map.map[i].type) {
+		case BOOT_MEM_RAM:
+		case BOOT_MEM_INIT_RAM:
+			break;
+		default:
+			continue;
+		}
+
+		skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
+
+		cfg[num_cfg].lower = boot_mem_map.map[i].addr;
+		cfg[num_cfg].lower += skip;
+
+		cfg[num_cfg].upper = cfg[num_cfg].lower;
+		cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
+		cfg[num_cfg].upper -= skip;
+
+		cfg[num_cfg].attrs = MIPS_MAAR_S;
+		num_cfg++;
+	}
+
+	num_configured = maar_config(cfg, num_cfg, num_pairs);
+	if (num_configured < num_cfg)
+		pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
+			num_pairs, num_cfg);
+
+	return num_configured;
 }
 
 static void maar_init(void)
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 4ceafd13870c..53ea8391f9bb 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -14,6 +14,7 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 #include <asm/r4kcache.h>
+#include <asm/mips-cm.h>
 
 /*
  * MIPS32/MIPS64 L2 cache handling
@@ -94,6 +95,38 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 	return 1;
 }
 
+static int __init mips_sc_probe_cm3(void)
+{
+	struct cpuinfo_mips *c = &current_cpu_data;
+	unsigned long cfg = read_gcr_l2_config();
+	unsigned long sets, line_sz, assoc;
+
+	if (cfg & CM_GCR_L2_CONFIG_BYPASS_MSK)
+		return 0;
+
+	sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK;
+	sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF;
+	c->scache.sets = 64 << sets;
+
+	line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK;
+	line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF;
+	c->scache.linesz = 2 << line_sz;
+
+	assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK;
+	assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF;
+	c->scache.ways = assoc + 1;
+	c->scache.waysize = c->scache.sets * c->scache.linesz;
+	c->scache.waybit = __ffs(c->scache.waysize);
+
+	c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
+
+	return 1;
+}
+
+void __weak platform_early_l2_init(void)
+{
+}
+
 static inline int __init mips_sc_probe(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
@@ -103,6 +136,15 @@ static inline int __init mips_sc_probe(void)
 	/* Mark as not present until probe completed */
 	c->scache.flags |= MIPS_CACHE_NOT_PRESENT;
 
+	/*
+	 * Do we need some platform specific probing before
+	 * we configure L2?
+	 */
+	platform_early_l2_init();
+
+	if (mips_cm_revision() >= CM_REV_CM3)
+		return mips_sc_probe_cm3();
+
 	/* Ignore anything but MIPSxx processors */
 	if (!(c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
 			      MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R1 |
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index 2b75b8f880ed..b4f366f7c0f5 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -36,7 +36,7 @@ extern void build_tlb_refill_handler(void);
 		"nop\n\t"		\
 		".set	pop\n\t")
 
-static int r3k_have_wired_reg;			/* Should be in cpu_data? */
+int r3k_have_wired_reg;			/* Should be in cpu_data? */
 
 /* TLB operations. */
 static void local_flush_tlb_from(int entry)
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index cec3e187c48f..53c24784a2f7 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -303,3 +303,10 @@ mips_pci_controller:
 	if (!register_vsmp_smp_ops())
 		return;
 }
+
+void platform_early_l2_init(void)
+{
+	/* L2 configuration lives in the CM3 */
+	if (mips_cm_revision() >= CM_REV_CM3)
+		mips_cm_probe();
+}
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index d1392f8f5811..c6a6c7afddab 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -222,7 +222,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
@@ -382,122 +382,12 @@ void malta_be_init(void)
 	/* Could change CM error mask register. */
 }
 
-
-static char *tr[8] = {
-	"mem",	"gcr",	"gic",	"mmio",
-	"0x04", "0x05", "0x06", "0x07"
-};
-
-static char *mcmd[32] = {
-	[0x00] = "0x00",
-	[0x01] = "Legacy Write",
-	[0x02] = "Legacy Read",
-	[0x03] = "0x03",
-	[0x04] = "0x04",
-	[0x05] = "0x05",
-	[0x06] = "0x06",
-	[0x07] = "0x07",
-	[0x08] = "Coherent Read Own",
-	[0x09] = "Coherent Read Share",
-	[0x0a] = "Coherent Read Discard",
-	[0x0b] = "Coherent Ready Share Always",
-	[0x0c] = "Coherent Upgrade",
-	[0x0d] = "Coherent Writeback",
-	[0x0e] = "0x0e",
-	[0x0f] = "0x0f",
-	[0x10] = "Coherent Copyback",
-	[0x11] = "Coherent Copyback Invalidate",
-	[0x12] = "Coherent Invalidate",
-	[0x13] = "Coherent Write Invalidate",
-	[0x14] = "Coherent Completion Sync",
-	[0x15] = "0x15",
-	[0x16] = "0x16",
-	[0x17] = "0x17",
-	[0x18] = "0x18",
-	[0x19] = "0x19",
-	[0x1a] = "0x1a",
-	[0x1b] = "0x1b",
-	[0x1c] = "0x1c",
-	[0x1d] = "0x1d",
-	[0x1e] = "0x1e",
-	[0x1f] = "0x1f"
-};
-
-static char *core[8] = {
-	"Invalid/OK",	"Invalid/Data",
-	"Shared/OK",	"Shared/Data",
-	"Modified/OK",	"Modified/Data",
-	"Exclusive/OK", "Exclusive/Data"
-};
-
-static char *causes[32] = {
-	"None", "GC_WR_ERR", "GC_RD_ERR", "COH_WR_ERR",
-	"COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07",
-	"0x08", "0x09", "0x0a", "0x0b",
-	"0x0c", "0x0d", "0x0e", "0x0f",
-	"0x10", "0x11", "0x12", "0x13",
-	"0x14", "0x15", "0x16", "INTVN_WR_ERR",
-	"INTVN_RD_ERR", "0x19", "0x1a", "0x1b",
-	"0x1c", "0x1d", "0x1e", "0x1f"
-};
-
 int malta_be_handler(struct pt_regs *regs, int is_fixup)
 {
 	/* This duplicates the handling in do_be which seems wrong */
 	int retval = is_fixup ? MIPS_BE_FIXUP : MIPS_BE_FATAL;
 
-	if (mips_cm_present()) {
-		unsigned long cm_error = read_gcr_error_cause();
-		unsigned long cm_addr = read_gcr_error_addr();
-		unsigned long cm_other = read_gcr_error_mult();
-		unsigned long cause, ocause;
-		char buf[256];
-
-		cause = cm_error & CM_GCR_ERROR_CAUSE_ERRTYPE_MSK;
-		if (cause != 0) {
-			cause >>= CM_GCR_ERROR_CAUSE_ERRTYPE_SHF;
-			if (cause < 16) {
-				unsigned long cca_bits = (cm_error >> 15) & 7;
-				unsigned long tr_bits = (cm_error >> 12) & 7;
-				unsigned long cmd_bits = (cm_error >> 7) & 0x1f;
-				unsigned long stag_bits = (cm_error >> 3) & 15;
-				unsigned long sport_bits = (cm_error >> 0) & 7;
-
-				snprintf(buf, sizeof(buf),
-					 "CCA=%lu TR=%s MCmd=%s STag=%lu "
-					 "SPort=%lu\n",
-					 cca_bits, tr[tr_bits], mcmd[cmd_bits],
-					 stag_bits, sport_bits);
-			} else {
-				/* glob state & sresp together */
-				unsigned long c3_bits = (cm_error >> 18) & 7;
-				unsigned long c2_bits = (cm_error >> 15) & 7;
-				unsigned long c1_bits = (cm_error >> 12) & 7;
-				unsigned long c0_bits = (cm_error >> 9) & 7;
-				unsigned long sc_bit = (cm_error >> 8) & 1;
-				unsigned long cmd_bits = (cm_error >> 3) & 0x1f;
-				unsigned long sport_bits = (cm_error >> 0) & 7;
-				snprintf(buf, sizeof(buf),
-					 "C3=%s C2=%s C1=%s C0=%s SC=%s "
-					 "MCmd=%s SPort=%lu\n",
-					 core[c3_bits], core[c2_bits],
-					 core[c1_bits], core[c0_bits],
-					 sc_bit ? "True" : "False",
-					 mcmd[cmd_bits], sport_bits);
-			}
-
-			ocause = (cm_other & CM_GCR_ERROR_MULT_ERR2ND_MSK) >>
-				 CM_GCR_ERROR_MULT_ERR2ND_SHF;
-
-			pr_err("CM_ERROR=%08lx %s <%s>\n", cm_error,
-			       causes[cause], buf);
-			pr_err("CM_ADDR =%08lx\n", cm_addr);
-			pr_err("CM_OTHER=%08lx %s\n", cm_other, causes[ocause]);
-
-			/* reprime cause register */
-			write_gcr_error_cause(0);
-		}
-	}
+	mips_cm_error_report();
 
 	return retval;
 }
diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c
index b769657be4d4..dadeb8379182 100644
--- a/arch/mips/mti-malta/malta-memory.c
+++ b/arch/mips/mti-malta/malta-memory.c
@@ -179,31 +179,6 @@ void __init prom_free_prom_memory(void)
 	}
 }
 
-unsigned platform_maar_init(unsigned num_pairs)
-{
-	phys_addr_t mem_end = (physical_memsize & ~0xffffull) - 1;
-	struct maar_config cfg[] = {
-		/* DRAM preceding I/O */
-		{ 0x00000000, 0x0fffffff, MIPS_MAAR_S },
-
-		/* DRAM following I/O */
-		{ 0x20000000, mem_end, MIPS_MAAR_S },
-
-		/* DRAM alias in upper half of physical */
-		{ 0x80000000, 0x80000000 + mem_end, MIPS_MAAR_S },
-	};
-	unsigned i, num_cfg = ARRAY_SIZE(cfg);
-
-	/* If DRAM fits before I/O, drop the region following it */
-	if (physical_memsize <= 0x10000000) {
-		num_cfg--;
-		for (i = 1; i < num_cfg; i++)
-			cfg[i] = cfg[i + 1];
-	}
-
-	return maar_config(cfg, num_cfg, num_pairs);
-}
-
 phys_addr_t mips_cdmm_phys_base(void)
 {
 	/* This address is "typically unused" */
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 185e68261f45..b7bf721eabf5 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -119,18 +119,24 @@ void read_persistent_clock(struct timespec *ts)
 
 int get_c0_fdc_int(void)
 {
-	int mips_cpu_fdc_irq;
+	/*
+	 * Some cores claim the FDC is routable through the GIC, but it doesn't
+	 * actually seem to be connected for those Malta bitstreams.
+	 */
+	switch (current_cpu_type()) {
+	case CPU_INTERAPTIV:
+	case CPU_PROAPTIV:
+		return -1;
+	};
 
 	if (cpu_has_veic)
-		mips_cpu_fdc_irq = -1;
+		return -1;
 	else if (gic_present)
-		mips_cpu_fdc_irq = gic_get_c0_fdc_int();
+		return gic_get_c0_fdc_int();
 	else if (cp0_fdc_irq >= 0)
-		mips_cpu_fdc_irq = MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
+		return MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
 	else
-		mips_cpu_fdc_irq = -1;
-
-	return mips_cpu_fdc_irq;
+		return -1;
 }
 
 int get_c0_perfcount_int(void)
@@ -148,6 +154,7 @@ int get_c0_perfcount_int(void)
 
 	return mips_cpu_perf_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
@@ -165,14 +172,17 @@ unsigned int get_c0_compare_int(void)
 
 static void __init init_rtc(void)
 {
-	/* stop the clock whilst setting it up */
-	CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL);
+	unsigned char freq, ctrl;
 
-	/* 32KHz time base */
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
+	/* Set 32KHz time base if not already set */
+	freq = CMOS_READ(RTC_FREQ_SELECT);
+	if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ)
+		CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
 
-	/* start the clock */
-	CMOS_WRITE(RTC_24H, RTC_CONTROL);
+	/* Ensure SET bit is clear so RTC can run */
+	ctrl = CMOS_READ(RTC_CONTROL);
+	if (ctrl & RTC_SET)
+		CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
 }
 
 void __init plat_time_init(void)
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
index e1d69895fb1d..a120b7a5a8fe 100644
--- a/arch/mips/mti-sead3/sead3-time.c
+++ b/arch/mips/mti-sead3/sead3-time.c
@@ -77,6 +77,7 @@ int get_c0_perfcount_int(void)
 		return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
 	return -1;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/netlogic/common/irq.c b/arch/mips/netlogic/common/irq.c
index 5f5d18b0e94d..3660dc67d544 100644
--- a/arch/mips/netlogic/common/irq.c
+++ b/arch/mips/netlogic/common/irq.c
@@ -87,7 +87,7 @@ struct nlm_pic_irq {
 static void xlp_pic_enable(struct irq_data *d)
 {
 	unsigned long flags;
-	struct nlm_pic_irq *pd = irq_data_get_irq_handler_data(d);
+	struct nlm_pic_irq *pd = irq_data_get_irq_chip_data(d);
 
 	BUG_ON(!pd);
 	spin_lock_irqsave(&pd->node->piclock, flags);
@@ -97,7 +97,7 @@ static void xlp_pic_enable(struct irq_data *d)
 
 static void xlp_pic_disable(struct irq_data *d)
 {
-	struct nlm_pic_irq *pd = irq_data_get_irq_handler_data(d);
+	struct nlm_pic_irq *pd = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
 	BUG_ON(!pd);
@@ -108,7 +108,7 @@ static void xlp_pic_disable(struct irq_data *d)
 
 static void xlp_pic_mask_ack(struct irq_data *d)
 {
-	struct nlm_pic_irq *pd = irq_data_get_irq_handler_data(d);
+	struct nlm_pic_irq *pd = irq_data_get_irq_chip_data(d);
 
 	clear_c0_eimr(pd->picirq);
 	ack_c0_eirr(pd->picirq);
@@ -116,7 +116,7 @@ static void xlp_pic_mask_ack(struct irq_data *d)
 
 static void xlp_pic_unmask(struct irq_data *d)
 {
-	struct nlm_pic_irq *pd = irq_data_get_irq_handler_data(d);
+	struct nlm_pic_irq *pd = irq_data_get_irq_chip_data(d);
 
 	BUG_ON(!pd);
 
@@ -193,7 +193,7 @@ void nlm_setup_pic_irq(int node, int picirq, int irq, int irt)
 	pic_data->picirq = picirq;
 	pic_data->node = nlm_get_node(node);
 	irq_set_chip_and_handler(xirq, &xlp_pic, handle_level_irq);
-	irq_set_handler_data(xirq, pic_data);
+	irq_set_chip_data(xirq, pic_data);
 }
 
 void nlm_set_pic_extra_ack(int node, int irq, void (*xack)(struct irq_data *))
@@ -202,7 +202,7 @@ void nlm_set_pic_extra_ack(int node, int irq, void (*xack)(struct irq_data *))
 	int xirq;
 
 	xirq = nlm_irq_to_xirq(node, irq);
-	pic_data = irq_get_handler_data(xirq);
+	pic_data = irq_get_chip_data(xirq);
 	if (WARN_ON(!pic_data))
 		return;
 	pic_data->extra_ack = xack;
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index dc3e327fbbac..0136b4f9c9cd 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -82,17 +82,19 @@ void nlm_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 }
 
 /* IRQ_IPI_SMP_FUNCTION Handler */
-void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc)
+void nlm_smp_function_ipi_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	clear_c0_eimr(irq);
 	ack_c0_eirr(irq);
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	set_c0_eimr(irq);
 }
 
 /* IRQ_IPI_SMP_RESCHEDULE  handler */
-void nlm_smp_resched_ipi_handler(unsigned int irq, struct irq_desc *desc)
+void nlm_smp_resched_ipi_handler(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	clear_c0_eimr(irq);
 	ack_c0_eirr(irq);
 	scheduler_ipi();
diff --git a/arch/mips/netlogic/xlp/ahci-init-xlp2.c b/arch/mips/netlogic/xlp/ahci-init-xlp2.c
index 7b066a44e679..c11b9c7dc7c8 100644
--- a/arch/mips/netlogic/xlp/ahci-init-xlp2.c
+++ b/arch/mips/netlogic/xlp/ahci-init-xlp2.c
@@ -152,7 +152,7 @@ static const u8 sata_phy_config1[]  = {
 	0xC9, 0xC9, 0x07, 0x07, 0x18, 0x18, 0x01, 0x01, 0x22, 0x00
 };
 
-/* SATA PHY config for register block 2 0x0x8065 .. 0x0x80A4 */
+/* SATA PHY config for register block 2 0x8065 .. 0x80A4 */
 static const u8 sata_phy_config2[]  = {
 	0xAA, 0x00, 0x4C, 0xC9, 0xC9, 0x07, 0x07, 0x18,
 	0x18, 0x05, 0x0C, 0x10, 0x00, 0x10, 0x00, 0xFF,
diff --git a/arch/mips/netlogic/xlp/nlm_hal.c b/arch/mips/netlogic/xlp/nlm_hal.c
index a8f4144a0297..80ec929747c3 100644
--- a/arch/mips/netlogic/xlp/nlm_hal.c
+++ b/arch/mips/netlogic/xlp/nlm_hal.c
@@ -91,6 +91,8 @@ static int xlp9xx_irq_to_irt(int irq)
 		return 134;
 	case PIC_SATA_IRQ:
 		return 143;
+	case PIC_NAND_IRQ:
+		return 151;
 	case PIC_SPI_IRQ:
 		return 152;
 	case PIC_MMC_IRQ:
diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c
index 81f58958cf08..3c9ec3ddca84 100644
--- a/arch/mips/oprofile/common.c
+++ b/arch/mips/oprofile/common.c
@@ -91,6 +91,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	case CPU_INTERAPTIV:
 	case CPU_PROAPTIV:
 	case CPU_P5600:
+	case CPU_I6400:
 	case CPU_M5150:
 	case CPU_LOONGSON1:
 	case CPU_SB1:
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index 6a6e2cc55b89..8f988a61b7a8 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -392,6 +392,10 @@ static int __init mipsxx_init(void)
 		op_model_mipsxx_ops.cpu_type = "mips/P5600";
 		break;
 
+	case CPU_I6400:
+		op_model_mipsxx_ops.cpu_type = "mips/I6400";
+		break;
+
 	case CPU_M5150:
 		op_model_mipsxx_ops.cpu_type = "mips/M5150";
 		break;
diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c
index 42181c7105df..f8d3e081b2eb 100644
--- a/arch/mips/paravirt/paravirt-smp.c
+++ b/arch/mips/paravirt/paravirt-smp.c
@@ -114,7 +114,7 @@ static irqreturn_t paravirt_reched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index cffaaf4aae3c..2a5bb849b10e 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -200,7 +200,7 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		ret = arch_setup_msi_irq(dev, entry);
 		if (ret < 0)
 			return ret;
diff --git a/arch/mips/pci/msi-xlp.c b/arch/mips/pci/msi-xlp.c
index 3407495fcbe2..bb14335f804b 100644
--- a/arch/mips/pci/msi-xlp.c
+++ b/arch/mips/pci/msi-xlp.c
@@ -131,7 +131,7 @@ struct xlp_msi_data {
  */
 static void xlp_msi_enable(struct irq_data *d)
 {
-	struct xlp_msi_data *md = irq_data_get_irq_handler_data(d);
+	struct xlp_msi_data *md = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 	int vec;
 
@@ -148,7 +148,7 @@ static void xlp_msi_enable(struct irq_data *d)
 
 static void xlp_msi_disable(struct irq_data *d)
 {
-	struct xlp_msi_data *md = irq_data_get_irq_handler_data(d);
+	struct xlp_msi_data *md = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 	int vec;
 
@@ -165,7 +165,7 @@ static void xlp_msi_disable(struct irq_data *d)
 
 static void xlp_msi_mask_ack(struct irq_data *d)
 {
-	struct xlp_msi_data *md = irq_data_get_irq_handler_data(d);
+	struct xlp_msi_data *md = irq_data_get_irq_chip_data(d);
 	int link, vec;
 
 	link = nlm_irq_msilink(d->irq);
@@ -211,7 +211,7 @@ static void xlp_msix_mask_ack(struct irq_data *d)
 	msixvec = nlm_irq_msixvec(d->irq);
 	link = nlm_irq_msixlink(msixvec);
 	pci_msi_mask_irq(d);
-	md = irq_data_get_irq_handler_data(d);
+	md = irq_data_get_irq_chip_data(d);
 
 	/* Ack MSI on bridge */
 	if (cpu_is_xlp9xx()) {
@@ -302,7 +302,7 @@ static int xlp_setup_msi(uint64_t lnkbase, int node, int link,
 	/* Get MSI data for the link */
 	lirq = PIC_PCIE_LINK_MSI_IRQ(link);
 	xirq = nlm_irq_to_xirq(node, nlm_link_msiirq(link, 0));
-	md = irq_get_handler_data(xirq);
+	md = irq_get_chip_data(xirq);
 	msiaddr = MSI_LINK_ADDR(node, link);
 
 	spin_lock_irqsave(&md->msi_lock, flags);
@@ -409,7 +409,7 @@ static int xlp_setup_msix(uint64_t lnkbase, int node, int link,
 	/* Get MSI data for the link */
 	lirq = PIC_PCIE_MSIX_IRQ(link);
 	xirq = nlm_irq_to_xirq(node, nlm_link_msixirq(link, 0));
-	md = irq_get_handler_data(xirq);
+	md = irq_get_chip_data(xirq);
 	msixaddr = MSIX_LINK_ADDR(node, link);
 
 	spin_lock_irqsave(&md->msi_lock, flags);
@@ -485,7 +485,7 @@ void __init xlp_init_node_msi_irqs(int node, int link)
 	irq = nlm_irq_to_xirq(node, nlm_link_msiirq(link, 0));
 	for (i = irq; i < irq + XLP_MSIVEC_PER_LINK; i++) {
 		irq_set_chip_and_handler(i, &xlp_msi_chip, handle_level_irq);
-		irq_set_handler_data(i, md);
+		irq_set_chip_data(i, md);
 	}
 
 	for (i = 0; i < XLP_MSIXVEC_PER_LINK ; i++) {
@@ -508,7 +508,7 @@ void __init xlp_init_node_msi_irqs(int node, int link)
 		/* Initialize MSI-X extended irq space for the link  */
 		irq = nlm_irq_to_xirq(node, nlm_link_msixirq(link, i));
 		irq_set_chip_and_handler(irq, &xlp_msix_chip, handle_level_irq);
-		irq_set_handler_data(irq, md);
+		irq_set_chip_data(irq, md);
 	}
 }
 
@@ -520,7 +520,7 @@ void nlm_dispatch_msi(int node, int lirq)
 
 	link = lirq - PIC_PCIE_LINK_MSI_IRQ_BASE;
 	irqbase = nlm_irq_to_xirq(node, nlm_link_msiirq(link, 0));
-	md = irq_get_handler_data(irqbase);
+	md = irq_get_chip_data(irqbase);
 	if (cpu_is_xlp9xx())
 		status = nlm_read_reg(md->lnkbase, PCIE_9XX_MSI_STATUS) &
 						md->msi_enabled_mask;
@@ -550,7 +550,7 @@ void nlm_dispatch_msix(int node, int lirq)
 
 	link = lirq - PIC_PCIE_MSIX_IRQ_BASE;
 	irqbase = nlm_irq_to_xirq(node, nlm_link_msixirq(link, 0));
-	md = irq_get_handler_data(irqbase);
+	md = irq_get_chip_data(irqbase);
 	if (cpu_is_xlp9xx())
 		status = nlm_read_reg(md->lnkbase, PCIE_9XX_MSIX_STATUSX(link));
 	else
diff --git a/arch/mips/pci/ops-emma2rh.c b/arch/mips/pci/ops-emma2rh.c
index 710aef5c070e..2dc97c45685e 100644
--- a/arch/mips/pci/ops-emma2rh.c
+++ b/arch/mips/pci/ops-emma2rh.c
@@ -25,7 +25,6 @@
 #include <linux/types.h>
 
 #include <asm/addrspace.h>
-#include <asm/debug.h>
 
 #include <asm/emma/emma2rh.h>
 
@@ -40,10 +39,9 @@
 static int check_args(struct pci_bus *bus, u32 devfn, u32 * bus_num)
 {
 	/* check if the bus is top-level */
-	if (bus->parent != NULL) {
+	if (bus->parent != NULL)
 		*bus_num = bus->number;
-		db_assert(bus_num != NULL);
-	} else
+	else
 		*bus_num = 0;
 
 	if (*bus_num == 0) {
diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c
index 283157f8dc64..ad35a5e6a56c 100644
--- a/arch/mips/pci/pci-ar71xx.c
+++ b/arch/mips/pci/pci-ar71xx.c
@@ -312,8 +312,8 @@ static void ar71xx_pci_irq_init(struct ar71xx_pci_controller *apc)
 		irq_set_chip_data(i, apc);
 	}
 
-	irq_set_handler_data(apc->irq, apc);
-	irq_set_chained_handler(apc->irq, ar71xx_pci_irq_handler);
+	irq_set_chained_handler_and_data(apc->irq, ar71xx_pci_irq_handler,
+					 apc);
 }
 
 static void ar71xx_pci_reset(void)
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 0af362b5af92..907d11dd921b 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -321,8 +321,8 @@ static void ar724x_pci_irq_init(struct ar724x_pci_controller *apc,
 		irq_set_chip_data(i, apc);
 	}
 
-	irq_set_handler_data(apc->irq, apc);
-	irq_set_chained_handler(apc->irq, ar724x_pci_irq_handler);
+	irq_set_chained_handler_and_data(apc->irq, ar724x_pci_irq_handler,
+					 apc);
 }
 
 static int ar724x_pci_probe(struct platform_device *pdev)
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index c5347d99cf3a..6a15dbd085aa 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -20,7 +20,6 @@
 #include <linux/of_irq.h>
 #include <linux/of_pci.h>
 
-#include <asm/gpio.h>
 #include <asm/addrspace.h>
 
 #include <lantiq_soc.h>
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 80fafe646e74..53c8efaf1572 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -129,7 +129,7 @@ static void rt3883_pci_write_cfg32(struct rt3883_pci_controller *rpc,
 	rt3883_pci_w32(rpc, val, RT3883_PCI_REG_CFGDATA);
 }
 
-static void rt3883_pci_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void rt3883_pci_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
 	struct rt3883_pci_controller *rpc;
 	u32 pending;
@@ -145,7 +145,7 @@ static void rt3883_pci_irq_handler(unsigned int irq, struct irq_desc *desc)
 	}
 
 	while (pending) {
-		unsigned bit = __ffs(pending);
+		unsigned irq, bit = __ffs(pending);
 
 		irq = irq_find_mapping(rpc->irq_domain, bit);
 		generic_handle_irq(irq);
@@ -225,8 +225,7 @@ static int rt3883_pci_irq_init(struct device *dev,
 		return -ENODEV;
 	}
 
-	irq_set_handler_data(irq, rpc);
-	irq_set_chained_handler(irq, rt3883_pci_irq_handler);
+	irq_set_chained_handler_and_data(irq, rt3883_pci_irq_handler, rpc);
 
 	return 0;
 }
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index b8a0bf5766f2..c6996cf67a5c 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -311,12 +311,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	struct pci_dev *dev = bus->self;
-
-	if (pci_has_flag(PCI_PROBE_ONLY) && dev &&
-	    (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
-		pci_read_bridge_bases(bus);
-	}
 }
 
 EXPORT_SYMBOL(PCIBIOS_MIN_IO);
diff --git a/arch/mips/pistachio/Kconfig b/arch/mips/pistachio/Kconfig
new file mode 100644
index 000000000000..97731ea94322
--- /dev/null
+++ b/arch/mips/pistachio/Kconfig
@@ -0,0 +1,13 @@
+config PISTACHIO_GPTIMER_CLKSRC
+	bool "Enable General Purpose Timer based clocksource"
+	depends on MACH_PISTACHIO
+	select CLKSRC_PISTACHIO
+	select MIPS_EXTERNAL_TIMER
+	help
+	  This option enables a clocksource driver based on a Pistachio
+	  SoC General Purpose external timer.
+
+	  If you want to enable the CPUFreq, you need to enable
+	  this option.
+
+	  If you don't want to enable CPUFreq, you can leave this disabled.
diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c
index d2dc836523a3..8bd8ebb20a72 100644
--- a/arch/mips/pistachio/init.c
+++ b/arch/mips/pistachio/init.c
@@ -63,13 +63,19 @@ void __init plat_mem_setup(void)
 	plat_setup_iocoherency();
 }
 
-#define DEFAULT_CPC_BASE_ADDR 0x1bde0000
+#define DEFAULT_CPC_BASE_ADDR	0x1bde0000
+#define DEFAULT_CDMM_BASE_ADDR	0x1bdd0000
 
 phys_addr_t mips_cpc_default_phys_base(void)
 {
 	return DEFAULT_CPC_BASE_ADDR;
 }
 
+phys_addr_t mips_cdmm_phys_base(void)
+{
+	return DEFAULT_CDMM_BASE_ADDR;
+}
+
 static void __init mips_nmi_setup(void)
 {
 	void *base;
diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c
index 67889fcea8aa..8a377346f0ca 100644
--- a/arch/mips/pistachio/time.c
+++ b/arch/mips/pistachio/time.c
@@ -26,6 +26,12 @@ int get_c0_perfcount_int(void)
 {
 	return gic_get_c0_perfcount_int();
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
+
+int get_c0_fdc_int(void)
+{
+	return gic_get_c0_fdc_int();
+}
 
 void __init plat_time_init(void)
 {
diff --git a/arch/mips/pmcs-msp71xx/msp_irq_cic.c b/arch/mips/pmcs-msp71xx/msp_irq_cic.c
index 1207ec4dfb77..8b9cf6463040 100644
--- a/arch/mips/pmcs-msp71xx/msp_irq_cic.c
+++ b/arch/mips/pmcs-msp71xx/msp_irq_cic.c
@@ -88,7 +88,8 @@ static void unmask_cic_irq(struct irq_data *d)
 	* Make sure we have IRQ affinity.  It may have changed while
 	* we were processing the IRQ.
 	*/
-	if (!cpumask_test_cpu(smp_processor_id(), d->affinity))
+	if (!cpumask_test_cpu(smp_processor_id(),
+			      irq_data_get_affinity_mask(d)))
 		return;
 #endif
 
diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c
index 10170580a2de..ffa0f7101a97 100644
--- a/arch/mips/pmcs-msp71xx/msp_smp.c
+++ b/arch/mips/pmcs-msp71xx/msp_smp.c
@@ -44,7 +44,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/ralink/cevt-rt3352.c b/arch/mips/ralink/cevt-rt3352.c
index 24bf057a3613..a8e70a9f274b 100644
--- a/arch/mips/ralink/cevt-rt3352.c
+++ b/arch/mips/ralink/cevt-rt3352.c
@@ -36,8 +36,8 @@ struct systick_device {
 	int freq_scale;
 };
 
-static void systick_set_clock_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt);
+static int systick_set_oneshot(struct clock_event_device *evt);
+static int systick_shutdown(struct clock_event_device *evt);
 
 static int systick_next_event(unsigned long delta,
 				struct clock_event_device *evt)
@@ -73,11 +73,12 @@ static struct systick_device systick = {
 		 * cevt-r4k uses 300, make sure systick
 		 * gets used if available
 		 */
-		.rating		= 310,
-		.features	= CLOCK_EVT_FEAT_ONESHOT,
-		.set_next_event	= systick_next_event,
-		.set_mode	= systick_set_clock_mode,
-		.event_handler	= systick_event_handler,
+		.rating			= 310,
+		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.set_next_event		= systick_next_event,
+		.set_state_shutdown	= systick_shutdown,
+		.set_state_oneshot	= systick_set_oneshot,
+		.event_handler		= systick_event_handler,
 	},
 };
 
@@ -87,33 +88,33 @@ static struct irqaction systick_irqaction = {
 	.dev_id = &systick.dev,
 };
 
-static void systick_set_clock_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int systick_shutdown(struct clock_event_device *evt)
 {
 	struct systick_device *sdev;
 
 	sdev = container_of(evt, struct systick_device, dev);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		if (!sdev->irq_requested)
-			setup_irq(systick.dev.irq, &systick_irqaction);
-		sdev->irq_requested = 1;
-		iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN,
-				systick.membase + SYSTICK_CONFIG);
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		if (sdev->irq_requested)
-			free_irq(systick.dev.irq, &systick_irqaction);
-		sdev->irq_requested = 0;
-		iowrite32(0, systick.membase + SYSTICK_CONFIG);
-		break;
-
-	default:
-		pr_err("%s: Unhandeled mips clock_mode\n", systick.dev.name);
-		break;
-	}
+	if (sdev->irq_requested)
+		free_irq(systick.dev.irq, &systick_irqaction);
+	sdev->irq_requested = 0;
+	iowrite32(0, systick.membase + SYSTICK_CONFIG);
+
+	return 0;
+}
+
+static int systick_set_oneshot(struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+
+	sdev = container_of(evt, struct systick_device, dev);
+
+	if (!sdev->irq_requested)
+		setup_irq(systick.dev.irq, &systick_irqaction);
+	sdev->irq_requested = 1;
+	iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN,
+		  systick.membase + SYSTICK_CONFIG);
+
+	return 0;
 }
 
 static void __init ralink_systick_init(struct device_node *np)
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 53707aacc0f8..8c624a8b9ea2 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -89,6 +89,7 @@ int get_c0_perfcount_int(void)
 {
 	return rt_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c
index e31e8cdcb296..9bd7a2de0765 100644
--- a/arch/mips/rb532/devices.c
+++ b/arch/mips/rb532/devices.c
@@ -23,6 +23,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
+#include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 #include <linux/serial_8250.h>
diff --git a/arch/mips/rb532/gpio.c b/arch/mips/rb532/gpio.c
index 5aa3df853082..650d5d39f34d 100644
--- a/arch/mips/rb532/gpio.c
+++ b/arch/mips/rb532/gpio.c
@@ -140,6 +140,11 @@ static int rb532_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
+static int rb532_gpio_to_irq(struct gpio_chip *chip, unsigned gpio)
+{
+	return 8 + 4 * 32 + gpio;
+}
+
 static struct rb532_gpio_chip rb532_gpio_chip[] = {
 	[0] = {
 		.chip = {
@@ -148,6 +153,7 @@ static struct rb532_gpio_chip rb532_gpio_chip[] = {
 			.direction_output	= rb532_gpio_direction_output,
 			.get			= rb532_gpio_get,
 			.set			= rb532_gpio_set,
+			.to_irq			= rb532_gpio_to_irq,
 			.base			= 0,
 			.ngpio			= 32,
 		},
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 3fbaef97a1b8..16ec4e12daa3 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -107,10 +107,14 @@ static void ip27_do_irq_mask0(void)
 		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else if (pend0 & (1UL << CPU_CALL_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_B_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else
 #endif
 	{
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index a6d10f607f34..42d6cb9f956e 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -64,12 +64,6 @@ static int rt_next_event(unsigned long delta, struct clock_event_device *evt)
 	return LOCAL_HUB_L(PI_RT_COUNT) >= cnt ? -ETIME : 0;
 }
 
-static void rt_set_mode(enum clock_event_mode mode,
-		struct clock_event_device *evt)
-{
-	/* Nothing to do ...  */
-}
-
 unsigned int rt_timer_irq;
 
 static DEFINE_PER_CPU(struct clock_event_device, hub_rt_clockevent);
@@ -124,7 +118,6 @@ void hub_rt_clock_event_init(void)
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= rt_next_event;
-	cd->set_mode		= rt_set_mode;
 	clockevents_register_device(cd);
 }
 
diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig
index a8bb972fd9fd..cb9a095f5c5e 100644
--- a/arch/mips/sibyte/Kconfig
+++ b/arch/mips/sibyte/Kconfig
@@ -81,11 +81,6 @@ choice
 	prompt "SiByte SOC Stepping"
 	depends on SIBYTE_SB1xxx_SOC
 
-config CPU_SB1_PASS_1
-	bool "1250 Pass1"
-	depends on SIBYTE_SB1250
-	select CPU_HAS_PREFETCH
-
 config CPU_SB1_PASS_2_1250
 	bool "1250 An"
 	depends on SIBYTE_SB1250
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index af7d44edd9a8..4c71aea25663 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -29,8 +29,6 @@
 #include <asm/sibyte/bcm1480_regs.h>
 #include <asm/sibyte/bcm1480_int.h>
 
-extern void smp_call_function_interrupt(void);
-
 /*
  * These are routines for dealing with the bcm1480 smp capabilities
  * independent of board/firmware
@@ -184,6 +182,9 @@ void bcm1480_mailbox_interrupt(void)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }
diff --git a/arch/mips/sibyte/common/bus_watcher.c b/arch/mips/sibyte/common/bus_watcher.c
index 5581844c9194..a4e55999ecb4 100644
--- a/arch/mips/sibyte/common/bus_watcher.c
+++ b/arch/mips/sibyte/common/bus_watcher.c
@@ -81,10 +81,7 @@ void check_bus_watcher(void)
 {
 	u32 status, l2_err, memio_err;
 
-#ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-	/* Destructive read, clears register and interrupt */
-	status = csr_in32(IOADDR(A_SCD_BUS_ERR_STATUS));
-#elif defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250)
+#if defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250)
 	/* Use non-destructive register */
 	status = csr_in32(IOADDR(A_SCD_BUS_ERR_STATUS_DEBUG));
 #elif defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80)
@@ -253,4 +250,4 @@ int __init sibyte_bus_watcher(void)
 	return 0;
 }
 
-__initcall(sibyte_bus_watcher);
+device_initcall(sibyte_bus_watcher);
diff --git a/arch/mips/sibyte/sb1250/setup.c b/arch/mips/sibyte/sb1250/setup.c
index 3c02b2a77ae9..9d3c24efdf4a 100644
--- a/arch/mips/sibyte/sb1250/setup.c
+++ b/arch/mips/sibyte/sb1250/setup.c
@@ -202,12 +202,10 @@ void __init sb1250_setup(void)
 
 	switch (war_pass) {
 	case K_SYS_REVISION_BCM1250_PASS1:
-#ifndef CONFIG_SB1_PASS_1_WORKAROUNDS
 		printk("@@@@ This is a BCM1250 A0-A2 (Pass 1) board, "
 			    "and the kernel doesn't have the proper "
 			    "workarounds compiled in. @@@@\n");
 		bad_config = 1;
-#endif
 		break;
 	case K_SYS_REVISION_BCM1250_PASS2:
 		/* Pass 2 - easiest as default for now - so many numbers */
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index c0c4b3f88a08..1cf66f5ff23d 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -172,6 +172,9 @@ void sb1250_mailbox_interrupt(void)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }
diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c
index cf8ec568b9df..fb4b3520cdc6 100644
--- a/arch/mips/sni/time.c
+++ b/arch/mips/sni/time.c
@@ -14,44 +14,33 @@
 #define SNI_COUNTER2_DIV	64
 #define SNI_COUNTER0_DIV	((SNI_CLOCK_TICK_RATE / SNI_COUNTER2_DIV) / HZ)
 
-static void a20r_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt)
+static int a20r_set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		*(volatile u8 *)(A20R_PT_CLOCK_BASE + 12) = 0x34;
-		wmb();
-		*(volatile u8 *)(A20R_PT_CLOCK_BASE +  0) = SNI_COUNTER0_DIV;
-		wmb();
-		*(volatile u8 *)(A20R_PT_CLOCK_BASE +  0) = SNI_COUNTER0_DIV >> 8;
-		wmb();
-
-		*(volatile u8 *)(A20R_PT_CLOCK_BASE + 12) = 0xb4;
-		wmb();
-		*(volatile u8 *)(A20R_PT_CLOCK_BASE +  8) = SNI_COUNTER2_DIV;
-		wmb();
-		*(volatile u8 *)(A20R_PT_CLOCK_BASE +  8) = SNI_COUNTER2_DIV >> 8;
-		wmb();
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 12) = 0x34;
+	wmb();
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 0) = SNI_COUNTER0_DIV;
+	wmb();
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 0) = SNI_COUNTER0_DIV >> 8;
+	wmb();
 
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 12) = 0xb4;
+	wmb();
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 8) = SNI_COUNTER2_DIV;
+	wmb();
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 8) = SNI_COUNTER2_DIV >> 8;
+	wmb();
+	return 0;
 }
 
 static struct clock_event_device a20r_clockevent_device = {
-	.name		= "a20r-timer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC,
+	.name			= "a20r-timer",
+	.features		= CLOCK_EVT_FEAT_PERIODIC,
 
 	/* .mult, .shift, .max_delta_ns and .min_delta_ns left uninitialized */
 
-	.rating		= 300,
-	.irq		= SNI_A20R_IRQ_TIMER,
-	.set_mode	= a20r_set_mode,
+	.rating			= 300,
+	.irq			= SNI_A20R_IRQ_TIMER,
+	.set_state_periodic	= a20r_set_periodic,
 };
 
 static irqreturn_t a20r_interrupt(int irq, void *dev_id)
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 2791b8641df6..9d9962ab7d25 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -117,22 +117,6 @@ void clk_put(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_put);
 
-/* GPIO support */
-
-#ifdef CONFIG_GPIOLIB
-int gpio_to_irq(unsigned gpio)
-{
-	return -EINVAL;
-}
-EXPORT_SYMBOL(gpio_to_irq);
-
-int irq_to_gpio(unsigned irq)
-{
-	return -EINVAL;
-}
-EXPORT_SYMBOL(irq_to_gpio);
-#endif
-
 #define BOARD_VEC(board)	extern struct txx9_board_vec board;
 #include <asm/txx9/boards.h>
 #undef BOARD_VEC
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index de30b0c88796..6edb9ee6128e 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index 5be655e83e70..375e59140c9c 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -89,6 +89,10 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -127,73 +131,6 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-/**
- * atomic_clear_mask - Atomically clear bits in memory
- * @mask: Mask of the bits to be cleared
- * @v: pointer to word in memory
- *
- * Atomically clears the bits set in mask from the memory word specified.
- */
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-#ifdef CONFIG_SMP
-	int status;
-
-	asm volatile(
-		"1:	mov	%3,(_AAR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"
-		"	and	%4,%0		\n"
-		"	mov	%0,(_ADR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"	/* flush */
-		"	mov	(_ASR,%2),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=m"(*addr)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(addr), "r"(~mask)
-		: "memory", "cc");
-#else
-	unsigned long flags;
-
-	mask = ~mask;
-	flags = arch_local_cli_save();
-	*addr &= mask;
-	arch_local_irq_restore(flags);
-#endif
-}
-
-/**
- * atomic_set_mask - Atomically set bits in memory
- * @mask: Mask of the bits to be set
- * @v: pointer to word in memory
- *
- * Atomically sets the bits set in mask from the memory word specified.
- */
-static inline void atomic_set_mask(unsigned long mask, unsigned long *addr)
-{
-#ifdef CONFIG_SMP
-	int status;
-
-	asm volatile(
-		"1:	mov	%3,(_AAR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"
-		"	or	%4,%0		\n"
-		"	mov	%0,(_ADR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"	/* flush */
-		"	mov	(_ASR,%2),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=m"(*addr)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(addr), "r"(mask)
-		: "memory", "cc");
-#else
-	unsigned long flags;
-
-	flags = arch_local_cli_save();
-	*addr |= mask;
-	arch_local_irq_restore(flags);
-#endif
-}
-
 #endif /* __KERNEL__ */
 #endif /* CONFIG_SMP */
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/mn10300/include/asm/io.h b/arch/mn10300/include/asm/io.h
index 07c5b4a3903b..62189353d2f6 100644
--- a/arch/mn10300/include/asm/io.h
+++ b/arch/mn10300/include/asm/io.h
@@ -283,6 +283,7 @@ static inline void __iomem *ioremap_nocache(unsigned long offset, unsigned long
 
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 static inline void iounmap(void __iomem *addr)
 {
diff --git a/arch/mn10300/include/asm/mm-arch-hooks.h b/arch/mn10300/include/asm/mm-arch-hooks.h
deleted file mode 100644
index e2029a652f4c..000000000000
--- a/arch/mn10300/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_MN10300_MM_ARCH_HOOKS_H
-#define _ASM_MN10300_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_MN10300_MM_ARCH_HOOKS_H */
diff --git a/arch/mn10300/kernel/cevt-mn10300.c b/arch/mn10300/kernel/cevt-mn10300.c
index 60f64ca1752a..d9b34dd44f04 100644
--- a/arch/mn10300/kernel/cevt-mn10300.c
+++ b/arch/mn10300/kernel/cevt-mn10300.c
@@ -41,12 +41,6 @@ static int next_event(unsigned long delta,
 	return 0;
 }
 
-static void set_clock_mode(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
-{
-	/* Nothing to do ...  */
-}
-
 static DEFINE_PER_CPU(struct clock_event_device, mn10300_clockevent_device);
 static DEFINE_PER_CPU(struct irqaction, timer_irq);
 
@@ -108,7 +102,6 @@ int __init init_clockevents(void)
 
 	cd->rating		= 200;
 	cd->cpumask		= cpumask_of(smp_processor_id());
-	cd->set_mode		= set_clock_mode;
 	cd->event_handler	= event_handler;
 	cd->set_next_event	= next_event;
 
@@ -123,7 +116,7 @@ int __init init_clockevents(void)
 	{
 		struct irq_data *data;
 		data = irq_get_irq_data(cd->irq);
-		cpumask_copy(data->affinity, cpumask_of(cpu));
+		cpumask_copy(irq_data_get_affinity_mask(data), cpumask_of(cpu));
 		iact->flags |= IRQF_NOBALANCING;
 	}
 #endif
diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c
index 480de70f4059..c716437baa2c 100644
--- a/arch/mn10300/kernel/irq.c
+++ b/arch/mn10300/kernel/irq.c
@@ -87,7 +87,8 @@ static void mn10300_cpupic_mask_ack(struct irq_data *d)
 		tmp2 = GxICR(irq);
 
 		irq_affinity_online[irq] =
-			cpumask_any_and(d->affinity, cpu_online_mask);
+			cpumask_any_and(irq_data_get_affinity_mask(d),
+					cpu_online_mask);
 		CROSS_GxICR(irq, irq_affinity_online[irq]) =
 			(tmp & (GxICR_LEVEL | GxICR_ENABLE)) | GxICR_DETECT;
 		tmp = CROSS_GxICR(irq, irq_affinity_online[irq]);
@@ -124,7 +125,7 @@ static void mn10300_cpupic_unmask_clear(struct irq_data *d)
 	} else {
 		tmp = GxICR(irq);
 
-		irq_affinity_online[irq] = cpumask_any_and(d->affinity,
+		irq_affinity_online[irq] = cpumask_any_and(irq_data_get_affinity_mask(d),
 							   cpu_online_mask);
 		CROSS_GxICR(irq, irq_affinity_online[irq]) = (tmp & GxICR_LEVEL) | GxICR_ENABLE | GxICR_DETECT;
 		tmp = CROSS_GxICR(irq, irq_affinity_online[irq]);
@@ -316,15 +317,16 @@ void migrate_irqs(void)
 	self = smp_processor_id();
 	for (irq = 0; irq < NR_IRQS; irq++) {
 		struct irq_data *data = irq_get_irq_data(irq);
+		struct cpumask *mask = irq_data_get_affinity_mask(data);
 
 		if (irqd_is_per_cpu(data))
 			continue;
 
-		if (cpumask_test_cpu(self, data->affinity) &&
+		if (cpumask_test_cpu(self, mask) &&
 		    !cpumask_intersects(&irq_affinity[irq], cpu_online_mask)) {
 			int cpu_id;
 			cpu_id = cpumask_first(cpu_online_mask);
-			cpumask_set_cpu(cpu_id, data->affinity);
+			cpumask_set_cpu(cpu_id, mask);
 		}
 		/* We need to operate irq_affinity_online atomically. */
 		arch_local_cli_save(flags);
@@ -335,8 +337,7 @@ void migrate_irqs(void)
 			GxICR(irq) = x & GxICR_LEVEL;
 			tmp = GxICR(irq);
 
-			new = cpumask_any_and(data->affinity,
-					      cpu_online_mask);
+			new = cpumask_any_and(mask, cpu_online_mask);
 			irq_affinity_online[irq] = new;
 
 			CROSS_GxICR(irq, new) =
diff --git a/arch/mn10300/mm/tlb-smp.c b/arch/mn10300/mm/tlb-smp.c
index e5d0ef722bfa..9a39ea9031d4 100644
--- a/arch/mn10300/mm/tlb-smp.c
+++ b/arch/mn10300/mm/tlb-smp.c
@@ -119,7 +119,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	flush_mm = mm;
 	flush_va = va;
 #if NR_CPUS <= BITS_PER_LONG
-	atomic_set_mask(cpumask.bits[0], &flush_cpumask.bits[0]);
+	atomic_or(cpumask.bits[0], (atomic_t *)&flush_cpumask.bits[0]);
 #else
 #error Not supported.
 #endif
diff --git a/arch/mn10300/unit-asb2305/pci-asb2305.c b/arch/mn10300/unit-asb2305/pci-asb2305.c
index b5b036f64275..b7ab8378964c 100644
--- a/arch/mn10300/unit-asb2305/pci-asb2305.c
+++ b/arch/mn10300/unit-asb2305/pci-asb2305.c
@@ -183,18 +183,16 @@ static int __init pcibios_assign_resources(void)
 	struct pci_dev *dev = NULL;
 	struct resource *r;
 
-	if (!(pci_probe & PCI_ASSIGN_ROMS)) {
-		/* Try to use BIOS settings for ROMs, otherwise let
-		   pci_assign_unassigned_resources() allocate the new
-		   addresses. */
-		for_each_pci_dev(dev) {
-			r = &dev->resource[PCI_ROM_RESOURCE];
-			if (!r->flags || !r->start)
-				continue;
-			if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
-				r->end -= r->start;
-				r->start = 0;
-			}
+	/* Try to use BIOS settings for ROMs, otherwise let
+	   pci_assign_unassigned_resources() allocate the new
+	   addresses. */
+	for_each_pci_dev(dev) {
+		r = &dev->resource[PCI_ROM_RESOURCE];
+		if (!r->flags || !r->start)
+			continue;
+		if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
+			r->end -= r->start;
+			r->start = 0;
 		}
 	}
 
diff --git a/arch/mn10300/unit-asb2305/pci-asb2305.h b/arch/mn10300/unit-asb2305/pci-asb2305.h
index 9e17aca5a2a1..96c484b12226 100644
--- a/arch/mn10300/unit-asb2305/pci-asb2305.h
+++ b/arch/mn10300/unit-asb2305/pci-asb2305.h
@@ -20,13 +20,6 @@
 #define DBG(x...)
 #endif
 
-#define PCI_PROBE_BIOS 1
-#define PCI_PROBE_CONF1 2
-#define PCI_PROBE_CONF2 4
-#define PCI_NO_CHECKS 0x400
-#define PCI_ASSIGN_ROMS 0x1000
-#define PCI_BIOS_IRQ_SCAN 0x2000
-
 extern unsigned int pci_probe;
 
 /* pci-asb2305.c */
diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c
index 3dfe2d31c67b..deaa893efba5 100644
--- a/arch/mn10300/unit-asb2305/pci.c
+++ b/arch/mn10300/unit-asb2305/pci.c
@@ -324,7 +324,6 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	if (bus->self) {
-		pci_read_bridge_bases(bus);
 		pcibios_fixup_bridge_resources(bus->self);
 	}
 
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 434639d510b3..914864eb5a25 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -30,6 +30,7 @@ generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
diff --git a/arch/nios2/include/asm/mm-arch-hooks.h b/arch/nios2/include/asm/mm-arch-hooks.h
deleted file mode 100644
index d7290dc68558..000000000000
--- a/arch/nios2/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_NIOS2_MM_ARCH_HOOKS_H
-#define _ASM_NIOS2_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_NIOS2_MM_ARCH_HOOKS_H */
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index e5a693b16da2..443f44de1020 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -17,6 +17,7 @@ config OPENRISC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IOMAP
 	select GENERIC_CPU_DEVICES
+	select HAVE_UID16
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_STRNCPY_FROM_USER
@@ -31,9 +32,6 @@ config MMU
 config HAVE_DMA_ATTRS
 	def_bool y
 
-config UID16
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 2a2e39b8109a..2832f031fb11 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -36,6 +36,7 @@ generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
diff --git a/arch/openrisc/include/asm/mm-arch-hooks.h b/arch/openrisc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 6d33cb555fe1..000000000000
--- a/arch/openrisc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_OPENRISC_MM_ARCH_HOOKS_H
-#define _ASM_OPENRISC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_OPENRISC_MM_ARCH_HOOKS_H */
diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c
index 7c52e9494a8d..50e970183dcd 100644
--- a/arch/openrisc/kernel/time.c
+++ b/arch/openrisc/kernel/time.c
@@ -48,29 +48,6 @@ static int openrisc_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void openrisc_timer_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *evt)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		pr_debug(KERN_INFO "%s: periodic\n", __func__);
-		BUG();
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		pr_debug(KERN_INFO "%s: oneshot\n", __func__);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-		pr_debug(KERN_INFO "%s: unused\n", __func__);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		pr_debug(KERN_INFO "%s: shutdown\n", __func__);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		pr_debug(KERN_INFO "%s: resume\n", __func__);
-		break;
-	}
-}
-
 /* This is the clock event device based on the OR1K tick timer.
  * As the timer is being used as a continuous clock-source (required for HR
  * timers) we cannot enable the PERIODIC feature.  The tick timer can run using
@@ -82,7 +59,6 @@ static struct clock_event_device clockevent_openrisc_timer = {
 	.features = CLOCK_EVT_FEAT_ONESHOT,
 	.rating = 300,
 	.set_next_event = openrisc_timer_set_next_event,
-	.set_mode = openrisc_timer_set_mode,
 };
 
 static inline void timer_ack(void)
diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig
index 269c23d23fcb..1a8f6f95689e 100644
--- a/arch/parisc/configs/c8000_defconfig
+++ b/arch/parisc/configs/c8000_defconfig
@@ -242,7 +242,6 @@ CONFIG_LOCKUP_DETECTOR=y
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_RT_MUTEX_TESTER=y
 CONFIG_PROVE_RCU_DELAY=y
 CONFIG_DEBUG_BLOCK_EXT_DEVT=y
 CONFIG_LATENCYTOP=y
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index 33b148f825ba..0ffb08ff5125 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -295,7 +295,6 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_TIMER_STATS=y
 CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_RT_MUTEX_TESTER=y
 CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_RCU_CPU_STALL_INFO=y
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 12b341d04f88..f9b3a81aefcd 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -15,6 +15,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 226f8ca993f6..2536965d00ea 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -126,6 +126,10 @@ static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
 
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -185,6 +189,9 @@ static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v)	\
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
+ATOMIC64_OP(and, &=)
+ATOMIC64_OP(or, |=)
+ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/parisc/include/asm/mm-arch-hooks.h b/arch/parisc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 654ec63b0ee9..000000000000
--- a/arch/parisc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_PARISC_MM_ARCH_HOOKS_H
-#define _ASM_PARISC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_PARISC_MM_ARCH_HOOKS_H */
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index 3a08eae3318f..3edbb9fc91b4 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -72,7 +72,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
+	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
 		/*
 		 * This is the permanent pmd attached to the pgd;
 		 * cannot free it.
@@ -81,6 +81,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 		 */
 		mm_inc_nr_pmds(mm);
 		return;
+	}
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 0a183756d6ec..f93c4a4e6580 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -16,7 +16,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-extern spinlock_t pa_dbit_lock;
+extern spinlock_t pa_tlb_lock;
 
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
@@ -33,6 +33,19 @@ extern spinlock_t pa_dbit_lock;
  */
 #define kern_addr_valid(addr)	(1)
 
+/* Purge data and instruction TLB entries.  Must be called holding
+ * the pa_tlb_lock.  The TLB purge instructions are slow on SMP
+ * machines since the purge must be broadcast to all CPUs.
+ */
+
+static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+	mtsp(mm->context, 1);
+	pdtlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
+}
+
 /* Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
@@ -42,15 +55,20 @@ extern spinlock_t pa_dbit_lock;
                 *(pteptr) = (pteval);                           \
         } while(0)
 
-extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+#define pte_inserted(x)						\
+	((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED))		\
+	 == (_PAGE_PRESENT|_PAGE_ACCESSED))
 
-#define set_pte_at(mm, addr, ptep, pteval)                      \
-	do {                                                    \
+#define set_pte_at(mm, addr, ptep, pteval)			\
+	do {							\
+		pte_t old_pte;					\
 		unsigned long flags;				\
-		spin_lock_irqsave(&pa_dbit_lock, flags);	\
-		set_pte(ptep, pteval);                          \
-		purge_tlb_entries(mm, addr);                    \
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);	\
+		spin_lock_irqsave(&pa_tlb_lock, flags);		\
+		old_pte = *ptep;				\
+		set_pte(ptep, pteval);				\
+		if (pte_inserted(old_pte))			\
+			purge_tlb_entries(mm, addr);		\
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);	\
 	} while (0)
 
 #endif /* !__ASSEMBLY__ */
@@ -268,7 +286,7 @@ extern unsigned long *empty_zero_page;
 
 #define pte_none(x)     (pte_val(x) == 0)
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
-#define pte_clear(mm,addr,xp)	do { pte_val(*(xp)) = 0; } while (0)
+#define pte_clear(mm, addr, xp)  set_pte_at(mm, addr, xp, __pte(0))
 
 #define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
 #define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
@@ -435,15 +453,15 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
 	if (!pte_young(*ptep))
 		return 0;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	pte = *ptep;
 	if (!pte_young(pte)) {
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);
 		return 0;
 	}
 	set_pte(ptep, pte_mkold(pte));
 	purge_tlb_entries(vma->vm_mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 	return 1;
 }
 
@@ -453,11 +471,12 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 	pte_t old_pte;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	old_pte = *ptep;
-	pte_clear(mm,addr,ptep);
-	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	set_pte(ptep, __pte(0));
+	if (pte_inserted(old_pte))
+		purge_tlb_entries(mm, addr);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 
 	return old_pte;
 }
@@ -465,10 +484,10 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	set_pte(ptep, pte_wrprotect(*ptep));
 	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 }
 
 #define pte_same(A,B)	(pte_val(A) == pte_val(B))
diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h
index 9d086a599fa0..e84b96478193 100644
--- a/arch/parisc/include/asm/tlbflush.h
+++ b/arch/parisc/include/asm/tlbflush.h
@@ -13,6 +13,9 @@
  * active at any one time on the Merced bus.  This tlb purge
  * synchronisation is fairly lightweight and harmless so we activate
  * it on all systems not just the N class.
+
+ * It is also used to ensure PTE updates are atomic and consistent
+ * with the TLB.
  */
 extern spinlock_t pa_tlb_lock;
 
@@ -24,20 +27,24 @@ extern void flush_tlb_all_local(void *);
 
 #define smp_flush_tlb_all()	flush_tlb_all()
 
+int __flush_tlb_range(unsigned long sid,
+	unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma, start, end) \
+	__flush_tlb_range((vma)->vm_mm->context, start, end)
+
+#define flush_tlb_kernel_range(start, end) \
+	__flush_tlb_range(0, start, end)
+
 /*
  * flush_tlb_mm()
  *
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
+ * The code to switch to a new context is NOT valid for processes
+ * which play with the space id's.  Thus, we have to preserve the
+ * space and just flush the entire tlb.  However, the compilers,
+ * dynamic linker, etc, do not manipulate space id's, so there
+ * could be a significant performance benefit in switching contexts
+ * and not flushing the whole tlb.
  */
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
@@ -45,10 +52,18 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	BUG_ON(mm == &init_mm); /* Should never happen */
 
 #if 1 || defined(CONFIG_SMP)
+	/* Except for very small threads, flushing the whole TLB is
+	 * faster than using __flush_tlb_range.  The pdtlb and pitlb
+	 * instructions are very slow because of the TLB broadcast.
+	 * It might be faster to do local range flushes on all CPUs
+	 * on PA 2.0 systems.
+	 */
 	flush_tlb_all();
 #else
 	/* FIXME: currently broken, causing space id and protection ids
-	 *  to go out of sync, resulting in faults on userspace accesses.
+	 * to go out of sync, resulting in faults on userspace accesses.
+	 * This approach needs further investigation since running many
+	 * small applications (e.g., GCC testsuite) is faster on HP-UX.
 	 */
 	if (mm) {
 		if (mm->context != 0)
@@ -65,22 +80,12 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 {
 	unsigned long flags, sid;
 
-	/* For one page, it's not worth testing the split_tlb variable */
-
-	mb();
 	sid = vma->vm_mm->context;
 	purge_tlb_start(flags);
 	mtsp(sid, 1);
 	pdtlb(addr);
-	pitlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
 	purge_tlb_end(flags);
 }
-
-void __flush_tlb_range(unsigned long sid,
-	unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
 #endif
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index f6448c7c62b5..cda6dbbe9842 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -342,12 +342,15 @@ EXPORT_SYMBOL(flush_data_cache_local);
 EXPORT_SYMBOL(flush_kernel_icache_range_asm);
 
 #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
-int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+
+#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */
+static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD;
 
 void __init parisc_setup_cache_timing(void)
 {
 	unsigned long rangetime, alltime;
-	unsigned long size;
+	unsigned long size, start;
 
 	alltime = mfctl(16);
 	flush_data_cache();
@@ -364,14 +367,43 @@ void __init parisc_setup_cache_timing(void)
 	/* Racy, but if we see an intermediate value, it's ok too... */
 	parisc_cache_flush_threshold = size * alltime / rangetime;
 
-	parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); 
+	parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
 	if (!parisc_cache_flush_threshold)
 		parisc_cache_flush_threshold = FLUSH_THRESHOLD;
 
 	if (parisc_cache_flush_threshold > cache_info.dc_size)
 		parisc_cache_flush_threshold = cache_info.dc_size;
 
-	printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
+	printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+		parisc_cache_flush_threshold/1024);
+
+	/* calculate TLB flush threshold */
+
+	alltime = mfctl(16);
+	flush_tlb_all();
+	alltime = mfctl(16) - alltime;
+
+	size = PAGE_SIZE;
+	start = (unsigned long) _text;
+	rangetime = mfctl(16);
+	while (start < (unsigned long) _end) {
+		flush_tlb_kernel_range(start, start + PAGE_SIZE);
+		start += PAGE_SIZE;
+		size += PAGE_SIZE;
+	}
+	rangetime = mfctl(16) - rangetime;
+
+	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
+		alltime, size, rangetime);
+
+	parisc_tlb_flush_threshold = size * alltime / rangetime;
+	parisc_tlb_flush_threshold *= num_online_cpus();
+	parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
+	if (!parisc_tlb_flush_threshold)
+		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+
+	printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+		parisc_tlb_flush_threshold/1024);
 }
 
 extern void purge_kernel_dcache_page_asm(unsigned long);
@@ -403,48 +435,45 @@ void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
 }
 EXPORT_SYMBOL(copy_user_page);
 
-void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
-{
-	unsigned long flags;
-
-	/* Note: purge_tlb_entries can be called at startup with
-	   no context.  */
-
-	purge_tlb_start(flags);
-	mtsp(mm->context, 1);
-	pdtlb(addr);
-	pitlb(addr);
-	purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(purge_tlb_entries);
-
-void __flush_tlb_range(unsigned long sid, unsigned long start,
-		       unsigned long end)
+/* __flush_tlb_range()
+ *
+ * returns 1 if all TLBs were flushed.
+ */
+int __flush_tlb_range(unsigned long sid, unsigned long start,
+		      unsigned long end)
 {
-	unsigned long npages;
+	unsigned long flags, size;
 
-	npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-	if (npages >= 512)  /* 2MB of space: arbitrary, should be tuned */
+	size = (end - start);
+	if (size >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
-	else {
-		unsigned long flags;
+		return 1;
+	}
 
+	/* Purge TLB entries for small ranges using the pdtlb and
+	   pitlb instructions.  These instructions execute locally
+	   but cause a purge request to be broadcast to other TLBs.  */
+	if (likely(!split_tlb)) {
+		while (start < end) {
+			purge_tlb_start(flags);
+			mtsp(sid, 1);
+			pdtlb(start);
+			purge_tlb_end(flags);
+			start += PAGE_SIZE;
+		}
+		return 0;
+	}
+
+	/* split TLB case */
+	while (start < end) {
 		purge_tlb_start(flags);
 		mtsp(sid, 1);
-		if (split_tlb) {
-			while (npages--) {
-				pdtlb(start);
-				pitlb(start);
-				start += PAGE_SIZE;
-			}
-		} else {
-			while (npages--) {
-				pdtlb(start);
-				start += PAGE_SIZE;
-			}
-		}
+		pdtlb(start);
+		pitlb(start);
 		purge_tlb_end(flags);
+		start += PAGE_SIZE;
 	}
+	return 0;
 }
 
 static void cacheflush_h_tmp_function(void *dummy)
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 75819617f93b..c5ef4081b01d 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -45,7 +45,7 @@
 	.level 2.0
 #endif
 
-	.import         pa_dbit_lock,data
+	.import		pa_tlb_lock,data
 
 	/* space_to_prot macro creates a prot id from a space id */
 
@@ -420,8 +420,8 @@
 	SHLREG		%r9,PxD_VALUE_SHIFT,\pmd
 	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
-	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd
-	LDREG		%r0(\pmd),\pte		/* pmd is now pte */
+	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
+	LDREG		%r0(\pmd),\pte
 	bb,>=,n		\pte,_PAGE_PRESENT_BIT,\fault
 	.endm
 
@@ -453,57 +453,53 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
-	/* Acquire pa_dbit_lock lock. */
-	.macro		dbit_lock	spc,tmp,tmp1
+	/* Acquire pa_tlb_lock lock and recheck page is still present. */
+	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
 	cmpib,COND(=),n	0,\spc,2f
-	load32		PA(pa_dbit_lock),\tmp
+	load32		PA(pa_tlb_lock),\tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
+	LDREG		0(\ptp),\pte
+	bb,<,n		\pte,_PAGE_PRESENT_BIT,2f
+	b		\fault
+	stw		 \spc,0(\tmp)
 2:
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock without reloading lock address. */
-	.macro		dbit_unlock0	spc,tmp
+	/* Release pa_tlb_lock lock without reloading lock address. */
+	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock. */
-	.macro		dbit_unlock1	spc,tmp
+	/* Release pa_tlb_lock lock. */
+	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load32		PA(pa_dbit_lock),\tmp
-	dbit_unlock0	\spc,\tmp
+	load32		PA(pa_tlb_lock),\tmp
+	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
 
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
-	.macro		update_ptep	spc,ptep,pte,tmp,tmp1
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_accessed	ptp,pte,tmp,tmp1
 	ldi		_PAGE_ACCESSED,\tmp1
 	or		\tmp1,\pte,\tmp
 	and,COND(<>)	\tmp1,\pte,%r0
-	STREG		\tmp,0(\ptep)
+	STREG		\tmp,0(\ptp)
 	.endm
 
 	/* Set the dirty bit (and accessed bit).  No need to be
 	 * clever, this is only used from the dirty fault */
-	.macro		update_dirty	spc,ptep,pte,tmp
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_dirty	ptp,pte,tmp
 	ldi		_PAGE_ACCESSED|_PAGE_DIRTY,\tmp
 	or		\tmp,\pte,\pte
-	STREG		\pte,0(\ptep)
+	STREG		\pte,0(\ptp)
 	.endm
 
 	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
@@ -1148,14 +1144,14 @@ dtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1174,14 +1170,14 @@ nadtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1202,20 +1198,20 @@ dtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1235,21 +1231,20 @@ nadtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1269,16 +1264,16 @@ dtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1297,16 +1292,16 @@ nadtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock1	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1406,14 +1401,14 @@ itlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1430,14 +1425,14 @@ naitlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1458,20 +1453,20 @@ itlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1482,20 +1477,20 @@ naitlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1516,16 +1511,16 @@ itlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0	
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1536,16 +1531,16 @@ naitlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1568,14 +1563,14 @@ dbit_trap_20w:
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 		
 	idtlbt          pte,prot
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #else
@@ -1588,8 +1583,8 @@ dbit_trap_11:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1600,8 +1595,8 @@ dbit_trap_11:
 	idtlbp		prot,(%sr1,va)
 
 	mtsp            t1, %sr1     /* Restore sr1 */
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 
@@ -1612,16 +1607,16 @@ dbit_trap_20:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock0	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #endif
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index f3191db6e2e9..413ec3c3f9cc 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -131,7 +131,7 @@ static int cpu_set_affinity_irq(struct irq_data *d, const struct cpumask *dest,
 	if (cpu_dest < 0)
 		return -1;
 
-	cpumask_copy(d->affinity, dest);
+	cpumask_copy(irq_data_get_affinity_mask(d), dest);
 
 	return 0;
 }
@@ -339,7 +339,7 @@ unsigned long txn_affinity_addr(unsigned int irq, int cpu)
 {
 #ifdef CONFIG_SMP
 	struct irq_data *d = irq_get_irq_data(irq);
-	cpumask_copy(d->affinity, cpumask_of(cpu));
+	cpumask_copy(irq_data_get_affinity_mask(d), cpumask_of(cpu));
 #endif
 
 	return per_cpu(cpu_data, cpu).txn_addr;
@@ -508,7 +508,7 @@ void do_cpu_irq_mask(struct pt_regs *regs)
 	unsigned long eirr_val;
 	int irq, cpu = smp_processor_id();
 #ifdef CONFIG_SMP
-	struct irq_desc *desc;
+	struct irq_data *irq_data;
 	cpumask_t dest;
 #endif
 
@@ -522,9 +522,9 @@ void do_cpu_irq_mask(struct pt_regs *regs)
 	irq = eirr_to_irq(eirr_val);
 
 #ifdef CONFIG_SMP
-	desc = irq_to_desc(irq);
-	cpumask_copy(&dest, desc->irq_data.affinity);
-	if (irqd_is_per_cpu(&desc->irq_data) &&
+	irq_data = irq_get_irq_data(irq);
+	cpumask_copy(&dest, irq_data_get_affinity_mask(irq_data));
+	if (irqd_is_per_cpu(irq_data) &&
 	    !cpumask_test_cpu(smp_processor_id(), &dest)) {
 		int cpu = cpumask_first(&dest);
 
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 6548fd1d2e62..b99b39f1da02 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -43,10 +43,6 @@
 
 #include "../math-emu/math-emu.h"	/* for handle_fpe() */
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-DEFINE_SPINLOCK(pa_dbit_lock);
-#endif
-
 static void parisc_show_stack(struct task_struct *task, unsigned long *sp,
 	struct pt_regs *regs);
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 5ef27113b898..b447918b9e2c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -82,6 +82,9 @@ config GENERIC_HWEIGHT
 	bool
 	default y
 
+config ARCH_HAS_DMA_SET_COHERENT_MASK
+        bool
+
 config PPC
 	bool
 	default y
@@ -155,6 +158,8 @@ config PPC
 	select HAVE_PERF_EVENTS_NMI if PPC64
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select HAVE_ARCH_SECCOMP_FILTER
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -514,11 +519,6 @@ config NODES_SPAN_OTHER_NODES
 	def_bool y
 	depends on NEED_MULTIPLE_NODES
 
-config PPC_HAS_HASH_64K
-	bool
-	depends on PPC64
-	default n
-
 config STDBINUTILS
 	bool "Using standard binutils settings"
 	depends on 44x
@@ -560,16 +560,16 @@ config PPC_4K_PAGES
 	bool "4k page size"
 
 config PPC_16K_PAGES
-	bool "16k page size" if 44x || PPC_8xx
+	bool "16k page size"
+	depends on 44x || PPC_8xx
 
 config PPC_64K_PAGES
-	bool "64k page size" if 44x || PPC_STD_MMU_64 || PPC_BOOK3E_64
-	depends on !PPC_FSL_BOOK3E
-	select PPC_HAS_HASH_64K if PPC_STD_MMU_64
+	bool "64k page size"
+	depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64)
 
 config PPC_256K_PAGES
-	bool "256k page size" if 44x
-	depends on !STDBINUTILS
+	bool "256k page size"
+	depends on 44x && !STDBINUTILS
 	help
 	  Make the page size 256k.
 
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 05f464eb6952..b9b4af2af9a5 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -67,7 +67,7 @@ UTS_MACHINE := $(OLDARCH)
 
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 override CC	+= -mlittle-endian
-ifneq ($(COMPILER),clang)
+ifneq ($(cc-name),clang)
 override CC	+= -mno-strict-align
 endif
 override AS	+= -mlittle-endian
@@ -288,6 +288,26 @@ PHONY += pseries_le_defconfig
 pseries_le_defconfig:
 	$(call merge_into_defconfig,pseries_defconfig,le)
 
+PHONY += mpc85xx_defconfig
+mpc85xx_defconfig:
+	$(call merge_into_defconfig,mpc85xx_basic_defconfig,\
+		85xx-32bit 85xx-hw fsl-emb-nonhw)
+
+PHONY += mpc85xx_smp_defconfig
+mpc85xx_smp_defconfig:
+	$(call merge_into_defconfig,mpc85xx_basic_defconfig,\
+		85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw)
+
+PHONY += corenet32_smp_defconfig
+corenet32_smp_defconfig:
+	$(call merge_into_defconfig,corenet_basic_defconfig,\
+		85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw)
+
+PHONY += corenet64_smp_defconfig
+corenet64_smp_defconfig:
+	$(call merge_into_defconfig,corenet_basic_defconfig,\
+		85xx-64bit 85xx-smp altivec 85xx-hw fsl-emb-nonhw)
+
 define archhelp
   @echo '* zImage          - Build default images selected by kernel config'
   @echo '  zImage.*        - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)'
@@ -333,7 +353,7 @@ TOUT	:= .tmp_gas_check
 # - Require gcc 4.0 or above on 64-bit
 # - gcc-4.2.0 has issues compiling modules on 64-bit
 checkbin:
-	@if test "${COMPILER}" != "clang" \
+	@if test "$(cc-name)" != "clang" \
 	    && test "$(cc-version)" = "0304" ; then \
 		if ! /bin/echo mftb 5 | $(AS) -v -mppc -many -o $(TOUT) >/dev/null 2>&1 ; then \
 			echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build '; \
@@ -342,14 +362,14 @@ checkbin:
 			false; \
 		fi ; \
 	fi
-	@if test "${COMPILER}" != "clang" \
+	@if test "$(cc-name)" != "clang" \
 	    && test "$(cc-version)" -lt "0400" \
 	    && test "x${CONFIG_PPC64}" = "xy" ; then \
                 echo -n "Sorry, GCC v4.0 or above is required to build " ; \
                 echo "the 64-bit powerpc kernel." ; \
                 false ; \
         fi
-	@if test "${COMPILER}" != "clang" \
+	@if test "$(cc-name)" != "clang" \
 	    && test "$(cc-fullversion)" = "040200" \
 	    && test "x${CONFIG_MODULES}${CONFIG_PPC64}" = "xyy" ; then \
 		echo -n '*** GCC-4.2.0 cannot compile the 64-bit powerpc ' ; \
diff --git a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
index ebf202234549..426bf4103b9e 100644
--- a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
@@ -175,7 +175,7 @@
 
 /include/ "pq3-gpio-0.dtsi"
 
-	display@10000 {
+	display: display@10000 {
 		compatible = "fsl,diu", "fsl,p1022-diu";
 		reg = <0x10000 1000>;
 		interrupts = <64 2 0 0>;
diff --git a/arch/powerpc/boot/dts/fsl/p1022si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-pre.dtsi
index 1956dea040cc..de76ae8992c6 100644
--- a/arch/powerpc/boot/dts/fsl/p1022si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1022si-pre.dtsi
@@ -50,6 +50,8 @@
 		pci0 = &pci0;
 		pci1 = &pci1;
 		pci2 = &pci2;
+		vga = &display;
+		display = &display;
 	};
 
 	cpus {
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 9e9f7e201d43..9770d0278493 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -484,6 +484,11 @@
 		reg	   = <0xea000 0x4000>;
 	};
 
+	scfg: global-utilities@fc000 {
+		compatible = "fsl,t1040-scfg";
+		reg = <0xfc000 0x1000>;
+	};
+
 /include/ "elo3-dma-0.dtsi"
 /include/ "elo3-dma-1.dtsi"
 /include/ "qoriq-espi-0.dtsi"
diff --git a/arch/powerpc/boot/dts/t1023rdb.dts b/arch/powerpc/boot/dts/t1023rdb.dts
index 06b090aba066..d3fa8294cd49 100644
--- a/arch/powerpc/boot/dts/t1023rdb.dts
+++ b/arch/powerpc/boot/dts/t1023rdb.dts
@@ -60,7 +60,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "fsl,ifc-nand";
-			reg = <0x2 0x0 0x10000>;
+			reg = <0x1 0x0 0x10000>;
 		};
 	};
 
@@ -99,6 +99,17 @@
 		};
 
 		i2c@118100 {
+			current-sensor@40 {
+				compatible = "ti,ina220";
+				reg = <0x40>;
+				shunt-resistor = <1000>;
+			};
+
+			current-sensor@41 {
+				compatible = "ti,ina220";
+				reg = <0x41>;
+				shunt-resistor = <1000>;
+			};
 		};
 	};
 
diff --git a/arch/powerpc/boot/dts/t1024rdb.dts b/arch/powerpc/boot/dts/t1024rdb.dts
index 733e723ffed6..bf05e324fda2 100644
--- a/arch/powerpc/boot/dts/t1024rdb.dts
+++ b/arch/powerpc/boot/dts/t1024rdb.dts
@@ -114,6 +114,12 @@
 				reg = <0x4c>;
 			};
 
+			current-sensor@40 {
+				compatible = "ti,ina220";
+				reg = <0x40>;
+				shunt-resistor = <1000>;
+			};
+
 			eeprom@50 {
 				compatible = "atmel,24c256";
 				reg = <0x50>;
diff --git a/arch/powerpc/boot/dts/t1040d4rdb.dts b/arch/powerpc/boot/dts/t1040d4rdb.dts
new file mode 100644
index 000000000000..2d1315a1670e
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1040d4rdb.dts
@@ -0,0 +1,46 @@
+/*
+ * T1040D4RDB Device Tree Source
+ *
+ * Copyright 2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xd4rdb.dtsi"
+
+/ {
+	model = "fsl,T1040D4RDB";
+	compatible = "fsl,T1040D4RDB";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+};
+
+/include/ "fsl/t1040si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1042d4rdb.dts b/arch/powerpc/boot/dts/t1042d4rdb.dts
new file mode 100644
index 000000000000..846f8c87e85a
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1042d4rdb.dts
@@ -0,0 +1,53 @@
+/*
+ * T1042D4RDB Device Tree Source
+ *
+ * Copyright 2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xd4rdb.dtsi"
+
+/ {
+	model = "fsl,T1042D4RDB";
+	compatible = "fsl,T1042D4RDB";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	ifc: localbus@ffe124000 {
+		cpld@3,0 {
+			compatible = "fsl,t1040d4rdb-cpld",
+					"fsl,deepsleep-cpld";
+		};
+	};
+};
+
+/include/ "fsl/t1040si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t104xd4rdb.dtsi b/arch/powerpc/boot/dts/t104xd4rdb.dtsi
new file mode 100644
index 000000000000..491367bd3883
--- /dev/null
+++ b/arch/powerpc/boot/dts/t104xd4rdb.dtsi
@@ -0,0 +1,205 @@
+/*
+ * T1040D4RDB/T1042D4RDB Device Tree Source
+ *
+ * Copyright 2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/ {
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		bman_fbpr: bman-fbpr {
+			size = <0 0x1000000>;
+			alignment = <0 0x1000000>;
+		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
+	};
+
+	ifc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x2000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  2 0 0xf 0xff800000 0x00010000
+			  3 0 0xf 0xffdf0000 0x00008000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+			bank-width = <2>;
+			device-width = <1>;
+		};
+
+		nand@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x2 0x0 0x10000>;
+		};
+
+		cpld@3,0 {
+			compatible = "fsl,t1040d4rdb-cpld";
+			reg = <3 0 0x300>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+	};
+
+	bportals: bman-portals@ff4000000 {
+		ranges = <0x0 0xf 0xf4000000 0x2000000>;
+	};
+
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "micron,n25q512ax3";
+				reg = <0>;
+				/* input clock */
+				spi-max-frequency = <10000000>;
+			};
+		};
+		i2c@118000 {
+			hwmon@4c {
+				compatible = "adi,adt7461";
+				reg = <0x4c>;
+			};
+
+			rtc@68 {
+				compatible = "dallas,ds1337";
+				reg = <0x68>;
+				interrupts = <0x2 0x1 0 0>;
+			};
+		};
+
+		i2c@118100 {
+			mux@77 {
+				/*
+				 * Child nodes of mux depend on which i2c
+				 * devices are connected via the mini PCI
+				 * connector slot1, the mini PCI connector
+				 * slot2, the HDMI connector, and the PEX
+				 * slot. Systems with such devices attached
+				 * should provide a wrapper .dts file that
+				 * includes this one, and adds those nodes
+				 */
+				compatible = "nxp,pca9546";
+				reg = <0x77>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+	};
+
+	pci0: pcie@ffe240000 {
+		reg = <0xf 0xfe240000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x0 0x0 0x10000000
+			  0x01000000 0 0x0 0xf 0xf8000000 0x0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe250000 {
+		reg = <0xf 0xfe250000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+			  0x01000000 0 0 0xf 0xf8010000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe260000 {
+		reg = <0xf 0xfe260000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci3: pcie@ffe270000 {
+		reg = <0xf 0xfe270000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x30000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
diff --git a/arch/powerpc/configs/85xx-32bit.config b/arch/powerpc/configs/85xx-32bit.config
new file mode 100644
index 000000000000..6b8894d727a2
--- /dev/null
+++ b/arch/powerpc/configs/85xx-32bit.config
@@ -0,0 +1,5 @@
+CONFIG_HIGHMEM=y
+CONFIG_KEXEC=y
+CONFIG_PPC_85xx=y
+CONFIG_PROC_KCORE=y
+CONFIG_PHYS_64BIT=y
diff --git a/arch/powerpc/configs/85xx-64bit.config b/arch/powerpc/configs/85xx-64bit.config
new file mode 100644
index 000000000000..4aba81222885
--- /dev/null
+++ b/arch/powerpc/configs/85xx-64bit.config
@@ -0,0 +1,4 @@
+CONFIG_MATH_EMULATION=y
+CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED=y
+CONFIG_PPC64=y
+CONFIG_PPC_BOOK3E_64=y
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
new file mode 100644
index 000000000000..528ff0e714e6
--- /dev/null
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -0,0 +1,142 @@
+CONFIG_AQUANTIA_PHY=y
+CONFIG_AT803X_PHY=y
+CONFIG_ATA=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_BROADCOM_PHY=y
+CONFIG_C293_PCIE=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_CHR_DEV_ST=y
+CONFIG_CICADA_PHY=y
+CONFIG_CLK_QORIQ=y
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
+CONFIG_CRYPTO_DEV_TALITOS=y
+CONFIG_DAVICOM_PHY=y
+CONFIG_DMADEVICES=y
+CONFIG_E1000E=y
+CONFIG_E1000=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_MPC85XX=y
+CONFIG_EDAC=y
+CONFIG_EEPROM_AT24=y
+CONFIG_EEPROM_LEGACY=y
+CONFIG_FB_FSL_DIU=y
+CONFIG_FS_ENET=y
+CONFIG_FSL_CORENET_CF=y
+CONFIG_FSL_DMA=y
+CONFIG_FSL_HV_MANAGER=y
+CONFIG_FSL_PQ_MDIO=y
+CONFIG_FSL_RIO=y
+CONFIG_FSL_XGMAC_MDIO=y
+CONFIG_GIANFAR=y
+CONFIG_GPIO_MPC8XXX=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_CPM=m
+CONFIG_I2C_MPC=y
+CONFIG_I2C_MUX_PCA954x=y
+CONFIG_I2C_MUX=y
+CONFIG_I2C=y
+CONFIG_IGB=y
+CONFIG_INPUT_FF_MEMLESS=m
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_MARVELL_PHY=y
+CONFIG_MDIO_BUS_MUX_GPIO=y
+CONFIG_MDIO_BUS_MUX_MMIOREG=y
+CONFIG_MMC_SDHCI_OF_ESDHC=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_M25P80=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_MTD_NAND_FSL_IFC=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PLATRAM=y
+CONFIG_MTD_SPI_NOR=y
+CONFIG_NETDEVICES=y
+CONFIG_NVRAM=y
+CONFIG_PATA_ALI=y
+CONFIG_PATA_SIL680=y
+CONFIG_PATA_VIA=y
+# CONFIG_PCIEASPM is not set
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_MSI=y
+CONFIG_PCI=y
+CONFIG_PPC_EPAPR_HV_BYTECHAN=y
+# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
+CONFIG_QE_GPIO=y
+CONFIG_QUICC_ENGINE=y
+CONFIG_RAPIDIO=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_CMOS=y
+CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_DS1374=y
+CONFIG_RTC_DRV_DS3232=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_FSL=y
+CONFIG_SATA_SIL24=y
+CONFIG_SATA_SIL=y
+CONFIG_SCSI_LOGGING=y
+CONFIG_SCSI_SYM53C8XX_2=y
+CONFIG_SENSORS_INA2XX=y
+CONFIG_SENSORS_LM90=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_NR_UARTS=6
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_SERIAL_8250_RUNTIME_UARTS=6
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_QE=m
+CONFIG_SERIO_LIBPS2=y
+# CONFIG_SND_DRIVERS is not set
+CONFIG_SND_INTEL8X0=y
+CONFIG_SND_POWERPC_SOC=y
+# CONFIG_SND_PPC is not set
+CONFIG_SND_SOC=y
+# CONFIG_SND_SUPPORT_OLD_API is not set
+# CONFIG_SND_USB is not set
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_SPI_FSL_ESPI=y
+CONFIG_SPI_FSL_SPI=y
+CONFIG_SPI_GPIO=y
+CONFIG_SPI=y
+CONFIG_TERANETICS_PHY=y
+CONFIG_UCC_GETH=y
+CONFIG_USB_EHCI_FSL=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_HID=m
+CONFIG_USB_MON=y
+CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
+CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_VIRT_DRIVERS=y
+CONFIG_VITESSE_PHY=y
diff --git a/arch/powerpc/configs/85xx-smp.config b/arch/powerpc/configs/85xx-smp.config
new file mode 100644
index 000000000000..3b4d1e54636d
--- /dev/null
+++ b/arch/powerpc/configs/85xx-smp.config
@@ -0,0 +1,2 @@
+CONFIG_NR_CPUS=24
+CONFIG_SMP=y
diff --git a/arch/powerpc/configs/altivec.config b/arch/powerpc/configs/altivec.config
new file mode 100644
index 000000000000..58a697cb5a62
--- /dev/null
+++ b/arch/powerpc/configs/altivec.config
@@ -0,0 +1 @@
+CONFIG_ALTIVEC=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
deleted file mode 100644
index 37659937bd12..000000000000
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ /dev/null
@@ -1,185 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=8
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_EMBEDDED=y
-CONFIG_PERF_EVENTS=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_CORENET_GENERIC=y
-CONFIG_HIGHMEM=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_BINFMT_MISC=m
-CONFIG_KEXEC=y
-CONFIG_FORCE_MAX_ZONEORDER=13
-CONFIG_PCI=y
-CONFIG_PCIEPORTBUS=y
-# CONFIG_PCIEASPM is not set
-CONFIG_PCI_MSI=y
-CONFIG_RAPIDIO=y
-CONFIG_FSL_RIO=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_XFRM_SUB_POLICY=y
-CONFIG_XFRM_STATISTICS=y
-CONFIG_NET_KEY=y
-CONFIG_NET_KEY_MIGRATE=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NET_IPIP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_IP_SCTP=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_FSL_ELBC=y
-CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_SPI_NOR=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_FSL=y
-CONFIG_SATA_SIL24=y
-CONFIG_SATA_SIL=y
-CONFIG_PATA_SIL680=y
-CONFIG_NETDEVICES=y
-CONFIG_FSL_PQ_MDIO=y
-CONFIG_FSL_XGMAC_MDIO=y
-CONFIG_E1000=y
-CONFIG_E1000E=y
-CONFIG_AT803X_PHY=y
-CONFIG_VITESSE_PHY=y
-CONFIG_FIXED_PHY=y
-CONFIG_MDIO_BUS_MUX_GPIO=y
-CONFIG_MDIO_BUS_MUX_MMIOREG=y
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_SERIO_LIBPS2=y
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_PPC_EPAPR_HV_BYTECHAN=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_DETECT_IRQ=y
-CONFIG_SERIAL_8250_RSA=y
-CONFIG_NVRAM=y
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_MPC=y
-CONFIG_I2C_MUX=y
-CONFIG_I2C_MUX_PCA954x=y
-CONFIG_SPI=y
-CONFIG_SPI_GPIO=y
-CONFIG_SPI_FSL_SPI=y
-CONFIG_SPI_FSL_ESPI=y
-CONFIG_SENSORS_LM90=y
-CONFIG_SENSORS_INA2XX=y
-CONFIG_USB_HID=m
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_FSL=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
-CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_MMC_SDHCI=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_EDAC_MPC85XX=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_RTC_DRV_DS1374=y
-CONFIG_RTC_DRV_DS3232=y
-CONFIG_UIO=y
-CONFIG_VIRT_DRIVERS=y
-CONFIG_FSL_HV_MANAGER=y
-CONFIG_STAGING=y
-CONFIG_FSL_CORENET_CF=y
-CONFIG_CLK_QORIQ=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_ISO9660_FS=m
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_NTFS_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_INFO=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_SHIRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_RCU_TRACE=y
-CONFIG_CRYPTO_NULL=y
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_MD4=y
-CONFIG_CRYPTO_SHA256=y
-CONFIG_CRYPTO_SHA512=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DEV_FSL_CAAM=y
diff --git a/arch/powerpc/configs/corenet_basic_defconfig b/arch/powerpc/configs/corenet_basic_defconfig
new file mode 100644
index 000000000000..b568d465e59e
--- /dev/null
+++ b/arch/powerpc/configs/corenet_basic_defconfig
@@ -0,0 +1 @@
+CONFIG_CORENET_GENERIC=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/fsl-emb-nonhw.config
index 33cd1df818ad..41e4d359524d 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -1,176 +1,126 @@
-CONFIG_PPC64=y
-CONFIG_PPC_BOOK3E_64=y
-CONFIG_ALTIVEC=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=24
-CONFIG_SYSVIPC=y
-CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
+CONFIG_ADFS_FS=m
+CONFIG_AFFS_FS=m
+CONFIG_AUDIT=y
+CONFIG_BEFS_FS=m
+CONFIG_BFS_FS=m
+CONFIG_BINFMT_MISC=m
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=y
+CONFIG_BLK_DEV_RAM_SIZE=131072
+CONFIG_BLK_DEV_RAM=y
 CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_CGROUPS=y
-CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_BLK_DEV_INITRD=y
+CONFIG_CGROUPS=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_CRC_T10DIF=y
+CONFIG_CPUSETS=y
+CONFIG_CRAMFS=y
+CONFIG_CRYPTO_MD4=y
+CONFIG_CRYPTO_NULL=y
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DEVTMPFS=y
+CONFIG_DUMMY=y
+CONFIG_EFS_FS=m
 CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_CORENET_GENERIC=y
-# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
-CONFIG_BINFMT_MISC=m
-CONFIG_MATH_EMULATION=y
-CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED=y
-CONFIG_PCIEPORTBUS=y
-CONFIG_PCI_MSI=y
-CONFIG_RAPIDIO=y
-CONFIG_FSL_RIO=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
+CONFIG_EXT2_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT3_FS=y
+CONFIG_FB=y
+CONFIG_FHANDLE=y
+CONFIG_FIXED_PHY=y
+CONFIG_FONT_8x16=y
+CONFIG_FONT_8x8=y
+CONFIG_FONTS=y
+CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAME_WARN=1024
+CONFIG_FTL=y
+CONFIG_HFS_FS=m
+CONFIG_HFSPLUS_FS=m
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_HPFS_FS=m
+CONFIG_HUGETLBFS=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_IKCONFIG=y
+CONFIG_INET_AH=y
+CONFIG_INET_ESP=y
+CONFIG_INET_IPCOMP=y
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NET_IPIP=y
 CONFIG_IP_MROUTE=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_INET_ESP=y
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_PNP=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_IP_SCTP=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_FTL=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_FSL_ELBC=y
-CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_SPI_NOR=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_EEPROM_LEGACY=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_ATA=y
-CONFIG_SATA_FSL=y
-CONFIG_SATA_SIL24=y
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=y
-CONFIG_FSL_PQ_MDIO=y
-CONFIG_FSL_XGMAC_MDIO=y
-CONFIG_E1000E=y
-CONFIG_VITESSE_PHY=y
-CONFIG_FIXED_PHY=y
-CONFIG_MDIO_BUS_MUX_GPIO=y
-CONFIG_MDIO_BUS_MUX_MMIOREG=y
-CONFIG_INPUT_FF_MEMLESS=m
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_SERIO_LIBPS2=y
-CONFIG_PPC_EPAPR_HV_BYTECHAN=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_DETECT_IRQ=y
-CONFIG_SERIAL_8250_RSA=y
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_MPC=y
-CONFIG_I2C_MUX=y
-CONFIG_I2C_MUX_PCA954x=y
-CONFIG_SPI=y
-CONFIG_SPI_GPIO=y
-CONFIG_SPI_FSL_SPI=y
-CONFIG_SPI_FSL_ESPI=y
-CONFIG_SENSORS_LM90=y
-CONFIG_SENSORS_INA2XX=y
-CONFIG_USB_HID=m
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_FSL=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_MMC_SDHCI=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_RTC_DRV_DS1374=y
-CONFIG_RTC_DRV_DS3232=y
-CONFIG_DMADEVICES=y
-CONFIG_FSL_DMA=y
-CONFIG_VIRT_DRIVERS=y
-CONFIG_FSL_HV_MANAGER=y
-CONFIG_CLK_QORIQ=y
-CONFIG_FSL_CORENET_CF=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_IPV6=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_ISO9660_FS=m
+CONFIG_JFFS2_FS_DEBUG=1
+CONFIG_JFFS2_FS=y
 CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_MAC_PARTITION=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
 CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_NTFS_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_FS_DEBUG=1
-CONFIG_UBIFS_FS=y
+CONFIG_MTD_UBI=y
+CONFIG_MTD=y
+CONFIG_NET_IPIP=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_NET_KEY=y
+CONFIG_NET=y
+CONFIG_NFSD=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
-CONFIG_CRC_T10DIF=y
-CONFIG_DEBUG_INFO=y
-CONFIG_FRAME_WARN=1024
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_SHIRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_NULL=y
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_MD4=y
-CONFIG_CRYPTO_SHA256=y
-CONFIG_CRYPTO_SHA512=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DEV_FSL_CAAM=y
+CONFIG_NO_HZ=y
+CONFIG_NTFS_FS=y
+CONFIG_PACKET=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_PERF_EVENTS=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_QNX4FS_FS=m
+CONFIG_RCU_TRACE=y
+CONFIG_ROOT_NFS=y
+CONFIG_SYSV_FS=m
+CONFIG_SYSVIPC=y
+CONFIG_TMPFS=y
+CONFIG_UBIFS_FS=y
+CONFIG_UDF_FS=m
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_UFS_FS=m
+CONFIG_UIO=y
+CONFIG_UNIX=y
+CONFIG_VFAT_FS=y
+CONFIG_VXFS_FS=m
+CONFIG_XFRM_STATISTICS=y
+CONFIG_XFRM_SUB_POLICY=y
+CONFIG_XFRM_USER=y
+CONFIG_ZISOFS=y
diff --git a/arch/powerpc/configs/mpc85xx_basic_defconfig b/arch/powerpc/configs/mpc85xx_basic_defconfig
new file mode 100644
index 000000000000..850bd195d0e8
--- /dev/null
+++ b/arch/powerpc/configs/mpc85xx_basic_defconfig
@@ -0,0 +1,23 @@
+CONFIG_MATH_EMULATION=y
+CONFIG_MPC8536_DS=y
+CONFIG_MPC8540_ADS=y
+CONFIG_MPC8560_ADS=y
+CONFIG_MPC85xx_CDS=y
+CONFIG_MPC85xx_DS=y
+CONFIG_MPC85xx_MDS=y
+CONFIG_MPC85xx_RDB=y
+CONFIG_KSI8560=y
+CONFIG_MVME2500=y
+CONFIG_P1010_RDB=y
+CONFIG_P1022_DS=y
+CONFIG_P1022_RDK=y
+CONFIG_P1023_RDB=y
+CONFIG_SBC8548=y
+CONFIG_SOCRATES=y
+CONFIG_STX_GP3=y
+CONFIG_TQM8540=y
+CONFIG_TQM8541=y
+CONFIG_TQM8548=y
+CONFIG_TQM8555=y
+CONFIG_TQM8560=y
+CONFIG_XES_MPC85xx=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
deleted file mode 100644
index 6ecf7bdbc2f9..000000000000
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ /dev/null
@@ -1,252 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_PHYS_64BIT=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_C293_PCIE=y
-CONFIG_MPC8540_ADS=y
-CONFIG_MPC8560_ADS=y
-CONFIG_MPC85xx_CDS=y
-CONFIG_MPC85xx_MDS=y
-CONFIG_MPC8536_DS=y
-CONFIG_MPC85xx_DS=y
-CONFIG_MPC85xx_RDB=y
-CONFIG_P1010_RDB=y
-CONFIG_P1022_DS=y
-CONFIG_P1022_RDK=y
-CONFIG_P1023_RDB=y
-CONFIG_SOCRATES=y
-CONFIG_KSI8560=y
-CONFIG_XES_MPC85xx=y
-CONFIG_STX_GP3=y
-CONFIG_TQM8540=y
-CONFIG_TQM8541=y
-CONFIG_TQM8548=y
-CONFIG_TQM8555=y
-CONFIG_TQM8560=y
-CONFIG_SBC8548=y
-CONFIG_MVME2500=y
-CONFIG_QUICC_ENGINE=y
-CONFIG_QE_GPIO=y
-CONFIG_HIGHMEM=y
-CONFIG_BINFMT_MISC=m
-CONFIG_MATH_EMULATION=y
-CONFIG_FORCE_MAX_ZONEORDER=12
-CONFIG_PCI=y
-CONFIG_PCIEPORTBUS=y
-# CONFIG_PCIEASPM is not set
-CONFIG_PCI_MSI=y
-CONFIG_RAPIDIO=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NET_IPIP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_INET_ESP=y
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_IP_SCTP=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_FTL=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_PLATRAM=y
-CONFIG_MTD_M25P80=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_FSL_ELBC=y
-CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_SPI_NOR=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_EEPROM_AT24=y
-CONFIG_EEPROM_LEGACY=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_FSL=y
-CONFIG_SATA_SIL24=y
-CONFIG_PATA_ALI=y
-CONFIG_PATA_VIA=y
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=y
-CONFIG_FS_ENET=y
-CONFIG_UCC_GETH=y
-CONFIG_GIANFAR=y
-CONFIG_E1000=y
-CONFIG_E1000E=y
-CONFIG_IGB=y
-CONFIG_AT803X_PHY=y
-CONFIG_MARVELL_PHY=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_CICADA_PHY=y
-CONFIG_VITESSE_PHY=y
-CONFIG_BROADCOM_PHY=y
-CONFIG_FIXED_PHY=y
-CONFIG_INPUT_FF_MEMLESS=m
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_SERIO_LIBPS2=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=6
-CONFIG_SERIAL_8250_RUNTIME_UARTS=6
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_DETECT_IRQ=y
-CONFIG_SERIAL_8250_RSA=y
-CONFIG_SERIAL_QE=m
-CONFIG_NVRAM=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_CPM=m
-CONFIG_I2C_MPC=y
-CONFIG_SPI=y
-CONFIG_SPI_FSL_SPI=y
-CONFIG_SPI_FSL_ESPI=y
-CONFIG_GPIO_MPC8XXX=y
-CONFIG_SENSORS_LM90=y
-CONFIG_FB=y
-CONFIG_FB_FSL_DIU=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_INTEL8X0=y
-# CONFIG_SND_PPC is not set
-# CONFIG_SND_USB is not set
-CONFIG_SND_SOC=y
-CONFIG_SND_POWERPC_SOC=y
-CONFIG_HID_A4TECH=y
-CONFIG_HID_APPLE=y
-CONFIG_HID_BELKIN=y
-CONFIG_HID_CHERRY=y
-CONFIG_HID_CHICONY=y
-CONFIG_HID_CYPRESS=y
-CONFIG_HID_EZKEY=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_LOGITECH=y
-CONFIG_HID_MICROSOFT=y
-CONFIG_HID_MONTEREY=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_FSL=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
-CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_MMC_SDHCI=y
-CONFIG_MMC_SDHCI_PLTFM=y
-CONFIG_MMC_SDHCI_OF_ESDHC=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_EDAC_MPC85XX=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_RTC_DRV_DS1374=y
-CONFIG_RTC_DRV_DS3232=y
-CONFIG_RTC_DRV_CMOS=y
-CONFIG_DMADEVICES=y
-CONFIG_FSL_DMA=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_ISO9660_FS=m
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_NTFS_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_ADFS_FS=m
-CONFIG_AFFS_FS=m
-CONFIG_HFS_FS=m
-CONFIG_HFSPLUS_FS=m
-CONFIG_BEFS_FS=m
-CONFIG_BFS_FS=m
-CONFIG_EFS_FS=m
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_FS_DEBUG=1
-CONFIG_UBIFS_FS=y
-CONFIG_CRAMFS=y
-CONFIG_VXFS_FS=m
-CONFIG_HPFS_FS=m
-CONFIG_QNX4FS_FS=m
-CONFIG_SYSV_FS=m
-CONFIG_UFS_FS=m
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
-CONFIG_FONTS=y
-CONFIG_FONT_8x8=y
-CONFIG_FONT_8x16=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_FS=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_SHA256=y
-CONFIG_CRYPTO_SHA512=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DEV_FSL_CAAM=y
-CONFIG_CRYPTO_DEV_TALITOS=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
deleted file mode 100644
index b6c7111ea913..000000000000
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ /dev/null
@@ -1,244 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_PHYS_64BIT=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=8
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_C293_PCIE=y
-CONFIG_MPC8540_ADS=y
-CONFIG_MPC8560_ADS=y
-CONFIG_MPC85xx_CDS=y
-CONFIG_MPC85xx_MDS=y
-CONFIG_MPC8536_DS=y
-CONFIG_MPC85xx_DS=y
-CONFIG_MPC85xx_RDB=y
-CONFIG_P1010_RDB=y
-CONFIG_P1022_DS=y
-CONFIG_P1022_RDK=y
-CONFIG_P1023_RDB=y
-CONFIG_SOCRATES=y
-CONFIG_KSI8560=y
-CONFIG_XES_MPC85xx=y
-CONFIG_STX_GP3=y
-CONFIG_TQM8540=y
-CONFIG_TQM8541=y
-CONFIG_TQM8548=y
-CONFIG_TQM8555=y
-CONFIG_TQM8560=y
-CONFIG_SBC8548=y
-CONFIG_QUICC_ENGINE=y
-CONFIG_QE_GPIO=y
-CONFIG_HIGHMEM=y
-CONFIG_BINFMT_MISC=m
-CONFIG_MATH_EMULATION=y
-CONFIG_FORCE_MAX_ZONEORDER=12
-CONFIG_PCI=y
-CONFIG_PCI_MSI=y
-CONFIG_RAPIDIO=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NET_IPIP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_INET_ESP=y
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_IP_SCTP=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_FTL=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_FSL_ELBC=y
-CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_SPI_NOR=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_EEPROM_AT24=y
-CONFIG_EEPROM_LEGACY=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_FSL=y
-CONFIG_SATA_SIL24=y
-CONFIG_PATA_ALI=y
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=y
-CONFIG_FS_ENET=y
-CONFIG_UCC_GETH=y
-CONFIG_GIANFAR=y
-CONFIG_E1000E=y
-CONFIG_AT803X_PHY=y
-CONFIG_MARVELL_PHY=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_CICADA_PHY=y
-CONFIG_VITESSE_PHY=y
-CONFIG_FIXED_PHY=y
-CONFIG_INPUT_FF_MEMLESS=m
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_SERIO_LIBPS2=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=2
-CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_DETECT_IRQ=y
-CONFIG_SERIAL_8250_RSA=y
-CONFIG_SERIAL_QE=m
-CONFIG_NVRAM=y
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_CPM=m
-CONFIG_I2C_MPC=y
-CONFIG_SPI=y
-CONFIG_SPI_FSL_SPI=y
-CONFIG_SPI_FSL_ESPI=y
-CONFIG_GPIO_MPC8XXX=y
-CONFIG_SENSORS_LM90=y
-CONFIG_FB=y
-CONFIG_FB_FSL_DIU=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_INTEL8X0=y
-# CONFIG_SND_PPC is not set
-# CONFIG_SND_USB is not set
-CONFIG_SND_SOC=y
-CONFIG_SND_POWERPC_SOC=y
-CONFIG_HID_A4TECH=y
-CONFIG_HID_APPLE=y
-CONFIG_HID_BELKIN=y
-CONFIG_HID_CHERRY=y
-CONFIG_HID_CHICONY=y
-CONFIG_HID_CYPRESS=y
-CONFIG_HID_EZKEY=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_LOGITECH=y
-CONFIG_HID_MICROSOFT=y
-CONFIG_HID_MONTEREY=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_FSL=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
-CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_MMC_SDHCI=y
-CONFIG_MMC_SDHCI_PLTFM=y
-CONFIG_MMC_SDHCI_OF_ESDHC=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_RTC_DRV_DS1374=y
-CONFIG_RTC_DRV_DS3232=y
-CONFIG_RTC_DRV_CMOS=y
-CONFIG_DMADEVICES=y
-CONFIG_FSL_DMA=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_ISO9660_FS=m
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_NTFS_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_ADFS_FS=m
-CONFIG_AFFS_FS=m
-CONFIG_HFS_FS=m
-CONFIG_HFSPLUS_FS=m
-CONFIG_BEFS_FS=m
-CONFIG_BFS_FS=m
-CONFIG_EFS_FS=m
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_FS_DEBUG=1
-CONFIG_UBIFS_FS=y
-CONFIG_CRAMFS=y
-CONFIG_VXFS_FS=m
-CONFIG_HPFS_FS=m
-CONFIG_QNX4FS_FS=m
-CONFIG_SYSV_FS=m
-CONFIG_UFS_FS=m
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
-CONFIG_FONTS=y
-CONFIG_FONT_8x8=y
-CONFIG_FONT_8x16=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_FS=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_SHA256=y
-CONFIG_CRYPTO_SHA512=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DEV_FSL_CAAM=y
-CONFIG_CRYPTO_DEV_TALITOS=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index a97efc2146fd..6bc0ee4b1070 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -355,3 +355,6 @@ CONFIG_CRYPTO_DEV_NX_ENCRYPT=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=m
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=m
+CONFIG_LEDS_POWERNV=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 0d9efcedaf34..7991f37e5fe2 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -190,7 +190,8 @@ CONFIG_HVC_RTAS=y
 CONFIG_HVCS=m
 CONFIG_VIRTIO_CONSOLE=m
 CONFIG_IBM_BSR=m
-CONFIG_GEN_RTC=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_GENERIC=y
 CONFIG_RAW_DRIVER=y
 CONFIG_MAX_RAW_DEVS=1024
 CONFIG_FB=y
@@ -319,3 +320,6 @@ CONFIG_CRYPTO_DEV_NX_ENCRYPT=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=m
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=m
+CONFIG_LEDS_POWERNV=m
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 050712e1ce41..ab9f4e0ed4cf 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -6,5 +6,4 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h
-generic-y += trace_clock.h
 generic-y += vtime.h
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index 0cc6eedc4780..85e88f7a59c0 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -7,14 +7,23 @@
 
 static inline int arch_get_random_long(unsigned long *v)
 {
-	if (ppc_md.get_random_long)
-		return ppc_md.get_random_long(v);
-
 	return 0;
 }
 
 static inline int arch_get_random_int(unsigned int *v)
 {
+	return 0;
+}
+
+static inline int arch_get_random_seed_long(unsigned long *v)
+{
+	if (ppc_md.get_random_seed)
+		return ppc_md.get_random_seed(v);
+
+	return 0;
+}
+static inline int arch_get_random_seed_int(unsigned int *v)
+{
 	unsigned long val;
 	int rc;
 
@@ -27,22 +36,13 @@ static inline int arch_get_random_int(unsigned int *v)
 
 static inline int arch_has_random(void)
 {
-	return !!ppc_md.get_random_long;
-}
-
-static inline int arch_get_random_seed_long(unsigned long *v)
-{
-	return 0;
-}
-static inline int arch_get_random_seed_int(unsigned int *v)
-{
 	return 0;
 }
+
 static inline int arch_has_random_seed(void)
 {
-	return 0;
+	return !!ppc_md.get_random_seed;
 }
-
 #endif /* CONFIG_ARCH_RANDOM */
 
 #ifdef CONFIG_PPC_POWERNV
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 512d2782b043..55f106ed12bf 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -67,6 +67,10 @@ static __inline__ int atomic_##op##_return(int a, atomic_t *v)		\
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)
 
+ATOMIC_OP(and, and)
+ATOMIC_OP(or, or)
+ATOMIC_OP(xor, xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -304,6 +308,9 @@ static __inline__ long atomic64_##op##_return(long a, atomic64_t *v)	\
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(or, or)
+ATOMIC64_OP(xor, xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index 51ccc7232042..0eca6efc0631 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -76,12 +76,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_lwsync();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_lwsync();							\
 	___p1;								\
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 30b35fff2dea..6229e6b6037b 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -40,7 +40,12 @@ extern void __flush_dcache_icache(void *page_va);
 extern void flush_dcache_icache_page(struct page *page);
 #if defined(CONFIG_PPC32) && !defined(CONFIG_BOOKE)
 extern void __flush_dcache_icache_phys(unsigned long physaddr);
-#endif /* CONFIG_PPC32 && !CONFIG_BOOKE */
+#else
+static inline void __flush_dcache_icache_phys(unsigned long physaddr)
+{
+	BUG();
+}
+#endif
 
 extern void flush_dcache_range(unsigned long start, unsigned long stop);
 #ifdef CONFIG_PPC32
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 8251a3ba870f..e8d9ef4755a4 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -20,15 +20,6 @@
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 
 /*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-extern __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
-					__wsum sum);
-
-/*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
  *
@@ -127,6 +118,34 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 #endif
 }
 
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+#ifdef __powerpc64__
+	u64 res = (__force u64)csum;
+
+	res += (__force u64)addend;
+	return (__force __wsum)((u32)res + (res >> 32));
+#else
+	asm("addc %0,%0,%1;"
+	    "addze %0,%0;"
+	    : "+r" (csum) : "r" (addend));
+	return csum;
+#endif
+}
+
 #endif
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index b142b8e0ed9e..4f2df589ec1d 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -174,6 +174,13 @@ typedef struct compat_siginfo {
 			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
 			int _fd;
 		} _sigpoll;
+
+		/* SIGSYS */
+		struct {
+			unsigned int _call_addr; /* calling insn */
+			int _syscall;		 /* triggering system call number */
+			unsigned int _arch;	 /* AUDIT_ARCH_* of syscall */
+		} _sigsys;
 	} _sifields;
 } compat_siginfo_t;
 
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index e9bdda88f1fb..406c2b1ff82d 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -10,6 +10,7 @@ struct dma_map_ops;
 struct device_node;
 #ifdef CONFIG_PPC64
 struct pci_dn;
+struct iommu_table;
 #endif
 
 /*
@@ -23,13 +24,15 @@ struct dev_archdata {
 	struct dma_map_ops	*dma_ops;
 
 	/*
-	 * When an iommu is in use, dma_data is used as a ptr to the base of the
-	 * iommu_table.  Otherwise, it is a simple numerical offset.
+	 * These two used to be a union. However, with the hybrid ops we need
+	 * both so here we store both a DMA offset for direct mappings and
+	 * an iommu_table for remapped DMA.
 	 */
-	union {
-		dma_addr_t	dma_offset;
-		void		*iommu_table_base;
-	} dma_data;
+	dma_addr_t		dma_offset;
+
+#ifdef CONFIG_PPC64
+	struct iommu_table	*iommu_table_base;
+#endif
 
 #ifdef CONFIG_IOMMU_API
 	void			*iommu_domain;
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 9103687b0436..710f60e380e0 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -21,12 +21,12 @@
 #define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
 
 /* Some dma direct funcs must be visible for use in other dma_ops */
-extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
+extern void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
+					 dma_addr_t *dma_handle, gfp_t flag,
+					 struct dma_attrs *attrs);
+extern void __dma_direct_free_coherent(struct device *dev, size_t size,
+				       void *vaddr, dma_addr_t dma_handle,
 				       struct dma_attrs *attrs);
-extern void dma_direct_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle,
-				     struct dma_attrs *attrs);
 extern int dma_direct_mmap_coherent(struct device *dev,
 				    struct vm_area_struct *vma,
 				    void *cpu_addr, dma_addr_t handle,
@@ -106,7 +106,7 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 static inline dma_addr_t get_dma_offset(struct device *dev)
 {
 	if (dev)
-		return dev->archdata.dma_data.dma_offset;
+		return dev->archdata.dma_offset;
 
 	return PCI_DRAM_OFFSET;
 }
@@ -114,7 +114,7 @@ static inline dma_addr_t get_dma_offset(struct device *dev)
 static inline void set_dma_offset(struct device *dev, dma_addr_t off)
 {
 	if (dev)
-		dev->archdata.dma_data.dma_offset = off;
+		dev->archdata.dma_offset = off;
 }
 
 /* this will be removed soon */
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index e3661872fbea..ef89b1465573 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -2,7 +2,7 @@
 #define _ASM_POWERPC_FTRACE
 
 #ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR		((long)(_mcount))
+#define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifdef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index a8d2ef30d473..5879fde56f3c 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -721,6 +721,7 @@ extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size,
 				  unsigned long flags);
 extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
 #define ioremap_nocache(addr, size)	ioremap((addr), (size))
+#define ioremap_uc(addr, size)		ioremap((addr), (size))
 
 extern void iounmap(volatile void __iomem *addr);
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index ca18cff90900..7b87bab09564 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -2,17 +2,17 @@
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  * Rewrite, cleanup:
  * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
- * 
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
- * 
+ *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- * 
+ *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
@@ -131,16 +131,21 @@ int get_iommu_order(unsigned long size, struct iommu_table *tbl)
 
 struct scatterlist;
 
-static inline void set_iommu_table_base(struct device *dev, void *base)
+#ifdef CONFIG_PPC64
+
+static inline void set_iommu_table_base(struct device *dev,
+					struct iommu_table *base)
 {
-	dev->archdata.dma_data.iommu_table_base = base;
+	dev->archdata.iommu_table_base = base;
 }
 
 static inline void *get_iommu_table_base(struct device *dev)
 {
-	return dev->archdata.dma_data.iommu_table_base;
+	return dev->archdata.iommu_table_base;
 }
 
+extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
+
 /* Frees table for an individual device node */
 extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
 
@@ -225,6 +230,20 @@ static inline int __init tce_iommu_bus_notifier_init(void)
 }
 #endif /* !CONFIG_IOMMU_API */
 
+#else
+
+static inline void *get_iommu_table_base(struct device *dev)
+{
+	return NULL;
+}
+
+static inline int dma_iommu_dma_supported(struct device *dev, u64 mask)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PPC64 */
+
 extern int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			    struct scatterlist *sglist, int nelems,
 			    unsigned long mask,
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index efbf9a322a23..47e155f15433 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -18,14 +18,29 @@
 #define JUMP_ENTRY_TYPE		stringify_in_c(FTR_ENTRY_LONG)
 #define JUMP_LABEL_NOP_SIZE	4
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
 		 ".popsection \n\t"
-		 : :  "i" (key) : : l_yes);
+		 : :  "i" (&((char *)key)[branch]) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		 "b %l[l_yes]\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
+		 ".popsection \n\t"
+		 : :  "i" (&((char *)key)[branch]) : : l_yes);
+
 	return false;
 l_yes:
 	return true;
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 952579f5e79a..cab6753f1be5 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -249,7 +249,7 @@ struct machdep_calls {
 #endif
 
 #ifdef CONFIG_ARCH_RANDOM
-	int (*get_random_long)(unsigned long *v);
+	int (*get_random_seed)(unsigned long *v);
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/mpc52xx_psc.h b/arch/powerpc/include/asm/mpc52xx_psc.h
index d0ece257d310..04c7e8fc24c2 100644
--- a/arch/powerpc/include/asm/mpc52xx_psc.h
+++ b/arch/powerpc/include/asm/mpc52xx_psc.h
@@ -150,7 +150,10 @@
 
 /* Structure of the hardware registers */
 struct mpc52xx_psc {
-	u8		mode;		/* PSC + 0x00 */
+	union {
+		u8	mode;		/* PSC + 0x00 */
+		u8	mr2;
+	};
 	u8		reserved0[3];
 	union {				/* PSC + 0x04 */
 		u16	status;
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index e9e4c52f3685..8374afed9d0a 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -154,7 +154,10 @@
 #define OPAL_FLASH_WRITE			111
 #define OPAL_FLASH_ERASE			112
 #define OPAL_PRD_MSG				113
-#define OPAL_LAST				113
+#define OPAL_LEDS_GET_INDICATOR			114
+#define OPAL_LEDS_SET_INDICATOR			115
+#define OPAL_CEC_REBOOT2			116
+#define OPAL_LAST				116
 
 /* Device tree flags */
 
@@ -340,6 +343,18 @@ enum OpalPciResetState {
 	OPAL_ASSERT_RESET   = 1
 };
 
+enum OpalSlotLedType {
+	OPAL_SLOT_LED_TYPE_ID = 0,	/* IDENTIFY LED */
+	OPAL_SLOT_LED_TYPE_FAULT = 1,	/* FAULT LED */
+	OPAL_SLOT_LED_TYPE_ATTN = 2,	/* System Attention LED */
+	OPAL_SLOT_LED_TYPE_MAX = 3
+};
+
+enum OpalSlotLedState {
+	OPAL_SLOT_LED_STATE_OFF = 0,	/* LED is OFF */
+	OPAL_SLOT_LED_STATE_ON = 1	/* LED is ON */
+};
+
 /*
  * Address cycle types for LPC accesses. These also correspond
  * to the content of the first cell of the "reg" property for
@@ -361,6 +376,7 @@ enum opal_msg_type {
 	OPAL_MSG_HMI_EVT,
 	OPAL_MSG_DPO,
 	OPAL_MSG_PRD,
+	OPAL_MSG_OCC,
 	OPAL_MSG_TYPE_MAX,
 };
 
@@ -437,6 +453,7 @@ struct OpalMemoryErrorData {
 /* HMI interrupt event */
 enum OpalHMI_Version {
 	OpalHMIEvt_V1 = 1,
+	OpalHMIEvt_V2 = 2,
 };
 
 enum OpalHMI_Severity {
@@ -467,6 +484,49 @@ enum OpalHMI_ErrType {
 	OpalHMI_ERROR_CAPP_RECOVERY,
 };
 
+enum OpalHMI_XstopType {
+	CHECKSTOP_TYPE_UNKNOWN	=	0,
+	CHECKSTOP_TYPE_CORE	=	1,
+	CHECKSTOP_TYPE_NX	=	2,
+};
+
+enum OpalHMI_CoreXstopReason {
+	CORE_CHECKSTOP_IFU_REGFILE		= 0x00000001,
+	CORE_CHECKSTOP_IFU_LOGIC		= 0x00000002,
+	CORE_CHECKSTOP_PC_DURING_RECOV		= 0x00000004,
+	CORE_CHECKSTOP_ISU_REGFILE		= 0x00000008,
+	CORE_CHECKSTOP_ISU_LOGIC		= 0x00000010,
+	CORE_CHECKSTOP_FXU_LOGIC		= 0x00000020,
+	CORE_CHECKSTOP_VSU_LOGIC		= 0x00000040,
+	CORE_CHECKSTOP_PC_RECOV_IN_MAINT_MODE	= 0x00000080,
+	CORE_CHECKSTOP_LSU_REGFILE		= 0x00000100,
+	CORE_CHECKSTOP_PC_FWD_PROGRESS		= 0x00000200,
+	CORE_CHECKSTOP_LSU_LOGIC		= 0x00000400,
+	CORE_CHECKSTOP_PC_LOGIC			= 0x00000800,
+	CORE_CHECKSTOP_PC_HYP_RESOURCE		= 0x00001000,
+	CORE_CHECKSTOP_PC_HANG_RECOV_FAILED	= 0x00002000,
+	CORE_CHECKSTOP_PC_AMBI_HANG_DETECTED	= 0x00004000,
+	CORE_CHECKSTOP_PC_DEBUG_TRIG_ERR_INJ	= 0x00008000,
+	CORE_CHECKSTOP_PC_SPRD_HYP_ERR_INJ	= 0x00010000,
+};
+
+enum OpalHMI_NestAccelXstopReason {
+	NX_CHECKSTOP_SHM_INVAL_STATE_ERR	= 0x00000001,
+	NX_CHECKSTOP_DMA_INVAL_STATE_ERR_1	= 0x00000002,
+	NX_CHECKSTOP_DMA_INVAL_STATE_ERR_2	= 0x00000004,
+	NX_CHECKSTOP_DMA_CH0_INVAL_STATE_ERR	= 0x00000008,
+	NX_CHECKSTOP_DMA_CH1_INVAL_STATE_ERR	= 0x00000010,
+	NX_CHECKSTOP_DMA_CH2_INVAL_STATE_ERR	= 0x00000020,
+	NX_CHECKSTOP_DMA_CH3_INVAL_STATE_ERR	= 0x00000040,
+	NX_CHECKSTOP_DMA_CH4_INVAL_STATE_ERR	= 0x00000080,
+	NX_CHECKSTOP_DMA_CH5_INVAL_STATE_ERR	= 0x00000100,
+	NX_CHECKSTOP_DMA_CH6_INVAL_STATE_ERR	= 0x00000200,
+	NX_CHECKSTOP_DMA_CH7_INVAL_STATE_ERR	= 0x00000400,
+	NX_CHECKSTOP_DMA_CRB_UE			= 0x00000800,
+	NX_CHECKSTOP_DMA_CRB_SUE		= 0x00001000,
+	NX_CHECKSTOP_PBI_ISN_UE			= 0x00002000,
+};
+
 struct OpalHMIEvent {
 	uint8_t		version;	/* 0x00 */
 	uint8_t		severity;	/* 0x01 */
@@ -477,6 +537,23 @@ struct OpalHMIEvent {
 	__be64		hmer;
 	/* TFMR register. Valid only for TFAC and TFMR_PARITY error type. */
 	__be64		tfmr;
+
+	/* version 2 and later */
+	union {
+		/*
+		 * checkstop info (Core/NX).
+		 * Valid for OpalHMI_ERROR_MALFUNC_ALERT.
+		 */
+		struct {
+			uint8_t	xstop_type;	/* enum OpalHMI_XstopType */
+			uint8_t reserved_1[3];
+			__be32  xstop_reason;
+			union {
+				__be32 pir;	/* for CHECKSTOP_TYPE_CORE */
+				__be32 chip_id;	/* for CHECKSTOP_TYPE_NX */
+			} u;
+		} xstop_error;
+	} u;
 };
 
 enum {
@@ -700,6 +777,17 @@ struct opal_prd_msg_header {
 
 struct opal_prd_msg;
 
+#define OCC_RESET                       0
+#define OCC_LOAD                        1
+#define OCC_THROTTLE                    2
+#define OCC_MAX_THROTTLE_STATUS         5
+
+struct opal_occ_msg {
+	__be64 type;
+	__be64 chip;
+	__be64 throttle_status;
+};
+
 /*
  * SG entries
  *
@@ -756,6 +844,52 @@ struct opal_i2c_request {
 	__be64 buffer_ra;		/* Buffer real address */
 };
 
+/*
+ * EPOW status sharing (OPAL and the host)
+ *
+ * The host will pass on OPAL, a buffer of length OPAL_SYSEPOW_MAX
+ * with individual elements being 16 bits wide to fetch the system
+ * wide EPOW status. Each element in the buffer will contain the
+ * EPOW status in it's bit representation for a particular EPOW sub
+ * class as defiend here. So multiple detailed EPOW status bits
+ * specific for any sub class can be represented in a single buffer
+ * element as it's bit representation.
+ */
+
+/* System EPOW type */
+enum OpalSysEpow {
+	OPAL_SYSEPOW_POWER	= 0,	/* Power EPOW */
+	OPAL_SYSEPOW_TEMP	= 1,	/* Temperature EPOW */
+	OPAL_SYSEPOW_COOLING	= 2,	/* Cooling EPOW */
+	OPAL_SYSEPOW_MAX	= 3,	/* Max EPOW categories */
+};
+
+/* Power EPOW */
+enum OpalSysPower {
+	OPAL_SYSPOWER_UPS	= 0x0001, /* System on UPS power */
+	OPAL_SYSPOWER_CHNG	= 0x0002, /* System power config change */
+	OPAL_SYSPOWER_FAIL	= 0x0004, /* System impending power failure */
+	OPAL_SYSPOWER_INCL	= 0x0008, /* System incomplete power */
+};
+
+/* Temperature EPOW */
+enum OpalSysTemp {
+	OPAL_SYSTEMP_AMB	= 0x0001, /* System over ambient temperature */
+	OPAL_SYSTEMP_INT	= 0x0002, /* System over internal temperature */
+	OPAL_SYSTEMP_HMD	= 0x0004, /* System over ambient humidity */
+};
+
+/* Cooling EPOW */
+enum OpalSysCooling {
+	OPAL_SYSCOOL_INSF	= 0x0001, /* System insufficient cooling */
+};
+
+/* Argument to OPAL_CEC_REBOOT2() */
+enum {
+	OPAL_REBOOT_NORMAL		= 0,
+	OPAL_REBOOT_PLATFORM_ERROR	= 1,
+};
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_API_H */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 958e941c0cda..800115910e43 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -44,6 +44,7 @@ int64_t opal_tpo_write(uint64_t token, uint32_t year_mon_day,
 		       uint32_t hour_min);
 int64_t opal_cec_power_down(uint64_t request);
 int64_t opal_cec_reboot(void);
+int64_t opal_cec_reboot2(uint32_t reboot_type, char *diag);
 int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
 int64_t opal_write_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
 int64_t opal_handle_interrupt(uint64_t isn, __be64 *outstanding_event_mask);
@@ -141,7 +142,8 @@ int64_t opal_pci_fence_phb(uint64_t phb_id);
 int64_t opal_pci_reinit(uint64_t phb_id, uint64_t reinit_scope, uint64_t data);
 int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action);
 int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action);
-int64_t opal_get_epow_status(__be64 *status);
+int64_t opal_get_epow_status(__be16 *epow_status, __be16 *num_epow_classes);
+int64_t opal_get_dpo_status(__be64 *dpo_timeout);
 int64_t opal_set_system_attention_led(uint8_t led_action);
 int64_t opal_pci_next_error(uint64_t phb_id, __be64 *first_frozen_pe,
 			    __be16 *pci_error_type, __be16 *severity);
@@ -195,6 +197,10 @@ int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
 int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id,
 			 struct opal_i2c_request *oreq);
 int64_t opal_prd_msg(struct opal_prd_msg *msg);
+int64_t opal_leds_get_ind(char *loc_code, __be64 *led_mask,
+			  __be64 *led_value, __be64 *max_led_type);
+int64_t opal_leds_set_ind(uint64_t token, char *loc_code, const u64 led_mask,
+			  const u64 led_value, __be64 *max_led_type);
 
 int64_t opal_flash_read(uint64_t id, uint64_t offset, uint64_t buf,
 		uint64_t size, uint64_t token);
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 712add590445..37fc53587bb4 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -42,6 +42,7 @@ struct pci_controller_ops {
 #endif
 
 	int             (*dma_set_mask)(struct pci_dev *dev, u64 dma_mask);
+	u64		(*dma_get_required_mask)(struct pci_dev *dev);
 
 	void		(*shutdown)(struct pci_controller *);
 };
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 3bb7488bd24b..fa1dfb7f7b48 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -134,11 +134,11 @@
 
 #define pte_iterate_hashed_end() } while(0)
 
-#ifdef CONFIG_PPC_HAS_HASH_64K
-#define pte_pagesize_index(mm, addr, pte)	get_slice_psize(mm, addr)
-#else
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
 #define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
-#endif
 
 #endif /* __real_pte */
 
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 11a38635dd65..0717693c8428 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -169,6 +169,17 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * cases, and 32-bit non-hash with 32-bit PTEs.
 	 */
 	*ptep = pte;
+
+#ifdef CONFIG_PPC_BOOK3E_64
+	/*
+	 * With hardware tablewalk, a sync is needed to ensure that
+	 * subsequent accesses see the PTE we just wrote.  Unlike userspace
+	 * mappings, we can't tolerate spurious faults, so make sure
+	 * the new PTE will be seen the first time.
+	 */
+	if (is_kernel_addr(addr))
+		mb();
+#endif
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 4122a86d6858..ca0c5bff7849 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -61,6 +61,7 @@ int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
 int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
 void eeh_pe_state_mark(struct eeh_pe *pe, int state);
 void eeh_pe_state_clear(struct eeh_pe *pe, int state);
+void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state);
 void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode);
 
 void eeh_sysfs_add_device(struct pci_dev *pdev);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 28ded5d9b579..5afea361beaa 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -264,7 +264,6 @@ struct thread_struct {
 	u64		tm_tfhar;	/* Transaction fail handler addr */
 	u64		tm_texasr;	/* Transaction exception & summary */
 	u64		tm_tfiar;	/* Transaction fail instr address reg */
-	unsigned long	tm_orig_msr;	/* Thread's MSR on ctx switch */
 	struct pt_regs	ckpt_regs;	/* Checkpointed registers */
 
 	unsigned long	tm_tar;
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index b7c8d079c121..71537a319fc8 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -109,7 +109,8 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
  * the processor might need it for DMA coherency.
  */
 #define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU)
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU) || \
+	defined(CONFIG_PPC_E500MC)
 #define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
 #else
 #define _PAGE_BASE	(_PAGE_BASE_NC)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index af56b5c6c81a..aa1cc5f015ee 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1193,8 +1193,7 @@
 #ifdef CONFIG_PPC_BOOK3S_64
 #define __mtmsrd(v, l)	asm volatile("mtmsrd %0," __stringify(l) \
 				     : : "r" (v) : "memory")
-#define mtmsrd(v)	__mtmsrd((v), 0)
-#define mtmsr(v)	mtmsrd(v)
+#define mtmsr(v)	__mtmsrd((v), 0)
 #else
 #define mtmsr(v)	asm volatile("mtmsr %0" : \
 				     : "r" ((unsigned long)(v)) \
@@ -1281,6 +1280,15 @@ struct pt_regs;
 
 extern void ppc_save_regs(struct pt_regs *regs);
 
+static inline void update_power8_hid0(unsigned long hid0)
+{
+	/*
+	 *  The HID0 update on Power8 should at the very least be
+	 *  preceded by a a SYNC instruction followed by an ISYNC
+	 *  instruction
+	 */
+	asm volatile("sync; mtspr %0,%1; isync":: "i"(SPRN_HID0), "r"(hid0));
+}
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_REG_H */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 7a4ede16b283..b77ef369c0f0 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -343,6 +343,7 @@ extern void rtas_power_off(void);
 extern void rtas_halt(void);
 extern void rtas_os_term(char *str);
 extern int rtas_get_sensor(int sensor, int index, int *state);
+extern int rtas_get_sensor_fast(int sensor, int index, int *state);
 extern int rtas_get_power_level(int powerdomain, int *level);
 extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
 extern bool rtas_indicator_present(int token, int *maxindex);
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 4dbe072eecbe..523673d7583c 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -28,8 +28,6 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
-#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
-
 #ifdef CONFIG_PPC64
 /* use 0x800000yy when locked, where yy == CPU number */
 #ifdef __BIG_ENDIAN__
diff --git a/arch/powerpc/include/asm/spu_csa.h b/arch/powerpc/include/asm/spu_csa.h
index a40fd491250c..51f80b41cda3 100644
--- a/arch/powerpc/include/asm/spu_csa.h
+++ b/arch/powerpc/include/asm/spu_csa.h
@@ -241,12 +241,6 @@ struct spu_priv2_collapsed {
  */
 struct spu_state {
 	struct spu_lscsa *lscsa;
-#ifdef CONFIG_SPU_FS_64K_LS
-	int		use_big_pages;
-	/* One struct page per 64k page */
-#define SPU_LSCSA_NUM_BIG_PAGES	(sizeof(struct spu_lscsa) / 0x10000)
-	struct page	*lscsa_pages[SPU_LSCSA_NUM_BIG_PAGES];
-#endif
 	struct spu_problem_collapsed prob;
 	struct spu_priv1_collapsed priv1;
 	struct spu_priv2_collapsed priv2;
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 58abeda64cb7..15cca17cba4b 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -29,6 +29,7 @@ static inline void save_early_sprs(struct thread_struct *prev) {}
 
 extern void enable_kernel_fp(void);
 extern void enable_kernel_altivec(void);
+extern void enable_kernel_vsx(void);
 extern int emulate_altivec(struct pt_regs *);
 extern void __giveup_vsx(struct task_struct *);
 extern void giveup_vsx(struct task_struct *);
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index ff21b7a2f0cc..ab9f3f0a8637 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -22,10 +22,15 @@
 extern const unsigned long sys_call_table[];
 #endif /* CONFIG_FTRACE_SYSCALLS */
 
-static inline long syscall_get_nr(struct task_struct *task,
-				  struct pt_regs *regs)
+static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	return TRAP(regs) == 0xc00 ? regs->gpr[0] : -1L;
+	/*
+	 * Note that we are returning an int here. That means 0xffffffff, ie.
+	 * 32-bit negative 1, will be interpreted as -1 on a 64-bit kernel.
+	 * This is important for seccomp so that compat tasks can set r0 = -1
+	 * to reject the syscall.
+	 */
+	return TRAP(regs) == 0xc00 ? regs->gpr[0] : -1;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
@@ -34,12 +39,6 @@ static inline void syscall_rollback(struct task_struct *task,
 	regs->gpr[3] = regs->orig_gpr3;
 }
 
-static inline long syscall_get_error(struct task_struct *task,
-				     struct pt_regs *regs)
-{
-	return (regs->ccr & 0x10000000) ? -regs->gpr[3] : 0;
-}
-
 static inline long syscall_get_return_value(struct task_struct *task,
 					    struct pt_regs *regs)
 {
@@ -50,9 +49,15 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
+	/*
+	 * In the general case it's not obvious that we must deal with CCR
+	 * here, as the syscall exit path will also do that for us. However
+	 * there are some places, eg. the signal code, which check ccr to
+	 * decide if the value in r3 is actually an error.
+	 */
 	if (error) {
 		regs->ccr |= 0x10000000L;
-		regs->gpr[3] = -error;
+		regs->gpr[3] = error;
 	} else {
 		regs->ccr &= ~0x10000000L;
 		regs->gpr[3] = val;
@@ -64,19 +69,22 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	unsigned long val, mask = -1UL;
+
 	BUG_ON(i + n > 6);
-#ifdef CONFIG_PPC64
-	if (test_tsk_thread_flag(task, TIF_32BIT)) {
-		/*
-		 * Zero-extend 32-bit argument values.  The high bits are
-		 * garbage ignored by the actual syscall dispatch.
-		 */
-		while (n-- > 0)
-			args[n] = (u32) regs->gpr[3 + i + n];
-		return;
-	}
+
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_32BIT))
+		mask = 0xffffffff;
 #endif
-	memcpy(args, &regs->gpr[3 + i], n * sizeof(args[0]));
+	while (n--) {
+		if (n == 0 && i == 0)
+			val = regs->orig_gpr3;
+		else
+			val = regs->gpr[3 + i + n];
+
+		args[n] = val & mask;
+	}
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
@@ -86,6 +94,10 @@ static inline void syscall_set_arguments(struct task_struct *task,
 {
 	BUG_ON(i + n > 6);
 	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
+
+	/* Also copy the first argument into orig_gpr3 */
+	if (i == 0 && n > 0)
+		regs->orig_gpr3 = args[0];
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/powerpc/include/asm/trace_clock.h b/arch/powerpc/include/asm/trace_clock.h
new file mode 100644
index 000000000000..cf1ee75ca069
--- /dev/null
+++ b/arch/powerpc/include/asm/trace_clock.h
@@ -0,0 +1,19 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#ifndef _ASM_PPC_TRACE_CLOCK_H
+#define _ASM_PPC_TRACE_CLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+extern u64 notrace trace_clock_ppc_tb(void);
+
+#define ARCH_TRACE_CLOCKS { trace_clock_ppc_tb, "ppc-tb", 0 },
+
+#endif  /* _ASM_PPC_TRACE_CLOCK_H */
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index f44a027818af..dab3717e3ea0 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -6,6 +6,7 @@ header-y += bitsperlong.h
 header-y += bootx.h
 header-y += byteorder.h
 header-y += cputable.h
+header-y += eeh.h
 header-y += elf.h
 header-y += epapr_hcalls.h
 header-y += errno.h
diff --git a/arch/powerpc/include/uapi/asm/errno.h b/arch/powerpc/include/uapi/asm/errno.h
index 8c145fd17d86..e8b6b5f7de7c 100644
--- a/arch/powerpc/include/uapi/asm/errno.h
+++ b/arch/powerpc/include/uapi/asm/errno.h
@@ -6,6 +6,4 @@
 #undef	EDEADLOCK
 #define	EDEADLOCK	58	/* File locking deadlock error */
 
-#define _LAST_ERRNO	516
-
 #endif	/* _ASM_POWERPC_ERRNO_H */
diff --git a/arch/powerpc/include/uapi/asm/sigcontext.h b/arch/powerpc/include/uapi/asm/sigcontext.h
index 9c1f24fd5d11..3ad0c7f001a9 100644
--- a/arch/powerpc/include/uapi/asm/sigcontext.h
+++ b/arch/powerpc/include/uapi/asm/sigcontext.h
@@ -28,7 +28,7 @@ struct sigcontext {
 /*
  * To maintain compatibility with current implementations the sigcontext is
  * extended by appending a pointer (v_regs) to a quadword type (elf_vrreg_t)
- * followed by an unstructured (vmx_reserve) field of 69 doublewords.  This
+ * followed by an unstructured (vmx_reserve) field of 101 doublewords. This
  * allows the array of vector registers to be quadword aligned independent of
  * the alignment of the containing sigcontext or ucontext. It is the
  * responsibility of the code setting the sigcontext to set this pointer to
@@ -80,7 +80,7 @@ struct sigcontext {
  * registers and vscr/vrsave.
  */
 	elf_vrreg_t	__user *v_regs;
-	long		vmx_reserve[ELF_NVRREG+ELF_NVRREG+32+1];
+	long		vmx_reserve[ELF_NVRREG + ELF_NVRREG + 1 + 32];
 #endif
 };
 
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 12868b1c4e05..ba336930d448 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -118,6 +118,7 @@ obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
+obj-$(CONFIG_TRACING)		+= trace_clock.o
 
 ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y				+= iomap.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 98230579d99c..810f433731dc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -213,7 +213,6 @@ int main(void)
 		offsetof(struct tlb_core_data, esel_max));
 	DEFINE(TCD_ESEL_FIRST,
 		offsetof(struct tlb_core_data, esel_first));
-	DEFINE(TCD_LOCK, offsetof(struct tlb_core_data, lock));
 #endif /* CONFIG_PPC_BOOK3E */
 
 #ifdef CONFIG_PPC_STD_MMU_64
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 4c68bfe4108a..41a7d9d49a5a 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -73,7 +73,7 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 }
 
 /* We support DMA to/from any memory page via the iommu */
-static int dma_iommu_dma_supported(struct device *dev, u64 mask)
+int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 6e8d764ce47b..c6689f658b50 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -47,8 +47,8 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
  * for everything else.
  */
 struct dma_map_ops swiotlb_dma_ops = {
-	.alloc = dma_direct_alloc_coherent,
-	.free = dma_direct_free_coherent,
+	.alloc = __dma_direct_alloc_coherent,
+	.free = __dma_direct_free_coherent,
 	.mmap = dma_direct_mmap_coherent,
 	.map_sg = swiotlb_map_sg_attrs,
 	.unmap_sg = swiotlb_unmap_sg_attrs,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 35e4dcc5dce3..59503ed98e5f 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -16,6 +16,7 @@
 #include <asm/bug.h>
 #include <asm/machdep.h>
 #include <asm/swiotlb.h>
+#include <asm/iommu.h>
 
 /*
  * Generic direct DMA implementation
@@ -39,9 +40,31 @@ static u64 __maybe_unused get_pfn_limit(struct device *dev)
 	return pfn;
 }
 
-void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag,
-				struct dma_attrs *attrs)
+static int dma_direct_dma_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_PPC64
+	u64 limit = get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
+
+	/* Limit fits in the mask, we are good */
+	if (mask >= limit)
+		return 1;
+
+#ifdef CONFIG_FSL_SOC
+	/* Freescale gets another chance via ZONE_DMA/ZONE_DMA32, however
+	 * that will have to be refined if/when they support iommus
+	 */
+	return 1;
+#endif
+	/* Sorry ... */
+	return 0;
+#else
+	return 1;
+#endif
+}
+
+void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flag,
+				  struct dma_attrs *attrs)
 {
 	void *ret;
 #ifdef CONFIG_NOT_COHERENT_CACHE
@@ -96,9 +119,9 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 #endif
 }
 
-void dma_direct_free_coherent(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle,
-			      struct dma_attrs *attrs)
+void __dma_direct_free_coherent(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle,
+				struct dma_attrs *attrs)
 {
 #ifdef CONFIG_NOT_COHERENT_CACHE
 	__dma_free_coherent(size, vaddr);
@@ -107,6 +130,51 @@ void dma_direct_free_coherent(struct device *dev, size_t size,
 #endif
 }
 
+static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs)
+{
+	struct iommu_table *iommu;
+
+	/* The coherent mask may be smaller than the real mask, check if
+	 * we can really use the direct ops
+	 */
+	if (dma_direct_dma_supported(dev, dev->coherent_dma_mask))
+		return __dma_direct_alloc_coherent(dev, size, dma_handle,
+						   flag, attrs);
+
+	/* Ok we can't ... do we have an iommu ? If not, fail */
+	iommu = get_iommu_table_base(dev);
+	if (!iommu)
+		return NULL;
+
+	/* Try to use the iommu */
+	return iommu_alloc_coherent(dev, iommu, size, dma_handle,
+				    dev->coherent_dma_mask, flag,
+				    dev_to_node(dev));
+}
+
+static void dma_direct_free_coherent(struct device *dev, size_t size,
+				     void *vaddr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs)
+{
+	struct iommu_table *iommu;
+
+	/* See comments in dma_direct_alloc_coherent() */
+	if (dma_direct_dma_supported(dev, dev->coherent_dma_mask))
+		return __dma_direct_free_coherent(dev, size, vaddr, dma_handle,
+						  attrs);
+	/* Maybe we used an iommu ... */
+	iommu = get_iommu_table_base(dev);
+
+	/* If we hit that we should have never allocated in the first
+	 * place so how come we are freeing ?
+	 */
+	if (WARN_ON(!iommu))
+		return;
+	iommu_free_coherent(iommu, size, vaddr, dma_handle);
+}
+
 int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 			     void *cpu_addr, dma_addr_t handle, size_t size,
 			     struct dma_attrs *attrs)
@@ -147,18 +215,6 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
 {
 }
 
-static int dma_direct_dma_supported(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_PPC64
-	/* Could be improved so platforms can set the limit in case
-	 * they have limited DMA windows
-	 */
-	return mask >= get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
-#else
-	return 1;
-#endif
-}
-
 static u64 dma_direct_get_required_mask(struct device *dev)
 {
 	u64 end, mask;
@@ -230,6 +286,25 @@ struct dma_map_ops dma_direct_ops = {
 };
 EXPORT_SYMBOL(dma_direct_ops);
 
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (!dma_supported(dev, mask)) {
+		/*
+		 * We need to special case the direct DMA ops which can
+		 * support a fallback for coherent allocations. There
+		 * is no dma_op->set_coherent_mask() so we have to do
+		 * things the hard way:
+		 */
+		if (get_dma_ops(dev) != &dma_direct_ops ||
+		    get_iommu_table_base(dev) == NULL ||
+		    !dma_iommu_dma_supported(dev, mask))
+			return -EIO;
+	}
+	dev->coherent_dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_set_coherent_mask);
+
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
 int __dma_set_mask(struct device *dev, u64 dma_mask)
@@ -278,6 +353,13 @@ u64 dma_get_required_mask(struct device *dev)
 	if (ppc_md.dma_get_required_mask)
 		return ppc_md.dma_get_required_mask(dev);
 
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+		if (phb->controller_ops.dma_get_required_mask)
+			return phb->controller_ops.dma_get_required_mask(pdev);
+	}
+
 	return __dma_get_required_mask(dev);
 }
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index af9b597b10af..e968533e3e05 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -308,11 +308,26 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	if (!(pe->type & EEH_PE_PHB)) {
 		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+
+		/*
+		 * The config space of some PCI devices can't be accessed
+		 * when their PEs are in frozen state. Otherwise, fenced
+		 * PHB might be seen. Those PEs are identified with flag
+		 * EEH_PE_CFG_RESTRICTED, indicating EEH_PE_CFG_BLOCKED
+		 * is set automatically when the PE is put to EEH_PE_ISOLATED.
+		 *
+		 * Restoring BARs possibly triggers PCI config access in
+		 * (OPAL) firmware and then causes fenced PHB. If the
+		 * PCI config is blocked with flag EEH_PE_CFG_BLOCKED, it's
+		 * pointless to restore BARs and dump config space.
+		 */
 		eeh_ops->configure_bridge(pe);
-		eeh_pe_restore_bars(pe);
+		if (!(pe->state & EEH_PE_CFG_BLOCKED)) {
+			eeh_pe_restore_bars(pe);
 
-		pci_regs_buf[0] = 0;
-		eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+			pci_regs_buf[0] = 0;
+			eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+		}
 	}
 
 	eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
@@ -750,14 +765,14 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 		break;
 	case pcie_hot_reset:
-		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
-		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
@@ -1116,9 +1131,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 		return;
 	}
 
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->probe(pdn, NULL);
-
 	/*
 	 * The EEH cache might not be removed correctly because of
 	 * unbalanced kref to the device during unplug time, which
@@ -1142,6 +1154,9 @@ void eeh_add_device_late(struct pci_dev *dev)
 		dev->dev.archdata.edev = NULL;
 	}
 
+	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
+		eeh_ops->probe(pdn, NULL);
+
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 35f0b62259bb..8654cb166c19 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -657,6 +657,28 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
 	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
 }
 
+/**
+ * eeh_pe_state_mark_with_cfg - Mark PE state with unblocked config space
+ * @pe: PE
+ * @state: PE state to be set
+ *
+ * Set specified flag to PE and its child PEs. The PCI config space
+ * of some PEs is blocked automatically when EEH_PE_ISOLATED is set,
+ * which isn't needed in some situations. The function allows to set
+ * the specified flag to indicated PEs without blocking their PCI
+ * config space.
+ */
+void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state)
+{
+	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
+	if (!(state & EEH_PE_ISOLATED))
+		return;
+
+	/* Clear EEH_PE_CFG_BLOCKED, which might be set just now */
+	state = EEH_PE_CFG_BLOCKED;
+	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
+}
+
 /*
  * Some PCI bridges (e.g. PLX bridges) have primary/secondary
  * buses assigned explicitly by firmware, and we probably have
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 46fc0f4d8982..2405631e91a2 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -20,6 +20,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/sys.h>
 #include <linux/threads.h>
 #include <asm/reg.h>
@@ -354,7 +355,7 @@ ret_from_syscall:
 	SYNC
 	MTMSRD(r10)
 	lwz	r9,TI_FLAGS(r12)
-	li	r8,-_LAST_ERRNO
+	li	r8,-MAX_ERRNO
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	syscall_exit_work
 	cmplw	0,r3,r8
@@ -457,6 +458,10 @@ syscall_dotrace:
 	lwz	r7,GPR7(r1)
 	lwz	r8,GPR8(r1)
 	REST_NVGPRS(r1)
+
+	cmplwi	r0,NR_syscalls
+	/* Return code is already in r3 thanks to do_syscall_trace_enter() */
+	bge-	ret_from_syscall
 	b	syscall_dotrace_cont
 
 syscall_exit_work:
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 579e0f9a2d57..a94f155db78e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -19,6 +19,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/page.h>
@@ -150,8 +151,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	CURRENT_THREAD_INFO(r11, r1)
 	ld	r10,TI_FLAGS(r11)
 	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
-	bne	syscall_dotrace
-.Lsyscall_dotrace_cont:
+	bne	syscall_dotrace		/* does not return */
 	cmpldi	0,r0,NR_syscalls
 	bge-	syscall_enosys
 
@@ -207,7 +207,7 @@ system_call:			/* label this so stack traces look sane */
 #endif /* CONFIG_PPC_BOOK3E */
 
 	ld	r9,TI_FLAGS(r12)
-	li	r11,-_LAST_ERRNO
+	li	r11,-MAX_ERRNO
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	syscall_exit_work
 	cmpld	r3,r11
@@ -245,22 +245,34 @@ syscall_dotrace:
 	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_syscall_trace_enter
+
 	/*
-	 * Restore argument registers possibly just changed.
-	 * We use the return value of do_syscall_trace_enter
-	 * for the call number to look up in the table (r0).
+	 * We use the return value of do_syscall_trace_enter() as the syscall
+	 * number. If the syscall was rejected for any reason do_syscall_trace_enter()
+	 * returns an invalid syscall number and the test below against
+	 * NR_syscalls will fail.
 	 */
 	mr	r0,r3
+
+	/* Restore argument registers just clobbered and/or possibly changed. */
 	ld	r3,GPR3(r1)
 	ld	r4,GPR4(r1)
 	ld	r5,GPR5(r1)
 	ld	r6,GPR6(r1)
 	ld	r7,GPR7(r1)
 	ld	r8,GPR8(r1)
+
+	/* Repopulate r9 and r10 for the system_call path */
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 	CURRENT_THREAD_INFO(r10, r1)
 	ld	r10,TI_FLAGS(r10)
-	b	.Lsyscall_dotrace_cont
+
+	cmpldi	r0,NR_syscalls
+	blt+	system_call
+
+	/* Return code is already in r3 thanks to do_syscall_trace_enter() */
+	b	.Lsyscall_exit
+
 
 syscall_enosys:
 	li	r3,-ENOSYS
@@ -277,7 +289,7 @@ syscall_exit_work:
 	beq+	0f
 	REST_NVGPRS(r1)
 	b	2f
-0:	cmpld	r3,r11		/* r10 is -LAST_ERRNO */
+0:	cmpld	r3,r11		/* r11 is -MAX_ERRNO */
 	blt+	1f
 	andi.	r0,r9,_TIF_NOERROR
 	bne-	1f
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 3e68d1c69718..f3bd5e747ed8 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1313,11 +1313,14 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	sync
 	isync
 
-/* The mapping only needs to be cache-coherent on SMP */
-#ifdef CONFIG_SMP
-#define M_IF_SMP	MAS2_M
+/*
+ * The mapping only needs to be cache-coherent on SMP, except on
+ * Freescale e500mc derivatives where it's also needed for coherent DMA.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
+#define M_IF_NEEDED	MAS2_M
 #else
-#define M_IF_SMP	0
+#define M_IF_NEEDED	0
 #endif
 
 /* 6. Setup KERNELBASE mapping in TLB[0]
@@ -1332,7 +1335,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	ori	r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
 	mtspr	SPRN_MAS1,r6
 
-	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_SMP)
+	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_NEEDED)
 	mtspr	SPRN_MAS2,r6
 
 	rlwinm	r5,r5,0,0,25
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index f22e7e44fbf3..83dd0f6776b3 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -152,11 +152,14 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	tlbivax 0,r9
 	TLBSYNC
 
-/* The mapping only needs to be cache-coherent on SMP */
-#ifdef CONFIG_SMP
-#define M_IF_SMP	MAS2_M
+/*
+ * The mapping only needs to be cache-coherent on SMP, except on
+ * Freescale e500mc derivatives where it's also needed for coherent DMA.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
+#define M_IF_NEEDED	MAS2_M
 #else
-#define M_IF_SMP	0
+#define M_IF_NEEDED	0
 #endif
 
 #if defined(ENTRY_MAPPING_BOOT_SETUP)
@@ -167,8 +170,8 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	lis	r6,(MAS1_VALID|MAS1_IPROT)@h
 	ori	r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
 	mtspr	SPRN_MAS1,r6
-	lis	r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_SMP)@h
-	ori	r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_SMP)@l
+	lis	r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@h
+	ori	r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@l
 	mtspr	SPRN_MAS2,r6
 	mtspr	SPRN_MAS3,r8
 	tlbwe
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index ccde8f084ce4..112ccf497562 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -52,6 +52,22 @@
 	.text
 
 /*
+ * Used by threads when the lock bit of core_idle_state is set.
+ * Threads will spin in HMT_LOW until the lock bit is cleared.
+ * r14 - pointer to core_idle_state
+ * r15 - used to load contents of core_idle_state
+ */
+
+core_idle_lock_held:
+	HMT_LOW
+3:	lwz	r15,0(r14)
+	andi.   r15,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	3b
+	HMT_MEDIUM
+	lwarx	r15,0,r14
+	blr
+
+/*
  * Pass requested state in r3:
  *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE
  *
@@ -150,6 +166,10 @@ power7_enter_nap_mode:
 	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
 lwarx_loop1:
 	lwarx	r15,0,r14
+
+	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bnel	core_idle_lock_held
+
 	andc	r15,r15,r7			/* Clear thread bit */
 
 	andi.	r15,r15,PNV_CORE_IDLE_THREAD_BITS
@@ -294,7 +314,7 @@ lwarx_loop2:
 	 * workaround undo code or resyncing timebase or restoring context
 	 * In either case loop until the lock bit is cleared.
 	 */
-	bne	core_idle_lock_held
+	bnel	core_idle_lock_held
 
 	cmpwi	cr2,r15,0
 	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
@@ -319,15 +339,6 @@ lwarx_loop2:
 	isync
 	b	common_exit
 
-core_idle_lock_held:
-	HMT_LOW
-core_idle_lock_loop:
-	lwz	r15,0(14)
-	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
-	bne	core_idle_lock_loop
-	HMT_MEDIUM
-	b	lwarx_loop2
-
 first_thread_in_subcore:
 	/* First thread in subcore to wakeup */
 	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index a1ed8a8c7cb4..6472472093d0 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -17,7 +17,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 {
 	u32 *addr = (u32 *)(unsigned long)entry->code;
 
-	if (type == JUMP_LABEL_ENABLE)
+	if (type == JUMP_LABEL_JMP)
 		patch_branch(addr, entry->target, 0);
 	else
 		patch_instruction(addr, PPC_INST_NOP);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 33aa4ddf597d..9ad37f827a97 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -649,7 +649,6 @@ static void kvm_check_ins(u32 *inst, u32 features)
 			kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
 		}
 		break;
-		break;
 #endif
 	}
 
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7c6bb4b17b49..ed3ab509faca 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -596,25 +596,6 @@ _GLOBAL(copy_page)
 	b	2b
 
 /*
- * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
- * void atomic_set_mask(atomic_t mask, atomic_t *addr);
- */
-_GLOBAL(atomic_clear_mask)
-10:	lwarx	r5,0,r4
-	andc	r5,r5,r3
-	PPC405_ERR77(0,r4)
-	stwcx.	r5,0,r4
-	bne-	10b
-	blr
-_GLOBAL(atomic_set_mask)
-10:	lwarx	r5,0,r4
-	or	r5,r5,r3
-	PPC405_ERR77(0,r4)
-	stwcx.	r5,0,r4
-	bne-	10b
-	blr
-
-/*
  * Extended precision shifts.
  *
  * Updated to be valid for shift counts from 0 to 63 inclusive.
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4e314b90c75d..6e4168cf4698 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -475,9 +475,18 @@ _GLOBAL(kexec_wait)
 #ifdef CONFIG_KEXEC		/* use no memory without kexec */
 	lwz	r4,0(r5)
 	cmpwi	0,r4,0
-	bnea	0x60
+	beq	99b
+#ifdef CONFIG_PPC_BOOK3S_64
+	li	r10,0x60
+	mfmsr	r11
+	clrrdi	r11,r11,1	/* Clear MSR_LE */
+	mtsrr0	r10
+	mtsrr1	r11
+	rfid
+#else
+	ba	0x60
+#endif
 #endif
-	b	99b
 
 /* this can be in text because we won't change it until we are
  * running in real anyways
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 1e703f8ebad4..98ba106a59ef 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -541,10 +541,9 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 			time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
 			time->tv_nsec = 0;
 		}
-		*buf = kmalloc(length, GFP_KERNEL);
+		*buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
 		if (*buf == NULL)
 			return -ENOMEM;
-		memcpy(*buf, buff + hdr_size, length);
 		kfree(buff);
 
 		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
@@ -582,9 +581,10 @@ static int nvram_pstore_init(void)
 	spin_lock_init(&nvram_pstore_info.buf_lock);
 
 	rc = pstore_register(&nvram_pstore_info);
-	if (rc != 0)
-		pr_err("nvram: pstore_register() failed, defaults to "
-				"kmsg_dump; returned %d\n", rc);
+	if (rc && (rc != -EPERM))
+		/* Print error only when pstore.backend == nvram */
+		pr_err("nvram: pstore_register() failed, returned %d. "
+				"Defaults to kmsg_dump\n", rc);
 
 	return rc;
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index b9de34d44fcb..a1d0632d97c6 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -823,23 +823,15 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		    (reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
 			/* Only print message if not re-assigning */
 			if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC))
-				pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] "
-					 "is unassigned\n",
-					 pci_name(dev), i,
-					 (unsigned long long)res->start,
-					 (unsigned long long)res->end,
-					 (unsigned int)res->flags);
+				pr_debug("PCI:%s Resource %d %pR is unassigned\n",
+					 pci_name(dev), i, res);
 			res->end -= res->start;
 			res->start = 0;
 			res->flags |= IORESOURCE_UNSET;
 			continue;
 		}
 
-		pr_debug("PCI:%s Resource %d %016llx-%016llx [%x]\n",
-			 pci_name(dev), i,
-			 (unsigned long long)res->start,\
-			 (unsigned long long)res->end,
-			 (unsigned int)res->flags);
+		pr_debug("PCI:%s Resource %d %pR\n", pci_name(dev), i, res);
 	}
 
 	/* Call machine specific resource fixup */
@@ -943,11 +935,7 @@ static void pcibios_fixup_bridge(struct pci_bus *bus)
 			continue;
 		}
 
-		pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x]\n",
-			 pci_name(dev), i,
-			 (unsigned long long)res->start,\
-			 (unsigned long long)res->end,
-			 (unsigned int)res->flags);
+		pr_debug("PCI:%s Bus rsrc %d %pR\n", pci_name(dev), i, res);
 
 		/* Try to detect uninitialized P2P bridge resources,
 		 * and clear them out so they get re-assigned later
@@ -1044,13 +1032,7 @@ void pcibios_set_master(struct pci_dev *dev)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	/* When called from the generic PCI probe, read PCI<->PCI bridge
-	 * bases. This is -not- called when generating the PCI tree from
-	 * the OF device-tree.
-	 */
-	pci_read_bridge_bases(bus);
-
-	/* Now fixup the bus bus */
+	/* Fixup the bus */
 	pcibios_setup_bus_self(bus);
 
 	/* Now fixup devices on that bus */
@@ -1132,10 +1114,8 @@ static int reparent_resources(struct resource *parent,
 	*pp = NULL;
 	for (p = res->child; p != NULL; p = p->sibling) {
 		p->parent = res;
-		pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n",
-			 p->name,
-			 (unsigned long long)p->start,
-			 (unsigned long long)p->end, res->name);
+		pr_debug("PCI: Reparented %s %pR under %s\n",
+			 p->name, p, res->name);
 	}
 	return 0;
 }
@@ -1204,14 +1184,9 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			}
 		}
 
-		pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
-			 "[0x%x], parent %p (%s)\n",
-			 bus->self ? pci_name(bus->self) : "PHB",
-			 bus->number, i,
-			 (unsigned long long)res->start,
-			 (unsigned long long)res->end,
-			 (unsigned int)res->flags,
-			 pr, (pr && pr->name) ? pr->name : "nil");
+		pr_debug("PCI: %s (bus %d) bridge rsrc %d: %pR, parent %p (%s)\n",
+			 bus->self ? pci_name(bus->self) : "PHB", bus->number,
+			 i, res, pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
 			struct pci_dev *dev = bus->self;
@@ -1253,11 +1228,8 @@ static inline void alloc_resource(struct pci_dev *dev, int idx)
 {
 	struct resource *pr, *r = &dev->resource[idx];
 
-	pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
-		 pci_name(dev), idx,
-		 (unsigned long long)r->start,
-		 (unsigned long long)r->end,
-		 (unsigned int)r->flags);
+	pr_debug("PCI: Allocating %s: Resource %d: %pR\n",
+		 pci_name(dev), idx, r);
 
 	pr = pci_find_parent_resource(dev, r);
 	if (!pr || (pr->flags & IORESOURCE_UNSET) ||
@@ -1265,11 +1237,7 @@ static inline void alloc_resource(struct pci_dev *dev, int idx)
 		printk(KERN_WARNING "PCI: Cannot allocate resource region %d"
 		       " of device %s, will remap\n", idx, pci_name(dev));
 		if (pr)
-			pr_debug("PCI:  parent is %p: %016llx-%016llx [%x]\n",
-				 pr,
-				 (unsigned long long)pr->start,
-				 (unsigned long long)pr->end,
-				 (unsigned int)pr->flags);
+			pr_debug("PCI:  parent is %p: %pR\n", pr, pr);
 		/* We'll assign a new address later */
 		r->flags |= IORESOURCE_UNSET;
 		r->end -= r->start;
@@ -1431,12 +1399,8 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
 			if (r->parent || !r->start || !r->flags)
 				continue;
 
-			pr_debug("PCI: Claiming %s: "
-				 "Resource %d: %016llx..%016llx [%x]\n",
-				 pci_name(dev), i,
-				 (unsigned long long)r->start,
-				 (unsigned long long)r->end,
-				 (unsigned int)r->flags);
+			pr_debug("PCI: Claiming %s: Resource %d: %pR\n",
+				 pci_name(dev), i, r);
 
 			if (pci_claim_resource(dev, i) == 0)
 				continue;
@@ -1520,11 +1484,8 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 	} else {
 		offset = pcibios_io_space_offset(hose);
 
-		pr_debug("PCI: PHB IO resource    = %08llx-%08llx [%lx] off 0x%08llx\n",
-			 (unsigned long long)res->start,
-			 (unsigned long long)res->end,
-			 (unsigned long)res->flags,
-			 (unsigned long long)offset);
+		pr_debug("PCI: PHB IO resource    = %pR off 0x%08llx\n",
+			 res, (unsigned long long)offset);
 		pci_add_resource_offset(resources, res, offset);
 	}
 
@@ -1541,11 +1502,8 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 		offset = hose->mem_offset[i];
 
 
-		pr_debug("PCI: PHB MEM resource %d = %08llx-%08llx [%lx] off 0x%08llx\n", i,
-			 (unsigned long long)res->start,
-			 (unsigned long long)res->end,
-			 (unsigned long)res->flags,
-			 (unsigned long long)offset);
+		pr_debug("PCI: PHB MEM resource %d = %pR off 0x%08llx\n", i,
+			 res, (unsigned long long)offset);
 
 		pci_add_resource_offset(resources, res, offset);
 	}
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 42e02a2d570b..c8c62c7fc31c 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -126,7 +126,6 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 {
 	struct pci_dev *dev;
 	const char *type;
-	struct pci_slot *slot;
 
 	dev = pci_alloc_dev(bus);
 	if (!dev)
@@ -145,10 +144,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	dev->needs_freset = 0;		/* pcie fundamental reset required */
 	set_pcie_port_type(dev);
 
-	list_for_each_entry(slot, &dev->bus->slots, list)
-		if (PCI_SLOT(dev->devfn) == slot->number)
-			dev->slot = slot;
-
+	pci_dev_assign_slot(dev);
 	dev->vendor = get_int_prop(node, "vendor-id", 0xffff);
 	dev->device = get_int_prop(node, "device-id", 0xffff);
 	dev->subsystem_vendor = get_int_prop(node, "subsystem-vendor-id", 0);
@@ -191,6 +187,9 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
 	pci_device_add(dev, bus);
 
+	/* Setup MSI caps & disable MSI/MSI-X interrupts */
+	pci_msi_setup_pci_dev(dev);
+
 	return dev;
 }
 EXPORT_SYMBOL(of_create_pci_dev);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8005e18d1b40..75b6676c1a0b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -86,7 +86,7 @@ void giveup_fpu_maybe_transactional(struct task_struct *tsk)
 	if (tsk == current && tsk->thread.regs &&
 	    MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
 	    !test_thread_flag(TIF_RESTORE_TM)) {
-		tsk->thread.tm_orig_msr = tsk->thread.regs->msr;
+		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
 		set_thread_flag(TIF_RESTORE_TM);
 	}
 
@@ -104,7 +104,7 @@ void giveup_altivec_maybe_transactional(struct task_struct *tsk)
 	if (tsk == current && tsk->thread.regs &&
 	    MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
 	    !test_thread_flag(TIF_RESTORE_TM)) {
-		tsk->thread.tm_orig_msr = tsk->thread.regs->msr;
+		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
 		set_thread_flag(TIF_RESTORE_TM);
 	}
 
@@ -204,8 +204,6 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
-#if 0
-/* not currently used, but some crazy RAID module might want to later */
 void enable_kernel_vsx(void)
 {
 	WARN_ON(preemptible());
@@ -220,7 +218,6 @@ void enable_kernel_vsx(void)
 #endif /* CONFIG_SMP */
 }
 EXPORT_SYMBOL(enable_kernel_vsx);
-#endif
 
 void giveup_vsx(struct task_struct *tsk)
 {
@@ -543,7 +540,7 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	 * the thread will no longer be transactional.
 	 */
 	if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) {
-		msr_diff = thr->tm_orig_msr & ~thr->regs->msr;
+		msr_diff = thr->ckpt_regs.msr & ~thr->regs->msr;
 		if (msr_diff & MSR_FP)
 			memcpy(&thr->transact_fp, &thr->fp_state,
 			       sizeof(struct thread_fp_state));
@@ -594,10 +591,10 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
 	/* Stash the original thread MSR, as giveup_fpu et al will
 	 * modify it.  We hold onto it to see whether the task used
 	 * FP & vector regs.  If the TIF_RESTORE_TM flag is set,
-	 * tm_orig_msr is already set.
+	 * ckpt_regs.msr is already set.
 	 */
 	if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM))
-		thr->tm_orig_msr = thr->regs->msr;
+		thr->ckpt_regs.msr = thr->regs->msr;
 
 	TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
 		 "ccr=%lx, msr=%lx, trap=%lx)\n",
@@ -666,7 +663,7 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
 		tm_restore_sprs(&new->thread);
 		return;
 	}
-	msr = new->thread.tm_orig_msr;
+	msr = new->thread.ckpt_regs.msr;
 	/* Recheckpoint to restore original checkpointed register state. */
 	TM_DEBUG("*** tm_recheckpoint of pid %d "
 		 "(new->msr 0x%lx, new->origmsr 0x%lx)\n",
@@ -726,7 +723,7 @@ void restore_tm_state(struct pt_regs *regs)
 	if (!MSR_TM_ACTIVE(regs->msr))
 		return;
 
-	msr_diff = current->thread.tm_orig_msr & ~regs->msr;
+	msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
 	msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
 	if (msr_diff & MSR_FP) {
 		fp_enable();
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 8b888b12a475..bef76c5033e4 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -218,22 +218,18 @@ static void __init check_cpu_pa_features(unsigned long node)
 }
 
 #ifdef CONFIG_PPC_STD_MMU_64
-static void __init check_cpu_slb_size(unsigned long node)
+static void __init init_mmu_slb_size(unsigned long node)
 {
 	const __be32 *slb_size_ptr;
 
-	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
-	if (slb_size_ptr != NULL) {
-		mmu_slb_size = be32_to_cpup(slb_size_ptr);
-		return;
-	}
-	slb_size_ptr = of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
-	if (slb_size_ptr != NULL) {
+	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL) ? :
+			of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
+
+	if (slb_size_ptr)
 		mmu_slb_size = be32_to_cpup(slb_size_ptr);
-	}
 }
 #else
-#define check_cpu_slb_size(node) do { } while(0)
+#define init_mmu_slb_size(node) do { } while(0)
 #endif
 
 static struct feature_property {
@@ -380,7 +376,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 
 	check_cpu_feature_properties(node);
 	check_cpu_pa_features(node);
-	check_cpu_slb_size(node);
+	init_mmu_slb_size(node);
 
 #ifdef CONFIG_PPC64
 	if (nthreads > 1)
@@ -476,9 +472,10 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 		flags = of_read_number(&dm[3], 1);
 		/* skip DRC index, pad, assoc. list index, flags */
 		dm += 4;
-		/* skip this block if the reserved bit is set in flags (0x80)
-		   or if the block is not assigned to this partition (0x8) */
-		if ((flags & 0x80) || !(flags & 0x8))
+		/* skip this block if the reserved bit is set in flags
+		   or if the block is not assigned to this partition */
+		if ((flags & DRCONF_MEM_RESERVED) ||
+				!(flags & DRCONF_MEM_ASSIGNED))
 			continue;
 		size = memblock_size;
 		rngs = 1;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index fcca8077e6a2..15099c41622e 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -641,6 +641,15 @@ static void __init early_cmdline_parse(void)
 #define W(x)	((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \
 		((x) >> 8) & 0xff, (x) & 0xff
 
+/* Firmware expects the value to be n - 1, where n is the # of vectors */
+#define NUM_VECTORS(n)		((n) - 1)
+
+/*
+ * Firmware expects 1 + n - 2, where n is the length of the option vector in
+ * bytes. The 1 accounts for the length byte itself, the - 2 .. ?
+ */
+#define VECTOR_LENGTH(n)	(1 + (n) - 2)
+
 unsigned char ibm_architecture_vec[] = {
 	W(0xfffe0000), W(0x003a0000),	/* POWER5/POWER5+ */
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
@@ -651,16 +660,16 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
 	W(0xffffffff), W(0x0f000002),	/* all 2.05-compliant */
 	W(0xfffffffe), W(0x0f000001),	/* all 2.04-compliant and earlier */
-	6 - 1,				/* 6 option vectors */
+	NUM_VECTORS(6),			/* 6 option vectors */
 
 	/* option vector 1: processor architectures supported */
-	3 - 2,				/* length */
+	VECTOR_LENGTH(2),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 |
 	OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07,
 
 	/* option vector 2: Open Firmware options supported */
-	34 - 2,				/* length */
+	VECTOR_LENGTH(33),		/* length */
 	OV2_REAL_MODE,
 	0, 0,
 	W(0xffffffff),			/* real_base */
@@ -674,17 +683,17 @@ unsigned char ibm_architecture_vec[] = {
 	48,				/* max log_2(hash table size) */
 
 	/* option vector 3: processor options supported */
-	3 - 2,				/* length */
+	VECTOR_LENGTH(2),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV3_FP | OV3_VMX | OV3_DFP,
 
 	/* option vector 4: IBM PAPR implementation */
-	3 - 2,				/* length */
+	VECTOR_LENGTH(2),		/* length */
 	0,				/* don't halt */
 	OV4_MIN_ENT_CAP,		/* minimum VP entitled capacity */
 
 	/* option vector 5: PAPR/OF options */
-	19 - 2,				/* length */
+	VECTOR_LENGTH(18),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
 	OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -717,12 +726,12 @@ unsigned char ibm_architecture_vec[] = {
 	OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
 	OV5_FEAT(OV5_PFO_HW_842),
 	OV5_FEAT(OV5_SUB_PROCESSORS),
+
 	/* option vector 6: IBM PAPR hints */
-	4 - 2,				/* length */
+	VECTOR_LENGTH(3),		/* length */
 	0,
 	0,
 	OV6_LINUX,
-
 };
 
 /* Old method - ELF header with PT_NOTE sections only works on BE */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index f21897b42057..737c0d0b53ac 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1762,26 +1762,81 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-/*
- * We must return the syscall number to actually look up in the table.
- * This can be -1L to skip running any syscall at all.
+#ifdef CONFIG_SECCOMP
+static int do_seccomp(struct pt_regs *regs)
+{
+	if (!test_thread_flag(TIF_SECCOMP))
+		return 0;
+
+	/*
+	 * The ABI we present to seccomp tracers is that r3 contains
+	 * the syscall return value and orig_gpr3 contains the first
+	 * syscall parameter. This is different to the ptrace ABI where
+	 * both r3 and orig_gpr3 contain the first syscall parameter.
+	 */
+	regs->gpr[3] = -ENOSYS;
+
+	/*
+	 * We use the __ version here because we have already checked
+	 * TIF_SECCOMP. If this fails, there is nothing left to do, we
+	 * have already loaded -ENOSYS into r3, or seccomp has put
+	 * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
+	 */
+	if (__secure_computing())
+		return -1;
+
+	/*
+	 * The syscall was allowed by seccomp, restore the register
+	 * state to what ptrace and audit expect.
+	 * Note that we use orig_gpr3, which means a seccomp tracer can
+	 * modify the first syscall parameter (in orig_gpr3) and also
+	 * allow the syscall to proceed.
+	 */
+	regs->gpr[3] = regs->orig_gpr3;
+
+	return 0;
+}
+#else
+static inline int do_seccomp(struct pt_regs *regs) { return 0; }
+#endif /* CONFIG_SECCOMP */
+
+/**
+ * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
+ * @regs: the pt_regs of the task to trace (current)
+ *
+ * Performs various types of tracing on syscall entry. This includes seccomp,
+ * ptrace, syscall tracepoints and audit.
+ *
+ * The pt_regs are potentially visible to userspace via ptrace, so their
+ * contents is ABI.
+ *
+ * One or more of the tracers may modify the contents of pt_regs, in particular
+ * to modify arguments or even the syscall number itself.
+ *
+ * It's also possible that a tracer can choose to reject the system call. In
+ * that case this function will return an illegal syscall number, and will put
+ * an appropriate return value in regs->r3.
+ *
+ * Return: the (possibly changed) syscall number.
  */
 long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	long ret = 0;
+	bool abort = false;
 
 	user_exit();
 
-	secure_computing_strict(regs->gpr[0]);
+	if (do_seccomp(regs))
+		return -1;
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs))
+	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
 		/*
-		 * Tracing decided this syscall should not happen.
-		 * We'll return a bogus call number to get an ENOSYS
-		 * error, but leave the original number in regs->gpr[0].
+		 * The tracer may decide to abort the syscall, if so tracehook
+		 * will return !0. Note that the tracer may also just change
+		 * regs->gpr[0] to an invalid syscall number, that is handled
+		 * below on the exit path.
 		 */
-		ret = -1L;
+		abort = tracehook_report_syscall_entry(regs) != 0;
+	}
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->gpr[0]);
@@ -1798,7 +1853,17 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 				    regs->gpr[5] & 0xffffffff,
 				    regs->gpr[6] & 0xffffffff);
 
-	return ret ?: regs->gpr[0];
+	if (abort || regs->gpr[0] >= NR_syscalls) {
+		/*
+		 * If we are aborting explicitly, or if the syscall number is
+		 * now invalid, set the return value to -ENOSYS.
+		 */
+		regs->gpr[3] = -ENOSYS;
+		return -1;
+	}
+
+	/* Return the possibly modified but valid syscall number */
+	return regs->gpr[0];
 }
 
 void do_syscall_trace_leave(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 7a488c108410..84bf934cf748 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -478,8 +478,9 @@ unsigned int rtas_busy_delay_time(int status)
 
 	if (status == RTAS_BUSY) {
 		ms = 1;
-	} else if (status >= 9900 && status <= 9905) {
-		order = status - 9900;
+	} else if (status >= RTAS_EXTENDED_DELAY_MIN &&
+		   status <= RTAS_EXTENDED_DELAY_MAX) {
+		order = status - RTAS_EXTENDED_DELAY_MIN;
 		for (ms = 1; order > 0; order--)
 			ms *= 10;
 	}
@@ -584,6 +585,23 @@ int rtas_get_sensor(int sensor, int index, int *state)
 }
 EXPORT_SYMBOL(rtas_get_sensor);
 
+int rtas_get_sensor_fast(int sensor, int index, int *state)
+{
+	int token = rtas_token("get-sensor-state");
+	int rc;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	rc = rtas_call(token, 2, 2, state, sensor, index);
+	WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
+				    rc <= RTAS_EXTENDED_DELAY_MAX));
+
+	if (rc < 0)
+		return rtas_error_rc(rc);
+	return rc;
+}
+
 bool rtas_indicator_present(int token, int *maxindex)
 {
 	int proplen, count, i;
@@ -641,7 +659,8 @@ int rtas_set_indicator_fast(int indicator, int index, int new_value)
 
 	rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
 
-	WARN_ON(rc == -2 || (rc >= 9900 && rc <= 9905));
+	WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
+				    rc <= RTAS_EXTENDED_DELAY_MAX));
 
 	if (rc < 0)
 		return rtas_error_rc(rc);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index d3a831ac0f92..0dbee465af7a 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -949,6 +949,11 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 		err |= __put_user(s->si_overrun, &d->si_overrun);
 		err |= __put_user(s->si_int, &d->si_int);
 		break;
+	case __SI_SYS >> 16:
+		err |= __put_user(ptr_to_compat(s->si_call_addr), &d->si_call_addr);
+		err |= __put_user(s->si_syscall, &d->si_syscall);
+		err |= __put_user(s->si_arch, &d->si_arch);
+		break;
 	case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
 	case __SI_MESGQ >> 16:
 		err |= __put_user(s->si_int, &d->si_int);
@@ -966,8 +971,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c7c24d2e2bdb..20756dfb9f34 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -74,6 +74,19 @@ static const char fmt64[] = KERN_INFO \
 	"%s[%d]: bad frame in %s: %016lx nip %016lx lr %016lx\n";
 
 /*
+ * This computes a quad word aligned pointer inside the vmx_reserve array
+ * element. For historical reasons sigcontext might not be quad word aligned,
+ * but the location we write the VMX regs to must be. See the comment in
+ * sigcontext for more detail.
+ */
+#ifdef CONFIG_ALTIVEC
+static elf_vrreg_t __user *sigcontext_vmx_regs(struct sigcontext __user *sc)
+{
+	return (elf_vrreg_t __user *) (((unsigned long)sc->vmx_reserve + 15) & ~0xful);
+}
+#endif
+
+/*
  * Set up the sigcontext for the signal frame.
  */
 
@@ -90,7 +103,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	 * v_regs pointer or not
 	 */
 #ifdef CONFIG_ALTIVEC
-	elf_vrreg_t __user *v_regs = (elf_vrreg_t __user *)(((unsigned long)sc->vmx_reserve + 15) & ~0xful);
+	elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
 #endif
 	unsigned long msr = regs->msr;
 	long err = 0;
@@ -181,10 +194,8 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	 * v_regs pointer or not.
 	 */
 #ifdef CONFIG_ALTIVEC
-	elf_vrreg_t __user *v_regs = (elf_vrreg_t __user *)
-		(((unsigned long)sc->vmx_reserve + 15) & ~0xful);
-	elf_vrreg_t __user *tm_v_regs = (elf_vrreg_t __user *)
-		(((unsigned long)tm_sc->vmx_reserve + 15) & ~0xful);
+	elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
+	elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
 #endif
 	unsigned long msr = regs->msr;
 	long err = 0;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 43922509a483..1be1092c7204 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -99,16 +99,17 @@ static struct clocksource clocksource_timebase = {
 
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev);
-static void decrementer_set_mode(enum clock_event_mode mode,
-				 struct clock_event_device *dev);
+static int decrementer_shutdown(struct clock_event_device *evt);
 
 struct clock_event_device decrementer_clockevent = {
-	.name           = "decrementer",
-	.rating         = 200,
-	.irq            = 0,
-	.set_next_event = decrementer_set_next_event,
-	.set_mode       = decrementer_set_mode,
-	.features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
+	.name			= "decrementer",
+	.rating			= 200,
+	.irq			= 0,
+	.set_next_event		= decrementer_set_next_event,
+	.set_state_shutdown	= decrementer_shutdown,
+	.tick_resume		= decrementer_shutdown,
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_C3STOP,
 };
 EXPORT_SYMBOL(decrementer_clockevent);
 
@@ -862,11 +863,10 @@ static int decrementer_set_next_event(unsigned long evt,
 	return 0;
 }
 
-static void decrementer_set_mode(enum clock_event_mode mode,
-				 struct clock_event_device *dev)
+static int decrementer_shutdown(struct clock_event_device *dev)
 {
-	if (mode != CLOCK_EVT_MODE_ONESHOT)
-		decrementer_set_next_event(DECREMENTER_MAX, dev);
+	decrementer_set_next_event(DECREMENTER_MAX, dev);
+	return 0;
 }
 
 /* Interrupt handler for the timer broadcast IPI */
diff --git a/arch/powerpc/kernel/trace_clock.c b/arch/powerpc/kernel/trace_clock.c
new file mode 100644
index 000000000000..49170690946d
--- /dev/null
+++ b/arch/powerpc/kernel/trace_clock.c
@@ -0,0 +1,15 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include <asm/trace_clock.h>
+#include <asm/time.h>
+
+u64 notrace trace_clock_ppc_tb(void)
+{
+	return get_tb();
+}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6530f1b8874d..37de90f8a845 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -297,6 +297,8 @@ long machine_check_early(struct pt_regs *regs)
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 05ea8fc7f829..6d6398f4d632 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -902,7 +902,7 @@ int kvmppc_core_check_processor_compat(void)
 {
 	/*
 	 * We always return 0 for book3s. We check
-	 * for compatability while loading the HV
+	 * for compatibility while loading the HV
 	 * or PR module
 	 */
 	return 0;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 68d067ad4222..a9f753fb73a8 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2178,7 +2178,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		vc->runner = vcpu;
 		if (n_ceded == vc->n_runnable) {
 			kvmppc_vcore_blocked(vc);
-		} else if (should_resched()) {
+		} else if (need_resched()) {
 			vc->vcore_state = VCORE_PREEMPT;
 			/* Let something else run */
 			cond_resched_lock(&vc->lock);
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 7874e8a80455..6d67e057f15e 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -41,22 +41,6 @@ _GLOBAL(ip_fast_csum)
 	blr
 
 /*
- * Compute checksum of TCP or UDP pseudo-header:
- *   csum_tcpudp_magic(saddr, daddr, len, proto, sum)
- */	
-_GLOBAL(csum_tcpudp_magic)
-	rlwimi	r5,r6,16,0,15	/* put proto in upper half of len */
-	addc	r0,r3,r4	/* add 4 32-bit words together */
-	adde	r0,r0,r5
-	adde	r0,r0,r7
-	addze	r0,r0		/* add in final carry */
-	rlwinm	r3,r0,16,0,31	/* fold two halves together */
-	add	r3,r0,r3
-	not	r3,r3
-	srwi	r3,r3,16
-	blr
-
-/*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
  *
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 57a072065057..f3ef35436612 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -45,27 +45,6 @@ _GLOBAL(ip_fast_csum)
 	blr
 
 /*
- * Compute checksum of TCP or UDP pseudo-header:
- *   csum_tcpudp_magic(r3=saddr, r4=daddr, r5=len, r6=proto, r7=sum)
- * No real gain trying to do this specially for 64 bit, but
- * the 32 bit addition may spill into the upper bits of
- * the doubleword so we still must fold it down from 64.
- */	
-_GLOBAL(csum_tcpudp_magic)
-	rlwimi	r5,r6,16,0,15	/* put proto in upper half of len */
-	addc	r0,r3,r4	/* add 4 32-bit words together */
-	adde	r0,r0,r5
-	adde	r0,r0,r7
-        rldicl  r4,r0,32,0      /* fold 64 bit value */
-        add     r0,r4,r0
-        srdi    r0,r0,32
-	rlwinm	r3,r0,16,0,31	/* fold two halves together */
-	add	r3,r0,r3
-	not	r3,r3
-	srwi	r3,r3,16
-	blr
-
-/*
  * Computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit).
  *
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 6813f80d1eec..2ef50c629470 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -69,9 +69,15 @@ CACHELINE_BYTES = L1_CACHE_BYTES
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
+/*
+ * Use dcbz on the complete cache lines in the destination
+ * to set them to zero.  This requires that the destination
+ * area is cacheable.  -- paulus
+ */
 _GLOBAL(memset)
 	rlwimi	r4,r4,8,16,23
 	rlwimi	r4,r4,16,0,15
+
 	addi	r6,r3,-4
 	cmplwi	0,r5,4
 	blt	7f
@@ -80,7 +86,29 @@ _GLOBAL(memset)
 	andi.	r0,r6,3
 	add	r5,r0,r5
 	subf	r6,r0,r6
-	srwi	r0,r5,2
+	cmplwi	0,r4,0
+	bne	2f	/* Use normal procedure if r4 is not zero */
+
+	clrlwi	r7,r6,32-LG_CACHELINE_BYTES
+	add	r8,r7,r5
+	srwi	r9,r8,LG_CACHELINE_BYTES
+	addic.	r9,r9,-1	/* total number of complete cachelines */
+	ble	2f
+	xori	r0,r7,CACHELINE_MASK & ~3
+	srwi.	r0,r0,2
+	beq	3f
+	mtctr	r0
+4:	stwu	r4,4(r6)
+	bdnz	4b
+3:	mtctr	r9
+	li	r7,4
+10:	dcbz	r7,r6
+	addi	r6,r6,CACHELINE_BYTES
+	bdnz	10b
+	clrlwi	r5,r8,32-LG_CACHELINE_BYTES
+	addi	r5,r5,4
+
+2:	srwi	r0,r5,2
 	mtctr	r0
 	bdz	6f
 1:	stwu	r4,4(r6)
@@ -94,12 +122,91 @@ _GLOBAL(memset)
 	bdnz	8b
 	blr
 
+/*
+ * This version uses dcbz on the complete cache lines in the
+ * destination area to reduce memory traffic.  This requires that
+ * the destination area is cacheable.
+ * We only use this version if the source and dest don't overlap.
+ * -- paulus.
+ */
 _GLOBAL(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	/* fall through */
 
 _GLOBAL(memcpy)
+	add	r7,r3,r5		/* test if the src & dst overlap */
+	add	r8,r4,r5
+	cmplw	0,r4,r7
+	cmplw	1,r3,r8
+	crand	0,0,4			/* cr0.lt &= cr1.lt */
+	blt	generic_memcpy		/* if regions overlap */
+
+	addi	r4,r4,-4
+	addi	r6,r3,-4
+	neg	r0,r3
+	andi.	r0,r0,CACHELINE_MASK	/* # bytes to start of cache line */
+	beq	58f
+
+	cmplw	0,r5,r0			/* is this more than total to do? */
+	blt	63f			/* if not much to do */
+	andi.	r8,r0,3			/* get it word-aligned first */
+	subf	r5,r0,r5
+	mtctr	r8
+	beq+	61f
+70:	lbz	r9,4(r4)		/* do some bytes */
+	addi	r4,r4,1
+	addi	r6,r6,1
+	stb	r9,3(r6)
+	bdnz	70b
+61:	srwi.	r0,r0,2
+	mtctr	r0
+	beq	58f
+72:	lwzu	r9,4(r4)		/* do some words */
+	stwu	r9,4(r6)
+	bdnz	72b
+
+58:	srwi.	r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */
+	clrlwi	r5,r5,32-LG_CACHELINE_BYTES
+	li	r11,4
+	mtctr	r0
+	beq	63f
+53:
+	dcbz	r11,r6
+	COPY_16_BYTES
+#if L1_CACHE_BYTES >= 32
+	COPY_16_BYTES
+#if L1_CACHE_BYTES >= 64
+	COPY_16_BYTES
+	COPY_16_BYTES
+#if L1_CACHE_BYTES >= 128
+	COPY_16_BYTES
+	COPY_16_BYTES
+	COPY_16_BYTES
+	COPY_16_BYTES
+#endif
+#endif
+#endif
+	bdnz	53b
+
+63:	srwi.	r0,r5,2
+	mtctr	r0
+	beq	64f
+30:	lwzu	r0,4(r4)
+	stwu	r0,4(r6)
+	bdnz	30b
+
+64:	andi.	r0,r5,3
+	mtctr	r0
+	beq+	65f
+	addi	r4,r4,3
+	addi	r6,r6,3
+40:	lbzu	r0,1(r4)
+	stbu	r0,1(r6)
+	bdnz	40b
+65:	blr
+
+_GLOBAL(generic_memcpy)
 	srwi.	r7,r5,3
 	addi	r6,r3,-4
 	addi	r4,r4,-4
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6d535973b200..a67c6d781c52 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -529,6 +529,10 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"instruction fetch\n");
 		break;
+	case 0x600:
+		printk(KERN_ALERT "Unable to handle kernel paging request for "
+			"unaligned access at address 0x%08lx\n", regs->dar);
+		break;
 	default:
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"unknown fault\n");
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 9c90e66cffb6..354ba3c09ef3 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -112,7 +112,7 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 
 	tsize = __ilog2(size) - 10;
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
 	if ((flags & _PAGE_NO_CACHE) == 0)
 		flags |= _PAGE_COHERENT;
 #endif
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 463174a4a647..3b49e3295901 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -701,7 +701,7 @@ htab_pte_insert_failure:
 
 #endif /* CONFIG_PPC_64K_PAGES */
 
-#ifdef CONFIG_PPC_HAS_HASH_64K
+#ifdef CONFIG_PPC_64K_PAGES
 
 /*****************************************************************************
  *                                                                           *
@@ -993,7 +993,7 @@ ht64_pte_insert_failure:
 	b	ht64_bail
 
 
-#endif /* CONFIG_PPC_HAS_HASH_64K */
+#endif /* CONFIG_PPC_64K_PAGES */
 
 
 /*****************************************************************************
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5ec987f65b2c..aee70171355b 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -640,7 +640,7 @@ extern u32 ht64_call_hpte_updatepp[];
 
 static void __init htab_finish_init(void)
 {
-#ifdef CONFIG_PPC_HAS_HASH_64K
+#ifdef CONFIG_PPC_64K_PAGES
 	patch_branch(ht64_call_hpte_insert1,
 		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
@@ -653,7 +653,7 @@ static void __init htab_finish_init(void)
 	patch_branch(ht64_call_hpte_updatepp,
 		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
-#endif /* CONFIG_PPC_HAS_HASH_64K */
+#endif /* CONFIG_PPC_64K_PAGES */
 
 	patch_branch(htab_call_hpte_insert1,
 		ppc_function_entry(ppc_md.hpte_insert),
@@ -1151,12 +1151,12 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
-#ifdef CONFIG_PPC_HAS_HASH_64K
+#ifdef CONFIG_PPC_64K_PAGES
 	if (psize == MMU_PAGE_64K)
 		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
 				     flags, ssize);
 	else
-#endif /* CONFIG_PPC_HAS_HASH_64K */
+#endif /* CONFIG_PPC_64K_PAGES */
 	{
 		int spp = subpage_protection(mm, ea);
 		if (access & spp)
@@ -1264,12 +1264,12 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 		update_flags |= HPTE_LOCAL_UPDATE;
 
 	/* Hash it in */
-#ifdef CONFIG_PPC_HAS_HASH_64K
+#ifdef CONFIG_PPC_64K_PAGES
 	if (mm->context.user_psize == MMU_PAGE_64K)
 		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
 				     update_flags, ssize);
 	else
-#endif /* CONFIG_PPC_HAS_HASH_64K */
+#endif /* CONFIG_PPC_64K_PAGES */
 		rc = __hash_page_4K(ea, access, vsid, ptep, trap, update_flags,
 				    ssize, subpage_protection(mm, ea));
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index bb0bd7025cb8..06c14523b787 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -808,14 +808,6 @@ static int __init add_huge_page_size(unsigned long long size)
 	if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
 		return -EINVAL;
 
-#ifdef CONFIG_SPU_FS_64K_LS
-	/* Disable support for 64K huge pages when 64K SPU local store
-	 * support is enabled as the current implementation conflicts.
-	 */
-	if (shift == PAGE_SHIFT_64K)
-		return -EINVAL;
-#endif /* CONFIG_SPU_FS_64K_LS */
-
 	BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
 
 	/* Return if huge page size has already been setup */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 0f11819d8f1d..e1fe333da946 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -414,17 +414,17 @@ void flush_dcache_icache_page(struct page *page)
 		return;
 	}
 #endif
-#ifdef CONFIG_BOOKE
-	{
+#if defined(CONFIG_8xx) || defined(CONFIG_PPC64)
+	/* On 8xx there is no need to kmap since highmem is not supported */
+	__flush_dcache_icache(page_address(page));
+#else
+	if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
 		void *start = kmap_atomic(page);
 		__flush_dcache_icache(start);
 		kunmap_atomic(start);
+	} else {
+		__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
 	}
-#elif defined(CONFIG_8xx) || defined(CONFIG_PPC64)
-	/* On 8xx there is no need to kmap since highmem is not supported */
-	__flush_dcache_icache(page_address(page)); 
-#else
-	__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
 #endif
 }
 EXPORT_SYMBOL(flush_dcache_icache_page);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5e80621d9324..8b9502adaf79 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -225,7 +225,7 @@ static void initialize_distance_lookup_table(int nid,
 	for (i = 0; i < distance_ref_points_depth; i++) {
 		const __be32 *entry;
 
-		entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+		entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
 		distance_lookup_table[nid][i] = of_read_number(entry, 1);
 	}
 }
@@ -248,8 +248,12 @@ static int associativity_to_nid(const __be32 *associativity)
 		nid = -1;
 
 	if (nid > 0 &&
-	    of_read_number(associativity, 1) >= distance_ref_points_depth)
-		initialize_distance_lookup_table(nid, associativity);
+		of_read_number(associativity, 1) >= distance_ref_points_depth) {
+		/*
+		 * Skip the length field and send start of associativity array
+		 */
+		initialize_distance_lookup_table(nid, associativity + 1);
+	}
 
 out:
 	return nid;
@@ -507,6 +511,12 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
 
 		if (nid == 0xffff || nid >= MAX_NUMNODES)
 			nid = default_nid;
+
+		if (nid > 0) {
+			index = drmem->aa_index * aa->array_sz;
+			initialize_distance_lookup_table(nid,
+							&aa->arrays[index]);
+		}
 	}
 
 	return nid;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 876232d64126..e92cb2146b18 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -149,17 +149,7 @@ int map_kernel_page(unsigned long ea, unsigned long pa, int flags)
 #endif /* !CONFIG_PPC_MMU_NOHASH */
 	}
 
-#ifdef CONFIG_PPC_BOOK3E_64
-	/*
-	 * With hardware tablewalk, a sync is needed to ensure that
-	 * subsequent accesses see the PTE we just wrote.  Unlike userspace
-	 * mappings, we can't tolerate spurious faults, so make sure
-	 * the new PTE will be seen the first time.
-	 */
-	mb();
-#else
 	smp_wmb();
-#endif
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 6e450ca66526..8a32a2be3c53 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -41,9 +41,9 @@ static void slb_allocate(unsigned long ea)
 	(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)
 
 static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
-					 unsigned long slot)
+					 unsigned long entry)
 {
-	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
+	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | entry;
 }
 
 static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
@@ -249,11 +249,24 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 static inline void patch_slb_encoding(unsigned int *insn_addr,
 				      unsigned int immed)
 {
-	int insn = (*insn_addr & 0xffff0000) | immed;
+
+	/*
+	 * This function patches either an li or a cmpldi instruction with
+	 * a new immediate value. This relies on the fact that both li
+	 * (which is actually addi) and cmpldi both take a 16-bit immediate
+	 * value, and it is situated in the same location in the instruction,
+	 * ie. bits 16-31 (Big endian bit order) or the lower 16 bits.
+	 * The signedness of the immediate operand differs between the two
+	 * instructions however this code is only ever patching a small value,
+	 * much less than 1 << 15, so we can get away with it.
+	 * To patch the value we read the existing instruction, clear the
+	 * immediate value, and or in our new value, then write the instruction
+	 * back.
+	 */
+	unsigned int insn = (*insn_addr & 0xffff0000) | immed;
 	patch_instruction(insn_addr, insn);
 }
 
-extern u32 slb_compare_rr_to_size[];
 extern u32 slb_miss_kernel_load_linear[];
 extern u32 slb_miss_kernel_load_io[];
 extern u32 slb_compare_rr_to_size[];
@@ -309,12 +322,11 @@ void slb_initialize(void)
 	lflags = SLB_VSID_KERNEL | linear_llp;
 	vflags = SLB_VSID_KERNEL | vmalloc_llp;
 
-	/* Invalidate the entire SLB (even slot 0) & all the ERATS */
+	/* Invalidate the entire SLB (even entry 0) & all the ERATS */
 	asm volatile("isync":::"memory");
 	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
 	asm volatile("isync; slbia; isync":::"memory");
 	create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, 0);
-
 	create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, 1);
 
 	/* For the boot cpu, we're running on the stack in init_thread_union,
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 765b419883f2..e4185581c5a7 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -308,11 +308,11 @@ BEGIN_FTR_SECTION		/* CPU_FTR_SMT */
 	 *
 	 * MAS6:IND should be already set based on MAS4
 	 */
-1:	lbarx	r15,0,r11
 	lhz	r10,PACAPACAINDEX(r13)
-	cmpdi	r15,0
-	cmpdi	cr1,r15,1	/* set cr1.eq = 0 for non-recursive */
 	addi	r10,r10,1
+	crclr	cr1*4+eq	/* set cr1.eq = 0 for non-recursive */
+1:	lbarx	r15,0,r11
+	cmpdi	r15,0
 	bne	2f
 	stbcx.	r10,0,r11
 	bne	1b
@@ -320,9 +320,9 @@ BEGIN_FTR_SECTION		/* CPU_FTR_SMT */
 	.subsection 1
 2:	cmpd	cr1,r15,r10	/* recursive lock due to mcheck/crit/etc? */
 	beq	cr1,3b		/* unlock will happen if cr1.eq = 0 */
-	lbz	r15,0(r11)
+10:	lbz	r15,0(r11)
 	cmpdi	r15,0
-	bne	2b
+	bne	10b
 	b	1b
 	.previous
 
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 962fe7b3e3fb..4b32e9404bbe 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -207,7 +207,7 @@ static int power4_start(struct op_counter_config *ctr)
 	unsigned int mmcr0;
 
 	/* set the PMM bit (see comment below) */
-	mtmsrd(mfmsr() | MSR_PMM);
+	mtmsr(mfmsr() | MSR_PMM);
 
 	for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
 		if (ctr[i].enabled) {
@@ -377,7 +377,7 @@ static void power4_handle_interrupt(struct pt_regs *regs,
 	is_kernel = get_kernel(pc, mmcra);
 
 	/* set the PMM bit (see comment below) */
-	mtmsrd(mfmsr() | MSR_PMM);
+	mtmsr(mfmsr() | MSR_PMM);
 
 	/* Check that the SIAR  valid bit in MMCRA is set to 1. */
 	if ((mmcra & MMCRA_SIAR_VALID_MASK) == MMCRA_SIAR_VALID_MASK)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index d90893b76e7c..b0382f3f1095 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -53,7 +53,7 @@ struct cpu_hw_events {
 
 	/* BHRB bits */
 	u64				bhrb_filter;	/* BHRB HW branch filter */
-	int				bhrb_users;
+	unsigned int			bhrb_users;
 	void				*bhrb_context;
 	struct	perf_branch_stack	bhrb_stack;
 	struct	perf_branch_entry	bhrb_entries[BHRB_MAX_ENTRIES];
@@ -369,8 +369,8 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 	if (!ppmu->bhrb_nr)
 		return;
 
+	WARN_ON_ONCE(!cpuhw->bhrb_users);
 	cpuhw->bhrb_users--;
-	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
 	perf_sched_cb_dec(event->ctx->pmu);
 
 	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index ec2eb20631d1..527c8b98e97e 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -320,6 +320,8 @@ static struct attribute *device_str_attr_create_(char *name, char *str)
 	if (!attr)
 		return NULL;
 
+	sysfs_attr_init(&attr->attr.attr);
+
 	attr->var = str;
 	attr->attr.attr.name = name;
 	attr->attr.attr.mode = 0444;
@@ -414,7 +416,7 @@ out_val:
 }
 
 static struct attribute *event_to_desc_attr(struct hv_24x7_event_data *event,
-				int nonce)
+					    int nonce)
 {
 	int nl, dl;
 	char *name = event_name(event, &nl);
@@ -442,7 +444,7 @@ event_to_long_desc_attr(struct hv_24x7_event_data *event, int nonce)
 }
 
 static ssize_t event_data_to_attrs(unsigned ix, struct attribute **attrs,
-		struct hv_24x7_event_data *event, int nonce)
+				   struct hv_24x7_event_data *event, int nonce)
 {
 	unsigned i;
 
@@ -510,7 +512,7 @@ static int memord(const void *d1, size_t s1, const void *d2, size_t s2)
 }
 
 static int ev_uniq_ord(const void *v1, size_t s1, unsigned d1, const void *v2,
-					size_t s2, unsigned d2)
+		       size_t s2, unsigned d2)
 {
 	int r = memord(v1, s1, v2, s2);
 
@@ -524,7 +526,7 @@ static int ev_uniq_ord(const void *v1, size_t s1, unsigned d1, const void *v2,
 }
 
 static int event_uniq_add(struct rb_root *root, const char *name, int nl,
-				unsigned domain)
+			  unsigned domain)
 {
 	struct rb_node **new = &(root->rb_node), *parent = NULL;
 	struct event_uniq *data;
@@ -648,8 +650,8 @@ static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event,
 #define MAX_4K (SIZE_MAX / 4096)
 
 static int create_events_from_catalog(struct attribute ***events_,
-		struct attribute ***event_descs_,
-		struct attribute ***event_long_descs_)
+				      struct attribute ***event_descs_,
+				      struct attribute ***event_long_descs_)
 {
 	unsigned long hret;
 	size_t catalog_len, catalog_page_len, event_entry_count,
@@ -1006,8 +1008,8 @@ static const struct attribute_group *attr_groups[] = {
 };
 
 static void log_24x7_hcall(struct hv_24x7_request_buffer *request_buffer,
-			struct hv_24x7_data_result_buffer *result_buffer,
-			unsigned long ret)
+			   struct hv_24x7_data_result_buffer *result_buffer,
+			   unsigned long ret)
 {
 	struct hv_24x7_request *req;
 
@@ -1024,7 +1026,7 @@ static void log_24x7_hcall(struct hv_24x7_request_buffer *request_buffer,
  * Start the process for a new H_GET_24x7_DATA hcall.
  */
 static void init_24x7_request(struct hv_24x7_request_buffer *request_buffer,
-			struct hv_24x7_data_result_buffer *result_buffer)
+			      struct hv_24x7_data_result_buffer *result_buffer)
 {
 
 	memset(request_buffer, 0, 4096);
@@ -1039,7 +1041,7 @@ static void init_24x7_request(struct hv_24x7_request_buffer *request_buffer,
  * by 'init_24x7_request()' and 'add_event_to_24x7_request()'.
  */
 static int make_24x7_request(struct hv_24x7_request_buffer *request_buffer,
-			struct hv_24x7_data_result_buffer *result_buffer)
+			     struct hv_24x7_data_result_buffer *result_buffer)
 {
 	unsigned long ret;
 
@@ -1102,7 +1104,6 @@ static unsigned long single_24x7_request(struct perf_event *event, u64 *count)
 	unsigned long ret;
 	struct hv_24x7_request_buffer *request_buffer;
 	struct hv_24x7_data_result_buffer *result_buffer;
-	struct hv_24x7_result *resb;
 
 	BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
 	BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
@@ -1123,8 +1124,7 @@ static unsigned long single_24x7_request(struct perf_event *event, u64 *count)
 	}
 
 	/* process result from hcall */
-	resb = &result_buffer->results[0];
-	*count = be64_to_cpu(resb->elements[0].element_data[0]);
+	*count = be64_to_cpu(result_buffer->results[0].elements[0].element_data[0]);
 
 out:
 	put_cpu_var(hv_24x7_reqb);
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index 5aa3f4b5332c..48bf38d0de35 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -7,8 +7,8 @@ config PPC_MPC512x
 	select PPC_PCI_CHOICE
 	select FSL_PCI if PCI
 	select ARCH_WANT_OPTIONAL_GPIOLIB
-	select USB_EHCI_BIG_ENDIAN_MMIO
-	select USB_EHCI_BIG_ENDIAN_DESC
+	select USB_EHCI_BIG_ENDIAN_MMIO if USB_EHCI_HCD
+	select USB_EHCI_BIG_ENDIAN_DESC if USB_EHCI_HCD
 
 config MPC5121_ADS
 	bool "Freescale MPC5121E ADS"
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index f691bcabd710..c50ea76ba66c 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/device.h>
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index ca3a062ed1b9..11090ab4bf59 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -123,7 +123,8 @@ cpld_pic_cascade(unsigned int irq, struct irq_desc *desc)
 }
 
 static int
-cpld_pic_host_match(struct irq_domain *h, struct device_node *node)
+cpld_pic_host_match(struct irq_domain *h, struct device_node *node,
+		    enum irq_domain_bus_token bus_token)
 {
 	return cpld_pic_node == node;
 }
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
index 84476b646005..61bc851e9a8e 100644
--- a/arch/powerpc/platforms/85xx/c293pcie.c
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -66,10 +66,6 @@ define_machine(c293_pcie) {
 	.probe			= c293_pcie_probe,
 	.setup_arch		= c293_pcie_setup_arch,
 	.init_IRQ		= c293_pcie_pic_init,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-	.pcibios_fixup_phb      = fsl_pcibios_fixup_phb,
-#endif
 	.get_irq		= mpic_get_irq,
 	.restart		= fsl_rstcr_restart,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index bd839dc287fe..b39557120cbb 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -153,6 +153,8 @@ static const char * const boards[] __initconst = {
 	"fsl,T1023RDB",
 	"fsl,T1024QDS",
 	"fsl,T1024RDB",
+	"fsl,T1040D4RDB",
+	"fsl,T1042D4RDB",
 	"fsl,T1040QDS",
 	"fsl,T1042QDS",
 	"fsl,T1040RDB",
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 2f23133ab3d1..b0ac1773cea6 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -57,21 +57,6 @@ config SPU_FS
 	  Units on machines implementing the Broadband Processor
 	  Architecture.
 
-config SPU_FS_64K_LS
-	bool "Use 64K pages to map SPE local  store"
-	# we depend on PPC_MM_SLICES for now rather than selecting
-	# it because we depend on hugetlbfs hooks being present. We
-	# will fix that when the generic code has been improved to
-	# not require hijacking hugetlbfs hooks.
-	depends on SPU_FS && PPC_MM_SLICES && !PPC_64K_PAGES
-	default y
-	select PPC_HAS_HASH_64K
-	help
-	  This option causes SPE local stores to be mapped in process
-	  address spaces using 64K pages while the rest of the kernel
-	  uses 4K pages. This can improve performances of applications
-	  using multiple SPEs by lowering the TLB pressure on them.
-
 config SPU_BASE
 	bool
 	default n
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index fe51de4fcf13..306888acb737 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -213,7 +213,7 @@ static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
 		return -ENODEV;
 	}
 
-	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+	entry = first_pci_msi_entry(dev);
 
 	for (; dn; dn = of_get_next_parent(dn)) {
 		if (entry->msi_attrib.is_64) {
@@ -269,7 +269,7 @@ static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (rc)
 		return rc;
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		virq = irq_create_direct_mapping(msic->irq_domain);
 		if (virq == NO_IRQ) {
 			dev_warn(&dev->dev,
@@ -292,7 +292,7 @@ static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
 
 	dev_dbg(&dev->dev, "axon_msi: tearing down msi irqs\n");
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 3af8324c122e..a15f1efc295f 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -222,7 +222,8 @@ void iic_request_IPIs(void)
 #endif /* CONFIG_SMP */
 
 
-static int iic_host_match(struct irq_domain *h, struct device_node *node)
+static int iic_host_match(struct irq_domain *h, struct device_node *node,
+			  enum irq_domain_bus_token bus_token)
 {
 	return of_device_is_compatible(node,
 				    "IBM,CBEA-Internal-Interrupt-Controller");
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index d966bbe58b8f..5038fd578e65 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -239,23 +239,6 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	unsigned long address = (unsigned long)vmf->virtual_address;
 	unsigned long pfn, offset;
 
-#ifdef CONFIG_SPU_FS_64K_LS
-	struct spu_state *csa = &ctx->csa;
-	int psize;
-
-	/* Check what page size we are using */
-	psize = get_slice_psize(vma->vm_mm, address);
-
-	/* Some sanity checking */
-	BUG_ON(csa->use_big_pages != (psize == MMU_PAGE_64K));
-
-	/* Wow, 64K, cool, we need to align the address though */
-	if (csa->use_big_pages) {
-		BUG_ON(vma->vm_start & 0xffff);
-		address &= ~0xfffful;
-	}
-#endif /* CONFIG_SPU_FS_64K_LS */
-
 	offset = vmf->pgoff << PAGE_SHIFT;
 	if (offset >= LS_SIZE)
 		return VM_FAULT_SIGBUS;
@@ -310,22 +293,6 @@ static const struct vm_operations_struct spufs_mem_mmap_vmops = {
 
 static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma)
 {
-#ifdef CONFIG_SPU_FS_64K_LS
-	struct spu_context	*ctx = file->private_data;
-	struct spu_state	*csa = &ctx->csa;
-
-	/* Sanity check VMA alignment */
-	if (csa->use_big_pages) {
-		pr_debug("spufs_mem_mmap 64K, start=0x%lx, end=0x%lx,"
-			 " pgoff=0x%lx\n", vma->vm_start, vma->vm_end,
-			 vma->vm_pgoff);
-		if (vma->vm_start & 0xffff)
-			return -EINVAL;
-		if (vma->vm_pgoff & 0xf)
-			return -EINVAL;
-	}
-#endif /* CONFIG_SPU_FS_64K_LS */
-
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
@@ -336,25 +303,6 @@ static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-#ifdef CONFIG_SPU_FS_64K_LS
-static unsigned long spufs_get_unmapped_area(struct file *file,
-		unsigned long addr, unsigned long len, unsigned long pgoff,
-		unsigned long flags)
-{
-	struct spu_context	*ctx = file->private_data;
-	struct spu_state	*csa = &ctx->csa;
-
-	/* If not using big pages, fallback to normal MM g_u_a */
-	if (!csa->use_big_pages)
-		return current->mm->get_unmapped_area(file, addr, len,
-						      pgoff, flags);
-
-	/* Else, try to obtain a 64K pages slice */
-	return slice_get_unmapped_area(addr, len, flags,
-				       MMU_PAGE_64K, 1);
-}
-#endif /* CONFIG_SPU_FS_64K_LS */
-
 static const struct file_operations spufs_mem_fops = {
 	.open			= spufs_mem_open,
 	.release		= spufs_mem_release,
@@ -362,9 +310,6 @@ static const struct file_operations spufs_mem_fops = {
 	.write			= spufs_mem_write,
 	.llseek			= generic_file_llseek,
 	.mmap			= spufs_mem_mmap,
-#ifdef CONFIG_SPU_FS_64K_LS
-	.get_unmapped_area	= spufs_get_unmapped_area,
-#endif
 };
 
 static int spufs_ps_fault(struct vm_area_struct *vma,
diff --git a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
index 147069938cfe..b847e9403566 100644
--- a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
+++ b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
@@ -31,7 +31,7 @@
 
 #include "spufs.h"
 
-static int spu_alloc_lscsa_std(struct spu_state *csa)
+int spu_alloc_lscsa(struct spu_state *csa)
 {
 	struct spu_lscsa *lscsa;
 	unsigned char *p;
@@ -48,7 +48,7 @@ static int spu_alloc_lscsa_std(struct spu_state *csa)
 	return 0;
 }
 
-static void spu_free_lscsa_std(struct spu_state *csa)
+void spu_free_lscsa(struct spu_state *csa)
 {
 	/* Clear reserved bit before vfree. */
 	unsigned char *p;
@@ -61,123 +61,3 @@ static void spu_free_lscsa_std(struct spu_state *csa)
 
 	vfree(csa->lscsa);
 }
-
-#ifdef CONFIG_SPU_FS_64K_LS
-
-#define SPU_64K_PAGE_SHIFT	16
-#define SPU_64K_PAGE_ORDER	(SPU_64K_PAGE_SHIFT - PAGE_SHIFT)
-#define SPU_64K_PAGE_COUNT	(1ul << SPU_64K_PAGE_ORDER)
-
-int spu_alloc_lscsa(struct spu_state *csa)
-{
-	struct page	**pgarray;
-	unsigned char	*p;
-	int		i, j, n_4k;
-
-	/* Check availability of 64K pages */
-	if (!spu_64k_pages_available())
-		goto fail;
-
-	csa->use_big_pages = 1;
-
-	pr_debug("spu_alloc_lscsa(csa=0x%p), trying to allocate 64K pages\n",
-		 csa);
-
-	/* First try to allocate our 64K pages. We need 5 of them
-	 * with the current implementation. In the future, we should try
-	 * to separate the lscsa with the actual local store image, thus
-	 * allowing us to require only 4 64K pages per context
-	 */
-	for (i = 0; i < SPU_LSCSA_NUM_BIG_PAGES; i++) {
-		/* XXX This is likely to fail, we should use a special pool
-		 *     similar to what hugetlbfs does.
-		 */
-		csa->lscsa_pages[i] = alloc_pages(GFP_KERNEL,
-						  SPU_64K_PAGE_ORDER);
-		if (csa->lscsa_pages[i] == NULL)
-			goto fail;
-	}
-
-	pr_debug(" success ! creating vmap...\n");
-
-	/* Now we need to create a vmalloc mapping of these for the kernel
-	 * and SPU context switch code to use. Currently, we stick to a
-	 * normal kernel vmalloc mapping, which in our case will be 4K
-	 */
-	n_4k = SPU_64K_PAGE_COUNT * SPU_LSCSA_NUM_BIG_PAGES;
-	pgarray = kmalloc(sizeof(struct page *) * n_4k, GFP_KERNEL);
-	if (pgarray == NULL)
-		goto fail;
-	for (i = 0; i < SPU_LSCSA_NUM_BIG_PAGES; i++)
-		for (j = 0; j < SPU_64K_PAGE_COUNT; j++)
-			/* We assume all the struct page's are contiguous
-			 * which should be hopefully the case for an order 4
-			 * allocation..
-			 */
-			pgarray[i * SPU_64K_PAGE_COUNT + j] =
-				csa->lscsa_pages[i] + j;
-	csa->lscsa = vmap(pgarray, n_4k, VM_USERMAP, PAGE_KERNEL);
-	kfree(pgarray);
-	if (csa->lscsa == NULL)
-		goto fail;
-
-	memset(csa->lscsa, 0, sizeof(struct spu_lscsa));
-
-	/* Set LS pages reserved to allow for user-space mapping.
-	 *
-	 * XXX isn't that a bit obsolete ? I think we should just
-	 * make sure the page count is high enough. Anyway, won't harm
-	 * for now
-	 */
-	for (p = csa->lscsa->ls; p < csa->lscsa->ls + LS_SIZE; p += PAGE_SIZE)
-		SetPageReserved(vmalloc_to_page(p));
-
-	pr_debug(" all good !\n");
-
-	return 0;
-fail:
-	pr_debug("spufs: failed to allocate lscsa 64K pages, falling back\n");
-	spu_free_lscsa(csa);
-	return spu_alloc_lscsa_std(csa);
-}
-
-void spu_free_lscsa(struct spu_state *csa)
-{
-	unsigned char *p;
-	int i;
-
-	if (!csa->use_big_pages) {
-		spu_free_lscsa_std(csa);
-		return;
-	}
-	csa->use_big_pages = 0;
-
-	if (csa->lscsa == NULL)
-		goto free_pages;
-
-	for (p = csa->lscsa->ls; p < csa->lscsa->ls + LS_SIZE; p += PAGE_SIZE)
-		ClearPageReserved(vmalloc_to_page(p));
-
-	vunmap(csa->lscsa);
-	csa->lscsa = NULL;
-
- free_pages:
-
-	for (i = 0; i < SPU_LSCSA_NUM_BIG_PAGES; i++)
-		if (csa->lscsa_pages[i])
-			__free_pages(csa->lscsa_pages[i], SPU_64K_PAGE_ORDER);
-}
-
-#else /* CONFIG_SPU_FS_64K_LS */
-
-int spu_alloc_lscsa(struct spu_state *csa)
-{
-	return spu_alloc_lscsa_std(csa);
-}
-
-void spu_free_lscsa(struct spu_state *csa)
-{
-	spu_free_lscsa_std(csa);
-}
-
-#endif /* !defined(CONFIG_SPU_FS_64K_LS) */
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index 4cde8e7da4b8..b7866e01483d 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -108,7 +108,8 @@ static int flipper_pic_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static int flipper_pic_match(struct irq_domain *h, struct device_node *np)
+static int flipper_pic_match(struct irq_domain *h, struct device_node *np,
+			     enum irq_domain_bus_token bus_token)
 {
 	return 1;
 }
diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c
index 27f2b187a91b..e66ef1943338 100644
--- a/arch/powerpc/platforms/pasemi/msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -66,7 +66,7 @@ static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 
 	pr_debug("pasemi_msi_teardown_msi_irqs, pdev %p\n", pdev);
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
@@ -94,7 +94,7 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	msg.address_hi = 0;
 	msg.address_lo = PASEMI_MSI_ADDR;
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		/* Allocate 16 interrupts for now, since that's the grouping for
 		 * affinity. This can be changed later if it turns out 32 is too
 		 * few MSIs for someone, but restrictions will apply to how the
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 59cfc9d63c2d..6f4f8b060def 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -268,7 +268,8 @@ static struct irqaction gatwick_cascade_action = {
 	.name		= "cascade",
 };
 
-static int pmac_pic_host_match(struct irq_domain *h, struct device_node *node)
+static int pmac_pic_host_match(struct irq_domain *h, struct device_node *node,
+			       enum irq_domain_bus_token bus_token)
 {
 	/* We match all, we don't always have a node anyway */
 	return 1;
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5cf5e6ea213b..3bb6acb76339 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1394,11 +1394,19 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 			 */
 			if (pnv_eeh_get_pe(hose,
 				be64_to_cpu(frozen_pe_no), pe)) {
-				/* Try best to clear it */
 				pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
-					hose->global_number, frozen_pe_no);
+					hose->global_number, be64_to_cpu(frozen_pe_no));
 				pr_info("EEH: PHB location: %s\n",
 					eeh_pe_loc_get(phb_pe));
+
+				/* Dump PHB diag-data */
+				rc = opal_pci_get_phb_diag_data2(phb->opal_id,
+					phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+				if (rc == OPAL_SUCCESS)
+					pnv_pci_dump_phb_diag_data(hose,
+							phb->diag.blob);
+
+				/* Try best to clear it */
 				opal_pci_eeh_freeze_clear(phb->opal_id,
 					frozen_pe_no,
 					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
@@ -1478,7 +1486,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	}
 
 	/* Unmask the event */
-	if (eeh_enabled())
+	if (ret == EEH_NEXT_ERR_NONE && eeh_enabled())
 		enable_irq(eeh_event_irq);
 
 	return ret;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 4949ef0d9400..37f959bf392e 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -237,7 +237,7 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type)
 	return elog;
 }
 
-static void elog_work_fn(struct work_struct *work)
+static irqreturn_t elog_event(int irq, void *data)
 {
 	__be64 size;
 	__be64 id;
@@ -251,7 +251,7 @@ static void elog_work_fn(struct work_struct *work)
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
 		pr_err("ELOG: OPAL log info read failed\n");
-		return;
+		return IRQ_HANDLED;
 	}
 
 	elog_size = be64_to_cpu(size);
@@ -270,16 +270,10 @@ static void elog_work_fn(struct work_struct *work)
 	 * entries.
 	 */
 	if (kset_find_obj(elog_kset, name))
-		return;
+		return IRQ_HANDLED;
 
 	create_elog_obj(log_id, elog_size, elog_type);
-}
-
-static DECLARE_WORK(elog_work, elog_work_fn);
 
-static irqreturn_t elog_event(int irq, void *data)
-{
-	schedule_work(&elog_work);
 	return IRQ_HANDLED;
 }
 
@@ -304,8 +298,8 @@ int __init opal_elog_init(void)
 		return irq;
 	}
 
-	rc = request_irq(irq, elog_event,
-			IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL);
+	rc = request_threaded_irq(irq, NULL, elog_event,
+			IRQF_TRIGGER_HIGH | IRQF_ONESHOT, "opal-elog", NULL);
 	if (rc) {
 		pr_err("%s: Can't request OPAL event irq (%d)\n",
 		       __func__, rc);
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index a8f49d380449..d000f4e21981 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -35,9 +35,134 @@ struct OpalHmiEvtNode {
 	struct list_head list;
 	struct OpalHMIEvent hmi_evt;
 };
+
+struct xstop_reason {
+	uint32_t xstop_reason;
+	const char *unit_failed;
+	const char *description;
+};
+
 static LIST_HEAD(opal_hmi_evt_list);
 static DEFINE_SPINLOCK(opal_hmi_evt_lock);
 
+static void print_core_checkstop_reason(const char *level,
+					struct OpalHMIEvent *hmi_evt)
+{
+	int i;
+	static const struct xstop_reason xstop_reason[] = {
+		{ CORE_CHECKSTOP_IFU_REGFILE, "IFU",
+				"RegFile core check stop" },
+		{ CORE_CHECKSTOP_IFU_LOGIC, "IFU", "Logic core check stop" },
+		{ CORE_CHECKSTOP_PC_DURING_RECOV, "PC",
+				"Core checkstop during recovery" },
+		{ CORE_CHECKSTOP_ISU_REGFILE, "ISU",
+				"RegFile core check stop (mapper error)" },
+		{ CORE_CHECKSTOP_ISU_LOGIC, "ISU", "Logic core check stop" },
+		{ CORE_CHECKSTOP_FXU_LOGIC, "FXU", "Logic core check stop" },
+		{ CORE_CHECKSTOP_VSU_LOGIC, "VSU", "Logic core check stop" },
+		{ CORE_CHECKSTOP_PC_RECOV_IN_MAINT_MODE, "PC",
+				"Recovery in maintenance mode" },
+		{ CORE_CHECKSTOP_LSU_REGFILE, "LSU",
+				"RegFile core check stop" },
+		{ CORE_CHECKSTOP_PC_FWD_PROGRESS, "PC",
+				"Forward Progress Error" },
+		{ CORE_CHECKSTOP_LSU_LOGIC, "LSU", "Logic core check stop" },
+		{ CORE_CHECKSTOP_PC_LOGIC, "PC", "Logic core check stop" },
+		{ CORE_CHECKSTOP_PC_HYP_RESOURCE, "PC",
+				"Hypervisor Resource error - core check stop" },
+		{ CORE_CHECKSTOP_PC_HANG_RECOV_FAILED, "PC",
+				"Hang Recovery Failed (core check stop)" },
+		{ CORE_CHECKSTOP_PC_AMBI_HANG_DETECTED, "PC",
+				"Ambiguous Hang Detected (unknown source)" },
+		{ CORE_CHECKSTOP_PC_DEBUG_TRIG_ERR_INJ, "PC",
+				"Debug Trigger Error inject" },
+		{ CORE_CHECKSTOP_PC_SPRD_HYP_ERR_INJ, "PC",
+				"Hypervisor check stop via SPRC/SPRD" },
+	};
+
+	/* Validity check */
+	if (!hmi_evt->u.xstop_error.xstop_reason) {
+		printk("%s	Unknown Core check stop.\n", level);
+		return;
+	}
+
+	printk("%s	CPU PIR: %08x\n", level,
+			be32_to_cpu(hmi_evt->u.xstop_error.u.pir));
+	for (i = 0; i < ARRAY_SIZE(xstop_reason); i++)
+		if (be32_to_cpu(hmi_evt->u.xstop_error.xstop_reason) &
+					xstop_reason[i].xstop_reason)
+			printk("%s	[Unit: %-3s] %s\n", level,
+					xstop_reason[i].unit_failed,
+					xstop_reason[i].description);
+}
+
+static void print_nx_checkstop_reason(const char *level,
+					struct OpalHMIEvent *hmi_evt)
+{
+	int i;
+	static const struct xstop_reason xstop_reason[] = {
+		{ NX_CHECKSTOP_SHM_INVAL_STATE_ERR, "DMA & Engine",
+					"SHM invalid state error" },
+		{ NX_CHECKSTOP_DMA_INVAL_STATE_ERR_1, "DMA & Engine",
+					"DMA invalid state error bit 15" },
+		{ NX_CHECKSTOP_DMA_INVAL_STATE_ERR_2, "DMA & Engine",
+					"DMA invalid state error bit 16" },
+		{ NX_CHECKSTOP_DMA_CH0_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 0 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH1_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 1 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH2_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 2 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH3_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 3 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH4_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 4 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH5_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 5 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH6_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 6 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CH7_INVAL_STATE_ERR, "DMA & Engine",
+					"Channel 7 invalid state error" },
+		{ NX_CHECKSTOP_DMA_CRB_UE, "DMA & Engine",
+					"UE error on CRB(CSB address, CCB)" },
+		{ NX_CHECKSTOP_DMA_CRB_SUE, "DMA & Engine",
+					"SUE error on CRB(CSB address, CCB)" },
+		{ NX_CHECKSTOP_PBI_ISN_UE, "PowerBus Interface",
+		"CRB Kill ISN received while holding ISN with UE error" },
+	};
+
+	/* Validity check */
+	if (!hmi_evt->u.xstop_error.xstop_reason) {
+		printk("%s	Unknown NX check stop.\n", level);
+		return;
+	}
+
+	printk("%s	NX checkstop on CHIP ID: %x\n", level,
+			be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id));
+	for (i = 0; i < ARRAY_SIZE(xstop_reason); i++)
+		if (be32_to_cpu(hmi_evt->u.xstop_error.xstop_reason) &
+					xstop_reason[i].xstop_reason)
+			printk("%s	[Unit: %-3s] %s\n", level,
+					xstop_reason[i].unit_failed,
+					xstop_reason[i].description);
+}
+
+static void print_checkstop_reason(const char *level,
+					struct OpalHMIEvent *hmi_evt)
+{
+	switch (hmi_evt->u.xstop_error.xstop_type) {
+	case CHECKSTOP_TYPE_CORE:
+		print_core_checkstop_reason(level, hmi_evt);
+		break;
+	case CHECKSTOP_TYPE_NX:
+		print_nx_checkstop_reason(level, hmi_evt);
+		break;
+	case CHECKSTOP_TYPE_UNKNOWN:
+		printk("%s	Unknown Malfunction Alert.\n", level);
+		break;
+	}
+}
+
 static void print_hmi_event_info(struct OpalHMIEvent *hmi_evt)
 {
 	const char *level, *sevstr, *error_info;
@@ -95,6 +220,13 @@ static void print_hmi_event_info(struct OpalHMIEvent *hmi_evt)
 		(hmi_evt->type == OpalHMI_ERROR_TFMR_PARITY))
 		printk("%s	TFMR: %016llx\n", level,
 						be64_to_cpu(hmi_evt->tfmr));
+
+	if (hmi_evt->version < OpalHMIEvt_V2)
+		return;
+
+	/* OpalHMIEvt_V2 and above provides reason for malfunction alert. */
+	if (hmi_evt->type == OpalHMI_ERROR_MALFUNC_ALERT)
+		print_checkstop_reason(level, hmi_evt);
 }
 
 static void hmi_event_handler(struct work_struct *work)
@@ -103,6 +235,8 @@ static void hmi_event_handler(struct work_struct *work)
 	struct OpalHMIEvent *hmi_evt;
 	struct OpalHmiEvtNode *msg_node;
 	uint8_t disposition;
+	struct opal_msg msg;
+	int unrecoverable = 0;
 
 	spin_lock_irqsave(&opal_hmi_evt_lock, flags);
 	while (!list_empty(&opal_hmi_evt_list)) {
@@ -118,14 +252,53 @@ static void hmi_event_handler(struct work_struct *work)
 
 		/*
 		 * Check if HMI event has been recovered or not. If not
-		 * then we can't continue, invoke panic.
+		 * then kernel can't continue, we need to panic.
+		 * But before we do that, display all the HMI event
+		 * available on the list and set unrecoverable flag to 1.
 		 */
 		if (disposition != OpalHMI_DISPOSITION_RECOVERED)
-			panic("Unrecoverable HMI exception");
+			unrecoverable = 1;
 
 		spin_lock_irqsave(&opal_hmi_evt_lock, flags);
 	}
 	spin_unlock_irqrestore(&opal_hmi_evt_lock, flags);
+
+	if (unrecoverable) {
+		int ret;
+
+		/* Pull all HMI events from OPAL before we panic. */
+		while (opal_get_msg(__pa(&msg), sizeof(msg)) == OPAL_SUCCESS) {
+			u32 type;
+
+			type = be32_to_cpu(msg.msg_type);
+
+			/* skip if not HMI event */
+			if (type != OPAL_MSG_HMI_EVT)
+				continue;
+
+			/* HMI event info starts from param[0] */
+			hmi_evt = (struct OpalHMIEvent *)&msg.params[0];
+			print_hmi_event_info(hmi_evt);
+		}
+
+		/*
+		 * Unrecoverable HMI exception. We need to inform BMC/OCC
+		 * about this error so that it can collect relevant data
+		 * for error analysis before rebooting.
+		 */
+		ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR,
+			"Unrecoverable HMI exception");
+		if (ret == OPAL_UNSUPPORTED) {
+			pr_emerg("Reboot type %d not supported\n",
+						OPAL_REBOOT_PLATFORM_ERROR);
+		}
+
+		/*
+		 * Fall through and panic if opal_cec_reboot2() returns
+		 * OPAL_UNSUPPORTED.
+		 */
+		panic("Unrecoverable HMI exception");
+	}
 }
 
 static DECLARE_WORK(hmi_event_work, hmi_event_handler);
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index e2e7d75f52f3..2c91ee7800b9 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -134,7 +134,8 @@ static void opal_handle_irq_work(struct irq_work *work)
 	opal_handle_events(be64_to_cpu(last_outstanding_events));
 }
 
-static int opal_event_match(struct irq_domain *h, struct device_node *node)
+static int opal_event_match(struct irq_domain *h, struct device_node *node,
+			    enum irq_domain_bus_token bus_token)
 {
 	return h->of_node == node;
 }
diff --git a/arch/powerpc/platforms/powernv/opal-power.c b/arch/powerpc/platforms/powernv/opal-power.c
index ac46c2c24f99..58dc3308237f 100644
--- a/arch/powerpc/platforms/powernv/opal-power.c
+++ b/arch/powerpc/platforms/powernv/opal-power.c
@@ -9,9 +9,12 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt)	"opal-power: "	fmt
+
 #include <linux/kernel.h>
 #include <linux/reboot.h>
 #include <linux/notifier.h>
+#include <linux/of.h>
 
 #include <asm/opal.h>
 #include <asm/machdep.h>
@@ -19,30 +22,116 @@
 #define SOFT_OFF 0x00
 #define SOFT_REBOOT 0x01
 
+/* Detect EPOW event */
+static bool detect_epow(void)
+{
+	u16 epow;
+	int i, rc;
+	__be16 epow_classes;
+	__be16 opal_epow_status[OPAL_SYSEPOW_MAX] = {0};
+
+	/*
+	* Check for EPOW event. Kernel sends supported EPOW classes info
+	* to OPAL. OPAL returns EPOW info along with classes present.
+	*/
+	epow_classes = cpu_to_be16(OPAL_SYSEPOW_MAX);
+	rc = opal_get_epow_status(opal_epow_status, &epow_classes);
+	if (rc != OPAL_SUCCESS) {
+		pr_err("Failed to get EPOW event information\n");
+		return false;
+	}
+
+	/* Look for EPOW events present */
+	for (i = 0; i < be16_to_cpu(epow_classes); i++) {
+		epow = be16_to_cpu(opal_epow_status[i]);
+
+		/* Filter events which do not need shutdown. */
+		if (i == OPAL_SYSEPOW_POWER)
+			epow &= ~(OPAL_SYSPOWER_CHNG | OPAL_SYSPOWER_FAIL |
+					OPAL_SYSPOWER_INCL);
+		if (epow)
+			return true;
+	}
+
+	return false;
+}
+
+/* Check for existing EPOW, DPO events */
+static bool poweroff_pending(void)
+{
+	int rc;
+	__be64 opal_dpo_timeout;
+
+	/* Check for DPO event */
+	rc = opal_get_dpo_status(&opal_dpo_timeout);
+	if (rc == OPAL_SUCCESS) {
+		pr_info("Existing DPO event detected.\n");
+		return true;
+	}
+
+	/* Check for EPOW event */
+	if (detect_epow()) {
+		pr_info("Existing EPOW event detected.\n");
+		return true;
+	}
+
+	return false;
+}
+
+/* OPAL power-control events notifier */
 static int opal_power_control_event(struct notifier_block *nb,
-				    unsigned long msg_type, void *msg)
+					unsigned long msg_type, void *msg)
 {
-	struct opal_msg *power_msg = msg;
 	uint64_t type;
 
-	type = be64_to_cpu(power_msg->params[0]);
-
-	switch (type) {
-	case SOFT_REBOOT:
-		pr_info("OPAL: reboot requested\n");
-		orderly_reboot();
+	switch (msg_type) {
+	case OPAL_MSG_EPOW:
+		if (detect_epow()) {
+			pr_info("EPOW msg received. Powering off system\n");
+			orderly_poweroff(true);
+		}
 		break;
-	case SOFT_OFF:
-		pr_info("OPAL: poweroff requested\n");
+	case OPAL_MSG_DPO:
+		pr_info("DPO msg received. Powering off system\n");
 		orderly_poweroff(true);
 		break;
+	case OPAL_MSG_SHUTDOWN:
+		type = be64_to_cpu(((struct opal_msg *)msg)->params[0]);
+		switch (type) {
+		case SOFT_REBOOT:
+			pr_info("Reboot requested\n");
+			orderly_reboot();
+			break;
+		case SOFT_OFF:
+			pr_info("Poweroff requested\n");
+			orderly_poweroff(true);
+			break;
+		default:
+			pr_err("Unknown power-control type %llu\n", type);
+		}
+		break;
 	default:
-		pr_err("OPAL: power control type unexpected %016llx\n", type);
+		pr_err("Unknown OPAL message type %lu\n", msg_type);
 	}
 
 	return 0;
 }
 
+/* OPAL EPOW event notifier block */
+static struct notifier_block opal_epow_nb = {
+	.notifier_call	= opal_power_control_event,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+/* OPAL DPO event notifier block */
+static struct notifier_block opal_dpo_nb = {
+	.notifier_call	= opal_power_control_event,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+/* OPAL power-control event notifier block */
 static struct notifier_block opal_power_control_nb = {
 	.notifier_call	= opal_power_control_event,
 	.next		= NULL,
@@ -51,16 +140,40 @@ static struct notifier_block opal_power_control_nb = {
 
 static int __init opal_power_control_init(void)
 {
-	int ret;
+	int ret, supported = 0;
+	struct device_node *np;
 
+	/* Register OPAL power-control events notifier */
 	ret = opal_message_notifier_register(OPAL_MSG_SHUTDOWN,
-					     &opal_power_control_nb);
-	if (ret) {
-		pr_err("%s: Can't register OPAL event notifier (%d)\n",
-				__func__, ret);
-		return ret;
+						&opal_power_control_nb);
+	if (ret)
+		pr_err("Failed to register SHUTDOWN notifier, ret = %d\n", ret);
+
+	/* Determine OPAL EPOW, DPO support */
+	np = of_find_node_by_path("/ibm,opal/epow");
+	if (np) {
+		supported = of_device_is_compatible(np, "ibm,opal-v3-epow");
+		of_node_put(np);
 	}
 
+	if (!supported)
+		return 0;
+	pr_info("OPAL EPOW, DPO support detected.\n");
+
+	/* Register EPOW event notifier */
+	ret = opal_message_notifier_register(OPAL_MSG_EPOW, &opal_epow_nb);
+	if (ret)
+		pr_err("Failed to register EPOW notifier, ret = %d\n", ret);
+
+	/* Register DPO event notifier */
+	ret = opal_message_notifier_register(OPAL_MSG_DPO, &opal_dpo_nb);
+	if (ret)
+		pr_err("Failed to register DPO notifier, ret = %d\n", ret);
+
+	/* Check for any pending EPOW or DPO events. */
+	if (poweroff_pending())
+		orderly_poweroff(true);
+
 	return 0;
 }
 machine_subsys_initcall(powernv, opal_power_control_init);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 46cb3feb0a13..4ece8e40dd54 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -112,6 +112,7 @@ static int opal_prd_open(struct inode *inode, struct file *file)
 static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	size_t addr, size;
+	pgprot_t page_prot;
 	int rc;
 
 	pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n",
@@ -125,13 +126,11 @@ static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!opal_prd_range_is_valid(addr, size))
 		return -EINVAL;
 
-	vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file,
-						vma->vm_pgoff,
-						 size, vma->vm_page_prot))
-					| _PAGE_SPECIAL);
+	page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
+					 size, vma->vm_page_prot);
 
 	rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size,
-			vma->vm_page_prot);
+				page_prot);
 
 	return rc;
 }
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index d6a7b8252e4d..b7a464fef7a7 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -202,6 +202,7 @@ OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
 OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
 OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
 OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
+OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
 OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
 OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
 OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
@@ -249,6 +250,7 @@ OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
 OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
 OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
 OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
+OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
 OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
 OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
 OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
@@ -297,3 +299,5 @@ OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
 OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
 OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
 OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
+OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
+OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index f084afa0e3ba..230f3a7cdea4 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -441,6 +441,7 @@ static int opal_recover_mce(struct pt_regs *regs,
 int opal_machine_check(struct pt_regs *regs)
 {
 	struct machine_check_event evt;
+	int ret;
 
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return 0;
@@ -455,6 +456,40 @@ int opal_machine_check(struct pt_regs *regs)
 
 	if (opal_recover_mce(regs, &evt))
 		return 1;
+
+	/*
+	 * Unrecovered machine check, we are heading to panic path.
+	 *
+	 * We may have hit this MCE in very early stage of kernel
+	 * initialization even before opal-prd has started running. If
+	 * this is the case then this MCE error may go un-noticed or
+	 * un-analyzed if we go down panic path. We need to inform
+	 * BMC/OCC about this error so that they can collect relevant
+	 * data for error analysis before rebooting.
+	 * Use opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR) to do so.
+	 * This function may not return on BMC based system.
+	 */
+	ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR,
+			"Unrecoverable Machine Check exception");
+	if (ret == OPAL_UNSUPPORTED) {
+		pr_emerg("Reboot type %d not supported\n",
+					OPAL_REBOOT_PLATFORM_ERROR);
+	}
+
+	/*
+	 * We reached here. There can be three possibilities:
+	 * 1. We are running on a firmware level that do not support
+	 *    opal_cec_reboot2()
+	 * 2. We are running on a firmware level that do not support
+	 *    OPAL_REBOOT_PLATFORM_ERROR reboot type.
+	 * 3. We are running on FSP based system that does not need opal
+	 *    to trigger checkstop explicitly for error analysis. The FSP
+	 *    PRD component would have already got notified about this
+	 *    error through other channels.
+	 *
+	 * In any case, let us just fall through. We anyway heading
+	 * down to panic path.
+	 */
 	return 0;
 }
 
@@ -648,7 +683,7 @@ static void opal_init_heartbeat(void)
 
 static int __init opal_init(void)
 {
-	struct device_node *np, *consoles;
+	struct device_node *np, *consoles, *leds;
 	int rc;
 
 	opal_node = of_find_node_by_path("/ibm,opal");
@@ -689,6 +724,13 @@ static int __init opal_init(void)
 	/* Setup a heatbeat thread if requested by OPAL */
 	opal_init_heartbeat();
 
+	/* Create leds platform devices */
+	leds = of_find_node_by_path("/ibm,opal/leds");
+	if (leds) {
+		of_platform_device_create(leds, "opal_leds", NULL);
+		of_node_put(leds);
+	}
+
 	/* Create "opal" kobject under /sys/firmware */
 	rc = opal_sysfs_init();
 	if (rc == 0) {
@@ -841,3 +883,6 @@ EXPORT_SYMBOL_GPL(opal_rtc_write);
 EXPORT_SYMBOL_GPL(opal_tpo_read);
 EXPORT_SYMBOL_GPL(opal_tpo_write);
 EXPORT_SYMBOL_GPL(opal_i2c_request);
+/* Export these symbols for PowerNV LED class driver */
+EXPORT_SYMBOL_GPL(opal_leds_get_ind);
+EXPORT_SYMBOL_GPL(opal_leds_set_ind);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5738d315248b..2927cd5c8303 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -140,11 +140,9 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 		return;
 	}
 
-	if (test_and_set_bit(pe_no, phb->ioda.pe_alloc)) {
-		pr_warn("%s: PE %d was assigned on PHB#%x\n",
-			__func__, pe_no, phb->hose->global_number);
-		return;
-	}
+	if (test_and_set_bit(pe_no, phb->ioda.pe_alloc))
+		pr_debug("%s: PE %d was reserved on PHB#%x\n",
+			 __func__, pe_no, phb->hose->global_number);
 
 	phb->ioda.pe_array[pe_no].phb = phb;
 	phb->ioda.pe_array[pe_no].pe_number = pe_no;
@@ -231,61 +229,60 @@ fail:
 	return -EIO;
 }
 
-static void pnv_ioda2_reserve_m64_pe(struct pnv_phb *phb)
+static void pnv_ioda2_reserve_dev_m64_pe(struct pci_dev *pdev,
+					 unsigned long *pe_bitmap)
 {
-	resource_size_t sgsz = phb->ioda.m64_segsize;
-	struct pci_dev *pdev;
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
 	struct resource *r;
-	int base, step, i;
-
-	/*
-	 * Root bus always has full M64 range and root port has
-	 * M64 range used in reality. So we're checking root port
-	 * instead of root bus.
-	 */
-	list_for_each_entry(pdev, &phb->hose->bus->devices, bus_list) {
-		for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) {
-			r = &pdev->resource[PCI_BRIDGE_RESOURCES + i];
-			if (!r->parent ||
-			    !pnv_pci_is_mem_pref_64(r->flags))
-				continue;
+	resource_size_t base, sgsz, start, end;
+	int segno, i;
+
+	base = phb->ioda.m64_base;
+	sgsz = phb->ioda.m64_segsize;
+	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+		r = &pdev->resource[i];
+		if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags))
+			continue;
 
-			base = (r->start - phb->ioda.m64_base) / sgsz;
-			for (step = 0; step < resource_size(r) / sgsz; step++)
-				pnv_ioda_reserve_pe(phb, base + step);
+		start = _ALIGN_DOWN(r->start - base, sgsz);
+		end = _ALIGN_UP(r->end - base, sgsz);
+		for (segno = start / sgsz; segno < end / sgsz; segno++) {
+			if (pe_bitmap)
+				set_bit(segno, pe_bitmap);
+			else
+				pnv_ioda_reserve_pe(phb, segno);
 		}
 	}
 }
 
-static int pnv_ioda2_pick_m64_pe(struct pnv_phb *phb,
-				 struct pci_bus *bus, int all)
+static void pnv_ioda2_reserve_m64_pe(struct pci_bus *bus,
+				     unsigned long *pe_bitmap,
+				     bool all)
 {
-	resource_size_t segsz = phb->ioda.m64_segsize;
 	struct pci_dev *pdev;
-	struct resource *r;
+
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		pnv_ioda2_reserve_dev_m64_pe(pdev, pe_bitmap);
+
+		if (all && pdev->subordinate)
+			pnv_ioda2_reserve_m64_pe(pdev->subordinate,
+						 pe_bitmap, all);
+	}
+}
+
+static int pnv_ioda2_pick_m64_pe(struct pci_bus *bus, bool all)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
 	struct pnv_ioda_pe *master_pe, *pe;
 	unsigned long size, *pe_alloc;
-	bool found;
-	int start, i, j;
+	int i;
 
 	/* Root bus shouldn't use M64 */
 	if (pci_is_root_bus(bus))
 		return IODA_INVALID_PE;
 
-	/* We support only one M64 window on each bus */
-	found = false;
-	pci_bus_for_each_resource(bus, r, i) {
-		if (r && r->parent &&
-		    pnv_pci_is_mem_pref_64(r->flags)) {
-			found = true;
-			break;
-		}
-	}
-
-	/* No M64 window found ? */
-	if (!found)
-		return IODA_INVALID_PE;
-
 	/* Allocate bitmap */
 	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
 	pe_alloc = kzalloc(size, GFP_KERNEL);
@@ -295,35 +292,8 @@ static int pnv_ioda2_pick_m64_pe(struct pnv_phb *phb,
 		return IODA_INVALID_PE;
 	}
 
-	/*
-	 * Figure out reserved PE numbers by the PE
-	 * the its child PEs.
-	 */
-	start = (r->start - phb->ioda.m64_base) / segsz;
-	for (i = 0; i < resource_size(r) / segsz; i++)
-		set_bit(start + i, pe_alloc);
-
-	if (all)
-		goto done;
-
-	/*
-	 * If the PE doesn't cover all subordinate buses,
-	 * we need subtract from reserved PEs for children.
-	 */
-	list_for_each_entry(pdev, &bus->devices, bus_list) {
-		if (!pdev->subordinate)
-			continue;
-
-		pci_bus_for_each_resource(pdev->subordinate, r, i) {
-			if (!r || !r->parent ||
-			    !pnv_pci_is_mem_pref_64(r->flags))
-				continue;
-
-			start = (r->start - phb->ioda.m64_base) / segsz;
-			for (j = 0; j < resource_size(r) / segsz ; j++)
-				clear_bit(start + j, pe_alloc);
-                }
-        }
+	/* Figure out reserved PE numbers by the PE */
+	pnv_ioda2_reserve_m64_pe(bus, pe_alloc, all);
 
 	/*
 	 * the current bus might not own M64 window and that's all
@@ -339,7 +309,6 @@ static int pnv_ioda2_pick_m64_pe(struct pnv_phb *phb,
 	 * Figure out the master PE and put all slave PEs to master
 	 * PE's list to form compound PE.
 	 */
-done:
 	master_pe = NULL;
 	i = -1;
 	while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) <
@@ -653,7 +622,7 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 		pdev = pe->pdev->bus->self;
 #ifdef CONFIG_PCI_IOV
 	else if (pe->flags & PNV_IODA_PE_VF)
-		pdev = pe->parent_dev->bus->self;
+		pdev = pe->parent_dev;
 #endif /* CONFIG_PCI_IOV */
 	while (pdev) {
 		struct pci_dn *pdn = pci_get_pdn(pdev);
@@ -732,7 +701,7 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		parent = parent->bus->self;
 	}
 
-	opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number,
+	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
 				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
 
 	/* Disassociate PE in PELT */
@@ -946,8 +915,9 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
 		res2 = *res;
 		res->start += size * offset;
 
-		dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (enabling %d VFs shifted by %d)\n",
-			 i, &res2, res, num_vfs, offset);
+		dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (%sabling %d VFs shifted by %d)\n",
+			 i, &res2, res, (offset > 0) ? "En" : "Dis",
+			 num_vfs, offset);
 		pci_update_resource(dev, i + PCI_IOV_RESOURCES);
 	}
 	return 0;
@@ -1050,7 +1020,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
  * subordinate PCI devices and buses. The second type of PE is normally
  * orgiriated by PCIe-to-PCI bridge or PLX switch downstream ports.
  */
-static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
+static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 {
 	struct pci_controller *hose = pci_bus_to_host(bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -1059,7 +1029,7 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 
 	/* Check if PE is determined by M64 */
 	if (phb->pick_m64_pe)
-		pe_num = phb->pick_m64_pe(phb, bus, all);
+		pe_num = phb->pick_m64_pe(bus, all);
 
 	/* The PE number isn't pinned by M64 */
 	if (pe_num == IODA_INVALID_PE)
@@ -1117,12 +1087,12 @@ static void pnv_ioda_setup_PEs(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
-	pnv_ioda_setup_bus_PE(bus, 0);
+	pnv_ioda_setup_bus_PE(bus, false);
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (dev->subordinate) {
 			if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
-				pnv_ioda_setup_bus_PE(dev->subordinate, 1);
+				pnv_ioda_setup_bus_PE(dev->subordinate, true);
 			else
 				pnv_ioda_setup_PEs(dev->subordinate);
 		}
@@ -1147,7 +1117,7 @@ static void pnv_pci_ioda_setup_PEs(void)
 
 		/* M64 layout might affect PE allocation */
 		if (phb->reserve_m64_pe)
-			phb->reserve_m64_pe(phb);
+			phb->reserve_m64_pe(hose->bus, NULL, true);
 
 		pnv_ioda_setup_PEs(hose->bus);
 	}
@@ -1590,6 +1560,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
+	set_dma_offset(&pdev->dev, pe->tce_bypass_base);
 	set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
 	/*
 	 * Note: iommu_add_device() will fail here as
@@ -1620,19 +1591,18 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 	if (bypass) {
 		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
 		set_dma_ops(&pdev->dev, &dma_direct_ops);
-		set_dma_offset(&pdev->dev, pe->tce_bypass_base);
 	} else {
 		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
 	}
 	*pdev->dev.dma_mask = dma_mask;
 	return 0;
 }
 
-static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
-					      struct pci_dev *pdev)
+static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
 {
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 	u64 end, mask;
@@ -1659,6 +1629,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
+		set_dma_offset(&dev->dev, pe->tce_bypass_base);
 		iommu_add_device(&dev->dev);
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
@@ -2220,7 +2191,7 @@ static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
 
 static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 		unsigned levels, unsigned long limit,
-		unsigned long *current_offset)
+		unsigned long *current_offset, unsigned long *total_allocated)
 {
 	struct page *tce_mem = NULL;
 	__be64 *addr, *tmp;
@@ -2236,6 +2207,7 @@ static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 	}
 	addr = page_address(tce_mem);
 	memset(addr, 0, allocated);
+	*total_allocated += allocated;
 
 	--levels;
 	if (!levels) {
@@ -2245,7 +2217,7 @@ static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 
 	for (i = 0; i < entries; ++i) {
 		tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
-				levels, limit, current_offset);
+				levels, limit, current_offset, total_allocated);
 		if (!tmp)
 			break;
 
@@ -2267,7 +2239,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 		struct iommu_table *tbl)
 {
 	void *addr;
-	unsigned long offset = 0, level_shift;
+	unsigned long offset = 0, level_shift, total_allocated = 0;
 	const unsigned window_shift = ilog2(window_size);
 	unsigned entries_shift = window_shift - page_shift;
 	unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
@@ -2286,7 +2258,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-			levels, tce_table_size, &offset);
+			levels, tce_table_size, &offset, &total_allocated);
 
 	/* addr==NULL means that the first level allocation failed */
 	if (!addr)
@@ -2308,7 +2280,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 			page_shift);
 	tbl->it_level_size = 1ULL << (level_shift - 3);
 	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = offset;
+	tbl->it_allocated_size = total_allocated;
 
 	pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
 			window_size, tce_table_size, bus_offset);
@@ -3056,6 +3028,7 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
        .window_alignment = pnv_pci_window_alignment,
        .reset_secondary_bus = pnv_pci_reset_secondary_bus,
        .dma_set_mask = pnv_pci_ioda_dma_set_mask,
+       .dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask,
        .shutdown = pnv_pci_ioda_shutdown,
 };
 
@@ -3202,7 +3175,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
-	phb->dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask;
 
 	/* Setup MSI support */
 	pnv_pci_init_ioda_msis(phb);
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 765d8ed558d0..9b2480b265c0 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -61,7 +61,7 @@ int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	if (pdev->no_64bit_msi && !phb->msi32_support)
 		return -ENODEV;
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
 			pr_warn("%s: Supports only 64-bit MSIs\n",
 				pci_name(pdev));
@@ -103,7 +103,7 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev)
 	if (WARN_ON(!phb))
 		return;
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 		irq_set_msi_desc(entry->irq, NULL);
@@ -761,17 +761,6 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		phb->dma_dev_setup(phb, pdev);
 }
 
-u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	if (phb && phb->dma_get_required_mask)
-		return phb->dma_get_required_mask(phb, pdev);
-
-	return __dma_get_required_mask(&pdev->dev);
-}
-
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 8ef2d28aded0..c8ff50e90766 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -105,13 +105,12 @@ struct pnv_phb {
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
-	u64 (*dma_get_required_mask)(struct pnv_phb *phb,
-				     struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	int (*init_m64)(struct pnv_phb *phb);
-	void (*reserve_m64_pe)(struct pnv_phb *phb);
-	int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all);
+	void (*reserve_m64_pe)(struct pci_bus *bus,
+			       unsigned long *pe_bitmap, bool all);
+	int (*pick_m64_pe)(struct pci_bus *bus, bool all);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
 	int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 9269e30e4ca0..6dbc0a1da1f6 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -12,15 +12,9 @@ struct pci_dev;
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
-extern u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
-
-static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
-{
-	return 0;
-}
 #endif
 
 extern u32 pnv_get_supported_cpuidle_states(void);
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 6eb808ff637e..5dcbdea1afac 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -128,7 +128,7 @@ static __init int rng_create(struct device_node *dn)
 
 	pr_info_once("Registering arch random hook.\n");
 
-	ppc_md.get_random_long = powernv_get_random_long;
+	ppc_md.get_random_seed = powernv_get_random_long;
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 53737e019ae3..685b3cbe1362 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -165,14 +165,6 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
-static u64 pnv_dma_get_required_mask(struct device *dev)
-{
-	if (dev_is_pci(dev))
-		return pnv_pci_dma_get_required_mask(to_pci_dev(dev));
-
-	return __dma_get_required_mask(dev);
-}
-
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -243,6 +235,13 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 	} else {
 		/* Primary waits for the secondaries to have reached OPAL */
 		pnv_kexec_wait_secondaries_down();
+
+		/*
+		 * We might be running as little-endian - now that interrupts
+		 * are disabled, reset the HILE bit to big-endian so we don't
+		 * take interrupts in the wrong endian later
+		 */
+		opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE);
 	}
 }
 #endif /* CONFIG_KEXEC */
@@ -314,7 +313,6 @@ define_machine(powernv) {
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
-	.dma_get_required_mask	= pnv_dma_get_required_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index f60f80ada903..503a73f59359 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -190,7 +190,7 @@ static void unsplit_core(void)
 
 	hid0 = mfspr(SPRN_HID0);
 	hid0 &= ~HID0_POWER8_DYNLPARDIS;
-	mtspr(SPRN_HID0, hid0);
+	update_power8_hid0(hid0);
 	update_hid_in_slw(hid0);
 
 	while (mfspr(SPRN_HID0) & mask)
@@ -227,7 +227,7 @@ static void split_core(int new_mode)
 	/* Write new mode */
 	hid0  = mfspr(SPRN_HID0);
 	hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value;
-	mtspr(SPRN_HID0, hid0);
+	update_power8_hid0(hid0);
 	update_hid_in_slw(hid0);
 
 	/* Wait for it to happen */
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index a6c42f34303a..638c4060938e 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -678,7 +678,8 @@ static int ps3_host_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static int ps3_host_match(struct irq_domain *h, struct device_node *np)
+static int ps3_host_match(struct irq_domain *h, struct device_node *np,
+			  enum irq_domain_bus_token bus_token)
 {
 	/* Match all */
 	return 1;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 0ced387e1463..e9ff44cd5d86 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -92,13 +92,12 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 		return NULL;
 
 	new_prop->name = kstrdup(prop->name, GFP_KERNEL);
-	new_prop->value = kmalloc(prop->length, GFP_KERNEL);
+	new_prop->value = kmemdup(prop->value, prop->length, GFP_KERNEL);
 	if (!new_prop->name || !new_prop->value) {
 		dlpar_free_drconf_property(new_prop);
 		return NULL;
 	}
 
-	memcpy(new_prop->value, prop->value, prop->length);
 	new_prop->length = prop->length;
 
 	/* Convert the property to cpu endian-ness */
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 10510dea16b3..0946b98d75d4 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1253,11 +1253,10 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
 		}
 	}
 
-	/* fall back on iommu ops, restore table pointer with ops */
+	/* fall back on iommu ops */
 	if (!ddw_enabled && get_dma_ops(dev) != &dma_iommu_ops) {
 		dev_info(dev, "Restoring 32-bit DMA via iommu\n");
 		set_dma_ops(dev, &dma_iommu_ops);
-		pci_dma_dev_setup_pSeriesLP(pdev);
 	}
 
 check_mask:
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index c22bb647cce6..272e9ec1ab54 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -118,7 +118,7 @@ static void rtas_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
@@ -350,7 +350,7 @@ static int check_msix_entries(struct pci_dev *pdev)
 	 * So we must reject such requests. */
 
 	expected = 0;
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->msi_attrib.entry_nr != expected) {
 			pr_debug("rtas_msi: bad MSI-X entries.\n");
 			return -EINVAL;
@@ -462,7 +462,7 @@ again:
 	}
 
 	i = 0;
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		hwirq = rtas_query_irq_number(pdn, i++);
 		if (hwirq < 0) {
 			pr_debug("rtas_msi: error (%d) getting hwirq\n", rc);
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 02e4a1745516..3b6647e574b6 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -189,7 +189,8 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 	int state;
 	int critical;
 
-	status = rtas_get_sensor(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, &state);
+	status = rtas_get_sensor_fast(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX,
+				      &state);
 
 	if (state > 3)
 		critical = 1;		/* Time Critical */
diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c
index e09608770909..31ca557af60b 100644
--- a/arch/powerpc/platforms/pseries/rng.c
+++ b/arch/powerpc/platforms/pseries/rng.c
@@ -38,7 +38,7 @@ static __init int rng_init(void)
 
 	pr_info("Registering arch random hook.\n");
 
-	ppc_md.get_random_long = pseries_get_random_long;
+	ppc_md.get_random_seed = pseries_get_random_long;
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index df6a7041922b..39a74fad3e04 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -254,19 +254,26 @@ static void __init pseries_discover_pic(void)
 static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct of_reconfig_data *rd = data;
-	struct device_node *np = rd->dn;
-	struct pci_dn *pci = NULL;
+	struct device_node *parent, *np = rd->dn;
+	struct pci_dn *pdn;
 	int err = NOTIFY_OK;
 
 	switch (action) {
 	case OF_RECONFIG_ATTACH_NODE:
-		pci = np->parent->data;
-		if (pci) {
-			update_dn_pci_info(np, pci->phb);
-
-			/* Create EEH device for the OF node */
-			eeh_dev_init(PCI_DN(np), pci->phb);
+		parent = of_get_parent(np);
+		pdn = parent ? PCI_DN(parent) : NULL;
+		if (pdn) {
+			/* Create pdn and EEH device */
+			update_dn_pci_info(np, pdn->phb);
+			eeh_dev_init(PCI_DN(np), pdn->phb);
 		}
+
+		of_node_put(parent);
+		break;
+	case OF_RECONFIG_DETACH_NODE:
+		pdn = PCI_DN(np);
+		if (pdn)
+			list_del(&pdn->list);
 		break;
 	default:
 		err = NOTIFY_DONE;
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ee90db17b097..f86250c48b53 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -132,7 +132,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
 		phys_mem += vec.bv_len;
 		transfered += vec.bv_len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 /**
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 4f7869571290..e2ea51961979 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -147,7 +147,7 @@ unsigned long cpm_muram_alloc(unsigned long size, unsigned long align)
 	spin_lock_irqsave(&cpm_muram_lock, flags);
 	cpm_muram_info.alignment = align;
 	start = rh_alloc(&cpm_muram_info, size, "commproc");
-	memset(cpm_muram_addr(start), 0, size);
+	memset_io(cpm_muram_addr(start), 0, size);
 	spin_unlock_irqrestore(&cpm_muram_lock, flags);
 
 	return start;
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 90bcdfeedf48..b7348637eae0 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -313,20 +313,11 @@ static void iommu_table_dart_setup(void)
 	set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
 }
 
-static void dma_dev_setup_dart(struct device *dev)
-{
-	/* We only have one iommu table on the mac for now, which makes
-	 * things simple. Setup all PCI devices to point to this table
-	 */
-	if (get_dma_ops(dev) == &dma_direct_ops)
-		set_dma_offset(dev, DART_U4_BYPASS_BASE);
-	else
-		set_iommu_table_base(dev, &iommu_table_dart);
-}
-
 static void pci_dma_dev_setup_dart(struct pci_dev *dev)
 {
-	dma_dev_setup_dart(&dev->dev);
+	if (dart_is_u4)
+		set_dma_offset(&dev->dev, DART_U4_BYPASS_BASE);
+	set_iommu_table_base(&dev->dev, &iommu_table_dart);
 }
 
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
@@ -370,7 +361,6 @@ static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
 		dev_info(dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(dev, &dma_iommu_ops);
 	}
-	dma_dev_setup_dart(dev);
 
 	*dev->dma_mask = dma_mask;
 	return 0;
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index 2d20f10a4203..eca0b00794fa 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -177,7 +177,8 @@ unsigned int ehv_pic_get_irq(void)
 	return irq_linear_revmap(global_ehv_pic->irqhost, irq);
 }
 
-static int ehv_pic_host_match(struct irq_domain *h, struct device_node *node)
+static int ehv_pic_host_match(struct irq_domain *h, struct device_node *node,
+			      enum irq_domain_bus_token bus_token)
 {
 	/* Exact match, unless ehv_pic node is NULL */
 	return h->of_node == NULL || h->of_node == node;
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 5236e5427c38..5916da1856a7 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -129,7 +129,7 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev)
 	struct msi_desc *entry;
 	struct fsl_msi *msi_data;
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 		msi_data = irq_get_chip_data(entry->irq);
@@ -219,7 +219,7 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		}
 	}
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		/*
 		 * Loop over all the MSI devices until we find one that has an
 		 * available interrupt.
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 9a8fcf0d79d7..ebc1f412cf49 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1113,7 +1113,7 @@ static int fsl_pci_pme_probe(struct pci_controller *hose)
 			IRQF_SHARED,
 			"[PCI] PME", hose);
 	if (res < 0) {
-		dev_err(&dev->dev, "Unable to requiest irq %d for PME\n", pme_irq);
+		dev_err(&dev->dev, "Unable to request irq %d for PME\n", pme_irq);
 		irq_dispose_mapping(pme_irq);
 
 		return -ENODEV;
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 31c33475c7b7..e1a9c2c2d5d3 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -162,7 +162,8 @@ static struct resource pic_edgectrl_iores = {
 	.flags = IORESOURCE_BUSY,
 };
 
-static int i8259_host_match(struct irq_domain *h, struct device_node *node)
+static int i8259_host_match(struct irq_domain *h, struct device_node *node,
+			    enum irq_domain_bus_token bus_token)
 {
 	return h->of_node == NULL || h->of_node == node;
 }
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index d78f1364b639..6b2b68914810 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -671,7 +671,8 @@ static struct irq_chip ipic_edge_irq_chip = {
 	.irq_set_type	= ipic_set_irq_type,
 };
 
-static int ipic_host_match(struct irq_domain *h, struct device_node *node)
+static int ipic_host_match(struct irq_domain *h, struct device_node *node,
+			   enum irq_domain_bus_token bus_token)
 {
 	/* Exact match, unless ipic node is NULL */
 	return h->of_node == NULL || h->of_node == node;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index c8e73332eaad..97a8ae8f94dd 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1007,7 +1007,8 @@ static struct irq_chip mpic_irq_ht_chip = {
 #endif /* CONFIG_MPIC_U3_HT_IRQS */
 
 
-static int mpic_host_match(struct irq_domain *h, struct device_node *node)
+static int mpic_host_match(struct irq_domain *h, struct device_node *node,
+			   enum irq_domain_bus_token bus_token)
 {
 	/* Exact match, unless mpic node is NULL */
 	return h->of_node == NULL || h->of_node == node;
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index fc46ef3b816e..70fbd5694a8b 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -108,7 +108,7 @@ static void u3msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
 
-        list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
@@ -140,7 +140,7 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		return -ENXIO;
 	}
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(entry, pdev) {
 		hwirq = msi_bitmap_alloc_hwirqs(&msi_mpic->msi_bitmap, 1);
 		if (hwirq < 0) {
 			pr_debug("u3msi: failed allocating hwirq\n");
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index 2bc33674ebfc..52a93dcae262 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/semaphore.h>
 #include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
 
 struct ppc4xx_hsta_msi {
 	struct device *dev;
@@ -50,7 +51,7 @@ static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return -EINVAL;
 	}
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		irq = msi_bitmap_alloc_hwirqs(&ppc4xx_hsta_msi.bmp, 1);
 		if (irq < 0) {
 			pr_debug("%s: Failed to allocate msi interrupt\n",
@@ -108,7 +109,7 @@ static void hsta_teardown_msi_irqs(struct pci_dev *dev)
 	struct msi_desc *entry;
 	int irq;
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
@@ -131,7 +132,7 @@ static int hsta_msi_probe(struct platform_device *pdev)
 	struct pci_controller *phb;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (IS_ERR(mem)) {
+	if (!mem) {
 		dev_err(dev, "Unable to get mmio space\n");
 		return -EINVAL;
 	}
@@ -156,7 +157,7 @@ static int hsta_msi_probe(struct platform_device *pdev)
 		goto out;
 
 	ppc4xx_hsta_msi.irq_map = kmalloc(sizeof(int) * irq_count, GFP_KERNEL);
-	if (IS_ERR(ppc4xx_hsta_msi.irq_map)) {
+	if (!ppc4xx_hsta_msi.irq_map) {
 		ret = -ENOMEM;
 		goto out1;
 	}
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 6eb21f2ea585..24d0470c1698 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -93,7 +93,7 @@ static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (!msi_data->msi_virqs)
 		return -ENOMEM;
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		int_no = msi_bitmap_alloc_hwirqs(&msi_data->bitmap, 1);
 		if (int_no >= 0)
 			break;
@@ -127,7 +127,7 @@ void ppc4xx_teardown_msi_irqs(struct pci_dev *dev)
 
 	dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n");
 
-	list_for_each_entry(entry, &dev->msi_list, list) {
+	for_each_pci_msi_entry(entry, dev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 		irq_set_msi_desc(entry->irq, NULL);
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 6512cd8caa51..47b352e4bc74 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -244,7 +244,8 @@ static struct irq_chip qe_ic_irq_chip = {
 	.irq_mask_ack = qe_ic_mask_irq,
 };
 
-static int qe_ic_host_match(struct irq_domain *h, struct device_node *node)
+static int qe_ic_host_match(struct irq_domain *h, struct device_node *node,
+			    enum irq_domain_bus_token bus_token)
 {
 	/* Exact match, unless qe_ic node is NULL */
 	return h->of_node == NULL || h->of_node == node;
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index 68c7e5cc98e0..11ac964d5175 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -72,7 +72,7 @@ static unsigned int ics_opal_startup(struct irq_data *d)
 	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
 	 * at that level, so we do it here by hand.
 	 */
-	if (d->msi_desc)
+	if (irq_data_get_msi_desc(d))
 		pci_msi_unmask_irq(d);
 #endif
 
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index 0af97deb83f3..d1c625c4cc5a 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -75,7 +75,7 @@ static unsigned int ics_rtas_startup(struct irq_data *d)
 	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
 	 * at that level, so we do it here by hand.
 	 */
-	if (d->msi_desc)
+	if (irq_data_get_msi_desc(d))
 		pci_msi_unmask_irq(d);
 #endif
 	/* unmask it */
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 08c248eb491b..47e43b7b076b 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -298,7 +298,8 @@ int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
 }
 #endif /* CONFIG_SMP */
 
-static int xics_host_match(struct irq_domain *h, struct device_node *node)
+static int xics_host_match(struct irq_domain *h, struct device_node *node,
+			   enum irq_domain_bus_token bus_token)
 {
 	struct ics *ics;
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index e599259d84fc..6ef1231c6e9c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1987,7 +1987,6 @@ memex(void)
 			case '^':
 				adrs -= size;
 				break;
-				break;
 			case '/':
 				if (nslash > 0)
 					adrs -= 1 << nslash;
@@ -2731,7 +2730,7 @@ static void xmon_print_symbol(unsigned long address, const char *mid,
 void dump_segments(void)
 {
 	int i;
-	unsigned long esid,vsid,valid;
+	unsigned long esid,vsid;
 	unsigned long llp;
 
 	printf("SLB contents of cpu 0x%x\n", smp_processor_id());
@@ -2739,10 +2738,9 @@ void dump_segments(void)
 	for (i = 0; i < mmu_slb_size; i++) {
 		asm volatile("slbmfee  %0,%1" : "=r" (esid) : "r" (i));
 		asm volatile("slbmfev  %0,%1" : "=r" (vsid) : "r" (i));
-		valid = (esid & SLB_ESID_V);
-		if (valid | esid | vsid) {
+		if (esid || vsid) {
 			printf("%02d %016lx %016lx", i, esid, vsid);
-			if (valid) {
+			if (esid & SLB_ESID_V) {
 				llp = vsid & SLB_VSID_LLP;
 				if (vsid & SLB_VSID_B_1T) {
 					printf("  1T  ESID=%9lx  VSID=%13lx LLP:%3lx \n",
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index 2938934c6518..e256592eb66e 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -6,3 +6,4 @@ obj-$(CONFIG_S390_HYPFS_FS)	+= hypfs/
 obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
 obj-y				+= net/
 obj-$(CONFIG_PCI)		+= pci/
+obj-$(CONFIG_NUMA)		+= numa/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b06dc3839268..4827870f7a6d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -99,18 +99,22 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_DEVICES if !SMP
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_EARLY_PFN_TO_NID
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
@@ -153,6 +157,7 @@ config S390
 	select VIRT_CPU_ACCOUNTING
 	select VIRT_TO_BUS
 
+
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
 
@@ -385,6 +390,76 @@ config HOTPLUG_CPU
 config SCHED_SMT
 	def_bool n
 
+# Some NUMA nodes have memory ranges that span
+# other nodes.	Even though a pfn is valid and
+# between a node's start and end pfns, it may not
+# reside on that node.	See memmap_init_zone()
+# for details. <- They meant memory holes!
+config NODES_SPAN_OTHER_NODES
+	def_bool NUMA
+
+config NUMA
+	bool "NUMA support"
+	depends on SMP && 64BIT && SCHED_TOPOLOGY
+	default n
+	help
+	  Enable NUMA support
+
+	  This option adds NUMA support to the kernel.
+
+	  An operation mode can be selected by appending
+	  numa=<method> to the kernel command line.
+
+	  The default behaviour is identical to appending numa=plain to
+	  the command line. This will create just one node with all
+	  available memory and all CPUs in it.
+
+config NODES_SHIFT
+	int "Maximum NUMA nodes (as a power of 2)"
+	range 1 10
+	depends on NUMA
+	default "4"
+	help
+	  Specify the maximum number of NUMA nodes available on the target
+	  system. Increases memory reserved to accommodate various tables.
+
+menu "Select NUMA modes"
+	depends on NUMA
+
+config NUMA_EMU
+	bool "NUMA emulation"
+	default y
+	help
+	  Numa emulation mode will split the available system memory into
+	  equal chunks which then are distributed over the configured number
+	  of nodes in a round-robin manner.
+
+	  The number of fake nodes is limited by the number of available memory
+	  chunks (i.e. memory size / fake size) and the number of supported
+	  nodes in the kernel.
+
+	  The CPUs are assigned to the nodes in a way that partially respects
+	  the original machine topology (if supported by the machine).
+	  Fair distribution of the CPUs is not guaranteed.
+
+config EMU_SIZE
+	hex "NUMA emulation memory chunk size"
+	default 0x10000000
+	range 0x400000 0x100000000
+	depends on NUMA_EMU
+	help
+	  Select the default size by which the memory is chopped and then
+	  assigned to emulated NUMA nodes.
+
+	  This can be overridden by specifying
+
+	  emu_size=<n>
+
+	  on the kernel command line where also suffixes K, M, G, and T are
+	  supported.
+
+endmenu
+
 config SCHED_MC
 	def_bool n
 
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 667b1bca5681..e8d4423e4f85 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -33,6 +33,8 @@ mflags-$(CONFIG_MARCH_Z196)   := -march=z196
 mflags-$(CONFIG_MARCH_ZEC12)  := -march=zEC12
 mflags-$(CONFIG_MARCH_Z13)   := -march=z13
 
+export CC_FLAGS_MARCH := $(mflags-y)
+
 aflags-y += $(mflags-y)
 cflags-y += $(mflags-y)
 
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 940cbddd9237..0c98f1508542 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -13,6 +13,7 @@ CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
@@ -50,6 +51,7 @@ CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z196=y
 CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
+CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index d793fec91797..82083e1fbdc4 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -13,6 +13,7 @@ CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
@@ -49,6 +50,7 @@ CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z196=y
 CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
+CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 38a77e9c8aa6..c05c9e0821e3 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -13,6 +13,8 @@ CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_NUMA_BALANCING=y
+# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
@@ -48,6 +50,7 @@ CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z196=y
 CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=512
+CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 5566ce80abdb..0b9b95f3c703 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -24,6 +24,7 @@
 #include <crypto/algapi.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include "crypt_s390.h"
@@ -976,7 +977,7 @@ static void __exit aes_s390_fini(void)
 	crypto_unregister_alg(&aes_alg);
 }
 
-module_init(aes_s390_init);
+module_cpu_feature_match(MSA, aes_s390_init);
 module_exit(aes_s390_fini);
 
 MODULE_ALIAS_CRYPTO("aes-all");
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 9e05cc453a40..fba1c10a2dd0 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -16,6 +16,7 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <crypto/algapi.h>
 #include <crypto/des.h>
@@ -616,7 +617,7 @@ static void __exit des_s390_exit(void)
 	crypto_unregister_alg(&des_alg);
 }
 
-module_init(des_s390_init);
+module_cpu_feature_match(MSA, des_s390_init);
 module_exit(des_s390_exit);
 
 MODULE_ALIAS_CRYPTO("des");
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index b258110da952..26e14efd30a7 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -9,6 +9,7 @@
 
 #include <crypto/internal/hash.h>
 #include <linux/module.h>
+#include <linux/cpufeature.h>
 
 #include "crypt_s390.h"
 
@@ -158,7 +159,7 @@ static void __exit ghash_mod_exit(void)
 	crypto_unregister_shash(&ghash_alg);
 }
 
-module_init(ghash_mod_init);
+module_cpu_feature_match(MSA, ghash_mod_init);
 module_exit(ghash_mod_exit);
 
 MODULE_ALIAS_CRYPTO("ghash");
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 9d5192c94963..b8045b97f4fb 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/mutex.h>
+#include <linux/cpufeature.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <asm/debug.h>
@@ -914,6 +915,5 @@ static void __exit prng_exit(void)
 	}
 }
 
-
-module_init(prng_init);
+module_cpu_feature_match(MSA, prng_init);
 module_exit(prng_exit);
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index 5b2bee323694..9208eadae9f0 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -26,6 +26,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/cpufeature.h>
 #include <crypto/sha.h>
 
 #include "crypt_s390.h"
@@ -100,7 +101,7 @@ static void __exit sha1_s390_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(sha1_s390_init);
+module_cpu_feature_match(MSA, sha1_s390_init);
 module_exit(sha1_s390_fini);
 
 MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index b74ff158108c..667888f5c964 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -16,6 +16,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/cpufeature.h>
 #include <crypto/sha.h>
 
 #include "crypt_s390.h"
@@ -140,7 +141,7 @@ static void __exit sha256_s390_fini(void)
 	crypto_unregister_shash(&sha256_alg);
 }
 
-module_init(sha256_s390_init);
+module_cpu_feature_match(MSA, sha256_s390_init);
 module_exit(sha256_s390_fini);
 
 MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 0c36989ba182..2ba66b1518f0 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/cpufeature.h>
 
 #include "sha.h"
 #include "crypt_s390.h"
@@ -148,7 +149,7 @@ static void __exit fini(void)
 	crypto_unregister_shash(&sha384_alg);
 }
 
-module_init(init);
+module_cpu_feature_match(MSA, init);
 module_exit(fini);
 
 MODULE_LICENSE("GPL");
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index dc5385ebb071..5ad26dd94d77 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -3,5 +3,6 @@
 generic-y += clkdev.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index adbe3802e377..117fa5c921c1 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -27,6 +27,7 @@
 #define __ATOMIC_OR	"lao"
 #define __ATOMIC_AND	"lan"
 #define __ATOMIC_ADD	"laa"
+#define __ATOMIC_XOR	"lax"
 #define __ATOMIC_BARRIER "bcr	14,0\n"
 
 #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -49,6 +50,7 @@
 #define __ATOMIC_OR	"or"
 #define __ATOMIC_AND	"nr"
 #define __ATOMIC_ADD	"ar"
+#define __ATOMIC_XOR	"xr"
 #define __ATOMIC_BARRIER "\n"
 
 #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -118,15 +120,17 @@ static inline void atomic_add(int i, atomic_t *v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 #define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	__ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER);
+#define ATOMIC_OP(op, OP)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER);	\
 }
 
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	__ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER);
-}
+ATOMIC_OP(and, AND)
+ATOMIC_OP(or, OR)
+ATOMIC_OP(xor, XOR)
+
+#undef ATOMIC_OP
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -167,6 +171,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"laog"
 #define __ATOMIC64_AND	"lang"
 #define __ATOMIC64_ADD	"laag"
+#define __ATOMIC64_XOR	"laxg"
 #define __ATOMIC64_BARRIER "bcr	14,0\n"
 
 #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -189,6 +194,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"ogr"
 #define __ATOMIC64_AND	"ngr"
 #define __ATOMIC64_ADD	"agr"
+#define __ATOMIC64_XOR	"xgr"
 #define __ATOMIC64_BARRIER "\n"
 
 #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -247,16 +253,6 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	__ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
 }
 
-static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v)
-{
-	__ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER);
-}
-
-static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
-{
-	__ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER);
-}
-
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
 static inline long long atomic64_cmpxchg(atomic64_t *v,
@@ -270,6 +266,17 @@ static inline long long atomic64_cmpxchg(atomic64_t *v,
 	return old;
 }
 
+#define ATOMIC64_OP(op, OP)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	__ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER);	\
+}
+
+ATOMIC64_OP(and, AND)
+ATOMIC64_OP(or, OR)
+ATOMIC64_OP(xor, XOR)
+
+#undef ATOMIC64_OP
 #undef __ATOMIC64_LOOP
 
 static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index e6f8615a11eb..d48fe0162331 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -42,12 +42,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	___p1;								\
diff --git a/arch/s390/include/asm/cpufeature.h b/arch/s390/include/asm/cpufeature.h
new file mode 100644
index 000000000000..fa7e69b7c299
--- /dev/null
+++ b/arch/s390/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Module interface for CPU features
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_S390_CPUFEATURE_H
+#define __ASM_S390_CPUFEATURE_H
+
+#include <asm/elf.h>
+
+/* Hardware features on Linux on z Systems are indicated by facility bits that
+ * are mapped to the so-called machine flags.  Particular machine flags are
+ * then used to define ELF hardware capabilities; most notably hardware flags
+ * that are essential for user space / glibc.
+ *
+ * Restrict the set of exposed CPU features to ELF hardware capabilities for
+ * now.  Additional machine flags can be indicated by values larger than
+ * MAX_ELF_HWCAP_FEATURES.
+ */
+#define MAX_ELF_HWCAP_FEATURES	(8 * sizeof(elf_hwcap))
+#define MAX_CPU_FEATURES	MAX_ELF_HWCAP_FEATURES
+
+#define cpu_feature(feat)	ilog2(HWCAP_S390_ ## feat)
+
+int cpu_have_feature(unsigned int nr);
+
+#endif /* __ASM_S390_CPUFEATURE_H */
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index cfad7fca01d6..17a373576868 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -46,6 +46,8 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 	__ctl_load(reg, cr, cr);
 }
 
+void __ctl_set_vx(void);
+
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);
 
@@ -57,7 +59,10 @@ union ctlreg0 {
 		unsigned long lap  : 1; /* Low-address-protection control */
 		unsigned long	   : 4;
 		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
-		unsigned long	   : 23;
+		unsigned long	   : 4;
+		unsigned long afp  : 1; /* AFP-register control */
+		unsigned long vx   : 1; /* Vector enablement control */
+		unsigned long	   : 17;
 	};
 };
 
diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h
index 629b79a93165..f7e5c36688c3 100644
--- a/arch/s390/include/asm/etr.h
+++ b/arch/s390/include/asm/etr.h
@@ -214,6 +214,9 @@ static inline int etr_ptff(void *ptff_block, unsigned int func)
 void etr_switch_to_local(void);
 void etr_sync_check(void);
 
+/* notifier for syncs */
+extern struct atomic_notifier_head s390_epoch_delta_notifier;
+
 /* STP interruption parameter */
 struct stp_irq_parm {
 	unsigned int _pad0	: 14;
diff --git a/arch/s390/include/asm/fpu-internal.h b/arch/s390/include/asm/fpu-internal.h
new file mode 100644
index 000000000000..55dc2c0fb40a
--- /dev/null
+++ b/arch/s390/include/asm/fpu-internal.h
@@ -0,0 +1,110 @@
+/*
+ * General floating pointer and vector register helpers
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_S390_FPU_INTERNAL_H
+#define _ASM_S390_FPU_INTERNAL_H
+
+#define FPU_USE_VX		1	/* Vector extension is active */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <asm/linkage.h>
+#include <asm/ctl_reg.h>
+#include <asm/sigcontext.h>
+
+struct fpu {
+	__u32 fpc;			/* Floating-point control */
+	__u32 flags;
+	union {
+		void *regs;
+		freg_t *fprs;		/* Floating-point register save area */
+		__vector128 *vxrs;	/* Vector register save area */
+	};
+};
+
+void save_fpu_regs(void);
+
+#define is_vx_fpu(fpu) (!!((fpu)->flags & FPU_USE_VX))
+#define is_vx_task(tsk) (!!((tsk)->thread.fpu.flags & FPU_USE_VX))
+
+/* VX array structure for address operand constraints in inline assemblies */
+struct vx_array { __vector128 _[__NUM_VXRS]; };
+
+static inline int test_fp_ctl(u32 fpc)
+{
+	u32 orig_fpc;
+	int rc;
+
+	asm volatile(
+		"	efpc    %1\n"
+		"	sfpc	%2\n"
+		"0:	sfpc	%1\n"
+		"	la	%0,0\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "=d" (rc), "=d" (orig_fpc)
+		: "d" (fpc), "0" (-EINVAL));
+	return rc;
+}
+
+static inline void save_vx_regs_safe(__vector128 *vxrs)
+{
+	unsigned long cr0, flags;
+
+	flags = arch_local_irq_save();
+	__ctl_store(cr0, 0, 0);
+	__ctl_set_bit(0, 17);
+	__ctl_set_bit(0, 18);
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
+		: "=Q" (*(struct vx_array *) vxrs) : : "1");
+	__ctl_load(cr0, 0, 0);
+	arch_local_irq_restore(flags);
+}
+
+static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs)
+{
+	int i;
+
+	for (i = 0; i < __NUM_FPRS; i++)
+		fprs[i] = *(freg_t *)(vxrs + i);
+}
+
+static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
+{
+	int i;
+
+	for (i = 0; i < __NUM_FPRS; i++)
+		*(freg_t *)(vxrs + i) = fprs[i];
+}
+
+static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
+{
+	fpregs->pad = 0;
+	if (is_vx_fpu(fpu))
+		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
+	else
+		memcpy((freg_t *)&fpregs->fprs, fpu->fprs,
+		       sizeof(fpregs->fprs));
+}
+
+static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
+{
+	if (is_vx_fpu(fpu))
+		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
+	else
+		memcpy(fpu->fprs, (freg_t *)&fpregs->fprs,
+		       sizeof(fpregs->fprs));
+}
+
+#endif
+
+#endif /* _ASM_S390_FPU_INTERNAL_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 0130d0379edd..d9be7c0c1291 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -14,6 +14,7 @@
 
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range			free_pgd_range
+#define hugepages_supported()			(MACHINE_HAS_HPAGE)
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index cb5fdf3a78fc..437e9af96688 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -57,6 +57,8 @@ static inline void ioport_unmap(void __iomem *p)
  */
 #define pci_iomap pci_iomap
 #define pci_iounmap pci_iounmap
+#define pci_iomap_wc pci_iomap
+#define pci_iomap_wc_range pci_iomap_range
 
 #define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
 #define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 69972b7957ee..7f9fd5e3f1bf 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -12,14 +12,29 @@
  * We use a brcl 0,2 instruction for jump labels at compile time so it
  * can be easily distinguished from a hotpatch generated instruction.
  */
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("0:	brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
 		".pushsection __jump_table, \"aw\"\n"
 		".balign 8\n"
 		".quad 0b, %l[label], %0\n"
 		".popsection\n"
-		: : "X" (key) : : label);
+		: : "X" (&((char *)key)[branch]) : : label);
+
+	return false;
+label:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("0:	brcl 15, %l[label]\n"
+		".pushsection __jump_table, \"aw\"\n"
+		".balign 8\n"
+		".quad 0b, %l[label], %0\n"
+		".popsection\n"
+		: : "X" (&((char *)key)[branch]) : : label);
+
 	return false;
 label:
 	return true;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3024acbe1f9d..3d012e071647 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -22,6 +22,7 @@
 #include <linux/kvm.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
+#include <asm/fpu-internal.h>
 #include <asm/isc.h>
 
 #define KVM_MAX_VCPUS 64
@@ -258,6 +259,9 @@ struct kvm_vcpu_stat {
 	u32 diagnose_10;
 	u32 diagnose_44;
 	u32 diagnose_9c;
+	u32 diagnose_258;
+	u32 diagnose_308;
+	u32 diagnose_500;
 };
 
 #define PGM_OPERATION			0x01
@@ -498,10 +502,9 @@ struct kvm_guestdbg_info_arch {
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
-	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
-	s390_fp_regs      guest_fpregs;
-	struct kvm_s390_vregs	*host_vregs;
+	struct fpu	  host_fpregs;
+	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
@@ -630,7 +633,6 @@ extern char sie_exit;
 
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_check_processor_compat(void *rtn) {}
-static inline void kvm_arch_exit(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index fc8a8284778e..27da78cf416d 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -6,4 +6,26 @@
 #define __ALIGN .align 4, 0x07
 #define __ALIGN_STR __stringify(__ALIGN)
 
+#ifndef __ASSEMBLY__
+
+/*
+ * Helper macro for exception table entries
+ */
+#define EX_TABLE(_fault, _target)	\
+	".section __ex_table,\"a\"\n"	\
+	".align	4\n"			\
+	".long	(" #_fault ") - .\n"	\
+	".long	(" #_target ") - .\n"	\
+	".previous\n"
+
+#else /* __ASSEMBLY__ */
+
+#define EX_TABLE(_fault, _target)	\
+	.section __ex_table,"a"	;	\
+	.align	4 ;			\
+	.long	(_fault) - . ;		\
+	.long	(_target) - . ;		\
+	.previous
+
+#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/s390/include/asm/mm-arch-hooks.h b/arch/s390/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 07680b2f3c59..000000000000
--- a/arch/s390/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_S390_MM_ARCH_HOOKS_H
-#define _ASM_S390_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_S390_MM_ARCH_HOOKS_H */
diff --git a/arch/s390/include/asm/mmzone.h b/arch/s390/include/asm/mmzone.h
new file mode 100644
index 000000000000..a9e834e60b84
--- /dev/null
+++ b/arch/s390/include/asm/mmzone.h
@@ -0,0 +1,16 @@
+/*
+ * NUMA support for s390
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#ifndef _ASM_S390_MMZONE_H
+#define _ASM_S390_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid) (node_data[nid])
+
+#endif /* CONFIG_NUMA */
+#endif /* _ASM_S390_MMZONE_H */
diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h
new file mode 100644
index 000000000000..2a0efc63b9e5
--- /dev/null
+++ b/arch/s390/include/asm/numa.h
@@ -0,0 +1,35 @@
+/*
+ * NUMA support for s390
+ *
+ * Declare the NUMA core code structures and functions.
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#ifndef _ASM_S390_NUMA_H
+#define _ASM_S390_NUMA_H
+
+#ifdef CONFIG_NUMA
+
+#include <linux/numa.h>
+#include <linux/cpumask.h>
+
+void numa_setup(void);
+int numa_pfn_to_nid(unsigned long pfn);
+int __node_distance(int a, int b);
+void numa_update_cpu_topology(void);
+
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+extern int numa_debug_enabled;
+
+#else
+
+static inline void numa_setup(void) { }
+static inline void numa_update_cpu_topology(void) { }
+static inline int numa_pfn_to_nid(unsigned long pfn)
+{
+	return 0;
+}
+
+#endif /* CONFIG_NUMA */
+#endif /* _ASM_S390_NUMA_H */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index dd345238d9a7..53eacbd4f09b 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -17,10 +17,7 @@
 #define PAGE_DEFAULT_ACC	0
 #define PAGE_DEFAULT_KEY	(PAGE_DEFAULT_ACC << 4)
 
-#include <asm/setup.h>
-#ifndef __ASSEMBLY__
-
-extern int HPAGE_SHIFT;
+#define HPAGE_SHIFT	20
 #define HPAGE_SIZE	(1UL << HPAGE_SHIFT)
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
@@ -30,6 +27,9 @@ extern int HPAGE_SHIFT;
 #define ARCH_HAS_PREPARE_HUGEPAGE
 #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
 
+#include <asm/setup.h>
+#ifndef __ASSEMBLY__
+
 static inline void storage_key_init_range(unsigned long start, unsigned long end)
 {
 #if PAGE_DEFAULT_KEY
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index a648338c434a..34d960353a08 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -170,7 +170,11 @@ static inline void zpci_exit_slot(struct zpci_dev *zdev) {}
 #endif /* CONFIG_HOTPLUG_PCI_S390 */
 
 /* Helpers */
-struct zpci_dev *get_zdev(struct pci_dev *);
+static inline struct zpci_dev *to_zpci(struct pci_dev *pdev)
+{
+	return pdev->sysdata;
+}
+
 struct zpci_dev *get_zdev_by_fid(u32);
 
 /* DMA */
@@ -188,4 +192,20 @@ void zpci_debug_init_device(struct zpci_dev *);
 void zpci_debug_exit_device(struct zpci_dev *);
 void zpci_debug_info(struct zpci_dev *, struct seq_file *);
 
+#ifdef CONFIG_NUMA
+
+/* Returns the node based on PCI bus */
+static inline int __pcibus_to_node(const struct pci_bus *bus)
+{
+	return NUMA_NO_NODE;
+}
+
+static inline const struct cpumask *
+cpumask_of_pcibus(const struct pci_bus *bus)
+{
+	return cpu_online_mask;
+}
+
+#endif /* CONFIG_NUMA */
+
 #endif
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 4cb19fe76dd9..f897ec73dc8c 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -87,7 +87,15 @@ struct sf_raw_sample {
 } __packed;
 
 /* Perf hardware reserve and release functions */
+#ifdef CONFIG_PERF_EVENTS
 int perf_reserve_sampling(void);
 void perf_release_sampling(void);
+#else /* CONFIG_PERF_EVENTS */
+static inline int perf_reserve_sampling(void)
+{
+	return 0;
+}
+static inline void perf_release_sampling(void) {}
+#endif /* CONFIG_PERF_EVENTS */
 
 #endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index f66d82798a6a..bdb2f51124ed 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -576,6 +576,19 @@ static inline int pte_same(pte_t a, pte_t b)
 	return pte_val(a) == pte_val(b);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline int pte_protnone(pte_t pte)
+{
+	return pte_present(pte) && !(pte_val(pte) & _PAGE_READ);
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	/* pmd_large(pmd) implies pmd_present(pmd) */
+	return pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_READ);
+}
+#endif
+
 static inline pgste_t pgste_get_lock(pte_t *ptep)
 {
 	unsigned long new = 0;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dedb6218544b..085fb0d3c54e 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,10 +14,12 @@
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
 #define CIF_ASCE		1	/* user asce needs fixup / uaccess */
 #define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
+#define CIF_FPU			3	/* restore vector registers */
 
 #define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
 #define _CIF_ASCE		(1<<CIF_ASCE)
 #define _CIF_NOHZ_DELAY		(1<<CIF_NOHZ_DELAY)
+#define _CIF_FPU		(1<<CIF_FPU)
 
 #ifndef __ASSEMBLY__
 
@@ -28,6 +30,7 @@
 #include <asm/ptrace.h>
 #include <asm/setup.h>
 #include <asm/runtime_instr.h>
+#include <asm/fpu-internal.h>
 
 static inline void set_cpu_flag(int flag)
 {
@@ -85,7 +88,7 @@ typedef struct {
  * Thread structure
  */
 struct thread_struct {
-	s390_fp_regs fp_regs;
+	struct fpu fpu;			/* FP and VX register save area */
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	mm_segment_t mm_segment;
@@ -101,7 +104,6 @@ struct thread_struct {
 	struct runtime_instr_cb *ri_cb;
 	int ri_signum;
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
-	__vector128 *vxrs;		/* Vector register save area */
 };
 
 /* Flag to disable transactions. */
@@ -231,6 +233,17 @@ static inline void __load_psw_mask (unsigned long mask)
 }
 
 /*
+ * Extract current PSW mask
+ */
+static inline unsigned long __extract_psw(void)
+{
+	unsigned int reg1, reg2;
+
+	asm volatile("epsw %0,%1" : "=d" (reg1), "=a" (reg2));
+	return (((unsigned long) reg1) << 32) | ((unsigned long) reg2);
+}
+
+/*
  * Rewind PSW instruction address by specified number of bytes.
  */
 static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc)
@@ -336,25 +349,6 @@ extern void memcpy_absolute(void *, void *, size_t);
 	memcpy_absolute(&(dest), &__tmp, sizeof(__tmp));	\
 }
 
-/*
- * Helper macro for exception table entries
- */
-#define EX_TABLE(_fault, _target)	\
-	".section __ex_table,\"a\"\n"	\
-	".align	4\n"			\
-	".long	(" #_fault ") - .\n"	\
-	".long	(" #_target ") - .\n"	\
-	".previous\n"
-
-#else /* __ASSEMBLY__ */
-
-#define EX_TABLE(_fault, _target)	\
-	.section __ex_table,"a"	;	\
-	.align	4 ;			\
-	.long	(_fault) - . ;		\
-	.long	(_target) - . ;		\
-	.previous
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_S390_PROCESSOR_H */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index f6ff06077631..821dde5f425d 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -79,6 +79,6 @@ int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 void sclp_early_detect(void);
-long _sclp_print_early(const char *);
+int _sclp_print_early(const char *);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index d62e7a69605f..dcadfde32265 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -8,139 +8,12 @@
 #define __ASM_SWITCH_TO_H
 
 #include <linux/thread_info.h>
+#include <asm/fpu-internal.h>
 #include <asm/ptrace.h>
 
 extern struct task_struct *__switch_to(void *, void *);
 extern void update_cr_regs(struct task_struct *task);
 
-static inline int test_fp_ctl(u32 fpc)
-{
-	u32 orig_fpc;
-	int rc;
-
-	asm volatile(
-		"	efpc    %1\n"
-		"	sfpc	%2\n"
-		"0:	sfpc	%1\n"
-		"	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "=d" (rc), "=d" (orig_fpc)
-		: "d" (fpc), "0" (-EINVAL));
-	return rc;
-}
-
-static inline void save_fp_ctl(u32 *fpc)
-{
-	asm volatile(
-		"       stfpc   %0\n"
-		: "+Q" (*fpc));
-}
-
-static inline int restore_fp_ctl(u32 *fpc)
-{
-	int rc;
-
-	asm volatile(
-		"	lfpc    %1\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "=d" (rc) : "Q" (*fpc), "0" (-EINVAL));
-	return rc;
-}
-
-static inline void save_fp_regs(freg_t *fprs)
-{
-	asm volatile("std 0,%0" : "=Q" (fprs[0]));
-	asm volatile("std 2,%0" : "=Q" (fprs[2]));
-	asm volatile("std 4,%0" : "=Q" (fprs[4]));
-	asm volatile("std 6,%0" : "=Q" (fprs[6]));
-	asm volatile("std 1,%0" : "=Q" (fprs[1]));
-	asm volatile("std 3,%0" : "=Q" (fprs[3]));
-	asm volatile("std 5,%0" : "=Q" (fprs[5]));
-	asm volatile("std 7,%0" : "=Q" (fprs[7]));
-	asm volatile("std 8,%0" : "=Q" (fprs[8]));
-	asm volatile("std 9,%0" : "=Q" (fprs[9]));
-	asm volatile("std 10,%0" : "=Q" (fprs[10]));
-	asm volatile("std 11,%0" : "=Q" (fprs[11]));
-	asm volatile("std 12,%0" : "=Q" (fprs[12]));
-	asm volatile("std 13,%0" : "=Q" (fprs[13]));
-	asm volatile("std 14,%0" : "=Q" (fprs[14]));
-	asm volatile("std 15,%0" : "=Q" (fprs[15]));
-}
-
-static inline void restore_fp_regs(freg_t *fprs)
-{
-	asm volatile("ld 0,%0" : : "Q" (fprs[0]));
-	asm volatile("ld 2,%0" : : "Q" (fprs[2]));
-	asm volatile("ld 4,%0" : : "Q" (fprs[4]));
-	asm volatile("ld 6,%0" : : "Q" (fprs[6]));
-	asm volatile("ld 1,%0" : : "Q" (fprs[1]));
-	asm volatile("ld 3,%0" : : "Q" (fprs[3]));
-	asm volatile("ld 5,%0" : : "Q" (fprs[5]));
-	asm volatile("ld 7,%0" : : "Q" (fprs[7]));
-	asm volatile("ld 8,%0" : : "Q" (fprs[8]));
-	asm volatile("ld 9,%0" : : "Q" (fprs[9]));
-	asm volatile("ld 10,%0" : : "Q" (fprs[10]));
-	asm volatile("ld 11,%0" : : "Q" (fprs[11]));
-	asm volatile("ld 12,%0" : : "Q" (fprs[12]));
-	asm volatile("ld 13,%0" : : "Q" (fprs[13]));
-	asm volatile("ld 14,%0" : : "Q" (fprs[14]));
-	asm volatile("ld 15,%0" : : "Q" (fprs[15]));
-}
-
-static inline void save_vx_regs(__vector128 *vxrs)
-{
-	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
-
-	asm volatile(
-		"	la	1,%0\n"
-		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
-		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
-		: "=Q" (*(addrtype *) vxrs) : : "1");
-}
-
-static inline void save_vx_regs_safe(__vector128 *vxrs)
-{
-	unsigned long cr0, flags;
-
-	flags = arch_local_irq_save();
-	__ctl_store(cr0, 0, 0);
-	__ctl_set_bit(0, 17);
-	__ctl_set_bit(0, 18);
-	save_vx_regs(vxrs);
-	__ctl_load(cr0, 0, 0);
-	arch_local_irq_restore(flags);
-}
-
-static inline void restore_vx_regs(__vector128 *vxrs)
-{
-	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
-
-	asm volatile(
-		"	la	1,%0\n"
-		"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
-		"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
-		: : "Q" (*(addrtype *) vxrs) : "1");
-}
-
-static inline void save_fp_vx_regs(struct task_struct *task)
-{
-	if (task->thread.vxrs)
-		save_vx_regs(task->thread.vxrs);
-	else
-		save_fp_regs(task->thread.fp_regs.fprs);
-}
-
-static inline void restore_fp_vx_regs(struct task_struct *task)
-{
-	if (task->thread.vxrs)
-		restore_vx_regs(task->thread.vxrs);
-	else
-		restore_fp_regs(task->thread.fp_regs.fprs);
-}
-
 static inline void save_access_regs(unsigned int *acrs)
 {
 	typedef struct { int _[NUM_ACRS]; } acrstype;
@@ -157,15 +30,13 @@ static inline void restore_access_regs(unsigned int *acrs)
 
 #define switch_to(prev,next,last) do {					\
 	if (prev->mm) {							\
-		save_fp_ctl(&prev->thread.fp_regs.fpc);			\
-		save_fp_vx_regs(prev);					\
+		save_fpu_regs();					\
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
 	}								\
 	if (next->mm) {							\
 		update_cr_regs(next);					\
-		restore_fp_ctl(&next->thread.fp_regs.fpc);		\
-		restore_fp_vx_regs(next);				\
+		set_cpu_flag(CIF_FPU);					\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
 	}								\
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 4990f6c66288..27ebde643933 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -2,6 +2,7 @@
 #define _ASM_S390_TOPOLOGY_H
 
 #include <linux/cpumask.h>
+#include <asm/numa.h>
 
 struct sysinfo_15_1_x;
 struct cpu;
@@ -13,6 +14,7 @@ struct cpu_topology_s390 {
 	unsigned short core_id;
 	unsigned short socket_id;
 	unsigned short book_id;
+	unsigned short node_id;
 	cpumask_t thread_mask;
 	cpumask_t core_mask;
 	cpumask_t book_mask;
@@ -52,6 +54,43 @@ static inline void topology_expect_change(void) { }
 #define POLARIZATION_VM		(2)
 #define POLARIZATION_VH		(3)
 
+#define SD_BOOK_INIT	SD_CPU_INIT
+
+#ifdef CONFIG_NUMA
+
+#define cpu_to_node cpu_to_node
+static inline int cpu_to_node(int cpu)
+{
+	return per_cpu(cpu_topology, cpu).node_id;
+}
+
+/* Returns a pointer to the cpumask of CPUs on node 'node'. */
+#define cpumask_of_node cpumask_of_node
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+	return node_to_cpumask_map[node];
+}
+
+/*
+ * Returns the number of the node containing node 'node'. This
+ * architecture is flat, so it is a pretty simple function!
+ */
+#define parent_node(node) (node)
+
+#define pcibus_to_node(bus) __pcibus_to_node(bus)
+
+#define node_distance(a, b) __node_distance(a, b)
+
+#else /* !CONFIG_NUMA */
+
+#define numa_node_id numa_node_id
+static inline int numa_node_id(void)
+{
+	return 0;
+}
+
+#endif /* CONFIG_NUMA */
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 91f56b1d8156..525cef73b085 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -11,16 +11,24 @@
 
 #define __IGNORE_time
 
-/* Ignore NUMA system calls. Not wired up on s390. */
-#define __IGNORE_mbind
-#define __IGNORE_get_mempolicy
-#define __IGNORE_set_mempolicy
-#define __IGNORE_migrate_pages
-#define __IGNORE_move_pages
-
-/* Ignore system calls that are also reachable via sys_socket */
+/* Ignore system calls that are also reachable via sys_socketcall */
 #define __IGNORE_recvmmsg
 #define __IGNORE_sendmmsg
+#define __IGNORE_socket
+#define __IGNORE_socketpair
+#define __IGNORE_bind
+#define __IGNORE_connect
+#define __IGNORE_listen
+#define __IGNORE_accept4
+#define __IGNORE_getsockopt
+#define __IGNORE_setsockopt
+#define __IGNORE_getsockname
+#define __IGNORE_getpeername
+#define __IGNORE_sendto
+#define __IGNORE_sendmsg
+#define __IGNORE_recvfrom
+#define __IGNORE_recvmsg
+#define __IGNORE_shutdown
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h
new file mode 100644
index 000000000000..4a3135620f5e
--- /dev/null
+++ b/arch/s390/include/asm/vx-insn.h
@@ -0,0 +1,480 @@
+/*
+ * Support for Vector Instructions
+ *
+ * Assembler macros to generate .byte/.word code for particular
+ * vector instructions that are supported by recent binutils (>= 2.26) only.
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_S390_VX_INSN_H
+#define __ASM_S390_VX_INSN_H
+
+#ifdef __ASSEMBLY__
+
+
+/* Macros to generate vector instruction byte code */
+
+#define REG_NUM_INVALID	       255
+
+/* GR_NUM - Retrieve general-purpose register number
+ *
+ * @opd:	Operand to store register number
+ * @r64:	String designation register in the format "%rN"
+ */
+.macro	GR_NUM	opd gr
+	\opd = REG_NUM_INVALID
+	.ifc \gr,%r0
+		\opd = 0
+	.endif
+	.ifc \gr,%r1
+		\opd = 1
+	.endif
+	.ifc \gr,%r2
+		\opd = 2
+	.endif
+	.ifc \gr,%r3
+		\opd = 3
+	.endif
+	.ifc \gr,%r4
+		\opd = 4
+	.endif
+	.ifc \gr,%r5
+		\opd = 5
+	.endif
+	.ifc \gr,%r6
+		\opd = 6
+	.endif
+	.ifc \gr,%r7
+		\opd = 7
+	.endif
+	.ifc \gr,%r8
+		\opd = 8
+	.endif
+	.ifc \gr,%r9
+		\opd = 9
+	.endif
+	.ifc \gr,%r10
+		\opd = 10
+	.endif
+	.ifc \gr,%r11
+		\opd = 11
+	.endif
+	.ifc \gr,%r12
+		\opd = 12
+	.endif
+	.ifc \gr,%r13
+		\opd = 13
+	.endif
+	.ifc \gr,%r14
+		\opd = 14
+	.endif
+	.ifc \gr,%r15
+		\opd = 15
+	.endif
+	.if \opd == REG_NUM_INVALID
+		.error "Invalid general-purpose register designation: \gr"
+	.endif
+.endm
+
+/* VX_R() - Macro to encode the VX_NUM into the instruction */
+#define VX_R(v)		(v & 0x0F)
+
+/* VX_NUM - Retrieve vector register number
+ *
+ * @opd:	Operand to store register number
+ * @vxr:	String designation register in the format "%vN"
+ *
+ * The vector register number is used for as input number to the
+ * instruction and, as well as, to compute the RXB field of the
+ * instruction.  To encode the particular vector register number,
+ * use the VX_R(v) macro to extract the instruction opcode.
+ */
+.macro	VX_NUM	opd vxr
+	\opd = REG_NUM_INVALID
+	.ifc \vxr,%v0
+		\opd = 0
+	.endif
+	.ifc \vxr,%v1
+		\opd = 1
+	.endif
+	.ifc \vxr,%v2
+		\opd = 2
+	.endif
+	.ifc \vxr,%v3
+		\opd = 3
+	.endif
+	.ifc \vxr,%v4
+		\opd = 4
+	.endif
+	.ifc \vxr,%v5
+		\opd = 5
+	.endif
+	.ifc \vxr,%v6
+		\opd = 6
+	.endif
+	.ifc \vxr,%v7
+		\opd = 7
+	.endif
+	.ifc \vxr,%v8
+		\opd = 8
+	.endif
+	.ifc \vxr,%v9
+		\opd = 9
+	.endif
+	.ifc \vxr,%v10
+		\opd = 10
+	.endif
+	.ifc \vxr,%v11
+		\opd = 11
+	.endif
+	.ifc \vxr,%v12
+		\opd = 12
+	.endif
+	.ifc \vxr,%v13
+		\opd = 13
+	.endif
+	.ifc \vxr,%v14
+		\opd = 14
+	.endif
+	.ifc \vxr,%v15
+		\opd = 15
+	.endif
+	.ifc \vxr,%v16
+		\opd = 16
+	.endif
+	.ifc \vxr,%v17
+		\opd = 17
+	.endif
+	.ifc \vxr,%v18
+		\opd = 18
+	.endif
+	.ifc \vxr,%v19
+		\opd = 19
+	.endif
+	.ifc \vxr,%v20
+		\opd = 20
+	.endif
+	.ifc \vxr,%v21
+		\opd = 21
+	.endif
+	.ifc \vxr,%v22
+		\opd = 22
+	.endif
+	.ifc \vxr,%v23
+		\opd = 23
+	.endif
+	.ifc \vxr,%v24
+		\opd = 24
+	.endif
+	.ifc \vxr,%v25
+		\opd = 25
+	.endif
+	.ifc \vxr,%v26
+		\opd = 26
+	.endif
+	.ifc \vxr,%v27
+		\opd = 27
+	.endif
+	.ifc \vxr,%v28
+		\opd = 28
+	.endif
+	.ifc \vxr,%v29
+		\opd = 29
+	.endif
+	.ifc \vxr,%v30
+		\opd = 30
+	.endif
+	.ifc \vxr,%v31
+		\opd = 31
+	.endif
+	.if \opd == REG_NUM_INVALID
+		.error "Invalid vector register designation: \vxr"
+	.endif
+.endm
+
+/* RXB - Compute most significant bit used vector registers
+ *
+ * @rxb:	Operand to store computed RXB value
+ * @v1:		First vector register designated operand
+ * @v2:		Second vector register designated operand
+ * @v3:		Third vector register designated operand
+ * @v4:		Fourth vector register designated operand
+ */
+.macro	RXB	rxb v1 v2=0 v3=0 v4=0
+	\rxb = 0
+	.if \v1 & 0x10
+		\rxb = \rxb | 0x08
+	.endif
+	.if \v2 & 0x10
+		\rxb = \rxb | 0x04
+	.endif
+	.if \v3 & 0x10
+		\rxb = \rxb | 0x02
+	.endif
+	.if \v4 & 0x10
+		\rxb = \rxb | 0x01
+	.endif
+.endm
+
+/* MRXB - Generate Element Size Control and RXB value
+ *
+ * @m:		Element size control
+ * @v1:		First vector register designated operand (for RXB)
+ * @v2:		Second vector register designated operand (for RXB)
+ * @v3:		Third vector register designated operand (for RXB)
+ * @v4:		Fourth vector register designated operand (for RXB)
+ */
+.macro	MRXB	m v1 v2=0 v3=0 v4=0
+	rxb = 0
+	RXB	rxb, \v1, \v2, \v3, \v4
+	.byte	(\m << 4) | rxb
+.endm
+
+/* MRXBOPC - Generate Element Size Control, RXB, and final Opcode fields
+ *
+ * @m:		Element size control
+ * @opc:	Opcode
+ * @v1:		First vector register designated operand (for RXB)
+ * @v2:		Second vector register designated operand (for RXB)
+ * @v3:		Third vector register designated operand (for RXB)
+ * @v4:		Fourth vector register designated operand (for RXB)
+ */
+.macro	MRXBOPC	m opc v1 v2=0 v3=0 v4=0
+	MRXB	\m, \v1, \v2, \v3, \v4
+	.byte	\opc
+.endm
+
+/* Vector support instructions */
+
+/* VECTOR GENERATE BYTE MASK */
+.macro	VGBM	vr imm2
+	VX_NUM	v1, \vr
+	.word	(0xE700 | (VX_R(v1) << 4))
+	.word	\imm2
+	MRXBOPC	0, 0x44, v1
+.endm
+.macro	VZERO	vxr
+	VGBM	\vxr, 0
+.endm
+.macro	VONE	vxr
+	VGBM	\vxr, 0xFFFF
+.endm
+
+/* VECTOR LOAD VR ELEMENT FROM GR */
+.macro	VLVG	v, gr, disp, m
+	VX_NUM	v1, \v
+	GR_NUM	b2, "%r0"
+	GR_NUM	r3, \gr
+	.word	0xE700 | (VX_R(v1) << 4) | r3
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m, 0x22, v1
+.endm
+.macro	VLVGB	v, gr, index, base
+	VLVG	\v, \gr, \index, \base, 0
+.endm
+.macro	VLVGH	v, gr, index
+	VLVG	\v, \gr, \index, 1
+.endm
+.macro	VLVGF	v, gr, index
+	VLVG	\v, \gr, \index, 2
+.endm
+.macro	VLVGG	v, gr, index
+	VLVG	\v, \gr, \index, 3
+.endm
+
+/* VECTOR LOAD */
+.macro	VL	v, disp, index="%r0", base
+	VX_NUM	v1, \v
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base
+	.word	0xE700 | (VX_R(v1) << 4) | x2
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC 0, 0x06, v1
+.endm
+
+/* VECTOR LOAD ELEMENT */
+.macro	VLEx	vr1, disp, index="%r0", base, m3, opc
+	VX_NUM	v1, \vr1
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base
+	.word	0xE700 | (VX_R(v1) << 4) | x2
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m3, \opc, v1
+.endm
+.macro	VLEB	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x00
+.endm
+.macro	VLEH	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x01
+.endm
+.macro	VLEF	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x03
+.endm
+.macro	VLEG	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x02
+.endm
+
+/* VECTOR LOAD ELEMENT IMMEDIATE */
+.macro	VLEIx	vr1, imm2, m3, opc
+	VX_NUM	v1, \vr1
+	.word	0xE700 | (VX_R(v1) << 4)
+	.word	\imm2
+	MRXBOPC	\m3, \opc, v1
+.endm
+.macro	VLEIB	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x40
+.endm
+.macro	VLEIH	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x41
+.endm
+.macro	VLEIF	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x43
+.endm
+.macro	VLEIG	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x42
+.endm
+
+/* VECTOR LOAD GR FROM VR ELEMENT */
+.macro	VLGV	gr, vr, disp, base="%r0", m
+	GR_NUM	r1, \gr
+	GR_NUM	b2, \base
+	VX_NUM	v3, \vr
+	.word	0xE700 | (r1 << 4) | VX_R(v3)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m, 0x21, v3
+.endm
+.macro	VLGVB	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 0
+.endm
+.macro	VLGVH	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 1
+.endm
+.macro	VLGVF	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 2
+.endm
+.macro	VLGVG	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 3
+.endm
+
+/* VECTOR LOAD MULTIPLE */
+.macro	VLM	vfrom, vto, disp, base
+	VX_NUM	v1, \vfrom
+	VX_NUM	v3, \vto
+	GR_NUM	b2, \base	    /* Base register */
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v3)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	0, 0x36, v1, v3
+.endm
+
+/* VECTOR STORE MULTIPLE */
+.macro	VSTM	vfrom, vto, disp, base
+	VX_NUM	v1, \vfrom
+	VX_NUM	v3, \vto
+	GR_NUM	b2, \base	    /* Base register */
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v3)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	0, 0x3E, v1, v3
+.endm
+
+/* VECTOR PERMUTE */
+.macro	VPERM	vr1, vr2, vr3, vr4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	VX_NUM	v4, \vr4
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	VX_R(v4), 0x8C, v1, v2, v3, v4
+.endm
+
+/* VECTOR UNPACK LOGICAL LOW */
+.macro	VUPLL	vr1, vr2, m3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	0x0000
+	MRXBOPC	\m3, 0xD4, v1, v2
+.endm
+.macro	VUPLLB	vr1, vr2
+	VUPLL	\vr1, \vr2, 0
+.endm
+.macro	VUPLLH	vr1, vr2
+	VUPLL	\vr1, \vr2, 1
+.endm
+.macro	VUPLLF	vr1, vr2
+	VUPLL	\vr1, \vr2, 2
+.endm
+
+
+/* Vector integer instructions */
+
+/* VECTOR EXCLUSIVE OR */
+.macro	VX	vr1, vr2, vr3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	0, 0x6D, v1, v2, v3
+.endm
+
+/* VECTOR GALOIS FIELD MULTIPLY SUM */
+.macro	VGFM	vr1, vr2, vr3, m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	\m4, 0xB4, v1, v2, v3
+.endm
+.macro	VGFMB	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 0
+.endm
+.macro	VGFMH	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 1
+.endm
+.macro	VGFMF	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 2
+.endm
+.macro	VGFMG	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 3
+.endm
+
+/* VECTOR GALOIS FIELD MULTIPLY SUM AND ACCUMULATE */
+.macro	VGFMA	vr1, vr2, vr3, vr4, m5
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	VX_NUM	v4, \vr4
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12) | (\m5 << 8)
+	MRXBOPC	VX_R(v4), 0xBC, v1, v2, v3, v4
+.endm
+.macro	VGFMAB	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 0
+.endm
+.macro	VGFMAH	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 1
+.endm
+.macro	VGFMAF	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 2
+.endm
+.macro	VGFMAG	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 3
+.endm
+
+/* VECTOR SHIFT RIGHT LOGICAL BY BYTE */
+.macro	VSRLB	vr1, vr2, vr3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	0, 0x7D, v1, v2, v3
+.endm
+
+
+#endif	/* __ASSEMBLY__ */
+#endif	/* __ASM_S390_VX_INSN_H */
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 67878af257a0..59d2bb4e2d0c 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -204,9 +204,9 @@
 #define __NR_statfs64		265
 #define __NR_fstatfs64		266
 #define __NR_remap_file_pages	267
-/* Number 268 is reserved for new sys_mbind */
-/* Number 269 is reserved for new sys_get_mempolicy */
-/* Number 270 is reserved for new sys_set_mempolicy */
+#define __NR_mbind		268
+#define __NR_get_mempolicy	269
+#define __NR_set_mempolicy	270
 #define __NR_mq_open		271
 #define __NR_mq_unlink		272
 #define __NR_mq_timedsend	273
@@ -223,7 +223,7 @@
 #define __NR_inotify_init	284
 #define __NR_inotify_add_watch	285
 #define __NR_inotify_rm_watch	286
-/* Number 287 is reserved for new sys_migrate_pages */
+#define __NR_migrate_pages	287
 #define __NR_openat		288
 #define __NR_mkdirat		289
 #define __NR_mknodat		290
@@ -245,7 +245,7 @@
 #define __NR_sync_file_range	307
 #define __NR_tee		308
 #define __NR_vmsplice		309
-/* Number 310 is reserved for new sys_move_pages */
+#define __NR_move_pages		310
 #define __NR_getcpu		311
 #define __NR_epoll_pwait	312
 #define __NR_utimes		313
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index ffb87617a36c..b756c6348ac6 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -28,6 +28,17 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 CFLAGS_sysinfo.o += -w
 
+#
+# Use -march=z900 for sclp.c to be able to print an error message if
+# the kernel is started on a machine which is too old
+#
+CFLAGS_REMOVE_sclp.o = $(CC_FLAGS_FTRACE)
+ifneq ($(CC_FLAGS_MARCH),-march=z900)
+CFLAGS_REMOVE_sclp.o += $(CC_FLAGS_MARCH)
+CFLAGS_sclp.o	+= -march=z900
+endif
+GCOV_PROFILE_sclp.o := n
+
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index c7d1b9d09011..48c9af7a7683 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -23,15 +23,18 @@
 
 int main(void)
 {
-	DEFINE(__THREAD_info, offsetof(struct task_struct, stack));
-	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp));
-	DEFINE(__THREAD_mm_segment, offsetof(struct task_struct, thread.mm_segment));
-	BLANK();
+	DEFINE(__TASK_thread_info, offsetof(struct task_struct, stack));
+	DEFINE(__TASK_thread, offsetof(struct task_struct, thread));
 	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
 	BLANK();
-	DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause));
-	DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address));
-	DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid));
+	DEFINE(__THREAD_ksp, offsetof(struct thread_struct, ksp));
+	DEFINE(__THREAD_FPU_fpc, offsetof(struct thread_struct, fpu.fpc));
+	DEFINE(__THREAD_FPU_flags, offsetof(struct thread_struct, fpu.flags));
+	DEFINE(__THREAD_FPU_regs, offsetof(struct thread_struct, fpu.regs));
+	DEFINE(__THREAD_per_cause, offsetof(struct thread_struct, per_event.cause));
+	DEFINE(__THREAD_per_address, offsetof(struct thread_struct, per_event.address));
+	DEFINE(__THREAD_per_paid, offsetof(struct thread_struct, per_event.paid));
+	DEFINE(__THREAD_trap_tdb, offsetof(struct thread_struct, trap_tdb));
 	BLANK();
 	DEFINE(__TI_task, offsetof(struct thread_info, task));
 	DEFINE(__TI_flags, offsetof(struct thread_info, flags));
@@ -176,7 +179,6 @@ int main(void)
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
-	DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb));
 	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 	DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c));
 	DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20));
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index bff5e3b6d822..8ba32436effe 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -138,6 +138,8 @@ int init_cache_level(unsigned int cpu)
 	union cache_topology ct;
 	enum cache_type ctype;
 
+	if (!test_facility(34))
+		return -EOPNOTSUPP;
 	if (!this_cpu_ci)
 		return -EINVAL;
 	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index fe8d6924efaa..eb4664238613 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -153,33 +153,14 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 /* Store registers needed to create the signal frame */
 static void store_sigregs(void)
 {
-	int i;
-
 	save_access_regs(current->thread.acrs);
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	if (current->thread.vxrs) {
-		save_vx_regs(current->thread.vxrs);
-		for (i = 0; i < __NUM_FPRS; i++)
-			current->thread.fp_regs.fprs[i] =
-				*(freg_t *)(current->thread.vxrs + i);
-	} else
-		save_fp_regs(current->thread.fp_regs.fprs);
+	save_fpu_regs();
 }
 
 /* Load registers after signal return */
 static void load_sigregs(void)
 {
-	int i;
-
 	restore_access_regs(current->thread.acrs);
-	/* restore_fp_ctl is done in restore_sigregs */
-	if (current->thread.vxrs) {
-		for (i = 0; i < __NUM_FPRS; i++)
-			*(freg_t *)(current->thread.vxrs + i) =
-				current->thread.fp_regs.fprs[i];
-		restore_vx_regs(current->thread.vxrs);
-	} else
-		restore_fp_regs(current->thread.fp_regs.fprs);
 }
 
 static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
@@ -196,8 +177,7 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 		user_sregs.regs.gprs[i] = (__u32) regs->gprs[i];
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
-	       sizeof(user_sregs.fpregs));
+	fpregs_store((_s390_fp_regs *) &user_sregs.fpregs, &current->thread.fpu);
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32)))
 		return -EFAULT;
 	return 0;
@@ -217,8 +197,8 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW32_MASK_RI))
 		return -EINVAL;
 
-	/* Loading the floating-point-control word can fail. Do that first. */
-	if (restore_fp_ctl(&user_sregs.fpregs.fpc))
+	/* Test the floating-point-control word. */
+	if (test_fp_ctl(user_sregs.fpregs.fpc))
 		return -EINVAL;
 
 	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
@@ -235,9 +215,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 		regs->gprs[i] = (__u64) user_sregs.regs.gprs[i];
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-
-	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
-	       sizeof(current->thread.fp_regs));
+	fpregs_load((_s390_fp_regs *) &user_sregs.fpregs, &current->thread.fpu);
 
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
@@ -258,13 +236,13 @@ static int save_sigregs_ext32(struct pt_regs *regs,
 		return -EFAULT;
 
 	/* Save vector registers to signal stack */
-	if (current->thread.vxrs) {
+	if (is_vx_task(current)) {
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+			vxrs[i] = *((__u64 *)(current->thread.fpu.vxrs + i) + 1);
 		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
 				   sizeof(sregs_ext->vxrs_low)) ||
 		    __copy_to_user(&sregs_ext->vxrs_high,
-				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   current->thread.fpu.vxrs + __NUM_VXRS_LOW,
 				   sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 	}
@@ -286,15 +264,15 @@ static int restore_sigregs_ext32(struct pt_regs *regs,
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
 
 	/* Restore vector registers from signal stack */
-	if (current->thread.vxrs) {
+	if (is_vx_task(current)) {
 		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
 				     sizeof(sregs_ext->vxrs_low)) ||
-		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+		    __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW,
 				     &sregs_ext->vxrs_high,
 				     sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+			*((__u64 *)(current->thread.fpu.vxrs + i) + 1) = vxrs[i];
 	}
 	return 0;
 }
@@ -308,6 +286,7 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
 		goto badframe;
 	set_current_blocked(&set);
+	save_fpu_regs();
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
 	if (restore_sigregs_ext32(regs, &frame->sregs_ext))
@@ -330,6 +309,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 	set_current_blocked(&set);
 	if (compat_restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
+	save_fpu_regs();
 	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 	if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
@@ -472,7 +452,7 @@ static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 	 */
 	uc_flags = UC_GPRS_HIGH;
 	if (MACHINE_HAS_VX) {
-		if (current->thread.vxrs)
+		if (is_vx_task(current))
 			uc_flags |= UC_VXRS;
 	} else
 		frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) +
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3238893c9d4f..247b7aae4c6d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -20,6 +20,8 @@
 #include <asm/page.h>
 #include <asm/sigp.h>
 #include <asm/irq.h>
+#include <asm/fpu-internal.h>
+#include <asm/vx-insn.h>
 
 __PT_R0      =	__PT_GPRS
 __PT_R1      =	__PT_GPRS + 8
@@ -46,10 +48,10 @@ _TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		   _TIF_UPROBE)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
-_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE)
+_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE | _CIF_FPU)
 _PIF_WORK	= (_PIF_PER_TRAP)
 
-#define BASED(name) name-system_call(%r13)
+#define BASED(name) name-cleanup_critical(%r13)
 
 	.macro	TRACE_IRQS_ON
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -73,38 +75,6 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 #endif
 	.endm
 
-	.macro LPP newpp
-#if IS_ENABLED(CONFIG_KVM)
-	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_LPP
-	jz	.+8
-	.insn	s,0xb2800000,\newpp
-#endif
-	.endm
-
-	.macro	HANDLE_SIE_INTERCEPT scratch,reason
-#if IS_ENABLED(CONFIG_KVM)
-	tmhh	%r8,0x0001		# interrupting from user ?
-	jnz	.+62
-	lgr	\scratch,%r9
-	slg	\scratch,BASED(.Lsie_critical)
-	clg	\scratch,BASED(.Lsie_critical_length)
-	.if	\reason==1
-	# Some program interrupts are suppressing (e.g. protection).
-	# We must also check the instruction after SIE in that case.
-	# do_protection_exception will rewind to .Lrewind_pad
-	jh	.+42
-	.else
-	jhe	.+42
-	.endif
-	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
-	LPP	__SF_EMPTY+16(%r15)		# set host id
-	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
-	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-	larl	%r9,sie_exit			# skip forward to sie_exit
-	mvi	__SF_EMPTY+31(%r15),\reason	# set exit reason
-#endif
-	.endm
-
 	.macro	CHECK_STACK stacksize,savearea
 #ifdef CONFIG_CHECK_STACK
 	tml	%r15,\stacksize - CONFIG_STACK_GUARD
@@ -113,7 +83,7 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 #endif
 	.endm
 
-	.macro	SWITCH_ASYNC savearea,stack,shift
+	.macro	SWITCH_ASYNC savearea,timer
 	tmhh	%r8,0x0001		# interrupting from user ?
 	jnz	1f
 	lgr	%r14,%r9
@@ -124,26 +94,28 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 	brasl	%r14,cleanup_critical
 	tmhh	%r8,0x0001		# retest problem state after cleanup
 	jnz	1f
-0:	lg	%r14,\stack		# are we already on the target stack?
+0:	lg	%r14,__LC_ASYNC_STACK	# are we already on the async stack?
 	slgr	%r14,%r15
-	srag	%r14,%r14,\shift
-	jnz	1f
-	CHECK_STACK 1<<\shift,\savearea
+	srag	%r14,%r14,STACK_SHIFT
+	jnz	2f
+	CHECK_STACK 1<<STACK_SHIFT,\savearea
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	j	2f
-1:	lg	%r15,\stack		# load target stack
-2:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	j	3f
+1:	LAST_BREAK %r14
+	UPDATE_VTIME %r14,%r15,\timer
+2:	lg	%r15,__LC_ASYNC_STACK	# load async stack
+3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	.endm
 
-	.macro UPDATE_VTIME scratch,enter_timer
-	lg	\scratch,__LC_EXIT_TIMER
-	slg	\scratch,\enter_timer
-	alg	\scratch,__LC_USER_TIMER
-	stg	\scratch,__LC_USER_TIMER
-	lg	\scratch,__LC_LAST_UPDATE_TIMER
-	slg	\scratch,__LC_EXIT_TIMER
-	alg	\scratch,__LC_SYSTEM_TIMER
-	stg	\scratch,__LC_SYSTEM_TIMER
+	.macro UPDATE_VTIME w1,w2,enter_timer
+	lg	\w1,__LC_EXIT_TIMER
+	lg	\w2,__LC_LAST_UPDATE_TIMER
+	slg	\w1,\enter_timer
+	slg	\w2,__LC_EXIT_TIMER
+	alg	\w1,__LC_USER_TIMER
+	alg	\w2,__LC_SYSTEM_TIMER
+	stg	\w1,__LC_USER_TIMER
+	stg	\w2,__LC_SYSTEM_TIMER
 	mvc	__LC_LAST_UPDATE_TIMER(8),\enter_timer
 	.endm
 
@@ -178,21 +150,88 @@ _PIF_WORK	= (_PIF_PER_TRAP)
  */
 ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
-	stg	%r15,__THREAD_ksp(%r2)		# store kernel stack of prev
-	lg	%r4,__THREAD_info(%r2)		# get thread_info of prev
-	lg	%r5,__THREAD_info(%r3)		# get thread_info of next
+	lgr	%r1,%r2
+	aghi	%r1,__TASK_thread		# thread_struct of prev task
+	lg	%r4,__TASK_thread_info(%r2)	# get thread_info of prev
+	lg	%r5,__TASK_thread_info(%r3)	# get thread_info of next
+	stg	%r15,__THREAD_ksp(%r1)		# store kernel stack of prev
+	lgr	%r1,%r3
+	aghi	%r1,__TASK_thread		# thread_struct of next task
 	lgr	%r15,%r5
 	aghi	%r15,STACK_INIT			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
+	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
-	lg	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
 .L__critical_start:
+
+#if IS_ENABLED(CONFIG_KVM)
+/*
+ * sie64a calling convention:
+ * %r2 pointer to sie control block
+ * %r3 guest register save area
+ */
+ENTRY(sie64a)
+	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
+	stg	%r2,__SF_EMPTY(%r15)		# save control block pointer
+	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
+	xc	__SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU	# load guest fp/vx registers ?
+	jno	.Lsie_load_guest_gprs
+	brasl	%r14,load_fpu_regs		# load guest fp/vx regs
+.Lsie_load_guest_gprs:
+	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
+	lg	%r14,__LC_GMAP			# get gmap pointer
+	ltgr	%r14,%r14
+	jz	.Lsie_gmap
+	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
+.Lsie_gmap:
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
+	tm	__SIE_PROG20+3(%r14),3		# last exit...
+	jnz	.Lsie_skip
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	jo	.Lsie_skip			# exit if fp/vx regs changed
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_LPP
+	jz	.Lsie_enter
+	.insn	s,0xb2800000,__LC_CURRENT_PID	# set guest id to pid
+.Lsie_enter:
+	sie	0(%r14)
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_LPP
+	jz	.Lsie_skip
+	.insn	s,0xb2800000,__SF_EMPTY+16(%r15)# set host id
+.Lsie_skip:
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+.Lsie_done:
+# some program checks are suppressing. C code (e.g. do_protection_exception)
+# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
+# instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# See also .Lcleanup_sie
+.Lrewind_pad:
+	nop	0
+	.globl sie_exit
+sie_exit:
+	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
+	lg	%r2,__SF_EMPTY+24(%r15)		# return exit reason code
+	br	%r14
+.Lsie_fault:
+	lghi	%r14,-EFAULT
+	stg	%r14,__SF_EMPTY+24(%r15)	# set exit reason code
+	j	sie_exit
+
+	EX_TABLE(.Lrewind_pad,.Lsie_fault)
+	EX_TABLE(sie_exit,.Lsie_fault)
+#endif
+
 /*
  * SVC interrupt handler routine. System calls are synchronous events and
  * are executed with interrupts enabled.
@@ -208,9 +247,9 @@ ENTRY(system_call)
 .Lsysc_per:
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
-.Lsysc_vtime:
-	UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER
 	LAST_BREAK %r13
+.Lsysc_vtime:
+	UPDATE_VTIME %r10,%r13,__LC_SYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
@@ -240,8 +279,6 @@ ENTRY(system_call)
 .Lsysc_return:
 	LOCKDEP_SYS_EXIT
 .Lsysc_tif:
-	tm	__PT_PSW+1(%r11),0x01		# returning to user ?
-	jno	.Lsysc_restore
 	tm	__PT_FLAGS+7(%r11),_PIF_WORK
 	jnz	.Lsysc_work
 	tm	__TI_flags+7(%r12),_TIF_WORK
@@ -276,6 +313,8 @@ ENTRY(system_call)
 	jo	.Lsysc_sigpending
 	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
 	jo	.Lsysc_notify_resume
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	jo	.Lsysc_vxrs
 	tm	__LC_CPU_FLAGS+7,_CIF_ASCE
 	jo	.Lsysc_uaccess
 	j	.Lsysc_return		# beware of critical section cleanup
@@ -303,6 +342,13 @@ ENTRY(system_call)
 	j	.Lsysc_return
 
 #
+# CIF_FPU is set, restore floating-point controls and floating-point registers.
+#
+.Lsysc_vxrs:
+	larl	%r14,.Lsysc_return
+	jg	load_fpu_regs
+
+#
 # _TIF_SIGPENDING is set, call do_signal
 #
 .Lsysc_sigpending:
@@ -401,27 +447,35 @@ ENTRY(pgm_check_handler)
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_THREAD_INFO
-	larl	%r13,system_call
+	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_PGM_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,1
 	tmhh	%r8,0x0001		# test problem state bit
-	jnz	1f			# -> fault in user space
-	tmhh	%r8,0x4000		# PER bit set in old PSW ?
-	jnz	0f			# -> enabled, can't be a double fault
+	jnz	2f			# -> fault in user space
+#if IS_ENABLED(CONFIG_KVM)
+	# cleanup critical section for sie64a
+	lgr	%r14,%r9
+	slg	%r14,BASED(.Lsie_critical_start)
+	clg	%r14,BASED(.Lsie_critical_length)
+	jhe	0f
+	brasl	%r14,.Lcleanup_sie
+#endif
+0:	tmhh	%r8,0x4000		# PER bit set in old PSW ?
+	jnz	1f			# -> enabled, can't be a double fault
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
 	jnz	.Lpgm_svcper		# -> single stepped svc
-0:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+1:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	j	2f
-1:	UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER
-	LAST_BREAK %r14
+	j	3f
+2:	LAST_BREAK %r14
+	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
 	lg	%r15,__LC_KERNEL_STACK
 	lg	%r14,__TI_task(%r12)
+	aghi	%r14,__TASK_thread	# pointer to thread_struct
 	lghi	%r13,__LC_PGM_TDB
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
-	jz	2f
+	jz	3f
 	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
-2:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
@@ -430,24 +484,28 @@ ENTRY(pgm_check_handler)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	stg	%r10,__PT_ARGS(%r11)
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
-	jz	0f
+	jz	4f
 	tmhh	%r8,0x0001		# kernel per event ?
 	jz	.Lpgm_kprobe
 	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
 	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
 	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
-0:	REENABLE_IRQS
+4:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
 	nill	%r10,0x007f
 	sll	%r10,2
-	je	.Lsysc_return
+	je	.Lpgm_return
 	lgf	%r1,0(%r10,%r1)		# load address of handler routine
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	basr	%r14,%r1		# branch to interrupt-handler
-	j	.Lsysc_return
+.Lpgm_return:
+	LOCKDEP_SYS_EXIT
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jno	.Lsysc_restore
+	j	.Lsysc_tif
 
 #
 # PER event in supervisor state, must be kprobes
@@ -457,7 +515,7 @@ ENTRY(pgm_check_handler)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,do_per_trap
-	j	.Lsysc_return
+	j	.Lpgm_return
 
 #
 # single stepped system call
@@ -478,15 +536,9 @@ ENTRY(io_int_handler)
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
 	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_THREAD_INFO
-	larl	%r13,system_call
+	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_IO_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,2
-	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
-	tmhh	%r8,0x0001		# interrupting from user?
-	jz	.Lio_skip
-	UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER
-	LAST_BREAK %r14
-.Lio_skip:
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
@@ -582,6 +634,8 @@ ENTRY(io_int_handler)
 	jo	.Lio_sigpending
 	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
 	jo	.Lio_notify_resume
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	jo	.Lio_vxrs
 	tm	__LC_CPU_FLAGS+7,_CIF_ASCE
 	jo	.Lio_uaccess
 	j	.Lio_return		# beware of critical section cleanup
@@ -604,6 +658,13 @@ ENTRY(io_int_handler)
 	j	.Lio_return
 
 #
+# CIF_FPU is set, restore floating-point controls and floating-point registers.
+#
+.Lio_vxrs:
+	larl	%r14,.Lio_return
+	jg	load_fpu_regs
+
+#
 # _TIF_NEED_RESCHED is set, call schedule
 #
 .Lio_reschedule:
@@ -647,15 +708,9 @@ ENTRY(ext_int_handler)
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
 	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_THREAD_INFO
-	larl	%r13,system_call
+	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_EXT_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,3
-	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
-	tmhh	%r8,0x0001		# interrupting from user ?
-	jz	.Lext_skip
-	UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER
-	LAST_BREAK %r14
-.Lext_skip:
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
@@ -685,6 +740,122 @@ ENTRY(psw_idle)
 	br	%r14
 .Lpsw_idle_end:
 
+/* Store floating-point controls and floating-point or vector extension
+ * registers instead.  A critical section cleanup assures that the registers
+ * are stored even if interrupted for some other work.	The register %r2
+ * designates a struct fpu to store register contents.	If the specified
+ * structure does not contain a register save area, the register store is
+ * omitted (see also comments in arch_dup_task_struct()).
+ *
+ * The CIF_FPU flag is set in any case.  The CIF_FPU triggers a lazy restore
+ * of the register contents at system call or io return.
+ */
+ENTRY(save_fpu_regs)
+	lg	%r2,__LC_CURRENT
+	aghi	%r2,__TASK_thread
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	bor	%r14
+	stfpc	__THREAD_FPU_fpc(%r2)
+.Lsave_fpu_regs_fpc_end:
+	lg	%r3,__THREAD_FPU_regs(%r2)
+	ltgr	%r3,%r3
+	jz	.Lsave_fpu_regs_done	  # no save area -> set CIF_FPU
+	tm	__THREAD_FPU_flags+3(%r2),FPU_USE_VX
+	jz	.Lsave_fpu_regs_fp	  # no -> store FP regs
+.Lsave_fpu_regs_vx_low:
+	VSTM	%v0,%v15,0,%r3		  # vstm 0,15,0(3)
+.Lsave_fpu_regs_vx_high:
+	VSTM	%v16,%v31,256,%r3	  # vstm 16,31,256(3)
+	j	.Lsave_fpu_regs_done	  # -> set CIF_FPU flag
+.Lsave_fpu_regs_fp:
+	std	0,0(%r3)
+	std	1,8(%r3)
+	std	2,16(%r3)
+	std	3,24(%r3)
+	std	4,32(%r3)
+	std	5,40(%r3)
+	std	6,48(%r3)
+	std	7,56(%r3)
+	std	8,64(%r3)
+	std	9,72(%r3)
+	std	10,80(%r3)
+	std	11,88(%r3)
+	std	12,96(%r3)
+	std	13,104(%r3)
+	std	14,112(%r3)
+	std	15,120(%r3)
+.Lsave_fpu_regs_done:
+	oi	__LC_CPU_FLAGS+7,_CIF_FPU
+	br	%r14
+.Lsave_fpu_regs_end:
+
+/* Load floating-point controls and floating-point or vector extension
+ * registers.  A critical section cleanup assures that the register contents
+ * are loaded even if interrupted for some other work.	Depending on the saved
+ * FP/VX state, the vector-enablement control, CR0.46, is either set or cleared.
+ *
+ * There are special calling conventions to fit into sysc and io return work:
+ *	%r15:	<kernel stack>
+ * The function requires:
+ *	%r4 and __SF_EMPTY+32(%r15)
+ */
+load_fpu_regs:
+	lg	%r4,__LC_CURRENT
+	aghi	%r4,__TASK_thread
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	bnor	%r14
+	lfpc	__THREAD_FPU_fpc(%r4)
+	stctg	%c0,%c0,__SF_EMPTY+32(%r15)	# store CR0
+	tm	__THREAD_FPU_flags+3(%r4),FPU_USE_VX	# VX-enabled task ?
+	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
+	jz	.Lload_fpu_regs_fp_ctl		# -> no VX, load FP regs
+.Lload_fpu_regs_vx_ctl:
+	tm	__SF_EMPTY+32+5(%r15),2		# test VX control
+	jo	.Lload_fpu_regs_vx
+	oi	__SF_EMPTY+32+5(%r15),2		# set VX control
+	lctlg	%c0,%c0,__SF_EMPTY+32(%r15)
+.Lload_fpu_regs_vx:
+	VLM	%v0,%v15,0,%r4
+.Lload_fpu_regs_vx_high:
+	VLM	%v16,%v31,256,%r4
+	j	.Lload_fpu_regs_done
+.Lload_fpu_regs_fp_ctl:
+	tm	__SF_EMPTY+32+5(%r15),2		# test VX control
+	jz	.Lload_fpu_regs_fp
+	ni	__SF_EMPTY+32+5(%r15),253	# clear VX control
+	lctlg	%c0,%c0,__SF_EMPTY+32(%r15)
+.Lload_fpu_regs_fp:
+	ld	0,0(%r4)
+	ld	1,8(%r4)
+	ld	2,16(%r4)
+	ld	3,24(%r4)
+	ld	4,32(%r4)
+	ld	5,40(%r4)
+	ld	6,48(%r4)
+	ld	7,56(%r4)
+	ld	8,64(%r4)
+	ld	9,72(%r4)
+	ld	10,80(%r4)
+	ld	11,88(%r4)
+	ld	12,96(%r4)
+	ld	13,104(%r4)
+	ld	14,112(%r4)
+	ld	15,120(%r4)
+.Lload_fpu_regs_done:
+	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
+	br	%r14
+.Lload_fpu_regs_end:
+
+/* Test and set the vector enablement control in CR0.46 */
+ENTRY(__ctl_set_vx)
+	stctg	%c0,%c0,__SF_EMPTY(%r15)
+	tm	__SF_EMPTY+5(%r15),2
+	bor	%r14
+	oi	__SF_EMPTY+5(%r15),2
+	lctlg	%c0,%c0,__SF_EMPTY(%r15)
+	br	%r14
+.L__ctl_set_vx_end:
+
 .L__critical_end:
 
 /*
@@ -697,9 +868,8 @@ ENTRY(mcck_int_handler)
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs
 	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_THREAD_INFO
-	larl	%r13,system_call
+	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,4
 	tm	__LC_MCCK_CODE,0x80	# system damage?
 	jo	.Lmcck_panic		# yes -> rest of mcck code invalid
 	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
@@ -720,11 +890,7 @@ ENTRY(mcck_int_handler)
 	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
 3:	tm	__LC_MCCK_CODE+2,0x09	# mwp + ia of old psw valid?
 	jno	.Lmcck_panic		# no -> skip cleanup critical
-	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_PANIC_STACK,PAGE_SHIFT
-	tm	%r8,0x0001		# interrupting from user ?
-	jz	.Lmcck_skip
-	UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER
-	LAST_BREAK %r14
+	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
 .Lmcck_skip:
 	lghi	%r14,__LC_GPREGS_SAVE_AREA+64
 	stmg	%r0,%r7,__PT_R0(%r11)
@@ -759,12 +925,8 @@ ENTRY(mcck_int_handler)
 	lpswe	__LC_RETURN_MCCK_PSW
 
 .Lmcck_panic:
-	lg	%r14,__LC_PANIC_STACK
-	slgr	%r14,%r15
-	srag	%r14,%r14,PAGE_SHIFT
-	jz	0f
 	lg	%r15,__LC_PANIC_STACK
-0:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	.Lmcck_skip
 
 #
@@ -814,20 +976,13 @@ stack_overflow:
 	jg	kernel_stack_overflow
 #endif
 
-	.align	8
-.Lcleanup_table:
-	.quad	system_call
-	.quad	.Lsysc_do_svc
-	.quad	.Lsysc_tif
-	.quad	.Lsysc_restore
-	.quad	.Lsysc_done
-	.quad	.Lio_tif
-	.quad	.Lio_restore
-	.quad	.Lio_done
-	.quad	psw_idle
-	.quad	.Lpsw_idle_end
-
 cleanup_critical:
+#if IS_ENABLED(CONFIG_KVM)
+	clg	%r9,BASED(.Lcleanup_table_sie)	# .Lsie_gmap
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table_sie+8)# .Lsie_done
+	jl	.Lcleanup_sie
+#endif
 	clg	%r9,BASED(.Lcleanup_table)	# system_call
 	jl	0f
 	clg	%r9,BASED(.Lcleanup_table+8)	# .Lsysc_do_svc
@@ -848,8 +1003,54 @@ cleanup_critical:
 	jl	0f
 	clg	%r9,BASED(.Lcleanup_table+72)	# .Lpsw_idle_end
 	jl	.Lcleanup_idle
+	clg	%r9,BASED(.Lcleanup_table+80)	# save_fpu_regs
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+88)	# .Lsave_fpu_regs_end
+	jl	.Lcleanup_save_fpu_regs
+	clg	%r9,BASED(.Lcleanup_table+96)	# load_fpu_regs
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
+	jl	.Lcleanup_load_fpu_regs
+	clg	%r9,BASED(.Lcleanup_table+112)	# __ctl_set_vx
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+120)	# .L__ctl_set_vx_end
+	jl	.Lcleanup___ctl_set_vx
 0:	br	%r14
 
+	.align	8
+.Lcleanup_table:
+	.quad	system_call
+	.quad	.Lsysc_do_svc
+	.quad	.Lsysc_tif
+	.quad	.Lsysc_restore
+	.quad	.Lsysc_done
+	.quad	.Lio_tif
+	.quad	.Lio_restore
+	.quad	.Lio_done
+	.quad	psw_idle
+	.quad	.Lpsw_idle_end
+	.quad	save_fpu_regs
+	.quad	.Lsave_fpu_regs_end
+	.quad	load_fpu_regs
+	.quad	.Lload_fpu_regs_end
+	.quad	__ctl_set_vx
+	.quad	.L__ctl_set_vx_end
+
+#if IS_ENABLED(CONFIG_KVM)
+.Lcleanup_table_sie:
+	.quad	.Lsie_gmap
+	.quad	.Lsie_done
+
+.Lcleanup_sie:
+	lg	%r9,__SF_EMPTY(%r15)		# get control block pointer
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_LPP
+	jz	0f
+	.insn	s,0xb2800000,__SF_EMPTY+16(%r15)# set host id
+0:	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	larl	%r9,sie_exit			# skip forward to sie_exit
+	br	%r14
+#endif
 
 .Lcleanup_system_call:
 	# check if stpt has been executed
@@ -910,7 +1111,7 @@ cleanup_critical:
 	.quad	system_call
 	.quad	.Lsysc_stmg
 	.quad	.Lsysc_per
-	.quad	.Lsysc_vtime+18
+	.quad	.Lsysc_vtime+36
 	.quad	.Lsysc_vtime+42
 
 .Lcleanup_sysc_tif:
@@ -976,6 +1177,145 @@ cleanup_critical:
 .Lcleanup_idle_insn:
 	.quad	.Lpsw_idle_lpsw
 
+.Lcleanup_save_fpu_regs:
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	bor	%r14
+	clg	%r9,BASED(.Lcleanup_save_fpu_regs_done)
+	jhe	5f
+	clg	%r9,BASED(.Lcleanup_save_fpu_regs_fp)
+	jhe	4f
+	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_high)
+	jhe	3f
+	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_low)
+	jhe	2f
+	clg	%r9,BASED(.Lcleanup_save_fpu_fpc_end)
+	jhe	1f
+	lg	%r2,__LC_CURRENT
+0:	# Store floating-point controls
+	stfpc	__THREAD_FPU_fpc(%r2)
+1:	# Load register save area and check if VX is active
+	lg	%r3,__THREAD_FPU_regs(%r2)
+	ltgr	%r3,%r3
+	jz	5f			  # no save area -> set CIF_FPU
+	tm	__THREAD_FPU_flags+3(%r2),FPU_USE_VX
+	jz	4f			  # no VX -> store FP regs
+2:	# Store vector registers (V0-V15)
+	VSTM	%v0,%v15,0,%r3		  # vstm 0,15,0(3)
+3:	# Store vector registers (V16-V31)
+	VSTM	%v16,%v31,256,%r3	  # vstm 16,31,256(3)
+	j	5f			  # -> done, set CIF_FPU flag
+4:	# Store floating-point registers
+	std	0,0(%r3)
+	std	1,8(%r3)
+	std	2,16(%r3)
+	std	3,24(%r3)
+	std	4,32(%r3)
+	std	5,40(%r3)
+	std	6,48(%r3)
+	std	7,56(%r3)
+	std	8,64(%r3)
+	std	9,72(%r3)
+	std	10,80(%r3)
+	std	11,88(%r3)
+	std	12,96(%r3)
+	std	13,104(%r3)
+	std	14,112(%r3)
+	std	15,120(%r3)
+5:	# Set CIF_FPU flag
+	oi	__LC_CPU_FLAGS+7,_CIF_FPU
+	lg	%r9,48(%r11)		# return from save_fpu_regs
+	br	%r14
+.Lcleanup_save_fpu_fpc_end:
+	.quad	.Lsave_fpu_regs_fpc_end
+.Lcleanup_save_fpu_regs_vx_low:
+	.quad	.Lsave_fpu_regs_vx_low
+.Lcleanup_save_fpu_regs_vx_high:
+	.quad	.Lsave_fpu_regs_vx_high
+.Lcleanup_save_fpu_regs_fp:
+	.quad	.Lsave_fpu_regs_fp
+.Lcleanup_save_fpu_regs_done:
+	.quad	.Lsave_fpu_regs_done
+
+.Lcleanup_load_fpu_regs:
+	tm	__LC_CPU_FLAGS+7,_CIF_FPU
+	bnor	%r14
+	clg	%r9,BASED(.Lcleanup_load_fpu_regs_done)
+	jhe	1f
+	clg	%r9,BASED(.Lcleanup_load_fpu_regs_fp)
+	jhe	2f
+	clg	%r9,BASED(.Lcleanup_load_fpu_regs_fp_ctl)
+	jhe	3f
+	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx_high)
+	jhe	4f
+	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx)
+	jhe	5f
+	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx_ctl)
+	jhe	6f
+	lg	%r4,__LC_CURRENT
+	lfpc	__THREAD_FPU_fpc(%r4)
+	tm	__THREAD_FPU_flags+3(%r4),FPU_USE_VX	# VX-enabled task ?
+	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
+	jz	3f				# -> no VX, load FP regs
+6:	# Set VX-enablement control
+	stctg	%c0,%c0,__SF_EMPTY+32(%r15)	# store CR0
+	tm	__SF_EMPTY+32+5(%r15),2		# test VX control
+	jo	5f
+	oi	__SF_EMPTY+32+5(%r15),2		# set VX control
+	lctlg	%c0,%c0,__SF_EMPTY+32(%r15)
+5:	# Load V0 ..V15 registers
+	VLM	%v0,%v15,0,%r4
+4:	# Load V16..V31 registers
+	VLM	%v16,%v31,256,%r4
+	j	1f
+3:	# Clear VX-enablement control for FP
+	stctg	%c0,%c0,__SF_EMPTY+32(%r15)	# store CR0
+	tm	__SF_EMPTY+32+5(%r15),2		# test VX control
+	jz	2f
+	ni	__SF_EMPTY+32+5(%r15),253	# clear VX control
+	lctlg	%c0,%c0,__SF_EMPTY+32(%r15)
+2:	# Load floating-point registers
+	ld	0,0(%r4)
+	ld	1,8(%r4)
+	ld	2,16(%r4)
+	ld	3,24(%r4)
+	ld	4,32(%r4)
+	ld	5,40(%r4)
+	ld	6,48(%r4)
+	ld	7,56(%r4)
+	ld	8,64(%r4)
+	ld	9,72(%r4)
+	ld	10,80(%r4)
+	ld	11,88(%r4)
+	ld	12,96(%r4)
+	ld	13,104(%r4)
+	ld	14,112(%r4)
+	ld	15,120(%r4)
+1:	# Clear CIF_FPU bit
+	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
+	lg	%r9,48(%r11)		# return from load_fpu_regs
+	br	%r14
+.Lcleanup_load_fpu_regs_vx_ctl:
+	.quad	.Lload_fpu_regs_vx_ctl
+.Lcleanup_load_fpu_regs_vx:
+	.quad	.Lload_fpu_regs_vx
+.Lcleanup_load_fpu_regs_vx_high:
+	.quad	.Lload_fpu_regs_vx_high
+.Lcleanup_load_fpu_regs_fp_ctl:
+	.quad	.Lload_fpu_regs_fp_ctl
+.Lcleanup_load_fpu_regs_fp:
+	.quad	.Lload_fpu_regs_fp
+.Lcleanup_load_fpu_regs_done:
+	.quad	.Lload_fpu_regs_done
+
+.Lcleanup___ctl_set_vx:
+	stctg	%c0,%c0,__SF_EMPTY(%r15)
+	tm	__SF_EMPTY+5(%r15),2
+	bor	%r14
+	oi	__SF_EMPTY+5(%r15),2
+	lctlg	%c0,%c0,__SF_EMPTY(%r15)
+	lg	%r9,48(%r11)		# return from __ctl_set_vx
+	br	%r14
+
 /*
  * Integer constants
  */
@@ -984,62 +1324,11 @@ cleanup_critical:
 	.quad	.L__critical_start
 .Lcritical_length:
 	.quad	.L__critical_end - .L__critical_start
-
-
 #if IS_ENABLED(CONFIG_KVM)
-/*
- * sie64a calling convention:
- * %r2 pointer to sie control block
- * %r3 guest register save area
- */
-ENTRY(sie64a)
-	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
-	stg	%r2,__SF_EMPTY(%r15)		# save control block pointer
-	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
-	xc	__SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason
-	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
-	lg	%r14,__LC_GMAP			# get gmap pointer
-	ltgr	%r14,%r14
-	jz	.Lsie_gmap
-	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
-.Lsie_gmap:
-	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
-	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
-	tm	__SIE_PROG20+3(%r14),3		# last exit...
-	jnz	.Lsie_done
-	LPP	__SF_EMPTY(%r15)		# set guest id
-	sie	0(%r14)
-.Lsie_done:
-	LPP	__SF_EMPTY+16(%r15)		# set host id
-	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
-	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-# some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions between sie64a and .Lsie_done should not cause program
-# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
-# See also HANDLE_SIE_INTERCEPT
-.Lrewind_pad:
-	nop	0
-	.globl sie_exit
-sie_exit:
-	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
-	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
-	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
-	lg	%r2,__SF_EMPTY+24(%r15)		# return exit reason code
-	br	%r14
-.Lsie_fault:
-	lghi	%r14,-EFAULT
-	stg	%r14,__SF_EMPTY+24(%r15)	# set exit reason code
-	j	sie_exit
-
-	.align	8
-.Lsie_critical:
+.Lsie_critical_start:
 	.quad	.Lsie_gmap
 .Lsie_critical_length:
 	.quad	.Lsie_done - .Lsie_gmap
-
-	EX_TABLE(.Lrewind_pad,.Lsie_fault)
-	EX_TABLE(sie_exit,.Lsie_fault)
 #endif
 
 	.section .rodata, "a"
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 59b7c6470567..1255c6c5353e 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -370,6 +370,7 @@ ENTRY(startup_kdump)
 	xc	0x200(256),0x200	# partially clear lowcore
 	xc	0x300(256),0x300
 	xc	0xe00(256),0xe00
+	lctlg	%c0,%c15,0x200(%r0)	# initialize control registers
 	stck	__LC_LAST_UPDATE_CLOCK
 	spt	6f-.LPG0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
@@ -413,9 +414,9 @@ ENTRY(startup_kdump)
 # followed by the facility words.
 
 #if defined(CONFIG_MARCH_Z13)
-	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
+	.long 2, 0xc100eff2, 0xf46cc800
 #elif defined(CONFIG_MARCH_ZEC12)
-	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
+	.long 2, 0xc100eff2, 0xf46cc800
 #elif defined(CONFIG_MARCH_Z196)
 	.long 2, 0xc100eff2, 0xf46c0000
 #elif defined(CONFIG_MARCH_Z10)
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index a90299600483..083b05f5f5ab 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -44,12 +44,9 @@ static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
 	unsigned char *ipn = (unsigned char *)new;
 
 	pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc);
-	pr_emerg("Found:    %02x %02x %02x %02x %02x %02x\n",
-		 ipc[0], ipc[1], ipc[2], ipc[3], ipc[4], ipc[5]);
-	pr_emerg("Expected: %02x %02x %02x %02x %02x %02x\n",
-		 ipe[0], ipe[1], ipe[2], ipe[3], ipe[4], ipe[5]);
-	pr_emerg("New:      %02x %02x %02x %02x %02x %02x\n",
-		 ipn[0], ipn[1], ipn[2], ipn[3], ipn[4], ipn[5]);
+	pr_emerg("Found:    %6ph\n", ipc);
+	pr_emerg("Expected: %6ph\n", ipe);
+	pr_emerg("New:      %6ph\n", ipn);
 	panic("Corrupted kernel text");
 }
 
@@ -64,7 +61,7 @@ static void __jump_label_transform(struct jump_entry *entry,
 {
 	struct insn old, new;
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		jump_label_make_nop(entry, &old);
 		jump_label_make_branch(entry, &new);
 	} else {
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 505c17c0ae1a..0ae6f8e74840 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -21,6 +21,8 @@
 #include <asm/nmi.h>
 #include <asm/crw.h>
 #include <asm/switch_to.h>
+#include <asm/fpu-internal.h>
+#include <asm/ctl_reg.h>
 
 struct mcck_struct {
 	int kill_task;
@@ -129,26 +131,30 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 	} else
 		asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area));
 
-	asm volatile(
-		"	ld	0,0(%0)\n"
-		"	ld	1,8(%0)\n"
-		"	ld	2,16(%0)\n"
-		"	ld	3,24(%0)\n"
-		"	ld	4,32(%0)\n"
-		"	ld	5,40(%0)\n"
-		"	ld	6,48(%0)\n"
-		"	ld	7,56(%0)\n"
-		"	ld	8,64(%0)\n"
-		"	ld	9,72(%0)\n"
-		"	ld	10,80(%0)\n"
-		"	ld	11,88(%0)\n"
-		"	ld	12,96(%0)\n"
-		"	ld	13,104(%0)\n"
-		"	ld	14,112(%0)\n"
-		"	ld	15,120(%0)\n"
-		: : "a" (fpt_save_area));
-	/* Revalidate vector registers */
-	if (MACHINE_HAS_VX && current->thread.vxrs) {
+	if (!MACHINE_HAS_VX) {
+		/* Revalidate floating point registers */
+		asm volatile(
+			"	ld	0,0(%0)\n"
+			"	ld	1,8(%0)\n"
+			"	ld	2,16(%0)\n"
+			"	ld	3,24(%0)\n"
+			"	ld	4,32(%0)\n"
+			"	ld	5,40(%0)\n"
+			"	ld	6,48(%0)\n"
+			"	ld	7,56(%0)\n"
+			"	ld	8,64(%0)\n"
+			"	ld	9,72(%0)\n"
+			"	ld	10,80(%0)\n"
+			"	ld	11,88(%0)\n"
+			"	ld	12,96(%0)\n"
+			"	ld	13,104(%0)\n"
+			"	ld	14,112(%0)\n"
+			"	ld	15,120(%0)\n"
+			: : "a" (fpt_save_area));
+	} else {
+		/* Revalidate vector registers */
+		union ctlreg0 cr0;
+
 		if (!mci->vr) {
 			/*
 			 * Vector registers can't be restored and therefore
@@ -156,8 +162,16 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			 */
 			kill_task = 1;
 		}
-		restore_vx_regs((__vector128 *)
-				S390_lowcore.vector_save_area_addr);
+		cr0.val = S390_lowcore.cregs_save_area[0];
+		cr0.afp = cr0.vx = 1;
+		__ctl_load(cr0.val, 0, 0);
+		asm volatile(
+			"	la	1,%0\n"
+			"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
+			"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
+			: : "Q" (*(struct vx_array *)
+				 &S390_lowcore.vector_save_area) : "1");
+		__ctl_load(S390_lowcore.cregs_save_area[0], 0, 0);
 	}
 	/* Revalidate access registers */
 	asm volatile(
@@ -349,4 +363,4 @@ static int __init machine_check_init(void)
 	ctl_set_bit(14, 24);	/* enable warning MCH */
 	return 0;
 }
-arch_initcall(machine_check_init);
+early_initcall(machine_check_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index afe05bfb7e00..b973972f6ba5 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1019,12 +1019,9 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 		break;
 	}
 
-	/* The host-program-parameter (hpp) contains the sie control
-	 * block that is set by sie64a() in entry64.S.	Check if hpp
-	 * refers to a valid control block and set sde_regs flags
-	 * accordingly.  This would allow to use hpp values for other
-	 * purposes too.
-	 * For now, simply use a non-zero value as guest indicator.
+	/* The host-program-parameter (hpp) contains the pid of
+	 * the CPU thread as set by sie64a() in entry.S.
+	 * If non-zero assume a guest sample.
 	 */
 	if (sfr->basic.hpp)
 		sde_regs->in_guest = 1;
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index dc5edc29b73a..f2dac9f0799d 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -81,8 +81,38 @@ void release_thread(struct task_struct *dead_task)
 
 void arch_release_task_struct(struct task_struct *tsk)
 {
-	if (tsk->thread.vxrs)
-		kfree(tsk->thread.vxrs);
+	/* Free either the floating-point or the vector register save area */
+	kfree(tsk->thread.fpu.regs);
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	*dst = *src;
+
+	/* Set up a new floating-point register save area */
+	dst->thread.fpu.fpc = 0;
+	dst->thread.fpu.flags = 0;	/* Always start with VX disabled */
+	dst->thread.fpu.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
+				       GFP_KERNEL|__GFP_REPEAT);
+	if (!dst->thread.fpu.fprs)
+		return -ENOMEM;
+
+	/*
+	 * Save the floating-point or vector register state of the current
+	 * task.  The state is not saved for early kernel threads, for example,
+	 * the init_task, which do not have an allocated save area.
+	 * The CIF_FPU flag is set in any case to lazy clear or restore a saved
+	 * state when switching to a different task or returning to user space.
+	 */
+	save_fpu_regs();
+	dst->thread.fpu.fpc = current->thread.fpu.fpc;
+	if (is_vx_task(current))
+		convert_vx_to_fp(dst->thread.fpu.fprs,
+				 current->thread.fpu.vxrs);
+	else
+		memcpy(dst->thread.fpu.fprs, current->thread.fpu.fprs,
+		       sizeof(freg_t) * __NUM_FPRS);
+	return 0;
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
@@ -142,11 +172,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	p->thread.ri_signum = 0;
 	frame->childregs.psw.mask &= ~PSW_MASK_RI;
 
-	/* Save the fpu registers to new thread structure. */
-	save_fp_ctl(&p->thread.fp_regs.fpc);
-	save_fp_regs(p->thread.fp_regs.fprs);
-	p->thread.fp_regs.pad = 0;
-	p->thread.vxrs = NULL;
 	/* Set a new TLS ?  */
 	if (clone_flags & CLONE_SETTLS) {
 		unsigned long tls = frame->childregs.gprs[6];
@@ -162,8 +187,8 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 
 asmlinkage void execve_tail(void)
 {
-	current->thread.fp_regs.fpc = 0;
-	asm volatile("sfpc %0,%0" : : "d" (0));
+	current->thread.fpu.fpc = 0;
+	asm volatile("sfpc %0" : : "d" (0));
 }
 
 /*
@@ -171,8 +196,15 @@ asmlinkage void execve_tail(void)
  */
 int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
 {
-	save_fp_ctl(&fpregs->fpc);
-	save_fp_regs(fpregs->fprs);
+	save_fpu_regs();
+	fpregs->fpc = current->thread.fpu.fpc;
+	fpregs->pad = 0;
+	if (is_vx_task(current))
+		convert_vx_to_fp((freg_t *)&fpregs->fprs,
+				 current->thread.fpu.vxrs);
+	else
+		memcpy(&fpregs->fprs, current->thread.fpu.fprs,
+		       sizeof(fpregs->fprs));
 	return 1;
 }
 EXPORT_SYMBOL(dump_fpu);
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index dc488e13b7e3..e6e077ae3990 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -41,6 +41,15 @@ void cpu_init(void)
 }
 
 /*
+ * cpu_have_feature - Test CPU features on module initialization
+ */
+int cpu_have_feature(unsigned int num)
+{
+	return elf_hwcap & (1UL << num);
+}
+EXPORT_SYMBOL(cpu_have_feature);
+
+/*
  * show_cpuinfo - Get information on one CPU for use by procfs.
  */
 static int show_cpuinfo(struct seq_file *m, void *v)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index d363c9c322a1..8b1c8e33f184 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -45,39 +45,27 @@ void update_cr_regs(struct task_struct *task)
 	struct per_regs old, new;
 
 	/* Take care of the enable/disable of transactional execution. */
-	if (MACHINE_HAS_TE || MACHINE_HAS_VX) {
+	if (MACHINE_HAS_TE) {
 		unsigned long cr, cr_new;
 
 		__ctl_store(cr, 0, 0);
-		cr_new = cr;
-		if (MACHINE_HAS_TE) {
-			/* Set or clear transaction execution TXC bit 8. */
-			cr_new |= (1UL << 55);
-			if (task->thread.per_flags & PER_FLAG_NO_TE)
-				cr_new &= ~(1UL << 55);
-		}
-		if (MACHINE_HAS_VX) {
-			/* Enable/disable of vector extension */
-			cr_new &= ~(1UL << 17);
-			if (task->thread.vxrs)
-				cr_new |= (1UL << 17);
-		}
+		/* Set or clear transaction execution TXC bit 8. */
+		cr_new = cr | (1UL << 55);
+		if (task->thread.per_flags & PER_FLAG_NO_TE)
+			cr_new &= ~(1UL << 55);
 		if (cr_new != cr)
 			__ctl_load(cr_new, 0, 0);
-		if (MACHINE_HAS_TE) {
-			/* Set/clear transaction execution TDC bits 62/63. */
-			__ctl_store(cr, 2, 2);
-			cr_new = cr & ~3UL;
-			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
-				if (task->thread.per_flags &
-				    PER_FLAG_TE_ABORT_RAND_TEND)
-					cr_new |= 1UL;
-				else
-					cr_new |= 2UL;
-			}
-			if (cr_new != cr)
-				__ctl_load(cr_new, 2, 2);
+		/* Set or clear transaction execution TDC bits 62 and 63. */
+		__ctl_store(cr, 2, 2);
+		cr_new = cr & ~3UL;
+		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
+			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
+				cr_new |= 1UL;
+			else
+				cr_new |= 2UL;
 		}
+		if (cr_new != cr)
+			__ctl_load(cr_new, 2, 2);
 	}
 	/* Copy user specified PER registers */
 	new.control = thread->per_user.control;
@@ -242,21 +230,21 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr)
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		tmp = child->thread.fp_regs.fpc;
+		tmp = child->thread.fpu.fpc;
 		tmp <<= BITS_PER_LONG - 32;
 
 	} else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) {
 		/*
-		 * floating point regs. are either in child->thread.fp_regs
-		 * or the child->thread.vxrs array
+		 * floating point regs. are either in child->thread.fpu
+		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - (addr_t) &dummy->regs.fp_regs.fprs;
-		if (child->thread.vxrs)
+		if (is_vx_task(child))
 			tmp = *(addr_t *)
-			       ((addr_t) child->thread.vxrs + 2*offset);
+			       ((addr_t) child->thread.fpu.vxrs + 2*offset);
 		else
 			tmp = *(addr_t *)
-			       ((addr_t) &child->thread.fp_regs.fprs + offset);
+			       ((addr_t) &child->thread.fpu.fprs + offset);
 
 	} else if (addr < (addr_t) (&dummy->regs.per_info + 1)) {
 		/*
@@ -387,20 +375,20 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		if ((unsigned int) data != 0 ||
 		    test_fp_ctl(data >> (BITS_PER_LONG - 32)))
 			return -EINVAL;
-		child->thread.fp_regs.fpc = data >> (BITS_PER_LONG - 32);
+		child->thread.fpu.fpc = data >> (BITS_PER_LONG - 32);
 
 	} else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) {
 		/*
-		 * floating point regs. are either in child->thread.fp_regs
-		 * or the child->thread.vxrs array
+		 * floating point regs. are either in child->thread.fpu
+		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - (addr_t) &dummy->regs.fp_regs.fprs;
-		if (child->thread.vxrs)
+		if (is_vx_task(child))
 			*(addr_t *)((addr_t)
-				child->thread.vxrs + 2*offset) = data;
+				child->thread.fpu.vxrs + 2*offset) = data;
 		else
 			*(addr_t *)((addr_t)
-				&child->thread.fp_regs.fprs + offset) = data;
+				&child->thread.fpu.fprs + offset) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.per_info + 1)) {
 		/*
@@ -621,20 +609,20 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr)
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		tmp = child->thread.fp_regs.fpc;
+		tmp = child->thread.fpu.fpc;
 
 	} else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) {
 		/*
-		 * floating point regs. are either in child->thread.fp_regs
-		 * or the child->thread.vxrs array
+		 * floating point regs. are either in child->thread.fpu
+		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - (addr_t) &dummy32->regs.fp_regs.fprs;
-		if (child->thread.vxrs)
+		if (is_vx_task(child))
 			tmp = *(__u32 *)
-			       ((addr_t) child->thread.vxrs + 2*offset);
+			       ((addr_t) child->thread.fpu.vxrs + 2*offset);
 		else
 			tmp = *(__u32 *)
-			       ((addr_t) &child->thread.fp_regs.fprs + offset);
+			       ((addr_t) &child->thread.fpu.fprs + offset);
 
 	} else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) {
 		/*
@@ -746,20 +734,20 @@ static int __poke_user_compat(struct task_struct *child,
 		 */
 		if (test_fp_ctl(tmp))
 			return -EINVAL;
-		child->thread.fp_regs.fpc = data;
+		child->thread.fpu.fpc = data;
 
 	} else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) {
 		/*
-		 * floating point regs. are either in child->thread.fp_regs
-		 * or the child->thread.vxrs array
+		 * floating point regs. are either in child->thread.fpu
+		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - (addr_t) &dummy32->regs.fp_regs.fprs;
-		if (child->thread.vxrs)
+		if (is_vx_task(child))
 			*(__u32 *)((addr_t)
-				child->thread.vxrs + 2*offset) = tmp;
+				child->thread.fpu.vxrs + 2*offset) = tmp;
 		else
 			*(__u32 *)((addr_t)
-				&child->thread.fp_regs.fprs + offset) = tmp;
+				&child->thread.fpu.fprs + offset) = tmp;
 
 	} else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) {
 		/*
@@ -952,18 +940,16 @@ static int s390_fpregs_get(struct task_struct *target,
 			   const struct user_regset *regset, unsigned int pos,
 			   unsigned int count, void *kbuf, void __user *ubuf)
 {
-	if (target == current) {
-		save_fp_ctl(&target->thread.fp_regs.fpc);
-		save_fp_regs(target->thread.fp_regs.fprs);
-	} else if (target->thread.vxrs) {
-		int i;
+	_s390_fp_regs fp_regs;
+
+	if (target == current)
+		save_fpu_regs();
+
+	fp_regs.fpc = target->thread.fpu.fpc;
+	fpregs_store(&fp_regs, &target->thread.fpu);
 
-		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			target->thread.fp_regs.fprs[i] =
-				*(freg_t *)(target->thread.vxrs + i);
-	}
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.fp_regs, 0, -1);
+				   &fp_regs, 0, -1);
 }
 
 static int s390_fpregs_set(struct task_struct *target,
@@ -972,41 +958,33 @@ static int s390_fpregs_set(struct task_struct *target,
 			   const void __user *ubuf)
 {
 	int rc = 0;
+	freg_t fprs[__NUM_FPRS];
 
-	if (target == current) {
-		save_fp_ctl(&target->thread.fp_regs.fpc);
-		save_fp_regs(target->thread.fp_regs.fprs);
-	}
+	if (target == current)
+		save_fpu_regs();
 
 	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
-		u32 ufpc[2] = { target->thread.fp_regs.fpc, 0 };
+		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
 		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc,
 					0, offsetof(s390_fp_regs, fprs));
 		if (rc)
 			return rc;
 		if (ufpc[1] != 0 || test_fp_ctl(ufpc[0]))
 			return -EINVAL;
-		target->thread.fp_regs.fpc = ufpc[0];
+		target->thread.fpu.fpc = ufpc[0];
 	}
 
 	if (rc == 0 && count > 0)
 		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					target->thread.fp_regs.fprs,
-					offsetof(s390_fp_regs, fprs), -1);
-
-	if (rc == 0) {
-		if (target == current) {
-			restore_fp_ctl(&target->thread.fp_regs.fpc);
-			restore_fp_regs(target->thread.fp_regs.fprs);
-		} else if (target->thread.vxrs) {
-			int i;
-
-			for (i = 0; i < __NUM_VXRS_LOW; i++)
-				*(freg_t *)(target->thread.vxrs + i) =
-					target->thread.fp_regs.fprs[i];
-		}
-	}
+					fprs, offsetof(s390_fp_regs, fprs), -1);
+	if (rc)
+		return rc;
+
+	if (is_vx_task(target))
+		convert_fp_to_vx(target->thread.fpu.vxrs, fprs);
+	else
+		memcpy(target->thread.fpu.fprs, &fprs, sizeof(fprs));
 
 	return rc;
 }
@@ -1069,11 +1047,11 @@ static int s390_vxrs_low_get(struct task_struct *target,
 
 	if (!MACHINE_HAS_VX)
 		return -ENODEV;
-	if (target->thread.vxrs) {
+	if (is_vx_task(target)) {
 		if (target == current)
-			save_vx_regs(target->thread.vxrs);
+			save_fpu_regs();
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			vxrs[i] = *((__u64 *)(target->thread.vxrs + i) + 1);
+			vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
 	} else
 		memset(vxrs, 0, sizeof(vxrs));
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
@@ -1089,20 +1067,17 @@ static int s390_vxrs_low_set(struct task_struct *target,
 
 	if (!MACHINE_HAS_VX)
 		return -ENODEV;
-	if (!target->thread.vxrs) {
+	if (!is_vx_task(target)) {
 		rc = alloc_vector_registers(target);
 		if (rc)
 			return rc;
 	} else if (target == current)
-		save_vx_regs(target->thread.vxrs);
+		save_fpu_regs();
 
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
-	if (rc == 0) {
+	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			*((__u64 *)(target->thread.vxrs + i) + 1) = vxrs[i];
-		if (target == current)
-			restore_vx_regs(target->thread.vxrs);
-	}
+			*((__u64 *)(target->thread.fpu.vxrs + i) + 1) = vxrs[i];
 
 	return rc;
 }
@@ -1116,10 +1091,10 @@ static int s390_vxrs_high_get(struct task_struct *target,
 
 	if (!MACHINE_HAS_VX)
 		return -ENODEV;
-	if (target->thread.vxrs) {
+	if (is_vx_task(target)) {
 		if (target == current)
-			save_vx_regs(target->thread.vxrs);
-		memcpy(vxrs, target->thread.vxrs + __NUM_VXRS_LOW,
+			save_fpu_regs();
+		memcpy(vxrs, target->thread.fpu.vxrs + __NUM_VXRS_LOW,
 		       sizeof(vxrs));
 	} else
 		memset(vxrs, 0, sizeof(vxrs));
@@ -1135,18 +1110,15 @@ static int s390_vxrs_high_set(struct task_struct *target,
 
 	if (!MACHINE_HAS_VX)
 		return -ENODEV;
-	if (!target->thread.vxrs) {
+	if (!is_vx_task(target)) {
 		rc = alloc_vector_registers(target);
 		if (rc)
 			return rc;
 	} else if (target == current)
-		save_vx_regs(target->thread.vxrs);
+		save_fpu_regs();
 
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				target->thread.vxrs + __NUM_VXRS_LOW, 0, -1);
-	if (rc == 0 && target == current)
-		restore_vx_regs(target->thread.vxrs);
-
+				target->thread.fpu.vxrs + __NUM_VXRS_LOW, 0, -1);
 	return rc;
 }
 
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 9f60467938d1..5090d3dad10b 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -1,5 +1,6 @@
 #include <linux/module.h>
 #include <linux/kvm_host.h>
+#include <asm/fpu-internal.h>
 #include <asm/ftrace.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
@@ -8,6 +9,8 @@ EXPORT_SYMBOL(_mcount);
 #if IS_ENABLED(CONFIG_KVM)
 EXPORT_SYMBOL(sie64a);
 EXPORT_SYMBOL(sie_exit);
+EXPORT_SYMBOL(save_fpu_regs);
+EXPORT_SYMBOL(__ctl_set_vx);
 #endif
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
deleted file mode 100644
index 43c3169ea49c..000000000000
--- a/arch/s390/kernel/sclp.S
+++ /dev/null
@@ -1,351 +0,0 @@
-/*
- * Mini SCLP driver.
- *
- * Copyright IBM Corp. 2004, 2009
- *
- *   Author(s):	Peter Oberparleiter <Peter.Oberparleiter@de.ibm.com>,
- *		Heiko Carstens <heiko.carstens@de.ibm.com>,
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/irq.h>
-
-LC_EXT_NEW_PSW		= 0x58			# addr of ext int handler
-LC_EXT_NEW_PSW_64	= 0x1b0			# addr of ext int handler 64 bit
-LC_EXT_INT_PARAM	= 0x80			# addr of ext int parameter
-LC_EXT_INT_CODE		= 0x86			# addr of ext int code
-LC_AR_MODE_ID		= 0xa3
-
-#
-# Subroutine which waits synchronously until either an external interruption
-# or a timeout occurs.
-#
-# Parameters:
-#   R2	= 0 for no timeout, non-zero for timeout in (approximated) seconds
-#
-# Returns:
-#   R2	= 0 on interrupt, 2 on timeout
-#   R3	= external interruption parameter if R2=0
-#
-
-_sclp_wait_int:
-	stm	%r6,%r15,24(%r15)		# save registers
-	basr	%r13,0				# get base register
-.LbaseS1:
-	ahi	%r15,-96			# create stack frame
-	la	%r8,LC_EXT_NEW_PSW		# register int handler
-	la	%r9,.LextpswS1-.LbaseS1(%r13)
-	tm	LC_AR_MODE_ID,1
-	jno	.Lesa1
-	la	%r8,LC_EXT_NEW_PSW_64		# register int handler 64 bit
-	la	%r9,.LextpswS1_64-.LbaseS1(%r13)
-.Lesa1:
-	mvc	.LoldpswS1-.LbaseS1(16,%r13),0(%r8)
-	mvc	0(16,%r8),0(%r9)
-	epsw	%r6,%r7				# set current addressing mode
-	nill	%r6,0x1				# in new psw (31 or 64 bit mode)
-	nilh	%r7,0x8000
-	stm	%r6,%r7,0(%r8)
-	lhi	%r6,0x0200			# cr mask for ext int (cr0.54)
-	ltr	%r2,%r2
-	jz	.LsetctS1
-	ahi	%r6,0x0800			# cr mask for clock int (cr0.52)
-	stck	.LtimeS1-.LbaseS1(%r13)		# initiate timeout
-	al	%r2,.LtimeS1-.LbaseS1(%r13)
-	st	%r2,.LtimeS1-.LbaseS1(%r13)
-	sckc	.LtimeS1-.LbaseS1(%r13)
-
-.LsetctS1:
-	stctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)	# enable required interrupts
-	l	%r0,.LctlS1-.LbaseS1(%r13)
-	lhi	%r1,~(0x200 | 0x800)		# clear old values
-	nr	%r1,%r0
-	or	%r1,%r6				# set new value
-	st	%r1,.LctlS1-.LbaseS1(%r13)
-	lctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)
-	st	%r0,.LctlS1-.LbaseS1(%r13)
-	lhi	%r2,2				# return code for timeout
-.LloopS1:
-	lpsw	.LwaitpswS1-.LbaseS1(%r13)	# wait until interrupt
-.LwaitS1:
-	lh	%r7,LC_EXT_INT_CODE
-	chi	%r7,EXT_IRQ_CLK_COMP		# timeout?
-	je	.LtimeoutS1
-	chi	%r7,EXT_IRQ_SERVICE_SIG		# service int?
-	jne	.LloopS1
-	sr	%r2,%r2
-	l	%r3,LC_EXT_INT_PARAM
-.LtimeoutS1:
-	lctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)	# restore interrupt setting
-	# restore old handler
-	mvc	0(16,%r8),.LoldpswS1-.LbaseS1(%r13)
-	lm	%r6,%r15,120(%r15)		# restore registers
-	br	%r14				# return to caller
-
-	.align	8
-.LoldpswS1:
-	.long	0, 0, 0, 0			# old ext int PSW
-.LextpswS1:
-	.long	0x00080000, 0x80000000+.LwaitS1	# PSW to handle ext int
-.LextpswS1_64:
-	.quad	0, .LwaitS1			# PSW to handle ext int, 64 bit
-.LwaitpswS1:
-	.long	0x010a0000, 0x00000000+.LloopS1	# PSW to wait for ext int
-.LtimeS1:
-	.quad	0				# current time
-.LctlS1:
-	.long	0				# CT0 contents
-
-#
-# Subroutine to synchronously issue a service call.
-#
-# Parameters:
-#   R2	= command word
-#   R3	= sccb address
-#
-# Returns:
-#   R2	= 0 on success, 1 on failure
-#   R3	= sccb response code if R2 = 0
-#
-
-_sclp_servc:
-	stm	%r6,%r15,24(%r15)		# save registers
-	ahi	%r15,-96			# create stack frame
-	lr	%r6,%r2				# save command word
-	lr	%r7,%r3				# save sccb address
-.LretryS2:
-	lhi	%r2,1				# error return code
-	.insn	rre,0xb2200000,%r6,%r7		# servc
-	brc	1,.LendS2			# exit if not operational
-	brc	8,.LnotbusyS2			# go on if not busy
-	sr	%r2,%r2				# wait until no longer busy
-	bras	%r14,_sclp_wait_int
-	j	.LretryS2			# retry
-.LnotbusyS2:
-	sr	%r2,%r2				# wait until result
-	bras	%r14,_sclp_wait_int
-	sr	%r2,%r2
-	lh	%r3,6(%r7)
-.LendS2:
-	lm	%r6,%r15,120(%r15)		# restore registers
-	br	%r14
-
-#
-# Subroutine to set up the SCLP interface.
-#
-# Parameters:
-#   R2	= 0 to activate, non-zero to deactivate
-#
-# Returns:
-#   R2	= 0 on success, non-zero on failure
-#
-
-_sclp_setup:
-	stm	%r6,%r15,24(%r15)		# save registers
-	ahi	%r15,-96			# create stack frame
-	basr	%r13,0				# get base register
-.LbaseS3:
-	l	%r6,.LsccbS0-.LbaseS3(%r13)	# prepare init mask sccb
-	mvc	0(.LinitendS3-.LinitsccbS3,%r6),.LinitsccbS3-.LbaseS3(%r13)
-	ltr	%r2,%r2				# initialization?
-	jz	.LdoinitS3			# go ahead
-	# clear masks
-	xc	.LinitmaskS3-.LinitsccbS3(8,%r6),.LinitmaskS3-.LinitsccbS3(%r6)
-.LdoinitS3:
-	l	%r2,.LwritemaskS3-.LbaseS3(%r13)# get command word
-	lr	%r3,%r6				# get sccb address
-	bras	%r14,_sclp_servc		# issue service call
-	ltr	%r2,%r2				# servc successful?
-	jnz	.LerrorS3
-	chi	%r3,0x20			# write mask successful?
-	jne	.LerrorS3
-	# check masks
-	la	%r2,.LinitmaskS3-.LinitsccbS3(%r6)
-	l	%r1,0(%r2)			# receive mask ok?
-	n	%r1,12(%r2)
-	cl	%r1,0(%r2)
-	jne	.LerrorS3
-	l	%r1,4(%r2)			# send mask ok?
-	n	%r1,8(%r2)
-	cl	%r1,4(%r2)
-	sr	%r2,%r2
-	je	.LendS3
-.LerrorS3:
-	lhi	%r2,1				# error return code
-.LendS3:
-	lm	%r6,%r15,120(%r15)		# restore registers
-	br	%r14
-.LwritemaskS3:
-	.long	0x00780005			# SCLP command for write mask
-.LinitsccbS3:
-	.word	.LinitendS3-.LinitsccbS3
-	.byte	0,0,0,0
-	.word	0
-	.word	0
-	.word	4
-.LinitmaskS3:
-	.long	0x80000000
-	.long	0x40000000
-	.long	0
-	.long	0
-.LinitendS3:
-
-#
-# Subroutine which prints a given text to the SCLP console.
-#
-# Parameters:
-#   R2	= address of nil-terminated ASCII text
-#
-# Returns:
-#   R2	= 0 on success, 1 on failure
-#
-
-_sclp_print:
-	stm	%r6,%r15,24(%r15)		# save registers
-	ahi	%r15,-96			# create stack frame
-	basr	%r13,0				# get base register
-.LbaseS4:
-	l	%r8,.LsccbS0-.LbaseS4(%r13)	# prepare write data sccb
-	mvc	0(.LmtoS4-.LwritesccbS4,%r8),.LwritesccbS4-.LbaseS4(%r13)
-	la	%r7,.LmtoS4-.LwritesccbS4(%r8)	# current mto addr
-	sr	%r0,%r0
-	l	%r10,.Lascebc-.LbaseS4(%r13)	# address of translation table
-.LinitmtoS4:
-	# initialize mto
-	mvc	0(.LmtoendS4-.LmtoS4,%r7),.LmtoS4-.LbaseS4(%r13)
-	lhi	%r6,.LmtoendS4-.LmtoS4		# current mto length
-.LloopS4:
-	ic	%r0,0(%r2)			# get character
-	ahi	%r2,1
-	ltr	%r0,%r0				# end of string?
-	jz	.LfinalizemtoS4
-	chi	%r0,0x0a			# end of line (NL)?
-	jz	.LfinalizemtoS4
-	stc	%r0,0(%r6,%r7)			# copy to mto
-	la	%r11,0(%r6,%r7)
-	tr	0(1,%r11),0(%r10)		# translate to EBCDIC
-	ahi	%r6,1
-	j	.LloopS4
-.LfinalizemtoS4:
-	sth	%r6,0(%r7)			# update mto length
-	lh	%r9,.LmdbS4-.LwritesccbS4(%r8)	# update mdb length
-	ar	%r9,%r6
-	sth	%r9,.LmdbS4-.LwritesccbS4(%r8)
-	lh	%r9,.LevbufS4-.LwritesccbS4(%r8)# update evbuf length
-	ar	%r9,%r6
-	sth	%r9,.LevbufS4-.LwritesccbS4(%r8)
-	lh	%r9,0(%r8)			# update sccb length
-	ar	%r9,%r6
-	sth	%r9,0(%r8)
-	ar	%r7,%r6				# update current mto address
-	ltr	%r0,%r0				# more characters?
-	jnz	.LinitmtoS4
-	l	%r2,.LwritedataS4-.LbaseS4(%r13)# write data
-	lr	%r3,%r8
-	bras	%r14,_sclp_servc
-	ltr	%r2,%r2				# servc successful?
-	jnz	.LendS4
-	chi	%r3,0x20			# write data successful?
-	je	.LendS4
-	lhi	%r2,1				# error return code
-.LendS4:
-	lm	%r6,%r15,120(%r15)		# restore registers
-	br	%r14
-
-#
-# Function which prints a given text to the SCLP console.
-#
-# Parameters:
-#   R2	= address of nil-terminated ASCII text
-#
-# Returns:
-#   R2	= 0 on success, 1 on failure
-#
-
-ENTRY(_sclp_print_early)
-	stm	%r6,%r15,24(%r15)		# save registers
-	ahi	%r15,-96			# create stack frame
-	tm	LC_AR_MODE_ID,1
-	jno	.Lesa2
-	ahi	%r15,-80
-	stmh	%r6,%r15,96(%r15)		# store upper register halves
-.Lesa2:
-	lr	%r10,%r2			# save string pointer
-	lhi	%r2,0
-	bras	%r14,_sclp_setup		# enable console
-	ltr	%r2,%r2
-	jnz	.LendS5
-	lr	%r2,%r10
-	bras	%r14,_sclp_print		# print string
-	ltr	%r2,%r2
-	jnz	.LendS5
-	lhi	%r2,1
-	bras	%r14,_sclp_setup		# disable console
-.LendS5:
-	tm	LC_AR_MODE_ID,1
-	jno	.Lesa3
-	lgfr	%r2,%r2				# sign extend return value
-	lmh	%r6,%r15,96(%r15)		# restore upper register halves
-	ahi	%r15,80
-.Lesa3:
-	lm	%r6,%r15,120(%r15)		# restore registers
-	br	%r14
-
-.LwritedataS4:
-	.long	0x00760005			# SCLP command for write data
-.LwritesccbS4:
-	# sccb
-	.word	.LmtoS4-.LwritesccbS4
-	.byte	0
-	.byte	0,0,0
-	.word	0
-
-	# evbuf
-.LevbufS4:
-	.word	.LmtoS4-.LevbufS4
-	.byte	0x02
-	.byte	0
-	.word	0
-
-.LmdbS4:
-	# mdb
-	.word	.LmtoS4-.LmdbS4
-	.word	1
-	.long	0xd4c4c240
-	.long	1
-
-	# go
-.LgoS4:
-	.word	.LmtoS4-.LgoS4
-	.word	1
-	.long	0
-	.byte	0,0,0,0,0,0,0,0
-	.byte	0,0,0
-	.byte	0
-	.byte	0,0,0,0,0,0,0
-	.byte	0
-	.word	0
-	.byte	0,0,0,0,0,0,0,0,0,0
-	.byte	0,0,0,0,0,0,0,0
-	.byte	0,0,0,0,0,0,0,0
-
-.LmtoS4:
-	.word	.LmtoendS4-.LmtoS4
-	.word	4
-	.word	0x1000
-	.byte	0
-	.byte	0,0,0
-.LmtoendS4:
-
-	# Global constants
-.LsccbS0:
-	.long	_sclp_work_area
-.Lascebc:
-	.long	_ascebc
-
-.section .data,"aw",@progbits
-	.balign 4096
-_sclp_work_area:
-	.fill	4096
-.previous
diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c
new file mode 100644
index 000000000000..fa0bdff1d413
--- /dev/null
+++ b/arch/s390/kernel/sclp.c
@@ -0,0 +1,160 @@
+/*
+ *    Copyright IBM Corp. 2015
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+#include <linux/kernel.h>
+#include <asm/ebcdic.h>
+#include <asm/irq.h>
+#include <asm/lowcore.h>
+#include <asm/processor.h>
+#include <asm/sclp.h>
+
+static char _sclp_work_area[4096] __aligned(PAGE_SIZE);
+
+static void _sclp_wait_int(void)
+{
+	unsigned long cr0, cr0_new, psw_mask, addr;
+	psw_t psw_ext_save, psw_wait;
+
+	__ctl_store(cr0, 0, 0);
+	cr0_new = cr0 | 0x200;
+	__ctl_load(cr0_new, 0, 0);
+
+	psw_ext_save = S390_lowcore.external_new_psw;
+	psw_mask = __extract_psw() & (PSW_MASK_EA | PSW_MASK_BA);
+	S390_lowcore.external_new_psw.mask = psw_mask;
+	psw_wait.mask = psw_mask | PSW_MASK_EXT | PSW_MASK_WAIT;
+	S390_lowcore.ext_int_code = 0;
+
+	do {
+		asm volatile(
+			"	larl	%[addr],0f\n"
+			"	stg	%[addr],%[psw_wait_addr]\n"
+			"	stg	%[addr],%[psw_ext_addr]\n"
+			"	lpswe	%[psw_wait]\n"
+			"0:\n"
+			: [addr] "=&d" (addr),
+			  [psw_wait_addr] "=Q" (psw_wait.addr),
+			  [psw_ext_addr] "=Q" (S390_lowcore.external_new_psw.addr)
+			: [psw_wait] "Q" (psw_wait)
+			: "cc", "memory");
+	} while (S390_lowcore.ext_int_code != EXT_IRQ_SERVICE_SIG);
+
+	__ctl_load(cr0, 0, 0);
+	S390_lowcore.external_new_psw = psw_ext_save;
+}
+
+static int _sclp_servc(unsigned int cmd, char *sccb)
+{
+	unsigned int cc;
+
+	do {
+		asm volatile(
+			"	.insn	rre,0xb2200000,%1,%2\n"
+			"	ipm	%0\n"
+			: "=d" (cc) : "d" (cmd), "a" (sccb)
+			: "cc", "memory");
+		cc >>= 28;
+		if (cc == 3)
+			return -EINVAL;
+		_sclp_wait_int();
+	} while (cc != 0);
+	return (*(unsigned short *)(sccb + 6) == 0x20) ? 0 : -EIO;
+}
+
+static int _sclp_setup(int disable)
+{
+	static unsigned char init_sccb[] = {
+		0x00, 0x1c,
+		0x00, 0x00, 0x00, 0x00,	0x00, 0x00, 0x00, 0x00,
+		0x00, 0x04,
+		0x80, 0x00, 0x00, 0x00,	0x40, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00,	0x00, 0x00, 0x00, 0x00
+	};
+	unsigned int *masks;
+	int rc;
+
+	memcpy(_sclp_work_area, init_sccb, 28);
+	masks = (unsigned int *)(_sclp_work_area + 12);
+	if (disable)
+		memset(masks, 0, 16);
+	/* SCLP write mask */
+	rc = _sclp_servc(0x00780005, _sclp_work_area);
+	if (rc)
+		return rc;
+	if ((masks[0] & masks[3]) != masks[0] ||
+	    (masks[1] & masks[2]) != masks[1])
+		return -EIO;
+	return 0;
+}
+
+static int _sclp_print(const char *str)
+{
+	static unsigned char write_head[] = {
+		/* sccb header */
+		0x00, 0x52,					/* 0 */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00,		/* 2 */
+		/* evbuf */
+		0x00, 0x4a,					/* 8 */
+		0x02, 0x00, 0x00, 0x00,				/* 10 */
+		/* mdb */
+		0x00, 0x44,					/* 14 */
+		0x00, 0x01,					/* 16 */
+		0xd4, 0xc4, 0xc2, 0x40,				/* 18 */
+		0x00, 0x00, 0x00, 0x01,				/* 22 */
+		/* go */
+		0x00, 0x38,					/* 26 */
+		0x00, 0x01,					/* 28 */
+		0x00, 0x00, 0x00, 0x00,				/* 30 */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 34 */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 42 */
+		0x00, 0x00, 0x00, 0x00,				/* 50 */
+		0x00, 0x00,					/* 54 */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 56 */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 64 */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 72 */
+		0x00, 0x00,					/* 80 */
+	};
+	static unsigned char write_mto[] = {
+		/* mto	*/
+		0x00, 0x0a,					/* 0 */
+		0x00, 0x04,					/* 2 */
+		0x10, 0x00,					/* 4 */
+		0x00, 0x00, 0x00, 0x00				/* 6 */
+	};
+	unsigned char *ptr, ch;
+	unsigned int count;
+
+	memcpy(_sclp_work_area, write_head, sizeof(write_head));
+	ptr = _sclp_work_area + sizeof(write_head);
+	do {
+		memcpy(ptr, write_mto, sizeof(write_mto));
+		for (count = sizeof(write_mto); (ch = *str++) != 0; count++) {
+			if (ch == 0x0a)
+				break;
+			ptr[count] = _ascebc[ch];
+		}
+		/* Update length fields in mto, mdb, evbuf and sccb */
+		*(unsigned short *) ptr = count;
+		*(unsigned short *)(_sclp_work_area + 14) += count;
+		*(unsigned short *)(_sclp_work_area + 8) += count;
+		*(unsigned short *)(_sclp_work_area + 0) += count;
+		ptr += count;
+	} while (ch != 0);
+
+	/* SCLP write data */
+	return _sclp_servc(0x00760005, _sclp_work_area);
+}
+
+int _sclp_print_early(const char *str)
+{
+	int rc;
+
+	rc = _sclp_setup(0);
+	if (rc)
+		return rc;
+	rc = _sclp_print(str);
+	if (rc)
+		return rc;
+	return _sclp_setup(1);
+}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f7f027caaaaa..ce0cbd6ba7ca 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -62,6 +62,7 @@
 #include <asm/os_info.h>
 #include <asm/sclp.h>
 #include <asm/sysinfo.h>
+#include <asm/numa.h>
 #include "entry.h"
 
 /*
@@ -76,7 +77,7 @@ EXPORT_SYMBOL(console_devno);
 unsigned int console_irq = -1;
 EXPORT_SYMBOL(console_irq);
 
-unsigned long elf_hwcap = 0;
+unsigned long elf_hwcap __read_mostly = 0;
 char elf_platform[ELF_PLATFORM_SIZE];
 
 int __initdata memory_end_set;
@@ -688,7 +689,7 @@ static void __init setup_memory(void)
 /*
  * Setup hardware capabilities.
  */
-static void __init setup_hwcaps(void)
+static int __init setup_hwcaps(void)
 {
 	static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
 	struct cpuid cpu_id;
@@ -754,9 +755,11 @@ static void __init setup_hwcaps(void)
 		elf_hwcap |= HWCAP_S390_TE;
 
 	/*
-	 * Vector extension HWCAP_S390_VXRS is bit 11.
+	 * Vector extension HWCAP_S390_VXRS is bit 11. The Vector extension
+	 * can be disabled with the "novx" parameter. Use MACHINE_HAS_VX
+	 * instead of facility bit 129.
 	 */
-	if (test_facility(129))
+	if (MACHINE_HAS_VX)
 		elf_hwcap |= HWCAP_S390_VXRS;
 	get_cpu_id(&cpu_id);
 	add_device_randomness(&cpu_id, sizeof(cpu_id));
@@ -793,7 +796,9 @@ static void __init setup_hwcaps(void)
 		strcpy(elf_platform, "z13");
 		break;
 	}
+	return 0;
 }
+arch_initcall(setup_hwcaps);
 
 /*
  * Add system information as device randomness
@@ -879,13 +884,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_lowcore();
 	smp_fill_possible_mask();
         cpu_init();
-
-	/*
-	 * Setup capabilities (ELF_HWCAP & ELF_PLATFORM).
-	 */
-	setup_hwcaps();
-
-	HPAGE_SHIFT = MACHINE_HAS_HPAGE ? 20 : 0;
+	numa_setup();
 
 	/*
 	 * Create kernel page tables and switch to virtual addressing.
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index c551f22ce066..9549af102d75 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -105,32 +105,13 @@ struct rt_sigframe
 static void store_sigregs(void)
 {
 	save_access_regs(current->thread.acrs);
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	if (current->thread.vxrs) {
-		int i;
-
-		save_vx_regs(current->thread.vxrs);
-		for (i = 0; i < __NUM_FPRS; i++)
-			current->thread.fp_regs.fprs[i] =
-				*(freg_t *)(current->thread.vxrs + i);
-	} else
-		save_fp_regs(current->thread.fp_regs.fprs);
+	save_fpu_regs();
 }
 
 /* Load registers after signal return */
 static void load_sigregs(void)
 {
 	restore_access_regs(current->thread.acrs);
-	/* restore_fp_ctl is done in restore_sigregs */
-	if (current->thread.vxrs) {
-		int i;
-
-		for (i = 0; i < __NUM_FPRS; i++)
-			*(freg_t *)(current->thread.vxrs + i) =
-				current->thread.fp_regs.fprs[i];
-		restore_vx_regs(current->thread.vxrs);
-	} else
-		restore_fp_regs(current->thread.fp_regs.fprs);
 }
 
 /* Returns non-zero on fault. */
@@ -146,8 +127,7 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&user_sregs.regs.gprs, &regs->gprs, sizeof(sregs->regs.gprs));
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
-	       sizeof(user_sregs.fpregs));
+	fpregs_store(&user_sregs.fpregs, &current->thread.fpu);
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs)))
 		return -EFAULT;
 	return 0;
@@ -166,8 +146,8 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI))
 		return -EINVAL;
 
-	/* Loading the floating-point-control word can fail. Do that first. */
-	if (restore_fp_ctl(&user_sregs.fpregs.fpc))
+	/* Test the floating-point-control word. */
+	if (test_fp_ctl(user_sregs.fpregs.fpc))
 		return -EINVAL;
 
 	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
@@ -185,8 +165,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
 
-	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
-	       sizeof(current->thread.fp_regs));
+	fpregs_load(&user_sregs.fpregs, &current->thread.fpu);
 
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
@@ -200,13 +179,13 @@ static int save_sigregs_ext(struct pt_regs *regs,
 	int i;
 
 	/* Save vector registers to signal stack */
-	if (current->thread.vxrs) {
+	if (is_vx_task(current)) {
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+			vxrs[i] = *((__u64 *)(current->thread.fpu.vxrs + i) + 1);
 		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
 				   sizeof(sregs_ext->vxrs_low)) ||
 		    __copy_to_user(&sregs_ext->vxrs_high,
-				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   current->thread.fpu.vxrs + __NUM_VXRS_LOW,
 				   sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 	}
@@ -220,15 +199,15 @@ static int restore_sigregs_ext(struct pt_regs *regs,
 	int i;
 
 	/* Restore vector registers from signal stack */
-	if (current->thread.vxrs) {
+	if (is_vx_task(current)) {
 		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
 				     sizeof(sregs_ext->vxrs_low)) ||
-		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+		    __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW,
 				     &sregs_ext->vxrs_high,
 				     sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+			*((__u64 *)(current->thread.fpu.vxrs + i) + 1) = vxrs[i];
 	}
 	return 0;
 }
@@ -243,6 +222,7 @@ SYSCALL_DEFINE0(sigreturn)
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
 		goto badframe;
 	set_current_blocked(&set);
+	save_fpu_regs();
 	if (restore_sigregs(regs, &frame->sregs))
 		goto badframe;
 	if (restore_sigregs_ext(regs, &frame->sregs_ext))
@@ -266,6 +246,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	set_current_blocked(&set);
 	if (restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
+	save_fpu_regs();
 	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 	if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
@@ -400,7 +381,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	uc_flags = 0;
 	if (MACHINE_HAS_VX) {
 		frame_size += sizeof(_sigregs_ext);
-		if (current->thread.vxrs)
+		if (is_vx_task(current))
 			uc_flags |= UC_VXRS;
 	}
 	frame = get_sigframe(&ksig->ka, regs, frame_size);
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 6f54c175f5c9..c6355e6f3fcc 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -532,8 +532,8 @@ EXPORT_SYMBOL(smp_ctl_clear_bit);
 
 #ifdef CONFIG_CRASH_DUMP
 
-static void __smp_store_cpu_state(struct save_area_ext *sa_ext, u16 address,
-				  int is_boot_cpu)
+static void __init __smp_store_cpu_state(struct save_area_ext *sa_ext,
+					 u16 address, int is_boot_cpu)
 {
 	void *lc = (void *)(unsigned long) store_prefix();
 	unsigned long vx_sa;
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 1acad02681c4..f3f4a137aef6 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -276,9 +276,9 @@ SYSCALL(sys_ni_syscall,compat_sys_s390_fadvise64_64)
 SYSCALL(sys_statfs64,compat_sys_statfs64)
 SYSCALL(sys_fstatfs64,compat_sys_fstatfs64)
 SYSCALL(sys_remap_file_pages,compat_sys_remap_file_pages)
-NI_SYSCALL						/* 268 sys_mbind */
-NI_SYSCALL						/* 269 sys_get_mempolicy */
-NI_SYSCALL						/* 270 sys_set_mempolicy */
+SYSCALL(sys_mbind,compat_sys_mbind)
+SYSCALL(sys_get_mempolicy,compat_sys_get_mempolicy)
+SYSCALL(sys_set_mempolicy,compat_sys_set_mempolicy)
 SYSCALL(sys_mq_open,compat_sys_mq_open)
 SYSCALL(sys_mq_unlink,compat_sys_mq_unlink)
 SYSCALL(sys_mq_timedsend,compat_sys_mq_timedsend)
@@ -295,7 +295,7 @@ SYSCALL(sys_ioprio_get,compat_sys_ioprio_get)
 SYSCALL(sys_inotify_init,sys_inotify_init)
 SYSCALL(sys_inotify_add_watch,compat_sys_inotify_add_watch)	/* 285 */
 SYSCALL(sys_inotify_rm_watch,compat_sys_inotify_rm_watch)
-NI_SYSCALL						/* 287 sys_migrate_pages */
+SYSCALL(sys_migrate_pages,compat_sys_migrate_pages)
 SYSCALL(sys_openat,compat_sys_openat)
 SYSCALL(sys_mkdirat,compat_sys_mkdirat)
 SYSCALL(sys_mknodat,compat_sys_mknodat)			/* 290 */
@@ -318,7 +318,7 @@ SYSCALL(sys_splice,compat_sys_splice)
 SYSCALL(sys_sync_file_range,compat_sys_s390_sync_file_range)
 SYSCALL(sys_tee,compat_sys_tee)
 SYSCALL(sys_vmsplice,compat_sys_vmsplice)
-NI_SYSCALL						/* 310 sys_move_pages */
+SYSCALL(sys_move_pages,compat_sys_move_pages)
 SYSCALL(sys_getcpu,compat_sys_getcpu)
 SYSCALL(sys_epoll_pwait,compat_sys_epoll_pwait)
 SYSCALL(sys_utimes,compat_sys_utimes)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 9e733d965e08..017c3a9bfc28 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -58,6 +58,9 @@ EXPORT_SYMBOL_GPL(sched_clock_base_cc);
 
 static DEFINE_PER_CPU(struct clock_event_device, comparators);
 
+ATOMIC_NOTIFIER_HEAD(s390_epoch_delta_notifier);
+EXPORT_SYMBOL(s390_epoch_delta_notifier);
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -117,11 +120,6 @@ static int s390_next_event(unsigned long delta,
 	return 0;
 }
 
-static void s390_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt)
-{
-}
-
 /*
  * Set up lowcore and control register of the current cpu to
  * enable TOD clock and clock comparator interrupts.
@@ -145,7 +143,6 @@ void init_cpu_timer(void)
 	cd->rating		= 400;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= s390_next_event;
-	cd->set_mode		= s390_set_mode;
 
 	clockevents_register_device(cd);
 
@@ -381,7 +378,7 @@ static void disable_sync_clock(void *dummy)
 	 * increase the "sequence" counter to avoid the race of an
 	 * etr event and the complete recovery against get_sync_clock.
 	 */
-	atomic_clear_mask(0x80000000, sw_ptr);
+	atomic_andnot(0x80000000, sw_ptr);
 	atomic_inc(sw_ptr);
 }
 
@@ -392,7 +389,7 @@ static void disable_sync_clock(void *dummy)
 static void enable_sync_clock(void)
 {
 	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
-	atomic_set_mask(0x80000000, sw_ptr);
+	atomic_or(0x80000000, sw_ptr);
 }
 
 /*
@@ -752,7 +749,7 @@ static void clock_sync_cpu(struct clock_sync_data *sync)
 static int etr_sync_clock(void *data)
 {
 	static int first;
-	unsigned long long clock, old_clock, delay, delta;
+	unsigned long long clock, old_clock, clock_delta, delay, delta;
 	struct clock_sync_data *etr_sync;
 	struct etr_aib *sync_port, *aib;
 	int port;
@@ -789,6 +786,9 @@ static int etr_sync_clock(void *data)
 		delay = (unsigned long long)
 			(aib->edf2.etv - sync_port->edf2.etv) << 32;
 		delta = adjust_time(old_clock, clock, delay);
+		clock_delta = clock - old_clock;
+		atomic_notifier_call_chain(&s390_epoch_delta_notifier, 0,
+					   &clock_delta);
 		etr_sync->fixup_cc = delta;
 		fixup_clock_comparator(delta);
 		/* Verify that the clock is properly set. */
@@ -1526,7 +1526,7 @@ void stp_island_check(void)
 static int stp_sync_clock(void *data)
 {
 	static int first;
-	unsigned long long old_clock, delta;
+	unsigned long long old_clock, delta, new_clock, clock_delta;
 	struct clock_sync_data *stp_sync;
 	int rc;
 
@@ -1551,7 +1551,11 @@ static int stp_sync_clock(void *data)
 		old_clock = get_tod_clock();
 		rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0);
 		if (rc == 0) {
-			delta = adjust_time(old_clock, get_tod_clock(), 0);
+			new_clock = get_tod_clock();
+			delta = adjust_time(old_clock, new_clock, 0);
+			clock_delta = new_clock - old_clock;
+			atomic_notifier_call_chain(&s390_epoch_delta_notifier,
+						   0, &clock_delta);
 			fixup_clock_comparator(delta);
 			rc = chsc_sstpi(stp_page, &stp_info,
 					sizeof(struct stp_sstpi));
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 5728c5bd44a8..bf05e7fc3e70 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -18,7 +18,10 @@
 #include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/nodemask.h>
+#include <linux/node.h>
 #include <asm/sysinfo.h>
+#include <asm/numa.h>
 
 #define PTF_HORIZONTAL	(0UL)
 #define PTF_VERTICAL	(1UL)
@@ -37,8 +40,10 @@ static struct sysinfo_15_1_x *tl_info;
 static int topology_enabled = 1;
 static DECLARE_WORK(topology_work, topology_work_fn);
 
-/* topology_lock protects the socket and book linked lists */
-static DEFINE_SPINLOCK(topology_lock);
+/*
+ * Socket/Book linked lists and per_cpu(cpu_topology) updates are
+ * protected by "sched_domains_mutex".
+ */
 static struct mask_info socket_info;
 static struct mask_info book_info;
 
@@ -188,7 +193,6 @@ static void tl_to_masks(struct sysinfo_15_1_x *info)
 {
 	struct cpuid cpu_id;
 
-	spin_lock_irq(&topology_lock);
 	get_cpu_id(&cpu_id);
 	clear_masks();
 	switch (cpu_id.machine) {
@@ -199,7 +203,6 @@ static void tl_to_masks(struct sysinfo_15_1_x *info)
 	default:
 		__tl_to_masks_generic(info);
 	}
-	spin_unlock_irq(&topology_lock);
 }
 
 static void topology_update_polarization_simple(void)
@@ -244,10 +247,8 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_masks(void)
 {
-	unsigned long flags;
 	int cpu;
 
-	spin_lock_irqsave(&topology_lock, flags);
 	for_each_possible_cpu(cpu) {
 		per_cpu(cpu_topology, cpu).thread_mask = cpu_thread_map(cpu);
 		per_cpu(cpu_topology, cpu).core_mask = cpu_group_map(&socket_info, cpu);
@@ -259,7 +260,7 @@ static void update_cpu_masks(void)
 			per_cpu(cpu_topology, cpu).book_id = cpu;
 		}
 	}
-	spin_unlock_irqrestore(&topology_lock, flags);
+	numa_update_cpu_topology();
 }
 
 void store_topology(struct sysinfo_15_1_x *info)
@@ -274,21 +275,21 @@ int arch_update_cpu_topology(void)
 {
 	struct sysinfo_15_1_x *info = tl_info;
 	struct device *dev;
-	int cpu;
+	int cpu, rc = 0;
 
-	if (!MACHINE_HAS_TOPOLOGY) {
-		update_cpu_masks();
-		topology_update_polarization_simple();
-		return 0;
+	if (MACHINE_HAS_TOPOLOGY) {
+		rc = 1;
+		store_topology(info);
+		tl_to_masks(info);
 	}
-	store_topology(info);
-	tl_to_masks(info);
 	update_cpu_masks();
+	if (!MACHINE_HAS_TOPOLOGY)
+		topology_update_polarization_simple();
 	for_each_online_cpu(cpu) {
 		dev = get_cpu_device(cpu);
 		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
 	}
-	return 1;
+	return rc;
 }
 
 static void topology_work_fn(struct work_struct *work)
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 4d96c9f53455..9861613fb35a 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -19,7 +19,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <asm/switch_to.h>
+#include <asm/fpu-internal.h>
 #include "entry.h"
 
 int show_unhandled_signals = 1;
@@ -151,7 +151,7 @@ DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN,
 DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN,
 	      "transaction constraint exception")
 
-static inline void do_fp_trap(struct pt_regs *regs, int fpc)
+static inline void do_fp_trap(struct pt_regs *regs, __u32 fpc)
 {
 	int si_code = 0;
 	/* FPC[2] is Data Exception Code */
@@ -227,7 +227,7 @@ DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
 int alloc_vector_registers(struct task_struct *tsk)
 {
 	__vector128 *vxrs;
-	int i;
+	freg_t *fprs;
 
 	/* Allocate vector register save area. */
 	vxrs = kzalloc(sizeof(__vector128) * __NUM_VXRS,
@@ -236,15 +236,13 @@ int alloc_vector_registers(struct task_struct *tsk)
 		return -ENOMEM;
 	preempt_disable();
 	if (tsk == current)
-		save_fp_regs(tsk->thread.fp_regs.fprs);
+		save_fpu_regs();
 	/* Copy the 16 floating point registers */
-	for (i = 0; i < 16; i++)
-		*(freg_t *) &vxrs[i] = tsk->thread.fp_regs.fprs[i];
-	tsk->thread.vxrs = vxrs;
-	if (tsk == current) {
-		__ctl_set_bit(0, 17);
-		restore_vx_regs(vxrs);
-	}
+	convert_fp_to_vx(vxrs, tsk->thread.fpu.fprs);
+	fprs = tsk->thread.fpu.fprs;
+	tsk->thread.fpu.vxrs = vxrs;
+	tsk->thread.fpu.flags |= FPU_USE_VX;
+	kfree(fprs);
 	preempt_enable();
 	return 0;
 }
@@ -259,8 +257,8 @@ void vector_exception(struct pt_regs *regs)
 	}
 
 	/* get vector interrupt code from fpc */
-	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
-	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
+	save_fpu_regs();
+	vic = (current->thread.fpu.fpc & 0xf00) >> 8;
 	switch (vic) {
 	case 1: /* invalid vector operation */
 		si_code = FPE_FLTINV;
@@ -297,22 +295,22 @@ void data_exception(struct pt_regs *regs)
 
 	location = get_trap_ip(regs);
 
-	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	save_fpu_regs();
 	/* Check for vector register enablement */
-	if (MACHINE_HAS_VX && !current->thread.vxrs &&
-	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
+	if (MACHINE_HAS_VX && !is_vx_task(current) &&
+	    (current->thread.fpu.fpc & FPC_DXC_MASK) == 0xfe00) {
 		alloc_vector_registers(current);
 		/* Vector data exception is suppressing, rewind psw. */
 		regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
 		clear_pt_regs_flag(regs, PIF_PER_TRAP);
 		return;
 	}
-	if (current->thread.fp_regs.fpc & FPC_DXC_MASK)
+	if (current->thread.fpu.fpc & FPC_DXC_MASK)
 		signal = SIGFPE;
 	else
 		signal = SIGILL;
 	if (signal == SIGFPE)
-		do_fp_trap(regs, current->thread.fp_regs.fpc);
+		do_fp_trap(regs, current->thread.fpu.fpc);
 	else if (signal)
 		do_trap(regs, signal, ILL_ILLOPN, "data exception");
 }
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 8ad2b34ad151..ee8a18e50a25 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -13,7 +13,7 @@ KBUILD_AFLAGS_31 += -m31 -s
 KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin
 KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
-			$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+			$(call cc-ldoption, -Wl$(comma)--hash-style=both)
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31)
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 2a8ddfd12a5b..c4b03f9ed228 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -13,7 +13,7 @@ KBUILD_AFLAGS_64 += -m64 -s
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
 KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
-			$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+			$(call cc-ldoption, -Wl$(comma)--hash-style=both)
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index e53d3595a7c8..b9ce650e9e99 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -28,6 +28,7 @@ static atomic64_t virt_timer_elapsed;
 static DEFINE_PER_CPU(u64, mt_cycles[32]);
 static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 };
 static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 };
+static DEFINE_PER_CPU(u64, mt_scaling_jiffies);
 
 static inline u64 get_vtimer(void)
 {
@@ -85,7 +86,8 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
 
 	/* Do MT utilization calculation */
-	if (smp_cpu_mtid) {
+	if (smp_cpu_mtid &&
+	    time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) {
 		u64 cycles_new[32], *cycles_old;
 		u64 delta, mult, div;
 
@@ -105,6 +107,7 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 				       sizeof(u64) * (smp_cpu_mtid + 1));
 			}
 		}
+		__this_cpu_write(mt_scaling_jiffies, jiffies_64);
 	}
 
 	user = S390_lowcore.user_timer - ti->user_timer;
@@ -376,4 +379,11 @@ void vtime_init(void)
 {
 	/* set initial cpu timer */
 	set_vtimer(VTIMER_MAX_SLICE);
+	/* Setup initial MT scaling values */
+	if (smp_cpu_mtid) {
+		__this_cpu_write(mt_scaling_jiffies, jiffies);
+		__this_cpu_write(mt_scaling_mult, 1);
+		__this_cpu_write(mt_scaling_div, 1);
+		stcctm5(smp_cpu_mtid + 1, this_cpu_ptr(mt_cycles));
+	}
 }
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index fc7ec95848c3..5fbfb88f8477 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -27,13 +27,13 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 
 	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+	vcpu->stat.diagnose_10++;
 
 	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
 	    || start < 2 * PAGE_SIZE)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end);
-	vcpu->stat.diagnose_10++;
 
 	/*
 	 * We checked for start >= end above, so lets check for the
@@ -75,6 +75,9 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 	u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
 	u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
 
+	VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx",
+		   vcpu->run->s.regs.gprs[rx]);
+	vcpu->stat.diagnose_258++;
 	if (vcpu->run->s.regs.gprs[rx] & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
@@ -85,6 +88,9 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 
 	switch (parm.subcode) {
 	case 0: /* TOKEN */
+		VCPU_EVENT(vcpu, 3, "pageref token addr 0x%llx "
+			   "select mask 0x%llx compare mask 0x%llx",
+			   parm.token_addr, parm.select_mask, parm.compare_mask);
 		if (vcpu->arch.pfault_token != KVM_S390_PFAULT_TOKEN_INVALID) {
 			/*
 			 * If the pagefault handshake is already activated,
@@ -114,6 +120,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 		 * the cancel, therefore to reduce code complexity, we assume
 		 * all outstanding tokens are already pending.
 		 */
+		VCPU_EVENT(vcpu, 3, "pageref cancel addr 0x%llx", parm.token_addr);
 		if (parm.token_addr || parm.select_mask ||
 		    parm.compare_mask || parm.zarch)
 			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -174,7 +181,8 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
 	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
 
-	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
+	VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode);
+	vcpu->stat.diagnose_308++;
 	switch (subcode) {
 	case 3:
 		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
@@ -202,6 +210,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 {
 	int ret;
 
+	vcpu->stat.diagnose_500++;
 	/* No virtio-ccw notification? Get out quickly. */
 	if (!vcpu->kvm->arch.css_support ||
 	    (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index e97b3455d7e6..47518a324d75 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -473,10 +473,45 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->iprcc &= ~PGM_PER;
 }
 
+#define pssec(vcpu) (vcpu->arch.sie_block->gcr[1] & _ASCE_SPACE_SWITCH)
+#define hssec(vcpu) (vcpu->arch.sie_block->gcr[13] & _ASCE_SPACE_SWITCH)
+#define old_ssec(vcpu) ((vcpu->arch.sie_block->tecmc >> 31) & 0x1)
+#define old_as_is_home(vcpu) !(vcpu->arch.sie_block->tecmc & 0xffff)
+
 void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
 {
+	int new_as;
+
 	if (debug_exit_required(vcpu))
 		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
 
 	filter_guest_per_event(vcpu);
+
+	/*
+	 * Only RP, SAC, SACF, PT, PTI, PR, PC instructions can trigger
+	 * a space-switch event. PER events enforce space-switch events
+	 * for these instructions. So if no PER event for the guest is left,
+	 * we might have to filter the space-switch element out, too.
+	 */
+	if (vcpu->arch.sie_block->iprcc == PGM_SPACE_SWITCH) {
+		vcpu->arch.sie_block->iprcc = 0;
+		new_as = psw_bits(vcpu->arch.sie_block->gpsw).as;
+
+		/*
+		 * If the AS changed from / to home, we had RP, SAC or SACF
+		 * instruction. Check primary and home space-switch-event
+		 * controls. (theoretically home -> home produced no event)
+		 */
+		if (((new_as == PSW_AS_HOME) ^ old_as_is_home(vcpu)) &&
+		     (pssec(vcpu) || hssec(vcpu)))
+			vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
+
+		/*
+		 * PT, PTI, PR, PC instruction operate on primary AS only. Check
+		 * if the primary-space-switch-event control was or got set.
+		 */
+		if (new_as == PSW_AS_PRIMARY && !old_as_is_home(vcpu) &&
+		    (pssec(vcpu) || old_ssec(vcpu)))
+			vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
+	}
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c98d89708e99..5c2c169395c3 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -30,7 +30,6 @@
 #define IOINT_SCHID_MASK 0x0000ffff
 #define IOINT_SSID_MASK 0x00030000
 #define IOINT_CSSID_MASK 0x03fc0000
-#define IOINT_AI_MASK 0x04000000
 #define PFAULT_INIT 0x0600
 #define PFAULT_DONE 0x0680
 #define VIRTIO_PARAM 0x0d00
@@ -72,9 +71,13 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
 
 static int ckc_irq_pending(struct kvm_vcpu *vcpu)
 {
+	preempt_disable();
 	if (!(vcpu->arch.sie_block->ckc <
-	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
+	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) {
+		preempt_enable();
 		return 0;
+	}
+	preempt_enable();
 	return ckc_interrupts_enabled(vcpu);
 }
 
@@ -170,20 +173,20 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 
 static void __set_cpu_idle(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
 	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
 }
 
 static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
 	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
 }
 
 static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
-			  &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
+		    &vcpu->arch.sie_block->cpuflags);
 	vcpu->arch.sie_block->lctl = 0x0000;
 	vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
 
@@ -196,7 +199,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
 {
-	atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
 }
 
 static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
@@ -311,8 +314,8 @@ static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
 	li->irq.ext.ext_params2 = 0;
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx",
-		   0, ext.ext_params2);
+	VCPU_EVENT(vcpu, 4, "deliver: pfault init token 0x%llx",
+		   ext.ext_params2);
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 					 KVM_S390_INT_PFAULT_INIT,
 					 0, ext.ext_params2);
@@ -368,7 +371,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
 	spin_unlock(&fi->lock);
 
 	if (deliver) {
-		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+		VCPU_EVENT(vcpu, 3, "deliver: machine check mcic 0x%llx",
 			   mchk.mcic);
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 						 KVM_S390_MCHK,
@@ -403,7 +406,7 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	int rc;
 
-	VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+	VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
 	vcpu->stat.deliver_restart_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
 
@@ -427,7 +430,6 @@ static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
 	clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address);
 	vcpu->stat.deliver_prefix_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 					 KVM_S390_SIGP_SET_PREFIX,
@@ -450,7 +452,7 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
 		clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp emerg");
 	vcpu->stat.deliver_emergency_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
 					 cpu_addr, 0);
@@ -477,7 +479,7 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
 	clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
+	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp ext call");
 	vcpu->stat.deliver_external_call++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 					 KVM_S390_INT_EXTERNAL_CALL,
@@ -506,7 +508,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	memset(&li->irq.pgm, 0, sizeof(pgm_info));
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
+	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
 		   pgm_info.code, ilc);
 	vcpu->stat.deliver_program_int++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
@@ -622,7 +624,7 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
 	clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
 	spin_unlock(&fi->lock);
 
-	VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+	VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
 		   ext.ext_params);
 	vcpu->stat.deliver_service_signal++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
@@ -651,9 +653,6 @@ static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
 					struct kvm_s390_interrupt_info,
 					list);
 	if (inti) {
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
-				KVM_S390_INT_PFAULT_DONE, 0,
-				inti->ext.ext_params2);
 		list_del(&inti->list);
 		fi->counters[FIRQ_CNTR_PFAULT] -= 1;
 	}
@@ -662,6 +661,12 @@ static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
 	spin_unlock(&fi->lock);
 
 	if (inti) {
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+						 KVM_S390_INT_PFAULT_DONE, 0,
+						 inti->ext.ext_params2);
+		VCPU_EVENT(vcpu, 4, "deliver: pfault done token 0x%llx",
+			   inti->ext.ext_params2);
+
 		rc  = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE,
 				(u16 *)__LC_EXT_INT_CODE);
 		rc |= put_guest_lc(vcpu, PFAULT_DONE,
@@ -691,7 +696,7 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
 					list);
 	if (inti) {
 		VCPU_EVENT(vcpu, 4,
-			   "interrupt: virtio parm:%x,parm64:%llx",
+			   "deliver: virtio parm: 0x%x,parm64: 0x%llx",
 			   inti->ext.ext_params, inti->ext.ext_params2);
 		vcpu->stat.deliver_virtio_interrupt++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
@@ -741,7 +746,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 					struct kvm_s390_interrupt_info,
 					list);
 	if (inti) {
-		VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
+		VCPU_EVENT(vcpu, 4, "deliver: I/O 0x%llx", inti->type);
 		vcpu->stat.deliver_io_int++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 				inti->type,
@@ -855,7 +860,9 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		goto no_timer;
 	}
 
+	preempt_disable();
 	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+	preempt_enable();
 	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
 	/* underflow */
@@ -864,7 +871,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 
 	__set_cpu_idle(vcpu);
 	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
-	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
+	VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	kvm_vcpu_block(vcpu);
@@ -894,7 +901,9 @@ enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 	u64 now, sltime;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
+	preempt_disable();
 	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+	preempt_enable();
 	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
 	/*
@@ -919,7 +928,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
 	spin_unlock(&li->lock);
 
 	/* clear pending external calls set by sigp interpretation facility */
-	atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags);
+	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
 	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
 }
 
@@ -968,6 +977,10 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	VCPU_EVENT(vcpu, 3, "inject: program irq code 0x%x", irq->u.pgm.code);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
+				   irq->u.pgm.code, 0);
+
 	li->irq.pgm = irq->u.pgm;
 	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
 	return 0;
@@ -978,9 +991,6 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_irq irq;
 
-	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code,
-				   0, 1);
 	spin_lock(&li->lock);
 	irq.u.pgm.code = code;
 	__inject_prog(vcpu, &irq);
@@ -996,10 +1006,6 @@ int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
 	struct kvm_s390_irq irq;
 	int rc;
 
-	VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)",
-		   pgm_info->code);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
-				   pgm_info->code, 0, 1);
 	spin_lock(&li->lock);
 	irq.u.pgm = *pgm_info;
 	rc = __inject_prog(vcpu, &irq);
@@ -1012,15 +1018,15 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: external irq params:%x, params2:%llx",
-		   irq->u.ext.ext_params, irq->u.ext.ext_params2);
+	VCPU_EVENT(vcpu, 4, "inject: pfault init parameter block at 0x%llx",
+		   irq->u.ext.ext_params2);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
 				   irq->u.ext.ext_params,
-				   irq->u.ext.ext_params2, 2);
+				   irq->u.ext.ext_params2);
 
 	li->irq.ext = irq->u.ext;
 	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1035,7 +1041,7 @@ static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
 		/* another external call is pending */
 		return -EBUSY;
 	}
-	atomic_set_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
 	return 0;
 }
 
@@ -1045,10 +1051,10 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
 	uint16_t src_id = irq->u.extcall.code;
 
-	VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
+	VCPU_EVENT(vcpu, 4, "inject: external call source-cpu:%u",
 		   src_id);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
-				   src_id, 0, 2);
+				   src_id, 0);
 
 	/* sending vcpu invalid */
 	if (src_id >= KVM_MAX_VCPUS ||
@@ -1061,7 +1067,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
 	*extcall = irq->u.extcall;
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1070,10 +1076,10 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
 
-	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
+	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x",
 		   irq->u.prefix.address);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
-				   irq->u.prefix.address, 0, 2);
+				   irq->u.prefix.address, 0);
 
 	if (!is_vcpu_stopped(vcpu))
 		return -EBUSY;
@@ -1090,7 +1096,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_stop_info *stop = &li->irq.stop;
 	int rc = 0;
 
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0);
 
 	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
 		return -EINVAL;
@@ -1114,8 +1120,8 @@ static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: restart type %llx", irq->type);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0, 2);
+	VCPU_EVENT(vcpu, 3, "%s", "inject: restart int");
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
 
 	set_bit(IRQ_PEND_RESTART, &li->pending_irqs);
 	return 0;
@@ -1126,14 +1132,14 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: emergency %u\n",
+	VCPU_EVENT(vcpu, 4, "inject: emergency from cpu %u",
 		   irq->u.emerg.code);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
-				   irq->u.emerg.code, 0, 2);
+				   irq->u.emerg.code, 0);
 
 	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
 	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1142,10 +1148,10 @@ static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
 
-	VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+	VCPU_EVENT(vcpu, 3, "inject: machine check mcic 0x%llx",
 		   irq->u.mchk.mcic);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
-				   irq->u.mchk.mcic, 2);
+				   irq->u.mchk.mcic);
 
 	/*
 	 * Because repressible machine checks can be indicated along with
@@ -1172,12 +1178,12 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CLOCK_COMP);
+	VCPU_EVENT(vcpu, 3, "%s", "inject: clock comparator external");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
-				   0, 0, 2);
+				   0, 0);
 
 	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1185,12 +1191,12 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CPU_TIMER);
+	VCPU_EVENT(vcpu, 3, "%s", "inject: cpu timer external");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
-				   0, 0, 2);
+				   0, 0);
 
 	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1369,13 +1375,13 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
 	spin_lock(&li->lock);
 	switch (type) {
 	case KVM_S390_MCHK:
-		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+		atomic_or(CPUSTAT_STOP_INT, li->cpuflags);
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
+		atomic_or(CPUSTAT_IO_INT, li->cpuflags);
 		break;
 	default:
-		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+		atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 		break;
 	}
 	spin_unlock(&li->lock);
@@ -1435,20 +1441,20 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		inti->ext.ext_params2 = s390int->parm64;
 		break;
 	case KVM_S390_INT_SERVICE:
-		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
+		VM_EVENT(kvm, 4, "inject: sclp parm:%x", s390int->parm);
 		inti->ext.ext_params = s390int->parm;
 		break;
 	case KVM_S390_INT_PFAULT_DONE:
 		inti->ext.ext_params2 = s390int->parm64;
 		break;
 	case KVM_S390_MCHK:
-		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
+		VM_EVENT(kvm, 3, "inject: machine check mcic 0x%llx",
 			 s390int->parm64);
 		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
 		inti->mchk.mcic = s390int->parm64;
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (inti->type & IOINT_AI_MASK)
+		if (inti->type & KVM_S390_INT_IO_AI_MASK)
 			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
 		else
 			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
@@ -1535,8 +1541,6 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 
 	switch (irq->type) {
 	case KVM_S390_PROGRAM_INT:
-		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
-			   irq->u.pgm.code);
 		rc = __inject_prog(vcpu, irq);
 		break;
 	case KVM_S390_SIGP_SET_PREFIX:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2078f92d15ac..c91eb941b444 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -28,6 +28,7 @@
 #include <linux/vmalloc.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
+#include <asm/etr.h>
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
@@ -108,6 +109,9 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "diagnose_10", VCPU_STAT(diagnose_10) },
 	{ "diagnose_44", VCPU_STAT(diagnose_44) },
 	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
+	{ "diagnose_258", VCPU_STAT(diagnose_258) },
+	{ "diagnose_308", VCPU_STAT(diagnose_308) },
+	{ "diagnose_500", VCPU_STAT(diagnose_500) },
 	{ NULL }
 };
 
@@ -124,6 +128,7 @@ unsigned long kvm_s390_fac_list_mask_size(void)
 }
 
 static struct gmap_notifier gmap_notifier;
+debug_info_t *kvm_s390_dbf;
 
 /* Section: not file related */
 int kvm_arch_hardware_enable(void)
@@ -134,24 +139,69 @@ int kvm_arch_hardware_enable(void)
 
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
 
+/*
+ * This callback is executed during stop_machine(). All CPUs are therefore
+ * temporarily stopped. In order not to change guest behavior, we have to
+ * disable preemption whenever we touch the epoch of kvm and the VCPUs,
+ * so a CPU won't be stopped while calculating with the epoch.
+ */
+static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
+			  void *v)
+{
+	struct kvm *kvm;
+	struct kvm_vcpu *vcpu;
+	int i;
+	unsigned long long *delta = v;
+
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		kvm->arch.epoch -= *delta;
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			vcpu->arch.sie_block->epoch -= *delta;
+		}
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_clock_notifier = {
+	.notifier_call = kvm_clock_sync,
+};
+
 int kvm_arch_hardware_setup(void)
 {
 	gmap_notifier.notifier_call = kvm_gmap_notifier;
 	gmap_register_ipte_notifier(&gmap_notifier);
+	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
+				       &kvm_clock_notifier);
 	return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)
 {
 	gmap_unregister_ipte_notifier(&gmap_notifier);
+	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
+					 &kvm_clock_notifier);
 }
 
 int kvm_arch_init(void *opaque)
 {
+	kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
+	if (!kvm_s390_dbf)
+		return -ENOMEM;
+
+	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
+		debug_unregister(kvm_s390_dbf);
+		return -ENOMEM;
+	}
+
 	/* Register floating interrupt controller interface. */
 	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 }
 
+void kvm_arch_exit(void)
+{
+	debug_unregister(kvm_s390_dbf);
+}
+
 /* Section: device related */
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg)
@@ -281,10 +331,12 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 
 	switch (cap->cap) {
 	case KVM_CAP_S390_IRQCHIP:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_IRQCHIP");
 		kvm->arch.use_irqchip = 1;
 		r = 0;
 		break;
 	case KVM_CAP_S390_USER_SIGP:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_SIGP");
 		kvm->arch.user_sigp = 1;
 		r = 0;
 		break;
@@ -295,8 +347,11 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 			r = 0;
 		} else
 			r = -EINVAL;
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
+			 r ? "(not available)" : "(success)");
 		break;
 	case KVM_CAP_S390_USER_STSI:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
 		r = 0;
 		break;
@@ -314,6 +369,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	switch (attr->attr) {
 	case KVM_S390_VM_MEM_LIMIT_SIZE:
 		ret = 0;
+		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
+			 kvm->arch.gmap->asce_end);
 		if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
 			ret = -EFAULT;
 		break;
@@ -330,7 +387,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	unsigned int idx;
 	switch (attr->attr) {
 	case KVM_S390_VM_MEM_ENABLE_CMMA:
+		/* enable CMMA only for z10 and later (EDAT_1) */
+		ret = -EINVAL;
+		if (!MACHINE_IS_LPAR || !MACHINE_HAS_EDAT1)
+			break;
+
 		ret = -EBUSY;
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
 		if (atomic_read(&kvm->online_vcpus) == 0) {
 			kvm->arch.use_cmma = 1;
@@ -339,6 +402,11 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		mutex_unlock(&kvm->lock);
 		break;
 	case KVM_S390_VM_MEM_CLR_CMMA:
+		ret = -EINVAL;
+		if (!kvm->arch.use_cmma)
+			break;
+
+		VM_EVENT(kvm, 3, "%s", "RESET: CMMA states");
 		mutex_lock(&kvm->lock);
 		idx = srcu_read_lock(&kvm->srcu);
 		s390_reset_cmma(kvm->arch.gmap->mm);
@@ -374,6 +442,7 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 			}
 		}
 		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
 		break;
 	}
 	default:
@@ -400,22 +469,26 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 			kvm->arch.crypto.crycb->aes_wrapping_key_mask,
 			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
 		kvm->arch.crypto.aes_kw = 1;
+		VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
 		get_random_bytes(
 			kvm->arch.crypto.crycb->dea_wrapping_key_mask,
 			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
 		kvm->arch.crypto.dea_kw = 1;
+		VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
 		kvm->arch.crypto.aes_kw = 0;
 		memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
 			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
+		VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
 		kvm->arch.crypto.dea_kw = 0;
 		memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
 			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
+		VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
 		break;
 	default:
 		mutex_unlock(&kvm->lock);
@@ -440,6 +513,7 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 
 	if (gtod_high != 0)
 		return -EINVAL;
+	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x\n", gtod_high);
 
 	return 0;
 }
@@ -459,12 +533,15 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 		return r;
 
 	mutex_lock(&kvm->lock);
+	preempt_disable();
 	kvm->arch.epoch = gtod - host_tod;
 	kvm_s390_vcpu_block_all(kvm);
 	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm)
 		cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
 	kvm_s390_vcpu_unblock_all(kvm);
+	preempt_enable();
 	mutex_unlock(&kvm->lock);
+	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx\n", gtod);
 	return 0;
 }
 
@@ -496,6 +573,7 @@ static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 	if (copy_to_user((void __user *)attr->addr, &gtod_high,
 					 sizeof(gtod_high)))
 		return -EFAULT;
+	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x\n", gtod_high);
 
 	return 0;
 }
@@ -509,9 +587,12 @@ static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 	if (r)
 		return r;
 
+	preempt_disable();
 	gtod = host_tod + kvm->arch.epoch;
+	preempt_enable();
 	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
 		return -EFAULT;
+	VM_EVENT(kvm, 3, "QUERY: TOD base: 0x%llx\n", gtod);
 
 	return 0;
 }
@@ -821,7 +902,9 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	}
 
 	/* Enable storage key handling for the guest */
-	s390_enable_skey();
+	r = s390_enable_skey();
+	if (r)
+		goto out;
 
 	for (i = 0; i < args->count; i++) {
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
@@ -879,8 +962,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.use_irqchip) {
 			/* Set up dummy routing. */
 			memset(&routing, 0, sizeof(routing));
-			kvm_set_irq_routing(kvm, &routing, 0, 0);
-			r = 0;
+			r = kvm_set_irq_routing(kvm, &routing, 0, 0);
 		}
 		break;
 	}
@@ -1043,7 +1125,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	sprintf(debug_name, "kvm-%u", current->pid);
 
-	kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
+	kvm->arch.dbf = debug_register(debug_name, 32, 1, 7 * sizeof(long));
 	if (!kvm->arch.dbf)
 		goto out_err;
 
@@ -1086,7 +1168,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.ipte_mutex);
 
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
-	VM_EVENT(kvm, 3, "%s", "vm created");
+	VM_EVENT(kvm, 3, "vm created with type %lu", type);
 
 	if (type & KVM_VM_S390_UCONTROL) {
 		kvm->arch.gmap = NULL;
@@ -1103,6 +1185,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
+	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
@@ -1110,6 +1193,7 @@ out_err:
 	free_page((unsigned long)kvm->arch.model.fac);
 	debug_unregister(kvm->arch.dbf);
 	free_page((unsigned long)(kvm->arch.sca));
+	KVM_EVENT(3, "creation of vm failed: %d", rc);
 	return rc;
 }
 
@@ -1131,7 +1215,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_free(vcpu->arch.gmap);
 
-	if (kvm_s390_cmma_enabled(vcpu->kvm))
+	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
 	free_page((unsigned long)(vcpu->arch.sie_block));
 
@@ -1166,6 +1250,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
+	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -1198,43 +1283,79 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+/*
+ * Backs up the current FP/VX register save area on a particular
+ * destination.  Used to switch between different register save
+ * areas.
+ */
+static inline void save_fpu_to(struct fpu *dst)
+{
+	dst->fpc = current->thread.fpu.fpc;
+	dst->flags = current->thread.fpu.flags;
+	dst->regs = current->thread.fpu.regs;
+}
+
+/*
+ * Switches the FP/VX register save area from which to lazy
+ * restore register contents.
+ */
+static inline void load_fpu_from(struct fpu *from)
+{
+	current->thread.fpu.fpc = from->fpc;
+	current->thread.fpu.flags = from->flags;
+	current->thread.fpu.regs = from->regs;
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
-	if (test_kvm_facility(vcpu->kvm, 129))
-		save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
-	else
-		save_fp_regs(vcpu->arch.host_fpregs.fprs);
-	save_access_regs(vcpu->arch.host_acrs);
+	/* Save host register state */
+	save_fpu_regs();
+	save_fpu_to(&vcpu->arch.host_fpregs);
+
 	if (test_kvm_facility(vcpu->kvm, 129)) {
-		restore_fp_ctl(&vcpu->run->s.regs.fpc);
-		restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
-	} else {
-		restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-		restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
-	}
+		current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
+		current->thread.fpu.flags = FPU_USE_VX;
+		/*
+		 * Use the register save area in the SIE-control block
+		 * for register restore and save in kvm_arch_vcpu_put()
+		 */
+		current->thread.fpu.vxrs =
+			(__vector128 *)&vcpu->run->s.regs.vrs;
+		/* Always enable the vector extension for KVM */
+		__ctl_set_vx();
+	} else
+		load_fpu_from(&vcpu->arch.guest_fpregs);
+
+	if (test_fp_ctl(current->thread.fpu.fpc))
+		/* User space provided an invalid FPC, let's clear it */
+		current->thread.fpu.fpc = 0;
+
+	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
-	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		save_fp_ctl(&vcpu->run->s.regs.fpc);
-		save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
-	} else {
-		save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-		save_fp_regs(vcpu->arch.guest_fpregs.fprs);
-	}
-	save_access_regs(vcpu->run->s.regs.acrs);
-	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
+
+	save_fpu_regs();
+
 	if (test_kvm_facility(vcpu->kvm, 129))
-		restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
+		/*
+		 * kvm_arch_vcpu_load() set up the register save area to
+		 * the &vcpu->run->s.regs.vrs and, thus, the vector registers
+		 * are already saved.  Only the floating-point control must be
+		 * copied.
+		 */
+		vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 	else
-		restore_fp_regs(vcpu->arch.host_fpregs.fprs);
+		save_fpu_to(&vcpu->arch.guest_fpregs);
+	load_fpu_from(&vcpu->arch.host_fpregs);
+
+	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
 }
 
@@ -1264,7 +1385,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 	mutex_lock(&vcpu->kvm->lock);
+	preempt_disable();
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
+	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
 	if (!kvm_is_ucontrol(vcpu->kvm))
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
@@ -1320,9 +1443,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 						    CPUSTAT_STOPPED);
 
 	if (test_kvm_facility(vcpu->kvm, 78))
-		atomic_set_mask(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+		atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
 	else if (test_kvm_facility(vcpu->kvm, 8))
-		atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+		atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
 
 	kvm_s390_vcpu_setup_model(vcpu);
 
@@ -1342,7 +1465,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	}
 	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
 
-	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
+	if (vcpu->kvm->arch.use_cmma) {
 		rc = kvm_s390_vcpu_setup_cmma(vcpu);
 		if (rc)
 			return rc;
@@ -1377,7 +1500,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	vcpu->arch.sie_block = &sie_page->sie_block;
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
-	vcpu->arch.host_vregs = &sie_page->vregs;
 
 	vcpu->arch.sie_block->icpua = id;
 	if (!kvm_is_ucontrol(kvm)) {
@@ -1399,6 +1521,19 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
 
+	/*
+	 * Allocate a save area for floating-point registers.  If the vector
+	 * extension is available, register contents are saved in the SIE
+	 * control block.  The allocated save area is still required in
+	 * particular places, for example, in kvm_s390_vcpu_store_status().
+	 */
+	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
+					       GFP_KERNEL);
+	if (!vcpu->arch.guest_fpregs.fprs) {
+		rc = -ENOMEM;
+		goto out_free_sie_block;
+	}
+
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
@@ -1422,24 +1557,24 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 
 void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+	atomic_or(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 	exit_sie(vcpu);
 }
 
 void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+	atomic_andnot(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 }
 
 static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
 	exit_sie(vcpu);
 }
 
 static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
 }
 
 /*
@@ -1448,7 +1583,7 @@ static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
  * return immediately. */
 void exit_sie(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
 	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
 		cpu_relax();
 }
@@ -1621,16 +1756,16 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
+	memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
-	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	save_fpu_regs();
+	load_fpu_from(&vcpu->arch.guest_fpregs);
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
+	memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
 	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
 	return 0;
 }
@@ -1672,19 +1807,19 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	if (dbg->control & KVM_GUESTDBG_ENABLE) {
 		vcpu->guest_debug = dbg->control;
 		/* enforce guest PER */
-		atomic_set_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
 
 		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
 			rc = kvm_s390_import_bp_data(vcpu, dbg);
 	} else {
-		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
 		vcpu->arch.guestdbg.last_bp = 0;
 	}
 
 	if (rc) {
 		vcpu->guest_debug = 0;
 		kvm_s390_clear_bp_data(vcpu);
-		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
 	}
 
 	return rc;
@@ -1723,18 +1858,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return rc;
 }
 
-bool kvm_s390_cmma_enabled(struct kvm *kvm)
-{
-	if (!MACHINE_IS_LPAR)
-		return false;
-	/* only enable for z10 and later */
-	if (!MACHINE_HAS_EDAT1)
-		return false;
-	if (!kvm->arch.use_cmma)
-		return false;
-	return true;
-}
-
 static bool ibs_enabled(struct kvm_vcpu *vcpu)
 {
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
@@ -1742,10 +1865,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->requests)
-		return 0;
 retry:
 	kvm_s390_vcpu_request_handled(vcpu);
+	if (!vcpu->requests)
+		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
@@ -1771,7 +1894,7 @@ retry:
 	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
 		if (!ibs_enabled(vcpu)) {
 			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
-			atomic_set_mask(CPUSTAT_IBS,
+			atomic_or(CPUSTAT_IBS,
 					&vcpu->arch.sie_block->cpuflags);
 		}
 		goto retry;
@@ -1780,7 +1903,7 @@ retry:
 	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
 		if (ibs_enabled(vcpu)) {
 			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
-			atomic_clear_mask(CPUSTAT_IBS,
+			atomic_andnot(CPUSTAT_IBS,
 					  &vcpu->arch.sie_block->cpuflags);
 		}
 		goto retry;
@@ -2193,8 +2316,21 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	 * copying in vcpu load/put. Lets update our copies before we save
 	 * it into the save area
 	 */
-	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	save_fpu_regs();
+	if (test_kvm_facility(vcpu->kvm, 129)) {
+		/*
+		 * If the vector extension is available, the vector registers
+		 * which overlaps with floating-point registers are saved in
+		 * the SIE-control block.  Hence, extract the floating-point
+		 * registers and the FPC value and store them in the
+		 * guest_fpregs structure.
+		 */
+		WARN_ON(!is_vx_task(current));	  /* XXX remove later */
+		vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
+		convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
+				 current->thread.fpu.vxrs);
+	} else
+		save_fpu_to(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);
@@ -2221,10 +2357,13 @@ int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
 
 	/*
 	 * The guest VXRS are in the host VXRs due to the lazy
-	 * copying in vcpu load/put. Let's update our copies before we save
-	 * it into the save area.
+	 * copying in vcpu load/put. We can simply call save_fpu_regs()
+	 * to save the current register state because we are in the
+	 * middle of a load/put cycle.
+	 *
+	 * Let's update our copies before we save it into the save area.
 	 */
-	save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+	save_fpu_regs();
 
 	return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
 }
@@ -2280,7 +2419,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 		__disable_ibs_on_all_vcpus(vcpu->kvm);
 	}
 
-	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 	/*
 	 * Another VCPU might have used IBS while we were offline.
 	 * Let's play safe and flush the VCPU at startup.
@@ -2306,7 +2445,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
 	kvm_s390_clear_stop_irq(vcpu);
 
-	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
@@ -2340,6 +2479,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	case KVM_CAP_S390_CSS_SUPPORT:
 		if (!vcpu->kvm->arch.css_support) {
 			vcpu->kvm->arch.css_support = 1;
+			VM_EVENT(vcpu->kvm, 3, "%s", "ENABLE: CSS support");
 			trace_kvm_s390_enable_css(vcpu->kvm);
 		}
 		r = 0;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index c5704786e473..c446aabf60d3 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -27,6 +27,13 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 #define TDB_FORMAT1		1
 #define IS_ITDB_VALID(vcpu)	((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1))
 
+extern debug_info_t *kvm_s390_dbf;
+#define KVM_EVENT(d_loglevel, d_string, d_args...)\
+do { \
+	debug_sprintf_event(kvm_s390_dbf, d_loglevel, d_string "\n", \
+	  d_args); \
+} while (0)
+
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
 do { \
 	debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \
@@ -65,6 +72,8 @@ static inline u32 kvm_s390_get_prefix(struct kvm_vcpu *vcpu)
 
 static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 {
+	VCPU_EVENT(vcpu, 3, "set prefix of cpu %03u to 0x%x", vcpu->vcpu_id,
+		   prefix);
 	vcpu->arch.sie_block->prefix = prefix >> GUEST_PREFIX_SHIFT;
 	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
@@ -217,8 +226,6 @@ void exit_sie(struct kvm_vcpu *vcpu);
 void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
 int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
-/* is cmma enabled */
-bool kvm_s390_cmma_enabled(struct kvm *kvm);
 unsigned long kvm_s390_fac_list_mask_size(void);
 extern unsigned long kvm_s390_fac_list_mask[];
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ad4242245771..4d21dc4d1a84 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -53,11 +53,14 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
 		kvm_s390_set_psw_cc(vcpu, 3);
 		return 0;
 	}
+	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val);
 	val = (val - hostclk) & ~0x3fUL;
 
 	mutex_lock(&vcpu->kvm->lock);
+	preempt_disable();
 	kvm_for_each_vcpu(i, cpup, vcpu->kvm)
 		cpup->arch.sie_block->epoch = val;
+	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
 
 	kvm_s390_set_psw_cc(vcpu, 0);
@@ -98,8 +101,6 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 	kvm_s390_set_prefix(vcpu, address);
-
-	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
 	trace_kvm_s390_handle_prefix(vcpu, 1, address);
 	return 0;
 }
@@ -129,7 +130,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+	VCPU_EVENT(vcpu, 3, "STPX: storing prefix 0x%x into 0x%llx", address, operand2);
 	trace_kvm_s390_handle_prefix(vcpu, 0, address);
 	return 0;
 }
@@ -155,7 +156,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", ga);
+	VCPU_EVENT(vcpu, 3, "STAP: storing cpu address (%u) to 0x%llx", vcpu_id, ga);
 	trace_kvm_s390_handle_stap(vcpu, ga);
 	return 0;
 }
@@ -167,6 +168,7 @@ static int __skey_check_enable(struct kvm_vcpu *vcpu)
 		return rc;
 
 	rc = s390_enable_skey();
+	VCPU_EVENT(vcpu, 3, "%s", "enabling storage keys for guest");
 	trace_kvm_s390_skey_related_inst(vcpu);
 	vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
 	return rc;
@@ -370,7 +372,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 			    &fac, sizeof(fac));
 	if (rc)
 		return rc;
-	VCPU_EVENT(vcpu, 5, "store facility list value %x", fac);
+	VCPU_EVENT(vcpu, 3, "STFL: store facility list 0x%x", fac);
 	trace_kvm_s390_handle_stfl(vcpu, fac);
 	return 0;
 }
@@ -468,7 +470,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
+	VCPU_EVENT(vcpu, 3, "STIDP: store cpu id 0x%llx", stidp_data);
 	return 0;
 }
 
@@ -521,7 +523,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	ar_t ar;
 
 	vcpu->stat.instruction_stsi++;
-	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
+	VCPU_EVENT(vcpu, 3, "STSI: fc: %u sel1: %u sel2: %u", fc, sel1, sel2);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -758,10 +760,10 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 	struct gmap *gmap;
 	int i;
 
-	VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries);
+	VCPU_EVENT(vcpu, 4, "ESSA: release %d pages", entries);
 	gmap = vcpu->arch.gmap;
 	vcpu->stat.instruction_essa++;
-	if (!kvm_s390_cmma_enabled(vcpu->kvm))
+	if (!vcpu->kvm->arch.use_cmma)
 		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
@@ -829,7 +831,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
 	if (ga & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "LCTL: r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga);
 
 	nr_regs = ((reg3 - reg1) & 0xf) + 1;
@@ -868,7 +870,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
 	if (ga & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "stctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "STCTL r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga);
 
 	reg = reg1;
@@ -902,7 +904,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 	if (ga & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "LCTLG: r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga);
 
 	nr_regs = ((reg3 - reg1) & 0xf) + 1;
@@ -940,7 +942,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
 	if (ga & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	VCPU_EVENT(vcpu, 4, "STCTG r1:%d, r3:%d, addr: 0x%llx", reg1, reg3, ga);
 	trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga);
 
 	reg = reg1;
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 72e58bd2bee7..da690b69f9fe 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -205,9 +205,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
 		return SIGP_CC_STATUS_STORED;
-	} else if (rc == 0) {
-		VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x",
-			   dst_vcpu->vcpu_id, irq.u.prefix.address);
 	}
 
 	return rc;
@@ -371,7 +368,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 	return rc;
 }
 
-static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
+static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code,
+					   u16 cpu_addr)
 {
 	if (!vcpu->kvm->arch.user_sigp)
 		return 0;
@@ -414,9 +412,8 @@ static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
 	default:
 		vcpu->stat.instruction_sigp_unknown++;
 	}
-
-	VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space",
-		   order_code);
+	VCPU_EVENT(vcpu, 3, "SIGP: order %u for CPU %d handled in userspace",
+		   order_code, cpu_addr);
 
 	return 1;
 }
@@ -435,7 +432,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
 	order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
-	if (handle_sigp_order_in_user_space(vcpu, order_code))
+	if (handle_sigp_order_in_user_space(vcpu, order_code, cpu_addr))
 		return -EOPNOTSUPP;
 
 	if (r1 % 2)
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 3208d33a48cb..cc1d6c68356f 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -105,11 +105,22 @@ TRACE_EVENT(kvm_s390_vcpu_start_stop,
 	{KVM_S390_PROGRAM_INT, "program interrupt"},			\
 	{KVM_S390_SIGP_SET_PREFIX, "sigp set prefix"},			\
 	{KVM_S390_RESTART, "sigp restart"},				\
+	{KVM_S390_INT_PFAULT_INIT, "pfault init"},			\
+	{KVM_S390_INT_PFAULT_DONE, "pfault done"},			\
+	{KVM_S390_MCHK, "machine check"},				\
+	{KVM_S390_INT_CLOCK_COMP, "clock comparator"},			\
+	{KVM_S390_INT_CPU_TIMER, "cpu timer"},				\
 	{KVM_S390_INT_VIRTIO, "virtio interrupt"},			\
 	{KVM_S390_INT_SERVICE, "sclp interrupt"},			\
 	{KVM_S390_INT_EMERGENCY, "sigp emergency"},			\
 	{KVM_S390_INT_EXTERNAL_CALL, "sigp ext call"}
 
+#define get_irq_name(__type) \
+	(__type > KVM_S390_INT_IO_MAX ? \
+	__print_symbolic(__type, kvm_s390_int_type) : \
+		(__type & KVM_S390_INT_IO_AI_MASK ? \
+		 "adapter I/O interrupt" : "subchannel I/O interrupt"))
+
 TRACE_EVENT(kvm_s390_inject_vm,
 	    TP_PROTO(__u64 type, __u32 parm, __u64 parm64, int who),
 	    TP_ARGS(type, parm, parm64, who),
@@ -131,22 +142,19 @@ TRACE_EVENT(kvm_s390_inject_vm,
 	    TP_printk("inject%s: type:%x (%s) parm:%x parm64:%llx",
 		      (__entry->who == 1) ? " (from kernel)" :
 		      (__entry->who == 2) ? " (from user)" : "",
-		      __entry->inttype,
-		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->inttype, get_irq_name(__entry->inttype),
 		      __entry->parm, __entry->parm64)
 	);
 
 TRACE_EVENT(kvm_s390_inject_vcpu,
-	    TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64, \
-		     int who),
-	    TP_ARGS(id, type, parm, parm64, who),
+	    TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64),
+	    TP_ARGS(id, type, parm, parm64),
 
 	    TP_STRUCT__entry(
 		    __field(int, id)
 		    __field(__u32, inttype)
 		    __field(__u32, parm)
 		    __field(__u64, parm64)
-		    __field(int, who)
 		    ),
 
 	    TP_fast_assign(
@@ -154,15 +162,12 @@ TRACE_EVENT(kvm_s390_inject_vcpu,
 		    __entry->inttype = type & 0x00000000ffffffff;
 		    __entry->parm = parm;
 		    __entry->parm64 = parm64;
-		    __entry->who = who;
 		    ),
 
-	    TP_printk("inject%s (vcpu %d): type:%x (%s) parm:%x parm64:%llx",
-		      (__entry->who == 1) ? " (from kernel)" :
-		      (__entry->who == 2) ? " (from user)" : "",
+	    TP_printk("inject (vcpu %d): type:%x (%s) parm:%x parm64:%llx",
 		      __entry->id, __entry->inttype,
-		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
-		      __entry->parm, __entry->parm64)
+		      get_irq_name(__entry->inttype), __entry->parm,
+		      __entry->parm64)
 	);
 
 /*
@@ -189,8 +194,8 @@ TRACE_EVENT(kvm_s390_deliver_interrupt,
 	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
 		      "data:%08llx %016llx",
 		      __entry->id, __entry->inttype,
-		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
-		      __entry->data0, __entry->data1)
+		      get_irq_name(__entry->inttype), __entry->data0,
+		      __entry->data1)
 	);
 
 /*
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 16dc42d83f93..246a7eb4b680 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -26,6 +26,7 @@ void __delay(unsigned long loops)
          */
 	asm volatile("0: brct %0,0b" : : "d" ((loops/2) + 1));
 }
+EXPORT_SYMBOL(__delay);
 
 static void __udelay_disabled(unsigned long long usecs)
 {
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index 4614d415bb58..ae4de559e3a0 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -15,7 +15,7 @@
 #include <asm/mmu_context.h>
 #include <asm/facility.h>
 
-static struct static_key have_mvcos = STATIC_KEY_INIT_FALSE;
+static DEFINE_STATIC_KEY_FALSE(have_mvcos);
 
 static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr,
 						 unsigned long size)
@@ -104,7 +104,7 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
 
 unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (static_key_false(&have_mvcos))
+	if (static_branch_likely(&have_mvcos))
 		return copy_from_user_mvcos(to, from, n);
 	return copy_from_user_mvcp(to, from, n);
 }
@@ -177,7 +177,7 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x,
 
 unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (static_key_false(&have_mvcos))
+	if (static_branch_likely(&have_mvcos))
 		return copy_to_user_mvcos(to, from, n);
 	return copy_to_user_mvcs(to, from, n);
 }
@@ -240,7 +240,7 @@ static inline unsigned long copy_in_user_mvc(void __user *to, const void __user
 
 unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
-	if (static_key_false(&have_mvcos))
+	if (static_branch_likely(&have_mvcos))
 		return copy_in_user_mvcos(to, from, n);
 	return copy_in_user_mvc(to, from, n);
 }
@@ -312,7 +312,7 @@ static inline unsigned long clear_user_xc(void __user *to, unsigned long size)
 
 unsigned long __clear_user(void __user *to, unsigned long size)
 {
-	if (static_key_false(&have_mvcos))
+	if (static_branch_likely(&have_mvcos))
 			return clear_user_mvcos(to, size);
 	return clear_user_xc(to, size);
 }
@@ -370,23 +370,10 @@ long __strncpy_from_user(char *dst, const char __user *src, long size)
 }
 EXPORT_SYMBOL(__strncpy_from_user);
 
-/*
- * The "old" uaccess variant without mvcos can be enforced with the
- * uaccess_primary kernel parameter. This is mainly for debugging purposes.
- */
-static int uaccess_primary __initdata;
-
-static int __init parse_uaccess_pt(char *__unused)
-{
-	uaccess_primary = 1;
-	return 0;
-}
-early_param("uaccess_primary", parse_uaccess_pt);
-
 static int __init uaccess_init(void)
 {
-	if (!uaccess_primary && test_facility(27))
-		static_key_slow_inc(&have_mvcos);
+	if (test_facility(27))
+		static_branch_enable(&have_mvcos);
 	return 0;
 }
 early_initcall(uaccess_init);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 4c8f5d7f9c23..f985856a538b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -646,7 +646,7 @@ static void pfault_interrupt(struct ext_code ext_code,
 		return;
 	inc_irq_stat(IRQEXT_PFL);
 	/* Get the token (= pid of the affected task). */
-	pid = sizeof(void *) == 4 ? param32 : param64;
+	pid = param64;
 	rcu_read_lock();
 	tsk = find_task_by_pid_ns(pid, &init_pid_ns);
 	if (tsk)
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 1eb41bb3010c..12bbf0e8478f 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -30,6 +30,9 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	do {
 		pte = *ptep;
 		barrier();
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_protnone(pte))
+			return 0;
 		if ((pte_val(pte) & mask) != 0)
 			return 0;
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
@@ -125,6 +128,13 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_protnone(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmdp, pmd, addr, next,
 					  write, pages, nr))
 				return 0;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 76e873748b56..2963b563621c 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -27,6 +27,7 @@
 #include <linux/initrd.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
+#include <linux/memblock.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -138,7 +139,7 @@ void __init mem_init(void)
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
 	atomic_set(&init_mm.context.attach_count, 1);
 
-        max_mapnr = max_low_pfn;
+	set_max_mapnr(max_low_pfn);
         high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 	/* Setup guest page hinting */
@@ -170,37 +171,36 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size)
 {
-	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
+	unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS);
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long size_pages = PFN_DOWN(size);
-	struct zone *zone;
-	int rc;
+	unsigned long nr_pages;
+	int rc, zone_enum;
 
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;
-	for_each_zone(zone) {
-		if (zone_idx(zone) != ZONE_MOVABLE) {
-			/* Add range within existing zone limits */
-			zone_start_pfn = zone->zone_start_pfn;
-			zone_end_pfn = zone->zone_start_pfn +
-				       zone->spanned_pages;
+
+	while (size_pages > 0) {
+		if (start_pfn < dma_end_pfn) {
+			nr_pages = (start_pfn + size_pages > dma_end_pfn) ?
+				   dma_end_pfn - start_pfn : size_pages;
+			zone_enum = ZONE_DMA;
+		} else if (start_pfn < normal_end_pfn) {
+			nr_pages = (start_pfn + size_pages > normal_end_pfn) ?
+				   normal_end_pfn - start_pfn : size_pages;
+			zone_enum = ZONE_NORMAL;
 		} else {
-			/* Add remaining range to ZONE_MOVABLE */
-			zone_start_pfn = start_pfn;
-			zone_end_pfn = start_pfn + size_pages;
+			nr_pages = size_pages;
+			zone_enum = ZONE_MOVABLE;
 		}
-		if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
-			continue;
-		nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
-			   zone_end_pfn - start_pfn : size_pages;
-		rc = __add_pages(nid, zone, start_pfn, nr_pages);
+		rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum,
+				 start_pfn, size_pages);
 		if (rc)
 			break;
 		start_pfn += nr_pages;
 		size_pages -= nr_pages;
-		if (!size_pages)
-			break;
 	}
 	if (rc)
 		vmem_remove_mapping(start, size);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 33082d0d101b..54ef3bc01b43 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -10,11 +10,7 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/smp.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
-#include <linux/quicklist.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/swapops.h>
@@ -28,14 +24,9 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 
-#define ALLOC_ORDER	2
-#define FRAG_MASK	0x03
-
-int HPAGE_SHIFT;
-
 unsigned long *crst_table_alloc(struct mm_struct *mm)
 {
-	struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
+	struct page *page = alloc_pages(GFP_KERNEL, 2);
 
 	if (!page)
 		return NULL;
@@ -44,7 +35,7 @@ unsigned long *crst_table_alloc(struct mm_struct *mm)
 
 void crst_table_free(struct mm_struct *mm, unsigned long *table)
 {
-	free_pages((unsigned long) table, ALLOC_ORDER);
+	free_pages((unsigned long) table, 2);
 }
 
 static void __crst_table_upgrade(void *arg)
@@ -178,7 +169,7 @@ struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
 	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
 	spin_lock_init(&gmap->guest_table_lock);
 	gmap->mm = mm;
-	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL, 2);
 	if (!page)
 		goto out_free;
 	page->index = 0;
@@ -249,7 +240,7 @@ void gmap_free(struct gmap *gmap)
 
 	/* Free all segment & region tables. */
 	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
-		__free_pages(page, ALLOC_ORDER);
+		__free_pages(page, 2);
 	gmap_radix_tree_free(&gmap->guest_to_host);
 	gmap_radix_tree_free(&gmap->host_to_guest);
 	down_write(&gmap->mm->mmap_sem);
@@ -289,7 +280,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 	unsigned long *new;
 
 	/* since we dont free the gmap table until gmap_free we can unlock */
-	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL, 2);
 	if (!page)
 		return -ENOMEM;
 	new = (unsigned long *) page_to_phys(page);
@@ -304,7 +295,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 	}
 	spin_unlock(&gmap->mm->page_table_lock);
 	if (page)
-		__free_pages(page, ALLOC_ORDER);
+		__free_pages(page, 2);
 	return 0;
 }
 
@@ -797,40 +788,6 @@ void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte)
 }
 EXPORT_SYMBOL_GPL(gmap_do_ipte_notify);
 
-static inline int page_table_with_pgste(struct page *page)
-{
-	return atomic_read(&page->_mapcount) == 0;
-}
-
-static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
-{
-	struct page *page;
-	unsigned long *table;
-
-	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
-	if (!page)
-		return NULL;
-	if (!pgtable_page_ctor(page)) {
-		__free_page(page);
-		return NULL;
-	}
-	atomic_set(&page->_mapcount, 0);
-	table = (unsigned long *) page_to_phys(page);
-	clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
-	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
-	return table;
-}
-
-static inline void page_table_free_pgste(unsigned long *table)
-{
-	struct page *page;
-
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	pgtable_page_dtor(page);
-	atomic_set(&page->_mapcount, -1);
-	__free_page(page);
-}
-
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq)
 {
@@ -959,20 +916,6 @@ __initcall(page_table_register_sysctl);
 
 #else /* CONFIG_PGSTE */
 
-static inline int page_table_with_pgste(struct page *page)
-{
-	return 0;
-}
-
-static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
-{
-	return NULL;
-}
-
-static inline void page_table_free_pgste(unsigned long *table)
-{
-}
-
 static inline void gmap_unlink(struct mm_struct *mm, unsigned long *table,
 			unsigned long vmaddr)
 {
@@ -996,44 +939,55 @@ static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
  */
 unsigned long *page_table_alloc(struct mm_struct *mm)
 {
-	unsigned long *uninitialized_var(table);
-	struct page *uninitialized_var(page);
+	unsigned long *table;
+	struct page *page;
 	unsigned int mask, bit;
 
-	if (mm_alloc_pgste(mm))
-		return page_table_alloc_pgste(mm);
-	/* Allocate fragments of a 4K page as 1K/2K page table */
-	spin_lock_bh(&mm->context.list_lock);
-	mask = FRAG_MASK;
-	if (!list_empty(&mm->context.pgtable_list)) {
-		page = list_first_entry(&mm->context.pgtable_list,
-					struct page, lru);
-		table = (unsigned long *) page_to_phys(page);
-		mask = atomic_read(&page->_mapcount);
-		mask = mask | (mask >> 4);
-	}
-	if ((mask & FRAG_MASK) == FRAG_MASK) {
-		spin_unlock_bh(&mm->context.list_lock);
-		page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
-		if (!page)
-			return NULL;
-		if (!pgtable_page_ctor(page)) {
-			__free_page(page);
-			return NULL;
+	/* Try to get a fragment of a 4K page as a 2K page table */
+	if (!mm_alloc_pgste(mm)) {
+		table = NULL;
+		spin_lock_bh(&mm->context.list_lock);
+		if (!list_empty(&mm->context.pgtable_list)) {
+			page = list_first_entry(&mm->context.pgtable_list,
+						struct page, lru);
+			mask = atomic_read(&page->_mapcount);
+			mask = (mask | (mask >> 4)) & 3;
+			if (mask != 3) {
+				table = (unsigned long *) page_to_phys(page);
+				bit = mask & 1;		/* =1 -> second 2K */
+				if (bit)
+					table += PTRS_PER_PTE;
+				atomic_xor_bits(&page->_mapcount, 1U << bit);
+				list_del(&page->lru);
+			}
 		}
+		spin_unlock_bh(&mm->context.list_lock);
+		if (table)
+			return table;
+	}
+	/* Allocate a fresh page */
+	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	if (!page)
+		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	/* Initialize page table */
+	table = (unsigned long *) page_to_phys(page);
+	if (mm_alloc_pgste(mm)) {
+		/* Return 4K page table with PGSTEs */
+		atomic_set(&page->_mapcount, 3);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+		clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	} else {
+		/* Return the first 2K fragment of the page */
 		atomic_set(&page->_mapcount, 1);
-		table = (unsigned long *) page_to_phys(page);
 		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
 		spin_lock_bh(&mm->context.list_lock);
 		list_add(&page->lru, &mm->context.pgtable_list);
-	} else {
-		for (bit = 1; mask & bit; bit <<= 1)
-			table += PTRS_PER_PTE;
-		mask = atomic_xor_bits(&page->_mapcount, bit);
-		if ((mask & FRAG_MASK) == FRAG_MASK)
-			list_del(&page->lru);
+		spin_unlock_bh(&mm->context.list_lock);
 	}
-	spin_unlock_bh(&mm->context.list_lock);
 	return table;
 }
 
@@ -1043,37 +997,23 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	unsigned int bit, mask;
 
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	if (page_table_with_pgste(page))
-		return page_table_free_pgste(table);
-	/* Free 1K/2K page table fragment of a 4K page */
-	bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
-	spin_lock_bh(&mm->context.list_lock);
-	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
-		list_del(&page->lru);
-	mask = atomic_xor_bits(&page->_mapcount, bit);
-	if (mask & FRAG_MASK)
-		list_add(&page->lru, &mm->context.pgtable_list);
-	spin_unlock_bh(&mm->context.list_lock);
-	if (mask == 0) {
-		pgtable_page_dtor(page);
-		atomic_set(&page->_mapcount, -1);
-		__free_page(page);
+	if (!mm_alloc_pgste(mm)) {
+		/* Free 2K page table fragment of a 4K page */
+		bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
+		spin_lock_bh(&mm->context.list_lock);
+		mask = atomic_xor_bits(&page->_mapcount, 1U << bit);
+		if (mask & 3)
+			list_add(&page->lru, &mm->context.pgtable_list);
+		else
+			list_del(&page->lru);
+		spin_unlock_bh(&mm->context.list_lock);
+		if (mask != 0)
+			return;
 	}
-}
-
-static void __page_table_free_rcu(void *table, unsigned bit)
-{
-	struct page *page;
 
-	if (bit == FRAG_MASK)
-		return page_table_free_pgste(table);
-	/* Free 1K/2K page table fragment of a 4K page */
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	if (atomic_xor_bits(&page->_mapcount, bit) == 0) {
-		pgtable_page_dtor(page);
-		atomic_set(&page->_mapcount, -1);
-		__free_page(page);
-	}
+	pgtable_page_dtor(page);
+	atomic_set(&page->_mapcount, -1);
+	__free_page(page);
 }
 
 void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
@@ -1085,34 +1025,45 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
 
 	mm = tlb->mm;
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	if (page_table_with_pgste(page)) {
+	if (mm_alloc_pgste(mm)) {
 		gmap_unlink(mm, table, vmaddr);
-		table = (unsigned long *) (__pa(table) | FRAG_MASK);
+		table = (unsigned long *) (__pa(table) | 3);
 		tlb_remove_table(tlb, table);
 		return;
 	}
-	bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)));
+	bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
 	spin_lock_bh(&mm->context.list_lock);
-	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
-		list_del(&page->lru);
-	mask = atomic_xor_bits(&page->_mapcount, bit | (bit << 4));
-	if (mask & FRAG_MASK)
+	mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);
+	if (mask & 3)
 		list_add_tail(&page->lru, &mm->context.pgtable_list);
+	else
+		list_del(&page->lru);
 	spin_unlock_bh(&mm->context.list_lock);
-	table = (unsigned long *) (__pa(table) | (bit << 4));
+	table = (unsigned long *) (__pa(table) | (1U << bit));
 	tlb_remove_table(tlb, table);
 }
 
 static void __tlb_remove_table(void *_table)
 {
-	const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK;
-	void *table = (void *)((unsigned long) _table & ~mask);
-	unsigned type = (unsigned long) _table & mask;
-
-	if (type)
-		__page_table_free_rcu(table, type);
-	else
-		free_pages((unsigned long) table, ALLOC_ORDER);
+	unsigned int mask = (unsigned long) _table & 3;
+	void *table = (void *)((unsigned long) _table ^ mask);
+	struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+
+	switch (mask) {
+	case 0:		/* pmd or pud */
+		free_pages((unsigned long) table, 2);
+		break;
+	case 1:		/* lower 2K of a 4K page table */
+	case 2:		/* higher 2K of a 4K page table */
+		if (atomic_xor_bits(&page->_mapcount, mask << 4) != 0)
+			break;
+		/* fallthrough */
+	case 3:		/* 4K page table with pgstes */
+		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
+		__free_page(page);
+		break;
+	}
 }
 
 static void tlb_remove_table_smp_sync(void *arg)
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index f6498eec9ee1..f010c93a88b1 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -36,6 +36,8 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |   BPF stack   |     |
  *	      |		      |     |
  *	      +---------------+     |
+ *	      | 8 byte skbp   |     |
+ * R15+170 -> +---------------+     |
  *	      | 8 byte hlen   |     |
  * R15+168 -> +---------------+     |
  *	      | 4 byte align  |     |
@@ -51,11 +53,12 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * We get 160 bytes stack space from calling function, but only use
  * 12 * 8 byte for old backchain, r15..r6, and tail_call_cnt.
  */
-#define STK_SPACE	(MAX_BPF_STACK + 8 + 4 + 4 + 160)
+#define STK_SPACE	(MAX_BPF_STACK + 8 + 8 + 4 + 4 + 160)
 #define STK_160_UNUSED	(160 - 12 * 8)
 #define STK_OFF		(STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
+#define STK_OFF_SKBP	170	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index fee782acc2ee..eeda051442c3 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -45,7 +45,7 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };
 
-#define BPF_SIZE_MAX	4096	/* Max size for program */
+#define BPF_SIZE_MAX	0x7ffff	/* Max size for program (20 bit signed displ) */
 
 #define SEEN_SKB	1	/* skb access */
 #define SEEN_MEM	2	/* use mem[] for temporary storage */
@@ -53,6 +53,7 @@ struct bpf_jit {
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
 #define SEEN_TAIL_CALL	32	/* code uses tail calls */
+#define SEEN_SKB_CHANGE	64	/* code changes skb data */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -203,19 +204,11 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	_EMIT6(op1 | __disp, op2);				\
 })
 
-#define EMIT6_DISP(op1, op2, b1, b2, b3, disp)			\
-({								\
-	_EMIT6_DISP(op1 | reg(b1, b2) << 16 |			\
-		    reg_high(b3) << 8, op2, disp);		\
-	REG_SET_SEEN(b1);					\
-	REG_SET_SEEN(b2);					\
-	REG_SET_SEEN(b3);					\
-})
-
 #define _EMIT6_DISP_LH(op1, op2, disp)				\
 ({								\
-	unsigned int __disp_h = ((u32)disp) & 0xff000;		\
-	unsigned int __disp_l = ((u32)disp) & 0x00fff;		\
+	u32 _disp = (u32) disp;					\
+	unsigned int __disp_h = _disp & 0xff000;		\
+	unsigned int __disp_l = _disp & 0x00fff;		\
 	_EMIT6(op1 | __disp_l, op2 | __disp_h >> 4);		\
 })
 
@@ -390,12 +383,32 @@ static void save_restore_regs(struct bpf_jit *jit, int op)
 }
 
 /*
+ * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
+ * we store the SKB header length on the stack and the SKB data
+ * pointer in REG_SKB_DATA.
+ */
+static void emit_load_skb_data_hlen(struct bpf_jit *jit)
+{
+	/* Header length: llgf %w1,<len>(%b1) */
+	EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
+		      offsetof(struct sk_buff, len));
+	/* s %w1,<data_len>(%b1) */
+	EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
+		   offsetof(struct sk_buff, data_len));
+	/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
+	EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
+	/* lg %skb_data,data_off(%b1) */
+	EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
+		      BPF_REG_1, offsetof(struct sk_buff, data));
+}
+
+/*
  * Emit function prologue
  *
  * Save registers and create stack frame if necessary.
  * See stack frame layout desription in "bpf_jit.h"!
  */
-static void bpf_jit_prologue(struct bpf_jit *jit)
+static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
 {
 	if (jit->seen & SEEN_TAIL_CALL) {
 		/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
@@ -429,32 +442,21 @@ static void bpf_jit_prologue(struct bpf_jit *jit)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	/*
-	 * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
-	 * we store the SKB header length on the stack and the SKB data
-	 * pointer in REG_SKB_DATA.
-	 */
-	if (jit->seen & SEEN_SKB) {
-		/* Header length: llgf %w1,<len>(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
-			      offsetof(struct sk_buff, len));
-		/* s %w1,<data_len>(%b1) */
-		EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
-			   offsetof(struct sk_buff, data_len));
-		/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
+	if (jit->seen & SEEN_SKB)
+		emit_load_skb_data_hlen(jit);
+	if (jit->seen & SEEN_SKB_CHANGE)
+		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
-			      STK_OFF_HLEN);
-		/* lg %skb_data,data_off(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-			      BPF_REG_1, offsetof(struct sk_buff, data));
+			      STK_OFF_SKBP);
+	/* Clear A (%b0) and X (%b7) registers for converted BPF programs */
+	if (is_classic) {
+		if (REG_SEEN(BPF_REG_A))
+			/* lghi %ba,0 */
+			EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
+		if (REG_SEEN(BPF_REG_X))
+			/* lghi %bx,0 */
+			EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
 	}
-	/* BPF compatibility: clear A (%b7) and X (%b8) registers */
-	if (REG_SEEN(BPF_REG_7))
-		/* lghi %b7,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_7, 0);
-	if (REG_SEEN(BPF_REG_8))
-		/* lghi %b8,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_8, 0);
 }
 
 /*
@@ -976,12 +978,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		REG_SET_SEEN(BPF_REG_5);
 		jit->seen |= SEEN_FUNC;
 		/* lg %w1,<d(imm)>(%l) */
-		EMIT6_DISP(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
-			   EMIT_CONST_U64(func));
+		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
+			      EMIT_CONST_U64(func));
 		/* basr %r14,%w1 */
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
+		if (bpf_helper_changes_skb_data((void *)func)) {
+			jit->seen |= SEEN_SKB_CHANGE;
+			/* lg %b1,ST_OFF_SKBP(%r15) */
+			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
+				      REG_15, STK_OFF_SKBP);
+			emit_load_skb_data_hlen(jit);
+		}
 		break;
 	}
 	case BPF_JMP | BPF_CALL | BPF_X:
@@ -1023,7 +1032,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 				      MAX_TAIL_CALL_CNT, 0, 0x2);
 
 		/*
-		 * prog = array->prog[index];
+		 * prog = array->ptrs[index];
 		 * if (prog == NULL)
 		 *         goto out;
 		 */
@@ -1032,7 +1041,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
 		/* lg %r1,prog(%b2,%r1) */
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
-			      REG_1, offsetof(struct bpf_array, prog));
+			      REG_1, offsetof(struct bpf_array, ptrs));
 		/* clgij %r1,0,0x8,label0 */
 		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8);
 
@@ -1236,7 +1245,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 	jit->lit = jit->lit_start;
 	jit->prg = 0;
 
-	bpf_jit_prologue(jit);
+	bpf_jit_prologue(jit, bpf_prog_was_classic(fp));
 	for (i = 0; i < fp->len; i += insn_count) {
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
diff --git a/arch/s390/numa/Makefile b/arch/s390/numa/Makefile
new file mode 100644
index 000000000000..f94ecaffa71b
--- /dev/null
+++ b/arch/s390/numa/Makefile
@@ -0,0 +1,3 @@
+obj-y			+= numa.o
+obj-y			+= toptree.o
+obj-$(CONFIG_NUMA_EMU)	+= mode_emu.o
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
new file mode 100644
index 000000000000..7de4e2f780d7
--- /dev/null
+++ b/arch/s390/numa/mode_emu.c
@@ -0,0 +1,530 @@
+/*
+ * NUMA support for s390
+ *
+ * NUMA emulation (aka fake NUMA) distributes the available memory to nodes
+ * without using real topology information about the physical memory of the
+ * machine.
+ *
+ * It distributes the available CPUs to nodes while respecting the original
+ * machine topology information. This is done by trying to avoid to separate
+ * CPUs which reside on the same book or even on the same MC.
+ *
+ * Because the current Linux scheduler code requires a stable cpu to node
+ * mapping, cores are pinned to nodes when the first CPU thread is set online.
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#define KMSG_COMPONENT "numa_emu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/cpumask.h>
+#include <linux/memblock.h>
+#include <linux/node.h>
+#include <linux/memory.h>
+#include <linux/slab.h>
+#include <asm/smp.h>
+#include <asm/topology.h>
+#include "numa_mode.h"
+#include "toptree.h"
+
+/* Distances between the different system components */
+#define DIST_EMPTY	0
+#define DIST_CORE	1
+#define DIST_MC		2
+#define DIST_BOOK	3
+#define DIST_MAX	4
+
+/* Node distance reported to common code */
+#define EMU_NODE_DIST	10
+
+/* Node ID for free (not yet pinned) cores */
+#define NODE_ID_FREE	-1
+
+/* Different levels of toptree */
+enum toptree_level {CORE, MC, BOOK, NODE, TOPOLOGY};
+
+/* The two toptree IDs */
+enum {TOPTREE_ID_PHYS, TOPTREE_ID_NUMA};
+
+/* Number of NUMA nodes */
+static int emu_nodes = 1;
+/* NUMA stripe size */
+static unsigned long emu_size;
+
+/*
+ * Node to core pinning information updates are protected by
+ * "sched_domains_mutex".
+ */
+static struct {
+	s32 to_node_id[CONFIG_NR_CPUS];	/* Pinned core to node mapping */
+	int total;			/* Total number of pinned cores */
+	int per_node_target;		/* Cores per node without extra cores */
+	int per_node[MAX_NUMNODES];	/* Number of cores pinned to node */
+} *emu_cores;
+
+/*
+ * Pin a core to a node
+ */
+static void pin_core_to_node(int core_id, int node_id)
+{
+	if (emu_cores->to_node_id[core_id] == NODE_ID_FREE) {
+		emu_cores->per_node[node_id]++;
+		emu_cores->to_node_id[core_id] = node_id;
+		emu_cores->total++;
+	} else {
+		WARN_ON(emu_cores->to_node_id[core_id] != node_id);
+	}
+}
+
+/*
+ * Number of pinned cores of a node
+ */
+static int cores_pinned(struct toptree *node)
+{
+	return emu_cores->per_node[node->id];
+}
+
+/*
+ * ID of the node where the core is pinned (or NODE_ID_FREE)
+ */
+static int core_pinned_to_node_id(struct toptree *core)
+{
+	return emu_cores->to_node_id[core->id];
+}
+
+/*
+ * Number of cores in the tree that are not yet pinned
+ */
+static int cores_free(struct toptree *tree)
+{
+	struct toptree *core;
+	int count = 0;
+
+	toptree_for_each(core, tree, CORE) {
+		if (core_pinned_to_node_id(core) == NODE_ID_FREE)
+			count++;
+	}
+	return count;
+}
+
+/*
+ * Return node of core
+ */
+static struct toptree *core_node(struct toptree *core)
+{
+	return core->parent->parent->parent;
+}
+
+/*
+ * Return book of core
+ */
+static struct toptree *core_book(struct toptree *core)
+{
+	return core->parent->parent;
+}
+
+/*
+ * Return mc of core
+ */
+static struct toptree *core_mc(struct toptree *core)
+{
+	return core->parent;
+}
+
+/*
+ * Distance between two cores
+ */
+static int dist_core_to_core(struct toptree *core1, struct toptree *core2)
+{
+	if (core_book(core1)->id != core_book(core2)->id)
+		return DIST_BOOK;
+	if (core_mc(core1)->id != core_mc(core2)->id)
+		return DIST_MC;
+	/* Same core or sibling on same MC */
+	return DIST_CORE;
+}
+
+/*
+ * Distance of a node to a core
+ */
+static int dist_node_to_core(struct toptree *node, struct toptree *core)
+{
+	struct toptree *core_node;
+	int dist_min = DIST_MAX;
+
+	toptree_for_each(core_node, node, CORE)
+		dist_min = min(dist_min, dist_core_to_core(core_node, core));
+	return dist_min == DIST_MAX ? DIST_EMPTY : dist_min;
+}
+
+/*
+ * Unify will delete empty nodes, therefore recreate nodes.
+ */
+static void toptree_unify_tree(struct toptree *tree)
+{
+	int nid;
+
+	toptree_unify(tree);
+	for (nid = 0; nid < emu_nodes; nid++)
+		toptree_get_child(tree, nid);
+}
+
+/*
+ * Find the best/nearest node for a given core and ensure that no node
+ * gets more than "emu_cores->per_node_target + extra" cores.
+ */
+static struct toptree *node_for_core(struct toptree *numa, struct toptree *core,
+				     int extra)
+{
+	struct toptree *node, *node_best = NULL;
+	int dist_cur, dist_best, cores_target;
+
+	cores_target = emu_cores->per_node_target + extra;
+	dist_best = DIST_MAX;
+	node_best = NULL;
+	toptree_for_each(node, numa, NODE) {
+		/* Already pinned cores must use their nodes */
+		if (core_pinned_to_node_id(core) == node->id) {
+			node_best = node;
+			break;
+		}
+		/* Skip nodes that already have enough cores */
+		if (cores_pinned(node) >= cores_target)
+			continue;
+		dist_cur = dist_node_to_core(node, core);
+		if (dist_cur < dist_best) {
+			dist_best = dist_cur;
+			node_best = node;
+		}
+	}
+	return node_best;
+}
+
+/*
+ * Find the best node for each core with respect to "extra" core count
+ */
+static void toptree_to_numa_single(struct toptree *numa, struct toptree *phys,
+				   int extra)
+{
+	struct toptree *node, *core, *tmp;
+
+	toptree_for_each_safe(core, tmp, phys, CORE) {
+		node = node_for_core(numa, core, extra);
+		if (!node)
+			return;
+		toptree_move(core, node);
+		pin_core_to_node(core->id, node->id);
+	}
+}
+
+/*
+ * Move structures of given level to specified NUMA node
+ */
+static void move_level_to_numa_node(struct toptree *node, struct toptree *phys,
+				    enum toptree_level level, bool perfect)
+{
+	int cores_free, cores_target = emu_cores->per_node_target;
+	struct toptree *cur, *tmp;
+
+	toptree_for_each_safe(cur, tmp, phys, level) {
+		cores_free = cores_target - toptree_count(node, CORE);
+		if (perfect) {
+			if (cores_free == toptree_count(cur, CORE))
+				toptree_move(cur, node);
+		} else {
+			if (cores_free >= toptree_count(cur, CORE))
+				toptree_move(cur, node);
+		}
+	}
+}
+
+/*
+ * Move structures of a given level to NUMA nodes. If "perfect" is specified
+ * move only perfectly fitting structures. Otherwise move also smaller
+ * than needed structures.
+ */
+static void move_level_to_numa(struct toptree *numa, struct toptree *phys,
+			       enum toptree_level level, bool perfect)
+{
+	struct toptree *node;
+
+	toptree_for_each(node, numa, NODE)
+		move_level_to_numa_node(node, phys, level, perfect);
+}
+
+/*
+ * For the first run try to move the big structures
+ */
+static void toptree_to_numa_first(struct toptree *numa, struct toptree *phys)
+{
+	struct toptree *core;
+
+	/* Always try to move perfectly fitting structures first */
+	move_level_to_numa(numa, phys, BOOK, true);
+	move_level_to_numa(numa, phys, BOOK, false);
+	move_level_to_numa(numa, phys, MC, true);
+	move_level_to_numa(numa, phys, MC, false);
+	/* Now pin all the moved cores */
+	toptree_for_each(core, numa, CORE)
+		pin_core_to_node(core->id, core_node(core)->id);
+}
+
+/*
+ * Allocate new topology and create required nodes
+ */
+static struct toptree *toptree_new(int id, int nodes)
+{
+	struct toptree *tree;
+	int nid;
+
+	tree = toptree_alloc(TOPOLOGY, id);
+	if (!tree)
+		goto fail;
+	for (nid = 0; nid < nodes; nid++) {
+		if (!toptree_get_child(tree, nid))
+			goto fail;
+	}
+	return tree;
+fail:
+	panic("NUMA emulation could not allocate topology");
+}
+
+/*
+ * Allocate and initialize core to node mapping
+ */
+static void create_core_to_node_map(void)
+{
+	int i;
+
+	emu_cores = kzalloc(sizeof(*emu_cores), GFP_KERNEL);
+	if (emu_cores == NULL)
+		panic("Could not allocate cores to node memory");
+	for (i = 0; i < ARRAY_SIZE(emu_cores->to_node_id); i++)
+		emu_cores->to_node_id[i] = NODE_ID_FREE;
+}
+
+/*
+ * Move cores from physical topology into NUMA target topology
+ * and try to keep as much of the physical topology as possible.
+ */
+static struct toptree *toptree_to_numa(struct toptree *phys)
+{
+	static int first = 1;
+	struct toptree *numa;
+	int cores_total;
+
+	cores_total = emu_cores->total + cores_free(phys);
+	emu_cores->per_node_target = cores_total / emu_nodes;
+	numa = toptree_new(TOPTREE_ID_NUMA, emu_nodes);
+	if (first) {
+		toptree_to_numa_first(numa, phys);
+		first = 0;
+	}
+	toptree_to_numa_single(numa, phys, 0);
+	toptree_to_numa_single(numa, phys, 1);
+	toptree_unify_tree(numa);
+
+	WARN_ON(cpumask_weight(&phys->mask));
+	return numa;
+}
+
+/*
+ * Create a toptree out of the physical topology that we got from the hypervisor
+ */
+static struct toptree *toptree_from_topology(void)
+{
+	struct toptree *phys, *node, *book, *mc, *core;
+	struct cpu_topology_s390 *top;
+	int cpu;
+
+	phys = toptree_new(TOPTREE_ID_PHYS, 1);
+
+	for_each_online_cpu(cpu) {
+		top = &per_cpu(cpu_topology, cpu);
+		node = toptree_get_child(phys, 0);
+		book = toptree_get_child(node, top->book_id);
+		mc = toptree_get_child(book, top->socket_id);
+		core = toptree_get_child(mc, top->core_id);
+		if (!book || !mc || !core)
+			panic("NUMA emulation could not allocate memory");
+		cpumask_set_cpu(cpu, &core->mask);
+		toptree_update_mask(mc);
+	}
+	return phys;
+}
+
+/*
+ * Add toptree core to topology and create correct CPU masks
+ */
+static void topology_add_core(struct toptree *core)
+{
+	struct cpu_topology_s390 *top;
+	int cpu;
+
+	for_each_cpu(cpu, &core->mask) {
+		top = &per_cpu(cpu_topology, cpu);
+		cpumask_copy(&top->thread_mask, &core->mask);
+		cpumask_copy(&top->core_mask, &core_mc(core)->mask);
+		cpumask_copy(&top->book_mask, &core_book(core)->mask);
+		cpumask_set_cpu(cpu, node_to_cpumask_map[core_node(core)->id]);
+		top->node_id = core_node(core)->id;
+	}
+}
+
+/*
+ * Apply toptree to topology and create CPU masks
+ */
+static void toptree_to_topology(struct toptree *numa)
+{
+	struct toptree *core;
+	int i;
+
+	/* Clear all node masks */
+	for (i = 0; i < MAX_NUMNODES; i++)
+		cpumask_clear(node_to_cpumask_map[i]);
+
+	/* Rebuild all masks */
+	toptree_for_each(core, numa, CORE)
+		topology_add_core(core);
+}
+
+/*
+ * Show the node to core mapping
+ */
+static void print_node_to_core_map(void)
+{
+	int nid, cid;
+
+	if (!numa_debug_enabled)
+		return;
+	printk(KERN_DEBUG "NUMA node to core mapping\n");
+	for (nid = 0; nid < emu_nodes; nid++) {
+		printk(KERN_DEBUG "  node %3d: ", nid);
+		for (cid = 0; cid < ARRAY_SIZE(emu_cores->to_node_id); cid++) {
+			if (emu_cores->to_node_id[cid] == nid)
+				printk(KERN_CONT "%d ", cid);
+		}
+		printk(KERN_CONT "\n");
+	}
+}
+
+/*
+ * Transfer physical topology into a NUMA topology and modify CPU masks
+ * according to the NUMA topology.
+ *
+ * Must be called with "sched_domains_mutex" lock held.
+ */
+static void emu_update_cpu_topology(void)
+{
+	struct toptree *phys, *numa;
+
+	if (emu_cores == NULL)
+		create_core_to_node_map();
+	phys = toptree_from_topology();
+	numa = toptree_to_numa(phys);
+	toptree_free(phys);
+	toptree_to_topology(numa);
+	toptree_free(numa);
+	print_node_to_core_map();
+}
+
+/*
+ * If emu_size is not set, use CONFIG_EMU_SIZE. Then round to minimum
+ * alignment (needed for memory hotplug).
+ */
+static unsigned long emu_setup_size_adjust(unsigned long size)
+{
+	size = size ? : CONFIG_EMU_SIZE;
+	size = roundup(size, memory_block_size_bytes());
+	return size;
+}
+
+/*
+ * If we have not enough memory for the specified nodes, reduce the node count.
+ */
+static int emu_setup_nodes_adjust(int nodes)
+{
+	int nodes_max;
+
+	nodes_max = memblock.memory.total_size / emu_size;
+	nodes_max = max(nodes_max, 1);
+	if (nodes_max >= nodes)
+		return nodes;
+	pr_warn("Not enough memory for %d nodes, reducing node count\n", nodes);
+	return nodes_max;
+}
+
+/*
+ * Early emu setup
+ */
+static void emu_setup(void)
+{
+	emu_size = emu_setup_size_adjust(emu_size);
+	emu_nodes = emu_setup_nodes_adjust(emu_nodes);
+	pr_info("Creating %d nodes with memory stripe size %ld MB\n",
+		emu_nodes, emu_size >> 20);
+}
+
+/*
+ * Return node id for given page number
+ */
+static int emu_pfn_to_nid(unsigned long pfn)
+{
+	return (pfn / (emu_size >> PAGE_SHIFT)) % emu_nodes;
+}
+
+/*
+ * Return stripe size
+ */
+static unsigned long emu_align(void)
+{
+	return emu_size;
+}
+
+/*
+ * Return distance between two nodes
+ */
+static int emu_distance(int node1, int node2)
+{
+	return (node1 != node2) * EMU_NODE_DIST;
+}
+
+/*
+ * Define callbacks for generic s390 NUMA infrastructure
+ */
+const struct numa_mode numa_mode_emu = {
+	.name = "emu",
+	.setup = emu_setup,
+	.update_cpu_topology = emu_update_cpu_topology,
+	.__pfn_to_nid = emu_pfn_to_nid,
+	.align = emu_align,
+	.distance = emu_distance,
+};
+
+/*
+ * Kernel parameter: emu_nodes=<n>
+ */
+static int __init early_parse_emu_nodes(char *p)
+{
+	int count;
+
+	if (kstrtoint(p, 0, &count) != 0 || count <= 0)
+		return 0;
+	if (count <= 0)
+		return 0;
+	emu_nodes = min(count, MAX_NUMNODES);
+	return 0;
+}
+early_param("emu_nodes", early_parse_emu_nodes);
+
+/*
+ * Kernel parameter: emu_size=[<n>[k|M|G|T]]
+ */
+static int __init early_parse_emu_size(char *p)
+{
+	emu_size = memparse(p, NULL);
+	return 0;
+}
+early_param("emu_size", early_parse_emu_size);
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
new file mode 100644
index 000000000000..09b1d2355bd9
--- /dev/null
+++ b/arch/s390/numa/numa.c
@@ -0,0 +1,184 @@
+/*
+ * NUMA support for s390
+ *
+ * Implement NUMA core code.
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#define KMSG_COMPONENT "numa"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/mmzone.h>
+#include <linux/cpumask.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+#include <linux/node.h>
+
+#include <asm/numa.h>
+#include "numa_mode.h"
+
+pg_data_t *node_data[MAX_NUMNODES];
+EXPORT_SYMBOL(node_data);
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+const struct numa_mode numa_mode_plain = {
+	.name = "plain",
+};
+
+static const struct numa_mode *mode = &numa_mode_plain;
+
+int numa_pfn_to_nid(unsigned long pfn)
+{
+	return mode->__pfn_to_nid ? mode->__pfn_to_nid(pfn) : 0;
+}
+
+void numa_update_cpu_topology(void)
+{
+	if (mode->update_cpu_topology)
+		mode->update_cpu_topology();
+}
+
+int __node_distance(int a, int b)
+{
+	return mode->distance ? mode->distance(a, b) : 0;
+}
+
+int numa_debug_enabled;
+
+/*
+ * alloc_node_data() - Allocate node data
+ */
+static __init pg_data_t *alloc_node_data(void)
+{
+	pg_data_t *res;
+
+	res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 1);
+	if (!res)
+		panic("Could not allocate memory for node data!\n");
+	memset(res, 0, sizeof(pg_data_t));
+	return res;
+}
+
+/*
+ * numa_setup_memory() - Assign bootmem to nodes
+ *
+ * The memory is first added to memblock without any respect to nodes.
+ * This is fixed before remaining memblock memory is handed over to the
+ * buddy allocator.
+ * An important side effect is that large bootmem allocations might easily
+ * cross node boundaries, which can be needed for large allocations with
+ * smaller memory stripes in each node (i.e. when using NUMA emulation).
+ *
+ * Memory defines nodes:
+ * Therefore this routine also sets the nodes online with memory.
+ */
+static void __init numa_setup_memory(void)
+{
+	unsigned long cur_base, align, end_of_dram;
+	int nid = 0;
+
+	end_of_dram = memblock_end_of_DRAM();
+	align = mode->align ? mode->align() : ULONG_MAX;
+
+	/*
+	 * Step through all available memory and assign it to the nodes
+	 * indicated by the mode implementation.
+	 * All nodes which are seen here will be set online.
+	 */
+	cur_base = 0;
+	do {
+		nid = numa_pfn_to_nid(PFN_DOWN(cur_base));
+		node_set_online(nid);
+		memblock_set_node(cur_base, align, &memblock.memory, nid);
+		cur_base += align;
+	} while (cur_base < end_of_dram);
+
+	/* Allocate and fill out node_data */
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		NODE_DATA(nid) = alloc_node_data();
+
+	for_each_online_node(nid) {
+		unsigned long start_pfn, end_pfn;
+		unsigned long t_start, t_end;
+		int i;
+
+		start_pfn = ULONG_MAX;
+		end_pfn = 0;
+		for_each_mem_pfn_range(i, nid, &t_start, &t_end, NULL) {
+			if (t_start < start_pfn)
+				start_pfn = t_start;
+			if (t_end > end_pfn)
+				end_pfn = t_end;
+		}
+		NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
+		NODE_DATA(nid)->node_id = nid;
+	}
+}
+
+/*
+ * numa_setup() - Earliest initialization
+ *
+ * Assign the mode and call the mode's setup routine.
+ */
+void __init numa_setup(void)
+{
+	pr_info("NUMA mode: %s\n", mode->name);
+	if (mode->setup)
+		mode->setup();
+	numa_setup_memory();
+	memblock_dump_all();
+}
+
+
+/*
+ * numa_init_early() - Initialization initcall
+ *
+ * This runs when only one CPU is online and before the first
+ * topology update is called for by the scheduler.
+ */
+static int __init numa_init_early(void)
+{
+	/* Attach all possible CPUs to node 0 for now. */
+	cpumask_copy(node_to_cpumask_map[0], cpu_possible_mask);
+	return 0;
+}
+early_initcall(numa_init_early);
+
+/*
+ * numa_init_late() - Initialization initcall
+ *
+ * Register NUMA nodes.
+ */
+static int __init numa_init_late(void)
+{
+	int nid;
+
+	for_each_online_node(nid)
+		register_one_node(nid);
+	return 0;
+}
+device_initcall(numa_init_late);
+
+static int __init parse_debug(char *parm)
+{
+	numa_debug_enabled = 1;
+	return 0;
+}
+early_param("numa_debug", parse_debug);
+
+static int __init parse_numa(char *parm)
+{
+	if (strcmp(parm, numa_mode_plain.name) == 0)
+		mode = &numa_mode_plain;
+#ifdef CONFIG_NUMA_EMU
+	if (strcmp(parm, numa_mode_emu.name) == 0)
+		mode = &numa_mode_emu;
+#endif
+	return 0;
+}
+early_param("numa", parse_numa);
diff --git a/arch/s390/numa/numa_mode.h b/arch/s390/numa/numa_mode.h
new file mode 100644
index 000000000000..08953b0b1c7f
--- /dev/null
+++ b/arch/s390/numa/numa_mode.h
@@ -0,0 +1,24 @@
+/*
+ * NUMA support for s390
+ *
+ * Define declarations used for communication between NUMA mode
+ * implementations and NUMA core functionality.
+ *
+ * Copyright IBM Corp. 2015
+ */
+#ifndef __S390_NUMA_MODE_H
+#define __S390_NUMA_MODE_H
+
+struct numa_mode {
+	char *name;				/* Name of mode */
+	void (*setup)(void);			/* Initizalize mode */
+	void (*update_cpu_topology)(void);	/* Called by topology code */
+	int (*__pfn_to_nid)(unsigned long pfn);	/* PFN to node ID */
+	unsigned long (*align)(void);		/* Minimum node alignment */
+	int (*distance)(int a, int b);		/* Distance between two nodes */
+};
+
+extern const struct numa_mode numa_mode_plain;
+extern const struct numa_mode numa_mode_emu;
+
+#endif /* __S390_NUMA_MODE_H */
diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c
new file mode 100644
index 000000000000..902d350d859a
--- /dev/null
+++ b/arch/s390/numa/toptree.c
@@ -0,0 +1,342 @@
+/*
+ * NUMA support for s390
+ *
+ * A tree structure used for machine topology mangling
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpumask.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
+#include <linux/slab.h>
+#include <asm/numa.h>
+
+#include "toptree.h"
+
+/**
+ * toptree_alloc - Allocate and initialize a new tree node.
+ * @level: The node's vertical level; level 0 contains the leaves.
+ * @id: ID number, explicitly not unique beyond scope of node's siblings
+ *
+ * Allocate a new tree node and initialize it.
+ *
+ * RETURNS:
+ * Pointer to the new tree node or NULL on error
+ */
+struct toptree *toptree_alloc(int level, int id)
+{
+	struct toptree *res = kzalloc(sizeof(struct toptree), GFP_KERNEL);
+
+	if (!res)
+		return res;
+
+	INIT_LIST_HEAD(&res->children);
+	INIT_LIST_HEAD(&res->sibling);
+	cpumask_clear(&res->mask);
+	res->level = level;
+	res->id = id;
+	return res;
+}
+
+/**
+ * toptree_remove - Remove a tree node from a tree
+ * @cand: Pointer to the node to remove
+ *
+ * The node is detached from its parent node. The parent node's
+ * masks will be updated to reflect the loss of the child.
+ */
+static void toptree_remove(struct toptree *cand)
+{
+	struct toptree *oldparent;
+
+	list_del_init(&cand->sibling);
+	oldparent = cand->parent;
+	cand->parent = NULL;
+	toptree_update_mask(oldparent);
+}
+
+/**
+ * toptree_free - discard a tree node
+ * @cand: Pointer to the tree node to discard
+ *
+ * Checks if @cand is attached to a parent node. Detaches it
+ * cleanly using toptree_remove. Possible children are freed
+ * recursively. In the end @cand itself is freed.
+ */
+void toptree_free(struct toptree *cand)
+{
+	struct toptree *child, *tmp;
+
+	if (cand->parent)
+		toptree_remove(cand);
+	toptree_for_each_child_safe(child, tmp, cand)
+		toptree_free(child);
+	kfree(cand);
+}
+
+/**
+ * toptree_update_mask - Update node bitmasks
+ * @cand: Pointer to a tree node
+ *
+ * The node's cpumask will be updated by combining all children's
+ * masks. Then toptree_update_mask is called recursively for the
+ * parent if applicable.
+ *
+ * NOTE:
+ * This must not be called on leaves. If called on a leaf, its
+ * CPU mask is cleared and lost.
+ */
+void toptree_update_mask(struct toptree *cand)
+{
+	struct toptree *child;
+
+	cpumask_clear(&cand->mask);
+	list_for_each_entry(child, &cand->children, sibling)
+		cpumask_or(&cand->mask, &cand->mask, &child->mask);
+	if (cand->parent)
+		toptree_update_mask(cand->parent);
+}
+
+/**
+ * toptree_insert - Insert a tree node into tree
+ * @cand: Pointer to the node to insert
+ * @target: Pointer to the node to which @cand will added as a child
+ *
+ * Insert a tree node into a tree. Masks will be updated automatically.
+ *
+ * RETURNS:
+ * 0 on success, -1 if NULL is passed as argument or the node levels
+ * don't fit.
+ */
+static int toptree_insert(struct toptree *cand, struct toptree *target)
+{
+	if (!cand || !target)
+		return -1;
+	if (target->level != (cand->level + 1))
+		return -1;
+	list_add_tail(&cand->sibling, &target->children);
+	cand->parent = target;
+	toptree_update_mask(target);
+	return 0;
+}
+
+/**
+ * toptree_move_children - Move all child nodes of a node to a new place
+ * @cand: Pointer to the node whose children are to be moved
+ * @target: Pointer to the node to which @cand's children will be attached
+ *
+ * Take all child nodes of @cand and move them using toptree_move.
+ */
+static void toptree_move_children(struct toptree *cand, struct toptree *target)
+{
+	struct toptree *child, *tmp;
+
+	toptree_for_each_child_safe(child, tmp, cand)
+		toptree_move(child, target);
+}
+
+/**
+ * toptree_unify - Merge children with same ID
+ * @cand: Pointer to node whose direct children should be made unique
+ *
+ * When mangling the tree it is possible that a node has two or more children
+ * which have the same ID. This routine merges these children into one and
+ * moves all children of the merged nodes into the unified node.
+ */
+void toptree_unify(struct toptree *cand)
+{
+	struct toptree *child, *tmp, *cand_copy;
+
+	/* Threads cannot be split, cores are not split */
+	if (cand->level < 2)
+		return;
+
+	cand_copy = toptree_alloc(cand->level, 0);
+	toptree_for_each_child_safe(child, tmp, cand) {
+		struct toptree *tmpchild;
+
+		if (!cpumask_empty(&child->mask)) {
+			tmpchild = toptree_get_child(cand_copy, child->id);
+			toptree_move_children(child, tmpchild);
+		}
+		toptree_free(child);
+	}
+	toptree_move_children(cand_copy, cand);
+	toptree_free(cand_copy);
+
+	toptree_for_each_child(child, cand)
+		toptree_unify(child);
+}
+
+/**
+ * toptree_move - Move a node to another context
+ * @cand: Pointer to the node to move
+ * @target: Pointer to the node where @cand should go
+ *
+ * In the easiest case @cand is exactly on the level below @target
+ * and will be immediately moved to the target.
+ *
+ * If @target's level is not the direct parent level of @cand,
+ * nodes for the missing levels are created and put between
+ * @cand and @target. The "stacking" nodes' IDs are taken from
+ * @cand's parents.
+ *
+ * After this it is likely to have redundant nodes in the tree
+ * which are addressed by means of toptree_unify.
+ */
+void toptree_move(struct toptree *cand, struct toptree *target)
+{
+	struct toptree *stack_target, *real_insert_point, *ptr, *tmp;
+
+	if (cand->level + 1 == target->level) {
+		toptree_remove(cand);
+		toptree_insert(cand, target);
+		return;
+	}
+
+	real_insert_point = NULL;
+	ptr = cand;
+	stack_target = NULL;
+
+	do {
+		tmp = stack_target;
+		stack_target = toptree_alloc(ptr->level + 1,
+					     ptr->parent->id);
+		toptree_insert(tmp, stack_target);
+		if (!real_insert_point)
+			real_insert_point = stack_target;
+		ptr = ptr->parent;
+	} while (stack_target->level < (target->level - 1));
+
+	toptree_remove(cand);
+	toptree_insert(cand, real_insert_point);
+	toptree_insert(stack_target, target);
+}
+
+/**
+ * toptree_get_child - Access a tree node's child by its ID
+ * @cand: Pointer to tree node whose child is to access
+ * @id: The desired child's ID
+ *
+ * @cand's children are searched for a child with matching ID.
+ * If no match can be found, a new child with the desired ID
+ * is created and returned.
+ */
+struct toptree *toptree_get_child(struct toptree *cand, int id)
+{
+	struct toptree *child;
+
+	toptree_for_each_child(child, cand)
+		if (child->id == id)
+			return child;
+	child = toptree_alloc(cand->level-1, id);
+	toptree_insert(child, cand);
+	return child;
+}
+
+/**
+ * toptree_first - Find the first descendant on specified level
+ * @context: Pointer to tree node whose descendants are to be used
+ * @level: The level of interest
+ *
+ * RETURNS:
+ * @context's first descendant on the specified level, or NULL
+ * if there is no matching descendant
+ */
+struct toptree *toptree_first(struct toptree *context, int level)
+{
+	struct toptree *child, *tmp;
+
+	if (context->level == level)
+		return context;
+
+	if (!list_empty(&context->children)) {
+		list_for_each_entry(child, &context->children, sibling) {
+			tmp = toptree_first(child, level);
+			if (tmp)
+				return tmp;
+		}
+	}
+	return NULL;
+}
+
+/**
+ * toptree_next_sibling - Return next sibling
+ * @cur: Pointer to a tree node
+ *
+ * RETURNS:
+ * If @cur has a parent and is not the last in the parent's children list,
+ * the next sibling is returned. Or NULL when there are no siblings left.
+ */
+static struct toptree *toptree_next_sibling(struct toptree *cur)
+{
+	if (cur->parent == NULL)
+		return NULL;
+
+	if (cur == list_last_entry(&cur->parent->children,
+				   struct toptree, sibling))
+		return NULL;
+	return (struct toptree *) list_next_entry(cur, sibling);
+}
+
+/**
+ * toptree_next - Tree traversal function
+ * @cur: Pointer to current element
+ * @context: Pointer to the root node of the tree or subtree to
+ * be traversed.
+ * @level: The level of interest.
+ *
+ * RETURNS:
+ * Pointer to the next node on level @level
+ * or NULL when there is no next node.
+ */
+struct toptree *toptree_next(struct toptree *cur, struct toptree *context,
+			     int level)
+{
+	struct toptree *cur_context, *tmp;
+
+	if (!cur)
+		return NULL;
+
+	if (context->level == level)
+		return NULL;
+
+	tmp = toptree_next_sibling(cur);
+	if (tmp != NULL)
+		return tmp;
+
+	cur_context = cur;
+	while (cur_context->level < context->level - 1) {
+		/* Step up */
+		cur_context = cur_context->parent;
+		/* Step aside */
+		tmp = toptree_next_sibling(cur_context);
+		if (tmp != NULL) {
+			/* Step down */
+			tmp = toptree_first(tmp, level);
+			if (tmp != NULL)
+				return tmp;
+		}
+	}
+	return NULL;
+}
+
+/**
+ * toptree_count - Count descendants on specified level
+ * @context: Pointer to node whose descendants are to be considered
+ * @level: Only descendants on the specified level will be counted
+ *
+ * RETURNS:
+ * Number of descendants on the specified level
+ */
+int toptree_count(struct toptree *context, int level)
+{
+	struct toptree *cur;
+	int cnt = 0;
+
+	toptree_for_each(cur, context, level)
+		cnt++;
+	return cnt;
+}
diff --git a/arch/s390/numa/toptree.h b/arch/s390/numa/toptree.h
new file mode 100644
index 000000000000..bdf502027af4
--- /dev/null
+++ b/arch/s390/numa/toptree.h
@@ -0,0 +1,60 @@
+/*
+ * NUMA support for s390
+ *
+ * A tree structure used for machine topology mangling
+ *
+ * Copyright IBM Corp. 2015
+ */
+#ifndef S390_TOPTREE_H
+#define S390_TOPTREE_H
+
+#include <linux/cpumask.h>
+#include <linux/list.h>
+
+struct toptree {
+	int level;
+	int id;
+	cpumask_t mask;
+	struct toptree *parent;
+	struct list_head sibling;
+	struct list_head children;
+};
+
+struct toptree *toptree_alloc(int level, int id);
+void toptree_free(struct toptree *cand);
+void toptree_update_mask(struct toptree *cand);
+void toptree_unify(struct toptree *cand);
+struct toptree *toptree_get_child(struct toptree *cand, int id);
+void toptree_move(struct toptree *cand, struct toptree *target);
+int toptree_count(struct toptree *context, int level);
+
+struct toptree *toptree_first(struct toptree *context, int level);
+struct toptree *toptree_next(struct toptree *cur, struct toptree *context,
+			     int level);
+
+#define toptree_for_each_child(child, ptree)				\
+	list_for_each_entry(child,  &ptree->children, sibling)
+
+#define toptree_for_each_child_safe(child, ptmp, ptree)			\
+	list_for_each_entry_safe(child, ptmp, &ptree->children, sibling)
+
+#define toptree_is_last(ptree)					\
+	((ptree->parent == NULL) ||				\
+	 (ptree->parent->children.prev == &ptree->sibling))
+
+#define toptree_for_each(ptree, cont, ttype)		\
+	for (ptree = toptree_first(cont, ttype);	\
+	     ptree != NULL;				\
+	     ptree = toptree_next(ptree, cont, ttype))
+
+#define toptree_for_each_safe(ptree, tmp, cont, ttype)		\
+	for (ptree = toptree_first(cont, ttype),		\
+		     tmp = toptree_next(ptree, cont, ttype);	\
+	     ptree != NULL;					\
+	     ptree = tmp,					\
+		     tmp = toptree_next(ptree, cont, ttype))
+
+#define toptree_for_each_sibling(ptree, start)			\
+	toptree_for_each(ptree, start->parent, start->level)
+
+#endif /* S390_TOPTREE_H */
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index bc927a09a172..9cfa2ffaa9d6 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <asm/processor.h>
+#include <asm/perf_event.h>
 
 #include "../../../drivers/oprofile/oprof.h"
 
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 598f023cf8a6..7ef12a3ace3a 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -76,11 +76,6 @@ EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
 static struct kmem_cache *zdev_fmb_cache;
 
-struct zpci_dev *get_zdev(struct pci_dev *pdev)
-{
-	return (struct zpci_dev *) pdev->sysdata;
-}
-
 struct zpci_dev *get_zdev_by_fid(u32 fid)
 {
 	struct zpci_dev *tmp, *zdev = NULL;
@@ -269,7 +264,7 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev,
 			      unsigned long offset,
 			      unsigned long max)
 {
-	struct zpci_dev *zdev =	get_zdev(pdev);
+	struct zpci_dev *zdev =	to_zpci(pdev);
 	u64 addr;
 	int idx;
 
@@ -385,7 +380,7 @@ static void zpci_irq_handler(struct airq_struct *airq)
 
 int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 	unsigned int hwirq, msi_vecs;
 	unsigned long aisb;
 	struct msi_desc *msi;
@@ -414,7 +409,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 
 	/* Request MSI interrupts */
 	hwirq = 0;
-	list_for_each_entry(msi, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(msi, pdev) {
 		rc = -EIO;
 		irq = irq_alloc_desc(0);	/* Alloc irq on node 0 */
 		if (irq < 0)
@@ -440,7 +435,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	return (msi_vecs == nvec) ? 0 : msi_vecs;
 
 out_msi:
-	list_for_each_entry(msi, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(msi, pdev) {
 		if (hwirq-- == 0)
 			break;
 		irq_set_msi_desc(msi->irq, NULL);
@@ -460,7 +455,7 @@ out:
 
 void arch_teardown_msi_irqs(struct pci_dev *pdev)
 {
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 	struct msi_desc *msi;
 	int rc;
 
@@ -470,7 +465,7 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 		return;
 
 	/* Release MSI interrupts */
-	list_for_each_entry(msi, &pdev->msi_list, list) {
+	for_each_pci_msi_entry(msi, pdev) {
 		if (msi->msi_attrib.is_msix)
 			__pci_msix_desc_mask_irq(msi, 1);
 		else
@@ -637,7 +632,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
 	int i;
 
 	for (i = 0; i < PCI_BAR_COUNT; i++) {
-		if (!zdev->bars[i].size)
+		if (!zdev->bars[i].size || !zdev->bars[i].res)
 			continue;
 
 		zpci_free_iomap(zdev, zdev->bars[i].map_idx);
@@ -648,7 +643,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
 
 int pcibios_add_device(struct pci_dev *pdev)
 {
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 	struct resource *res;
 	int i;
 
@@ -673,7 +668,7 @@ void pcibios_release_device(struct pci_dev *pdev)
 
 int pcibios_enable_device(struct pci_dev *pdev, int mask)
 {
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 
 	zdev->pdev = pdev;
 	zpci_debug_init_device(zdev);
@@ -684,7 +679,7 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask)
 
 void pcibios_disable_device(struct pci_dev *pdev)
 {
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 
 	zpci_fmb_disable_device(zdev);
 	zpci_debug_exit_device(zdev);
@@ -695,7 +690,7 @@ void pcibios_disable_device(struct pci_dev *pdev)
 static int zpci_restore(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 	int ret = 0;
 
 	if (zdev->state != ZPCI_FN_STATE_ONLINE)
@@ -717,7 +712,7 @@ out:
 static int zpci_freeze(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 
 	if (zdev->state != ZPCI_FN_STATE_ONLINE)
 		return 0;
@@ -777,17 +772,22 @@ static int zpci_scan_bus(struct zpci_dev *zdev)
 
 	ret = zpci_setup_bus_resources(zdev, &resources);
 	if (ret)
-		return ret;
+		goto error;
 
 	zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops,
 				      zdev, &resources);
 	if (!zdev->bus) {
-		zpci_cleanup_bus_resources(zdev);
-		return -EIO;
+		ret = -EIO;
+		goto error;
 	}
 	zdev->bus->max_bus_speed = zdev->max_bus_speed;
 	pci_bus_add_devices(zdev->bus);
 	return 0;
+
+error:
+	zpci_cleanup_bus_resources(zdev);
+	pci_free_resource_list(&resources);
+	return ret;
 }
 
 int zpci_enable_device(struct zpci_dev *zdev)
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 6fd8d5836138..42b76580c8b8 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -277,7 +277,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 				     enum dma_data_direction direction,
 				     struct dma_attrs *attrs)
 {
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	unsigned long nr_pages, iommu_page_index;
 	unsigned long pa = page_to_phys(page) + offset;
 	int flags = ZPCI_PTE_VALID;
@@ -316,7 +316,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
 				 size_t size, enum dma_data_direction direction,
 				 struct dma_attrs *attrs)
 {
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	unsigned long iommu_page_index;
 	int npages;
 
@@ -337,7 +337,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
 			    dma_addr_t *dma_handle, gfp_t flag,
 			    struct dma_attrs *attrs)
 {
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	struct page *page;
 	unsigned long pa;
 	dma_addr_t map;
@@ -367,7 +367,7 @@ static void s390_dma_free(struct device *dev, size_t size,
 			  void *pa, dma_addr_t dma_handle,
 			  struct dma_attrs *attrs)
 {
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 
 	size = PAGE_ALIGN(size);
 	atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages);
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index ed2394dd14e9..369a3e05d468 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -46,15 +46,13 @@ struct zpci_ccdf_avail {
 static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+	struct pci_dev *pdev = zdev ? zdev->pdev : NULL;
 
 	zpci_err("error CCDF:\n");
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
-	if (!zdev)
-		return;
-
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
-	       pci_name(zdev->pdev), ccdf->pec, ccdf->fid);
+	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
 }
 
 void zpci_event_error(void *data)
@@ -89,7 +87,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		ret = zpci_enable_device(zdev);
 		if (ret)
 			break;
+		pci_lock_rescan_remove();
 		pci_rescan_bus(zdev->bus);
+		pci_unlock_rescan_remove();
 		break;
 	case 0x0302: /* Reserved -> Standby */
 		if (!zdev)
@@ -97,7 +97,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		break;
 	case 0x0303: /* Deconfiguration requested */
 		if (pdev)
-			pci_stop_and_remove_bus_device(pdev);
+			pci_stop_and_remove_bus_device_locked(pdev);
 
 		ret = zpci_disable_device(zdev);
 		if (ret)
@@ -114,7 +114,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			/* Give the driver a hint that the function is
 			 * already unusable. */
 			pdev->error_state = pci_channel_io_perm_failure;
-			pci_stop_and_remove_bus_device(pdev);
+			pci_stop_and_remove_bus_device_locked(pdev);
 		}
 
 		zdev->fh = ccdf->fh;
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 85267c058af8..dcc2634ccbe2 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -8,10 +8,23 @@
 #include <linux/errno.h>
 #include <linux/delay.h>
 #include <asm/pci_insn.h>
+#include <asm/pci_debug.h>
 #include <asm/processor.h>
 
 #define ZPCI_INSN_BUSY_DELAY	1	/* 1 microsecond */
 
+static inline void zpci_err_insn(u8 cc, u8 status, u64 req, u64 offset)
+{
+	struct {
+		u8 cc;
+		u8 status;
+		u64 req;
+		u64 offset;
+	} data = {cc, status, req, offset};
+
+	zpci_err_hex(&data, sizeof(data));
+}
+
 /* Modify PCI Function Controls */
 static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
 {
@@ -38,8 +51,8 @@ int zpci_mod_fc(u64 req, struct zpci_fib *fib)
 	} while (cc == 2);
 
 	if (cc)
-		printk_once(KERN_ERR "%s: error cc: %d  status: %d\n",
-			     __func__, cc, status);
+		zpci_err_insn(cc, status, req, 0);
+
 	return (cc) ? -EIO : 0;
 }
 
@@ -72,8 +85,8 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 	} while (cc == 2);
 
 	if (cc)
-		printk_once(KERN_ERR "%s: error cc: %d  status: %d  dma_addr: %Lx  size: %Lx\n",
-			    __func__, cc, status, addr, range);
+		zpci_err_insn(cc, status, addr, range);
+
 	return (cc) ? -EIO : 0;
 }
 
@@ -121,8 +134,8 @@ int zpci_load(u64 *data, u64 req, u64 offset)
 	} while (cc == 2);
 
 	if (cc)
-		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
-			    __func__, cc, status, req, offset);
+		zpci_err_insn(cc, status, req, offset);
+
 	return (cc > 0) ? -EIO : cc;
 }
 EXPORT_SYMBOL_GPL(zpci_load);
@@ -159,8 +172,8 @@ int zpci_store(u64 data, u64 req, u64 offset)
 	} while (cc == 2);
 
 	if (cc)
-		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
-			__func__, cc, status, req, offset);
+		zpci_err_insn(cc, status, req, offset);
+
 	return (cc > 0) ? -EIO : cc;
 }
 EXPORT_SYMBOL_GPL(zpci_store);
@@ -195,8 +208,8 @@ int zpci_store_block(const u64 *data, u64 req, u64 offset)
 	} while (cc == 2);
 
 	if (cc)
-		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
-			    __func__, cc, status, req, offset);
+		zpci_err_insn(cc, status, req, offset);
+
 	return (cc > 0) ? -EIO : cc;
 }
 EXPORT_SYMBOL_GPL(zpci_store_block);
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index fa3ce891e597..f37a5808883d 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -16,7 +16,7 @@
 static ssize_t name##_show(struct device *dev,				\
 			   struct device_attribute *attr, char *buf)	\
 {									\
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));		\
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));		\
 									\
 	return sprintf(buf, fmt, zdev->member);				\
 }									\
@@ -38,23 +38,30 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 	int ret;
 
 	if (!device_remove_file_self(dev, attr))
 		return count;
 
+	pci_lock_rescan_remove();
 	pci_stop_and_remove_bus_device(pdev);
 	ret = zpci_disable_device(zdev);
 	if (ret)
-		return ret;
+		goto error;
 
 	ret = zpci_enable_device(zdev);
 	if (ret)
-		return ret;
+		goto error;
 
 	pci_rescan_bus(zdev->bus);
+	pci_unlock_rescan_remove();
+
 	return count;
+
+error:
+	pci_unlock_rescan_remove();
+	return ret;
 }
 static DEVICE_ATTR_WO(recover);
 
@@ -64,7 +71,7 @@ static ssize_t util_string_read(struct file *filp, struct kobject *kobj,
 {
 	struct device *dev = kobj_to_dev(kobj);
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct zpci_dev *zdev = get_zdev(pdev);
+	struct zpci_dev *zdev = to_zpci(pdev);
 
 	return memory_read_from_buffer(buf, count, &off, zdev->util_str,
 				       sizeof(zdev->util_str));
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 138fb3db45ba..92ffe397b893 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/score/include/asm/mm-arch-hooks.h b/arch/score/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 5e38689f189a..000000000000
--- a/arch/score/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_SCORE_MM_ARCH_HOOKS_H
-#define _ASM_SCORE_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_SCORE_MM_ARCH_HOOKS_H */
diff --git a/arch/score/include/asm/switch_to.h b/arch/score/include/asm/switch_to.h
index 031756b59ece..fda3f83308d2 100644
--- a/arch/score/include/asm/switch_to.h
+++ b/arch/score/include/asm/switch_to.h
@@ -8,6 +8,4 @@ do {								\
 	(last) = resume(prev, next, task_thread_info(next));	\
 } while (0)
 
-#define finish_arch_switch(prev)	do {} while (0)
-
 #endif /* _ASM_SCORE_SWITCH_TO_H */
diff --git a/arch/score/kernel/time.c b/arch/score/kernel/time.c
index 24770cd9b473..679b8d7b0350 100644
--- a/arch/score/kernel/time.c
+++ b/arch/score/kernel/time.c
@@ -55,31 +55,20 @@ static int score_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void score_timer_set_mode(enum clock_event_mode mode,
-		struct clock_event_device *evdev)
+static int score_timer_set_periodic(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		outl((TMR_M_PERIODIC | TMR_IE_ENABLE), P_TIMER0_CTRL);
-		outl(SYSTEM_CLOCK/HZ, P_TIMER0_PRELOAD);
-		outl(inl(P_TIMER0_CTRL) | TMR_ENABLE, P_TIMER0_CTRL);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_UNUSED:
-		break;
-	default:
-		BUG();
-	}
+	outl((TMR_M_PERIODIC | TMR_IE_ENABLE), P_TIMER0_CTRL);
+	outl(SYSTEM_CLOCK / HZ, P_TIMER0_PRELOAD);
+	outl(inl(P_TIMER0_CTRL) | TMR_ENABLE, P_TIMER0_CTRL);
+	return 0;
 }
 
 static struct clock_event_device score_clockevent = {
-	.name		= "score_clockevent",
-	.features	= CLOCK_EVT_FEAT_PERIODIC,
-	.shift		= 16,
-	.set_next_event	= score_timer_set_next_event,
-	.set_mode	= score_timer_set_mode,
+	.name			= "score_clockevent",
+	.features		= CLOCK_EVT_FEAT_PERIODIC,
+	.shift			= 16,
+	.set_next_event		= score_timer_set_next_event,
+	.set_state_periodic	= score_timer_set_periodic,
 };
 
 void __init time_init(void)
diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c
index 1087dba9b015..6f97a8f0d0d6 100644
--- a/arch/sh/boards/mach-se/7343/irq.c
+++ b/arch/sh/boards/mach-se/7343/irq.c
@@ -31,7 +31,7 @@ struct irq_domain *se7343_irq_domain;
 
 static void se7343_irq_demux(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_data *data = irq_get_irq_data(irq);
+	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	unsigned long mask;
 	int bit;
diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c
index 00e699232621..60aebd14ccf8 100644
--- a/arch/sh/boards/mach-se/7722/irq.c
+++ b/arch/sh/boards/mach-se/7722/irq.c
@@ -30,7 +30,7 @@ struct irq_domain *se7722_irq_domain;
 
 static void se7722_irq_demux(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_data *data = irq_get_irq_data(irq);
+	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	unsigned long mask;
 	int bit;
diff --git a/arch/sh/boards/mach-se/7724/irq.c b/arch/sh/boards/mach-se/7724/irq.c
index 5d1d3ec9a6cd..9f2033898652 100644
--- a/arch/sh/boards/mach-se/7724/irq.c
+++ b/arch/sh/boards/mach-se/7724/irq.c
@@ -92,8 +92,9 @@ static struct irq_chip se7724_irq_chip __read_mostly = {
 	.irq_unmask	= enable_se7724_irq,
 };
 
-static void se7724_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void se7724_irq_demux(unsigned int __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	struct fpga_irq set = get_fpga_irq(irq);
 	unsigned short intv = __raw_readw(set.sraddr);
 	unsigned int ext_irq = set.base;
diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c
index f035a7ac6456..24555c364d5b 100644
--- a/arch/sh/boards/mach-x3proto/gpio.c
+++ b/arch/sh/boards/mach-x3proto/gpio.c
@@ -62,7 +62,7 @@ static int x3proto_gpio_to_irq(struct gpio_chip *chip, unsigned gpio)
 
 static void x3proto_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_data *data = irq_get_irq_data(irq);
+	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	unsigned long mask;
 	int pin;
diff --git a/arch/sh/drivers/pci/pci-sh4.h b/arch/sh/drivers/pci/pci-sh4.h
index cbf763b3015e..0288efc17ff3 100644
--- a/arch/sh/drivers/pci/pci-sh4.h
+++ b/arch/sh/drivers/pci/pci-sh4.h
@@ -11,14 +11,6 @@
 
 #include <asm/io.h>
 
-/* startup values */
-#define PCI_PROBE_BIOS		1
-#define PCI_PROBE_CONF1		2
-#define PCI_PROBE_CONF2		4
-#define PCI_NO_CHECKS		0x400
-#define PCI_ASSIGN_ROMS		0x1000
-#define PCI_BIOS_IRQ_SCAN	0x2000
-
 #define SH4_PCICR		0x100		/* PCI Control Register */
   #define SH4_PCICR_PREFIX	  0xA5000000	/* CR prefix for write */
   #define SH4_PCICR_FTO		  0x00000400	/* TRDY/IRDY Enable */
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 9ac4626e7284..aac452b26aa8 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
index 97a5fda83450..b94df40e5f2d 100644
--- a/arch/sh/include/asm/atomic-grb.h
+++ b/arch/sh/include/asm/atomic-grb.h
@@ -48,47 +48,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	int tmp;
-	unsigned int _mask = ~mask;
-
-	__asm__ __volatile__ (
-		"   .align 2              \n\t"
-		"   mova    1f,   r0      \n\t" /* r0 = end point */
-		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
-		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   and     %2,   %0      \n\t" /* add */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (_mask)
-		: "memory" , "r0", "r1");
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	int tmp;
-
-	__asm__ __volatile__ (
-		"   .align 2              \n\t"
-		"   mova    1f,   r0      \n\t" /* r0 = end point */
-		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
-		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   or      %2,   %0      \n\t" /* or */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (mask)
-		: "memory" , "r0", "r1");
-}
-
 #endif /* __ASM_SH_ATOMIC_GRB_H */
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 61d107523f06..23fcdad5773e 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -37,27 +37,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	v->counter &= ~mask;
-	raw_local_irq_restore(flags);
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	v->counter |= mask;
-	raw_local_irq_restore(flags);
-}
-
 #endif /* __ASM_SH_ATOMIC_IRQ_H */
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index 8575dccb9ef7..33d34b16d4d6 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -52,37 +52,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
-"	and	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (~mask), "r" (&v->counter)
-	: "t");
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_set_mask	\n"
-"	or	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (mask), "r" (&v->counter)
-	: "t");
-}
-
 #endif /* __ASM_SH_ATOMIC_LLSC_H */
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index e79fb6ebaa42..1f157b86eaa7 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -9,7 +9,7 @@
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 
-#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_ADDR		((unsigned long)(mcount))
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define CALL_ADDR		((long)(ftrace_call))
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 728c4c571f40..93ec9066dbef 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -368,6 +368,7 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
 #endif
 
 #define ioremap_nocache	ioremap
+#define ioremap_uc	ioremap
 #define iounmap		__iounmap
 
 /*
diff --git a/arch/sh/include/asm/mm-arch-hooks.h b/arch/sh/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 18087298b728..000000000000
--- a/arch/sh/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_SH_MM_ARCH_HOOKS_H
-#define _ASM_SH_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_SH_MM_ARCH_HOOKS_H */
diff --git a/arch/sh/include/asm/switch_to_32.h b/arch/sh/include/asm/switch_to_32.h
index 0c065513e7ac..7661b4ba8259 100644
--- a/arch/sh/include/asm/switch_to_32.h
+++ b/arch/sh/include/asm/switch_to_32.h
@@ -78,6 +78,8 @@ do {								\
 								\
 	if (is_dsp_enabled(prev))				\
 		__save_dsp(prev);				\
+	if (is_dsp_enabled(next))				\
+		__restore_dsp(next);				\
 								\
 	__ts1 = (u32 *)&prev->thread.sp;			\
 	__ts2 = (u32 *)&prev->thread.pc;			\
@@ -125,10 +127,4 @@ do {								\
 	last = __last;						\
 } while (0)
 
-#define finish_arch_switch(prev)				\
-do {								\
-	if (is_dsp_enabled(prev))				\
-		__restore_dsp(prev);				\
-} while (0)
-
 #endif /* __ASM_SH_SWITCH_TO_32_H */
diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c
index 0a47bd3e7bee..4ca78ed71ad2 100644
--- a/arch/sh/kernel/cpu/sh4/sq.c
+++ b/arch/sh/kernel/cpu/sh4/sq.c
@@ -355,13 +355,12 @@ static int sq_dev_add(struct device *dev, struct subsys_interface *sif)
 	return error;
 }
 
-static int sq_dev_remove(struct device *dev, struct subsys_interface *sif)
+static void sq_dev_remove(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id;
 	struct kobject *kobj = sq_kobject[cpu];
 
 	kobject_put(kobj);
-	return 0;
 }
 
 static struct subsys_interface sq_interface = {
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c
index c187b9579c21..f27c618de527 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c
@@ -343,7 +343,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("2ddmac0", &mstp_clks[HWBLK_2DDMAC]),
 	CLKDEV_DEV_ID("sh_fsi.0", &mstp_clks[HWBLK_SPU]),
 	CLKDEV_CON_ID("jpu0", &mstp_clks[HWBLK_JPU]),
-	CLKDEV_DEV_ID("sh-vou.0", &mstp_clks[HWBLK_VOU]),
+	CLKDEV_DEV_ID("sh-vou", &mstp_clks[HWBLK_VOU]),
 	CLKDEV_CON_ID("beu0", &mstp_clks[HWBLK_BEU0]),
 	CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[HWBLK_CEU0]),
 	CLKDEV_CON_ID("veu0", &mstp_clks[HWBLK_VEU0]),
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index eb10ff84015c..6c0378c0b8b5 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -227,16 +227,17 @@ void migrate_irqs(void)
 	for_each_active_irq(irq) {
 		struct irq_data *data = irq_get_irq_data(irq);
 
-		if (data->node == cpu) {
-			unsigned int newcpu = cpumask_any_and(data->affinity,
+		if (irq_data_get_node(data) == cpu) {
+			struct cpumask *mask = irq_data_get_affinity_mask(data);
+			unsigned int newcpu = cpumask_any_and(mask,
 							      cpu_online_mask);
 			if (newcpu >= nr_cpu_ids) {
 				pr_info_ratelimited("IRQ%u no longer affine to CPU%u\n",
 						    irq, cpu);
 
-				cpumask_setall(data->affinity);
+				cpumask_setall(mask);
 			}
-			irq_set_affinity(irq, data->affinity);
+			irq_set_affinity(irq, mask);
 		}
 	}
 }
diff --git a/arch/sh/kernel/localtimer.c b/arch/sh/kernel/localtimer.c
index b880a7e2ace7..cbb7d4636ec0 100644
--- a/arch/sh/kernel/localtimer.c
+++ b/arch/sh/kernel/localtimer.c
@@ -39,11 +39,6 @@ void local_timer_interrupt(void)
 	irq_exit();
 }
 
-static void dummy_timer_set_mode(enum clock_event_mode mode,
-				 struct clock_event_device *clk)
-{
-}
-
 void local_timer_setup(unsigned int cpu)
 {
 	struct clock_event_device *clk = &per_cpu(local_clockevent, cpu);
@@ -54,7 +49,6 @@ void local_timer_setup(unsigned int cpu)
 				  CLOCK_EVT_FEAT_DUMMY;
 	clk->rating		= 400;
 	clk->mult		= 1;
-	clk->set_mode		= dummy_timer_set_mode;
 	clk->broadcast		= smp_timer_broadcast;
 	clk->cpumask		= cpumask_of(cpu);
 
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 2790b6a64157..17f486233db0 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -488,7 +488,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	pg_data_t *pgdat;
-	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
@@ -517,7 +517,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 int arch_remove_memory(u64 start, u64 size)
 {
-	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
 	int ret;
diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c
index bce52ba66206..05713d190247 100644
--- a/arch/sh/mm/numa.c
+++ b/arch/sh/mm/numa.c
@@ -33,8 +33,8 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
 	/* Don't allow bogus node assignment */
 	BUG_ON(nid >= MAX_NUMNODES || nid <= 0);
 
-	start_pfn = start >> PAGE_SHIFT;
-	end_pfn = end >> PAGE_SHIFT;
+	start_pfn = PFN_DOWN(start);
+	end_pfn = PFN_DOWN(end);
 
 	pmb_bolt_mapping((unsigned long)__va(start), start, end - start,
 			 PAGE_KERNEL);
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 2b2a69dcc467..e928618838bc 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += preempt.h
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 0e69b7e7a439..7dcbebbcaec6 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -17,10 +17,12 @@
 #include <asm/barrier.h>
 #include <asm-generic/atomic64.h>
 
-
 #define ATOMIC_INIT(i)  { (i) }
 
 int atomic_add_return(int, atomic_t *);
+void atomic_and(int, atomic_t *);
+void atomic_or(int, atomic_t *);
+void atomic_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 4082749913ce..917084ace49d 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -33,6 +33,10 @@ long atomic64_##op##_return(long, atomic64_t *);
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 809941e33e12..14a928601657 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -60,12 +60,12 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	___p1;								\
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index 9ec94ad116fb..3192a8e42fd6 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -2,7 +2,7 @@
 #define _ASM_SPARC64_FTRACE
 
 #ifdef CONFIG_MCOUNT
-#define MCOUNT_ADDR		((long)(_mcount))
+#define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index cc9b04a2b11b..62d0354d1727 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -7,16 +7,33 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-		asm_volatile_goto("1:\n\t"
-			 "nop\n\t"
-			 "nop\n\t"
-			 ".pushsection __jump_table,  \"aw\"\n\t"
-			 ".align 4\n\t"
-			 ".word 1b, %l[l_yes], %c0\n\t"
-			 ".popsection \n\t"
-			 : :  "i" (key) : : l_yes);
+	asm_volatile_goto("1:\n\t"
+		 "nop\n\t"
+		 "nop\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align 4\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection \n\t"
+		 : :  "i" (&((char *)key)[branch]) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		 "b %l[l_yes]\n\t"
+		 "nop\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align 4\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection \n\t"
+		 : :  "i" (&((char *)key)[branch]) : : l_yes);
+
 	return false;
 l_yes:
 	return true;
diff --git a/arch/sparc/include/asm/mm-arch-hooks.h b/arch/sparc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b89ba44c16f1..000000000000
--- a/arch/sparc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_SPARC_MM_ARCH_HOOKS_H
-#define _ASM_SPARC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_SPARC_MM_ARCH_HOOKS_H */
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 1f0aa2024e94..6424249d5f78 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,16 +28,10 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
+
+#define VISExitHalf					\
+	VISExit
 
 #define VISEntryHalfFast(fail_label)			\
 	rd		%fprs, %o5;			\
@@ -47,7 +41,7 @@
 	ba,a,pt		%xcc, fail_label;		\
 297:	wr		%o5, FPRS_FEF, %fprs;
 
-#define VISExitHalf					\
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/uapi/asm/pstate.h b/arch/sparc/include/uapi/asm/pstate.h
index 4b6b998afd99..cf832e14aa05 100644
--- a/arch/sparc/include/uapi/asm/pstate.h
+++ b/arch/sparc/include/uapi/asm/pstate.h
@@ -88,7 +88,7 @@
 #define VERS_MAXTL	_AC(0x000000000000ff00,UL) /* Max Trap Level.	*/
 #define VERS_MAXWIN	_AC(0x000000000000001f,UL) /* Max RegWindow Idx.*/
 
-/* Compatability Feature Register (%asr26), SPARC-T4 and later  */
+/* Compatibility Feature Register (%asr26), SPARC-T4 and later  */
 #define CFR_AES		_AC(0x0000000000000001,UL) /* Supports AES opcodes     */
 #define CFR_DES		_AC(0x0000000000000002,UL) /* Supports DES opcodes     */
 #define CFR_KASUMI	_AC(0x0000000000000004,UL) /* Supports KASUMI opcodes  */
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 4033c23bdfa6..e22416ce56ea 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -210,21 +210,21 @@ struct irq_handler_data {
 
 static inline unsigned int irq_data_to_handle(struct irq_data *data)
 {
-	struct irq_handler_data *ihd = data->handler_data;
+	struct irq_handler_data *ihd = irq_data_get_irq_handler_data(data);
 
 	return ihd->dev_handle;
 }
 
 static inline unsigned int irq_data_to_ino(struct irq_data *data)
 {
-	struct irq_handler_data *ihd = data->handler_data;
+	struct irq_handler_data *ihd = irq_data_get_irq_handler_data(data);
 
 	return ihd->dev_ino;
 }
 
 static inline unsigned long irq_data_to_sysino(struct irq_data *data)
 {
-	struct irq_handler_data *ihd = data->handler_data;
+	struct irq_handler_data *ihd = irq_data_get_irq_handler_data(data);
 
 	return ihd->sysino;
 }
@@ -370,13 +370,15 @@ static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity)
 
 static void sun4u_irq_enable(struct irq_data *data)
 {
-	struct irq_handler_data *handler_data = data->handler_data;
+	struct irq_handler_data *handler_data;
 
+	handler_data = irq_data_get_irq_handler_data(data);
 	if (likely(handler_data)) {
 		unsigned long cpuid, imap, val;
 		unsigned int tid;
 
-		cpuid = irq_choose_cpu(data->irq, data->affinity);
+		cpuid = irq_choose_cpu(data->irq,
+				       irq_data_get_affinity_mask(data));
 		imap = handler_data->imap;
 
 		tid = sun4u_compute_tid(imap, cpuid);
@@ -393,8 +395,9 @@ static void sun4u_irq_enable(struct irq_data *data)
 static int sun4u_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask, bool force)
 {
-	struct irq_handler_data *handler_data = data->handler_data;
+	struct irq_handler_data *handler_data;
 
+	handler_data = irq_data_get_irq_handler_data(data);
 	if (likely(handler_data)) {
 		unsigned long cpuid, imap, val;
 		unsigned int tid;
@@ -438,15 +441,17 @@ static void sun4u_irq_disable(struct irq_data *data)
 
 static void sun4u_irq_eoi(struct irq_data *data)
 {
-	struct irq_handler_data *handler_data = data->handler_data;
+	struct irq_handler_data *handler_data;
 
+	handler_data = irq_data_get_irq_handler_data(data);
 	if (likely(handler_data))
 		upa_writeq(ICLR_IDLE, handler_data->iclr);
 }
 
 static void sun4v_irq_enable(struct irq_data *data)
 {
-	unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity);
+	unsigned long cpuid = irq_choose_cpu(data->irq,
+					     irq_data_get_affinity_mask(data));
 	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
@@ -508,7 +513,7 @@ static void sun4v_virq_enable(struct irq_data *data)
 	unsigned long cpuid;
 	int err;
 
-	cpuid = irq_choose_cpu(data->irq, data->affinity);
+	cpuid = irq_choose_cpu(data->irq, irq_data_get_affinity_mask(data));
 
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
@@ -881,8 +886,8 @@ void fixup_irqs(void)
 		if (desc->action && !irqd_is_per_cpu(data)) {
 			if (data->chip->irq_set_affinity)
 				data->chip->irq_set_affinity(data,
-							     data->affinity,
-							     false);
+					irq_data_get_affinity_mask(data),
+					false);
 		}
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 48565c11e82a..59bbeff55024 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -16,7 +16,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	u32 val;
 	u32 *insn = (u32 *) (unsigned long) entry->code;
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		s32 off = (s32)entry->target - (s32)entry->code;
 
 #ifdef CONFIG_SPARC64
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 9bbb8f2bbfcc..0299f052a2ef 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -126,7 +126,7 @@ static int leon_set_affinity(struct irq_data *data, const struct cpumask *dest,
 	int oldcpu, newcpu;
 
 	mask = (unsigned long)data->chip_data;
-	oldcpu = irq_choose_cpu(data->affinity);
+	oldcpu = irq_choose_cpu(irq_data_get_affinity_mask(data));
 	newcpu = irq_choose_cpu(dest);
 
 	if (oldcpu == newcpu)
@@ -149,7 +149,7 @@ static void leon_unmask_irq(struct irq_data *data)
 	int cpu;
 
 	mask = (unsigned long)data->chip_data;
-	cpu = irq_choose_cpu(data->affinity);
+	cpu = irq_choose_cpu(irq_data_get_affinity_mask(data));
 	spin_lock_irqsave(&leon_irq_lock, flags);
 	oldmask = LEON3_BYPASS_LOAD_PA(LEON_IMASK(cpu));
 	LEON3_BYPASS_STORE_PA(LEON_IMASK(cpu), (oldmask | mask));
@@ -162,7 +162,7 @@ static void leon_mask_irq(struct irq_data *data)
 	int cpu;
 
 	mask = (unsigned long)data->chip_data;
-	cpu = irq_choose_cpu(data->affinity);
+	cpu = irq_choose_cpu(irq_data_get_affinity_mask(data));
 	spin_lock_irqsave(&leon_irq_lock, flags);
 	oldmask = LEON3_BYPASS_LOAD_PA(LEON_IMASK(cpu));
 	LEON3_BYPASS_STORE_PA(LEON_IMASK(cpu), (oldmask & ~mask));
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index c928bc64b4ba..3a14a35592fe 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -249,7 +249,6 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm,
 					 struct pci_bus *bus, int devfn)
 {
 	struct dev_archdata *sd;
-	struct pci_slot *slot;
 	struct platform_device *op;
 	struct pci_dev *dev;
 	const char *type;
@@ -290,10 +289,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm,
 	dev->multifunction = 0;		/* maybe a lie? */
 	set_pcie_port_type(dev);
 
-	list_for_each_entry(slot, &dev->bus->slots, list)
-		if (PCI_SLOT(dev->devfn) == slot->number)
-			dev->slot = slot;
-
+	pci_dev_assign_slot(dev);
 	dev->vendor = of_getintprop_default(node, "vendor-id", 0xffff);
 	dev->device = of_getintprop_default(node, "device-id", 0xffff);
 	dev->subsystem_vendor =
@@ -918,7 +914,7 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 void arch_teardown_msi_irq(unsigned int irq)
 {
 	struct msi_desc *entry = irq_get_msi_desc(irq);
-	struct pci_dev *pdev = entry->dev;
+	struct pci_dev *pdev = msi_desc_to_pci_dev(entry);
 	struct pci_pbm_info *pbm = pdev->dev.archdata.host_controller;
 
 	if (pbm->teardown_msi_irq)
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 50e7b626afe8..c5113c7ce2fd 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -333,11 +333,11 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	childregs = (struct pt_regs *) (new_stack + STACKFRAME_SZ);
 
 	/*
-	 * A new process must start with interrupts closed in 2.5,
-	 * because this is how Mingo's scheduler works (see schedule_tail
-	 * and finish_arch_switch). If we do not do it, a timer interrupt hits
-	 * before we unlock, attempts to re-take the rq->lock, and then we die.
-	 * Thus, kpsr|=PSR_PIL.
+	 * A new process must start with interrupts disabled, see schedule_tail()
+	 * and finish_task_switch(). (If we do not do it and if a timer interrupt
+	 * hits before we unlock and attempts to take the rq->lock, we deadlock.)
+	 *
+	 * Thus, kpsr |= PSR_PIL.
 	 */
 	ti->ksp = (unsigned long) new_stack;
 	p->thread.kregs = childregs;
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index a1bb2675b280..a87d0e47c168 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -188,7 +188,7 @@ void sun4d_handler_irq(unsigned int pil, struct pt_regs *regs)
 
 static void sun4d_mask_irq(struct irq_data *data)
 {
-	struct sun4d_handler_data *handler_data = data->handler_data;
+	struct sun4d_handler_data *handler_data = irq_data_get_irq_handler_data(data);
 	unsigned int real_irq;
 #ifdef CONFIG_SMP
 	int cpuid = handler_data->cpuid;
@@ -206,7 +206,7 @@ static void sun4d_mask_irq(struct irq_data *data)
 
 static void sun4d_unmask_irq(struct irq_data *data)
 {
-	struct sun4d_handler_data *handler_data = data->handler_data;
+	struct sun4d_handler_data *handler_data = irq_data_get_irq_handler_data(data);
 	unsigned int real_irq;
 #ifdef CONFIG_SMP
 	int cpuid = handler_data->cpuid;
diff --git a/arch/sparc/kernel/sun4m_irq.c b/arch/sparc/kernel/sun4m_irq.c
index 8bb3b3fddea7..da737c712fa8 100644
--- a/arch/sparc/kernel/sun4m_irq.c
+++ b/arch/sparc/kernel/sun4m_irq.c
@@ -188,9 +188,10 @@ static unsigned long sun4m_imask[0x50] = {
 
 static void sun4m_mask_irq(struct irq_data *data)
 {
-	struct sun4m_handler_data *handler_data = data->handler_data;
+	struct sun4m_handler_data *handler_data;
 	int cpu = smp_processor_id();
 
+	handler_data = irq_data_get_irq_handler_data(data);
 	if (handler_data->mask) {
 		unsigned long flags;
 
@@ -206,9 +207,10 @@ static void sun4m_mask_irq(struct irq_data *data)
 
 static void sun4m_unmask_irq(struct irq_data *data)
 {
-	struct sun4m_handler_data *handler_data = data->handler_data;
+	struct sun4m_handler_data *handler_data;
 	int cpu = smp_processor_id();
 
+	handler_data = irq_data_get_irq_handler_data(data);
 	if (handler_data->mask) {
 		unsigned long flags;
 
diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c
index d3408e72d20c..278c40abce82 100644
--- a/arch/sparc/kernel/sun4m_smp.c
+++ b/arch/sparc/kernel/sun4m_smp.c
@@ -247,7 +247,7 @@ void smp4m_percpu_timer_interrupt(struct pt_regs *regs)
 
 	ce = &per_cpu(sparc32_clockevent, cpu);
 
-	if (ce->mode & CLOCK_EVT_MODE_PERIODIC)
+	if (clockevent_state_periodic(ce))
 		sun4m_clear_profile_irq(cpu);
 	else
 		sparc_config.load_profile_irq(cpu, 0); /* Is this needless? */
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index c9692f387cee..1affabc96b08 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -101,21 +101,18 @@ irqreturn_t notrace timer_interrupt(int dummy, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void timer_ce_set_mode(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int timer_ce_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-		case CLOCK_EVT_MODE_PERIODIC:
-		case CLOCK_EVT_MODE_RESUME:
-			timer_ce_enabled = 1;
-			break;
-		case CLOCK_EVT_MODE_SHUTDOWN:
-			timer_ce_enabled = 0;
-			break;
-		default:
-			break;
-	}
+	timer_ce_enabled = 0;
+	smp_mb();
+	return 0;
+}
+
+static int timer_ce_set_periodic(struct clock_event_device *evt)
+{
+	timer_ce_enabled = 1;
 	smp_mb();
+	return 0;
 }
 
 static __init void setup_timer_ce(void)
@@ -127,7 +124,9 @@ static __init void setup_timer_ce(void)
 	ce->name     = "timer_ce";
 	ce->rating   = 100;
 	ce->features = CLOCK_EVT_FEAT_PERIODIC;
-	ce->set_mode = timer_ce_set_mode;
+	ce->set_state_shutdown = timer_ce_shutdown;
+	ce->set_state_periodic = timer_ce_set_periodic;
+	ce->tick_resume = timer_ce_set_periodic;
 	ce->cpumask  = cpu_possible_mask;
 	ce->shift    = 32;
 	ce->mult     = div_sc(sparc_config.clock_rate, NSEC_PER_SEC,
@@ -183,24 +182,20 @@ static __init int setup_timer_cs(void)
 }
 
 #ifdef CONFIG_SMP
-static void percpu_ce_setup(enum clock_event_mode mode,
-			struct clock_event_device *evt)
+static int percpu_ce_shutdown(struct clock_event_device *evt)
 {
 	int cpu = cpumask_first(evt->cpumask);
 
-	switch (mode) {
-		case CLOCK_EVT_MODE_PERIODIC:
-			sparc_config.load_profile_irq(cpu,
-						      SBUS_CLOCK_RATE / HZ);
-			break;
-		case CLOCK_EVT_MODE_ONESHOT:
-		case CLOCK_EVT_MODE_SHUTDOWN:
-		case CLOCK_EVT_MODE_UNUSED:
-			sparc_config.load_profile_irq(cpu, 0);
-			break;
-		default:
-			break;
-	}
+	sparc_config.load_profile_irq(cpu, 0);
+	return 0;
+}
+
+static int percpu_ce_set_periodic(struct clock_event_device *evt)
+{
+	int cpu = cpumask_first(evt->cpumask);
+
+	sparc_config.load_profile_irq(cpu, SBUS_CLOCK_RATE / HZ);
+	return 0;
 }
 
 static int percpu_ce_set_next_event(unsigned long delta,
@@ -224,7 +219,9 @@ void register_percpu_ce(int cpu)
 	ce->name           = "percpu_ce";
 	ce->rating         = 200;
 	ce->features       = features;
-	ce->set_mode       = percpu_ce_setup;
+	ce->set_state_shutdown = percpu_ce_shutdown;
+	ce->set_state_periodic = percpu_ce_set_periodic;
+	ce->set_state_oneshot = percpu_ce_shutdown;
 	ce->set_next_event = percpu_ce_set_next_event;
 	ce->cpumask        = cpumask_of(cpu);
 	ce->shift          = 32;
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 2e6035c0a8ca..c69b21e51efc 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -674,32 +674,19 @@ static int sparc64_next_event(unsigned long delta,
 	return tick_ops->add_compare(delta) ? -ETIME : 0;
 }
 
-static void sparc64_timer_setup(enum clock_event_mode mode,
-				struct clock_event_device *evt)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		tick_ops->disable_irq();
-		break;
-
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_UNUSED:
-		WARN_ON(1);
-		break;
-	}
+static int sparc64_timer_shutdown(struct clock_event_device *evt)
+{
+	tick_ops->disable_irq();
+	return 0;
 }
 
 static struct clock_event_device sparc64_clockevent = {
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= sparc64_timer_setup,
-	.set_next_event	= sparc64_next_event,
-	.rating		= 100,
-	.shift		= 30,
-	.irq		= -1,
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= sparc64_timer_shutdown,
+	.set_next_event		= sparc64_next_event,
+	.rating			= 100,
+	.shift			= 30,
+	.irq			= -1,
 };
 static DEFINE_PER_CPU(struct clock_event_device, sparc64_events);
 
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 140527a20e7d..83aeeb1dffdb 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -240,8 +240,11 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+	VISExitHalfFast
+#else
 	VISExitHalf
-
+#endif
 	brz,pn		%o2, .Lexit
 	 cmp		%o2, 19
 	ble,pn		%icc, .Lsmall_unaligned
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9e2e2e..a063d84336d6 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 71cd65ab200c..b9d63c0a7aab 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,22 +27,38 @@ static DEFINE_SPINLOCK(dummy);
 
 #endif /* SMP */
 
-#define ATOMIC_OP(op, cop)						\
+#define ATOMIC_OP_RETURN(op, c_op)					\
 int atomic_##op##_return(int i, atomic_t *v)				\
 {									\
 	int ret;							\
 	unsigned long flags;						\
 	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
 									\
-	ret = (v->counter cop i);					\
+	ret = (v->counter c_op i);					\
 									\
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
 	return ret;							\
 }									\
 EXPORT_SYMBOL(atomic_##op##_return);
 
-ATOMIC_OP(add, +=)
+#define ATOMIC_OP(op, c_op)						\
+void atomic_##op(int i, atomic_t *v)					\
+{									\
+	unsigned long flags;						\
+	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
+									\
+	v->counter c_op i;						\
+									\
+	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
+}									\
+EXPORT_SYMBOL(atomic_##op);
+
+ATOMIC_OP_RETURN(add, +=)
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
 
+#undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
 int atomic_xchg(atomic_t *v, int new)
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index 05dac43907d1..d6b0363f345b 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -47,6 +47,9 @@ ENDPROC(atomic_##op##_return);
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
@@ -84,6 +87,9 @@ ENDPROC(atomic64_##op##_return);
 
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1d649a95660c..8eb454cfe05c 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -111,6 +111,9 @@ EXPORT_SYMBOL(atomic64_##op##_return);
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
@@ -135,10 +138,6 @@ EXPORT_SYMBOL(copy_user_page);
 void VISenter(void);
 EXPORT_SYMBOL(VISenter);
 
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
 extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
 extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
 		unsigned long *);
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 7931eeeb649a..f8b9f71b9a2b 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -807,7 +807,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 	}
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(flen, proglen, pass, image);
+		bpf_jit_dump(flen, proglen, pass + 1, image);
 
 	if (image) {
 		bpf_flush_icache(image, image + proglen);
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 9def1f52d03a..2ba12d761723 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -32,6 +32,7 @@ config TILE
 	select EDAC_SUPPORT
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select HAVE_ARCH_SECCOMP_FILTER
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
@@ -221,6 +222,22 @@ config COMPAT
 	  If enabled, the kernel will support running TILE-Gx binaries
 	  that were built with the -m32 option.
 
+config SECCOMP
+	bool "Enable seccomp to safely compute untrusted bytecode"
+	depends on PROC_FS
+	help
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl, it cannot be disabled and the task is only
+	  allowed to execute a few safe syscalls defined by each seccomp
+	  mode.
+
+	  If unsure, say N.
+
 config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index d53654488c2c..ba35c41c71ff 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -19,6 +19,7 @@ generic-y += irq_regs.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
@@ -27,6 +28,7 @@ generic-y += poll.h
 generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
+generic-y += seccomp.h
 generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index 1b109fad9fff..d320ce253d86 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -34,6 +34,19 @@ static inline void atomic_add(int i, atomic_t *v)
 	_atomic_xchg_add(&v->counter, i);
 }
 
+#define ATOMIC_OP(op)							\
+unsigned long _atomic_##op(volatile unsigned long *p, unsigned long mask); \
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	_atomic_##op((unsigned long *)&v->counter, i);			\
+}
+
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
 /**
  * atomic_add_return - add integer and return
  * @v: pointer of type atomic_t
@@ -113,6 +126,17 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	_atomic64_xchg_add(&v->counter, i);
 }
 
+#define ATOMIC64_OP(op)						\
+long long _atomic64_##op(long long *v, long long n);		\
+static inline void atomic64_##op(long long i, atomic64_t *v)	\
+{								\
+	_atomic64_##op(&v->counter, i);				\
+}
+
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
+
 /**
  * atomic64_add_return - add integer and return
  * @v: pointer of type atomic64_t
@@ -225,6 +249,7 @@ extern struct __get_user __atomic_xchg_add(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
 						  int *lock, int o, int n);
 extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic_and(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
 extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
@@ -234,6 +259,9 @@ extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
 					long long n);
 extern long long __atomic64_xchg_add_unless(volatile long long *p,
 					int *lock, long long o, long long n);
+extern long long __atomic64_and(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_or(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_xor(volatile long long *p, int *lock, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 0496970cef82..096a56d6ead4 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -58,6 +58,26 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return oldval;
 }
 
+static inline void atomic_and(int i, atomic_t *v)
+{
+	__insn_fetchand4((void *)&v->counter, i);
+}
+
+static inline void atomic_or(int i, atomic_t *v)
+{
+	__insn_fetchor4((void *)&v->counter, i);
+}
+
+static inline void atomic_xor(int i, atomic_t *v)
+{
+	int guess, oldval = v->counter;
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch4(&v->counter, guess ^ i);
+	} while (guess != oldval);
+}
+
 /* Now the true 64-bit operations. */
 
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -91,6 +111,26 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 	return oldval != u;
 }
 
+static inline void atomic64_and(long i, atomic64_t *v)
+{
+	__insn_fetchand((void *)&v->counter, i);
+}
+
+static inline void atomic64_or(long i, atomic64_t *v)
+{
+	__insn_fetchor((void *)&v->counter, i);
+}
+
+static inline void atomic64_xor(long i, atomic64_t *v)
+{
+	long guess, oldval = v->counter;
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch(&v->counter, guess ^ i);
+	} while (guess != oldval);
+}
+
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1, (v))
diff --git a/arch/tile/include/asm/elf.h b/arch/tile/include/asm/elf.h
index 41d9878a9686..c505d77e4d06 100644
--- a/arch/tile/include/asm/elf.h
+++ b/arch/tile/include/asm/elf.h
@@ -22,6 +22,7 @@
 #include <arch/chip.h>
 
 #include <linux/ptrace.h>
+#include <linux/elf-em.h>
 #include <asm/byteorder.h>
 #include <asm/page.h>
 
@@ -30,9 +31,6 @@ typedef unsigned long elf_greg_t;
 #define ELF_NGREG (sizeof(struct pt_regs) / sizeof(elf_greg_t))
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
-#define EM_TILEPRO 188
-#define EM_TILEGX  191
-
 /* Provide a nominal data structure. */
 #define ELF_NFPREG	0
 typedef double elf_fpreg_t;
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index dc61de15c1f9..322b5fe94781 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -55,6 +55,7 @@ extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_wc(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_wt(physaddr, size)		ioremap(physaddr, size)
+#define ioremap_uc(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_fullcache(physaddr, size)	ioremap(physaddr, size)
 
 #define mmiowb()
diff --git a/arch/tile/include/asm/mm-arch-hooks.h b/arch/tile/include/asm/mm-arch-hooks.h
deleted file mode 100644
index d1709ea774f7..000000000000
--- a/arch/tile/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_TILE_MM_ARCH_HOOKS_H
-#define _ASM_TILE_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_TILE_MM_ARCH_HOOKS_H */
diff --git a/arch/tile/include/asm/switch_to.h b/arch/tile/include/asm/switch_to.h
index b8f888cbe6b0..34ee72705521 100644
--- a/arch/tile/include/asm/switch_to.h
+++ b/arch/tile/include/asm/switch_to.h
@@ -53,15 +53,13 @@ extern unsigned long get_switch_to_pc(void);
  * Kernel threads can check to see if they need to migrate their
  * stack whenever they return from a context switch; for user
  * threads, we defer until they are returning to user-space.
+ * We defer homecache migration until the runqueue lock is released.
  */
-#define finish_arch_switch(prev) do {                                     \
-	if (unlikely((prev)->state == TASK_DEAD))                         \
-		__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_EXIT |       \
-			((prev)->pid << _SIM_CONTROL_OPERATOR_BITS));     \
+#define finish_arch_post_lock_switch() do {                               \
 	__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_SWITCH |             \
 		(current->pid << _SIM_CONTROL_OPERATOR_BITS));            \
 	if (current->mm == NULL && !kstack_hash &&                        \
-	    current_thread_info()->homecache_cpu != smp_processor_id())   \
+	    current_thread_info()->homecache_cpu != raw_smp_processor_id()) \
 		homecache_migrate_kthread();                              \
 } while (0)
 
diff --git a/arch/tile/include/asm/syscall.h b/arch/tile/include/asm/syscall.h
index 9644b88f133d..373d73064ea1 100644
--- a/arch/tile/include/asm/syscall.h
+++ b/arch/tile/include/asm/syscall.h
@@ -20,6 +20,8 @@
 
 #include <linux/sched.h>
 #include <linux/err.h>
+#include <linux/audit.h>
+#include <linux/compat.h>
 #include <arch/abi.h>
 
 /* The array of function pointers for syscalls. */
@@ -61,7 +63,15 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	regs->regs[0] = (long) error ?: val;
+	if (error) {
+		/* R0 is the passed-in negative error, R1 is positive. */
+		regs->regs[0] = error;
+		regs->regs[1] = -error;
+	} else {
+		/* R1 set to zero to indicate no error. */
+		regs->regs[0] = val;
+		regs->regs[1] = 0;
+	}
 }
 
 static inline void syscall_get_arguments(struct task_struct *task,
@@ -82,4 +92,20 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs[i], args, n * sizeof(args[0]));
 }
 
+/*
+ * We don't care about endianness (__AUDIT_ARCH_LE bit) here because
+ * tile has the same system calls both on little- and big- endian.
+ */
+static inline int syscall_get_arch(void)
+{
+	if (is_compat_task())
+		return AUDIT_ARCH_TILEGX32;
+
+#ifdef CONFIG_TILEGX
+	return AUDIT_ARCH_TILEGX;
+#else
+	return AUDIT_ARCH_TILEPRO;
+#endif
+}
+
 #endif	/* _ASM_TILE_SYSCALL_H */
diff --git a/arch/tile/include/uapi/arch/opcode_tilegx.h b/arch/tile/include/uapi/arch/opcode_tilegx.h
index d76ff2db745e..9e46eaa847d4 100644
--- a/arch/tile/include/uapi/arch/opcode_tilegx.h
+++ b/arch/tile/include/uapi/arch/opcode_tilegx.h
@@ -830,11 +830,11 @@ enum
   ADDX_RRR_0_OPCODE_X0 = 2,
   ADDX_RRR_0_OPCODE_X1 = 2,
   ADDX_RRR_0_OPCODE_Y0 = 0,
-  ADDX_SPECIAL_0_OPCODE_Y1 = 0,
+  ADDX_RRR_0_OPCODE_Y1 = 0,
   ADD_RRR_0_OPCODE_X0 = 3,
   ADD_RRR_0_OPCODE_X1 = 3,
   ADD_RRR_0_OPCODE_Y0 = 1,
-  ADD_SPECIAL_0_OPCODE_Y1 = 1,
+  ADD_RRR_0_OPCODE_Y1 = 1,
   ANDI_IMM8_OPCODE_X0 = 3,
   ANDI_IMM8_OPCODE_X1 = 3,
   ANDI_OPCODE_Y0 = 2,
@@ -995,6 +995,7 @@ enum
   LD4U_ADD_IMM8_OPCODE_X1 = 12,
   LD4U_OPCODE_Y2 = 2,
   LD4U_UNARY_OPCODE_X1 = 20,
+  LDNA_ADD_IMM8_OPCODE_X1 = 21,
   LDNA_UNARY_OPCODE_X1 = 21,
   LDNT1S_ADD_IMM8_OPCODE_X1 = 13,
   LDNT1S_UNARY_OPCODE_X1 = 22,
@@ -1015,7 +1016,6 @@ enum
   LD_UNARY_OPCODE_X1 = 29,
   LNK_UNARY_OPCODE_X1 = 30,
   LNK_UNARY_OPCODE_Y1 = 14,
-  LWNA_ADD_IMM8_OPCODE_X1 = 21,
   MFSPR_IMM8_OPCODE_X1 = 22,
   MF_UNARY_OPCODE_X1 = 31,
   MM_BF_OPCODE_X0 = 7,
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index e8c2c04143cd..c667e104a0c2 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
 		return -EFAULT;
 
-	memset(to, 0, sizeof(*to));
-
 	err = __get_user(to->si_signo, &from->si_signo);
 	err |= __get_user(to->si_errno, &from->si_errno);
 	err |= __get_user(to->si_code, &from->si_code);
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index cdbda45a4e4b..fbbe2ea882ea 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -1224,6 +1224,7 @@ handle_syscall:
 	 jal    do_syscall_trace_enter
 	}
 	FEEDBACK_REENTER(handle_syscall)
+	blz     r0, .Lsyscall_sigreturn_skip
 
 	/*
 	 * We always reload our registers from the stack at this
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 800b91d3f9dc..58964d209d4d 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -1247,6 +1247,7 @@ handle_syscall:
 	 jal    do_syscall_trace_enter
 	}
 	FEEDBACK_REENTER(handle_syscall)
+	bltz    r0, .Lsyscall_sigreturn_skip
 
 	/*
 	 * We always reload our registers from the stack at this
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index b1df847d0686..b3f73fd764a3 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -304,11 +304,12 @@ static struct irq_chip tilegx_legacy_irq_chip = {
  * to Linux which just calls handle_level_irq() after clearing the
  * MAC INTx Assert status bit associated with this interrupt.
  */
-static void trio_handle_level_irq(unsigned int irq, struct irq_desc *desc)
+static void trio_handle_level_irq(unsigned int __irq, struct irq_desc *desc)
 {
 	struct pci_controller *controller = irq_desc_get_handler_data(desc);
 	gxio_trio_context_t *trio_context = controller->trio;
 	uint64_t intx = (uint64_t)irq_desc_get_chip_data(desc);
+	unsigned int irq = irq_desc_get_irq(desc);
 	int mac = controller->mac;
 	unsigned int reg_offset;
 	uint64_t level_mask;
@@ -1442,7 +1443,7 @@ static struct pci_ops tile_cfg_ops = {
 /* MSI support starts here. */
 static unsigned int tilegx_msi_startup(struct irq_data *d)
 {
-	if (d->msi_desc)
+	if (irq_data_get_msi_desc(d))
 		pci_msi_unmask_irq(d);
 
 	return 0;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index a45213781ad0..7d5769310bef 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -446,6 +446,11 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
 	hardwall_switch_tasks(prev, next);
 #endif
 
+	/* Notify the simulator of task exit. */
+	if (unlikely(prev->state == TASK_DEAD))
+		__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_EXIT |
+			     (prev->pid << _SIM_CONTROL_OPERATOR_BITS));
+
 	/*
 	 * Switch kernel SP, PC, and callee-saved registers.
 	 * In the context of the new task, return the old task pointer
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index f84eed8243da..bdc126faf741 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -262,6 +262,9 @@ int do_syscall_trace_enter(struct pt_regs *regs)
 	if (work & _TIF_NOHZ)
 		user_exit();
 
+	if (secure_computing() == -1)
+		return -1;
+
 	if (work & _TIF_SYSCALL_TRACE) {
 		if (tracehook_report_syscall_entry(regs))
 			regs->regs[TREG_SYSCALL_NR] = -1;
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 99c9ff87e018..6b755d125783 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1139,7 +1139,7 @@ static void __init load_hv_initrd(void)
 
 void __init free_initrd_mem(unsigned long begin, unsigned long end)
 {
-	free_bootmem(__pa(begin), end - begin);
+	free_bootmem_late(__pa(begin), end - begin);
 }
 
 static int __init setup_initrd(char *str)
diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c
index a3ed12f8f83b..825867c53853 100644
--- a/arch/tile/kernel/sysfs.c
+++ b/arch/tile/kernel/sysfs.c
@@ -198,16 +198,13 @@ static int hv_stats_device_add(struct device *dev, struct subsys_interface *sif)
 	return err;
 }
 
-static int hv_stats_device_remove(struct device *dev,
-				  struct subsys_interface *sif)
+static void hv_stats_device_remove(struct device *dev,
+				   struct subsys_interface *sif)
 {
 	int cpu = dev->id;
 
-	if (!cpu_online(cpu))
-		return 0;
-
-	sysfs_remove_file(&dev->kobj, &dev_attr_hv_stats.attr);
-	return 0;
+	if (cpu_online(cpu))
+		sysfs_remove_file(&dev->kobj, &dev_attr_hv_stats.attr);
 }
 
 
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 00178ecf9aea..178989e6d3e3 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -140,10 +140,10 @@ static int tile_timer_set_next_event(unsigned long ticks,
  * Whenever anyone tries to change modes, we just mask interrupts
  * and wait for the next event to get set.
  */
-static void tile_timer_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int tile_timer_shutdown(struct clock_event_device *evt)
 {
 	arch_local_irq_mask_now(INT_TILE_TIMER);
+	return 0;
 }
 
 /*
@@ -157,7 +157,9 @@ static DEFINE_PER_CPU(struct clock_event_device, tile_timer) = {
 	.rating = 100,
 	.irq = -1,
 	.set_next_event = tile_timer_set_next_event,
-	.set_mode = tile_timer_set_mode,
+	.set_state_shutdown = tile_timer_shutdown,
+	.set_state_oneshot = tile_timer_shutdown,
+	.tick_resume = tile_timer_shutdown,
 };
 
 void setup_tile_timer(void)
diff --git a/arch/tile/kernel/vdso/Makefile b/arch/tile/kernel/vdso/Makefile
index a025f63d54cd..c54fff37b5ff 100644
--- a/arch/tile/kernel/vdso/Makefile
+++ b/arch/tile/kernel/vdso/Makefile
@@ -54,7 +54,7 @@ $(obj)/built-in.o: $(obj)/vdso-syms.o
 $(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
 
 SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
-                            $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+                            $(call cc-ldoption, -Wl$(comma)--hash-style=both)
 SYSCFLAGS_vdso_syms.o = -r
 $(obj)/vdso-syms.o: $(src)/vdso.lds $(obj)/vrt_sigreturn.o FORCE
 	$(call if_changed,vdsold)
@@ -113,6 +113,6 @@ $(obj)/vrt_sigreturn32.o: $(obj)/vrt_sigreturn.S
 $(obj)/vdso32.o: $(obj)/vdso32.so
 
 SYSCFLAGS_vdso32.so.dbg = -m32 -shared -s -Wl,-soname=linux-vdso32.so.1 \
-			    $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+			    $(call cc-ldoption, -Wl$(comma)--hash-style=both)
 $(obj)/vdso32.so.dbg: $(src)/vdso.lds $(obj-vdso32)
 	$(call if_changed,vdsold)
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index c89b211fd9e7..298df1e9912a 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -94,6 +94,12 @@ unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask)
 }
 EXPORT_SYMBOL(_atomic_or);
 
+unsigned long _atomic_and(volatile unsigned long *p, unsigned long mask)
+{
+	return __atomic_and((int *)p, __atomic_setup(p), mask).val;
+}
+EXPORT_SYMBOL(_atomic_and);
+
 unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask)
 {
 	return __atomic_andn((int *)p, __atomic_setup(p), mask).val;
@@ -136,6 +142,23 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
+long long _atomic64_and(long long *v, long long n)
+{
+	return __atomic64_and(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_and);
+
+long long _atomic64_or(long long *v, long long n)
+{
+	return __atomic64_or(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_or);
+
+long long _atomic64_xor(long long *v, long long n)
+{
+	return __atomic64_xor(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_xor);
 
 /*
  * If any of the atomic or futex routines hit a bad address (not in
diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index 6bda3132cd61..f611265633d6 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -178,6 +178,7 @@ atomic_op _xchg_add, 32, "add r24, r22, r2"
 atomic_op _xchg_add_unless, 32, \
 	"sne r26, r22, r2; { bbns r26, 3f; add r24, r22, r3 }"
 atomic_op _or, 32, "or r24, r22, r2"
+atomic_op _and, 32, "and r24, r22, r2"
 atomic_op _andn, 32, "nor r2, r2, zero; and r24, r22, r2"
 atomic_op _xor, 32, "xor r24, r22, r2"
 
@@ -191,6 +192,9 @@ atomic_op 64_xchg_add_unless, 64, \
 	{ bbns r26, 3f; add r24, r22, r4 }; \
 	{ bbns r27, 3f; add r25, r23, r5 }; \
 	slt_u r26, r24, r22; add r25, r25, r26"
+atomic_op 64_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
+atomic_op 64_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
+atomic_op 64_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
 
 	jrp     lr              /* happy backtracer */
 
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
index 88c7016492c4..97bbb6060b25 100644
--- a/arch/tile/lib/memcpy_user_64.c
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -28,7 +28,7 @@
 #define _ST(p, inst, v)						\
 	({							\
 		asm("1: " #inst " %0, %1;"			\
-		    ".pushsection .coldtext.memcpy,\"ax\";"	\
+		    ".pushsection .coldtext,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
 		    ".align 8;"					\
@@ -41,7 +41,7 @@
 	({							\
 		unsigned long __v;				\
 		asm("1: " #inst " %0, %1;"			\
-		    ".pushsection .coldtext.memcpy,\"ax\";"	\
+		    ".pushsection .coldtext,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
 		    ".align 8;"					\
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 3d63ff6f583f..149ec55f9c46 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += irq_regs.h
 generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += pci.h
diff --git a/arch/um/include/asm/mm-arch-hooks.h b/arch/um/include/asm/mm-arch-hooks.h
deleted file mode 100644
index a7c8b0dfdd4e..000000000000
--- a/arch/um/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_UM_MM_ARCH_HOOKS_H
-#define _ASM_UM_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_UM_MM_ARCH_HOOKS_H */
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index 83a91f976330..35ab97e4bb9b 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -22,7 +22,8 @@ extern int kmalloc_ok;
 extern unsigned long alloc_stack(int order, int atomic);
 extern void free_stack(unsigned long stack, int order);
 
-extern int do_signal(void);
+struct pt_regs;
+extern void do_signal(struct pt_regs *regs);
 extern void interrupt_end(void);
 extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs);
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 68b9119841cd..a6d922672b9f 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -90,12 +90,14 @@ void *__switch_to(struct task_struct *from, struct task_struct *to)
 
 void interrupt_end(void)
 {
+	struct pt_regs *regs = &current->thread.regs;
+
 	if (need_resched())
 		schedule();
 	if (test_thread_flag(TIF_SIGPENDING))
-		do_signal();
+		do_signal(regs);
 	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
-		tracehook_notify_resume(&current->thread.regs);
+		tracehook_notify_resume(regs);
 }
 
 void exit_thread(void)
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 4f60e4aad790..57acbd67d85d 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -64,7 +64,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	signal_setup_done(err, ksig, singlestep);
 }
 
-static int kern_do_signal(struct pt_regs *regs)
+void do_signal(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 	int handled_sig = 0;
@@ -110,10 +110,4 @@ static int kern_do_signal(struct pt_regs *regs)
 	 */
 	if (!handled_sig)
 		restore_saved_sigmask();
-	return handled_sig;
-}
-
-int do_signal(void)
-{
-	return kern_do_signal(&current->thread.regs);
 }
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 117568d4f64a..5af441efb377 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -22,23 +22,16 @@ void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 	local_irq_restore(flags);
 }
 
-static void itimer_set_mode(enum clock_event_mode mode,
-			    struct clock_event_device *evt)
+static int itimer_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		set_interval();
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_ONESHOT:
-		disable_timer();
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	disable_timer();
+	return 0;
+}
+
+static int itimer_set_periodic(struct clock_event_device *evt)
+{
+	set_interval();
+	return 0;
 }
 
 static int itimer_next_event(unsigned long delta,
@@ -48,14 +41,17 @@ static int itimer_next_event(unsigned long delta,
 }
 
 static struct clock_event_device itimer_clockevent = {
-	.name		= "itimer",
-	.rating		= 250,
-	.cpumask	= cpu_all_mask,
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= itimer_set_mode,
-	.set_next_event = itimer_next_event,
-	.shift		= 32,
-	.irq		= 0,
+	.name			= "itimer",
+	.rating			= 250,
+	.cpumask		= cpu_all_mask,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= itimer_shutdown,
+	.set_state_periodic	= itimer_set_periodic,
+	.set_state_oneshot	= itimer_shutdown,
+	.set_next_event		= itimer_next_event,
+	.shift			= 32,
+	.irq			= 0,
 };
 
 static irqreturn_t um_timer(int irq, void *dev)
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index f1b3eb14b855..2077248e8a72 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -291,7 +291,7 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 		/* We are under mmap_sem, release it such that current can terminate */
 		up_write(&current->mm->mmap_sem);
 		force_sig(SIGKILL, current);
-		do_signal();
+		do_signal(&current->thread.regs);
 	}
 }
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 557232f758b6..d8a9fce6ee2e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -173,7 +173,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip)
 void fatal_sigsegv(void)
 {
 	force_sigsegv(SIGSEGV, current);
-	do_signal();
+	do_signal(&current->thread.regs);
 	/*
 	 * This is to tell gcc that we're not returning - do_signal
 	 * can, in general, return, but in this case, it's not, since
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index d12b377b5a8b..1fc7a286dc6f 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -26,6 +26,7 @@ generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
diff --git a/arch/unicore32/include/asm/mm-arch-hooks.h b/arch/unicore32/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 4d79a850c509..000000000000
--- a/arch/unicore32/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_UNICORE32_MM_ARCH_HOOKS_H
-#define _ASM_UNICORE32_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_UNICORE32_MM_ARCH_HOOKS_H */
diff --git a/arch/unicore32/kernel/irq.c b/arch/unicore32/kernel/irq.c
index 0be5ccd7ccd2..c53729d92e8d 100644
--- a/arch/unicore32/kernel/irq.c
+++ b/arch/unicore32/kernel/irq.c
@@ -112,10 +112,9 @@ static struct irq_chip puv3_low_gpio_chip = {
  * irq_controller_lock held, and IRQs disabled.  Decode the IRQ
  * and call the handler.
  */
-static void
-puv3_gpio_handler(unsigned int irq, struct irq_desc *desc)
+static void puv3_gpio_handler(unsigned int __irq, struct irq_desc *desc)
 {
-	unsigned int mask;
+	unsigned int mask, irq;
 
 	mask = readl(GPIO_GEDR);
 	do {
diff --git a/arch/unicore32/kernel/time.c b/arch/unicore32/kernel/time.c
index d3824b2ff644..ac4c5449bb88 100644
--- a/arch/unicore32/kernel/time.c
+++ b/arch/unicore32/kernel/time.c
@@ -46,29 +46,20 @@ puv3_osmr0_set_next_event(unsigned long delta, struct clock_event_device *c)
 	return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0;
 }
 
-static void
-puv3_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *c)
+static int puv3_osmr0_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		writel(readl(OST_OIER) & ~OST_OIER_E0, OST_OIER);
-		writel(readl(OST_OSSR) & ~OST_OSSR_M0, OST_OSSR);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		break;
-	}
+	writel(readl(OST_OIER) & ~OST_OIER_E0, OST_OIER);
+	writel(readl(OST_OSSR) & ~OST_OSSR_M0, OST_OSSR);
+	return 0;
 }
 
 static struct clock_event_device ckevt_puv3_osmr0 = {
-	.name		= "osmr0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= puv3_osmr0_set_next_event,
-	.set_mode	= puv3_osmr0_set_mode,
+	.name			= "osmr0",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= puv3_osmr0_set_next_event,
+	.set_state_shutdown	= puv3_osmr0_shutdown,
+	.set_state_oneshot	= puv3_osmr0_shutdown,
 };
 
 static cycle_t puv3_read_oscr(struct clocksource *cs)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 55bced17dc95..117e2f373e50 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -41,6 +41,8 @@ config X86
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP
+	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
 	select ARCH_WANT_OPTIONAL_GPIOLIB
@@ -132,7 +134,7 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_UID16			if X86_32
+	select HAVE_UID16			if X86_32 || IA32_EMULATION
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
 	select IRQ_FORCED_THREADING
@@ -254,6 +256,11 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0xdffffc0000000000
+
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
@@ -949,6 +956,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
 
 config X86_MCE
 	bool "Machine Check / overheating reporting"
+	select GENERIC_ALLOCATOR
 	default y
 	---help---
 	  Machine Check support allows the processor to notify the
@@ -996,19 +1004,41 @@ config X86_THERMAL_VECTOR
 	def_bool y
 	depends on X86_MCE_INTEL
 
-config VM86
-	bool "Enable VM86 support" if EXPERT
-	default y
+config X86_LEGACY_VM86
+	bool "Legacy VM86 support (obsolete)"
+	default n
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run
-	  16-bit real mode legacy code on x86 processors. It also may
-	  be needed by software like XFree86 to initialize some video
-	  cards via BIOS. Disabling this option saves about 6K.
+	  This option allows user programs to put the CPU into V8086
+	  mode, which is an 80286-era approximation of 16-bit real mode.
+
+	  Some very old versions of X and/or vbetool require this option
+	  for user mode setting.  Similarly, DOSEMU will use it if
+	  available to accelerate real mode DOS programs.  However, any
+	  recent version of DOSEMU, X, or vbetool should be fully
+	  functional even without kernel VM86 support, as they will all
+	  fall back to (pretty well performing) software emulation.
+
+	  Anything that works on a 64-bit kernel is unlikely to need
+	  this option, as 64-bit kernels don't, and can't, support V8086
+	  mode.  This option is also unrelated to 16-bit protected mode
+	  and is not needed to run most 16-bit programs under Wine.
+
+	  Enabling this option adds considerable attack surface to the
+	  kernel and slows down system calls and exception handling.
+
+	  Unless you use very old userspace or need the last drop of
+	  performance in your real mode DOS games and can't use KVM,
+	  say N here.
+
+config VM86
+       bool
+       default X86_LEGACY_VM86
 
 config X86_16BIT
 	bool "Enable support for 16-bit segments" if EXPERT
 	default y
+	depends on MODIFY_LDT_SYSCALL
 	---help---
 	  This option is required by programs like Wine to run 16-bit
 	  protected mode legacy code on x86 processors.  Disabling
@@ -1503,6 +1533,7 @@ config X86_RESERVE_LOW
 
 config MATH_EMULATION
 	bool
+	depends on MODIFY_LDT_SYSCALL
 	prompt "Math emulation" if X86_32
 	---help---
 	  Linux can emulate a math coprocessor (used for floating point
@@ -2015,7 +2046,7 @@ config CMDLINE_BOOL
 
 	  To compile command line arguments into the kernel,
 	  set this option to 'Y', then fill in the
-	  the boot arguments in CONFIG_CMDLINE.
+	  boot arguments in CONFIG_CMDLINE.
 
 	  Systems with fully functional boot loaders (i.e. non-embedded)
 	  should leave this option set to 'N'.
@@ -2047,6 +2078,22 @@ config CMDLINE_OVERRIDE
 	  This is used to work around broken boot loaders.  This should
 	  be set to 'N' under normal conditions.
 
+config MODIFY_LDT_SYSCALL
+	bool "Enable the LDT (local descriptor table)" if EXPERT
+	default y
+	---help---
+	  Linux can allow user programs to install a per-process x86
+	  Local Descriptor Table (LDT) using the modify_ldt(2) system
+	  call.  This is required to run 16-bit or segmented code such as
+	  DOSEMU or some Wine programs.  It is also used by some very old
+	  threading libraries.
+
+	  Enabling this feature adds a small amount of overhead to
+	  context switches and increases the low-level kernel attack
+	  surface.  Disabling it removes the modify_ldt(2) system call.
+
+	  Saying 'N' here may make sense for embedded or server kernels.
+
 source "kernel/livepatch/Kconfig"
 
 endmenu
@@ -2516,7 +2563,7 @@ config IA32_EMULATION
 	depends on X86_64
 	select BINFMT_ELF
 	select COMPAT_BINFMT_ELF
-	select HAVE_UID16
+	select ARCH_WANT_OLD_COMPAT_IPC
 	---help---
 	  Include code to run legacy 32-bit programs under a
 	  64-bit kernel. You should likely turn this on, unless you're
@@ -2530,7 +2577,7 @@ config IA32_AOUT
 
 config X86_X32
 	bool "x32 ABI for 64-bit mode"
-	depends on X86_64 && IA32_EMULATION
+	depends on X86_64
 	---help---
 	  Include code to run binaries for the x32 native 32-bit ABI
 	  for 64-bit processors.  An x32 process gets access to the
@@ -2544,7 +2591,6 @@ config X86_X32
 config COMPAT
 	def_bool y
 	depends on IA32_EMULATION || X86_X32
-	select ARCH_WANT_OLD_COMPAT_IPC
 
 if COMPAT
 config COMPAT_FOR_U64_ALIGNMENT
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index a15893d17c55..d8c0d3266173 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -297,6 +297,18 @@ config OPTIMIZE_INLINING
 
 	  If unsure, say N.
 
+config DEBUG_ENTRY
+	bool "Debug low-level entry code"
+	depends on DEBUG_KERNEL
+	---help---
+	  This option enables sanity checks in x86's low-level entry code.
+	  Some of these sanity checks may slow down kernel entries and
+	  exits or otherwise impact performance.
+
+	  This is currently used to help test NMI code.
+
+	  If unsure, say N.
+
 config DEBUG_NMI_SELFTEST
 	bool "NMI Selftest"
 	depends on DEBUG_KERNEL && X86_LOCAL_APIC
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 118e6debc483..747860c696e1 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -39,6 +39,16 @@ ifdef CONFIG_X86_NEED_RELOCS
         LDFLAGS_vmlinux := --emit-relocs
 endif
 
+#
+# Prevent GCC from generating any FP code by mistake.
+#
+# This must happen before we try the -mpreferred-stack-boundary, see:
+#
+#    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
+#
+KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
+
 ifeq ($(CONFIG_X86_32),y)
         BITS := 32
         UTS_MACHINE := i386
@@ -167,9 +177,6 @@ KBUILD_CFLAGS += -pipe
 KBUILD_CFLAGS += -Wno-sign-compare
 #
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-# prevent gcc from generating any FP code by mistake
-KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
-KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
@@ -212,6 +219,8 @@ drivers-$(CONFIG_PM) += arch/x86/power/
 
 drivers-$(CONFIG_FB) += arch/x86/video/
 
+drivers-$(CONFIG_RAS) += arch/x86/ras/
+
 ####
 # boot loader support. Several targets are kept for legacy purposes
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 57bbf2fb21f6..0d553e54171b 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -23,7 +23,7 @@ targets		+= fdimage fdimage144 fdimage288 image.iso mtools.conf
 subdir-		:= compressed
 
 setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o
-setup-y		+= early_serial_console.o edd.o header.o main.o mca.o memory.o
+setup-y		+= early_serial_console.o edd.o header.o main.o memory.o
 setup-y		+= pm.o pmjump.o printf.o regs.o string.o tty.o video.o
 setup-y		+= video-mode.o version.o
 setup-$(CONFIG_X86_APM_BOOT) += apm.o
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index bd49ec61255c..0033e96c3f09 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -307,9 +307,6 @@ void query_edd(void);
 /* header.S */
 void __attribute__((noreturn)) die(void);
 
-/* mca.c */
-int query_mca(void);
-
 /* memory.c */
 int detect_memory(void);
 
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index d7b1f655b3ef..6a9b96b4624d 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -82,7 +82,7 @@ static unsigned long get_random_long(void)
 
 	if (has_cpuflag(X86_FEATURE_TSC)) {
 		debug_putstr(" RDTSC");
-		rdtscll(raw);
+		raw = rdtsc();
 
 		random ^= raw;
 		use_i8254 = false;
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c82bd150d43..ee1b6d346b98 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1041,7 +1041,6 @@ void setup_graphics(struct boot_params *boot_params)
 struct boot_params *make_boot_params(struct efi_config *c)
 {
 	struct boot_params *boot_params;
-	struct sys_desc_table *sdt;
 	struct apm_bios_info *bi;
 	struct setup_header *hdr;
 	struct efi_info *efi;
@@ -1089,7 +1088,6 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	hdr = &boot_params->hdr;
 	efi = &boot_params->efi_info;
 	bi = &boot_params->apm_bios_info;
-	sdt = &boot_params->sys_desc_table;
 
 	/* Copy the second sector to boot_params */
 	memcpy(&hdr->jump, image->image_base + 512, 512);
@@ -1118,8 +1116,6 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	/* Clear APM BIOS info */
 	memset(bi, 0, sizeof(*bi));
 
-	memset(sdt, 0, sizeof(*sdt));
-
 	status = efi_parse_options(cmdline_ptr);
 	if (status != EFI_SUCCESS)
 		goto fail2;
@@ -1193,6 +1189,10 @@ static efi_status_t setup_e820(struct boot_params *params,
 		unsigned int e820_type = 0;
 		unsigned long m = efi->efi_memmap;
 
+#ifdef CONFIG_X86_64
+		m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
 		d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
 		switch (d->type) {
 		case EFI_RESERVED_TYPE:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index a107b935e22f..f63797942bb5 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -220,6 +220,23 @@ void __putstr(const char *s)
 	outb(0xff & (pos >> 1), vidport+1);
 }
 
+void __puthex(unsigned long value)
+{
+	char alpha[2] = "0";
+	int bits;
+
+	for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) {
+		unsigned long digit = (value >> bits) & 0xf;
+
+		if (digit < 0xA)
+			alpha[0] = '0' + digit;
+		else
+			alpha[0] = 'a' + (digit - 0xA);
+
+		__putstr(alpha);
+	}
+}
+
 static void error(char *x)
 {
 	error_putstr("\n\n");
@@ -399,6 +416,13 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	/* Report initial kernel position details. */
+	debug_putaddr(input_data);
+	debug_putaddr(input_len);
+	debug_putaddr(output);
+	debug_putaddr(output_len);
+	debug_putaddr(run_size);
+
 	/*
 	 * The memory hole needed for the kernel is the larger of either
 	 * the entire decompressed kernel plus relocation table, or the
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 805d25ca5f1d..3783dc3e10b3 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -34,16 +34,27 @@ extern memptr free_mem_ptr;
 extern memptr free_mem_end_ptr;
 extern struct boot_params *real_mode;		/* Pointer to real-mode data */
 void __putstr(const char *s);
+void __puthex(unsigned long value);
 #define error_putstr(__x)  __putstr(__x)
+#define error_puthex(__x)  __puthex(__x)
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 
 #define debug_putstr(__x)  __putstr(__x)
+#define debug_puthex(__x)  __puthex(__x)
+#define debug_putaddr(__x) { \
+		debug_putstr(#__x ": 0x"); \
+		debug_puthex((unsigned long)(__x)); \
+		debug_putstr("\n"); \
+	}
 
 #else
 
 static inline void debug_putstr(const char *s)
 { }
+static inline void debug_puthex(const char *s)
+{ }
+#define debug_putaddr(x) /* */
 
 #endif
 
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index fd6c9f236996..9bcea386db65 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -161,9 +161,6 @@ void main(void)
 	/* Set keyboard repeat rate (why?) and query the lock flags */
 	keyboard_init();
 
-	/* Query MCA information */
-	query_mca();
-
 	/* Query Intel SpeedStep (IST) information */
 	query_ist();
 
diff --git a/arch/x86/boot/mca.c b/arch/x86/boot/mca.c
deleted file mode 100644
index a95a531148ef..000000000000
--- a/arch/x86/boot/mca.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright (C) 1991, 1992 Linus Torvalds
- *   Copyright 2007 rPath, Inc. - All Rights Reserved
- *   Copyright 2009 Intel Corporation; author H. Peter Anvin
- *
- *   This file is part of the Linux kernel, and is made available under
- *   the terms of the GNU General Public License version 2.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * Get the MCA system description table
- */
-
-#include "boot.h"
-
-int query_mca(void)
-{
-	struct biosregs ireg, oreg;
-	u16 len;
-
-	initregs(&ireg);
-	ireg.ah = 0xc0;
-	intcall(0x15, &ireg, &oreg);
-
-	if (oreg.eflags & X86_EFLAGS_CF)
-		return -1;	/* No MCA present */
-
-	set_fs(oreg.es);
-	len = rdfs16(oreg.bx);
-
-	if (len > sizeof(boot_params.sys_desc_table))
-		len = sizeof(boot_params.sys_desc_table);
-
-	copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len);
-	return 0;
-}
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index aaa1118bf01e..028be48c8839 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -23,6 +23,7 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 315b86106572..cb5b3ab5beec 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -22,6 +22,7 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
@@ -207,7 +208,6 @@ CONFIG_AGP_AMD64=y
 CONFIG_AGP_INTEL=y
 CONFIG_DRM=y
 CONFIG_DRM_I915=y
-CONFIG_DRM_I915_KMS=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 5a4a089e8b1f..9a2838cf0591 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
 obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
+obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
@@ -30,6 +31,7 @@ obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
+obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -60,6 +62,7 @@ blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
 salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
+chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 
 ifeq ($(avx_supported),yes)
@@ -75,6 +78,7 @@ endif
 
 ifeq ($(avx2_supported),yes)
 	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
+	chacha20-x86_64-y += chacha20-avx2-x86_64.o
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 endif
 
@@ -82,8 +86,10 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
+poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o
 ifeq ($(avx2_supported),yes)
 sha1-ssse3-y += sha1_avx2_x86_64_asm.o
+poly1305-x86_64-y += poly1305-avx2-x86_64.o
 endif
 crc32c-intel-y := crc32c-intel_glue.o
 crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index dccad38b59a8..3633ad6145c5 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -803,10 +803,7 @@ static int rfc4106_init(struct crypto_aead *aead)
 		return PTR_ERR(cryptd_tfm);
 
 	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(
-		aead,
-		sizeof(struct aead_request) +
-		crypto_aead_reqsize(&cryptd_tfm->base));
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
 	return 0;
 }
 
@@ -955,8 +952,8 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length equal */
-	/* to 8 or 12 bytes */
-	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
+	/* to 16 or 20 bytes */
+	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
 		return -EINVAL;
 
 	/* IV below built */
@@ -992,9 +989,9 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 	}
 
 	kernel_fpu_begin();
-	aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
-		ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst
-		+ ((unsigned long)req->cryptlen), auth_tag_len);
+	aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv,
+			  ctx->hash_subkey, assoc, req->assoclen - 8,
+			  dst + req->cryptlen, auth_tag_len);
 	kernel_fpu_end();
 
 	/* The authTag (aka the Integrity Check Value) needs to be written
@@ -1033,12 +1030,12 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 	struct scatter_walk dst_sg_walk;
 	unsigned int i;
 
-	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
+	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
 		return -EINVAL;
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length */
-	/* equal to 8 or 12 bytes */
+	/* equal to 16 or 20 bytes */
 
 	tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len);
 	/* IV below built */
@@ -1075,8 +1072,8 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 
 	kernel_fpu_begin();
 	aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
-		ctx->hash_subkey, assoc, (unsigned long)req->assoclen,
-		authTag, auth_tag_len);
+			  ctx->hash_subkey, assoc, req->assoclen - 8,
+			  authTag, auth_tag_len);
 	kernel_fpu_end();
 
 	/* Compare generated tag with passed in tag. */
@@ -1105,19 +1102,12 @@ static int rfc4106_encrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
-	struct aead_request *subreq = aead_request_ctx(req);
 
-	aead_request_set_tfm(subreq, irq_fpu_usable() ?
-				     cryptd_aead_child(cryptd_tfm) :
-				     &cryptd_tfm->base);
+	aead_request_set_tfm(req, irq_fpu_usable() ?
+				  cryptd_aead_child(cryptd_tfm) :
+				  &cryptd_tfm->base);
 
-	aead_request_set_callback(subreq, req->base.flags,
-				  req->base.complete, req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst,
-			       req->cryptlen, req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
-
-	return crypto_aead_encrypt(subreq);
+	return crypto_aead_encrypt(req);
 }
 
 static int rfc4106_decrypt(struct aead_request *req)
@@ -1125,19 +1115,12 @@ static int rfc4106_decrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
-	struct aead_request *subreq = aead_request_ctx(req);
-
-	aead_request_set_tfm(subreq, irq_fpu_usable() ?
-				     cryptd_aead_child(cryptd_tfm) :
-				     &cryptd_tfm->base);
 
-	aead_request_set_callback(subreq, req->base.flags,
-				  req->base.complete, req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst,
-			       req->cryptlen, req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
+	aead_request_set_tfm(req, irq_fpu_usable() ?
+				  cryptd_aead_child(cryptd_tfm) :
+				  &cryptd_tfm->base);
 
-	return crypto_aead_decrypt(subreq);
+	return crypto_aead_decrypt(req);
 }
 #endif
 
diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S
new file mode 100644
index 000000000000..16694e625f77
--- /dev/null
+++ b/arch/x86/crypto/chacha20-avx2-x86_64.S
@@ -0,0 +1,443 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX2 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+.data
+.align 32
+
+ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
+	.octa 0x0e0d0c0f0a09080b0605040702010003
+ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
+	.octa 0x0d0c0f0e09080b0a0504070601000302
+CTRINC:	.octa 0x00000003000000020000000100000000
+	.octa 0x00000007000000060000000500000004
+
+.text
+
+ENTRY(chacha20_8block_xor_avx2)
+	# %rdi: Input state matrix, s
+	# %rsi: 8 data blocks output, o
+	# %rdx: 8 data blocks input, i
+
+	# This function encrypts eight consecutive ChaCha20 blocks by loading
+	# the state matrix in AVX registers eight times. As we need some
+	# scratch registers, we save the first four registers on the stack. The
+	# algorithm performs each operation on the corresponding word of each
+	# state matrix, hence requires no word shuffling. For final XORing step
+	# we transpose the matrix by interleaving 32-, 64- and then 128-bit
+	# words, which allows us to do XOR in AVX registers. 8/16-bit word
+	# rotation is done with the slightly better performing byte shuffling,
+	# 7/12-bit word rotation uses traditional shift+OR.
+
+	vzeroupper
+	# 4 * 32 byte stack, 32-byte aligned
+	mov		%rsp, %r8
+	and		$~31, %rsp
+	sub		$0x80, %rsp
+
+	# x0..15[0-7] = s[0..15]
+	vpbroadcastd	0x00(%rdi),%ymm0
+	vpbroadcastd	0x04(%rdi),%ymm1
+	vpbroadcastd	0x08(%rdi),%ymm2
+	vpbroadcastd	0x0c(%rdi),%ymm3
+	vpbroadcastd	0x10(%rdi),%ymm4
+	vpbroadcastd	0x14(%rdi),%ymm5
+	vpbroadcastd	0x18(%rdi),%ymm6
+	vpbroadcastd	0x1c(%rdi),%ymm7
+	vpbroadcastd	0x20(%rdi),%ymm8
+	vpbroadcastd	0x24(%rdi),%ymm9
+	vpbroadcastd	0x28(%rdi),%ymm10
+	vpbroadcastd	0x2c(%rdi),%ymm11
+	vpbroadcastd	0x30(%rdi),%ymm12
+	vpbroadcastd	0x34(%rdi),%ymm13
+	vpbroadcastd	0x38(%rdi),%ymm14
+	vpbroadcastd	0x3c(%rdi),%ymm15
+	# x0..3 on stack
+	vmovdqa		%ymm0,0x00(%rsp)
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		%ymm2,0x40(%rsp)
+	vmovdqa		%ymm3,0x60(%rsp)
+
+	vmovdqa		CTRINC(%rip),%ymm1
+	vmovdqa		ROT8(%rip),%ymm2
+	vmovdqa		ROT16(%rip),%ymm3
+
+	# x12 += counter values 0-3
+	vpaddd		%ymm1,%ymm12,%ymm12
+
+	mov		$10,%ecx
+
+.Ldoubleround8:
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	vpaddd		0x00(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm3,%ymm12,%ymm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	vpaddd		0x20(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm3,%ymm13,%ymm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	vpaddd		0x40(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm3,%ymm14,%ymm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	vpaddd		0x60(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm3,%ymm15,%ymm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	vpaddd		%ymm12,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm4,%ymm4
+	vpslld		$12,%ymm4,%ymm0
+	vpsrld		$20,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	vpaddd		%ymm13,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm5,%ymm5
+	vpslld		$12,%ymm5,%ymm0
+	vpsrld		$20,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	vpaddd		%ymm14,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm6,%ymm6
+	vpslld		$12,%ymm6,%ymm0
+	vpsrld		$20,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	vpaddd		%ymm15,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm7,%ymm7
+	vpslld		$12,%ymm7,%ymm0
+	vpsrld		$20,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	vpaddd		0x00(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm2,%ymm12,%ymm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	vpaddd		0x20(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm2,%ymm13,%ymm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	vpaddd		0x40(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm2,%ymm14,%ymm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	vpaddd		0x60(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm2,%ymm15,%ymm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	vpaddd		%ymm12,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm4,%ymm4
+	vpslld		$7,%ymm4,%ymm0
+	vpsrld		$25,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	vpaddd		%ymm13,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm5,%ymm5
+	vpslld		$7,%ymm5,%ymm0
+	vpsrld		$25,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	vpaddd		%ymm14,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm6,%ymm6
+	vpslld		$7,%ymm6,%ymm0
+	vpsrld		$25,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	vpaddd		%ymm15,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm7,%ymm7
+	vpslld		$7,%ymm7,%ymm0
+	vpsrld		$25,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	vpaddd		0x00(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm3,%ymm15,%ymm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 16)%ymm0
+	vpaddd		0x20(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm3,%ymm12,%ymm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	vpaddd		0x40(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm3,%ymm13,%ymm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	vpaddd		0x60(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm3,%ymm14,%ymm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	vpaddd		%ymm15,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm5,%ymm5
+	vpslld		$12,%ymm5,%ymm0
+	vpsrld		$20,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	vpaddd		%ymm12,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm6,%ymm6
+	vpslld		$12,%ymm6,%ymm0
+	vpsrld		$20,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	vpaddd		%ymm13,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm7,%ymm7
+	vpslld		$12,%ymm7,%ymm0
+	vpsrld		$20,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	vpaddd		%ymm14,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm4,%ymm4
+	vpslld		$12,%ymm4,%ymm0
+	vpsrld		$20,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	vpaddd		0x00(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm2,%ymm15,%ymm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	vpaddd		0x20(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm2,%ymm12,%ymm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	vpaddd		0x40(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm2,%ymm13,%ymm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	vpaddd		0x60(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm2,%ymm14,%ymm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	vpaddd		%ymm15,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm5,%ymm5
+	vpslld		$7,%ymm5,%ymm0
+	vpsrld		$25,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	vpaddd		%ymm12,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm6,%ymm6
+	vpslld		$7,%ymm6,%ymm0
+	vpsrld		$25,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	vpaddd		%ymm13,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm7,%ymm7
+	vpslld		$7,%ymm7,%ymm0
+	vpsrld		$25,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	vpaddd		%ymm14,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm4,%ymm4
+	vpslld		$7,%ymm4,%ymm0
+	vpsrld		$25,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+
+	dec		%ecx
+	jnz		.Ldoubleround8
+
+	# x0..15[0-3] += s[0..15]
+	vpbroadcastd	0x00(%rdi),%ymm0
+	vpaddd		0x00(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpbroadcastd	0x04(%rdi),%ymm0
+	vpaddd		0x20(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpbroadcastd	0x08(%rdi),%ymm0
+	vpaddd		0x40(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpbroadcastd	0x0c(%rdi),%ymm0
+	vpaddd		0x60(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpbroadcastd	0x10(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm4,%ymm4
+	vpbroadcastd	0x14(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm5,%ymm5
+	vpbroadcastd	0x18(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm6,%ymm6
+	vpbroadcastd	0x1c(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm7,%ymm7
+	vpbroadcastd	0x20(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm8,%ymm8
+	vpbroadcastd	0x24(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm9,%ymm9
+	vpbroadcastd	0x28(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm10,%ymm10
+	vpbroadcastd	0x2c(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm11,%ymm11
+	vpbroadcastd	0x30(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm12,%ymm12
+	vpbroadcastd	0x34(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm13,%ymm13
+	vpbroadcastd	0x38(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm14,%ymm14
+	vpbroadcastd	0x3c(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm15,%ymm15
+
+	# x12 += counter values 0-3
+	vpaddd		%ymm1,%ymm12,%ymm12
+
+	# interleave 32-bit words in state n, n+1
+	vmovdqa		0x00(%rsp),%ymm0
+	vmovdqa		0x20(%rsp),%ymm1
+	vpunpckldq	%ymm1,%ymm0,%ymm2
+	vpunpckhdq	%ymm1,%ymm0,%ymm1
+	vmovdqa		%ymm2,0x00(%rsp)
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		0x40(%rsp),%ymm0
+	vmovdqa		0x60(%rsp),%ymm1
+	vpunpckldq	%ymm1,%ymm0,%ymm2
+	vpunpckhdq	%ymm1,%ymm0,%ymm1
+	vmovdqa		%ymm2,0x40(%rsp)
+	vmovdqa		%ymm1,0x60(%rsp)
+	vmovdqa		%ymm4,%ymm0
+	vpunpckldq	%ymm5,%ymm0,%ymm4
+	vpunpckhdq	%ymm5,%ymm0,%ymm5
+	vmovdqa		%ymm6,%ymm0
+	vpunpckldq	%ymm7,%ymm0,%ymm6
+	vpunpckhdq	%ymm7,%ymm0,%ymm7
+	vmovdqa		%ymm8,%ymm0
+	vpunpckldq	%ymm9,%ymm0,%ymm8
+	vpunpckhdq	%ymm9,%ymm0,%ymm9
+	vmovdqa		%ymm10,%ymm0
+	vpunpckldq	%ymm11,%ymm0,%ymm10
+	vpunpckhdq	%ymm11,%ymm0,%ymm11
+	vmovdqa		%ymm12,%ymm0
+	vpunpckldq	%ymm13,%ymm0,%ymm12
+	vpunpckhdq	%ymm13,%ymm0,%ymm13
+	vmovdqa		%ymm14,%ymm0
+	vpunpckldq	%ymm15,%ymm0,%ymm14
+	vpunpckhdq	%ymm15,%ymm0,%ymm15
+
+	# interleave 64-bit words in state n, n+2
+	vmovdqa		0x00(%rsp),%ymm0
+	vmovdqa		0x40(%rsp),%ymm2
+	vpunpcklqdq	%ymm2,%ymm0,%ymm1
+	vpunpckhqdq	%ymm2,%ymm0,%ymm2
+	vmovdqa		%ymm1,0x00(%rsp)
+	vmovdqa		%ymm2,0x40(%rsp)
+	vmovdqa		0x20(%rsp),%ymm0
+	vmovdqa		0x60(%rsp),%ymm2
+	vpunpcklqdq	%ymm2,%ymm0,%ymm1
+	vpunpckhqdq	%ymm2,%ymm0,%ymm2
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		%ymm2,0x60(%rsp)
+	vmovdqa		%ymm4,%ymm0
+	vpunpcklqdq	%ymm6,%ymm0,%ymm4
+	vpunpckhqdq	%ymm6,%ymm0,%ymm6
+	vmovdqa		%ymm5,%ymm0
+	vpunpcklqdq	%ymm7,%ymm0,%ymm5
+	vpunpckhqdq	%ymm7,%ymm0,%ymm7
+	vmovdqa		%ymm8,%ymm0
+	vpunpcklqdq	%ymm10,%ymm0,%ymm8
+	vpunpckhqdq	%ymm10,%ymm0,%ymm10
+	vmovdqa		%ymm9,%ymm0
+	vpunpcklqdq	%ymm11,%ymm0,%ymm9
+	vpunpckhqdq	%ymm11,%ymm0,%ymm11
+	vmovdqa		%ymm12,%ymm0
+	vpunpcklqdq	%ymm14,%ymm0,%ymm12
+	vpunpckhqdq	%ymm14,%ymm0,%ymm14
+	vmovdqa		%ymm13,%ymm0
+	vpunpcklqdq	%ymm15,%ymm0,%ymm13
+	vpunpckhqdq	%ymm15,%ymm0,%ymm15
+
+	# interleave 128-bit words in state n, n+4
+	vmovdqa		0x00(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm4,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm4,%ymm0,%ymm4
+	vmovdqa		%ymm1,0x00(%rsp)
+	vmovdqa		0x20(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm5,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm5,%ymm0,%ymm5
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		0x40(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm6,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm6,%ymm0,%ymm6
+	vmovdqa		%ymm1,0x40(%rsp)
+	vmovdqa		0x60(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm7,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm7,%ymm0,%ymm7
+	vmovdqa		%ymm1,0x60(%rsp)
+	vperm2i128	$0x20,%ymm12,%ymm8,%ymm0
+	vperm2i128	$0x31,%ymm12,%ymm8,%ymm12
+	vmovdqa		%ymm0,%ymm8
+	vperm2i128	$0x20,%ymm13,%ymm9,%ymm0
+	vperm2i128	$0x31,%ymm13,%ymm9,%ymm13
+	vmovdqa		%ymm0,%ymm9
+	vperm2i128	$0x20,%ymm14,%ymm10,%ymm0
+	vperm2i128	$0x31,%ymm14,%ymm10,%ymm14
+	vmovdqa		%ymm0,%ymm10
+	vperm2i128	$0x20,%ymm15,%ymm11,%ymm0
+	vperm2i128	$0x31,%ymm15,%ymm11,%ymm15
+	vmovdqa		%ymm0,%ymm11
+
+	# xor with corresponding input, write to output
+	vmovdqa		0x00(%rsp),%ymm0
+	vpxor		0x0000(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0000(%rsi)
+	vmovdqa		0x20(%rsp),%ymm0
+	vpxor		0x0080(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0080(%rsi)
+	vmovdqa		0x40(%rsp),%ymm0
+	vpxor		0x0040(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0040(%rsi)
+	vmovdqa		0x60(%rsp),%ymm0
+	vpxor		0x00c0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x00c0(%rsi)
+	vpxor		0x0100(%rdx),%ymm4,%ymm4
+	vmovdqu		%ymm4,0x0100(%rsi)
+	vpxor		0x0180(%rdx),%ymm5,%ymm5
+	vmovdqu		%ymm5,0x00180(%rsi)
+	vpxor		0x0140(%rdx),%ymm6,%ymm6
+	vmovdqu		%ymm6,0x0140(%rsi)
+	vpxor		0x01c0(%rdx),%ymm7,%ymm7
+	vmovdqu		%ymm7,0x01c0(%rsi)
+	vpxor		0x0020(%rdx),%ymm8,%ymm8
+	vmovdqu		%ymm8,0x0020(%rsi)
+	vpxor		0x00a0(%rdx),%ymm9,%ymm9
+	vmovdqu		%ymm9,0x00a0(%rsi)
+	vpxor		0x0060(%rdx),%ymm10,%ymm10
+	vmovdqu		%ymm10,0x0060(%rsi)
+	vpxor		0x00e0(%rdx),%ymm11,%ymm11
+	vmovdqu		%ymm11,0x00e0(%rsi)
+	vpxor		0x0120(%rdx),%ymm12,%ymm12
+	vmovdqu		%ymm12,0x0120(%rsi)
+	vpxor		0x01a0(%rdx),%ymm13,%ymm13
+	vmovdqu		%ymm13,0x01a0(%rsi)
+	vpxor		0x0160(%rdx),%ymm14,%ymm14
+	vmovdqu		%ymm14,0x0160(%rsi)
+	vpxor		0x01e0(%rdx),%ymm15,%ymm15
+	vmovdqu		%ymm15,0x01e0(%rsi)
+
+	vzeroupper
+	mov		%r8,%rsp
+	ret
+ENDPROC(chacha20_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
new file mode 100644
index 000000000000..712b13047b41
--- /dev/null
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -0,0 +1,625 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+.data
+.align 16
+
+ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
+ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
+CTRINC:	.octa 0x00000003000000020000000100000000
+
+.text
+
+ENTRY(chacha20_block_xor_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: 1 data block output, o
+	# %rdx: 1 data block input, i
+
+	# This function encrypts one ChaCha20 block by loading the state matrix
+	# in four SSE registers. It performs matrix operation on four words in
+	# parallel, but requireds shuffling to rearrange the words after each
+	# round. 8/16-bit word rotation is done with the slightly better
+	# performing SSSE3 byte shuffling, 7/12-bit word rotation uses
+	# traditional shift+OR.
+
+	# x0..3 = s0..3
+	movdqa		0x00(%rdi),%xmm0
+	movdqa		0x10(%rdi),%xmm1
+	movdqa		0x20(%rdi),%xmm2
+	movdqa		0x30(%rdi),%xmm3
+	movdqa		%xmm0,%xmm8
+	movdqa		%xmm1,%xmm9
+	movdqa		%xmm2,%xmm10
+	movdqa		%xmm3,%xmm11
+
+	movdqa		ROT8(%rip),%xmm4
+	movdqa		ROT16(%rip),%xmm5
+
+	mov	$10,%ecx
+
+.Ldoubleround:
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm5,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm6
+	pslld		$12,%xmm6
+	psrld		$20,%xmm1
+	por		%xmm6,%xmm1
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm4,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm7
+	pslld		$7,%xmm7
+	psrld		$25,%xmm1
+	por		%xmm7,%xmm1
+
+	# x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+	pshufd		$0x39,%xmm1,%xmm1
+	# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	pshufd		$0x4e,%xmm2,%xmm2
+	# x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+	pshufd		$0x93,%xmm3,%xmm3
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm5,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm6
+	pslld		$12,%xmm6
+	psrld		$20,%xmm1
+	por		%xmm6,%xmm1
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm4,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm7
+	pslld		$7,%xmm7
+	psrld		$25,%xmm1
+	por		%xmm7,%xmm1
+
+	# x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+	pshufd		$0x93,%xmm1,%xmm1
+	# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	pshufd		$0x4e,%xmm2,%xmm2
+	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+	pshufd		$0x39,%xmm3,%xmm3
+
+	dec		%ecx
+	jnz		.Ldoubleround
+
+	# o0 = i0 ^ (x0 + s0)
+	movdqu		0x00(%rdx),%xmm4
+	paddd		%xmm8,%xmm0
+	pxor		%xmm4,%xmm0
+	movdqu		%xmm0,0x00(%rsi)
+	# o1 = i1 ^ (x1 + s1)
+	movdqu		0x10(%rdx),%xmm5
+	paddd		%xmm9,%xmm1
+	pxor		%xmm5,%xmm1
+	movdqu		%xmm1,0x10(%rsi)
+	# o2 = i2 ^ (x2 + s2)
+	movdqu		0x20(%rdx),%xmm6
+	paddd		%xmm10,%xmm2
+	pxor		%xmm6,%xmm2
+	movdqu		%xmm2,0x20(%rsi)
+	# o3 = i3 ^ (x3 + s3)
+	movdqu		0x30(%rdx),%xmm7
+	paddd		%xmm11,%xmm3
+	pxor		%xmm7,%xmm3
+	movdqu		%xmm3,0x30(%rsi)
+
+	ret
+ENDPROC(chacha20_block_xor_ssse3)
+
+ENTRY(chacha20_4block_xor_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: 4 data blocks output, o
+	# %rdx: 4 data blocks input, i
+
+	# This function encrypts four consecutive ChaCha20 blocks by loading the
+	# the state matrix in SSE registers four times. As we need some scratch
+	# registers, we save the first four registers on the stack. The
+	# algorithm performs each operation on the corresponding word of each
+	# state matrix, hence requires no word shuffling. For final XORing step
+	# we transpose the matrix by interleaving 32- and then 64-bit words,
+	# which allows us to do XOR in SSE registers. 8/16-bit word rotation is
+	# done with the slightly better performing SSSE3 byte shuffling,
+	# 7/12-bit word rotation uses traditional shift+OR.
+
+	sub		$0x40,%rsp
+
+	# x0..15[0-3] = s0..3[0..3]
+	movq		0x00(%rdi),%xmm1
+	pshufd		$0x00,%xmm1,%xmm0
+	pshufd		$0x55,%xmm1,%xmm1
+	movq		0x08(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	movq		0x10(%rdi),%xmm5
+	pshufd		$0x00,%xmm5,%xmm4
+	pshufd		$0x55,%xmm5,%xmm5
+	movq		0x18(%rdi),%xmm7
+	pshufd		$0x00,%xmm7,%xmm6
+	pshufd		$0x55,%xmm7,%xmm7
+	movq		0x20(%rdi),%xmm9
+	pshufd		$0x00,%xmm9,%xmm8
+	pshufd		$0x55,%xmm9,%xmm9
+	movq		0x28(%rdi),%xmm11
+	pshufd		$0x00,%xmm11,%xmm10
+	pshufd		$0x55,%xmm11,%xmm11
+	movq		0x30(%rdi),%xmm13
+	pshufd		$0x00,%xmm13,%xmm12
+	pshufd		$0x55,%xmm13,%xmm13
+	movq		0x38(%rdi),%xmm15
+	pshufd		$0x00,%xmm15,%xmm14
+	pshufd		$0x55,%xmm15,%xmm15
+	# x0..3 on stack
+	movdqa		%xmm0,0x00(%rsp)
+	movdqa		%xmm1,0x10(%rsp)
+	movdqa		%xmm2,0x20(%rsp)
+	movdqa		%xmm3,0x30(%rsp)
+
+	movdqa		CTRINC(%rip),%xmm1
+	movdqa		ROT8(%rip),%xmm2
+	movdqa		ROT16(%rip),%xmm3
+
+	# x12 += counter values 0-3
+	paddd		%xmm1,%xmm12
+
+	mov		$10,%ecx
+
+.Ldoubleround4:
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm3,%xmm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm3,%xmm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm3,%xmm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm3,%xmm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	paddd		%xmm12,%xmm8
+	pxor		%xmm8,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm4
+	por		%xmm0,%xmm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	paddd		%xmm13,%xmm9
+	pxor		%xmm9,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm5
+	por		%xmm0,%xmm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	paddd		%xmm14,%xmm10
+	pxor		%xmm10,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm6
+	por		%xmm0,%xmm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	paddd		%xmm15,%xmm11
+	pxor		%xmm11,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm7
+	por		%xmm0,%xmm7
+
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm2,%xmm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm2,%xmm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm2,%xmm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm2,%xmm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	paddd		%xmm12,%xmm8
+	pxor		%xmm8,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm4
+	por		%xmm0,%xmm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	paddd		%xmm13,%xmm9
+	pxor		%xmm9,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm5
+	por		%xmm0,%xmm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	paddd		%xmm14,%xmm10
+	pxor		%xmm10,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm6
+	por		%xmm0,%xmm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	paddd		%xmm15,%xmm11
+	pxor		%xmm11,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm7
+	por		%xmm0,%xmm7
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm3,%xmm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm3,%xmm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm3,%xmm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm3,%xmm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	paddd		%xmm15,%xmm10
+	pxor		%xmm10,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm5
+	por		%xmm0,%xmm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	paddd		%xmm12,%xmm11
+	pxor		%xmm11,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm6
+	por		%xmm0,%xmm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	paddd		%xmm13,%xmm8
+	pxor		%xmm8,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm7
+	por		%xmm0,%xmm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	paddd		%xmm14,%xmm9
+	pxor		%xmm9,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm4
+	por		%xmm0,%xmm4
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm2,%xmm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm2,%xmm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm2,%xmm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm2,%xmm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	paddd		%xmm15,%xmm10
+	pxor		%xmm10,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm5
+	por		%xmm0,%xmm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	paddd		%xmm12,%xmm11
+	pxor		%xmm11,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm6
+	por		%xmm0,%xmm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	paddd		%xmm13,%xmm8
+	pxor		%xmm8,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm7
+	por		%xmm0,%xmm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	paddd		%xmm14,%xmm9
+	pxor		%xmm9,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm4
+	por		%xmm0,%xmm4
+
+	dec		%ecx
+	jnz		.Ldoubleround4
+
+	# x0[0-3] += s0[0]
+	# x1[0-3] += s0[1]
+	movq		0x00(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		0x00(%rsp),%xmm2
+	movdqa		%xmm2,0x00(%rsp)
+	paddd		0x10(%rsp),%xmm3
+	movdqa		%xmm3,0x10(%rsp)
+	# x2[0-3] += s0[2]
+	# x3[0-3] += s0[3]
+	movq		0x08(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		0x20(%rsp),%xmm2
+	movdqa		%xmm2,0x20(%rsp)
+	paddd		0x30(%rsp),%xmm3
+	movdqa		%xmm3,0x30(%rsp)
+
+	# x4[0-3] += s1[0]
+	# x5[0-3] += s1[1]
+	movq		0x10(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm4
+	paddd		%xmm3,%xmm5
+	# x6[0-3] += s1[2]
+	# x7[0-3] += s1[3]
+	movq		0x18(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm6
+	paddd		%xmm3,%xmm7
+
+	# x8[0-3] += s2[0]
+	# x9[0-3] += s2[1]
+	movq		0x20(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm8
+	paddd		%xmm3,%xmm9
+	# x10[0-3] += s2[2]
+	# x11[0-3] += s2[3]
+	movq		0x28(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm10
+	paddd		%xmm3,%xmm11
+
+	# x12[0-3] += s3[0]
+	# x13[0-3] += s3[1]
+	movq		0x30(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm12
+	paddd		%xmm3,%xmm13
+	# x14[0-3] += s3[2]
+	# x15[0-3] += s3[3]
+	movq		0x38(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm14
+	paddd		%xmm3,%xmm15
+
+	# x12 += counter values 0-3
+	paddd		%xmm1,%xmm12
+
+	# interleave 32-bit words in state n, n+1
+	movdqa		0x00(%rsp),%xmm0
+	movdqa		0x10(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpckldq	%xmm1,%xmm2
+	punpckhdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x00(%rsp)
+	movdqa		%xmm0,0x10(%rsp)
+	movdqa		0x20(%rsp),%xmm0
+	movdqa		0x30(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpckldq	%xmm1,%xmm2
+	punpckhdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x20(%rsp)
+	movdqa		%xmm0,0x30(%rsp)
+	movdqa		%xmm4,%xmm0
+	punpckldq	%xmm5,%xmm4
+	punpckhdq	%xmm5,%xmm0
+	movdqa		%xmm0,%xmm5
+	movdqa		%xmm6,%xmm0
+	punpckldq	%xmm7,%xmm6
+	punpckhdq	%xmm7,%xmm0
+	movdqa		%xmm0,%xmm7
+	movdqa		%xmm8,%xmm0
+	punpckldq	%xmm9,%xmm8
+	punpckhdq	%xmm9,%xmm0
+	movdqa		%xmm0,%xmm9
+	movdqa		%xmm10,%xmm0
+	punpckldq	%xmm11,%xmm10
+	punpckhdq	%xmm11,%xmm0
+	movdqa		%xmm0,%xmm11
+	movdqa		%xmm12,%xmm0
+	punpckldq	%xmm13,%xmm12
+	punpckhdq	%xmm13,%xmm0
+	movdqa		%xmm0,%xmm13
+	movdqa		%xmm14,%xmm0
+	punpckldq	%xmm15,%xmm14
+	punpckhdq	%xmm15,%xmm0
+	movdqa		%xmm0,%xmm15
+
+	# interleave 64-bit words in state n, n+2
+	movdqa		0x00(%rsp),%xmm0
+	movdqa		0x20(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpcklqdq	%xmm1,%xmm2
+	punpckhqdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x00(%rsp)
+	movdqa		%xmm0,0x20(%rsp)
+	movdqa		0x10(%rsp),%xmm0
+	movdqa		0x30(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpcklqdq	%xmm1,%xmm2
+	punpckhqdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x10(%rsp)
+	movdqa		%xmm0,0x30(%rsp)
+	movdqa		%xmm4,%xmm0
+	punpcklqdq	%xmm6,%xmm4
+	punpckhqdq	%xmm6,%xmm0
+	movdqa		%xmm0,%xmm6
+	movdqa		%xmm5,%xmm0
+	punpcklqdq	%xmm7,%xmm5
+	punpckhqdq	%xmm7,%xmm0
+	movdqa		%xmm0,%xmm7
+	movdqa		%xmm8,%xmm0
+	punpcklqdq	%xmm10,%xmm8
+	punpckhqdq	%xmm10,%xmm0
+	movdqa		%xmm0,%xmm10
+	movdqa		%xmm9,%xmm0
+	punpcklqdq	%xmm11,%xmm9
+	punpckhqdq	%xmm11,%xmm0
+	movdqa		%xmm0,%xmm11
+	movdqa		%xmm12,%xmm0
+	punpcklqdq	%xmm14,%xmm12
+	punpckhqdq	%xmm14,%xmm0
+	movdqa		%xmm0,%xmm14
+	movdqa		%xmm13,%xmm0
+	punpcklqdq	%xmm15,%xmm13
+	punpckhqdq	%xmm15,%xmm0
+	movdqa		%xmm0,%xmm15
+
+	# xor with corresponding input, write to output
+	movdqa		0x00(%rsp),%xmm0
+	movdqu		0x00(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x00(%rsi)
+	movdqa		0x10(%rsp),%xmm0
+	movdqu		0x80(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x80(%rsi)
+	movdqa		0x20(%rsp),%xmm0
+	movdqu		0x40(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x40(%rsi)
+	movdqa		0x30(%rsp),%xmm0
+	movdqu		0xc0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xc0(%rsi)
+	movdqu		0x10(%rdx),%xmm1
+	pxor		%xmm1,%xmm4
+	movdqu		%xmm4,0x10(%rsi)
+	movdqu		0x90(%rdx),%xmm1
+	pxor		%xmm1,%xmm5
+	movdqu		%xmm5,0x90(%rsi)
+	movdqu		0x50(%rdx),%xmm1
+	pxor		%xmm1,%xmm6
+	movdqu		%xmm6,0x50(%rsi)
+	movdqu		0xd0(%rdx),%xmm1
+	pxor		%xmm1,%xmm7
+	movdqu		%xmm7,0xd0(%rsi)
+	movdqu		0x20(%rdx),%xmm1
+	pxor		%xmm1,%xmm8
+	movdqu		%xmm8,0x20(%rsi)
+	movdqu		0xa0(%rdx),%xmm1
+	pxor		%xmm1,%xmm9
+	movdqu		%xmm9,0xa0(%rsi)
+	movdqu		0x60(%rdx),%xmm1
+	pxor		%xmm1,%xmm10
+	movdqu		%xmm10,0x60(%rsi)
+	movdqu		0xe0(%rdx),%xmm1
+	pxor		%xmm1,%xmm11
+	movdqu		%xmm11,0xe0(%rsi)
+	movdqu		0x30(%rdx),%xmm1
+	pxor		%xmm1,%xmm12
+	movdqu		%xmm12,0x30(%rsi)
+	movdqu		0xb0(%rdx),%xmm1
+	pxor		%xmm1,%xmm13
+	movdqu		%xmm13,0xb0(%rsi)
+	movdqu		0x70(%rdx),%xmm1
+	pxor		%xmm1,%xmm14
+	movdqu		%xmm14,0x70(%rsi)
+	movdqu		0xf0(%rdx),%xmm1
+	pxor		%xmm1,%xmm15
+	movdqu		%xmm15,0xf0(%rsi)
+
+	add		$0x40,%rsp
+	ret
+ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
new file mode 100644
index 000000000000..effe2160b7c5
--- /dev/null
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -0,0 +1,150 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/chacha20.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/simd.h>
+
+#define CHACHA20_STATE_ALIGN 16
+
+asmlinkage void chacha20_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
+asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
+#ifdef CONFIG_AS_AVX2
+asmlinkage void chacha20_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src);
+static bool chacha20_use_avx2;
+#endif
+
+static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
+			    unsigned int bytes)
+{
+	u8 buf[CHACHA20_BLOCK_SIZE];
+
+#ifdef CONFIG_AS_AVX2
+	if (chacha20_use_avx2) {
+		while (bytes >= CHACHA20_BLOCK_SIZE * 8) {
+			chacha20_8block_xor_avx2(state, dst, src);
+			bytes -= CHACHA20_BLOCK_SIZE * 8;
+			src += CHACHA20_BLOCK_SIZE * 8;
+			dst += CHACHA20_BLOCK_SIZE * 8;
+			state[12] += 8;
+		}
+	}
+#endif
+	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+		chacha20_4block_xor_ssse3(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE * 4;
+		src += CHACHA20_BLOCK_SIZE * 4;
+		dst += CHACHA20_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block_xor_ssse3(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		src += CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha20_block_xor_ssse3(state, buf, buf);
+		memcpy(dst, buf, bytes);
+	}
+}
+
+static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
+			 struct scatterlist *src, unsigned int nbytes)
+{
+	u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1];
+	struct blkcipher_walk walk;
+	int err;
+
+	if (!may_use_simd())
+		return crypto_chacha20_crypt(desc, dst, src, nbytes);
+
+	state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+
+	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+
+	kernel_fpu_begin();
+
+	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
+				rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % CHACHA20_BLOCK_SIZE);
+	}
+
+	if (walk.nbytes) {
+		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
+				walk.nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	kernel_fpu_end();
+
+	return err;
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "chacha20",
+	.cra_driver_name	= "chacha20-simd",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_ctxsize		= sizeof(struct chacha20_ctx),
+	.cra_alignmask		= sizeof(u32) - 1,
+	.cra_module		= THIS_MODULE,
+	.cra_u			= {
+		.blkcipher = {
+			.min_keysize	= CHACHA20_KEY_SIZE,
+			.max_keysize	= CHACHA20_KEY_SIZE,
+			.ivsize		= CHACHA20_IV_SIZE,
+			.geniv		= "seqiv",
+			.setkey		= crypto_chacha20_setkey,
+			.encrypt	= chacha20_simd,
+			.decrypt	= chacha20_simd,
+		},
+	},
+};
+
+static int __init chacha20_simd_mod_init(void)
+{
+	if (!cpu_has_ssse3)
+		return -ENODEV;
+
+#ifdef CONFIG_AS_AVX2
+	chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+			    cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL);
+#endif
+	return crypto_register_alg(&alg);
+}
+
+static void __exit chacha20_simd_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+module_init(chacha20_simd_mod_init);
+module_exit(chacha20_simd_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("chacha20 cipher algorithm, SIMD accelerated");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-simd");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 64d7cf1b50e1..440df0c7a2ee 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -294,6 +294,7 @@ static struct ahash_alg ghash_async_alg = {
 			.cra_name		= "ghash",
 			.cra_driver_name	= "ghash-clmulni",
 			.cra_priority		= 400,
+			.cra_ctxsize		= sizeof(struct ghash_async_ctx),
 			.cra_flags		= CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
 			.cra_blocksize		= GHASH_BLOCK_SIZE,
 			.cra_type		= &crypto_ahash_type,
diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
new file mode 100644
index 000000000000..eff2f414e22b
--- /dev/null
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -0,0 +1,386 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539, x64 AVX2 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+.data
+.align 32
+
+ANMASK:	.octa 0x0000000003ffffff0000000003ffffff
+	.octa 0x0000000003ffffff0000000003ffffff
+ORMASK:	.octa 0x00000000010000000000000001000000
+	.octa 0x00000000010000000000000001000000
+
+.text
+
+#define h0 0x00(%rdi)
+#define h1 0x04(%rdi)
+#define h2 0x08(%rdi)
+#define h3 0x0c(%rdi)
+#define h4 0x10(%rdi)
+#define r0 0x00(%rdx)
+#define r1 0x04(%rdx)
+#define r2 0x08(%rdx)
+#define r3 0x0c(%rdx)
+#define r4 0x10(%rdx)
+#define u0 0x00(%r8)
+#define u1 0x04(%r8)
+#define u2 0x08(%r8)
+#define u3 0x0c(%r8)
+#define u4 0x10(%r8)
+#define w0 0x14(%r8)
+#define w1 0x18(%r8)
+#define w2 0x1c(%r8)
+#define w3 0x20(%r8)
+#define w4 0x24(%r8)
+#define y0 0x28(%r8)
+#define y1 0x2c(%r8)
+#define y2 0x30(%r8)
+#define y3 0x34(%r8)
+#define y4 0x38(%r8)
+#define m %rsi
+#define hc0 %ymm0
+#define hc1 %ymm1
+#define hc2 %ymm2
+#define hc3 %ymm3
+#define hc4 %ymm4
+#define hc0x %xmm0
+#define hc1x %xmm1
+#define hc2x %xmm2
+#define hc3x %xmm3
+#define hc4x %xmm4
+#define t1 %ymm5
+#define t2 %ymm6
+#define t1x %xmm5
+#define t2x %xmm6
+#define ruwy0 %ymm7
+#define ruwy1 %ymm8
+#define ruwy2 %ymm9
+#define ruwy3 %ymm10
+#define ruwy4 %ymm11
+#define ruwy0x %xmm7
+#define ruwy1x %xmm8
+#define ruwy2x %xmm9
+#define ruwy3x %xmm10
+#define ruwy4x %xmm11
+#define svxz1 %ymm12
+#define svxz2 %ymm13
+#define svxz3 %ymm14
+#define svxz4 %ymm15
+#define d0 %r9
+#define d1 %r10
+#define d2 %r11
+#define d3 %r12
+#define d4 %r13
+
+ENTRY(poly1305_4block_avx2)
+	# %rdi: Accumulator h[5]
+	# %rsi: 64 byte input block m
+	# %rdx: Poly1305 key r[5]
+	# %rcx: Quadblock count
+	# %r8:  Poly1305 derived key r^2 u[5], r^3 w[5], r^4 y[5],
+
+	# This four-block variant uses loop unrolled block processing. It
+	# requires 4 Poly1305 keys: r, r^2, r^3 and r^4:
+	# h = (h + m) * r  =>  h = (h + m1) * r^4 + m2 * r^3 + m3 * r^2 + m4 * r
+
+	vzeroupper
+	push		%rbx
+	push		%r12
+	push		%r13
+
+	# combine r0,u0,w0,y0
+	vmovd		y0,ruwy0x
+	vmovd		w0,t1x
+	vpunpcklqdq	t1,ruwy0,ruwy0
+	vmovd		u0,t1x
+	vmovd		r0,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy0,ruwy0
+
+	# combine r1,u1,w1,y1 and s1=r1*5,v1=u1*5,x1=w1*5,z1=y1*5
+	vmovd		y1,ruwy1x
+	vmovd		w1,t1x
+	vpunpcklqdq	t1,ruwy1,ruwy1
+	vmovd		u1,t1x
+	vmovd		r1,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy1,ruwy1
+	vpslld		$2,ruwy1,svxz1
+	vpaddd		ruwy1,svxz1,svxz1
+
+	# combine r2,u2,w2,y2 and s2=r2*5,v2=u2*5,x2=w2*5,z2=y2*5
+	vmovd		y2,ruwy2x
+	vmovd		w2,t1x
+	vpunpcklqdq	t1,ruwy2,ruwy2
+	vmovd		u2,t1x
+	vmovd		r2,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy2,ruwy2
+	vpslld		$2,ruwy2,svxz2
+	vpaddd		ruwy2,svxz2,svxz2
+
+	# combine r3,u3,w3,y3 and s3=r3*5,v3=u3*5,x3=w3*5,z3=y3*5
+	vmovd		y3,ruwy3x
+	vmovd		w3,t1x
+	vpunpcklqdq	t1,ruwy3,ruwy3
+	vmovd		u3,t1x
+	vmovd		r3,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy3,ruwy3
+	vpslld		$2,ruwy3,svxz3
+	vpaddd		ruwy3,svxz3,svxz3
+
+	# combine r4,u4,w4,y4 and s4=r4*5,v4=u4*5,x4=w4*5,z4=y4*5
+	vmovd		y4,ruwy4x
+	vmovd		w4,t1x
+	vpunpcklqdq	t1,ruwy4,ruwy4
+	vmovd		u4,t1x
+	vmovd		r4,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy4,ruwy4
+	vpslld		$2,ruwy4,svxz4
+	vpaddd		ruwy4,svxz4,svxz4
+
+.Ldoblock4:
+	# hc0 = [m[48-51] & 0x3ffffff, m[32-35] & 0x3ffffff,
+	#	 m[16-19] & 0x3ffffff, m[ 0- 3] & 0x3ffffff + h0]
+	vmovd		0x00(m),hc0x
+	vmovd		0x10(m),t1x
+	vpunpcklqdq	t1,hc0,hc0
+	vmovd		0x20(m),t1x
+	vmovd		0x30(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc0,hc0
+	vpand		ANMASK(%rip),hc0,hc0
+	vmovd		h0,t1x
+	vpaddd		t1,hc0,hc0
+	# hc1 = [(m[51-54] >> 2) & 0x3ffffff, (m[35-38] >> 2) & 0x3ffffff,
+	#	 (m[19-22] >> 2) & 0x3ffffff, (m[ 3- 6] >> 2) & 0x3ffffff + h1]
+	vmovd		0x03(m),hc1x
+	vmovd		0x13(m),t1x
+	vpunpcklqdq	t1,hc1,hc1
+	vmovd		0x23(m),t1x
+	vmovd		0x33(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc1,hc1
+	vpsrld		$2,hc1,hc1
+	vpand		ANMASK(%rip),hc1,hc1
+	vmovd		h1,t1x
+	vpaddd		t1,hc1,hc1
+	# hc2 = [(m[54-57] >> 4) & 0x3ffffff, (m[38-41] >> 4) & 0x3ffffff,
+	#	 (m[22-25] >> 4) & 0x3ffffff, (m[ 6- 9] >> 4) & 0x3ffffff + h2]
+	vmovd		0x06(m),hc2x
+	vmovd		0x16(m),t1x
+	vpunpcklqdq	t1,hc2,hc2
+	vmovd		0x26(m),t1x
+	vmovd		0x36(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc2,hc2
+	vpsrld		$4,hc2,hc2
+	vpand		ANMASK(%rip),hc2,hc2
+	vmovd		h2,t1x
+	vpaddd		t1,hc2,hc2
+	# hc3 = [(m[57-60] >> 6) & 0x3ffffff, (m[41-44] >> 6) & 0x3ffffff,
+	#	 (m[25-28] >> 6) & 0x3ffffff, (m[ 9-12] >> 6) & 0x3ffffff + h3]
+	vmovd		0x09(m),hc3x
+	vmovd		0x19(m),t1x
+	vpunpcklqdq	t1,hc3,hc3
+	vmovd		0x29(m),t1x
+	vmovd		0x39(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc3,hc3
+	vpsrld		$6,hc3,hc3
+	vpand		ANMASK(%rip),hc3,hc3
+	vmovd		h3,t1x
+	vpaddd		t1,hc3,hc3
+	# hc4 = [(m[60-63] >> 8) | (1<<24), (m[44-47] >> 8) | (1<<24),
+	#	 (m[28-31] >> 8) | (1<<24), (m[12-15] >> 8) | (1<<24) + h4]
+	vmovd		0x0c(m),hc4x
+	vmovd		0x1c(m),t1x
+	vpunpcklqdq	t1,hc4,hc4
+	vmovd		0x2c(m),t1x
+	vmovd		0x3c(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc4,hc4
+	vpsrld		$8,hc4,hc4
+	vpor		ORMASK(%rip),hc4,hc4
+	vmovd		h4,t1x
+	vpaddd		t1,hc4,hc4
+
+	# t1 = [ hc0[3] * r0, hc0[2] * u0, hc0[1] * w0, hc0[0] * y0 ]
+	vpmuludq	hc0,ruwy0,t1
+	# t1 += [ hc1[3] * s4, hc1[2] * v4, hc1[1] * x4, hc1[0] * z4 ]
+	vpmuludq	hc1,svxz4,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * s3, hc2[2] * v3, hc2[1] * x3, hc2[0] * z3 ]
+	vpmuludq	hc2,svxz3,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * s2, hc3[2] * v2, hc3[1] * x2, hc3[0] * z2 ]
+	vpmuludq	hc3,svxz2,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s1, hc4[2] * v1, hc4[1] * x1, hc4[0] * z1 ]
+	vpmuludq	hc4,svxz1,t2
+	vpaddq		t2,t1,t1
+	# d0 = t1[0] + t1[1] + t[2] + t[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d0
+
+	# t1 = [ hc0[3] * r1, hc0[2] * u1,hc0[1] * w1, hc0[0] * y1 ]
+	vpmuludq	hc0,ruwy1,t1
+	# t1 += [ hc1[3] * r0, hc1[2] * u0, hc1[1] * w0, hc1[0] * y0 ]
+	vpmuludq	hc1,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * s4, hc2[2] * v4, hc2[1] * x4, hc2[0] * z4 ]
+	vpmuludq	hc2,svxz4,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * s3, hc3[2] * v3, hc3[1] * x3, hc3[0] * z3 ]
+	vpmuludq	hc3,svxz3,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s2, hc4[2] * v2, hc4[1] * x2, hc4[0] * z2 ]
+	vpmuludq	hc4,svxz2,t2
+	vpaddq		t2,t1,t1
+	# d1 = t1[0] + t1[1] + t1[3] + t1[4]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d1
+
+	# t1 = [ hc0[3] * r2, hc0[2] * u2, hc0[1] * w2, hc0[0] * y2 ]
+	vpmuludq	hc0,ruwy2,t1
+	# t1 += [ hc1[3] * r1, hc1[2] * u1, hc1[1] * w1, hc1[0] * y1 ]
+	vpmuludq	hc1,ruwy1,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * r0, hc2[2] * u0, hc2[1] * w0, hc2[0] * y0 ]
+	vpmuludq	hc2,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * s4, hc3[2] * v4, hc3[1] * x4, hc3[0] * z4 ]
+	vpmuludq	hc3,svxz4,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s3, hc4[2] * v3, hc4[1] * x3, hc4[0] * z3 ]
+	vpmuludq	hc4,svxz3,t2
+	vpaddq		t2,t1,t1
+	# d2 = t1[0] + t1[1] + t1[2] + t1[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d2
+
+	# t1 = [ hc0[3] * r3, hc0[2] * u3, hc0[1] * w3, hc0[0] * y3 ]
+	vpmuludq	hc0,ruwy3,t1
+	# t1 += [ hc1[3] * r2, hc1[2] * u2, hc1[1] * w2, hc1[0] * y2 ]
+	vpmuludq	hc1,ruwy2,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * r1, hc2[2] * u1, hc2[1] * w1, hc2[0] * y1 ]
+	vpmuludq	hc2,ruwy1,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * r0, hc3[2] * u0, hc3[1] * w0, hc3[0] * y0 ]
+	vpmuludq	hc3,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s4, hc4[2] * v4, hc4[1] * x4, hc4[0] * z4 ]
+	vpmuludq	hc4,svxz4,t2
+	vpaddq		t2,t1,t1
+	# d3 = t1[0] + t1[1] + t1[2] + t1[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d3
+
+	# t1 = [ hc0[3] * r4, hc0[2] * u4, hc0[1] * w4, hc0[0] * y4 ]
+	vpmuludq	hc0,ruwy4,t1
+	# t1 += [ hc1[3] * r3, hc1[2] * u3, hc1[1] * w3, hc1[0] * y3 ]
+	vpmuludq	hc1,ruwy3,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * r2, hc2[2] * u2, hc2[1] * w2, hc2[0] * y2 ]
+	vpmuludq	hc2,ruwy2,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * r1, hc3[2] * u1, hc3[1] * w1, hc3[0] * y1 ]
+	vpmuludq	hc3,ruwy1,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * r0, hc4[2] * u0, hc4[1] * w0, hc4[0] * y0 ]
+	vpmuludq	hc4,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# d4 = t1[0] + t1[1] + t1[2] + t1[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d4
+
+	# d1 += d0 >> 26
+	mov		d0,%rax
+	shr		$26,%rax
+	add		%rax,d1
+	# h0 = d0 & 0x3ffffff
+	mov		d0,%rbx
+	and		$0x3ffffff,%ebx
+
+	# d2 += d1 >> 26
+	mov		d1,%rax
+	shr		$26,%rax
+	add		%rax,d2
+	# h1 = d1 & 0x3ffffff
+	mov		d1,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h1
+
+	# d3 += d2 >> 26
+	mov		d2,%rax
+	shr		$26,%rax
+	add		%rax,d3
+	# h2 = d2 & 0x3ffffff
+	mov		d2,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h2
+
+	# d4 += d3 >> 26
+	mov		d3,%rax
+	shr		$26,%rax
+	add		%rax,d4
+	# h3 = d3 & 0x3ffffff
+	mov		d3,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h3
+
+	# h0 += (d4 >> 26) * 5
+	mov		d4,%rax
+	shr		$26,%rax
+	lea		(%eax,%eax,4),%eax
+	add		%eax,%ebx
+	# h4 = d4 & 0x3ffffff
+	mov		d4,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h4
+
+	# h1 += h0 >> 26
+	mov		%ebx,%eax
+	shr		$26,%eax
+	add		%eax,h1
+	# h0 = h0 & 0x3ffffff
+	andl		$0x3ffffff,%ebx
+	mov		%ebx,h0
+
+	add		$0x40,m
+	dec		%rcx
+	jnz		.Ldoblock4
+
+	vzeroupper
+	pop		%r13
+	pop		%r12
+	pop		%rbx
+	ret
+ENDPROC(poly1305_4block_avx2)
diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S
new file mode 100644
index 000000000000..338c748054ed
--- /dev/null
+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S
@@ -0,0 +1,582 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539, x64 SSE2 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+.data
+.align 16
+
+ANMASK:	.octa 0x0000000003ffffff0000000003ffffff
+ORMASK:	.octa 0x00000000010000000000000001000000
+
+.text
+
+#define h0 0x00(%rdi)
+#define h1 0x04(%rdi)
+#define h2 0x08(%rdi)
+#define h3 0x0c(%rdi)
+#define h4 0x10(%rdi)
+#define r0 0x00(%rdx)
+#define r1 0x04(%rdx)
+#define r2 0x08(%rdx)
+#define r3 0x0c(%rdx)
+#define r4 0x10(%rdx)
+#define s1 0x00(%rsp)
+#define s2 0x04(%rsp)
+#define s3 0x08(%rsp)
+#define s4 0x0c(%rsp)
+#define m %rsi
+#define h01 %xmm0
+#define h23 %xmm1
+#define h44 %xmm2
+#define t1 %xmm3
+#define t2 %xmm4
+#define t3 %xmm5
+#define t4 %xmm6
+#define mask %xmm7
+#define d0 %r8
+#define d1 %r9
+#define d2 %r10
+#define d3 %r11
+#define d4 %r12
+
+ENTRY(poly1305_block_sse2)
+	# %rdi: Accumulator h[5]
+	# %rsi: 16 byte input block m
+	# %rdx: Poly1305 key r[5]
+	# %rcx: Block count
+
+	# This single block variant tries to improve performance by doing two
+	# multiplications in parallel using SSE instructions. There is quite
+	# some quardword packing involved, hence the speedup is marginal.
+
+	push		%rbx
+	push		%r12
+	sub		$0x10,%rsp
+
+	# s1..s4 = r1..r4 * 5
+	mov		r1,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s1
+	mov		r2,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s2
+	mov		r3,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s3
+	mov		r4,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s4
+
+	movdqa		ANMASK(%rip),mask
+
+.Ldoblock:
+	# h01 = [0, h1, 0, h0]
+	# h23 = [0, h3, 0, h2]
+	# h44 = [0, h4, 0, h4]
+	movd		h0,h01
+	movd		h1,t1
+	movd		h2,h23
+	movd		h3,t2
+	movd		h4,h44
+	punpcklqdq	t1,h01
+	punpcklqdq	t2,h23
+	punpcklqdq	h44,h44
+
+	# h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ]
+	movd		0x00(m),t1
+	movd		0x03(m),t2
+	psrld		$2,t2
+	punpcklqdq	t2,t1
+	pand		mask,t1
+	paddd		t1,h01
+	# h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ]
+	movd		0x06(m),t1
+	movd		0x09(m),t2
+	psrld		$4,t1
+	psrld		$6,t2
+	punpcklqdq	t2,t1
+	pand		mask,t1
+	paddd		t1,h23
+	# h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ]
+	mov		0x0c(m),%eax
+	shr		$8,%eax
+	or		$0x01000000,%eax
+	movd		%eax,t1
+	pshufd		$0xc4,t1,t1
+	paddd		t1,h44
+
+	# t1[0] = h0 * r0 + h2 * s3
+	# t1[1] = h1 * s4 + h3 * s2
+	movd		r0,t1
+	movd		s4,t2
+	punpcklqdq	t2,t1
+	pmuludq		h01,t1
+	movd		s3,t2
+	movd		s2,t3
+	punpcklqdq	t3,t2
+	pmuludq		h23,t2
+	paddq		t2,t1
+	# t2[0] = h0 * r1 + h2 * s4
+	# t2[1] = h1 * r0 + h3 * s3
+	movd		r1,t2
+	movd		r0,t3
+	punpcklqdq	t3,t2
+	pmuludq		h01,t2
+	movd		s4,t3
+	movd		s3,t4
+	punpcklqdq	t4,t3
+	pmuludq		h23,t3
+	paddq		t3,t2
+	# t3[0] = h4 * s1
+	# t3[1] = h4 * s2
+	movd		s1,t3
+	movd		s2,t4
+	punpcklqdq	t4,t3
+	pmuludq		h44,t3
+	# d0 = t1[0] + t1[1] + t3[0]
+	# d1 = t2[0] + t2[1] + t3[1]
+	movdqa		t1,t4
+	punpcklqdq	t2,t4
+	punpckhqdq	t2,t1
+	paddq		t4,t1
+	paddq		t3,t1
+	movq		t1,d0
+	psrldq		$8,t1
+	movq		t1,d1
+
+	# t1[0] = h0 * r2 + h2 * r0
+	# t1[1] = h1 * r1 + h3 * s4
+	movd		r2,t1
+	movd		r1,t2
+	punpcklqdq 	t2,t1
+	pmuludq		h01,t1
+	movd		r0,t2
+	movd		s4,t3
+	punpcklqdq	t3,t2
+	pmuludq		h23,t2
+	paddq		t2,t1
+	# t2[0] = h0 * r3 + h2 * r1
+	# t2[1] = h1 * r2 + h3 * r0
+	movd		r3,t2
+	movd		r2,t3
+	punpcklqdq	t3,t2
+	pmuludq		h01,t2
+	movd		r1,t3
+	movd		r0,t4
+	punpcklqdq	t4,t3
+	pmuludq		h23,t3
+	paddq		t3,t2
+	# t3[0] = h4 * s3
+	# t3[1] = h4 * s4
+	movd		s3,t3
+	movd		s4,t4
+	punpcklqdq	t4,t3
+	pmuludq		h44,t3
+	# d2 = t1[0] + t1[1] + t3[0]
+	# d3 = t2[0] + t2[1] + t3[1]
+	movdqa		t1,t4
+	punpcklqdq	t2,t4
+	punpckhqdq	t2,t1
+	paddq		t4,t1
+	paddq		t3,t1
+	movq		t1,d2
+	psrldq		$8,t1
+	movq		t1,d3
+
+	# t1[0] = h0 * r4 + h2 * r2
+	# t1[1] = h1 * r3 + h3 * r1
+	movd		r4,t1
+	movd		r3,t2
+	punpcklqdq	t2,t1
+	pmuludq		h01,t1
+	movd		r2,t2
+	movd		r1,t3
+	punpcklqdq	t3,t2
+	pmuludq		h23,t2
+	paddq		t2,t1
+	# t3[0] = h4 * r0
+	movd		r0,t3
+	pmuludq		h44,t3
+	# d4 = t1[0] + t1[1] + t3[0]
+	movdqa		t1,t4
+	psrldq		$8,t4
+	paddq		t4,t1
+	paddq		t3,t1
+	movq		t1,d4
+
+	# d1 += d0 >> 26
+	mov		d0,%rax
+	shr		$26,%rax
+	add		%rax,d1
+	# h0 = d0 & 0x3ffffff
+	mov		d0,%rbx
+	and		$0x3ffffff,%ebx
+
+	# d2 += d1 >> 26
+	mov		d1,%rax
+	shr		$26,%rax
+	add		%rax,d2
+	# h1 = d1 & 0x3ffffff
+	mov		d1,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h1
+
+	# d3 += d2 >> 26
+	mov		d2,%rax
+	shr		$26,%rax
+	add		%rax,d3
+	# h2 = d2 & 0x3ffffff
+	mov		d2,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h2
+
+	# d4 += d3 >> 26
+	mov		d3,%rax
+	shr		$26,%rax
+	add		%rax,d4
+	# h3 = d3 & 0x3ffffff
+	mov		d3,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h3
+
+	# h0 += (d4 >> 26) * 5
+	mov		d4,%rax
+	shr		$26,%rax
+	lea		(%eax,%eax,4),%eax
+	add		%eax,%ebx
+	# h4 = d4 & 0x3ffffff
+	mov		d4,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h4
+
+	# h1 += h0 >> 26
+	mov		%ebx,%eax
+	shr		$26,%eax
+	add		%eax,h1
+	# h0 = h0 & 0x3ffffff
+	andl		$0x3ffffff,%ebx
+	mov		%ebx,h0
+
+	add		$0x10,m
+	dec		%rcx
+	jnz		.Ldoblock
+
+	add		$0x10,%rsp
+	pop		%r12
+	pop		%rbx
+	ret
+ENDPROC(poly1305_block_sse2)
+
+
+#define u0 0x00(%r8)
+#define u1 0x04(%r8)
+#define u2 0x08(%r8)
+#define u3 0x0c(%r8)
+#define u4 0x10(%r8)
+#define hc0 %xmm0
+#define hc1 %xmm1
+#define hc2 %xmm2
+#define hc3 %xmm5
+#define hc4 %xmm6
+#define ru0 %xmm7
+#define ru1 %xmm8
+#define ru2 %xmm9
+#define ru3 %xmm10
+#define ru4 %xmm11
+#define sv1 %xmm12
+#define sv2 %xmm13
+#define sv3 %xmm14
+#define sv4 %xmm15
+#undef d0
+#define d0 %r13
+
+ENTRY(poly1305_2block_sse2)
+	# %rdi: Accumulator h[5]
+	# %rsi: 16 byte input block m
+	# %rdx: Poly1305 key r[5]
+	# %rcx: Doubleblock count
+	# %r8:  Poly1305 derived key r^2 u[5]
+
+	# This two-block variant further improves performance by using loop
+	# unrolled block processing. This is more straight forward and does
+	# less byte shuffling, but requires a second Poly1305 key r^2:
+	# h = (h + m) * r    =>    h = (h + m1) * r^2 + m2 * r
+
+	push		%rbx
+	push		%r12
+	push		%r13
+
+	# combine r0,u0
+	movd		u0,ru0
+	movd		r0,t1
+	punpcklqdq	t1,ru0
+
+	# combine r1,u1 and s1=r1*5,v1=u1*5
+	movd		u1,ru1
+	movd		r1,t1
+	punpcklqdq	t1,ru1
+	movdqa		ru1,sv1
+	pslld		$2,sv1
+	paddd		ru1,sv1
+
+	# combine r2,u2 and s2=r2*5,v2=u2*5
+	movd		u2,ru2
+	movd		r2,t1
+	punpcklqdq	t1,ru2
+	movdqa		ru2,sv2
+	pslld		$2,sv2
+	paddd		ru2,sv2
+
+	# combine r3,u3 and s3=r3*5,v3=u3*5
+	movd		u3,ru3
+	movd		r3,t1
+	punpcklqdq	t1,ru3
+	movdqa		ru3,sv3
+	pslld		$2,sv3
+	paddd		ru3,sv3
+
+	# combine r4,u4 and s4=r4*5,v4=u4*5
+	movd		u4,ru4
+	movd		r4,t1
+	punpcklqdq	t1,ru4
+	movdqa		ru4,sv4
+	pslld		$2,sv4
+	paddd		ru4,sv4
+
+.Ldoblock2:
+	# hc0 = [ m[16-19] & 0x3ffffff, h0 + m[0-3] & 0x3ffffff ]
+	movd		0x00(m),hc0
+	movd		0x10(m),t1
+	punpcklqdq	t1,hc0
+	pand		ANMASK(%rip),hc0
+	movd		h0,t1
+	paddd		t1,hc0
+	# hc1 = [ (m[19-22] >> 2) & 0x3ffffff, h1 + (m[3-6] >> 2) & 0x3ffffff ]
+	movd		0x03(m),hc1
+	movd		0x13(m),t1
+	punpcklqdq	t1,hc1
+	psrld		$2,hc1
+	pand		ANMASK(%rip),hc1
+	movd		h1,t1
+	paddd		t1,hc1
+	# hc2 = [ (m[22-25] >> 4) & 0x3ffffff, h2 + (m[6-9] >> 4) & 0x3ffffff ]
+	movd		0x06(m),hc2
+	movd		0x16(m),t1
+	punpcklqdq	t1,hc2
+	psrld		$4,hc2
+	pand		ANMASK(%rip),hc2
+	movd		h2,t1
+	paddd		t1,hc2
+	# hc3 = [ (m[25-28] >> 6) & 0x3ffffff, h3 + (m[9-12] >> 6) & 0x3ffffff ]
+	movd		0x09(m),hc3
+	movd		0x19(m),t1
+	punpcklqdq	t1,hc3
+	psrld		$6,hc3
+	pand		ANMASK(%rip),hc3
+	movd		h3,t1
+	paddd		t1,hc3
+	# hc4 = [ (m[28-31] >> 8) | (1<<24), h4 + (m[12-15] >> 8) | (1<<24) ]
+	movd		0x0c(m),hc4
+	movd		0x1c(m),t1
+	punpcklqdq	t1,hc4
+	psrld		$8,hc4
+	por		ORMASK(%rip),hc4
+	movd		h4,t1
+	paddd		t1,hc4
+
+	# t1 = [ hc0[1] * r0, hc0[0] * u0 ]
+	movdqa		ru0,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * s4, hc1[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * s3, hc2[0] * v3 ]
+	movdqa		sv3,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * s2, hc3[0] * v2 ]
+	movdqa		sv2,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s1, hc4[0] * v1 ]
+	movdqa		sv1,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d0 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d0
+
+	# t1 = [ hc0[1] * r1, hc0[0] * u1 ]
+	movdqa		ru1,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r0, hc1[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * s4, hc2[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * s3, hc3[0] * v3 ]
+	movdqa		sv3,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s2, hc4[0] * v2 ]
+	movdqa		sv2,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d1 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d1
+
+	# t1 = [ hc0[1] * r2, hc0[0] * u2 ]
+	movdqa		ru2,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r1, hc1[0] * u1 ]
+	movdqa		ru1,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * r0, hc2[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * s4, hc3[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s3, hc4[0] * v3 ]
+	movdqa		sv3,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d2 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d2
+
+	# t1 = [ hc0[1] * r3, hc0[0] * u3 ]
+	movdqa		ru3,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r2, hc1[0] * u2 ]
+	movdqa		ru2,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * r1, hc2[0] * u1 ]
+	movdqa		ru1,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * r0, hc3[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s4, hc4[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d3 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d3
+
+	# t1 = [ hc0[1] * r4, hc0[0] * u4 ]
+	movdqa		ru4,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r3, hc1[0] * u3 ]
+	movdqa		ru3,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * r2, hc2[0] * u2 ]
+	movdqa		ru2,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * r1, hc3[0] * u1 ]
+	movdqa		ru1,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * r0, hc4[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d4 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d4
+
+	# d1 += d0 >> 26
+	mov		d0,%rax
+	shr		$26,%rax
+	add		%rax,d1
+	# h0 = d0 & 0x3ffffff
+	mov		d0,%rbx
+	and		$0x3ffffff,%ebx
+
+	# d2 += d1 >> 26
+	mov		d1,%rax
+	shr		$26,%rax
+	add		%rax,d2
+	# h1 = d1 & 0x3ffffff
+	mov		d1,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h1
+
+	# d3 += d2 >> 26
+	mov		d2,%rax
+	shr		$26,%rax
+	add		%rax,d3
+	# h2 = d2 & 0x3ffffff
+	mov		d2,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h2
+
+	# d4 += d3 >> 26
+	mov		d3,%rax
+	shr		$26,%rax
+	add		%rax,d4
+	# h3 = d3 & 0x3ffffff
+	mov		d3,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h3
+
+	# h0 += (d4 >> 26) * 5
+	mov		d4,%rax
+	shr		$26,%rax
+	lea		(%eax,%eax,4),%eax
+	add		%eax,%ebx
+	# h4 = d4 & 0x3ffffff
+	mov		d4,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h4
+
+	# h1 += h0 >> 26
+	mov		%ebx,%eax
+	shr		$26,%eax
+	add		%eax,h1
+	# h0 = h0 & 0x3ffffff
+	andl		$0x3ffffff,%ebx
+	mov		%ebx,h0
+
+	add		$0x20,m
+	dec		%rcx
+	jnz		.Ldoblock2
+
+	pop		%r13
+	pop		%r12
+	pop		%rbx
+	ret
+ENDPROC(poly1305_2block_sse2)
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
new file mode 100644
index 000000000000..f7170d764f32
--- /dev/null
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -0,0 +1,207 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/poly1305.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/simd.h>
+
+struct poly1305_simd_desc_ctx {
+	struct poly1305_desc_ctx base;
+	/* derived key u set? */
+	bool uset;
+#ifdef CONFIG_AS_AVX2
+	/* derived keys r^3, r^4 set? */
+	bool wset;
+#endif
+	/* derived Poly1305 key r^2 */
+	u32 u[5];
+	/* ... silently appended r^3 and r^4 when using AVX2 */
+};
+
+asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src,
+				    const u32 *r, unsigned int blocks);
+asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r,
+				     unsigned int blocks, const u32 *u);
+#ifdef CONFIG_AS_AVX2
+asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r,
+				     unsigned int blocks, const u32 *u);
+static bool poly1305_use_avx2;
+#endif
+
+static int poly1305_simd_init(struct shash_desc *desc)
+{
+	struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc);
+
+	sctx->uset = false;
+#ifdef CONFIG_AS_AVX2
+	sctx->wset = false;
+#endif
+
+	return crypto_poly1305_init(desc);
+}
+
+static void poly1305_simd_mult(u32 *a, const u32 *b)
+{
+	u8 m[POLY1305_BLOCK_SIZE];
+
+	memset(m, 0, sizeof(m));
+	/* The poly1305 block function adds a hi-bit to the accumulator which
+	 * we don't need for key multiplication; compensate for it. */
+	a[4] -= 1 << 24;
+	poly1305_block_sse2(a, m, b, 1);
+}
+
+static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
+					 const u8 *src, unsigned int srclen)
+{
+	struct poly1305_simd_desc_ctx *sctx;
+	unsigned int blocks, datalen;
+
+	BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base));
+	sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base);
+
+	if (unlikely(!dctx->sset)) {
+		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+		src += srclen - datalen;
+		srclen = datalen;
+	}
+
+#ifdef CONFIG_AS_AVX2
+	if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) {
+		if (unlikely(!sctx->wset)) {
+			if (!sctx->uset) {
+				memcpy(sctx->u, dctx->r, sizeof(sctx->u));
+				poly1305_simd_mult(sctx->u, dctx->r);
+				sctx->uset = true;
+			}
+			memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u + 5, dctx->r);
+			memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u + 10, dctx->r);
+			sctx->wset = true;
+		}
+		blocks = srclen / (POLY1305_BLOCK_SIZE * 4);
+		poly1305_4block_avx2(dctx->h, src, dctx->r, blocks, sctx->u);
+		src += POLY1305_BLOCK_SIZE * 4 * blocks;
+		srclen -= POLY1305_BLOCK_SIZE * 4 * blocks;
+	}
+#endif
+	if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) {
+		if (unlikely(!sctx->uset)) {
+			memcpy(sctx->u, dctx->r, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u, dctx->r);
+			sctx->uset = true;
+		}
+		blocks = srclen / (POLY1305_BLOCK_SIZE * 2);
+		poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u);
+		src += POLY1305_BLOCK_SIZE * 2 * blocks;
+		srclen -= POLY1305_BLOCK_SIZE * 2 * blocks;
+	}
+	if (srclen >= POLY1305_BLOCK_SIZE) {
+		poly1305_block_sse2(dctx->h, src, dctx->r, 1);
+		srclen -= POLY1305_BLOCK_SIZE;
+	}
+	return srclen;
+}
+
+static int poly1305_simd_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int bytes;
+
+	/* kernel_fpu_begin/end is costly, use fallback for small updates */
+	if (srclen <= 288 || !may_use_simd())
+		return crypto_poly1305_update(desc, src, srclen);
+
+	kernel_fpu_begin();
+
+	if (unlikely(dctx->buflen)) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		srclen -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_simd_blocks(dctx, dctx->buf,
+					     POLY1305_BLOCK_SIZE);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		bytes = poly1305_simd_blocks(dctx, src, srclen);
+		src += srclen - bytes;
+		srclen = bytes;
+	}
+
+	kernel_fpu_end();
+
+	if (unlikely(srclen)) {
+		dctx->buflen = srclen;
+		memcpy(dctx->buf, src, srclen);
+	}
+
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.digestsize	= POLY1305_DIGEST_SIZE,
+	.init		= poly1305_simd_init,
+	.update		= poly1305_simd_update,
+	.final		= crypto_poly1305_final,
+	.setkey		= crypto_poly1305_setkey,
+	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
+	.base		= {
+		.cra_name		= "poly1305",
+		.cra_driver_name	= "poly1305-simd",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_alignmask		= sizeof(u32) - 1,
+		.cra_blocksize		= POLY1305_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init poly1305_simd_mod_init(void)
+{
+	if (!cpu_has_xmm2)
+		return -ENODEV;
+
+#ifdef CONFIG_AS_AVX2
+	poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+			    cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL);
+	alg.descsize = sizeof(struct poly1305_simd_desc_ctx);
+	if (poly1305_use_avx2)
+		alg.descsize += 10 * sizeof(u32);
+#endif
+	return crypto_register_shash(&alg);
+}
+
+static void __exit poly1305_simd_mod_exit(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(poly1305_simd_mod_init);
+module_exit(poly1305_simd_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("Poly1305 authenticator");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-simd");
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 7a144971db79..bd55dedd7614 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -2,6 +2,7 @@
 # Makefile for the x86 low level entry code
 #
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+obj-y				+= common.o
 
 obj-y				+= vdso/
 obj-y				+= vsyscall/
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index f4e6308c4200..3c71dd947c7b 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -135,9 +135,6 @@ For 32-bit we have the following conventions - kernel is built with
 	movq %rbp, 4*8+\offset(%rsp)
 	movq %rbx, 5*8+\offset(%rsp)
 	.endm
-	.macro SAVE_EXTRA_REGS_RBP offset=0
-	movq %rbp, 4*8+\offset(%rsp)
-	.endm
 
 	.macro RESTORE_EXTRA_REGS offset=0
 	movq 0*8+\offset(%rsp), %r15
@@ -193,12 +190,6 @@ For 32-bit we have the following conventions - kernel is built with
 	.macro RESTORE_C_REGS_EXCEPT_RCX_R11
 	RESTORE_C_REGS_HELPER 1,0,0,1,1
 	.endm
-	.macro RESTORE_RSI_RDI
-	RESTORE_C_REGS_HELPER 0,0,0,0,0
-	.endm
-	.macro RESTORE_RSI_RDI_RDX
-	RESTORE_C_REGS_HELPER 0,0,0,0,1
-	.endm
 
 	.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
 	subq $-(15*8+\addskip), %rsp
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
new file mode 100644
index 000000000000..80dcc9261ca3
--- /dev/null
+++ b/arch/x86/entry/common.c
@@ -0,0 +1,318 @@
+/*
+ * common.c - C code for kernel entry and exit
+ * Copyright (c) 2015 Andrew Lutomirski
+ * GPL v2
+ *
+ * Based on asm and ptrace code by many authors.  The code here originated
+ * in ptrace.c and signal.c.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/tracehook.h>
+#include <linux/audit.h>
+#include <linux/seccomp.h>
+#include <linux/signal.h>
+#include <linux/export.h>
+#include <linux/context_tracking.h>
+#include <linux/user-return-notifier.h>
+#include <linux/uprobes.h>
+
+#include <asm/desc.h>
+#include <asm/traps.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/* Called on entry from user mode with IRQs off. */
+__visible void enter_from_user_mode(void)
+{
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit();
+}
+#endif
+
+static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
+{
+#ifdef CONFIG_X86_64
+	if (arch == AUDIT_ARCH_X86_64) {
+		audit_syscall_entry(regs->orig_ax, regs->di,
+				    regs->si, regs->dx, regs->r10);
+	} else
+#endif
+	{
+		audit_syscall_entry(regs->orig_ax, regs->bx,
+				    regs->cx, regs->dx, regs->si);
+	}
+}
+
+/*
+ * We can return 0 to resume the syscall or anything else to go to phase
+ * 2.  If we resume the syscall, we need to put something appropriate in
+ * regs->orig_ax.
+ *
+ * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax
+ * are fully functional.
+ *
+ * For phase 2's benefit, our return value is:
+ * 0:			resume the syscall
+ * 1:			go to phase 2; no seccomp phase 2 needed
+ * anything else:	go to phase 2; pass return value to seccomp
+ */
+unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
+{
+	unsigned long ret = 0;
+	u32 work;
+
+	BUG_ON(regs != task_pt_regs(current));
+
+	work = ACCESS_ONCE(current_thread_info()->flags) &
+		_TIF_WORK_SYSCALL_ENTRY;
+
+#ifdef CONFIG_CONTEXT_TRACKING
+	/*
+	 * If TIF_NOHZ is set, we are required to call user_exit() before
+	 * doing anything that could touch RCU.
+	 */
+	if (work & _TIF_NOHZ) {
+		enter_from_user_mode();
+		work &= ~_TIF_NOHZ;
+	}
+#endif
+
+#ifdef CONFIG_SECCOMP
+	/*
+	 * Do seccomp first -- it should minimize exposure of other
+	 * code, and keeping seccomp fast is probably more valuable
+	 * than the rest of this.
+	 */
+	if (work & _TIF_SECCOMP) {
+		struct seccomp_data sd;
+
+		sd.arch = arch;
+		sd.nr = regs->orig_ax;
+		sd.instruction_pointer = regs->ip;
+#ifdef CONFIG_X86_64
+		if (arch == AUDIT_ARCH_X86_64) {
+			sd.args[0] = regs->di;
+			sd.args[1] = regs->si;
+			sd.args[2] = regs->dx;
+			sd.args[3] = regs->r10;
+			sd.args[4] = regs->r8;
+			sd.args[5] = regs->r9;
+		} else
+#endif
+		{
+			sd.args[0] = regs->bx;
+			sd.args[1] = regs->cx;
+			sd.args[2] = regs->dx;
+			sd.args[3] = regs->si;
+			sd.args[4] = regs->di;
+			sd.args[5] = regs->bp;
+		}
+
+		BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0);
+		BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1);
+
+		ret = seccomp_phase1(&sd);
+		if (ret == SECCOMP_PHASE1_SKIP) {
+			regs->orig_ax = -1;
+			ret = 0;
+		} else if (ret != SECCOMP_PHASE1_OK) {
+			return ret;  /* Go directly to phase 2 */
+		}
+
+		work &= ~_TIF_SECCOMP;
+	}
+#endif
+
+	/* Do our best to finish without phase 2. */
+	if (work == 0)
+		return ret;  /* seccomp and/or nohz only (ret == 0 here) */
+
+#ifdef CONFIG_AUDITSYSCALL
+	if (work == _TIF_SYSCALL_AUDIT) {
+		/*
+		 * If there is no more work to be done except auditing,
+		 * then audit in phase 1.  Phase 2 always audits, so, if
+		 * we audit here, then we can't go on to phase 2.
+		 */
+		do_audit_syscall_entry(regs, arch);
+		return 0;
+	}
+#endif
+
+	return 1;  /* Something is enabled that we can't handle in phase 1 */
+}
+
+/* Returns the syscall nr to run (which should match regs->orig_ax). */
+long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
+				unsigned long phase1_result)
+{
+	long ret = 0;
+	u32 work = ACCESS_ONCE(current_thread_info()->flags) &
+		_TIF_WORK_SYSCALL_ENTRY;
+
+	BUG_ON(regs != task_pt_regs(current));
+
+	/*
+	 * If we stepped into a sysenter/syscall insn, it trapped in
+	 * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
+	 * If user-mode had set TF itself, then it's still clear from
+	 * do_debug() and we need to set it again to restore the user
+	 * state.  If we entered on the slow path, TF was already set.
+	 */
+	if (work & _TIF_SINGLESTEP)
+		regs->flags |= X86_EFLAGS_TF;
+
+#ifdef CONFIG_SECCOMP
+	/*
+	 * Call seccomp_phase2 before running the other hooks so that
+	 * they can see any changes made by a seccomp tracer.
+	 */
+	if (phase1_result > 1 && seccomp_phase2(phase1_result)) {
+		/* seccomp failures shouldn't expose any additional code. */
+		return -1;
+	}
+#endif
+
+	if (unlikely(work & _TIF_SYSCALL_EMU))
+		ret = -1L;
+
+	if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
+	    tracehook_report_syscall_entry(regs))
+		ret = -1L;
+
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->orig_ax);
+
+	do_audit_syscall_entry(regs, arch);
+
+	return ret ?: regs->orig_ax;
+}
+
+long syscall_trace_enter(struct pt_regs *regs)
+{
+	u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+	unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch);
+
+	if (phase1_result == 0)
+		return regs->orig_ax;
+	else
+		return syscall_trace_enter_phase2(regs, arch, phase1_result);
+}
+
+static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
+{
+	unsigned long top_of_stack =
+		(unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING;
+	return (struct thread_info *)(top_of_stack - THREAD_SIZE);
+}
+
+/* Called with IRQs disabled. */
+__visible void prepare_exit_to_usermode(struct pt_regs *regs)
+{
+	if (WARN_ON(!irqs_disabled()))
+		local_irq_disable();
+
+	/*
+	 * In order to return to user mode, we need to have IRQs off with
+	 * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY,
+	 * _TIF_UPROBE, or _TIF_NEED_RESCHED set.  Several of these flags
+	 * can be set at any time on preemptable kernels if we have IRQs on,
+	 * so we need to loop.  Disabling preemption wouldn't help: doing the
+	 * work to clear some of the flags can sleep.
+	 */
+	while (true) {
+		u32 cached_flags =
+			READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+
+		if (!(cached_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME |
+				      _TIF_UPROBE | _TIF_NEED_RESCHED |
+				      _TIF_USER_RETURN_NOTIFY)))
+			break;
+
+		/* We have work to do. */
+		local_irq_enable();
+
+		if (cached_flags & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (cached_flags & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		/* deal with pending signal delivery */
+		if (cached_flags & _TIF_SIGPENDING)
+			do_signal(regs);
+
+		if (cached_flags & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(regs);
+		}
+
+		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
+			fire_user_return_notifiers();
+
+		/* Disable IRQs and retry */
+		local_irq_disable();
+	}
+
+	user_enter();
+}
+
+/*
+ * Called with IRQs on and fully valid regs.  Returns with IRQs off in a
+ * state such that we can immediately switch to user mode.
+ */
+__visible void syscall_return_slowpath(struct pt_regs *regs)
+{
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	u32 cached_flags = READ_ONCE(ti->flags);
+	bool step;
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (WARN(irqs_disabled(), "syscall %ld left IRQs disabled",
+		 regs->orig_ax))
+		local_irq_enable();
+
+	/*
+	 * First do one-time work.  If these work items are enabled, we
+	 * want to run them exactly once per syscall exit with IRQs on.
+	 */
+	if (cached_flags & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |
+			    _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)) {
+		audit_syscall_exit(regs);
+
+		if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
+			trace_sys_exit(regs, regs->ax);
+
+		/*
+		 * If TIF_SYSCALL_EMU is set, we only get here because of
+		 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
+		 * We already reported this syscall instruction in
+		 * syscall_trace_enter().
+		 */
+		step = unlikely(
+			(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
+			== _TIF_SINGLESTEP);
+		if (step || cached_flags & _TIF_SYSCALL_TRACE)
+			tracehook_report_syscall_exit(regs, step);
+	}
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
+	 * returning to user mode.
+	 */
+	ti->status &= ~TS_COMPAT;
+#endif
+
+	local_irq_disable();
+	prepare_exit_to_usermode(regs);
+}
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 21dc60a60b5f..b2909bf8cf70 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -45,16 +45,6 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE		0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-# define sysenter_audit		syscall_trace_entry
-# define sysexit_audit		syscall_exit_work
-#endif
-
 	.section .entry.text, "ax"
 
 /*
@@ -266,14 +256,10 @@ ret_from_intr:
 
 ENTRY(resume_userspace)
 	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
-						# setting need_resched or sigpending
-						# between sampling and the iret
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
-	movl	TI_flags(%ebp), %ecx
-	andl	$_TIF_WORK_MASK, %ecx		# is there any work to be done on
-						# int/exception return?
-	jne	work_pending
+	movl	%esp, %eax
+	call	prepare_exit_to_usermode
 	jmp	restore_all
 END(ret_from_exception)
 
@@ -339,7 +325,7 @@ sysenter_past_esp:
 	GET_THREAD_INFO(%ebp)
 
 	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
-	jnz	sysenter_audit
+	jnz	syscall_trace_entry
 sysenter_do_call:
 	cmpl	$(NR_syscalls), %eax
 	jae	sysenter_badsys
@@ -351,7 +337,7 @@ sysenter_after_call:
 	TRACE_IRQS_OFF
 	movl	TI_flags(%ebp), %ecx
 	testl	$_TIF_ALLWORK_MASK, %ecx
-	jnz	sysexit_audit
+	jnz	syscall_exit_work_irqs_off
 sysenter_exit:
 /* if something modifies registers it must also disable sysexit */
 	movl	PT_EIP(%esp), %edx
@@ -362,40 +348,6 @@ sysenter_exit:
 	PTGS_TO_GS
 	ENABLE_INTERRUPTS_SYSEXIT
 
-#ifdef CONFIG_AUDITSYSCALL
-sysenter_audit:
-	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp)
-	jnz	syscall_trace_entry
-	/* movl	PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
-	movl	PT_EBX(%esp), %edx		/* ebx/a0: 2nd arg to audit */
-	/* movl	PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
-	pushl	PT_ESI(%esp)			/* a3: 5th arg */
-	pushl	PT_EDX+4(%esp)			/* a2: 4th arg */
-	call	__audit_syscall_entry
-	popl	%ecx				/* get that remapped edx off the stack */
-	popl	%ecx				/* get that remapped esi off the stack */
-	movl	PT_EAX(%esp), %eax		/* reload syscall number */
-	jmp	sysenter_do_call
-
-sysexit_audit:
-	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
-	jnz	syscall_exit_work
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)
-	movl	%eax, %edx			/* second arg, syscall return value */
-	cmpl	$-MAX_ERRNO, %eax		/* is it an error ? */
-	setbe %al				/* 1 if so, 0 if not */
-	movzbl %al, %eax			/* zero-extend that */
-	call	__audit_syscall_exit
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl	TI_flags(%ebp), %ecx
-	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
-	jnz	syscall_exit_work
-	movl	PT_EAX(%esp), %eax		/* reload syscall return value */
-	jmp	sysenter_exit
-#endif
-
 .pushsection .fixup, "ax"
 2:	movl	$0, PT_FS(%esp)
 	jmp	1b
@@ -421,13 +373,7 @@ syscall_after_call:
 	movl	%eax, PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
-						# setting need_resched or sigpending
-						# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl	TI_flags(%ebp), %ecx
-	testl	$_TIF_ALLWORK_MASK, %ecx	# current->work
-	jnz	syscall_exit_work
+	jmp	syscall_exit_work
 
 restore_all:
 	TRACE_IRQS_IRET
@@ -504,57 +450,6 @@ ldt_ss:
 #endif
 ENDPROC(entry_INT80_32)
 
-	# perform work that needs to be done immediately before resumption
-	ALIGN
-work_pending:
-	testb	$_TIF_NEED_RESCHED, %cl
-	jz	work_notifysig
-work_resched:
-	call	schedule
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
-						# setting need_resched or sigpending
-						# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl	TI_flags(%ebp), %ecx
-	andl	$_TIF_WORK_MASK, %ecx		# is there any work to be done other
-						# than syscall tracing?
-	jz	restore_all
-	testb	$_TIF_NEED_RESCHED, %cl
-	jnz	work_resched
-
-work_notifysig:					# deal with pending signals and
-						# notify-resume requests
-#ifdef CONFIG_VM86
-	testl	$X86_EFLAGS_VM, PT_EFLAGS(%esp)
-	movl	%esp, %eax
-	jnz	work_notifysig_v86		# returning to kernel-space or
-						# vm86-space
-1:
-#else
-	movl	%esp, %eax
-#endif
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	movb	PT_CS(%esp), %bl
-	andb	$SEGMENT_RPL_MASK, %bl
-	cmpb	$USER_RPL, %bl
-	jb	resume_kernel
-	xorl	%edx, %edx
-	call	do_notify_resume
-	jmp	resume_userspace
-
-#ifdef CONFIG_VM86
-	ALIGN
-work_notifysig_v86:
-	pushl	%ecx				# save ti_flags for do_notify_resume
-	call	save_v86_state			# %eax contains pt_regs pointer
-	popl	%ecx
-	movl	%eax, %esp
-	jmp	1b
-#endif
-END(work_pending)
-
 	# perform syscall exit tracing
 	ALIGN
 syscall_trace_entry:
@@ -569,15 +464,14 @@ END(syscall_trace_entry)
 
 	# perform syscall exit tracing
 	ALIGN
-syscall_exit_work:
-	testl	$_TIF_WORK_SYSCALL_EXIT, %ecx
-	jz	work_pending
+syscall_exit_work_irqs_off:
 	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)		# could let syscall_trace_leave() call
-						# schedule() instead
+	ENABLE_INTERRUPTS(CLBR_ANY)
+
+syscall_exit_work:
 	movl	%esp, %eax
-	call	syscall_trace_leave
-	jmp	resume_userspace
+	call	syscall_return_slowpath
+	jmp	restore_all
 END(syscall_exit_work)
 
 syscall_fault:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 3bb2c4302df1..d3033183ed70 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -33,7 +33,6 @@
 #include <asm/paravirt.h>
 #include <asm/percpu.h>
 #include <asm/asm.h>
-#include <asm/context_tracking.h>
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
 #include <linux/err.h>
@@ -229,6 +228,11 @@ entry_SYSCALL_64_fastpath:
 	 */
 	USERGS_SYSRET64
 
+GLOBAL(int_ret_from_sys_call_irqs_off)
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	jmp int_ret_from_sys_call
+
 	/* Do syscall entry tracing */
 tracesys:
 	movq	%rsp, %rdi
@@ -272,69 +276,11 @@ tracesys_phase2:
  * Has correct iret frame.
  */
 GLOBAL(int_ret_from_sys_call)
-	DISABLE_INTERRUPTS(CLBR_NONE)
-int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
-	TRACE_IRQS_OFF
-	movl	$_TIF_ALLWORK_MASK, %edi
-	/* edi:	mask to check */
-GLOBAL(int_with_check)
-	LOCKDEP_SYS_EXIT_IRQ
-	GET_THREAD_INFO(%rcx)
-	movl	TI_flags(%rcx), %edx
-	andl	%edi, %edx
-	jnz	int_careful
-	andl	$~TS_COMPAT, TI_status(%rcx)
-	jmp	syscall_return
-
-	/*
-	 * Either reschedule or signal or syscall exit tracking needed.
-	 * First do a reschedule test.
-	 * edx:	work, edi: workmask
-	 */
-int_careful:
-	bt	$TIF_NEED_RESCHED, %edx
-	jnc	int_very_careful
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq	%rdi
-	SCHEDULE_USER
-	popq	%rdi
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	jmp	int_with_check
-
-	/* handle signals and tracing -- both require a full pt_regs */
-int_very_careful:
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_EXTRA_REGS
-	/* Check for syscall exit trace */
-	testl	$_TIF_WORK_SYSCALL_EXIT, %edx
-	jz	int_signal
-	pushq	%rdi
-	leaq	8(%rsp), %rdi			/* &ptregs -> arg1 */
-	call	syscall_trace_leave
-	popq	%rdi
-	andl	$~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi
-	jmp	int_restore_rest
-
-int_signal:
-	testl	$_TIF_DO_NOTIFY_MASK, %edx
-	jz	1f
-	movq	%rsp, %rdi			/* &ptregs -> arg1 */
-	xorl	%esi, %esi			/* oldset -> arg2 */
-	call	do_notify_resume
-1:	movl	$_TIF_WORK_MASK, %edi
-int_restore_rest:
+	movq	%rsp, %rdi
+	call	syscall_return_slowpath	/* returns with IRQs disabled */
 	RESTORE_EXTRA_REGS
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	jmp	int_with_check
-
-syscall_return:
-	/* The IRETQ could re-enable interrupts: */
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_IRETQ
+	TRACE_IRQS_IRETQ		/* we're about to change IF */
 
 	/*
 	 * Try to use SYSRET instead of IRET if we're returning to
@@ -555,23 +501,22 @@ END(irq_entries_start)
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
 	cld
-	/*
-	 * Since nothing in interrupt handling code touches r12...r15 members
-	 * of "struct pt_regs", and since interrupts can nest, we can save
-	 * four stack slots and simultaneously provide
-	 * an unwind-friendly stack layout by saving "truncated" pt_regs
-	 * exactly up to rbp slot, without these members.
-	 */
-	ALLOC_PT_GPREGS_ON_STACK -RBP
-	SAVE_C_REGS -RBP
-	/* this goes to 0(%rsp) for unwinder, not for saving the value: */
-	SAVE_EXTRA_REGS_RBP -RBP
-
-	leaq	-RBP(%rsp), %rdi		/* arg1 for \func (pointer to pt_regs) */
+	ALLOC_PT_GPREGS_ON_STACK
+	SAVE_C_REGS
+	SAVE_EXTRA_REGS
 
-	testb	$3, CS-RBP(%rsp)
+	testb	$3, CS(%rsp)
 	jz	1f
+
+	/*
+	 * IRQ from user mode.  Switch to kernel gsbase and inform context
+	 * tracking that we're in kernel mode.
+	 */
 	SWAPGS
+#ifdef CONFIG_CONTEXT_TRACKING
+	call enter_from_user_mode
+#endif
+
 1:
 	/*
 	 * Save previous stack pointer, optionally switch to interrupt stack.
@@ -580,14 +525,14 @@ END(irq_entries_start)
 	 * a little cheaper to use a separate counter in the PDA (short of
 	 * moving irq_enter into assembly, which would be too much work)
 	 */
-	movq	%rsp, %rsi
+	movq	%rsp, %rdi
 	incl	PER_CPU_VAR(irq_count)
 	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
-	pushq	%rsi
+	pushq	%rdi
 	/* We entered an interrupt context - irqs are off: */
 	TRACE_IRQS_OFF
 
-	call	\func
+	call	\func	/* rdi points to pt_regs */
 	.endm
 
 	/*
@@ -606,34 +551,19 @@ ret_from_intr:
 	decl	PER_CPU_VAR(irq_count)
 
 	/* Restore saved previous stack */
-	popq	%rsi
-	/* return code expects complete pt_regs - adjust rsp accordingly: */
-	leaq	-RBP(%rsi), %rsp
+	popq	%rsp
 
 	testb	$3, CS(%rsp)
 	jz	retint_kernel
-	/* Interrupt came from user space */
-retint_user:
-	GET_THREAD_INFO(%rcx)
 
-	/* %rcx: thread info. Interrupts are off. */
-retint_with_reschedule:
-	movl	$_TIF_WORK_MASK, %edi
-retint_check:
+	/* Interrupt came from user space */
 	LOCKDEP_SYS_EXIT_IRQ
-	movl	TI_flags(%rcx), %edx
-	andl	%edi, %edx
-	jnz	retint_careful
-
-retint_swapgs:					/* return to user-space */
-	/*
-	 * The iretq could re-enable interrupts:
-	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
+GLOBAL(retint_user)
+	mov	%rsp,%rdi
+	call	prepare_exit_to_usermode
 	TRACE_IRQS_IRETQ
-
 	SWAPGS
-	jmp	restore_c_regs_and_iret
+	jmp	restore_regs_and_iret
 
 /* Returning to kernel space */
 retint_kernel:
@@ -657,6 +587,8 @@ retint_kernel:
  * At this label, code paths which return to kernel and to user,
  * which come from interrupts/exception and from syscalls, merge.
  */
+restore_regs_and_iret:
+	RESTORE_EXTRA_REGS
 restore_c_regs_and_iret:
 	RESTORE_C_REGS
 	REMOVE_PT_GPREGS_FROM_STACK 8
@@ -707,37 +639,6 @@ native_irq_return_ldt:
 	popq	%rax
 	jmp	native_irq_return_iret
 #endif
-
-	/* edi: workmask, edx: work */
-retint_careful:
-	bt	$TIF_NEED_RESCHED, %edx
-	jnc	retint_signal
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq	%rdi
-	SCHEDULE_USER
-	popq	%rdi
-	GET_THREAD_INFO(%rcx)
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	jmp	retint_check
-
-retint_signal:
-	testl	$_TIF_DO_NOTIFY_MASK, %edx
-	jz	retint_swapgs
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	SAVE_EXTRA_REGS
-	movq	$-1, ORIG_RAX(%rsp)
-	xorl	%esi, %esi			/* oldset */
-	movq	%rsp, %rdi			/* &pt_regs */
-	call	do_notify_resume
-	RESTORE_EXTRA_REGS
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	GET_THREAD_INFO(%rcx)
-	jmp	retint_with_reschedule
-
 END(common_interrupt)
 
 /*
@@ -1143,12 +1044,22 @@ ENTRY(error_entry)
 	SAVE_EXTRA_REGS 8
 	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
-	jz	error_kernelspace
+	jz	.Lerror_kernelspace
 
-	/* We entered from user mode */
+.Lerror_entry_from_usermode_swapgs:
+	/*
+	 * We entered from user mode or we're pretending to have entered
+	 * from user mode due to an IRET fault.
+	 */
 	SWAPGS
 
-error_entry_done:
+.Lerror_entry_from_usermode_after_swapgs:
+#ifdef CONFIG_CONTEXT_TRACKING
+	call enter_from_user_mode
+#endif
+
+.Lerror_entry_done:
+
 	TRACE_IRQS_OFF
 	ret
 
@@ -1158,31 +1069,30 @@ error_entry_done:
 	 * truncated RIP for IRET exceptions returning to compat mode. Check
 	 * for these here too.
 	 */
-error_kernelspace:
+.Lerror_kernelspace:
 	incl	%ebx
 	leaq	native_irq_return_iret(%rip), %rcx
 	cmpq	%rcx, RIP+8(%rsp)
-	je	error_bad_iret
+	je	.Lerror_bad_iret
 	movl	%ecx, %eax			/* zero extend */
 	cmpq	%rax, RIP+8(%rsp)
-	je	bstep_iret
+	je	.Lbstep_iret
 	cmpq	$gs_change, RIP+8(%rsp)
-	jne	error_entry_done
+	jne	.Lerror_entry_done
 
 	/*
 	 * hack: gs_change can fail with user gsbase.  If this happens, fix up
 	 * gsbase and proceed.  We'll fix up the exception and land in
 	 * gs_change's error handler with kernel gsbase.
 	 */
-	SWAPGS
-	jmp	error_entry_done
+	jmp	.Lerror_entry_from_usermode_swapgs
 
-bstep_iret:
+.Lbstep_iret:
 	/* Fix truncated RIP */
 	movq	%rcx, RIP+8(%rsp)
 	/* fall through */
 
-error_bad_iret:
+.Lerror_bad_iret:
 	/*
 	 * We came from an IRET to user mode, so we have user gsbase.
 	 * Switch to kernel gsbase:
@@ -1198,7 +1108,7 @@ error_bad_iret:
 	call	fixup_bad_iret
 	mov	%rax, %rsp
 	decl	%ebx
-	jmp	error_entry_done
+	jmp	.Lerror_entry_from_usermode_after_swapgs
 END(error_entry)
 
 
@@ -1209,7 +1119,6 @@ END(error_entry)
  */
 ENTRY(error_exit)
 	movl	%ebx, %eax
-	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl	%eax, %eax
@@ -1237,11 +1146,12 @@ ENTRY(nmi)
 	 *  If the variable is not set and the stack is not the NMI
 	 *  stack then:
 	 *    o Set the special variable on the stack
-	 *    o Copy the interrupt frame into a "saved" location on the stack
-	 *    o Copy the interrupt frame into a "copy" location on the stack
+	 *    o Copy the interrupt frame into an "outermost" location on the
+	 *      stack
+	 *    o Copy the interrupt frame into an "iret" location on the stack
 	 *    o Continue processing the NMI
 	 *  If the variable is set or the previous stack is the NMI stack:
-	 *    o Modify the "copy" location to jump to the repeate_nmi
+	 *    o Modify the "iret" location to jump to the repeat_nmi
 	 *    o return back to the first NMI
 	 *
 	 * Now on exit of the first NMI, we first clear the stack variable
@@ -1250,31 +1160,151 @@ ENTRY(nmi)
 	 * a nested NMI that updated the copy interrupt stack frame, a
 	 * jump will be made to the repeat_nmi code that will handle the second
 	 * NMI.
+	 *
+	 * However, espfix prevents us from directly returning to userspace
+	 * with a single IRET instruction.  Similarly, IRET to user mode
+	 * can fault.  We therefore handle NMIs from user space like
+	 * other IST entries.
 	 */
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 
+	testb	$3, CS-RIP+8(%rsp)
+	jz	.Lnmi_from_kernel
+
+	/*
+	 * NMI from user mode.  We need to run on the thread stack, but we
+	 * can't go through the normal entry paths: NMIs are masked, and
+	 * we don't want to enable interrupts, because then we'll end
+	 * up in an awkward situation in which IRQs are on but NMIs
+	 * are off.
+	 */
+
+	SWAPGS
+	cld
+	movq	%rsp, %rdx
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	pushq	5*8(%rdx)	/* pt_regs->ss */
+	pushq	4*8(%rdx)	/* pt_regs->rsp */
+	pushq	3*8(%rdx)	/* pt_regs->flags */
+	pushq	2*8(%rdx)	/* pt_regs->cs */
+	pushq	1*8(%rdx)	/* pt_regs->rip */
+	pushq   $-1		/* pt_regs->orig_ax */
+	pushq   %rdi		/* pt_regs->di */
+	pushq   %rsi		/* pt_regs->si */
+	pushq   (%rdx)		/* pt_regs->dx */
+	pushq   %rcx		/* pt_regs->cx */
+	pushq   %rax		/* pt_regs->ax */
+	pushq   %r8		/* pt_regs->r8 */
+	pushq   %r9		/* pt_regs->r9 */
+	pushq   %r10		/* pt_regs->r10 */
+	pushq   %r11		/* pt_regs->r11 */
+	pushq	%rbx		/* pt_regs->rbx */
+	pushq	%rbp		/* pt_regs->rbp */
+	pushq	%r12		/* pt_regs->r12 */
+	pushq	%r13		/* pt_regs->r13 */
+	pushq	%r14		/* pt_regs->r14 */
+	pushq	%r15		/* pt_regs->r15 */
+
+	/*
+	 * At this point we no longer need to worry about stack damage
+	 * due to nesting -- we're on the normal thread stack and we're
+	 * done with the NMI stack.
+	 */
+
+	movq	%rsp, %rdi
+	movq	$-1, %rsi
+	call	do_nmi
+
+	/*
+	 * Return back to user mode.  We must *not* do the normal exit
+	 * work, because we don't want to enable interrupts.  Fortunately,
+	 * do_nmi doesn't modify pt_regs.
+	 */
+	SWAPGS
+	jmp	restore_c_regs_and_iret
+
+.Lnmi_from_kernel:
+	/*
+	 * Here's what our stack frame will look like:
+	 * +---------------------------------------------------------+
+	 * | original SS                                             |
+	 * | original Return RSP                                     |
+	 * | original RFLAGS                                         |
+	 * | original CS                                             |
+	 * | original RIP                                            |
+	 * +---------------------------------------------------------+
+	 * | temp storage for rdx                                    |
+	 * +---------------------------------------------------------+
+	 * | "NMI executing" variable                                |
+	 * +---------------------------------------------------------+
+	 * | iret SS          } Copied from "outermost" frame        |
+	 * | iret Return RSP  } on each loop iteration; overwritten  |
+	 * | iret RFLAGS      } by a nested NMI to force another     |
+	 * | iret CS          } iteration if needed.                 |
+	 * | iret RIP         }                                      |
+	 * +---------------------------------------------------------+
+	 * | outermost SS          } initialized in first_nmi;       |
+	 * | outermost Return RSP  } will not be changed before      |
+	 * | outermost RFLAGS      } NMI processing is done.         |
+	 * | outermost CS          } Copied to "iret" frame on each  |
+	 * | outermost RIP         } iteration.                      |
+	 * +---------------------------------------------------------+
+	 * | pt_regs                                                 |
+	 * +---------------------------------------------------------+
+	 *
+	 * The "original" frame is used by hardware.  Before re-enabling
+	 * NMIs, we need to be done with it, and we need to leave enough
+	 * space for the asm code here.
+	 *
+	 * We return by executing IRET while RSP points to the "iret" frame.
+	 * That will either return for real or it will loop back into NMI
+	 * processing.
+	 *
+	 * The "outermost" frame is copied to the "iret" frame on each
+	 * iteration of the loop, so each iteration starts with the "iret"
+	 * frame pointing to the final return target.
+	 */
+
 	/*
-	 * If %cs was not the kernel segment, then the NMI triggered in user
-	 * space, which means it is definitely not nested.
+	 * Determine whether we're a nested NMI.
+	 *
+	 * If we interrupted kernel code between repeat_nmi and
+	 * end_repeat_nmi, then we are a nested NMI.  We must not
+	 * modify the "iret" frame because it's being written by
+	 * the outer NMI.  That's okay; the outer NMI handler is
+	 * about to about to call do_nmi anyway, so we can just
+	 * resume the outer NMI.
 	 */
-	cmpl	$__KERNEL_CS, 16(%rsp)
-	jne	first_nmi
+
+	movq	$repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	1f
+	movq	$end_repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	nested_nmi_out
+1:
 
 	/*
-	 * Check the special variable on the stack to see if NMIs are
-	 * executing.
+	 * Now check "NMI executing".  If it's set, then we're nested.
+	 * This will not detect if we interrupted an outer NMI just
+	 * before IRET.
 	 */
 	cmpl	$1, -8(%rsp)
 	je	nested_nmi
 
 	/*
-	 * Now test if the previous stack was an NMI stack.
-	 * We need the double check. We check the NMI stack to satisfy the
-	 * race when the first NMI clears the variable before returning.
-	 * We check the variable because the first NMI could be in a
-	 * breakpoint routine using a breakpoint stack.
+	 * Now test if the previous stack was an NMI stack.  This covers
+	 * the case where we interrupt an outer NMI after it clears
+	 * "NMI executing" but before IRET.  We need to be careful, though:
+	 * there is one case in which RSP could point to the NMI stack
+	 * despite there being no NMI active: naughty userspace controls
+	 * RSP at the very beginning of the SYSCALL targets.  We can
+	 * pull a fast one on naughty userspace, though: we program
+	 * SYSCALL to mask DF, so userspace cannot cause DF to be set
+	 * if it controls the kernel's RSP.  We set DF before we clear
+	 * "NMI executing".
 	 */
 	lea	6*8(%rsp), %rdx
 	/* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
@@ -1286,25 +1316,20 @@ ENTRY(nmi)
 	cmpq	%rdx, 4*8(%rsp)
 	/* If it is below the NMI stack, it is a normal NMI */
 	jb	first_nmi
-	/* Ah, it is within the NMI stack, treat it as nested */
+
+	/* Ah, it is within the NMI stack. */
+
+	testb	$(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp)
+	jz	first_nmi	/* RSP was user controlled. */
+
+	/* This is a nested NMI. */
 
 nested_nmi:
 	/*
-	 * Do nothing if we interrupted the fixup in repeat_nmi.
-	 * It's about to repeat the NMI handler, so we are fine
-	 * with ignoring this one.
+	 * Modify the "iret" frame to point to repeat_nmi, forcing another
+	 * iteration of NMI handling.
 	 */
-	movq	$repeat_nmi, %rdx
-	cmpq	8(%rsp), %rdx
-	ja	1f
-	movq	$end_repeat_nmi, %rdx
-	cmpq	8(%rsp), %rdx
-	ja	nested_nmi_out
-
-1:
-	/* Set up the interrupted NMIs stack to jump to repeat_nmi */
-	leaq	-1*8(%rsp), %rdx
-	movq	%rdx, %rsp
+	subq	$8, %rsp
 	leaq	-10*8(%rsp), %rdx
 	pushq	$__KERNEL_DS
 	pushq	%rdx
@@ -1318,61 +1343,42 @@ nested_nmi:
 nested_nmi_out:
 	popq	%rdx
 
-	/* No need to check faults here */
+	/* We are returning to kernel mode, so this cannot result in a fault. */
 	INTERRUPT_RETURN
 
 first_nmi:
-	/*
-	 * Because nested NMIs will use the pushed location that we
-	 * stored in rdx, we must keep that space available.
-	 * Here's what our stack frame will look like:
-	 * +-------------------------+
-	 * | original SS             |
-	 * | original Return RSP     |
-	 * | original RFLAGS         |
-	 * | original CS             |
-	 * | original RIP            |
-	 * +-------------------------+
-	 * | temp storage for rdx    |
-	 * +-------------------------+
-	 * | NMI executing variable  |
-	 * +-------------------------+
-	 * | copied SS               |
-	 * | copied Return RSP       |
-	 * | copied RFLAGS           |
-	 * | copied CS               |
-	 * | copied RIP              |
-	 * +-------------------------+
-	 * | Saved SS                |
-	 * | Saved Return RSP        |
-	 * | Saved RFLAGS            |
-	 * | Saved CS                |
-	 * | Saved RIP               |
-	 * +-------------------------+
-	 * | pt_regs                 |
-	 * +-------------------------+
-	 *
-	 * The saved stack frame is used to fix up the copied stack frame
-	 * that a nested NMI may change to make the interrupted NMI iret jump
-	 * to the repeat_nmi. The original stack frame and the temp storage
-	 * is also used by nested NMIs and can not be trusted on exit.
-	 */
-	/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+	/* Restore rdx. */
 	movq	(%rsp), %rdx
 
-	/* Set the NMI executing variable on the stack. */
-	pushq	$1
+	/* Make room for "NMI executing". */
+	pushq	$0
 
-	/* Leave room for the "copied" frame */
+	/* Leave room for the "iret" frame */
 	subq	$(5*8), %rsp
 
-	/* Copy the stack frame to the Saved frame */
+	/* Copy the "original" frame to the "outermost" frame */
 	.rept 5
 	pushq	11*8(%rsp)
 	.endr
 
 	/* Everything up to here is safe from nested NMIs */
 
+#ifdef CONFIG_DEBUG_ENTRY
+	/*
+	 * For ease of testing, unmask NMIs right away.  Disabled by
+	 * default because IRET is very expensive.
+	 */
+	pushq	$0		/* SS */
+	pushq	%rsp		/* RSP (minus 8 because of the previous push) */
+	addq	$8, (%rsp)	/* Fix up RSP */
+	pushfq			/* RFLAGS */
+	pushq	$__KERNEL_CS	/* CS */
+	pushq	$1f		/* RIP */
+	INTERRUPT_RETURN	/* continues at repeat_nmi below */
+1:
+#endif
+
+repeat_nmi:
 	/*
 	 * If there was a nested NMI, the first NMI's iret will return
 	 * here. But NMIs are still enabled and we can take another
@@ -1381,16 +1387,20 @@ first_nmi:
 	 * it will just return, as we are about to repeat an NMI anyway.
 	 * This makes it safe to copy to the stack frame that a nested
 	 * NMI will update.
+	 *
+	 * RSP is pointing to "outermost RIP".  gsbase is unknown, but, if
+	 * we're repeating an NMI, gsbase has the same value that it had on
+	 * the first iteration.  paranoid_entry will load the kernel
+	 * gsbase if needed before we call do_nmi.  "NMI executing"
+	 * is zero.
 	 */
-repeat_nmi:
+	movq	$1, 10*8(%rsp)		/* Set "NMI executing". */
+
 	/*
-	 * Update the stack variable to say we are still in NMI (the update
-	 * is benign for the non-repeat case, where 1 was pushed just above
-	 * to this very stack slot).
+	 * Copy the "outermost" frame to the "iret" frame.  NMIs that nest
+	 * here must not modify the "iret" frame while we're writing to
+	 * it or it will end up containing garbage.
 	 */
-	movq	$1, 10*8(%rsp)
-
-	/* Make another copy, this one may be modified by nested NMIs */
 	addq	$(10*8), %rsp
 	.rept 5
 	pushq	-6*8(%rsp)
@@ -1399,9 +1409,9 @@ repeat_nmi:
 end_repeat_nmi:
 
 	/*
-	 * Everything below this point can be preempted by a nested
-	 * NMI if the first NMI took an exception and reset our iret stack
-	 * so that we repeat another NMI.
+	 * Everything below this point can be preempted by a nested NMI.
+	 * If this happens, then the inner NMI will change the "iret"
+	 * frame to point back to repeat_nmi.
 	 */
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	ALLOC_PT_GPREGS_ON_STACK
@@ -1415,28 +1425,11 @@ end_repeat_nmi:
 	 */
 	call	paranoid_entry
 
-	/*
-	 * Save off the CR2 register. If we take a page fault in the NMI then
-	 * it could corrupt the CR2 value. If the NMI preempts a page fault
-	 * handler before it was able to read the CR2 register, and then the
-	 * NMI itself takes a page fault, the page fault that was preempted
-	 * will read the information from the NMI page fault and not the
-	 * origin fault. Save it off and restore it if it changes.
-	 * Use the r12 callee-saved register.
-	 */
-	movq	%cr2, %r12
-
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	movq	%rsp, %rdi
 	movq	$-1, %rsi
 	call	do_nmi
 
-	/* Did the NMI take a page fault? Restore cr2 if it did */
-	movq	%cr2, %rcx
-	cmpq	%rcx, %r12
-	je	1f
-	movq	%r12, %cr2
-1:
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	nmi_restore
 nmi_swapgs:
@@ -1444,11 +1437,26 @@ nmi_swapgs:
 nmi_restore:
 	RESTORE_EXTRA_REGS
 	RESTORE_C_REGS
-	/* Pop the extra iret frame at once */
+
+	/* Point RSP at the "iret" frame. */
 	REMOVE_PT_GPREGS_FROM_STACK 6*8
 
-	/* Clear the NMI executing stack variable */
-	movq	$0, 5*8(%rsp)
+	/*
+	 * Clear "NMI executing".  Set DF first so that we can easily
+	 * distinguish the remaining code between here and IRET from
+	 * the SYSCALL entry and exit paths.  On a native kernel, we
+	 * could just inspect RIP, but, on paravirt kernels,
+	 * INTERRUPT_RETURN can translate into a jump into a
+	 * hypercall page.
+	 */
+	std
+	movq	$0, 5*8(%rsp)		/* clear "NMI executing" */
+
+	/*
+	 * INTERRUPT_RETURN reads the "iret" frame and exits the NMI
+	 * stack in a single instruction.  We are returning to kernel
+	 * mode, so this cannot result in a fault.
+	 */
 	INTERRUPT_RETURN
 END(nmi)
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index bb187a6a877c..a9360d40fb7f 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -22,8 +22,8 @@
 #define __AUDIT_ARCH_LE		0x40000000
 
 #ifndef CONFIG_AUDITSYSCALL
-# define sysexit_audit		ia32_ret_from_sys_call
-# define sysretl_audit		ia32_ret_from_sys_call
+# define sysexit_audit		ia32_ret_from_sys_call_irqs_off
+# define sysretl_audit		ia32_ret_from_sys_call_irqs_off
 #endif
 
 	.section .entry.text, "ax"
@@ -140,7 +140,9 @@ sysexit_from_sys_call:
 	 */
 	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
 	movl	RIP(%rsp), %ecx		/* User %eip */
-	RESTORE_RSI_RDI
+	movq    RAX(%rsp), %rax
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
 	xorl	%edx, %edx		/* Do not leak kernel information */
 	xorq	%r8, %r8
 	xorq	%r9, %r9
@@ -205,14 +207,13 @@ sysexit_from_sys_call:
 	movl	RDX(%rsp), %edx		/* arg3 */
 	movl	RSI(%rsp), %ecx		/* arg4 */
 	movl	RDI(%rsp), %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
 	.endm
 
 	.macro auditsys_exit exit
-	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	ia32_ret_from_sys_call
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	ia32_ret_from_sys_call
 	movl	%eax, %esi		/* second arg, syscall return value */
 	cmpl	$-MAX_ERRNO, %eax	/* is it an error ? */
 	jbe	1f
@@ -220,7 +221,6 @@ sysexit_from_sys_call:
 1:	setbe	%al			/* 1 if error, 0 if not */
 	movzbl	%al, %edi		/* zero-extend that into %edi */
 	call	__audit_syscall_exit
-	movq	RAX(%rsp), %rax		/* reload syscall return value */
 	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -231,11 +231,12 @@ sysexit_from_sys_call:
 	movq	%rax, R10(%rsp)
 	movq	%rax, R9(%rsp)
 	movq	%rax, R8(%rsp)
-	jmp	int_with_check
+	jmp	int_ret_from_sys_call_irqs_off
 	.endm
 
 sysenter_auditsys:
 	auditsys_entry_common
+	movl	%ebp, %r9d		/* reload 6th syscall arg */
 	jmp	sysenter_dispatch
 
 sysexit_audit:
@@ -336,7 +337,7 @@ ENTRY(entry_SYSCALL_compat)
 	 * 32-bit zero extended:
 	 */
 	ASM_STAC
-1:	movl	(%r8), %ebp
+1:	movl	(%r8), %r9d
 	_ASM_EXTABLE(1b, ia32_badarg)
 	ASM_CLAC
 	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
@@ -346,7 +347,7 @@ ENTRY(entry_SYSCALL_compat)
 cstar_do_call:
 	/* 32-bit syscall -> 64-bit C ABI argument conversion */
 	movl	%edi, %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
+	/* r9 already loaded */		/* arg6 */
 	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
 	movl	%ebx, %edi		/* arg1 */
 	movl	%edx, %edx		/* arg3 (zero extension) */
@@ -358,7 +359,6 @@ cstar_dispatch:
 	call	*ia32_sys_call_table(, %rax, 8)
 	movq	%rax, RAX(%rsp)
 1:
-	movl	RCX(%rsp), %ebp
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
@@ -366,9 +366,12 @@ cstar_dispatch:
 
 sysretl_from_sys_call:
 	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	RESTORE_RSI_RDI_RDX
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
 	movl	RIP(%rsp), %ecx
 	movl	EFLAGS(%rsp), %r11d
+	movq    RAX(%rsp), %rax
 	xorq	%r10, %r10
 	xorq	%r9, %r9
 	xorq	%r8, %r8
@@ -392,7 +395,9 @@ sysretl_from_sys_call:
 
 #ifdef CONFIG_AUDITSYSCALL
 cstar_auditsys:
+	movl	%r9d, R9(%rsp)		/* register to be clobbered by call */
 	auditsys_entry_common
+	movl	R9(%rsp), %r9d		/* reload 6th syscall arg */
 	jmp	cstar_dispatch
 
 sysretl_audit:
@@ -404,14 +409,16 @@ cstar_tracesys:
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
 	jz	cstar_auditsys
 #endif
+	xchgl	%r9d, %ebp
 	SAVE_EXTRA_REGS
 	xorl	%eax, %eax		/* Do not leak kernel information */
 	movq	%rax, R11(%rsp)
 	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
+	movq	%r9, R9(%rsp)
 	movq	%rax, R8(%rsp)
 	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
 	call	syscall_trace_enter
+	movl	R9(%rsp), %r9d
 
 	/* Reload arg registers from stack. (see sysenter_tracesys) */
 	movl	RCX(%rsp), %ecx
@@ -421,12 +428,53 @@ cstar_tracesys:
 	movl	%eax, %eax		/* zero extension */
 
 	RESTORE_EXTRA_REGS
+	xchgl	%ebp, %r9d
 	jmp	cstar_do_call
 END(entry_SYSCALL_compat)
 
 ia32_badarg:
-	ASM_CLAC
-	movq	$-EFAULT, RAX(%rsp)
+	/*
+	 * So far, we've entered kernel mode, set AC, turned on IRQs, and
+	 * saved C regs except r8-r11.  We haven't done any of the other
+	 * standard entry work, though.  We want to bail, but we shouldn't
+	 * treat this as a syscall entry since we don't even know what the
+	 * args are.  Instead, treat this as a non-syscall entry, finish
+	 * the entry work, and immediately exit after setting AX = -EFAULT.
+	 *
+	 * We're really just being polite here.  Killing the task outright
+	 * would be a reasonable action, too.  Given that the only valid
+	 * way to have gotten here is through the vDSO, and we already know
+	 * that the stack pointer is bad, the task isn't going to survive
+	 * for long no matter what we do.
+	 */
+
+	ASM_CLAC			/* undo STAC */
+	movq	$-EFAULT, RAX(%rsp)	/* return -EFAULT if possible */
+
+	/* Fill in the rest of pt_regs */
+	xorl	%eax, %eax
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	SAVE_EXTRA_REGS
+
+	/* Turn IRQs back off. */
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+
+	/* Now finish entering normal kernel mode. */
+#ifdef CONFIG_CONTEXT_TRACKING
+	call enter_from_user_mode
+#endif
+
+	/* And exit again. */
+	jmp retint_user
+
+ia32_ret_from_sys_call_irqs_off:
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
 ia32_ret_from_sys_call:
 	xorl	%eax, %eax		/* Do not leak kernel information */
 	movq	%rax, R11(%rsp)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ef8187f9d28d..477bfa6db370 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -365,3 +365,19 @@
 356	i386	memfd_create		sys_memfd_create
 357	i386	bpf			sys_bpf
 358	i386	execveat		sys_execveat			stub32_execveat
+359	i386	socket			sys_socket
+360	i386	socketpair		sys_socketpair
+361	i386	bind			sys_bind
+362	i386	connect			sys_connect
+363	i386	listen			sys_listen
+364	i386	accept4			sys_accept4
+365	i386	getsockopt		sys_getsockopt			compat_sys_getsockopt
+366	i386	setsockopt		sys_setsockopt			compat_sys_setsockopt
+367	i386	getsockname		sys_getsockname
+368	i386	getpeername		sys_getpeername
+369	i386	sendto			sys_sendto
+370	i386	sendmsg			sys_sendmsg			compat_sys_sendmsg
+371	i386	recvfrom		sys_recvfrom			compat_sys_recvfrom
+372	i386	recvmsg			sys_recvmsg			compat_sys_recvmsg
+373	i386	shutdown		sys_shutdown
+374	i386	userfaultfd		sys_userfaultfd
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5f1b19..81c490634db9 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -329,6 +329,7 @@
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
 322	64	execveat		stub_execveat
+323	common	userfaultfd		sys_userfaultfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index e97032069f88..a3d0767a6b29 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -8,7 +8,7 @@ KASAN_SANITIZE := n
 VDSO64-$(CONFIG_X86_64)		:= y
 VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
 VDSO32-$(CONFIG_X86_32)		:= y
-VDSO32-$(CONFIG_COMPAT)		:= y
+VDSO32-$(CONFIG_IA32_EMULATION)	:= y
 
 # files to link into the vdso
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
@@ -20,7 +20,7 @@ obj-y				+= vma.o
 vdso_img-$(VDSO64-y)		+= 64
 vdso_img-$(VDSOX32-y)		+= x32
 vdso_img-$(VDSO32-y)		+= 32-int80
-vdso_img-$(CONFIG_COMPAT)	+= 32-syscall
+vdso_img-$(CONFIG_IA32_EMULATION)	+= 32-syscall
 vdso_img-$(VDSO32-y)		+= 32-sysenter
 
 obj-$(VDSO32-y)			+= vdso32-setup.o
@@ -126,7 +126,7 @@ $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
 # Build multiple 32-bit vDSO images to choose from at boot time.
 #
 vdso32.so-$(VDSO32-y)		+= int80
-vdso32.so-$(CONFIG_COMPAT)	+= syscall
+vdso32.so-$(CONFIG_IA32_EMULATION)	+= syscall
 vdso32.so-$(VDSO32-y)		+= sysenter
 
 vdso32-images			= $(vdso32.so-y:%=vdso32-%.so)
@@ -175,7 +175,7 @@ quiet_cmd_vdso = VDSO    $@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
+VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \
 	$(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
 GCOV_PROFILE := n
 
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9793322751e0..ca94fa649251 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -175,20 +175,8 @@ static notrace cycle_t vread_pvclock(int *mode)
 
 notrace static cycle_t vread_tsc(void)
 {
-	cycle_t ret;
-	u64 last;
-
-	/*
-	 * Empirically, a fence (of type that depends on the CPU)
-	 * before rdtsc is enough to ensure that rdtsc is ordered
-	 * with respect to loads.  The various CPU manuals are unclear
-	 * as to whether rdtsc can be reordered with later loads,
-	 * but no one has ever seen it happen.
-	 */
-	rdtsc_barrier();
-	ret = (cycle_t)__native_read_tsc();
-
-	last = gtod->cycle_last;
+	cycle_t ret = (cycle_t)rdtsc_ordered();
+	u64 last = gtod->cycle_last;
 
 	if (likely(ret >= last))
 		return ret;
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 1c9f750c3859..434543145d78 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -177,7 +177,7 @@ up_fail:
 	return ret;
 }
 
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static int load_vdso32(void)
 {
 	int ret;
@@ -219,8 +219,11 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 		return map_vdso(&vdso_image_x32, true);
 	}
 #endif
-
+#ifdef CONFIG_IA32_EMULATION
 	return load_vdso32();
+#else
+	return 0;
+#endif
 }
 #endif
 #else
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 2dcc6ff6fdcc..26a46f44e298 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -290,7 +290,7 @@ static struct vm_area_struct gate_vma = {
 
 struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
-#ifdef CONFIG_IA32_EMULATION
+#ifdef CONFIG_COMPAT
 	if (!mm || mm->context.ia32_compat)
 		return NULL;
 #endif
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index ae3a29ae875b..a0a19b7ba22d 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -34,99 +34,6 @@
 #include <asm/sys_ia32.h>
 #include <asm/smap.h>
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	int err = 0;
-	bool ia32 = test_thread_flag(TIF_IA32);
-
-	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	put_user_try {
-		/* If you change siginfo_t structure, please make sure that
-		   this code is fixed accordingly.
-		   It should never copy any pad contained in the structure
-		   to avoid security leaks, but must copy the generic
-		   3 ints plus the relevant union member.  */
-		put_user_ex(from->si_signo, &to->si_signo);
-		put_user_ex(from->si_errno, &to->si_errno);
-		put_user_ex((short)from->si_code, &to->si_code);
-
-		if (from->si_code < 0) {
-			put_user_ex(from->si_pid, &to->si_pid);
-			put_user_ex(from->si_uid, &to->si_uid);
-			put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
-		} else {
-			/*
-			 * First 32bits of unions are always present:
-			 * si_pid === si_band === si_tid === si_addr(LS half)
-			 */
-			put_user_ex(from->_sifields._pad[0],
-					  &to->_sifields._pad[0]);
-			switch (from->si_code >> 16) {
-			case __SI_FAULT >> 16:
-				break;
-			case __SI_SYS >> 16:
-				put_user_ex(from->si_syscall, &to->si_syscall);
-				put_user_ex(from->si_arch, &to->si_arch);
-				break;
-			case __SI_CHLD >> 16:
-				if (ia32) {
-					put_user_ex(from->si_utime, &to->si_utime);
-					put_user_ex(from->si_stime, &to->si_stime);
-				} else {
-					put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
-					put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
-				}
-				put_user_ex(from->si_status, &to->si_status);
-				/* FALL THROUGH */
-			default:
-			case __SI_KILL >> 16:
-				put_user_ex(from->si_uid, &to->si_uid);
-				break;
-			case __SI_POLL >> 16:
-				put_user_ex(from->si_fd, &to->si_fd);
-				break;
-			case __SI_TIMER >> 16:
-				put_user_ex(from->si_overrun, &to->si_overrun);
-				put_user_ex(ptr_to_compat(from->si_ptr),
-					    &to->si_ptr);
-				break;
-				 /* This is not generated by the kernel as of now.  */
-			case __SI_RT >> 16:
-			case __SI_MESGQ >> 16:
-				put_user_ex(from->si_uid, &to->si_uid);
-				put_user_ex(from->si_int, &to->si_int);
-				break;
-			}
-		}
-	} put_user_catch(err);
-
-	return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
-	int err = 0;
-	u32 ptr32;
-
-	if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	get_user_try {
-		get_user_ex(to->si_signo, &from->si_signo);
-		get_user_ex(to->si_errno, &from->si_errno);
-		get_user_ex(to->si_code, &from->si_code);
-
-		get_user_ex(to->si_pid, &from->si_pid);
-		get_user_ex(to->si_uid, &from->si_uid);
-		get_user_ex(ptr32, &from->si_ptr);
-		to->si_ptr = compat_ptr(ptr32);
-	} get_user_catch(err);
-
-	return err;
-}
-
 /*
  * Do a signal return; undo the signal stack.
  */
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4dd1f2d770af..aeac434c9feb 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -9,3 +9,4 @@ generic-y += cputime.h
 generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index c8393634ca0c..ebf6d5e5668c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -313,7 +313,6 @@ struct apic {
 	/* wakeup_secondary_cpu */
 	int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
 
-	bool wait_for_init_deassert;
 	void (*inquire_remote_apic)(int apicid);
 
 	/* apic ops */
@@ -378,7 +377,6 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[];
  * APIC functionality to boot other CPUs - only used on SMP:
  */
 #ifdef CONFIG_SMP
-extern atomic_t init_deasserted;
 extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
 #endif
 
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 9686c3d9ff73..259a7c1ef709 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -21,7 +21,7 @@
  * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
  * compiler switches.
  */
-static inline unsigned int __arch_hweight32(unsigned int w)
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 	unsigned int res = 0;
 
@@ -42,20 +42,23 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 	return __arch_hweight32(w & 0xff);
 }
 
+#ifdef CONFIG_X86_32
 static inline unsigned long __arch_hweight64(__u64 w)
 {
-	unsigned long res = 0;
-
-#ifdef CONFIG_X86_32
 	return  __arch_hweight32((u32)w) +
 		__arch_hweight32((u32)(w >> 32));
+}
 #else
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+	unsigned long res = 0;
+
 	asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
 		     : "="REG_OUT (res)
 		     : REG_IN (w));
-#endif /* CONFIG_X86_32 */
 
 	return res;
 }
+#endif /* CONFIG_X86_32 */
 
 #endif
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index e9168955c42f..fb52aa644aab 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -182,6 +182,21 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	asm volatile(LOCK_PREFIX #op"l %1,%0"				\
+			: "+m" (v->counter)				\
+			: "ir" (i)					\
+			: "memory");					\
+}
+
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
 /**
  * __atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
@@ -219,16 +234,6 @@ static __always_inline short int atomic_inc_short(short int *v)
 	return *v;
 }
 
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "andl %0,%1"			\
-		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "orl %0,%1"			\
-		     : : "r" ((unsigned)(mask)), "m" (*(addr))	\
-		     : "memory")
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index b154de75c90c..a11c30b77fb5 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -313,4 +313,18 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
+#define ATOMIC64_OP(op, c_op)						\
+static inline void atomic64_##op(long long i, atomic64_t *v)		\
+{									\
+	long long old, c = 0;						\
+	while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c)		\
+		c = old;						\
+}
+
+ATOMIC64_OP(and, &)
+ATOMIC64_OP(or, |)
+ATOMIC64_OP(xor, ^)
+
+#undef ATOMIC64_OP
+
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index b965f9e03f2a..50e33eff58de 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -220,4 +220,19 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
+#define ATOMIC64_OP(op)							\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	asm volatile(LOCK_PREFIX #op"q %1,%0"				\
+			: "+m" (v->counter)				\
+			: "er" (i)					\
+			: "memory");					\
+}
+
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
+
+#undef ATOMIC64_OP
+
 #endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index e51a8f803f55..0681d2532527 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -57,12 +57,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
@@ -74,12 +74,12 @@ do {									\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	___p1;								\
@@ -91,15 +91,4 @@ do {									\
 #define smp_mb__before_atomic()	barrier()
 #define smp_mb__after_atomic()	barrier()
 
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- */
-static __always_inline void rdtsc_barrier(void)
-{
-	alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
-			  "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
 #endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h
deleted file mode 100644
index 1fe49704b146..000000000000
--- a/arch/x86/include/asm/context_tracking.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _ASM_X86_CONTEXT_TRACKING_H
-#define _ASM_X86_CONTEXT_TRACKING_H
-
-#ifdef CONFIG_CONTEXT_TRACKING
-# define SCHEDULE_USER call schedule_user
-#else
-# define SCHEDULE_USER call schedule
-#endif
-
-#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3d6606fb97d0..477fc28050e4 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -119,6 +119,7 @@
 #define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
 #define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
 #define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
 #define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
 #define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
 #define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
@@ -176,6 +177,7 @@
 #define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
 #define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
 #define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h
index 9b3b4f2754c7..36a760bda462 100644
--- a/arch/x86/include/asm/delay.h
+++ b/arch/x86/include/asm/delay.h
@@ -4,5 +4,6 @@
 #include <asm-generic/delay.h>
 
 void use_tsc_delay(void);
+void use_mwaitx_delay(void);
 
 #endif /* _ASM_X86_DELAY_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89fd2647..4e10d73cf018 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
 	set_ldt(NULL, 0);
 }
 
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
 	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f161c189c27b..141c561f4664 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -78,7 +78,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
 #ifdef CONFIG_X86_64
 extern unsigned int vdso64_enabled;
 #endif
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 extern unsigned int vdso32_enabled;
 #endif
 
@@ -187,8 +187,8 @@ static inline void elf_common_init(struct thread_struct *t,
 #define	COMPAT_ELF_PLAT_INIT(regs, load_addr)		\
 	elf_common_init(&current->thread, regs, __USER_DS)
 
-void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
-#define compat_start_thread start_thread_ia32
+void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp);
+#define compat_start_thread compat_start_thread
 
 void set_personality_ia32(bool);
 #define COMPAT_SET_PERSONALITY(ex)			\
@@ -344,14 +344,9 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
  */
 static inline int mmap_is_ia32(void)
 {
-#ifdef CONFIG_X86_32
-	return 1;
-#endif
-#ifdef CONFIG_IA32_EMULATION
-	if (test_thread_flag(TIF_ADDR32))
-		return 1;
-#endif
-	return 0;
+	return config_enabled(CONFIG_X86_32) ||
+	       (config_enabled(CONFIG_COMPAT) &&
+		test_thread_flag(TIF_ADDR32));
 }
 
 /* Do not change the values. See get_align_mask() */
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 99efebb2f69d..ca3ce9ab9385 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -9,7 +9,7 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
 DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
-extern void init_espfix_ap(void);
+extern void init_espfix_ap(int cpu);
 
 #endif /* CONFIG_X86_64 */
 
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 0637826292de..c49c5173158e 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -189,6 +189,7 @@ union fpregs_state {
 	struct fxregs_state		fxsave;
 	struct swregs_state		soft;
 	struct xregs_state		xsave;
+	u8 __padding[PAGE_SIZE];
 };
 
 /*
@@ -198,40 +199,6 @@ union fpregs_state {
  */
 struct fpu {
 	/*
-	 * @state:
-	 *
-	 * In-memory copy of all FPU registers that we save/restore
-	 * over context switches. If the task is using the FPU then
-	 * the registers in the FPU are more recent than this state
-	 * copy. If the task context-switches away then they get
-	 * saved here and represent the FPU state.
-	 *
-	 * After context switches there may be a (short) time period
-	 * during which the in-FPU hardware registers are unchanged
-	 * and still perfectly match this state, if the tasks
-	 * scheduled afterwards are not using the FPU.
-	 *
-	 * This is the 'lazy restore' window of optimization, which
-	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
-	 *
-	 * We detect whether a subsequent task uses the FPU via setting
-	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
-	 *
-	 * During this window, if the task gets scheduled again, we
-	 * might be able to skip having to do a restore from this
-	 * memory buffer to the hardware registers - at the cost of
-	 * incurring the overhead of #NM fault traps.
-	 *
-	 * Note that on modern CPUs that support the XSAVEOPT (or other
-	 * optimized XSAVE instructions), we don't use #NM traps anymore,
-	 * as the hardware can track whether FPU registers need saving
-	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
-	 * logic, which unconditionally saves/restores all FPU state
-	 * across context switches. (if FPU state exists.)
-	 */
-	union fpregs_state		state;
-
-	/*
 	 * @last_cpu:
 	 *
 	 * Records the last CPU on which this context was loaded into
@@ -288,6 +255,43 @@ struct fpu {
 	 * deal with bursty apps that only use the FPU for a short time:
 	 */
 	unsigned char			counter;
+	/*
+	 * @state:
+	 *
+	 * In-memory copy of all FPU registers that we save/restore
+	 * over context switches. If the task is using the FPU then
+	 * the registers in the FPU are more recent than this state
+	 * copy. If the task context-switches away then they get
+	 * saved here and represent the FPU state.
+	 *
+	 * After context switches there may be a (short) time period
+	 * during which the in-FPU hardware registers are unchanged
+	 * and still perfectly match this state, if the tasks
+	 * scheduled afterwards are not using the FPU.
+	 *
+	 * This is the 'lazy restore' window of optimization, which
+	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+	 *
+	 * We detect whether a subsequent task uses the FPU via setting
+	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+	 *
+	 * During this window, if the task gets scheduled again, we
+	 * might be able to skip having to do a restore from this
+	 * memory buffer to the hardware registers - at the cost of
+	 * incurring the overhead of #NM fault traps.
+	 *
+	 * Note that on modern CPUs that support the XSAVEOPT (or other
+	 * optimized XSAVE instructions), we don't use #NM traps anymore,
+	 * as the hardware can track whether FPU registers need saving
+	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+	 * logic, which unconditionally saves/restores all FPU state
+	 * across context switches. (if FPU state exists.)
+	 */
+	union fpregs_state		state;
+	/*
+	 * WARNING: 'state' is dynamically-sized.  Do not put
+	 * anything after it here.
+	 */
 };
 
 #endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index f45acad3c4b6..24938852db30 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -3,9 +3,9 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CC_USING_FENTRY
-# define MCOUNT_ADDR		((long)(__fentry__))
+# define MCOUNT_ADDR		((unsigned long)(__fentry__))
 #else
-# define MCOUNT_ADDR		((long)(mcount))
+# define MCOUNT_ADDR		((unsigned long)(mcount))
 #endif
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
 
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 6615032e19c8..1e3408e88604 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -182,10 +182,10 @@ extern char irq_entries_start[];
 #define trace_irq_entries_start irq_entries_start
 #endif
 
-#define VECTOR_UNDEFINED	(-1)
-#define VECTOR_RETRIGGERED	(-2)
+#define VECTOR_UNUSED		NULL
+#define VECTOR_RETRIGGERED	((void *)~0UL)
 
-typedef int vector_irq_t[NR_VECTORS];
+typedef struct irq_desc* vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
 
 #endif /* !ASSEMBLY_ */
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index d0e8e0141041..28019765442e 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -22,15 +22,6 @@ struct ucontext_ia32 {
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
 
-struct ucontext_x32 {
-	unsigned int	  uc_flags;
-	unsigned int 	  uc_link;
-	compat_stack_t	  uc_stack;
-	unsigned int	  uc__pad0;     /* needed for alignment */
-	struct sigcontext uc_mcontext;  /* the 64-bit sigcontext type */
-	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
 /* This matches struct stat64 in glibc2.2, hence the absolutely
  * insane amounts of padding around dev_t's.
  */
diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h
index 200ec2e7821d..cd0310e186f4 100644
--- a/arch/x86/include/asm/intel_pmc_ipc.h
+++ b/arch/x86/include/asm/intel_pmc_ipc.h
@@ -25,36 +25,9 @@
 
 #if IS_ENABLED(CONFIG_INTEL_PMC_IPC)
 
-/*
- * intel_pmc_ipc_simple_command
- * @cmd: command
- * @sub: sub type
- */
 int intel_pmc_ipc_simple_command(int cmd, int sub);
-
-/*
- * intel_pmc_ipc_raw_cmd
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- * @sptr: data writing to SPTR register
- * @dptr: data writing to DPTR register
- */
 int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen, u32 dptr, u32 sptr);
-
-/*
- * intel_pmc_ipc_command
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- */
 int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen);
 
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index cc9c61bc1abe..7cfc085b6879 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -180,6 +180,8 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
+#define ioremap_uc ioremap_uc
+
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
 				unsigned long prot_val);
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 57995f0596a6..b72ad0faa6c5 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -52,20 +52,20 @@
 
 /* Quark available units */
 #define QRK_MBI_UNIT_HBA	0x00
-#define QRK_MBI_UNIT_HB	0x03
+#define QRK_MBI_UNIT_HB		0x03
 #define QRK_MBI_UNIT_RMU	0x04
-#define QRK_MBI_UNIT_MM	0x05
+#define QRK_MBI_UNIT_MM		0x05
 #define QRK_MBI_UNIT_MMESRAM	0x05
 #define QRK_MBI_UNIT_SOC	0x31
 
 /* Quark read/write opcodes */
 #define QRK_MBI_HBA_READ	0x10
 #define QRK_MBI_HBA_WRITE	0x11
-#define QRK_MBI_HB_READ	0x10
+#define QRK_MBI_HB_READ		0x10
 #define QRK_MBI_HB_WRITE	0x11
 #define QRK_MBI_RMU_READ	0x10
 #define QRK_MBI_RMU_WRITE	0x11
-#define QRK_MBI_MM_READ	0x10
+#define QRK_MBI_MM_READ		0x10
 #define QRK_MBI_MM_WRITE	0x11
 #define QRK_MBI_MMESRAM_READ	0x12
 #define QRK_MBI_MMESRAM_WRITE	0x13
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 8008d06581c7..881b4768644a 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -36,7 +36,9 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
 
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
-extern bool handle_irq(unsigned irq, struct pt_regs *regs);
+
+struct irq_desc;
+extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
 
 extern __visible unsigned int do_IRQ(struct pt_regs *regs);
 
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 4c2d2eb2060a..6ca9fd6234e1 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -117,16 +117,6 @@
 
 #define FPU_IRQ				  13
 
-#define	FIRST_VM86_IRQ			   3
-#define LAST_VM86_IRQ			  15
-
-#ifndef __ASSEMBLY__
-static inline int invalid_vm86_irq(int irq)
-{
-	return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
-}
-#endif
-
 /*
  * Size the maximum number of interrupts.
  *
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index a4c1cf7e93f8..5daeca3d0f9e 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -16,15 +16,32 @@
 # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
 #endif
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:"
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
-		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
 		".popsection \n\t"
-		: :  "i" (key) : : l_yes);
+		: :  "i" (key), "i" (branch) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:"
+		".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"
+		"2:\n\t"
+		".pushsection __jump_table,  \"aw\" \n\t"
+		_ASM_ALIGN "\n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
+		".popsection \n\t"
+		: :  "i" (key), "i" (branch) : : l_yes);
+
 	return false;
 l_yes:
 	return true;
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 8b22422fbad8..1410b567ecde 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -1,6 +1,9 @@
 #ifndef _ASM_X86_KASAN_H
 #define _ASM_X86_KASAN_H
 
+#include <linux/const.h>
+#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+
 /*
  * Compiler uses shadow offset assuming that addresses start
  * from 0. Kernel addresses don't start from 0, so shadow
@@ -14,15 +17,11 @@
 
 #ifndef __ASSEMBLY__
 
-extern pte_t kasan_zero_pte[];
-extern pte_t kasan_zero_pmd[];
-extern pte_t kasan_zero_pud[];
-
 #ifdef CONFIG_KASAN
-void __init kasan_map_early_shadow(pgd_t *pgd);
+void __init kasan_early_init(void);
 void __init kasan_init(void);
 #else
-static inline void kasan_map_early_shadow(pgd_t *pgd) { }
+static inline void kasan_early_init(void) { }
 static inline void kasan_init(void) { }
 #endif
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2a7f5d782c33..c12e845f59e6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -252,6 +252,11 @@ struct kvm_pio_request {
 	int size;
 };
 
+struct rsvd_bits_validate {
+	u64 rsvd_bits_mask[2][4];
+	u64 bad_mt_xwr;
+};
+
 /*
  * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
  * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
@@ -289,8 +294,15 @@ struct kvm_mmu {
 
 	u64 *pae_root;
 	u64 *lm_root;
-	u64 rsvd_bits_mask[2][4];
-	u64 bad_mt_xwr;
+
+	/*
+	 * check zero bits on shadow page table entries, these
+	 * bits include not only hardware reserved bits but also
+	 * the bits spte never used.
+	 */
+	struct rsvd_bits_validate shadow_zero_check;
+
+	struct rsvd_bits_validate guest_rsvd_check;
 
 	/*
 	 * Bitmap: bit set = last pte in walk
@@ -358,6 +370,11 @@ struct kvm_mtrr {
 	struct list_head head;
 };
 
+/* Hyper-V per vcpu emulation context */
+struct kvm_vcpu_hv {
+	u64 hv_vapic;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -514,8 +531,7 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
-	/* fields used by HYPER-V emulation */
-	u64 hv_vapic;
+	struct kvm_vcpu_hv hyperv;
 
 	cpumask_var_t wbinvd_dirty_mask;
 
@@ -586,6 +602,17 @@ struct kvm_apic_map {
 	struct kvm_lapic *logical_map[16][16];
 };
 
+/* Hyper-V emulation context */
+struct kvm_hv {
+	u64 hv_guest_os_id;
+	u64 hv_hypercall;
+	u64 hv_tsc_page;
+
+	/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
+	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
+	u64 hv_crash_ctl;
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -604,6 +631,8 @@ struct kvm_arch {
 	bool iommu_noncoherent;
 #define __KVM_HAVE_ARCH_NONCOHERENT_DMA
 	atomic_t noncoherent_dma_count;
+#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
+	atomic_t assigned_device_count;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
@@ -643,16 +672,14 @@ struct kvm_arch {
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
-	/* fields used by HYPER-V emulation */
-	u64 hv_guest_os_id;
-	u64 hv_hypercall;
-	u64 hv_tsc_page;
+	struct kvm_hv hyperv;
 
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
 
 	bool boot_vcpu_runs_old_kvmclock;
+	u32 bsp_vcpu_id;
 
 	u64 disabled_quirks;
 };
@@ -1201,5 +1228,7 @@ int __x86_set_memory_region(struct kvm *kvm,
 			    const struct kvm_userspace_memory_region *mem);
 int x86_set_memory_region(struct kvm *kvm,
 			  const struct kvm_userspace_memory_region *mem);
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h
index 031f6266f425..0d9b14f60d2c 100644
--- a/arch/x86/include/asm/math_emu.h
+++ b/arch/x86/include/asm/math_emu.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_MATH_EMU_H
 
 #include <asm/ptrace.h>
-#include <asm/vm86.h>
 
 /* This structure matches the layout of the data saved to the stack
    following a device-not-present interrupt, part of it saved
@@ -10,9 +9,6 @@
    */
 struct math_emu_info {
 	long ___orig_eip;
-	union {
-		struct pt_regs *regs;
-		struct kernel_vm86_regs *vm86;
-	};
+	struct pt_regs *regs;
 };
 #endif /* _ASM_X86_MATH_EMU_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 982dfc3679ad..2dbc0bf2b9f3 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -151,10 +151,12 @@ extern int mce_p5_enabled;
 #ifdef CONFIG_X86_MCE
 int mcheck_init(void);
 void mcheck_cpu_init(struct cpuinfo_x86 *c);
+void mcheck_cpu_clear(struct cpuinfo_x86 *c);
 void mcheck_vendor_init_severity(void);
 #else
 static inline int mcheck_init(void) { return 0; }
 static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
+static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
 static inline void mcheck_vendor_init_severity(void) {}
 #endif
 
@@ -181,20 +183,18 @@ DECLARE_PER_CPU(struct device *, mce_device);
 
 #ifdef CONFIG_X86_MCE_INTEL
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
+void mce_intel_feature_clear(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);
 void cmci_rediscover(void);
 void cmci_recheck(void);
-void lmce_clear(void);
-void lmce_enable(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
+static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { }
 static inline void cmci_clear(void) {}
 static inline void cmci_reenable(void) {}
 static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
-static inline void lmce_clear(void) {}
-static inline void lmce_enable(void) {}
 #endif
 
 #ifdef CONFIG_X86_MCE_AMD
diff --git a/arch/x86/include/asm/mm-arch-hooks.h b/arch/x86/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 4e881a342236..000000000000
--- a/arch/x86/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_X86_MM_ARCH_HOOKS_H
-#define _ASM_X86_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_X86_MM_ARCH_HOOKS_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620a73b4..55234d5e7160 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,9 @@
  * we put the segment information here.
  */
 typedef struct {
-	void *ldt;
-	int size;
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	struct ldt_struct *ldt;
+#endif
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5e8daee7c5c9..379cd3658799 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -23,7 +23,7 @@ extern struct static_key rdpmc_always_available;
 
 static inline void load_mm_cr4(struct mm_struct *mm)
 {
-	if (static_key_true(&rdpmc_always_available) ||
+	if (static_key_false(&rdpmc_always_available) ||
 	    atomic_read(&mm->context.perf_rdpmc_allowed))
 		cr4_set_bits(X86_CR4_PCE);
 	else
@@ -33,12 +33,68 @@ static inline void load_mm_cr4(struct mm_struct *mm)
 static inline void load_mm_cr4(struct mm_struct *mm) {}
 #endif
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+/*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+	/*
+	 * Xen requires page-aligned LDTs with special permissions.  This is
+	 * needed to prevent us from installing evil descriptors such as
+	 * call gates.  On native, we could merge the ldt_struct and LDT
+	 * allocations, but it's not worth trying to optimize.
+	 */
+	struct desc_struct *entries;
+	int size;
+};
+
 /*
  * Used for LDT copy/destruction.
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
+#else	/* CONFIG_MODIFY_LDT_SYSCALL */
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	return 0;
+}
+static inline void destroy_context(struct mm_struct *mm) {}
+#endif
 
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	struct ldt_struct *ldt;
+
+	/* lockless_dereference synchronizes with smp_store_release */
+	ldt = lockless_dereference(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt))
+		set_ldt(ldt->entries, ldt->size);
+	else
+		clear_LDT();
+#else
+	clear_LDT();
+#endif
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
@@ -70,6 +126,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Load per-mm CR4 state */
 		load_mm_cr4(next);
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 		/*
 		 * Load the LDT, if the LDT is different.
 		 *
@@ -78,12 +135,13 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		 * was called and then modify_ldt changed
 		 * prev->context.ldt but suppressed an IPI to this CPU.
 		 * In this case, prev->context.ldt != NULL, because we
-		 * never free an LDT while the mm still exists.  That
-		 * means that next->context.ldt != prev->context.ldt,
-		 * because mms never share an LDT.
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
 		 */
 		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
+#endif
 	}
 #ifdef CONFIG_SMP
 	  else {
@@ -106,7 +164,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			load_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 			load_mm_cr4(next);
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 		}
 	}
 #endif
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index c163215abb9a..aaf59b7da98a 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
 
 struct ms_hyperv_info {
 	u32 features;
+	u32 misc_features;
 	u32 hints;
 };
 
@@ -20,4 +21,8 @@ void hyperv_vector_handler(struct pt_regs *regs);
 void hv_setup_vmbus_irq(void (*handler)(void));
 void hv_remove_vmbus_irq(void);
 
+void hv_setup_kexec_handler(void (*handler)(void));
+void hv_remove_kexec_handler(void);
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
+void hv_remove_crash_handler(void);
 #endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9ebc3d009373..c1c0a1c14344 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -73,6 +73,12 @@
 #define MSR_LBR_CORE_FROM		0x00000040
 #define MSR_LBR_CORE_TO			0x00000060
 
+#define MSR_LBR_INFO_0			0x00000dc0 /* ... 0xddf for _31 */
+#define LBR_INFO_MISPRED		BIT_ULL(63)
+#define LBR_INFO_IN_TX			BIT_ULL(62)
+#define LBR_INFO_ABORT			BIT_ULL(61)
+#define LBR_INFO_CYCLES			0xffff
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
@@ -80,13 +86,21 @@
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)
+#define RTIT_CTL_CYCLEACC		BIT(1)
 #define RTIT_CTL_OS			BIT(2)
 #define RTIT_CTL_USR			BIT(3)
 #define RTIT_CTL_CR3EN			BIT(7)
 #define RTIT_CTL_TOPA			BIT(8)
+#define RTIT_CTL_MTC_EN			BIT(9)
 #define RTIT_CTL_TSC_EN			BIT(10)
 #define RTIT_CTL_DISRETC		BIT(11)
 #define RTIT_CTL_BRANCH_EN		BIT(13)
+#define RTIT_CTL_MTC_RANGE_OFFSET	14
+#define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
+#define RTIT_CTL_CYC_THRESH_OFFSET	19
+#define RTIT_CTL_CYC_THRESH		(0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
+#define RTIT_CTL_PSB_FREQ_OFFSET	24
+#define RTIT_CTL_PSB_FREQ      		(0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
 #define MSR_IA32_RTIT_STATUS		0x00000571
 #define RTIT_STATUS_CONTEXTEN		BIT(1)
 #define RTIT_STATUS_TRIGGEREN		BIT(2)
@@ -170,6 +184,12 @@
 #define MSR_PP1_ENERGY_STATUS		0x00000641
 #define MSR_PP1_POLICY			0x00000642
 
+#define MSR_CONFIG_TDP_NOMINAL		0x00000648
+#define MSR_CONFIG_TDP_LEVEL_1		0x00000649
+#define MSR_CONFIG_TDP_LEVEL_2		0x0000064A
+#define MSR_CONFIG_TDP_CONTROL		0x0000064B
+#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
+
 #define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
 #define MSR_PKG_ANY_CORE_C0_RES		0x00000659
 #define MSR_PKG_ANY_GFXE_C0_RES		0x0000065A
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index e6a707eb5081..77d8b284e4a7 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -47,14 +47,13 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
  * it means rax *or* rdx.
  */
 #ifdef CONFIG_X86_64
-#define DECLARE_ARGS(val, low, high)	unsigned low, high
-#define EAX_EDX_VAL(val, low, high)	((low) | ((u64)(high) << 32))
-#define EAX_EDX_ARGS(val, low, high)	"a" (low), "d" (high)
+/* Using 64-bit values saves one instruction clearing the high half of low */
+#define DECLARE_ARGS(val, low, high)	unsigned long low, high
+#define EAX_EDX_VAL(val, low, high)	((low) | (high) << 32)
 #define EAX_EDX_RET(val, low, high)	"=a" (low), "=d" (high)
 #else
 #define DECLARE_ARGS(val, low, high)	unsigned long long val
 #define EAX_EDX_VAL(val, low, high)	(val)
-#define EAX_EDX_ARGS(val, low, high)	"A" (val)
 #define EAX_EDX_RET(val, low, high)	"=A" (val)
 #endif
 
@@ -106,12 +105,19 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 	return err;
 }
 
-extern unsigned long long native_read_tsc(void);
-
 extern int rdmsr_safe_regs(u32 regs[8]);
 extern int wrmsr_safe_regs(u32 regs[8]);
 
-static __always_inline unsigned long long __native_read_tsc(void)
+/**
+ * rdtsc() - returns the current TSC without ordering constraints
+ *
+ * rdtsc() returns the result of RDTSC as a 64-bit integer.  The
+ * only ordering constraint it supplies is the ordering implied by
+ * "asm volatile": it will put the RDTSC in the place you expect.  The
+ * CPU can and will speculatively execute that RDTSC, though, so the
+ * results can be non-monotonic if compared on different CPUs.
+ */
+static __always_inline unsigned long long rdtsc(void)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -120,6 +126,35 @@ static __always_inline unsigned long long __native_read_tsc(void)
 	return EAX_EDX_VAL(val, low, high);
 }
 
+/**
+ * rdtsc_ordered() - read the current TSC in program order
+ *
+ * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
+ * It is ordered like a load to a global in-memory counter.  It should
+ * be impossible to observe non-monotonic rdtsc_unordered() behavior
+ * across multiple CPUs as long as the TSC is synced.
+ */
+static __always_inline unsigned long long rdtsc_ordered(void)
+{
+	/*
+	 * The RDTSC instruction is not ordered relative to memory
+	 * access.  The Intel SDM and the AMD APM are both vague on this
+	 * point, but empirically an RDTSC instruction can be
+	 * speculatively executed before prior loads.  An RDTSC
+	 * immediately after an appropriate barrier appears to be
+	 * ordered as a normal load, that is, it provides the same
+	 * ordering guarantees as reading from a global memory location
+	 * that some other imaginary CPU is updating continuously with a
+	 * time stamp.
+	 */
+	alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
+			  "lfence", X86_FEATURE_LFENCE_RDTSC);
+	return rdtsc();
+}
+
+/* Deprecated, keep it for a cycle for easier merging: */
+#define rdtscll(now)	do { (now) = rdtsc_ordered(); } while (0)
+
 static inline unsigned long long native_read_pmc(int counter)
 {
 	DECLARE_ARGS(val, low, high);
@@ -153,8 +188,10 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
 #define rdmsrl(msr, val)			\
 	((val) = native_read_msr((msr)))
 
-#define wrmsrl(msr, val)						\
-	native_write_msr((msr), (u32)((u64)(val)), (u32)((u64)(val) >> 32))
+static inline void wrmsrl(unsigned msr, u64 val)
+{
+	native_write_msr(msr, (u32)val, (u32)(val >> 32));
+}
 
 /* wrmsr with exception handling */
 static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
@@ -180,12 +217,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	return err;
 }
 
-#define rdtscl(low)						\
-	((low) = (u32)__native_read_tsc())
-
-#define rdtscll(val)						\
-	((val) = __native_read_tsc())
-
 #define rdpmc(counter, low, high)			\
 do {							\
 	u64 _l = native_read_pmc((counter));		\
@@ -195,15 +226,6 @@ do {							\
 
 #define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
 
-#define rdtscp(low, high, aux)					\
-do {                                                            \
-	unsigned long long _val = native_read_tscp(&(aux));     \
-	(low) = (u32)_val;                                      \
-	(high) = (u32)(_val >> 32);                             \
-} while (0)
-
-#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux))
-
 #endif	/* !CONFIG_PARAVIRT */
 
 /*
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 653dfa7662e1..c70689b5e5aa 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -14,6 +14,9 @@
 #define CPUID5_ECX_INTERRUPT_BREAK	0x2
 
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
+#define MWAITX_ECX_TIMER_ENABLE		BIT(1)
+#define MWAITX_MAX_LOOPS		((u32)-1)
+#define MWAITX_DISABLE_CSTATES		0xf
 
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
@@ -23,6 +26,14 @@ static inline void __monitor(const void *eax, unsigned long ecx,
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
+static inline void __monitorx(const void *eax, unsigned long ecx,
+			      unsigned long edx)
+{
+	/* "monitorx %eax, %ecx, %edx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xfa;"
+		     :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
 static inline void __mwait(unsigned long eax, unsigned long ecx)
 {
 	/* "mwait %eax, %ecx;" */
@@ -30,6 +41,40 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 		     :: "a" (eax), "c" (ecx));
 }
 
+/*
+ * MWAITX allows for a timer expiration to get the core out a wait state in
+ * addition to the default MWAIT exit condition of a store appearing at a
+ * monitored virtual address.
+ *
+ * Registers:
+ *
+ * MWAITX ECX[1]: enable timer if set
+ * MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks. The software P0
+ * frequency is the same as the TSC frequency.
+ *
+ * Below is a comparison between MWAIT and MWAITX on AMD processors:
+ *
+ *                 MWAIT                           MWAITX
+ * opcode          0f 01 c9           |            0f 01 fb
+ * ECX[0]                  value of RFLAGS.IF seen by instruction
+ * ECX[1]          unused/#GP if set  |            enable timer if set
+ * ECX[31:2]                     unused/#GP if set
+ * EAX                           unused (reserve for hint)
+ * EBX[31:0]       unused             |            max wait time (P0 clocks)
+ *
+ *                 MONITOR                         MONITORX
+ * opcode          0f 01 c8           |            0f 01 fa
+ * EAX                     (logical) address to monitor
+ * ECX                     #GP if not zero
+ */
+static inline void __mwaitx(unsigned long eax, unsigned long ebx,
+			    unsigned long ecx)
+{
+	/* "mwaitx %eax, %ebx, %ecx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xfb;"
+		     :: "a" (eax), "b" (ebx), "c" (ecx));
+}
+
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
 	trace_hardirqs_on();
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index d143bfad45d7..10d0596433f8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -153,7 +153,11 @@ do {						\
 	val = paravirt_read_msr(msr, &_err);	\
 } while (0)
 
-#define wrmsrl(msr, val)	wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32)
+static inline void wrmsrl(unsigned msr, u64 val)
+{
+	wrmsr(msr, (u32)val, (u32)(val>>32));
+}
+
 #define wrmsr_safe(msr, a, b)	paravirt_write_msr(msr, a, b)
 
 /* rdmsr with exception handling */
@@ -174,19 +178,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	return err;
 }
 
-static inline u64 paravirt_read_tsc(void)
-{
-	return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
-}
-
-#define rdtscl(low)				\
-do {						\
-	u64 _l = paravirt_read_tsc();		\
-	low = (int)_l;				\
-} while (0)
-
-#define rdtscll(val) (val = paravirt_read_tsc())
-
 static inline unsigned long long paravirt_sched_clock(void)
 {
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
@@ -215,27 +206,6 @@ do {						\
 
 #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
 
-static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
-{
-	return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
-}
-
-#define rdtscp(low, high, aux)				\
-do {							\
-	int __aux;					\
-	unsigned long __val = paravirt_rdtscp(&__aux);	\
-	(low) = (u32)__val;				\
-	(high) = (u32)(__val >> 32);			\
-	(aux) = __aux;					\
-} while (0)
-
-#define rdtscpll(val, aux)				\
-do {							\
-	unsigned long __aux; 				\
-	val = paravirt_rdtscp(&__aux);			\
-	(aux) = __aux;					\
-} while (0)
-
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
 	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index a6b8f9fadb06..ce029e4fa7c6 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -156,9 +156,7 @@ struct pv_cpu_ops {
 	u64 (*read_msr)(unsigned int msr, int *err);
 	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
 
-	u64 (*read_tsc)(void);
 	u64 (*read_pmc)(int counter);
-	unsigned long long (*read_tscp)(unsigned int *aux);
 
 #ifdef CONFIG_X86_32
 	/*
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 164e3f8d3c3d..fa1195dae425 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,8 +93,6 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
-extern bool mp_should_keep_irq(struct device *dev);
-
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index dc0f6ed35b08..7bcb861a04e5 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -159,6 +159,13 @@ struct x86_pmu_capability {
  */
 #define INTEL_PMC_IDX_FIXED_BTS				(INTEL_PMC_IDX_FIXED + 16)
 
+#define GLOBAL_STATUS_COND_CHG				BIT_ULL(63)
+#define GLOBAL_STATUS_BUFFER_OVF			BIT_ULL(62)
+#define GLOBAL_STATUS_UNC_OVF				BIT_ULL(61)
+#define GLOBAL_STATUS_ASIF				BIT_ULL(60)
+#define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
+#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+
 /*
  * IBS cpuid feature detection
  */
diff --git a/arch/x86/include/asm/pmc_atom.h b/arch/x86/include/asm/pmc_atom.h
index bc0fc0866553..aa8744c77c6d 100644
--- a/arch/x86/include/asm/pmc_atom.h
+++ b/arch/x86/include/asm/pmc_atom.h
@@ -18,6 +18,8 @@
 
 /* ValleyView Power Control Unit PCI Device ID */
 #define	PCI_DEVICE_ID_VLV_PMC	0x0F1C
+/* CherryTrail Power Control Unit PCI Device ID */
+#define	PCI_DEVICE_ID_CHT_PMC	0x229C
 
 /* PMC Memory mapped IO registers */
 #define	PMC_BASE_ADDR_OFFSET	0x44
@@ -29,6 +31,10 @@
 #define	PMC_FUNC_DIS		0x34
 #define	PMC_FUNC_DIS_2		0x38
 
+/* CHT specific bits in FUNC_DIS2 register */
+#define	BIT_FD_GMM		BIT(3)
+#define	BIT_FD_ISH		BIT(4)
+
 /* S0ix wake event control */
 #define	PMC_S0IX_WAKE_EN	0x3C
 
@@ -75,6 +81,21 @@
 #define PMC_PSS_BIT_USB			BIT(16)
 #define PMC_PSS_BIT_USB_SUS		BIT(17)
 
+/* CHT specific bits in PSS register */
+#define	PMC_PSS_BIT_CHT_UFS		BIT(7)
+#define	PMC_PSS_BIT_CHT_UXD		BIT(11)
+#define	PMC_PSS_BIT_CHT_UXD_FD		BIT(12)
+#define	PMC_PSS_BIT_CHT_UX_ENG		BIT(15)
+#define	PMC_PSS_BIT_CHT_USB_SUS		BIT(16)
+#define	PMC_PSS_BIT_CHT_GMM		BIT(17)
+#define	PMC_PSS_BIT_CHT_ISH		BIT(18)
+#define	PMC_PSS_BIT_CHT_DFX_MASTER	BIT(26)
+#define	PMC_PSS_BIT_CHT_DFX_CLUSTER1	BIT(27)
+#define	PMC_PSS_BIT_CHT_DFX_CLUSTER2	BIT(28)
+#define	PMC_PSS_BIT_CHT_DFX_CLUSTER3	BIT(29)
+#define	PMC_PSS_BIT_CHT_DFX_CLUSTER4	BIT(30)
+#define	PMC_PSS_BIT_CHT_DFX_CLUSTER5	BIT(31)
+
 /* These registers reflect D3 status of functions */
 #define	PMC_D3_STS_0		0xA0
 
@@ -117,6 +138,10 @@
 #define	BIT_USH_SS_PHY		BIT(2)
 #define	BIT_DFX			BIT(3)
 
+/* CHT specific bits in PMC_D3_STS_1 register */
+#define	BIT_STS_GMM		BIT(1)
+#define	BIT_STS_ISH		BIT(2)
+
 /* PMC I/O Registers */
 #define	ACPI_BASE_ADDR_OFFSET	0x40
 #define	ACPI_BASE_ADDR_MASK	0xFFFFFE00
@@ -126,4 +151,8 @@
 #define	SLEEP_TYPE_MASK		0xFFFFECFF
 #define	SLEEP_TYPE_S5		0x1C00
 #define	SLEEP_ENABLE		0x2000
+
+extern int pmc_atom_read(int offset, u32 *value);
+extern int pmc_atom_write(int offset, u32 value);
+
 #endif /* PMC_ATOM_H */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index dca71714f860..b12f81022a6b 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -90,9 +90,9 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!raw_cpu_read_4(__preempt_count));
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 43e6519df0d5..19577dd325fa 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -6,8 +6,8 @@
 /* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
+struct vm86;
 
-#include <asm/vm86.h>
 #include <asm/math_emu.h>
 #include <asm/segment.h>
 #include <asm/types.h>
@@ -390,9 +390,6 @@ struct thread_struct {
 #endif
 	unsigned long		gs;
 
-	/* Floating point and extended processor state */
-	struct fpu		fpu;
-
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
@@ -403,21 +400,22 @@ struct thread_struct {
 	unsigned long		cr2;
 	unsigned long		trap_nr;
 	unsigned long		error_code;
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_VM86
 	/* Virtual 86 mode info */
-	struct vm86_struct __user *vm86_info;
-	unsigned long		screen_bitmap;
-	unsigned long		v86flags;
-	unsigned long		v86mask;
-	unsigned long		saved_sp0;
-	unsigned int		saved_fs;
-	unsigned int		saved_gs;
+	struct vm86		*vm86;
 #endif
 	/* IO permissions: */
 	unsigned long		*io_bitmap_ptr;
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
+
+	/* Floating point and extended processor state */
+	struct fpu		fpu;
+	/*
+	 * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
+	 * the end.
+	 */
 };
 
 /*
@@ -647,14 +645,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 
 extern void set_task_blockstep(struct task_struct *task, bool on);
 
-/*
- * from system description table in BIOS. Mostly for MCA use, but
- * others may find it useful:
- */
-extern unsigned int		machine_id;
-extern unsigned int		machine_submodel_id;
-extern unsigned int		BIOS_revision;
-
 /* Boot loader type from the setup header: */
 extern int			bootloader_type;
 extern int			bootloader_version;
@@ -716,7 +706,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #define INIT_THREAD  {							  \
 	.sp0			= TOP_OF_INIT_STACK,			  \
-	.vm86_info		= NULL,					  \
 	.sysenter_cs		= __KERNEL_CS,				  \
 	.io_bitmap_ptr		= NULL,					  \
 }
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5fabf1362942..6271281f947d 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -88,7 +88,6 @@ extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch,
 				       unsigned long phase1_result);
 
 extern long syscall_trace_enter(struct pt_regs *);
-extern void syscall_trace_leave(struct pt_regs *);
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 628954ceede1..7a6bed5c08bc 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -62,7 +62,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 static __always_inline
 u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
 {
-	u64 delta = __native_read_tsc() - src->tsc_timestamp;
+	u64 delta = rdtsc_ordered() - src->tsc_timestamp;
 	return pvclock_scale_delta(delta, src->tsc_to_system_mul,
 				   src->tsc_shift);
 }
@@ -76,13 +76,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	u8 ret_flags;
 
 	version = src->version;
-	/* Note: emulated platforms which do not advertise SSE2 support
-	 * result in kvmclock not using the necessary RDTSC barriers.
-	 * Without barriers, it is possible that RDTSC instruction reads from
-	 * the time stamp counter outside rdtsc_barrier protected section
-	 * below, resulting in violation of monotonicity.
-	 */
-	rdtsc_barrier();
+
 	offset = pvclock_get_nsec_offset(src);
 	ret = src->system_time + offset;
 	ret_flags = src->flags;
diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h
index ae0e241e228b..c537cbb038a7 100644
--- a/arch/x86/include/asm/qrwlock.h
+++ b/arch/x86/include/asm/qrwlock.h
@@ -2,16 +2,6 @@
 #define _ASM_X86_QRWLOCK_H
 
 #include <asm-generic/qrwlock_types.h>
-
-#ifndef CONFIG_X86_PPRO_FENCE
-#define queue_write_unlock queue_write_unlock
-static inline void queue_write_unlock(struct qrwlock *lock)
-{
-        barrier();
-        ACCESS_ONCE(*(u8 *)&lock->cnts) = 0;
-}
-#endif
-
 #include <asm-generic/qrwlock.h>
 
 #endif /* _ASM_X86_QRWLOCK_H */
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 6fe6b182c998..9dfce4e0417d 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -57,9 +57,9 @@ struct sigcontext {
 	unsigned long ip;
 	unsigned long flags;
 	unsigned short cs;
-	unsigned short __pad2;	/* Was called gs, but was always zero. */
-	unsigned short __pad1;	/* Was called fs, but was always zero. */
-	unsigned short ss;
+	unsigned short gs;
+	unsigned short fs;
+	unsigned short __pad0;
 	unsigned long err;
 	unsigned long trapno;
 	unsigned long oldmask;
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 7c7c27c97daa..1f3175bb994e 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -4,6 +4,7 @@
 #include <asm/sigcontext.h>
 #include <asm/siginfo.h>
 #include <asm/ucontext.h>
+#include <linux/compat.h>
 
 #ifdef CONFIG_X86_32
 #define sigframe_ia32		sigframe
@@ -69,6 +70,15 @@ struct rt_sigframe {
 
 #ifdef CONFIG_X86_X32_ABI
 
+struct ucontext_x32 {
+	unsigned int	  uc_flags;
+	unsigned int 	  uc_link;
+	compat_stack_t	  uc_stack;
+	unsigned int	  uc__pad0;     /* needed for alignment */
+	struct sigcontext uc_mcontext;  /* the 64-bit sigcontext type */
+	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
 struct rt_sigframe_x32 {
 	u64 pretcode;
 	struct ucontext_x32 uc;
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 31eab867e6d3..c481be78fcf1 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -30,7 +30,7 @@ typedef sigset_t compat_sigset_t;
 #endif /* __ASSEMBLY__ */
 #include <uapi/asm/signal.h>
 #ifndef __ASSEMBLY__
-extern void do_notify_resume(struct pt_regs *, void *, __u32);
+extern void do_signal(struct pt_regs *regs);
 
 #define __ARCH_HAS_SA_RESTORER
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index c2e00bb2a136..58505f01962f 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -72,7 +72,7 @@ static __always_inline void boot_init_stack_canary(void)
 	 * on during the bootup the random pool has true entropy too.
 	 */
 	get_random_bytes(&canary, sizeof(canary));
-	tsc = __native_read_tsc();
+	tsc = rdtsc();
 	canary += tsc + (tsc << 32UL);
 
 	current->stack_canary = canary;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b7bf11..d7f3b3b78ac3 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -79,12 +79,12 @@ do {									\
 #else /* CONFIG_X86_32 */
 
 /* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
 
 #define __EXTRA_CLOBBER  \
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15", "flags"
+	  "r12", "r13", "r14", "r15"
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #define __switch_canary							  \
@@ -100,11 +100,7 @@ do {									\
 #define __switch_canary_iparam
 #endif	/* CC_STACKPROTECTOR */
 
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL.  Kernel IOPL
- * has no effect.
- */
+/* Save restore flags to clear handle leaking NT */
 #define switch_to(prev, next, last) \
 	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 592a6a672e07..91dfcafe27a6 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -37,6 +37,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *);
 asmlinkage unsigned long sys_sigreturn(void);
 
 /* kernel/vm86_32.c */
+struct vm86_struct;
 asmlinkage long sys_vm86old(struct vm86_struct __user *);
 asmlinkage long sys_vm86(unsigned long, unsigned long);
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 225ee545e1a0..8afdc3e44247 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -27,14 +27,17 @@
  * Without this offset, that can result in a page fault.  (We are
  * careful that, in this case, the value we read doesn't matter.)
  *
- * In vm86 mode, the hardware frame is much longer still, but we neither
- * access the extra members from NMI context, nor do we write such a
- * frame at sp0 at all.
+ * In vm86 mode, the hardware frame is much longer still, so add 16
+ * bytes to make room for the real-mode segments.
  *
  * x86_64 has a fixed-length stack frame.
  */
 #ifdef CONFIG_X86_32
-# define TOP_OF_KERNEL_STACK_PADDING 8
+# ifdef CONFIG_VM86
+#  define TOP_OF_KERNEL_STACK_PADDING 16
+# else
+#  define TOP_OF_KERNEL_STACK_PADDING 8
+# endif
 #else
 # define TOP_OF_KERNEL_STACK_PADDING 0
 #endif
@@ -140,27 +143,11 @@ struct thread_info {
 	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT |	\
 	 _TIF_NOHZ)
 
-/* work to do in syscall_trace_leave() */
-#define _TIF_WORK_SYSCALL_EXIT	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |	\
-	 _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK							\
-	(0x0000FFFF &							\
-	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|			\
-	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
-
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK						\
 	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT |	\
 	_TIF_NOHZ)
 
-/* Only used for 64 bit */
-#define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME |				\
-	 _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
-
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
 	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cd791948b286..6df2029405a3 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -261,6 +261,12 @@ static inline void reset_lazy_tlbstate(void)
 
 #endif	/* SMP */
 
+/* Not inlined due to inc_irq_stat not being defined yet */
+#define flush_tlb_local() {		\
+	inc_irq_stat(irq_tlb_count);	\
+	local_flush_tlb();		\
+}
+
 #ifndef CONFIG_PARAVIRT
 #define flush_tlb_others(mask, mm, start, end)	\
 	native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c5380bea2a36..c3496619740a 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -112,8 +112,8 @@ asmlinkage void smp_threshold_interrupt(void);
 asmlinkage void smp_deferred_error_interrupt(void);
 #endif
 
-extern enum ctx_state ist_enter(struct pt_regs *regs);
-extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state);
+extern void ist_enter(struct pt_regs *regs);
+extern void ist_exit(struct pt_regs *regs);
 extern void ist_begin_non_atomic(struct pt_regs *regs);
 extern void ist_end_non_atomic(void);
 
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 94605c0e9cee..6d7c5479bcea 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -21,28 +21,12 @@ extern void disable_TSC(void);
 
 static inline cycles_t get_cycles(void)
 {
-	unsigned long long ret = 0;
-
 #ifndef CONFIG_X86_TSC
 	if (!cpu_has_tsc)
 		return 0;
 #endif
-	rdtscll(ret);
-
-	return ret;
-}
 
-static __always_inline cycles_t vget_cycles(void)
-{
-	/*
-	 * We only do VDSOs on TSC capable CPUs, so this shouldn't
-	 * access boot_cpu_data (which is not VDSO-safe):
-	 */
-#ifndef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
-		return 0;
-#endif
-	return (cycles_t)__native_read_tsc();
+	return rdtsc();
 }
 
 extern void tsc_init(void);
@@ -51,6 +35,7 @@ extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern int check_tsc_disabled(void);
 extern unsigned long native_calibrate_tsc(void);
+extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
 
 extern int tsc_clocksource_reliable;
 
diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h
index 1d8de3f3feca..1e491f3af317 100644
--- a/arch/x86/include/asm/vm86.h
+++ b/arch/x86/include/asm/vm86.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_VM86_H
 #define _ASM_X86_VM86_H
 
-
 #include <asm/ptrace.h>
 #include <uapi/asm/vm86.h>
 
@@ -28,43 +27,49 @@ struct kernel_vm86_regs {
 	unsigned short gs, __gsh;
 };
 
-struct kernel_vm86_struct {
-	struct kernel_vm86_regs regs;
-/*
- * the below part remains on the kernel stack while we are in VM86 mode.
- * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we
- * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above
- * 'struct kernel_vm86_regs' with the then actual values.
- * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct'
- * in kernelspace, hence we need not reget the data from userspace.
- */
-#define VM86_TSS_ESP0 flags
+struct vm86 {
+	struct vm86plus_struct __user *user_vm86;
+	struct pt_regs regs32;
+	unsigned long veflags;
+	unsigned long veflags_mask;
+	unsigned long saved_sp0;
+
 	unsigned long flags;
 	unsigned long screen_bitmap;
 	unsigned long cpu_type;
 	struct revectored_struct int_revectored;
 	struct revectored_struct int21_revectored;
 	struct vm86plus_info_struct vm86plus;
-	struct pt_regs *regs32;   /* here we save the pointer to the old regs */
-/*
- * The below is not part of the structure, but the stack layout continues
- * this way. In front of 'return-eip' may be some data, depending on
- * compilation, so we don't rely on this and save the pointer to 'oldregs'
- * in 'regs32' above.
- * However, with GCC-2.7.2 and the current CFLAGS you see exactly this:
-
-	long return-eip;        from call to vm86()
-	struct pt_regs oldregs;  user space registers as saved by syscall
- */
 };
 
 #ifdef CONFIG_VM86
 
 void handle_vm86_fault(struct kernel_vm86_regs *, long);
 int handle_vm86_trap(struct kernel_vm86_regs *, long, int);
-struct pt_regs *save_v86_state(struct kernel_vm86_regs *);
+void save_v86_state(struct kernel_vm86_regs *, int);
 
 struct task_struct;
+
+#define free_vm86(t) do {				\
+	struct thread_struct *__t = (t);		\
+	if (__t->vm86 != NULL) {			\
+		kfree(__t->vm86);			\
+		__t->vm86 = NULL;			\
+	}						\
+} while (0)
+
+/*
+ * Support for VM86 programs to request interrupts for
+ * real mode hardware drivers:
+ */
+#define FIRST_VM86_IRQ		 3
+#define LAST_VM86_IRQ		15
+
+static inline int invalid_vm86_irq(int irq)
+{
+	return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
+}
+
 void release_vm86_irqs(struct task_struct *);
 
 #else
@@ -77,6 +82,10 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
 	return 0;
 }
 
+static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { }
+
+#define free_vm86(t) do { } while(0)
+
 #endif /* CONFIG_VM86 */
 
 #endif /* _ASM_X86_VM86_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index da772edd19ab..448b7ca61aee 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -47,6 +47,7 @@
 #define CPU_BASED_MOV_DR_EXITING                0x00800000
 #define CPU_BASED_UNCOND_IO_EXITING             0x01000000
 #define CPU_BASED_USE_IO_BITMAPS                0x02000000
+#define CPU_BASED_MONITOR_TRAP_FLAG             0x08000000
 #define CPU_BASED_USE_MSR_BITMAPS               0x10000000
 #define CPU_BASED_MONITOR_EXITING               0x20000000
 #define CPU_BASED_PAUSE_EXITING                 0x40000000
@@ -367,29 +368,29 @@ enum vmcs_field {
 #define TYPE_PHYSICAL_APIC_EVENT        (10 << 12)
 #define TYPE_PHYSICAL_APIC_INST         (15 << 12)
 
-/* segment AR */
-#define SEGMENT_AR_L_MASK (1 << 13)
-
-#define AR_TYPE_ACCESSES_MASK 1
-#define AR_TYPE_READABLE_MASK (1 << 1)
-#define AR_TYPE_WRITEABLE_MASK (1 << 2)
-#define AR_TYPE_CODE_MASK (1 << 3)
-#define AR_TYPE_MASK 0x0f
-#define AR_TYPE_BUSY_64_TSS 11
-#define AR_TYPE_BUSY_32_TSS 11
-#define AR_TYPE_BUSY_16_TSS 3
-#define AR_TYPE_LDT 2
-
-#define AR_UNUSABLE_MASK (1 << 16)
-#define AR_S_MASK (1 << 4)
-#define AR_P_MASK (1 << 7)
-#define AR_L_MASK (1 << 13)
-#define AR_DB_MASK (1 << 14)
-#define AR_G_MASK (1 << 15)
-#define AR_DPL_SHIFT 5
-#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
-
-#define AR_RESERVD_MASK 0xfffe0f00
+/* segment AR in VMCS -- these are different from what LAR reports */
+#define VMX_SEGMENT_AR_L_MASK (1 << 13)
+
+#define VMX_AR_TYPE_ACCESSES_MASK 1
+#define VMX_AR_TYPE_READABLE_MASK (1 << 1)
+#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2)
+#define VMX_AR_TYPE_CODE_MASK (1 << 3)
+#define VMX_AR_TYPE_MASK 0x0f
+#define VMX_AR_TYPE_BUSY_64_TSS 11
+#define VMX_AR_TYPE_BUSY_32_TSS 11
+#define VMX_AR_TYPE_BUSY_16_TSS 3
+#define VMX_AR_TYPE_LDT 2
+
+#define VMX_AR_UNUSABLE_MASK (1 << 16)
+#define VMX_AR_S_MASK (1 << 4)
+#define VMX_AR_P_MASK (1 << 7)
+#define VMX_AR_L_MASK (1 << 13)
+#define VMX_AR_DB_MASK (1 << 14)
+#define VMX_AR_G_MASK (1 << 15)
+#define VMX_AR_DPL_SHIFT 5
+#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3)
+
+#define VMX_AR_RESERVD_MASK 0xfffe0f00
 
 #define TSS_PRIVATE_MEMSLOT			(KVM_USER_MEM_SLOTS + 0)
 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 1)
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 608a79d5a466..e6911caf5bbf 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -20,4 +20,15 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 /* No need for a barrier -- XCHG is a barrier on x86. */
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
+extern int xen_have_vector_callback;
+
+/*
+ * Events delivered via platform PCI interrupts are always
+ * routed to vcpu 0 and hence cannot be rebound.
+ */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return (!xen_hvm_domain() || xen_have_vector_callback);
+}
+
 #endif /* _ASM_X86_XEN_EVENTS_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index ca08a27b90b3..83aea8055119 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -465,6 +465,12 @@ HYPERVISOR_tmem_op(
 	return _hypercall1(int, tmem_op, op);
 }
 
+static inline int
+HYPERVISOR_xenpmu_op(unsigned int op, void *arg)
+{
+	return _hypercall2(int, xenpmu_op, op, arg);
+}
+
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 3400dbaec3c3..62ca03ef5c65 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -3,12 +3,38 @@
  *
  * Guest OS interface to x86 Xen.
  *
- * Copyright (c) 2004, K A Fraser
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2004-2006, K A Fraser
  */
 
 #ifndef _ASM_X86_XEN_INTERFACE_H
 #define _ASM_X86_XEN_INTERFACE_H
 
+/*
+ * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field
+ * in a struct in memory.
+ * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an
+ * hypercall argument.
+ * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but
+ * they might not be on other architectures.
+ */
 #ifdef __XEN__
 #define __DEFINE_GUEST_HANDLE(name, type) \
     typedef struct { type *p; } __guest_handle_ ## name
@@ -88,13 +114,16 @@ DEFINE_GUEST_HANDLE(xen_ulong_t);
  * start of the GDT because some stupid OSes export hard-coded selector values
  * in their ABI. These hard-coded values are always near the start of the GDT,
  * so Xen places itself out of the way, at the far end of the GDT.
+ *
+ * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op
  */
 #define FIRST_RESERVED_GDT_PAGE  14
 #define FIRST_RESERVED_GDT_BYTE  (FIRST_RESERVED_GDT_PAGE * 4096)
 #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
 
 /*
- * Send an array of these to HYPERVISOR_set_trap_table()
+ * Send an array of these to HYPERVISOR_set_trap_table().
+ * Terminate the array with a sentinel entry, with traps[].address==0.
  * The privilege level specifies which modes may enter a trap via a software
  * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
  * privilege levels as follows:
@@ -118,10 +147,41 @@ struct trap_info {
 DEFINE_GUEST_HANDLE_STRUCT(trap_info);
 
 struct arch_shared_info {
-    unsigned long max_pfn;                  /* max pfn that appears in table */
-    /* Frame containing list of mfns containing list of mfns containing p2m. */
-    unsigned long pfn_to_mfn_frame_list_list;
-    unsigned long nmi_reason;
+	/*
+	 * Number of valid entries in the p2m table(s) anchored at
+	 * pfn_to_mfn_frame_list_list and/or p2m_vaddr.
+	 */
+	unsigned long max_pfn;
+	/*
+	 * Frame containing list of mfns containing list of mfns containing p2m.
+	 * A value of 0 indicates it has not yet been set up, ~0 indicates it
+	 * has been set to invalid e.g. due to the p2m being too large for the
+	 * 3-level p2m tree. In this case the linear mapper p2m list anchored
+	 * at p2m_vaddr is to be used.
+	 */
+	xen_pfn_t pfn_to_mfn_frame_list_list;
+	unsigned long nmi_reason;
+	/*
+	 * Following three fields are valid if p2m_cr3 contains a value
+	 * different from 0.
+	 * p2m_cr3 is the root of the address space where p2m_vaddr is valid.
+	 * p2m_cr3 is in the same format as a cr3 value in the vcpu register
+	 * state and holds the folded machine frame number (via xen_pfn_to_cr3)
+	 * of a L3 or L4 page table.
+	 * p2m_vaddr holds the virtual address of the linear p2m list. All
+	 * entries in the range [0...max_pfn[ are accessible via this pointer.
+	 * p2m_generation will be incremented by the guest before and after each
+	 * change of the mappings of the p2m list. p2m_generation starts at 0
+	 * and a value with the least significant bit set indicates that a
+	 * mapping update is in progress. This allows guest external software
+	 * (e.g. in Dom0) to verify that read mappings are consistent and
+	 * whether they have changed since the last check.
+	 * Modifying a p2m element in the linear p2m list is allowed via an
+	 * atomic write only.
+	 */
+	unsigned long p2m_cr3;		/* cr3 value of the p2m address space */
+	unsigned long p2m_vaddr;	/* virtual address of the p2m list */
+	unsigned long p2m_generation;	/* generation count of p2m mapping */
 };
 #endif	/* !__ASSEMBLY__ */
 
@@ -137,13 +197,31 @@ struct arch_shared_info {
 /*
  * The following is all CPU context. Note that the fpu_ctxt block is filled
  * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
+ *
+ * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise
+ * for HVM and PVH guests, not all information in this structure is updated:
+ *
+ * - For HVM guests, the structures read include: fpu_ctxt (if
+ * VGCT_I387_VALID is set), flags, user_regs, debugreg[*]
+ *
+ * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to
+ * set cr3. All other fields not used should be set to 0.
  */
 struct vcpu_guest_context {
     /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
     struct { char x[512]; } fpu_ctxt;       /* User-level FPU registers     */
-#define VGCF_I387_VALID (1<<0)
-#define VGCF_HVM_GUEST  (1<<1)
-#define VGCF_IN_KERNEL  (1<<2)
+#define VGCF_I387_VALID                (1<<0)
+#define VGCF_IN_KERNEL                 (1<<2)
+#define _VGCF_i387_valid               0
+#define VGCF_i387_valid                (1<<_VGCF_i387_valid)
+#define _VGCF_in_kernel                2
+#define VGCF_in_kernel                 (1<<_VGCF_in_kernel)
+#define _VGCF_failsafe_disables_events 3
+#define VGCF_failsafe_disables_events  (1<<_VGCF_failsafe_disables_events)
+#define _VGCF_syscall_disables_events  4
+#define VGCF_syscall_disables_events   (1<<_VGCF_syscall_disables_events)
+#define _VGCF_online                   5
+#define VGCF_online                    (1<<_VGCF_online)
     unsigned long flags;                    /* VGCF_* flags                 */
     struct cpu_user_regs user_regs;         /* User-level CPU registers     */
     struct trap_info trap_ctxt[256];        /* Virtual IDT                  */
@@ -172,6 +250,129 @@ struct vcpu_guest_context {
 #endif
 };
 DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
+
+/* AMD PMU registers and structures */
+struct xen_pmu_amd_ctxt {
+	/*
+	 * Offsets to counter and control MSRs (relative to xen_pmu_arch.c.amd).
+	 * For PV(H) guests these fields are RO.
+	 */
+	uint32_t counters;
+	uint32_t ctrls;
+
+	/* Counter MSRs */
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+	uint64_t regs[];
+#elif defined(__GNUC__)
+	uint64_t regs[0];
+#endif
+};
+
+/* Intel PMU registers and structures */
+struct xen_pmu_cntr_pair {
+	uint64_t counter;
+	uint64_t control;
+};
+
+struct xen_pmu_intel_ctxt {
+	/*
+	 * Offsets to fixed and architectural counter MSRs (relative to
+	 * xen_pmu_arch.c.intel).
+	 * For PV(H) guests these fields are RO.
+	 */
+	uint32_t fixed_counters;
+	uint32_t arch_counters;
+
+	/* PMU registers */
+	uint64_t global_ctrl;
+	uint64_t global_ovf_ctrl;
+	uint64_t global_status;
+	uint64_t fixed_ctrl;
+	uint64_t ds_area;
+	uint64_t pebs_enable;
+	uint64_t debugctl;
+
+	/* Fixed and architectural counter MSRs */
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+	uint64_t regs[];
+#elif defined(__GNUC__)
+	uint64_t regs[0];
+#endif
+};
+
+/* Sampled domain's registers */
+struct xen_pmu_regs {
+	uint64_t ip;
+	uint64_t sp;
+	uint64_t flags;
+	uint16_t cs;
+	uint16_t ss;
+	uint8_t cpl;
+	uint8_t pad[3];
+};
+
+/* PMU flags */
+#define PMU_CACHED	   (1<<0) /* PMU MSRs are cached in the context */
+#define PMU_SAMPLE_USER	   (1<<1) /* Sample is from user or kernel mode */
+#define PMU_SAMPLE_REAL	   (1<<2) /* Sample is from realmode */
+#define PMU_SAMPLE_PV	   (1<<3) /* Sample from a PV guest */
+
+/*
+ * Architecture-specific information describing state of the processor at
+ * the time of PMU interrupt.
+ * Fields of this structure marked as RW for guest should only be written by
+ * the guest when PMU_CACHED bit in pmu_flags is set (which is done by the
+ * hypervisor during PMU interrupt). Hypervisor will read updated data in
+ * XENPMU_flush hypercall and clear PMU_CACHED bit.
+ */
+struct xen_pmu_arch {
+	union {
+		/*
+		 * Processor's registers at the time of interrupt.
+		 * WO for hypervisor, RO for guests.
+		 */
+		struct xen_pmu_regs regs;
+		/*
+		 * Padding for adding new registers to xen_pmu_regs in
+		 * the future
+		 */
+#define XENPMU_REGS_PAD_SZ  64
+		uint8_t pad[XENPMU_REGS_PAD_SZ];
+	} r;
+
+	/* WO for hypervisor, RO for guest */
+	uint64_t pmu_flags;
+
+	/*
+	 * APIC LVTPC register.
+	 * RW for both hypervisor and guest.
+	 * Only APIC_LVT_MASKED bit is loaded by the hypervisor into hardware
+	 * during XENPMU_flush or XENPMU_lvtpc_set.
+	 */
+	union {
+		uint32_t lapic_lvtpc;
+		uint64_t pad;
+	} l;
+
+	/*
+	 * Vendor-specific PMU registers.
+	 * RW for both hypervisor and guest (see exceptions above).
+	 * Guest's updates to this field are verified and then loaded by the
+	 * hypervisor into hardware during XENPMU_flush
+	 */
+	union {
+		struct xen_pmu_amd_ctxt amd;
+		struct xen_pmu_intel_ctxt intel;
+
+		/*
+		 * Padding for contexts (fixed parts only, does not include
+		 * MSR banks that are specified by offsets)
+		 */
+#define XENPMU_CTXT_PAD_SZ  128
+		uint8_t pad[XENPMU_CTXT_PAD_SZ];
+	} c;
+};
+
 #endif	/* !__ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c44a5d53e464..a3804fbe1f36 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -35,9 +35,7 @@ typedef struct xpaddr {
 #define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
 #define IDENTITY_FRAME(m)	((m) | IDENTITY_FRAME_BIT)
 
-/* Maximum amount of memory we can handle in a domain in pages */
-#define MAX_DOMAIN_PAGES						\
-    ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
+#define P2M_PER_PAGE		(PAGE_SIZE / sizeof(unsigned long))
 
 extern unsigned long *machine_to_phys_mapping;
 extern unsigned long  machine_to_phys_nr;
@@ -48,8 +46,8 @@ extern unsigned long  xen_max_p2m_pfn;
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-extern unsigned long set_phys_range_identity(unsigned long pfn_s,
-					     unsigned long pfn_e);
+extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
+						    unsigned long pfn_e);
 
 extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct gnttab_map_grant_ref *kmap_ops,
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index ab456dc233b5..329254373479 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -120,7 +120,7 @@ struct boot_params {
 	__u8  _pad3[16];				/* 0x070 */
 	__u8  hd0_info[16];	/* obsolete! */		/* 0x080 */
 	__u8  hd1_info[16];	/* obsolete! */		/* 0x090 */
-	struct sys_desc_table sys_desc_table;		/* 0x0a0 */
+	struct sys_desc_table sys_desc_table; /* obsolete! */	/* 0x0a0 */
 	struct olpc_ofw_header olpc_ofw_header;		/* 0x0b0 */
 	__u32 ext_ramdisk_image;			/* 0x0c0 */
 	__u32 ext_ramdisk_size;				/* 0x0c4 */
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 8fba544e9cc4..f0412c50c47b 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -27,6 +27,8 @@
 #define HV_X64_MSR_VP_RUNTIME_AVAILABLE		(1 << 0)
 /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
 #define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE	(1 << 1)
+/* Partition reference TSC MSR is available */
+#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE              (1 << 9)
 
 /* A partition's reference time stamp counter (TSC) page */
 #define HV_X64_MSR_REFERENCE_TSC		0x40000021
@@ -108,6 +110,8 @@
 #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		(1 << 4)
 /* Support for a virtual guest idle state is available */
 #define HV_X64_GUEST_IDLE_STATE_AVAILABLE		(1 << 5)
+/* Guest crash data handler available */
+#define HV_X64_GUEST_CRASH_MSR_AVAILABLE		(1 << 10)
 
 /*
  * Implementation recommendations. Indicates which behaviors the hypervisor
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a4ae82eb82aa..cd54147cb365 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -354,7 +354,7 @@ struct kvm_xcrs {
 struct kvm_sync_regs {
 };
 
-#define KVM_QUIRK_LINT0_REENABLED	(1 << 0)
-#define KVM_QUIRK_CD_NW_CLEARED		(1 << 1)
+#define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index a0eab85ce7b8..76880ede9a35 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -15,7 +15,8 @@ struct mce {
 	__u64 time;	/* wall time_t when error was detected */
 	__u8  cpuvendor;	/* cpu vendor as encoded in system.h */
 	__u8  inject_flags;	/* software inject flags */
-	__u16  pad;
+	__u8  severity;
+	__u8  usable_addr;
 	__u32 cpuid;	/* CPUID 1 EAX */
 	__u8  cs;		/* code segment */
 	__u8  bank;	/* machine check bank */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 180a0c3c224d..79887abcb5e1 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -37,8 +37,6 @@
 #define X86_EFLAGS_VM		_BITUL(X86_EFLAGS_VM_BIT)
 #define X86_EFLAGS_AC_BIT	18 /* Alignment Check/Access Control */
 #define X86_EFLAGS_AC		_BITUL(X86_EFLAGS_AC_BIT)
-#define X86_EFLAGS_AC_BIT	18 /* Alignment Check/Access Control */
-#define X86_EFLAGS_AC		_BITUL(X86_EFLAGS_AC_BIT)
 #define X86_EFLAGS_VIF_BIT	19 /* Virtual Interrupt Flag */
 #define X86_EFLAGS_VIF		_BITUL(X86_EFLAGS_VIF_BIT)
 #define X86_EFLAGS_VIP_BIT	20 /* Virtual Interrupt Pending */
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 0e8a973de9ee..40836a9a7250 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -177,24 +177,9 @@ struct sigcontext {
 	__u64 rip;
 	__u64 eflags;		/* RFLAGS */
 	__u16 cs;
-
-	/*
-	 * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
-	 * Linux saved and restored fs and gs in these slots.  This
-	 * was counterproductive, as fsbase and gsbase were never
-	 * saved, so arch_prctl was presumably unreliable.
-	 *
-	 * If these slots are ever needed for any other purpose, there
-	 * is some risk that very old 64-bit binaries could get
-	 * confused.  I doubt that many such binaries still work,
-	 * though, since the same patch in 2.5.64 also removed the
-	 * 64-bit set_thread_area syscall, so it appears that there is
-	 * no TLS API that works in both pre- and post-2.5.64 kernels.
-	 */
-	__u16 __pad2;		/* Was gs. */
-	__u16 __pad1;		/* Was fs. */
-
-	__u16 ss;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
 	__u64 err;
 	__u64 trapno;
 	__u64 oldmask;
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 1fe92181ee9e..37fee272618f 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -58,6 +58,7 @@
 #define EXIT_REASON_INVALID_STATE       33
 #define EXIT_REASON_MSR_LOAD_FAIL       34
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_TRAP_FLAG   37
 #define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY  41
@@ -106,6 +107,7 @@
 	{ EXIT_REASON_MSR_READ,              "MSR_READ" }, \
 	{ EXIT_REASON_MSR_WRITE,             "MSR_WRITE" }, \
 	{ EXIT_REASON_MWAIT_INSTRUCTION,     "MWAIT_INSTRUCTION" }, \
+	{ EXIT_REASON_MONITOR_TRAP_FLAG,     "MONITOR_TRAP_FLAG" }, \
 	{ EXIT_REASON_MONITOR_INSTRUCTION,   "MONITOR_INSTRUCTION" }, \
 	{ EXIT_REASON_PAUSE_INSTRUCTION,     "PAUSE_INSTRUCTION" }, \
 	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0f15af41bd80..3c3622176340 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -23,8 +23,10 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
 obj-y			:= process_$(BITS).o signal.o
+obj-$(CONFIG_COMPAT)	+= signal_compat.o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
+obj-y			+= time.o ioport.o dumpstack.o nmi.o
+obj-$(CONFIG_MODIFY_LDT_SYSCALL)	+= ldt.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
@@ -107,8 +109,6 @@ obj-$(CONFIG_EFI)			+= sysfb_efi.o
 
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
-obj-$(CONFIG_IOSF_MBI)			+= iosf_mbi.o
-obj-$(CONFIG_PMC_ATOM)			+= pmc_atom.o
 
 ###
 # 64 bit specific files
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e49ee24da85e..ded848c20e05 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -445,6 +445,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 		polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
 
 	mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+	acpi_penalize_sci_irq(bus_irq, trigger, polarity);
 
 	/*
 	 * stash over-ride to indicate we've been here
@@ -710,7 +711,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 #endif
 }
 
-static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
 {
 	int cpu;
 
@@ -726,12 +727,6 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 	*pcpu = cpu;
 	return 0;
 }
-
-/* wrapper to silence section mismatch warning */
-int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
-{
-	return _acpi_map_lsapic(handle, physid, pcpu);
-}
 EXPORT_SYMBOL(acpi_map_cpu);
 
 int acpi_unmap_cpu(int cpu)
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index ede92c3364d3..222a57076039 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -263,7 +263,7 @@ static int apbt_clocksource_register(void)
 
 	/* Verify whether apbt counter works */
 	t1 = dw_apb_clocksource_read(clocksource_apbt);
-	rdtscll(start);
+	start = rdtsc();
 
 	/*
 	 * We don't know the TSC frequency yet, but waiting for
@@ -273,7 +273,7 @@ static int apbt_clocksource_register(void)
 	 */
 	do {
 		rep_nop();
-		rdtscll(now);
+		now = rdtsc();
 	} while ((now - start) < 200000UL);
 
 	/* APBT is the only always on clocksource, it has to work! */
@@ -390,13 +390,13 @@ unsigned long apbt_quick_calibrate(void)
 	old = dw_apb_clocksource_read(clocksource_apbt);
 	old += loop;
 
-	t1 = __native_read_tsc();
+	t1 = rdtsc();
 
 	do {
 		new = dw_apb_clocksource_read(clocksource_apbt);
 	} while (new < old);
 
-	t2 = __native_read_tsc();
+	t2 = rdtsc();
 
 	shift = 5;
 	if (unlikely(loop >> shift == 0)) {
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index dcb52850a28f..3ca3e46aa405 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -457,45 +457,45 @@ static int lapic_next_deadline(unsigned long delta,
 {
 	u64 tsc;
 
-	rdtscll(tsc);
+	tsc = rdtsc();
 	wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
 	return 0;
 }
 
-/*
- * Setup the lapic timer in periodic or oneshot mode
- */
-static void lapic_timer_setup(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int lapic_timer_shutdown(struct clock_event_device *evt)
 {
-	unsigned long flags;
 	unsigned int v;
 
 	/* Lapic used as dummy for broadcast ? */
 	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
-		return;
+		return 0;
 
-	local_irq_save(flags);
+	v = apic_read(APIC_LVTT);
+	v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+	apic_write(APIC_LVTT, v);
+	apic_write(APIC_TMICT, 0);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
-		__setup_APIC_LVTT(lapic_timer_frequency,
-				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		v = apic_read(APIC_LVTT);
-		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
-		apic_write(APIC_LVTT, v);
-		apic_write(APIC_TMICT, 0);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
+static inline int
+lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot)
+{
+	/* Lapic used as dummy for broadcast ? */
+	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
 
-	local_irq_restore(flags);
+	__setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1);
+	return 0;
+}
+
+static int lapic_timer_set_periodic(struct clock_event_device *evt)
+{
+	return lapic_timer_set_periodic_oneshot(evt, false);
+}
+
+static int lapic_timer_set_oneshot(struct clock_event_device *evt)
+{
+	return lapic_timer_set_periodic_oneshot(evt, true);
 }
 
 /*
@@ -513,15 +513,18 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
  * The local apic timer can be used for any function which is CPU local.
  */
 static struct clock_event_device lapic_clockevent = {
-	.name		= "lapic",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
-			| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
-	.shift		= 32,
-	.set_mode	= lapic_timer_setup,
-	.set_next_event	= lapic_next_event,
-	.broadcast	= lapic_timer_broadcast,
-	.rating		= 100,
-	.irq		= -1,
+	.name			= "lapic",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
+				  | CLOCK_EVT_FEAT_DUMMY,
+	.shift			= 32,
+	.set_state_shutdown	= lapic_timer_shutdown,
+	.set_state_periodic	= lapic_timer_set_periodic,
+	.set_state_oneshot	= lapic_timer_set_oneshot,
+	.set_next_event		= lapic_next_event,
+	.broadcast		= lapic_timer_broadcast,
+	.rating			= 100,
+	.irq			= -1,
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
@@ -592,7 +595,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
 	unsigned long pm = acpi_pm_read_early();
 
 	if (cpu_has_tsc)
-		rdtscll(tsc);
+		tsc = rdtsc();
 
 	switch (lapic_cal_loops++) {
 	case 0:
@@ -778,7 +781,7 @@ static int __init calibrate_APIC_clock(void)
 		 * Setup the apic timer manually
 		 */
 		levt->event_handler = lapic_cal_handler;
-		lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt);
+		lapic_timer_set_periodic(levt);
 		lapic_cal_loops = -1;
 
 		/* Let the interrupts run */
@@ -788,7 +791,8 @@ static int __init calibrate_APIC_clock(void)
 			cpu_relax();
 
 		/* Stop the lapic timer */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
+		local_irq_disable();
+		lapic_timer_shutdown(levt);
 
 		/* Jiffies delta */
 		deltaj = lapic_cal_j2 - lapic_cal_j1;
@@ -799,8 +803,8 @@ static int __init calibrate_APIC_clock(void)
 			apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
 		else
 			levt->features |= CLOCK_EVT_FEAT_DUMMY;
-	} else
-		local_irq_enable();
+	}
+	local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
 		pr_warning("APIC timer disabled due to verification failure\n");
@@ -878,7 +882,7 @@ static void local_apic_timer_interrupt(void)
 	if (!evt->event_handler) {
 		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu);
 		/* Switch it off */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+		lapic_timer_shutdown(evt);
 		return;
 	}
 
@@ -1209,7 +1213,7 @@ void setup_local_APIC(void)
 	long long max_loops = cpu_khz ? cpu_khz : 1000000;
 
 	if (cpu_has_tsc)
-		rdtscll(tsc);
+		tsc = rdtsc();
 
 	if (disable_apic) {
 		disable_ioapic_support();
@@ -1293,7 +1297,7 @@ void setup_local_APIC(void)
 		}
 		if (queued) {
 			if (cpu_has_tsc && cpu_khz) {
-				rdtscll(ntsc);
+				ntsc = rdtsc();
 				max_loops = (cpu_khz << 10) - (ntsc - tsc);
 			} else
 				max_loops--;
@@ -1424,7 +1428,7 @@ static inline void __x2apic_disable(void)
 {
 	u64 msr;
 
-	if (cpu_has_apic)
+	if (!cpu_has_apic)
 		return;
 
 	rdmsrl(MSR_IA32_APICBASE, msr);
@@ -1483,10 +1487,13 @@ void x2apic_setup(void)
 
 static __init void x2apic_disable(void)
 {
-	u32 x2apic_id;
+	u32 x2apic_id, state = x2apic_state;
 
-	if (x2apic_state != X2APIC_ON)
-		goto out;
+	x2apic_mode = 0;
+	x2apic_state = X2APIC_DISABLED;
+
+	if (state != X2APIC_ON)
+		return;
 
 	x2apic_id = read_apic_id();
 	if (x2apic_id >= 255)
@@ -1494,9 +1501,6 @@ static __init void x2apic_disable(void)
 
 	__x2apic_disable();
 	register_lapic_address(mp_lapic_addr);
-out:
-	x2apic_state = X2APIC_DISABLED;
-	x2apic_mode = 0;
 }
 
 static __init void x2apic_enable(void)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index de918c410eae..f92ab36979a2 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -191,7 +191,6 @@ static struct apic apic_flat =  {
 	.send_IPI_all			= flat_send_IPI_all,
 	.send_IPI_self			= apic_send_IPI_self,
 
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
 	.read				= native_apic_mem_read,
@@ -299,7 +298,6 @@ static struct apic apic_physflat =  {
 	.send_IPI_all			= physflat_send_IPI_all,
 	.send_IPI_self			= apic_send_IPI_self,
 
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
 	.read				= native_apic_mem_read,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index b205cdbdbe6a..0d96749cfcac 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -152,7 +152,6 @@ struct apic apic_noop = {
 
 	.wakeup_secondary_cpu		= noop_wakeup_secondary_cpu,
 
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= NULL,
 
 	.read				= noop_apic_read,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 017149cded07..b548fd3b764b 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -92,7 +92,6 @@ static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 
 	write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
 
-	atomic_set(&init_deasserted, 1);
 	return 0;
 }
 
@@ -235,7 +234,6 @@ static const struct apic apic_numachip __refconst = {
 	.send_IPI_self			= numachip_send_IPI_self,
 
 	.wakeup_secondary_cpu		= numachip_wakeup_secondary,
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= NULL, /* REMRD not supported */
 
 	.read				= native_apic_mem_read,
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index c4a8d63f8220..971cf8875939 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -186,7 +186,6 @@ static struct apic apic_bigsmp = {
 	.send_IPI_all			= bigsmp_send_IPI_all,
 	.send_IPI_self			= default_send_IPI_self,
 
-	.wait_for_init_deassert		= true,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
 	.read				= native_apic_mem_read,
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 6873ab925d00..045e424fb368 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -28,146 +28,21 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh)
 #endif
 
 #ifdef arch_trigger_all_cpu_backtrace
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-static cpumask_t printtrace_mask;
-
-#define NMI_BUF_SIZE		4096
-
-struct nmi_seq_buf {
-	unsigned char		buffer[NMI_BUF_SIZE];
-	struct seq_buf		seq;
-};
-
-/* Safe printing in NMI context */
-static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
-
-/* "in progress" flag of arch_trigger_all_cpu_backtrace */
-static unsigned long backtrace_flag;
-
-static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void nmi_raise_cpu_backtrace(cpumask_t *mask)
 {
-	const char *buf = s->buffer + start;
-
-	printk("%.*s", (end - start) + 1, buf);
+	apic->send_IPI_mask(mask, NMI_VECTOR);
 }
 
 void arch_trigger_all_cpu_backtrace(bool include_self)
 {
-	struct nmi_seq_buf *s;
-	int len;
-	int cpu;
-	int i;
-	int this_cpu = get_cpu();
-
-	if (test_and_set_bit(0, &backtrace_flag)) {
-		/*
-		 * If there is already a trigger_all_cpu_backtrace() in progress
-		 * (backtrace_flag == 1), don't output double cpu dump infos.
-		 */
-		put_cpu();
-		return;
-	}
-
-	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
-	if (!include_self)
-		cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
-
-	cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask));
-	/*
-	 * Set up per_cpu seq_buf buffers that the NMIs running on the other
-	 * CPUs will write to.
-	 */
-	for_each_cpu(cpu, to_cpumask(backtrace_mask)) {
-		s = &per_cpu(nmi_print_seq, cpu);
-		seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE);
-	}
-
-	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
-		pr_info("sending NMI to %s CPUs:\n",
-			(include_self ? "all" : "other"));
-		apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR);
-	}
-
-	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
-	for (i = 0; i < 10 * 1000; i++) {
-		if (cpumask_empty(to_cpumask(backtrace_mask)))
-			break;
-		mdelay(1);
-		touch_softlockup_watchdog();
-	}
-
-	/*
-	 * Now that all the NMIs have triggered, we can dump out their
-	 * back traces safely to the console.
-	 */
-	for_each_cpu(cpu, &printtrace_mask) {
-		int last_i = 0;
-
-		s = &per_cpu(nmi_print_seq, cpu);
-		len = seq_buf_used(&s->seq);
-		if (!len)
-			continue;
-
-		/* Print line by line. */
-		for (i = 0; i < len; i++) {
-			if (s->buffer[i] == '\n') {
-				print_seq_line(s, last_i, i);
-				last_i = i + 1;
-			}
-		}
-		/* Check if there was a partial line. */
-		if (last_i < len) {
-			print_seq_line(s, last_i, len - 1);
-			pr_cont("\n");
-		}
-	}
-
-	clear_bit(0, &backtrace_flag);
-	smp_mb__after_atomic();
-	put_cpu();
-}
-
-/*
- * It is not safe to call printk() directly from NMI handlers.
- * It may be fine if the NMI detected a lock up and we have no choice
- * but to do so, but doing a NMI on all other CPUs to get a back trace
- * can be done with a sysrq-l. We don't want that to lock up, which
- * can happen if the NMI interrupts a printk in progress.
- *
- * Instead, we redirect the vprintk() to this nmi_vprintk() that writes
- * the content into a per cpu seq_buf buffer. Then when the NMIs are
- * all done, we can safely dump the contents of the seq_buf to a printk()
- * from a non NMI context.
- */
-static int nmi_vprintk(const char *fmt, va_list args)
-{
-	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
-	unsigned int len = seq_buf_used(&s->seq);
-
-	seq_buf_vprintf(&s->seq, fmt, args);
-	return seq_buf_used(&s->seq) - len;
+	nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace);
 }
 
 static int
 arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	int cpu;
-
-	cpu = smp_processor_id();
-
-	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		printk_func_t printk_func_save = this_cpu_read(printk_func);
-
-		/* Replace printk to write into the NMI seq */
-		this_cpu_write(printk_func, nmi_vprintk);
-		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
-		show_regs(regs);
-		this_cpu_write(printk_func, printk_func_save);
-
-		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+	if (nmi_cpu_backtrace(regs))
 		return NMI_HANDLED;
-	}
 
 	return NMI_DONE;
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 845dc0df2002..38a76f826530 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
 	 */
 	if (irq < nr_legacy_irqs() && data->count == 1) {
 		if (info->ioapic_trigger != data->trigger)
-			mp_register_handler(irq, data->trigger);
+			mp_register_handler(irq, info->ioapic_trigger);
 		data->entry.trigger = data->trigger = info->ioapic_trigger;
 		data->entry.polarity = data->polarity = info->ioapic_polarity;
 	}
@@ -2541,7 +2541,7 @@ void __init setup_ioapic_dest(void)
 		 * Honour affinities which have been set in early boot
 		 */
 		if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
-			mask = idata->affinity;
+			mask = irq_data_get_affinity_mask(idata);
 		else
 			mask = apic->target_cpus();
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 1a9d735e09c6..5f1feb6854af 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -264,7 +264,7 @@ static inline int hpet_dev_id(struct irq_domain *domain)
 
 static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	hpet_msi_write(data->handler_data, msg);
+	hpet_msi_write(irq_data_get_irq_handler_data(data), msg);
 }
 
 static struct irq_chip hpet_msi_controller = {
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index bda488680dbc..7694ae6c1199 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -111,7 +111,6 @@ static struct apic apic_default = {
 	.send_IPI_all			= default_send_IPI_all,
 	.send_IPI_self			= default_send_IPI_self,
 
-	.wait_for_init_deassert		= true,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
 	.read				= native_apic_mem_read,
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 28eba2d38b15..1bbd0fe2c806 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -169,8 +169,7 @@ next:
 			goto next;
 
 		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
-			if (per_cpu(vector_irq, new_cpu)[vector] >
-			    VECTOR_UNDEFINED)
+			if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
 				goto next;
 		}
 		/* Found one! */
@@ -182,7 +181,7 @@ next:
 			   cpumask_intersects(d->old_domain, cpu_online_mask);
 		}
 		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
-			per_cpu(vector_irq, new_cpu)[vector] = irq;
+			per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
 		d->cfg.vector = vector;
 		cpumask_copy(d->domain, vector_cpumask);
 		err = 0;
@@ -224,15 +223,16 @@ static int assign_irq_vector_policy(int irq, int node,
 
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
-	int cpu, vector;
+	struct irq_desc *desc;
 	unsigned long flags;
+	int cpu, vector;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
 	BUG_ON(!data->cfg.vector);
 
 	vector = data->cfg.vector;
 	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
-		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 
 	data->cfg.vector = 0;
 	cpumask_clear(data->domain);
@@ -242,12 +242,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 		return;
 	}
 
+	desc = irq_to_desc(irq);
 	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 		     vector++) {
-			if (per_cpu(vector_irq, cpu)[vector] != irq)
+			if (per_cpu(vector_irq, cpu)[vector] != desc)
 				continue;
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 			break;
 		}
 	}
@@ -296,7 +297,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	struct irq_alloc_info *info = arg;
 	struct apic_chip_data *data;
 	struct irq_data *irq_data;
-	int i, err;
+	int i, err, node;
 
 	if (disable_apic)
 		return -ENXIO;
@@ -308,12 +309,13 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		BUG_ON(!irq_data);
+		node = irq_data_get_node(irq_data);
 #ifdef	CONFIG_X86_IO_APIC
 		if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
 			data = legacy_irq_data[virq + i];
 		else
 #endif
-			data = alloc_apic_chip_data(irq_data->node);
+			data = alloc_apic_chip_data(node);
 		if (!data) {
 			err = -ENOMEM;
 			goto error;
@@ -322,8 +324,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
-		err = assign_irq_vector_policy(virq, irq_data->node, data,
-					       info);
+		err = assign_irq_vector_policy(virq + i, node, data, info);
 		if (err)
 			goto error;
 	}
@@ -403,49 +404,43 @@ int __init arch_early_irq_init(void)
 	return arch_early_ioapic_init();
 }
 
+/* Initialize vector_irq on a new cpu */
 static void __setup_vector_irq(int cpu)
 {
-	/* Initialize vector_irq on a new cpu */
-	int irq, vector;
 	struct apic_chip_data *data;
+	struct irq_desc *desc;
+	int irq, vector;
 
-	/*
-	 * vector_lock will make sure that we don't run into irq vector
-	 * assignments that might be happening on another cpu in parallel,
-	 * while we setup our initial vector to irq mappings.
-	 */
-	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
-	for_each_active_irq(irq) {
-		data = apic_chip_data(irq_get_irq_data(irq));
-		if (!data)
-			continue;
+	for_each_irq_desc(irq, desc) {
+		struct irq_data *idata = irq_desc_get_irq_data(desc);
 
-		if (!cpumask_test_cpu(cpu, data->domain))
+		data = apic_chip_data(idata);
+		if (!data || !cpumask_test_cpu(cpu, data->domain))
 			continue;
 		vector = data->cfg.vector;
-		per_cpu(vector_irq, cpu)[vector] = irq;
+		per_cpu(vector_irq, cpu)[vector] = desc;
 	}
 	/* Mark the free vectors */
 	for (vector = 0; vector < NR_VECTORS; ++vector) {
-		irq = per_cpu(vector_irq, cpu)[vector];
-		if (irq <= VECTOR_UNDEFINED)
+		desc = per_cpu(vector_irq, cpu)[vector];
+		if (IS_ERR_OR_NULL(desc))
 			continue;
 
-		data = apic_chip_data(irq_get_irq_data(irq));
+		data = apic_chip_data(irq_desc_get_irq_data(desc));
 		if (!cpumask_test_cpu(cpu, data->domain))
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 	}
-	raw_spin_unlock(&vector_lock);
 }
 
 /*
- * Setup the vector to irq mappings.
+ * Setup the vector to irq mappings. Must be called with vector_lock held.
  */
 void setup_vector_irq(int cpu)
 {
 	int irq;
 
+	lockdep_assert_held(&vector_lock);
 	/*
 	 * On most of the platforms, legacy PIC delivers the interrupts on the
 	 * boot cpu. But there are certain platforms where PIC interrupts are
@@ -454,7 +449,7 @@ void setup_vector_irq(int cpu)
 	 * legacy vector to irq mapping:
 	 */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++)
-		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
+		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq);
 
 	__setup_vector_irq(cpu);
 }
@@ -496,7 +491,8 @@ static int apic_set_affinity(struct irq_data *irq_data,
 	if (err) {
 		struct irq_data *top = irq_get_irq_data(irq);
 
-		if (assign_irq_vector(irq, data, top->affinity))
+		if (assign_irq_vector(irq, data,
+				      irq_data_get_affinity_mask(top)))
 			pr_err("Failed to recover vector for irq %d\n", irq);
 		return err;
 	}
@@ -544,27 +540,30 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 
 	entering_ack_irq();
 
+	/* Prevent vectors vanishing under us */
+	raw_spin_lock(&vector_lock);
+
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		int irq;
-		unsigned int irr;
-		struct irq_desc *desc;
 		struct apic_chip_data *data;
+		struct irq_desc *desc;
+		unsigned int irr;
 
-		irq = __this_cpu_read(vector_irq[vector]);
-
-		if (irq <= VECTOR_UNDEFINED)
+	retry:
+		desc = __this_cpu_read(vector_irq[vector]);
+		if (IS_ERR_OR_NULL(desc))
 			continue;
 
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
+		if (!raw_spin_trylock(&desc->lock)) {
+			raw_spin_unlock(&vector_lock);
+			cpu_relax();
+			raw_spin_lock(&vector_lock);
+			goto retry;
+		}
 
-		data = apic_chip_data(&desc->irq_data);
+		data = apic_chip_data(irq_desc_get_irq_data(desc));
 		if (!data)
-			continue;
-
-		raw_spin_lock(&desc->lock);
+			goto unlock;
 
 		/*
 		 * Check if the irq migration is in progress. If so, we
@@ -589,11 +588,13 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
 			goto unlock;
 		}
-		__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
 
+	raw_spin_unlock(&vector_lock);
+
 	exiting_irq();
 }
 
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index ab3219b3fbda..cc8311c4d298 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -182,7 +182,7 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block __refdata x2apic_cpu_notifier = {
+static struct notifier_block x2apic_cpu_notifier = {
 	.notifier_call = update_clusterinfo,
 };
 
@@ -272,7 +272,6 @@ static struct apic apic_x2apic_cluster = {
 	.send_IPI_all			= x2apic_send_IPI_all,
 	.send_IPI_self			= x2apic_send_IPI_self,
 
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= NULL,
 
 	.read				= native_apic_msr_read,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 3ffd925655e0..662e9150ea6f 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -128,7 +128,6 @@ static struct apic apic_x2apic_phys = {
 	.send_IPI_all			= x2apic_send_IPI_all,
 	.send_IPI_self			= x2apic_send_IPI_self,
 
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= NULL,
 
 	.read				= native_apic_msr_read,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index c8d92950bc04..4a139465f1d4 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -248,7 +248,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 	    APIC_DM_STARTUP;
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 
-	atomic_set(&init_deasserted, 1);
 	return 0;
 }
 
@@ -414,7 +413,6 @@ static struct apic __refdata apic_x2apic_uv_x = {
 	.send_IPI_self			= uv_send_IPI_self,
 
 	.wakeup_secondary_cpu		= uv_wakeup_secondary,
-	.wait_for_init_deassert		= false,
 	.inquire_remote_apic		= NULL,
 
 	.read				= native_apic_msr_read,
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 927ec9235947..052c9c3026cc 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -919,7 +919,7 @@ recalc:
 	} else if (jiffies_since_last_check > idle_period) {
 		unsigned int idle_percentage;
 
-		idle_percentage = stime - last_stime;
+		idle_percentage = cputime_to_jiffies(stime - last_stime);
 		idle_percentage *= 100;
 		idle_percentage /= jiffies_since_last_check;
 		use_apm_idle = (idle_percentage > idle_threshold);
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 58118e207a69..145863d4d343 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
@@ -163,6 +163,5 @@ static int start_periodic_check_for_corruption(void)
 	schedule_delayed_work(&bios_check_work, 0);
 	return 0;
 }
-
-module_init(start_periodic_check_for_corruption);
+device_initcall(start_periodic_check_for_corruption);
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 9bff68798836..4eb065c6bed2 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -46,6 +46,8 @@ obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= perf_event_intel_uncore.o \
 					   perf_event_intel_uncore_snb.o \
 					   perf_event_intel_uncore_snbep.o \
 					   perf_event_intel_uncore_nhmex.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_msr.o
+obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_msr.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index dd3a4baffe50..4a70fc6d400a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -11,6 +11,7 @@
 #include <asm/cpu.h>
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
+#include <asm/delay.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -114,7 +115,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		const int K6_BUG_LOOP = 1000000;
 		int n;
 		void (*f_vide)(void);
-		unsigned long d, d2;
+		u64 d, d2;
 
 		printk(KERN_INFO "AMD K6 stepping B detected - ");
 
@@ -125,10 +126,10 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 
 		n = K6_BUG_LOOP;
 		f_vide = vide;
-		rdtscl(d);
+		d = rdtsc();
 		while (n--)
 			f_vide();
-		rdtscl(d2);
+		d2 = rdtsc();
 		d = d2-d;
 
 		if (d > 20*K6_BUG_LOOP)
@@ -506,6 +507,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		/* A random value per boot for bit slice [12:upper_bit) */
 		va_align.bits = get_random_int() & va_align.mask;
 	}
+
+	if (cpu_has(c, X86_FEATURE_MWAITX))
+		use_mwaitx_delay();
 }
 
 static void early_init_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 922c5e0cea4c..07ce52c22ec8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -13,6 +13,7 @@
 #include <linux/kgdb.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/stackprotector.h>
 #include <asm/perf_event.h>
@@ -1185,10 +1186,10 @@ void syscall_init(void)
 	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
 	 */
 	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
-	wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
+	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
-	wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
+	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
 	/*
 	 * This only works on Intel CPUs.
 	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1199,7 +1200,7 @@ void syscall_init(void)
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
-	wrmsrl(MSR_CSTAR, ignore_sysret);
+	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
@@ -1410,7 +1411,7 @@ void cpu_init(void)
 	load_sp0(t, &current->thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
@@ -1459,7 +1460,7 @@ void cpu_init(void)
 	load_sp0(t, thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
 
@@ -1488,3 +1489,20 @@ inline bool __static_cpu_has_safe(u16 bit)
 	return boot_cpu_has(bit);
 }
 EXPORT_SYMBOL_GPL(__static_cpu_has_safe);
+
+static void bsp_resume(void)
+{
+	if (this_cpu->c_bsp_resume)
+		this_cpu->c_bsp_resume(&boot_cpu_data);
+}
+
+static struct syscore_ops cpu_syscore_ops = {
+	.resume		= bsp_resume,
+};
+
+static int __init init_cpu_syscore(void)
+{
+	register_syscore_ops(&cpu_syscore_ops);
+	return 0;
+}
+core_initcall(init_cpu_syscore);
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index c37dc37e8317..2584265d4745 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -13,6 +13,7 @@ struct cpu_dev {
 	void		(*c_init)(struct cpuinfo_x86 *);
 	void		(*c_identify)(struct cpuinfo_x86 *);
 	void		(*c_detect_tlb)(struct cpuinfo_x86 *);
+	void		(*c_bsp_resume)(struct cpuinfo_x86 *);
 	int		c_x86_vendor;
 #ifdef CONFIG_X86_32
 	/* Optional vendor specific routine to obtain the cache size. */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 50163fa9034f..98a13db5f4be 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -371,6 +371,36 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_intel_energy_perf(struct cpuinfo_x86 *c)
+{
+	u64 epb;
+
+	/*
+	 * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized.
+	 * (x86_energy_perf_policy(8) is available to change it at run-time.)
+	 */
+	if (!cpu_has(c, X86_FEATURE_EPB))
+		return;
+
+	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
+		return;
+
+	pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+	pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
+	epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
+	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+}
+
+static void intel_bsp_resume(struct cpuinfo_x86 *c)
+{
+	/*
+	 * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume,
+	 * so reinitialize it properly like during bootup:
+	 */
+	init_intel_energy_perf(c);
+}
+
 static void init_intel(struct cpuinfo_x86 *c)
 {
 	unsigned int l2 = 0;
@@ -478,21 +508,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_VMX))
 		detect_vmx_virtcap(c);
 
-	/*
-	 * Initialize MSR_IA32_ENERGY_PERF_BIAS if BIOS did not.
-	 * x86_energy_perf_policy(8) is available to change it at run-time
-	 */
-	if (cpu_has(c, X86_FEATURE_EPB)) {
-		u64 epb;
-
-		rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-		if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) {
-			pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
-			pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
-			epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
-			wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-		}
-	}
+	init_intel_energy_perf(c);
 }
 
 #ifdef CONFIG_X86_32
@@ -747,6 +763,7 @@ static const struct cpu_dev intel_cpu_dev = {
 	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
 	.c_init		= init_intel,
+	.c_bsp_resume	= intel_bsp_resume,
 	.c_x86_vendor	= X86_VENDOR_INTEL,
 };
 
diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/kernel/cpu/intel_pt.h
index 1c338b0eba05..336878a5d205 100644
--- a/arch/x86/kernel/cpu/intel_pt.h
+++ b/arch/x86/kernel/cpu/intel_pt.h
@@ -25,32 +25,11 @@
  */
 #define TOPA_PMI_MARGIN 512
 
-/*
- * Table of Physical Addresses bits
- */
-enum topa_sz {
-	TOPA_4K	= 0,
-	TOPA_8K,
-	TOPA_16K,
-	TOPA_32K,
-	TOPA_64K,
-	TOPA_128K,
-	TOPA_256K,
-	TOPA_512K,
-	TOPA_1MB,
-	TOPA_2MB,
-	TOPA_4MB,
-	TOPA_8MB,
-	TOPA_16MB,
-	TOPA_32MB,
-	TOPA_64MB,
-	TOPA_128MB,
-	TOPA_SZ_END,
-};
+#define TOPA_SHIFT 12
 
-static inline unsigned int sizes(enum topa_sz tsz)
+static inline unsigned int sizes(unsigned int tsz)
 {
-	return 1 << (tsz + 12);
+	return 1 << (tsz + TOPA_SHIFT);
 };
 
 struct topa_entry {
@@ -66,20 +45,26 @@ struct topa_entry {
 	u64	rsvd4	: 16;
 };
 
-#define TOPA_SHIFT 12
-#define PT_CPUID_LEAVES 2
+#define PT_CPUID_LEAVES		2
+#define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
 
 enum pt_capabilities {
 	PT_CAP_max_subleaf = 0,
 	PT_CAP_cr3_filtering,
+	PT_CAP_psb_cyc,
+	PT_CAP_mtc,
 	PT_CAP_topa_output,
 	PT_CAP_topa_multiple_entries,
+	PT_CAP_single_range_output,
 	PT_CAP_payloads_lip,
+	PT_CAP_mtc_periods,
+	PT_CAP_cycle_thresholds,
+	PT_CAP_psb_periods,
 };
 
 struct pt_pmu {
 	struct pmu		pmu;
-	u32			caps[4 * PT_CPUID_LEAVES];
+	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index bb34b03af252..a3311c886194 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -1,4 +1,4 @@
-obj-y				=  mce.o mce-severity.o
+obj-y				=  mce.o mce-severity.o mce-genpool.o
 
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
 obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index a1aef9533154..34c89a3e8260 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -57,7 +57,6 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 
 	m.addr = mem_err->physical_addr;
 	mce_log(&m);
-	mce_notify_irq();
 }
 EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
new file mode 100644
index 000000000000..0a850100c594
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -0,0 +1,99 @@
+/*
+ * MCE event pool management in MCE context
+ *
+ * Copyright (C) 2015 Intel Corp.
+ * Author: Chen, Gong <gong.chen@linux.intel.com>
+ *
+ * This file is licensed under GPLv2.
+ */
+#include <linux/smp.h>
+#include <linux/mm.h>
+#include <linux/genalloc.h>
+#include <linux/llist.h>
+#include "mce-internal.h"
+
+/*
+ * printk() is not safe in MCE context. This is a lock-less memory allocator
+ * used to save error information organized in a lock-less list.
+ *
+ * This memory pool is only to be used to save MCE records in MCE context.
+ * MCE events are rare, so a fixed size memory pool should be enough. Use
+ * 2 pages to save MCE events for now (~80 MCE records at most).
+ */
+#define MCE_POOLSZ	(2 * PAGE_SIZE)
+
+static struct gen_pool *mce_evt_pool;
+static LLIST_HEAD(mce_event_llist);
+static char gen_pool_buf[MCE_POOLSZ];
+
+void mce_gen_pool_process(void)
+{
+	struct llist_node *head;
+	struct mce_evt_llist *node;
+	struct mce *mce;
+
+	head = llist_del_all(&mce_event_llist);
+	if (!head)
+		return;
+
+	head = llist_reverse_order(head);
+	llist_for_each_entry(node, head, llnode) {
+		mce = &node->mce;
+		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
+	}
+}
+
+bool mce_gen_pool_empty(void)
+{
+	return llist_empty(&mce_event_llist);
+}
+
+int mce_gen_pool_add(struct mce *mce)
+{
+	struct mce_evt_llist *node;
+
+	if (!mce_evt_pool)
+		return -EINVAL;
+
+	node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node));
+	if (!node) {
+		pr_warn_ratelimited("MCE records pool full!\n");
+		return -ENOMEM;
+	}
+
+	memcpy(&node->mce, mce, sizeof(*mce));
+	llist_add(&node->llnode, &mce_event_llist);
+
+	return 0;
+}
+
+static int mce_gen_pool_create(void)
+{
+	struct gen_pool *tmpp;
+	int ret = -ENOMEM;
+
+	tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
+	if (!tmpp)
+		goto out;
+
+	ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+	if (ret) {
+		gen_pool_destroy(tmpp);
+		goto out;
+	}
+
+	mce_evt_pool = tmpp;
+
+out:
+	return ret;
+}
+
+int mce_gen_pool_init(void)
+{
+	/* Just init mce_gen_pool once. */
+	if (mce_evt_pool)
+		return 0;
+
+	return mce_gen_pool_create();
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index fe32074b865b..547720efd923 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -13,6 +13,8 @@ enum severity_level {
 	MCE_PANIC_SEVERITY,
 };
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
 
@@ -24,6 +26,16 @@ struct mce_bank {
 	char			attrname[ATTR_LEN];	/* attribute name */
 };
 
+struct mce_evt_llist {
+	struct llist_node llnode;
+	struct mce mce;
+};
+
+void mce_gen_pool_process(void);
+bool mce_gen_pool_empty(void);
+int mce_gen_pool_add(struct mce *mce);
+int mce_gen_pool_init(void);
+
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
@@ -67,3 +79,5 @@ static inline int apei_clear_mce(u64 record_id)
 	return -EINVAL;
 }
 #endif
+
+void mce_inject_log(struct mce *m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index df919ff103c3..9d014b82a124 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -52,11 +52,11 @@
 
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
-#define rcu_dereference_check_mce(p) \
+#define mce_log_get_idx_check(p) \
 ({ \
-	rcu_lockdep_assert(rcu_read_lock_sched_held() || \
-			   lockdep_is_held(&mce_chrdev_read_mutex), \
-			   "suspicious rcu_dereference_check_mce() usage"); \
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
+			 !lockdep_is_held(&mce_chrdev_read_mutex), \
+			 "suspicious mce_log_get_idx_check() usage"); \
 	smp_load_acquire(&(p)); \
 })
 
@@ -110,22 +110,24 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
  */
 mce_banks_t mce_banks_ce_disabled;
 
-static DEFINE_PER_CPU(struct work_struct, mce_work);
+static struct work_struct mce_work;
+static struct irq_work mce_irq_work;
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
+static int mce_usable_address(struct mce *m);
 
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
  */
-static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	rdtscll(m->tsc);
+	m->tsc = rdtsc();
 	/* We hope get_seconds stays lockless */
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -157,12 +159,13 @@ void mce_log(struct mce *mce)
 	/* Emit the trace record: */
 	trace_mce_record(mce);
 
-	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+	if (!mce_gen_pool_add(mce))
+		irq_work_queue(&mce_irq_work);
 
 	mce->finished = 0;
 	wmb();
 	for (;;) {
-		entry = rcu_dereference_check_mce(mcelog.next);
+		entry = mce_log_get_idx_check(mcelog.next);
 		for (;;) {
 
 			/*
@@ -196,48 +199,23 @@ void mce_log(struct mce *mce)
 	set_bit(0, &mce_need_notify);
 }
 
-static void drain_mcelog_buffer(void)
+void mce_inject_log(struct mce *m)
 {
-	unsigned int next, i, prev = 0;
-
-	next = ACCESS_ONCE(mcelog.next);
-
-	do {
-		struct mce *m;
-
-		/* drain what was logged during boot */
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			unsigned retries = 1;
-
-			m = &mcelog.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2*retries))
-					retries++;
-
-				cpu_relax();
-
-				if (!m->finished && retries >= 4) {
-					pr_err("skipping error being logged currently!\n");
-					break;
-				}
-			}
-			smp_rmb();
-			atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
-		}
-
-		memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m));
-		prev = next;
-		next = cmpxchg(&mcelog.next, prev, 0);
-	} while (next != prev);
+	mutex_lock(&mce_chrdev_read_mutex);
+	mce_log(m);
+	mutex_unlock(&mce_chrdev_read_mutex);
 }
+EXPORT_SYMBOL_GPL(mce_inject_log);
 
+static struct notifier_block mce_srao_nb;
 
 void mce_register_decode_chain(struct notifier_block *nb)
 {
+	/* Ensure SRAO notifier has the highest priority in the decode chain. */
+	if (nb != &mce_srao_nb && nb->priority == INT_MAX)
+		nb->priority -= 1;
+
 	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
-	drain_mcelog_buffer();
 }
 EXPORT_SYMBOL_GPL(mce_register_decode_chain);
 
@@ -461,61 +439,6 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
 	}
 }
 
-/*
- * Simple lockless ring to communicate PFNs from the exception handler with the
- * process context work function. This is vastly simplified because there's
- * only a single reader and a single writer.
- */
-#define MCE_RING_SIZE 16	/* we use one entry less */
-
-struct mce_ring {
-	unsigned short start;
-	unsigned short end;
-	unsigned long ring[MCE_RING_SIZE];
-};
-static DEFINE_PER_CPU(struct mce_ring, mce_ring);
-
-/* Runs with CPU affinity in workqueue */
-static int mce_ring_empty(void)
-{
-	struct mce_ring *r = this_cpu_ptr(&mce_ring);
-
-	return r->start == r->end;
-}
-
-static int mce_ring_get(unsigned long *pfn)
-{
-	struct mce_ring *r;
-	int ret = 0;
-
-	*pfn = 0;
-	get_cpu();
-	r = this_cpu_ptr(&mce_ring);
-	if (r->start == r->end)
-		goto out;
-	*pfn = r->ring[r->start];
-	r->start = (r->start + 1) % MCE_RING_SIZE;
-	ret = 1;
-out:
-	put_cpu();
-	return ret;
-}
-
-/* Always runs in MCE context with preempt off */
-static int mce_ring_add(unsigned long pfn)
-{
-	struct mce_ring *r = this_cpu_ptr(&mce_ring);
-	unsigned next;
-
-	next = (r->end + 1) % MCE_RING_SIZE;
-	if (next == r->start)
-		return -1;
-	r->ring[r->end] = pfn;
-	wmb();
-	r->end = next;
-	return 0;
-}
-
 int mce_available(struct cpuinfo_x86 *c)
 {
 	if (mca_cfg.disabled)
@@ -525,12 +448,10 @@ int mce_available(struct cpuinfo_x86 *c)
 
 static void mce_schedule_work(void)
 {
-	if (!mce_ring_empty())
-		schedule_work(this_cpu_ptr(&mce_work));
+	if (!mce_gen_pool_empty() && keventd_up())
+		schedule_work(&mce_work);
 }
 
-static DEFINE_PER_CPU(struct irq_work, mce_irq_work);
-
 static void mce_irq_work_cb(struct irq_work *entry)
 {
 	mce_notify_irq();
@@ -551,8 +472,29 @@ static void mce_report_event(struct pt_regs *regs)
 		return;
 	}
 
-	irq_work_queue(this_cpu_ptr(&mce_irq_work));
+	irq_work_queue(&mce_irq_work);
+}
+
+static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	unsigned long pfn;
+
+	if (!mce)
+		return NOTIFY_DONE;
+
+	if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) {
+		pfn = mce->addr >> PAGE_SHIFT;
+		memory_failure(pfn, MCE_VECTOR, 0);
+	}
+
+	return NOTIFY_OK;
 }
+static struct notifier_block mce_srao_nb = {
+	.notifier_call	= srao_decode_notifier,
+	.priority = INT_MAX,
+};
 
 /*
  * Read ADDR and MISC registers.
@@ -672,8 +614,11 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		 */
 		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) {
 			if (m.status & MCI_STATUS_ADDRV) {
-				mce_ring_add(m.addr >> PAGE_SHIFT);
-				mce_schedule_work();
+				m.severity = severity;
+				m.usable_addr = mce_usable_address(&m);
+
+				if (!mce_gen_pool_add(&m))
+					mce_schedule_work();
 			}
 		}
 
@@ -1029,7 +974,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 {
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
-	enum ctx_state prev_state;
 	int i;
 	int worst = 0;
 	int severity;
@@ -1055,7 +999,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1143,15 +1087,9 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 		mce_read_aux(&m, i);
 
-		/*
-		 * Action optional error. Queue address for later processing.
-		 * When the ring overflows we just ignore the AO error.
-		 * RED-PEN add some logging mechanism when
-		 * usable_address or mce_add_ring fails.
-		 * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0
-		 */
-		if (severity == MCE_AO_SEVERITY && mce_usable_address(&m))
-			mce_ring_add(m.addr >> PAGE_SHIFT);
+		/* assuming valid severity level != 0 */
+		m.severity = severity;
+		m.usable_addr = mce_usable_address(&m);
 
 		mce_log(&m);
 
@@ -1227,7 +1165,7 @@ out:
 	local_irq_disable();
 	ist_end_non_atomic();
 done:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1247,14 +1185,11 @@ int memory_failure(unsigned long pfn, int vector, int flags)
 /*
  * Action optional processing happens here (picking up
  * from the list of faulting pages that do_machine_check()
- * placed into the "ring").
+ * placed into the genpool).
  */
 static void mce_process_work(struct work_struct *dummy)
 {
-	unsigned long pfn;
-
-	while (mce_ring_get(&pfn))
-		memory_failure(pfn, MCE_VECTOR, 0);
+	mce_gen_pool_process();
 }
 
 #ifdef CONFIG_X86_MCE_INTEL
@@ -1678,6 +1613,17 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 	}
 }
 
+static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_vendor) {
+	case X86_VENDOR_INTEL:
+		mce_intel_feature_clear(c);
+		break;
+	default:
+		break;
+	}
+}
+
 static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 {
 	unsigned long iv = check_interval * HZ;
@@ -1731,13 +1677,36 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 		return;
 	}
 
+	if (mce_gen_pool_init()) {
+		mca_cfg.disabled = true;
+		pr_emerg("Couldn't allocate MCE records pool!\n");
+		return;
+	}
+
 	machine_check_vector = do_machine_check;
 
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_timer();
-	INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
-	init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
+}
+
+/*
+ * Called for each booted CPU to clear some machine checks opt-ins
+ */
+void mcheck_cpu_clear(struct cpuinfo_x86 *c)
+{
+	if (mca_cfg.disabled)
+		return;
+
+	if (!mce_available(c))
+		return;
+
+	/*
+	 * Possibly to clear general settings generic to x86
+	 * __mcheck_cpu_clear_generic(c);
+	 */
+	__mcheck_cpu_clear_vendor(c);
+
 }
 
 /*
@@ -1784,7 +1753,7 @@ static void collect_tscs(void *data)
 {
 	unsigned long *cpu_tsc = (unsigned long *)data;
 
-	rdtscll(cpu_tsc[smp_processor_id()]);
+	cpu_tsc[smp_processor_id()] = rdtsc();
 }
 
 static int mce_apei_read_done;
@@ -1850,7 +1819,7 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 			goto out;
 	}
 
-	next = rcu_dereference_check_mce(mcelog.next);
+	next = mce_log_get_idx_check(mcelog.next);
 
 	/* Only supports full reads right now */
 	err = -EINVAL;
@@ -2056,8 +2025,12 @@ __setup("mce", mcheck_enable);
 int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
+	mce_register_decode_chain(&mce_srao_nb);
 	mcheck_vendor_init_severity();
 
+	INIT_WORK(&mce_work, mce_process_work);
+	init_irq_work(&mce_irq_work, mce_irq_work_cb);
+
 	return 0;
 }
 
@@ -2591,5 +2564,20 @@ static int __init mcheck_debugfs_init(void)
 
 	return 0;
 }
-late_initcall(mcheck_debugfs_init);
+#else
+static int __init mcheck_debugfs_init(void) { return -EINVAL; }
 #endif
+
+static int __init mcheck_late_init(void)
+{
+	mcheck_debugfs_init();
+
+	/*
+	 * Flush out everything that has been logged during early boot, now that
+	 * everything has been initialized (workqueues, decoders, ...).
+	 */
+	mce_schedule_work();
+
+	return 0;
+}
+late_initcall(mcheck_late_init);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 844f56c5616d..1e8bb6c94f14 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -146,6 +146,27 @@ void mce_intel_hcpu_update(unsigned long cpu)
 	per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
 }
 
+static void cmci_toggle_interrupt_mode(bool on)
+{
+	unsigned long flags, *owned;
+	int bank;
+	u64 val;
+
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	owned = this_cpu_ptr(mce_banks_owned);
+	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+
+		if (on)
+			val |= MCI_CTL2_CMCI_EN;
+		else
+			val &= ~MCI_CTL2_CMCI_EN;
+
+		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	}
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
 unsigned long cmci_intel_adjust_timer(unsigned long interval)
 {
 	if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
@@ -175,7 +196,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 		 */
 		if (!atomic_read(&cmci_storm_on_cpus)) {
 			__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
-			cmci_reenable();
+			cmci_toggle_interrupt_mode(true);
 			cmci_recheck();
 		}
 		return CMCI_POLL_INTERVAL;
@@ -186,22 +207,6 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 	}
 }
 
-static void cmci_storm_disable_banks(void)
-{
-	unsigned long flags, *owned;
-	int bank;
-	u64 val;
-
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = this_cpu_ptr(mce_banks_owned);
-	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
-		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
-		val &= ~MCI_CTL2_CMCI_EN;
-		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	}
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
-
 static bool cmci_storm_detect(void)
 {
 	unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
@@ -223,7 +228,7 @@ static bool cmci_storm_detect(void)
 	if (cnt <= CMCI_STORM_THRESHOLD)
 		return false;
 
-	cmci_storm_disable_banks();
+	cmci_toggle_interrupt_mode(false);
 	__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
 	r = atomic_add_return(1, &cmci_storm_on_cpus);
 	mce_timer_kick(CMCI_STORM_INTERVAL);
@@ -246,7 +251,6 @@ static void intel_threshold_interrupt(void)
 		return;
 
 	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
-	mce_notify_irq();
 }
 
 /*
@@ -435,7 +439,7 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
-void intel_init_lmce(void)
+static void intel_init_lmce(void)
 {
 	u64 val;
 
@@ -448,9 +452,26 @@ void intel_init_lmce(void)
 		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
+static void intel_clear_lmce(void)
+{
+	u64 val;
+
+	if (!lmce_supported())
+		return;
+
+	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	val &= ~MCG_EXT_CTL_LMCE_EN;
+	wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
+}
+
 void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 	intel_init_cmci();
 	intel_init_lmce();
 }
+
+void mce_intel_feature_clear(struct cpuinfo_x86 *c)
+{
+	intel_clear_lmce();
+}
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 737b0ad4e61a..12402e10aeff 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly;
 /* Machine check handler for Pentium class Intel CPUs: */
 static void pentium_machine_check(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
 	u32 loaddr, hi, lotype;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
@@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 44f138296fbe..01dd8702880b 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -15,12 +15,12 @@
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 
 /* Set up machine check reporting on the Winchip C6 series */
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 6236a54a63f4..9e3f3c7dd5d7 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -377,17 +377,16 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif)
 	return err;
 }
 
-static int mc_device_remove(struct device *dev, struct subsys_interface *sif)
+static void mc_device_remove(struct device *dev, struct subsys_interface *sif)
 {
 	int cpu = dev->id;
 
 	if (!cpu_online(cpu))
-		return 0;
+		return;
 
 	pr_debug("CPU%d removed\n", cpu);
 	microcode_fini_cpu(cpu);
 	sysfs_remove_group(&dev->kobj, &mc_attr_group);
-	return 0;
 }
 
 static struct subsys_interface mc_cpu_interface = {
@@ -460,7 +459,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __refdata mc_cpu_notifier = {
+static struct notifier_block mc_cpu_notifier = {
 	.notifier_call	= mc_cpu_callback,
 };
 
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 8187b7247d1c..37ea89c11520 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -390,7 +390,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 }
 
 #ifdef DEBUG
-static void __ref show_saved_mc(void)
+static void show_saved_mc(void)
 {
 	int i, j;
 	unsigned int sig, pf, rev, total_size, data_size, date;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index aad4bd84b475..381c8b9b3a33 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -18,6 +18,7 @@
 #include <linux/efi.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/kexec.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>
@@ -28,10 +29,14 @@
 #include <asm/i8259.h>
 #include <asm/apic.h>
 #include <asm/timer.h>
+#include <asm/reboot.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
+static void (*hv_kexec_handler)(void);
+static void (*hv_crash_handler)(struct pt_regs *regs);
+
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
 
@@ -67,8 +72,47 @@ void hv_remove_vmbus_irq(void)
 }
 EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
 EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
+
+void hv_setup_kexec_handler(void (*handler)(void))
+{
+	hv_kexec_handler = handler;
+}
+EXPORT_SYMBOL_GPL(hv_setup_kexec_handler);
+
+void hv_remove_kexec_handler(void)
+{
+	hv_kexec_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_remove_kexec_handler);
+
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs))
+{
+	hv_crash_handler = handler;
+}
+EXPORT_SYMBOL_GPL(hv_setup_crash_handler);
+
+void hv_remove_crash_handler(void)
+{
+	hv_crash_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
 #endif
 
+static void hv_machine_shutdown(void)
+{
+	if (kexec_in_progress && hv_kexec_handler)
+		hv_kexec_handler();
+	native_machine_shutdown();
+}
+
+static void hv_machine_crash_shutdown(struct pt_regs *regs)
+{
+	if (hv_crash_handler)
+		hv_crash_handler(regs);
+	native_machine_crash_shutdown(regs);
+}
+
+
 static uint32_t  __init ms_hyperv_platform(void)
 {
 	u32 eax;
@@ -114,6 +158,7 @@ static void __init ms_hyperv_init_platform(void)
 	 * Extract the features and hints
 	 */
 	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
+	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
 	printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
@@ -141,6 +186,9 @@ static void __init ms_hyperv_init_platform(void)
 	no_timer_check = 1;
 #endif
 
+	machine_ops.shutdown = hv_machine_shutdown;
+	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
+	mark_tsc_unstable("running on Hyper-V");
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index e7ed0d8ebacb..f891b4750f04 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -448,7 +448,6 @@ int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
 	return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
 			     increment);
 }
-EXPORT_SYMBOL(mtrr_add);
 
 /**
  * mtrr_del_page - delete a memory type region
@@ -537,7 +536,6 @@ int mtrr_del(int reg, unsigned long base, unsigned long size)
 		return -EINVAL;
 	return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
 }
-EXPORT_SYMBOL(mtrr_del);
 
 /**
  * arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3658de47900f..66dd3fe99b82 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1551,7 +1551,7 @@ static void __init filter_events(struct attribute **attrs)
 }
 
 /* Merge two pointer arrays */
-static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
+__init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
 {
 	struct attribute **new;
 	int j, i;
@@ -2179,24 +2179,32 @@ static unsigned long get_segment_base(unsigned int segment)
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+		struct ldt_struct *ldt;
+
 		if (idx > LDT_ENTRIES)
 			return 0;
 
-		if (idx > current->active_mm->context.size)
+		/* IRQs are off, so this synchronizes with smp_store_release */
+		ldt = lockless_dereference(current->active_mm->context.ldt);
+		if (!ldt || idx > ldt->size)
 			return 0;
 
-		desc = current->active_mm->context.ldt;
+		desc = &ldt->entries[idx];
+#else
+		return 0;
+#endif
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = raw_cpu_ptr(gdt_page.gdt);
+		desc = raw_cpu_ptr(gdt_page.gdt) + idx;
 	}
 
-	return get_desc_base(desc + idx);
+	return get_desc_base(desc);
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_IA32_EMULATION
 
 #include <asm/compat.h>
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3e7fd27dfe20..5edf6d868fc1 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -165,7 +165,7 @@ struct intel_excl_cntrs {
 	unsigned	core_id;	/* per-core: core id */
 };
 
-#define MAX_LBR_ENTRIES		16
+#define MAX_LBR_ENTRIES		32
 
 enum {
 	X86_PERF_KFREE_SHARED = 0,
@@ -594,6 +594,7 @@ struct x86_pmu {
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	int 		max_pebs_events;
+	unsigned long	free_running_flags;
 
 	/*
 	 * Intel LBR
@@ -624,6 +625,7 @@ struct x86_pmu {
 struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
+	u64 lbr_info[MAX_LBR_ENTRIES];
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };
@@ -793,6 +795,8 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
 ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
 ssize_t intel_event_sysfs_show(char *page, u64 config);
 
+struct attribute **merge_attr(struct attribute **a, struct attribute **b);
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
@@ -808,20 +812,6 @@ static inline int amd_pmu_init(void)
 
 #ifdef CONFIG_CPU_SUP_INTEL
 
-static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
-{
-	/* user explicitly requested branch sampling */
-	if (has_branch_stack(event))
-		return true;
-
-	/* implicit branch sampling to correct PEBS skid */
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 &&
-	    x86_pmu.intel_cap.pebs_format < 2)
-		return true;
-
-	return false;
-}
-
 static inline bool intel_pmu_has_bts(struct perf_event *event)
 {
 	if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
@@ -873,6 +863,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[];
 
 extern struct event_constraint intel_hsw_pebs_event_constraints[];
 
+extern struct event_constraint intel_skl_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_enable(struct perf_event *event);
@@ -911,6 +903,8 @@ void intel_pmu_lbr_init_snb(void);
 
 void intel_pmu_lbr_init_hsw(void);
 
+void intel_pmu_lbr_init_skl(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
@@ -934,6 +928,7 @@ static inline int is_ht_workaround_enabled(void)
 {
 	return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
 }
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b9826a981fb2..cd9b6d0b10bf 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <linux/watchdog.h>
+#include <linux/nmi.h>
 
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
@@ -177,6 +177,14 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_skl_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+	EVENT_CONSTRAINT_END
+};
+
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
@@ -193,6 +201,13 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	EVENT_EXTRA_END
+};
+
 EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
@@ -244,6 +259,200 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
+/*
+ * Notes on the events:
+ * - data reads do not include code reads (comparable to earlier tables)
+ * - data counts include speculative execution (except L1 write, dtlb, bpu)
+ * - remote node access includes remote memory, remote cache, remote mmio.
+ * - prefetches are not included in the counts.
+ * - icache miss does not include decoded icache
+ */
+
+#define SKL_DEMAND_DATA_RD		BIT_ULL(0)
+#define SKL_DEMAND_RFO			BIT_ULL(1)
+#define SKL_ANY_RESPONSE		BIT_ULL(16)
+#define SKL_SUPPLIER_NONE		BIT_ULL(17)
+#define SKL_L3_MISS_LOCAL_DRAM		BIT_ULL(26)
+#define SKL_L3_MISS_REMOTE_HOP0_DRAM	BIT_ULL(27)
+#define SKL_L3_MISS_REMOTE_HOP1_DRAM	BIT_ULL(28)
+#define SKL_L3_MISS_REMOTE_HOP2P_DRAM	BIT_ULL(29)
+#define SKL_L3_MISS			(SKL_L3_MISS_LOCAL_DRAM| \
+					 SKL_L3_MISS_REMOTE_HOP0_DRAM| \
+					 SKL_L3_MISS_REMOTE_HOP1_DRAM| \
+					 SKL_L3_MISS_REMOTE_HOP2P_DRAM)
+#define SKL_SPL_HIT			BIT_ULL(30)
+#define SKL_SNOOP_NONE			BIT_ULL(31)
+#define SKL_SNOOP_NOT_NEEDED		BIT_ULL(32)
+#define SKL_SNOOP_MISS			BIT_ULL(33)
+#define SKL_SNOOP_HIT_NO_FWD		BIT_ULL(34)
+#define SKL_SNOOP_HIT_WITH_FWD		BIT_ULL(35)
+#define SKL_SNOOP_HITM			BIT_ULL(36)
+#define SKL_SNOOP_NON_DRAM		BIT_ULL(37)
+#define SKL_ANY_SNOOP			(SKL_SPL_HIT|SKL_SNOOP_NONE| \
+					 SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \
+					 SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \
+					 SKL_SNOOP_HITM|SKL_SNOOP_NON_DRAM)
+#define SKL_DEMAND_READ			SKL_DEMAND_DATA_RD
+#define SKL_SNOOP_DRAM			(SKL_SNOOP_NONE| \
+					 SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \
+					 SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \
+					 SKL_SNOOP_HITM|SKL_SPL_HIT)
+#define SKL_DEMAND_WRITE		SKL_DEMAND_RFO
+#define SKL_LLC_ACCESS			SKL_ANY_RESPONSE
+#define SKL_L3_MISS_REMOTE		(SKL_L3_MISS_REMOTE_HOP0_DRAM| \
+					 SKL_L3_MISS_REMOTE_HOP1_DRAM| \
+					 SKL_L3_MISS_REMOTE_HOP2P_DRAM)
+
+static __initconst const u64 skl_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,	/* MEM_INST_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151,	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,	/* MEM_INST_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x283,	/* ICACHE_64B.MISS */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,	/* MEM_INST_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x608,	/* DTLB_LOAD_MISSES.WALK_COMPLETED */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,	/* MEM_INST_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x649,	/* DTLB_STORE_MISSES.WALK_COMPLETED */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2085,	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0xe85,	/* ITLB_MISSES.WALK_COMPLETED */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4,	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5,	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
+static __initconst const u64 skl_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SKL_DEMAND_READ|
+				       SKL_LLC_ACCESS|SKL_ANY_SNOOP,
+		[ C(RESULT_MISS)   ] = SKL_DEMAND_READ|
+				       SKL_L3_MISS|SKL_ANY_SNOOP|
+				       SKL_SUPPLIER_NONE,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE|
+				       SKL_LLC_ACCESS|SKL_ANY_SNOOP,
+		[ C(RESULT_MISS)   ] = SKL_DEMAND_WRITE|
+				       SKL_L3_MISS|SKL_ANY_SNOOP|
+				       SKL_SUPPLIER_NONE,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SKL_DEMAND_READ|
+				       SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM,
+		[ C(RESULT_MISS)   ] = SKL_DEMAND_READ|
+				       SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE|
+				       SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM,
+		[ C(RESULT_MISS)   ] = SKL_DEMAND_WRITE|
+				       SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 #define SNB_DMND_DATA_RD	(1ULL << 0)
 #define SNB_DMND_RFO		(1ULL << 1)
 #define SNB_DMND_IFETCH		(1ULL << 2)
@@ -1114,7 +1323,7 @@ static struct extra_reg intel_slm_extra_regs[] __read_mostly =
 {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x368005ffffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -1594,6 +1803,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	loops = 0;
 again:
+	intel_pmu_lbr_read();
 	intel_pmu_ack_status(status);
 	if (++loops > 100) {
 		static bool warned = false;
@@ -1608,16 +1818,16 @@ again:
 
 	inc_irq_stat(apic_perf_irqs);
 
-	intel_pmu_lbr_read();
 
 	/*
-	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
-	 * and clear the bit.
+	 * Ignore a range of extra bits in status that do not indicate
+	 * overflow by themselves.
 	 */
-	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
-		if (!status)
-			goto done;
-	}
+	status &= ~(GLOBAL_STATUS_COND_CHG |
+		    GLOBAL_STATUS_ASIF |
+		    GLOBAL_STATUS_LBRS_FROZEN);
+	if (!status)
+		goto done;
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -1699,18 +1909,22 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
-static int intel_alt_er(int idx)
+static int intel_alt_er(int idx, u64 config)
 {
+	int alt_idx;
 	if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
 		return idx;
 
 	if (idx == EXTRA_REG_RSP_0)
-		return EXTRA_REG_RSP_1;
+		alt_idx = EXTRA_REG_RSP_1;
 
 	if (idx == EXTRA_REG_RSP_1)
-		return EXTRA_REG_RSP_0;
+		alt_idx = EXTRA_REG_RSP_0;
 
-	return idx;
+	if (config & ~x86_pmu.extra_regs[alt_idx].valid_mask)
+		return idx;
+
+	return alt_idx;
 }
 
 static void intel_fixup_er(struct perf_event *event, int idx)
@@ -1799,7 +2013,7 @@ again:
 		 */
 		c = NULL;
 	} else {
-		idx = intel_alt_er(idx);
+		idx = intel_alt_er(idx, reg->config);
 		if (idx != reg->idx) {
 			raw_spin_unlock_irqrestore(&era->lock, flags);
 			goto again;
@@ -2253,6 +2467,15 @@ static void intel_pebs_aliases_snb(struct perf_event *event)
 	}
 }
 
+static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+{
+	unsigned long flags = x86_pmu.free_running_flags;
+
+	if (event->attr.use_clockid)
+		flags &= ~PERF_SAMPLE_TIME;
+	return flags;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -2263,7 +2486,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (event->attr.precise_ip) {
 		if (!event->attr.freq) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
-			if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+			if (!(event->attr.sample_type &
+			      ~intel_pmu_free_running_flags(event)))
 				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
 		}
 		if (x86_pmu.pebs_aliases)
@@ -2534,7 +2758,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
-			return NOTIFY_BAD;
+			goto err;
 	}
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
@@ -2542,18 +2766,27 @@ static int intel_pmu_cpu_prepare(int cpu)
 
 		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
 		if (!cpuc->constraint_list)
-			return NOTIFY_BAD;
+			goto err_shared_regs;
 
 		cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
-		if (!cpuc->excl_cntrs) {
-			kfree(cpuc->constraint_list);
-			kfree(cpuc->shared_regs);
-			return NOTIFY_BAD;
-		}
+		if (!cpuc->excl_cntrs)
+			goto err_constraint_list;
+
 		cpuc->excl_thread_id = 0;
 	}
 
 	return NOTIFY_OK;
+
+err_constraint_list:
+	kfree(cpuc->constraint_list);
+	cpuc->constraint_list = NULL;
+
+err_shared_regs:
+	kfree(cpuc->shared_regs);
+	cpuc->shared_regs = NULL;
+
+err:
+	return NOTIFY_BAD;
 }
 
 static void intel_pmu_cpu_starting(int cpu)
@@ -2685,6 +2918,8 @@ static __initconst const struct x86_pmu core_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
+	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32-bit width,
 	 * so we install an artificial 1<<31 period regardless of
@@ -2723,6 +2958,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
+	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32 bit width,
 	 * so we install an artificial 1<<31 period regardless of
@@ -3260,6 +3496,29 @@ __init int intel_pmu_init(void)
 		pr_cont("Broadwell events, ");
 		break;
 
+	case 78: /* 14nm Skylake Mobile */
+	case 94: /* 14nm Skylake Desktop */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_skl_event_constraints;
+		x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_skl_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		WARN_ON(!x86_pmu.format_attrs);
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Skylake events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
@@ -3329,7 +3588,7 @@ __init int intel_pmu_init(void)
 	 */
 	if (x86_pmu.extra_regs) {
 		for (er = x86_pmu.extra_regs; er->msr; er++) {
-			er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+			er->extra_msr_access = check_msr(er->msr, 0x11UL);
 			/* Disable LBR select mapping */
 			if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
 				x86_pmu.lbr_sel_map = NULL;
@@ -3368,7 +3627,10 @@ static __init int fixup_ht_bug(void)
 		return 0;
 	}
 
-	watchdog_nmi_disable_all();
+	if (lockup_detector_suspend() != 0) {
+		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
+		return 0;
+	}
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -3376,7 +3638,7 @@ static __init int fixup_ht_bug(void)
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	watchdog_nmi_enable_all();
+	lockup_detector_resume();
 
 	get_online_cpus();
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index 43dd672d788b..54690e885759 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -62,9 +62,6 @@ struct bts_buffer {
 
 struct pmu bts_pmu;
 
-void intel_pmu_enable_bts(u64 config);
-void intel_pmu_disable_bts(void);
-
 static size_t buf_size(struct page *page)
 {
 	return 1 << (PAGE_SHIFT + page_private(page));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 188076161c1b..377e8f8ed391 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -952,6 +952,14 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 		return 0;
 
 	/*
+	 * Getting up-to-date values requires an SMP IPI which is not
+	 * possible if we're being called in interrupt context. Return
+	 * the cached values instead.
+	 */
+	if (unlikely(in_interrupt()))
+		goto out;
+
+	/*
 	 * Notice that we don't perform the reading of an RMID
 	 * atomically, because we can't hold a spin lock across the
 	 * IPIs.
@@ -1247,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu)
 	cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
-static void intel_cqm_cpu_prepare(unsigned int cpu)
+static void intel_cqm_cpu_starting(unsigned int cpu)
 {
 	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1288,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb,
 	unsigned int cpu  = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		intel_cqm_cpu_prepare(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
 		intel_cqm_cpu_exit(cpu);
 		break;
 	case CPU_STARTING:
+		intel_cqm_cpu_starting(cpu);
 		cqm_pick_event_reader(cpu);
 		break;
 	}
@@ -1365,7 +1371,7 @@ static int __init intel_cqm_init(void)
 		goto out;
 
 	for_each_online_cpu(i) {
-		intel_cqm_cpu_prepare(i);
+		intel_cqm_cpu_starting(i);
 		cqm_pick_event_reader(i);
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 71fc40238843..84f236ab96b0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -224,6 +224,19 @@ union hsw_tsx_tuning {
 
 #define PEBS_HSW_TSX_FLAGS	0xff00000000ULL
 
+/* Same as HSW, plus TSC */
+
+struct pebs_record_skl {
+	u64 flags, ip;
+	u64 ax, bx, cx, dx;
+	u64 si, di, bp, sp;
+	u64 r8,  r9,  r10, r11;
+	u64 r12, r13, r14, r15;
+	u64 status, dla, dse, lat;
+	u64 real_ip, tsx_tuning;
+	u64 tsc;
+};
+
 void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -675,6 +688,28 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_skl_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_PLD_CONSTRAINT(0x1cd, 0xf),		      /* MEM_TRANS_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x22d0, 0xf), /* MEM_INST_RETIRED.LOCK_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf),    /* MEM_LOAD_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf),    /* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf),    /* MEM_LOAD_L3_MISS_RETIRED.* */
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -754,6 +789,11 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
+	bool large_pebs = ds->pebs_interrupt_threshold >
+		ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+	if (large_pebs)
+		intel_pmu_drain_pebs_buffer();
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
@@ -762,12 +802,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
-	if (ds->pebs_interrupt_threshold >
-	    ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
-		intel_pmu_drain_pebs_buffer();
-		if (!pebs_is_enabled(cpuc))
-			perf_sched_cb_dec(event->ctx->pmu);
-	}
+	if (large_pebs && !pebs_is_enabled(cpuc))
+		perf_sched_cb_dec(event->ctx->pmu);
 
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -885,7 +921,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	return 0;
 }
 
-static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
+static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
 {
 	if (pebs->tsx_tuning) {
 		union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
@@ -894,7 +930,7 @@ static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
 	return 0;
 }
 
-static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
+static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
 {
 	u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
 
@@ -918,7 +954,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	 * unconditionally access the 'extra' entries.
 	 */
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct pebs_record_hsw *pebs = __pebs;
+	struct pebs_record_skl *pebs = __pebs;
 	u64 sample_type;
 	int fll, fst, dsrc;
 	int fl = event->hw.flags;
@@ -1016,6 +1052,16 @@ static void setup_pebs_sample_data(struct perf_event *event,
 			data->txn = intel_hsw_transaction(pebs);
 	}
 
+	/*
+	 * v3 supplies an accurate time stamp, so we use that
+	 * for the time stamp.
+	 *
+	 * We can only do this for the default trace clock.
+	 */
+	if (x86_pmu.intel_cap.pebs_format >= 3 &&
+		event->attr.use_clockid == 0)
+		data->time = native_sched_clock_from_tsc(pebs->tsc);
+
 	if (has_branch_stack(event))
 		data->br_stack = &cpuc->lbr_stack;
 }
@@ -1142,6 +1188,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
 		struct pebs_record_nhm *p = at;
+		u64 pebs_status;
 
 		/* PEBS v3 has accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
@@ -1152,12 +1199,17 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 		}
 
-		bit = find_first_bit((unsigned long *)&p->status,
+		pebs_status = p->status & cpuc->pebs_enabled;
+		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+		bit = find_first_bit((unsigned long *)&pebs_status,
 					x86_pmu.max_pebs_events);
-		if (bit >= x86_pmu.max_pebs_events)
-			continue;
-		if (!test_bit(bit, cpuc->active_mask))
+		if (WARN(bit >= x86_pmu.max_pebs_events,
+			 "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx",
+			 (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled,
+			 *(unsigned long long *)cpuc->active_mask))
 			continue;
+
 		/*
 		 * The PEBS hardware does not deal well with the situation
 		 * when events happen near to each other and multiple bits
@@ -1172,27 +1224,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * one, and it's not possible to reconstruct all events
 		 * that caused the PEBS record. It's called collision.
 		 * If collision happened, the record will be dropped.
-		 *
 		 */
-		if (p->status != (1 << bit)) {
-			u64 pebs_status;
-
-			/* slow path */
-			pebs_status = p->status & cpuc->pebs_enabled;
-			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
-			if (pebs_status != (1 << bit)) {
-				for_each_set_bit(i, (unsigned long *)&pebs_status,
-						 MAX_PEBS_EVENTS)
-					error[i]++;
-				continue;
-			}
+		if (p->status != (1ULL << bit)) {
+			for_each_set_bit(i, (unsigned long *)&pebs_status,
+					 x86_pmu.max_pebs_events)
+				error[i]++;
+			continue;
 		}
+
 		counts[bit]++;
 	}
 
 	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
+
 		event = cpuc->events[bit];
 		WARN_ON_ONCE(!event);
 		WARN_ON_ONCE(!event->attr.precise_ip);
@@ -1245,6 +1291,14 @@ void __init intel_ds_init(void)
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			break;
 
+		case 3:
+			pr_cont("PEBS fmt3%c, ", pebs_type);
+			x86_pmu.pebs_record_size =
+						sizeof(struct pebs_record_skl);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
+			x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+			break;
+
 		default:
 			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 452a7bd2dedb..b2c9475b7ff2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -13,7 +13,8 @@ enum {
 	LBR_FORMAT_EIP		= 0x02,
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
 	LBR_FORMAT_EIP_FLAGS2	= 0x04,
-	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_EIP_FLAGS2,
+	LBR_FORMAT_INFO		= 0x05,
+	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_INFO,
 };
 
 static enum {
@@ -140,6 +141,13 @@ static void __intel_pmu_lbr_enable(bool pmi)
 	u64 debugctl, lbr_select = 0, orig_debugctl;
 
 	/*
+	 * No need to unfreeze manually, as v4 can do that as part
+	 * of the GLOBAL_STATUS ack.
+	 */
+	if (pmi && x86_pmu.version >= 4)
+		return;
+
+	/*
 	 * No need to reprogram LBR_SELECT in a PMI, as it
 	 * did not change.
 	 */
@@ -186,6 +194,8 @@ static void intel_pmu_lbr_reset_64(void)
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		wrmsrl(x86_pmu.lbr_from + i, 0);
 		wrmsrl(x86_pmu.lbr_to   + i, 0);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + i, 0);
 	}
 }
 
@@ -230,10 +240,12 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
 		wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
@@ -251,10 +263,12 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
 		rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
@@ -411,16 +425,31 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 	int out = 0;
+	int num = x86_pmu.lbr_nr;
 
-	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+	if (cpuc->lbr_sel->config & LBR_CALL_STACK)
+		num = tos;
+
+	for (i = 0; i < num; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
 		u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0;
 		int skip = 0;
+		u16 cycles = 0;
 		int lbr_flags = lbr_desc[lbr_format];
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
+		if (lbr_format == LBR_FORMAT_INFO) {
+			u64 info;
+
+			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info);
+			mis = !!(info & LBR_INFO_MISPRED);
+			pred = !mis;
+			in_tx = !!(info & LBR_INFO_IN_TX);
+			abort = !!(info & LBR_INFO_ABORT);
+			cycles = (info & LBR_INFO_CYCLES);
+		}
 		if (lbr_flags & LBR_EIP_FLAGS) {
 			mis = !!(from & LBR_FROM_FLAG_MISPRED);
 			pred = !mis;
@@ -450,6 +479,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[out].predicted = pred;
 		cpuc->lbr_entries[out].in_tx	 = in_tx;
 		cpuc->lbr_entries[out].abort	 = abort;
+		cpuc->lbr_entries[out].cycles	 = cycles;
 		cpuc->lbr_entries[out].reserved	 = 0;
 		out++;
 	}
@@ -947,6 +977,26 @@ void intel_pmu_lbr_init_hsw(void)
 	pr_cont("16-deep LBR, ");
 }
 
+/* skylake */
+__init void intel_pmu_lbr_init_skl(void)
+{
+	x86_pmu.lbr_nr	 = 32;
+	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
+	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("32-deep LBR, ");
+}
+
 /* atom */
 void __init intel_pmu_lbr_init_atom(void)
 {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 183de719628d..42169283448b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -65,15 +65,21 @@ static struct pt_cap_desc {
 } pt_caps[] = {
 	PT_CAP(max_subleaf,		0, CR_EAX, 0xffffffff),
 	PT_CAP(cr3_filtering,		0, CR_EBX, BIT(0)),
+	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
+	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
 	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
 	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
+	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
 	PT_CAP(payloads_lip,		0, CR_ECX, BIT(31)),
+	PT_CAP(mtc_periods,		1, CR_EAX, 0xffff0000),
+	PT_CAP(cycle_thresholds,	1, CR_EBX, 0xffff),
+	PT_CAP(psb_periods,		1, CR_EBX, 0xffff0000),
 };
 
 static u32 pt_cap_get(enum pt_capabilities cap)
 {
 	struct pt_cap_desc *cd = &pt_caps[cap];
-	u32 c = pt_pmu.caps[cd->leaf * 4 + cd->reg];
+	u32 c = pt_pmu.caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg];
 	unsigned int shift = __ffs(cd->mask);
 
 	return (c & cd->mask) >> shift;
@@ -94,12 +100,22 @@ static struct attribute_group pt_cap_group = {
 	.name	= "caps",
 };
 
+PMU_FORMAT_ATTR(cyc,		"config:1"	);
+PMU_FORMAT_ATTR(mtc,		"config:9"	);
 PMU_FORMAT_ATTR(tsc,		"config:10"	);
 PMU_FORMAT_ATTR(noretcomp,	"config:11"	);
+PMU_FORMAT_ATTR(mtc_period,	"config:14-17"	);
+PMU_FORMAT_ATTR(cyc_thresh,	"config:19-22"	);
+PMU_FORMAT_ATTR(psb_period,	"config:24-27"	);
 
 static struct attribute *pt_formats_attr[] = {
+	&format_attr_cyc.attr,
+	&format_attr_mtc.attr,
 	&format_attr_tsc.attr,
 	&format_attr_noretcomp.attr,
+	&format_attr_mtc_period.attr,
+	&format_attr_cyc_thresh.attr,
+	&format_attr_psb_period.attr,
 	NULL,
 };
 
@@ -129,10 +145,10 @@ static int __init pt_pmu_hw_init(void)
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
-			    &pt_pmu.caps[CR_EAX + i*4],
-			    &pt_pmu.caps[CR_EBX + i*4],
-			    &pt_pmu.caps[CR_ECX + i*4],
-			    &pt_pmu.caps[CR_EDX + i*4]);
+			    &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]);
 	}
 
 	ret = -ENOMEM;
@@ -170,15 +186,65 @@ fail:
 	return ret;
 }
 
-#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC)
+#define RTIT_CTL_CYC_PSB (RTIT_CTL_CYCLEACC	| \
+			  RTIT_CTL_CYC_THRESH	| \
+			  RTIT_CTL_PSB_FREQ)
+
+#define RTIT_CTL_MTC	(RTIT_CTL_MTC_EN	| \
+			 RTIT_CTL_MTC_RANGE)
+
+#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN		| \
+			RTIT_CTL_DISRETC	| \
+			RTIT_CTL_CYC_PSB	| \
+			RTIT_CTL_MTC)
 
 static bool pt_event_valid(struct perf_event *event)
 {
 	u64 config = event->attr.config;
+	u64 allowed, requested;
 
 	if ((config & PT_CONFIG_MASK) != config)
 		return false;
 
+	if (config & RTIT_CTL_CYC_PSB) {
+		if (!pt_cap_get(PT_CAP_psb_cyc))
+			return false;
+
+		allowed = pt_cap_get(PT_CAP_psb_periods);
+		requested = (config & RTIT_CTL_PSB_FREQ) >>
+			RTIT_CTL_PSB_FREQ_OFFSET;
+		if (requested && (!(allowed & BIT(requested))))
+			return false;
+
+		allowed = pt_cap_get(PT_CAP_cycle_thresholds);
+		requested = (config & RTIT_CTL_CYC_THRESH) >>
+			RTIT_CTL_CYC_THRESH_OFFSET;
+		if (requested && (!(allowed & BIT(requested))))
+			return false;
+	}
+
+	if (config & RTIT_CTL_MTC) {
+		/*
+		 * In the unlikely case that CPUID lists valid mtc periods,
+		 * but not the mtc capability, drop out here.
+		 *
+		 * Spec says that setting mtc period bits while mtc bit in
+		 * CPUID is 0 will #GP, so better safe than sorry.
+		 */
+		if (!pt_cap_get(PT_CAP_mtc))
+			return false;
+
+		allowed = pt_cap_get(PT_CAP_mtc_periods);
+		if (!allowed)
+			return false;
+
+		requested = (config & RTIT_CTL_MTC_RANGE) >>
+			RTIT_CTL_MTC_RANGE_OFFSET;
+
+		if (!(allowed & BIT(requested)))
+			return false;
+	}
+
 	return true;
 }
 
@@ -191,6 +257,11 @@ static void pt_config(struct perf_event *event)
 {
 	u64 reg;
 
+	if (!event->hw.itrace_started) {
+		event->hw.itrace_started = 1;
+		wrmsrl(MSR_IA32_RTIT_STATUS, 0);
+	}
+
 	reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
 
 	if (!event->attr.exclude_kernel)
@@ -910,7 +981,6 @@ void intel_pt_interrupt(void)
 
 		pt_config_buffer(buf->cur->table, buf->cur_idx,
 				 buf->output_off);
-		wrmsrl(MSR_IA32_RTIT_STATUS, 0);
 		pt_config(event);
 	}
 }
@@ -934,7 +1004,6 @@ static void pt_event_start(struct perf_event *event, int mode)
 
 	pt_config_buffer(buf->cur->table, buf->cur_idx,
 			 buf->output_off);
-	wrmsrl(MSR_IA32_RTIT_STATUS, 0);
 	pt_config(event);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 5cbd4e64feb5..81431c0f0614 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -86,6 +86,10 @@ static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
 			 1<<RAPL_IDX_RAM_NRG_STAT|\
 			 1<<RAPL_IDX_PP1_NRG_STAT)
 
+/* Knights Landing has PKG, RAM */
+#define RAPL_IDX_KNL	(1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT)
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -486,6 +490,18 @@ static struct attribute *rapl_events_hsw_attr[] = {
 	NULL,
 };
 
+static struct attribute *rapl_events_knl_attr[] = {
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
 static struct attribute_group rapl_pmu_events_group = {
 	.name = "events",
 	.attrs = NULL, /* patched at runtime */
@@ -730,6 +746,10 @@ static int __init rapl_pmu_init(void)
 		rapl_cntr_mask = RAPL_IDX_SRV;
 		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
 		break;
+	case 87: /* Knights Landing */
+		rapl_add_quirk(rapl_hsw_server_quirk);
+		rapl_cntr_mask = RAPL_IDX_KNL;
+		rapl_pmu_events_group.attrs = rapl_events_knl_attr;
 
 	default:
 		/* unsupported */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 21b5e38c921b..560e5255b15e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -911,6 +911,9 @@ static int __init uncore_pci_init(void)
 	case 63: /* Haswell-EP */
 		ret = hswep_uncore_pci_init();
 		break;
+	case 86: /* BDX-DE */
+		ret = bdx_uncore_pci_init();
+		break;
 	case 42: /* Sandy Bridge */
 		ret = snb_uncore_pci_init();
 		break;
@@ -1209,6 +1212,11 @@ static int __init uncore_cpu_init(void)
 		break;
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
+	case 60: /* Haswell */
+	case 69: /* Haswell */
+	case 70: /* Haswell */
+	case 61: /* Broadwell */
+	case 71: /* Broadwell */
 		snb_uncore_cpu_init();
 		break;
 	case 45: /* Sandy Bridge-EP */
@@ -1224,6 +1232,9 @@ static int __init uncore_cpu_init(void)
 	case 63: /* Haswell-EP */
 		hswep_uncore_cpu_init();
 		break;
+	case 86: /* BDX-DE */
+		bdx_uncore_cpu_init();
+		break;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 0f77f0a196e4..72c54c2e5b1a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -336,6 +336,8 @@ int ivbep_uncore_pci_init(void);
 void ivbep_uncore_cpu_init(void);
 int hswep_uncore_pci_init(void);
 void hswep_uncore_cpu_init(void);
+int bdx_uncore_pci_init(void);
+void bdx_uncore_cpu_init(void);
 
 /* perf_event_intel_uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index b005a78c7012..f78574b3cb55 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -45,6 +45,11 @@
 #define SNB_UNC_CBO_0_PER_CTR0                  0x706
 #define SNB_UNC_CBO_MSR_OFFSET                  0x10
 
+/* SNB ARB register */
+#define SNB_UNC_ARB_PER_CTR0			0x3b0
+#define SNB_UNC_ARB_PERFEVTSEL0			0x3b2
+#define SNB_UNC_ARB_MSR_OFFSET			0x10
+
 /* NHM global control register */
 #define NHM_UNC_PERF_GLOBAL_CTL                 0x391
 #define NHM_UNC_FIXED_CTR                       0x394
@@ -115,7 +120,7 @@ static struct intel_uncore_ops snb_uncore_msr_ops = {
 	.read_counter	= uncore_msr_read_counter,
 };
 
-static struct event_constraint snb_uncore_cbox_constraints[] = {
+static struct event_constraint snb_uncore_arb_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
 	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
 	EVENT_CONSTRAINT_END
@@ -134,14 +139,28 @@ static struct intel_uncore_type snb_uncore_cbox = {
 	.single_fixed	= 1,
 	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
 	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
-	.constraints	= snb_uncore_cbox_constraints,
 	.ops		= &snb_uncore_msr_ops,
 	.format_group	= &snb_uncore_format_group,
 	.event_descs	= snb_uncore_events,
 };
 
+static struct intel_uncore_type snb_uncore_arb = {
+	.name		= "arb",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.perf_ctr	= SNB_UNC_ARB_PER_CTR0,
+	.event_ctl	= SNB_UNC_ARB_PERFEVTSEL0,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= SNB_UNC_ARB_MSR_OFFSET,
+	.constraints	= snb_uncore_arb_constraints,
+	.ops		= &snb_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+};
+
 static struct intel_uncore_type *snb_msr_uncores[] = {
 	&snb_uncore_cbox,
+	&snb_uncore_arb,
 	NULL,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 6d6e85dd5849..694510a887dc 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -2215,7 +2215,7 @@ static struct intel_uncore_type *hswep_pci_uncores[] = {
 	NULL,
 };
 
-static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
+static const struct pci_device_id hswep_uncore_pci_ids[] = {
 	{ /* Home Agent 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30),
 		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0),
@@ -2321,3 +2321,167 @@ int hswep_uncore_pci_init(void)
 	return 0;
 }
 /* end of Haswell-EP uncore support */
+
+/* BDX-DE uncore support */
+
+static struct intel_uncore_type bdx_uncore_ubox = {
+	.name			= "ubox",
+	.num_counters		= 2,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_U_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_U_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &ivbep_uncore_msr_ops,
+	.format_group		= &ivbep_uncore_ubox_format_group,
+};
+
+static struct event_constraint bdx_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type bdx_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
+	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= bdx_uncore_cbox_constraints,
+	.ops			= &hswep_uncore_cbox_ops,
+	.format_group		= &hswep_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_type *bdx_msr_uncores[] = {
+	&bdx_uncore_ubox,
+	&bdx_uncore_cbox,
+	&hswep_uncore_pcu,
+	NULL,
+};
+
+void bdx_uncore_cpu_init(void)
+{
+	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = bdx_msr_uncores;
+}
+
+static struct intel_uncore_type bdx_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type bdx_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 5,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= hswep_uncore_imc_events,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type bdx_uncore_irp = {
+	.name			= "irp",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.ops			= &hswep_uncore_irp_ops,
+	.format_group		= &snbep_uncore_format_group,
+};
+
+
+static struct event_constraint bdx_uncore_r2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type bdx_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.constraints	= bdx_uncore_r2pcie_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	BDX_PCI_UNCORE_HA,
+	BDX_PCI_UNCORE_IMC,
+	BDX_PCI_UNCORE_IRP,
+	BDX_PCI_UNCORE_R2PCIE,
+};
+
+static struct intel_uncore_type *bdx_pci_uncores[] = {
+	[BDX_PCI_UNCORE_HA]	= &bdx_uncore_ha,
+	[BDX_PCI_UNCORE_IMC]	= &bdx_uncore_imc,
+	[BDX_PCI_UNCORE_IRP]	= &bdx_uncore_irp,
+	[BDX_PCI_UNCORE_R2PCIE]	= &bdx_uncore_r2pcie,
+	NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(bdx_uncore_pci_ids) = {
+	{ /* Home Agent 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0),
+	},
+	{ /* MC0 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC0 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1),
+	},
+	{ /* IRP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0),
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver bdx_uncore_pci_driver = {
+	.name		= "bdx_uncore",
+	.id_table	= bdx_uncore_pci_ids,
+};
+
+int bdx_uncore_pci_init(void)
+{
+	int ret = snbep_pci2phy_map_init(0x6f1e);
+
+	if (ret)
+		return ret;
+	uncore_pci_uncores = bdx_pci_uncores;
+	uncore_pci_driver = &bdx_uncore_pci_driver;
+	return 0;
+}
+
+/* end of BDX-DE uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
new file mode 100644
index 000000000000..086b12eae794
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -0,0 +1,242 @@
+#include <linux/perf_event.h>
+
+enum perf_msr_id {
+	PERF_MSR_TSC			= 0,
+	PERF_MSR_APERF			= 1,
+	PERF_MSR_MPERF			= 2,
+	PERF_MSR_PPERF			= 3,
+	PERF_MSR_SMI			= 4,
+
+	PERF_MSR_EVENT_MAX,
+};
+
+bool test_aperfmperf(int idx)
+{
+	return boot_cpu_has(X86_FEATURE_APERFMPERF);
+}
+
+bool test_intel(int idx)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+	    boot_cpu_data.x86 != 6)
+		return false;
+
+	switch (boot_cpu_data.x86_model) {
+	case 30: /* 45nm Nehalem    */
+	case 26: /* 45nm Nehalem-EP */
+	case 46: /* 45nm Nehalem-EX */
+
+	case 37: /* 32nm Westmere    */
+	case 44: /* 32nm Westmere-EP */
+	case 47: /* 32nm Westmere-EX */
+
+	case 42: /* 32nm SandyBridge         */
+	case 45: /* 32nm SandyBridge-E/EN/EP */
+
+	case 58: /* 22nm IvyBridge       */
+	case 62: /* 22nm IvyBridge-EP/EX */
+
+	case 60: /* 22nm Haswell Core */
+	case 63: /* 22nm Haswell Server */
+	case 69: /* 22nm Haswell ULT */
+	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
+
+	case 61: /* 14nm Broadwell Core-M */
+	case 86: /* 14nm Broadwell Xeon D */
+	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+	case 79: /* 14nm Broadwell Server */
+
+	case 55: /* 22nm Atom "Silvermont"                */
+	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
+	case 76: /* 14nm Atom "Airmont"                   */
+		if (idx == PERF_MSR_SMI)
+			return true;
+		break;
+
+	case 78: /* 14nm Skylake Mobile */
+	case 94: /* 14nm Skylake Desktop */
+		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
+			return true;
+		break;
+	}
+
+	return false;
+}
+
+struct perf_msr {
+	u64	msr;
+	struct	perf_pmu_events_attr *attr;
+	bool	(*test)(int idx);
+};
+
+PMU_EVENT_ATTR_STRING(tsc,   evattr_tsc,   "event=0x00");
+PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01");
+PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02");
+PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03");
+PMU_EVENT_ATTR_STRING(smi,   evattr_smi,   "event=0x04");
+
+static struct perf_msr msr[] = {
+	[PERF_MSR_TSC]   = { 0,			&evattr_tsc,	NULL,		 },
+	[PERF_MSR_APERF] = { MSR_IA32_APERF,	&evattr_aperf,	test_aperfmperf, },
+	[PERF_MSR_MPERF] = { MSR_IA32_MPERF,	&evattr_mperf,	test_aperfmperf, },
+	[PERF_MSR_PPERF] = { MSR_PPERF,		&evattr_pperf,	test_intel,	 },
+	[PERF_MSR_SMI]   = { MSR_SMI_COUNT,	&evattr_smi,	test_intel,	 },
+};
+
+static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
+	NULL,
+};
+
+static struct attribute_group events_attr_group = {
+	.name = "events",
+	.attrs = events_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+static struct attribute *format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+static struct attribute_group format_attr_group = {
+	.name = "format",
+	.attrs = format_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&events_attr_group,
+	&format_attr_group,
+	NULL,
+};
+
+static int msr_event_init(struct perf_event *event)
+{
+	u64 cfg = event->attr.config;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (cfg >= PERF_MSR_EVENT_MAX)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	if (!msr[cfg].attr)
+		return -EINVAL;
+
+	event->hw.idx = -1;
+	event->hw.event_base = msr[cfg].msr;
+	event->hw.config = cfg;
+
+	return 0;
+}
+
+static inline u64 msr_read_counter(struct perf_event *event)
+{
+	u64 now;
+
+	if (event->hw.event_base)
+		rdmsrl(event->hw.event_base, now);
+	else
+		rdtscll(now);
+
+	return now;
+}
+static void msr_event_update(struct perf_event *event)
+{
+	u64 prev, now;
+	s64 delta;
+
+	/* Careful, an NMI might modify the previous event value. */
+again:
+	prev = local64_read(&event->hw.prev_count);
+	now = msr_read_counter(event);
+
+	if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev)
+		goto again;
+
+	delta = now - prev;
+	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
+		delta <<= 32;
+		delta >>= 32; /* sign extend */
+	}
+	local64_add(now - prev, &event->count);
+}
+
+static void msr_event_start(struct perf_event *event, int flags)
+{
+	u64 now;
+
+	now = msr_read_counter(event);
+	local64_set(&event->hw.prev_count, now);
+}
+
+static void msr_event_stop(struct perf_event *event, int flags)
+{
+	msr_event_update(event);
+}
+
+static void msr_event_del(struct perf_event *event, int flags)
+{
+	msr_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int msr_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		msr_event_start(event, flags);
+
+	return 0;
+}
+
+static struct pmu pmu_msr = {
+	.task_ctx_nr	= perf_sw_context,
+	.attr_groups	= attr_groups,
+	.event_init	= msr_event_init,
+	.add		= msr_event_add,
+	.del		= msr_event_del,
+	.start		= msr_event_start,
+	.stop		= msr_event_stop,
+	.read		= msr_event_update,
+	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static int __init msr_init(void)
+{
+	int i, j = 0;
+
+	if (!boot_cpu_has(X86_FEATURE_TSC)) {
+		pr_cont("no MSR PMU driver.\n");
+		return 0;
+	}
+
+	/* Probe the MSRs. */
+	for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
+		u64 val;
+
+		/*
+		 * Virt sucks arse; you cannot tell if a R/O MSR is present :/
+		 */
+		if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
+			msr[i].attr = NULL;
+	}
+
+	/* List remaining MSRs in the sysfs attrs. */
+	for (i = 0; i < PERF_MSR_EVENT_MAX; i++) {
+		if (msr[i].attr)
+			events_attrs[j++] = &msr[i].attr->attr.attr;
+	}
+	events_attrs[j] = NULL;
+
+	perf_pmu_register(&pmu_msr, "msr", -1);
+
+	return 0;
+}
+device_initcall(msr_init);
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 83741a71558f..bd3507da39f0 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -170,7 +170,7 @@ static int cpuid_class_cpu_callback(struct notifier_block *nfb,
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block __refdata cpuid_class_cpu_notifier =
+static struct notifier_block cpuid_class_cpu_notifier =
 {
 	.notifier_call = cpuid_class_cpu_callback,
 };
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 89427d8d4fc5..eec40f595ab9 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -175,7 +175,9 @@ static __init void early_serial_init(char *s)
 	}
 
 	if (*s) {
-		if (kstrtoul(s, 0, &baud) < 0 || baud == 0)
+		baud = simple_strtoull(s, &e, 0);
+
+		if (baud == 0 || s == e)
 			baud = DEFAULT_BAUD;
 	}
 
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index f5d0730e7b08..4d38416e2a7f 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -110,7 +110,7 @@ static void init_espfix_random(void)
 	 */
 	if (!arch_get_random_long(&rand)) {
 		/* The constant is an arbitrary large prime */
-		rdtscll(rand);
+		rand = rdtsc();
 		rand *= 0xc345c6b72fd16123UL;
 	}
 
@@ -131,25 +131,24 @@ void __init init_espfix_bsp(void)
 	init_espfix_random();
 
 	/* The rest is the same as for any other processor */
-	init_espfix_ap();
+	init_espfix_ap(0);
 }
 
-void init_espfix_ap(void)
+void init_espfix_ap(int cpu)
 {
-	unsigned int cpu, page;
+	unsigned int page;
 	unsigned long addr;
 	pud_t pud, *pud_p;
 	pmd_t pmd, *pmd_p;
 	pte_t pte, *pte_p;
-	int n;
+	int n, node;
 	void *stack_page;
 	pteval_t ptemask;
 
 	/* We only have to do this once... */
-	if (likely(this_cpu_read(espfix_stack)))
+	if (likely(per_cpu(espfix_stack, cpu)))
 		return;		/* Already initialized */
 
-	cpu = smp_processor_id();
 	addr = espfix_base_addr(cpu);
 	page = cpu/ESPFIX_STACKS_PER_PAGE;
 
@@ -165,12 +164,15 @@ void init_espfix_ap(void)
 	if (stack_page)
 		goto unlock_done;
 
+	node = cpu_to_node(cpu);
 	ptemask = __supported_pte_mask;
 
 	pud_p = &espfix_pud_page[pud_index(addr)];
 	pud = *pud_p;
 	if (!pud_present(pud)) {
-		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pmd_p = (pmd_t *)page_address(page);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
@@ -180,7 +182,9 @@ void init_espfix_ap(void)
 	pmd_p = pmd_offset(&pud, addr);
 	pmd = *pmd_p;
 	if (!pmd_present(pmd)) {
-		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pte_p = (pte_t *)page_address(page);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
@@ -188,7 +192,7 @@ void init_espfix_ap(void)
 	}
 
 	pte_p = pte_offset_kernel(&pmd, addr);
-	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
@@ -199,7 +203,7 @@ void init_espfix_ap(void)
 unlock_done:
 	mutex_unlock(&espfix_init_mutex);
 done:
-	this_cpu_write(espfix_stack, addr);
-	this_cpu_write(espfix_waddr, (unsigned long)stack_page
-		       + (addr & ~PAGE_MASK));
+	per_cpu(espfix_stack, cpu) = addr;
+	per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page
+				      + (addr & ~PAGE_MASK);
 }
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 79de954626fd..d25097c3fc1d 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -270,7 +270,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (src_fpu->fpstate_active)
+	if (src_fpu->fpstate_active && cpu_has_fpu)
 		fpu_copy(dst_fpu, src_fpu);
 
 	return 0;
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 32826791e675..d14e9ac3235a 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -4,6 +4,8 @@
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 
+#include <linux/sched.h>
+
 /*
  * Initialize the TS bit in CR0 according to the style of context-switches
  * we are using:
@@ -38,7 +40,12 @@ static void fpu__init_cpu_generic(void)
 	write_cr0(cr0);
 
 	/* Flush out any pending x87 state: */
-	asm volatile ("fninit");
+#ifdef CONFIG_MATH_EMULATION
+	if (!cpu_has_fpu)
+		fpstate_init_soft(&current->thread.fpu.state.soft);
+	else
+#endif
+		asm volatile ("fninit");
 }
 
 /*
@@ -136,6 +143,43 @@ static void __init fpu__init_system_generic(void)
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 
+/* Enforce that 'MEMBER' is the last field of 'TYPE': */
+#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
+	BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER))
+
+/*
+ * We append the 'struct fpu' to the task_struct:
+ */
+static void __init fpu__init_task_struct_size(void)
+{
+	int task_size = sizeof(struct task_struct);
+
+	/*
+	 * Subtract off the static size of the register state.
+	 * It potentially has a bunch of padding.
+	 */
+	task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state);
+
+	/*
+	 * Add back the dynamically-calculated register state
+	 * size.
+	 */
+	task_size += xstate_size;
+
+	/*
+	 * We dynamically size 'struct fpu', so we require that
+	 * it be at the end of 'thread_struct' and that
+	 * 'thread_struct' be at the end of 'task_struct'.  If
+	 * you hit a compile error here, check the structure to
+	 * see if something got added to the end.
+	 */
+	CHECK_MEMBER_AT_END_OF(struct fpu, state);
+	CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
+	CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
+
+	arch_task_struct_size = task_size;
+}
+
 /*
  * Set up the xstate_size based on the legacy FPU context size.
  *
@@ -287,6 +331,7 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 	fpu__init_system_generic();
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate();
+	fpu__init_task_struct_size();
 
 	fpu__init_system_ctx_switch();
 }
@@ -311,9 +356,15 @@ static int __init x86_noxsave_setup(char *s)
 
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEC);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
 	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512F);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
 
 	return 1;
 }
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 5a4668136e98..f129a9af6357 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -161,11 +161,12 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
-	kasan_map_early_shadow(early_level4_pgt);
-
-	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();
 
+	clear_page(init_level4_pgt);
+
+	kasan_early_init();
+
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
 		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
@@ -177,12 +178,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	 */
 	load_ucode_bsp();
 
-	clear_page(init_level4_pgt);
 	/* set init_level4_pgt kernel high mapping*/
 	init_level4_pgt[511] = early_level4_pgt[511];
 
-	kasan_map_early_shadow(init_level4_pgt);
-
 	x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e5c27f729a38..1d40ca8a73f2 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -516,38 +516,9 @@ ENTRY(phys_base)
 	/* This must match the first entry in level2_kernel_pgt */
 	.quad   0x0000000000000000
 
-#ifdef CONFIG_KASAN
-#define FILL(VAL, COUNT)				\
-	.rept (COUNT) ;					\
-	.quad	(VAL) ;					\
-	.endr
-
-NEXT_PAGE(kasan_zero_pte)
-	FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pmd)
-	FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pud)
-	FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512)
-
-#undef FILL
-#endif
-
-
 #include "../../x86/xen/xen-head.S"
 	
 	__PAGE_ALIGNED_BSS
 NEXT_PAGE(empty_zero_page)
 	.skip PAGE_SIZE
 
-#ifdef CONFIG_KASAN
-/*
- * This page used as early shadow. We don't use empty_zero_page
- * at early stages, stack instrumentation could write some garbage
- * to this page.
- * Latter we reuse it as zero shadow for large ranges of memory
- * that allowed to access, but not instrumented by kasan
- * (vmalloc/vmemmap ...).
- */
-NEXT_PAGE(kasan_zero_page)
-	.skip PAGE_SIZE
-#endif
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 10757d0a3fcf..88b4da373081 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -226,22 +226,7 @@ static void hpet_reserve_platform_timers(unsigned int id) { }
  */
 static unsigned long hpet_freq;
 
-static void hpet_legacy_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt);
-static int hpet_legacy_next_event(unsigned long delta,
-			   struct clock_event_device *evt);
-
-/*
- * The hpet clock event device
- */
-static struct clock_event_device hpet_clockevent = {
-	.name		= "hpet",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= hpet_legacy_set_mode,
-	.set_next_event = hpet_legacy_next_event,
-	.irq		= 0,
-	.rating		= 50,
-};
+static struct clock_event_device hpet_clockevent;
 
 static void hpet_stop_counter(void)
 {
@@ -306,64 +291,74 @@ static void hpet_legacy_clockevent_register(void)
 	printk(KERN_DEBUG "hpet clockevent registered\n");
 }
 
-static void hpet_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt, int timer)
+static int hpet_set_periodic(struct clock_event_device *evt, int timer)
 {
 	unsigned int cfg, cmp, now;
 	uint64_t delta;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		hpet_stop_counter();
-		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
-		delta >>= evt->shift;
-		now = hpet_readl(HPET_COUNTER);
-		cmp = now + (unsigned int) delta;
-		cfg = hpet_readl(HPET_Tn_CFG(timer));
-		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
-		       HPET_TN_SETVAL | HPET_TN_32BIT;
-		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		hpet_writel(cmp, HPET_Tn_CMP(timer));
-		udelay(1);
-		/*
-		 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
-		 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
-		 * bit is automatically cleared after the first write.
-		 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
-		 * Publication # 24674)
-		 */
-		hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer));
-		hpet_start_counter();
-		hpet_print_config();
-		break;
+	hpet_stop_counter();
+	delta = ((uint64_t)(NSEC_PER_SEC / HZ)) * evt->mult;
+	delta >>= evt->shift;
+	now = hpet_readl(HPET_COUNTER);
+	cmp = now + (unsigned int)delta;
+	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
+	       HPET_TN_32BIT;
+	hpet_writel(cfg, HPET_Tn_CFG(timer));
+	hpet_writel(cmp, HPET_Tn_CMP(timer));
+	udelay(1);
+	/*
+	 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
+	 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
+	 * bit is automatically cleared after the first write.
+	 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
+	 * Publication # 24674)
+	 */
+	hpet_writel((unsigned int)delta, HPET_Tn_CMP(timer));
+	hpet_start_counter();
+	hpet_print_config();
 
-	case CLOCK_EVT_MODE_ONESHOT:
-		cfg = hpet_readl(HPET_Tn_CFG(timer));
-		cfg &= ~HPET_TN_PERIODIC;
-		cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
-		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		break;
+	return 0;
+}
 
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		cfg = hpet_readl(HPET_Tn_CFG(timer));
-		cfg &= ~HPET_TN_ENABLE;
-		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		break;
+static int hpet_set_oneshot(struct clock_event_device *evt, int timer)
+{
+	unsigned int cfg;
 
-	case CLOCK_EVT_MODE_RESUME:
-		if (timer == 0) {
-			hpet_enable_legacy_int();
-		} else {
-			struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-			irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-			disable_irq(hdev->irq);
-			irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
-			enable_irq(hdev->irq);
-		}
-		hpet_print_config();
-		break;
+	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg &= ~HPET_TN_PERIODIC;
+	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+	hpet_writel(cfg, HPET_Tn_CFG(timer));
+
+	return 0;
+}
+
+static int hpet_shutdown(struct clock_event_device *evt, int timer)
+{
+	unsigned int cfg;
+
+	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg &= ~HPET_TN_ENABLE;
+	hpet_writel(cfg, HPET_Tn_CFG(timer));
+
+	return 0;
+}
+
+static int hpet_resume(struct clock_event_device *evt, int timer)
+{
+	if (!timer) {
+		hpet_enable_legacy_int();
+	} else {
+		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
+		disable_irq(hdev->irq);
+		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
+		enable_irq(hdev->irq);
 	}
+	hpet_print_config();
+
+	return 0;
 }
 
 static int hpet_next_event(unsigned long delta,
@@ -403,10 +398,24 @@ static int hpet_next_event(unsigned long delta,
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
-static void hpet_legacy_set_mode(enum clock_event_mode mode,
-			struct clock_event_device *evt)
+static int hpet_legacy_shutdown(struct clock_event_device *evt)
+{
+	return hpet_shutdown(evt, 0);
+}
+
+static int hpet_legacy_set_oneshot(struct clock_event_device *evt)
+{
+	return hpet_set_oneshot(evt, 0);
+}
+
+static int hpet_legacy_set_periodic(struct clock_event_device *evt)
 {
-	hpet_set_mode(mode, evt, 0);
+	return hpet_set_periodic(evt, 0);
+}
+
+static int hpet_legacy_resume(struct clock_event_device *evt)
+{
+	return hpet_resume(evt, 0);
 }
 
 static int hpet_legacy_next_event(unsigned long delta,
@@ -416,6 +425,22 @@ static int hpet_legacy_next_event(unsigned long delta,
 }
 
 /*
+ * The hpet clock event device
+ */
+static struct clock_event_device hpet_clockevent = {
+	.name			= "hpet",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_periodic	= hpet_legacy_set_periodic,
+	.set_state_oneshot	= hpet_legacy_set_oneshot,
+	.set_state_shutdown	= hpet_legacy_shutdown,
+	.tick_resume		= hpet_legacy_resume,
+	.set_next_event		= hpet_legacy_next_event,
+	.irq			= 0,
+	.rating			= 50,
+};
+
+/*
  * HPET MSI Support
  */
 #ifdef CONFIG_PCI_MSI
@@ -426,7 +451,7 @@ static struct irq_domain *hpet_domain;
 
 void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = data->handler_data;
+	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
 	/* unmask it */
@@ -437,7 +462,7 @@ void hpet_msi_unmask(struct irq_data *data)
 
 void hpet_msi_mask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = data->handler_data;
+	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
 	/* mask it */
@@ -459,11 +484,32 @@ void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
 	msg->address_hi = 0;
 }
 
-static void hpet_msi_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int hpet_msi_shutdown(struct clock_event_device *evt)
+{
+	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+	return hpet_shutdown(evt, hdev->num);
+}
+
+static int hpet_msi_set_oneshot(struct clock_event_device *evt)
+{
+	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+	return hpet_set_oneshot(evt, hdev->num);
+}
+
+static int hpet_msi_set_periodic(struct clock_event_device *evt)
 {
 	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-	hpet_set_mode(mode, evt, hdev->num);
+
+	return hpet_set_periodic(evt, hdev->num);
+}
+
+static int hpet_msi_resume(struct clock_event_device *evt)
+{
+	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+	return hpet_resume(evt, hdev->num);
 }
 
 static int hpet_msi_next_event(unsigned long delta,
@@ -523,10 +569,14 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
 
 	evt->rating = 110;
 	evt->features = CLOCK_EVT_FEAT_ONESHOT;
-	if (hdev->flags & HPET_DEV_PERI_CAP)
+	if (hdev->flags & HPET_DEV_PERI_CAP) {
 		evt->features |= CLOCK_EVT_FEAT_PERIODIC;
+		evt->set_state_periodic = hpet_msi_set_periodic;
+	}
 
-	evt->set_mode = hpet_msi_set_mode;
+	evt->set_state_shutdown = hpet_msi_shutdown;
+	evt->set_state_oneshot = hpet_msi_set_oneshot;
+	evt->tick_resume = hpet_msi_resume;
 	evt->set_next_event = hpet_msi_next_event;
 	evt->cpumask = cpumask_of(hdev->cpu);
 
@@ -735,7 +785,7 @@ static int hpet_clocksource_register(void)
 
 	/* Verify whether hpet counter works */
 	t1 = hpet_readl(HPET_COUNTER);
-	rdtscll(start);
+	start = rdtsc();
 
 	/*
 	 * We don't know the TSC frequency yet, but waiting for
@@ -745,7 +795,7 @@ static int hpet_clocksource_register(void)
 	 */
 	do {
 		rep_nop();
-		rdtscll(now);
+		now = rdtsc();
 	} while ((now - start) < 200000UL);
 
 	if (t1 == hpet_readl(HPET_COUNTER)) {
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 7114ba220fd4..50a3fad5b89f 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -32,6 +32,7 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/kallsyms.h>
+#include <linux/kprobes.h>
 #include <linux/percpu.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
@@ -179,7 +180,11 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 	va = info->address;
 	len = bp->attr.bp_len;
 
-	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
+	/*
+	 * We don't need to worry about va + len - 1 overflowing:
+	 * we already require that va is aligned to a multiple of len.
+	 */
+	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
 }
 
 int arch_bp_generic_fields(int x86_len, int x86_type,
@@ -243,6 +248,20 @@ static int arch_build_bp_info(struct perf_event *bp)
 		info->type = X86_BREAKPOINT_RW;
 		break;
 	case HW_BREAKPOINT_X:
+		/*
+		 * We don't allow kernel breakpoints in places that are not
+		 * acceptable for kprobes.  On non-kprobes kernels, we don't
+		 * allow kernel breakpoints at all.
+		 */
+		if (bp->attr.bp_addr >= TASK_SIZE_MAX) {
+#ifdef CONFIG_KPROBES
+			if (within_kprobe_blacklist(bp->attr.bp_addr))
+				return -EINVAL;
+#else
+			return -EINVAL;
+#endif
+		}
+
 		info->type = X86_BREAKPOINT_EXECUTE;
 		/*
 		 * x86 inst breakpoints need to have a specific undefined len.
@@ -276,8 +295,18 @@ static int arch_build_bp_info(struct perf_event *bp)
 		break;
 #endif
 	default:
+		/* AMD range breakpoint */
 		if (!is_power_of_2(bp->attr.bp_len))
 			return -EINVAL;
+		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
+			return -EINVAL;
+		/*
+		 * It's impossible to use a range breakpoint to fake out
+		 * user vs kernel detection because bp_len - 1 can't
+		 * have the high bit set.  If we ever allow range instruction
+		 * breakpoints, then we'll have to check for kprobe-blacklisted
+		 * addresses anywhere in the range.
+		 */
 		if (!cpu_has_bpext)
 			return -EOPNOTSUPP;
 		info->mask = bp->attr.bp_len - 1;
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index f2b96de3c7c1..efb82f07b29c 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -34,7 +34,7 @@ static int __init init_pit_clocksource(void)
 	  * - when local APIC timer is active (PIT is switched off)
 	  */
 	if (num_possible_cpus() > 1 || is_hpet_enabled() ||
-	    i8253_clockevent.mode != CLOCK_EVT_MODE_PERIODIC)
+	    !clockevent_state_periodic(&i8253_clockevent))
 		return 0;
 
 	return clocksource_i8253_init();
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 88b366487b0e..f8062aaf5df9 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -139,10 +139,13 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_puts(p, "  Machine check polls\n");
 #endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
-	seq_printf(p, "%*s: ", prec, "HYP");
-	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
-	seq_puts(p, "  Hypervisor callback interrupts\n");
+	if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) {
+		seq_printf(p, "%*s: ", prec, "HYP");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				   irq_stats(j)->irq_hv_callback_count);
+		seq_puts(p, "  Hypervisor callback interrupts\n");
+	}
 #endif
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
@@ -211,24 +214,38 @@ u64 arch_irq_stat(void)
 __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-
+	struct irq_desc * desc;
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
-	unsigned irq;
+
+	/*
+	 * NB: Unlike exception entries, IRQ entries do not reliably
+	 * handle context tracking in the low-level entry code.  This is
+	 * because syscall entries execute briefly with IRQs on before
+	 * updating context tracking state, so we can take an IRQ from
+	 * kernel mode with CONTEXT_USER.  The low-level entry code only
+	 * updates the context if we came from user mode, so we won't
+	 * switch to CONTEXT_KERNEL.  We'll fix that once the syscall
+	 * code is cleaned up enough that we can cleanly defer enabling
+	 * IRQs.
+	 */
 
 	entering_irq();
 
-	irq = __this_cpu_read(vector_irq[vector]);
+	/* entering_irq() tells RCU that we're not quiescent.  Check it. */
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
+
+	desc = __this_cpu_read(vector_irq[vector]);
 
-	if (!handle_irq(irq, regs)) {
+	if (!handle_irq(desc, regs)) {
 		ack_APIC_irq();
 
-		if (irq != VECTOR_RETRIGGERED) {
-			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n",
+		if (desc != VECTOR_RETRIGGERED) {
+			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
 					     __func__, smp_processor_id(),
-					     vector, irq);
+					     vector);
 		} else {
-			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 		}
 	}
 
@@ -330,10 +347,10 @@ static struct cpumask affinity_new, online_new;
  */
 int check_irq_vectors_for_cpu_disable(void)
 {
-	int irq, cpu;
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
+	int cpu;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);
@@ -341,39 +358,43 @@ int check_irq_vectors_for_cpu_disable(void)
 
 	this_count = 0;
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		irq = __this_cpu_read(vector_irq[vector]);
-		if (irq >= 0) {
-			desc = irq_to_desc(irq);
-			if (!desc)
-				continue;
+		desc = __this_cpu_read(vector_irq[vector]);
+		if (IS_ERR_OR_NULL(desc))
+			continue;
+		/*
+		 * Protect against concurrent action removal, affinity
+		 * changes etc.
+		 */
+		raw_spin_lock(&desc->lock);
+		data = irq_desc_get_irq_data(desc);
+		cpumask_copy(&affinity_new,
+			     irq_data_get_affinity_mask(data));
+		cpumask_clear_cpu(this_cpu, &affinity_new);
 
-			data = irq_desc_get_irq_data(desc);
-			cpumask_copy(&affinity_new, data->affinity);
-			cpumask_clear_cpu(this_cpu, &affinity_new);
-
-			/* Do not count inactive or per-cpu irqs. */
-			if (!irq_has_action(irq) || irqd_is_per_cpu(data))
-				continue;
-
-			/*
-			 * A single irq may be mapped to multiple
-			 * cpu's vector_irq[] (for example IOAPIC cluster
-			 * mode).  In this case we have two
-			 * possibilities:
-			 *
-			 * 1) the resulting affinity mask is empty; that is
-			 * this the down'd cpu is the last cpu in the irq's
-			 * affinity mask, or
-			 *
-			 * 2) the resulting affinity mask is no longer
-			 * a subset of the online cpus but the affinity
-			 * mask is not zero; that is the down'd cpu is the
-			 * last online cpu in a user set affinity mask.
-			 */
-			if (cpumask_empty(&affinity_new) ||
-			    !cpumask_subset(&affinity_new, &online_new))
-				this_count++;
+		/* Do not count inactive or per-cpu irqs. */
+		if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) {
+			raw_spin_unlock(&desc->lock);
+			continue;
 		}
+
+		raw_spin_unlock(&desc->lock);
+		/*
+		 * A single irq may be mapped to multiple cpu's
+		 * vector_irq[] (for example IOAPIC cluster mode).  In
+		 * this case we have two possibilities:
+		 *
+		 * 1) the resulting affinity mask is empty; that is
+		 * this the down'd cpu is the last cpu in the irq's
+		 * affinity mask, or
+		 *
+		 * 2) the resulting affinity mask is no longer a
+		 * subset of the online cpus but the affinity mask is
+		 * not zero; that is the down'd cpu is the last online
+		 * cpu in a user set affinity mask.
+		 */
+		if (cpumask_empty(&affinity_new) ||
+		    !cpumask_subset(&affinity_new, &online_new))
+			this_count++;
 	}
 
 	count = 0;
@@ -385,12 +406,15 @@ int check_irq_vectors_for_cpu_disable(void)
 		 * vector. If the vector is marked in the used vectors
 		 * bitmap or an irq is assigned to it, we don't count
 		 * it as available.
+		 *
+		 * As this is an inaccurate snapshot anyway, we can do
+		 * this w/o holding vector_lock.
 		 */
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
 			if (!test_bit(vector, used_vectors) &&
-			    per_cpu(vector_irq, cpu)[vector] < 0)
-					count++;
+			    IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
+			    count++;
 		}
 	}
 
@@ -426,7 +450,7 @@ void fixup_irqs(void)
 		raw_spin_lock(&desc->lock);
 
 		data = irq_desc_get_irq_data(desc);
-		affinity = data->affinity;
+		affinity = irq_data_get_affinity_mask(data);
 		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
 		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
@@ -486,20 +510,24 @@ void fixup_irqs(void)
 	 */
 	mdelay(1);
 
+	/*
+	 * We can walk the vector array of this cpu without holding
+	 * vector_lock because the cpu is already marked !online, so
+	 * nothing else will touch it.
+	 */
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
-		if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED)
+		if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
 			continue;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
 		if (irr  & (1 << (vector % 32))) {
-			irq = __this_cpu_read(vector_irq[vector]);
+			desc = __this_cpu_read(vector_irq[vector]);
 
-			desc = irq_to_desc(irq);
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
-			raw_spin_lock(&desc->lock);
 			if (chip->irq_retrigger) {
 				chip->irq_retrigger(data);
 				__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
@@ -507,7 +535,7 @@ void fixup_irqs(void)
 			raw_spin_unlock(&desc->lock);
 		}
 		if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED)
-			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 	}
 }
 #endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index cd74f5978ab9..c80cf6699678 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -148,21 +148,21 @@ void do_softirq_own_stack(void)
 	call_on_stack(__do_softirq, isp);
 }
 
-bool handle_irq(unsigned irq, struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	struct irq_desc *desc;
+	unsigned int irq;
 	int overflow;
 
 	overflow = check_stack_overflow();
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc))
+	if (IS_ERR_OR_NULL(desc))
 		return false;
 
+	irq = irq_desc_get_irq(desc);
 	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
-		desc->handle_irq(irq, desc);
+		generic_handle_irq_desc(irq, desc);
 	}
 
 	return true;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index bc4604e500a3..ff16ccb918f2 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -68,16 +68,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 #endif
 }
 
-bool handle_irq(unsigned irq, struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	struct irq_desc *desc;
-
 	stack_overflow_check(regs);
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc))
+	if (unlikely(IS_ERR_OR_NULL(desc)))
 		return false;
 
-	generic_handle_irq_desc(irq, desc);
+	generic_handle_irq_desc(irq_desc_get_irq(desc), desc);
 	return true;
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a3a5e158ed69..1423ab1b0312 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -52,7 +52,7 @@ static struct irqaction irq2 = {
 };
 
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED,
+	[0 ... NR_VECTORS - 1] = VECTOR_UNUSED,
 };
 
 int vector_used_by_percpu_irq(unsigned int vector)
@@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED)
+		if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
 			return 1;
 	}
 
@@ -94,7 +94,7 @@ void __init init_IRQ(void)
 	 * irq's migrate etc.
 	 */
 	for (i = 0; i < nr_legacy_irqs(); i++)
-		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
+		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i);
 
 	x86_init.irqs.intr_init();
 }
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 26d5a55a2736..e565e0e4d216 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -45,7 +45,7 @@ static void __jump_label_transform(struct jump_entry *entry,
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			/*
 			 * Jump label is enabled for the first time.
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index ca83f7ac388b..0f8a6bbaaa44 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -223,9 +223,6 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	memset(&params->hd0_info, 0, sizeof(params->hd0_info));
 	memset(&params->hd1_info, 0, sizeof(params->hd1_info));
 
-	/* Default sysdesc table */
-	params->sys_desc_table.length = 0;
-
 	if (image->type == KEXEC_TYPE_CRASH) {
 		ret = crash_setup_memmap_entries(image, params);
 		if (ret)
@@ -536,7 +533,9 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 	int ret;
 
 	ret = verify_pefile_signature(kernel, kernel_len,
-				      system_trusted_keyring, &trusted);
+				      system_trusted_keyring,
+				      VERIFYING_KEXEC_PE_SIGNATURE,
+				      &trusted);
 	if (ret < 0)
 		return ret;
 	if (!trusted)
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d759cc..2bcc0525f1c1 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
@@ -20,82 +21,82 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm == current_mm)
-		load_LDT(&current->active_mm->context);
+	mm_context_t *pc;
+
+	if (current->active_mm != current_mm)
+		return;
+
+	pc = &current->active_mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
-#endif
 
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
 {
-	void *oldldt, *newldt;
-	int oldsize;
-
-	if (mincount <= pc->size)
-		return 0;
-	oldsize = pc->size;
-	mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
-			(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
-	if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
-		newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+	struct ldt_struct *new_ldt;
+	int alloc_size;
+
+	if (size > LDT_ENTRIES)
+		return NULL;
+
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	if (!new_ldt)
+		return NULL;
+
+	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+	alloc_size = size * LDT_ENTRY_SIZE;
+
+	/*
+	 * Xen is very picky: it requires a page-aligned LDT that has no
+	 * trailing nonzero bytes in any page that contains LDT descriptors.
+	 * Keep it simple: zero the whole allocation and never allocate less
+	 * than PAGE_SIZE.
+	 */
+	if (alloc_size > PAGE_SIZE)
+		new_ldt->entries = vzalloc(alloc_size);
 	else
-		newldt = (void *)__get_free_page(GFP_KERNEL);
-
-	if (!newldt)
-		return -ENOMEM;
+		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (oldsize)
-		memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
-	oldldt = pc->ldt;
-	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
-	       (mincount - oldsize) * LDT_ENTRY_SIZE);
+	if (!new_ldt->entries) {
+		kfree(new_ldt);
+		return NULL;
+	}
 
-	paravirt_alloc_ldt(newldt, mincount);
+	new_ldt->size = size;
+	return new_ldt;
+}
 
-#ifdef CONFIG_X86_64
-	/* CHECKME: Do we really need this ? */
-	wmb();
-#endif
-	pc->ldt = newldt;
-	wmb();
-	pc->size = mincount;
-	wmb();
-
-	if (reload) {
-#ifdef CONFIG_SMP
-		preempt_disable();
-		load_LDT(pc);
-		if (!cpumask_equal(mm_cpumask(current->mm),
-				   cpumask_of(smp_processor_id())))
-			smp_call_function(flush_ldt, current->mm, 1);
-		preempt_enable();
-#else
-		load_LDT(pc);
-#endif
-	}
-	if (oldsize) {
-		paravirt_free_ldt(oldldt, oldsize);
-		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(oldldt);
-		else
-			put_page(virt_to_page(oldldt));
-	}
-	return 0;
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
+{
+	paravirt_alloc_ldt(ldt->entries, ldt->size);
 }
 
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+			struct ldt_struct *ldt)
 {
-	int err = alloc_ldt(new, old->size, 0);
-	int i;
+	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	smp_store_release(&current_mm->context.ldt, ldt);
+
+	/* Activate the LDT for all CPUs using current_mm. */
+	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
 
-	if (err < 0)
-		return err;
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (likely(!ldt))
+		return;
 
-	for (i = 0; i < old->size; i++)
-		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
-	return 0;
+	paravirt_free_ldt(ldt->entries, ldt->size);
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		kfree(ldt->entries);
+	kfree(ldt);
 }
 
 /*
@@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
 	int retval = 0;
 
 	mutex_init(&mm->context.lock);
-	mm->context.size = 0;
 	old_mm = current->mm;
-	if (old_mm && old_mm->context.size > 0) {
-		mutex_lock(&old_mm->context.lock);
-		retval = copy_ldt(&mm->context, &old_mm->context);
-		mutex_unlock(&old_mm->context.lock);
+	if (!old_mm) {
+		mm->context.ldt = NULL;
+		return 0;
 	}
+
+	mutex_lock(&old_mm->context.lock);
+	if (!old_mm->context.ldt) {
+		mm->context.ldt = NULL;
+		goto out_unlock;
+	}
+
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	if (!new_ldt) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+	       new_ldt->size * LDT_ENTRY_SIZE);
+	finalize_ldt_struct(new_ldt);
+
+	mm->context.ldt = new_ldt;
+
+out_unlock:
+	mutex_unlock(&old_mm->context.lock);
 	return retval;
 }
 
@@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
  */
 void destroy_context(struct mm_struct *mm)
 {
-	if (mm->context.size) {
-#ifdef CONFIG_X86_32
-		/* CHECKME: Can this ever happen ? */
-		if (mm == current->active_mm)
-			clear_LDT();
-#endif
-		paravirt_free_ldt(mm->context.ldt, mm->context.size);
-		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(mm->context.ldt);
-		else
-			put_page(virt_to_page(mm->context.ldt));
-		mm->context.size = 0;
-	}
+	free_ldt_struct(mm->context.ldt);
+	mm->context.ldt = NULL;
 }
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int err;
+	int retval;
 	unsigned long size;
 	struct mm_struct *mm = current->mm;
 
-	if (!mm->context.size)
-		return 0;
+	mutex_lock(&mm->context.lock);
+
+	if (!mm->context.ldt) {
+		retval = 0;
+		goto out_unlock;
+	}
+
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	mutex_lock(&mm->context.lock);
-	size = mm->context.size * LDT_ENTRY_SIZE;
+	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
 
-	err = 0;
-	if (copy_to_user(ptr, mm->context.ldt, size))
-		err = -EFAULT;
-	mutex_unlock(&mm->context.lock);
-	if (err < 0)
-		goto error_return;
+	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+		retval = -EFAULT;
+		goto out_unlock;
+	}
+
 	if (size != bytecount) {
-		/* zero-fill the rest */
-		if (clear_user(ptr + size, bytecount - size) != 0) {
-			err = -EFAULT;
-			goto error_return;
+		/* Zero-fill the rest and pretend we read bytecount bytes. */
+		if (clear_user(ptr + size, bytecount - size)) {
+			retval = -EFAULT;
+			goto out_unlock;
 		}
 	}
-	return bytecount;
-error_return:
-	return err;
+	retval = bytecount;
+
+out_unlock:
+	mutex_unlock(&mm->context.lock);
+	return retval;
 }
 
 static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	struct desc_struct ldt;
 	int error;
 	struct user_desc ldt_info;
+	int oldsize, newsize;
+	struct ldt_struct *new_ldt, *old_ldt;
 
 	error = -EINVAL;
 	if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			goto out;
 	}
 
-	mutex_lock(&mm->context.lock);
-	if (ldt_info.entry_number >= mm->context.size) {
-		error = alloc_ldt(&current->mm->context,
-				  ldt_info.entry_number + 1, 1);
-		if (error < 0)
-			goto out_unlock;
-	}
-
-	/* Allow LDTs to be cleared by the user. */
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
-		if (oldmode || LDT_empty(&ldt_info)) {
-			memset(&ldt, 0, sizeof(ldt));
-			goto install;
+	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+	    LDT_empty(&ldt_info)) {
+		/* The user wants to clear the entry. */
+		memset(&ldt, 0, sizeof(ldt));
+	} else {
+		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+			error = -EINVAL;
+			goto out;
 		}
+
+		fill_ldt(&ldt, &ldt_info);
+		if (oldmode)
+			ldt.avl = 0;
 	}
 
-	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
-		error = -EINVAL;
+	mutex_lock(&mm->context.lock);
+
+	old_ldt = mm->context.ldt;
+	oldsize = old_ldt ? old_ldt->size : 0;
+	newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+	error = -ENOMEM;
+	new_ldt = alloc_ldt_struct(newsize);
+	if (!new_ldt)
 		goto out_unlock;
-	}
 
-	fill_ldt(&ldt, &ldt_info);
-	if (oldmode)
-		ldt.avl = 0;
+	if (old_ldt)
+		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+	new_ldt->entries[ldt_info.entry_number] = ldt;
+	finalize_ldt_struct(new_ldt);
 
-	/* Install the new entry ...  */
-install:
-	write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+	install_ldt(mm, new_ldt);
+	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index c3e985d1751c..697f90db0e37 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -110,7 +110,7 @@ static void nmi_max_handler(struct irq_work *w)
 		a->handler, whole_msecs, decimal_msecs);
 }
 
-static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
+static int nmi_handle(unsigned int type, struct pt_regs *regs)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
 	struct nmiaction *a;
@@ -213,7 +213,7 @@ static void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
 	/* check to see if anyone registered against these types of errors */
-	if (nmi_handle(NMI_SERR, regs, false))
+	if (nmi_handle(NMI_SERR, regs))
 		return;
 
 	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
@@ -247,7 +247,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	unsigned long i;
 
 	/* check to see if anyone registered against these types of errors */
-	if (nmi_handle(NMI_IO_CHECK, regs, false))
+	if (nmi_handle(NMI_IO_CHECK, regs))
 		return;
 
 	pr_emerg(
@@ -284,7 +284,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 	 * as only the first one is ever run (unless it can actually determine
 	 * if it caused the NMI)
 	 */
-	handled = nmi_handle(NMI_UNKNOWN, regs, false);
+	handled = nmi_handle(NMI_UNKNOWN, regs);
 	if (handled) {
 		__this_cpu_add(nmi_stats.unknown, handled);
 		return;
@@ -332,7 +332,7 @@ static void default_do_nmi(struct pt_regs *regs)
 
 	__this_cpu_write(last_nmi_rip, regs->ip);
 
-	handled = nmi_handle(NMI_LOCAL, regs, b2b);
+	handled = nmi_handle(NMI_LOCAL, regs);
 	__this_cpu_add(nmi_stats.normal, handled);
 	if (handled) {
 		/*
@@ -408,15 +408,15 @@ static void default_do_nmi(struct pt_regs *regs)
 NOKPROBE_SYMBOL(default_do_nmi);
 
 /*
- * NMIs can hit breakpoints which will cause it to lose its
- * NMI context with the CPU when the breakpoint does an iret.
- */
-#ifdef CONFIG_X86_32
-/*
- * For i386, NMIs use the same stack as the kernel, and we can
- * add a workaround to the iret problem in C (preventing nested
- * NMIs if an NMI takes a trap). Simply have 3 states the NMI
- * can be in:
+ * NMIs can page fault or hit breakpoints which will cause it to lose
+ * its NMI context with the CPU when the breakpoint or page fault does an IRET.
+ *
+ * As a result, NMIs can nest if NMIs get unmasked due an IRET during
+ * NMI processing.  On x86_64, the asm glue protects us from nested NMIs
+ * if the outer NMI came from kernel mode, but we can still nest if the
+ * outer NMI came from user mode.
+ *
+ * To handle these nested NMIs, we have three states:
  *
  *  1) not running
  *  2) executing
@@ -430,15 +430,14 @@ NOKPROBE_SYMBOL(default_do_nmi);
  * (Note, the latch is binary, thus multiple NMIs triggering,
  *  when one is running, are ignored. Only one NMI is restarted.)
  *
- * If an NMI hits a breakpoint that executes an iret, another
- * NMI can preempt it. We do not want to allow this new NMI
- * to run, but we want to execute it when the first one finishes.
- * We set the state to "latched", and the exit of the first NMI will
- * perform a dec_return, if the result is zero (NOT_RUNNING), then
- * it will simply exit the NMI handler. If not, the dec_return
- * would have set the state to NMI_EXECUTING (what we want it to
- * be when we are running). In this case, we simply jump back
- * to rerun the NMI handler again, and restart the 'latched' NMI.
+ * If an NMI executes an iret, another NMI can preempt it. We do not
+ * want to allow this new NMI to run, but we want to execute it when the
+ * first one finishes.  We set the state to "latched", and the exit of
+ * the first NMI will perform a dec_return, if the result is zero
+ * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the
+ * dec_return would have set the state to NMI_EXECUTING (what we want it
+ * to be when we are running). In this case, we simply jump back to
+ * rerun the NMI handler again, and restart the 'latched' NMI.
  *
  * No trap (breakpoint or page fault) should be hit before nmi_restart,
  * thus there is no race between the first check of state for NOT_RUNNING
@@ -461,49 +460,36 @@ enum nmi_states {
 static DEFINE_PER_CPU(enum nmi_states, nmi_state);
 static DEFINE_PER_CPU(unsigned long, nmi_cr2);
 
-#define nmi_nesting_preprocess(regs)					\
-	do {								\
-		if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {	\
-			this_cpu_write(nmi_state, NMI_LATCHED);		\
-			return;						\
-		}							\
-		this_cpu_write(nmi_state, NMI_EXECUTING);		\
-		this_cpu_write(nmi_cr2, read_cr2());			\
-	} while (0);							\
-	nmi_restart:
-
-#define nmi_nesting_postprocess()					\
-	do {								\
-		if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))	\
-			write_cr2(this_cpu_read(nmi_cr2));		\
-		if (this_cpu_dec_return(nmi_state))			\
-			goto nmi_restart;				\
-	} while (0)
-#else /* x86_64 */
+#ifdef CONFIG_X86_64
 /*
- * In x86_64 things are a bit more difficult. This has the same problem
- * where an NMI hitting a breakpoint that calls iret will remove the
- * NMI context, allowing a nested NMI to enter. What makes this more
- * difficult is that both NMIs and breakpoints have their own stack.
- * When a new NMI or breakpoint is executed, the stack is set to a fixed
- * point. If an NMI is nested, it will have its stack set at that same
- * fixed address that the first NMI had, and will start corrupting the
- * stack. This is handled in entry_64.S, but the same problem exists with
- * the breakpoint stack.
+ * In x86_64, we need to handle breakpoint -> NMI -> breakpoint.  Without
+ * some care, the inner breakpoint will clobber the outer breakpoint's
+ * stack.
  *
- * If a breakpoint is being processed, and the debug stack is being used,
- * if an NMI comes in and also hits a breakpoint, the stack pointer
- * will be set to the same fixed address as the breakpoint that was
- * interrupted, causing that stack to be corrupted. To handle this case,
- * check if the stack that was interrupted is the debug stack, and if
- * so, change the IDT so that new breakpoints will use the current stack
- * and not switch to the fixed address. On return of the NMI, switch back
- * to the original IDT.
+ * If a breakpoint is being processed, and the debug stack is being
+ * used, if an NMI comes in and also hits a breakpoint, the stack
+ * pointer will be set to the same fixed address as the breakpoint that
+ * was interrupted, causing that stack to be corrupted. To handle this
+ * case, check if the stack that was interrupted is the debug stack, and
+ * if so, change the IDT so that new breakpoints will use the current
+ * stack and not switch to the fixed address. On return of the NMI,
+ * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+#endif
 
-static inline void nmi_nesting_preprocess(struct pt_regs *regs)
+dotraplinkage notrace void
+do_nmi(struct pt_regs *regs, long error_code)
 {
+	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
+		this_cpu_write(nmi_state, NMI_LATCHED);
+		return;
+	}
+	this_cpu_write(nmi_state, NMI_EXECUTING);
+	this_cpu_write(nmi_cr2, read_cr2());
+nmi_restart:
+
+#ifdef CONFIG_X86_64
 	/*
 	 * If we interrupted a breakpoint, it is possible that
 	 * the nmi handler will have breakpoints too. We need to
@@ -514,22 +500,8 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs)
 		debug_stack_set_zero();
 		this_cpu_write(update_debug_stack, 1);
 	}
-}
-
-static inline void nmi_nesting_postprocess(void)
-{
-	if (unlikely(this_cpu_read(update_debug_stack))) {
-		debug_stack_reset();
-		this_cpu_write(update_debug_stack, 0);
-	}
-}
 #endif
 
-dotraplinkage notrace void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_nesting_preprocess(regs);
-
 	nmi_enter();
 
 	inc_irq_stat(__nmi_count);
@@ -539,8 +511,17 @@ do_nmi(struct pt_regs *regs, long error_code)
 
 	nmi_exit();
 
-	/* On i386, may loop back to preprocess */
-	nmi_nesting_postprocess();
+#ifdef CONFIG_X86_64
+	if (unlikely(this_cpu_read(update_debug_stack))) {
+		debug_stack_reset();
+		this_cpu_write(update_debug_stack, 0);
+	}
+#endif
+
+	if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+		write_cr2(this_cpu_read(nmi_cr2));
+	if (this_cpu_dec_return(nmi_state))
+		goto nmi_restart;
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 58bcfb67c01f..f68e48f5f6c2 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -351,9 +351,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 	.wbinvd = native_wbinvd,
 	.read_msr = native_read_msr_safe,
 	.write_msr = native_write_msr_safe,
-	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
-	.read_tscp = native_read_tscp,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,
 	.load_gdt = native_load_gdt,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index e1b013696dde..c89f50a76e97 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -10,7 +10,6 @@ DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
-DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
@@ -52,7 +51,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
-		PATCH_SITE(pv_cpu_ops, read_tsc);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
 			if (pv_is_native_spin_unlock()) {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9cad694ed7c4..6d0e62ae8516 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -29,6 +29,8 @@
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
 #include <asm/tlbflush.h>
+#include <asm/mce.h>
+#include <asm/vm86.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -81,7 +83,7 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister);
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	*dst = *src;
+	memcpy(dst, src, arch_task_struct_size);
 
 	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }
@@ -110,6 +112,8 @@ void exit_thread(void)
 		kfree(bp);
 	}
 
+	free_vm86(t);
+
 	fpu__drop(fpu);
 }
 
@@ -319,6 +323,7 @@ void stop_this_cpu(void *dummy)
 	 */
 	set_cpu_online(smp_processor_id(), false);
 	disable_local_APIC();
+	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 
 	for (;;)
 		halt();
@@ -408,6 +413,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 static void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
 			smp_mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
@@ -419,6 +425,7 @@ static void mwait_idle(void)
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 	}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f73c962fe636..c13df2c735f8 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -53,6 +53,7 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
+#include <asm/vm86.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71d7849a07f7..3c1bbcf12924 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,13 +121,15 @@ void __show_regs(struct pt_regs *regs, int all)
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
-		if (dead_task->mm->context.size) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt,
-				dead_task->mm->context.size);
+				dead_task->mm->context.ldt->size);
 			BUG();
 		}
+#endif
 	}
 }
 
@@ -248,8 +250,8 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 			    __USER_CS, __USER_DS, 0);
 }
 
-#ifdef CONFIG_IA32_EMULATION
-void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
+#ifdef CONFIG_COMPAT
+void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
 {
 	start_thread_common(regs, new_ip, new_sp,
 			    test_thread_flag(TIF_X32)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 9be72bc3613f..558f50edebca 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -37,12 +37,10 @@
 #include <asm/proto.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/traps.h>
+#include <asm/syscall.h>
 
 #include "tls.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
 enum x86_regset {
 	REGSET_GENERAL,
 	REGSET_FP,
@@ -1123,6 +1121,73 @@ static int genregs32_set(struct task_struct *target,
 	return ret;
 }
 
+static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request,
+			     compat_ulong_t caddr, compat_ulong_t cdata)
+{
+	unsigned long addr = caddr;
+	unsigned long data = cdata;
+	void __user *datap = compat_ptr(data);
+	int ret;
+	__u32 val;
+
+	switch (request) {
+	case PTRACE_PEEKUSR:
+		ret = getreg32(child, addr, &val);
+		if (ret == 0)
+			ret = put_user(val, (__u32 __user *)datap);
+		break;
+
+	case PTRACE_POKEUSR:
+		ret = putreg32(child, addr, data);
+		break;
+
+	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
+		return copy_regset_to_user(child, &user_x86_32_view,
+					   REGSET_GENERAL,
+					   0, sizeof(struct user_regs_struct32),
+					   datap);
+
+	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
+		return copy_regset_from_user(child, &user_x86_32_view,
+					     REGSET_GENERAL, 0,
+					     sizeof(struct user_regs_struct32),
+					     datap);
+
+	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
+		return copy_regset_to_user(child, &user_x86_32_view,
+					   REGSET_FP, 0,
+					   sizeof(struct user_i387_ia32_struct),
+					   datap);
+
+	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
+		return copy_regset_from_user(
+			child, &user_x86_32_view, REGSET_FP,
+			0, sizeof(struct user_i387_ia32_struct), datap);
+
+	case PTRACE_GETFPXREGS:	/* Get the child extended FPU state. */
+		return copy_regset_to_user(child, &user_x86_32_view,
+					   REGSET_XFP, 0,
+					   sizeof(struct user32_fxsr_struct),
+					   datap);
+
+	case PTRACE_SETFPXREGS:	/* Set the child extended FPU state. */
+		return copy_regset_from_user(child, &user_x86_32_view,
+					     REGSET_XFP, 0,
+					     sizeof(struct user32_fxsr_struct),
+					     datap);
+
+	case PTRACE_GET_THREAD_AREA:
+	case PTRACE_SET_THREAD_AREA:
+		return arch_ptrace(child, request, addr, data);
+
+	default:
+		return compat_ptrace_request(child, request, addr, data);
+	}
+
+	return ret;
+}
+#endif /* CONFIG_IA32_EMULATION */
+
 #ifdef CONFIG_X86_X32_ABI
 static long x32_arch_ptrace(struct task_struct *child,
 			    compat_long_t request, compat_ulong_t caddr,
@@ -1211,78 +1276,21 @@ static long x32_arch_ptrace(struct task_struct *child,
 }
 #endif
 
+#ifdef CONFIG_COMPAT
 long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			compat_ulong_t caddr, compat_ulong_t cdata)
 {
-	unsigned long addr = caddr;
-	unsigned long data = cdata;
-	void __user *datap = compat_ptr(data);
-	int ret;
-	__u32 val;
-
 #ifdef CONFIG_X86_X32_ABI
 	if (!is_ia32_task())
 		return x32_arch_ptrace(child, request, caddr, cdata);
 #endif
-
-	switch (request) {
-	case PTRACE_PEEKUSR:
-		ret = getreg32(child, addr, &val);
-		if (ret == 0)
-			ret = put_user(val, (__u32 __user *)datap);
-		break;
-
-	case PTRACE_POKEUSR:
-		ret = putreg32(child, addr, data);
-		break;
-
-	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
-		return copy_regset_to_user(child, &user_x86_32_view,
-					   REGSET_GENERAL,
-					   0, sizeof(struct user_regs_struct32),
-					   datap);
-
-	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
-		return copy_regset_from_user(child, &user_x86_32_view,
-					     REGSET_GENERAL, 0,
-					     sizeof(struct user_regs_struct32),
-					     datap);
-
-	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
-		return copy_regset_to_user(child, &user_x86_32_view,
-					   REGSET_FP, 0,
-					   sizeof(struct user_i387_ia32_struct),
-					   datap);
-
-	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
-		return copy_regset_from_user(
-			child, &user_x86_32_view, REGSET_FP,
-			0, sizeof(struct user_i387_ia32_struct), datap);
-
-	case PTRACE_GETFPXREGS:	/* Get the child extended FPU state. */
-		return copy_regset_to_user(child, &user_x86_32_view,
-					   REGSET_XFP, 0,
-					   sizeof(struct user32_fxsr_struct),
-					   datap);
-
-	case PTRACE_SETFPXREGS:	/* Set the child extended FPU state. */
-		return copy_regset_from_user(child, &user_x86_32_view,
-					     REGSET_XFP, 0,
-					     sizeof(struct user32_fxsr_struct),
-					     datap);
-
-	case PTRACE_GET_THREAD_AREA:
-	case PTRACE_SET_THREAD_AREA:
-		return arch_ptrace(child, request, addr, data);
-
-	default:
-		return compat_ptrace_request(child, request, addr, data);
-	}
-
-	return ret;
+#ifdef CONFIG_IA32_EMULATION
+	return ia32_arch_ptrace(child, request, caddr, cdata);
+#else
+	return 0;
+#endif
 }
-
-#endif	/* CONFIG_IA32_EMULATION */
+#endif	/* CONFIG_COMPAT */
 
 #ifdef CONFIG_X86_64
 
@@ -1434,201 +1442,3 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 	/* Send us the fake SIGTRAP */
 	force_sig_info(SIGTRAP, &info, tsk);
 }
-
-static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
-{
-#ifdef CONFIG_X86_64
-	if (arch == AUDIT_ARCH_X86_64) {
-		audit_syscall_entry(regs->orig_ax, regs->di,
-				    regs->si, regs->dx, regs->r10);
-	} else
-#endif
-	{
-		audit_syscall_entry(regs->orig_ax, regs->bx,
-				    regs->cx, regs->dx, regs->si);
-	}
-}
-
-/*
- * We can return 0 to resume the syscall or anything else to go to phase
- * 2.  If we resume the syscall, we need to put something appropriate in
- * regs->orig_ax.
- *
- * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax
- * are fully functional.
- *
- * For phase 2's benefit, our return value is:
- * 0:			resume the syscall
- * 1:			go to phase 2; no seccomp phase 2 needed
- * anything else:	go to phase 2; pass return value to seccomp
- */
-unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
-{
-	unsigned long ret = 0;
-	u32 work;
-
-	BUG_ON(regs != task_pt_regs(current));
-
-	work = ACCESS_ONCE(current_thread_info()->flags) &
-		_TIF_WORK_SYSCALL_ENTRY;
-
-	/*
-	 * If TIF_NOHZ is set, we are required to call user_exit() before
-	 * doing anything that could touch RCU.
-	 */
-	if (work & _TIF_NOHZ) {
-		user_exit();
-		work &= ~_TIF_NOHZ;
-	}
-
-#ifdef CONFIG_SECCOMP
-	/*
-	 * Do seccomp first -- it should minimize exposure of other
-	 * code, and keeping seccomp fast is probably more valuable
-	 * than the rest of this.
-	 */
-	if (work & _TIF_SECCOMP) {
-		struct seccomp_data sd;
-
-		sd.arch = arch;
-		sd.nr = regs->orig_ax;
-		sd.instruction_pointer = regs->ip;
-#ifdef CONFIG_X86_64
-		if (arch == AUDIT_ARCH_X86_64) {
-			sd.args[0] = regs->di;
-			sd.args[1] = regs->si;
-			sd.args[2] = regs->dx;
-			sd.args[3] = regs->r10;
-			sd.args[4] = regs->r8;
-			sd.args[5] = regs->r9;
-		} else
-#endif
-		{
-			sd.args[0] = regs->bx;
-			sd.args[1] = regs->cx;
-			sd.args[2] = regs->dx;
-			sd.args[3] = regs->si;
-			sd.args[4] = regs->di;
-			sd.args[5] = regs->bp;
-		}
-
-		BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0);
-		BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1);
-
-		ret = seccomp_phase1(&sd);
-		if (ret == SECCOMP_PHASE1_SKIP) {
-			regs->orig_ax = -1;
-			ret = 0;
-		} else if (ret != SECCOMP_PHASE1_OK) {
-			return ret;  /* Go directly to phase 2 */
-		}
-
-		work &= ~_TIF_SECCOMP;
-	}
-#endif
-
-	/* Do our best to finish without phase 2. */
-	if (work == 0)
-		return ret;  /* seccomp and/or nohz only (ret == 0 here) */
-
-#ifdef CONFIG_AUDITSYSCALL
-	if (work == _TIF_SYSCALL_AUDIT) {
-		/*
-		 * If there is no more work to be done except auditing,
-		 * then audit in phase 1.  Phase 2 always audits, so, if
-		 * we audit here, then we can't go on to phase 2.
-		 */
-		do_audit_syscall_entry(regs, arch);
-		return 0;
-	}
-#endif
-
-	return 1;  /* Something is enabled that we can't handle in phase 1 */
-}
-
-/* Returns the syscall nr to run (which should match regs->orig_ax). */
-long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
-				unsigned long phase1_result)
-{
-	long ret = 0;
-	u32 work = ACCESS_ONCE(current_thread_info()->flags) &
-		_TIF_WORK_SYSCALL_ENTRY;
-
-	BUG_ON(regs != task_pt_regs(current));
-
-	/*
-	 * If we stepped into a sysenter/syscall insn, it trapped in
-	 * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
-	 * If user-mode had set TF itself, then it's still clear from
-	 * do_debug() and we need to set it again to restore the user
-	 * state.  If we entered on the slow path, TF was already set.
-	 */
-	if (work & _TIF_SINGLESTEP)
-		regs->flags |= X86_EFLAGS_TF;
-
-#ifdef CONFIG_SECCOMP
-	/*
-	 * Call seccomp_phase2 before running the other hooks so that
-	 * they can see any changes made by a seccomp tracer.
-	 */
-	if (phase1_result > 1 && seccomp_phase2(phase1_result)) {
-		/* seccomp failures shouldn't expose any additional code. */
-		return -1;
-	}
-#endif
-
-	if (unlikely(work & _TIF_SYSCALL_EMU))
-		ret = -1L;
-
-	if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
-	    tracehook_report_syscall_entry(regs))
-		ret = -1L;
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_enter(regs, regs->orig_ax);
-
-	do_audit_syscall_entry(regs, arch);
-
-	return ret ?: regs->orig_ax;
-}
-
-long syscall_trace_enter(struct pt_regs *regs)
-{
-	u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
-	unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch);
-
-	if (phase1_result == 0)
-		return regs->orig_ax;
-	else
-		return syscall_trace_enter_phase2(regs, arch, phase1_result);
-}
-
-void syscall_trace_leave(struct pt_regs *regs)
-{
-	bool step;
-
-	/*
-	 * We may come here right after calling schedule_user()
-	 * or do_notify_resume(), in which case we can be in RCU
-	 * user mode.
-	 */
-	user_exit();
-
-	audit_syscall_exit(regs);
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->ax);
-
-	/*
-	 * If TIF_SYSCALL_EMU is set, we only get here because of
-	 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
-	 * We already reported this syscall instruction in
-	 * syscall_trace_enter().
-	 */
-	step = unlikely(test_thread_flag(TIF_SINGLESTEP)) &&
-			!test_thread_flag(TIF_SYSCALL_EMU);
-	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
-		tracehook_report_syscall_exit(regs, step);
-
-	user_enter();
-}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 80f874bf999e..b143c2d04420 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -916,11 +916,6 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_X86_32
 	apm_info.bios = boot_params.apm_bios_info;
 	ist_info = boot_params.ist_info;
-	if (boot_params.sys_desc_table.length != 0) {
-		machine_id = boot_params.sys_desc_table.table[0];
-		machine_submodel_id = boot_params.sys_desc_table.table[1];
-		BIOS_revision = boot_params.sys_desc_table.table[2];
-	}
 #endif
 	saved_video_mode = boot_params.hdr.vid_mode;
 	bootloader_type = boot_params.hdr.type_of_loader;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 206996c1669d..da52e6bb5c7f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -31,11 +31,11 @@
 #include <asm/vdso.h>
 #include <asm/mce.h>
 #include <asm/sighandling.h>
+#include <asm/vm86.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
-#include <asm/sys_ia32.h>
 #endif /* CONFIG_X86_64 */
 
 #include <asm/syscall.h>
@@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		COPY(r15);
 #endif /* CONFIG_X86_64 */
 
+#ifdef CONFIG_X86_32
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+		/* Kernel saves and restores only the CS segment register on signals,
+		 * which is the bare minimum needed to allow mixed 32/64-bit code.
+		 * App's signal handler can save/restore other segments if needed. */
+		COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
 
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 #else /* !CONFIG_X86_32 */
 		put_user_ex(regs->flags, &sc->flags);
 		put_user_ex(regs->cs, &sc->cs);
-		put_user_ex(0, &sc->__pad2);
-		put_user_ex(0, &sc->__pad1);
-		put_user_ex(regs->ss, &sc->ss);
+		put_user_ex(0, &sc->gs);
+		put_user_ex(0, &sc->fs);
 #endif /* CONFIG_X86_32 */
 
 		put_user_ex(fpstate, &sc->fpstate);
@@ -451,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	regs->sp = (unsigned long)frame;
 
-	/*
-	 * Set up the CS and SS registers to run signal handlers in
-	 * 64-bit mode, even if the handler happens to be interrupting
-	 * 32-bit or 16-bit code.
-	 *
-	 * SS is subtle.  In 64-bit mode, we don't need any particular
-	 * SS descriptor, but we do need SS to be valid.  It's possible
-	 * that the old SS is entirely bogus -- this can happen if the
-	 * signal we're trying to deliver is #GP or #SS caused by a bad
-	 * SS value.
-	 */
+	/* Set up the CS register to run signal handlers in 64-bit mode,
+	   even if the handler happens to be interrupting 32-bit code. */
 	regs->cs = __USER_CS;
-	regs->ss = __USER_DS;
 
 	return 0;
 }
@@ -636,6 +632,9 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	bool stepping, failed;
 	struct fpu *fpu = &current->thread.fpu;
 
+	if (v8086_mode(regs))
+		save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
+
 	/* Are we from a system call? */
 	if (syscall_get_nr(current, regs) >= 0) {
 		/* If so, check system call restarting.. */
@@ -701,7 +700,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-static void do_signal(struct pt_regs *regs)
+void do_signal(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 
@@ -736,32 +735,6 @@ static void do_signal(struct pt_regs *regs)
 	restore_saved_sigmask();
 }
 
-/*
- * notification of userspace execution resumption
- * - triggered by the TIF_WORK_MASK flags
- */
-__visible void
-do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
-{
-	user_exit();
-
-	if (thread_info_flags & _TIF_UPROBE)
-		uprobe_notify_resume(regs);
-
-	/* deal with pending signal delivery */
-	if (thread_info_flags & _TIF_SIGPENDING)
-		do_signal(regs);
-
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
-		fire_user_return_notifiers();
-
-	user_enter();
-}
-
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 {
 	struct task_struct *me = current;
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
new file mode 100644
index 000000000000..dc3c0b1c816f
--- /dev/null
+++ b/arch/x86/kernel/signal_compat.c
@@ -0,0 +1,95 @@
+#include <linux/compat.h>
+#include <linux/uaccess.h>
+
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
+{
+	int err = 0;
+	bool ia32 = test_thread_flag(TIF_IA32);
+
+	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
+		return -EFAULT;
+
+	put_user_try {
+		/* If you change siginfo_t structure, please make sure that
+		   this code is fixed accordingly.
+		   It should never copy any pad contained in the structure
+		   to avoid security leaks, but must copy the generic
+		   3 ints plus the relevant union member.  */
+		put_user_ex(from->si_signo, &to->si_signo);
+		put_user_ex(from->si_errno, &to->si_errno);
+		put_user_ex((short)from->si_code, &to->si_code);
+
+		if (from->si_code < 0) {
+			put_user_ex(from->si_pid, &to->si_pid);
+			put_user_ex(from->si_uid, &to->si_uid);
+			put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
+		} else {
+			/*
+			 * First 32bits of unions are always present:
+			 * si_pid === si_band === si_tid === si_addr(LS half)
+			 */
+			put_user_ex(from->_sifields._pad[0],
+					  &to->_sifields._pad[0]);
+			switch (from->si_code >> 16) {
+			case __SI_FAULT >> 16:
+				break;
+			case __SI_SYS >> 16:
+				put_user_ex(from->si_syscall, &to->si_syscall);
+				put_user_ex(from->si_arch, &to->si_arch);
+				break;
+			case __SI_CHLD >> 16:
+				if (ia32) {
+					put_user_ex(from->si_utime, &to->si_utime);
+					put_user_ex(from->si_stime, &to->si_stime);
+				} else {
+					put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
+					put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
+				}
+				put_user_ex(from->si_status, &to->si_status);
+				/* FALL THROUGH */
+			default:
+			case __SI_KILL >> 16:
+				put_user_ex(from->si_uid, &to->si_uid);
+				break;
+			case __SI_POLL >> 16:
+				put_user_ex(from->si_fd, &to->si_fd);
+				break;
+			case __SI_TIMER >> 16:
+				put_user_ex(from->si_overrun, &to->si_overrun);
+				put_user_ex(ptr_to_compat(from->si_ptr),
+					    &to->si_ptr);
+				break;
+				 /* This is not generated by the kernel as of now.  */
+			case __SI_RT >> 16:
+			case __SI_MESGQ >> 16:
+				put_user_ex(from->si_uid, &to->si_uid);
+				put_user_ex(from->si_int, &to->si_int);
+				break;
+			}
+		}
+	} put_user_catch(err);
+
+	return err;
+}
+
+int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
+{
+	int err = 0;
+	u32 ptr32;
+
+	if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
+		return -EFAULT;
+
+	get_user_try {
+		get_user_ex(to->si_signo, &from->si_signo);
+		get_user_ex(to->si_errno, &from->si_errno);
+		get_user_ex(to->si_code, &from->si_code);
+
+		get_user_ex(to->si_pid, &from->si_pid);
+		get_user_ex(to->si_uid, &from->si_uid);
+		get_user_ex(ptr32, &from->si_ptr);
+		to->si_ptr = compat_ptr(ptr32);
+	} get_user_catch(err);
+
+	return err;
+}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 15aaa69bbb5e..12c8286206ce 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -30,6 +30,7 @@
 #include <asm/proto.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
+#include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
@@ -243,6 +244,7 @@ static void native_stop_other_cpus(int wait)
 finish:
 	local_irq_save(flags);
 	disable_local_APIC();
+	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 	local_irq_restore(flags);
 }
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8add66b22f33..e0c198e5f920 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -97,8 +97,6 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
-atomic_t init_deasserted;
-
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
@@ -146,16 +144,11 @@ static void smp_callin(void)
 
 	/*
 	 * If waken up by an INIT in an 82489DX configuration
-	 * we may get here before an INIT-deassert IPI reaches
-	 * our local APIC.  We have to wait for the IPI or we'll
-	 * lock up on an APIC access.
-	 *
-	 * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
+	 * cpu_callout_mask guarantees we don't get here before
+	 * an INIT_deassert IPI reaches our local APIC, so it is
+	 * now safe to touch our local APIC.
 	 */
 	cpuid = smp_processor_id();
-	if (apic->wait_for_init_deassert && cpuid)
-		while (!atomic_read(&init_deasserted))
-			cpu_relax();
 
 	/*
 	 * (This works even if the APIC is not enabled.)
@@ -171,11 +164,6 @@ static void smp_callin(void)
 	apic_ap_setup();
 
 	/*
-	 * Need to setup vector mappings before we enable interrupts.
-	 */
-	setup_vector_irq(smp_processor_id());
-
-	/*
 	 * Save our processor parameters. Note: this information
 	 * is needed for clock calibration.
 	 */
@@ -239,18 +227,13 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
-	 * Enable the espfix hack for this CPU
-	 */
-#ifdef CONFIG_X86_ESPFIX64
-	init_espfix_ap();
-#endif
-
-	/*
-	 * We need to hold vector_lock so there the set of online cpus
-	 * does not change while we are assigning vectors to cpus.  Holding
-	 * this lock ensures we don't half assign or remove an irq from a cpu.
+	 * Lock vector_lock and initialize the vectors on this cpu
+	 * before setting the cpu online. We must set it online with
+	 * vector_lock held to prevent a concurrent setup/teardown
+	 * from seeing a half valid vector space.
 	 */
 	lock_vector_lock();
+	setup_vector_irq(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
 	cpu_set_state_online(smp_processor_id());
@@ -630,7 +613,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	send_status = safe_apic_wait_icr_idle();
 
 	mb();
-	atomic_set(&init_deasserted, 1);
 
 	/*
 	 * Should we send STARTUP IPIs ?
@@ -675,7 +657,8 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		/*
 		 * Give the other CPU some time to accept the IPI.
 		 */
-		udelay(300);
+		if (init_udelay)
+			udelay(300);
 
 		pr_debug("Startup point 1\n");
 
@@ -685,7 +668,8 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		/*
 		 * Give the other CPU some time to accept the IPI.
 		 */
-		udelay(200);
+		if (init_udelay)
+			udelay(200);
 
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
@@ -854,6 +838,13 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	initial_code = (unsigned long)start_secondary;
 	stack_start  = idle->thread.sp;
 
+	/*
+	 * Enable the espfix hack for this CPU
+	*/
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap(cpu);
+#endif
+
 	/* So we see what's up */
 	announce_cpu(cpu, apicid);
 
@@ -862,8 +853,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	 * the targeted processor.
 	 */
 
-	atomic_set(&init_deasserted, 0);
-
 	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
 
 		pr_debug("Setting warm reset code and vector.\n");
@@ -901,7 +890,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 
 	if (!boot_error) {
 		/*
-		 * Wait 10s total for a response from AP
+		 * Wait 10s total for first sign of life from AP
 		 */
 		boot_error = -1;
 		timeout = jiffies + 10*HZ;
@@ -914,7 +903,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 				boot_error = 0;
 				break;
 			}
-			udelay(100);
 			schedule();
 		}
 	}
@@ -930,7 +918,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 			 * for the MTRR work(triggered by the AP coming online)
 			 * to be completed in the stop machine context.
 			 */
-			udelay(100);
 			schedule();
 		}
 	}
@@ -995,8 +982,17 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	common_cpu_up(cpu, tidle);
 
+	/*
+	 * We have to walk the irq descriptors to setup the vector
+	 * space for the cpu which comes online.  Prevent irq
+	 * alloc/free across the bringup.
+	 */
+	irq_lock_sparse();
+
 	err = do_boot_cpu(apicid, cpu, tidle);
+
 	if (err) {
+		irq_unlock_sparse();
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
 		return -EIO;
 	}
@@ -1014,6 +1010,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 		touch_nmi_watchdog();
 	}
 
+	irq_unlock_sparse();
+
 	return 0;
 }
 
@@ -1350,7 +1348,7 @@ static void remove_siblinginfo(int cpu)
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
 }
 
-static void __ref remove_cpu_from_maps(int cpu)
+static void remove_cpu_from_maps(int cpu)
 {
 	set_cpu_online(cpu, false);
 	cpumask_clear_cpu(cpu, cpu_callout_mask);
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d0c0d0..c9a073866ca7 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
+#include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
 {
@@ -17,6 +18,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		return addr;
 	}
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 	/*
 	 * We'll assume that the code segments in the GDT
 	 * are all zero-based. That is largely true: the
@@ -27,13 +29,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		struct desc_struct *desc;
 		unsigned long base;
 
-		seg &= ~7UL;
+		seg >>= 3;
 
 		mutex_lock(&child->mm->context.lock);
-		if (unlikely((seg >> 3) >= child->mm->context.size))
+		if (unlikely(!child->mm->context.ldt ||
+			     seg >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
-			desc = child->mm->context.ldt + seg;
+			desc = &child->mm->context.ldt->entries[seg];
 			base = get_desc_base(desc);
 
 			/* 16-bit code segment? */
@@ -43,6 +46,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		}
 		mutex_unlock(&child->mm->context.lock);
 	}
+#endif
 
 	return addr;
 }
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 649b010da00b..12cbe2b88c0f 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -57,7 +57,7 @@ __setup("cpu0_hotplug", enable_cpu0_hotplug);
  *
  * This is only called for debugging CPU offline/online feature.
  */
-int __ref _debug_hotplug_cpu(int cpu, int action)
+int _debug_hotplug_cpu(int cpu, int action)
 {
 	struct device *dev = get_cpu_device(cpu);
 	int ret;
@@ -104,7 +104,7 @@ static int __init debug_hotplug_cpu(void)
 late_initcall_sync(debug_hotplug_cpu);
 #endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */
 
-int __ref arch_register_cpu(int num)
+int arch_register_cpu(int num)
 {
 	struct cpuinfo_x86 *c = &cpu_data(num);
 
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
index 25b993729f9b..80bb24d9b880 100644
--- a/arch/x86/kernel/trace_clock.c
+++ b/arch/x86/kernel/trace_clock.c
@@ -12,10 +12,5 @@
  */
 u64 notrace trace_clock_x86_tsc(void)
 {
-	u64 ret;
-
-	rdtsc_barrier();
-	rdtscll(ret);
-
-	return ret;
+	return rdtsc_ordered();
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index f5791927aa64..346eec73f7db 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -62,6 +62,7 @@
 #include <asm/fpu/xstate.h>
 #include <asm/trace/mpx.h>
 #include <asm/mpx.h>
+#include <asm/vm86.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -108,13 +109,10 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 	preempt_count_dec();
 }
 
-enum ctx_state ist_enter(struct pt_regs *regs)
+void ist_enter(struct pt_regs *regs)
 {
-	enum ctx_state prev_state;
-
 	if (user_mode(regs)) {
-		/* Other than that, we're just an exception. */
-		prev_state = exception_enter();
+		RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	} else {
 		/*
 		 * We might have interrupted pretty much anything.  In
@@ -123,32 +121,25 @@ enum ctx_state ist_enter(struct pt_regs *regs)
 		 * but we need to notify RCU.
 		 */
 		rcu_nmi_enter();
-		prev_state = CONTEXT_KERNEL;  /* the value is irrelevant. */
 	}
 
 	/*
-	 * We are atomic because we're on the IST stack (or we're on x86_32,
-	 * in which case we still shouldn't schedule).
-	 *
-	 * This must be after exception_enter(), because exception_enter()
-	 * won't do anything if in_interrupt() returns true.
+	 * We are atomic because we're on the IST stack; or we're on
+	 * x86_32, in which case we still shouldn't schedule; or we're
+	 * on x86_64 and entered from user mode, in which case we're
+	 * still atomic unless ist_begin_non_atomic is called.
 	 */
 	preempt_count_add(HARDIRQ_OFFSET);
 
 	/* This code is a bit fragile.  Test it. */
-	rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work");
-
-	return prev_state;
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
 }
 
-void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
+void ist_exit(struct pt_regs *regs)
 {
-	/* Must be before exception_exit. */
 	preempt_count_sub(HARDIRQ_OFFSET);
 
-	if (user_mode(regs))
-		return exception_exit(prev_state);
-	else
+	if (!user_mode(regs))
 		rcu_nmi_exit();
 }
 
@@ -162,7 +153,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
  * a double fault, it can be safe to schedule.  ist_begin_non_atomic()
  * begins a non-atomic section within an ist_enter()/ist_exit() region.
  * Callers are responsible for enabling interrupts themselves inside
- * the non-atomic section, and callers must call is_end_non_atomic()
+ * the non-atomic section, and callers must call ist_end_non_atomic()
  * before ist_exit().
  */
 void ist_begin_non_atomic(struct pt_regs *regs)
@@ -289,17 +280,16 @@ NOKPROBE_SYMBOL(do_trap);
 static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 			  unsigned long trapnr, int signr)
 {
-	enum ctx_state prev_state = exception_enter();
 	siginfo_t info;
 
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
 			NOTIFY_STOP) {
 		conditional_sti(regs);
 		do_trap(trapnr, signr, str, regs, error_code,
 			fill_trap_info(regs, signr, trapnr, &info));
 	}
-
-	exception_exit(prev_state);
 }
 
 #define DO_ERROR(trapnr, signr, str, name)				\
@@ -351,7 +341,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	}
 #endif
 
-	ist_enter(regs);  /* Discard prev_state because we won't return. */
+	ist_enter(regs);
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
 	tsk->thread.error_code = error_code;
@@ -371,14 +361,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
 	const struct bndcsr *bndcsr;
 	siginfo_t *info;
 
-	prev_state = exception_enter();
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
 			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
-		goto exit;
+		return;
 	conditional_sti(regs);
 
 	if (!user_mode(regs))
@@ -435,9 +424,8 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 		die("bounds", regs, error_code);
 	}
 
-exit:
-	exception_exit(prev_state);
 	return;
+
 exit_trap:
 	/*
 	 * This path out is for all the cases where we could not
@@ -447,35 +435,33 @@ exit_trap:
 	 * time..
 	 */
 	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
-	exception_exit(prev_state);
 }
 
 dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk;
-	enum ctx_state prev_state;
 
-	prev_state = exception_enter();
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	conditional_sti(regs);
 
 	if (v8086_mode(regs)) {
 		local_irq_enable();
 		handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
-		goto exit;
+		return;
 	}
 
 	tsk = current;
 	if (!user_mode(regs)) {
 		if (fixup_exception(regs))
-			goto exit;
+			return;
 
 		tsk->thread.error_code = error_code;
 		tsk->thread.trap_nr = X86_TRAP_GP;
 		if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
 			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
 			die("general protection fault", regs, error_code);
-		goto exit;
+		return;
 	}
 
 	tsk->thread.error_code = error_code;
@@ -491,16 +477,12 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	}
 
 	force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
-exit:
-	exception_exit(prev_state);
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
 /* May run on IST stack. */
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 	/*
 	 * ftrace must be first, everything else may cause a recursive crash.
@@ -513,7 +495,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	if (poke_int3_handler(regs))
 		return;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
@@ -539,7 +522,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 exit:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_int3);
 
@@ -615,12 +598,11 @@ NOKPROBE_SYMBOL(fixup_bad_iret);
 dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
-	enum ctx_state prev_state;
 	int user_icebp = 0;
 	unsigned long dr6;
 	int si_code;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	get_debugreg(dr6, 6);
 
@@ -695,7 +677,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug);
 
@@ -747,21 +729,15 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
-
-	prev_state = exception_enter();
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	math_error(regs, error_code, X86_TRAP_MF);
-	exception_exit(prev_state);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
-
-	prev_state = exception_enter();
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	math_error(regs, error_code, X86_TRAP_XF);
-	exception_exit(prev_state);
 }
 
 dotraplinkage void
@@ -773,9 +749,7 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
-
-	prev_state = exception_enter();
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
@@ -786,7 +760,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
 		info.regs = regs;
 		math_emulate(&info);
-		exception_exit(prev_state);
 		return;
 	}
 #endif
@@ -794,7 +767,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
-	exception_exit(prev_state);
 }
 NOKPROBE_SYMBOL(do_device_not_available);
 
@@ -802,9 +774,8 @@ NOKPROBE_SYMBOL(do_device_not_available);
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
 	siginfo_t info;
-	enum ctx_state prev_state;
 
-	prev_state = exception_enter();
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	local_irq_enable();
 
 	info.si_signo = SIGILL;
@@ -816,7 +787,6 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
 			&info);
 	}
-	exception_exit(prev_state);
 }
 #endif
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 505449700e0c..c8d52cb4cb6e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -38,7 +38,7 @@ static int __read_mostly tsc_unstable;
    erroneous rdtsc usage on !cpu_has_tsc processors */
 static int __read_mostly tsc_disabled = -1;
 
-static struct static_key __use_tsc = STATIC_KEY_INIT;
+static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
@@ -248,7 +248,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 
 	data = cyc2ns_write_begin(cpu);
 
-	rdtscll(tsc_now);
+	tsc_now = rdtsc();
 	ns_now = cycles_2_ns(tsc_now);
 
 	/*
@@ -274,7 +274,12 @@ done:
  */
 u64 native_sched_clock(void)
 {
-	u64 tsc_now;
+	if (static_branch_likely(&__use_tsc)) {
+		u64 tsc_now = rdtsc();
+
+		/* return the value in ns */
+		return cycles_2_ns(tsc_now);
+	}
 
 	/*
 	 * Fall back to jiffies if there's no TSC available:
@@ -284,16 +289,17 @@ u64 native_sched_clock(void)
 	 *   very important for it to be as fast as the platform
 	 *   can achieve it. )
 	 */
-	if (!static_key_false(&__use_tsc)) {
-		/* No locking but a rare wrong value is not a big deal: */
-		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
-	}
 
-	/* read the Time Stamp Counter: */
-	rdtscll(tsc_now);
+	/* No locking but a rare wrong value is not a big deal: */
+	return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
+}
 
-	/* return the value in ns */
-	return cycles_2_ns(tsc_now);
+/*
+ * Generate a sched_clock if you already have a TSC value.
+ */
+u64 native_sched_clock_from_tsc(u64 tsc)
+{
+	return cycles_2_ns(tsc);
 }
 
 /* We need to define a real function for sched_clock, to override the
@@ -308,12 +314,6 @@ unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
 #endif
 
-unsigned long long native_read_tsc(void)
-{
-	return __native_read_tsc();
-}
-EXPORT_SYMBOL(native_read_tsc);
-
 int check_tsc_unstable(void)
 {
 	return tsc_unstable;
@@ -598,10 +598,19 @@ static unsigned long quick_pit_calibrate(void)
 			if (!pit_expect_msb(0xff-i, &delta, &d2))
 				break;
 
+			delta -= tsc;
+
+			/*
+			 * Extrapolate the error and fail fast if the error will
+			 * never be below 500 ppm.
+			 */
+			if (i == 1 &&
+			    d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11)
+				return 0;
+
 			/*
 			 * Iterate until the error is less than 500 ppm
 			 */
-			delta -= tsc;
 			if (d1+d2 >= delta >> 11)
 				continue;
 
@@ -967,7 +976,7 @@ static struct clocksource clocksource_tsc;
  */
 static cycle_t read_tsc(struct clocksource *cs)
 {
-	return (cycle_t)get_cycles();
+	return (cycle_t)rdtsc_ordered();
 }
 
 /*
@@ -1201,7 +1210,7 @@ void __init tsc_init(void)
 	/* now allow native_sched_clock() to use rdtsc */
 
 	tsc_disabled = 0;
-	static_key_slow_inc(&__use_tsc);
+	static_branch_enable(&__use_tsc);
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index dd8d0791dfb5..78083bf23ed1 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -39,16 +39,15 @@ static cycles_t max_warp;
 static int nr_warps;
 
 /*
- * TSC-warp measurement loop running on both CPUs:
+ * TSC-warp measurement loop running on both CPUs.  This is not called
+ * if there is no TSC.
  */
 static void check_tsc_warp(unsigned int timeout)
 {
 	cycles_t start, now, prev, end;
 	int i;
 
-	rdtsc_barrier();
-	start = get_cycles();
-	rdtsc_barrier();
+	start = rdtsc_ordered();
 	/*
 	 * The measurement runs for 'timeout' msecs:
 	 */
@@ -63,9 +62,7 @@ static void check_tsc_warp(unsigned int timeout)
 		 */
 		arch_spin_lock(&sync_lock);
 		prev = last_tsc;
-		rdtsc_barrier();
-		now = get_cycles();
-		rdtsc_barrier();
+		now = rdtsc_ordered();
 		last_tsc = now;
 		arch_spin_unlock(&sync_lock);
 
@@ -126,7 +123,7 @@ void check_tsc_sync_source(int cpu)
 
 	/*
 	 * No need to check if we already know that the TSC is not
-	 * synchronized:
+	 * synchronized or if we have no TSC.
 	 */
 	if (unsynchronized_tsc())
 		return;
@@ -190,6 +187,7 @@ void check_tsc_sync_target(void)
 {
 	int cpus = 2;
 
+	/* Also aborts if there is no TSC. */
 	if (unsynchronized_tsc() || tsc_clocksource_reliable)
 		return;
 
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 66476244731e..bf4db6eaec8f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -985,3 +985,12 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
 
 	return -1;
 }
+
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+				struct pt_regs *regs)
+{
+	if (ctx == RP_CHECK_CALL) /* sp was just decremented by "call" insn */
+		return regs->sp < ret->stack;
+	else
+		return regs->sp <= ret->stack;
+}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index fc9db6ef2a95..abd8b856bd2b 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -44,11 +44,14 @@
 #include <linux/ptrace.h>
 #include <linux/audit.h>
 #include <linux/stddef.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
 #include <asm/irq.h>
+#include <asm/traps.h>
+#include <asm/vm86.h>
 
 /*
  * Known problems:
@@ -66,10 +69,6 @@
  */
 
 
-#define KVM86	((struct kernel_vm86_struct *)regs)
-#define VMPI	KVM86->vm86plus
-
-
 /*
  * 8- and 16-bit register defines..
  */
@@ -81,8 +80,8 @@
 /*
  * virtual flags (16 and 32-bit versions)
  */
-#define VFLAGS	(*(unsigned short *)&(current->thread.v86flags))
-#define VEFLAGS	(current->thread.v86flags)
+#define VFLAGS	(*(unsigned short *)&(current->thread.vm86->veflags))
+#define VEFLAGS	(current->thread.vm86->veflags)
 
 #define set_flags(X, new, mask) \
 ((X) = ((X) & ~(mask)) | ((new) & (mask)))
@@ -90,46 +89,13 @@
 #define SAFE_MASK	(0xDD5)
 #define RETURN_MASK	(0xDFF)
 
-/* convert kernel_vm86_regs to vm86_regs */
-static int copy_vm86_regs_to_user(struct vm86_regs __user *user,
-				  const struct kernel_vm86_regs *regs)
-{
-	int ret = 0;
-
-	/*
-	 * kernel_vm86_regs is missing gs, so copy everything up to
-	 * (but not including) orig_eax, and then rest including orig_eax.
-	 */
-	ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_ax));
-	ret += copy_to_user(&user->orig_eax, &regs->pt.orig_ax,
-			    sizeof(struct kernel_vm86_regs) -
-			    offsetof(struct kernel_vm86_regs, pt.orig_ax));
-
-	return ret;
-}
-
-/* convert vm86_regs to kernel_vm86_regs */
-static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs,
-				    const struct vm86_regs __user *user,
-				    unsigned extra)
-{
-	int ret = 0;
-
-	/* copy ax-fs inclusive */
-	ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.orig_ax));
-	/* copy orig_ax-__gsh+extra */
-	ret += copy_from_user(&regs->pt.orig_ax, &user->orig_eax,
-			      sizeof(struct kernel_vm86_regs) -
-			      offsetof(struct kernel_vm86_regs, pt.orig_ax) +
-			      extra);
-	return ret;
-}
-
-struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs)
+void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 {
 	struct tss_struct *tss;
-	struct pt_regs *ret;
-	unsigned long tmp;
+	struct task_struct *tsk = current;
+	struct vm86plus_struct __user *user;
+	struct vm86 *vm86 = current->thread.vm86;
+	long err = 0;
 
 	/*
 	 * This gets called from entry.S with interrupts disabled, but
@@ -138,31 +104,57 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs)
 	 */
 	local_irq_enable();
 
-	if (!current->thread.vm86_info) {
-		pr_alert("no vm86_info: BAD\n");
+	if (!vm86 || !vm86->user_vm86) {
+		pr_alert("no user_vm86: BAD\n");
 		do_exit(SIGSEGV);
 	}
-	set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask);
-	tmp = copy_vm86_regs_to_user(&current->thread.vm86_info->regs, regs);
-	tmp += put_user(current->thread.screen_bitmap, &current->thread.vm86_info->screen_bitmap);
-	if (tmp) {
-		pr_alert("could not access userspace vm86_info\n");
+	set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask);
+	user = vm86->user_vm86;
+
+	if (!access_ok(VERIFY_WRITE, user, vm86->vm86plus.is_vm86pus ?
+		       sizeof(struct vm86plus_struct) :
+		       sizeof(struct vm86_struct))) {
+		pr_alert("could not access userspace vm86 info\n");
+		do_exit(SIGSEGV);
+	}
+
+	put_user_try {
+		put_user_ex(regs->pt.bx, &user->regs.ebx);
+		put_user_ex(regs->pt.cx, &user->regs.ecx);
+		put_user_ex(regs->pt.dx, &user->regs.edx);
+		put_user_ex(regs->pt.si, &user->regs.esi);
+		put_user_ex(regs->pt.di, &user->regs.edi);
+		put_user_ex(regs->pt.bp, &user->regs.ebp);
+		put_user_ex(regs->pt.ax, &user->regs.eax);
+		put_user_ex(regs->pt.ip, &user->regs.eip);
+		put_user_ex(regs->pt.cs, &user->regs.cs);
+		put_user_ex(regs->pt.flags, &user->regs.eflags);
+		put_user_ex(regs->pt.sp, &user->regs.esp);
+		put_user_ex(regs->pt.ss, &user->regs.ss);
+		put_user_ex(regs->es, &user->regs.es);
+		put_user_ex(regs->ds, &user->regs.ds);
+		put_user_ex(regs->fs, &user->regs.fs);
+		put_user_ex(regs->gs, &user->regs.gs);
+
+		put_user_ex(vm86->screen_bitmap, &user->screen_bitmap);
+	} put_user_catch(err);
+	if (err) {
+		pr_alert("could not access userspace vm86 info\n");
 		do_exit(SIGSEGV);
 	}
 
 	tss = &per_cpu(cpu_tss, get_cpu());
-	current->thread.sp0 = current->thread.saved_sp0;
-	current->thread.sysenter_cs = __KERNEL_CS;
-	load_sp0(tss, &current->thread);
-	current->thread.saved_sp0 = 0;
+	tsk->thread.sp0 = vm86->saved_sp0;
+	tsk->thread.sysenter_cs = __KERNEL_CS;
+	load_sp0(tss, &tsk->thread);
+	vm86->saved_sp0 = 0;
 	put_cpu();
 
-	ret = KVM86->regs32;
+	memcpy(&regs->pt, &vm86->regs32, sizeof(struct pt_regs));
 
-	ret->fs = current->thread.saved_fs;
-	set_user_gs(ret, current->thread.saved_gs);
+	lazy_load_gs(vm86->regs32.gs);
 
-	return ret;
+	regs->pt.ax = retval;
 }
 
 static void mark_screen_rdonly(struct mm_struct *mm)
@@ -200,45 +192,16 @@ out:
 
 
 static int do_vm86_irq_handling(int subfunction, int irqnumber);
-static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk);
+static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus);
 
-SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, v86)
+SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, user_vm86)
 {
-	struct kernel_vm86_struct info; /* declare this _on top_,
-					 * this avoids wasting of stack space.
-					 * This remains on the stack until we
-					 * return to 32 bit user space.
-					 */
-	struct task_struct *tsk = current;
-	int tmp;
-
-	if (tsk->thread.saved_sp0)
-		return -EPERM;
-	tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs,
-				       offsetof(struct kernel_vm86_struct, vm86plus) -
-				       sizeof(info.regs));
-	if (tmp)
-		return -EFAULT;
-	memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus);
-	info.regs32 = current_pt_regs();
-	tsk->thread.vm86_info = v86;
-	do_sys_vm86(&info, tsk);
-	return 0;	/* we never return here */
+	return do_sys_vm86((struct vm86plus_struct __user *) user_vm86, false);
 }
 
 
 SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg)
 {
-	struct kernel_vm86_struct info; /* declare this _on top_,
-					 * this avoids wasting of stack space.
-					 * This remains on the stack until we
-					 * return to 32 bit user space.
-					 */
-	struct task_struct *tsk;
-	int tmp;
-	struct vm86plus_struct __user *v86;
-
-	tsk = current;
 	switch (cmd) {
 	case VM86_REQUEST_IRQ:
 	case VM86_FREE_IRQ:
@@ -256,114 +219,133 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg)
 	}
 
 	/* we come here only for functions VM86_ENTER, VM86_ENTER_NO_BYPASS */
-	if (tsk->thread.saved_sp0)
-		return -EPERM;
-	v86 = (struct vm86plus_struct __user *)arg;
-	tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs,
-				       offsetof(struct kernel_vm86_struct, regs32) -
-				       sizeof(info.regs));
-	if (tmp)
-		return -EFAULT;
-	info.regs32 = current_pt_regs();
-	info.vm86plus.is_vm86pus = 1;
-	tsk->thread.vm86_info = (struct vm86_struct __user *)v86;
-	do_sys_vm86(&info, tsk);
-	return 0;	/* we never return here */
+	return do_sys_vm86((struct vm86plus_struct __user *) arg, true);
 }
 
 
-static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk)
+static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 {
 	struct tss_struct *tss;
-/*
- * make sure the vm86() system call doesn't try to do anything silly
- */
-	info->regs.pt.ds = 0;
-	info->regs.pt.es = 0;
-	info->regs.pt.fs = 0;
-#ifndef CONFIG_X86_32_LAZY_GS
-	info->regs.pt.gs = 0;
-#endif
+	struct task_struct *tsk = current;
+	struct vm86 *vm86 = tsk->thread.vm86;
+	struct kernel_vm86_regs vm86regs;
+	struct pt_regs *regs = current_pt_regs();
+	unsigned long err = 0;
+
+	if (!vm86) {
+		if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL)))
+			return -ENOMEM;
+		tsk->thread.vm86 = vm86;
+	}
+	if (vm86->saved_sp0)
+		return -EPERM;
+
+	if (!access_ok(VERIFY_READ, user_vm86, plus ?
+		       sizeof(struct vm86_struct) :
+		       sizeof(struct vm86plus_struct)))
+		return -EFAULT;
+
+	memset(&vm86regs, 0, sizeof(vm86regs));
+	get_user_try {
+		unsigned short seg;
+		get_user_ex(vm86regs.pt.bx, &user_vm86->regs.ebx);
+		get_user_ex(vm86regs.pt.cx, &user_vm86->regs.ecx);
+		get_user_ex(vm86regs.pt.dx, &user_vm86->regs.edx);
+		get_user_ex(vm86regs.pt.si, &user_vm86->regs.esi);
+		get_user_ex(vm86regs.pt.di, &user_vm86->regs.edi);
+		get_user_ex(vm86regs.pt.bp, &user_vm86->regs.ebp);
+		get_user_ex(vm86regs.pt.ax, &user_vm86->regs.eax);
+		get_user_ex(vm86regs.pt.ip, &user_vm86->regs.eip);
+		get_user_ex(seg, &user_vm86->regs.cs);
+		vm86regs.pt.cs = seg;
+		get_user_ex(vm86regs.pt.flags, &user_vm86->regs.eflags);
+		get_user_ex(vm86regs.pt.sp, &user_vm86->regs.esp);
+		get_user_ex(seg, &user_vm86->regs.ss);
+		vm86regs.pt.ss = seg;
+		get_user_ex(vm86regs.es, &user_vm86->regs.es);
+		get_user_ex(vm86regs.ds, &user_vm86->regs.ds);
+		get_user_ex(vm86regs.fs, &user_vm86->regs.fs);
+		get_user_ex(vm86regs.gs, &user_vm86->regs.gs);
+
+		get_user_ex(vm86->flags, &user_vm86->flags);
+		get_user_ex(vm86->screen_bitmap, &user_vm86->screen_bitmap);
+		get_user_ex(vm86->cpu_type, &user_vm86->cpu_type);
+	} get_user_catch(err);
+	if (err)
+		return err;
+
+	if (copy_from_user(&vm86->int_revectored,
+			   &user_vm86->int_revectored,
+			   sizeof(struct revectored_struct)))
+		return -EFAULT;
+	if (copy_from_user(&vm86->int21_revectored,
+			   &user_vm86->int21_revectored,
+			   sizeof(struct revectored_struct)))
+		return -EFAULT;
+	if (plus) {
+		if (copy_from_user(&vm86->vm86plus, &user_vm86->vm86plus,
+				   sizeof(struct vm86plus_info_struct)))
+			return -EFAULT;
+		vm86->vm86plus.is_vm86pus = 1;
+	} else
+		memset(&vm86->vm86plus, 0,
+		       sizeof(struct vm86plus_info_struct));
+
+	memcpy(&vm86->regs32, regs, sizeof(struct pt_regs));
+	vm86->user_vm86 = user_vm86;
 
 /*
  * The flags register is also special: we cannot trust that the user
  * has set it up safely, so this makes sure interrupt etc flags are
  * inherited from protected mode.
  */
-	VEFLAGS = info->regs.pt.flags;
-	info->regs.pt.flags &= SAFE_MASK;
-	info->regs.pt.flags |= info->regs32->flags & ~SAFE_MASK;
-	info->regs.pt.flags |= X86_VM_MASK;
+	VEFLAGS = vm86regs.pt.flags;
+	vm86regs.pt.flags &= SAFE_MASK;
+	vm86regs.pt.flags |= regs->flags & ~SAFE_MASK;
+	vm86regs.pt.flags |= X86_VM_MASK;
+
+	vm86regs.pt.orig_ax = regs->orig_ax;
 
-	switch (info->cpu_type) {
+	switch (vm86->cpu_type) {
 	case CPU_286:
-		tsk->thread.v86mask = 0;
+		vm86->veflags_mask = 0;
 		break;
 	case CPU_386:
-		tsk->thread.v86mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL;
+		vm86->veflags_mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL;
 		break;
 	case CPU_486:
-		tsk->thread.v86mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL;
+		vm86->veflags_mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL;
 		break;
 	default:
-		tsk->thread.v86mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL;
+		vm86->veflags_mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL;
 		break;
 	}
 
 /*
- * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL)
+ * Save old state
  */
-	info->regs32->ax = VM86_SIGNAL;
-	tsk->thread.saved_sp0 = tsk->thread.sp0;
-	tsk->thread.saved_fs = info->regs32->fs;
-	tsk->thread.saved_gs = get_user_gs(info->regs32);
+	vm86->saved_sp0 = tsk->thread.sp0;
+	lazy_save_gs(vm86->regs32.gs);
 
 	tss = &per_cpu(cpu_tss, get_cpu());
-	tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0;
+	/* make room for real-mode segments */
+	tsk->thread.sp0 += 16;
 	if (cpu_has_sep)
 		tsk->thread.sysenter_cs = 0;
 	load_sp0(tss, &tsk->thread);
 	put_cpu();
 
-	tsk->thread.screen_bitmap = info->screen_bitmap;
-	if (info->flags & VM86_SCREEN_BITMAP)
+	if (vm86->flags & VM86_SCREEN_BITMAP)
 		mark_screen_rdonly(tsk->mm);
 
-	/*call __audit_syscall_exit since we do not exit via the normal paths */
-#ifdef CONFIG_AUDITSYSCALL
-	if (unlikely(current->audit_context))
-		__audit_syscall_exit(1, 0);
-#endif
-
-	__asm__ __volatile__(
-		"movl %0,%%esp\n\t"
-		"movl %1,%%ebp\n\t"
-#ifdef CONFIG_X86_32_LAZY_GS
-		"mov  %2, %%gs\n\t"
-#endif
-		"jmp resume_userspace"
-		: /* no outputs */
-		:"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0));
-	/* we never return here */
-}
-
-static inline void return_to_32bit(struct kernel_vm86_regs *regs16, int retval)
-{
-	struct pt_regs *regs32;
-
-	regs32 = save_v86_state(regs16);
-	regs32->ax = retval;
-	__asm__ __volatile__("movl %0,%%esp\n\t"
-		"movl %1,%%ebp\n\t"
-		"jmp resume_userspace"
-		: : "r" (regs32), "r" (current_thread_info()));
+	memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs));
+	force_iret();
+	return regs->ax;
 }
 
 static inline void set_IF(struct kernel_vm86_regs *regs)
 {
 	VEFLAGS |= X86_EFLAGS_VIF;
-	if (VEFLAGS & X86_EFLAGS_VIP)
-		return_to_32bit(regs, VM86_STI);
 }
 
 static inline void clear_IF(struct kernel_vm86_regs *regs)
@@ -395,7 +377,7 @@ static inline void clear_AC(struct kernel_vm86_regs *regs)
 
 static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs *regs)
 {
-	set_flags(VEFLAGS, flags, current->thread.v86mask);
+	set_flags(VEFLAGS, flags, current->thread.vm86->veflags_mask);
 	set_flags(regs->pt.flags, flags, SAFE_MASK);
 	if (flags & X86_EFLAGS_IF)
 		set_IF(regs);
@@ -405,7 +387,7 @@ static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs
 
 static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs *regs)
 {
-	set_flags(VFLAGS, flags, current->thread.v86mask);
+	set_flags(VFLAGS, flags, current->thread.vm86->veflags_mask);
 	set_flags(regs->pt.flags, flags, SAFE_MASK);
 	if (flags & X86_EFLAGS_IF)
 		set_IF(regs);
@@ -420,7 +402,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs)
 	if (VEFLAGS & X86_EFLAGS_VIF)
 		flags |= X86_EFLAGS_IF;
 	flags |= X86_EFLAGS_IOPL;
-	return flags | (VEFLAGS & current->thread.v86mask);
+	return flags | (VEFLAGS & current->thread.vm86->veflags_mask);
 }
 
 static inline int is_revectored(int nr, struct revectored_struct *bitmap)
@@ -518,12 +500,13 @@ static void do_int(struct kernel_vm86_regs *regs, int i,
 {
 	unsigned long __user *intr_ptr;
 	unsigned long segoffs;
+	struct vm86 *vm86 = current->thread.vm86;
 
 	if (regs->pt.cs == BIOSSEG)
 		goto cannot_handle;
-	if (is_revectored(i, &KVM86->int_revectored))
+	if (is_revectored(i, &vm86->int_revectored))
 		goto cannot_handle;
-	if (i == 0x21 && is_revectored(AH(regs), &KVM86->int21_revectored))
+	if (i == 0x21 && is_revectored(AH(regs), &vm86->int21_revectored))
 		goto cannot_handle;
 	intr_ptr = (unsigned long __user *) (i << 2);
 	if (get_user(segoffs, intr_ptr))
@@ -542,18 +525,16 @@ static void do_int(struct kernel_vm86_regs *regs, int i,
 	return;
 
 cannot_handle:
-	return_to_32bit(regs, VM86_INTx + (i << 8));
+	save_v86_state(regs, VM86_INTx + (i << 8));
 }
 
 int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
 {
-	if (VMPI.is_vm86pus) {
+	struct vm86 *vm86 = current->thread.vm86;
+
+	if (vm86->vm86plus.is_vm86pus) {
 		if ((trapno == 3) || (trapno == 1)) {
-			KVM86->regs32->ax = VM86_TRAP + (trapno << 8);
-			/* setting this flag forces the code in entry_32.S to
-			   the path where we call save_v86_state() and change
-			   the stack pointer to KVM86->regs32 */
-			set_thread_flag(TIF_NOTIFY_RESUME);
+			save_v86_state(regs, VM86_TRAP + (trapno << 8));
 			return 0;
 		}
 		do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs));
@@ -574,16 +555,11 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 	unsigned char __user *ssp;
 	unsigned short ip, sp, orig_flags;
 	int data32, pref_done;
+	struct vm86plus_info_struct *vmpi = &current->thread.vm86->vm86plus;
 
 #define CHECK_IF_IN_TRAP \
-	if (VMPI.vm86dbg_active && VMPI.vm86dbg_TFpendig) \
+	if (vmpi->vm86dbg_active && vmpi->vm86dbg_TFpendig) \
 		newflags |= X86_EFLAGS_TF
-#define VM86_FAULT_RETURN do { \
-	if (VMPI.force_return_for_pic  && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) \
-		return_to_32bit(regs, VM86_PICRETURN); \
-	if (orig_flags & X86_EFLAGS_TF) \
-		handle_vm86_trap(regs, 0, 1); \
-	return; } while (0)
 
 	orig_flags = *(unsigned short *)&regs->pt.flags;
 
@@ -622,7 +598,7 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 			SP(regs) -= 2;
 		}
 		IP(regs) = ip;
-		VM86_FAULT_RETURN;
+		goto vm86_fault_return;
 
 	/* popf */
 	case 0x9d:
@@ -642,16 +618,18 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 		else
 			set_vflags_short(newflags, regs);
 
-		VM86_FAULT_RETURN;
+		goto check_vip;
 		}
 
 	/* int xx */
 	case 0xcd: {
 		int intno = popb(csp, ip, simulate_sigsegv);
 		IP(regs) = ip;
-		if (VMPI.vm86dbg_active) {
-			if ((1 << (intno & 7)) & VMPI.vm86dbg_intxxtab[intno >> 3])
-				return_to_32bit(regs, VM86_INTx + (intno << 8));
+		if (vmpi->vm86dbg_active) {
+			if ((1 << (intno & 7)) & vmpi->vm86dbg_intxxtab[intno >> 3]) {
+				save_v86_state(regs, VM86_INTx + (intno << 8));
+				return;
+			}
 		}
 		do_int(regs, intno, ssp, sp);
 		return;
@@ -682,14 +660,14 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 		} else {
 			set_vflags_short(newflags, regs);
 		}
-		VM86_FAULT_RETURN;
+		goto check_vip;
 		}
 
 	/* cli */
 	case 0xfa:
 		IP(regs) = ip;
 		clear_IF(regs);
-		VM86_FAULT_RETURN;
+		goto vm86_fault_return;
 
 	/* sti */
 	/*
@@ -701,14 +679,29 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 	case 0xfb:
 		IP(regs) = ip;
 		set_IF(regs);
-		VM86_FAULT_RETURN;
+		goto check_vip;
 
 	default:
-		return_to_32bit(regs, VM86_UNKNOWN);
+		save_v86_state(regs, VM86_UNKNOWN);
 	}
 
 	return;
 
+check_vip:
+	if (VEFLAGS & X86_EFLAGS_VIP) {
+		save_v86_state(regs, VM86_STI);
+		return;
+	}
+
+vm86_fault_return:
+	if (vmpi->force_return_for_pic  && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) {
+		save_v86_state(regs, VM86_PICRETURN);
+		return;
+	}
+	if (orig_flags & X86_EFLAGS_TF)
+		handle_vm86_trap(regs, 0, X86_TRAP_DB);
+	return;
+
 simulate_sigsegv:
 	/* FIXME: After a long discussion with Stas we finally
 	 *        agreed, that this is wrong. Here we should
@@ -720,7 +713,7 @@ simulate_sigsegv:
 	 *        should be a mixture of the two, but how do we
 	 *        get the information? [KD]
 	 */
-	return_to_32bit(regs, VM86_UNKNOWN);
+	save_v86_state(regs, VM86_UNKNOWN);
 }
 
 /* ---------------- vm86 special IRQ passing stuff ----------------- */
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 67d215cb8953..a1ff508bb423 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,7 +12,9 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
+			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
+			   hyperv.o
+
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
 kvm-intel-y		+= vmx.o pmu_intel.o
 kvm-amd-y		+= svm.o pmu_amd.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 64dd46793099..2fbea2544f24 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -98,6 +98,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
 	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+	if (vcpu->arch.eager_fpu)
+		kvm_x86_ops->fpu_activate(vcpu);
 
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
new file mode 100644
index 000000000000..a8160d2ae362
--- /dev/null
+++ b/arch/x86/kvm/hyperv.c
@@ -0,0 +1,377 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Amit Shah    <amit.shah@qumranet.com>
+ *   Ben-Ami Yassour <benami@il.ibm.com>
+ *   Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "x86.h"
+#include "lapic.h"
+#include "hyperv.h"
+
+#include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+	bool r = false;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+	case HV_X64_MSR_HYPERCALL:
+	case HV_X64_MSR_REFERENCE_TSC:
+	case HV_X64_MSR_TIME_REF_COUNT:
+	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		r = true;
+		break;
+	}
+
+	return r;
+}
+
+static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
+				     u32 index, u64 *pdata)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+		return -EINVAL;
+
+	*pdata = hv->hv_crash_param[index];
+	return 0;
+}
+
+static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	*pdata = hv->hv_crash_ctl;
+	return 0;
+}
+
+static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (host)
+		hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY;
+
+	if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) {
+
+		vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
+			  hv->hv_crash_param[0],
+			  hv->hv_crash_param[1],
+			  hv->hv_crash_param[2],
+			  hv->hv_crash_param[3],
+			  hv->hv_crash_param[4]);
+
+		/* Send notification about crash to user space */
+		kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
+	}
+
+	return 0;
+}
+
+static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
+				     u32 index, u64 data)
+{
+	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+		return -EINVAL;
+
+	hv->hv_crash_param[index] = data;
+	return 0;
+}
+
+static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
+			     bool host)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		hv->hv_guest_os_id = data;
+		/* setting guest os id to zero disables hypercall page */
+		if (!hv->hv_guest_os_id)
+			hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+		break;
+	case HV_X64_MSR_HYPERCALL: {
+		u64 gfn;
+		unsigned long addr;
+		u8 instructions[4];
+
+		/* if guest os id is not set hypercall should remain disabled */
+		if (!hv->hv_guest_os_id)
+			break;
+		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+			hv->hv_hypercall = data;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		kvm_x86_ops->patch_hypercall(vcpu, instructions);
+		((unsigned char *)instructions)[3] = 0xc3; /* ret */
+		if (__copy_to_user((void __user *)addr, instructions, 4))
+			return 1;
+		hv->hv_hypercall = data;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC: {
+		u64 gfn;
+		HV_REFERENCE_TSC_PAGE tsc_ref;
+
+		memset(&tsc_ref, 0, sizeof(tsc_ref));
+		hv->hv_tsc_page = data;
+		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+			break;
+		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+		if (kvm_write_guest(
+				kvm,
+				gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
+				&tsc_ref, sizeof(tsc_ref)))
+			return 1;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		return kvm_hv_msr_set_crash_data(vcpu,
+						 msr - HV_X64_MSR_CRASH_P0,
+						 data);
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+			    msr, data);
+		return 1;
+	}
+	return 0;
+}
+
+static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		u64 gfn;
+		unsigned long addr;
+
+		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+			hv->hv_vapic = data;
+			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+				return 1;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
+		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if (__clear_user((void __user *)addr, PAGE_SIZE))
+			return 1;
+		hv->hv_vapic = data;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+		if (kvm_lapic_enable_pv_eoi(vcpu,
+					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+			return 1;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+			    msr, data);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		data = hv->hv_guest_os_id;
+		break;
+	case HV_X64_MSR_HYPERCALL:
+		data = hv->hv_hypercall;
+		break;
+	case HV_X64_MSR_TIME_REF_COUNT: {
+		data =
+		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC:
+		data = hv->hv_tsc_page;
+		break;
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+		return kvm_hv_msr_get_crash_data(vcpu,
+						 msr - HV_X64_MSR_CRASH_P0,
+						 pdata);
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+
+	*pdata = data;
+	return 0;
+}
+
+static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+	switch (msr) {
+	case HV_X64_MSR_VP_INDEX: {
+		int r;
+		struct kvm_vcpu *v;
+
+		kvm_for_each_vcpu(r, v, vcpu->kvm) {
+			if (v == vcpu) {
+				data = r;
+				break;
+			}
+		}
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+	case HV_X64_MSR_APIC_ASSIST_PAGE:
+		data = hv->hv_vapic;
+		break;
+	default:
+		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+	*pdata = data;
+	return 0;
+}
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
+{
+	if (kvm_hv_msr_partition_wide(msr)) {
+		int r;
+
+		mutex_lock(&vcpu->kvm->lock);
+		r = kvm_hv_set_msr_pw(vcpu, msr, data, host);
+		mutex_unlock(&vcpu->kvm->lock);
+		return r;
+	} else
+		return kvm_hv_set_msr(vcpu, msr, data);
+}
+
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	if (kvm_hv_msr_partition_wide(msr)) {
+		int r;
+
+		mutex_lock(&vcpu->kvm->lock);
+		r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
+		mutex_unlock(&vcpu->kvm->lock);
+		return r;
+	} else
+		return kvm_hv_get_msr(vcpu, msr, pdata);
+}
+
+bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+	return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	u64 param, ingpa, outgpa, ret;
+	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	bool fast, longmode;
+
+	/*
+	 * hypercall generates UD from non zero cpl and real mode
+	 * per HYPER-V spec
+	 */
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	longmode = is_64_bit_mode(vcpu);
+
+	if (!longmode) {
+		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+	}
+#ifdef CONFIG_X86_64
+	else {
+		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+	}
+#endif
+
+	code = param & 0xffff;
+	fast = (param >> 16) & 0x1;
+	rep_cnt = (param >> 32) & 0xfff;
+	rep_idx = (param >> 48) & 0xfff;
+
+	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+	switch (code) {
+	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+		kvm_vcpu_on_spin(vcpu);
+		break;
+	default:
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		break;
+	}
+
+	ret = res | (((u64)rep_done & 0xfff) << 32);
+	if (longmode) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	} else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+	}
+
+	return 1;
+}
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
new file mode 100644
index 000000000000..c7bce559f67b
--- /dev/null
+++ b/arch/x86/kvm/hyperv.h
@@ -0,0 +1,32 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Amit Shah    <amit.shah@qumranet.com>
+ *   Ben-Ami Yassour <benami@il.ibm.com>
+ *   Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef __ARCH_X86_KVM_HYPERV_H__
+#define __ARCH_X86_KVM_HYPERV_H__
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+bool kvm_hv_hypercall_enabled(struct kvm *kvm);
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index fef922ff2635..7cc2360f1848 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -651,15 +651,10 @@ fail_unlock:
 	return NULL;
 }
 
-void kvm_destroy_pic(struct kvm *kvm)
+void kvm_destroy_pic(struct kvm_pic *vpic)
 {
-	struct kvm_pic *vpic = kvm->arch.vpic;
-
-	if (vpic) {
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master);
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave);
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr);
-		kvm->arch.vpic = NULL;
-		kfree(vpic);
-	}
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
+	kfree(vpic);
 }
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index 7dbced309ddb..5c520ebf6343 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
 			goto out_unmap;
 	}
 
+	kvm_arch_start_assignment(kvm);
 	pci_set_dev_assigned(pdev);
 
 	dev_info(&pdev->dev, "kvm assign device\n");
@@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
 	iommu_detach_device(domain, &pdev->dev);
 
 	pci_clear_dev_assigned(pdev);
+	kvm_arch_end_assignment(kvm);
 
 	dev_info(&pdev->dev, "kvm deassign device\n");
 
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index ad68c73008c5..3d782a2c336a 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -74,7 +74,7 @@ struct kvm_pic {
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
-void kvm_destroy_pic(struct kvm *kvm);
+void kvm_destroy_pic(struct kvm_pic *vpic);
 int kvm_pic_read_irq(struct kvm *kvm);
 void kvm_pic_update_irq(struct kvm_pic *s);
 
@@ -85,11 +85,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
 
 static inline int irqchip_in_kernel(struct kvm *kvm)
 {
-	int ret;
+	struct kvm_pic *vpic = pic_irqchip(kvm);
 
-	ret = (pic_irqchip(kvm) != NULL);
+	/* Read vpic before kvm->irq_routing.  */
 	smp_rmb();
-	return ret;
+	return vpic != NULL;
 }
 
 void kvm_pic_reset(struct kvm_kpic_state *s);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 954e98a8c2e3..8d9013c5e1ee 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1172,7 +1172,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 
 	tsc_deadline = apic->lapic_timer.expired_tscdeadline;
 	apic->lapic_timer.expired_tscdeadline = 0;
-	guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+	guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc());
 	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
 
 	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
@@ -1240,7 +1240,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		local_irq_save(flags);
 
 		now = apic->lapic_timer.timer.base->get_time();
-		guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+		guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc());
 		if (likely(tscdeadline > guest_tsc)) {
 			ns = (tscdeadline - guest_tsc) * 1000000ULL;
 			do_div(ns, this_tsc_khz);
@@ -1595,7 +1595,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	for (i = 0; i < APIC_LVT_NUM; i++)
 		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
-	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
 		apic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
@@ -1900,8 +1900,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
-				sizeof(u32));
+	if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				  sizeof(u32)))
+		return;
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 71952748222a..764037991d26 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -91,7 +91,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 
 static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
+	return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
 }
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f807496b62c2..fb16a8ea3dee 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -357,12 +357,6 @@ static u64 __get_spte_lockless(u64 *sptep)
 {
 	return ACCESS_ONCE(*sptep);
 }
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
-	/* It is valid if the spte is zapped. */
-	return spte == 0ull;
-}
 #else
 union split_spte {
 	struct {
@@ -478,23 +472,6 @@ retry:
 
 	return spte.spte;
 }
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
-	union split_spte sspte = (union split_spte)spte;
-	u32 high_mmio_mask = shadow_mmio_mask >> 32;
-
-	/* It is valid if the spte is zapped. */
-	if (spte == 0ull)
-		return true;
-
-	/* It is valid if the spte is being zapped. */
-	if (sspte.spte_low == 0ull &&
-	    (sspte.spte_high & high_mmio_mask) == high_mmio_mask)
-		return true;
-
-	return false;
-}
 #endif
 
 static bool spte_is_locklessly_modifiable(u64 spte)
@@ -2479,6 +2456,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return 0;
 }
 
+static bool kvm_is_mmio_pfn(pfn_t pfn)
+{
+	if (pfn_valid(pfn))
+		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+
+	return true;
+}
+
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
@@ -2506,7 +2491,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
-			kvm_is_reserved_pfn(pfn));
+			kvm_is_mmio_pfn(pfn));
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;
@@ -3283,54 +3268,89 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
 	return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
 }
 
-static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+static bool
+__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level)
 {
-	if (direct)
-		return vcpu_match_mmio_gpa(vcpu, addr);
+	int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f;
 
-	return vcpu_match_mmio_gva(vcpu, addr);
+	return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) |
+		((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0);
 }
 
+static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level);
+}
 
-/*
- * On direct hosts, the last spte is only allows two states
- * for mmio page fault:
- *   - It is the mmio spte
- *   - It is zapped or it is being zapped.
- *
- * This function completely checks the spte when the last spte
- * is not the mmio spte.
- */
-static bool check_direct_spte_mmio_pf(u64 spte)
+static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
 {
-	return __check_direct_spte_mmio_pf(spte);
+	return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
 }
 
-static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
+static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+{
+	if (direct)
+		return vcpu_match_mmio_gpa(vcpu, addr);
+
+	return vcpu_match_mmio_gva(vcpu, addr);
+}
+
+/* return true if reserved bit is detected on spte. */
+static bool
+walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	u64 spte = 0ull;
+	u64 sptes[PT64_ROOT_LEVEL], spte = 0ull;
+	int root, leaf;
+	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		return spte;
+		goto exit;
 
 	walk_shadow_page_lockless_begin(vcpu);
-	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
+
+	for (shadow_walk_init(&iterator, vcpu, addr), root = iterator.level;
+	     shadow_walk_okay(&iterator);
+	     __shadow_walk_next(&iterator, spte)) {
+		leaf = iterator.level;
+		spte = mmu_spte_get_lockless(iterator.sptep);
+
+		sptes[leaf - 1] = spte;
+
 		if (!is_shadow_present_pte(spte))
 			break;
+
+		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+						    leaf);
+	}
+
 	walk_shadow_page_lockless_end(vcpu);
 
-	return spte;
+	if (reserved) {
+		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
+		       __func__, addr);
+		while (root >= leaf) {
+			pr_err("------ spte 0x%llx level %d.\n",
+			       sptes[root - 1], root);
+			root--;
+		}
+	}
+exit:
+	*sptep = spte;
+	return reserved;
 }
 
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 {
 	u64 spte;
+	bool reserved;
 
 	if (quickly_check_mmio_pf(vcpu, addr, direct))
 		return RET_MMIO_PF_EMULATE;
 
-	spte = walk_shadow_page_get_mmio_spte(vcpu, addr);
+	reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
+	if (unlikely(reserved))
+		return RET_MMIO_PF_BUG;
 
 	if (is_mmio_spte(spte)) {
 		gfn_t gfn = get_mmio_spte_gfn(spte);
@@ -3348,13 +3368,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	}
 
 	/*
-	 * It's ok if the gva is remapped by other cpus on shadow guest,
-	 * it's a BUG if the gfn is not a mmio page.
-	 */
-	if (direct && !check_direct_spte_mmio_pf(spte))
-		return RET_MMIO_PF_BUG;
-
-	/*
 	 * If the page table is zapped by other cpus, let CPU fault again on
 	 * the address.
 	 */
@@ -3596,19 +3609,21 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp
 #include "paging_tmpl.h"
 #undef PTTYPE
 
-static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu *context)
+static void
+__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+			struct rsvd_bits_validate *rsvd_check,
+			int maxphyaddr, int level, bool nx, bool gbpages,
+			bool pse)
 {
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
 	u64 nonleaf_bit8_rsvd = 0;
 
-	context->bad_mt_xwr = 0;
+	rsvd_check->bad_mt_xwr = 0;
 
-	if (!context->nx)
+	if (!nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
-	if (!guest_cpuid_has_gbpages(vcpu))
+	if (!gbpages)
 		gbpages_bit_rsvd = rsvd_bits(7, 7);
 
 	/*
@@ -3618,80 +3633,95 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	if (guest_cpuid_is_amd(vcpu))
 		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
 
-	switch (context->root_level) {
+	switch (level) {
 	case PT32_ROOT_LEVEL:
 		/* no rsvd bits for 2 level 4K page table entries */
-		context->rsvd_bits_mask[0][1] = 0;
-		context->rsvd_bits_mask[0][0] = 0;
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+		rsvd_check->rsvd_bits_mask[0][1] = 0;
+		rsvd_check->rsvd_bits_mask[0][0] = 0;
+		rsvd_check->rsvd_bits_mask[1][0] =
+			rsvd_check->rsvd_bits_mask[0][0];
 
-		if (!is_pse(vcpu)) {
-			context->rsvd_bits_mask[1][1] = 0;
+		if (!pse) {
+			rsvd_check->rsvd_bits_mask[1][1] = 0;
 			break;
 		}
 
 		if (is_cpuid_PSE36())
 			/* 36bits PSE 4MB page */
-			context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
 		else
 			/* 32 bits PSE 4MB page */
-			context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
 		break;
 	case PT32E_ROOT_LEVEL:
-		context->rsvd_bits_mask[0][2] =
+		rsvd_check->rsvd_bits_mask[0][2] =
 			rsvd_bits(maxphyaddr, 63) |
 			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
-		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62);	/* PDE */
-		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62); 	/* PTE */
-		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+		rsvd_check->rsvd_bits_mask[1][0] =
+			rsvd_check->rsvd_bits_mask[0][0];
 		break;
 	case PT64_ROOT_LEVEL:
-		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
+			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
+			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
-		context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
-		context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[1][3] =
+			rsvd_check->rsvd_bits_mask[0][3];
+		rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd |
 			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 29);
-		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+		rsvd_check->rsvd_bits_mask[1][0] =
+			rsvd_check->rsvd_bits_mask[0][0];
 		break;
 	}
 }
 
-static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *context, bool execonly)
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu *context)
+{
+	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
+				cpuid_maxphyaddr(vcpu), context->root_level,
+				context->nx, guest_cpuid_has_gbpages(vcpu),
+				is_pse(vcpu));
+}
+
+static void
+__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
+			    int maxphyaddr, bool execonly)
 {
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	int pte;
 
-	context->rsvd_bits_mask[0][3] =
+	rsvd_check->rsvd_bits_mask[0][3] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
-	context->rsvd_bits_mask[0][2] =
+	rsvd_check->rsvd_bits_mask[0][2] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
-	context->rsvd_bits_mask[0][1] =
+	rsvd_check->rsvd_bits_mask[0][1] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
-	context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+	rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
 
 	/* large page */
-	context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
-	context->rsvd_bits_mask[1][2] =
+	rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
+	rsvd_check->rsvd_bits_mask[1][2] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
-	context->rsvd_bits_mask[1][1] =
+	rsvd_check->rsvd_bits_mask[1][1] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
-	context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+	rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
 
 	for (pte = 0; pte < 64; pte++) {
 		int rwx_bits = pte & 7;
@@ -3699,10 +3729,64 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
 				rwx_bits == 0x2 || rwx_bits == 0x6 ||
 				(rwx_bits == 0x4 && !execonly))
-			context->bad_mt_xwr |= (1ull << pte);
+			rsvd_check->bad_mt_xwr |= (1ull << pte);
 	}
 }
 
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *context, bool execonly)
+{
+	__reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
+				    cpuid_maxphyaddr(vcpu), execonly);
+}
+
+/*
+ * the page table on host is the shadow page table for the page
+ * table in guest or amd nested guest, its mmu features completely
+ * follow the features in guest.
+ */
+void
+reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
+{
+	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+				boot_cpu_data.x86_phys_bits,
+				context->shadow_root_level, context->nx,
+				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+}
+EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
+
+/*
+ * the direct page table on host, use as much mmu features as
+ * possible, however, kvm currently does not do execution-protection.
+ */
+static void
+reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+				struct kvm_mmu *context)
+{
+	if (guest_cpuid_is_amd(vcpu))
+		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+					boot_cpu_data.x86_phys_bits,
+					context->shadow_root_level, false,
+					cpu_has_gbpages, true);
+	else
+		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+					    boot_cpu_data.x86_phys_bits,
+					    false);
+
+}
+
+/*
+ * as the comments in reset_shadow_zero_bits_mask() except it
+ * is the shadow page table for intel nested guest.
+ */
+static void
+reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+				struct kvm_mmu *context, bool execonly)
+{
+	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+				    boot_cpu_data.x86_phys_bits, execonly);
+}
+
 static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 				      struct kvm_mmu *mmu, bool ept)
 {
@@ -3881,6 +3965,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 
 	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
+	reset_tdp_shadow_zero_bits_mask(vcpu, context);
 }
 
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
@@ -3908,6 +3993,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 	context->base_role.smap_andnot_wp
 		= smap && !is_write_protection(vcpu);
 	context->base_role.smm = is_smm(vcpu);
+	reset_shadow_zero_bits_mask(vcpu, context);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -3931,6 +4017,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly)
 
 	update_permission_bitmask(vcpu, context, true);
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
 
@@ -4852,28 +4939,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	return nr_mmu_pages;
 }
 
-int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
-{
-	struct kvm_shadow_walk_iterator iterator;
-	u64 spte;
-	int nr_sptes = 0;
-
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		return nr_sptes;
-
-	walk_shadow_page_lockless_begin(vcpu);
-	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
-		sptes[iterator.level-1] = spte;
-		nr_sptes++;
-		if (!is_shadow_present_pte(spte))
-			break;
-	}
-	walk_shadow_page_lockless_end(vcpu);
-
-	return nr_sptes;
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
-
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_unload(vcpu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 398d21c0f6dd..e4202e41d535 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -50,9 +50,11 @@ static inline u64 rsvd_bits(int s, int e)
 	return ((1ULL << (e - s + 1)) - 1) << s;
 }
 
-int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
 
+void
+reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+
 /*
  * Return values of handle_mmio_page_fault_common:
  * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index de1d2d8062e2..9e8bf13572e6 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -120,6 +120,16 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
 	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
 }
 
+static u8 mtrr_disabled_type(void)
+{
+	/*
+	 * Intel SDM 11.11.2.2: all MTRRs are disabled when
+	 * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
+	 * memory type is applied to all of physical memory.
+	 */
+	return MTRR_TYPE_UNCACHABLE;
+}
+
 /*
 * Three terms are used in the following code:
 * - segment, it indicates the address segments covered by fixed MTRRs.
@@ -434,6 +444,8 @@ struct mtrr_iter {
 
 	/* output fields. */
 	int mem_type;
+	/* mtrr is completely disabled? */
+	bool mtrr_disabled;
 	/* [start, end) is not fully covered in MTRRs? */
 	bool partial_map;
 
@@ -549,7 +561,7 @@ static void mtrr_lookup_var_next(struct mtrr_iter *iter)
 static void mtrr_lookup_start(struct mtrr_iter *iter)
 {
 	if (!mtrr_is_enabled(iter->mtrr_state)) {
-		iter->partial_map = true;
+		iter->mtrr_disabled = true;
 		return;
 	}
 
@@ -563,6 +575,7 @@ static void mtrr_lookup_init(struct mtrr_iter *iter,
 	iter->mtrr_state = mtrr_state;
 	iter->start = start;
 	iter->end = end;
+	iter->mtrr_disabled = false;
 	iter->partial_map = false;
 	iter->fixed = false;
 	iter->range = NULL;
@@ -656,15 +669,19 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 		return MTRR_TYPE_WRBACK;
 	}
 
-	/* It is not covered by MTRRs. */
-	if (iter.partial_map) {
-		/*
-		 * We just check one page, partially covered by MTRRs is
-		 * impossible.
-		 */
-		WARN_ON(type != -1);
-		type = mtrr_default_type(mtrr_state);
-	}
+	if (iter.mtrr_disabled)
+		return mtrr_disabled_type();
+
+	/* not contained in any MTRRs. */
+	if (type == -1)
+		return mtrr_default_type(mtrr_state);
+
+	/*
+	 * We just check one page, partially covered by MTRRs is
+	 * impossible.
+	 */
+	WARN_ON(iter.partial_map);
+
 	return type;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
@@ -689,6 +706,9 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 			return false;
 	}
 
+	if (iter.mtrr_disabled)
+		return true;
+
 	if (!iter.partial_map)
 		return true;
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 0f67d7e24800..736e6ab8784d 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -128,14 +128,6 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
 	*access &= mask;
 }
 
-static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
-{
-	int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
-
-	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
-		((mmu->bad_mt_xwr & (1ull << low6)) != 0);
-}
-
 static inline int FNAME(is_present_gpte)(unsigned long pte)
 {
 #if PTTYPE != PTTYPE_EPT
@@ -172,7 +164,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu_page *sp, u64 *spte,
 				  u64 gpte)
 {
-	if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
 		goto no_present;
 
 	if (!FNAME(is_present_gpte)(gpte))
@@ -353,8 +345,7 @@ retry_walk:
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte,
-					             walker->level))) {
+		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
 			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 886aa25a7131..39b91127ef07 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -133,8 +133,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	/* MSR_K7_PERFCTRn */
 	pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
 	if (pmc) {
-		if (!msr_info->host_initiated)
-			data = (s64)data;
 		pmc->counter += data - pmc_read_counter(pmc);
 		return 0;
 	}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 602b974a60a6..fdb8cb63a6c0 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -865,6 +865,64 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
+#define MTRR_TYPE_UC_MINUS	7
+#define MTRR2PROTVAL_INVALID 0xff
+
+static u8 mtrr2protval[8];
+
+static u8 fallback_mtrr_type(int mtrr)
+{
+	/*
+	 * WT and WP aren't always available in the host PAT.  Treat
+	 * them as UC and UC- respectively.  Everything else should be
+	 * there.
+	 */
+	switch (mtrr)
+	{
+	case MTRR_TYPE_WRTHROUGH:
+		return MTRR_TYPE_UNCACHABLE;
+	case MTRR_TYPE_WRPROT:
+		return MTRR_TYPE_UC_MINUS;
+	default:
+		BUG();
+	}
+}
+
+static void build_mtrr2protval(void)
+{
+	int i;
+	u64 pat;
+
+	for (i = 0; i < 8; i++)
+		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
+
+	/* Ignore the invalid MTRR types.  */
+	mtrr2protval[2] = 0;
+	mtrr2protval[3] = 0;
+
+	/*
+	 * Use host PAT value to figure out the mapping from guest MTRR
+	 * values to nested page table PAT/PCD/PWT values.  We do not
+	 * want to change the host PAT value every time we enter the
+	 * guest.
+	 */
+	rdmsrl(MSR_IA32_CR_PAT, pat);
+	for (i = 0; i < 8; i++) {
+		u8 mtrr = pat >> (8 * i);
+
+		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
+			mtrr2protval[mtrr] = __cm_idx2pte(i);
+	}
+
+	for (i = 0; i < 8; i++) {
+		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
+			u8 fallback = fallback_mtrr_type(i);
+			mtrr2protval[i] = mtrr2protval[fallback];
+			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
+		}
+	}
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -931,6 +989,7 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
+	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1080,11 +1139,48 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
 	u64 tsc;
 
-	tsc = svm_scale_tsc(vcpu, native_read_tsc());
+	tsc = svm_scale_tsc(vcpu, rdtsc());
 
 	return target_tsc - tsc;
 }
 
+static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
+	 *
+	 * AMD does not have IPAT.  To emulate it for the case of guests
+	 * with no assigned devices, just set everything to WB.  If guests
+	 * have assigned devices, however, we cannot force WB for RAM
+	 * pages only, so use the guest PAT directly.
+	 */
+	if (!kvm_arch_has_assigned_device(vcpu->kvm))
+		*g_pat = 0x0606060606060606;
+	else
+		*g_pat = vcpu->arch.pat;
+}
+
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	u8 mtrr;
+
+	/*
+	 * 1. MMIO: trust guest MTRR, so same as item 3.
+	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
+	 * 3. Passthrough: can't guarantee the result, try to trust guest.
+	 */
+	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
+		return 0;
+
+	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
+	    kvm_read_cr0(vcpu) & X86_CR0_CD)
+		return _PAGE_NOCACHE;
+
+	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+	return mtrr2protval[mtrr];
+}
+
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1180,6 +1276,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
+		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -1574,13 +1671,10 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if (!vcpu->fpu_active)
 		cr0 |= X86_CR0_TS;
-	/*
-	 * re-enable caching here because the QEMU bios
-	 * does not do it - this results in some delay at
-	 * reboot
-	 */
-	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
-		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+
+	/* These are emulated via page tables.  */
+	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
 	update_cr0_intercept(svm);
@@ -2013,6 +2107,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.get_pdptr         = nested_svm_get_tdp_pdptr;
 	vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
 	vcpu->arch.mmu.shadow_root_level = get_npt_level();
+	reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
 }
 
@@ -3079,7 +3174,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	switch (msr_info->index) {
 	case MSR_IA32_TSC: {
 		msr_info->data = svm->vmcb->control.tsc_offset +
-			svm_scale_tsc(vcpu, native_read_tsc());
+			svm_scale_tsc(vcpu, rdtsc());
 
 		break;
 	}
@@ -3254,6 +3349,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
+	case MSR_IA32_CR_PAT:
+		if (npt_enabled) {
+			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+				return 1;
+			vcpu->arch.pat = data;
+			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
+			mark_dirty(svm->vmcb, VMCB_NPT);
+			break;
+		}
+		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4088,11 +4193,6 @@ static bool svm_has_high_real_mode_segbase(void)
 	return true;
 }
 
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	return 0;
-}
-
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e856dd566f4c..4a4eec30cc08 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2236,7 +2236,7 @@ static u64 guest_read_tsc(void)
 {
 	u64 host_tsc, tsc_offset;
 
-	rdtscll(host_tsc);
+	host_tsc = rdtsc();
 	tsc_offset = vmcs_read64(TSC_OFFSET);
 	return host_tsc + tsc_offset;
 }
@@ -2317,7 +2317,7 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho
 
 static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
-	return target_tsc - native_read_tsc();
+	return target_tsc - rdtsc();
 }
 
 static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
@@ -2443,10 +2443,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING |
 #endif
 		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
-		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
-		CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
-		CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
-		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG |
+		CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING |
+		CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING |
+		CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	/*
 	 * We can allow some features even when not supported by the
 	 * hardware. For example, L1 can specify an MSR bitmap - and we
@@ -3423,12 +3423,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 	vmx_segment_cache_clear(to_vmx(vcpu));
 
 	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
-	if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
+	if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) {
 		pr_debug_ratelimited("%s: tss fixup for long mode. \n",
 				     __func__);
 		vmcs_write32(GUEST_TR_AR_BYTES,
-			     (guest_tr_ar & ~AR_TYPE_MASK)
-			     | AR_TYPE_BUSY_64_TSS);
+			     (guest_tr_ar & ~VMX_AR_TYPE_MASK)
+			     | VMX_AR_TYPE_BUSY_64_TSS);
 	}
 	vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
 }
@@ -3719,7 +3719,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu)
 		return 0;
 	else {
 		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
-		return AR_DPL(ar);
+		return VMX_AR_DPL(ar);
 	}
 }
 
@@ -3847,11 +3847,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
 
 	if (cs.unusable)
 		return false;
-	if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
+	if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK))
 		return false;
 	if (!cs.s)
 		return false;
-	if (cs.type & AR_TYPE_WRITEABLE_MASK) {
+	if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) {
 		if (cs.dpl > cs_rpl)
 			return false;
 	} else {
@@ -3901,7 +3901,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
 		return false;
 	if (!var.present)
 		return false;
-	if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) {
+	if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) {
 		if (var.dpl < rpl) /* DPL < RPL */
 			return false;
 	}
@@ -5759,73 +5759,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
 }
 
-static u64 ept_rsvd_mask(u64 spte, int level)
-{
-	int i;
-	u64 mask = 0;
-
-	for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
-		mask |= (1ULL << i);
-
-	if (level == 4)
-		/* bits 7:3 reserved */
-		mask |= 0xf8;
-	else if (spte & (1ULL << 7))
-		/*
-		 * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively,
-		 * level == 1 if the hypervisor is using the ignored bit 7.
-		 */
-		mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE;
-	else if (level > 1)
-		/* bits 6:3 reserved */
-		mask |= 0x78;
-
-	return mask;
-}
-
-static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
-				       int level)
-{
-	printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
-
-	/* 010b (write-only) */
-	WARN_ON((spte & 0x7) == 0x2);
-
-	/* 110b (write/execute) */
-	WARN_ON((spte & 0x7) == 0x6);
-
-	/* 100b (execute-only) and value not supported by logical processor */
-	if (!cpu_has_vmx_ept_execute_only())
-		WARN_ON((spte & 0x7) == 0x4);
-
-	/* not 000b */
-	if ((spte & 0x7)) {
-		u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
-
-		if (rsvd_bits != 0) {
-			printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
-					 __func__, rsvd_bits);
-			WARN_ON(1);
-		}
-
-		/* bits 5:3 are _not_ reserved for large page or leaf page */
-		if ((rsvd_bits & 0x38) == 0) {
-			u64 ept_mem_type = (spte & 0x38) >> 3;
-
-			if (ept_mem_type == 2 || ept_mem_type == 3 ||
-			    ept_mem_type == 7) {
-				printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
-						__func__, ept_mem_type);
-				WARN_ON(1);
-			}
-		}
-	}
-}
-
 static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 {
-	u64 sptes[4];
-	int nr_sptes, i, ret;
+	int ret;
 	gpa_t gpa;
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
@@ -5846,13 +5782,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 		return 1;
 
 	/* It is the real ept misconfig */
-	printk(KERN_ERR "EPT: Misconfiguration.\n");
-	printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
-
-	nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
-
-	for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
-		ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
+	WARN_ON(1);
 
 	vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
 	vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
@@ -6246,6 +6176,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu)
 	return handle_nop(vcpu);
 }
 
+static int handle_monitor_trap(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 static int handle_monitor(struct kvm_vcpu *vcpu)
 {
 	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
@@ -6408,8 +6343,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
  */
 static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 				 unsigned long exit_qualification,
-				 u32 vmx_instruction_info, gva_t *ret)
+				 u32 vmx_instruction_info, bool wr, gva_t *ret)
 {
+	gva_t off;
+	bool exn;
+	struct kvm_segment s;
+
 	/*
 	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
 	 * Execution", on an exit, vmx_instruction_info holds most of the
@@ -6434,22 +6373,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 
 	/* Addr = segment_base + offset */
 	/* offset = base + [index * scale] + displacement */
-	*ret = vmx_get_segment_base(vcpu, seg_reg);
+	off = exit_qualification; /* holds the displacement */
 	if (base_is_valid)
-		*ret += kvm_register_read(vcpu, base_reg);
+		off += kvm_register_read(vcpu, base_reg);
 	if (index_is_valid)
-		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
-	*ret += exit_qualification; /* holds the displacement */
+		off += kvm_register_read(vcpu, index_reg)<<scaling;
+	vmx_get_segment(vcpu, &s, seg_reg);
+	*ret = s.base + off;
 
 	if (addr_size == 1) /* 32 bit */
 		*ret &= 0xffffffff;
 
-	/*
-	 * TODO: throw #GP (and return 1) in various cases that the VM*
-	 * instructions require it - e.g., offset beyond segment limit,
-	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
-	 * address, and so on. Currently these are not checked.
-	 */
+	/* Checks for #GP/#SS exceptions. */
+	exn = false;
+	if (is_protmode(vcpu)) {
+		/* Protected mode: apply checks for segment validity in the
+		 * following order:
+		 * - segment type check (#GP(0) may be thrown)
+		 * - usability check (#GP(0)/#SS(0))
+		 * - limit check (#GP(0)/#SS(0))
+		 */
+		if (wr)
+			/* #GP(0) if the destination operand is located in a
+			 * read-only data segment or any code segment.
+			 */
+			exn = ((s.type & 0xa) == 0 || (s.type & 8));
+		else
+			/* #GP(0) if the source operand is located in an
+			 * execute-only code segment
+			 */
+			exn = ((s.type & 0xa) == 8);
+	}
+	if (exn) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+		return 1;
+	}
+	if (is_long_mode(vcpu)) {
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is an only check for long mode.
+		 */
+		exn = is_noncanonical_address(*ret);
+	} else if (is_protmode(vcpu)) {
+		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
+		 */
+		exn = (s.unusable != 0);
+		/* Protected mode: #GP(0)/#SS(0) if the memory
+		 * operand is outside the segment limit.
+		 */
+		exn = exn || (off + sizeof(u64) > s.limit);
+	}
+	if (exn) {
+		kvm_queue_exception_e(vcpu,
+				      seg_reg == VCPU_SREG_SS ?
+						SS_VECTOR : GP_VECTOR,
+				      0);
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -6471,7 +6451,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
 		return 1;
 
 	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
@@ -6999,7 +6979,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 			field_value);
 	} else {
 		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, &gva))
+				vmx_instruction_info, true, &gva))
 			return 1;
 		/* _system ok, as nested_vmx_check_permission verified cpl=0 */
 		kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
@@ -7036,7 +7016,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 			(((vmx_instruction_info) >> 3) & 0xf));
 	else {
 		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, &gva))
+				vmx_instruction_info, false, &gva))
 			return 1;
 		if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
 			   &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
@@ -7128,7 +7108,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (get_vmx_mem_address(vcpu, exit_qualification,
-			vmx_instruction_info, &vmcs_gva))
+			vmx_instruction_info, true, &vmcs_gva))
 		return 1;
 	/* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */
 	if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
@@ -7184,7 +7164,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	 * operand is read even if it isn't needed (e.g., for type==global)
 	 */
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmx_instruction_info, &gva))
+			vmx_instruction_info, false, &gva))
 		return 1;
 	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
 				sizeof(operand), &e)) {
@@ -7282,6 +7262,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_TRAP_FLAG]       = handle_monitor_trap,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
 	[EXIT_REASON_INVVPID]                 = handle_invvpid,
@@ -7542,6 +7523,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return true;
 	case EXIT_REASON_MWAIT_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
+	case EXIT_REASON_MONITOR_TRAP_FLAG:
+		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
 	case EXIT_REASON_MONITOR_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
 	case EXIT_REASON_PAUSE_INSTRUCTION:
@@ -8632,22 +8615,17 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: always map as UC
+	 * 1. MMIO: guest may want to apply WC, trust it.
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.
+	 *	result, try to trust guest.  So the same as item 1.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (is_mmio) {
-		cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
-
-	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;
@@ -8655,7 +8633,10 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 
 	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
 		ipat = VMX_EPT_IPAT_BIT;
-		cache = MTRR_TYPE_UNCACHABLE;
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+			cache = MTRR_TYPE_WRBACK;
+		else
+			cache = MTRR_TYPE_UNCACHABLE;
 		goto exit;
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bbaf44e8f0d3..1e7e76e14e89 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -29,6 +29,7 @@
 #include "cpuid.h"
 #include "assigned-dev.h"
 #include "pmu.h"
+#include "hyperv.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
@@ -221,11 +222,9 @@ static void shared_msr_update(unsigned slot, u32 msr)
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
 	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
+	shared_msrs_global.msrs[slot] = msr;
 	if (slot >= shared_msrs_global.nr)
 		shared_msrs_global.nr = slot + 1;
-	shared_msrs_global.msrs[slot] = msr;
-	/* we need ensured the shared_msr_global have been updated */
-	smp_wmb();
 }
 EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
 
@@ -526,7 +525,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
 		if (is_present_gpte(pdpte[i]) &&
-		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
+		    (pdpte[i] &
+		     vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
 			ret = 0;
 			goto out;
 		}
@@ -949,6 +949,8 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+	HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
+	HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 
@@ -1217,11 +1219,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 		 __func__, base_khz, scaled_khz, shift, *pmultiplier);
 }
 
-static inline u64 get_kernel_ns(void)
-{
-	return ktime_get_boot_ns();
-}
-
 #ifdef CONFIG_X86_64
 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
 #endif
@@ -1444,20 +1441,8 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc);
 
 static cycle_t read_tsc(void)
 {
-	cycle_t ret;
-	u64 last;
-
-	/*
-	 * Empirically, a fence (of type that depends on the CPU)
-	 * before rdtsc is enough to ensure that rdtsc is ordered
-	 * with respect to loads.  The various CPU manuals are unclear
-	 * as to whether rdtsc can be reordered with later loads,
-	 * but no one has ever seen it happen.
-	 */
-	rdtsc_barrier();
-	ret = (cycle_t)vget_cycles();
-
-	last = pvclock_gtod_data.clock.cycle_last;
+	cycle_t ret = (cycle_t)rdtsc_ordered();
+	u64 last = pvclock_gtod_data.clock.cycle_last;
 
 	if (likely(ret >= last))
 		return ret;
@@ -1646,7 +1631,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		return 1;
 	}
 	if (!use_master_clock) {
-		host_tsc = native_read_tsc();
+		host_tsc = rdtsc();
 		kernel_ns = get_kernel_ns();
 	}
 
@@ -1869,123 +1854,6 @@ out:
 	return r;
 }
 
-static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
-{
-	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
-}
-
-static bool kvm_hv_msr_partition_wide(u32 msr)
-{
-	bool r = false;
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-	case HV_X64_MSR_HYPERCALL:
-	case HV_X64_MSR_REFERENCE_TSC:
-	case HV_X64_MSR_TIME_REF_COUNT:
-		r = true;
-		break;
-	}
-
-	return r;
-}
-
-static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	struct kvm *kvm = vcpu->kvm;
-
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-		kvm->arch.hv_guest_os_id = data;
-		/* setting guest os id to zero disables hypercall page */
-		if (!kvm->arch.hv_guest_os_id)
-			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
-		break;
-	case HV_X64_MSR_HYPERCALL: {
-		u64 gfn;
-		unsigned long addr;
-		u8 instructions[4];
-
-		/* if guest os id is not set hypercall should remain disabled */
-		if (!kvm->arch.hv_guest_os_id)
-			break;
-		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
-			kvm->arch.hv_hypercall = data;
-			break;
-		}
-		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
-		addr = gfn_to_hva(kvm, gfn);
-		if (kvm_is_error_hva(addr))
-			return 1;
-		kvm_x86_ops->patch_hypercall(vcpu, instructions);
-		((unsigned char *)instructions)[3] = 0xc3; /* ret */
-		if (__copy_to_user((void __user *)addr, instructions, 4))
-			return 1;
-		kvm->arch.hv_hypercall = data;
-		mark_page_dirty(kvm, gfn);
-		break;
-	}
-	case HV_X64_MSR_REFERENCE_TSC: {
-		u64 gfn;
-		HV_REFERENCE_TSC_PAGE tsc_ref;
-		memset(&tsc_ref, 0, sizeof(tsc_ref));
-		kvm->arch.hv_tsc_page = data;
-		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
-			break;
-		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-		if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
-			&tsc_ref, sizeof(tsc_ref)))
-			return 1;
-		mark_page_dirty(kvm, gfn);
-		break;
-	}
-	default:
-		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
-			    "data 0x%llx\n", msr, data);
-		return 1;
-	}
-	return 0;
-}
-
-static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	switch (msr) {
-	case HV_X64_MSR_APIC_ASSIST_PAGE: {
-		u64 gfn;
-		unsigned long addr;
-
-		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
-			vcpu->arch.hv_vapic = data;
-			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
-				return 1;
-			break;
-		}
-		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
-		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
-		if (kvm_is_error_hva(addr))
-			return 1;
-		if (__clear_user((void __user *)addr, PAGE_SIZE))
-			return 1;
-		vcpu->arch.hv_vapic = data;
-		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-		if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
-			return 1;
-		break;
-	}
-	case HV_X64_MSR_EOI:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
-	case HV_X64_MSR_ICR:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
-	case HV_X64_MSR_TPR:
-		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
-	default:
-		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
-			    "data 0x%llx\n", msr, data);
-		return 1;
-	}
-
-	return 0;
-}
-
 static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
 	gpa_t gpa = data & ~0x3f;
@@ -2105,7 +1973,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (guest_cpuid_has_tsc_adjust(vcpu)) {
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
-				kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true);
+				adjust_tsc_offset_guest(vcpu, adj);
 			}
 			vcpu->arch.ia32_tsc_adjust_msr = data;
 		}
@@ -2224,15 +2092,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 */
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr)) {
-			int r;
-			mutex_lock(&vcpu->kvm->lock);
-			r = set_msr_hyperv_pw(vcpu, msr, data);
-			mutex_unlock(&vcpu->kvm->lock);
-			return r;
-		} else
-			return set_msr_hyperv(vcpu, msr, data);
-		break;
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_set_msr_common(vcpu, msr, data,
+					     msr_info->host_initiated);
 	case MSR_IA32_BBL_CR_CTL3:
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
@@ -2315,68 +2178,6 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
-static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 data = 0;
-	struct kvm *kvm = vcpu->kvm;
-
-	switch (msr) {
-	case HV_X64_MSR_GUEST_OS_ID:
-		data = kvm->arch.hv_guest_os_id;
-		break;
-	case HV_X64_MSR_HYPERCALL:
-		data = kvm->arch.hv_hypercall;
-		break;
-	case HV_X64_MSR_TIME_REF_COUNT: {
-		data =
-		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
-		break;
-	}
-	case HV_X64_MSR_REFERENCE_TSC:
-		data = kvm->arch.hv_tsc_page;
-		break;
-	default:
-		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
-		return 1;
-	}
-
-	*pdata = data;
-	return 0;
-}
-
-static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 data = 0;
-
-	switch (msr) {
-	case HV_X64_MSR_VP_INDEX: {
-		int r;
-		struct kvm_vcpu *v;
-		kvm_for_each_vcpu(r, v, vcpu->kvm) {
-			if (v == vcpu) {
-				data = r;
-				break;
-			}
-		}
-		break;
-	}
-	case HV_X64_MSR_EOI:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
-	case HV_X64_MSR_ICR:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
-	case HV_X64_MSR_TPR:
-		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
-	case HV_X64_MSR_APIC_ASSIST_PAGE:
-		data = vcpu->arch.hv_vapic;
-		break;
-	default:
-		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
-		return 1;
-	}
-	*pdata = data;
-	return 0;
-}
-
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	switch (msr_info->index) {
@@ -2493,14 +2294,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 0x20000000;
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr_info->index)) {
-			int r;
-			mutex_lock(&vcpu->kvm->lock);
-			r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data);
-			mutex_unlock(&vcpu->kvm->lock);
-			return r;
-		} else
-			return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data);
+	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+	case HV_X64_MSR_CRASH_CTL:
+		return kvm_hv_get_msr_common(vcpu,
+					     msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_BBL_CR_CTL3:
 		/* This legacy MSR exists but isn't fully documented in current
@@ -2651,6 +2448,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_TSC_DEADLINE_TIMER:
 	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_DISABLE_QUIRKS:
+	case KVM_CAP_SET_BOOT_CPU_ID:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
@@ -2810,7 +2608,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
 		s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
-				native_read_tsc() - vcpu->arch.last_host_tsc;
+				rdtsc() - vcpu->arch.last_host_tsc;
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 		if (check_tsc_unstable()) {
@@ -2838,7 +2636,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
-	vcpu->arch.last_host_tsc = native_read_tsc();
+	vcpu->arch.last_host_tsc = rdtsc();
 }
 
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -3157,8 +2955,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
 			memcpy(dest, src + offset, size);
-		} else
-			WARN_ON_ONCE(1);
+		}
 
 		valid -= feature;
 	}
@@ -3818,30 +3615,25 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = kvm_ioapic_init(kvm);
 			if (r) {
 				mutex_lock(&kvm->slots_lock);
-				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-							  &vpic->dev_master);
-				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-							  &vpic->dev_slave);
-				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-							  &vpic->dev_eclr);
+				kvm_destroy_pic(vpic);
 				mutex_unlock(&kvm->slots_lock);
-				kfree(vpic);
 				goto create_irqchip_unlock;
 			}
 		} else
 			goto create_irqchip_unlock;
-		smp_wmb();
-		kvm->arch.vpic = vpic;
-		smp_wmb();
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
 			mutex_lock(&kvm->slots_lock);
 			mutex_lock(&kvm->irq_lock);
 			kvm_ioapic_destroy(kvm);
-			kvm_destroy_pic(kvm);
+			kvm_destroy_pic(vpic);
 			mutex_unlock(&kvm->irq_lock);
 			mutex_unlock(&kvm->slots_lock);
+			goto create_irqchip_unlock;
 		}
+		/* Write kvm->irq_routing before kvm->arch.vpic.  */
+		smp_wmb();
+		kvm->arch.vpic = vpic;
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
@@ -3968,6 +3760,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_reinject(kvm, &control);
 		break;
 	}
+	case KVM_SET_BOOT_CPU_ID:
+		r = 0;
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus) != 0)
+			r = -EBUSY;
+		else
+			kvm->arch.bsp_vcpu_id = arg;
+		mutex_unlock(&kvm->lock);
+		break;
 	case KVM_XEN_HVM_CONFIG: {
 		r = -EFAULT;
 		if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
@@ -5883,66 +5684,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
-int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
-{
-	u64 param, ingpa, outgpa, ret;
-	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
-	bool fast, longmode;
-
-	/*
-	 * hypercall generates UD from non zero cpl and real mode
-	 * per HYPER-V spec
-	 */
-	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 0;
-	}
-
-	longmode = is_64_bit_mode(vcpu);
-
-	if (!longmode) {
-		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
-		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
-		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
-	}
-#ifdef CONFIG_X86_64
-	else {
-		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
-		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
-		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
-	}
-#endif
-
-	code = param & 0xffff;
-	fast = (param >> 16) & 0x1;
-	rep_cnt = (param >> 32) & 0xfff;
-	rep_idx = (param >> 48) & 0xfff;
-
-	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
-
-	switch (code) {
-	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
-		kvm_vcpu_on_spin(vcpu);
-		break;
-	default:
-		res = HV_STATUS_INVALID_HYPERCALL_CODE;
-		break;
-	}
-
-	ret = res | (((u64)rep_done & 0xfff) << 32);
-	if (longmode) {
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
-	} else {
-		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
-	}
-
-	return 1;
-}
-
 /*
  * kvm_pv_kick_cpu_op:  Kick a vcpu.
  *
@@ -6328,6 +6069,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 static void process_smi(struct kvm_vcpu *vcpu)
 {
 	struct kvm_segment cs, ds;
+	struct desc_ptr dt;
 	char buf[512];
 	u32 cr0;
 
@@ -6360,6 +6102,10 @@ static void process_smi(struct kvm_vcpu *vcpu)
 
 	kvm_x86_ops->set_cr4(vcpu, 0);
 
+	/* Undocumented: IDT limit is set to zero on entry to SMM.  */
+	dt.address = dt.size = 0;
+	kvm_x86_ops->set_idt(vcpu, &dt);
+
 	__kvm_set_dr(vcpu, 7, DR7_FIXED_1);
 
 	cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
@@ -6514,6 +6260,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			vcpu_scan_ioapic(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
 			kvm_vcpu_reload_apic_access_page(vcpu);
+		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
+			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
+			r = 0;
+			goto out;
+		}
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -6623,7 +6375,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		hw_breakpoint_restore();
 
 	vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu,
-							   native_read_tsc());
+							   rdtsc());
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
@@ -7315,11 +7067,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
 
-	/*
-	 * Activate fpu unconditionally in case the guest needs eager FPU.  It will be
-	 * deactivated soon if it doesn't.
-	 */
-	kvm_x86_ops->fpu_activate(vcpu);
 	return vcpu;
 }
 
@@ -7437,7 +7184,7 @@ int kvm_arch_hardware_enable(void)
 	if (ret != 0)
 		return ret;
 
-	local_tsc = native_read_tsc();
+	local_tsc = rdtsc();
 	stable = !check_tsc_unstable();
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -7541,6 +7288,17 @@ void kvm_arch_check_processor_compat(void *rtn)
 	kvm_x86_ops->check_processor_compatibility(rtn);
 }
 
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
+
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
+}
+
 bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 {
 	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
@@ -8218,6 +7976,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+void kvm_arch_start_assignment(struct kvm *kvm)
+{
+	atomic_inc(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
+
+void kvm_arch_end_assignment(struct kvm *kvm)
+{
+	atomic_dec(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
+
+bool kvm_arch_has_assigned_device(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
+
 void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
 {
 	atomic_inc(&kvm->arch.noncoherent_dma_count);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index edc8cdcd786b..2f822cd886c2 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -147,6 +147,16 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
 	return kvm_register_write(vcpu, reg, val);
 }
 
+static inline u64 get_kernel_ns(void)
+{
+	return ktime_get_boot_ns();
+}
+
+static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
+{
+	return !(kvm->arch.disabled_quirks & quirk);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index f2dc08c003eb..161804de124a 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -835,16 +835,46 @@ static struct irq_chip lguest_irq_controller = {
 	.irq_unmask	= enable_lguest_irq,
 };
 
+/*
+ * Interrupt descriptors are allocated as-needed, but low-numbered ones are
+ * reserved by the generic x86 code.  So we ignore irq_alloc_desc_at if it
+ * tells us the irq is already used: other errors (ie. ENOMEM) we take
+ * seriously.
+ */
+static int lguest_setup_irq(unsigned int irq)
+{
+	struct irq_desc *desc;
+	int err;
+
+	/* Returns -ve error or vector number. */
+	err = irq_alloc_desc_at(irq, 0);
+	if (err < 0 && err != -EEXIST)
+		return err;
+
+	/*
+	 * Tell the Linux infrastructure that the interrupt is
+	 * controlled by our level-based lguest interrupt controller.
+	 */
+	irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
+				      handle_level_irq, "level");
+
+	/* Some systems map "vectors" to interrupts weirdly.  Not us! */
+	desc = irq_to_desc(irq);
+	__this_cpu_write(vector_irq[FIRST_EXTERNAL_VECTOR + irq], desc);
+	return 0;
+}
+
 static int lguest_enable_irq(struct pci_dev *dev)
 {
+	int err;
 	u8 line = 0;
 
 	/* We literally use the PCI interrupt line as the irq number. */
 	pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line);
-	irq_set_chip_and_handler_name(line, &lguest_irq_controller,
-				      handle_level_irq, "level");
-	dev->irq = line;
-	return 0;
+	err = lguest_setup_irq(line);
+	if (!err)
+		dev->irq = line;
+	return err;
 }
 
 /* We don't do hotplug PCI, so this shouldn't be called. */
@@ -855,17 +885,13 @@ static void lguest_disable_irq(struct pci_dev *dev)
 
 /*
  * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware
- * interrupt (except 128, which is used for system calls), and then tells the
- * Linux infrastructure that each interrupt is controlled by our level-based
- * lguest interrupt controller.
+ * interrupt (except 128, which is used for system calls).
  */
 static void __init lguest_init_IRQ(void)
 {
 	unsigned int i;
 
 	for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
-		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
-		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
 		if (i != IA32_SYSCALL_VECTOR)
 			set_intr_gate(i, irq_entries_start +
 					8 * (i - FIRST_EXTERNAL_VECTOR));
@@ -879,26 +905,6 @@ static void __init lguest_init_IRQ(void)
 }
 
 /*
- * Interrupt descriptors are allocated as-needed, but low-numbered ones are
- * reserved by the generic x86 code.  So we ignore irq_alloc_desc_at if it
- * tells us the irq is already used: other errors (ie. ENOMEM) we take
- * seriously.
- */
-int lguest_setup_irq(unsigned int irq)
-{
-	int err;
-
-	/* Returns -ve error or vector number. */
-	err = irq_alloc_desc_at(irq, 0);
-	if (err < 0 && err != -EEXIST)
-		return err;
-
-	irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
-				      handle_level_irq, "level");
-	return 0;
-}
-
-/*
  * Time.
  *
  * It would be far better for everyone if the Guest had its own clock, but
@@ -985,23 +991,11 @@ static int lguest_clockevent_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void lguest_clockevent_set_mode(enum clock_event_mode mode,
-                                      struct clock_event_device *evt)
+static int lguest_clockevent_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/* A 0 argument shuts the clock down. */
-		hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* This is what we expect. */
-		break;
-	case CLOCK_EVT_MODE_PERIODIC:
-		BUG();
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	/* A 0 argument shuts the clock down. */
+	hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0);
+	return 0;
 }
 
 /* This describes our primitive timer chip. */
@@ -1009,7 +1003,7 @@ static struct clock_event_device lguest_clockevent = {
 	.name                   = "lguest",
 	.features               = CLOCK_EVT_FEAT_ONESHOT,
 	.set_next_event         = lguest_clockevent_set_next_event,
-	.set_mode               = lguest_clockevent_set_mode,
+	.set_state_shutdown	= lguest_clockevent_shutdown,
 	.rating                 = INT_MAX,
 	.mult                   = 1,
 	.shift                  = 0,
@@ -1040,7 +1034,8 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
-	lguest_setup_irq(0);
+	if (lguest_setup_irq(0) != 0)
+		panic("Could not set up timer irq");
 	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 39d6a3db0b96..e912b2f6d36e 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -20,6 +20,7 @@
 #include <asm/processor.h>
 #include <asm/delay.h>
 #include <asm/timer.h>
+#include <asm/mwait.h>
 
 #ifdef CONFIG_SMP
 # include <asm/smp.h>
@@ -49,16 +50,14 @@ static void delay_loop(unsigned long loops)
 /* TSC based delay: */
 static void delay_tsc(unsigned long __loops)
 {
-	u32 bclock, now, loops = __loops;
+	u64 bclock, now, loops = __loops;
 	int cpu;
 
 	preempt_disable();
 	cpu = smp_processor_id();
-	rdtsc_barrier();
-	rdtscl(bclock);
+	bclock = rdtsc_ordered();
 	for (;;) {
-		rdtsc_barrier();
-		rdtscl(now);
+		now = rdtsc_ordered();
 		if ((now - bclock) >= loops)
 			break;
 
@@ -79,14 +78,51 @@ static void delay_tsc(unsigned long __loops)
 		if (unlikely(cpu != smp_processor_id())) {
 			loops -= (now - bclock);
 			cpu = smp_processor_id();
-			rdtsc_barrier();
-			rdtscl(bclock);
+			bclock = rdtsc_ordered();
 		}
 	}
 	preempt_enable();
 }
 
 /*
+ * On some AMD platforms, MWAITX has a configurable 32-bit timer, that
+ * counts with TSC frequency. The input value is the loop of the
+ * counter, it will exit when the timer expires.
+ */
+static void delay_mwaitx(unsigned long __loops)
+{
+	u64 start, end, delay, loops = __loops;
+
+	start = rdtsc_ordered();
+
+	for (;;) {
+		delay = min_t(u64, MWAITX_MAX_LOOPS, loops);
+
+		/*
+		 * Use cpu_tss as a cacheline-aligned, seldomly
+		 * accessed per-cpu variable as the monitor target.
+		 */
+		__monitorx(this_cpu_ptr(&cpu_tss), 0, 0);
+
+		/*
+		 * AMD, like Intel, supports the EAX hint and EAX=0xf
+		 * means, do not enter any deep C-state and we use it
+		 * here in delay() to minimize wakeup latency.
+		 */
+		__mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
+
+		end = rdtsc_ordered();
+
+		if (loops <= end - start)
+			break;
+
+		loops -= end - start;
+
+		start = end;
+	}
+}
+
+/*
  * Since we calibrate only once at boot, this
  * function should be set once at boot and not changed
  */
@@ -94,13 +130,19 @@ static void (*delay_fn)(unsigned long) = delay_loop;
 
 void use_tsc_delay(void)
 {
-	delay_fn = delay_tsc;
+	if (delay_fn == delay_loop)
+		delay_fn = delay_tsc;
+}
+
+void use_mwaitx_delay(void)
+{
+	delay_fn = delay_mwaitx;
 }
 
 int read_current_timer(unsigned long *timer_val)
 {
 	if (delay_fn == delay_tsc) {
-		rdtscll(*timer_val);
+		*timer_val = rdtsc();
 		return 0;
 	}
 	return -1;
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ddf9ecb53cc3..e342586db6e4 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -20,7 +20,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	unsigned long ret;
 
 	if (__range_not_ok(from, n, TASK_SIZE))
-		return 0;
+		return n;
 
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index f37e84ab49f3..3d8f2e421466 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -29,7 +29,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/traps.h>
-#include <asm/desc.h>
 #include <asm/user.h>
 #include <asm/fpu/internal.h>
 
@@ -181,7 +180,7 @@ void math_emulate(struct math_emu_info *info)
 			math_abort(FPU_info, SIGILL);
 		}
 
-		code_descriptor = LDT_DESCRIPTOR(FPU_CS);
+		code_descriptor = FPU_get_ldt_descriptor(FPU_CS);
 		if (SEG_D_SIZE(code_descriptor)) {
 			/* The above test may be wrong, the book is not clear */
 			/* Segmented 32 bit protected mode */
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 9ccecb61a4fa..5e044d506b7a 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -16,9 +16,24 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 
-/* s is always from a cpu register, and the cpu does bounds checking
- * during register load --> no further bounds checks needed */
-#define LDT_DESCRIPTOR(s)	(((struct desc_struct *)current->mm->context.ldt)[(s) >> 3])
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
+{
+	static struct desc_struct zero_desc;
+	struct desc_struct ret = zero_desc;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	seg >>= 3;
+	mutex_lock(&current->mm->context.lock);
+	if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
+		ret = current->mm->context.ldt->entries[seg];
+	mutex_unlock(&current->mm->context.lock);
+#endif
+	return ret;
+}
+
 #define SEG_D_SIZE(x)		((x).b & (3 << 21))
 #define SEG_G_BIT(x)		((x).b & (1 << 23))
 #define SEG_GRANULARITY(x)	(((x).b & (1 << 23)) ? 4096 : 1)
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index 6ef5e99380f9..8db26591d91a 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -20,7 +20,7 @@
 #include <linux/stddef.h>
 
 #include <asm/uaccess.h>
-#include <asm/desc.h>
+#include <asm/vm86.h>
 
 #include "fpu_system.h"
 #include "exception.h"
@@ -158,7 +158,7 @@ static long pm_address(u_char FPU_modrm, u_char segment,
 		addr->selector = PM_REG_(segment);
 	}
 
-	descriptor = LDT_DESCRIPTOR(PM_REG_(segment));
+	descriptor = FPU_get_ldt_descriptor(addr->selector);
 	base_address = SEG_BASE_ADDR(descriptor);
 	address = base_address + offset;
 	limit = base_address
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9dc909841739..eef44d9a3f77 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,6 +20,7 @@
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_ADDR		*/
 #include <asm/vsyscall.h>		/* emulate_vsyscall		*/
+#include <asm/vm86.h>			/* struct vm86			*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -301,14 +302,16 @@ static inline void
 check_v8086_mode(struct pt_regs *regs, unsigned long address,
 		 struct task_struct *tsk)
 {
+#ifdef CONFIG_VM86
 	unsigned long bit;
 
-	if (!v8086_mode(regs))
+	if (!v8086_mode(regs) || !tsk->thread.vm86)
 		return;
 
 	bit = (address - 0xA0000) >> PAGE_SHIFT;
 	if (bit < 32)
-		tsk->thread.screen_bitmap |= 1 << bit;
+		tsk->thread.vm86->screen_bitmap |= 1 << bit;
+#endif
 }
 
 static bool low_pfn(unsigned long pfn)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 8533b46e6bee..1d8a83df153a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -30,8 +30,11 @@
 /*
  * Tables translating between page_cache_type_t and pte encoding.
  *
- * Minimal supported modes are defined statically, they are modified
- * during bootup if more supported cache modes are available.
+ * The default values are defined statically as minimal supported mode;
+ * WC and WT fall back to UC-.  pat_init() updates these values to support
+ * more cache modes, WC and WT, when it is safe to do so.  See pat_init()
+ * for the details.  Note, __early_ioremap() used during early boot-time
+ * takes pgprot_t (pte encoding) and does not use these tables.
  *
  *   Index into __cachemode2pte_tbl[] is the cachemode.
  *
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8340e45c891a..68aec42545c2 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -137,6 +137,7 @@ page_table_range_init_count(unsigned long start, unsigned long end)
 
 	vaddr = start;
 	pgd_idx = pgd_index(vaddr);
+	pmd_idx = pmd_index(vaddr);
 
 	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index cc5ccc415cc0..b9c78f3bcd67 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -63,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
 		    !PageReserved(pfn_to_page(start_pfn + i)))
 			return 1;
 
-	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
-
 	return 0;
 }
 
@@ -94,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
-	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -117,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	/* First check if whole region can be identified as RAM or not */
-	ram_region = region_is_ram(phys_addr, size);
-	if (ram_region > 0) {
-		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
-				(unsigned long int)phys_addr,
-				(unsigned long int)last_addr);
+	pfn      = phys_addr >> PAGE_SHIFT;
+	last_pfn = last_addr >> PAGE_SHIFT;
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+					  __ioremap_check_ram) == 1) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
 		return NULL;
 	}
 
-	/* If could not be identified(-1), check page by page */
-	if (ram_region < 0) {
-		pfn      = phys_addr >> PAGE_SHIFT;
-		last_pfn = last_addr >> PAGE_SHIFT;
-		if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-					  __ioremap_check_ram) == 1)
-			return NULL;
-	}
 	/*
 	 * Mappings have to be page-aligned
 	 */
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 4860906c6b9f..9ce5da27b136 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
 #include <linux/kdebug.h>
@@ -11,8 +12,6 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern struct range pfn_mapped[E820_X_MAX];
 
-extern unsigned char kasan_zero_page[PAGE_SIZE];
-
 static int __init map_range(struct range *range)
 {
 	unsigned long start;
@@ -36,7 +35,7 @@ static void __init clear_pgds(unsigned long start,
 		pgd_clear(pgd_offset_k(start));
 }
 
-void __init kasan_map_early_shadow(pgd_t *pgd)
+static void __init kasan_map_early_shadow(pgd_t *pgd)
 {
 	int i;
 	unsigned long start = KASAN_SHADOW_START;
@@ -49,106 +48,6 @@ void __init kasan_map_early_shadow(pgd_t *pgd)
 	}
 }
 
-static int __init zero_pte_populate(pmd_t *pmd, unsigned long addr,
-				unsigned long end)
-{
-	pte_t *pte = pte_offset_kernel(pmd, addr);
-
-	while (addr + PAGE_SIZE <= end) {
-		WARN_ON(!pte_none(*pte));
-		set_pte(pte, __pte(__pa_nodebug(kasan_zero_page)
-					| __PAGE_KERNEL_RO));
-		addr += PAGE_SIZE;
-		pte = pte_offset_kernel(pmd, addr);
-	}
-	return 0;
-}
-
-static int __init zero_pmd_populate(pud_t *pud, unsigned long addr,
-				unsigned long end)
-{
-	int ret = 0;
-	pmd_t *pmd = pmd_offset(pud, addr);
-
-	while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) {
-		WARN_ON(!pmd_none(*pmd));
-		set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte)
-					| __PAGE_KERNEL_RO));
-		addr += PMD_SIZE;
-		pmd = pmd_offset(pud, addr);
-	}
-	if (addr < end) {
-		if (pmd_none(*pmd)) {
-			void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE);
-			if (!p)
-				return -ENOMEM;
-			set_pmd(pmd, __pmd(__pa_nodebug(p) | _KERNPG_TABLE));
-		}
-		ret = zero_pte_populate(pmd, addr, end);
-	}
-	return ret;
-}
-
-
-static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
-				unsigned long end)
-{
-	int ret = 0;
-	pud_t *pud = pud_offset(pgd, addr);
-
-	while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) {
-		WARN_ON(!pud_none(*pud));
-		set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd)
-					| __PAGE_KERNEL_RO));
-		addr += PUD_SIZE;
-		pud = pud_offset(pgd, addr);
-	}
-
-	if (addr < end) {
-		if (pud_none(*pud)) {
-			void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE);
-			if (!p)
-				return -ENOMEM;
-			set_pud(pud, __pud(__pa_nodebug(p) | _KERNPG_TABLE));
-		}
-		ret = zero_pmd_populate(pud, addr, end);
-	}
-	return ret;
-}
-
-static int __init zero_pgd_populate(unsigned long addr, unsigned long end)
-{
-	int ret = 0;
-	pgd_t *pgd = pgd_offset_k(addr);
-
-	while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) {
-		WARN_ON(!pgd_none(*pgd));
-		set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud)
-					| __PAGE_KERNEL_RO));
-		addr += PGDIR_SIZE;
-		pgd = pgd_offset_k(addr);
-	}
-
-	if (addr < end) {
-		if (pgd_none(*pgd)) {
-			void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE);
-			if (!p)
-				return -ENOMEM;
-			set_pgd(pgd, __pgd(__pa_nodebug(p) | _KERNPG_TABLE));
-		}
-		ret = zero_pud_populate(pgd, addr, end);
-	}
-	return ret;
-}
-
-
-static void __init populate_zero_shadow(const void *start, const void *end)
-{
-	if (zero_pgd_populate((unsigned long)start, (unsigned long)end))
-		panic("kasan: unable to map zero shadow!");
-}
-
-
 #ifdef CONFIG_KASAN_INLINE
 static int kasan_die_handler(struct notifier_block *self,
 			     unsigned long val,
@@ -166,6 +65,26 @@ static struct notifier_block kasan_die_notifier = {
 };
 #endif
 
+void __init kasan_early_init(void)
+{
+	int i;
+	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
+	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		kasan_zero_pte[i] = __pte(pte_val);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		kasan_zero_pmd[i] = __pmd(pmd_val);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		kasan_zero_pud[i] = __pud(pud_val);
+
+	kasan_map_early_shadow(early_level4_pgt);
+	kasan_map_early_shadow(init_level4_pgt);
+}
+
 void __init kasan_init(void)
 {
 	int i;
@@ -176,10 +95,11 @@ void __init kasan_init(void)
 
 	memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt));
 	load_cr3(early_level4_pgt);
+	__flush_tlb_all();
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
-	populate_zero_shadow((void *)KASAN_SHADOW_START,
+	kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
 			kasan_mem_to_shadow((void *)PAGE_OFFSET));
 
 	for (i = 0; i < E820_X_MAX; i++) {
@@ -189,18 +109,22 @@ void __init kasan_init(void)
 		if (map_range(&pfn_mapped[i]))
 			panic("kasan: unable to allocate shadow!");
 	}
-	populate_zero_shadow(kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
-			kasan_mem_to_shadow((void *)__START_KERNEL_map));
+	kasan_populate_zero_shadow(
+		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
+		kasan_mem_to_shadow((void *)__START_KERNEL_map));
 
 	vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext),
 			(unsigned long)kasan_mem_to_shadow(_end),
 			NUMA_NO_NODE);
 
-	populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
+	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
 			(void *)KASAN_SHADOW_END);
 
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 
 	load_cr3(init_level4_pgt);
+	__flush_tlb_all();
 	init_task.kasan_depth = 0;
+
+	pr_info("Kernel address sanitizer initialized\n");
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 9d518d693b4b..844b06d67df4 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -126,3 +126,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_MPX)
+		return "[mpx]";
+	return NULL;
+}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 7a657f58bbea..db1b0bc5017c 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -20,20 +20,6 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/mpx.h>
 
-static const char *mpx_mapping_name(struct vm_area_struct *vma)
-{
-	return "[mpx]";
-}
-
-static struct vm_operations_struct mpx_vma_ops = {
-	.name = mpx_mapping_name,
-};
-
-static int is_mpx_vma(struct vm_area_struct *vma)
-{
-	return (vma->vm_ops == &mpx_vma_ops);
-}
-
 static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
 {
 	if (is_64bit_mm(mm))
@@ -53,9 +39,6 @@ static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
- *
- * Later on, we use the vma->vm_ops to uniquely identify these
- * VMAs.
  */
 static unsigned long mpx_mmap(unsigned long len)
 {
@@ -101,7 +84,6 @@ static unsigned long mpx_mmap(unsigned long len)
 		ret = -ENOMEM;
 		goto out;
 	}
-	vma->vm_ops = &mpx_vma_ops;
 
 	if (vm_flags & VM_LOCKED) {
 		up_write(&mm->mmap_sem);
@@ -812,7 +794,7 @@ static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 		 * so stop immediately and return an error.  This
 		 * probably results in a SIGSEGV.
 		 */
-		if (!is_mpx_vma(vma))
+		if (!(vma->vm_flags & VM_MPX))
 			return -EINVAL;
 
 		len = min(vma->vm_end, end) - addr;
@@ -945,9 +927,9 @@ static int try_unmap_single_bt(struct mm_struct *mm,
 	 * lots of tables even though we have no actual table
 	 * entries in use.
 	 */
-	while (next && is_mpx_vma(next))
+	while (next && (next->vm_flags & VM_MPX))
 		next = next->vm_next;
-	while (prev && is_mpx_vma(prev))
+	while (prev && (prev->vm_flags & VM_MPX))
 		prev = prev->vm_prev;
 	/*
 	 * We know 'start' and 'end' lie within an area controlled
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 8ff686aa7e8c..5f169d5d76a8 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -8,6 +8,7 @@
 #include <linux/kthread.h>
 #include <linux/random.h>
 #include <linux/kernel.h>
+#include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 
@@ -256,5 +257,4 @@ static int start_pageattr_test(void)
 
 	return 0;
 }
-
-module_init(start_pageattr_test);
+device_initcall(start_pageattr_test);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 727158cb3b3c..2c44c0792301 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -4,7 +4,6 @@
  */
 #include <linux/highmem.h>
 #include <linux/bootmem.h>
-#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3250f2371aea..8ddb5d0d66fb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -117,7 +117,7 @@ static void flush_tlb_func(void *info)
 		} else {
 			unsigned long addr;
 			unsigned long nr_pages =
-				f->flush_end - f->flush_start / PAGE_SIZE;
+				(f->flush_end - f->flush_start) / PAGE_SIZE;
 			addr = f->flush_start;
 			while (addr < f->flush_end) {
 				__flush_tlb_single(addr);
@@ -140,6 +140,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_end = end;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
+	trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 579a8fd74be0..70efcd0940f9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -246,7 +246,7 @@ static void emit_prologue(u8 **pprog)
  *     goto out;
  *   if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
  *     goto out;
- *   prog = array->prog[index];
+ *   prog = array->ptrs[index];
  *   if (prog == NULL)
  *     goto out;
  *   goto *(prog->bpf_func + prologue_size);
@@ -269,7 +269,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
 	      offsetof(struct bpf_array, map.max_entries));
 	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
-#define OFFSET1 44 /* number of bytes to jump */
+#define OFFSET1 47 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -278,15 +278,15 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 */
 	EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 33
+#define OFFSET2 36
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
 
-	/* prog = array->prog[index]; */
-	EMIT4(0x48, 0x8D, 0x44, 0xD6);            /* lea rax, [rsi + rdx * 8 + 0x50] */
-	EMIT1(offsetof(struct bpf_array, prog));
+	/* prog = array->ptrs[index]; */
+	EMIT4_off32(0x48, 0x8D, 0x84, 0xD6,       /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+		    offsetof(struct bpf_array, ptrs));
 	EMIT3(0x48, 0x8B, 0x00);                  /* mov rax, qword ptr [rax] */
 
 	/* if (prog == NULL)
@@ -315,6 +315,26 @@ static void emit_bpf_tail_call(u8 **pprog)
 	*pprog = prog;
 }
 
+
+static void emit_load_skb_data_hlen(u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	/* r9d = skb->len - skb->data_len (headlen)
+	 * r10 = skb->data
+	 */
+	/* mov %r9d, off32(%rdi) */
+	EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len));
+
+	/* sub %r9d, off32(%rdi) */
+	EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len));
+
+	/* mov %r10, off32(%rdi) */
+	EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data));
+	*pprog = prog;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
@@ -329,36 +349,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 
 	emit_prologue(&prog);
 
-	if (seen_ld_abs) {
-		/* r9d : skb->len - skb->data_len (headlen)
-		 * r10 : skb->data
-		 */
-		if (is_imm8(offsetof(struct sk_buff, len)))
-			/* mov %r9d, off8(%rdi) */
-			EMIT4(0x44, 0x8b, 0x4f,
-			      offsetof(struct sk_buff, len));
-		else
-			/* mov %r9d, off32(%rdi) */
-			EMIT3_off32(0x44, 0x8b, 0x8f,
-				    offsetof(struct sk_buff, len));
-
-		if (is_imm8(offsetof(struct sk_buff, data_len)))
-			/* sub %r9d, off8(%rdi) */
-			EMIT4(0x44, 0x2b, 0x4f,
-			      offsetof(struct sk_buff, data_len));
-		else
-			EMIT3_off32(0x44, 0x2b, 0x8f,
-				    offsetof(struct sk_buff, data_len));
-
-		if (is_imm8(offsetof(struct sk_buff, data)))
-			/* mov %r10, off8(%rdi) */
-			EMIT4(0x4c, 0x8b, 0x57,
-			      offsetof(struct sk_buff, data));
-		else
-			/* mov %r10, off32(%rdi) */
-			EMIT3_off32(0x4c, 0x8b, 0x97,
-				    offsetof(struct sk_buff, data));
-	}
+	if (seen_ld_abs)
+		emit_load_skb_data_hlen(&prog);
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
@@ -367,6 +359,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		u8 b1 = 0, b2 = 0, b3 = 0;
 		s64 jmp_offset;
 		u8 jmp_cond;
+		bool reload_skb_data;
 		int ilen;
 		u8 *func;
 
@@ -818,12 +811,18 @@ xadd:			if (is_imm8(insn->off))
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
 			if (seen_ld_abs) {
-				EMIT2(0x41, 0x52); /* push %r10 */
-				EMIT2(0x41, 0x51); /* push %r9 */
-				/* need to adjust jmp offset, since
-				 * pop %r9, pop %r10 take 4 bytes after call insn
-				 */
-				jmp_offset += 4;
+				reload_skb_data = bpf_helper_changes_skb_data(func);
+				if (reload_skb_data) {
+					EMIT1(0x57); /* push %rdi */
+					jmp_offset += 22; /* pop, mov, sub, mov */
+				} else {
+					EMIT2(0x41, 0x52); /* push %r10 */
+					EMIT2(0x41, 0x51); /* push %r9 */
+					/* need to adjust jmp offset, since
+					 * pop %r9, pop %r10 take 4 bytes after call insn
+					 */
+					jmp_offset += 4;
+				}
 			}
 			if (!imm32 || !is_simm32(jmp_offset)) {
 				pr_err("unsupported bpf func %d addr %p image %p\n",
@@ -832,8 +831,13 @@ xadd:			if (is_imm8(insn->off))
 			}
 			EMIT1_off32(0xE8, jmp_offset);
 			if (seen_ld_abs) {
-				EMIT2(0x41, 0x59); /* pop %r9 */
-				EMIT2(0x41, 0x5A); /* pop %r10 */
+				if (reload_skb_data) {
+					EMIT1(0x5F); /* pop %rdi */
+					emit_load_skb_data_hlen(&prog);
+				} else {
+					EMIT2(0x41, 0x59); /* pop %r9 */
+					EMIT2(0x41, 0x5A); /* pop %r10 */
+				}
 			}
 			break;
 
@@ -1099,7 +1103,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, proglen, 0, image);
+		bpf_jit_dump(prog->len, proglen, pass + 1, image);
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8fd6f44aee83..09d3afc0a181 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -166,7 +166,6 @@ void pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
-	pci_read_bridge_bases(b);
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 }
@@ -673,24 +672,22 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
-int pcibios_enable_device(struct pci_dev *dev, int mask)
+int pcibios_alloc_irq(struct pci_dev *dev)
 {
-	int err;
-
-	if ((err = pci_enable_resources(dev, mask)) < 0)
-		return err;
-
-	if (!pci_dev_msi_enabled(dev))
-		return pcibios_enable_irq(dev);
-	return 0;
+	return pcibios_enable_irq(dev);
 }
 
-void pcibios_disable_device (struct pci_dev *dev)
+void pcibios_free_irq(struct pci_dev *dev)
 {
-	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+	if (pcibios_disable_irq)
 		pcibios_disable_irq(dev);
 }
 
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+	return pci_enable_resources(dev, mask);
+}
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 9a2b7101ae8a..e58565556703 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -62,19 +62,6 @@ static void pci_fixup_umc_ide(struct pci_dev *d)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_UMC, PCI_DEVICE_ID_UMC_UM8886BF, pci_fixup_umc_ide);
 
-static void pci_fixup_ncr53c810(struct pci_dev *d)
-{
-	/*
-	 * NCR 53C810 returns class code 0 (at least on some systems).
-	 * Fix class to be PCI_CLASS_STORAGE_SCSI
-	 */
-	if (!d->class) {
-		dev_warn(&d->dev, "Fixing NCR 53C810 class code\n");
-		d->class = PCI_CLASS_STORAGE_SCSI << 8;
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, pci_fixup_ncr53c810);
-
 static void pci_fixup_latency(struct pci_dev *d)
 {
 	/*
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 27062303c881..0d24e7c10145 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -35,6 +35,9 @@
 
 #define PCIE_CAP_OFFSET	0x100
 
+/* Quirks for the listed devices */
+#define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
+
 /* Fixed BAR fields */
 #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00	/* Fixed BAR (TBD) */
 #define PCI_FIXED_BAR_0_SIZE	0x04
@@ -210,22 +213,41 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
 	struct irq_alloc_info info;
 	int polarity;
+	int ret;
 
-	if (dev->irq_managed && dev->irq > 0)
+	if (pci_has_managed_irq(dev))
 		return 0;
 
-	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
-		polarity = 0; /* active high */
-	else
-		polarity = 1; /* active low */
+	switch (intel_mid_identify_cpu()) {
+	case INTEL_MID_CPU_CHIP_TANGIER:
+		polarity = IOAPIC_POL_HIGH;
+
+		/* Special treatment for IRQ0 */
+		if (dev->irq == 0) {
+			/*
+			 * TNG has IRQ0 assigned to eMMC controller. But there
+			 * are also other devices with bogus PCI configuration
+			 * that have IRQ0 assigned. This check ensures that
+			 * eMMC gets it.
+			 */
+			if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
+				return -EBUSY;
+		}
+		break;
+	default:
+		polarity = IOAPIC_POL_LOW;
+		break;
+	}
+
 	ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
 
 	/*
 	 * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
 	 * IOAPIC RTE entries, so we just enable RTE for the device.
 	 */
-	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0)
-		return -EBUSY;
+	ret = mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info);
+	if (ret < 0)
+		return ret;
 
 	dev->irq_managed = 1;
 
@@ -234,14 +256,17 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
-	    dev->irq > 0) {
+	if (pci_has_managed_irq(dev)) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
+		/*
+		 * Don't reset dev->irq here, otherwise
+		 * intel_mid_pci_irq_enable() will fail on next call.
+		 */
 	}
 }
 
-struct pci_ops intel_mid_pci_ops = {
+static struct pci_ops intel_mid_pci_ops = {
 	.read = pci_read,
 	.write = pci_write,
 };
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 9bd115484745..32e70343e6fd 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			struct pci_dev *temp_dev;
 			int irq;
 
-			if (dev->irq_managed && dev->irq > 0)
+			if (pci_has_managed_irq(dev))
 				return 0;
 
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
@@ -1230,8 +1230,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				dev->irq_managed = 1;
-				dev->irq = irq;
+				pci_set_managed_irq(dev, irq);
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
 				return 0;
@@ -1257,24 +1256,10 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
-bool mp_should_keep_irq(struct device *dev)
-{
-	if (dev->power.is_prepared)
-		return true;
-#ifdef CONFIG_PM
-	if (dev->power.runtime_status == RPM_SUSPENDING)
-		return true;
-#endif
-
-	return false;
-}
-
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
-	    dev->irq_managed && dev->irq) {
+	if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) {
 		mp_unmap_irq(dev->irq);
-		dev->irq = 0;
-		dev->irq_managed = 0;
+		pci_reset_managed_irq(dev);
 	}
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index d22f4b5bbc04..ff31ab464213 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -179,7 +179,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (ret)
 		goto error;
 	i = 0;
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
+	for_each_pci_msi_entry(msidesc, dev) {
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
@@ -230,7 +230,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
+	for_each_pci_msi_entry(msidesc, dev) {
 		__pci_read_msi_msg(msidesc, &msg);
 		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
 			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
@@ -274,7 +274,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	int ret = 0;
 	struct msi_desc *msidesc;
 
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
+	for_each_pci_msi_entry(msidesc, dev) {
 		struct physdev_map_pirq map_irq;
 		domid_t domid;
 
@@ -386,7 +386,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct msi_desc *msidesc;
 
-	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
+	msidesc = first_pci_msi_entry(dev);
 	if (msidesc->msi_attrib.is_msix)
 		xen_pci_frontend_disable_msix(dev);
 	else
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index f1a6c8e86ddd..184842ef332e 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -5,6 +5,7 @@ obj-y	+= efi/
 obj-y	+= geode/
 obj-y	+= goldfish/
 obj-y	+= iris/
+obj-y	+= intel/
 obj-y	+= intel-mid/
 obj-y	+= intel-quark/
 obj-y	+= olpc/
diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile
index 0a3a40cbc794..40983f5b0858 100644
--- a/arch/x86/platform/atom/Makefile
+++ b/arch/x86/platform/atom/Makefile
@@ -1 +1,2 @@
-obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o
+obj-$(CONFIG_PMC_ATOM)		+= pmc_atom.o
+obj-$(CONFIG_PUNIT_ATOM_DEBUG)	+= punit_atom_debug.o
diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/platform/atom/pmc_atom.c
index d66a4fe6caee..964ff4fc61f9 100644
--- a/arch/x86/kernel/pmc_atom.c
+++ b/arch/x86/platform/atom/pmc_atom.c
@@ -15,7 +15,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/device.h>
@@ -25,80 +24,149 @@
 
 #include <asm/pmc_atom.h>
 
+struct pmc_bit_map {
+	const char *name;
+	u32 bit_mask;
+};
+
+struct pmc_reg_map {
+	const struct pmc_bit_map *d3_sts_0;
+	const struct pmc_bit_map *d3_sts_1;
+	const struct pmc_bit_map *func_dis;
+	const struct pmc_bit_map *func_dis_2;
+	const struct pmc_bit_map *pss;
+};
+
 struct pmc_dev {
 	u32 base_addr;
 	void __iomem *regmap;
+	const struct pmc_reg_map *map;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dbgfs_dir;
 #endif /* CONFIG_DEBUG_FS */
+	bool init;
 };
 
 static struct pmc_dev pmc_device;
 static u32 acpi_base_addr;
 
-struct pmc_bit_map {
-	const char *name;
-	u32 bit_mask;
+static const struct pmc_bit_map d3_sts_0_map[] = {
+	{"LPSS1_F0_DMA",	BIT_LPSS1_F0_DMA},
+	{"LPSS1_F1_PWM1",	BIT_LPSS1_F1_PWM1},
+	{"LPSS1_F2_PWM2",	BIT_LPSS1_F2_PWM2},
+	{"LPSS1_F3_HSUART1",	BIT_LPSS1_F3_HSUART1},
+	{"LPSS1_F4_HSUART2",	BIT_LPSS1_F4_HSUART2},
+	{"LPSS1_F5_SPI",	BIT_LPSS1_F5_SPI},
+	{"LPSS1_F6_Reserved",	BIT_LPSS1_F6_XXX},
+	{"LPSS1_F7_Reserved",	BIT_LPSS1_F7_XXX},
+	{"SCC_EMMC",		BIT_SCC_EMMC},
+	{"SCC_SDIO",		BIT_SCC_SDIO},
+	{"SCC_SDCARD",		BIT_SCC_SDCARD},
+	{"SCC_MIPI",		BIT_SCC_MIPI},
+	{"HDA",			BIT_HDA},
+	{"LPE",			BIT_LPE},
+	{"OTG",			BIT_OTG},
+	{"USH",			BIT_USH},
+	{"GBE",			BIT_GBE},
+	{"SATA",		BIT_SATA},
+	{"USB_EHCI",		BIT_USB_EHCI},
+	{"SEC",			BIT_SEC},
+	{"PCIE_PORT0",		BIT_PCIE_PORT0},
+	{"PCIE_PORT1",		BIT_PCIE_PORT1},
+	{"PCIE_PORT2",		BIT_PCIE_PORT2},
+	{"PCIE_PORT3",		BIT_PCIE_PORT3},
+	{"LPSS2_F0_DMA",	BIT_LPSS2_F0_DMA},
+	{"LPSS2_F1_I2C1",	BIT_LPSS2_F1_I2C1},
+	{"LPSS2_F2_I2C2",	BIT_LPSS2_F2_I2C2},
+	{"LPSS2_F3_I2C3",	BIT_LPSS2_F3_I2C3},
+	{"LPSS2_F3_I2C4",	BIT_LPSS2_F4_I2C4},
+	{"LPSS2_F5_I2C5",	BIT_LPSS2_F5_I2C5},
+	{"LPSS2_F6_I2C6",	BIT_LPSS2_F6_I2C6},
+	{"LPSS2_F7_I2C7",	BIT_LPSS2_F7_I2C7},
+	{},
+};
+
+static struct pmc_bit_map byt_d3_sts_1_map[] = {
+	{"SMB",			BIT_SMB},
+	{"OTG_SS_PHY",		BIT_OTG_SS_PHY},
+	{"USH_SS_PHY",		BIT_USH_SS_PHY},
+	{"DFX",			BIT_DFX},
+	{},
 };
 
-static const struct pmc_bit_map dev_map[] = {
-	{"0  - LPSS1_F0_DMA",		BIT_LPSS1_F0_DMA},
-	{"1  - LPSS1_F1_PWM1",		BIT_LPSS1_F1_PWM1},
-	{"2  - LPSS1_F2_PWM2",		BIT_LPSS1_F2_PWM2},
-	{"3  - LPSS1_F3_HSUART1",	BIT_LPSS1_F3_HSUART1},
-	{"4  - LPSS1_F4_HSUART2",	BIT_LPSS1_F4_HSUART2},
-	{"5  - LPSS1_F5_SPI",		BIT_LPSS1_F5_SPI},
-	{"6  - LPSS1_F6_Reserved",	BIT_LPSS1_F6_XXX},
-	{"7  - LPSS1_F7_Reserved",	BIT_LPSS1_F7_XXX},
-	{"8  - SCC_EMMC",		BIT_SCC_EMMC},
-	{"9  - SCC_SDIO",		BIT_SCC_SDIO},
-	{"10 - SCC_SDCARD",		BIT_SCC_SDCARD},
-	{"11 - SCC_MIPI",		BIT_SCC_MIPI},
-	{"12 - HDA",			BIT_HDA},
-	{"13 - LPE",			BIT_LPE},
-	{"14 - OTG",			BIT_OTG},
-	{"15 - USH",			BIT_USH},
-	{"16 - GBE",			BIT_GBE},
-	{"17 - SATA",			BIT_SATA},
-	{"18 - USB_EHCI",		BIT_USB_EHCI},
-	{"19 - SEC",			BIT_SEC},
-	{"20 - PCIE_PORT0",		BIT_PCIE_PORT0},
-	{"21 - PCIE_PORT1",		BIT_PCIE_PORT1},
-	{"22 - PCIE_PORT2",		BIT_PCIE_PORT2},
-	{"23 - PCIE_PORT3",		BIT_PCIE_PORT3},
-	{"24 - LPSS2_F0_DMA",		BIT_LPSS2_F0_DMA},
-	{"25 - LPSS2_F1_I2C1",		BIT_LPSS2_F1_I2C1},
-	{"26 - LPSS2_F2_I2C2",		BIT_LPSS2_F2_I2C2},
-	{"27 - LPSS2_F3_I2C3",		BIT_LPSS2_F3_I2C3},
-	{"28 - LPSS2_F3_I2C4",		BIT_LPSS2_F4_I2C4},
-	{"29 - LPSS2_F5_I2C5",		BIT_LPSS2_F5_I2C5},
-	{"30 - LPSS2_F6_I2C6",		BIT_LPSS2_F6_I2C6},
-	{"31 - LPSS2_F7_I2C7",		BIT_LPSS2_F7_I2C7},
-	{"32 - SMB",			BIT_SMB},
-	{"33 - OTG_SS_PHY",		BIT_OTG_SS_PHY},
-	{"34 - USH_SS_PHY",		BIT_USH_SS_PHY},
-	{"35 - DFX",			BIT_DFX},
+static struct pmc_bit_map cht_d3_sts_1_map[] = {
+	{"SMB",			BIT_SMB},
+	{"GMM",			BIT_STS_GMM},
+	{"ISH",			BIT_STS_ISH},
+	{},
 };
 
-static const struct pmc_bit_map pss_map[] = {
-	{"0  - GBE",			PMC_PSS_BIT_GBE},
-	{"1  - SATA",			PMC_PSS_BIT_SATA},
-	{"2  - HDA",			PMC_PSS_BIT_HDA},
-	{"3  - SEC",			PMC_PSS_BIT_SEC},
-	{"4  - PCIE",			PMC_PSS_BIT_PCIE},
-	{"5  - LPSS",			PMC_PSS_BIT_LPSS},
-	{"6  - LPE",			PMC_PSS_BIT_LPE},
-	{"7  - DFX",			PMC_PSS_BIT_DFX},
-	{"8  - USH_CTRL",		PMC_PSS_BIT_USH_CTRL},
-	{"9  - USH_SUS",		PMC_PSS_BIT_USH_SUS},
-	{"10 - USH_VCCS",		PMC_PSS_BIT_USH_VCCS},
-	{"11 - USH_VCCA",		PMC_PSS_BIT_USH_VCCA},
-	{"12 - OTG_CTRL",		PMC_PSS_BIT_OTG_CTRL},
-	{"13 - OTG_VCCS",		PMC_PSS_BIT_OTG_VCCS},
-	{"14 - OTG_VCCA_CLK",		PMC_PSS_BIT_OTG_VCCA_CLK},
-	{"15 - OTG_VCCA",		PMC_PSS_BIT_OTG_VCCA},
-	{"16 - USB",			PMC_PSS_BIT_USB},
-	{"17 - USB_SUS",		PMC_PSS_BIT_USB_SUS},
+static struct pmc_bit_map cht_func_dis_2_map[] = {
+	{"SMB",			BIT_SMB},
+	{"GMM",			BIT_FD_GMM},
+	{"ISH",			BIT_FD_ISH},
+	{},
+};
+
+static const struct pmc_bit_map byt_pss_map[] = {
+	{"GBE",			PMC_PSS_BIT_GBE},
+	{"SATA",		PMC_PSS_BIT_SATA},
+	{"HDA",			PMC_PSS_BIT_HDA},
+	{"SEC",			PMC_PSS_BIT_SEC},
+	{"PCIE",		PMC_PSS_BIT_PCIE},
+	{"LPSS",		PMC_PSS_BIT_LPSS},
+	{"LPE",			PMC_PSS_BIT_LPE},
+	{"DFX",			PMC_PSS_BIT_DFX},
+	{"USH_CTRL",		PMC_PSS_BIT_USH_CTRL},
+	{"USH_SUS",		PMC_PSS_BIT_USH_SUS},
+	{"USH_VCCS",		PMC_PSS_BIT_USH_VCCS},
+	{"USH_VCCA",		PMC_PSS_BIT_USH_VCCA},
+	{"OTG_CTRL",		PMC_PSS_BIT_OTG_CTRL},
+	{"OTG_VCCS",		PMC_PSS_BIT_OTG_VCCS},
+	{"OTG_VCCA_CLK",	PMC_PSS_BIT_OTG_VCCA_CLK},
+	{"OTG_VCCA",		PMC_PSS_BIT_OTG_VCCA},
+	{"USB",			PMC_PSS_BIT_USB},
+	{"USB_SUS",		PMC_PSS_BIT_USB_SUS},
+	{},
+};
+
+static const struct pmc_bit_map cht_pss_map[] = {
+	{"SATA",		PMC_PSS_BIT_SATA},
+	{"HDA",			PMC_PSS_BIT_HDA},
+	{"SEC",			PMC_PSS_BIT_SEC},
+	{"PCIE",		PMC_PSS_BIT_PCIE},
+	{"LPSS",		PMC_PSS_BIT_LPSS},
+	{"LPE",			PMC_PSS_BIT_LPE},
+	{"UFS",			PMC_PSS_BIT_CHT_UFS},
+	{"UXD",			PMC_PSS_BIT_CHT_UXD},
+	{"UXD_FD",		PMC_PSS_BIT_CHT_UXD_FD},
+	{"UX_ENG",		PMC_PSS_BIT_CHT_UX_ENG},
+	{"USB_SUS",		PMC_PSS_BIT_CHT_USB_SUS},
+	{"GMM",			PMC_PSS_BIT_CHT_GMM},
+	{"ISH",			PMC_PSS_BIT_CHT_ISH},
+	{"DFX_MASTER",		PMC_PSS_BIT_CHT_DFX_MASTER},
+	{"DFX_CLUSTER1",	PMC_PSS_BIT_CHT_DFX_CLUSTER1},
+	{"DFX_CLUSTER2",	PMC_PSS_BIT_CHT_DFX_CLUSTER2},
+	{"DFX_CLUSTER3",	PMC_PSS_BIT_CHT_DFX_CLUSTER3},
+	{"DFX_CLUSTER4",	PMC_PSS_BIT_CHT_DFX_CLUSTER4},
+	{"DFX_CLUSTER5",	PMC_PSS_BIT_CHT_DFX_CLUSTER5},
+	{},
+};
+
+static const struct pmc_reg_map byt_reg_map = {
+	.d3_sts_0	= d3_sts_0_map,
+	.d3_sts_1	= byt_d3_sts_1_map,
+	.func_dis	= d3_sts_0_map,
+	.func_dis_2	= byt_d3_sts_1_map,
+	.pss		= byt_pss_map,
+};
+
+static const struct pmc_reg_map cht_reg_map = {
+	.d3_sts_0	= d3_sts_0_map,
+	.d3_sts_1	= cht_d3_sts_1_map,
+	.func_dis	= d3_sts_0_map,
+	.func_dis_2	= cht_func_dis_2_map,
+	.pss		= cht_pss_map,
 };
 
 static inline u32 pmc_reg_read(struct pmc_dev *pmc, int reg_offset)
@@ -111,6 +179,30 @@ static inline void pmc_reg_write(struct pmc_dev *pmc, int reg_offset, u32 val)
 	writel(val, pmc->regmap + reg_offset);
 }
 
+int pmc_atom_read(int offset, u32 *value)
+{
+	struct pmc_dev *pmc = &pmc_device;
+
+	if (!pmc->init)
+		return -ENODEV;
+
+	*value = pmc_reg_read(pmc, offset);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pmc_atom_read);
+
+int pmc_atom_write(int offset, u32 value)
+{
+	struct pmc_dev *pmc = &pmc_device;
+
+	if (!pmc->init)
+		return -ENODEV;
+
+	pmc_reg_write(pmc, offset, value);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pmc_atom_write);
+
 static void pmc_power_off(void)
 {
 	u16	pm1_cnt_port;
@@ -142,37 +234,39 @@ static void pmc_hw_reg_setup(struct pmc_dev *pmc)
 }
 
 #ifdef CONFIG_DEBUG_FS
+static void pmc_dev_state_print(struct seq_file *s, int reg_index,
+				u32 sts, const struct pmc_bit_map *sts_map,
+				u32 fd, const struct pmc_bit_map *fd_map)
+{
+	int offset = PMC_REG_BIT_WIDTH * reg_index;
+	int index;
+
+	for (index = 0; sts_map[index].name; index++) {
+		seq_printf(s, "Dev: %-2d - %-32s\tState: %s [%s]\n",
+			offset + index, sts_map[index].name,
+			fd_map[index].bit_mask & fd ?  "Disabled" : "Enabled ",
+			sts_map[index].bit_mask & sts ?  "D3" : "D0");
+	}
+}
+
 static int pmc_dev_state_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmc = s->private;
-	u32 func_dis, func_dis_2, func_dis_index;
-	u32 d3_sts_0, d3_sts_1, d3_sts_index;
-	int dev_num, dev_index, reg_index;
+	const struct pmc_reg_map *m = pmc->map;
+	u32 func_dis, func_dis_2;
+	u32 d3_sts_0, d3_sts_1;
 
 	func_dis = pmc_reg_read(pmc, PMC_FUNC_DIS);
 	func_dis_2 = pmc_reg_read(pmc, PMC_FUNC_DIS_2);
 	d3_sts_0 = pmc_reg_read(pmc, PMC_D3_STS_0);
 	d3_sts_1 = pmc_reg_read(pmc, PMC_D3_STS_1);
 
-	dev_num = ARRAY_SIZE(dev_map);
-
-	for (dev_index = 0; dev_index < dev_num; dev_index++) {
-		reg_index = dev_index / PMC_REG_BIT_WIDTH;
-		if (reg_index) {
-			func_dis_index = func_dis_2;
-			d3_sts_index = d3_sts_1;
-		} else {
-			func_dis_index = func_dis;
-			d3_sts_index = d3_sts_0;
-		}
-
-		seq_printf(s, "Dev: %-32s\tState: %s [%s]\n",
-			dev_map[dev_index].name,
-			dev_map[dev_index].bit_mask & func_dis_index ?
-			"Disabled" : "Enabled ",
-			dev_map[dev_index].bit_mask & d3_sts_index ?
-			"D3" : "D0");
-	}
+	/* Low part */
+	pmc_dev_state_print(s, 0, d3_sts_0, m->d3_sts_0, func_dis, m->func_dis);
+
+	/* High part */
+	pmc_dev_state_print(s, 1, d3_sts_1, m->d3_sts_1, func_dis_2, m->func_dis_2);
+
 	return 0;
 }
 
@@ -191,13 +285,14 @@ static const struct file_operations pmc_dev_state_ops = {
 static int pmc_pss_state_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmc = s->private;
+	const struct pmc_bit_map *map = pmc->map->pss;
 	u32 pss = pmc_reg_read(pmc, PMC_PSS);
-	int pss_index;
+	int index;
 
-	for (pss_index = 0; pss_index < ARRAY_SIZE(pss_map); pss_index++) {
-		seq_printf(s, "Island: %-32s\tState: %s\n",
-			pss_map[pss_index].name,
-			pss_map[pss_index].bit_mask & pss ? "Off" : "On");
+	for (index = 0; map[index].name; index++) {
+		seq_printf(s, "Island: %-2d - %-32s\tState: %s\n",
+			index, map[index].name,
+			map[index].bit_mask & pss ? "Off" : "On");
 	}
 	return 0;
 }
@@ -250,7 +345,7 @@ static void pmc_dbgfs_unregister(struct pmc_dev *pmc)
 	debugfs_remove_recursive(pmc->dbgfs_dir);
 }
 
-static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
+static int pmc_dbgfs_register(struct pmc_dev *pmc)
 {
 	struct dentry *dir, *f;
 
@@ -262,24 +357,18 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
 
 	f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO,
 				dir, pmc, &pmc_dev_state_ops);
-	if (!f) {
-		dev_err(&pdev->dev, "dev_state register failed\n");
+	if (!f)
 		goto err;
-	}
 
 	f = debugfs_create_file("pss_state", S_IFREG | S_IRUGO,
 				dir, pmc, &pmc_pss_state_ops);
-	if (!f) {
-		dev_err(&pdev->dev, "pss_state register failed\n");
+	if (!f)
 		goto err;
-	}
 
 	f = debugfs_create_file("sleep_state", S_IFREG | S_IRUGO,
 				dir, pmc, &pmc_sleep_tmr_ops);
-	if (!f) {
-		dev_err(&pdev->dev, "sleep_state register failed\n");
+	if (!f)
 		goto err;
-	}
 
 	return 0;
 err:
@@ -287,15 +376,16 @@ err:
 	return -ENODEV;
 }
 #else
-static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
+static int pmc_dbgfs_register(struct pmc_dev *pmc)
 {
 	return 0;
 }
 #endif /* CONFIG_DEBUG_FS */
 
-static int pmc_setup_dev(struct pci_dev *pdev)
+static int pmc_setup_dev(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct pmc_dev *pmc = &pmc_device;
+	const struct pmc_reg_map *map = (struct pmc_reg_map *)ent->driver_data;
 	int ret;
 
 	/* Obtain ACPI base address */
@@ -315,32 +405,30 @@ static int pmc_setup_dev(struct pci_dev *pdev)
 		return -ENOMEM;
 	}
 
+	pmc->map = map;
+
 	/* PMC hardware registers setup */
 	pmc_hw_reg_setup(pmc);
 
-	ret = pmc_dbgfs_register(pmc, pdev);
-	if (ret) {
-		iounmap(pmc->regmap);
-	}
+	ret = pmc_dbgfs_register(pmc);
+	if (ret)
+		dev_warn(&pdev->dev, "debugfs register failed\n");
 
+	pmc->init = true;
 	return ret;
 }
 
 /*
  * Data for PCI driver interface
  *
- * This data only exists for exporting the supported
- * PCI ids via MODULE_DEVICE_TABLE.  We do not actually
- * register a pci_driver, because lpc_ich will register
- * a driver on the same PCI id.
+ * used by pci_match_id() call below.
  */
 static const struct pci_device_id pmc_pci_ids[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_VLV_PMC) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_VLV_PMC), (kernel_ulong_t)&byt_reg_map },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_CHT_PMC), (kernel_ulong_t)&cht_reg_map },
 	{ 0, },
 };
 
-MODULE_DEVICE_TABLE(pci, pmc_pci_ids);
-
 static int __init pmc_atom_init(void)
 {
 	struct pci_dev *pdev = NULL;
@@ -357,15 +445,16 @@ static int __init pmc_atom_init(void)
 	for_each_pci_dev(pdev) {
 		ent = pci_match_id(pmc_pci_ids, pdev);
 		if (ent)
-			return pmc_setup_dev(pdev);
+			return pmc_setup_dev(pdev, ent);
 	}
 	/* Device not found. */
 	return -ENODEV;
 }
 
-module_init(pmc_atom_init);
-/* no module_exit, this driver shouldn't be unloaded */
+device_initcall(pmc_atom_init);
 
+/*
 MODULE_AUTHOR("Aubrey Li <aubrey.li@linux.intel.com>");
 MODULE_DESCRIPTION("Intel Atom SOC Power Management Controller Interface");
 MODULE_LICENSE("GPL v2");
+*/
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cfba30f27392..e4308fe6afe8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 
 static int __init arch_parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "old_map"))
 		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 	if (parse_option_str(str, "debug"))
diff --git a/arch/x86/platform/intel/Makefile b/arch/x86/platform/intel/Makefile
new file mode 100644
index 000000000000..b878032fbc82
--- /dev/null
+++ b/arch/x86/platform/intel/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_IOSF_MBI)			+= iosf_mbi.o
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c
index 82f8d02f0df2..edf2c54bf131 100644
--- a/arch/x86/kernel/iosf_mbi.c
+++ b/arch/x86/platform/intel/iosf_mbi.c
@@ -30,7 +30,9 @@
 #define PCI_DEVICE_ID_BAYTRAIL		0x0F00
 #define PCI_DEVICE_ID_BRASWELL		0x2280
 #define PCI_DEVICE_ID_QUARK_X1000	0x0958
+#define PCI_DEVICE_ID_TANGIER		0x1170
 
+static struct pci_dev *mbi_pdev;
 static DEFINE_SPINLOCK(iosf_mbi_lock);
 
 static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset)
@@ -38,8 +40,6 @@ static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset)
 	return (op << 24) | (port << 16) | (offset << 8) | MBI_ENABLE;
 }
 
-static struct pci_dev *mbi_pdev;	/* one mbi device */
-
 static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr)
 {
 	int result;
@@ -104,7 +104,7 @@ int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
 	unsigned long flags;
 	int ret;
 
-	/*Access to the GFX unit is handled by GPU code */
+	/* Access to the GFX unit is handled by GPU code */
 	if (port == BT_MBI_UNIT_GFX) {
 		WARN_ON(1);
 		return -EPERM;
@@ -127,7 +127,7 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr)
 	unsigned long flags;
 	int ret;
 
-	/*Access to the GFX unit is handled by GPU code */
+	/* Access to the GFX unit is handled by GPU code */
 	if (port == BT_MBI_UNIT_GFX) {
 		WARN_ON(1);
 		return -EPERM;
@@ -151,7 +151,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
 	unsigned long flags;
 	int ret;
 
-	/*Access to the GFX unit is handled by GPU code */
+	/* Access to the GFX unit is handled by GPU code */
 	if (port == BT_MBI_UNIT_GFX) {
 		WARN_ON(1);
 		return -EPERM;
@@ -240,17 +240,17 @@ static void iosf_sideband_debug_init(void)
 
 	/* mdr */
 	d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr);
-	if (IS_ERR_OR_NULL(d))
+	if (!d)
 		goto cleanup;
 
 	/* mcrx */
-	debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx);
-	if (IS_ERR_OR_NULL(d))
+	d = debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx);
+	if (!d)
 		goto cleanup;
 
 	/* mcr - initiates mailbox tranaction */
-	debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops);
-	if (IS_ERR_OR_NULL(d))
+	d = debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops);
+	if (!d)
 		goto cleanup;
 
 	return;
@@ -292,6 +292,7 @@ static const struct pci_device_id iosf_mbi_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_TANGIER) },
 	{ 0, },
 };
 MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids);
@@ -314,10 +315,8 @@ static void __exit iosf_mbi_exit(void)
 	iosf_debugfs_remove();
 
 	pci_unregister_driver(&iosf_mbi_pci_driver);
-	if (mbi_pdev) {
-		pci_dev_put(mbi_pdev);
-		mbi_pdev = NULL;
-	}
+	pci_dev_put(mbi_pdev);
+	mbi_pdev = NULL;
 }
 
 module_init(iosf_mbi_init);
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 8570abe68be1..e1c24631afbb 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -89,7 +89,7 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
 		return -EINVAL;
 
 	chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
-				 irq_data->node);
+				 irq_data_get_node(irq_data));
 	if (!chip_data)
 		return -ENOMEM;
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index a244237f3cfa..2b158a9fa1d7 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -32,8 +32,7 @@
 
 static cycle_t uv_read_rtc(struct clocksource *cs);
 static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
-static void uv_rtc_timer_setup(enum clock_event_mode,
-				struct clock_event_device *);
+static int uv_rtc_shutdown(struct clock_event_device *evt);
 
 static struct clocksource clocksource_uv = {
 	.name		= RTC_NAME,
@@ -44,14 +43,14 @@ static struct clocksource clocksource_uv = {
 };
 
 static struct clock_event_device clock_event_device_uv = {
-	.name		= RTC_NAME,
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.shift		= 20,
-	.rating		= 400,
-	.irq		= -1,
-	.set_next_event	= uv_rtc_next_event,
-	.set_mode	= uv_rtc_timer_setup,
-	.event_handler	= NULL,
+	.name			= RTC_NAME,
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.shift			= 20,
+	.rating			= 400,
+	.irq			= -1,
+	.set_next_event		= uv_rtc_next_event,
+	.set_state_shutdown	= uv_rtc_shutdown,
+	.event_handler		= NULL,
 };
 
 static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
@@ -321,24 +320,14 @@ static int uv_rtc_next_event(unsigned long delta,
 }
 
 /*
- * Setup the RTC timer in oneshot mode
+ * Shutdown the RTC timer
  */
-static void uv_rtc_timer_setup(enum clock_event_mode mode,
-			       struct clock_event_device *evt)
+static int uv_rtc_shutdown(struct clock_event_device *evt)
 {
 	int ced_cpu = cpumask_first(evt->cpumask);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here yet */
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		uv_rtc_unset_timer(ced_cpu, 1);
-		break;
-	}
+	uv_rtc_unset_timer(ced_cpu, 1);
+	return 0;
 }
 
 static void uv_rtc_interrupt(void)
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0d7dd1f5ac36..9ab52791fed5 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -22,6 +22,7 @@
 #include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
+#include <asm/mmu_context.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@ static void fix_processor_context(void)
 	syscall_init();				/* This sets MSR_*STAR and related */
 #endif
 	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
+	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
 }
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
new file mode 100644
index 000000000000..10fea5fc821e
--- /dev/null
+++ b/arch/x86/ras/Kconfig
@@ -0,0 +1,11 @@
+config AMD_MCE_INJ
+	tristate "Simple MCE injection interface for AMD processors"
+	depends on RAS && EDAC_DECODE_MCE && DEBUG_FS
+	default n
+	help
+	  This is a simple debugfs interface to inject MCEs and test different
+	  aspects of the MCE handling code.
+
+	  WARNING: Do not even assume this interface is staying stable!
+
+
diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile
new file mode 100644
index 000000000000..dd2c98b84037
--- /dev/null
+++ b/arch/x86/ras/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_AMD_MCE_INJ)		+= mce_amd_inj.o
+
diff --git a/drivers/edac/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 4c73e4d03d46..17e35b5bf779 100644
--- a/drivers/edac/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -6,7 +6,7 @@
  * This file may be distributed under the terms of the GNU General Public
  * License version 2.
  *
- * Copyright (c) 2010-14:  Borislav Petkov <bp@alien8.de>
+ * Copyright (c) 2010-15:  Borislav Petkov <bp@alien8.de>
  *			Advanced Micro Devices Inc.
  */
 
@@ -19,7 +19,7 @@
 #include <linux/uaccess.h>
 #include <asm/mce.h>
 
-#include "mce_amd.h"
+#include "../kernel/cpu/mcheck/mce-internal.h"
 
 /*
  * Collect all the MCi_XXX settings
@@ -195,7 +195,7 @@ static void do_inject(void)
 		i_mce.status |= MCI_STATUS_MISCV;
 
 	if (inj_type == SW_INJ) {
-		amd_decode_mce(NULL, 0, &i_mce);
+		mce_inject_log(&i_mce);
 		return;
 	}
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index b9531d343134..755481f14d90 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -45,17 +45,4 @@
 #define read_barrier_depends()		do { } while (0)
 #define smp_read_barrier_depends()	do { } while (0)
 
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
-	alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
-			  "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
 #endif
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index e88fda867a33..c7b15f3e2cf3 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -7,8 +7,9 @@ config XEN
 	depends on PARAVIRT
 	select PARAVIRT_CLOCK
 	select XEN_HAVE_PVMMU
+	select XEN_HAVE_VPMU
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_TSC
+	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the
@@ -17,20 +18,24 @@ config XEN
 config XEN_DOM0
 	def_bool y
 	depends on XEN && PCI_XEN && SWIOTLB_XEN
-	depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI
+	depends on X86_IO_APIC && ACPI && PCI
 
 config XEN_PVHVM
 	def_bool y
 	depends on XEN && PCI && X86_LOCAL_APIC
 
-config XEN_MAX_DOMAIN_MEMORY
-       int
-       default 500 if X86_64
-       default 64 if X86_32
-       depends on XEN
-       help
-         This only affects the sizing of some bss arrays, the unused
-         portions of which are freed.
+config XEN_512GB
+	bool "Limit Xen pv-domain memory to 512GB"
+	depends on XEN && X86_64
+	default y
+	help
+	  Limit paravirtualized user domains to 512GB of RAM.
+
+	  The Xen tools and crash dump analysis tools might not support
+	  pv-domains with more than 512 GB of RAM. This option controls the
+	  default setting of the kernel to use only up to 512 GB or more.
+	  It is always possible to change the default via specifying the
+	  boot parameter "xen_512gb_limit".
 
 config XEN_SAVE_RESTORE
        bool
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 7322755f337a..e47e52787d32 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,13 +13,13 @@ CFLAGS_mmu.o			:= $(nostackp)
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o
+			p2m.o apic.o pmu.o
 
 obj-$(CONFIG_EVENT_TRACING) += trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-obj-$(CONFIG_XEN_DOM0)		+= apic.o vga.o
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 70e060ad879a..acda713ab5be 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -7,6 +7,7 @@
 #include <xen/xen.h>
 #include <xen/interface/physdev.h>
 #include "xen-ops.h"
+#include "pmu.h"
 #include "smp.h"
 
 static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
@@ -72,6 +73,11 @@ static u32 xen_apic_read(u32 reg)
 
 static void xen_apic_write(u32 reg, u32 val)
 {
+	if (reg == APIC_LVTPC) {
+		(void)pmu_apic_update(reg);
+		return;
+	}
+
 	/* Warn to see if there's any stray references */
 	WARN(1,"register: %x, value: %x\n", reg, val);
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b95c9b8283f..30d12afe52ed 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -84,6 +84,7 @@
 #include "mmu.h"
 #include "smp.h"
 #include "multicalls.h"
+#include "pmu.h"
 
 EXPORT_SYMBOL_GPL(hypercall_page);
 
@@ -483,6 +484,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
+	unsigned char dummy;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
@@ -492,6 +494,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	pte = pfn_pte(pfn, prot);
 
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	pagefault_disable();	/* Avoid warnings due to being atomic. */
+	__get_user(dummy, (unsigned char __user __force *)v);
+	pagefault_enable();
+
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
@@ -503,6 +531,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 				BUG();
 	} else
 		kmap_flush_unused();
+
+	preempt_enable();
 }
 
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +540,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
@@ -970,8 +1011,7 @@ static void xen_write_cr0(unsigned long cr0)
 
 static void xen_write_cr4(unsigned long cr4)
 {
-	cr4 &= ~X86_CR4_PGE;
-	cr4 &= ~X86_CR4_PSE;
+	cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE);
 
 	native_write_cr4(cr4);
 }
@@ -990,6 +1030,9 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 {
 	u64 val;
 
+	if (pmu_msr_read(msr, &val, err))
+		return val;
+
 	val = native_read_msr_safe(msr, err);
 	switch (msr) {
 	case MSR_IA32_APICBASE:
@@ -1036,7 +1079,8 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		   Xen console noise. */
 
 	default:
-		ret = native_write_msr_safe(msr, low, high);
+		if (!pmu_msr_write(msr, low, high, &ret))
+			ret = native_write_msr_safe(msr, low, high);
 	}
 
 	return ret;
@@ -1175,10 +1219,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_msr = xen_read_msr_safe,
 	.write_msr = xen_write_msr_safe,
 
-	.read_tsc = native_read_tsc,
-	.read_pmc = native_read_pmc,
-
-	.read_tscp = native_read_tscp,
+	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
 #ifdef CONFIG_X86_64
@@ -1227,6 +1268,10 @@ static const struct pv_apic_ops xen_apic_ops __initconst = {
 static void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		xen_pmu_finish(cpu);
 
 	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
 		BUG();
@@ -1570,7 +1615,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	early_boot_irqs_disabled = true;
 
 	xen_raw_console_write("mapping kernel into physical memory\n");
-	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
+	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
+				   xen_start_info->nr_pages);
+	xen_reserve_special_pages();
 
 	/*
 	 * Modify the cache mode translation tables to match Xen's PAT
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index dd151b2045b0..2c50b445884e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -116,6 +116,7 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
 DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
 DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 
+static phys_addr_t xen_pt_base, xen_pt_size __initdata;
 
 /*
  * Just beyond the highest usermode address.  STACK_TOP_MAX has a
@@ -1093,6 +1094,16 @@ static void xen_exit_mmap(struct mm_struct *mm)
 
 static void xen_post_allocator_init(void);
 
+static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct mmuext_op op;
+
+	op.cmd = cmd;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+		BUG();
+}
+
 #ifdef CONFIG_X86_64
 static void __init xen_cleanhighmap(unsigned long vaddr,
 				    unsigned long vaddr_end)
@@ -1114,6 +1125,83 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
 	xen_mc_flush();
 }
 
+/*
+ * Make a page range writeable and free it.
+ */
+static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size)
+{
+	void *vaddr = __va(paddr);
+	void *vaddr_end = vaddr + size;
+
+	for (; vaddr < vaddr_end; vaddr += PAGE_SIZE)
+		make_lowmem_page_readwrite(vaddr);
+
+	memblock_free(paddr, size);
+}
+
+static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
+{
+	unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK;
+
+	if (unpin)
+		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa));
+	ClearPagePinned(virt_to_page(__va(pa)));
+	xen_free_ro_pages(pa, PAGE_SIZE);
+}
+
+/*
+ * Since it is well isolated we can (and since it is perhaps large we should)
+ * also free the page tables mapping the initial P->M table.
+ */
+static void __init xen_cleanmfnmap(unsigned long vaddr)
+{
+	unsigned long va = vaddr & PMD_MASK;
+	unsigned long pa;
+	pgd_t *pgd = pgd_offset_k(va);
+	pud_t *pud_page = pud_offset(pgd, 0);
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned int i;
+	bool unpin;
+
+	unpin = (vaddr == 2 * PGDIR_SIZE);
+	set_pgd(pgd, __pgd(0));
+	do {
+		pud = pud_page + pud_index(va);
+		if (pud_none(*pud)) {
+			va += PUD_SIZE;
+		} else if (pud_large(*pud)) {
+			pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
+			xen_free_ro_pages(pa, PUD_SIZE);
+			va += PUD_SIZE;
+		} else {
+			pmd = pmd_offset(pud, va);
+			if (pmd_large(*pmd)) {
+				pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
+				xen_free_ro_pages(pa, PMD_SIZE);
+			} else if (!pmd_none(*pmd)) {
+				pte = pte_offset_kernel(pmd, va);
+				set_pmd(pmd, __pmd(0));
+				for (i = 0; i < PTRS_PER_PTE; ++i) {
+					if (pte_none(pte[i]))
+						break;
+					pa = pte_pfn(pte[i]) << PAGE_SHIFT;
+					xen_free_ro_pages(pa, PAGE_SIZE);
+				}
+				xen_cleanmfnmap_free_pgtbl(pte, unpin);
+			}
+			va += PMD_SIZE;
+			if (pmd_index(va))
+				continue;
+			set_pud(pud, __pud(0));
+			xen_cleanmfnmap_free_pgtbl(pmd, unpin);
+		}
+
+	} while (pud_index(va) || pmd_index(va));
+	xen_cleanmfnmap_free_pgtbl(pud_page, unpin);
+}
+
 static void __init xen_pagetable_p2m_free(void)
 {
 	unsigned long size;
@@ -1128,18 +1216,31 @@ static void __init xen_pagetable_p2m_free(void)
 	/* using __ka address and sticking INVALID_P2M_ENTRY! */
 	memset((void *)xen_start_info->mfn_list, 0xff, size);
 
-	/* We should be in __ka space. */
-	BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map);
 	addr = xen_start_info->mfn_list;
-	/* We roundup to the PMD, which means that if anybody at this stage is
-	 * using the __ka address of xen_start_info or xen_start_info->shared_info
-	 * they are in going to crash. Fortunatly we have already revectored
-	 * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */
+	/*
+	 * We could be in __ka space.
+	 * We roundup to the PMD, which means that if anybody at this stage is
+	 * using the __ka address of xen_start_info or
+	 * xen_start_info->shared_info they are in going to crash. Fortunatly
+	 * we have already revectored in xen_setup_kernel_pagetable and in
+	 * xen_setup_shared_info.
+	 */
 	size = roundup(size, PMD_SIZE);
-	xen_cleanhighmap(addr, addr + size);
 
-	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
-	memblock_free(__pa(xen_start_info->mfn_list), size);
+	if (addr >= __START_KERNEL_map) {
+		xen_cleanhighmap(addr, addr + size);
+		size = PAGE_ALIGN(xen_start_info->nr_pages *
+				  sizeof(unsigned long));
+		memblock_free(__pa(addr), size);
+	} else {
+		xen_cleanmfnmap(addr);
+	}
+}
+
+static void __init xen_pagetable_cleanhighmap(void)
+{
+	unsigned long size;
+	unsigned long addr;
 
 	/* At this stage, cleanup_highmap has already cleaned __ka space
 	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
@@ -1172,6 +1273,8 @@ static void __init xen_pagetable_p2m_setup(void)
 
 #ifdef CONFIG_X86_64
 	xen_pagetable_p2m_free();
+
+	xen_pagetable_cleanhighmap();
 #endif
 	/* And revector! Bye bye old array */
 	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
@@ -1461,6 +1564,24 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 #else /* CONFIG_X86_64 */
 static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 {
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_writable_page_tables) ||
+	    xen_feature(XENFEAT_auto_translated_physmap) ||
+	    xen_start_info->mfn_list >= __START_KERNEL_map)
+		return pte;
+
+	/*
+	 * Pages belonging to the initial p2m list mapped outside the default
+	 * address range must be mapped read-only. This region contains the
+	 * page tables for mapping the p2m list, too, and page tables MUST be
+	 * mapped read-only.
+	 */
+	pfn = pte_pfn(pte);
+	if (pfn >= xen_start_info->first_p2m_pfn &&
+	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+		pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
+
 	return pte;
 }
 #endif /* CONFIG_X86_64 */
@@ -1489,15 +1610,6 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 	native_set_pte(ptep, pte);
 }
 
-static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
-{
-	struct mmuext_op op;
-	op.cmd = cmd;
-	op.arg1.mfn = pfn_to_mfn(pfn);
-	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
-		BUG();
-}
-
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
 static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
@@ -1815,7 +1927,10 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	 * mappings. Considering that on Xen after the kernel mappings we
 	 * have the mappings of some pages that don't exist in pfn space, we
 	 * set max_pfn_mapped to the last real pfn mapped. */
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+	if (xen_start_info->mfn_list < __START_KERNEL_map)
+		max_pfn_mapped = xen_start_info->first_p2m_pfn;
+	else
+		max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
 
 	pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
 	pt_end = pt_base + xen_start_info->nr_pt_frames;
@@ -1855,6 +1970,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
+	/* Copy the initial P->M table mappings if necessary. */
+	i = pgd_index(xen_start_info->mfn_list);
+	if (i && i < pgd_index(__START_KERNEL_map))
+		init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
+
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/* Make pagetable pieces RO */
 		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
@@ -1894,10 +2014,192 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		check_pt_base(&pt_base, &pt_end, addr[i]);
 
 	/* Our (by three pages) smaller Xen pagetable that we are using */
-	memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
+	xen_pt_base = PFN_PHYS(pt_base);
+	xen_pt_size = (pt_end - pt_base) * PAGE_SIZE;
+	memblock_reserve(xen_pt_base, xen_pt_size);
+
 	/* Revector the xen_start_info */
 	xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
 }
+
+/*
+ * Read a value from a physical address.
+ */
+static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
+{
+	unsigned long *vaddr;
+	unsigned long val;
+
+	vaddr = early_memremap_ro(addr, sizeof(val));
+	val = *vaddr;
+	early_memunmap(vaddr, sizeof(val));
+	return val;
+}
+
+/*
+ * Translate a virtual address to a physical one without relying on mapped
+ * page tables.
+ */
+static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
+{
+	phys_addr_t pa;
+	pgd_t pgd;
+	pud_t pud;
+	pmd_t pmd;
+	pte_t pte;
+
+	pa = read_cr3();
+	pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) *
+						       sizeof(pgd)));
+	if (!pgd_present(pgd))
+		return 0;
+
+	pa = pgd_val(pgd) & PTE_PFN_MASK;
+	pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) *
+						       sizeof(pud)));
+	if (!pud_present(pud))
+		return 0;
+	pa = pud_pfn(pud) << PAGE_SHIFT;
+	if (pud_large(pud))
+		return pa + (vaddr & ~PUD_MASK);
+
+	pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) *
+						       sizeof(pmd)));
+	if (!pmd_present(pmd))
+		return 0;
+	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	if (pmd_large(pmd))
+		return pa + (vaddr & ~PMD_MASK);
+
+	pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) *
+						       sizeof(pte)));
+	if (!pte_present(pte))
+		return 0;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+
+	return pa | (vaddr & ~PAGE_MASK);
+}
+
+/*
+ * Find a new area for the hypervisor supplied p2m list and relocate the p2m to
+ * this area.
+ */
+void __init xen_relocate_p2m(void)
+{
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys;
+	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
+	int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
+	pte_t *pt;
+	pmd_t *pmd;
+	pud_t *pud;
+	pgd_t *pgd;
+	unsigned long *new_p2m;
+
+	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
+	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
+	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
+	n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
+	n_frames = n_pte + n_pt + n_pmd + n_pud;
+
+	new_area = xen_find_free_area(PFN_PHYS(n_frames));
+	if (!new_area) {
+		xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n");
+		BUG();
+	}
+
+	/*
+	 * Setup the page tables for addressing the new p2m list.
+	 * We have asked the hypervisor to map the p2m list at the user address
+	 * PUD_SIZE. It may have done so, or it may have used a kernel space
+	 * address depending on the Xen version.
+	 * To avoid any possible virtual address collision, just use
+	 * 2 * PUD_SIZE for the new area.
+	 */
+	pud_phys = new_area;
+	pmd_phys = pud_phys + PFN_PHYS(n_pud);
+	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
+	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
+
+	pgd = __va(read_cr3());
+	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
+	for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
+		pud = early_memremap(pud_phys, PAGE_SIZE);
+		clear_page(pud);
+		for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
+		     idx_pmd++) {
+			pmd = early_memremap(pmd_phys, PAGE_SIZE);
+			clear_page(pmd);
+			for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
+			     idx_pt++) {
+				pt = early_memremap(pt_phys, PAGE_SIZE);
+				clear_page(pt);
+				for (idx_pte = 0;
+				     idx_pte < min(n_pte, PTRS_PER_PTE);
+				     idx_pte++) {
+					set_pte(pt + idx_pte,
+						pfn_pte(p2m_pfn, PAGE_KERNEL));
+					p2m_pfn++;
+				}
+				n_pte -= PTRS_PER_PTE;
+				early_memunmap(pt, PAGE_SIZE);
+				make_lowmem_page_readonly(__va(pt_phys));
+				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
+						  PFN_DOWN(pt_phys));
+				set_pmd(pmd + idx_pt,
+					__pmd(_PAGE_TABLE | pt_phys));
+				pt_phys += PAGE_SIZE;
+			}
+			n_pt -= PTRS_PER_PMD;
+			early_memunmap(pmd, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(pmd_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
+					  PFN_DOWN(pmd_phys));
+			set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+			pmd_phys += PAGE_SIZE;
+		}
+		n_pmd -= PTRS_PER_PUD;
+		early_memunmap(pud, PAGE_SIZE);
+		make_lowmem_page_readonly(__va(pud_phys));
+		pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+		set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
+		pud_phys += PAGE_SIZE;
+	}
+
+	/* Now copy the old p2m info to the new area. */
+	memcpy(new_p2m, xen_p2m_addr, size);
+	xen_p2m_addr = new_p2m;
+
+	/* Release the old p2m list and set new list info. */
+	p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list));
+	BUG_ON(!p2m_pfn);
+	p2m_pfn_end = p2m_pfn + PFN_DOWN(size);
+
+	if (xen_start_info->mfn_list < __START_KERNEL_map) {
+		pfn = xen_start_info->first_p2m_pfn;
+		pfn_end = xen_start_info->first_p2m_pfn +
+			  xen_start_info->nr_p2m_frames;
+		set_pgd(pgd + 1, __pgd(0));
+	} else {
+		pfn = p2m_pfn;
+		pfn_end = p2m_pfn_end;
+	}
+
+	memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
+	while (pfn < pfn_end) {
+		if (pfn == p2m_pfn) {
+			pfn = p2m_pfn_end;
+			continue;
+		}
+		make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+		pfn++;
+	}
+
+	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+	xen_start_info->first_p2m_pfn =  PFN_DOWN(new_area);
+	xen_start_info->nr_p2m_frames = n_frames;
+}
+
 #else	/* !CONFIG_X86_64 */
 static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
 static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
@@ -1938,18 +2240,41 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 
+/*
+ * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
+ * not the first page table in the page table pool.
+ * Iterate through the initial page tables to find the real page table base.
+ */
+static phys_addr_t xen_find_pt_base(pmd_t *pmd)
+{
+	phys_addr_t pt_base, paddr;
+	unsigned pmdidx;
+
+	pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
+
+	for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
+		if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
+			paddr = m2p(pmd[pmdidx].pmd);
+			pt_base = min(pt_base, paddr);
+		}
+
+	return pt_base;
+}
+
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 
+	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+
+	xen_pt_base = xen_find_pt_base(kernel_pmd);
+	xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
+
 	initial_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
-				  xen_start_info->nr_pt_frames * PAGE_SIZE +
-				  512*1024);
+	max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
 
-	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	copy_page(initial_kernel_pmd, kernel_pmd);
 
 	xen_map_identity_early(initial_kernel_pmd, max_pfn);
@@ -1968,11 +2293,33 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 			  PFN_DOWN(__pa(initial_page_table)));
 	xen_write_cr3(__pa(initial_page_table));
 
-	memblock_reserve(__pa(xen_start_info->pt_base),
-			 xen_start_info->nr_pt_frames * PAGE_SIZE);
+	memblock_reserve(xen_pt_base, xen_pt_size);
 }
 #endif	/* CONFIG_X86_64 */
 
+void __init xen_reserve_special_pages(void)
+{
+	phys_addr_t paddr;
+
+	memblock_reserve(__pa(xen_start_info), PAGE_SIZE);
+	if (xen_start_info->store_mfn) {
+		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->store_mfn));
+		memblock_reserve(paddr, PAGE_SIZE);
+	}
+	if (!xen_initial_domain()) {
+		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->console.domU.mfn));
+		memblock_reserve(paddr, PAGE_SIZE);
+	}
+}
+
+void __init xen_pt_check_e820(void)
+{
+	if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) {
+		xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n");
+		BUG();
+	}
+}
+
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
 
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b7f18e200aa..bfc08b13044b 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -79,10 +79,14 @@
 #include <xen/balloon.h>
 #include <xen/grant_table.h>
 
-#include "p2m.h"
 #include "multicalls.h"
 #include "xen-ops.h"
 
+#define P2M_MID_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long *))
+#define P2M_TOP_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long **))
+
+#define MAX_P2M_PFN	(P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
+
 #define PMDS_PER_MID_PAGE	(P2M_MID_PER_PAGE / PTRS_PER_PTE)
 
 unsigned long *xen_p2m_addr __read_mostly;
@@ -199,7 +203,8 @@ void __ref xen_build_mfn_list_list(void)
 	unsigned int level, topidx, mididx;
 	unsigned long *mid_mfn_p;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
+	if (xen_feature(XENFEAT_auto_translated_physmap) ||
+	    xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
 		return;
 
 	/* Pre-initialize p2m_top_mfn to be completely missing */
@@ -260,9 +265,16 @@ void xen_setup_mfn_list_list(void)
 
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
-	HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
-		virt_to_mfn(p2m_top_mfn);
+	if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
+		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = ~0UL;
+	else
+		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
+			virt_to_mfn(p2m_top_mfn);
 	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
+	HYPERVISOR_shared_info->arch.p2m_generation = 0;
+	HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr;
+	HYPERVISOR_shared_info->arch.p2m_cr3 =
+		xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
 }
 
 /* Set up p2m_top to point to the domain-builder provided p2m pages */
@@ -478,8 +490,12 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
 
 		ptechk = lookup_address(vaddr, &level);
 		if (ptechk == pte_pg) {
+			HYPERVISOR_shared_info->arch.p2m_generation++;
+			wmb(); /* Tools are synchronizing via p2m_generation. */
 			set_pmd(pmdp,
 				__pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE));
+			wmb(); /* Tools are synchronizing via p2m_generation. */
+			HYPERVISOR_shared_info->arch.p2m_generation++;
 			pte_newpg[i] = NULL;
 		}
 
@@ -505,7 +521,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
  */
 static bool alloc_p2m(unsigned long pfn)
 {
-	unsigned topidx, mididx;
+	unsigned topidx;
 	unsigned long *top_mfn_p, *mid_mfn;
 	pte_t *ptep, *pte_pg;
 	unsigned int level;
@@ -513,9 +529,6 @@ static bool alloc_p2m(unsigned long pfn)
 	unsigned long addr = (unsigned long)(xen_p2m_addr + pfn);
 	unsigned long p2m_pfn;
 
-	topidx = p2m_top_index(pfn);
-	mididx = p2m_mid_index(pfn);
-
 	ptep = lookup_address(addr, &level);
 	BUG_ON(!ptep || level != PG_LEVEL_4K);
 	pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
@@ -527,7 +540,8 @@ static bool alloc_p2m(unsigned long pfn)
 			return false;
 	}
 
-	if (p2m_top_mfn) {
+	if (p2m_top_mfn && pfn < MAX_P2M_PFN) {
+		topidx = p2m_top_index(pfn);
 		top_mfn_p = &p2m_top_mfn[topidx];
 		mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]);
 
@@ -577,10 +591,14 @@ static bool alloc_p2m(unsigned long pfn)
 		spin_lock_irqsave(&p2m_update_lock, flags);
 
 		if (pte_pfn(*ptep) == p2m_pfn) {
+			HYPERVISOR_shared_info->arch.p2m_generation++;
+			wmb(); /* Tools are synchronizing via p2m_generation. */
 			set_pte(ptep,
 				pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL));
+			wmb(); /* Tools are synchronizing via p2m_generation. */
+			HYPERVISOR_shared_info->arch.p2m_generation++;
 			if (mid_mfn)
-				mid_mfn[mididx] = virt_to_mfn(p2m);
+				mid_mfn[p2m_mid_index(pfn)] = virt_to_mfn(p2m);
 			p2m = NULL;
 		}
 
@@ -630,6 +648,11 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 		return true;
 	}
 
+	/*
+	 * The interface requires atomic updates on p2m elements.
+	 * xen_safe_write_ulong() is using __put_user which does an atomic
+	 * store via asm().
+	 */
 	if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn)))
 		return true;
 
diff --git a/arch/x86/xen/p2m.h b/arch/x86/xen/p2m.h
deleted file mode 100644
index ad8aee24ab72..000000000000
--- a/arch/x86/xen/p2m.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _XEN_P2M_H
-#define _XEN_P2M_H
-
-#define P2M_PER_PAGE        (PAGE_SIZE / sizeof(unsigned long))
-#define P2M_MID_PER_PAGE    (PAGE_SIZE / sizeof(unsigned long *))
-#define P2M_TOP_PER_PAGE    (PAGE_SIZE / sizeof(unsigned long **))
-
-#define MAX_P2M_PFN         (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
-
-#define MAX_REMAP_RANGES    10
-
-extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
-                                      unsigned long pfn_e);
-
-#endif  /* _XEN_P2M_H */
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index a8261716d58d..9586ff32810c 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -68,7 +68,7 @@ static int check_platform_magic(void)
 	return 0;
 }
 
-bool xen_has_pv_devices()
+bool xen_has_pv_devices(void)
 {
 	if (!xen_domain())
 		return false;
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
new file mode 100644
index 000000000000..724a08740a04
--- /dev/null
+++ b/arch/x86/xen/pmu.c
@@ -0,0 +1,570 @@
+#include <linux/types.h>
+#include <linux/interrupt.h>
+
+#include <asm/xen/hypercall.h>
+#include <xen/page.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/vcpu.h>
+#include <xen/interface/xenpmu.h>
+
+#include "xen-ops.h"
+#include "pmu.h"
+
+/* x86_pmu.handle_irq definition */
+#include "../kernel/cpu/perf_event.h"
+
+#define XENPMU_IRQ_PROCESSING    1
+struct xenpmu {
+	/* Shared page between hypervisor and domain */
+	struct xen_pmu_data *xenpmu_data;
+
+	uint8_t flags;
+};
+static DEFINE_PER_CPU(struct xenpmu, xenpmu_shared);
+#define get_xenpmu_data()    (this_cpu_ptr(&xenpmu_shared)->xenpmu_data)
+#define get_xenpmu_flags()   (this_cpu_ptr(&xenpmu_shared)->flags)
+
+/* Macro for computing address of a PMU MSR bank */
+#define field_offset(ctxt, field) ((void *)((uintptr_t)ctxt + \
+					    (uintptr_t)ctxt->field))
+
+/* AMD PMU */
+#define F15H_NUM_COUNTERS   6
+#define F10H_NUM_COUNTERS   4
+
+static __read_mostly uint32_t amd_counters_base;
+static __read_mostly uint32_t amd_ctrls_base;
+static __read_mostly int amd_msr_step;
+static __read_mostly int k7_counters_mirrored;
+static __read_mostly int amd_num_counters;
+
+/* Intel PMU */
+#define MSR_TYPE_COUNTER            0
+#define MSR_TYPE_CTRL               1
+#define MSR_TYPE_GLOBAL             2
+#define MSR_TYPE_ARCH_COUNTER       3
+#define MSR_TYPE_ARCH_CTRL          4
+
+/* Number of general pmu registers (CPUID.EAX[0xa].EAX[8..15]) */
+#define PMU_GENERAL_NR_SHIFT        8
+#define PMU_GENERAL_NR_BITS         8
+#define PMU_GENERAL_NR_MASK         (((1 << PMU_GENERAL_NR_BITS) - 1) \
+				     << PMU_GENERAL_NR_SHIFT)
+
+/* Number of fixed pmu registers (CPUID.EDX[0xa].EDX[0..4]) */
+#define PMU_FIXED_NR_SHIFT          0
+#define PMU_FIXED_NR_BITS           5
+#define PMU_FIXED_NR_MASK           (((1 << PMU_FIXED_NR_BITS) - 1) \
+				     << PMU_FIXED_NR_SHIFT)
+
+/* Alias registers (0x4c1) for full-width writes to PMCs */
+#define MSR_PMC_ALIAS_MASK          (~(MSR_IA32_PERFCTR0 ^ MSR_IA32_PMC0))
+
+#define INTEL_PMC_TYPE_SHIFT        30
+
+static __read_mostly int intel_num_arch_counters, intel_num_fixed_counters;
+
+
+static void xen_pmu_arch_init(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+
+		switch (boot_cpu_data.x86) {
+		case 0x15:
+			amd_num_counters = F15H_NUM_COUNTERS;
+			amd_counters_base = MSR_F15H_PERF_CTR;
+			amd_ctrls_base = MSR_F15H_PERF_CTL;
+			amd_msr_step = 2;
+			k7_counters_mirrored = 1;
+			break;
+		case 0x10:
+		case 0x12:
+		case 0x14:
+		case 0x16:
+		default:
+			amd_num_counters = F10H_NUM_COUNTERS;
+			amd_counters_base = MSR_K7_PERFCTR0;
+			amd_ctrls_base = MSR_K7_EVNTSEL0;
+			amd_msr_step = 1;
+			k7_counters_mirrored = 0;
+			break;
+		}
+	} else {
+		uint32_t eax, ebx, ecx, edx;
+
+		cpuid(0xa, &eax, &ebx, &ecx, &edx);
+
+		intel_num_arch_counters = (eax & PMU_GENERAL_NR_MASK) >>
+			PMU_GENERAL_NR_SHIFT;
+		intel_num_fixed_counters = (edx & PMU_FIXED_NR_MASK) >>
+			PMU_FIXED_NR_SHIFT;
+	}
+}
+
+static inline uint32_t get_fam15h_addr(u32 addr)
+{
+	switch (addr) {
+	case MSR_K7_PERFCTR0:
+	case MSR_K7_PERFCTR1:
+	case MSR_K7_PERFCTR2:
+	case MSR_K7_PERFCTR3:
+		return MSR_F15H_PERF_CTR + (addr - MSR_K7_PERFCTR0);
+	case MSR_K7_EVNTSEL0:
+	case MSR_K7_EVNTSEL1:
+	case MSR_K7_EVNTSEL2:
+	case MSR_K7_EVNTSEL3:
+		return MSR_F15H_PERF_CTL + (addr - MSR_K7_EVNTSEL0);
+	default:
+		break;
+	}
+
+	return addr;
+}
+
+static inline bool is_amd_pmu_msr(unsigned int msr)
+{
+	if ((msr >= MSR_F15H_PERF_CTL &&
+	     msr < MSR_F15H_PERF_CTR + (amd_num_counters * 2)) ||
+	    (msr >= MSR_K7_EVNTSEL0 &&
+	     msr < MSR_K7_PERFCTR0 + amd_num_counters))
+		return true;
+
+	return false;
+}
+
+static int is_intel_pmu_msr(u32 msr_index, int *type, int *index)
+{
+	u32 msr_index_pmc;
+
+	switch (msr_index) {
+	case MSR_CORE_PERF_FIXED_CTR_CTRL:
+	case MSR_IA32_DS_AREA:
+	case MSR_IA32_PEBS_ENABLE:
+		*type = MSR_TYPE_CTRL;
+		return true;
+
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+	case MSR_CORE_PERF_GLOBAL_STATUS:
+	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+		*type = MSR_TYPE_GLOBAL;
+		return true;
+
+	default:
+
+		if ((msr_index >= MSR_CORE_PERF_FIXED_CTR0) &&
+		    (msr_index < MSR_CORE_PERF_FIXED_CTR0 +
+				 intel_num_fixed_counters)) {
+			*index = msr_index - MSR_CORE_PERF_FIXED_CTR0;
+			*type = MSR_TYPE_COUNTER;
+			return true;
+		}
+
+		if ((msr_index >= MSR_P6_EVNTSEL0) &&
+		    (msr_index < MSR_P6_EVNTSEL0 +  intel_num_arch_counters)) {
+			*index = msr_index - MSR_P6_EVNTSEL0;
+			*type = MSR_TYPE_ARCH_CTRL;
+			return true;
+		}
+
+		msr_index_pmc = msr_index & MSR_PMC_ALIAS_MASK;
+		if ((msr_index_pmc >= MSR_IA32_PERFCTR0) &&
+		    (msr_index_pmc < MSR_IA32_PERFCTR0 +
+				     intel_num_arch_counters)) {
+			*type = MSR_TYPE_ARCH_COUNTER;
+			*index = msr_index_pmc - MSR_IA32_PERFCTR0;
+			return true;
+		}
+		return false;
+	}
+}
+
+static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
+				  int index, bool is_read)
+{
+	uint64_t *reg = NULL;
+	struct xen_pmu_intel_ctxt *ctxt;
+	uint64_t *fix_counters;
+	struct xen_pmu_cntr_pair *arch_cntr_pair;
+	struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+	uint8_t xenpmu_flags = get_xenpmu_flags();
+
+
+	if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING))
+		return false;
+
+	ctxt = &xenpmu_data->pmu.c.intel;
+
+	switch (msr) {
+	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+		reg = &ctxt->global_ovf_ctrl;
+		break;
+	case MSR_CORE_PERF_GLOBAL_STATUS:
+		reg = &ctxt->global_status;
+		break;
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		reg = &ctxt->global_ctrl;
+		break;
+	case MSR_CORE_PERF_FIXED_CTR_CTRL:
+		reg = &ctxt->fixed_ctrl;
+		break;
+	default:
+		switch (type) {
+		case MSR_TYPE_COUNTER:
+			fix_counters = field_offset(ctxt, fixed_counters);
+			reg = &fix_counters[index];
+			break;
+		case MSR_TYPE_ARCH_COUNTER:
+			arch_cntr_pair = field_offset(ctxt, arch_counters);
+			reg = &arch_cntr_pair[index].counter;
+			break;
+		case MSR_TYPE_ARCH_CTRL:
+			arch_cntr_pair = field_offset(ctxt, arch_counters);
+			reg = &arch_cntr_pair[index].control;
+			break;
+		default:
+			return false;
+		}
+	}
+
+	if (reg) {
+		if (is_read)
+			*val = *reg;
+		else {
+			*reg = *val;
+
+			if (msr == MSR_CORE_PERF_GLOBAL_OVF_CTRL)
+				ctxt->global_status &= (~(*val));
+		}
+		return true;
+	}
+
+	return false;
+}
+
+static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
+{
+	uint64_t *reg = NULL;
+	int i, off = 0;
+	struct xen_pmu_amd_ctxt *ctxt;
+	uint64_t *counter_regs, *ctrl_regs;
+	struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+	uint8_t xenpmu_flags = get_xenpmu_flags();
+
+	if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING))
+		return false;
+
+	if (k7_counters_mirrored &&
+	    ((msr >= MSR_K7_EVNTSEL0) && (msr <= MSR_K7_PERFCTR3)))
+		msr = get_fam15h_addr(msr);
+
+	ctxt = &xenpmu_data->pmu.c.amd;
+	for (i = 0; i < amd_num_counters; i++) {
+		if (msr == amd_ctrls_base + off) {
+			ctrl_regs = field_offset(ctxt, ctrls);
+			reg = &ctrl_regs[i];
+			break;
+		} else if (msr == amd_counters_base + off) {
+			counter_regs = field_offset(ctxt, counters);
+			reg = &counter_regs[i];
+			break;
+		}
+		off += amd_msr_step;
+	}
+
+	if (reg) {
+		if (is_read)
+			*val = *reg;
+		else
+			*reg = *val;
+
+		return true;
+	}
+	return false;
+}
+
+bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+		if (is_amd_pmu_msr(msr)) {
+			if (!xen_amd_pmu_emulate(msr, val, 1))
+				*val = native_read_msr_safe(msr, err);
+			return true;
+		}
+	} else {
+		int type, index;
+
+		if (is_intel_pmu_msr(msr, &type, &index)) {
+			if (!xen_intel_pmu_emulate(msr, val, type, index, 1))
+				*val = native_read_msr_safe(msr, err);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
+{
+	uint64_t val = ((uint64_t)high << 32) | low;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+		if (is_amd_pmu_msr(msr)) {
+			if (!xen_amd_pmu_emulate(msr, &val, 0))
+				*err = native_write_msr_safe(msr, low, high);
+			return true;
+		}
+	} else {
+		int type, index;
+
+		if (is_intel_pmu_msr(msr, &type, &index)) {
+			if (!xen_intel_pmu_emulate(msr, &val, type, index, 0))
+				*err = native_write_msr_safe(msr, low, high);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static unsigned long long xen_amd_read_pmc(int counter)
+{
+	struct xen_pmu_amd_ctxt *ctxt;
+	uint64_t *counter_regs;
+	struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+	uint8_t xenpmu_flags = get_xenpmu_flags();
+
+	if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
+		uint32_t msr;
+		int err;
+
+		msr = amd_counters_base + (counter * amd_msr_step);
+		return native_read_msr_safe(msr, &err);
+	}
+
+	ctxt = &xenpmu_data->pmu.c.amd;
+	counter_regs = field_offset(ctxt, counters);
+	return counter_regs[counter];
+}
+
+static unsigned long long xen_intel_read_pmc(int counter)
+{
+	struct xen_pmu_intel_ctxt *ctxt;
+	uint64_t *fixed_counters;
+	struct xen_pmu_cntr_pair *arch_cntr_pair;
+	struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+	uint8_t xenpmu_flags = get_xenpmu_flags();
+
+	if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
+		uint32_t msr;
+		int err;
+
+		if (counter & (1 << INTEL_PMC_TYPE_SHIFT))
+			msr = MSR_CORE_PERF_FIXED_CTR0 + (counter & 0xffff);
+		else
+			msr = MSR_IA32_PERFCTR0 + counter;
+
+		return native_read_msr_safe(msr, &err);
+	}
+
+	ctxt = &xenpmu_data->pmu.c.intel;
+	if (counter & (1 << INTEL_PMC_TYPE_SHIFT)) {
+		fixed_counters = field_offset(ctxt, fixed_counters);
+		return fixed_counters[counter & 0xffff];
+	}
+
+	arch_cntr_pair = field_offset(ctxt, arch_counters);
+	return arch_cntr_pair[counter].counter;
+}
+
+unsigned long long xen_read_pmc(int counter)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return xen_amd_read_pmc(counter);
+	else
+		return xen_intel_read_pmc(counter);
+}
+
+int pmu_apic_update(uint32_t val)
+{
+	int ret;
+	struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+
+	if (!xenpmu_data) {
+		pr_warn_once("%s: pmudata not initialized\n", __func__);
+		return -EINVAL;
+	}
+
+	xenpmu_data->pmu.l.lapic_lvtpc = val;
+
+	if (get_xenpmu_flags() & XENPMU_IRQ_PROCESSING)
+		return 0;
+
+	ret = HYPERVISOR_xenpmu_op(XENPMU_lvtpc_set, NULL);
+
+	return ret;
+}
+
+/* perf callbacks */
+static int xen_is_in_guest(void)
+{
+	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+
+	if (!xenpmu_data) {
+		pr_warn_once("%s: pmudata not initialized\n", __func__);
+		return 0;
+	}
+
+	if (!xen_initial_domain() || (xenpmu_data->domain_id >= DOMID_SELF))
+		return 0;
+
+	return 1;
+}
+
+static int xen_is_user_mode(void)
+{
+	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+
+	if (!xenpmu_data) {
+		pr_warn_once("%s: pmudata not initialized\n", __func__);
+		return 0;
+	}
+
+	if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV)
+		return (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER);
+	else
+		return !!(xenpmu_data->pmu.r.regs.cpl & 3);
+}
+
+static unsigned long xen_get_guest_ip(void)
+{
+	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+
+	if (!xenpmu_data) {
+		pr_warn_once("%s: pmudata not initialized\n", __func__);
+		return 0;
+	}
+
+	return xenpmu_data->pmu.r.regs.ip;
+}
+
+static struct perf_guest_info_callbacks xen_guest_cbs = {
+	.is_in_guest            = xen_is_in_guest,
+	.is_user_mode           = xen_is_user_mode,
+	.get_guest_ip           = xen_get_guest_ip,
+};
+
+/* Convert registers from Xen's format to Linux' */
+static void xen_convert_regs(const struct xen_pmu_regs *xen_regs,
+			     struct pt_regs *regs, uint64_t pmu_flags)
+{
+	regs->ip = xen_regs->ip;
+	regs->cs = xen_regs->cs;
+	regs->sp = xen_regs->sp;
+
+	if (pmu_flags & PMU_SAMPLE_PV) {
+		if (pmu_flags & PMU_SAMPLE_USER)
+			regs->cs |= 3;
+		else
+			regs->cs &= ~3;
+	} else {
+		if (xen_regs->cpl)
+			regs->cs |= 3;
+		else
+			regs->cs &= ~3;
+	}
+}
+
+irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
+{
+	int err, ret = IRQ_NONE;
+	struct pt_regs regs;
+	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+	uint8_t xenpmu_flags = get_xenpmu_flags();
+
+	if (!xenpmu_data) {
+		pr_warn_once("%s: pmudata not initialized\n", __func__);
+		return ret;
+	}
+
+	this_cpu_ptr(&xenpmu_shared)->flags =
+		xenpmu_flags | XENPMU_IRQ_PROCESSING;
+	xen_convert_regs(&xenpmu_data->pmu.r.regs, &regs,
+			 xenpmu_data->pmu.pmu_flags);
+	if (x86_pmu.handle_irq(&regs))
+		ret = IRQ_HANDLED;
+
+	/* Write out cached context to HW */
+	err = HYPERVISOR_xenpmu_op(XENPMU_flush, NULL);
+	this_cpu_ptr(&xenpmu_shared)->flags = xenpmu_flags;
+	if (err) {
+		pr_warn_once("%s: failed hypercall, err: %d\n", __func__, err);
+		return IRQ_NONE;
+	}
+
+	return ret;
+}
+
+bool is_xen_pmu(int cpu)
+{
+	return (get_xenpmu_data() != NULL);
+}
+
+void xen_pmu_init(int cpu)
+{
+	int err;
+	struct xen_pmu_params xp;
+	unsigned long pfn;
+	struct xen_pmu_data *xenpmu_data;
+
+	BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE);
+
+	if (xen_hvm_domain())
+		return;
+
+	xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL);
+	if (!xenpmu_data) {
+		pr_err("VPMU init: No memory\n");
+		return;
+	}
+	pfn = virt_to_pfn(xenpmu_data);
+
+	xp.val = pfn_to_mfn(pfn);
+	xp.vcpu = cpu;
+	xp.version.maj = XENPMU_VER_MAJ;
+	xp.version.min = XENPMU_VER_MIN;
+	err = HYPERVISOR_xenpmu_op(XENPMU_init, &xp);
+	if (err)
+		goto fail;
+
+	per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data;
+	per_cpu(xenpmu_shared, cpu).flags = 0;
+
+	if (cpu == 0) {
+		perf_register_guest_info_callbacks(&xen_guest_cbs);
+		xen_pmu_arch_init();
+	}
+
+	return;
+
+fail:
+	pr_warn_once("Could not initialize VPMU for cpu %d, error %d\n",
+		cpu, err);
+	free_pages((unsigned long)xenpmu_data, 0);
+}
+
+void xen_pmu_finish(int cpu)
+{
+	struct xen_pmu_params xp;
+
+	if (xen_hvm_domain())
+		return;
+
+	xp.vcpu = cpu;
+	xp.version.maj = XENPMU_VER_MAJ;
+	xp.version.min = XENPMU_VER_MIN;
+
+	(void)HYPERVISOR_xenpmu_op(XENPMU_finish, &xp);
+
+	free_pages((unsigned long)per_cpu(xenpmu_shared, cpu).xenpmu_data, 0);
+	per_cpu(xenpmu_shared, cpu).xenpmu_data = NULL;
+}
diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h
new file mode 100644
index 000000000000..af5f0ad94078
--- /dev/null
+++ b/arch/x86/xen/pmu.h
@@ -0,0 +1,15 @@
+#ifndef __XEN_PMU_H
+#define __XEN_PMU_H
+
+#include <xen/interface/xenpmu.h>
+
+irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
+void xen_pmu_init(int cpu);
+void xen_pmu_finish(int cpu);
+bool is_xen_pmu(int cpu);
+bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
+bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
+int pmu_apic_update(uint32_t reg);
+unsigned long long xen_read_pmc(int counter);
+
+#endif /* __XEN_PMU_H */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 55f388ef481a..f5ef6746d47a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -27,17 +27,23 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
+#include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "vdso.h"
-#include "p2m.h"
 #include "mmu.h"
 
+#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
+
 /* Amount of extra memory space we add to the e820 ranges */
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
 /* Number of pages released from the initial allocation. */
 unsigned long xen_released_pages;
 
+/* E820 map used during setting up memory. */
+static struct e820entry xen_e820_map[E820MAX] __initdata;
+static u32 xen_e820_map_entries __initdata;
+
 /*
  * Buffer used to remap identity mapped pages. We only need the virtual space.
  * The physical page behind this address is remapped as needed to different
@@ -64,62 +70,89 @@ static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
  */
 #define EXTRA_MEM_RATIO		(10)
 
-static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size)
+static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
+
+static void __init xen_parse_512gb(void)
+{
+	bool val = false;
+	char *arg;
+
+	arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit");
+	if (!arg)
+		return;
+
+	arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit=");
+	if (!arg)
+		val = true;
+	else if (strtobool(arg + strlen("xen_512gb_limit="), &val))
+		return;
+
+	xen_512gb_limit = val;
+}
+
+static void __init xen_add_extra_mem(unsigned long start_pfn,
+				     unsigned long n_pfns)
 {
 	int i;
 
+	/*
+	 * No need to check for zero size, should happen rarely and will only
+	 * write a new entry regarded to be unused due to zero size.
+	 */
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
 		/* Add new region. */
-		if (xen_extra_mem[i].size == 0) {
-			xen_extra_mem[i].start = start;
-			xen_extra_mem[i].size  = size;
+		if (xen_extra_mem[i].n_pfns == 0) {
+			xen_extra_mem[i].start_pfn = start_pfn;
+			xen_extra_mem[i].n_pfns = n_pfns;
 			break;
 		}
 		/* Append to existing region. */
-		if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) {
-			xen_extra_mem[i].size += size;
+		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
+		    start_pfn) {
+			xen_extra_mem[i].n_pfns += n_pfns;
 			break;
 		}
 	}
 	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
 		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
 
-	memblock_reserve(start, size);
+	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
 }
 
-static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size)
+static void __init xen_del_extra_mem(unsigned long start_pfn,
+				     unsigned long n_pfns)
 {
 	int i;
-	phys_addr_t start_r, size_r;
+	unsigned long start_r, size_r;
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
-		start_r = xen_extra_mem[i].start;
-		size_r = xen_extra_mem[i].size;
+		start_r = xen_extra_mem[i].start_pfn;
+		size_r = xen_extra_mem[i].n_pfns;
 
 		/* Start of region. */
-		if (start_r == start) {
-			BUG_ON(size > size_r);
-			xen_extra_mem[i].start += size;
-			xen_extra_mem[i].size -= size;
+		if (start_r == start_pfn) {
+			BUG_ON(n_pfns > size_r);
+			xen_extra_mem[i].start_pfn += n_pfns;
+			xen_extra_mem[i].n_pfns -= n_pfns;
 			break;
 		}
 		/* End of region. */
-		if (start_r + size_r == start + size) {
-			BUG_ON(size > size_r);
-			xen_extra_mem[i].size -= size;
+		if (start_r + size_r == start_pfn + n_pfns) {
+			BUG_ON(n_pfns > size_r);
+			xen_extra_mem[i].n_pfns -= n_pfns;
 			break;
 		}
 		/* Mid of region. */
-		if (start > start_r && start < start_r + size_r) {
-			BUG_ON(start + size > start_r + size_r);
-			xen_extra_mem[i].size = start - start_r;
+		if (start_pfn > start_r && start_pfn < start_r + size_r) {
+			BUG_ON(start_pfn + n_pfns > start_r + size_r);
+			xen_extra_mem[i].n_pfns = start_pfn - start_r;
 			/* Calling memblock_reserve() again is okay. */
-			xen_add_extra_mem(start + size, start_r + size_r -
-					  (start + size));
+			xen_add_extra_mem(start_pfn + n_pfns, start_r + size_r -
+					  (start_pfn + n_pfns));
 			break;
 		}
 	}
-	memblock_free(start, size);
+	memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
 }
 
 /*
@@ -130,11 +163,10 @@ static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size)
 unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
 {
 	int i;
-	phys_addr_t addr = PFN_PHYS(pfn);
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
-		if (addr >= xen_extra_mem[i].start &&
-		    addr < xen_extra_mem[i].start + xen_extra_mem[i].size)
+		if (pfn >= xen_extra_mem[i].start_pfn &&
+		    pfn < xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns)
 			return INVALID_P2M_ENTRY;
 	}
 
@@ -150,10 +182,10 @@ void __init xen_inv_extra_mem(void)
 	int i;
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
-		if (!xen_extra_mem[i].size)
+		if (!xen_extra_mem[i].n_pfns)
 			continue;
-		pfn_s = PFN_DOWN(xen_extra_mem[i].start);
-		pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size);
+		pfn_s = xen_extra_mem[i].start_pfn;
+		pfn_e = pfn_s + xen_extra_mem[i].n_pfns;
 		for (pfn = pfn_s; pfn < pfn_e; pfn++)
 			set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 	}
@@ -164,15 +196,13 @@ void __init xen_inv_extra_mem(void)
  * This function updates min_pfn with the pfn found and returns
  * the size of that range or zero if not found.
  */
-static unsigned long __init xen_find_pfn_range(
-	const struct e820entry *list, size_t map_size,
-	unsigned long *min_pfn)
+static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn)
 {
-	const struct e820entry *entry;
+	const struct e820entry *entry = xen_e820_map;
 	unsigned int i;
 	unsigned long done = 0;
 
-	for (i = 0, entry = list; i < map_size; i++, entry++) {
+	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
 		unsigned long s_pfn;
 		unsigned long e_pfn;
 
@@ -221,7 +251,7 @@ static int __init xen_free_mfn(unsigned long mfn)
  * as a fallback if the remapping fails.
  */
 static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
-	unsigned long end_pfn, unsigned long nr_pages, unsigned long *released)
+			unsigned long end_pfn, unsigned long nr_pages)
 {
 	unsigned long pfn, end;
 	int ret;
@@ -241,7 +271,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
 		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
 
 		if (ret == 1) {
-			(*released)++;
+			xen_released_pages++;
 			if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY))
 				break;
 		} else
@@ -356,9 +386,8 @@ static void __init xen_do_set_identity_and_remap_chunk(
  * to Xen and not remapped.
  */
 static unsigned long __init xen_set_identity_and_remap_chunk(
-        const struct e820entry *list, size_t map_size, unsigned long start_pfn,
-	unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn,
-	unsigned long *released, unsigned long *remapped)
+	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+	unsigned long remap_pfn)
 {
 	unsigned long pfn;
 	unsigned long i = 0;
@@ -379,12 +408,11 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		if (cur_pfn + size > nr_pages)
 			size = nr_pages - cur_pfn;
 
-		remap_range_size = xen_find_pfn_range(list, map_size,
-						      &remap_pfn);
+		remap_range_size = xen_find_pfn_range(&remap_pfn);
 		if (!remap_range_size) {
 			pr_warning("Unable to find available pfn range, not remapping identity pages\n");
 			xen_set_identity_and_release_chunk(cur_pfn,
-				cur_pfn + left, nr_pages, released);
+						cur_pfn + left, nr_pages);
 			break;
 		}
 		/* Adjust size to fit in current e820 RAM region */
@@ -396,7 +424,6 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		/* Update variables to reflect new mappings. */
 		i += size;
 		remap_pfn += size;
-		*remapped += size;
 	}
 
 	/*
@@ -411,15 +438,11 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 	return remap_pfn;
 }
 
-static void __init xen_set_identity_and_remap(
-	const struct e820entry *list, size_t map_size, unsigned long nr_pages,
-	unsigned long *released, unsigned long *remapped)
+static void __init xen_set_identity_and_remap(unsigned long nr_pages)
 {
 	phys_addr_t start = 0;
 	unsigned long last_pfn = nr_pages;
-	const struct e820entry *entry;
-	unsigned long num_released = 0;
-	unsigned long num_remapped = 0;
+	const struct e820entry *entry = xen_e820_map;
 	int i;
 
 	/*
@@ -433,9 +456,9 @@ static void __init xen_set_identity_and_remap(
 	 * example) the DMI tables in a reserved region that begins on
 	 * a non-page boundary.
 	 */
-	for (i = 0, entry = list; i < map_size; i++, entry++) {
+	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
 		phys_addr_t end = entry->addr + entry->size;
-		if (entry->type == E820_RAM || i == map_size - 1) {
+		if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) {
 			unsigned long start_pfn = PFN_DOWN(start);
 			unsigned long end_pfn = PFN_UP(end);
 
@@ -444,17 +467,13 @@ static void __init xen_set_identity_and_remap(
 
 			if (start_pfn < end_pfn)
 				last_pfn = xen_set_identity_and_remap_chunk(
-						list, map_size, start_pfn,
-						end_pfn, nr_pages, last_pfn,
-						&num_released, &num_remapped);
+						start_pfn, end_pfn, nr_pages,
+						last_pfn);
 			start = end;
 		}
 	}
 
-	*released = num_released;
-	*remapped = num_remapped;
-
-	pr_info("Released %ld page(s)\n", num_released);
+	pr_info("Released %ld page(s)\n", xen_released_pages);
 }
 
 /*
@@ -494,7 +513,7 @@ void __init xen_remap_memory(void)
 		} else if (pfn_s + len == xen_remap_buf.target_pfn) {
 			len += xen_remap_buf.size;
 		} else {
-			xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+			xen_del_extra_mem(pfn_s, len);
 			pfn_s = xen_remap_buf.target_pfn;
 			len = xen_remap_buf.size;
 		}
@@ -504,19 +523,36 @@ void __init xen_remap_memory(void)
 	}
 
 	if (pfn_s != ~0UL && len)
-		xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+		xen_del_extra_mem(pfn_s, len);
 
 	set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
 
 	pr_info("Remapped %ld page(s)\n", remapped);
 }
 
+static unsigned long __init xen_get_pages_limit(void)
+{
+	unsigned long limit;
+
+#ifdef CONFIG_X86_32
+	limit = GB(64) / PAGE_SIZE;
+#else
+	limit = MAXMEM / PAGE_SIZE;
+	if (!xen_initial_domain() && xen_512gb_limit)
+		limit = GB(512) / PAGE_SIZE;
+#endif
+	return limit;
+}
+
 static unsigned long __init xen_get_max_pages(void)
 {
-	unsigned long max_pages = MAX_DOMAIN_PAGES;
+	unsigned long max_pages, limit;
 	domid_t domid = DOMID_SELF;
 	int ret;
 
+	limit = xen_get_pages_limit();
+	max_pages = limit;
+
 	/*
 	 * For the initial domain we use the maximum reservation as
 	 * the maximum page.
@@ -532,7 +568,7 @@ static unsigned long __init xen_get_max_pages(void)
 			max_pages = ret;
 	}
 
-	return min(max_pages, MAX_DOMAIN_PAGES);
+	return min(max_pages, limit);
 }
 
 static void __init xen_align_and_add_e820_region(phys_addr_t start,
@@ -549,39 +585,188 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start,
 	e820_add_region(start, end - start, type);
 }
 
-static void __init xen_ignore_unusable(struct e820entry *list, size_t map_size)
+static void __init xen_ignore_unusable(void)
 {
-	struct e820entry *entry;
+	struct e820entry *entry = xen_e820_map;
 	unsigned int i;
 
-	for (i = 0, entry = list; i < map_size; i++, entry++) {
+	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
 		if (entry->type == E820_UNUSABLE)
 			entry->type = E820_RAM;
 	}
 }
 
+static unsigned long __init xen_count_remap_pages(unsigned long max_pfn)
+{
+	unsigned long extra = 0;
+	unsigned long start_pfn, end_pfn;
+	const struct e820entry *entry = xen_e820_map;
+	int i;
+
+	end_pfn = 0;
+	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
+		start_pfn = PFN_DOWN(entry->addr);
+		/* Adjacent regions on non-page boundaries handling! */
+		end_pfn = min(end_pfn, start_pfn);
+
+		if (start_pfn >= max_pfn)
+			return extra + max_pfn - end_pfn;
+
+		/* Add any holes in map to result. */
+		extra += start_pfn - end_pfn;
+
+		end_pfn = PFN_UP(entry->addr + entry->size);
+		end_pfn = min(end_pfn, max_pfn);
+
+		if (entry->type != E820_RAM)
+			extra += end_pfn - start_pfn;
+	}
+
+	return extra;
+}
+
+bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
+{
+	struct e820entry *entry;
+	unsigned mapcnt;
+	phys_addr_t end;
+
+	if (!size)
+		return false;
+
+	end = start + size;
+	entry = xen_e820_map;
+
+	for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) {
+		if (entry->type == E820_RAM && entry->addr <= start &&
+		    (entry->addr + entry->size) >= end)
+			return false;
+
+		entry++;
+	}
+
+	return true;
+}
+
+/*
+ * Find a free area in physical memory not yet reserved and compliant with
+ * E820 map.
+ * Used to relocate pre-allocated areas like initrd or p2m list which are in
+ * conflict with the to be used E820 map.
+ * In case no area is found, return 0. Otherwise return the physical address
+ * of the area which is already reserved for convenience.
+ */
+phys_addr_t __init xen_find_free_area(phys_addr_t size)
+{
+	unsigned mapcnt;
+	phys_addr_t addr, start;
+	struct e820entry *entry = xen_e820_map;
+
+	for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) {
+		if (entry->type != E820_RAM || entry->size < size)
+			continue;
+		start = entry->addr;
+		for (addr = start; addr < start + size; addr += PAGE_SIZE) {
+			if (!memblock_is_reserved(addr))
+				continue;
+			start = addr + PAGE_SIZE;
+			if (start + size > entry->addr + entry->size)
+				break;
+		}
+		if (addr >= start + size) {
+			memblock_reserve(start, size);
+			return start;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Like memcpy, but with physical addresses for dest and src.
+ */
+static void __init xen_phys_memcpy(phys_addr_t dest, phys_addr_t src,
+				   phys_addr_t n)
+{
+	phys_addr_t dest_off, src_off, dest_len, src_len, len;
+	void *from, *to;
+
+	while (n) {
+		dest_off = dest & ~PAGE_MASK;
+		src_off = src & ~PAGE_MASK;
+		dest_len = n;
+		if (dest_len > (NR_FIX_BTMAPS << PAGE_SHIFT) - dest_off)
+			dest_len = (NR_FIX_BTMAPS << PAGE_SHIFT) - dest_off;
+		src_len = n;
+		if (src_len > (NR_FIX_BTMAPS << PAGE_SHIFT) - src_off)
+			src_len = (NR_FIX_BTMAPS << PAGE_SHIFT) - src_off;
+		len = min(dest_len, src_len);
+		to = early_memremap(dest - dest_off, dest_len + dest_off);
+		from = early_memremap(src - src_off, src_len + src_off);
+		memcpy(to, from, len);
+		early_memunmap(to, dest_len + dest_off);
+		early_memunmap(from, src_len + src_off);
+		n -= len;
+		dest += len;
+		src += len;
+	}
+}
+
+/*
+ * Reserve Xen mfn_list.
+ */
+static void __init xen_reserve_xen_mfnlist(void)
+{
+	phys_addr_t start, size;
+
+	if (xen_start_info->mfn_list >= __START_KERNEL_map) {
+		start = __pa(xen_start_info->mfn_list);
+		size = PFN_ALIGN(xen_start_info->nr_pages *
+				 sizeof(unsigned long));
+	} else {
+		start = PFN_PHYS(xen_start_info->first_p2m_pfn);
+		size = PFN_PHYS(xen_start_info->nr_p2m_frames);
+	}
+
+	if (!xen_is_e820_reserved(start, size)) {
+		memblock_reserve(start, size);
+		return;
+	}
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Relocating the p2m on 32 bit system to an arbitrary virtual address
+	 * is not supported, so just give up.
+	 */
+	xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n");
+	BUG();
+#else
+	xen_relocate_p2m();
+#endif
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
 char * __init xen_memory_setup(void)
 {
-	static struct e820entry map[E820MAX] __initdata;
-
-	unsigned long max_pfn = xen_start_info->nr_pages;
-	phys_addr_t mem_end;
+	unsigned long max_pfn, pfn_s, n_pfns;
+	phys_addr_t mem_end, addr, size, chunk_size;
+	u32 type;
 	int rc;
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
 	unsigned long extra_pages = 0;
-	unsigned long remapped_pages;
 	int i;
 	int op;
 
-	max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
+	xen_parse_512gb();
+	max_pfn = xen_get_pages_limit();
+	max_pfn = min(max_pfn, xen_start_info->nr_pages);
 	mem_end = PFN_PHYS(max_pfn);
 
 	memmap.nr_entries = E820MAX;
-	set_xen_guest_handle(memmap.buffer, map);
+	set_xen_guest_handle(memmap.buffer, xen_e820_map);
 
 	op = xen_initial_domain() ?
 		XENMEM_machine_memory_map :
@@ -590,15 +775,16 @@ char * __init xen_memory_setup(void)
 	if (rc == -ENOSYS) {
 		BUG_ON(xen_initial_domain());
 		memmap.nr_entries = 1;
-		map[0].addr = 0ULL;
-		map[0].size = mem_end;
+		xen_e820_map[0].addr = 0ULL;
+		xen_e820_map[0].size = mem_end;
 		/* 8MB slack (to balance backend allocations). */
-		map[0].size += 8ULL << 20;
-		map[0].type = E820_RAM;
+		xen_e820_map[0].size += 8ULL << 20;
+		xen_e820_map[0].type = E820_RAM;
 		rc = 0;
 	}
 	BUG_ON(rc);
 	BUG_ON(memmap.nr_entries == 0);
+	xen_e820_map_entries = memmap.nr_entries;
 
 	/*
 	 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
@@ -609,24 +795,19 @@ char * __init xen_memory_setup(void)
 	 * a patch in the future.
 	 */
 	if (xen_initial_domain())
-		xen_ignore_unusable(map, memmap.nr_entries);
+		xen_ignore_unusable();
 
 	/* Make sure the Xen-supplied memory map is well-ordered. */
-	sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
+	sanitize_e820_map(xen_e820_map, xen_e820_map_entries,
+			  &xen_e820_map_entries);
 
 	max_pages = xen_get_max_pages();
-	if (max_pages > max_pfn)
-		extra_pages += max_pages - max_pfn;
 
-	/*
-	 * Set identity map on non-RAM pages and prepare remapping the
-	 * underlying RAM.
-	 */
-	xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
-				   &xen_released_pages, &remapped_pages);
+	/* How many extra pages do we need due to remapping? */
+	max_pages += xen_count_remap_pages(max_pfn);
 
-	extra_pages += xen_released_pages;
-	extra_pages += remapped_pages;
+	if (max_pages > max_pfn)
+		extra_pages += max_pages - max_pfn;
 
 	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
@@ -635,46 +816,54 @@ char * __init xen_memory_setup(void)
 	 * is limited to the max size of lowmem, so that it doesn't
 	 * get completely filled.
 	 *
+	 * Make sure we have no memory above max_pages, as this area
+	 * isn't handled by the p2m management.
+	 *
 	 * In principle there could be a problem in lowmem systems if
 	 * the initial memory is also very large with respect to
 	 * lowmem, but we won't try to deal with that here.
 	 */
-	extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
-			  extra_pages);
+	extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+			   extra_pages, max_pages - max_pfn);
 	i = 0;
-	while (i < memmap.nr_entries) {
-		phys_addr_t addr = map[i].addr;
-		phys_addr_t size = map[i].size;
-		u32 type = map[i].type;
+	addr = xen_e820_map[0].addr;
+	size = xen_e820_map[0].size;
+	while (i < xen_e820_map_entries) {
+		chunk_size = size;
+		type = xen_e820_map[i].type;
 
 		if (type == E820_RAM) {
 			if (addr < mem_end) {
-				size = min(size, mem_end - addr);
+				chunk_size = min(size, mem_end - addr);
 			} else if (extra_pages) {
-				size = min(size, PFN_PHYS(extra_pages));
-				extra_pages -= PFN_DOWN(size);
-				xen_add_extra_mem(addr, size);
-				xen_max_p2m_pfn = PFN_DOWN(addr + size);
+				chunk_size = min(size, PFN_PHYS(extra_pages));
+				pfn_s = PFN_UP(addr);
+				n_pfns = PFN_DOWN(addr + chunk_size) - pfn_s;
+				extra_pages -= n_pfns;
+				xen_add_extra_mem(pfn_s, n_pfns);
+				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
 				type = E820_UNUSABLE;
 		}
 
-		xen_align_and_add_e820_region(addr, size, type);
+		xen_align_and_add_e820_region(addr, chunk_size, type);
 
-		map[i].addr += size;
-		map[i].size -= size;
-		if (map[i].size == 0)
+		addr += chunk_size;
+		size -= chunk_size;
+		if (size == 0) {
 			i++;
+			if (i < xen_e820_map_entries) {
+				addr = xen_e820_map[i].addr;
+				size = xen_e820_map[i].size;
+			}
+		}
 	}
 
 	/*
 	 * Set the rest as identity mapped, in case PCI BARs are
 	 * located here.
-	 *
-	 * PFNs above MAX_P2M_PFN are considered identity mapped as
-	 * well.
 	 */
-	set_phys_range_identity(map[i-1].addr / PAGE_SIZE, ~0ul);
+	set_phys_range_identity(addr / PAGE_SIZE, ~0ul);
 
 	/*
 	 * In domU, the ISA region is normal, usable memory, but we
@@ -684,34 +873,53 @@ char * __init xen_memory_setup(void)
 	e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
 			E820_RESERVED);
 
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+
 	/*
-	 * Reserve Xen bits:
-	 *  - mfn_list
-	 *  - xen_start_info
-	 * See comment above "struct start_info" in <xen/interface/xen.h>
-	 * We tried to make the the memblock_reserve more selective so
-	 * that it would be clear what region is reserved. Sadly we ran
-	 * in the problem wherein on a 64-bit hypervisor with a 32-bit
-	 * initial domain, the pt_base has the cr3 value which is not
-	 * neccessarily where the pagetable starts! As Jan put it: "
-	 * Actually, the adjustment turns out to be correct: The page
-	 * tables for a 32-on-64 dom0 get allocated in the order "first L1",
-	 * "first L2", "first L3", so the offset to the page table base is
-	 * indeed 2. When reading xen/include/public/xen.h's comment
-	 * very strictly, this is not a violation (since there nothing is said
-	 * that the first thing in the page table space is pointed to by
-	 * pt_base; I admit that this seems to be implied though, namely
-	 * do I think that it is implied that the page table space is the
-	 * range [pt_base, pt_base + nt_pt_frames), whereas that
-	 * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames),
-	 * which - without a priori knowledge - the kernel would have
-	 * difficulty to figure out)." - so lets just fall back to the
-	 * easy way and reserve the whole region.
+	 * Check whether the kernel itself conflicts with the target E820 map.
+	 * Failing now is better than running into weird problems later due
+	 * to relocating (and even reusing) pages with kernel text or data.
 	 */
-	memblock_reserve(__pa(xen_start_info->mfn_list),
-			 xen_start_info->pt_base - xen_start_info->mfn_list);
+	if (xen_is_e820_reserved(__pa_symbol(_text),
+			__pa_symbol(__bss_stop) - __pa_symbol(_text))) {
+		xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n");
+		BUG();
+	}
 
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	/*
+	 * Check for a conflict of the hypervisor supplied page tables with
+	 * the target E820 map.
+	 */
+	xen_pt_check_e820();
+
+	xen_reserve_xen_mfnlist();
+
+	/* Check for a conflict of the initrd with the target E820 map. */
+	if (xen_is_e820_reserved(boot_params.hdr.ramdisk_image,
+				 boot_params.hdr.ramdisk_size)) {
+		phys_addr_t new_area, start, size;
+
+		new_area = xen_find_free_area(boot_params.hdr.ramdisk_size);
+		if (!new_area) {
+			xen_raw_console_write("Can't find new memory area for initrd needed due to E820 map conflict\n");
+			BUG();
+		}
+
+		start = boot_params.hdr.ramdisk_image;
+		size = boot_params.hdr.ramdisk_size;
+		xen_phys_memcpy(new_area, start, size);
+		pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n",
+			start, start + size, new_area, new_area + size);
+		memblock_free(start, size);
+		boot_params.hdr.ramdisk_image = new_area;
+		boot_params.ext_ramdisk_image = new_area >> 32;
+	}
+
+	/*
+	 * Set identity map on non-RAM pages and prepare remapping the
+	 * underlying RAM.
+	 */
+	xen_set_identity_and_remap(max_pfn);
 
 	return "Xen";
 }
@@ -721,26 +929,30 @@ char * __init xen_memory_setup(void)
  */
 char * __init xen_auto_xlated_memory_setup(void)
 {
-	static struct e820entry map[E820MAX] __initdata;
-
 	struct xen_memory_map memmap;
 	int i;
 	int rc;
 
 	memmap.nr_entries = E820MAX;
-	set_xen_guest_handle(memmap.buffer, map);
+	set_xen_guest_handle(memmap.buffer, xen_e820_map);
 
 	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
 	if (rc < 0)
 		panic("No memory map (%d)\n", rc);
 
-	sanitize_e820_map(map, ARRAY_SIZE(map), &memmap.nr_entries);
+	xen_e820_map_entries = memmap.nr_entries;
+
+	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
+			  &xen_e820_map_entries);
 
-	for (i = 0; i < memmap.nr_entries; i++)
-		e820_add_region(map[i].addr, map[i].size, map[i].type);
+	for (i = 0; i < xen_e820_map_entries; i++)
+		e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size,
+				xen_e820_map[i].type);
 
-	memblock_reserve(__pa(xen_start_info->mfn_list),
-			 xen_start_info->pt_base - xen_start_info->mfn_list);
+	/* Remove p2m info, it is not needed. */
+	xen_start_info->mfn_list = 0;
+	xen_start_info->first_p2m_pfn = 0;
+	xen_start_info->nr_p2m_frames = 0;
 
 	return "Xen";
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 86484384492e..2a9ff7342791 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -26,6 +26,7 @@
 
 #include <xen/interface/xen.h>
 #include <xen/interface/vcpu.h>
+#include <xen/interface/xenpmu.h>
 
 #include <asm/xen/interface.h>
 #include <asm/xen/hypercall.h>
@@ -38,6 +39,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 #include "smp.h"
+#include "pmu.h"
 
 cpumask_var_t xen_cpu_initialized_map;
 
@@ -50,6 +52,7 @@ static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_callfuncsingle_irq) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_debug_irq) = { .irq = -1 };
+static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
@@ -148,11 +151,18 @@ static void xen_smp_intr_free(unsigned int cpu)
 		kfree(per_cpu(xen_irq_work, cpu).name);
 		per_cpu(xen_irq_work, cpu).name = NULL;
 	}
+
+	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
+		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
+		per_cpu(xen_pmu_irq, cpu).irq = -1;
+		kfree(per_cpu(xen_pmu_irq, cpu).name);
+		per_cpu(xen_pmu_irq, cpu).name = NULL;
+	}
 };
 static int xen_smp_intr_init(unsigned int cpu)
 {
 	int rc;
-	char *resched_name, *callfunc_name, *debug_name;
+	char *resched_name, *callfunc_name, *debug_name, *pmu_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
@@ -218,6 +228,18 @@ static int xen_smp_intr_init(unsigned int cpu)
 	per_cpu(xen_irq_work, cpu).irq = rc;
 	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 
+	if (is_xen_pmu(cpu)) {
+		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
+		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
+					     xen_pmu_irq_handler,
+					     IRQF_PERCPU|IRQF_NOBALANCING,
+					     pmu_name, NULL);
+		if (rc < 0)
+			goto fail;
+		per_cpu(xen_pmu_irq, cpu).irq = rc;
+		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
+	}
+
 	return 0;
 
  fail:
@@ -335,6 +357,8 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	set_cpu_sibling_map(0);
 
+	xen_pmu_init(0);
+
 	if (xen_smp_intr_init(0))
 		BUG();
 
@@ -462,6 +486,8 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	if (rc)
 		return rc;
 
+	xen_pmu_init(cpu);
+
 	rc = xen_smp_intr_init(cpu);
 	if (rc)
 		return rc;
@@ -503,6 +529,7 @@ static void xen_cpu_die(unsigned int cpu)
 		xen_smp_intr_free(cpu);
 		xen_uninit_lock_cpu(cpu);
 		xen_teardown_timer(cpu);
+		xen_pmu_finish(cpu);
 	}
 }
 
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 53b4c0811f4f..feddabdab448 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -11,6 +11,7 @@
 
 #include "xen-ops.h"
 #include "mmu.h"
+#include "pmu.h"
 
 static void xen_pv_pre_suspend(void)
 {
@@ -67,16 +68,26 @@ static void xen_pv_post_suspend(int suspend_cancelled)
 
 void xen_arch_pre_suspend(void)
 {
-    if (xen_pv_domain())
-        xen_pv_pre_suspend();
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		xen_pmu_finish(cpu);
+
+	if (xen_pv_domain())
+		xen_pv_pre_suspend();
 }
 
 void xen_arch_post_suspend(int cancelled)
 {
-    if (xen_pv_domain())
-        xen_pv_post_suspend(cancelled);
-    else
-        xen_hvm_post_suspend(cancelled);
+	int cpu;
+
+	if (xen_pv_domain())
+		xen_pv_post_suspend(cancelled);
+	else
+		xen_hvm_post_suspend(cancelled);
+
+	for_each_online_cpu(cpu)
+		xen_pmu_init(cpu);
 }
 
 static void xen_vcpu_notify_restore(void *data)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 55da33b1d51c..f1ba6a092854 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -274,30 +274,18 @@ static s64 get_abs_timeout(unsigned long delta)
 	return xen_clocksource_read() + delta;
 }
 
-static void xen_timerop_set_mode(enum clock_event_mode mode,
-				 struct clock_event_device *evt)
+static int xen_timerop_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* unsupported */
-		WARN_ON(1);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		HYPERVISOR_set_timer_op(0);  /* cancel timeout */
-		break;
-	}
+	/* cancel timeout */
+	HYPERVISOR_set_timer_op(0);
+
+	return 0;
 }
 
 static int xen_timerop_set_next_event(unsigned long delta,
 				      struct clock_event_device *evt)
 {
-	WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
+	WARN_ON(!clockevent_state_oneshot(evt));
 
 	if (HYPERVISOR_set_timer_op(get_abs_timeout(delta)) < 0)
 		BUG();
@@ -310,46 +298,39 @@ static int xen_timerop_set_next_event(unsigned long delta,
 }
 
 static const struct clock_event_device xen_timerop_clockevent = {
-	.name = "xen",
-	.features = CLOCK_EVT_FEAT_ONESHOT,
+	.name			= "xen",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
 
-	.max_delta_ns = 0xffffffff,
-	.min_delta_ns = TIMER_SLOP,
+	.max_delta_ns		= 0xffffffff,
+	.min_delta_ns		= TIMER_SLOP,
 
-	.mult = 1,
-	.shift = 0,
-	.rating = 500,
+	.mult			= 1,
+	.shift			= 0,
+	.rating			= 500,
 
-	.set_mode = xen_timerop_set_mode,
-	.set_next_event = xen_timerop_set_next_event,
+	.set_state_shutdown	= xen_timerop_shutdown,
+	.set_next_event		= xen_timerop_set_next_event,
 };
 
+static int xen_vcpuop_shutdown(struct clock_event_device *evt)
+{
+	int cpu = smp_processor_id();
 
+	if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) ||
+	    HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+		BUG();
+
+	return 0;
+}
 
-static void xen_vcpuop_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int xen_vcpuop_set_oneshot(struct clock_event_device *evt)
 {
 	int cpu = smp_processor_id();
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		WARN_ON(1);	/* unsupported */
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
-			BUG();
-		break;
+	if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+		BUG();
 
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) ||
-		    HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
-			BUG();
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	return 0;
 }
 
 static int xen_vcpuop_set_next_event(unsigned long delta,
@@ -359,7 +340,7 @@ static int xen_vcpuop_set_next_event(unsigned long delta,
 	struct vcpu_set_singleshot_timer single;
 	int ret;
 
-	WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
+	WARN_ON(!clockevent_state_oneshot(evt));
 
 	single.timeout_abs_ns = get_abs_timeout(delta);
 	single.flags = VCPU_SSHOTTMR_future;
@@ -382,7 +363,8 @@ static const struct clock_event_device xen_vcpuop_clockevent = {
 	.shift = 0,
 	.rating = 500,
 
-	.set_mode = xen_vcpuop_set_mode,
+	.set_state_shutdown = xen_vcpuop_shutdown,
+	.set_state_oneshot = xen_vcpuop_set_oneshot,
 	.set_next_event = xen_vcpuop_set_next_event,
 };
 
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 8afdfccf6086..b65f59a358a2 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -104,6 +104,8 @@ ENTRY(hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE,      _ASM_PTR __PAGE_OFFSET)
 #else
 	ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE,      _ASM_PTR __START_KERNEL_map)
+	/* Map the p2m table to a 512GB-aligned user address. */
+	ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M,       .quad PGDIR_SIZE)
 #endif
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          _ASM_PTR startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c20fe29e65f4..1399423f3418 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -35,13 +35,20 @@ void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_reserve_top(void);
+void __init xen_reserve_special_pages(void);
+void __init xen_pt_check_e820(void);
 
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);
+#ifdef CONFIG_X86_64
+void __init xen_relocate_p2m(void);
+#endif
 
+bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size);
 unsigned long __ref xen_chk_extra_mem(unsigned long pfn);
 void __init xen_inv_extra_mem(void);
 void __init xen_remap_memory(void);
+phys_addr_t __init xen_find_free_area(phys_addr_t size);
 char * __init xen_memory_setup(void);
 char * xen_auto_xlated_memory_setup(void);
 void __init xen_arch_setup(void);
@@ -101,17 +108,15 @@ struct dom0_vga_console_info;
 
 #ifdef CONFIG_XEN_DOM0
 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
-void __init xen_init_apic(void);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 				       size_t size)
 {
 }
-static inline void __init xen_init_apic(void)
-{
-}
 #endif
 
+void __init xen_init_apic(void);
+
 #ifdef CONFIG_XEN_EFI
 extern void xen_efi_init(void);
 #else
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index e5b872ba2484..3bd3504a6cc7 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -14,12 +14,15 @@ config XTENSA
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
+	select HAVE_DMA_API_DEBUG
+	select HAVE_DMA_ATTRS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
+	select PERF_USE_VMALLOC
 	select VIRT_TO_BUS
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
@@ -61,9 +64,7 @@ config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
 config MMU
-	bool
-	default n if !XTENSA_VARIANT_CUSTOM
-	default XTENSA_VARIANT_MMU if XTENSA_VARIANT_CUSTOM
+	def_bool n
 
 config VARIANT_IRQ_SWITCH
 	def_bool n
@@ -71,9 +72,6 @@ config VARIANT_IRQ_SWITCH
 config HAVE_XTENSA_GPIO32
 	def_bool n
 
-config MAY_HAVE_SMP
-	def_bool n
-
 menu "Processor type and features"
 
 choice
@@ -100,7 +98,6 @@ config XTENSA_VARIANT_DC233C
 
 config XTENSA_VARIANT_CUSTOM
 	bool "Custom Xtensa processor configuration"
-	select MAY_HAVE_SMP
 	select HAVE_XTENSA_GPIO32
 	help
 	  Select this variant to use a custom Xtensa processor configuration.
@@ -126,10 +123,21 @@ config XTENSA_VARIANT_MMU
 	bool "Core variant has a Full MMU (TLB, Pages, Protection, etc)"
 	depends on XTENSA_VARIANT_CUSTOM
 	default y
+	select MMU
 	help
 	  Build a Conventional Kernel with full MMU support,
 	  ie: it supports a TLB with auto-loading, page protection.
 
+config XTENSA_VARIANT_HAVE_PERF_EVENTS
+	bool "Core variant has Performance Monitor Module"
+	depends on XTENSA_VARIANT_CUSTOM
+	default n
+	help
+	  Enable if core variant has Performance Monitor Module with
+	  External Registers Interface.
+
+	  If unsure, say N.
+
 config XTENSA_UNALIGNED_USER
 	bool "Unaligned memory access in use space"
 	help
@@ -143,7 +151,7 @@ source "kernel/Kconfig.preempt"
 
 config HAVE_SMP
 	bool "System Supports SMP (MX)"
-	depends on MAY_HAVE_SMP
+	depends on XTENSA_VARIANT_CUSTOM
 	select XTENSA_MX
 	help
 	  This option is use to indicate that the system-on-a-chip (SOC)
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index e4d193e7a300..f3dfe0d921c2 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -616,7 +616,6 @@ CONFIG_SCHED_DEBUG=y
 # CONFIG_SLUB_DEBUG_ON is not set
 # CONFIG_SLUB_STATS is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
-# CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
 # CONFIG_DEBUG_MUTEXES is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 14d15bf1a95b..63c223dff5f1 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -2,7 +2,6 @@ generic-y += bitsperlong.h
 generic-y += bug.h
 generic-y += clkdev.h
 generic-y += cputime.h
-generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
@@ -19,6 +18,7 @@ generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += resource.h
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 00b7d46b35b8..93795d047303 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -29,7 +29,7 @@
  *
  * Locking interrupts looks like this:
  *
- *    rsil a15, LOCKLEVEL
+ *    rsil a15, TOPLEVEL
  *    <code>
  *    wsr  a15, PS
  *    rsync
@@ -106,7 +106,7 @@ static inline void atomic_##op(int i, atomic_t * v)			\
 	unsigned int vval;						\
 									\
 	__asm__ __volatile__(						\
-			"       rsil    a15, "__stringify(LOCKLEVEL)"\n"\
+			"       rsil    a15, "__stringify(TOPLEVEL)"\n"\
 			"       l32i    %0, %2, 0\n"			\
 			"       " #op " %0, %0, %1\n"			\
 			"       s32i    %0, %2, 0\n"			\
@@ -124,7 +124,7 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 	unsigned int vval;						\
 									\
 	__asm__ __volatile__(						\
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"	\
+			"       rsil    a15,"__stringify(TOPLEVEL)"\n"	\
 			"       l32i    %0, %2, 0\n"			\
 			"       " #op " %0, %0, %1\n"			\
 			"       s32i    %0, %2, 0\n"			\
@@ -145,6 +145,10 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -250,75 +254,6 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       and     %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (~mask), "a" (v)
-			: "memory"
-			);
-#else
-	unsigned int all_f = -1;
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       xor     %1, %4, %3\n"
-			"       and     %0, %0, %4\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval), "=a" (mask)
-			: "a" (v), "a" (all_f), "1" (mask)
-			: "a15", "memory"
-			);
-#endif
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       or      %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (mask), "a" (v)
-			: "memory"
-			);
-#else
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       or      %0, %0, %1\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval)
-			: "a" (mask), "a" (v)
-			: "a15", "memory"
-			);
-#endif
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */
diff --git a/arch/xtensa/include/asm/cmpxchg.h b/arch/xtensa/include/asm/cmpxchg.h
index 370b26f38414..201e9009efd8 100644
--- a/arch/xtensa/include/asm/cmpxchg.h
+++ b/arch/xtensa/include/asm/cmpxchg.h
@@ -34,7 +34,7 @@ __cmpxchg_u32(volatile int *p, int old, int new)
 	return new;
 #else
 	__asm__ __volatile__(
-			"       rsil    a15, "__stringify(LOCKLEVEL)"\n"
+			"       rsil    a15, "__stringify(TOPLEVEL)"\n"
 			"       l32i    %0, %1, 0\n"
 			"       bne     %0, %2, 1f\n"
 			"       s32i    %3, %1, 0\n"
@@ -123,7 +123,7 @@ static inline unsigned long xchg_u32(volatile int * m, unsigned long val)
 #else
 	unsigned long tmp;
 	__asm__ __volatile__(
-			"       rsil    a15, "__stringify(LOCKLEVEL)"\n"
+			"       rsil    a15, "__stringify(TOPLEVEL)"\n"
 			"       l32i    %0, %1, 0\n"
 			"       s32i    %2, %1, 0\n"
 			"       wsr     a15, ps\n"
diff --git a/arch/xtensa/include/asm/device.h b/arch/xtensa/include/asm/device.h
new file mode 100644
index 000000000000..fe1f5c878493
--- /dev/null
+++ b/arch/xtensa/include/asm/device.h
@@ -0,0 +1,19 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef _ASM_XTENSA_DEVICE_H
+#define _ASM_XTENSA_DEVICE_H
+
+struct dma_map_ops;
+
+struct dev_archdata {
+	/* DMA operations on that device */
+	struct dma_map_ops *dma_ops;
+};
+
+struct pdev_archdata {
+};
+
+#endif /* _ASM_XTENSA_DEVICE_H */
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 1f5f6dc09736..f01cb3044e50 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -1,11 +1,10 @@
 /*
- * include/asm-xtensa/dma-mapping.h
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
  * Copyright (C) 2003 - 2005 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  */
 
 #ifndef _XTENSA_DMA_MAPPING_H
@@ -13,142 +12,67 @@
 
 #include <asm/cache.h>
 #include <asm/io.h>
+
+#include <asm-generic/dma-coherent.h>
+
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 
 #define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
 
-/*
- * DMA-consistent mapping functions.
- */
-
-extern void *consistent_alloc(int, size_t, dma_addr_t, unsigned long);
-extern void consistent_free(void*, size_t, dma_addr_t);
-extern void consistent_sync(void*, size_t, int);
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag);
+extern struct dma_map_ops xtensa_dma_map_ops;
 
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle);
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	consistent_sync(ptr, size, direction);
-	return virt_to_phys(ptr);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	BUG_ON(direction == DMA_NONE);
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	else
+		return &xtensa_dma_map_ops;
 }
 
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	   enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
-
-	for_each_sg(sglist, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
+#include <asm-generic/dma-mapping-common.h>
 
-		sg->dma_address = sg_phys(sg);
-		consistent_sync(sg_virt(sg), sg->length, direction);
-	}
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+#define dma_free_noncoherent(d, s, v, h) dma_free_attrs(d, s, v, h, NULL)
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
 
-	return nents;
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	return (dma_addr_t)(page_to_pfn(page)) * PAGE_SIZE + offset;
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t gfp,
+				    struct dma_attrs *attrs)
 {
-	BUG_ON(direction == DMA_NONE);
-}
+	void *ret;
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
+		return ret;
 
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	consistent_sync((void *)bus_to_virt(dma_handle), size, direction);
-}
+	ret = ops->alloc(dev, size, dma_handle, gfp, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
 
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-		           size_t size, enum dma_data_direction direction)
-{
-	consistent_sync((void *)bus_to_virt(dma_handle), size, direction);
+	return ret;
 }
 
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-
-	consistent_sync((void *)bus_to_virt(dma_handle)+offset,size,direction);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
-	consistent_sync((void *)bus_to_virt(dma_handle)+offset,size,direction);
-}
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
-		 enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
 
-	for_each_sg(sglist, sg, nelems, i)
-		consistent_sync(sg_virt(sg), sg->length, dir);
+	ops->free(dev, size, vaddr, dma_handle, attrs);
+	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
 }
 
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-		       int nelems, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		consistent_sync(sg_virt(sg), sg->length, dir);
-}
 static inline int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	return 0;
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	debug_dma_mapping_error(dev, dma_addr);
+	return ops->mapping_error(dev, dma_addr);
 }
 
 static inline int
@@ -168,39 +92,7 @@ dma_set_mask(struct device *dev, u64 mask)
 	return 0;
 }
 
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	consistent_sync(vaddr, size, direction);
-}
-
-/* Not supported for now */
-static inline int dma_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma, void *cpu_addr,
-				    dma_addr_t dma_addr, size_t size)
-{
-	return -EINVAL;
-}
-
-static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size)
-{
-	return -EINVAL;
-}
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flag,
-				    struct dma_attrs *attrs)
-{
-	return NULL;
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle,
-				  struct dma_attrs *attrs)
-{
-}
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction direction);
 
 #endif	/* _XTENSA_DMA_MAPPING_H */
diff --git a/arch/xtensa/include/asm/irqflags.h b/arch/xtensa/include/asm/irqflags.h
index ea36674c6ec5..8e090c709046 100644
--- a/arch/xtensa/include/asm/irqflags.h
+++ b/arch/xtensa/include/asm/irqflags.h
@@ -6,6 +6,7 @@
  * for more details.
  *
  * Copyright (C) 2001 - 2005 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  */
 
 #ifndef _XTENSA_IRQFLAGS_H
@@ -23,8 +24,27 @@ static inline unsigned long arch_local_save_flags(void)
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
-	asm volatile("rsil %0, "__stringify(LOCKLEVEL)
+#if XTENSA_FAKE_NMI
+#if defined(CONFIG_DEBUG_KERNEL) && (LOCKLEVEL | TOPLEVEL) >= XCHAL_DEBUGLEVEL
+	unsigned long tmp;
+
+	asm volatile("rsr	%0, ps\t\n"
+		     "extui	%1, %0, 0, 4\t\n"
+		     "bgei	%1, "__stringify(LOCKLEVEL)", 1f\t\n"
+		     "rsil	%0, "__stringify(LOCKLEVEL)"\n"
+		     "1:"
+		     : "=a" (flags), "=a" (tmp) :: "memory");
+#else
+	asm volatile("rsr	%0, ps\t\n"
+		     "or	%0, %0, %1\t\n"
+		     "xsr	%0, ps\t\n"
+		     "rsync"
+		     : "=&a" (flags) : "a" (LOCKLEVEL) : "memory");
+#endif
+#else
+	asm volatile("rsil	%0, "__stringify(LOCKLEVEL)
 		     : "=a" (flags) :: "memory");
+#endif
 	return flags;
 }
 
diff --git a/arch/xtensa/include/asm/mm-arch-hooks.h b/arch/xtensa/include/asm/mm-arch-hooks.h
deleted file mode 100644
index d2e5cfd3dd02..000000000000
--- a/arch/xtensa/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_XTENSA_MM_ARCH_HOOKS_H
-#define _ASM_XTENSA_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_XTENSA_MM_ARCH_HOOKS_H */
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index b61bdf0eea25..83e2e4bc01ba 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -1,11 +1,10 @@
 /*
- * include/asm-xtensa/processor.h
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
  * Copyright (C) 2001 - 2008 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  */
 
 #ifndef _XTENSA_PROCESSOR_H
@@ -45,6 +44,14 @@
 #define STACK_TOP_MAX	STACK_TOP
 
 /*
+ * General exception cause assigned to fake NMI. Fake NMI needs to be handled
+ * differently from other interrupts, but it uses common kernel entry/exit
+ * code.
+ */
+
+#define EXCCAUSE_MAPPED_NMI	62
+
+/*
  * General exception cause assigned to debug exceptions. Debug exceptions go
  * to their own vector, rather than the general exception vectors (user,
  * kernel, double); and their specific causes are reported via DEBUGCAUSE
@@ -65,10 +72,30 @@
 
 #define VALID_DOUBLE_EXCEPTION_ADDRESS	64
 
+#define XTENSA_INT_LEVEL(intno) _XTENSA_INT_LEVEL(intno)
+#define _XTENSA_INT_LEVEL(intno) XCHAL_INT##intno##_LEVEL
+
+#define XTENSA_INTLEVEL_MASK(level) _XTENSA_INTLEVEL_MASK(level)
+#define _XTENSA_INTLEVEL_MASK(level) (XCHAL_INTLEVEL##level##_MASK)
+
+#define IS_POW2(v) (((v) & ((v) - 1)) == 0)
+
+#define PROFILING_INTLEVEL XTENSA_INT_LEVEL(XCHAL_PROFILING_INTERRUPT)
+
 /* LOCKLEVEL defines the interrupt level that masks all
  * general-purpose interrupts.
  */
+#if defined(CONFIG_XTENSA_VARIANT_HAVE_PERF_EVENTS) && \
+	defined(XCHAL_PROFILING_INTERRUPT) && \
+	PROFILING_INTLEVEL == XCHAL_EXCM_LEVEL && \
+	XCHAL_EXCM_LEVEL > 1 && \
+	IS_POW2(XTENSA_INTLEVEL_MASK(PROFILING_INTLEVEL))
+#define LOCKLEVEL (XCHAL_EXCM_LEVEL - 1)
+#else
 #define LOCKLEVEL XCHAL_EXCM_LEVEL
+#endif
+#define TOPLEVEL XCHAL_EXCM_LEVEL
+#define XTENSA_FAKE_NMI (LOCKLEVEL < TOPLEVEL)
 
 /* WSBITS and WBBITS are the width of the WINDOWSTART and WINDOWBASE
  * registers
diff --git a/arch/xtensa/include/asm/stacktrace.h b/arch/xtensa/include/asm/stacktrace.h
index 6a05fcb0a20d..fe06e8ed162b 100644
--- a/arch/xtensa/include/asm/stacktrace.h
+++ b/arch/xtensa/include/asm/stacktrace.h
@@ -33,4 +33,12 @@ void walk_stackframe(unsigned long *sp,
 		int (*fn)(struct stackframe *frame, void *data),
 		void *data);
 
+void xtensa_backtrace_kernel(struct pt_regs *regs, unsigned int depth,
+			     int (*kfn)(struct stackframe *frame, void *data),
+			     int (*ufn)(struct stackframe *frame, void *data),
+			     void *data);
+void xtensa_backtrace_user(struct pt_regs *regs, unsigned int depth,
+			   int (*ufn)(struct stackframe *frame, void *data),
+			   void *data);
+
 #endif /* _XTENSA_STACKTRACE_H */
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 677bfcf4ee5d..28f33a8b7f5f 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -25,30 +25,39 @@ static inline void spill_registers(void)
 {
 #if XCHAL_NUM_AREGS > 16
 	__asm__ __volatile__ (
-		"	call12	1f\n"
+		"	call8	1f\n"
 		"	_j	2f\n"
 		"	retw\n"
 		"	.align	4\n"
 		"1:\n"
+#if XCHAL_NUM_AREGS == 32
+		"	_entry	a1, 32\n"
+		"	addi	a8, a0, 3\n"
+		"	_entry	a1, 16\n"
+		"	mov	a12, a12\n"
+		"	retw\n"
+#else
 		"	_entry	a1, 48\n"
-		"	addi	a12, a0, 3\n"
-#if XCHAL_NUM_AREGS > 32
-		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+		"	call12	1f\n"
+		"	retw\n"
+		"	.align	4\n"
+		"1:\n"
+		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 16) / 12\n"
 		"	_entry	a1, 48\n"
 		"	mov	a12, a0\n"
 		"	.endr\n"
-#endif
-		"	_entry	a1, 48\n"
+		"	_entry	a1, 16\n"
 #if XCHAL_NUM_AREGS % 12 == 0
-		"	mov	a8, a8\n"
-#elif XCHAL_NUM_AREGS % 12 == 4
 		"	mov	a12, a12\n"
-#elif XCHAL_NUM_AREGS % 12 == 8
+#elif XCHAL_NUM_AREGS % 12 == 4
 		"	mov	a4, a4\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+		"	mov	a8, a8\n"
 #endif
 		"	retw\n"
+#endif
 		"2:\n"
-		: : : "a12", "a13", "memory");
+		: : : "a8", "a9", "memory");
 #else
 	__asm__ __volatile__ (
 		"	mov	a12, a12\n"
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index d3a0f0fd56dd..50137bc9e150 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_PCI) += pci.o
 obj-$(CONFIG_MODULES) += xtensa_ksyms.o module.o
 obj-$(CONFIG_FUNCTION_TRACER) += mcount.o
 obj-$(CONFIG_SMP) += smp.o mxhead.o
+obj-$(CONFIG_XTENSA_VARIANT_HAVE_PERF_EVENTS) += perf_event.o
 
 AFLAGS_head.o += -mtext-section-literals
 
@@ -27,10 +28,11 @@ AFLAGS_head.o += -mtext-section-literals
 #
 # Replicate rules in scripts/Makefile.build
 
-sed-y = -e 's/\*(\(\.[a-z]*it\|\.ref\|\)\.text)/*(\1.literal \1.text)/g' \
-	-e 's/\.text\.unlikely/.literal.unlikely .text.unlikely/g'	 \
-	-e 's/\*(\(\.text .*\))/*(.literal \1)/g'			 \
-	-e 's/\*(\(\.text\.[a-z]*\))/*(\1.literal \1)/g'
+sed-y = -e ':a; s/\*(\([^)]*\)\.text\.unlikely/*(\1.literal.unlikely .{text}.unlikely/; ta; ' \
+	-e ':b; s/\*(\([^)]*\)\.text\(\.[a-z]*\)/*(\1.{text}\2.literal .{text}\2/; tb; ' \
+	-e ':c; s/\*(\([^)]*\)\(\.[a-z]*it\|\.ref\)\.text/*(\1\2.literal \2.{text}/; tc; ' \
+	-e ':d; s/\*(\([^)]\+ \|\)\.text/*(\1.literal .{text}/; td; ' \
+	-e 's/\.{text}/.text/g'
 
 quiet_cmd__cpp_lds_S = LDS     $@
 cmd__cpp_lds_S = $(CPP) $(cpp_flags) -P -C -Uxtensa -D__ASSEMBLY__ $<    \
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 82bbfa5a05b3..504130357597 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1,6 +1,4 @@
 /*
- * arch/xtensa/kernel/entry.S
- *
  * Low-level exception handling
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -8,6 +6,7 @@
  * for more details.
  *
  * Copyright (C) 2004 - 2008 by Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  *
  * Chris Zankel <chris@zankel.net>
  *
@@ -75,6 +74,27 @@
 #endif
 	.endm
 
+
+	.macro	irq_save flags tmp
+#if XTENSA_FAKE_NMI
+#if defined(CONFIG_DEBUG_KERNEL) && (LOCKLEVEL | TOPLEVEL) >= XCHAL_DEBUGLEVEL
+	rsr	\flags, ps
+	extui	\tmp, \flags, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH
+	bgei	\tmp, LOCKLEVEL, 99f
+	rsil	\tmp, LOCKLEVEL
+99:
+#else
+	movi	\tmp, LOCKLEVEL
+	rsr	\flags, ps
+	or	\flags, \flags, \tmp
+	xsr	\flags, ps
+	rsync
+#endif
+#else
+	rsil	\flags, LOCKLEVEL
+#endif
+	.endm
+
 /* ----------------- DEFAULT FIRST LEVEL EXCEPTION HANDLERS ----------------- */
 
 /*
@@ -122,6 +142,7 @@ _user_exception:
 	/* Save SAR and turn off single stepping */
 
 	movi	a2, 0
+	wsr	a2, depc		# terminate user stack trace with 0
 	rsr	a3, sar
 	xsr	a2, icountlevel
 	s32i	a3, a1, PT_SAR
@@ -301,7 +322,18 @@ _kernel_exception:
 	s32i	a14, a1, PT_AREG14
 	s32i	a15, a1, PT_AREG15
 
+	_bnei	a2, 1, 1f
+
+	/* Copy spill slots of a0 and a1 to imitate movsp
+	 * in order to keep exception stack continuous
+	 */
+	l32i	a3, a1, PT_SIZE
+	l32i	a0, a1, PT_SIZE + 4
+	s32e	a3, a1, -16
+	s32e	a0, a1, -12
 1:
+	l32i	a0, a1, PT_AREG0	# restore saved a0
+	wsr	a0, depc
 
 #ifdef KERNEL_STACK_OVERFLOW_CHECK
 
@@ -340,75 +372,88 @@ common_exception:
 
 	/* It is now save to restore the EXC_TABLE_FIXUP variable. */
 
-	rsr	a0, exccause
+	rsr	a2, exccause
 	movi	a3, 0
-	rsr	a2, excsave1
-	s32i	a0, a1, PT_EXCCAUSE
-	s32i	a3, a2, EXC_TABLE_FIXUP
-
-	/* All unrecoverable states are saved on stack, now, and a1 is valid,
-	 * so we can allow exceptions and interrupts (*) again.
-	 * Set PS(EXCM = 0, UM = 0, RING = 0, OWB = 0, WOE = 1, INTLEVEL = X)
+	rsr	a0, excsave1
+	s32i	a2, a1, PT_EXCCAUSE
+	s32i	a3, a0, EXC_TABLE_FIXUP
+
+	/* All unrecoverable states are saved on stack, now, and a1 is valid.
+	 * Now we can allow exceptions again. In case we've got an interrupt
+	 * PS.INTLEVEL is set to LOCKLEVEL disabling furhter interrupts,
+	 * otherwise it's left unchanged.
 	 *
-	 * (*) We only allow interrupts if they were previously enabled and
-	 *     we're not handling an IRQ
+	 * Set PS(EXCM = 0, UM = 0, RING = 0, OWB = 0, WOE = 1, INTLEVEL = X)
 	 */
 
 	rsr	a3, ps
-	addi	a0, a0, -EXCCAUSE_LEVEL1_INTERRUPT
-	movi	a2, LOCKLEVEL
+	s32i	a3, a1, PT_PS		# save ps
+
+#if XTENSA_FAKE_NMI
+	/* Correct PS needs to be saved in the PT_PS:
+	 * - in case of exception or level-1 interrupt it's in the PS,
+	 *   and is already saved.
+	 * - in case of medium level interrupt it's in the excsave2.
+	 */
+	movi	a0, EXCCAUSE_MAPPED_NMI
+	extui	a3, a3, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH
+	beq	a2, a0, .Lmedium_level_irq
+	bnei	a2, EXCCAUSE_LEVEL1_INTERRUPT, .Lexception
+	beqz	a3, .Llevel1_irq	# level-1 IRQ sets ps.intlevel to 0
+
+.Lmedium_level_irq:
+	rsr	a0, excsave2
+	s32i	a0, a1, PT_PS		# save medium-level interrupt ps
+	bgei	a3, LOCKLEVEL, .Lexception
+
+.Llevel1_irq:
+	movi	a3, LOCKLEVEL
+
+.Lexception:
+	movi	a0, 1 << PS_WOE_BIT
+	or	a3, a3, a0
+#else
+	addi	a2, a2, -EXCCAUSE_LEVEL1_INTERRUPT
+	movi	a0, LOCKLEVEL
 	extui	a3, a3, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH
 					# a3 = PS.INTLEVEL
-	moveqz	a3, a2, a0		# a3 = LOCKLEVEL iff interrupt
+	moveqz	a3, a0, a2		# a3 = LOCKLEVEL iff interrupt
 	movi	a2, 1 << PS_WOE_BIT
 	or	a3, a3, a2
-	rsr	a0, exccause
-	xsr	a3, ps
+	rsr	a2, exccause
+#endif
 
-	s32i	a3, a1, PT_PS		# save ps
+	/* restore return address (or 0 if return to userspace) */
+	rsr	a0, depc
+	wsr	a3, ps
+	rsync				# PS.WOE => rsync => overflow
 
 	/* Save lbeg, lend */
 
-	rsr	a2, lbeg
+	rsr	a4, lbeg
 	rsr	a3, lend
-	s32i	a2, a1, PT_LBEG
+	s32i	a4, a1, PT_LBEG
 	s32i	a3, a1, PT_LEND
 
 	/* Save SCOMPARE1 */
 
 #if XCHAL_HAVE_S32C1I
-	rsr     a2, scompare1
-	s32i    a2, a1, PT_SCOMPARE1
+	rsr     a3, scompare1
+	s32i    a3, a1, PT_SCOMPARE1
 #endif
 
 	/* Save optional registers. */
 
-	save_xtregs_opt a1 a2 a4 a5 a6 a7 PT_XTREGS_OPT
+	save_xtregs_opt a1 a3 a4 a5 a6 a7 PT_XTREGS_OPT
 	
-#ifdef CONFIG_TRACE_IRQFLAGS
-	l32i	a4, a1, PT_DEPC
-	/* Double exception means we came here with an exception
-	 * while PS.EXCM was set, i.e. interrupts disabled.
-	 */
-	bgeui	a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
-	l32i	a4, a1, PT_EXCCAUSE
-	bnei	a4, EXCCAUSE_LEVEL1_INTERRUPT, 1f
-	/* We came here with an interrupt means interrupts were enabled
-	 * and we've just disabled them.
-	 */
-	movi	a4, trace_hardirqs_off
-	callx4	a4
-1:
-#endif
-
 	/* Go to second-level dispatcher. Set up parameters to pass to the
 	 * exception handler and call the exception handler.
 	 */
 
 	rsr	a4, excsave1
 	mov	a6, a1			# pass stack frame
-	mov	a7, a0			# pass EXCCAUSE
-	addx4	a4, a0, a4
+	mov	a7, a2			# pass EXCCAUSE
+	addx4	a4, a2, a4
 	l32i	a4, a4, EXC_TABLE_DEFAULT		# load handler
 
 	/* Call the second-level handler */
@@ -419,8 +464,17 @@ common_exception:
 	.global common_exception_return
 common_exception_return:
 
+#if XTENSA_FAKE_NMI
+	l32i	a2, a1, PT_EXCCAUSE
+	movi	a3, EXCCAUSE_MAPPED_NMI
+	beq	a2, a3, .LNMIexit
+#endif
 1:
-	rsil	a2, LOCKLEVEL
+	irq_save a2, a3
+#ifdef CONFIG_TRACE_IRQFLAGS
+	movi	a4, trace_hardirqs_off
+	callx4	a4
+#endif
 
 	/* Jump if we are returning from kernel exceptions. */
 
@@ -445,6 +499,10 @@ common_exception_return:
 
 	/* Call do_signal() */
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	movi	a4, trace_hardirqs_on
+	callx4	a4
+#endif
 	rsil	a2, 0
 	movi	a4, do_notify_resume	# int do_notify_resume(struct pt_regs*)
 	mov	a6, a1
@@ -453,6 +511,10 @@ common_exception_return:
 
 3:	/* Reschedule */
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	movi	a4, trace_hardirqs_on
+	callx4	a4
+#endif
 	rsil	a2, 0
 	movi	a4, schedule	# void schedule (void)
 	callx4	a4
@@ -471,6 +533,12 @@ common_exception_return:
 	j	1b
 #endif
 
+#if XTENSA_FAKE_NMI
+.LNMIexit:
+	l32i	a3, a1, PT_PS
+	_bbci.l	a3, PS_UM_BIT, 4f
+#endif
+
 5:
 #ifdef CONFIG_DEBUG_TLB_SANITY
 	l32i	a4, a1, PT_DEPC
@@ -481,16 +549,8 @@ common_exception_return:
 6:
 4:
 #ifdef CONFIG_TRACE_IRQFLAGS
-	l32i	a4, a1, PT_DEPC
-	/* Double exception means we came here with an exception
-	 * while PS.EXCM was set, i.e. interrupts disabled.
-	 */
-	bgeui	a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
-	l32i	a4, a1, PT_EXCCAUSE
-	bnei	a4, EXCCAUSE_LEVEL1_INTERRUPT, 1f
-	/* We came here with an interrupt means interrupts were enabled
-	 * and we'll reenable them on return.
-	 */
+	extui	a4, a3, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH
+	bgei	a4, LOCKLEVEL, 1f
 	movi	a4, trace_hardirqs_on
 	callx4	a4
 1:
@@ -568,12 +628,13 @@ user_exception_exit:
 	 *	 (if we have restored WSBITS-1 frames).
 	 */
 
+2:
 #if XCHAL_HAVE_THREADPTR
 	l32i	a3, a1, PT_THREADPTR
 	wur	a3, threadptr
 #endif
 
-2:	j	common_exception_exit
+	j	common_exception_exit
 
 	/* This is the kernel exception exit.
 	 * We avoided to do a MOVSP when we entered the exception, but we
@@ -1561,6 +1622,13 @@ ENTRY(fast_second_level_miss)
 	rfde
 
 9:	l32i	a0, a1, TASK_ACTIVE_MM	# unlikely case mm == 0
+	bnez	a0, 8b
+
+	/* Even more unlikely case active_mm == 0.
+	 * We can get here with NMI in the middle of context_switch that
+	 * touches vmalloc area.
+	 */
+	movi	a0, init_mm
 	j	8b
 
 #if (DCACHE_WAY_SIZE > PAGE_SIZE)
@@ -1820,7 +1888,7 @@ ENDPROC(system_call)
 	mov	a12, a0
 	.endr
 #endif
-	_entry	a1, 48
+	_entry	a1, 16
 #if XCHAL_NUM_AREGS % 12 == 0
 	mov	a8, a8
 #elif XCHAL_NUM_AREGS % 12 == 4
@@ -1844,7 +1912,7 @@ ENDPROC(system_call)
 
 ENTRY(_switch_to)
 
-	entry	a1, 16
+	entry	a1, 48
 
 	mov	a11, a3			# and 'next' (a3)
 
@@ -1864,10 +1932,8 @@ ENTRY(_switch_to)
 
 	/* Disable ints while we manipulate the stack pointer. */
 
-	rsil	a14, LOCKLEVEL
-	rsr	a3, excsave1
+	irq_save a14, a3
 	rsync
-	s32i	a3, a3, EXC_TABLE_FIXUP	/* enter critical section */
 
 	/* Switch CPENABLE */
 
@@ -1888,9 +1954,7 @@ ENTRY(_switch_to)
 	 */
 
 	rsr	a3, excsave1		# exc_table
-	movi	a6, 0
 	addi	a7, a5, PT_REGS_OFFSET
-	s32i	a6, a3, EXC_TABLE_FIXUP
 	s32i	a7, a3, EXC_TABLE_KSTK
 
 	/* restore context of the task 'next' */
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 3eee94f621eb..4ac3d23161cf 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -28,7 +28,7 @@
 #include <asm/uaccess.h>
 #include <asm/platform.h>
 
-atomic_t irq_err_count;
+DECLARE_PER_CPU(unsigned long, nmi_count);
 
 asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
 {
@@ -57,11 +57,16 @@ asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
+	unsigned cpu __maybe_unused;
 #ifdef CONFIG_SMP
 	show_ipi_list(p, prec);
 #endif
-	seq_printf(p, "%*s: ", prec, "ERR");
-	seq_printf(p, "%10u\n", atomic_read(&irq_err_count));
+#if XTENSA_FAKE_NMI
+	seq_printf(p, "%*s:", prec, "NMI");
+	for_each_online_cpu(cpu)
+		seq_printf(p, " %10lu", per_cpu(nmi_count, cpu));
+	seq_puts(p, "   Non-maskable interrupts\n");
+#endif
 	return 0;
 }
 
@@ -106,6 +111,12 @@ int xtensa_irq_map(struct irq_domain *d, unsigned int irq,
 		irq_set_chip_and_handler_name(irq, irq_chip,
 				handle_percpu_irq, "timer");
 		irq_clear_status_flags(irq, IRQ_LEVEL);
+#ifdef XCHAL_INTTYPE_MASK_PROFILING
+	} else if (mask & XCHAL_INTTYPE_MASK_PROFILING) {
+		irq_set_chip_and_handler_name(irq, irq_chip,
+				handle_percpu_irq, "profiling");
+		irq_set_status_flags(irq, IRQ_LEVEL);
+#endif
 	} else {/* XCHAL_INTTYPE_MASK_WRITE_ERROR */
 		/* XCHAL_INTTYPE_MASK_NMI */
 		irq_set_chip_and_handler_name(irq, irq_chip,
@@ -166,23 +177,25 @@ void migrate_irqs(void)
 
 	for_each_active_irq(i) {
 		struct irq_data *data = irq_get_irq_data(i);
+		struct cpumask *mask;
 		unsigned int newcpu;
 
 		if (irqd_is_per_cpu(data))
 			continue;
 
-		if (!cpumask_test_cpu(cpu, data->affinity))
+		mask = irq_data_get_affinity_mask(data);
+		if (!cpumask_test_cpu(cpu, mask))
 			continue;
 
-		newcpu = cpumask_any_and(data->affinity, cpu_online_mask);
+		newcpu = cpumask_any_and(mask, cpu_online_mask);
 
 		if (newcpu >= nr_cpu_ids) {
 			pr_info_ratelimited("IRQ%u no longer affine to CPU%u\n",
 					    i, cpu);
 
-			cpumask_setall(data->affinity);
+			cpumask_setall(mask);
 		}
-		irq_set_affinity(i, data->affinity);
+		irq_set_affinity(i, mask);
 	}
 }
 #endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index e8b76b8e4b29..fb75ebf1463a 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -1,6 +1,4 @@
 /*
- * arch/xtensa/kernel/pci-dma.c
- *
  * DMA coherent memory allocation.
  *
  * This program is free software; you can redistribute  it and/or modify it
@@ -9,6 +7,7 @@
  * option) any later version.
  *
  * Copyright (C) 2002 - 2005 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  *
  * Based on version for i386.
  *
@@ -25,13 +24,107 @@
 #include <asm/io.h>
 #include <asm/cacheflush.h>
 
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		__flush_invalidate_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		__invalidate_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_TO_DEVICE:
+		__flush_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_NONE:
+		BUG();
+		break;
+	}
+}
+EXPORT_SYMBOL(dma_cache_sync);
+
+static void xtensa_sync_single_for_cpu(struct device *dev,
+				       dma_addr_t dma_handle, size_t size,
+				       enum dma_data_direction dir)
+{
+	void *vaddr;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+	case DMA_FROM_DEVICE:
+		vaddr = bus_to_virt(dma_handle);
+		__invalidate_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_NONE:
+		BUG();
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void xtensa_sync_single_for_device(struct device *dev,
+					  dma_addr_t dma_handle, size_t size,
+					  enum dma_data_direction dir)
+{
+	void *vaddr;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+	case DMA_TO_DEVICE:
+		vaddr = bus_to_virt(dma_handle);
+		__flush_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_NONE:
+		BUG();
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void xtensa_sync_sg_for_cpu(struct device *dev,
+				   struct scatterlist *sg, int nents,
+				   enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		xtensa_sync_single_for_cpu(dev, sg_dma_address(s),
+					   sg_dma_len(s), dir);
+	}
+}
+
+static void xtensa_sync_sg_for_device(struct device *dev,
+				      struct scatterlist *sg, int nents,
+				      enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		xtensa_sync_single_for_device(dev, sg_dma_address(s),
+					      sg_dma_len(s), dir);
+	}
+}
+
 /*
  * Note: We assume that the full memory space is always mapped to 'kseg'
  *	 Otherwise we have to use page attributes (not implemented).
  */
 
-void *
-dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
+static void *xtensa_dma_alloc(struct device *dev, size_t size,
+			      dma_addr_t *handle, gfp_t flag,
+			      struct dma_attrs *attrs)
 {
 	unsigned long ret;
 	unsigned long uncached = 0;
@@ -52,20 +145,15 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
 	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
 	       ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
+	uncached = ret + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
+	*handle = virt_to_bus((void *)ret);
+	__invalidate_dcache_range(ret, size);
 
-	if (ret != 0) {
-		memset((void*) ret, 0, size);
-		uncached = ret+XCHAL_KSEG_BYPASS_VADDR-XCHAL_KSEG_CACHED_VADDR;
-		*handle = virt_to_bus((void*)ret);
-		__flush_invalidate_dcache_range(ret, size);
-	}
-
-	return (void*)uncached;
+	return (void *)uncached;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *hwdev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle)
+static void xtensa_dma_free(struct device *hwdev, size_t size, void *vaddr,
+			    dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	unsigned long addr = (unsigned long)vaddr +
 		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
@@ -75,24 +163,79 @@ void dma_free_coherent(struct device *hwdev, size_t size,
 
 	free_pages(addr, get_order(size));
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
+static dma_addr_t xtensa_map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	dma_addr_t dma_handle = page_to_phys(page) + offset;
+
+	BUG_ON(PageHighMem(page));
+	xtensa_sync_single_for_device(dev, dma_handle, size, dir);
+	return dma_handle;
+}
 
-void consistent_sync(void *vaddr, size_t size, int direction)
+static void xtensa_unmap_page(struct device *dev, dma_addr_t dma_handle,
+			      size_t size, enum dma_data_direction dir,
+			      struct dma_attrs *attrs)
 {
-	switch (direction) {
-	case PCI_DMA_NONE:
-		BUG();
-	case PCI_DMA_FROMDEVICE:        /* invalidate only */
-		__invalidate_dcache_range((unsigned long)vaddr,
-				          (unsigned long)size);
-		break;
+	xtensa_sync_single_for_cpu(dev, dma_handle, size, dir);
+}
 
-	case PCI_DMA_TODEVICE:          /* writeback only */
-	case PCI_DMA_BIDIRECTIONAL:     /* writeback and invalidate */
-		__flush_invalidate_dcache_range((unsigned long)vaddr,
-				    		(unsigned long)size);
-		break;
+static int xtensa_map_sg(struct device *dev, struct scatterlist *sg,
+			 int nents, enum dma_data_direction dir,
+			 struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		s->dma_address = xtensa_map_page(dev, sg_page(s), s->offset,
+						 s->length, dir, attrs);
+	}
+	return nents;
+}
+
+static void xtensa_unmap_sg(struct device *dev,
+			    struct scatterlist *sg, int nents,
+			    enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		xtensa_unmap_page(dev, sg_dma_address(s),
+				  sg_dma_len(s), dir, attrs);
 	}
 }
-EXPORT_SYMBOL(consistent_sync);
+
+int xtensa_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+struct dma_map_ops xtensa_dma_map_ops = {
+	.alloc = xtensa_dma_alloc,
+	.free = xtensa_dma_free,
+	.map_page = xtensa_map_page,
+	.unmap_page = xtensa_unmap_page,
+	.map_sg = xtensa_map_sg,
+	.unmap_sg = xtensa_unmap_sg,
+	.sync_single_for_cpu = xtensa_sync_single_for_cpu,
+	.sync_single_for_device = xtensa_sync_single_for_device,
+	.sync_sg_for_cpu = xtensa_sync_sg_for_cpu,
+	.sync_sg_for_device = xtensa_sync_sg_for_device,
+	.mapping_error = xtensa_dma_mapping_error,
+};
+EXPORT_SYMBOL(xtensa_dma_map_ops);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+
+static int __init xtensa_dma_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+fs_initcall(xtensa_dma_init);
diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c
index b848cc3dc913..d27b4dcf221f 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -210,10 +210,6 @@ subsys_initcall(pcibios_init);
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	if (bus->parent) {
-		/* This is a subordinate bridge */
-		pci_read_bridge_bases(bus);
-	}
 }
 
 void pcibios_set_master(struct pci_dev *dev)
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
new file mode 100644
index 000000000000..54f01188c29c
--- /dev/null
+++ b/arch/xtensa/kernel/perf_event.c
@@ -0,0 +1,454 @@
+/*
+ * Xtensa Performance Monitor Module driver
+ * See Tensilica Debug User's Guide for PMU registers documentation.
+ *
+ * Copyright (C) 2015 Cadence Design Systems Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+
+#include <asm/processor.h>
+#include <asm/stacktrace.h>
+
+/* Global control/status for all perf counters */
+#define XTENSA_PMU_PMG			0x1000
+/* Perf counter values */
+#define XTENSA_PMU_PM(i)		(0x1080 + (i) * 4)
+/* Perf counter control registers */
+#define XTENSA_PMU_PMCTRL(i)		(0x1100 + (i) * 4)
+/* Perf counter status registers */
+#define XTENSA_PMU_PMSTAT(i)		(0x1180 + (i) * 4)
+
+#define XTENSA_PMU_PMG_PMEN		0x1
+
+#define XTENSA_PMU_COUNTER_MASK		0xffffffffULL
+#define XTENSA_PMU_COUNTER_MAX		0x7fffffff
+
+#define XTENSA_PMU_PMCTRL_INTEN		0x00000001
+#define XTENSA_PMU_PMCTRL_KRNLCNT	0x00000008
+#define XTENSA_PMU_PMCTRL_TRACELEVEL	0x000000f0
+#define XTENSA_PMU_PMCTRL_SELECT_SHIFT	8
+#define XTENSA_PMU_PMCTRL_SELECT	0x00001f00
+#define XTENSA_PMU_PMCTRL_MASK_SHIFT	16
+#define XTENSA_PMU_PMCTRL_MASK		0xffff0000
+
+#define XTENSA_PMU_MASK(select, mask) \
+	(((select) << XTENSA_PMU_PMCTRL_SELECT_SHIFT) | \
+	 ((mask) << XTENSA_PMU_PMCTRL_MASK_SHIFT) | \
+	 XTENSA_PMU_PMCTRL_TRACELEVEL | \
+	 XTENSA_PMU_PMCTRL_INTEN)
+
+#define XTENSA_PMU_PMSTAT_OVFL		0x00000001
+#define XTENSA_PMU_PMSTAT_INTASRT	0x00000010
+
+struct xtensa_pmu_events {
+	/* Array of events currently on this core */
+	struct perf_event *event[XCHAL_NUM_PERF_COUNTERS];
+	/* Bitmap of used hardware counters */
+	unsigned long used_mask[BITS_TO_LONGS(XCHAL_NUM_PERF_COUNTERS)];
+};
+static DEFINE_PER_CPU(struct xtensa_pmu_events, xtensa_pmu_events);
+
+static const u32 xtensa_hw_ctl[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= XTENSA_PMU_MASK(0, 0x1),
+	[PERF_COUNT_HW_INSTRUCTIONS]		= XTENSA_PMU_MASK(2, 0xffff),
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= XTENSA_PMU_MASK(10, 0x1),
+	[PERF_COUNT_HW_CACHE_MISSES]		= XTENSA_PMU_MASK(12, 0x1),
+	/* Taken and non-taken branches + taken loop ends */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= XTENSA_PMU_MASK(2, 0x490),
+	/* Instruction-related + other global stall cycles */
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= XTENSA_PMU_MASK(4, 0x1ff),
+	/* Data-related global stall cycles */
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= XTENSA_PMU_MASK(3, 0x1ff),
+};
+
+#define C(_x) PERF_COUNT_HW_CACHE_##_x
+
+static const u32 xtensa_cache_ctl[][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= XTENSA_PMU_MASK(10, 0x1),
+			[C(RESULT_MISS)]	= XTENSA_PMU_MASK(10, 0x2),
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= XTENSA_PMU_MASK(11, 0x1),
+			[C(RESULT_MISS)]	= XTENSA_PMU_MASK(11, 0x2),
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= XTENSA_PMU_MASK(8, 0x1),
+			[C(RESULT_MISS)]	= XTENSA_PMU_MASK(8, 0x2),
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= XTENSA_PMU_MASK(9, 0x1),
+			[C(RESULT_MISS)]	= XTENSA_PMU_MASK(9, 0x8),
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= XTENSA_PMU_MASK(7, 0x1),
+			[C(RESULT_MISS)]	= XTENSA_PMU_MASK(7, 0x8),
+		},
+	},
+};
+
+static int xtensa_pmu_cache_event(u64 config)
+{
+	unsigned int cache_type, cache_op, cache_result;
+	int ret;
+
+	cache_type = (config >>  0) & 0xff;
+	cache_op = (config >>  8) & 0xff;
+	cache_result = (config >> 16) & 0xff;
+
+	if (cache_type >= ARRAY_SIZE(xtensa_cache_ctl) ||
+	    cache_op >= C(OP_MAX) ||
+	    cache_result >= C(RESULT_MAX))
+		return -EINVAL;
+
+	ret = xtensa_cache_ctl[cache_type][cache_op][cache_result];
+
+	if (ret == 0)
+		return -EINVAL;
+
+	return ret;
+}
+
+static inline uint32_t xtensa_pmu_read_counter(int idx)
+{
+	return get_er(XTENSA_PMU_PM(idx));
+}
+
+static inline void xtensa_pmu_write_counter(int idx, uint32_t v)
+{
+	set_er(v, XTENSA_PMU_PM(idx));
+}
+
+static void xtensa_perf_event_update(struct perf_event *event,
+				     struct hw_perf_event *hwc, int idx)
+{
+	uint64_t prev_raw_count, new_raw_count;
+	int64_t delta;
+
+	do {
+		prev_raw_count = local64_read(&hwc->prev_count);
+		new_raw_count = xtensa_pmu_read_counter(event->hw.idx);
+	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+				 new_raw_count) != prev_raw_count);
+
+	delta = (new_raw_count - prev_raw_count) & XTENSA_PMU_COUNTER_MASK;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static bool xtensa_perf_event_set_period(struct perf_event *event,
+					 struct hw_perf_event *hwc, int idx)
+{
+	bool rc = false;
+	s64 left;
+
+	if (!is_sampling_event(event)) {
+		left = XTENSA_PMU_COUNTER_MAX;
+	} else {
+		s64 period = hwc->sample_period;
+
+		left = local64_read(&hwc->period_left);
+		if (left <= -period) {
+			left = period;
+			local64_set(&hwc->period_left, left);
+			hwc->last_period = period;
+			rc = true;
+		} else if (left <= 0) {
+			left += period;
+			local64_set(&hwc->period_left, left);
+			hwc->last_period = period;
+			rc = true;
+		}
+		if (left > XTENSA_PMU_COUNTER_MAX)
+			left = XTENSA_PMU_COUNTER_MAX;
+	}
+
+	local64_set(&hwc->prev_count, -left);
+	xtensa_pmu_write_counter(idx, -left);
+	perf_event_update_userpage(event);
+
+	return rc;
+}
+
+static void xtensa_pmu_enable(struct pmu *pmu)
+{
+	set_er(get_er(XTENSA_PMU_PMG) | XTENSA_PMU_PMG_PMEN, XTENSA_PMU_PMG);
+}
+
+static void xtensa_pmu_disable(struct pmu *pmu)
+{
+	set_er(get_er(XTENSA_PMU_PMG) & ~XTENSA_PMU_PMG_PMEN, XTENSA_PMU_PMG);
+}
+
+static int xtensa_pmu_event_init(struct perf_event *event)
+{
+	int ret;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		if (event->attr.config >= ARRAY_SIZE(xtensa_hw_ctl) ||
+		    xtensa_hw_ctl[event->attr.config] == 0)
+			return -EINVAL;
+		event->hw.config = xtensa_hw_ctl[event->attr.config];
+		return 0;
+
+	case PERF_TYPE_HW_CACHE:
+		ret = xtensa_pmu_cache_event(event->attr.config);
+		if (ret < 0)
+			return ret;
+		event->hw.config = ret;
+		return 0;
+
+	case PERF_TYPE_RAW:
+		/* Not 'previous counter' select */
+		if ((event->attr.config & XTENSA_PMU_PMCTRL_SELECT) ==
+		    (1 << XTENSA_PMU_PMCTRL_SELECT_SHIFT))
+			return -EINVAL;
+		event->hw.config = (event->attr.config &
+				    (XTENSA_PMU_PMCTRL_KRNLCNT |
+				     XTENSA_PMU_PMCTRL_TRACELEVEL |
+				     XTENSA_PMU_PMCTRL_SELECT |
+				     XTENSA_PMU_PMCTRL_MASK)) |
+			XTENSA_PMU_PMCTRL_INTEN;
+		return 0;
+
+	default:
+		return -ENOENT;
+	}
+}
+
+/*
+ * Starts/Stops a counter present on the PMU. The PMI handler
+ * should stop the counter when perf_event_overflow() returns
+ * !0. ->start() will be used to continue.
+ */
+static void xtensa_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		xtensa_perf_event_set_period(event, hwc, idx);
+	}
+
+	hwc->state = 0;
+
+	set_er(hwc->config, XTENSA_PMU_PMCTRL(idx));
+}
+
+static void xtensa_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		set_er(0, XTENSA_PMU_PMCTRL(idx));
+		set_er(get_er(XTENSA_PMU_PMSTAT(idx)),
+		       XTENSA_PMU_PMSTAT(idx));
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) &&
+	    !(event->hw.state & PERF_HES_UPTODATE)) {
+		xtensa_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+/*
+ * Adds/Removes a counter to/from the PMU, can be done inside
+ * a transaction, see the ->*_txn() methods.
+ */
+static int xtensa_pmu_add(struct perf_event *event, int flags)
+{
+	struct xtensa_pmu_events *ev = this_cpu_ptr(&xtensa_pmu_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (__test_and_set_bit(idx, ev->used_mask)) {
+		idx = find_first_zero_bit(ev->used_mask,
+					  XCHAL_NUM_PERF_COUNTERS);
+		if (idx == XCHAL_NUM_PERF_COUNTERS)
+			return -EAGAIN;
+
+		__set_bit(idx, ev->used_mask);
+		hwc->idx = idx;
+	}
+	ev->event[idx] = event;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		xtensa_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+	return 0;
+}
+
+static void xtensa_pmu_del(struct perf_event *event, int flags)
+{
+	struct xtensa_pmu_events *ev = this_cpu_ptr(&xtensa_pmu_events);
+
+	xtensa_pmu_stop(event, PERF_EF_UPDATE);
+	__clear_bit(event->hw.idx, ev->used_mask);
+	perf_event_update_userpage(event);
+}
+
+static void xtensa_pmu_read(struct perf_event *event)
+{
+	xtensa_perf_event_update(event, &event->hw, event->hw.idx);
+}
+
+static int callchain_trace(struct stackframe *frame, void *data)
+{
+	struct perf_callchain_entry *entry = data;
+
+	perf_callchain_store(entry, frame->pc);
+	return 0;
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
+{
+	xtensa_backtrace_kernel(regs, PERF_MAX_STACK_DEPTH,
+				callchain_trace, NULL, entry);
+}
+
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs)
+{
+	xtensa_backtrace_user(regs, PERF_MAX_STACK_DEPTH,
+			      callchain_trace, entry);
+}
+
+void perf_event_print_debug(void)
+{
+	unsigned long flags;
+	unsigned i;
+
+	local_irq_save(flags);
+	pr_info("CPU#%d: PMG: 0x%08lx\n", smp_processor_id(),
+		get_er(XTENSA_PMU_PMG));
+	for (i = 0; i < XCHAL_NUM_PERF_COUNTERS; ++i)
+		pr_info("PM%d: 0x%08lx, PMCTRL%d: 0x%08lx, PMSTAT%d: 0x%08lx\n",
+			i, get_er(XTENSA_PMU_PM(i)),
+			i, get_er(XTENSA_PMU_PMCTRL(i)),
+			i, get_er(XTENSA_PMU_PMSTAT(i)));
+	local_irq_restore(flags);
+}
+
+irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id)
+{
+	irqreturn_t rc = IRQ_NONE;
+	struct xtensa_pmu_events *ev = this_cpu_ptr(&xtensa_pmu_events);
+	unsigned i;
+
+	for (i = find_first_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS);
+	     i < XCHAL_NUM_PERF_COUNTERS;
+	     i = find_next_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS, i + 1)) {
+		uint32_t v = get_er(XTENSA_PMU_PMSTAT(i));
+		struct perf_event *event = ev->event[i];
+		struct hw_perf_event *hwc = &event->hw;
+		u64 last_period;
+
+		if (!(v & XTENSA_PMU_PMSTAT_OVFL))
+			continue;
+
+		set_er(v, XTENSA_PMU_PMSTAT(i));
+		xtensa_perf_event_update(event, hwc, i);
+		last_period = hwc->last_period;
+		if (xtensa_perf_event_set_period(event, hwc, i)) {
+			struct perf_sample_data data;
+			struct pt_regs *regs = get_irq_regs();
+
+			perf_sample_data_init(&data, 0, last_period);
+			if (perf_event_overflow(event, &data, regs))
+				xtensa_pmu_stop(event, 0);
+		}
+
+		rc = IRQ_HANDLED;
+	}
+	return rc;
+}
+
+static struct pmu xtensa_pmu = {
+	.pmu_enable = xtensa_pmu_enable,
+	.pmu_disable = xtensa_pmu_disable,
+	.event_init = xtensa_pmu_event_init,
+	.add = xtensa_pmu_add,
+	.del = xtensa_pmu_del,
+	.start = xtensa_pmu_start,
+	.stop = xtensa_pmu_stop,
+	.read = xtensa_pmu_read,
+};
+
+static void xtensa_pmu_setup(void)
+{
+	unsigned i;
+
+	set_er(0, XTENSA_PMU_PMG);
+	for (i = 0; i < XCHAL_NUM_PERF_COUNTERS; ++i) {
+		set_er(0, XTENSA_PMU_PMCTRL(i));
+		set_er(get_er(XTENSA_PMU_PMSTAT(i)), XTENSA_PMU_PMSTAT(i));
+	}
+}
+
+static int xtensa_pmu_notifier(struct notifier_block *self,
+			       unsigned long action, void *data)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		xtensa_pmu_setup();
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __init xtensa_pmu_init(void)
+{
+	int ret;
+	int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
+
+	perf_cpu_notifier(xtensa_pmu_notifier);
+#if XTENSA_FAKE_NMI
+	enable_irq(irq);
+#else
+	ret = request_irq(irq, xtensa_pmu_irq_handler, IRQF_PERCPU,
+			  "pmu", NULL);
+	if (ret < 0)
+		return ret;
+#endif
+
+	ret = perf_pmu_register(&xtensa_pmu, "cpu", PERF_TYPE_RAW);
+	if (ret)
+		free_irq(irq, NULL);
+
+	return ret;
+}
+early_initcall(xtensa_pmu_init);
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index 7d2c317bd98b..7538d802b65a 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -1,11 +1,12 @@
 /*
- * arch/xtensa/kernel/stacktrace.c
+ * Kernel and userspace stack tracing.
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
  * Copyright (C) 2001 - 2013 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  */
 #include <linux/export.h>
 #include <linux/sched.h>
@@ -13,6 +14,170 @@
 
 #include <asm/stacktrace.h>
 #include <asm/traps.h>
+#include <asm/uaccess.h>
+
+#if IS_ENABLED(CONFIG_OPROFILE) || IS_ENABLED(CONFIG_PERF_EVENTS)
+
+/* Address of common_exception_return, used to check the
+ * transition from kernel to user space.
+ */
+extern int common_exception_return;
+
+/* A struct that maps to the part of the frame containing the a0 and
+ * a1 registers.
+ */
+struct frame_start {
+	unsigned long a0;
+	unsigned long a1;
+};
+
+void xtensa_backtrace_user(struct pt_regs *regs, unsigned int depth,
+			   int (*ufn)(struct stackframe *frame, void *data),
+			   void *data)
+{
+	unsigned long windowstart = regs->windowstart;
+	unsigned long windowbase = regs->windowbase;
+	unsigned long a0 = regs->areg[0];
+	unsigned long a1 = regs->areg[1];
+	unsigned long pc = regs->pc;
+	struct stackframe frame;
+	int index;
+
+	if (!depth--)
+		return;
+
+	frame.pc = pc;
+	frame.sp = a1;
+
+	if (pc == 0 || pc >= TASK_SIZE || ufn(&frame, data))
+		return;
+
+	/* Two steps:
+	 *
+	 * 1. Look through the register window for the
+	 * previous PCs in the call trace.
+	 *
+	 * 2. Look on the stack.
+	 */
+
+	/* Step 1.  */
+	/* Rotate WINDOWSTART to move the bit corresponding to
+	 * the current window to the bit #0.
+	 */
+	windowstart = (windowstart << WSBITS | windowstart) >> windowbase;
+
+	/* Look for bits that are set, they correspond to
+	 * valid windows.
+	 */
+	for (index = WSBITS - 1; (index > 0) && depth; depth--, index--)
+		if (windowstart & (1 << index)) {
+			/* Get the PC from a0 and a1. */
+			pc = MAKE_PC_FROM_RA(a0, pc);
+			/* Read a0 and a1 from the
+			 * corresponding position in AREGs.
+			 */
+			a0 = regs->areg[index * 4];
+			a1 = regs->areg[index * 4 + 1];
+
+			frame.pc = pc;
+			frame.sp = a1;
+
+			if (pc == 0 || pc >= TASK_SIZE || ufn(&frame, data))
+				return;
+		}
+
+	/* Step 2. */
+	/* We are done with the register window, we need to
+	 * look through the stack.
+	 */
+	if (!depth)
+		return;
+
+	/* Start from the a1 register. */
+	/* a1 = regs->areg[1]; */
+	while (a0 != 0 && depth--) {
+		struct frame_start frame_start;
+		/* Get the location for a1, a0 for the
+		 * previous frame from the current a1.
+		 */
+		unsigned long *psp = (unsigned long *)a1;
+
+		psp -= 4;
+
+		/* Check if the region is OK to access. */
+		if (!access_ok(VERIFY_READ, psp, sizeof(frame_start)))
+			return;
+		/* Copy a1, a0 from user space stack frame. */
+		if (__copy_from_user_inatomic(&frame_start, psp,
+					      sizeof(frame_start)))
+			return;
+
+		pc = MAKE_PC_FROM_RA(a0, pc);
+		a0 = frame_start.a0;
+		a1 = frame_start.a1;
+
+		frame.pc = pc;
+		frame.sp = a1;
+
+		if (pc == 0 || pc >= TASK_SIZE || ufn(&frame, data))
+			return;
+	}
+}
+EXPORT_SYMBOL(xtensa_backtrace_user);
+
+void xtensa_backtrace_kernel(struct pt_regs *regs, unsigned int depth,
+			     int (*kfn)(struct stackframe *frame, void *data),
+			     int (*ufn)(struct stackframe *frame, void *data),
+			     void *data)
+{
+	unsigned long pc = regs->depc > VALID_DOUBLE_EXCEPTION_ADDRESS ?
+		regs->depc : regs->pc;
+	unsigned long sp_start, sp_end;
+	unsigned long a0 = regs->areg[0];
+	unsigned long a1 = regs->areg[1];
+
+	sp_start = a1 & ~(THREAD_SIZE - 1);
+	sp_end = sp_start + THREAD_SIZE;
+
+	/* Spill the register window to the stack first. */
+	spill_registers();
+
+	/* Read the stack frames one by one and create the PC
+	 * from the a0 and a1 registers saved there.
+	 */
+	while (a1 > sp_start && a1 < sp_end && depth--) {
+		struct stackframe frame;
+		unsigned long *psp = (unsigned long *)a1;
+
+		frame.pc = pc;
+		frame.sp = a1;
+
+		if (kernel_text_address(pc) && kfn(&frame, data))
+			return;
+
+		if (pc == (unsigned long)&common_exception_return) {
+			regs = (struct pt_regs *)a1;
+			if (user_mode(regs)) {
+				if (ufn == NULL)
+					return;
+				xtensa_backtrace_user(regs, depth, ufn, data);
+				return;
+			}
+			a0 = regs->areg[0];
+			a1 = regs->areg[1];
+			continue;
+		}
+
+		sp_start = a1;
+
+		pc = MAKE_PC_FROM_RA(a0, pc);
+		a0 = *(psp - 4);
+		a1 = *(psp - 3);
+	}
+}
+EXPORT_SYMBOL(xtensa_backtrace_kernel);
+
+#endif
 
 void walk_stackframe(unsigned long *sp,
 		int (*fn)(struct stackframe *frame, void *data),
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 2a1823de69cc..b97767dbc7c8 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -52,8 +52,6 @@ static struct clocksource ccount_clocksource = {
 
 static int ccount_timer_set_next_event(unsigned long delta,
 		struct clock_event_device *dev);
-static void ccount_timer_set_mode(enum clock_event_mode mode,
-		struct clock_event_device *evt);
 struct ccount_timer {
 	struct clock_event_device evt;
 	int irq_enabled;
@@ -77,35 +75,34 @@ static int ccount_timer_set_next_event(unsigned long delta,
 	return ret;
 }
 
-static void ccount_timer_set_mode(enum clock_event_mode mode,
-		struct clock_event_device *evt)
+/*
+ * There is no way to disable the timer interrupt at the device level,
+ * only at the intenable register itself. Since enable_irq/disable_irq
+ * calls are nested, we need to make sure that these calls are
+ * balanced.
+ */
+static int ccount_timer_shutdown(struct clock_event_device *evt)
+{
+	struct ccount_timer *timer =
+		container_of(evt, struct ccount_timer, evt);
+
+	if (timer->irq_enabled) {
+		disable_irq(evt->irq);
+		timer->irq_enabled = 0;
+	}
+	return 0;
+}
+
+static int ccount_timer_set_oneshot(struct clock_event_device *evt)
 {
 	struct ccount_timer *timer =
 		container_of(evt, struct ccount_timer, evt);
 
-	/*
-	 * There is no way to disable the timer interrupt at the device level,
-	 * only at the intenable register itself. Since enable_irq/disable_irq
-	 * calls are nested, we need to make sure that these calls are
-	 * balanced.
-	 */
-	switch (mode) {
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		if (timer->irq_enabled) {
-			disable_irq(evt->irq);
-			timer->irq_enabled = 0;
-		}
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_ONESHOT:
-		if (!timer->irq_enabled) {
-			enable_irq(evt->irq);
-			timer->irq_enabled = 1;
-		}
-	default:
-		break;
+	if (!timer->irq_enabled) {
+		enable_irq(evt->irq);
+		timer->irq_enabled = 1;
 	}
+	return 0;
 }
 
 static irqreturn_t timer_interrupt(int irq, void *dev_id);
@@ -126,7 +123,9 @@ void local_timer_setup(unsigned cpu)
 	clockevent->features = CLOCK_EVT_FEAT_ONESHOT;
 	clockevent->rating = 300;
 	clockevent->set_next_event = ccount_timer_set_next_event;
-	clockevent->set_mode = ccount_timer_set_mode;
+	clockevent->set_state_shutdown = ccount_timer_shutdown;
+	clockevent->set_state_oneshot = ccount_timer_set_oneshot;
+	clockevent->tick_resume = ccount_timer_set_oneshot;
 	clockevent->cpumask = cpumask_of(cpu);
 	clockevent->irq = irq_create_mapping(NULL, LINUX_TIMER_INT);
 	if (WARN(!clockevent->irq, "error: can't map timer irq"))
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 9d2f45f010ef..42d441f7898b 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -62,6 +62,7 @@ extern void fast_coprocessor(void);
 
 extern void do_illegal_instruction (struct pt_regs*);
 extern void do_interrupt (struct pt_regs*);
+extern void do_nmi(struct pt_regs *);
 extern void do_unaligned_user (struct pt_regs*);
 extern void do_multihit (struct pt_regs*, unsigned long);
 extern void do_page_fault (struct pt_regs*, unsigned long);
@@ -146,6 +147,9 @@ COPROCESSOR(6),
 #if XTENSA_HAVE_COPROCESSOR(7)
 COPROCESSOR(7),
 #endif
+#if XTENSA_FAKE_NMI
+{ EXCCAUSE_MAPPED_NMI,			0,		do_nmi },
+#endif
 { EXCCAUSE_MAPPED_DEBUG,		0,		do_debug },
 { -1, -1, 0 }
 
@@ -199,6 +203,28 @@ void do_multihit(struct pt_regs *regs, unsigned long exccause)
 
 extern void do_IRQ(int, struct pt_regs *);
 
+#if XTENSA_FAKE_NMI
+
+irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id);
+
+DEFINE_PER_CPU(unsigned long, nmi_count);
+
+void do_nmi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs;
+
+	if ((regs->ps & PS_INTLEVEL_MASK) < LOCKLEVEL)
+		trace_hardirqs_off();
+
+	old_regs = set_irq_regs(regs);
+	nmi_enter();
+	++*this_cpu_ptr(&nmi_count);
+	xtensa_pmu_irq_handler(0, NULL);
+	nmi_exit();
+	set_irq_regs(old_regs);
+}
+#endif
+
 void do_interrupt(struct pt_regs *regs)
 {
 	static const unsigned int_level_mask[] = {
@@ -211,8 +237,11 @@ void do_interrupt(struct pt_regs *regs)
 		XCHAL_INTLEVEL6_MASK,
 		XCHAL_INTLEVEL7_MASK,
 	};
-	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct pt_regs *old_regs;
+
+	trace_hardirqs_off();
 
+	old_regs = set_irq_regs(regs);
 	irq_enter();
 
 	for (;;) {
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index 1b397a902292..abcdb527f18a 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -627,7 +627,11 @@ ENTRY(_Level\level\()InterruptVector)
 	wsr	a0, excsave2
 	rsr	a0, epc\level
 	wsr	a0, epc1
+	.if	\level <= LOCKLEVEL
 	movi	a0, EXCCAUSE_LEVEL1_INTERRUPT
+	.else
+	movi	a0, EXCCAUSE_MAPPED_NMI
+	.endif
 	wsr	a0, exccause
 	rsr	a0, eps\level
 					# branch to user or kernel vector
@@ -682,11 +686,13 @@ ENDPROC(_WindowOverflow4)
 	.align 4
 _SimulateUserKernelVectorException:
 	addi	a0, a0, (1 << PS_EXCM_BIT)
+#if !XTENSA_FAKE_NMI
 	wsr	a0, ps
+#endif
 	bbsi.l	a0, PS_UM_BIT, 1f	# branch if user mode
-	rsr	a0, excsave2		# restore a0
+	xsr	a0, excsave2		# restore a0
 	j	_KernelExceptionVector	# simulate kernel vector exception
-1:	rsr	a0, excsave2		# restore a0
+1:	xsr	a0, excsave2		# restore a0
 	j	_UserExceptionVector	# simulate user vector exception
 #endif
 
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 83a44a33cfa1..c9784c1b18d8 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -15,6 +15,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/perf_event.h>
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
@@ -142,6 +143,12 @@ good_area:
 	}
 
 	up_read(&mm->mmap_sem);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+	if (flags & VM_FAULT_MAJOR)
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	else if (flags & VM_FAULT_MINOR)
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
 	return;
 
 	/* Something tried to access memory that isn't in our memory map..
diff --git a/arch/xtensa/oprofile/backtrace.c b/arch/xtensa/oprofile/backtrace.c
index 5f03a593d84f..8f952034e161 100644
--- a/arch/xtensa/oprofile/backtrace.c
+++ b/arch/xtensa/oprofile/backtrace.c
@@ -2,168 +2,26 @@
  * @file backtrace.c
  *
  * @remark Copyright 2008 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  * @remark Read the file COPYING
  *
  */
 
 #include <linux/oprofile.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
-#include <asm/traps.h>
+#include <asm/stacktrace.h>
 
-/* Address of common_exception_return, used to check the
- * transition from kernel to user space.
- */
-extern int common_exception_return;
-
-/* A struct that maps to the part of the frame containing the a0 and
- * a1 registers.
- */
-struct frame_start {
-	unsigned long a0;
-	unsigned long a1;
-};
-
-static void xtensa_backtrace_user(struct pt_regs *regs, unsigned int depth)
-{
-	unsigned long windowstart = regs->windowstart;
-	unsigned long windowbase = regs->windowbase;
-	unsigned long a0 = regs->areg[0];
-	unsigned long a1 = regs->areg[1];
-	unsigned long pc = MAKE_PC_FROM_RA(a0, regs->pc);
-	int index;
-
-	/* First add the current PC to the trace. */
-	if (pc != 0 && pc <= TASK_SIZE)
-		oprofile_add_trace(pc);
-	else
-		return;
-
-	/* Two steps:
-	 *
-	 * 1. Look through the register window for the
-	 * previous PCs in the call trace.
-	 *
-	 * 2. Look on the stack.
-	 */
-
-	/* Step 1.  */
-	/* Rotate WINDOWSTART to move the bit corresponding to
-	 * the current window to the bit #0.
-	 */
-	windowstart = (windowstart << WSBITS | windowstart) >> windowbase;
-
-	/* Look for bits that are set, they correspond to
-	 * valid windows.
-	 */
-	for (index = WSBITS - 1; (index > 0) && depth; depth--, index--)
-		if (windowstart & (1 << index)) {
-			/* Read a0 and a1 from the
-			 * corresponding position in AREGs.
-			 */
-			a0 = regs->areg[index * 4];
-			a1 = regs->areg[index * 4 + 1];
-			/* Get the PC from a0 and a1. */
-			pc = MAKE_PC_FROM_RA(a0, pc);
-
-			/* Add the PC to the trace. */
-			if (pc != 0 && pc <= TASK_SIZE)
-				oprofile_add_trace(pc);
-			else
-				return;
-		}
-
-	/* Step 2. */
-	/* We are done with the register window, we need to
-	 * look through the stack.
-	 */
-	if (depth > 0) {
-		/* Start from the a1 register. */
-		/* a1 = regs->areg[1]; */
-		while (a0 != 0 && depth--) {
-
-			struct frame_start frame_start;
-			/* Get the location for a1, a0 for the
-			 * previous frame from the current a1.
-			 */
-			unsigned long *psp = (unsigned long *)a1;
-			psp -= 4;
-
-			/* Check if the region is OK to access. */
-			if (!access_ok(VERIFY_READ, psp, sizeof(frame_start)))
-				return;
-			/* Copy a1, a0 from user space stack frame. */
-			if (__copy_from_user_inatomic(&frame_start, psp,
-						sizeof(frame_start)))
-				return;
-
-			a0 = frame_start.a0;
-			a1 = frame_start.a1;
-			pc = MAKE_PC_FROM_RA(a0, pc);
-
-			if (pc != 0 && pc <= TASK_SIZE)
-				oprofile_add_trace(pc);
-			else
-				return;
-		}
-	}
-}
-
-static void xtensa_backtrace_kernel(struct pt_regs *regs, unsigned int depth)
+static int xtensa_backtrace_cb(struct stackframe *frame, void *data)
 {
-	unsigned long pc = regs->pc;
-	unsigned long *psp;
-	unsigned long sp_start, sp_end;
-	unsigned long a0 = regs->areg[0];
-	unsigned long a1 = regs->areg[1];
-
-	sp_start = a1 & ~(THREAD_SIZE-1);
-	sp_end = sp_start + THREAD_SIZE;
-
-	/* Spill the register window to the stack first. */
-	spill_registers();
-
-	/* Read the stack frames one by one and create the PC
-	 * from the a0 and a1 registers saved there.
-	 */
-	while (a1 > sp_start && a1 < sp_end && depth--) {
-		pc = MAKE_PC_FROM_RA(a0, pc);
-
-		/* Add the PC to the trace. */
-		oprofile_add_trace(pc);
-		if (pc == (unsigned long) &common_exception_return) {
-			regs = (struct pt_regs *)a1;
-			if (user_mode(regs)) {
-				pc = regs->pc;
-				if (pc != 0 && pc <= TASK_SIZE)
-					oprofile_add_trace(pc);
-				else
-					return;
-				return xtensa_backtrace_user(regs, depth);
-			}
-			a0 = regs->areg[0];
-			a1 = regs->areg[1];
-			continue;
-		}
-
-		psp = (unsigned long *)a1;
-
-		a0 = *(psp - 4);
-		a1 = *(psp - 3);
-
-		if (a1 <= (unsigned long)psp)
-			return;
-
-	}
-	return;
+	oprofile_add_trace(frame->pc);
+	return 0;
 }
 
 void xtensa_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
 	if (user_mode(regs))
-		xtensa_backtrace_user(regs, depth);
+		xtensa_backtrace_user(regs, depth, xtensa_backtrace_cb, NULL);
 	else
-		xtensa_backtrace_kernel(regs, depth);
+		xtensa_backtrace_kernel(regs, depth, xtensa_backtrace_cb,
+					xtensa_backtrace_cb, NULL);
 }
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 8ab021b1f141..976a38594537 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -105,13 +105,17 @@ static char *split_if_spec(char *str, ...)
 
 	va_start(ap, str);
 	while ((arg = va_arg(ap, char**)) != NULL) {
-		if (*str == '\0')
+		if (*str == '\0') {
+			va_end(ap);
 			return NULL;
+		}
 		end = strchr(str, ',');
 		if (end != str)
 			*arg = str;
-		if (end == NULL)
+		if (end == NULL) {
+			va_end(ap);
 			return NULL;
+		}
 		*end++ = '\0';
 		str = end;
 	}
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 48eebacdf5fe..fa84ca990caa 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -101,8 +101,9 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 	spin_unlock(&dev->lock);
 }
 
-static int simdisk_xfer_bio(struct simdisk *dev, struct bio *bio)
+static void simdisk_make_request(struct request_queue *q, struct bio *bio)
 {
+	struct simdisk *dev = q->queuedata;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	sector_t sector = bio->bi_iter.bi_sector;
@@ -116,17 +117,10 @@ static int simdisk_xfer_bio(struct simdisk *dev, struct bio *bio)
 		sector += len;
 		__bio_kunmap_atomic(buffer);
 	}
-	return 0;
-}
 
-static void simdisk_make_request(struct request_queue *q, struct bio *bio)
-{
-	struct simdisk *dev = q->queuedata;
-	int status = simdisk_xfer_bio(dev, bio);
-	bio_endio(bio, status);
+	bio_endio(bio);
 }
 
-
 static int simdisk_open(struct block_device *bdev, fmode_t mode)
 {
 	struct simdisk *dev = bdev->bd_disk->private_data;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 0436c21db7f2..4aecca79374a 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -51,7 +51,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	unsigned long idx = BIO_POOL_NONE;
 	unsigned inline_vecs;
 
-	if (!bs) {
+	if (!bs || !bs->bio_integrity_pool) {
 		bip = kmalloc(sizeof(struct bio_integrity_payload) +
 			      sizeof(struct bio_vec) * nr_vecs, gfp_mask);
 		inline_vecs = nr_vecs;
@@ -104,7 +104,7 @@ void bio_integrity_free(struct bio *bio)
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
-	if (bs) {
+	if (bs && bs->bio_integrity_pool) {
 		if (bip->bip_slab != BIO_POOL_NONE)
 			bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
 				  bip->bip_slab);
@@ -355,13 +355,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	int error;
 
-	error = bio_integrity_process(bio, bi->verify_fn);
+	bio->bi_error = bio_integrity_process(bio, bi->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
-	bio_endio(bio, error);
+	bio_endio(bio);
 }
 
 /**
@@ -376,7 +375,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  * in process context.	This function postpones completion
  * accordingly.
  */
-void bio_integrity_endio(struct bio *bio, int error)
+void bio_integrity_endio(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
@@ -386,9 +385,9 @@ void bio_integrity_endio(struct bio *bio, int error)
 	 * integrity metadata.  Restore original bio end_io handler
 	 * and run it.
 	 */
-	if (error) {
+	if (bio->bi_error) {
 		bio->bi_end_io = bip->bip_end_io;
-		bio_endio(bio, error);
+		bio_endio(bio);
 
 		return;
 	}
diff --git a/block/bio.c b/block/bio.c
index 2a00d349cd68..515b5434fe2d 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -269,7 +269,6 @@ static void bio_free(struct bio *bio)
 void bio_init(struct bio *bio)
 {
 	memset(bio, 0, sizeof(*bio));
-	bio->bi_flags = 1 << BIO_UPTODATE;
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
 }
@@ -292,14 +291,17 @@ void bio_reset(struct bio *bio)
 	__bio_free(bio);
 
 	memset(bio, 0, BIO_RESET_BYTES);
-	bio->bi_flags = flags | (1 << BIO_UPTODATE);
+	bio->bi_flags = flags;
 	atomic_set(&bio->__bi_remaining, 1);
 }
 EXPORT_SYMBOL(bio_reset);
 
-static void bio_chain_endio(struct bio *bio, int error)
+static void bio_chain_endio(struct bio *bio)
 {
-	bio_endio(bio->bi_private, error);
+	struct bio *parent = bio->bi_private;
+
+	parent->bi_error = bio->bi_error;
+	bio_endio(parent);
 	bio_put(bio);
 }
 
@@ -309,7 +311,7 @@ static void bio_chain_endio(struct bio *bio, int error)
  */
 static inline void bio_inc_remaining(struct bio *bio)
 {
-	bio->bi_flags |= (1 << BIO_CHAIN);
+	bio_set_flag(bio, BIO_CHAIN);
 	smp_mb__before_atomic();
 	atomic_inc(&bio->__bi_remaining);
 }
@@ -493,7 +495,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		if (unlikely(!bvl))
 			goto err_free;
 
-		bio->bi_flags |= 1 << BIO_OWNS_VEC;
+		bio_set_flag(bio, BIO_OWNS_VEC);
 	} else if (nr_iovecs) {
 		bvl = bio->bi_inline_vecs;
 	}
@@ -578,7 +580,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	 * so we don't set nor calculate new physical/hw segment counts here
 	 */
 	bio->bi_bdev = bio_src->bi_bdev;
-	bio->bi_flags |= 1 << BIO_CLONED;
+	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_rw = bio_src->bi_rw;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
@@ -692,31 +694,22 @@ integrity_clone:
 EXPORT_SYMBOL(bio_clone_bioset);
 
 /**
- *	bio_get_nr_vecs		- return approx number of vecs
- *	@bdev:  I/O target
+ *	bio_add_pc_page	-	attempt to add page to bio
+ *	@q: the target queue
+ *	@bio: destination bio
+ *	@page: page to add
+ *	@len: vec entry length
+ *	@offset: vec entry offset
+ *
+ *	Attempt to add a page to the bio_vec maplist. This can fail for a
+ *	number of reasons, such as the bio being full or target block device
+ *	limitations. The target block device must allow bio's up to PAGE_SIZE,
+ *	so it is always possible to add a single page to an empty bio.
  *
- *	Return the approximate number of pages we can send to this target.
- *	There's no guarantee that you will be able to fit this number of pages
- *	into a bio, it does not account for dynamic restrictions that vary
- *	on offset.
+ *	This should only be used by REQ_PC bios.
  */
-int bio_get_nr_vecs(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-	int nr_pages;
-
-	nr_pages = min_t(unsigned,
-		     queue_max_segments(q),
-		     queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
-
-	return min_t(unsigned, nr_pages, BIO_MAX_PAGES);
-
-}
-EXPORT_SYMBOL(bio_get_nr_vecs);
-
-static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
-			  *page, unsigned int len, unsigned int offset,
-			  unsigned int max_sectors)
+int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
+		    *page, unsigned int len, unsigned int offset)
 {
 	int retried_segments = 0;
 	struct bio_vec *bvec;
@@ -727,7 +720,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	if (unlikely(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
-	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
+	if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
 		return 0;
 
 	/*
@@ -740,28 +733,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 
 		if (page == prev->bv_page &&
 		    offset == prev->bv_offset + prev->bv_len) {
-			unsigned int prev_bv_len = prev->bv_len;
 			prev->bv_len += len;
-
-			if (q->merge_bvec_fn) {
-				struct bvec_merge_data bvm = {
-					/* prev_bvec is already charged in
-					   bi_size, discharge it in order to
-					   simulate merging updated prev_bvec
-					   as new bvec. */
-					.bi_bdev = bio->bi_bdev,
-					.bi_sector = bio->bi_iter.bi_sector,
-					.bi_size = bio->bi_iter.bi_size -
-						prev_bv_len,
-					.bi_rw = bio->bi_rw,
-				};
-
-				if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
-					prev->bv_len -= len;
-					return 0;
-				}
-			}
-
 			bio->bi_iter.bi_size += len;
 			goto done;
 		}
@@ -770,8 +742,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
-		if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
-		    bvec_gap_to_prev(prev, offset))
+		if (bvec_gap_to_prev(q, prev, offset))
 			return 0;
 	}
 
@@ -804,30 +775,9 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		blk_recount_segments(q, bio);
 	}
 
-	/*
-	 * if queue has other restrictions (eg varying max sector size
-	 * depending on offset), it can specify a merge_bvec_fn in the
-	 * queue to get further control
-	 */
-	if (q->merge_bvec_fn) {
-		struct bvec_merge_data bvm = {
-			.bi_bdev = bio->bi_bdev,
-			.bi_sector = bio->bi_iter.bi_sector,
-			.bi_size = bio->bi_iter.bi_size - len,
-			.bi_rw = bio->bi_rw,
-		};
-
-		/*
-		 * merge_bvec_fn() returns number of bytes it can accept
-		 * at this offset
-		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
-			goto failed;
-	}
-
 	/* If we may be able to merge these biovecs, force a recount */
 	if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
-		bio->bi_flags &= ~(1 << BIO_SEG_VALID);
+		bio_clear_flag(bio, BIO_SEG_VALID);
 
  done:
 	return len;
@@ -841,28 +791,6 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	blk_recount_segments(q, bio);
 	return 0;
 }
-
-/**
- *	bio_add_pc_page	-	attempt to add page to bio
- *	@q: the target queue
- *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
- *
- *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block device
- *	limitations. The target block device must allow bio's up to PAGE_SIZE,
- *	so it is always possible to add a single page to an empty bio.
- *
- *	This should only be used by REQ_PC bios.
- */
-int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
-		    unsigned int len, unsigned int offset)
-{
-	return __bio_add_page(q, bio, page, len, offset,
-			      queue_max_hw_sectors(q));
-}
 EXPORT_SYMBOL(bio_add_pc_page);
 
 /**
@@ -872,22 +800,47 @@ EXPORT_SYMBOL(bio_add_pc_page);
  *	@len: vec entry length
  *	@offset: vec entry offset
  *
- *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block device
- *	limitations. The target block device must allow bio's up to PAGE_SIZE,
- *	so it is always possible to add a single page to an empty bio.
+ *	Attempt to add a page to the bio_vec maplist. This will only fail
+ *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
  */
-int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
-		 unsigned int offset)
+int bio_add_page(struct bio *bio, struct page *page,
+		 unsigned int len, unsigned int offset)
 {
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned int max_sectors;
+	struct bio_vec *bv;
+
+	/*
+	 * cloned bio must not modify vec list
+	 */
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+		return 0;
+
+	/*
+	 * For filesystems with a blocksize smaller than the pagesize
+	 * we will often be called with the same page as last time and
+	 * a consecutive offset.  Optimize this special case.
+	 */
+	if (bio->bi_vcnt > 0) {
+		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (page == bv->bv_page &&
+		    offset == bv->bv_offset + bv->bv_len) {
+			bv->bv_len += len;
+			goto done;
+		}
+	}
+
+	if (bio->bi_vcnt >= bio->bi_max_vecs)
+		return 0;
 
-	max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
-	if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
-		max_sectors = len >> 9;
+	bv		= &bio->bi_io_vec[bio->bi_vcnt];
+	bv->bv_page	= page;
+	bv->bv_len	= len;
+	bv->bv_offset	= offset;
 
-	return __bio_add_page(q, bio, page, len, offset, max_sectors);
+	bio->bi_vcnt++;
+done:
+	bio->bi_iter.bi_size += len;
+	return len;
 }
 EXPORT_SYMBOL(bio_add_page);
 
@@ -896,11 +849,11 @@ struct submit_bio_ret {
 	int error;
 };
 
-static void submit_bio_wait_endio(struct bio *bio, int error)
+static void submit_bio_wait_endio(struct bio *bio)
 {
 	struct submit_bio_ret *ret = bio->bi_private;
 
-	ret->error = error;
+	ret->error = bio->bi_error;
 	complete(&ret->event);
 }
 
@@ -1388,7 +1341,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	if (iter->type & WRITE)
 		bio->bi_rw |= REQ_WRITE;
 
-	bio->bi_flags |= (1 << BIO_USER_MAPPED);
+	bio_set_flag(bio, BIO_USER_MAPPED);
 
 	/*
 	 * subtle -- if __bio_map_user() ended up bouncing a bio,
@@ -1445,7 +1398,7 @@ void bio_unmap_user(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_unmap_user);
 
-static void bio_map_kern_endio(struct bio *bio, int err)
+static void bio_map_kern_endio(struct bio *bio)
 {
 	bio_put(bio);
 }
@@ -1501,13 +1454,13 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 }
 EXPORT_SYMBOL(bio_map_kern);
 
-static void bio_copy_kern_endio(struct bio *bio, int err)
+static void bio_copy_kern_endio(struct bio *bio)
 {
 	bio_free_pages(bio);
 	bio_put(bio);
 }
 
-static void bio_copy_kern_endio_read(struct bio *bio, int err)
+static void bio_copy_kern_endio_read(struct bio *bio)
 {
 	char *p = bio->bi_private;
 	struct bio_vec *bvec;
@@ -1518,7 +1471,7 @@ static void bio_copy_kern_endio_read(struct bio *bio, int err)
 		p += bvec->bv_len;
 	}
 
-	bio_copy_kern_endio(bio, err);
+	bio_copy_kern_endio(bio);
 }
 
 /**
@@ -1768,7 +1721,7 @@ static inline bool bio_remaining_done(struct bio *bio)
 	BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
 
 	if (atomic_dec_and_test(&bio->__bi_remaining)) {
-		clear_bit(BIO_CHAIN, &bio->bi_flags);
+		bio_clear_flag(bio, BIO_CHAIN);
 		return true;
 	}
 
@@ -1778,25 +1731,15 @@ static inline bool bio_remaining_done(struct bio *bio)
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
- * @error:	error, if any
  *
  * Description:
- *   bio_endio() will end I/O on the whole bio. bio_endio() is the
- *   preferred way to end I/O on a bio, it takes care of clearing
- *   BIO_UPTODATE on error. @error is 0 on success, and and one of the
- *   established -Exxxx (-EIO, for instance) error values in case
- *   something went wrong. No one should call bi_end_io() directly on a
- *   bio unless they own it and thus know that it has an end_io
- *   function.
+ *   bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
+ *   way to end I/O on a bio. No one should call bi_end_io() directly on a
+ *   bio unless they own it and thus know that it has an end_io function.
  **/
-void bio_endio(struct bio *bio, int error)
+void bio_endio(struct bio *bio)
 {
 	while (bio) {
-		if (error)
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
-		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-			error = -EIO;
-
 		if (unlikely(!bio_remaining_done(bio)))
 			break;
 
@@ -1810,11 +1753,12 @@ void bio_endio(struct bio *bio, int error)
 		 */
 		if (bio->bi_end_io == bio_chain_endio) {
 			struct bio *parent = bio->bi_private;
+			parent->bi_error = bio->bi_error;
 			bio_put(bio);
 			bio = parent;
 		} else {
 			if (bio->bi_end_io)
-				bio->bi_end_io(bio, error);
+				bio->bi_end_io(bio);
 			bio = NULL;
 		}
 	}
@@ -1831,8 +1775,9 @@ EXPORT_SYMBOL(bio_endio);
  * Allocates and returns a new bio which represents @sectors from the start of
  * @bio, and updates @bio to represent the remaining sectors.
  *
- * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
- * responsibility to ensure that @bio is not freed before the split.
+ * Unless this is a discard request the newly allocated bio will point
+ * to @bio's bi_io_vec; it is the caller's responsibility to ensure that
+ * @bio is not freed before the split.
  */
 struct bio *bio_split(struct bio *bio, int sectors,
 		      gfp_t gfp, struct bio_set *bs)
@@ -1842,7 +1787,15 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
 
-	split = bio_clone_fast(bio, gfp, bs);
+	/*
+	 * Discards need a mutable bio_vec to accommodate the payload
+	 * required by the DSM TRIM and UNMAP commands.
+	 */
+	if (bio->bi_rw & REQ_DISCARD)
+		split = bio_clone_bioset(bio, gfp, bs);
+	else
+		split = bio_clone_fast(bio, gfp, bs);
+
 	if (!split)
 		return NULL;
 
@@ -1873,7 +1826,7 @@ void bio_trim(struct bio *bio, int offset, int size)
 	if (offset == 0 && size == bio->bi_iter.bi_size)
 		return;
 
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	bio_advance(bio, offset << 9);
 
@@ -2009,6 +1962,7 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 	bio->bi_css = blkcg_css;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
  * bio_associate_current - associate a bio with %current
@@ -2039,6 +1993,7 @@ int bio_associate_current(struct bio *bio)
 	bio->bi_css = task_get_css(current, blkio_cgrp_id);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(bio_associate_current);
 
 /**
  * bio_disassociate_task - undo bio_associate_current()
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9f97da52d006..d6283b3f5db5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -29,6 +29,14 @@
 
 #define MAX_KEY_LEN 100
 
+/*
+ * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
+ * blkcg_pol_register_mutex nests outside of it and synchronizes entire
+ * policy [un]register operations including cgroup file additions /
+ * removals.  Putting cgroup file registration outside blkcg_pol_mutex
+ * allows grabbing it from cgroup callbacks.
+ */
+static DEFINE_MUTEX(blkcg_pol_register_mutex);
 static DEFINE_MUTEX(blkcg_pol_mutex);
 
 struct blkcg blkcg_root;
@@ -38,6 +46,8 @@ struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
+static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -453,20 +463,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	struct blkcg_gq *blkg;
 	int i;
 
-	/*
-	 * XXX: We invoke cgroup_add/rm_cftypes() under blkcg_pol_mutex
-	 * which ends up putting cgroup's internal cgroup_tree_mutex under
-	 * it; however, cgroup_tree_mutex is nested above cgroup file
-	 * active protection and grabbing blkcg_pol_mutex from a cgroup
-	 * file operation creates a possible circular dependency.  cgroup
-	 * internal locking is planned to go through further simplification
-	 * and this issue should go away soon.  For now, let's trylock
-	 * blkcg_pol_mutex and restart the write on failure.
-	 *
-	 * http://lkml.kernel.org/g/5363C04B.4010400@oracle.com
-	 */
-	if (!mutex_trylock(&blkcg_pol_mutex))
-		return restart_syscall();
+	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
 
 	/*
@@ -721,8 +718,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		return -EINVAL;
 
 	disk = get_gendisk(MKDEV(major, minor), &part);
-	if (!disk || part)
+	if (!disk)
+		return -EINVAL;
+	if (part) {
+		put_disk(disk);
 		return -EINVAL;
+	}
 
 	rcu_read_lock();
 	spin_lock_irq(disk->queue->queue_lock);
@@ -822,8 +823,17 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 
-	if (blkcg != &blkcg_root)
+	mutex_lock(&blkcg_pol_mutex);
+	list_del(&blkcg->all_blkcgs_node);
+	mutex_unlock(&blkcg_pol_mutex);
+
+	if (blkcg != &blkcg_root) {
+		int i;
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++)
+			kfree(blkcg->pd[i]);
 		kfree(blkcg);
+	}
 }
 
 static struct cgroup_subsys_state *
@@ -833,6 +843,8 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct cgroup_subsys_state *ret;
 	int i;
 
+	mutex_lock(&blkcg_pol_mutex);
+
 	if (!parent_css) {
 		blkcg = &blkcg_root;
 		goto done;
@@ -875,14 +887,17 @@ done:
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&blkcg->cgwb_list);
 #endif
+	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
+
+	mutex_unlock(&blkcg_pol_mutex);
 	return &blkcg->css;
 
 free_pd_blkcg:
 	for (i--; i >= 0; i--)
 		kfree(blkcg->pd[i]);
-
 free_blkcg:
 	kfree(blkcg);
+	mutex_unlock(&blkcg_pol_mutex);
 	return ret;
 }
 
@@ -1037,10 +1052,8 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	LIST_HEAD(pds);
-	LIST_HEAD(cpds);
 	struct blkcg_gq *blkg;
 	struct blkg_policy_data *pd, *nd;
-	struct blkcg_policy_data *cpd, *cnd;
 	int cnt = 0, ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1053,10 +1066,7 @@ int blkcg_activate_policy(struct request_queue *q,
 		cnt++;
 	spin_unlock_irq(q->queue_lock);
 
-	/*
-	 * Allocate per-blkg and per-blkcg policy data
-	 * for all existing blkgs.
-	 */
+	/* allocate per-blkg policy data for all existing blkgs */
 	while (cnt--) {
 		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
 		if (!pd) {
@@ -1064,15 +1074,6 @@ int blkcg_activate_policy(struct request_queue *q,
 			goto out_free;
 		}
 		list_add_tail(&pd->alloc_node, &pds);
-
-		if (!pol->cpd_size)
-			continue;
-		cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node);
-		if (!cpd) {
-			ret = -ENOMEM;
-			goto out_free;
-		}
-		list_add_tail(&cpd->alloc_node, &cpds);
 	}
 
 	/*
@@ -1082,32 +1083,17 @@ int blkcg_activate_policy(struct request_queue *q,
 	spin_lock_irq(q->queue_lock);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		if (WARN_ON(list_empty(&pds)) ||
-		    WARN_ON(pol->cpd_size && list_empty(&cpds))) {
+		if (WARN_ON(list_empty(&pds))) {
 			/* umm... this shouldn't happen, just abort */
 			ret = -ENOMEM;
 			goto out_unlock;
 		}
-		cpd = list_first_entry(&cpds, struct blkcg_policy_data,
-				       alloc_node);
-		list_del_init(&cpd->alloc_node);
 		pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
 		list_del_init(&pd->alloc_node);
 
 		/* grab blkcg lock too while installing @pd on @blkg */
 		spin_lock(&blkg->blkcg->lock);
 
-		if (!pol->cpd_size)
-			goto no_cpd;
-		if (!blkg->blkcg->pd[pol->plid]) {
-			/* Per-policy per-blkcg data */
-			blkg->blkcg->pd[pol->plid] = cpd;
-			cpd->plid = pol->plid;
-			pol->cpd_init_fn(blkg->blkcg);
-		} else { /* must free it as it has already been extracted */
-			kfree(cpd);
-		}
-no_cpd:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
@@ -1124,8 +1110,6 @@ out_free:
 	blk_queue_bypass_end(q);
 	list_for_each_entry_safe(pd, nd, &pds, alloc_node)
 		kfree(pd);
-	list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node)
-		kfree(cpd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1162,8 +1146,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 		kfree(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid] = NULL;
-		kfree(blkg->blkcg->pd[pol->plid]);
-		blkg->blkcg->pd[pol->plid] = NULL;
 
 		spin_unlock(&blkg->blkcg->lock);
 	}
@@ -1182,11 +1164,13 @@ EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
  */
 int blkcg_policy_register(struct blkcg_policy *pol)
 {
+	struct blkcg *blkcg;
 	int i, ret;
 
 	if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
 		return -EINVAL;
 
+	mutex_lock(&blkcg_pol_register_mutex);
 	mutex_lock(&blkcg_pol_mutex);
 
 	/* find an empty slot */
@@ -1195,19 +1179,49 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 		if (!blkcg_policy[i])
 			break;
 	if (i >= BLKCG_MAX_POLS)
-		goto out_unlock;
+		goto err_unlock;
 
-	/* register and update blkgs */
+	/* register @pol */
 	pol->plid = i;
-	blkcg_policy[i] = pol;
+	blkcg_policy[pol->plid] = pol;
+
+	/* allocate and install cpd's */
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			struct blkcg_policy_data *cpd;
+
+			cpd = kzalloc(pol->cpd_size, GFP_KERNEL);
+			if (!cpd) {
+				mutex_unlock(&blkcg_pol_mutex);
+				goto err_free_cpds;
+			}
+
+			blkcg->pd[pol->plid] = cpd;
+			cpd->plid = pol->plid;
+			pol->cpd_init_fn(blkcg);
+		}
+	}
+
+	mutex_unlock(&blkcg_pol_mutex);
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
 		WARN_ON(cgroup_add_legacy_cftypes(&blkio_cgrp_subsys,
 						  pol->cftypes));
-	ret = 0;
-out_unlock:
+	mutex_unlock(&blkcg_pol_register_mutex);
+	return 0;
+
+err_free_cpds:
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			kfree(blkcg->pd[pol->plid]);
+			blkcg->pd[pol->plid] = NULL;
+		}
+	}
+	blkcg_policy[pol->plid] = NULL;
+err_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
+	mutex_unlock(&blkcg_pol_register_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_register);
@@ -1220,7 +1234,9 @@ EXPORT_SYMBOL_GPL(blkcg_policy_register);
  */
 void blkcg_policy_unregister(struct blkcg_policy *pol)
 {
-	mutex_lock(&blkcg_pol_mutex);
+	struct blkcg *blkcg;
+
+	mutex_lock(&blkcg_pol_register_mutex);
 
 	if (WARN_ON(blkcg_policy[pol->plid] != pol))
 		goto out_unlock;
@@ -1229,9 +1245,19 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 	if (pol->cftypes)
 		cgroup_rm_cftypes(pol->cftypes);
 
-	/* unregister and update blkgs */
+	/* remove cpds and unregister */
+	mutex_lock(&blkcg_pol_mutex);
+
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			kfree(blkcg->pd[pol->plid]);
+			blkcg->pd[pol->plid] = NULL;
+		}
+	}
 	blkcg_policy[pol->plid] = NULL;
-out_unlock:
+
 	mutex_unlock(&blkcg_pol_mutex);
+out_unlock:
+	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
diff --git a/block/blk-core.c b/block/blk-core.c
index 82819e68f58b..60912e983f16 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -143,18 +143,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
 {
 	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
+		bio->bi_error = error;
 
 	if (unlikely(rq->cmd_flags & REQ_QUIET))
-		set_bit(BIO_QUIET, &bio->bi_flags);
+		bio_set_flag(bio, BIO_QUIET);
 
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
 	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
-		bio_endio(bio, error);
+		bio_endio(bio);
 }
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
@@ -645,6 +643,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (q->id < 0)
 		goto fail_q;
 
+	q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	if (!q->bio_split)
+		goto fail_id;
+
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
@@ -653,7 +655,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	err = bdi_init(&q->backing_dev_info);
 	if (err)
-		goto fail_id;
+		goto fail_split;
 
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
@@ -695,6 +697,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 fail_bdi:
 	bdi_destroy(&q->backing_dev_info);
+fail_split:
+	bioset_free(q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
 fail_q:
@@ -1612,6 +1616,8 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	struct request *req;
 	unsigned int request_count = 0;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1620,7 +1626,8 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_endio(bio, -EIO);
+		bio->bi_error = -EIO;
+		bio_endio(bio);
 		return;
 	}
 
@@ -1673,7 +1680,8 @@ get_rq:
 	 */
 	req = get_request(q, rw_flags, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
-		bio_endio(bio, PTR_ERR(req));	/* @q is dead */
+		bio->bi_error = PTR_ERR(req);
+		bio_endio(bio);
 		goto out_unlock;
 	}
 
@@ -1832,15 +1840,6 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
-	if (likely(bio_is_rw(bio) &&
-		   nr_sectors > queue_max_hw_sectors(q))) {
-		printk(KERN_ERR "bio too big device %s (%u > %u)\n",
-		       bdevname(bio->bi_bdev, b),
-		       bio_sectors(bio),
-		       queue_max_hw_sectors(q));
-		goto end_io;
-	}
-
 	part = bio->bi_bdev->bd_part;
 	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
@@ -1896,7 +1895,8 @@ generic_make_request_checks(struct bio *bio)
 	return true;
 
 end_io:
-	bio_endio(bio, err);
+	bio->bi_error = err;
+	bio_endio(bio);
 	return false;
 }
 
@@ -3370,7 +3370,7 @@ EXPORT_SYMBOL(blk_post_runtime_resume);
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
-			sizeof(((struct request *)0)->cmd_flags));
+			FIELD_SIZEOF(struct request, cmd_flags));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 20badd7b9d1b..9c423e53324a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -73,6 +73,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-tag.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -226,7 +227,12 @@ static void flush_end_io(struct request *flush_rq, int error)
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
 
 	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+
+		/* release the tag's ownership to the req cloned from */
 		spin_lock_irqsave(&fq->mq_flush_lock, flags);
+		hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+		blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
 		flush_rq->tag = -1;
 	}
 
@@ -308,11 +314,18 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 
 	/*
 	 * Borrow tag from the first request since they can't
-	 * be in flight at the same time.
+	 * be in flight at the same time. And acquire the tag's
+	 * ownership for flush req.
 	 */
 	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+
 		flush_rq->mq_ctx = first_rq->mq_ctx;
 		flush_rq->tag = first_rq->tag;
+		fq->orig_rq = first_rq;
+
+		hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 7688ee3f5d72..bd40292e5009 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -11,21 +11,28 @@
 
 struct bio_batch {
 	atomic_t		done;
-	unsigned long		flags;
+	int			error;
 	struct completion	*wait;
 };
 
-static void bio_batch_end_io(struct bio *bio, int err)
+static void bio_batch_end_io(struct bio *bio)
 {
 	struct bio_batch *bb = bio->bi_private;
 
-	if (err && (err != -EOPNOTSUPP))
-		clear_bit(BIO_UPTODATE, &bb->flags);
+	if (bio->bi_error && bio->bi_error != -EOPNOTSUPP)
+		bb->error = bio->bi_error;
 	if (atomic_dec_and_test(&bb->done))
 		complete(bb->wait);
 	bio_put(bio);
 }
 
+/*
+ * Ensure that max discard sectors doesn't overflow bi_size and hopefully
+ * it is of the proper granularity as long as the granularity is a power
+ * of two.
+ */
+#define MAX_BIO_SECTORS ((1U << 31) >> 9)
+
 /**
  * blkdev_issue_discard - queue a discard
  * @bdev:	blockdev to issue discard for
@@ -43,8 +50,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
-	unsigned int max_discard_sectors, granularity;
-	int alignment;
 	struct bio_batch bb;
 	struct bio *bio;
 	int ret = 0;
@@ -56,21 +61,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
-	/*
-	 * Ensure that max_discard_sectors is of the proper
-	 * granularity, so that requests stay aligned after a split.
-	 */
-	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-	max_discard_sectors -= max_discard_sectors % granularity;
-	if (unlikely(!max_discard_sectors)) {
-		/* Avoid infinite loop below. Being cautious never hurts. */
-		return -EOPNOTSUPP;
-	}
-
 	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secdiscard(q))
 			return -EOPNOTSUPP;
@@ -78,13 +68,13 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	}
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	blk_start_plug(&plug);
 	while (nr_sects) {
 		unsigned int req_sects;
-		sector_t end_sect, tmp;
+		sector_t end_sect;
 
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio) {
@@ -92,21 +82,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			break;
 		}
 
-		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
-
-		/*
-		 * If splitting a request, and the next starting sector would be
-		 * misaligned, stop the discard at the previous aligned sector.
-		 */
+		req_sects = min_t(sector_t, nr_sects, MAX_BIO_SECTORS);
 		end_sect = sector + req_sects;
-		tmp = end_sect;
-		if (req_sects < nr_sects &&
-		    sector_div(tmp, granularity) != alignment) {
-			end_sect = end_sect - alignment;
-			sector_div(end_sect, granularity);
-			end_sect = end_sect * granularity + alignment;
-			req_sects = end_sect - sector;
-		}
 
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
@@ -134,9 +111,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion_io(&wait);
 
-	if (!test_bit(BIO_UPTODATE, &bb.flags))
-		ret = -EIO;
-
+	if (bb.error)
+		return bb.error;
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
@@ -166,13 +142,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	if (!q)
 		return -ENXIO;
 
-	max_write_same_sectors = q->limits.max_write_same_sectors;
-
-	if (max_write_same_sectors == 0)
-		return -EOPNOTSUPP;
+	/* Ensure that max_write_same_sectors doesn't overflow bi_size */
+	max_write_same_sectors = UINT_MAX >> 9;
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	while (nr_sects) {
@@ -208,9 +182,8 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion_io(&wait);
 
-	if (!test_bit(BIO_UPTODATE, &bb.flags))
-		ret = -ENOTSUPP;
-
+	if (bb.error)
+		return bb.error;
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
@@ -236,7 +209,7 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	DECLARE_COMPLETION_ONSTACK(wait);
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	ret = 0;
@@ -270,10 +243,8 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion_io(&wait);
 
-	if (!test_bit(BIO_UPTODATE, &bb.flags))
-		/* One of bios in the batch was completed with error.*/
-		ret = -EIO;
-
+	if (bb.error)
+		return bb.error;
 	return ret;
 }
 
diff --git a/block/blk-map.c b/block/blk-map.c
index da310a105429..233841644c9d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -94,7 +94,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		return PTR_ERR(bio);
 
 	if (map_data && map_data->null_mapped)
-		bio->bi_flags |= (1 << BIO_NULL_MAPPED);
+		bio_set_flag(bio, BIO_NULL_MAPPED);
 
 	if (bio->bi_iter.bi_size != iter->count) {
 		/*
@@ -103,7 +103,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		 * normal IO completion path
 		 */
 		bio_get(bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		__blk_rq_unmap_user(bio);
 		return -EINVAL;
 	}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 30a0d9f89017..d088cffb8105 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,12 +9,146 @@
 
 #include "blk.h"
 
+static struct bio *blk_bio_discard_split(struct request_queue *q,
+					 struct bio *bio,
+					 struct bio_set *bs)
+{
+	unsigned int max_discard_sectors, granularity;
+	int alignment;
+	sector_t tmp;
+	unsigned split_sectors;
+
+	/* Zero-sector (unknown) and one-sector granularities are the same.  */
+	granularity = max(q->limits.discard_granularity >> 9, 1U);
+
+	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors -= max_discard_sectors % granularity;
+
+	if (unlikely(!max_discard_sectors)) {
+		/* XXX: warn */
+		return NULL;
+	}
+
+	if (bio_sectors(bio) <= max_discard_sectors)
+		return NULL;
+
+	split_sectors = max_discard_sectors;
+
+	/*
+	 * If the next starting sector would be misaligned, stop the discard at
+	 * the previous aligned sector.
+	 */
+	alignment = (q->limits.discard_alignment >> 9) % granularity;
+
+	tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
+	tmp = sector_div(tmp, granularity);
+
+	if (split_sectors > tmp)
+		split_sectors -= tmp;
+
+	return bio_split(bio, split_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_write_same_split(struct request_queue *q,
+					    struct bio *bio,
+					    struct bio_set *bs)
+{
+	if (!q->limits.max_write_same_sectors)
+		return NULL;
+
+	if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
+		return NULL;
+
+	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_segment_split(struct request_queue *q,
+					 struct bio *bio,
+					 struct bio_set *bs)
+{
+	struct bio *split;
+	struct bio_vec bv, bvprv;
+	struct bvec_iter iter;
+	unsigned seg_size = 0, nsegs = 0, sectors = 0;
+	int prev = 0;
+
+	bio_for_each_segment(bv, bio, iter) {
+		sectors += bv.bv_len >> 9;
+
+		if (sectors > queue_max_sectors(q))
+			goto split;
+
+		/*
+		 * If the queue doesn't support SG gaps and adding this
+		 * offset would create a gap, disallow it.
+		 */
+		if (prev && bvec_gap_to_prev(q, &bvprv, bv.bv_offset))
+			goto split;
+
+		if (prev && blk_queue_cluster(q)) {
+			if (seg_size + bv.bv_len > queue_max_segment_size(q))
+				goto new_segment;
+			if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
+				goto new_segment;
+			if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
+				goto new_segment;
+
+			seg_size += bv.bv_len;
+			bvprv = bv;
+			prev = 1;
+			continue;
+		}
+new_segment:
+		if (nsegs == queue_max_segments(q))
+			goto split;
+
+		nsegs++;
+		bvprv = bv;
+		prev = 1;
+		seg_size = bv.bv_len;
+	}
+
+	return NULL;
+split:
+	split = bio_clone_bioset(bio, GFP_NOIO, bs);
+
+	split->bi_iter.bi_size -= iter.bi_size;
+	bio->bi_iter = iter;
+
+	if (bio_integrity(bio)) {
+		bio_integrity_advance(bio, split->bi_iter.bi_size);
+		bio_integrity_trim(split, 0, bio_sectors(split));
+	}
+
+	return split;
+}
+
+void blk_queue_split(struct request_queue *q, struct bio **bio,
+		     struct bio_set *bs)
+{
+	struct bio *split;
+
+	if ((*bio)->bi_rw & REQ_DISCARD)
+		split = blk_bio_discard_split(q, *bio, bs);
+	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+		split = blk_bio_write_same_split(q, *bio, bs);
+	else
+		split = blk_bio_segment_split(q, *bio, q->bio_split);
+
+	if (split) {
+		bio_chain(split, *bio);
+		generic_make_request(*bio);
+		*bio = split;
+	}
+}
+EXPORT_SYMBOL(blk_queue_split);
+
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio,
 					     bool no_sg_merge)
 {
 	struct bio_vec bv, bvprv = { NULL };
-	int cluster, high, highprv = 1;
+	int cluster, prev = 0;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
@@ -36,7 +170,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	cluster = blk_queue_cluster(q);
 	seg_size = 0;
 	nr_phys_segs = 0;
-	high = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, iter) {
 			/*
@@ -46,13 +179,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 			if (no_sg_merge)
 				goto new_segment;
 
-			/*
-			 * the trick here is making sure that a high page is
-			 * never considered part of another segment, since
-			 * that might change with the bounce page.
-			 */
-			high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q);
-			if (!high && !highprv && cluster) {
+			if (prev && cluster) {
 				if (seg_size + bv.bv_len
 				    > queue_max_segment_size(q))
 					goto new_segment;
@@ -72,8 +199,8 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
+			prev = 1;
 			seg_size = bv.bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
@@ -116,7 +243,7 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio)
 		bio->bi_next = nxt;
 	}
 
-	bio->bi_flags |= (1 << BIO_SEG_VALID);
+	bio_set_flag(bio, BIO_SEG_VALID);
 }
 EXPORT_SYMBOL(blk_recount_segments);
 
@@ -266,7 +393,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		if (rq->cmd_flags & REQ_WRITE)
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
 
-		sg->page_link &= ~0x02;
+		sg_unmark_end(sg);
 		sg = sg_next(sg);
 		sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
 			    q->dma_drain_size,
@@ -356,12 +483,12 @@ static bool req_no_special_merge(struct request *req)
 	return !q->mq_ops && req->special;
 }
 
-static int req_gap_to_prev(struct request *req, struct request *next)
+static int req_gap_to_prev(struct request *req, struct bio *next)
 {
 	struct bio *prev = req->biotail;
 
-	return bvec_gap_to_prev(&prev->bi_io_vec[prev->bi_vcnt - 1],
-				next->bio->bi_io_vec[0].bv_offset);
+	return bvec_gap_to_prev(req->q, &prev->bi_io_vec[prev->bi_vcnt - 1],
+			next->bi_io_vec[0].bv_offset);
 }
 
 static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
@@ -378,8 +505,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	if (req_no_special_merge(req) || req_no_special_merge(next))
 		return 0;
 
-	if (test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags) &&
-	    req_gap_to_prev(req, next))
+	if (req_gap_to_prev(req, next->bio))
 		return 0;
 
 	/*
@@ -564,8 +690,6 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 {
-	struct request_queue *q = rq->q;
-
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
@@ -590,13 +714,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		return false;
 
 	/* Only check gaps if the bio carries data */
-	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) && bio_has_data(bio)) {
-		struct bio_vec *bprev;
-
-		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
-		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
-			return false;
-	}
+	if (bio_has_data(bio) && req_gap_to_prev(rq, bio))
+		return false;
 
 	return true;
 }
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index b79685e06b70..279c5d674edf 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -141,15 +141,26 @@ static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
 
 static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
 {
-	char *start_page = page;
 	struct request *rq;
+	int len = snprintf(page, PAGE_SIZE - 1, "%s:\n", msg);
+
+	list_for_each_entry(rq, list, queuelist) {
+		const int rq_len = 2 * sizeof(rq) + 2;
+
+		/* if the output will be truncated */
+		if (PAGE_SIZE - 1 < len + rq_len) {
+			/* backspacing if it can't hold '\t...\n' */
+			if (PAGE_SIZE - 1 < len + 5)
+				len -= rq_len;
+			len += snprintf(page + len, PAGE_SIZE - 1 - len,
+					"\t...\n");
+			break;
+		}
+		len += snprintf(page + len, PAGE_SIZE - 1 - len,
+				"\t%p\n", rq);
+	}
 
-	page += sprintf(page, "%s:\n", msg);
-
-	list_for_each_entry(rq, list, queuelist)
-		page += sprintf(page, "\t%p\n", rq);
-
-	return page - start_page;
+	return len;
 }
 
 static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 9b6e28830b82..9115c6d59948 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -429,7 +429,7 @@ static void bt_for_each(struct blk_mq_hw_ctx *hctx,
 		for (bit = find_first_bit(&bm->word, bm->depth);
 		     bit < bm->depth;
 		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
-		     	rq = blk_mq_tag_to_rq(hctx->tags, off + bit);
+			rq = hctx->tags->rqs[off + bit];
 			if (rq->q == hctx->queue)
 				fn(hctx, rq, data, reserved);
 		}
@@ -453,7 +453,7 @@ static void bt_tags_for_each(struct blk_mq_tags *tags,
 		for (bit = find_first_bit(&bm->word, bm->depth);
 		     bit < bm->depth;
 		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
-			rq = blk_mq_tag_to_rq(tags, off + bit);
+			rq = tags->rqs[off + bit];
 			fn(rq, data, reserved);
 		}
 
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 75893a34237d..9eb2cf4f01cb 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -89,4 +89,16 @@ static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 	__blk_mq_tag_idle(hctx);
 }
 
+/*
+ * This helper should only be used for flush request to share tag
+ * with the request cloned from, and both the two requests can't be
+ * in flight at the same time. The caller has to make sure the tag
+ * can't be freed.
+ */
+static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx,
+		unsigned int tag, struct request *rq)
+{
+	hctx->tags->rqs[tag] = rq;
+}
+
 #endif
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f53779692c77..f2d67b4047a0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -559,23 +559,9 @@ void blk_mq_abort_requeue_list(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_abort_requeue_list);
 
-static inline bool is_flush_request(struct request *rq,
-		struct blk_flush_queue *fq, unsigned int tag)
-{
-	return ((rq->cmd_flags & REQ_FLUSH_SEQ) &&
-			fq->flush_rq->tag == tag);
-}
-
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
-	struct request *rq = tags->rqs[tag];
-	/* mq_ctx of flush rq is always cloned from the corresponding req */
-	struct blk_flush_queue *fq = blk_get_flush_queue(rq->q, rq->mq_ctx);
-
-	if (!is_flush_request(rq, fq, tag))
-		return rq;
-
-	return fq->flush_rq;
+	return tags->rqs[tag];
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
@@ -1199,7 +1185,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	struct blk_mq_alloc_data alloc_data;
 
 	if (unlikely(blk_mq_queue_enter(q, GFP_KERNEL))) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return NULL;
 	}
 
@@ -1283,10 +1269,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return;
 	}
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return;
@@ -1368,10 +1356,12 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return;
 	}
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
@@ -1998,7 +1988,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		goto err_hctxs;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
-	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30000);
+	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
 	q->nr_queues = nr_cpu_ids;
 	q->nr_hw_queues = set->nr_hw_queues;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 12600bfffca9..7d8f129a1516 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -53,28 +53,6 @@ void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn)
 }
 EXPORT_SYMBOL(blk_queue_unprep_rq);
 
-/**
- * blk_queue_merge_bvec - set a merge_bvec function for queue
- * @q:		queue
- * @mbfn:	merge_bvec_fn
- *
- * Usually queues have static limitations on the max sectors or segments that
- * we can put in a request. Stacking drivers may have some settings that
- * are dynamic, and thus we have to query the queue whether it is ok to
- * add a new bio_vec to a bio at a given offset or not. If the block device
- * has such limitations, it needs to register a merge_bvec_fn to control
- * the size of bio's sent to it. Note that a block device *must* allow a
- * single page to be added to an empty bio. The block device driver may want
- * to use the bio_split() function to deal with these bio's. By default
- * no merge_bvec_fn is defined for a queue, and only the fixed limits are
- * honored.
- */
-void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
-{
-	q->merge_bvec_fn = mbfn;
-}
-EXPORT_SYMBOL(blk_queue_merge_bvec);
-
 void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
 {
 	q->softirq_done_fn = fn;
@@ -111,11 +89,13 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_segments = BLK_MAX_SEGMENTS;
 	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
+	lim->max_hw_discard_sectors = 0;
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
@@ -241,8 +221,8 @@ EXPORT_SYMBOL(blk_queue_bounce_limit);
  * Description:
  *    Enables a low level driver to set a hard upper limit,
  *    max_hw_sectors, on the size of requests.  max_hw_sectors is set by
- *    the device driver based upon the combined capabilities of I/O
- *    controller and storage device.
+ *    the device driver based upon the capabilities of the I/O
+ *    controller.
  *
  *    max_sectors is a soft limit imposed by the block layer for
  *    filesystem type requests.  This value can be overridden on a
@@ -257,7 +237,9 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_
 		       __func__, max_hw_sectors);
 	}
 
-	limits->max_sectors = limits->max_hw_sectors = max_hw_sectors;
+	limits->max_hw_sectors = max_hw_sectors;
+	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
+				    BLK_DEF_MAX_SECTORS);
 }
 EXPORT_SYMBOL(blk_limits_max_hw_sectors);
 
@@ -303,6 +285,7 @@ EXPORT_SYMBOL(blk_queue_chunk_sectors);
 void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors)
 {
+	q->limits.max_hw_discard_sectors = max_discard_sectors;
 	q->limits.max_discard_sectors = max_discard_sectors;
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
@@ -550,6 +533,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
+	t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
+					    b->virt_boundary_mask);
 
 	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
 	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
@@ -641,6 +626,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
 						      b->max_discard_sectors);
+		t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
+							 b->max_hw_discard_sectors);
 		t->discard_granularity = max(t->discard_granularity,
 					     b->discard_granularity);
 		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
@@ -788,6 +775,17 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
 EXPORT_SYMBOL(blk_queue_segment_boundary);
 
 /**
+ * blk_queue_virt_boundary - set boundary rules for bio merging
+ * @q:  the request queue for the device
+ * @mask:  the memory boundary mask
+ **/
+void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
+{
+	q->limits.virt_boundary_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_virt_boundary);
+
+/**
  * blk_queue_dma_alignment - set dma length and memory alignment
  * @q:     the request queue for the device
  * @mask:  alignment mask
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6264b382d4d1..3e44a9da2a13 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -145,12 +145,43 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 	return queue_var_show(q->limits.discard_granularity, page);
 }
 
+static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
+{
+	unsigned long long val;
+
+	val = q->limits.max_hw_discard_sectors << 9;
+	return sprintf(page, "%llu\n", val);
+}
+
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 {
 	return sprintf(page, "%llu\n",
 		       (unsigned long long)q->limits.max_discard_sectors << 9);
 }
 
+static ssize_t queue_discard_max_store(struct request_queue *q,
+				       const char *page, size_t count)
+{
+	unsigned long max_discard;
+	ssize_t ret = queue_var_store(&max_discard, page, count);
+
+	if (ret < 0)
+		return ret;
+
+	if (max_discard & (q->limits.discard_granularity - 1))
+		return -EINVAL;
+
+	max_discard >>= 9;
+	if (max_discard > UINT_MAX)
+		return -EINVAL;
+
+	if (max_discard > q->limits.max_hw_discard_sectors)
+		max_discard = q->limits.max_hw_discard_sectors;
+
+	q->limits.max_discard_sectors = max_discard;
+	return ret;
+}
+
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(queue_discard_zeroes_data(q), page);
@@ -360,9 +391,15 @@ static struct queue_sysfs_entry queue_discard_granularity_entry = {
 	.show = queue_discard_granularity_show,
 };
 
+static struct queue_sysfs_entry queue_discard_max_hw_entry = {
+	.attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO },
+	.show = queue_discard_max_hw_show,
+};
+
 static struct queue_sysfs_entry queue_discard_max_entry = {
-	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
+	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_discard_max_show,
+	.store = queue_discard_max_store,
 };
 
 static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
@@ -421,6 +458,7 @@ static struct attribute *default_attrs[] = {
 	&queue_io_opt_entry.attr,
 	&queue_discard_granularity_entry.attr,
 	&queue_discard_max_entry.attr,
+	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
 	&queue_write_same_max_entry.attr,
 	&queue_nonrot_entry.attr,
@@ -523,6 +561,9 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_trace_shutdown(q);
 
+	if (q->bio_split)
+		bioset_free(q->bio_split);
+
 	ida_simple_remove(&blk_queue_ida, q->id);
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);
 }
diff --git a/block/blk.h b/block/blk.h
index 026d9594142b..838188b35a83 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -22,6 +22,12 @@ struct blk_flush_queue {
 	struct list_head	flush_queue[2];
 	struct list_head	flush_data_in_flight;
 	struct request		*flush_rq;
+
+	/*
+	 * flush_rq shares tag with this rq, both can't be active
+	 * at the same time
+	 */
+	struct request		*orig_rq;
 	spinlock_t		mq_flush_lock;
 };
 
diff --git a/block/bounce.c b/block/bounce.c
index b17311227c12..0611aea1cfe9 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -123,7 +123,7 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 	}
 }
 
-static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
+static void bounce_end_io(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
 	struct bio_vec *bvec, *org_vec;
@@ -141,61 +141,44 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
 		mempool_free(bvec->bv_page, pool);
 	}
 
-	bio_endio(bio_orig, err);
+	bio_orig->bi_error = bio->bi_error;
+	bio_endio(bio_orig);
 	bio_put(bio);
 }
 
-static void bounce_end_io_write(struct bio *bio, int err)
+static void bounce_end_io_write(struct bio *bio)
 {
-	bounce_end_io(bio, page_pool, err);
+	bounce_end_io(bio, page_pool);
 }
 
-static void bounce_end_io_write_isa(struct bio *bio, int err)
+static void bounce_end_io_write_isa(struct bio *bio)
 {
 
-	bounce_end_io(bio, isa_page_pool, err);
+	bounce_end_io(bio, isa_page_pool);
 }
 
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
+static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
 
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		copy_to_high_bio_irq(bio_orig, bio);
 
-	bounce_end_io(bio, pool, err);
+	bounce_end_io(bio, pool);
 }
 
-static void bounce_end_io_read(struct bio *bio, int err)
+static void bounce_end_io_read(struct bio *bio)
 {
-	__bounce_end_io_read(bio, page_pool, err);
+	__bounce_end_io_read(bio, page_pool);
 }
 
-static void bounce_end_io_read_isa(struct bio *bio, int err)
+static void bounce_end_io_read_isa(struct bio *bio)
 {
-	__bounce_end_io_read(bio, isa_page_pool, err);
+	__bounce_end_io_read(bio, isa_page_pool);
 }
 
-#ifdef CONFIG_NEED_BOUNCE_POOL
-static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
-{
-	if (bio_data_dir(bio) != WRITE)
-		return 0;
-
-	if (!bdi_cap_stable_pages_required(&q->backing_dev_info))
-		return 0;
-
-	return test_bit(BIO_SNAP_STABLE, &bio->bi_flags);
-}
-#else
-static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
-{
-	return 0;
-}
-#endif /* CONFIG_NEED_BOUNCE_POOL */
-
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
-			       mempool_t *pool, int force)
+			       mempool_t *pool)
 {
 	struct bio *bio;
 	int rw = bio_data_dir(*bio_orig);
@@ -203,8 +186,6 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	struct bvec_iter iter;
 	unsigned i;
 
-	if (force)
-		goto bounce;
 	bio_for_each_segment(from, *bio_orig, iter)
 		if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q))
 			goto bounce;
@@ -216,7 +197,7 @@ bounce:
 	bio_for_each_segment_all(to, bio, i) {
 		struct page *page = to->bv_page;
 
-		if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
+		if (page_to_pfn(page) <= queue_bounce_pfn(q))
 			continue;
 
 		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
@@ -254,7 +235,6 @@ bounce:
 
 void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 {
-	int must_bounce;
 	mempool_t *pool;
 
 	/*
@@ -263,15 +243,13 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	if (!bio_has_data(*bio_orig))
 		return;
 
-	must_bounce = must_snapshot_stable_pages(q, *bio_orig);
-
 	/*
 	 * for non-isa bounce case, just check if the bounce pfn is equal
 	 * to or bigger than the highest pfn in the system -- in that case,
 	 * don't waste time iterating over bio segments
 	 */
 	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (queue_bounce_pfn(q) >= blk_max_pfn && !must_bounce)
+		if (queue_bounce_pfn(q) >= blk_max_pfn)
 			return;
 		pool = page_pool;
 	} else {
@@ -282,7 +260,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	/*
 	 * slow path
 	 */
-	__blk_queue_bounce(q, bio_orig, pool, must_bounce);
+	__blk_queue_bounce(q, bio_orig, pool);
 }
 
 EXPORT_SYMBOL(blk_queue_bounce);
diff --git a/block/genhd.c b/block/genhd.c
index 59a1395eedac..0c706f33a599 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1110,8 +1110,7 @@ static void disk_release(struct device *dev)
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
-	free_part_stats(&disk->part0);
-	free_part_info(&disk->part0);
+	hd_free_part(&disk->part0);
 	if (disk->queue)
 		blk_put_queue(disk->queue);
 	kfree(disk);
@@ -1285,7 +1284,11 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 		 * converted to make use of bd_mutex and sequence counters.
 		 */
 		seqcount_init(&disk->part0.nr_sects_seq);
-		hd_ref_init(&disk->part0);
+		if (hd_ref_init(&disk->part0)) {
+			hd_free_part(&disk->part0);
+			kfree(disk);
+			return NULL;
+		}
 
 		disk->minors = minors;
 		rand_initialize_disk(disk);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 0d9e5f97f0a8..e7711133284e 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -212,8 +212,7 @@ static void part_release(struct device *dev)
 {
 	struct hd_struct *p = dev_to_part(dev);
 	blk_free_devt(dev->devt);
-	free_part_stats(p);
-	free_part_info(p);
+	hd_free_part(p);
 	kfree(p);
 }
 
@@ -233,8 +232,9 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
 	put_device(part_to_dev(part));
 }
 
-void __delete_partition(struct hd_struct *part)
+void __delete_partition(struct percpu_ref *ref)
 {
+	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
 	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
 }
 
@@ -255,7 +255,7 @@ void delete_partition(struct gendisk *disk, int partno)
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
 
-	hd_struct_put(part);
+	hd_struct_kill(part);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -356,8 +356,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
-	hd_ref_init(p);
-	return p;
+	if (!hd_ref_init(p))
+		return p;
 
 out_free_info:
 	free_part_info(p);
diff --git a/certs/Kconfig b/certs/Kconfig
new file mode 100644
index 000000000000..b030b9c7ed34
--- /dev/null
+++ b/certs/Kconfig
@@ -0,0 +1,42 @@
+menu "Certificates for signature checking"
+
+config MODULE_SIG_KEY
+	string "File name or PKCS#11 URI of module signing key"
+	default "certs/signing_key.pem"
+	depends on MODULE_SIG
+	help
+         Provide the file name of a private key/certificate in PEM format,
+         or a PKCS#11 URI according to RFC7512. The file should contain, or
+         the URI should identify, both the certificate and its corresponding
+         private key.
+
+         If this option is unchanged from its default "certs/signing_key.pem",
+         then the kernel will automatically generate the private key and
+         certificate as described in Documentation/module-signing.txt
+
+config SYSTEM_TRUSTED_KEYRING
+	bool "Provide system-wide ring of trusted keys"
+	depends on KEYS
+	help
+	  Provide a system keyring to which trusted keys can be added.  Keys in
+	  the keyring are considered to be trusted.  Keys may be added at will
+	  by the kernel from compiled-in data and from hardware key stores, but
+	  userspace may only add extra keys if those keys can be verified by
+	  keys already in the keyring.
+
+	  Keys in this keyring are used by module signature checking.
+
+config SYSTEM_TRUSTED_KEYS
+	string "Additional X.509 keys for default system keyring"
+	depends on SYSTEM_TRUSTED_KEYRING
+	help
+	  If set, this option should be the filename of a PEM-formatted file
+	  containing trusted X.509 certificates to be included in the default
+	  system keyring. Any certificate used for module signing is implicitly
+	  also trusted.
+
+	  NOTE: If you previously provided keys for the system keyring in the
+	  form of DER-encoded *.x509 files in the top-level build directory,
+	  those are no longer used. You will need to set this option instead.
+
+endmenu
diff --git a/certs/Makefile b/certs/Makefile
new file mode 100644
index 000000000000..28ac694dd11a
--- /dev/null
+++ b/certs/Makefile
@@ -0,0 +1,94 @@
+#
+# Makefile for the linux kernel signature checking certificates.
+#
+
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
+
+ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
+
+$(eval $(call config_filename,SYSTEM_TRUSTED_KEYS))
+
+# GCC doesn't include .incbin files in -MD generated dependencies (PR#66871)
+$(obj)/system_certificates.o: $(obj)/x509_certificate_list
+
+# Cope with signing_key.x509 existing in $(srctree) not $(objtree)
+AFLAGS_system_certificates.o := -I$(srctree)
+
+quiet_cmd_extract_certs  = EXTRACT_CERTS   $(patsubst "%",%,$(2))
+      cmd_extract_certs  = scripts/extract-cert $(2) $@ || ( rm $@; exit 1)
+
+targets += x509_certificate_list
+$(obj)/x509_certificate_list: scripts/extract-cert $(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(SYSTEM_TRUSTED_KEYS_FILENAME) FORCE
+	$(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS))
+endif
+
+clean-files := x509_certificate_list .x509.list
+
+ifeq ($(CONFIG_MODULE_SIG),y)
+###############################################################################
+#
+# If module signing is requested, say by allyesconfig, but a key has not been
+# supplied, then one will need to be generated to make sure the build does not
+# fail and that the kernel may be used afterwards.
+#
+###############################################################################
+ifndef CONFIG_MODULE_SIG_HASH
+$(error Could not determine digest type to use from kernel config)
+endif
+
+# We do it this way rather than having a boolean option for enabling an
+# external private key, because 'make randconfig' might enable such a
+# boolean option and we unfortunately can't make it depend on !RANDCONFIG.
+ifeq ($(CONFIG_MODULE_SIG_KEY),"certs/signing_key.pem")
+$(obj)/signing_key.pem: $(obj)/x509.genkey
+	@echo "###"
+	@echo "### Now generating an X.509 key pair to be used for signing modules."
+	@echo "###"
+	@echo "### If this takes a long time, you might wish to run rngd in the"
+	@echo "### background to keep the supply of entropy topped up.  It"
+	@echo "### needs to be run as root, and uses a hardware random"
+	@echo "### number generator if one is available."
+	@echo "###"
+	openssl req -new -nodes -utf8 -$(CONFIG_MODULE_SIG_HASH) -days 36500 \
+		-batch -x509 -config $(obj)/x509.genkey \
+		-outform PEM -out $(obj)/signing_key.pem \
+		-keyout $(obj)/signing_key.pem 2>&1
+	@echo "###"
+	@echo "### Key pair generated."
+	@echo "###"
+
+$(obj)/x509.genkey:
+	@echo Generating X.509 key generation config
+	@echo  >$@ "[ req ]"
+	@echo >>$@ "default_bits = 4096"
+	@echo >>$@ "distinguished_name = req_distinguished_name"
+	@echo >>$@ "prompt = no"
+	@echo >>$@ "string_mask = utf8only"
+	@echo >>$@ "x509_extensions = myexts"
+	@echo >>$@
+	@echo >>$@ "[ req_distinguished_name ]"
+	@echo >>$@ "#O = Unspecified company"
+	@echo >>$@ "CN = Build time autogenerated kernel key"
+	@echo >>$@ "#emailAddress = unspecified.user@unspecified.company"
+	@echo >>$@
+	@echo >>$@ "[ myexts ]"
+	@echo >>$@ "basicConstraints=critical,CA:FALSE"
+	@echo >>$@ "keyUsage=digitalSignature"
+	@echo >>$@ "subjectKeyIdentifier=hash"
+	@echo >>$@ "authorityKeyIdentifier=keyid"
+endif
+
+$(eval $(call config_filename,MODULE_SIG_KEY))
+
+# If CONFIG_MODULE_SIG_KEY isn't a PKCS#11 URI, depend on it
+ifeq ($(patsubst pkcs11:%,%,$(firstword $(MODULE_SIG_KEY_FILENAME))),$(firstword $(MODULE_SIG_KEY_FILENAME)))
+X509_DEP := $(MODULE_SIG_KEY_SRCPREFIX)$(MODULE_SIG_KEY_FILENAME)
+endif
+
+# GCC PR#66871 again.
+$(obj)/system_certificates.o: $(obj)/signing_key.x509
+
+targets += signing_key.x509
+$(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE
+	$(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY))
+endif
diff --git a/kernel/system_certificates.S b/certs/system_certificates.S
index 3e9868d47535..9216e8c81764 100644
--- a/kernel/system_certificates.S
+++ b/certs/system_certificates.S
@@ -7,7 +7,10 @@
 	.globl VMLINUX_SYMBOL(system_certificate_list)
 VMLINUX_SYMBOL(system_certificate_list):
 __cert_list_start:
-	.incbin "kernel/x509_certificate_list"
+#ifdef CONFIG_MODULE_SIG
+	.incbin "certs/signing_key.x509"
+#endif
+	.incbin "certs/x509_certificate_list"
 __cert_list_end:
 
 	.align 8
diff --git a/kernel/system_keyring.c b/certs/system_keyring.c
index 875f64e8935b..2570598b784d 100644
--- a/kernel/system_keyring.c
+++ b/certs/system_keyring.c
@@ -16,7 +16,7 @@
 #include <linux/err.h>
 #include <keys/asymmetric-type.h>
 #include <keys/system_keyring.h>
-#include "module-internal.h"
+#include <crypto/pkcs7.h>
 
 struct key *system_trusted_keyring;
 EXPORT_SYMBOL_GPL(system_trusted_keyring);
@@ -104,3 +104,54 @@ dodgy_cert:
 	return 0;
 }
 late_initcall(load_system_certificate_list);
+
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+
+/**
+ * Verify a PKCS#7-based signature on system data.
+ * @data: The data to be verified.
+ * @len: Size of @data.
+ * @raw_pkcs7: The PKCS#7 message that is the signature.
+ * @pkcs7_len: The size of @raw_pkcs7.
+ * @usage: The use to which the key is being put.
+ */
+int system_verify_data(const void *data, unsigned long len,
+		       const void *raw_pkcs7, size_t pkcs7_len,
+		       enum key_being_used_for usage)
+{
+	struct pkcs7_message *pkcs7;
+	bool trusted;
+	int ret;
+
+	pkcs7 = pkcs7_parse_message(raw_pkcs7, pkcs7_len);
+	if (IS_ERR(pkcs7))
+		return PTR_ERR(pkcs7);
+
+	/* The data should be detached - so we need to supply it. */
+	if (pkcs7_supply_detached_data(pkcs7, data, len) < 0) {
+		pr_err("PKCS#7 signature with non-detached data\n");
+		ret = -EBADMSG;
+		goto error;
+	}
+
+	ret = pkcs7_verify(pkcs7, usage);
+	if (ret < 0)
+		goto error;
+
+	ret = pkcs7_validate_trust(pkcs7, system_trusted_keyring, &trusted);
+	if (ret < 0)
+		goto error;
+
+	if (!trusted) {
+		pr_err("PKCS#7 signature not signed with a trusted key\n");
+		ret = -ENOKEY;
+	}
+
+error:
+	pkcs7_free_message(pkcs7);
+	pr_devel("<==%s() = %d\n", __func__, ret);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(system_verify_data);
+
+#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
diff --git a/crypto/Kconfig b/crypto/Kconfig
index b4cfc5754033..48ee3e175dac 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -48,6 +48,8 @@ config CRYPTO_AEAD
 config CRYPTO_AEAD2
 	tristate
 	select CRYPTO_ALGAPI2
+	select CRYPTO_NULL2
+	select CRYPTO_RNG2
 
 config CRYPTO_BLKCIPHER
 	tristate
@@ -150,12 +152,16 @@ config CRYPTO_GF128MUL
 
 config CRYPTO_NULL
 	tristate "Null algorithms"
-	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_HASH
+	select CRYPTO_NULL2
 	help
 	  These are 'Null' algorithms, used by IPsec, which do nothing.
 
+config CRYPTO_NULL2
+	tristate
+	select CRYPTO_ALGAPI2
+	select CRYPTO_BLKCIPHER2
+	select CRYPTO_HASH2
+
 config CRYPTO_PCRYPT
 	tristate "Parallel crypto engine"
 	depends on SMP
@@ -200,6 +206,7 @@ config CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_HASH
+	select CRYPTO_NULL
 	help
 	  Authenc: Combined mode wrapper for IPsec.
 	  This is required for IPSec.
@@ -470,6 +477,18 @@ config CRYPTO_POLY1305
 	  It is used for the ChaCha20-Poly1305 AEAD, specified in RFC7539 for use
 	  in IETF protocols. This is the portable C implementation of Poly1305.
 
+config CRYPTO_POLY1305_X86_64
+	tristate "Poly1305 authenticator algorithm (x86_64/SSE2/AVX2)"
+	depends on X86 && 64BIT
+	select CRYPTO_POLY1305
+	help
+	  Poly1305 authenticator algorithm, RFC7539.
+
+	  Poly1305 is an authenticator algorithm designed by Daniel J. Bernstein.
+	  It is used for the ChaCha20-Poly1305 AEAD, specified in RFC7539 for use
+	  in IETF protocols. This is the x86_64 assembler implementation using SIMD
+	  instructions.
+
 config CRYPTO_MD4
 	tristate "MD4 digest algorithm"
 	select CRYPTO_HASH
@@ -1213,6 +1232,21 @@ config CRYPTO_CHACHA20
 	  See also:
 	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
 
+config CRYPTO_CHACHA20_X86_64
+	tristate "ChaCha20 cipher algorithm (x86_64/SSSE3/AVX2)"
+	depends on X86 && 64BIT
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_CHACHA20
+	help
+	  ChaCha20 cipher algorithm, RFC7539.
+
+	  ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
+	  Bernstein and further specified in RFC7539 for use in IETF protocols.
+	  This is the x86_64 assembler implementation using SIMD instructions.
+
+	  See also:
+	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
+
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
 	select CRYPTO_ALGAPI
@@ -1601,5 +1635,6 @@ config CRYPTO_HASH_INFO
 
 source "drivers/crypto/Kconfig"
 source crypto/asymmetric_keys/Kconfig
+source certs/Kconfig
 
 endif	# if CRYPTO
diff --git a/crypto/Makefile b/crypto/Makefile
index a16a7e7f2d60..e2c59819b236 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_CRYPTO_AEAD2) += aead.o
 
 crypto_blkcipher-y := ablkcipher.o
 crypto_blkcipher-y += blkcipher.o
+crypto_blkcipher-y += skcipher.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += chainiv.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += eseqiv.o
@@ -46,7 +47,7 @@ obj-$(CONFIG_CRYPTO_CMAC) += cmac.o
 obj-$(CONFIG_CRYPTO_HMAC) += hmac.o
 obj-$(CONFIG_CRYPTO_VMAC) += vmac.o
 obj-$(CONFIG_CRYPTO_XCBC) += xcbc.o
-obj-$(CONFIG_CRYPTO_NULL) += crypto_null.o
+obj-$(CONFIG_CRYPTO_NULL2) += crypto_null.o
 obj-$(CONFIG_CRYPTO_MD4) += md4.o
 obj-$(CONFIG_CRYPTO_MD5) += md5.o
 obj-$(CONFIG_CRYPTO_RMD128) += rmd128.o
diff --git a/crypto/aead.c b/crypto/aead.c
index 07bf99773548..9b18a1e40d6a 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -3,7 +3,7 @@
  *
  * This file provides API support for AEAD algorithms.
  *
- * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
+ * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -13,13 +13,14 @@
  */
 
 #include <crypto/internal/geniv.h>
+#include <crypto/internal/rng.h>
+#include <crypto/null.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/rtnetlink.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/cryptouser.h>
@@ -27,17 +28,6 @@
 
 #include "internal.h"
 
-struct compat_request_ctx {
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
-	struct scatterlist ivbuf[2];
-	struct scatterlist *ivsg;
-	struct aead_givcrypt_request subreq;
-};
-
-static int aead_null_givencrypt(struct aead_givcrypt_request *req);
-static int aead_null_givdecrypt(struct aead_givcrypt_request *req);
-
 static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 			    unsigned int keylen)
 {
@@ -53,7 +43,7 @@ static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 
 	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 	memcpy(alignbuffer, key, keylen);
-	ret = tfm->setkey(tfm, alignbuffer, keylen);
+	ret = crypto_aead_alg(tfm)->setkey(tfm, alignbuffer, keylen);
 	memset(alignbuffer, 0, keylen);
 	kfree(buffer);
 	return ret;
@@ -64,12 +54,10 @@ int crypto_aead_setkey(struct crypto_aead *tfm,
 {
 	unsigned long alignmask = crypto_aead_alignmask(tfm);
 
-	tfm = tfm->child;
-
 	if ((unsigned long)key & alignmask)
 		return setkey_unaligned(tfm, key, keylen);
 
-	return tfm->setkey(tfm, key, keylen);
+	return crypto_aead_alg(tfm)->setkey(tfm, key, keylen);
 }
 EXPORT_SYMBOL_GPL(crypto_aead_setkey);
 
@@ -80,100 +68,17 @@ int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 	if (authsize > crypto_aead_maxauthsize(tfm))
 		return -EINVAL;
 
-	if (tfm->setauthsize) {
-		err = tfm->setauthsize(tfm->child, authsize);
+	if (crypto_aead_alg(tfm)->setauthsize) {
+		err = crypto_aead_alg(tfm)->setauthsize(tfm, authsize);
 		if (err)
 			return err;
 	}
 
-	tfm->child->authsize = authsize;
 	tfm->authsize = authsize;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_aead_setauthsize);
 
-struct aead_old_request {
-	struct scatterlist srcbuf[2];
-	struct scatterlist dstbuf[2];
-	struct aead_request subreq;
-};
-
-unsigned int crypto_aead_reqsize(struct crypto_aead *tfm)
-{
-	return tfm->reqsize + sizeof(struct aead_old_request);
-}
-EXPORT_SYMBOL_GPL(crypto_aead_reqsize);
-
-static int old_crypt(struct aead_request *req,
-		     int (*crypt)(struct aead_request *req))
-{
-	struct aead_old_request *nreq = aead_request_ctx(req);
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct scatterlist *src, *dst;
-
-	if (req->old)
-		return crypt(req);
-
-	src = scatterwalk_ffwd(nreq->srcbuf, req->src, req->assoclen);
-	dst = req->src == req->dst ?
-	      src : scatterwalk_ffwd(nreq->dstbuf, req->dst, req->assoclen);
-
-	aead_request_set_tfm(&nreq->subreq, aead);
-	aead_request_set_callback(&nreq->subreq, aead_request_flags(req),
-				  req->base.complete, req->base.data);
-	aead_request_set_crypt(&nreq->subreq, src, dst, req->cryptlen,
-			       req->iv);
-	aead_request_set_assoc(&nreq->subreq, req->src, req->assoclen);
-
-	return crypt(&nreq->subreq);
-}
-
-static int old_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct old_aead_alg *alg = crypto_old_aead_alg(aead);
-
-	return old_crypt(req, alg->encrypt);
-}
-
-static int old_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct old_aead_alg *alg = crypto_old_aead_alg(aead);
-
-	return old_crypt(req, alg->decrypt);
-}
-
-static int no_givcrypt(struct aead_givcrypt_request *req)
-{
-	return -ENOSYS;
-}
-
-static int crypto_old_aead_init_tfm(struct crypto_tfm *tfm)
-{
-	struct old_aead_alg *alg = &tfm->__crt_alg->cra_aead;
-	struct crypto_aead *crt = __crypto_aead_cast(tfm);
-
-	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
-		return -EINVAL;
-
-	crt->setkey = alg->setkey;
-	crt->setauthsize = alg->setauthsize;
-	crt->encrypt = old_encrypt;
-	crt->decrypt = old_decrypt;
-	if (alg->ivsize) {
-		crt->givencrypt = alg->givencrypt ?: no_givcrypt;
-		crt->givdecrypt = alg->givdecrypt ?: no_givcrypt;
-	} else {
-		crt->givencrypt = aead_null_givencrypt;
-		crt->givdecrypt = aead_null_givdecrypt;
-	}
-	crt->child = __crypto_aead_cast(tfm);
-	crt->authsize = alg->maxauthsize;
-
-	return 0;
-}
-
 static void crypto_aead_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_aead *aead = __crypto_aead_cast(tfm);
@@ -187,14 +92,6 @@ static int crypto_aead_init_tfm(struct crypto_tfm *tfm)
 	struct crypto_aead *aead = __crypto_aead_cast(tfm);
 	struct aead_alg *alg = crypto_aead_alg(aead);
 
-	if (crypto_old_aead_alg(aead)->encrypt)
-		return crypto_old_aead_init_tfm(tfm);
-
-	aead->setkey = alg->setkey;
-	aead->setauthsize = alg->setauthsize;
-	aead->encrypt = alg->encrypt;
-	aead->decrypt = alg->decrypt;
-	aead->child = __crypto_aead_cast(tfm);
 	aead->authsize = alg->maxauthsize;
 
 	if (alg->exit)
@@ -207,64 +104,6 @@ static int crypto_aead_init_tfm(struct crypto_tfm *tfm)
 }
 
 #ifdef CONFIG_NET
-static int crypto_old_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_report_aead raead;
-	struct old_aead_alg *aead = &alg->cra_aead;
-
-	strncpy(raead.type, "aead", sizeof(raead.type));
-	strncpy(raead.geniv, aead->geniv ?: "<built-in>", sizeof(raead.geniv));
-
-	raead.blocksize = alg->cra_blocksize;
-	raead.maxauthsize = aead->maxauthsize;
-	raead.ivsize = aead->ivsize;
-
-	if (nla_put(skb, CRYPTOCFGA_REPORT_AEAD,
-		    sizeof(struct crypto_report_aead), &raead))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-#else
-static int crypto_old_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
-
-static void crypto_old_aead_show(struct seq_file *m, struct crypto_alg *alg)
-	__attribute__ ((unused));
-static void crypto_old_aead_show(struct seq_file *m, struct crypto_alg *alg)
-{
-	struct old_aead_alg *aead = &alg->cra_aead;
-
-	seq_printf(m, "type         : aead\n");
-	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
-					     "yes" : "no");
-	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
-	seq_printf(m, "ivsize       : %u\n", aead->ivsize);
-	seq_printf(m, "maxauthsize  : %u\n", aead->maxauthsize);
-	seq_printf(m, "geniv        : %s\n", aead->geniv ?: "<built-in>");
-}
-
-const struct crypto_type crypto_aead_type = {
-	.extsize = crypto_alg_extsize,
-	.init_tfm = crypto_aead_init_tfm,
-#ifdef CONFIG_PROC_FS
-	.show = crypto_old_aead_show,
-#endif
-	.report = crypto_old_aead_report,
-	.lookup = crypto_lookup_aead,
-	.maskclear = ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV),
-	.maskset = CRYPTO_ALG_TYPE_MASK,
-	.type = CRYPTO_ALG_TYPE_AEAD,
-	.tfmsize = offsetof(struct crypto_aead, base),
-};
-EXPORT_SYMBOL_GPL(crypto_aead_type);
-
-#ifdef CONFIG_NET
 static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_aead raead;
@@ -307,93 +146,31 @@ static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "geniv        : <none>\n");
 }
 
-static const struct crypto_type crypto_new_aead_type = {
-	.extsize = crypto_alg_extsize,
-	.init_tfm = crypto_aead_init_tfm,
-#ifdef CONFIG_PROC_FS
-	.show = crypto_aead_show,
-#endif
-	.report = crypto_aead_report,
-	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
-	.maskset = CRYPTO_ALG_TYPE_MASK,
-	.type = CRYPTO_ALG_TYPE_AEAD,
-	.tfmsize = offsetof(struct crypto_aead, base),
-};
-
-static int aead_null_givencrypt(struct aead_givcrypt_request *req)
-{
-	return crypto_aead_encrypt(&req->areq);
-}
-
-static int aead_null_givdecrypt(struct aead_givcrypt_request *req)
-{
-	return crypto_aead_decrypt(&req->areq);
-}
-
-#ifdef CONFIG_NET
-static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_report_aead raead;
-	struct old_aead_alg *aead = &alg->cra_aead;
-
-	strncpy(raead.type, "nivaead", sizeof(raead.type));
-	strncpy(raead.geniv, aead->geniv, sizeof(raead.geniv));
-
-	raead.blocksize = alg->cra_blocksize;
-	raead.maxauthsize = aead->maxauthsize;
-	raead.ivsize = aead->ivsize;
-
-	if (nla_put(skb, CRYPTOCFGA_REPORT_AEAD,
-		    sizeof(struct crypto_report_aead), &raead))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-#else
-static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
+static void crypto_aead_free_instance(struct crypto_instance *inst)
 {
-	return -ENOSYS;
-}
-#endif
-
+	struct aead_instance *aead = aead_instance(inst);
 
-static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
-	__attribute__ ((unused));
-static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
-{
-	struct old_aead_alg *aead = &alg->cra_aead;
+	if (!aead->free) {
+		inst->tmpl->free(inst);
+		return;
+	}
 
-	seq_printf(m, "type         : nivaead\n");
-	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
-					     "yes" : "no");
-	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
-	seq_printf(m, "ivsize       : %u\n", aead->ivsize);
-	seq_printf(m, "maxauthsize  : %u\n", aead->maxauthsize);
-	seq_printf(m, "geniv        : %s\n", aead->geniv);
+	aead->free(aead);
 }
 
-const struct crypto_type crypto_nivaead_type = {
+static const struct crypto_type crypto_aead_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_aead_init_tfm,
+	.free = crypto_aead_free_instance,
 #ifdef CONFIG_PROC_FS
-	.show = crypto_nivaead_show,
+	.show = crypto_aead_show,
 #endif
-	.report = crypto_nivaead_report,
-	.maskclear = ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV),
-	.maskset = CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV,
+	.report = crypto_aead_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
 	.type = CRYPTO_ALG_TYPE_AEAD,
 	.tfmsize = offsetof(struct crypto_aead, base),
 };
-EXPORT_SYMBOL_GPL(crypto_nivaead_type);
-
-static int crypto_grab_nivaead(struct crypto_aead_spawn *spawn,
-			       const char *name, u32 type, u32 mask)
-{
-	spawn->base.frontend = &crypto_nivaead_type;
-	return crypto_grab_spawn(&spawn->base, name, type, mask);
-}
 
 static int aead_geniv_setkey(struct crypto_aead *tfm,
 			     const u8 *key, unsigned int keylen)
@@ -411,169 +188,6 @@ static int aead_geniv_setauthsize(struct crypto_aead *tfm,
 	return crypto_aead_setauthsize(ctx->child, authsize);
 }
 
-static void compat_encrypt_complete2(struct aead_request *req, int err)
-{
-	struct compat_request_ctx *rctx = aead_request_ctx(req);
-	struct aead_givcrypt_request *subreq = &rctx->subreq;
-	struct crypto_aead *geniv;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	if (err)
-		goto out;
-
-	geniv = crypto_aead_reqtfm(req);
-	scatterwalk_map_and_copy(subreq->giv, rctx->ivsg, 0,
-				 crypto_aead_ivsize(geniv), 1);
-
-out:
-	kzfree(subreq->giv);
-}
-
-static void compat_encrypt_complete(struct crypto_async_request *base, int err)
-{
-	struct aead_request *req = base->data;
-
-	compat_encrypt_complete2(req, err);
-	aead_request_complete(req, err);
-}
-
-static int compat_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
-	struct compat_request_ctx *rctx = aead_request_ctx(req);
-	struct aead_givcrypt_request *subreq = &rctx->subreq;
-	unsigned int ivsize = crypto_aead_ivsize(geniv);
-	struct scatterlist *src, *dst;
-	crypto_completion_t compl;
-	void *data;
-	u8 *info;
-	__be64 seq;
-	int err;
-
-	if (req->cryptlen < ivsize)
-		return -EINVAL;
-
-	compl = req->base.complete;
-	data = req->base.data;
-
-	rctx->ivsg = scatterwalk_ffwd(rctx->ivbuf, req->dst, req->assoclen);
-	info = PageHighMem(sg_page(rctx->ivsg)) ? NULL : sg_virt(rctx->ivsg);
-
-	if (!info) {
-		info = kmalloc(ivsize, req->base.flags &
-				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
-								  GFP_ATOMIC);
-		if (!info)
-			return -ENOMEM;
-
-		compl = compat_encrypt_complete;
-		data = req;
-	}
-
-	memcpy(&seq, req->iv + ivsize - sizeof(seq), sizeof(seq));
-
-	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen + ivsize);
-	dst = req->src == req->dst ?
-	      src : scatterwalk_ffwd(rctx->dst, rctx->ivsg, ivsize);
-
-	aead_givcrypt_set_tfm(subreq, ctx->child);
-	aead_givcrypt_set_callback(subreq, req->base.flags,
-				   req->base.complete, req->base.data);
-	aead_givcrypt_set_crypt(subreq, src, dst,
-				req->cryptlen - ivsize, req->iv);
-	aead_givcrypt_set_assoc(subreq, req->src, req->assoclen);
-	aead_givcrypt_set_giv(subreq, info, be64_to_cpu(seq));
-
-	err = crypto_aead_givencrypt(subreq);
-	if (unlikely(PageHighMem(sg_page(rctx->ivsg))))
-		compat_encrypt_complete2(req, err);
-	return err;
-}
-
-static int compat_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
-	struct compat_request_ctx *rctx = aead_request_ctx(req);
-	struct aead_request *subreq = &rctx->subreq.areq;
-	unsigned int ivsize = crypto_aead_ivsize(geniv);
-	struct scatterlist *src, *dst;
-	crypto_completion_t compl;
-	void *data;
-
-	if (req->cryptlen < ivsize)
-		return -EINVAL;
-
-	aead_request_set_tfm(subreq, ctx->child);
-
-	compl = req->base.complete;
-	data = req->base.data;
-
-	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen + ivsize);
-	dst = req->src == req->dst ?
-	      src : scatterwalk_ffwd(rctx->dst, req->dst,
-				     req->assoclen + ivsize);
-
-	aead_request_set_callback(subreq, req->base.flags, compl, data);
-	aead_request_set_crypt(subreq, src, dst,
-			       req->cryptlen - ivsize, req->iv);
-	aead_request_set_assoc(subreq, req->src, req->assoclen);
-
-	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
-
-	return crypto_aead_decrypt(subreq);
-}
-
-static int compat_encrypt_first(struct aead_request *req)
-{
-	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
-	int err = 0;
-
-	spin_lock_bh(&ctx->lock);
-	if (geniv->encrypt != compat_encrypt_first)
-		goto unlock;
-
-	geniv->encrypt = compat_encrypt;
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	if (err)
-		return err;
-
-	return compat_encrypt(req);
-}
-
-static int aead_geniv_init_compat(struct crypto_tfm *tfm)
-{
-	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	crypto_aead_set_reqsize(geniv, sizeof(struct compat_request_ctx));
-
-	err = aead_geniv_init(tfm);
-
-	ctx->child = geniv->child;
-	geniv->child = geniv;
-
-	return err;
-}
-
-static void aead_geniv_exit_compat(struct crypto_tfm *tfm)
-{
-	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
-	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
-
-	crypto_free_aead(ctx->child);
-}
-
 struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 				       struct rtattr **tb, u32 type, u32 mask)
 {
@@ -590,8 +204,7 @@ struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	if (IS_ERR(algt))
 		return ERR_CAST(algt);
 
-	if ((algt->type ^ (CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_GENIV)) &
-	    algt->mask)
+	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
 		return ERR_PTR(-EINVAL);
 
 	name = crypto_attr_alg_name(tb[1]);
@@ -608,9 +221,7 @@ struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	mask |= crypto_requires_sync(algt->type, algt->mask);
 
 	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
-	err = (algt->mask & CRYPTO_ALG_GENIV) ?
-	      crypto_grab_nivaead(spawn, name, type, mask) :
-	      crypto_grab_aead(spawn, name, type, mask);
+	err = crypto_grab_aead(spawn, name, type, mask);
 	if (err)
 		goto err_free_inst;
 
@@ -623,43 +234,6 @@ struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	if (ivsize < sizeof(u64))
 		goto err_drop_alg;
 
-	/*
-	 * This is only true if we're constructing an algorithm with its
-	 * default IV generator.  For the default generator we elide the
-	 * template name and double-check the IV generator.
-	 */
-	if (algt->mask & CRYPTO_ALG_GENIV) {
-		if (!alg->base.cra_aead.encrypt)
-			goto err_drop_alg;
-		if (strcmp(tmpl->name, alg->base.cra_aead.geniv))
-			goto err_drop_alg;
-
-		memcpy(inst->alg.base.cra_name, alg->base.cra_name,
-		       CRYPTO_MAX_ALG_NAME);
-		memcpy(inst->alg.base.cra_driver_name,
-		       alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME);
-
-		inst->alg.base.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					   CRYPTO_ALG_GENIV;
-		inst->alg.base.cra_flags |= alg->base.cra_flags &
-					    CRYPTO_ALG_ASYNC;
-		inst->alg.base.cra_priority = alg->base.cra_priority;
-		inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
-		inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
-		inst->alg.base.cra_type = &crypto_aead_type;
-
-		inst->alg.base.cra_aead.ivsize = ivsize;
-		inst->alg.base.cra_aead.maxauthsize = maxauthsize;
-
-		inst->alg.base.cra_aead.setkey = alg->base.cra_aead.setkey;
-		inst->alg.base.cra_aead.setauthsize =
-			alg->base.cra_aead.setauthsize;
-		inst->alg.base.cra_aead.encrypt = alg->base.cra_aead.encrypt;
-		inst->alg.base.cra_aead.decrypt = alg->base.cra_aead.decrypt;
-
-		goto out;
-	}
-
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
 		     "%s(%s)", tmpl->name, alg->base.cra_name) >=
@@ -682,12 +256,6 @@ struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	inst->alg.ivsize = ivsize;
 	inst->alg.maxauthsize = maxauthsize;
 
-	inst->alg.encrypt = compat_encrypt_first;
-	inst->alg.decrypt = compat_decrypt;
-
-	inst->alg.base.cra_init = aead_geniv_init_compat;
-	inst->alg.base.cra_exit = aead_geniv_exit_compat;
-
 out:
 	return inst;
 
@@ -707,147 +275,58 @@ void aead_geniv_free(struct aead_instance *inst)
 }
 EXPORT_SYMBOL_GPL(aead_geniv_free);
 
-int aead_geniv_init(struct crypto_tfm *tfm)
+int aead_init_geniv(struct crypto_aead *aead)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(aead);
+	struct aead_instance *inst = aead_alg_instance(aead);
 	struct crypto_aead *child;
-	struct crypto_aead *aead;
-
-	aead = __crypto_aead_cast(tfm);
-
-	child = crypto_spawn_aead(crypto_instance_ctx(inst));
-	if (IS_ERR(child))
-		return PTR_ERR(child);
-
-	aead->child = child;
-	aead->reqsize += crypto_aead_reqsize(child);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(aead_geniv_init);
-
-void aead_geniv_exit(struct crypto_tfm *tfm)
-{
-	crypto_free_aead(__crypto_aead_cast(tfm)->child);
-}
-EXPORT_SYMBOL_GPL(aead_geniv_exit);
-
-static int crypto_nivaead_default(struct crypto_alg *alg, u32 type, u32 mask)
-{
-	struct rtattr *tb[3];
-	struct {
-		struct rtattr attr;
-		struct crypto_attr_type data;
-	} ptype;
-	struct {
-		struct rtattr attr;
-		struct crypto_attr_alg data;
-	} palg;
-	struct crypto_template *tmpl;
-	struct crypto_instance *inst;
-	struct crypto_alg *larval;
-	const char *geniv;
 	int err;
 
-	larval = crypto_larval_lookup(alg->cra_driver_name,
-				      CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_GENIV,
-				      CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	err = PTR_ERR(larval);
-	if (IS_ERR(larval))
-		goto out;
-
-	err = -EAGAIN;
-	if (!crypto_is_larval(larval))
-		goto drop_larval;
-
-	ptype.attr.rta_len = sizeof(ptype);
-	ptype.attr.rta_type = CRYPTOA_TYPE;
-	ptype.data.type = type | CRYPTO_ALG_GENIV;
-	/* GENIV tells the template that we're making a default geniv. */
-	ptype.data.mask = mask | CRYPTO_ALG_GENIV;
-	tb[0] = &ptype.attr;
-
-	palg.attr.rta_len = sizeof(palg);
-	palg.attr.rta_type = CRYPTOA_ALG;
-	/* Must use the exact name to locate ourselves. */
-	memcpy(palg.data.name, alg->cra_driver_name, CRYPTO_MAX_ALG_NAME);
-	tb[1] = &palg.attr;
-
-	tb[2] = NULL;
+	spin_lock_init(&ctx->lock);
 
-	geniv = alg->cra_aead.geniv;
+	err = crypto_get_default_rng();
+	if (err)
+		goto out;
 
-	tmpl = crypto_lookup_template(geniv);
-	err = -ENOENT;
-	if (!tmpl)
-		goto kill_larval;
+	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+				   crypto_aead_ivsize(aead));
+	crypto_put_default_rng();
+	if (err)
+		goto out;
 
-	if (tmpl->create) {
-		err = tmpl->create(tmpl, tb);
-		if (err)
-			goto put_tmpl;
-		goto ok;
-	}
+	ctx->null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(ctx->null);
+	if (IS_ERR(ctx->null))
+		goto out;
 
-	inst = tmpl->alloc(tb);
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto put_tmpl;
+	child = crypto_spawn_aead(aead_instance_ctx(inst));
+	err = PTR_ERR(child);
+	if (IS_ERR(child))
+		goto drop_null;
 
-	err = crypto_register_instance(tmpl, inst);
-	if (err) {
-		tmpl->free(inst);
-		goto put_tmpl;
-	}
+	ctx->child = child;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(child) +
+				      sizeof(struct aead_request));
 
-ok:
-	/* Redo the lookup to use the instance we just registered. */
-	err = -EAGAIN;
+	err = 0;
 
-put_tmpl:
-	crypto_tmpl_put(tmpl);
-kill_larval:
-	crypto_larval_kill(larval);
-drop_larval:
-	crypto_mod_put(larval);
 out:
-	crypto_mod_put(alg);
 	return err;
+
+drop_null:
+	crypto_put_default_null_skcipher();
+	goto out;
 }
+EXPORT_SYMBOL_GPL(aead_init_geniv);
 
-struct crypto_alg *crypto_lookup_aead(const char *name, u32 type, u32 mask)
+void aead_exit_geniv(struct crypto_aead *tfm)
 {
-	struct crypto_alg *alg;
-
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return alg;
-
-	if (alg->cra_type == &crypto_aead_type)
-		return alg;
-
-	if (!alg->cra_aead.ivsize)
-		return alg;
-
-	crypto_mod_put(alg);
-	alg = crypto_alg_mod_lookup(name, type | CRYPTO_ALG_TESTED,
-				    mask & ~CRYPTO_ALG_TESTED);
-	if (IS_ERR(alg))
-		return alg;
-
-	if (alg->cra_type == &crypto_aead_type) {
-		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
-			crypto_mod_put(alg);
-			alg = ERR_PTR(-ENOENT);
-		}
-		return alg;
-	}
-
-	BUG_ON(!alg->cra_aead.ivsize);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
 
-	return ERR_PTR(crypto_nivaead_default(alg, type, mask));
+	crypto_free_aead(ctx->child);
+	crypto_put_default_null_skcipher();
 }
-EXPORT_SYMBOL_GPL(crypto_lookup_aead);
+EXPORT_SYMBOL_GPL(aead_exit_geniv);
 
 int crypto_grab_aead(struct crypto_aead_spawn *spawn, const char *name,
 		     u32 type, u32 mask)
@@ -870,7 +349,7 @@ static int aead_prepare_alg(struct aead_alg *alg)
 	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
 		return -EINVAL;
 
-	base->cra_type = &crypto_new_aead_type;
+	base->cra_type = &crypto_aead_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AEAD;
 
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 3c079b7f23f6..d130b41dbaea 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -67,12 +67,22 @@ static int crypto_check_alg(struct crypto_alg *alg)
 	return crypto_set_driver_name(alg);
 }
 
+static void crypto_free_instance(struct crypto_instance *inst)
+{
+	if (!inst->alg.cra_type->free) {
+		inst->tmpl->free(inst);
+		return;
+	}
+
+	inst->alg.cra_type->free(inst);
+}
+
 static void crypto_destroy_instance(struct crypto_alg *alg)
 {
 	struct crypto_instance *inst = (void *)alg;
 	struct crypto_template *tmpl = inst->tmpl;
 
-	tmpl->free(inst);
+	crypto_free_instance(inst);
 	crypto_tmpl_put(tmpl);
 }
 
@@ -481,7 +491,7 @@ void crypto_unregister_template(struct crypto_template *tmpl)
 
 	hlist_for_each_entry_safe(inst, n, list, list) {
 		BUG_ON(atomic_read(&inst->alg.cra_refcnt) != 1);
-		tmpl->free(inst);
+		crypto_free_instance(inst);
 	}
 	crypto_remove_final(&users);
 }
@@ -892,7 +902,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(crypto_enqueue_request);
 
-void *__crypto_dequeue_request(struct crypto_queue *queue, unsigned int offset)
+struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue)
 {
 	struct list_head *request;
 
@@ -907,14 +917,7 @@ void *__crypto_dequeue_request(struct crypto_queue *queue, unsigned int offset)
 	request = queue->list.next;
 	list_del(request);
 
-	return (char *)list_entry(request, struct crypto_async_request, list) -
-	       offset;
-}
-EXPORT_SYMBOL_GPL(__crypto_dequeue_request);
-
-struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue)
-{
-	return __crypto_dequeue_request(queue, 0);
+	return list_entry(request, struct crypto_async_request, list);
 }
 EXPORT_SYMBOL_GPL(crypto_dequeue_request);
 
diff --git a/crypto/algboss.c b/crypto/algboss.c
index 76fc0b23fc6c..6e39d9c05b98 100644
--- a/crypto/algboss.c
+++ b/crypto/algboss.c
@@ -248,13 +248,11 @@ static int cryptomgr_schedule_test(struct crypto_alg *alg)
 	type = alg->cra_flags;
 
 	/* This piece of crap needs to disappear into per-type test hooks. */
-	if ((!((type ^ CRYPTO_ALG_TYPE_BLKCIPHER) &
-	       CRYPTO_ALG_TYPE_BLKCIPHER_MASK) && !(type & CRYPTO_ALG_GENIV) &&
-	     ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	      CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					  alg->cra_ablkcipher.ivsize)) ||
-	    (!((type ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK) &&
-	     alg->cra_type == &crypto_nivaead_type && alg->cra_aead.ivsize))
+	if (!((type ^ CRYPTO_ALG_TYPE_BLKCIPHER) &
+	      CRYPTO_ALG_TYPE_BLKCIPHER_MASK) && !(type & CRYPTO_ALG_GENIV) &&
+	    ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	     CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
+					 alg->cra_ablkcipher.ivsize))
 		type |= CRYPTO_ALG_TESTED;
 
 	param->type = type;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index e0408a480d2f..0aa6fdfb448a 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -90,6 +90,7 @@ static void aead_put_sgl(struct sock *sk)
 		put_page(sg_page(sg + i));
 		sg_assign_page(sg + i, NULL);
 	}
+	sg_init_table(sg, ALG_MAX_PAGES);
 	sgl->cur = 0;
 	ctx->used = 0;
 	ctx->more = 0;
@@ -514,8 +515,7 @@ static struct proto_ops algif_aead_ops = {
 
 static void *aead_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_aead(name, type | CRYPTO_ALG_AEAD_NEW,
-				 mask | CRYPTO_ALG_AEAD_NEW);
+	return crypto_alloc_aead(name, type, mask);
 }
 
 static void aead_release(void *private)
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 945075292bc9..af31a0ee4057 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -145,7 +145,7 @@ static int skcipher_alloc_sgl(struct sock *sk)
 		sgl->cur = 0;
 
 		if (sg)
-			scatterwalk_sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg);
+			sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg);
 
 		list_add_tail(&sgl->list, &ctx->tsgl);
 	}
diff --git a/crypto/asymmetric_keys/Makefile b/crypto/asymmetric_keys/Makefile
index e47fcd9ac5e8..cd1406f9b14a 100644
--- a/crypto/asymmetric_keys/Makefile
+++ b/crypto/asymmetric_keys/Makefile
@@ -15,15 +15,21 @@ obj-$(CONFIG_PUBLIC_KEY_ALGO_RSA) += rsa.o
 obj-$(CONFIG_X509_CERTIFICATE_PARSER) += x509_key_parser.o
 x509_key_parser-y := \
 	x509-asn1.o \
+	x509_akid-asn1.o \
 	x509_rsakey-asn1.o \
 	x509_cert_parser.o \
 	x509_public_key.o
 
-$(obj)/x509_cert_parser.o: $(obj)/x509-asn1.h $(obj)/x509_rsakey-asn1.h
+$(obj)/x509_cert_parser.o: \
+	$(obj)/x509-asn1.h \
+	$(obj)/x509_akid-asn1.h \
+	$(obj)/x509_rsakey-asn1.h
 $(obj)/x509-asn1.o: $(obj)/x509-asn1.c $(obj)/x509-asn1.h
+$(obj)/x509_akid-asn1.o: $(obj)/x509_akid-asn1.c $(obj)/x509_akid-asn1.h
 $(obj)/x509_rsakey-asn1.o: $(obj)/x509_rsakey-asn1.c $(obj)/x509_rsakey-asn1.h
 
 clean-files	+= x509-asn1.c x509-asn1.h
+clean-files	+= x509_akid-asn1.c x509_akid-asn1.h
 clean-files	+= x509_rsakey-asn1.c x509_rsakey-asn1.h
 
 #
diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index b0e4ed23d668..1916680ad81b 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -12,6 +12,7 @@
  */
 #include <keys/asymmetric-subtype.h>
 #include <keys/asymmetric-parser.h>
+#include <crypto/public_key.h>
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -20,6 +21,16 @@
 
 MODULE_LICENSE("GPL");
 
+const char *const key_being_used_for[NR__KEY_BEING_USED_FOR] = {
+	[VERIFYING_MODULE_SIGNATURE]		= "mod sig",
+	[VERIFYING_FIRMWARE_SIGNATURE]		= "firmware sig",
+	[VERIFYING_KEXEC_PE_SIGNATURE]		= "kexec PE sig",
+	[VERIFYING_KEY_SIGNATURE]		= "key sig",
+	[VERIFYING_KEY_SELF_SIGNATURE]		= "key self sig",
+	[VERIFYING_UNSPECIFIED_SIGNATURE]	= "unspec sig",
+};
+EXPORT_SYMBOL_GPL(key_being_used_for);
+
 static LIST_HEAD(asymmetric_key_parsers);
 static DECLARE_RWSEM(asymmetric_key_parsers_sem);
 
diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c
index 214a992123cd..adcef59eec0b 100644
--- a/crypto/asymmetric_keys/mscode_parser.c
+++ b/crypto/asymmetric_keys/mscode_parser.c
@@ -97,6 +97,15 @@ int mscode_note_digest_algo(void *context, size_t hdrlen,
 	case OID_sha256:
 		ctx->digest_algo = HASH_ALGO_SHA256;
 		break;
+	case OID_sha384:
+		ctx->digest_algo = HASH_ALGO_SHA384;
+		break;
+	case OID_sha512:
+		ctx->digest_algo = HASH_ALGO_SHA512;
+		break;
+	case OID_sha224:
+		ctx->digest_algo = HASH_ALGO_SHA224;
+		break;
 
 	case OID__NR:
 		sprint_oid(value, vlen, buffer, sizeof(buffer));
diff --git a/crypto/asymmetric_keys/pkcs7.asn1 b/crypto/asymmetric_keys/pkcs7.asn1
index a5a14ef28c86..1eca740b816a 100644
--- a/crypto/asymmetric_keys/pkcs7.asn1
+++ b/crypto/asymmetric_keys/pkcs7.asn1
@@ -1,14 +1,14 @@
 PKCS7ContentInfo ::= SEQUENCE {
-	contentType	ContentType,
+	contentType	ContentType ({ pkcs7_check_content_type }),
 	content		[0] EXPLICIT SignedData OPTIONAL
 }
 
 ContentType ::= OBJECT IDENTIFIER ({ pkcs7_note_OID })
 
 SignedData ::= SEQUENCE {
-	version			INTEGER,
+	version			INTEGER ({ pkcs7_note_signeddata_version }),
 	digestAlgorithms	DigestAlgorithmIdentifiers,
-	contentInfo		ContentInfo,
+	contentInfo		ContentInfo ({ pkcs7_note_content }),
 	certificates		CHOICE {
 		certSet		[0] IMPLICIT ExtendedCertificatesAndCertificates,
 		certSequence	[2] IMPLICIT Certificates
@@ -21,7 +21,7 @@ SignedData ::= SEQUENCE {
 }
 
 ContentInfo ::= SEQUENCE {
-	contentType	ContentType,
+	contentType	ContentType ({ pkcs7_note_OID }),
 	content		[0] EXPLICIT Data OPTIONAL
 }
 
@@ -68,8 +68,8 @@ SignerInfos ::= CHOICE {
 }
 
 SignerInfo ::= SEQUENCE {
-	version			INTEGER,
-	issuerAndSerialNumber	IssuerAndSerialNumber,
+	version			INTEGER ({ pkcs7_note_signerinfo_version }),
+	sid			SignerIdentifier, -- CMS variant, not PKCS#7
 	digestAlgorithm		DigestAlgorithmIdentifier ({ pkcs7_sig_note_digest_algo }),
 	authenticatedAttributes	CHOICE {
 		aaSet		[0] IMPLICIT SetOfAuthenticatedAttribute
@@ -88,6 +88,12 @@ SignerInfo ::= SEQUENCE {
 	} OPTIONAL
 } ({ pkcs7_note_signed_info })
 
+SignerIdentifier ::= CHOICE {
+	-- RFC5652 sec 5.3
+	issuerAndSerialNumber IssuerAndSerialNumber,
+        subjectKeyIdentifier [0] IMPLICIT SubjectKeyIdentifier
+}
+
 IssuerAndSerialNumber ::= SEQUENCE {
 	issuer			Name ({ pkcs7_sig_note_issuer }),
 	serialNumber		CertificateSerialNumber ({ pkcs7_sig_note_serial })
@@ -95,6 +101,8 @@ IssuerAndSerialNumber ::= SEQUENCE {
 
 CertificateSerialNumber ::= INTEGER
 
+SubjectKeyIdentifier ::= OCTET STRING ({ pkcs7_sig_note_skid })
+
 SetOfAuthenticatedAttribute ::= SET OF AuthenticatedAttribute
 
 AuthenticatedAttribute ::= SEQUENCE {
@@ -103,7 +111,7 @@ AuthenticatedAttribute ::= SEQUENCE {
 }
 
 UnauthenticatedAttribute ::= SEQUENCE {
-	type			OBJECT IDENTIFIER ({ pkcs7_note_OID }),
+	type			OBJECT IDENTIFIER,
 	values			SET OF ANY
 }
 
diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c
index 3d13b042da73..e2d0edbbc71a 100644
--- a/crypto/asymmetric_keys/pkcs7_key_type.c
+++ b/crypto/asymmetric_keys/pkcs7_key_type.c
@@ -14,16 +14,26 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/key-type.h>
+#include <keys/asymmetric-type.h>
 #include <crypto/pkcs7.h>
 #include <keys/user-type.h>
 #include <keys/system_keyring.h>
 #include "pkcs7_parser.h"
 
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("PKCS#7 testing key type");
+
+static unsigned pkcs7_usage;
+module_param_named(usage, pkcs7_usage, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(pkcs7_usage,
+		 "Usage to specify when verifying the PKCS#7 message");
+
 /*
  * Preparse a PKCS#7 wrapped and validated data blob.
  */
 static int pkcs7_preparse(struct key_preparsed_payload *prep)
 {
+	enum key_being_used_for usage = pkcs7_usage;
 	struct pkcs7_message *pkcs7;
 	const void *data, *saved_prep_data;
 	size_t datalen, saved_prep_datalen;
@@ -32,6 +42,11 @@ static int pkcs7_preparse(struct key_preparsed_payload *prep)
 
 	kenter("");
 
+	if (usage >= NR__KEY_BEING_USED_FOR) {
+		pr_err("Invalid usage type %d\n", usage);
+		return -EINVAL;
+	}
+
 	saved_prep_data = prep->data;
 	saved_prep_datalen = prep->datalen;
 	pkcs7 = pkcs7_parse_message(saved_prep_data, saved_prep_datalen);
@@ -40,7 +55,7 @@ static int pkcs7_preparse(struct key_preparsed_payload *prep)
 		goto error;
 	}
 
-	ret = pkcs7_verify(pkcs7);
+	ret = pkcs7_verify(pkcs7, usage);
 	if (ret < 0)
 		goto error_free;
 
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index 3bd5a1e4c493..758acabf2d81 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -33,6 +33,9 @@ struct pkcs7_parse_context {
 	unsigned	raw_serial_size;
 	unsigned	raw_issuer_size;
 	const void	*raw_issuer;
+	const void	*raw_skid;
+	unsigned	raw_skid_size;
+	bool		expect_skid;
 };
 
 /*
@@ -78,6 +81,30 @@ void pkcs7_free_message(struct pkcs7_message *pkcs7)
 }
 EXPORT_SYMBOL_GPL(pkcs7_free_message);
 
+/*
+ * Check authenticatedAttributes are provided or not provided consistently.
+ */
+static int pkcs7_check_authattrs(struct pkcs7_message *msg)
+{
+	struct pkcs7_signed_info *sinfo;
+	bool want;
+
+	sinfo = msg->signed_infos;
+	if (sinfo->authattrs) {
+		want = true;
+		msg->have_authattrs = true;
+	}
+
+	for (sinfo = sinfo->next; sinfo; sinfo = sinfo->next)
+		if (!!sinfo->authattrs != want)
+			goto inconsistent;
+	return 0;
+
+inconsistent:
+	pr_warn("Inconsistently supplied authAttrs\n");
+	return -EINVAL;
+}
+
 /**
  * pkcs7_parse_message - Parse a PKCS#7 message
  * @data: The raw binary ASN.1 encoded message to be parsed
@@ -110,6 +137,10 @@ struct pkcs7_message *pkcs7_parse_message(const void *data, size_t datalen)
 		goto out;
 	}
 
+	ret = pkcs7_check_authattrs(ctx->msg);
+	if (ret < 0)
+		goto out;
+
 	msg = ctx->msg;
 	ctx->msg = NULL;
 
@@ -198,6 +229,14 @@ int pkcs7_sig_note_digest_algo(void *context, size_t hdrlen,
 	case OID_sha256:
 		ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA256;
 		break;
+	case OID_sha384:
+		ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA384;
+		break;
+	case OID_sha512:
+		ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA512;
+		break;
+	case OID_sha224:
+		ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA224;
 	default:
 		printk("Unsupported digest algo: %u\n", ctx->last_oid);
 		return -ENOPKG;
@@ -226,6 +265,100 @@ int pkcs7_sig_note_pkey_algo(void *context, size_t hdrlen,
 }
 
 /*
+ * We only support signed data [RFC2315 sec 9].
+ */
+int pkcs7_check_content_type(void *context, size_t hdrlen,
+			     unsigned char tag,
+			     const void *value, size_t vlen)
+{
+	struct pkcs7_parse_context *ctx = context;
+
+	if (ctx->last_oid != OID_signed_data) {
+		pr_warn("Only support pkcs7_signedData type\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Note the SignedData version
+ */
+int pkcs7_note_signeddata_version(void *context, size_t hdrlen,
+				  unsigned char tag,
+				  const void *value, size_t vlen)
+{
+	struct pkcs7_parse_context *ctx = context;
+	unsigned version;
+
+	if (vlen != 1)
+		goto unsupported;
+
+	ctx->msg->version = version = *(const u8 *)value;
+	switch (version) {
+	case 1:
+		/* PKCS#7 SignedData [RFC2315 sec 9.1]
+		 * CMS ver 1 SignedData [RFC5652 sec 5.1]
+		 */
+		break;
+	case 3:
+		/* CMS ver 3 SignedData [RFC2315 sec 5.1] */
+		break;
+	default:
+		goto unsupported;
+	}
+
+	return 0;
+
+unsupported:
+	pr_warn("Unsupported SignedData version\n");
+	return -EINVAL;
+}
+
+/*
+ * Note the SignerInfo version
+ */
+int pkcs7_note_signerinfo_version(void *context, size_t hdrlen,
+				  unsigned char tag,
+				  const void *value, size_t vlen)
+{
+	struct pkcs7_parse_context *ctx = context;
+	unsigned version;
+
+	if (vlen != 1)
+		goto unsupported;
+
+	version = *(const u8 *)value;
+	switch (version) {
+	case 1:
+		/* PKCS#7 SignerInfo [RFC2315 sec 9.2]
+		 * CMS ver 1 SignerInfo [RFC5652 sec 5.3]
+		 */
+		if (ctx->msg->version != 1)
+			goto version_mismatch;
+		ctx->expect_skid = false;
+		break;
+	case 3:
+		/* CMS ver 3 SignerInfo [RFC2315 sec 5.3] */
+		if (ctx->msg->version == 1)
+			goto version_mismatch;
+		ctx->expect_skid = true;
+		break;
+	default:
+		goto unsupported;
+	}
+
+	return 0;
+
+unsupported:
+	pr_warn("Unsupported SignerInfo version\n");
+	return -EINVAL;
+version_mismatch:
+	pr_warn("SignedData-SignerInfo version mismatch\n");
+	return -EBADMSG;
+}
+
+/*
  * Extract a certificate and store it in the context.
  */
 int pkcs7_extract_cert(void *context, size_t hdrlen,
@@ -284,6 +417,25 @@ int pkcs7_note_certificate_list(void *context, size_t hdrlen,
 }
 
 /*
+ * Note the content type.
+ */
+int pkcs7_note_content(void *context, size_t hdrlen,
+		       unsigned char tag,
+		       const void *value, size_t vlen)
+{
+	struct pkcs7_parse_context *ctx = context;
+
+	if (ctx->last_oid != OID_data &&
+	    ctx->last_oid != OID_msIndirectData) {
+		pr_warn("Unsupported data type %d\n", ctx->last_oid);
+		return -EINVAL;
+	}
+
+	ctx->msg->data_type = ctx->last_oid;
+	return 0;
+}
+
+/*
  * Extract the data from the message and store that and its content type OID in
  * the context.
  */
@@ -298,45 +450,119 @@ int pkcs7_note_data(void *context, size_t hdrlen,
 	ctx->msg->data = value;
 	ctx->msg->data_len = vlen;
 	ctx->msg->data_hdrlen = hdrlen;
-	ctx->msg->data_type = ctx->last_oid;
 	return 0;
 }
 
 /*
- * Parse authenticated attributes
+ * Parse authenticated attributes.
  */
 int pkcs7_sig_note_authenticated_attr(void *context, size_t hdrlen,
 				      unsigned char tag,
 				      const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
+	struct pkcs7_signed_info *sinfo = ctx->sinfo;
+	enum OID content_type;
 
 	pr_devel("AuthAttr: %02x %zu [%*ph]\n", tag, vlen, (unsigned)vlen, value);
 
 	switch (ctx->last_oid) {
+	case OID_contentType:
+		if (__test_and_set_bit(sinfo_has_content_type, &sinfo->aa_set))
+			goto repeated;
+		content_type = look_up_OID(value, vlen);
+		if (content_type != ctx->msg->data_type) {
+			pr_warn("Mismatch between global data type (%d) and sinfo %u (%d)\n",
+				ctx->msg->data_type, sinfo->index,
+				content_type);
+			return -EBADMSG;
+		}
+		return 0;
+
+	case OID_signingTime:
+		if (__test_and_set_bit(sinfo_has_signing_time, &sinfo->aa_set))
+			goto repeated;
+		/* Should we check that the signing time is consistent
+		 * with the signer's X.509 cert?
+		 */
+		return x509_decode_time(&sinfo->signing_time,
+					hdrlen, tag, value, vlen);
+
 	case OID_messageDigest:
+		if (__test_and_set_bit(sinfo_has_message_digest, &sinfo->aa_set))
+			goto repeated;
 		if (tag != ASN1_OTS)
 			return -EBADMSG;
-		ctx->sinfo->msgdigest = value;
-		ctx->sinfo->msgdigest_len = vlen;
+		sinfo->msgdigest = value;
+		sinfo->msgdigest_len = vlen;
+		return 0;
+
+	case OID_smimeCapabilites:
+		if (__test_and_set_bit(sinfo_has_smime_caps, &sinfo->aa_set))
+			goto repeated;
+		if (ctx->msg->data_type != OID_msIndirectData) {
+			pr_warn("S/MIME Caps only allowed with Authenticode\n");
+			return -EKEYREJECTED;
+		}
+		return 0;
+
+		/* Microsoft SpOpusInfo seems to be contain cont[0] 16-bit BE
+		 * char URLs and cont[1] 8-bit char URLs.
+		 *
+		 * Microsoft StatementType seems to contain a list of OIDs that
+		 * are also used as extendedKeyUsage types in X.509 certs.
+		 */
+	case OID_msSpOpusInfo:
+		if (__test_and_set_bit(sinfo_has_ms_opus_info, &sinfo->aa_set))
+			goto repeated;
+		goto authenticode_check;
+	case OID_msStatementType:
+		if (__test_and_set_bit(sinfo_has_ms_statement_type, &sinfo->aa_set))
+			goto repeated;
+	authenticode_check:
+		if (ctx->msg->data_type != OID_msIndirectData) {
+			pr_warn("Authenticode AuthAttrs only allowed with Authenticode\n");
+			return -EKEYREJECTED;
+		}
+		/* I'm not sure how to validate these */
 		return 0;
 	default:
 		return 0;
 	}
+
+repeated:
+	/* We permit max one item per AuthenticatedAttribute and no repeats */
+	pr_warn("Repeated/multivalue AuthAttrs not permitted\n");
+	return -EKEYREJECTED;
 }
 
 /*
- * Note the set of auth attributes for digestion purposes [RFC2315 9.3]
+ * Note the set of auth attributes for digestion purposes [RFC2315 sec 9.3]
  */
 int pkcs7_sig_note_set_of_authattrs(void *context, size_t hdrlen,
 				    unsigned char tag,
 				    const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
+	struct pkcs7_signed_info *sinfo = ctx->sinfo;
+
+	if (!test_bit(sinfo_has_content_type, &sinfo->aa_set) ||
+	    !test_bit(sinfo_has_message_digest, &sinfo->aa_set) ||
+	    (ctx->msg->data_type == OID_msIndirectData &&
+	     !test_bit(sinfo_has_ms_opus_info, &sinfo->aa_set))) {
+		pr_warn("Missing required AuthAttr\n");
+		return -EBADMSG;
+	}
+
+	if (ctx->msg->data_type != OID_msIndirectData &&
+	    test_bit(sinfo_has_ms_opus_info, &sinfo->aa_set)) {
+		pr_warn("Unexpected Authenticode AuthAttr\n");
+		return -EBADMSG;
+	}
 
 	/* We need to switch the 'CONT 0' to a 'SET OF' when we digest */
-	ctx->sinfo->authattrs = value - (hdrlen - 1);
-	ctx->sinfo->authattrs_len = vlen + (hdrlen - 1);
+	sinfo->authattrs = value - (hdrlen - 1);
+	sinfo->authattrs_len = vlen + (hdrlen - 1);
 	return 0;
 }
 
@@ -367,6 +593,22 @@ int pkcs7_sig_note_issuer(void *context, size_t hdrlen,
 }
 
 /*
+ * Note the issuing cert's subjectKeyIdentifier
+ */
+int pkcs7_sig_note_skid(void *context, size_t hdrlen,
+			unsigned char tag,
+			const void *value, size_t vlen)
+{
+	struct pkcs7_parse_context *ctx = context;
+
+	pr_devel("SKID: %02x %zu [%*ph]\n", tag, vlen, (unsigned)vlen, value);
+
+	ctx->raw_skid = value;
+	ctx->raw_skid_size = vlen;
+	return 0;
+}
+
+/*
  * Note the signature data
  */
 int pkcs7_sig_note_signature(void *context, size_t hdrlen,
@@ -398,14 +640,27 @@ int pkcs7_note_signed_info(void *context, size_t hdrlen,
 	struct pkcs7_signed_info *sinfo = ctx->sinfo;
 	struct asymmetric_key_id *kid;
 
+	if (ctx->msg->data_type == OID_msIndirectData && !sinfo->authattrs) {
+		pr_warn("Authenticode requires AuthAttrs\n");
+		return -EBADMSG;
+	}
+
 	/* Generate cert issuer + serial number key ID */
-	kid = asymmetric_key_generate_id(ctx->raw_serial,
-					 ctx->raw_serial_size,
-					 ctx->raw_issuer,
-					 ctx->raw_issuer_size);
+	if (!ctx->expect_skid) {
+		kid = asymmetric_key_generate_id(ctx->raw_serial,
+						 ctx->raw_serial_size,
+						 ctx->raw_issuer,
+						 ctx->raw_issuer_size);
+	} else {
+		kid = asymmetric_key_generate_id(ctx->raw_skid,
+						 ctx->raw_skid_size,
+						 "", 0);
+	}
 	if (IS_ERR(kid))
 		return PTR_ERR(kid);
 
+	pr_devel("SINFO KID: %u [%*phN]\n", kid->len, kid->len, kid->data);
+
 	sinfo->signing_cert_id = kid;
 	sinfo->index = ++ctx->sinfo_index;
 	*ctx->ppsinfo = sinfo;
diff --git a/crypto/asymmetric_keys/pkcs7_parser.h b/crypto/asymmetric_keys/pkcs7_parser.h
index efc7dc9b8f9c..a66b19ebcf47 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.h
+++ b/crypto/asymmetric_keys/pkcs7_parser.h
@@ -21,9 +21,9 @@
 struct pkcs7_signed_info {
 	struct pkcs7_signed_info *next;
 	struct x509_certificate *signer; /* Signing certificate (in msg->certs) */
-	unsigned index;
-	bool trusted;
-	bool unsupported_crypto;	/* T if not usable due to missing crypto */
+	unsigned	index;
+	bool		trusted;
+	bool		unsupported_crypto;	/* T if not usable due to missing crypto */
 
 	/* Message digest - the digest of the Content Data (or NULL) */
 	const void	*msgdigest;
@@ -32,8 +32,18 @@ struct pkcs7_signed_info {
 	/* Authenticated Attribute data (or NULL) */
 	unsigned	authattrs_len;
 	const void	*authattrs;
+	unsigned long	aa_set;
+#define	sinfo_has_content_type		0
+#define	sinfo_has_signing_time		1
+#define	sinfo_has_message_digest	2
+#define sinfo_has_smime_caps		3
+#define	sinfo_has_ms_opus_info		4
+#define	sinfo_has_ms_statement_type	5
+	time64_t	signing_time;
 
-	/* Issuing cert serial number and issuer's name */
+	/* Issuing cert serial number and issuer's name [PKCS#7 or CMS ver 1]
+	 * or issuing cert's SKID [CMS ver 3].
+	 */
 	struct asymmetric_key_id *signing_cert_id;
 
 	/* Message signature.
@@ -50,6 +60,8 @@ struct pkcs7_message {
 	struct x509_certificate *certs;	/* Certificate list */
 	struct x509_certificate *crl;	/* Revocation list */
 	struct pkcs7_signed_info *signed_infos;
+	u8		version;	/* Version of cert (1 -> PKCS#7 or CMS; 3 -> CMS) */
+	bool		have_authattrs;	/* T if have authattrs */
 
 	/* Content Data (or NULL) */
 	enum OID	data_type;	/* Type of Data */
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index 1d29376072da..90d6d47965b0 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -54,7 +54,8 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 		/* Look to see if this certificate is present in the trusted
 		 * keys.
 		 */
-		key = x509_request_asymmetric_key(trust_keyring, x509->id,
+		key = x509_request_asymmetric_key(trust_keyring,
+						  x509->id, x509->skid,
 						  false);
 		if (!IS_ERR(key)) {
 			/* One of the X.509 certificates in the PKCS#7 message
@@ -85,8 +86,10 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 	/* No match - see if the root certificate has a signer amongst the
 	 * trusted keys.
 	 */
-	if (last && last->authority) {
-		key = x509_request_asymmetric_key(trust_keyring, last->authority,
+	if (last && (last->akid_id || last->akid_skid)) {
+		key = x509_request_asymmetric_key(trust_keyring,
+						  last->akid_id,
+						  last->akid_skid,
 						  false);
 		if (!IS_ERR(key)) {
 			x509 = last;
@@ -103,6 +106,7 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 	 */
 	key = x509_request_asymmetric_key(trust_keyring,
 					  sinfo->signing_cert_id,
+					  NULL,
 					  false);
 	if (!IS_ERR(key)) {
 		pr_devel("sinfo %u: Direct signer is key %x\n",
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index cd455450b069..d20c0b4b880e 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -70,9 +70,15 @@ static int pkcs7_digest(struct pkcs7_message *pkcs7,
 	 * message digest attribute amongst them which corresponds to the
 	 * digest we just calculated.
 	 */
-	if (sinfo->msgdigest) {
+	if (sinfo->authattrs) {
 		u8 tag;
 
+		if (!sinfo->msgdigest) {
+			pr_warn("Sig %u: No messageDigest\n", sinfo->index);
+			ret = -EKEYREJECTED;
+			goto error;
+		}
+
 		if (sinfo->msgdigest_len != sinfo->sig.digest_size) {
 			pr_debug("Sig %u: Invalid digest size (%u)\n",
 				 sinfo->index, sinfo->msgdigest_len);
@@ -170,6 +176,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 				  struct pkcs7_signed_info *sinfo)
 {
 	struct x509_certificate *x509 = sinfo->signer, *p;
+	struct asymmetric_key_id *auth;
 	int ret;
 
 	kenter("");
@@ -187,11 +194,14 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 			goto maybe_missing_crypto_in_x509;
 
 		pr_debug("- issuer %s\n", x509->issuer);
-		if (x509->authority)
-			pr_debug("- authkeyid %*phN\n",
-				 x509->authority->len, x509->authority->data);
-
-		if (!x509->authority ||
+		if (x509->akid_id)
+			pr_debug("- authkeyid.id %*phN\n",
+				 x509->akid_id->len, x509->akid_id->data);
+		if (x509->akid_skid)
+			pr_debug("- authkeyid.skid %*phN\n",
+				 x509->akid_skid->len, x509->akid_skid->data);
+
+		if ((!x509->akid_id && !x509->akid_skid) ||
 		    strcmp(x509->subject, x509->issuer) == 0) {
 			/* If there's no authority certificate specified, then
 			 * the certificate must be self-signed and is the root
@@ -215,21 +225,42 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		/* Look through the X.509 certificates in the PKCS#7 message's
 		 * list to see if the next one is there.
 		 */
-		pr_debug("- want %*phN\n",
-			 x509->authority->len, x509->authority->data);
-		for (p = pkcs7->certs; p; p = p->next) {
-			if (!p->skid)
-				continue;
-			pr_debug("- cmp [%u] %*phN\n",
-				 p->index, p->skid->len, p->skid->data);
-			if (asymmetric_key_id_same(p->skid, x509->authority))
-				goto found_issuer;
+		auth = x509->akid_id;
+		if (auth) {
+			pr_debug("- want %*phN\n", auth->len, auth->data);
+			for (p = pkcs7->certs; p; p = p->next) {
+				pr_debug("- cmp [%u] %*phN\n",
+					 p->index, p->id->len, p->id->data);
+				if (asymmetric_key_id_same(p->id, auth))
+					goto found_issuer_check_skid;
+			}
+		} else {
+			auth = x509->akid_skid;
+			pr_debug("- want %*phN\n", auth->len, auth->data);
+			for (p = pkcs7->certs; p; p = p->next) {
+				if (!p->skid)
+					continue;
+				pr_debug("- cmp [%u] %*phN\n",
+					 p->index, p->skid->len, p->skid->data);
+				if (asymmetric_key_id_same(p->skid, auth))
+					goto found_issuer;
+			}
 		}
 
 		/* We didn't find the root of this chain */
 		pr_debug("- top\n");
 		return 0;
 
+	found_issuer_check_skid:
+		/* We matched issuer + serialNumber, but if there's an
+		 * authKeyId.keyId, that must match the CA subjKeyId also.
+		 */
+		if (x509->akid_skid &&
+		    !asymmetric_key_id_same(p->skid, x509->akid_skid)) {
+			pr_warn("Sig %u: X.509 chain contains auth-skid nonmatch (%u->%u)\n",
+				sinfo->index, x509->index, p->index);
+			return -EKEYREJECTED;
+		}
 	found_issuer:
 		pr_debug("- subject %s\n", p->subject);
 		if (p->seen) {
@@ -289,6 +320,18 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7,
 	pr_devel("Using X.509[%u] for sig %u\n",
 		 sinfo->signer->index, sinfo->index);
 
+	/* Check that the PKCS#7 signing time is valid according to the X.509
+	 * certificate.  We can't, however, check against the system clock
+	 * since that may not have been set yet and may be wrong.
+	 */
+	if (test_bit(sinfo_has_signing_time, &sinfo->aa_set)) {
+		if (sinfo->signing_time < sinfo->signer->valid_from ||
+		    sinfo->signing_time > sinfo->signer->valid_to) {
+			pr_warn("Message signed outside of X.509 validity window\n");
+			return -EKEYREJECTED;
+		}
+	}
+
 	/* Verify the PKCS#7 binary against the key */
 	ret = public_key_verify_signature(sinfo->signer->pub, &sinfo->sig);
 	if (ret < 0)
@@ -303,6 +346,7 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7,
 /**
  * pkcs7_verify - Verify a PKCS#7 message
  * @pkcs7: The PKCS#7 message to be verified
+ * @usage: The use to which the key is being put
  *
  * Verify a PKCS#7 message is internally consistent - that is, the data digest
  * matches the digest in the AuthAttrs and any signature in the message or one
@@ -314,6 +358,9 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7,
  *
  * Returns, in order of descending priority:
  *
+ *  (*) -EKEYREJECTED if a key was selected that had a usage restriction at
+ *      odds with the specified usage, or:
+ *
  *  (*) -EKEYREJECTED if a signature failed to match for which we found an
  *	appropriate X.509 certificate, or:
  *
@@ -325,7 +372,8 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7,
  *  (*) 0 if all the signature chains that don't incur -ENOPKG can be verified
  *	(note that a signature chain may be of zero length), or:
  */
-int pkcs7_verify(struct pkcs7_message *pkcs7)
+int pkcs7_verify(struct pkcs7_message *pkcs7,
+		 enum key_being_used_for usage)
 {
 	struct pkcs7_signed_info *sinfo;
 	struct x509_certificate *x509;
@@ -334,12 +382,48 @@ int pkcs7_verify(struct pkcs7_message *pkcs7)
 
 	kenter("");
 
+	switch (usage) {
+	case VERIFYING_MODULE_SIGNATURE:
+		if (pkcs7->data_type != OID_data) {
+			pr_warn("Invalid module sig (not pkcs7-data)\n");
+			return -EKEYREJECTED;
+		}
+		if (pkcs7->have_authattrs) {
+			pr_warn("Invalid module sig (has authattrs)\n");
+			return -EKEYREJECTED;
+		}
+		break;
+	case VERIFYING_FIRMWARE_SIGNATURE:
+		if (pkcs7->data_type != OID_data) {
+			pr_warn("Invalid firmware sig (not pkcs7-data)\n");
+			return -EKEYREJECTED;
+		}
+		if (!pkcs7->have_authattrs) {
+			pr_warn("Invalid firmware sig (missing authattrs)\n");
+			return -EKEYREJECTED;
+		}
+		break;
+	case VERIFYING_KEXEC_PE_SIGNATURE:
+		if (pkcs7->data_type != OID_msIndirectData) {
+			pr_warn("Invalid kexec sig (not Authenticode)\n");
+			return -EKEYREJECTED;
+		}
+		/* Authattr presence checked in parser */
+		break;
+	case VERIFYING_UNSPECIFIED_SIGNATURE:
+		if (pkcs7->data_type != OID_data) {
+			pr_warn("Invalid unspecified sig (not pkcs7-data)\n");
+			return -EKEYREJECTED;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	for (n = 0, x509 = pkcs7->certs; x509; x509 = x509->next, n++) {
 		ret = x509_get_sig_params(x509);
 		if (ret < 0)
 			return ret;
-		pr_debug("X.509[%u] %*phN\n",
-			 n, x509->authority->len, x509->authority->data);
 	}
 
 	for (sinfo = pkcs7->signed_infos; sinfo; sinfo = sinfo->next) {
@@ -359,3 +443,28 @@ int pkcs7_verify(struct pkcs7_message *pkcs7)
 	return enopkg;
 }
 EXPORT_SYMBOL_GPL(pkcs7_verify);
+
+/**
+ * pkcs7_supply_detached_data - Supply the data needed to verify a PKCS#7 message
+ * @pkcs7: The PKCS#7 message
+ * @data: The data to be verified
+ * @datalen: The amount of data
+ *
+ * Supply the detached data needed to verify a PKCS#7 message.  Note that no
+ * attempt to retain/pin the data is made.  That is left to the caller.  The
+ * data will not be modified by pkcs7_verify() and will not be freed when the
+ * PKCS#7 message is freed.
+ *
+ * Returns -EINVAL if data is already supplied in the message, 0 otherwise.
+ */
+int pkcs7_supply_detached_data(struct pkcs7_message *pkcs7,
+			       const void *data, size_t datalen)
+{
+	if (pkcs7->data) {
+		pr_debug("Data already supplied\n");
+		return -EINVAL;
+	}
+	pkcs7->data = data;
+	pkcs7->data_len = datalen;
+	return 0;
+}
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index 2f6e4fb1a1ea..81efccbe22d5 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -39,6 +39,7 @@ EXPORT_SYMBOL_GPL(pkey_algo);
 const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST] = {
 	[PKEY_ID_PGP]		= "PGP",
 	[PKEY_ID_X509]		= "X509",
+	[PKEY_ID_PKCS7]		= "PKCS#7",
 };
 EXPORT_SYMBOL_GPL(pkey_id_type_name);
 
diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c
index 2421f46184ce..897b734dabf9 100644
--- a/crypto/asymmetric_keys/verify_pefile.c
+++ b/crypto/asymmetric_keys/verify_pefile.c
@@ -393,6 +393,7 @@ error_no_desc:
  * @pebuf: Buffer containing the PE binary image
  * @pelen: Length of the binary image
  * @trust_keyring: Signing certificates to use as starting points
+ * @usage: The use to which the key is being put.
  * @_trusted: Set to true if trustworth, false otherwise
  *
  * Validate that the certificate chain inside the PKCS#7 message inside the PE
@@ -417,7 +418,9 @@ error_no_desc:
  * May also return -ENOMEM.
  */
 int verify_pefile_signature(const void *pebuf, unsigned pelen,
-			    struct key *trusted_keyring, bool *_trusted)
+			    struct key *trusted_keyring,
+			    enum key_being_used_for usage,
+			    bool *_trusted)
 {
 	struct pkcs7_message *pkcs7;
 	struct pefile_context ctx;
@@ -462,7 +465,7 @@ int verify_pefile_signature(const void *pebuf, unsigned pelen,
 	if (ret < 0)
 		goto error;
 
-	ret = pkcs7_verify(pkcs7);
+	ret = pkcs7_verify(pkcs7, usage);
 	if (ret < 0)
 		goto error;
 
diff --git a/crypto/asymmetric_keys/x509_akid.asn1 b/crypto/asymmetric_keys/x509_akid.asn1
new file mode 100644
index 000000000000..1a33231a75a8
--- /dev/null
+++ b/crypto/asymmetric_keys/x509_akid.asn1
@@ -0,0 +1,35 @@
+-- X.509 AuthorityKeyIdentifier
+-- rfc5280 section 4.2.1.1
+
+AuthorityKeyIdentifier ::= SEQUENCE {
+	keyIdentifier			[0] IMPLICIT KeyIdentifier		OPTIONAL,
+	authorityCertIssuer		[1] IMPLICIT GeneralNames		OPTIONAL,
+	authorityCertSerialNumber	[2] IMPLICIT CertificateSerialNumber	OPTIONAL
+	}
+
+KeyIdentifier ::= OCTET STRING ({ x509_akid_note_kid })
+
+CertificateSerialNumber ::= INTEGER ({ x509_akid_note_serial })
+
+GeneralNames ::= SEQUENCE OF GeneralName
+
+GeneralName ::= CHOICE {
+	otherName			[0] ANY,
+	rfc822Name			[1] IA5String,
+	dNSName				[2] IA5String,
+	x400Address			[3] ANY,
+	directoryName			[4] Name ({ x509_akid_note_name }),
+	ediPartyName			[5] ANY,
+	uniformResourceIdentifier	[6] IA5String,
+	iPAddress			[7] OCTET STRING,
+	registeredID			[8] OBJECT IDENTIFIER
+	}
+
+Name ::= SEQUENCE OF RelativeDistinguishedName
+
+RelativeDistinguishedName ::= SET OF AttributeValueAssertion
+
+AttributeValueAssertion ::= SEQUENCE {
+	attributeType		OBJECT IDENTIFIER ({ x509_note_OID }),
+	attributeValue		ANY ({ x509_extract_name_segment })
+	}
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index a668d90302d3..af71878dc15b 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -18,6 +18,7 @@
 #include "public_key.h"
 #include "x509_parser.h"
 #include "x509-asn1.h"
+#include "x509_akid-asn1.h"
 #include "x509_rsakey-asn1.h"
 
 struct x509_parse_context {
@@ -35,6 +36,10 @@ struct x509_parse_context {
 	u16		o_offset;		/* Offset of organizationName (O) */
 	u16		cn_offset;		/* Offset of commonName (CN) */
 	u16		email_offset;		/* Offset of emailAddress */
+	unsigned	raw_akid_size;
+	const void	*raw_akid;		/* Raw authorityKeyId in ASN.1 */
+	const void	*akid_raw_issuer;	/* Raw directoryName in authorityKeyId */
+	unsigned	akid_raw_issuer_size;
 };
 
 /*
@@ -48,7 +53,8 @@ void x509_free_certificate(struct x509_certificate *cert)
 		kfree(cert->subject);
 		kfree(cert->id);
 		kfree(cert->skid);
-		kfree(cert->authority);
+		kfree(cert->akid_id);
+		kfree(cert->akid_skid);
 		kfree(cert->sig.digest);
 		mpi_free(cert->sig.rsa.s);
 		kfree(cert);
@@ -85,6 +91,18 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 	if (ret < 0)
 		goto error_decode;
 
+	/* Decode the AuthorityKeyIdentifier */
+	if (ctx->raw_akid) {
+		pr_devel("AKID: %u %*phN\n",
+			 ctx->raw_akid_size, ctx->raw_akid_size, ctx->raw_akid);
+		ret = asn1_ber_decoder(&x509_akid_decoder, ctx,
+				       ctx->raw_akid, ctx->raw_akid_size);
+		if (ret < 0) {
+			pr_warn("Couldn't decode AuthKeyIdentifier\n");
+			goto error_decode;
+		}
+	}
+
 	/* Decode the public key */
 	ret = asn1_ber_decoder(&x509_rsakey_decoder, ctx,
 			       ctx->key, ctx->key_size);
@@ -422,7 +440,6 @@ int x509_process_extension(void *context, size_t hdrlen,
 	struct x509_parse_context *ctx = context;
 	struct asymmetric_key_id *kid;
 	const unsigned char *v = value;
-	int i;
 
 	pr_debug("Extension: %u\n", ctx->last_oid);
 
@@ -437,9 +454,7 @@ int x509_process_extension(void *context, size_t hdrlen,
 
 		ctx->cert->raw_skid_size = vlen;
 		ctx->cert->raw_skid = v;
-		kid = asymmetric_key_generate_id(ctx->cert->raw_subject,
-						 ctx->cert->raw_subject_size,
-						 v, vlen);
+		kid = asymmetric_key_generate_id(v, vlen, "", 0);
 		if (IS_ERR(kid))
 			return PTR_ERR(kid);
 		ctx->cert->skid = kid;
@@ -449,117 +464,113 @@ int x509_process_extension(void *context, size_t hdrlen,
 
 	if (ctx->last_oid == OID_authorityKeyIdentifier) {
 		/* Get hold of the CA key fingerprint */
-		if (ctx->cert->authority || vlen < 5)
-			return -EBADMSG;
-
-		/* Authority Key Identifier must be a Constructed SEQUENCE */
-		if (v[0] != (ASN1_SEQ | (ASN1_CONS << 5)))
-			return -EBADMSG;
-
-		/* Authority Key Identifier is not indefinite length */
-		if (unlikely(vlen == ASN1_INDEFINITE_LENGTH))
-			return -EBADMSG;
-
-		if (vlen < ASN1_INDEFINITE_LENGTH) {
-			/* Short Form length */
-			if (v[1] != vlen - 2 ||
-			    v[2] != SEQ_TAG_KEYID ||
-			    v[3] > vlen - 4)
-				return -EBADMSG;
-
-			vlen = v[3];
-			v += 4;
-		} else {
-			/* Long Form length */
-			size_t seq_len = 0;
-			size_t sub = v[1] - ASN1_INDEFINITE_LENGTH;
-
-			if (sub > 2)
-				return -EBADMSG;
-
-			/* calculate the length from subsequent octets */
-			v += 2;
-			for (i = 0; i < sub; i++) {
-				seq_len <<= 8;
-				seq_len |= v[i];
-			}
-
-			if (seq_len != vlen - 2 - sub ||
-			    v[sub] != SEQ_TAG_KEYID ||
-			    v[sub + 1] > vlen - 4 - sub)
-				return -EBADMSG;
-
-			vlen = v[sub + 1];
-			v += (sub + 2);
-		}
-
-		kid = asymmetric_key_generate_id(ctx->cert->raw_issuer,
-						 ctx->cert->raw_issuer_size,
-						 v, vlen);
-		if (IS_ERR(kid))
-			return PTR_ERR(kid);
-		pr_debug("authkeyid %*phN\n", kid->len, kid->data);
-		ctx->cert->authority = kid;
+		ctx->raw_akid = v;
+		ctx->raw_akid_size = vlen;
 		return 0;
 	}
 
 	return 0;
 }
 
-/*
- * Record a certificate time.
+/**
+ * x509_decode_time - Decode an X.509 time ASN.1 object
+ * @_t: The time to fill in
+ * @hdrlen: The length of the object header
+ * @tag: The object tag
+ * @value: The object value
+ * @vlen: The size of the object value
+ *
+ * Decode an ASN.1 universal time or generalised time field into a struct the
+ * kernel can handle and check it for validity.  The time is decoded thus:
+ *
+ *	[RFC5280 §4.1.2.5]
+ *	CAs conforming to this profile MUST always encode certificate validity
+ *	dates through the year 2049 as UTCTime; certificate validity dates in
+ *	2050 or later MUST be encoded as GeneralizedTime.  Conforming
+ *	applications MUST be able to process validity dates that are encoded in
+ *	either UTCTime or GeneralizedTime.
  */
-static int x509_note_time(struct tm *tm,  size_t hdrlen,
-			  unsigned char tag,
-			  const unsigned char *value, size_t vlen)
+int x509_decode_time(time64_t *_t,  size_t hdrlen,
+		     unsigned char tag,
+		     const unsigned char *value, size_t vlen)
 {
+	static const unsigned char month_lengths[] = { 31, 29, 31, 30, 31, 30,
+						       31, 31, 30, 31, 30, 31 };
 	const unsigned char *p = value;
+	unsigned year, mon, day, hour, min, sec, mon_len;
 
-#define dec2bin(X) ((X) - '0')
+#define dec2bin(X) ({ unsigned char x = (X) - '0'; if (x > 9) goto invalid_time; x; })
 #define DD2bin(P) ({ unsigned x = dec2bin(P[0]) * 10 + dec2bin(P[1]); P += 2; x; })
 
 	if (tag == ASN1_UNITIM) {
 		/* UTCTime: YYMMDDHHMMSSZ */
 		if (vlen != 13)
 			goto unsupported_time;
-		tm->tm_year = DD2bin(p);
-		if (tm->tm_year >= 50)
-			tm->tm_year += 1900;
+		year = DD2bin(p);
+		if (year >= 50)
+			year += 1900;
 		else
-			tm->tm_year += 2000;
+			year += 2000;
 	} else if (tag == ASN1_GENTIM) {
 		/* GenTime: YYYYMMDDHHMMSSZ */
 		if (vlen != 15)
 			goto unsupported_time;
-		tm->tm_year = DD2bin(p) * 100 + DD2bin(p);
+		year = DD2bin(p) * 100 + DD2bin(p);
+		if (year >= 1950 && year <= 2049)
+			goto invalid_time;
 	} else {
 		goto unsupported_time;
 	}
 
-	tm->tm_year -= 1900;
-	tm->tm_mon  = DD2bin(p) - 1;
-	tm->tm_mday = DD2bin(p);
-	tm->tm_hour = DD2bin(p);
-	tm->tm_min  = DD2bin(p);
-	tm->tm_sec  = DD2bin(p);
+	mon  = DD2bin(p);
+	day = DD2bin(p);
+	hour = DD2bin(p);
+	min  = DD2bin(p);
+	sec  = DD2bin(p);
 
 	if (*p != 'Z')
 		goto unsupported_time;
 
+	mon_len = month_lengths[mon];
+	if (mon == 2) {
+		if (year % 4 == 0) {
+			mon_len = 29;
+			if (year % 100 == 0) {
+				year /= 100;
+				if (year % 4 != 0)
+					mon_len = 28;
+			}
+		}
+	}
+
+	if (year < 1970 ||
+	    mon < 1 || mon > 12 ||
+	    day < 1 || day > mon_len ||
+	    hour < 0 || hour > 23 ||
+	    min < 0 || min > 59 ||
+	    sec < 0 || sec > 59)
+		goto invalid_time;
+	
+	*_t = mktime64(year, mon, day, hour, min, sec);
 	return 0;
 
 unsupported_time:
-	pr_debug("Got unsupported time [tag %02x]: '%*.*s'\n",
-		 tag, (int)vlen, (int)vlen, value);
+	pr_debug("Got unsupported time [tag %02x]: '%*phN'\n",
+		 tag, (int)vlen, value);
+	return -EBADMSG;
+invalid_time:
+	pr_debug("Got invalid time [tag %02x]: '%*phN'\n",
+		 tag, (int)vlen, value);
 	return -EBADMSG;
 }
+EXPORT_SYMBOL_GPL(x509_decode_time);
 
 int x509_note_not_before(void *context, size_t hdrlen,
 			 unsigned char tag,
 			 const void *value, size_t vlen)
 {
 	struct x509_parse_context *ctx = context;
-	return x509_note_time(&ctx->cert->valid_from, hdrlen, tag, value, vlen);
+	return x509_decode_time(&ctx->cert->valid_from, hdrlen, tag, value, vlen);
 }
 
 int x509_note_not_after(void *context, size_t hdrlen,
@@ -567,5 +578,71 @@ int x509_note_not_after(void *context, size_t hdrlen,
 			const void *value, size_t vlen)
 {
 	struct x509_parse_context *ctx = context;
-	return x509_note_time(&ctx->cert->valid_to, hdrlen, tag, value, vlen);
+	return x509_decode_time(&ctx->cert->valid_to, hdrlen, tag, value, vlen);
+}
+
+/*
+ * Note a key identifier-based AuthorityKeyIdentifier
+ */
+int x509_akid_note_kid(void *context, size_t hdrlen,
+		       unsigned char tag,
+		       const void *value, size_t vlen)
+{
+	struct x509_parse_context *ctx = context;
+	struct asymmetric_key_id *kid;
+
+	pr_debug("AKID: keyid: %*phN\n", (int)vlen, value);
+
+	if (ctx->cert->akid_skid)
+		return 0;
+
+	kid = asymmetric_key_generate_id(value, vlen, "", 0);
+	if (IS_ERR(kid))
+		return PTR_ERR(kid);
+	pr_debug("authkeyid %*phN\n", kid->len, kid->data);
+	ctx->cert->akid_skid = kid;
+	return 0;
+}
+
+/*
+ * Note a directoryName in an AuthorityKeyIdentifier
+ */
+int x509_akid_note_name(void *context, size_t hdrlen,
+			unsigned char tag,
+			const void *value, size_t vlen)
+{
+	struct x509_parse_context *ctx = context;
+
+	pr_debug("AKID: name: %*phN\n", (int)vlen, value);
+
+	ctx->akid_raw_issuer = value;
+	ctx->akid_raw_issuer_size = vlen;
+	return 0;
+}
+
+/*
+ * Note a serial number in an AuthorityKeyIdentifier
+ */
+int x509_akid_note_serial(void *context, size_t hdrlen,
+			  unsigned char tag,
+			  const void *value, size_t vlen)
+{
+	struct x509_parse_context *ctx = context;
+	struct asymmetric_key_id *kid;
+
+	pr_debug("AKID: serial: %*phN\n", (int)vlen, value);
+
+	if (!ctx->akid_raw_issuer || ctx->cert->akid_id)
+		return 0;
+
+	kid = asymmetric_key_generate_id(value,
+					 vlen,
+					 ctx->akid_raw_issuer,
+					 ctx->akid_raw_issuer_size);
+	if (IS_ERR(kid))
+		return PTR_ERR(kid);
+
+	pr_debug("authkeyid %*phN\n", kid->len, kid->data);
+	ctx->cert->akid_id = kid;
+	return 0;
 }
diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h
index 3dfe6b5d6f0b..1de01eaec884 100644
--- a/crypto/asymmetric_keys/x509_parser.h
+++ b/crypto/asymmetric_keys/x509_parser.h
@@ -19,11 +19,12 @@ struct x509_certificate {
 	struct public_key_signature sig;	/* Signature parameters */
 	char		*issuer;		/* Name of certificate issuer */
 	char		*subject;		/* Name of certificate subject */
-	struct asymmetric_key_id *id;		/* Serial number + issuer */
+	struct asymmetric_key_id *id;		/* Issuer + Serial number */
 	struct asymmetric_key_id *skid;		/* Subject + subjectKeyId (optional) */
-	struct asymmetric_key_id *authority;	/* Authority key identifier (optional) */
-	struct tm	valid_from;
-	struct tm	valid_to;
+	struct asymmetric_key_id *akid_id;	/* CA AuthKeyId matching ->id (optional) */
+	struct asymmetric_key_id *akid_skid;	/* CA AuthKeyId matching ->skid (optional) */
+	time64_t	valid_from;
+	time64_t	valid_to;
 	const void	*tbs;			/* Signed data */
 	unsigned	tbs_size;		/* Size of signed data */
 	unsigned	raw_sig_size;		/* Size of sigature */
@@ -48,6 +49,9 @@ struct x509_certificate {
  */
 extern void x509_free_certificate(struct x509_certificate *cert);
 extern struct x509_certificate *x509_cert_parse(const void *data, size_t datalen);
+extern int x509_decode_time(time64_t *_t,  size_t hdrlen,
+			    unsigned char tag,
+			    const unsigned char *value, size_t vlen);
 
 /*
  * x509_public_key.c
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 24f17e6c5904..6d88dd15c98d 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -65,23 +65,37 @@ __setup("ca_keys=", ca_keys_setup);
 /**
  * x509_request_asymmetric_key - Request a key by X.509 certificate params.
  * @keyring: The keys to search.
- * @kid: The key ID.
+ * @id: The issuer & serialNumber to look for or NULL.
+ * @skid: The subjectKeyIdentifier to look for or NULL.
  * @partial: Use partial match if true, exact if false.
  *
- * Find a key in the given keyring by subject name and key ID.  These might,
- * for instance, be the issuer name and the authority key ID of an X.509
- * certificate that needs to be verified.
+ * Find a key in the given keyring by identifier.  The preferred identifier is
+ * the issuer + serialNumber and the fallback identifier is the
+ * subjectKeyIdentifier.  If both are given, the lookup is by the former, but
+ * the latter must also match.
  */
 struct key *x509_request_asymmetric_key(struct key *keyring,
-					const struct asymmetric_key_id *kid,
+					const struct asymmetric_key_id *id,
+					const struct asymmetric_key_id *skid,
 					bool partial)
 {
-	key_ref_t key;
-	char *id, *p;
-
+	struct key *key;
+	key_ref_t ref;
+	const char *lookup;
+	char *req, *p;
+	int len;
+
+	if (id) {
+		lookup = id->data;
+		len = id->len;
+	} else {
+		lookup = skid->data;
+		len = skid->len;
+	}
+	
 	/* Construct an identifier "id:<keyid>". */
-	p = id = kmalloc(2 + 1 + kid->len * 2 + 1, GFP_KERNEL);
-	if (!id)
+	p = req = kmalloc(2 + 1 + len * 2 + 1, GFP_KERNEL);
+	if (!req)
 		return ERR_PTR(-ENOMEM);
 
 	if (partial) {
@@ -92,32 +106,48 @@ struct key *x509_request_asymmetric_key(struct key *keyring,
 		*p++ = 'x';
 	}
 	*p++ = ':';
-	p = bin2hex(p, kid->data, kid->len);
+	p = bin2hex(p, lookup, len);
 	*p = 0;
 
-	pr_debug("Look up: \"%s\"\n", id);
+	pr_debug("Look up: \"%s\"\n", req);
 
-	key = keyring_search(make_key_ref(keyring, 1),
-			     &key_type_asymmetric, id);
-	if (IS_ERR(key))
-		pr_debug("Request for key '%s' err %ld\n", id, PTR_ERR(key));
-	kfree(id);
+	ref = keyring_search(make_key_ref(keyring, 1),
+			     &key_type_asymmetric, req);
+	if (IS_ERR(ref))
+		pr_debug("Request for key '%s' err %ld\n", req, PTR_ERR(ref));
+	kfree(req);
 
-	if (IS_ERR(key)) {
-		switch (PTR_ERR(key)) {
+	if (IS_ERR(ref)) {
+		switch (PTR_ERR(ref)) {
 			/* Hide some search errors */
 		case -EACCES:
 		case -ENOTDIR:
 		case -EAGAIN:
 			return ERR_PTR(-ENOKEY);
 		default:
-			return ERR_CAST(key);
+			return ERR_CAST(ref);
+		}
+	}
+
+	key = key_ref_to_ptr(ref);
+	if (id && skid) {
+		const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+		if (!kids->id[1]) {
+			pr_debug("issuer+serial match, but expected SKID missing\n");
+			goto reject;
+		}
+		if (!asymmetric_key_id_same(skid, kids->id[1])) {
+			pr_debug("issuer+serial match, but SKID does not\n");
+			goto reject;
 		}
 	}
+	
+	pr_devel("<==%s() = 0 [%x]\n", __func__, key_serial(key));
+	return key;
 
-	pr_devel("<==%s() = 0 [%x]\n", __func__,
-		 key_serial(key_ref_to_ptr(key)));
-	return key_ref_to_ptr(key);
+reject:
+	key_put(key);
+	return ERR_PTR(-EKEYREJECTED);
 }
 EXPORT_SYMBOL_GPL(x509_request_asymmetric_key);
 
@@ -227,10 +257,11 @@ static int x509_validate_trust(struct x509_certificate *cert,
 	if (!trust_keyring)
 		return -EOPNOTSUPP;
 
-	if (ca_keyid && !asymmetric_key_id_partial(cert->authority, ca_keyid))
+	if (ca_keyid && !asymmetric_key_id_partial(cert->akid_skid, ca_keyid))
 		return -EPERM;
 
-	key = x509_request_asymmetric_key(trust_keyring, cert->authority,
+	key = x509_request_asymmetric_key(trust_keyring,
+					  cert->akid_id, cert->akid_skid,
 					  false);
 	if (!IS_ERR(key))  {
 		if (!use_builtin_keys
@@ -271,14 +302,7 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 	}
 
 	pr_devel("Cert Key Algo: %s\n", pkey_algo_name[cert->pub->pkey_algo]);
-	pr_devel("Cert Valid From: %04ld-%02d-%02d %02d:%02d:%02d\n",
-		 cert->valid_from.tm_year + 1900, cert->valid_from.tm_mon + 1,
-		 cert->valid_from.tm_mday, cert->valid_from.tm_hour,
-		 cert->valid_from.tm_min,  cert->valid_from.tm_sec);
-	pr_devel("Cert Valid To: %04ld-%02d-%02d %02d:%02d:%02d\n",
-		 cert->valid_to.tm_year + 1900, cert->valid_to.tm_mon + 1,
-		 cert->valid_to.tm_mday, cert->valid_to.tm_hour,
-		 cert->valid_to.tm_min,  cert->valid_to.tm_sec);
+	pr_devel("Cert Valid period: %lld-%lld\n", cert->valid_from, cert->valid_to);
 	pr_devel("Cert Signature: %s + %s\n",
 		 pkey_algo_name[cert->sig.pkey_algo],
 		 hash_algo_name[cert->sig.pkey_hash_algo]);
@@ -287,8 +311,9 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 	cert->pub->id_type = PKEY_ID_X509;
 
 	/* Check the signature on the key if it appears to be self-signed */
-	if (!cert->authority ||
-	    asymmetric_key_id_same(cert->skid, cert->authority)) {
+	if ((!cert->akid_skid && !cert->akid_id) ||
+	    asymmetric_key_id_same(cert->skid, cert->akid_skid) ||
+	    asymmetric_key_id_same(cert->id, cert->akid_id)) {
 		ret = x509_check_signature(cert->pub, cert); /* self-signed */
 		if (ret < 0)
 			goto error_free_cert;
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 3e852299afb4..55a354d57251 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -1,7 +1,7 @@
 /*
  * Authenc: Simple AEAD wrapper for IPsec
  *
- * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
+ * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -14,6 +14,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
+#include <crypto/null.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -23,26 +24,21 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
-typedef u8 *(*authenc_ahash_t)(struct aead_request *req, unsigned int flags);
-
 struct authenc_instance_ctx {
 	struct crypto_ahash_spawn auth;
 	struct crypto_skcipher_spawn enc;
+	unsigned int reqoff;
 };
 
 struct crypto_authenc_ctx {
-	unsigned int reqoff;
 	struct crypto_ahash *auth;
 	struct crypto_ablkcipher *enc;
+	struct crypto_blkcipher *null;
 };
 
 struct authenc_request_ctx {
-	unsigned int cryptlen;
-	struct scatterlist *sg;
-	struct scatterlist asg[2];
-	struct scatterlist cipher[2];
-	crypto_completion_t complete;
-	crypto_completion_t update_complete;
+	struct scatterlist src[2];
+	struct scatterlist dst[2];
 	char tail[];
 };
 
@@ -119,189 +115,35 @@ badkey:
 	goto out;
 }
 
-static void authenc_geniv_ahash_update_done(struct crypto_async_request *areq,
-					    int err)
-{
-	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, ahreq->result,
-				areq_ctx->cryptlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		goto out;
-
-	scatterwalk_map_and_copy(ahreq->result, areq_ctx->sg,
-				 areq_ctx->cryptlen,
-				 crypto_aead_authsize(authenc), 1);
-
-out:
-	authenc_request_complete(req, err);
-}
-
 static void authenc_geniv_ahash_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
+	struct aead_instance *inst = aead_alg_instance(authenc);
+	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
+	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff);
 
 	if (err)
 		goto out;
 
-	scatterwalk_map_and_copy(ahreq->result, areq_ctx->sg,
-				 areq_ctx->cryptlen,
+	scatterwalk_map_and_copy(ahreq->result, req->dst,
+				 req->assoclen + req->cryptlen,
 				 crypto_aead_authsize(authenc), 1);
 
 out:
 	aead_request_complete(req, err);
 }
 
-static void authenc_verify_ahash_update_done(struct crypto_async_request *areq,
-					     int err)
-{
-	u8 *ihash;
-	unsigned int authsize;
-	struct ablkcipher_request *abreq;
-	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-	unsigned int cryptlen = req->cryptlen;
-
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, ahreq->result,
-				areq_ctx->cryptlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		goto out;
-
-	authsize = crypto_aead_authsize(authenc);
-	cryptlen -= authsize;
-	ihash = ahreq->result + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
-
-	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
-	if (err)
-		goto out;
-
-	abreq = aead_request_ctx(req);
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst,
-				     cryptlen, req->iv);
-
-	err = crypto_ablkcipher_decrypt(abreq);
-
-out:
-	authenc_request_complete(req, err);
-}
-
-static void authenc_verify_ahash_done(struct crypto_async_request *areq,
-				      int err)
-{
-	u8 *ihash;
-	unsigned int authsize;
-	struct ablkcipher_request *abreq;
-	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-	unsigned int cryptlen = req->cryptlen;
-
-	if (err)
-		goto out;
-
-	authsize = crypto_aead_authsize(authenc);
-	cryptlen -= authsize;
-	ihash = ahreq->result + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
-
-	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
-	if (err)
-		goto out;
-
-	abreq = aead_request_ctx(req);
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst,
-				     cryptlen, req->iv);
-
-	err = crypto_ablkcipher_decrypt(abreq);
-
-out:
-	authenc_request_complete(req, err);
-}
-
-static u8 *crypto_authenc_ahash_fb(struct aead_request *req, unsigned int flags)
-{
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct crypto_ahash *auth = ctx->auth;
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-	u8 *hash = areq_ctx->tail;
-	int err;
-
-	hash = (u8 *)ALIGN((unsigned long)hash + crypto_ahash_alignmask(auth),
-			    crypto_ahash_alignmask(auth) + 1);
-
-	ahash_request_set_tfm(ahreq, auth);
-
-	err = crypto_ahash_init(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	ahash_request_set_crypt(ahreq, req->assoc, hash, req->assoclen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) & flags,
-				   areq_ctx->update_complete, req);
-
-	err = crypto_ahash_update(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, hash,
-				areq_ctx->cryptlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) & flags,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	return hash;
-}
-
-static u8 *crypto_authenc_ahash(struct aead_request *req, unsigned int flags)
+static int crypto_authenc_genicv(struct aead_request *req, unsigned int flags)
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
+	struct aead_instance *inst = aead_alg_instance(authenc);
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
+	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_ahash *auth = ctx->auth;
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
+	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff);
 	u8 *hash = areq_ctx->tail;
 	int err;
 
@@ -309,66 +151,18 @@ static u8 *crypto_authenc_ahash(struct aead_request *req, unsigned int flags)
 			   crypto_ahash_alignmask(auth) + 1);
 
 	ahash_request_set_tfm(ahreq, auth);
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, hash,
-				areq_ctx->cryptlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) & flags,
-				   areq_ctx->complete, req);
+	ahash_request_set_crypt(ahreq, req->dst, hash,
+				req->assoclen + req->cryptlen);
+	ahash_request_set_callback(ahreq, flags,
+				   authenc_geniv_ahash_done, req);
 
 	err = crypto_ahash_digest(ahreq);
 	if (err)
-		return ERR_PTR(err);
-
-	return hash;
-}
-
-static int crypto_authenc_genicv(struct aead_request *req, u8 *iv,
-				 unsigned int flags)
-{
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct scatterlist *dst = req->dst;
-	struct scatterlist *assoc = req->assoc;
-	struct scatterlist *cipher = areq_ctx->cipher;
-	struct scatterlist *asg = areq_ctx->asg;
-	unsigned int ivsize = crypto_aead_ivsize(authenc);
-	unsigned int cryptlen = req->cryptlen;
-	authenc_ahash_t authenc_ahash_fn = crypto_authenc_ahash_fb;
-	struct page *dstp;
-	u8 *vdst;
-	u8 *hash;
-
-	dstp = sg_page(dst);
-	vdst = PageHighMem(dstp) ? NULL : page_address(dstp) + dst->offset;
-
-	if (ivsize) {
-		sg_init_table(cipher, 2);
-		sg_set_buf(cipher, iv, ivsize);
-		scatterwalk_crypto_chain(cipher, dst, vdst == iv + ivsize, 2);
-		dst = cipher;
-		cryptlen += ivsize;
-	}
-
-	if (req->assoclen && sg_is_last(assoc)) {
-		authenc_ahash_fn = crypto_authenc_ahash;
-		sg_init_table(asg, 2);
-		sg_set_page(asg, sg_page(assoc), assoc->length, assoc->offset);
-		scatterwalk_crypto_chain(asg, dst, 0, 2);
-		dst = asg;
-		cryptlen += req->assoclen;
-	}
-
-	areq_ctx->cryptlen = cryptlen;
-	areq_ctx->sg = dst;
-
-	areq_ctx->complete = authenc_geniv_ahash_done;
-	areq_ctx->update_complete = authenc_geniv_ahash_update_done;
-
-	hash = authenc_ahash_fn(req, flags);
-	if (IS_ERR(hash))
-		return PTR_ERR(hash);
+		return err;
 
-	scatterwalk_map_and_copy(hash, dst, cryptlen,
+	scatterwalk_map_and_copy(hash, req->dst, req->assoclen + req->cryptlen,
 				 crypto_aead_authsize(authenc), 1);
+
 	return 0;
 }
 
@@ -377,180 +171,155 @@ static void crypto_authenc_encrypt_done(struct crypto_async_request *req,
 {
 	struct aead_request *areq = req->data;
 
-	if (!err) {
-		struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
-		struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-		struct authenc_request_ctx *areq_ctx = aead_request_ctx(areq);
-		struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-							    + ctx->reqoff);
-		u8 *iv = (u8 *)abreq - crypto_ablkcipher_ivsize(ctx->enc);
+	if (err)
+		goto out;
 
-		err = crypto_authenc_genicv(areq, iv, 0);
-	}
+	err = crypto_authenc_genicv(areq, 0);
 
+out:
 	authenc_request_complete(areq, err);
 }
 
+static int crypto_authenc_copy_assoc(struct aead_request *req)
+{
+	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
+	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
+	struct blkcipher_desc desc = {
+		.tfm = ctx->null,
+	};
+
+	return crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					req->assoclen);
+}
+
 static int crypto_authenc_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
+	struct aead_instance *inst = aead_alg_instance(authenc);
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
+	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct crypto_ablkcipher *enc = ctx->enc;
-	struct scatterlist *dst = req->dst;
 	unsigned int cryptlen = req->cryptlen;
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-						    + ctx->reqoff);
-	u8 *iv = (u8 *)abreq - crypto_ablkcipher_ivsize(enc);
+	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail +
+						    ictx->reqoff);
+	struct scatterlist *src, *dst;
 	int err;
 
+	sg_init_table(areq_ctx->src, 2);
+	src = scatterwalk_ffwd(areq_ctx->src, req->src, req->assoclen);
+	dst = src;
+
+	if (req->src != req->dst) {
+		err = crypto_authenc_copy_assoc(req);
+		if (err)
+			return err;
+
+		sg_init_table(areq_ctx->dst, 2);
+		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, req->assoclen);
+	}
+
 	ablkcipher_request_set_tfm(abreq, enc);
 	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
 					crypto_authenc_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, req->src, dst, cryptlen, req->iv);
-
-	memcpy(iv, req->iv, crypto_aead_ivsize(authenc));
+	ablkcipher_request_set_crypt(abreq, src, dst, cryptlen, req->iv);
 
 	err = crypto_ablkcipher_encrypt(abreq);
 	if (err)
 		return err;
 
-	return crypto_authenc_genicv(req, iv, CRYPTO_TFM_REQ_MAY_SLEEP);
+	return crypto_authenc_genicv(req, aead_request_flags(req));
 }
 
-static void crypto_authenc_givencrypt_done(struct crypto_async_request *req,
-					   int err)
+static int crypto_authenc_decrypt_tail(struct aead_request *req,
+				       unsigned int flags)
 {
-	struct aead_request *areq = req->data;
-
-	if (!err) {
-		struct skcipher_givcrypt_request *greq = aead_request_ctx(areq);
-
-		err = crypto_authenc_genicv(areq, greq->giv, 0);
-	}
+	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
+	struct aead_instance *inst = aead_alg_instance(authenc);
+	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
+	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
+	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff);
+	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail +
+						    ictx->reqoff);
+	unsigned int authsize = crypto_aead_authsize(authenc);
+	u8 *ihash = ahreq->result + authsize;
+	struct scatterlist *src, *dst;
 
-	authenc_request_complete(areq, err);
-}
+	scatterwalk_map_and_copy(ihash, req->src, ahreq->nbytes, authsize, 0);
 
-static int crypto_authenc_givencrypt(struct aead_givcrypt_request *req)
-{
-	struct crypto_aead *authenc = aead_givcrypt_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct aead_request *areq = &req->areq;
-	struct skcipher_givcrypt_request *greq = aead_request_ctx(areq);
-	u8 *iv = req->giv;
-	int err;
+	if (crypto_memneq(ihash, ahreq->result, authsize))
+		return -EBADMSG;
 
-	skcipher_givcrypt_set_tfm(greq, ctx->enc);
-	skcipher_givcrypt_set_callback(greq, aead_request_flags(areq),
-				       crypto_authenc_givencrypt_done, areq);
-	skcipher_givcrypt_set_crypt(greq, areq->src, areq->dst, areq->cryptlen,
-				    areq->iv);
-	skcipher_givcrypt_set_giv(greq, iv, req->seq);
+	sg_init_table(areq_ctx->src, 2);
+	src = scatterwalk_ffwd(areq_ctx->src, req->src, req->assoclen);
+	dst = src;
 
-	err = crypto_skcipher_givencrypt(greq);
-	if (err)
-		return err;
+	if (req->src != req->dst) {
+		sg_init_table(areq_ctx->dst, 2);
+		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, req->assoclen);
+	}
 
-	return crypto_authenc_genicv(areq, iv, CRYPTO_TFM_REQ_MAY_SLEEP);
-}
+	ablkcipher_request_set_tfm(abreq, ctx->enc);
+	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
+					req->base.complete, req->base.data);
+	ablkcipher_request_set_crypt(abreq, src, dst,
+				     req->cryptlen - authsize, req->iv);
 
-static int crypto_authenc_verify(struct aead_request *req,
-				 authenc_ahash_t authenc_ahash_fn)
-{
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	u8 *ohash;
-	u8 *ihash;
-	unsigned int authsize;
-
-	areq_ctx->complete = authenc_verify_ahash_done;
-	areq_ctx->update_complete = authenc_verify_ahash_update_done;
-
-	ohash = authenc_ahash_fn(req, CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (IS_ERR(ohash))
-		return PTR_ERR(ohash);
-
-	authsize = crypto_aead_authsize(authenc);
-	ihash = ohash + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
-	return crypto_memneq(ihash, ohash, authsize) ? -EBADMSG : 0;
+	return crypto_ablkcipher_decrypt(abreq);
 }
 
-static int crypto_authenc_iverify(struct aead_request *req, u8 *iv,
-				  unsigned int cryptlen)
+static void authenc_verify_ahash_done(struct crypto_async_request *areq,
+				      int err)
 {
-	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct scatterlist *src = req->src;
-	struct scatterlist *assoc = req->assoc;
-	struct scatterlist *cipher = areq_ctx->cipher;
-	struct scatterlist *asg = areq_ctx->asg;
-	unsigned int ivsize = crypto_aead_ivsize(authenc);
-	authenc_ahash_t authenc_ahash_fn = crypto_authenc_ahash_fb;
-	struct page *srcp;
-	u8 *vsrc;
-
-	srcp = sg_page(src);
-	vsrc = PageHighMem(srcp) ? NULL : page_address(srcp) + src->offset;
-
-	if (ivsize) {
-		sg_init_table(cipher, 2);
-		sg_set_buf(cipher, iv, ivsize);
-		scatterwalk_crypto_chain(cipher, src, vsrc == iv + ivsize, 2);
-		src = cipher;
-		cryptlen += ivsize;
-	}
+	struct aead_request *req = areq->data;
 
-	if (req->assoclen && sg_is_last(assoc)) {
-		authenc_ahash_fn = crypto_authenc_ahash;
-		sg_init_table(asg, 2);
-		sg_set_page(asg, sg_page(assoc), assoc->length, assoc->offset);
-		scatterwalk_crypto_chain(asg, src, 0, 2);
-		src = asg;
-		cryptlen += req->assoclen;
-	}
+	if (err)
+		goto out;
 
-	areq_ctx->cryptlen = cryptlen;
-	areq_ctx->sg = src;
+	err = crypto_authenc_decrypt_tail(req, 0);
 
-	return crypto_authenc_verify(req, authenc_ahash_fn);
+out:
+	authenc_request_complete(req, err);
 }
 
 static int crypto_authenc_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct ablkcipher_request *abreq = aead_request_ctx(req);
-	unsigned int cryptlen = req->cryptlen;
 	unsigned int authsize = crypto_aead_authsize(authenc);
-	u8 *iv = req->iv;
+	struct aead_instance *inst = aead_alg_instance(authenc);
+	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
+	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct crypto_ahash *auth = ctx->auth;
+	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
+	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff);
+	u8 *hash = areq_ctx->tail;
 	int err;
 
-	if (cryptlen < authsize)
-		return -EINVAL;
-	cryptlen -= authsize;
+	hash = (u8 *)ALIGN((unsigned long)hash + crypto_ahash_alignmask(auth),
+			   crypto_ahash_alignmask(auth) + 1);
 
-	err = crypto_authenc_iverify(req, iv, cryptlen);
+	ahash_request_set_tfm(ahreq, auth);
+	ahash_request_set_crypt(ahreq, req->src, hash,
+				req->assoclen + req->cryptlen - authsize);
+	ahash_request_set_callback(ahreq, aead_request_flags(req),
+				   authenc_verify_ahash_done, req);
+
+	err = crypto_ahash_digest(ahreq);
 	if (err)
 		return err;
 
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst, cryptlen, iv);
-
-	return crypto_ablkcipher_decrypt(abreq);
+	return crypto_authenc_decrypt_tail(req, aead_request_flags(req));
 }
 
-static int crypto_authenc_init_tfm(struct crypto_tfm *tfm)
+static int crypto_authenc_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct authenc_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_authenc_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ahash *auth;
 	struct crypto_ablkcipher *enc;
+	struct crypto_blkcipher *null;
 	int err;
 
 	auth = crypto_spawn_ahash(&ictx->auth);
@@ -562,42 +331,57 @@ static int crypto_authenc_init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
+	null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(null);
+	if (IS_ERR(null))
+		goto err_free_skcipher;
+
 	ctx->auth = auth;
 	ctx->enc = enc;
+	ctx->null = null;
 
-	ctx->reqoff = ALIGN(2 * crypto_ahash_digestsize(auth) +
-			    crypto_ahash_alignmask(auth),
-			    crypto_ahash_alignmask(auth) + 1) +
-		      crypto_ablkcipher_ivsize(enc);
-
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+	crypto_aead_set_reqsize(
+		tfm,
 		sizeof(struct authenc_request_ctx) +
-		ctx->reqoff +
+		ictx->reqoff +
 		max_t(unsigned int,
-			crypto_ahash_reqsize(auth) +
-			sizeof(struct ahash_request),
-			sizeof(struct skcipher_givcrypt_request) +
-			crypto_ablkcipher_reqsize(enc)));
+		      crypto_ahash_reqsize(auth) +
+		      sizeof(struct ahash_request),
+		      sizeof(struct ablkcipher_request) +
+		      crypto_ablkcipher_reqsize(enc)));
 
 	return 0;
 
+err_free_skcipher:
+	crypto_free_ablkcipher(enc);
 err_free_ahash:
 	crypto_free_ahash(auth);
 	return err;
 }
 
-static void crypto_authenc_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_authenc_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_authenc_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->auth);
 	crypto_free_ablkcipher(ctx->enc);
+	crypto_put_default_null_skcipher();
 }
 
-static struct crypto_instance *crypto_authenc_alloc(struct rtattr **tb)
+static void crypto_authenc_free(struct aead_instance *inst)
+{
+	struct authenc_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_skcipher(&ctx->enc);
+	crypto_drop_ahash(&ctx->auth);
+	kfree(inst);
+}
+
+static int crypto_authenc_create(struct crypto_template *tmpl,
+				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
 	struct crypto_alg *enc;
@@ -607,15 +391,15 @@ static struct crypto_instance *crypto_authenc_alloc(struct rtattr **tb)
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
 			       CRYPTO_ALG_TYPE_AHASH_MASK);
 	if (IS_ERR(auth))
-		return ERR_CAST(auth);
+		return PTR_ERR(auth);
 
 	auth_base = &auth->base;
 
@@ -629,13 +413,14 @@ static struct crypto_instance *crypto_authenc_alloc(struct rtattr **tb)
 	if (!inst)
 		goto out_put_auth;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 
-	err = crypto_init_ahash_spawn(&ctx->auth, auth, inst);
+	err = crypto_init_ahash_spawn(&ctx->auth, auth,
+				      aead_crypto_instance(inst));
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->enc, inst);
+	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
 	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
 				   crypto_requires_sync(algt->type,
 							algt->mask));
@@ -644,41 +429,47 @@ static struct crypto_instance *crypto_authenc_alloc(struct rtattr **tb)
 
 	enc = crypto_skcipher_spawn_alg(&ctx->enc);
 
+	ctx->reqoff = ALIGN(2 * auth->digestsize + auth_base->cra_alignmask,
+			    auth_base->cra_alignmask + 1);
+
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
 		     "authenc(%s,%s)", auth_base->cra_name, enc->cra_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "authenc(%s,%s)", auth_base->cra_driver_name,
 		     enc->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= enc->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = enc->cra_priority *
-				 10 + auth_base->cra_priority;
-	inst->alg.cra_blocksize = enc->cra_blocksize;
-	inst->alg.cra_alignmask = auth_base->cra_alignmask | enc->cra_alignmask;
-	inst->alg.cra_type = &crypto_aead_type;
+	inst->alg.base.cra_flags = enc->cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = enc->cra_priority * 10 +
+				      auth_base->cra_priority;
+	inst->alg.base.cra_blocksize = enc->cra_blocksize;
+	inst->alg.base.cra_alignmask = auth_base->cra_alignmask |
+				       enc->cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_authenc_ctx);
+
+	inst->alg.ivsize = enc->cra_ablkcipher.ivsize;
+	inst->alg.maxauthsize = auth->digestsize;
 
-	inst->alg.cra_aead.ivsize = enc->cra_ablkcipher.ivsize;
-	inst->alg.cra_aead.maxauthsize = auth->digestsize;
+	inst->alg.init = crypto_authenc_init_tfm;
+	inst->alg.exit = crypto_authenc_exit_tfm;
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_authenc_ctx);
+	inst->alg.setkey = crypto_authenc_setkey;
+	inst->alg.encrypt = crypto_authenc_encrypt;
+	inst->alg.decrypt = crypto_authenc_decrypt;
 
-	inst->alg.cra_init = crypto_authenc_init_tfm;
-	inst->alg.cra_exit = crypto_authenc_exit_tfm;
+	inst->free = crypto_authenc_free;
 
-	inst->alg.cra_aead.setkey = crypto_authenc_setkey;
-	inst->alg.cra_aead.encrypt = crypto_authenc_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_authenc_decrypt;
-	inst->alg.cra_aead.givencrypt = crypto_authenc_givencrypt;
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_enc;
 
 out:
 	crypto_mod_put(auth_base);
-	return inst;
+	return err;
 
 err_drop_enc:
 	crypto_drop_skcipher(&ctx->enc);
@@ -687,23 +478,12 @@ err_drop_auth:
 err_free_inst:
 	kfree(inst);
 out_put_auth:
-	inst = ERR_PTR(err);
 	goto out;
 }
 
-static void crypto_authenc_free(struct crypto_instance *inst)
-{
-	struct authenc_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_skcipher(&ctx->enc);
-	crypto_drop_ahash(&ctx->auth);
-	kfree(inst);
-}
-
 static struct crypto_template crypto_authenc_tmpl = {
 	.name = "authenc",
-	.alloc = crypto_authenc_alloc,
-	.free = crypto_authenc_free,
+	.create = crypto_authenc_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index a3da6770bc9e..0c0468869e25 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2010 secunet Security Networks AG
  * Copyright (C) 2010 Steffen Klassert <steffen.klassert@secunet.com>
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -16,6 +17,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
+#include <crypto/null.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -34,19 +36,12 @@ struct crypto_authenc_esn_ctx {
 	unsigned int reqoff;
 	struct crypto_ahash *auth;
 	struct crypto_ablkcipher *enc;
+	struct crypto_blkcipher *null;
 };
 
 struct authenc_esn_request_ctx {
-	unsigned int cryptlen;
-	unsigned int headlen;
-	unsigned int trailen;
-	struct scatterlist *sg;
-	struct scatterlist hsg[2];
-	struct scatterlist tsg[1];
-	struct scatterlist cipher[2];
-	crypto_completion_t complete;
-	crypto_completion_t update_complete;
-	crypto_completion_t update_complete2;
+	struct scatterlist src[2];
+	struct scatterlist dst[2];
 	char tail[];
 };
 
@@ -56,6 +51,15 @@ static void authenc_esn_request_complete(struct aead_request *req, int err)
 		aead_request_complete(req, err);
 }
 
+static int crypto_authenc_esn_setauthsize(struct crypto_aead *authenc_esn,
+					  unsigned int authsize)
+{
+	if (authsize > 0 && authsize < 4)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int crypto_authenc_esn_setkey(struct crypto_aead *authenc_esn, const u8 *key,
 				     unsigned int keylen)
 {
@@ -93,556 +97,242 @@ badkey:
 	goto out;
 }
 
-static void authenc_esn_geniv_ahash_update_done(struct crypto_async_request *areq,
-						int err)
-{
-	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, ahreq->result,
-				areq_ctx->cryptlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->update_complete2, req);
-
-	err = crypto_ahash_update(ahreq);
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->tsg, ahreq->result,
-				areq_ctx->trailen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		goto out;
-
-	scatterwalk_map_and_copy(ahreq->result, areq_ctx->sg,
-				 areq_ctx->cryptlen,
-				 crypto_aead_authsize(authenc_esn), 1);
-
-out:
-	authenc_esn_request_complete(req, err);
-}
-
-static void authenc_esn_geniv_ahash_update_done2(struct crypto_async_request *areq,
-						 int err)
+static int crypto_authenc_esn_genicv_tail(struct aead_request *req,
+					  unsigned int flags)
 {
-	struct aead_request *req = areq->data;
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->tsg, ahreq->result,
-				areq_ctx->trailen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		goto out;
+	struct crypto_ahash *auth = ctx->auth;
+	u8 *hash = PTR_ALIGN((u8 *)areq_ctx->tail,
+			     crypto_ahash_alignmask(auth) + 1);
+	unsigned int authsize = crypto_aead_authsize(authenc_esn);
+	unsigned int assoclen = req->assoclen;
+	unsigned int cryptlen = req->cryptlen;
+	struct scatterlist *dst = req->dst;
+	u32 tmp[2];
 
-	scatterwalk_map_and_copy(ahreq->result, areq_ctx->sg,
-				 areq_ctx->cryptlen,
-				 crypto_aead_authsize(authenc_esn), 1);
+	/* Move high-order bits of sequence number back. */
+	scatterwalk_map_and_copy(tmp, dst, 4, 4, 0);
+	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0);
+	scatterwalk_map_and_copy(tmp, dst, 0, 8, 1);
 
-out:
-	authenc_esn_request_complete(req, err);
+	scatterwalk_map_and_copy(hash, dst, assoclen + cryptlen, authsize, 1);
+	return 0;
 }
 
-
 static void authenc_esn_geniv_ahash_done(struct crypto_async_request *areq,
 					 int err)
 {
 	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
 
-	if (err)
-		goto out;
-
-	scatterwalk_map_and_copy(ahreq->result, areq_ctx->sg,
-				 areq_ctx->cryptlen,
-				 crypto_aead_authsize(authenc_esn), 1);
-
-out:
+	err = err ?: crypto_authenc_esn_genicv_tail(req, 0);
 	aead_request_complete(req, err);
 }
 
-
-static void authenc_esn_verify_ahash_update_done(struct crypto_async_request *areq,
-						 int err)
+static int crypto_authenc_esn_genicv(struct aead_request *req,
+				     unsigned int flags)
 {
-	u8 *ihash;
-	unsigned int authsize;
-	struct ablkcipher_request *abreq;
-	struct aead_request *req = areq->data;
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-	unsigned int cryptlen = req->cryptlen;
-
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, ahreq->result,
-				areq_ctx->cryptlen);
-
-	ahash_request_set_callback(ahreq,
-				   aead_request_flags(req) &
-				   CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->update_complete2, req);
-
-	err = crypto_ahash_update(ahreq);
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->tsg, ahreq->result,
-				areq_ctx->trailen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		goto out;
-
-	authsize = crypto_aead_authsize(authenc_esn);
-	cryptlen -= authsize;
-	ihash = ahreq->result + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
-
-	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
-	if (err)
-		goto out;
-
-	abreq = aead_request_ctx(req);
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst,
-				     cryptlen, req->iv);
-
-	err = crypto_ablkcipher_decrypt(abreq);
-
-out:
-	authenc_esn_request_complete(req, err);
-}
-
-static void authenc_esn_verify_ahash_update_done2(struct crypto_async_request *areq,
-						  int err)
-{
-	u8 *ihash;
-	unsigned int authsize;
-	struct ablkcipher_request *abreq;
-	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
+	struct crypto_ahash *auth = ctx->auth;
+	u8 *hash = PTR_ALIGN((u8 *)areq_ctx->tail,
+			     crypto_ahash_alignmask(auth) + 1);
 	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
+	unsigned int authsize = crypto_aead_authsize(authenc_esn);
+	unsigned int assoclen = req->assoclen;
 	unsigned int cryptlen = req->cryptlen;
+	struct scatterlist *dst = req->dst;
+	u32 tmp[2];
 
-	if (err)
-		goto out;
-
-	ahash_request_set_crypt(ahreq, areq_ctx->tsg, ahreq->result,
-				areq_ctx->trailen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) &
-					  CRYPTO_TFM_REQ_MAY_SLEEP,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		goto out;
-
-	authsize = crypto_aead_authsize(authenc_esn);
-	cryptlen -= authsize;
-	ihash = ahreq->result + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
+	if (!authsize)
+		return 0;
 
-	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
-	if (err)
-		goto out;
+	/* Move high-order bits of sequence number to the end. */
+	scatterwalk_map_and_copy(tmp, dst, 0, 8, 0);
+	scatterwalk_map_and_copy(tmp, dst, 4, 4, 1);
+	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 1);
 
-	abreq = aead_request_ctx(req);
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst,
-				     cryptlen, req->iv);
+	sg_init_table(areq_ctx->dst, 2);
+	dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4);
 
-	err = crypto_ablkcipher_decrypt(abreq);
+	ahash_request_set_tfm(ahreq, auth);
+	ahash_request_set_crypt(ahreq, dst, hash, assoclen + cryptlen);
+	ahash_request_set_callback(ahreq, flags,
+				   authenc_esn_geniv_ahash_done, req);
 
-out:
-	authenc_esn_request_complete(req, err);
+	return crypto_ahash_digest(ahreq) ?:
+	       crypto_authenc_esn_genicv_tail(req, aead_request_flags(req));
 }
 
 
-static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
-					  int err)
+static void crypto_authenc_esn_encrypt_done(struct crypto_async_request *req,
+					    int err)
 {
-	u8 *ihash;
-	unsigned int authsize;
-	struct ablkcipher_request *abreq;
-	struct aead_request *req = areq->data;
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-	unsigned int cryptlen = req->cryptlen;
-
-	if (err)
-		goto out;
-
-	authsize = crypto_aead_authsize(authenc_esn);
-	cryptlen -= authsize;
-	ihash = ahreq->result + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
-
-	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
-	if (err)
-		goto out;
-
-	abreq = aead_request_ctx(req);
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst,
-				     cryptlen, req->iv);
+	struct aead_request *areq = req->data;
 
-	err = crypto_ablkcipher_decrypt(abreq);
+	if (!err)
+		err = crypto_authenc_esn_genicv(areq, 0);
 
-out:
-	authenc_esn_request_complete(req, err);
+	authenc_esn_request_complete(areq, err);
 }
 
-static u8 *crypto_authenc_esn_ahash(struct aead_request *req,
-				    unsigned int flags)
+static int crypto_authenc_esn_copy(struct aead_request *req, unsigned int len)
 {
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct crypto_ahash *auth = ctx->auth;
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
-	u8 *hash = areq_ctx->tail;
-	int err;
-
-	hash = (u8 *)ALIGN((unsigned long)hash + crypto_ahash_alignmask(auth),
-			    crypto_ahash_alignmask(auth) + 1);
-
-	ahash_request_set_tfm(ahreq, auth);
+	struct blkcipher_desc desc = {
+		.tfm = ctx->null,
+	};
 
-	err = crypto_ahash_init(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	ahash_request_set_crypt(ahreq, areq_ctx->hsg, hash, areq_ctx->headlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) & flags,
-				   areq_ctx->update_complete, req);
-
-	err = crypto_ahash_update(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	ahash_request_set_crypt(ahreq, areq_ctx->sg, hash, areq_ctx->cryptlen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) & flags,
-				   areq_ctx->update_complete2, req);
-
-	err = crypto_ahash_update(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	ahash_request_set_crypt(ahreq, areq_ctx->tsg, hash,
-				areq_ctx->trailen);
-	ahash_request_set_callback(ahreq, aead_request_flags(req) & flags,
-				   areq_ctx->complete, req);
-
-	err = crypto_ahash_finup(ahreq);
-	if (err)
-		return ERR_PTR(err);
-
-	return hash;
+	return crypto_blkcipher_encrypt(&desc, req->dst, req->src, len);
 }
 
-static int crypto_authenc_esn_genicv(struct aead_request *req, u8 *iv,
-				     unsigned int flags)
+static int crypto_authenc_esn_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct scatterlist *dst = req->dst;
-	struct scatterlist *assoc = req->assoc;
-	struct scatterlist *cipher = areq_ctx->cipher;
-	struct scatterlist *hsg = areq_ctx->hsg;
-	struct scatterlist *tsg = areq_ctx->tsg;
-	struct scatterlist *assoc1;
-	struct scatterlist *assoc2;
-	unsigned int ivsize = crypto_aead_ivsize(authenc_esn);
+	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
+	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
+						    + ctx->reqoff);
+	struct crypto_ablkcipher *enc = ctx->enc;
+	unsigned int assoclen = req->assoclen;
 	unsigned int cryptlen = req->cryptlen;
-	struct page *dstp;
-	u8 *vdst;
-	u8 *hash;
-
-	dstp = sg_page(dst);
-	vdst = PageHighMem(dstp) ? NULL : page_address(dstp) + dst->offset;
-
-	if (ivsize) {
-		sg_init_table(cipher, 2);
-		sg_set_buf(cipher, iv, ivsize);
-		scatterwalk_crypto_chain(cipher, dst, vdst == iv + ivsize, 2);
-		dst = cipher;
-		cryptlen += ivsize;
-	}
-
-	if (sg_is_last(assoc))
-		return -EINVAL;
-
-	assoc1 = assoc + 1;
-	if (sg_is_last(assoc1))
-		return -EINVAL;
-
-	assoc2 = assoc + 2;
-	if (!sg_is_last(assoc2))
-		return -EINVAL;
-
-	sg_init_table(hsg, 2);
-	sg_set_page(hsg, sg_page(assoc), assoc->length, assoc->offset);
-	sg_set_page(hsg + 1, sg_page(assoc2), assoc2->length, assoc2->offset);
-
-	sg_init_table(tsg, 1);
-	sg_set_page(tsg, sg_page(assoc1), assoc1->length, assoc1->offset);
-
-	areq_ctx->cryptlen = cryptlen;
-	areq_ctx->headlen = assoc->length + assoc2->length;
-	areq_ctx->trailen = assoc1->length;
-	areq_ctx->sg = dst;
-
-	areq_ctx->complete = authenc_esn_geniv_ahash_done;
-	areq_ctx->update_complete = authenc_esn_geniv_ahash_update_done;
-	areq_ctx->update_complete2 = authenc_esn_geniv_ahash_update_done2;
+	struct scatterlist *src, *dst;
+	int err;
 
-	hash = crypto_authenc_esn_ahash(req, flags);
-	if (IS_ERR(hash))
-		return PTR_ERR(hash);
+	sg_init_table(areq_ctx->src, 2);
+	src = scatterwalk_ffwd(areq_ctx->src, req->src, assoclen);
+	dst = src;
 
-	scatterwalk_map_and_copy(hash, dst, cryptlen,
-				 crypto_aead_authsize(authenc_esn), 1);
-	return 0;
-}
+	if (req->src != req->dst) {
+		err = crypto_authenc_esn_copy(req, assoclen);
+		if (err)
+			return err;
 
-
-static void crypto_authenc_esn_encrypt_done(struct crypto_async_request *req,
-					    int err)
-{
-	struct aead_request *areq = req->data;
-
-	if (!err) {
-		struct crypto_aead *authenc_esn = crypto_aead_reqtfm(areq);
-		struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-		struct ablkcipher_request *abreq = aead_request_ctx(areq);
-		u8 *iv = (u8 *)(abreq + 1) +
-			 crypto_ablkcipher_reqsize(ctx->enc);
-
-		err = crypto_authenc_esn_genicv(areq, iv, 0);
+		sg_init_table(areq_ctx->dst, 2);
+		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, assoclen);
 	}
 
-	authenc_esn_request_complete(areq, err);
-}
-
-static int crypto_authenc_esn_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct crypto_ablkcipher *enc = ctx->enc;
-	struct scatterlist *dst = req->dst;
-	unsigned int cryptlen = req->cryptlen;
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-						    + ctx->reqoff);
-	u8 *iv = (u8 *)abreq - crypto_ablkcipher_ivsize(enc);
-	int err;
-
 	ablkcipher_request_set_tfm(abreq, enc);
 	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
 					crypto_authenc_esn_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, req->src, dst, cryptlen, req->iv);
-
-	memcpy(iv, req->iv, crypto_aead_ivsize(authenc_esn));
+	ablkcipher_request_set_crypt(abreq, src, dst, cryptlen, req->iv);
 
 	err = crypto_ablkcipher_encrypt(abreq);
 	if (err)
 		return err;
 
-	return crypto_authenc_esn_genicv(req, iv, CRYPTO_TFM_REQ_MAY_SLEEP);
+	return crypto_authenc_esn_genicv(req, aead_request_flags(req));
 }
 
-static void crypto_authenc_esn_givencrypt_done(struct crypto_async_request *req,
-					       int err)
+static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
+					   unsigned int flags)
 {
-	struct aead_request *areq = req->data;
-
-	if (!err) {
-		struct skcipher_givcrypt_request *greq = aead_request_ctx(areq);
-
-		err = crypto_authenc_esn_genicv(areq, greq->giv, 0);
-	}
+	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
+	unsigned int authsize = crypto_aead_authsize(authenc_esn);
+	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
+	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
+	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
+						    + ctx->reqoff);
+	struct crypto_ahash *auth = ctx->auth;
+	u8 *ohash = PTR_ALIGN((u8 *)areq_ctx->tail,
+			      crypto_ahash_alignmask(auth) + 1);
+	unsigned int cryptlen = req->cryptlen - authsize;
+	unsigned int assoclen = req->assoclen;
+	struct scatterlist *dst = req->dst;
+	u8 *ihash = ohash + crypto_ahash_digestsize(auth);
+	u32 tmp[2];
 
-	authenc_esn_request_complete(areq, err);
-}
+	/* Move high-order bits of sequence number back. */
+	scatterwalk_map_and_copy(tmp, dst, 4, 4, 0);
+	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0);
+	scatterwalk_map_and_copy(tmp, dst, 0, 8, 1);
 
-static int crypto_authenc_esn_givencrypt(struct aead_givcrypt_request *req)
-{
-	struct crypto_aead *authenc_esn = aead_givcrypt_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct aead_request *areq = &req->areq;
-	struct skcipher_givcrypt_request *greq = aead_request_ctx(areq);
-	u8 *iv = req->giv;
-	int err;
+	if (crypto_memneq(ihash, ohash, authsize))
+		return -EBADMSG;
 
-	skcipher_givcrypt_set_tfm(greq, ctx->enc);
-	skcipher_givcrypt_set_callback(greq, aead_request_flags(areq),
-				       crypto_authenc_esn_givencrypt_done, areq);
-	skcipher_givcrypt_set_crypt(greq, areq->src, areq->dst, areq->cryptlen,
-				    areq->iv);
-	skcipher_givcrypt_set_giv(greq, iv, req->seq);
+	sg_init_table(areq_ctx->dst, 2);
+	dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen);
 
-	err = crypto_skcipher_givencrypt(greq);
-	if (err)
-		return err;
+	ablkcipher_request_set_tfm(abreq, ctx->enc);
+	ablkcipher_request_set_callback(abreq, flags,
+					req->base.complete, req->base.data);
+	ablkcipher_request_set_crypt(abreq, dst, dst, cryptlen, req->iv);
 
-	return crypto_authenc_esn_genicv(areq, iv, CRYPTO_TFM_REQ_MAY_SLEEP);
+	return crypto_ablkcipher_decrypt(abreq);
 }
 
-static int crypto_authenc_esn_verify(struct aead_request *req)
+static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
+					  int err)
 {
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	u8 *ohash;
-	u8 *ihash;
-	unsigned int authsize;
-
-	areq_ctx->complete = authenc_esn_verify_ahash_done;
-	areq_ctx->update_complete = authenc_esn_verify_ahash_update_done;
-
-	ohash = crypto_authenc_esn_ahash(req, CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (IS_ERR(ohash))
-		return PTR_ERR(ohash);
+	struct aead_request *req = areq->data;
 
-	authsize = crypto_aead_authsize(authenc_esn);
-	ihash = ohash + authsize;
-	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
-				 authsize, 0);
-	return crypto_memneq(ihash, ohash, authsize) ? -EBADMSG : 0;
+	err = err ?: crypto_authenc_esn_decrypt_tail(req, 0);
+	aead_request_complete(req, err);
 }
 
-static int crypto_authenc_esn_iverify(struct aead_request *req, u8 *iv,
-				      unsigned int cryptlen)
+static int crypto_authenc_esn_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct scatterlist *src = req->src;
-	struct scatterlist *assoc = req->assoc;
-	struct scatterlist *cipher = areq_ctx->cipher;
-	struct scatterlist *hsg = areq_ctx->hsg;
-	struct scatterlist *tsg = areq_ctx->tsg;
-	struct scatterlist *assoc1;
-	struct scatterlist *assoc2;
-	unsigned int ivsize = crypto_aead_ivsize(authenc_esn);
-	struct page *srcp;
-	u8 *vsrc;
-
-	srcp = sg_page(src);
-	vsrc = PageHighMem(srcp) ? NULL : page_address(srcp) + src->offset;
-
-	if (ivsize) {
-		sg_init_table(cipher, 2);
-		sg_set_buf(cipher, iv, ivsize);
-		scatterwalk_crypto_chain(cipher, src, vsrc == iv + ivsize, 2);
-		src = cipher;
-		cryptlen += ivsize;
-	}
-
-	if (sg_is_last(assoc))
-		return -EINVAL;
-
-	assoc1 = assoc + 1;
-	if (sg_is_last(assoc1))
-		return -EINVAL;
+	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
+	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ctx->reqoff);
+	unsigned int authsize = crypto_aead_authsize(authenc_esn);
+	struct crypto_ahash *auth = ctx->auth;
+	u8 *ohash = PTR_ALIGN((u8 *)areq_ctx->tail,
+			      crypto_ahash_alignmask(auth) + 1);
+	unsigned int assoclen = req->assoclen;
+	unsigned int cryptlen = req->cryptlen;
+	u8 *ihash = ohash + crypto_ahash_digestsize(auth);
+	struct scatterlist *dst = req->dst;
+	u32 tmp[2];
+	int err;
 
-	assoc2 = assoc + 2;
-	if (!sg_is_last(assoc2))
-		return -EINVAL;
+	cryptlen -= authsize;
 
-	sg_init_table(hsg, 2);
-	sg_set_page(hsg, sg_page(assoc), assoc->length, assoc->offset);
-	sg_set_page(hsg + 1, sg_page(assoc2), assoc2->length, assoc2->offset);
+	if (req->src != dst) {
+		err = crypto_authenc_esn_copy(req, assoclen + cryptlen);
+		if (err)
+			return err;
+	}
 
-	sg_init_table(tsg, 1);
-	sg_set_page(tsg, sg_page(assoc1), assoc1->length, assoc1->offset);
+	scatterwalk_map_and_copy(ihash, req->src, assoclen + cryptlen,
+				 authsize, 0);
 
-	areq_ctx->cryptlen = cryptlen;
-	areq_ctx->headlen = assoc->length + assoc2->length;
-	areq_ctx->trailen = assoc1->length;
-	areq_ctx->sg = src;
+	if (!authsize)
+		goto tail;
 
-	areq_ctx->complete = authenc_esn_verify_ahash_done;
-	areq_ctx->update_complete = authenc_esn_verify_ahash_update_done;
-	areq_ctx->update_complete2 = authenc_esn_verify_ahash_update_done2;
+	/* Move high-order bits of sequence number to the end. */
+	scatterwalk_map_and_copy(tmp, dst, 0, 8, 0);
+	scatterwalk_map_and_copy(tmp, dst, 4, 4, 1);
+	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 1);
 
-	return crypto_authenc_esn_verify(req);
-}
+	sg_init_table(areq_ctx->dst, 2);
+	dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4);
 
-static int crypto_authenc_esn_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
-	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct ablkcipher_request *abreq = aead_request_ctx(req);
-	unsigned int cryptlen = req->cryptlen;
-	unsigned int authsize = crypto_aead_authsize(authenc_esn);
-	u8 *iv = req->iv;
-	int err;
-
-	if (cryptlen < authsize)
-		return -EINVAL;
-	cryptlen -= authsize;
+	ahash_request_set_tfm(ahreq, auth);
+	ahash_request_set_crypt(ahreq, dst, ohash, assoclen + cryptlen);
+	ahash_request_set_callback(ahreq, aead_request_flags(req),
+				   authenc_esn_verify_ahash_done, req);
 
-	err = crypto_authenc_esn_iverify(req, iv, cryptlen);
+	err = crypto_ahash_digest(ahreq);
 	if (err)
 		return err;
 
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, req->src, req->dst, cryptlen, iv);
-
-	return crypto_ablkcipher_decrypt(abreq);
+tail:
+	return crypto_authenc_esn_decrypt_tail(req, aead_request_flags(req));
 }
 
-static int crypto_authenc_esn_init_tfm(struct crypto_tfm *tfm)
+static int crypto_authenc_esn_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct authenc_esn_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_authenc_esn_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct authenc_esn_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ahash *auth;
 	struct crypto_ablkcipher *enc;
+	struct crypto_blkcipher *null;
 	int err;
 
 	auth = crypto_spawn_ahash(&ictx->auth);
@@ -654,15 +344,20 @@ static int crypto_authenc_esn_init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
+	null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(null);
+	if (IS_ERR(null))
+		goto err_free_skcipher;
+
 	ctx->auth = auth;
 	ctx->enc = enc;
+	ctx->null = null;
 
-	ctx->reqoff = ALIGN(2 * crypto_ahash_digestsize(auth) +
-			    crypto_ahash_alignmask(auth),
-			    crypto_ahash_alignmask(auth) + 1) +
-		      crypto_ablkcipher_ivsize(enc);
+	ctx->reqoff = ALIGN(2 * crypto_ahash_digestsize(auth),
+			    crypto_ahash_alignmask(auth) + 1);
 
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+	crypto_aead_set_reqsize(
+		tfm,
 		sizeof(struct authenc_esn_request_ctx) +
 		ctx->reqoff +
 		max_t(unsigned int,
@@ -673,23 +368,36 @@ static int crypto_authenc_esn_init_tfm(struct crypto_tfm *tfm)
 
 	return 0;
 
+err_free_skcipher:
+	crypto_free_ablkcipher(enc);
 err_free_ahash:
 	crypto_free_ahash(auth);
 	return err;
 }
 
-static void crypto_authenc_esn_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_authenc_esn_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_authenc_esn_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->auth);
 	crypto_free_ablkcipher(ctx->enc);
+	crypto_put_default_null_skcipher();
 }
 
-static struct crypto_instance *crypto_authenc_esn_alloc(struct rtattr **tb)
+static void crypto_authenc_esn_free(struct aead_instance *inst)
+{
+	struct authenc_esn_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_skcipher(&ctx->enc);
+	crypto_drop_ahash(&ctx->auth);
+	kfree(inst);
+}
+
+static int crypto_authenc_esn_create(struct crypto_template *tmpl,
+				     struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
 	struct crypto_alg *enc;
@@ -699,15 +407,15 @@ static struct crypto_instance *crypto_authenc_esn_alloc(struct rtattr **tb)
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
 			       CRYPTO_ALG_TYPE_AHASH_MASK);
 	if (IS_ERR(auth))
-		return ERR_CAST(auth);
+		return PTR_ERR(auth);
 
 	auth_base = &auth->base;
 
@@ -721,13 +429,14 @@ static struct crypto_instance *crypto_authenc_esn_alloc(struct rtattr **tb)
 	if (!inst)
 		goto out_put_auth;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 
-	err = crypto_init_ahash_spawn(&ctx->auth, auth, inst);
+	err = crypto_init_ahash_spawn(&ctx->auth, auth,
+				      aead_crypto_instance(inst));
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->enc, inst);
+	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
 	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
 				   crypto_requires_sync(algt->type,
 							algt->mask));
@@ -737,40 +446,44 @@ static struct crypto_instance *crypto_authenc_esn_alloc(struct rtattr **tb)
 	enc = crypto_skcipher_spawn_alg(&ctx->enc);
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "authencesn(%s,%s)", auth_base->cra_name, enc->cra_name) >=
-	    CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "authencesn(%s,%s)", auth_base->cra_name,
+		     enc->cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "authencesn(%s,%s)", auth_base->cra_driver_name,
 		     enc->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= enc->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = enc->cra_priority *
-				 10 + auth_base->cra_priority;
-	inst->alg.cra_blocksize = enc->cra_blocksize;
-	inst->alg.cra_alignmask = auth_base->cra_alignmask | enc->cra_alignmask;
-	inst->alg.cra_type = &crypto_aead_type;
+	inst->alg.base.cra_flags = enc->cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = enc->cra_priority * 10 +
+				      auth_base->cra_priority;
+	inst->alg.base.cra_blocksize = enc->cra_blocksize;
+	inst->alg.base.cra_alignmask = auth_base->cra_alignmask |
+				       enc->cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_authenc_esn_ctx);
+
+	inst->alg.ivsize = enc->cra_ablkcipher.ivsize;
+	inst->alg.maxauthsize = auth->digestsize;
 
-	inst->alg.cra_aead.ivsize = enc->cra_ablkcipher.ivsize;
-	inst->alg.cra_aead.maxauthsize = auth->digestsize;
+	inst->alg.init = crypto_authenc_esn_init_tfm;
+	inst->alg.exit = crypto_authenc_esn_exit_tfm;
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_authenc_esn_ctx);
+	inst->alg.setkey = crypto_authenc_esn_setkey;
+	inst->alg.setauthsize = crypto_authenc_esn_setauthsize;
+	inst->alg.encrypt = crypto_authenc_esn_encrypt;
+	inst->alg.decrypt = crypto_authenc_esn_decrypt;
 
-	inst->alg.cra_init = crypto_authenc_esn_init_tfm;
-	inst->alg.cra_exit = crypto_authenc_esn_exit_tfm;
+	inst->free = crypto_authenc_esn_free,
 
-	inst->alg.cra_aead.setkey = crypto_authenc_esn_setkey;
-	inst->alg.cra_aead.encrypt = crypto_authenc_esn_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_authenc_esn_decrypt;
-	inst->alg.cra_aead.givencrypt = crypto_authenc_esn_givencrypt;
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_enc;
 
 out:
 	crypto_mod_put(auth_base);
-	return inst;
+	return err;
 
 err_drop_enc:
 	crypto_drop_skcipher(&ctx->enc);
@@ -779,23 +492,12 @@ err_drop_auth:
 err_free_inst:
 	kfree(inst);
 out_put_auth:
-	inst = ERR_PTR(err);
 	goto out;
 }
 
-static void crypto_authenc_esn_free(struct crypto_instance *inst)
-{
-	struct authenc_esn_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_skcipher(&ctx->enc);
-	crypto_drop_ahash(&ctx->auth);
-	kfree(inst);
-}
-
 static struct crypto_template crypto_authenc_esn_tmpl = {
 	.name = "authencesn",
-	.alloc = crypto_authenc_esn_alloc,
-	.free = crypto_authenc_esn_free,
+	.create = crypto_authenc_esn_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/ccm.c b/crypto/ccm.c
index a4d1a5eda18b..cc31ea4335bf 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -36,14 +36,20 @@ struct crypto_rfc4309_ctx {
 	u8 nonce[3];
 };
 
+struct crypto_rfc4309_req_ctx {
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
+	struct aead_request subreq;
+};
+
 struct crypto_ccm_req_priv_ctx {
 	u8 odata[16];
 	u8 idata[16];
 	u8 auth_tag[16];
 	u32 ilen;
 	u32 flags;
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
 	struct ablkcipher_request abreq;
 };
 
@@ -265,7 +271,7 @@ static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain,
 	/* format associated data and compute into mac */
 	if (assoclen) {
 		pctx->ilen = format_adata(idata, assoclen);
-		get_data_to_compute(cipher, pctx, req->assoc, req->assoclen);
+		get_data_to_compute(cipher, pctx, req->src, req->assoclen);
 	} else {
 		pctx->ilen = 0;
 	}
@@ -286,7 +292,8 @@ static void crypto_ccm_encrypt_done(struct crypto_async_request *areq, int err)
 	u8 *odata = pctx->odata;
 
 	if (!err)
-		scatterwalk_map_and_copy(odata, req->dst, req->cryptlen,
+		scatterwalk_map_and_copy(odata, req->dst,
+					 req->assoclen + req->cryptlen,
 					 crypto_aead_authsize(aead), 1);
 	aead_request_complete(req, err);
 }
@@ -300,6 +307,41 @@ static inline int crypto_ccm_check_iv(const u8 *iv)
 	return 0;
 }
 
+static int crypto_ccm_init_crypt(struct aead_request *req, u8 *tag)
+{
+	struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req);
+	struct scatterlist *sg;
+	u8 *iv = req->iv;
+	int err;
+
+	err = crypto_ccm_check_iv(iv);
+	if (err)
+		return err;
+
+	pctx->flags = aead_request_flags(req);
+
+	 /* Note: rfc 3610 and NIST 800-38C require counter of
+	 * zero to encrypt auth tag.
+	 */
+	memset(iv + 15 - iv[0], 0, iv[0] + 1);
+
+	sg_init_table(pctx->src, 3);
+	sg_set_buf(pctx->src, tag, 16);
+	sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen);
+	if (sg != pctx->src + 1)
+		sg_chain(pctx->src, 2, sg);
+
+	if (req->src != req->dst) {
+		sg_init_table(pctx->dst, 3);
+		sg_set_buf(pctx->dst, tag, 16);
+		sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen);
+		if (sg != pctx->dst + 1)
+			sg_chain(pctx->dst, 2, sg);
+	}
+
+	return 0;
+}
+
 static int crypto_ccm_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -312,32 +354,17 @@ static int crypto_ccm_encrypt(struct aead_request *req)
 	u8 *iv = req->iv;
 	int err;
 
-	err = crypto_ccm_check_iv(iv);
+	err = crypto_ccm_init_crypt(req, odata);
 	if (err)
 		return err;
 
-	pctx->flags = aead_request_flags(req);
-
-	err = crypto_ccm_auth(req, req->src, cryptlen);
+	err = crypto_ccm_auth(req, sg_next(pctx->src), cryptlen);
 	if (err)
 		return err;
 
-	 /* Note: rfc 3610 and NIST 800-38C require counter of
-	 * zero to encrypt auth tag.
-	 */
-	memset(iv + 15 - iv[0], 0, iv[0] + 1);
-
-	sg_init_table(pctx->src, 2);
-	sg_set_buf(pctx->src, odata, 16);
-	scatterwalk_sg_chain(pctx->src, 2, req->src);
-
 	dst = pctx->src;
-	if (req->src != req->dst) {
-		sg_init_table(pctx->dst, 2);
-		sg_set_buf(pctx->dst, odata, 16);
-		scatterwalk_sg_chain(pctx->dst, 2, req->dst);
+	if (req->src != req->dst)
 		dst = pctx->dst;
-	}
 
 	ablkcipher_request_set_tfm(abreq, ctx->ctr);
 	ablkcipher_request_set_callback(abreq, pctx->flags,
@@ -348,7 +375,7 @@ static int crypto_ccm_encrypt(struct aead_request *req)
 		return err;
 
 	/* copy authtag to end of dst */
-	scatterwalk_map_and_copy(odata, req->dst, cryptlen,
+	scatterwalk_map_and_copy(odata, sg_next(dst), cryptlen,
 				 crypto_aead_authsize(aead), 1);
 	return err;
 }
@@ -361,9 +388,14 @@ static void crypto_ccm_decrypt_done(struct crypto_async_request *areq,
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int cryptlen = req->cryptlen - authsize;
+	struct scatterlist *dst;
+
+	pctx->flags = 0;
+
+	dst = sg_next(req->src == req->dst ? pctx->src : pctx->dst);
 
 	if (!err) {
-		err = crypto_ccm_auth(req, req->dst, cryptlen);
+		err = crypto_ccm_auth(req, dst, cryptlen);
 		if (!err && crypto_memneq(pctx->auth_tag, pctx->odata, authsize))
 			err = -EBADMSG;
 	}
@@ -384,31 +416,18 @@ static int crypto_ccm_decrypt(struct aead_request *req)
 	u8 *iv = req->iv;
 	int err;
 
-	if (cryptlen < authsize)
-		return -EINVAL;
 	cryptlen -= authsize;
 
-	err = crypto_ccm_check_iv(iv);
+	err = crypto_ccm_init_crypt(req, authtag);
 	if (err)
 		return err;
 
-	pctx->flags = aead_request_flags(req);
-
-	scatterwalk_map_and_copy(authtag, req->src, cryptlen, authsize, 0);
-
-	memset(iv + 15 - iv[0], 0, iv[0] + 1);
-
-	sg_init_table(pctx->src, 2);
-	sg_set_buf(pctx->src, authtag, 16);
-	scatterwalk_sg_chain(pctx->src, 2, req->src);
+	scatterwalk_map_and_copy(authtag, sg_next(pctx->src), cryptlen,
+				 authsize, 0);
 
 	dst = pctx->src;
-	if (req->src != req->dst) {
-		sg_init_table(pctx->dst, 2);
-		sg_set_buf(pctx->dst, authtag, 16);
-		scatterwalk_sg_chain(pctx->dst, 2, req->dst);
+	if (req->src != req->dst)
 		dst = pctx->dst;
-	}
 
 	ablkcipher_request_set_tfm(abreq, ctx->ctr);
 	ablkcipher_request_set_callback(abreq, pctx->flags,
@@ -418,7 +437,7 @@ static int crypto_ccm_decrypt(struct aead_request *req)
 	if (err)
 		return err;
 
-	err = crypto_ccm_auth(req, req->dst, cryptlen);
+	err = crypto_ccm_auth(req, sg_next(dst), cryptlen);
 	if (err)
 		return err;
 
@@ -429,11 +448,11 @@ static int crypto_ccm_decrypt(struct aead_request *req)
 	return err;
 }
 
-static int crypto_ccm_init_tfm(struct crypto_tfm *tfm)
+static int crypto_ccm_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct ccm_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_ccm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct ccm_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_cipher *cipher;
 	struct crypto_ablkcipher *ctr;
 	unsigned long align;
@@ -451,9 +470,10 @@ static int crypto_ccm_init_tfm(struct crypto_tfm *tfm)
 	ctx->cipher = cipher;
 	ctx->ctr = ctr;
 
-	align = crypto_tfm_alg_alignmask(tfm);
+	align = crypto_aead_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+	crypto_aead_set_reqsize(
+		tfm,
 		align + sizeof(struct crypto_ccm_req_priv_ctx) +
 		crypto_ablkcipher_reqsize(ctr));
 
@@ -464,21 +484,31 @@ err_free_cipher:
 	return err;
 }
 
-static void crypto_ccm_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_ccm_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_ccm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_cipher(ctx->cipher);
 	crypto_free_ablkcipher(ctx->ctr);
 }
 
-static struct crypto_instance *crypto_ccm_alloc_common(struct rtattr **tb,
-						       const char *full_name,
-						       const char *ctr_name,
-						       const char *cipher_name)
+static void crypto_ccm_free(struct aead_instance *inst)
+{
+	struct ccm_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_spawn(&ctx->cipher);
+	crypto_drop_skcipher(&ctx->ctr);
+	kfree(inst);
+}
+
+static int crypto_ccm_create_common(struct crypto_template *tmpl,
+				    struct rtattr **tb,
+				    const char *full_name,
+				    const char *ctr_name,
+				    const char *cipher_name)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_alg *ctr;
 	struct crypto_alg *cipher;
 	struct ccm_instance_ctx *ictx;
@@ -486,15 +516,15 @@ static struct crypto_instance *crypto_ccm_alloc_common(struct rtattr **tb,
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	cipher = crypto_alg_mod_lookup(cipher_name,  CRYPTO_ALG_TYPE_CIPHER,
 				       CRYPTO_ALG_TYPE_MASK);
 	if (IS_ERR(cipher))
-		return ERR_CAST(cipher);
+		return PTR_ERR(cipher);
 
 	err = -EINVAL;
 	if (cipher->cra_blocksize != 16)
@@ -505,14 +535,15 @@ static struct crypto_instance *crypto_ccm_alloc_common(struct rtattr **tb,
 	if (!inst)
 		goto out_put_cipher;
 
-	ictx = crypto_instance_ctx(inst);
+	ictx = aead_instance_ctx(inst);
 
-	err = crypto_init_spawn(&ictx->cipher, cipher, inst,
+	err = crypto_init_spawn(&ictx->cipher, cipher,
+				aead_crypto_instance(inst),
 				CRYPTO_ALG_TYPE_MASK);
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ictx->ctr, inst);
+	crypto_set_skcipher_spawn(&ictx->ctr, aead_crypto_instance(inst));
 	err = crypto_grab_skcipher(&ictx->ctr, ctr_name, 0,
 				   crypto_requires_sync(algt->type,
 							algt->mask));
@@ -531,33 +562,39 @@ static struct crypto_instance *crypto_ccm_alloc_common(struct rtattr **tb,
 		goto err_drop_ctr;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "ccm_base(%s,%s)", ctr->cra_driver_name,
 		     cipher->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_ctr;
 
-	memcpy(inst->alg.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= ctr->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = cipher->cra_priority + ctr->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = cipher->cra_alignmask | ctr->cra_alignmask |
-				  (__alignof__(u32) - 1);
-	inst->alg.cra_type = &crypto_aead_type;
-	inst->alg.cra_aead.ivsize = 16;
-	inst->alg.cra_aead.maxauthsize = 16;
-	inst->alg.cra_ctxsize = sizeof(struct crypto_ccm_ctx);
-	inst->alg.cra_init = crypto_ccm_init_tfm;
-	inst->alg.cra_exit = crypto_ccm_exit_tfm;
-	inst->alg.cra_aead.setkey = crypto_ccm_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_ccm_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_ccm_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_ccm_decrypt;
+	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
+
+	inst->alg.base.cra_flags = ctr->cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = (cipher->cra_priority +
+				       ctr->cra_priority) / 2;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = cipher->cra_alignmask |
+				       ctr->cra_alignmask |
+				       (__alignof__(u32) - 1);
+	inst->alg.ivsize = 16;
+	inst->alg.maxauthsize = 16;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_ccm_ctx);
+	inst->alg.init = crypto_ccm_init_tfm;
+	inst->alg.exit = crypto_ccm_exit_tfm;
+	inst->alg.setkey = crypto_ccm_setkey;
+	inst->alg.setauthsize = crypto_ccm_setauthsize;
+	inst->alg.encrypt = crypto_ccm_encrypt;
+	inst->alg.decrypt = crypto_ccm_decrypt;
+
+	inst->free = crypto_ccm_free;
+
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_ctr;
 
-out:
+out_put_cipher:
 	crypto_mod_put(cipher);
-	return inst;
+	return err;
 
 err_drop_ctr:
 	crypto_drop_skcipher(&ictx->ctr);
@@ -565,12 +602,10 @@ err_drop_cipher:
 	crypto_drop_spawn(&ictx->cipher);
 err_free_inst:
 	kfree(inst);
-out_put_cipher:
-	inst = ERR_PTR(err);
-	goto out;
+	goto out_put_cipher;
 }
 
-static struct crypto_instance *crypto_ccm_alloc(struct rtattr **tb)
+static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
@@ -578,36 +613,28 @@ static struct crypto_instance *crypto_ccm_alloc(struct rtattr **tb)
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
-		return ERR_CAST(cipher_name);
+		return PTR_ERR(cipher_name);
 
 	if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)",
 		     cipher_name) >= CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
 	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm(%s)", cipher_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
-	return crypto_ccm_alloc_common(tb, full_name, ctr_name, cipher_name);
-}
-
-static void crypto_ccm_free(struct crypto_instance *inst)
-{
-	struct ccm_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_spawn(&ctx->cipher);
-	crypto_drop_skcipher(&ctx->ctr);
-	kfree(inst);
+	return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
+					cipher_name);
 }
 
 static struct crypto_template crypto_ccm_tmpl = {
 	.name = "ccm",
-	.alloc = crypto_ccm_alloc,
-	.free = crypto_ccm_free,
+	.create = crypto_ccm_create,
 	.module = THIS_MODULE,
 };
 
-static struct crypto_instance *crypto_ccm_base_alloc(struct rtattr **tb)
+static int crypto_ccm_base_create(struct crypto_template *tmpl,
+				  struct rtattr **tb)
 {
 	const char *ctr_name;
 	const char *cipher_name;
@@ -615,23 +642,23 @@ static struct crypto_instance *crypto_ccm_base_alloc(struct rtattr **tb)
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
-		return ERR_CAST(ctr_name);
+		return PTR_ERR(ctr_name);
 
 	cipher_name = crypto_attr_alg_name(tb[2]);
 	if (IS_ERR(cipher_name))
-		return ERR_CAST(cipher_name);
+		return PTR_ERR(cipher_name);
 
 	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)",
 		     ctr_name, cipher_name) >= CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
-	return crypto_ccm_alloc_common(tb, full_name, ctr_name, cipher_name);
+	return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
+					cipher_name);
 }
 
 static struct crypto_template crypto_ccm_base_tmpl = {
 	.name = "ccm_base",
-	.alloc = crypto_ccm_base_alloc,
-	.free = crypto_ccm_free,
+	.create = crypto_ccm_base_create,
 	.module = THIS_MODULE,
 };
 
@@ -677,10 +704,12 @@ static int crypto_rfc4309_setauthsize(struct crypto_aead *parent,
 
 static struct aead_request *crypto_rfc4309_crypt(struct aead_request *req)
 {
-	struct aead_request *subreq = aead_request_ctx(req);
+	struct crypto_rfc4309_req_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_aead *child = ctx->child;
+	struct scatterlist *sg;
 	u8 *iv = PTR_ALIGN((u8 *)(subreq + 1) + crypto_aead_reqsize(child),
 			   crypto_aead_alignmask(child) + 1);
 
@@ -690,17 +719,38 @@ static struct aead_request *crypto_rfc4309_crypt(struct aead_request *req)
 	memcpy(iv + 1, ctx->nonce, 3);
 	memcpy(iv + 4, req->iv, 8);
 
+	scatterwalk_map_and_copy(iv + 16, req->src, 0, req->assoclen - 8, 0);
+
+	sg_init_table(rctx->src, 3);
+	sg_set_buf(rctx->src, iv + 16, req->assoclen - 8);
+	sg = scatterwalk_ffwd(rctx->src + 1, req->src, req->assoclen);
+	if (sg != rctx->src + 1)
+		sg_chain(rctx->src, 2, sg);
+
+	if (req->src != req->dst) {
+		sg_init_table(rctx->dst, 3);
+		sg_set_buf(rctx->dst, iv + 16, req->assoclen - 8);
+		sg = scatterwalk_ffwd(rctx->dst + 1, req->dst, req->assoclen);
+		if (sg != rctx->dst + 1)
+			sg_chain(rctx->dst, 2, sg);
+	}
+
 	aead_request_set_tfm(subreq, child);
 	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
 				  req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, iv);
-	aead_request_set_assoc(subreq, req->assoc, req->assoclen);
+	aead_request_set_crypt(subreq, rctx->src,
+			       req->src == req->dst ? rctx->src : rctx->dst,
+			       req->cryptlen, iv);
+	aead_request_set_ad(subreq, req->assoclen - 8);
 
 	return subreq;
 }
 
 static int crypto_rfc4309_encrypt(struct aead_request *req)
 {
+	if (req->assoclen != 16 && req->assoclen != 20)
+		return -EINVAL;
+
 	req = crypto_rfc4309_crypt(req);
 
 	return crypto_aead_encrypt(req);
@@ -708,16 +758,19 @@ static int crypto_rfc4309_encrypt(struct aead_request *req)
 
 static int crypto_rfc4309_decrypt(struct aead_request *req)
 {
+	if (req->assoclen != 16 && req->assoclen != 20)
+		return -EINVAL;
+
 	req = crypto_rfc4309_crypt(req);
 
 	return crypto_aead_decrypt(req);
 }
 
-static int crypto_rfc4309_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc4309_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_aead_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_rfc4309_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct crypto_aead_spawn *spawn = aead_instance_ctx(inst);
+	struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
 	unsigned long align;
 
@@ -729,115 +782,118 @@ static int crypto_rfc4309_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
-		sizeof(struct aead_request) +
+	crypto_aead_set_reqsize(
+		tfm,
+		sizeof(struct crypto_rfc4309_req_ctx) +
 		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
-		align + 16);
+		align + 32);
 
 	return 0;
 }
 
-static void crypto_rfc4309_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc4309_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_rfc4309_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
 }
 
-static struct crypto_instance *crypto_rfc4309_alloc(struct rtattr **tb)
+static void crypto_rfc4309_free(struct aead_instance *inst)
+{
+	crypto_drop_aead(aead_instance_ctx(inst));
+	kfree(inst);
+}
+
+static int crypto_rfc4309_create(struct crypto_template *tmpl,
+				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_aead_spawn *spawn;
-	struct crypto_alg *alg;
+	struct aead_alg *alg;
 	const char *ccm_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ccm_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ccm_name))
-		return ERR_CAST(ccm_name);
+		return PTR_ERR(ccm_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	spawn = crypto_instance_ctx(inst);
-	crypto_set_aead_spawn(spawn, inst);
+	spawn = aead_instance_ctx(inst);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
 	err = crypto_grab_aead(spawn, ccm_name, 0,
 			       crypto_requires_sync(algt->type, algt->mask));
 	if (err)
 		goto out_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
+	alg = crypto_spawn_aead_alg(spawn);
 
 	err = -EINVAL;
 
 	/* We only support 16-byte blocks. */
-	if (alg->cra_aead.ivsize != 16)
+	if (crypto_aead_alg_ivsize(alg) != 16)
 		goto out_drop_alg;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
+	if (alg->base.cra_blocksize != 1)
 		goto out_drop_alg;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4309(%s)", alg->cra_name) >= CRYPTO_MAX_ALG_NAME ||
-	    snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4309(%s)", alg->cra_driver_name) >=
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4309(%s)", alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4309(%s)", alg->base.cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_drop_alg;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_aead.ivsize = 8;
-	inst->alg.cra_aead.maxauthsize = 16;
+	inst->alg.ivsize = 8;
+	inst->alg.maxauthsize = 16;
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx);
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx);
 
-	inst->alg.cra_init = crypto_rfc4309_init_tfm;
-	inst->alg.cra_exit = crypto_rfc4309_exit_tfm;
+	inst->alg.init = crypto_rfc4309_init_tfm;
+	inst->alg.exit = crypto_rfc4309_exit_tfm;
 
-	inst->alg.cra_aead.setkey = crypto_rfc4309_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_rfc4309_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_rfc4309_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_rfc4309_decrypt;
+	inst->alg.setkey = crypto_rfc4309_setkey;
+	inst->alg.setauthsize = crypto_rfc4309_setauthsize;
+	inst->alg.encrypt = crypto_rfc4309_encrypt;
+	inst->alg.decrypt = crypto_rfc4309_decrypt;
 
-	inst->alg.cra_aead.geniv = "seqiv";
+	inst->free = crypto_rfc4309_free;
+
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_alg;
 
 out:
-	return inst;
+	return err;
 
 out_drop_alg:
 	crypto_drop_aead(spawn);
 out_free_inst:
 	kfree(inst);
-	inst = ERR_PTR(err);
 	goto out;
 }
 
-static void crypto_rfc4309_free(struct crypto_instance *inst)
-{
-	crypto_drop_spawn(crypto_instance_ctx(inst));
-	kfree(inst);
-}
-
 static struct crypto_template crypto_rfc4309_tmpl = {
 	.name = "rfc4309",
-	.alloc = crypto_rfc4309_alloc,
-	.free = crypto_rfc4309_free,
+	.create = crypto_rfc4309_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index fa42e708aa96..da9c89968223 100644
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -13,14 +13,7 @@
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-
-#define CHACHA20_NONCE_SIZE 16
-#define CHACHA20_KEY_SIZE   32
-#define CHACHA20_BLOCK_SIZE 64
-
-struct chacha20_ctx {
-	u32 key[8];
-};
+#include <crypto/chacha20.h>
 
 static inline u32 rotl32(u32 v, u8 n)
 {
@@ -108,7 +101,7 @@ static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
-static void chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
+void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
 {
 	static const char constant[16] = "expand 32-byte k";
 
@@ -129,8 +122,9 @@ static void chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
 	state[14] = le32_to_cpuvp(iv +  8);
 	state[15] = le32_to_cpuvp(iv + 12);
 }
+EXPORT_SYMBOL_GPL(crypto_chacha20_init);
 
-static int chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
+int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
 			   unsigned int keysize)
 {
 	struct chacha20_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -144,8 +138,9 @@ static int chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(crypto_chacha20_setkey);
 
-static int chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+int crypto_chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 			  struct scatterlist *src, unsigned int nbytes)
 {
 	struct blkcipher_walk walk;
@@ -155,7 +150,7 @@ static int chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
 
-	chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
 
 	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
 		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
@@ -172,6 +167,7 @@ static int chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(crypto_chacha20_crypt);
 
 static struct crypto_alg alg = {
 	.cra_name		= "chacha20",
@@ -187,11 +183,11 @@ static struct crypto_alg alg = {
 		.blkcipher = {
 			.min_keysize	= CHACHA20_KEY_SIZE,
 			.max_keysize	= CHACHA20_KEY_SIZE,
-			.ivsize		= CHACHA20_NONCE_SIZE,
+			.ivsize		= CHACHA20_IV_SIZE,
 			.geniv		= "seqiv",
-			.setkey		= chacha20_setkey,
-			.encrypt	= chacha20_crypt,
-			.decrypt	= chacha20_crypt,
+			.setkey		= crypto_chacha20_setkey,
+			.encrypt	= crypto_chacha20_crypt,
+			.decrypt	= crypto_chacha20_crypt,
 		},
 	},
 };
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 7b46ed799a64..99c3cce01290 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -13,6 +13,8 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/chacha20.h>
+#include <crypto/poly1305.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -20,11 +22,6 @@
 
 #include "internal.h"
 
-#define POLY1305_BLOCK_SIZE	16
-#define POLY1305_DIGEST_SIZE	16
-#define POLY1305_KEY_SIZE	32
-#define CHACHA20_KEY_SIZE	32
-#define CHACHA20_IV_SIZE	16
 #define CHACHAPOLY_IV_SIZE	12
 
 struct chachapoly_instance_ctx {
@@ -60,12 +57,16 @@ struct chacha_req {
 };
 
 struct chachapoly_req_ctx {
+	struct scatterlist src[2];
+	struct scatterlist dst[2];
 	/* the key we generate for Poly1305 using Chacha20 */
 	u8 key[POLY1305_KEY_SIZE];
 	/* calculated Poly1305 tag */
 	u8 tag[POLY1305_DIGEST_SIZE];
 	/* length of data to en/decrypt, without ICV */
 	unsigned int cryptlen;
+	/* Actual AD, excluding IV */
+	unsigned int assoclen;
 	union {
 		struct poly_req poly;
 		struct chacha_req chacha;
@@ -98,7 +99,9 @@ static int poly_verify_tag(struct aead_request *req)
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 	u8 tag[sizeof(rctx->tag)];
 
-	scatterwalk_map_and_copy(tag, req->src, rctx->cryptlen, sizeof(tag), 0);
+	scatterwalk_map_and_copy(tag, req->src,
+				 req->assoclen + rctx->cryptlen,
+				 sizeof(tag), 0);
 	if (crypto_memneq(tag, rctx->tag, sizeof(tag)))
 		return -EBADMSG;
 	return 0;
@@ -108,7 +111,8 @@ static int poly_copy_tag(struct aead_request *req)
 {
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 
-	scatterwalk_map_and_copy(rctx->tag, req->dst, rctx->cryptlen,
+	scatterwalk_map_and_copy(rctx->tag, req->dst,
+				 req->assoclen + rctx->cryptlen,
 				 sizeof(rctx->tag), 1);
 	return 0;
 }
@@ -123,14 +127,24 @@ static int chacha_decrypt(struct aead_request *req)
 	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 	struct chacha_req *creq = &rctx->u.chacha;
+	struct scatterlist *src, *dst;
 	int err;
 
 	chacha_iv(creq->iv, req, 1);
 
+	sg_init_table(rctx->src, 2);
+	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen);
+	dst = src;
+
+	if (req->src != req->dst) {
+		sg_init_table(rctx->dst, 2);
+		dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);
+	}
+
 	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
 					chacha_decrypt_done, req);
 	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, req->src, req->dst,
+	ablkcipher_request_set_crypt(&creq->req, src, dst,
 				     rctx->cryptlen, creq->iv);
 	err = crypto_ablkcipher_decrypt(&creq->req);
 	if (err)
@@ -156,14 +170,15 @@ static void poly_tail_done(struct crypto_async_request *areq, int err)
 
 static int poly_tail(struct aead_request *req)
 {
-	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 	struct poly_req *preq = &rctx->u.poly;
 	__le64 len;
 	int err;
 
 	sg_init_table(preq->src, 1);
-	len = cpu_to_le64(req->assoclen);
+	len = cpu_to_le64(rctx->assoclen);
 	memcpy(&preq->tail.assoclen, &len, sizeof(len));
 	len = cpu_to_le64(rctx->cryptlen);
 	memcpy(&preq->tail.cryptlen, &len, sizeof(len));
@@ -228,6 +243,9 @@ static int poly_cipher(struct aead_request *req)
 	if (rctx->cryptlen == req->cryptlen) /* encrypting */
 		crypt = req->dst;
 
+	sg_init_table(rctx->src, 2);
+	crypt = scatterwalk_ffwd(rctx->src, crypt, req->assoclen);
+
 	ahash_request_set_callback(&preq->req, aead_request_flags(req),
 				   poly_cipher_done, req);
 	ahash_request_set_tfm(&preq->req, ctx->poly);
@@ -253,7 +271,7 @@ static int poly_adpad(struct aead_request *req)
 	unsigned int padlen, bs = POLY1305_BLOCK_SIZE;
 	int err;
 
-	padlen = (bs - (req->assoclen % bs)) % bs;
+	padlen = (bs - (rctx->assoclen % bs)) % bs;
 	memset(preq->pad, 0, sizeof(preq->pad));
 	sg_init_table(preq->src, 1);
 	sg_set_buf(preq->src, preq->pad, padlen);
@@ -285,7 +303,7 @@ static int poly_ad(struct aead_request *req)
 	ahash_request_set_callback(&preq->req, aead_request_flags(req),
 				   poly_ad_done, req);
 	ahash_request_set_tfm(&preq->req, ctx->poly);
-	ahash_request_set_crypt(&preq->req, req->assoc, NULL, req->assoclen);
+	ahash_request_set_crypt(&preq->req, req->src, NULL, rctx->assoclen);
 
 	err = crypto_ahash_update(&preq->req);
 	if (err)
@@ -351,11 +369,20 @@ static void poly_genkey_done(struct crypto_async_request *areq, int err)
 
 static int poly_genkey(struct aead_request *req)
 {
-	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 	struct chacha_req *creq = &rctx->u.chacha;
 	int err;
 
+	rctx->assoclen = req->assoclen;
+
+	if (crypto_aead_ivsize(tfm) == 8) {
+		if (rctx->assoclen < 8)
+			return -EINVAL;
+		rctx->assoclen -= 8;
+	}
+
 	sg_init_table(creq->src, 1);
 	memset(rctx->key, 0, sizeof(rctx->key));
 	sg_set_buf(creq->src, rctx->key, sizeof(rctx->key));
@@ -385,14 +412,24 @@ static int chacha_encrypt(struct aead_request *req)
 	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 	struct chacha_req *creq = &rctx->u.chacha;
+	struct scatterlist *src, *dst;
 	int err;
 
 	chacha_iv(creq->iv, req, 1);
 
+	sg_init_table(rctx->src, 2);
+	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen);
+	dst = src;
+
+	if (req->src != req->dst) {
+		sg_init_table(rctx->dst, 2);
+		dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);
+	}
+
 	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
 					chacha_encrypt_done, req);
 	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, req->src, req->dst,
+	ablkcipher_request_set_crypt(&creq->req, src, dst,
 				     req->cryptlen, creq->iv);
 	err = crypto_ablkcipher_encrypt(&creq->req);
 	if (err)
@@ -426,8 +463,6 @@ static int chachapoly_decrypt(struct aead_request *req)
 {
 	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
 
-	if (req->cryptlen < POLY1305_DIGEST_SIZE)
-		return -EINVAL;
 	rctx->cryptlen = req->cryptlen - POLY1305_DIGEST_SIZE;
 
 	/* decrypt call chain:
@@ -476,11 +511,11 @@ static int chachapoly_setauthsize(struct crypto_aead *tfm,
 	return 0;
 }
 
-static int chachapoly_init(struct crypto_tfm *tfm)
+static int chachapoly_init(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct chachapoly_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct chachapoly_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct chachapoly_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ablkcipher *chacha;
 	struct crypto_ahash *poly;
 	unsigned long align;
@@ -499,77 +534,87 @@ static int chachapoly_init(struct crypto_tfm *tfm)
 	ctx->poly = poly;
 	ctx->saltlen = ictx->saltlen;
 
-	align = crypto_tfm_alg_alignmask(tfm);
+	align = crypto_aead_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
-				align + offsetof(struct chachapoly_req_ctx, u) +
-				max(offsetof(struct chacha_req, req) +
-				    sizeof(struct ablkcipher_request) +
-				    crypto_ablkcipher_reqsize(chacha),
-				    offsetof(struct poly_req, req) +
-				    sizeof(struct ahash_request) +
-				    crypto_ahash_reqsize(poly)));
+	crypto_aead_set_reqsize(
+		tfm,
+		align + offsetof(struct chachapoly_req_ctx, u) +
+		max(offsetof(struct chacha_req, req) +
+		    sizeof(struct ablkcipher_request) +
+		    crypto_ablkcipher_reqsize(chacha),
+		    offsetof(struct poly_req, req) +
+		    sizeof(struct ahash_request) +
+		    crypto_ahash_reqsize(poly)));
 
 	return 0;
 }
 
-static void chachapoly_exit(struct crypto_tfm *tfm)
+static void chachapoly_exit(struct crypto_aead *tfm)
 {
-	struct chachapoly_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->poly);
 	crypto_free_ablkcipher(ctx->chacha);
 }
 
-static struct crypto_instance *chachapoly_alloc(struct rtattr **tb,
-						const char *name,
-						unsigned int ivsize)
+static void chachapoly_free(struct aead_instance *inst)
+{
+	struct chachapoly_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_skcipher(&ctx->chacha);
+	crypto_drop_ahash(&ctx->poly);
+	kfree(inst);
+}
+
+static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
+			     const char *name, unsigned int ivsize)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_alg *chacha;
 	struct crypto_alg *poly;
-	struct ahash_alg *poly_ahash;
+	struct hash_alg_common *poly_hash;
 	struct chachapoly_instance_ctx *ctx;
 	const char *chacha_name, *poly_name;
 	int err;
 
 	if (ivsize > CHACHAPOLY_IV_SIZE)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	chacha_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(chacha_name))
-		return ERR_CAST(chacha_name);
+		return PTR_ERR(chacha_name);
 	poly_name = crypto_attr_alg_name(tb[2]);
 	if (IS_ERR(poly_name))
-		return ERR_CAST(poly_name);
+		return PTR_ERR(poly_name);
 
 	poly = crypto_find_alg(poly_name, &crypto_ahash_type,
 			       CRYPTO_ALG_TYPE_HASH,
 			       CRYPTO_ALG_TYPE_AHASH_MASK);
 	if (IS_ERR(poly))
-		return ERR_CAST(poly);
+		return PTR_ERR(poly);
 
 	err = -ENOMEM;
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
 		goto out_put_poly;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 	ctx->saltlen = CHACHAPOLY_IV_SIZE - ivsize;
-	poly_ahash = container_of(poly, struct ahash_alg, halg.base);
-	err = crypto_init_ahash_spawn(&ctx->poly, &poly_ahash->halg, inst);
+	poly_hash = __crypto_hash_alg_common(poly);
+	err = crypto_init_ahash_spawn(&ctx->poly, poly_hash,
+				      aead_crypto_instance(inst));
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->chacha, inst);
+	crypto_set_skcipher_spawn(&ctx->chacha, aead_crypto_instance(inst));
 	err = crypto_grab_skcipher(&ctx->chacha, chacha_name, 0,
 				   crypto_requires_sync(algt->type,
 							algt->mask));
@@ -587,37 +632,42 @@ static struct crypto_instance *chachapoly_alloc(struct rtattr **tb,
 		goto out_drop_chacha;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
 		     "%s(%s,%s)", name, chacha_name,
 		     poly_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "%s(%s,%s)", name, chacha->cra_driver_name,
 		     poly->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= (chacha->cra_flags |
-				poly->cra_flags) & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = (chacha->cra_priority +
-				  poly->cra_priority) / 2;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = chacha->cra_alignmask | poly->cra_alignmask;
-	inst->alg.cra_type = &crypto_nivaead_type;
-	inst->alg.cra_aead.ivsize = ivsize;
-	inst->alg.cra_aead.maxauthsize = POLY1305_DIGEST_SIZE;
-	inst->alg.cra_ctxsize = sizeof(struct chachapoly_ctx) + ctx->saltlen;
-	inst->alg.cra_init = chachapoly_init;
-	inst->alg.cra_exit = chachapoly_exit;
-	inst->alg.cra_aead.encrypt = chachapoly_encrypt;
-	inst->alg.cra_aead.decrypt = chachapoly_decrypt;
-	inst->alg.cra_aead.setkey = chachapoly_setkey;
-	inst->alg.cra_aead.setauthsize = chachapoly_setauthsize;
-	inst->alg.cra_aead.geniv = "seqiv";
-
-out:
+	inst->alg.base.cra_flags = (chacha->cra_flags | poly->cra_flags) &
+				   CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = (chacha->cra_priority +
+				       poly->cra_priority) / 2;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = chacha->cra_alignmask |
+				       poly->cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct chachapoly_ctx) +
+				     ctx->saltlen;
+	inst->alg.ivsize = ivsize;
+	inst->alg.maxauthsize = POLY1305_DIGEST_SIZE;
+	inst->alg.init = chachapoly_init;
+	inst->alg.exit = chachapoly_exit;
+	inst->alg.encrypt = chachapoly_encrypt;
+	inst->alg.decrypt = chachapoly_decrypt;
+	inst->alg.setkey = chachapoly_setkey;
+	inst->alg.setauthsize = chachapoly_setauthsize;
+
+	inst->free = chachapoly_free;
+
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_chacha;
+
+out_put_poly:
 	crypto_mod_put(poly);
-	return inst;
+	return err;
 
 out_drop_chacha:
 	crypto_drop_skcipher(&ctx->chacha);
@@ -625,41 +675,28 @@ err_drop_poly:
 	crypto_drop_ahash(&ctx->poly);
 err_free_inst:
 	kfree(inst);
-out_put_poly:
-	inst = ERR_PTR(err);
-	goto out;
-}
-
-static struct crypto_instance *rfc7539_alloc(struct rtattr **tb)
-{
-	return chachapoly_alloc(tb, "rfc7539", 12);
+	goto out_put_poly;
 }
 
-static struct crypto_instance *rfc7539esp_alloc(struct rtattr **tb)
+static int rfc7539_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
-	return chachapoly_alloc(tb, "rfc7539esp", 8);
+	return chachapoly_create(tmpl, tb, "rfc7539", 12);
 }
 
-static void chachapoly_free(struct crypto_instance *inst)
+static int rfc7539esp_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
-	struct chachapoly_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_skcipher(&ctx->chacha);
-	crypto_drop_ahash(&ctx->poly);
-	kfree(inst);
+	return chachapoly_create(tmpl, tb, "rfc7539esp", 8);
 }
 
 static struct crypto_template rfc7539_tmpl = {
 	.name = "rfc7539",
-	.alloc = rfc7539_alloc,
-	.free = chachapoly_free,
+	.create = rfc7539_create,
 	.module = THIS_MODULE,
 };
 
 static struct crypto_template rfc7539esp_tmpl = {
 	.name = "rfc7539esp",
-	.alloc = rfc7539esp_alloc,
-	.free = chachapoly_free,
+	.create = rfc7539esp_create,
 	.module = THIS_MODULE,
 };
 
@@ -690,6 +727,5 @@ module_exit(chacha20poly1305_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
 MODULE_DESCRIPTION("ChaCha20-Poly1305 AEAD");
-MODULE_ALIAS_CRYPTO("chacha20poly1305");
 MODULE_ALIAS_CRYPTO("rfc7539");
 MODULE_ALIAS_CRYPTO("rfc7539esp");
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 22ba81f76764..c81861b1350b 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -176,10 +176,9 @@ static inline void cryptd_check_internal(struct rtattr **tb, u32 *type,
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
 		return;
-	if ((algt->type & CRYPTO_ALG_INTERNAL))
-		*type |= CRYPTO_ALG_INTERNAL;
-	if ((algt->mask & CRYPTO_ALG_INTERNAL))
-		*mask |= CRYPTO_ALG_INTERNAL;
+
+	*type |= algt->type & CRYPTO_ALG_INTERNAL;
+	*mask |= algt->mask & CRYPTO_ALG_INTERNAL;
 }
 
 static int cryptd_blkcipher_setkey(struct crypto_ablkcipher *parent,
@@ -688,16 +687,18 @@ static void cryptd_aead_crypt(struct aead_request *req,
 			int (*crypt)(struct aead_request *req))
 {
 	struct cryptd_aead_request_ctx *rctx;
+	crypto_completion_t compl;
+
 	rctx = aead_request_ctx(req);
+	compl = rctx->complete;
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 	aead_request_set_tfm(req, child);
 	err = crypt( req );
-	req->base.complete = rctx->complete;
 out:
 	local_bh_disable();
-	rctx->complete(&req->base, err);
+	compl(&req->base, err);
 	local_bh_enable();
 }
 
@@ -708,7 +709,7 @@ static void cryptd_aead_encrypt(struct crypto_async_request *areq, int err)
 	struct aead_request *req;
 
 	req = container_of(areq, struct aead_request, base);
-	cryptd_aead_crypt(req, child, err, crypto_aead_crt(child)->encrypt);
+	cryptd_aead_crypt(req, child, err, crypto_aead_alg(child)->encrypt);
 }
 
 static void cryptd_aead_decrypt(struct crypto_async_request *areq, int err)
@@ -718,7 +719,7 @@ static void cryptd_aead_decrypt(struct crypto_async_request *areq, int err)
 	struct aead_request *req;
 
 	req = container_of(areq, struct aead_request, base);
-	cryptd_aead_crypt(req, child, err, crypto_aead_crt(child)->decrypt);
+	cryptd_aead_crypt(req, child, err, crypto_aead_alg(child)->decrypt);
 }
 
 static int cryptd_aead_enqueue(struct aead_request *req,
@@ -756,7 +757,9 @@ static int cryptd_aead_init_tfm(struct crypto_aead *tfm)
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
-	crypto_aead_set_reqsize(tfm, sizeof(struct cryptd_aead_request_ctx));
+	crypto_aead_set_reqsize(
+		tfm, max((unsigned)sizeof(struct cryptd_aead_request_ctx),
+			 crypto_aead_reqsize(cipher)));
 	return 0;
 }
 
@@ -775,7 +778,7 @@ static int cryptd_create_aead(struct crypto_template *tmpl,
 	struct aead_alg *alg;
 	const char *name;
 	u32 type = 0;
-	u32 mask = 0;
+	u32 mask = CRYPTO_ALG_ASYNC;
 	int err;
 
 	cryptd_check_internal(tb, &type, &mask);
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 08ea2867fc8a..d94d99ffe8b9 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -25,7 +25,6 @@
 #include <net/netlink.h>
 #include <linux/security.h>
 #include <net/net_namespace.h>
-#include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/rng.h>
 #include <crypto/akcipher.h>
@@ -385,34 +384,6 @@ static struct crypto_alg *crypto_user_skcipher_alg(const char *name, u32 type,
 	return ERR_PTR(err);
 }
 
-static struct crypto_alg *crypto_user_aead_alg(const char *name, u32 type,
-					       u32 mask)
-{
-	int err;
-	struct crypto_alg *alg;
-
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	for (;;) {
-		alg = crypto_lookup_aead(name,  type, mask);
-		if (!IS_ERR(alg))
-			return alg;
-
-		err = PTR_ERR(alg);
-		if (err != -EAGAIN)
-			break;
-		if (signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
-
-	return ERR_PTR(err);
-}
-
 static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct nlattr **attrs)
 {
@@ -446,9 +417,6 @@ static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		name = p->cru_name;
 
 	switch (p->cru_type & p->cru_mask & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_AEAD:
-		alg = crypto_user_aead_alg(name, p->cru_type, p->cru_mask);
-		break;
 	case CRYPTO_ALG_TYPE_GIVCIPHER:
 	case CRYPTO_ALG_TYPE_BLKCIPHER:
 	case CRYPTO_ALG_TYPE_ABLKCIPHER:
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
index b6e43dc61356..b96a84560b67 100644
--- a/crypto/echainiv.c
+++ b/crypto/echainiv.c
@@ -19,8 +19,6 @@
  */
 
 #include <crypto/internal/geniv.h>
-#include <crypto/null.h>
-#include <crypto/rng.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -33,13 +31,6 @@
 
 #define MAX_IV_SIZE 16
 
-struct echainiv_ctx {
-	/* aead_geniv_ctx must be first the element */
-	struct aead_geniv_ctx geniv;
-	struct crypto_blkcipher *null;
-	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
-};
-
 static DEFINE_PER_CPU(u32 [MAX_IV_SIZE / sizeof(u32)], echainiv_iv);
 
 /* We don't care if we get preempted and read/write IVs from the next CPU. */
@@ -103,7 +94,7 @@ static void echainiv_encrypt_complete(struct crypto_async_request *base,
 static int echainiv_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
 	struct aead_request *subreq = aead_request_ctx(req);
 	crypto_completion_t compl;
 	void *data;
@@ -114,7 +105,7 @@ static int echainiv_encrypt(struct aead_request *req)
 	if (req->cryptlen < ivsize)
 		return -EINVAL;
 
-	aead_request_set_tfm(subreq, ctx->geniv.child);
+	aead_request_set_tfm(subreq, ctx->child);
 
 	compl = echainiv_encrypt_complete;
 	data = req;
@@ -145,8 +136,8 @@ static int echainiv_encrypt(struct aead_request *req)
 
 	aead_request_set_callback(subreq, req->base.flags, compl, data);
 	aead_request_set_crypt(subreq, req->dst, req->dst,
-			       req->cryptlen - ivsize, info);
-	aead_request_set_ad(subreq, req->assoclen + ivsize);
+			       req->cryptlen, info);
+	aead_request_set_ad(subreq, req->assoclen);
 
 	crypto_xor(info, ctx->salt, ivsize);
 	scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
@@ -160,16 +151,16 @@ static int echainiv_encrypt(struct aead_request *req)
 static int echainiv_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
 	struct aead_request *subreq = aead_request_ctx(req);
 	crypto_completion_t compl;
 	void *data;
 	unsigned int ivsize = crypto_aead_ivsize(geniv);
 
-	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+	if (req->cryptlen < ivsize)
 		return -EINVAL;
 
-	aead_request_set_tfm(subreq, ctx->geniv.child);
+	aead_request_set_tfm(subreq, ctx->child);
 
 	compl = req->base.complete;
 	data = req->base.data;
@@ -180,61 +171,10 @@ static int echainiv_decrypt(struct aead_request *req)
 	aead_request_set_ad(subreq, req->assoclen + ivsize);
 
 	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
-	if (req->src != req->dst)
-		scatterwalk_map_and_copy(req->iv, req->dst,
-					 req->assoclen, ivsize, 1);
 
 	return crypto_aead_decrypt(subreq);
 }
 
-static int echainiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
-	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
-	int err;
-
-	spin_lock_init(&ctx->geniv.lock);
-
-	crypto_aead_set_reqsize(geniv, sizeof(struct aead_request));
-
-	err = crypto_get_default_rng();
-	if (err)
-		goto out;
-
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_aead_ivsize(geniv));
-	crypto_put_default_rng();
-	if (err)
-		goto out;
-
-	ctx->null = crypto_get_default_null_skcipher();
-	err = PTR_ERR(ctx->null);
-	if (IS_ERR(ctx->null))
-		goto out;
-
-	err = aead_geniv_init(tfm);
-	if (err)
-		goto drop_null;
-
-	ctx->geniv.child = geniv->child;
-	geniv->child = geniv;
-
-out:
-	return err;
-
-drop_null:
-	crypto_put_default_null_skcipher();
-	goto out;
-}
-
-static void echainiv_exit(struct crypto_tfm *tfm)
-{
-	struct echainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_aead(ctx->geniv.child);
-	crypto_put_default_null_skcipher();
-}
-
 static int echainiv_aead_create(struct crypto_template *tmpl,
 				struct rtattr **tb)
 {
@@ -251,9 +191,6 @@ static int echainiv_aead_create(struct crypto_template *tmpl,
 	spawn = aead_instance_ctx(inst);
 	alg = crypto_spawn_aead_alg(spawn);
 
-	if (alg->base.cra_aead.encrypt)
-		goto done;
-
 	err = -EINVAL;
 	if (inst->alg.ivsize & (sizeof(u32) - 1) ||
 	    inst->alg.ivsize > MAX_IV_SIZE)
@@ -262,14 +199,15 @@ static int echainiv_aead_create(struct crypto_template *tmpl,
 	inst->alg.encrypt = echainiv_encrypt;
 	inst->alg.decrypt = echainiv_decrypt;
 
-	inst->alg.base.cra_init = echainiv_init;
-	inst->alg.base.cra_exit = echainiv_exit;
+	inst->alg.init = aead_init_geniv;
+	inst->alg.exit = aead_exit_geniv;
 
 	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
-	inst->alg.base.cra_ctxsize = sizeof(struct echainiv_ctx);
+	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
 	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
 
-done:
+	inst->free = aead_geniv_free;
+
 	err = aead_register_instance(tmpl, inst);
 	if (err)
 		goto free_inst;
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 7d32d4720564..bec329b3de8d 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -38,6 +38,12 @@ struct crypto_rfc4106_ctx {
 	u8 nonce[4];
 };
 
+struct crypto_rfc4106_req_ctx {
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
+	struct aead_request subreq;
+};
+
 struct crypto_rfc4543_instance_ctx {
 	struct crypto_aead_spawn aead;
 };
@@ -200,14 +206,14 @@ static void crypto_gcm_init_common(struct aead_request *req)
 	sg_set_buf(pctx->src, pctx->auth_tag, sizeof(pctx->auth_tag));
 	sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen);
 	if (sg != pctx->src + 1)
-		scatterwalk_sg_chain(pctx->src, 2, sg);
+		sg_chain(pctx->src, 2, sg);
 
 	if (req->src != req->dst) {
 		sg_init_table(pctx->dst, 3);
 		sg_set_buf(pctx->dst, pctx->auth_tag, sizeof(pctx->auth_tag));
 		sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen);
 		if (sg != pctx->dst + 1)
-			scatterwalk_sg_chain(pctx->dst, 2, sg);
+			sg_chain(pctx->dst, 2, sg);
 	}
 }
 
@@ -601,6 +607,15 @@ static void crypto_gcm_exit_tfm(struct crypto_aead *tfm)
 	crypto_free_ablkcipher(ctx->ctr);
 }
 
+static void crypto_gcm_free(struct aead_instance *inst)
+{
+	struct gcm_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_skcipher(&ctx->ctr);
+	crypto_drop_ahash(&ctx->ghash);
+	kfree(inst);
+}
+
 static int crypto_gcm_create_common(struct crypto_template *tmpl,
 				    struct rtattr **tb,
 				    const char *full_name,
@@ -689,6 +704,8 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 	inst->alg.encrypt = crypto_gcm_encrypt;
 	inst->alg.decrypt = crypto_gcm_decrypt;
 
+	inst->free = crypto_gcm_free;
+
 	err = aead_register_instance(tmpl, inst);
 	if (err)
 		goto out_put_ctr;
@@ -728,19 +745,9 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 					ctr_name, "ghash");
 }
 
-static void crypto_gcm_free(struct crypto_instance *inst)
-{
-	struct gcm_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_skcipher(&ctx->ctr);
-	crypto_drop_ahash(&ctx->ghash);
-	kfree(aead_instance(inst));
-}
-
 static struct crypto_template crypto_gcm_tmpl = {
 	.name = "gcm",
 	.create = crypto_gcm_create,
-	.free = crypto_gcm_free,
 	.module = THIS_MODULE,
 };
 
@@ -770,7 +777,6 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
 static struct crypto_template crypto_gcm_base_tmpl = {
 	.name = "gcm_base",
 	.create = crypto_gcm_base_create,
-	.free = crypto_gcm_free,
 	.module = THIS_MODULE,
 };
 
@@ -816,27 +822,50 @@ static int crypto_rfc4106_setauthsize(struct crypto_aead *parent,
 
 static struct aead_request *crypto_rfc4106_crypt(struct aead_request *req)
 {
-	struct aead_request *subreq = aead_request_ctx(req);
+	struct crypto_rfc4106_req_ctx *rctx = aead_request_ctx(req);
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_rfc4106_ctx *ctx = crypto_aead_ctx(aead);
+	struct aead_request *subreq = &rctx->subreq;
 	struct crypto_aead *child = ctx->child;
+	struct scatterlist *sg;
 	u8 *iv = PTR_ALIGN((u8 *)(subreq + 1) + crypto_aead_reqsize(child),
 			   crypto_aead_alignmask(child) + 1);
 
+	scatterwalk_map_and_copy(iv + 12, req->src, 0, req->assoclen - 8, 0);
+
 	memcpy(iv, ctx->nonce, 4);
 	memcpy(iv + 4, req->iv, 8);
 
+	sg_init_table(rctx->src, 3);
+	sg_set_buf(rctx->src, iv + 12, req->assoclen - 8);
+	sg = scatterwalk_ffwd(rctx->src + 1, req->src, req->assoclen);
+	if (sg != rctx->src + 1)
+		sg_chain(rctx->src, 2, sg);
+
+	if (req->src != req->dst) {
+		sg_init_table(rctx->dst, 3);
+		sg_set_buf(rctx->dst, iv + 12, req->assoclen - 8);
+		sg = scatterwalk_ffwd(rctx->dst + 1, req->dst, req->assoclen);
+		if (sg != rctx->dst + 1)
+			sg_chain(rctx->dst, 2, sg);
+	}
+
 	aead_request_set_tfm(subreq, child);
 	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
 				  req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, iv);
-	aead_request_set_ad(subreq, req->assoclen);
+	aead_request_set_crypt(subreq, rctx->src,
+			       req->src == req->dst ? rctx->src : rctx->dst,
+			       req->cryptlen, iv);
+	aead_request_set_ad(subreq, req->assoclen - 8);
 
 	return subreq;
 }
 
 static int crypto_rfc4106_encrypt(struct aead_request *req)
 {
+	if (req->assoclen != 16 && req->assoclen != 20)
+		return -EINVAL;
+
 	req = crypto_rfc4106_crypt(req);
 
 	return crypto_aead_encrypt(req);
@@ -844,6 +873,9 @@ static int crypto_rfc4106_encrypt(struct aead_request *req)
 
 static int crypto_rfc4106_decrypt(struct aead_request *req)
 {
+	if (req->assoclen != 16 && req->assoclen != 20)
+		return -EINVAL;
+
 	req = crypto_rfc4106_crypt(req);
 
 	return crypto_aead_decrypt(req);
@@ -867,9 +899,9 @@ static int crypto_rfc4106_init_tfm(struct crypto_aead *tfm)
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
 	crypto_aead_set_reqsize(
 		tfm,
-		sizeof(struct aead_request) +
+		sizeof(struct crypto_rfc4106_req_ctx) +
 		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
-		align + 12);
+		align + 24);
 
 	return 0;
 }
@@ -881,6 +913,12 @@ static void crypto_rfc4106_exit_tfm(struct crypto_aead *tfm)
 	crypto_free_aead(ctx->child);
 }
 
+static void crypto_rfc4106_free(struct aead_instance *inst)
+{
+	crypto_drop_aead(aead_instance_ctx(inst));
+	kfree(inst);
+}
+
 static int crypto_rfc4106_create(struct crypto_template *tmpl,
 				 struct rtattr **tb)
 {
@@ -934,7 +972,7 @@ static int crypto_rfc4106_create(struct crypto_template *tmpl,
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_drop_alg;
 
-	inst->alg.base.cra_flags |= alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = alg->base.cra_priority;
 	inst->alg.base.cra_blocksize = 1;
 	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
@@ -952,6 +990,8 @@ static int crypto_rfc4106_create(struct crypto_template *tmpl,
 	inst->alg.encrypt = crypto_rfc4106_encrypt;
 	inst->alg.decrypt = crypto_rfc4106_decrypt;
 
+	inst->free = crypto_rfc4106_free;
+
 	err = aead_register_instance(tmpl, inst);
 	if (err)
 		goto out_drop_alg;
@@ -966,16 +1006,9 @@ out_free_inst:
 	goto out;
 }
 
-static void crypto_rfc4106_free(struct crypto_instance *inst)
-{
-	crypto_drop_aead(crypto_instance_ctx(inst));
-	kfree(aead_instance(inst));
-}
-
 static struct crypto_template crypto_rfc4106_tmpl = {
 	.name = "rfc4106",
 	.create = crypto_rfc4106_create,
-	.free = crypto_rfc4106_free,
 	.module = THIS_MODULE,
 };
 
@@ -1114,6 +1147,15 @@ static void crypto_rfc4543_exit_tfm(struct crypto_aead *tfm)
 	crypto_put_default_null_skcipher();
 }
 
+static void crypto_rfc4543_free(struct aead_instance *inst)
+{
+	struct crypto_rfc4543_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_aead(&ctx->aead);
+
+	kfree(inst);
+}
+
 static int crypto_rfc4543_create(struct crypto_template *tmpl,
 				struct rtattr **tb)
 {
@@ -1187,6 +1229,8 @@ static int crypto_rfc4543_create(struct crypto_template *tmpl,
 	inst->alg.encrypt = crypto_rfc4543_encrypt;
 	inst->alg.decrypt = crypto_rfc4543_decrypt;
 
+	inst->free = crypto_rfc4543_free,
+
 	err = aead_register_instance(tmpl, inst);
 	if (err)
 		goto out_drop_alg;
@@ -1201,19 +1245,9 @@ out_free_inst:
 	goto out;
 }
 
-static void crypto_rfc4543_free(struct crypto_instance *inst)
-{
-	struct crypto_rfc4543_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_aead(&ctx->aead);
-
-	kfree(aead_instance(inst));
-}
-
 static struct crypto_template crypto_rfc4543_tmpl = {
 	.name = "rfc4543",
 	.create = crypto_rfc4543_create,
-	.free = crypto_rfc4543_free,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index b32d834144cd..ceea83d13168 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -79,7 +79,7 @@ int jent_fips_enabled(void)
 
 void jent_panic(char *s)
 {
-	panic(s);
+	panic("%s", s);
 }
 
 void jent_memcpy(void *dest, const void *src, unsigned int n)
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index 45e7d5155672..ee9cfb99fe25 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -274,11 +274,16 @@ static int pcrypt_create_aead(struct crypto_template *tmpl, struct rtattr **tb,
 			      u32 type, u32 mask)
 {
 	struct pcrypt_instance_ctx *ctx;
+	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
 	struct aead_alg *alg;
 	const char *name;
 	int err;
 
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return PTR_ERR(algt);
+
 	name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
@@ -299,6 +304,8 @@ static int pcrypt_create_aead(struct crypto_template *tmpl, struct rtattr **tb,
 	if (err)
 		goto out_drop_aead;
 
+	inst->alg.base.cra_flags = CRYPTO_ALG_ASYNC;
+
 	inst->alg.ivsize = crypto_aead_alg_ivsize(alg);
 	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index 387b5c887a80..2df9835dfbc0 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -13,31 +13,11 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/poly1305.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-#define POLY1305_BLOCK_SIZE	16
-#define POLY1305_KEY_SIZE	32
-#define POLY1305_DIGEST_SIZE	16
-
-struct poly1305_desc_ctx {
-	/* key */
-	u32 r[5];
-	/* finalize key */
-	u32 s[4];
-	/* accumulator */
-	u32 h[5];
-	/* partial buffer */
-	u8 buf[POLY1305_BLOCK_SIZE];
-	/* bytes used in partial buffer */
-	unsigned int buflen;
-	/* r key has been set */
-	bool rset;
-	/* s key has been set */
-	bool sset;
-};
-
 static inline u64 mlt(u64 a, u64 b)
 {
 	return a * b;
@@ -58,7 +38,7 @@ static inline u32 le32_to_cpuvp(const void *p)
 	return le32_to_cpup(p);
 }
 
-static int poly1305_init(struct shash_desc *desc)
+int crypto_poly1305_init(struct shash_desc *desc)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
 
@@ -69,8 +49,9 @@ static int poly1305_init(struct shash_desc *desc)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(crypto_poly1305_init);
 
-static int poly1305_setkey(struct crypto_shash *tfm,
+int crypto_poly1305_setkey(struct crypto_shash *tfm,
 			   const u8 *key, unsigned int keylen)
 {
 	/* Poly1305 requires a unique key for each tag, which implies that
@@ -79,6 +60,7 @@ static int poly1305_setkey(struct crypto_shash *tfm,
 	 * the update() call. */
 	return -ENOTSUPP;
 }
+EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
 
 static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
@@ -98,16 +80,10 @@ static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
 	dctx->s[3] = le32_to_cpuvp(key + 12);
 }
 
-static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
-				    const u8 *src, unsigned int srclen,
-				    u32 hibit)
+unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
+					const u8 *src, unsigned int srclen)
 {
-	u32 r0, r1, r2, r3, r4;
-	u32 s1, s2, s3, s4;
-	u32 h0, h1, h2, h3, h4;
-	u64 d0, d1, d2, d3, d4;
-
-	if (unlikely(!dctx->sset)) {
+	if (!dctx->sset) {
 		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
 			poly1305_setrkey(dctx, src);
 			src += POLY1305_BLOCK_SIZE;
@@ -121,6 +97,25 @@ static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
 			dctx->sset = true;
 		}
 	}
+	return srclen;
+}
+EXPORT_SYMBOL_GPL(crypto_poly1305_setdesckey);
+
+static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, unsigned int srclen,
+				    u32 hibit)
+{
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+	unsigned int datalen;
+
+	if (unlikely(!dctx->sset)) {
+		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+		src += srclen - datalen;
+		srclen = datalen;
+	}
 
 	r0 = dctx->r[0];
 	r1 = dctx->r[1];
@@ -181,7 +176,7 @@ static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
 	return srclen;
 }
 
-static int poly1305_update(struct shash_desc *desc,
+int crypto_poly1305_update(struct shash_desc *desc,
 			   const u8 *src, unsigned int srclen)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -214,8 +209,9 @@ static int poly1305_update(struct shash_desc *desc,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(crypto_poly1305_update);
 
-static int poly1305_final(struct shash_desc *desc, u8 *dst)
+int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
 	__le32 *mac = (__le32 *)dst;
@@ -282,13 +278,14 @@ static int poly1305_final(struct shash_desc *desc, u8 *dst)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(crypto_poly1305_final);
 
 static struct shash_alg poly1305_alg = {
 	.digestsize	= POLY1305_DIGEST_SIZE,
-	.init		= poly1305_init,
-	.update		= poly1305_update,
-	.final		= poly1305_final,
-	.setkey		= poly1305_setkey,
+	.init		= crypto_poly1305_init,
+	.update		= crypto_poly1305_update,
+	.final		= crypto_poly1305_final,
+	.setkey		= crypto_poly1305_setkey,
 	.descsize	= sizeof(struct poly1305_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
diff --git a/crypto/rsa.c b/crypto/rsa.c
index 752af0656f2e..466003e1a8cf 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -267,12 +267,36 @@ err_free_m:
 	return ret;
 }
 
+static int rsa_check_key_length(unsigned int len)
+{
+	switch (len) {
+	case 512:
+	case 1024:
+	case 1536:
+	case 2048:
+	case 3072:
+	case 4096:
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 static int rsa_setkey(struct crypto_akcipher *tfm, const void *key,
 		      unsigned int keylen)
 {
 	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	int ret;
 
-	return rsa_parse_key(pkey, key, keylen);
+	ret = rsa_parse_key(pkey, key, keylen);
+	if (ret)
+		return ret;
+
+	if (rsa_check_key_length(mpi_get_size(pkey->n) << 3)) {
+		rsa_free_key(pkey);
+		ret = -EINVAL;
+	}
+	return ret;
 }
 
 static void rsa_exit_tfm(struct crypto_akcipher *tfm)
diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c
index 3e8e0a9e5a8e..8d96ce969b44 100644
--- a/crypto/rsa_helper.c
+++ b/crypto/rsa_helper.c
@@ -28,7 +28,7 @@ int rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
 		return -ENOMEM;
 
 	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (mpi_get_size(key->n) != 256 ||
+	if (fips_enabled && (mpi_get_size(key->n) != 256 &&
 			     mpi_get_size(key->n) != 384)) {
 		pr_err("RSA: key size not allowed in FIPS mode\n");
 		mpi_free(key->n);
@@ -62,7 +62,7 @@ int rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
 		return -ENOMEM;
 
 	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (mpi_get_size(key->d) != 256 ||
+	if (fips_enabled && (mpi_get_size(key->d) != 256 &&
 			     mpi_get_size(key->d) != 384)) {
 		pr_err("RSA: key size not allowed in FIPS mode\n");
 		mpi_free(key->d);
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index 122c56e3491b..15a749a5cab7 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -15,7 +15,6 @@
 
 #include <crypto/internal/geniv.h>
 #include <crypto/internal/skcipher.h>
-#include <crypto/null.h>
 #include <crypto/rng.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
@@ -26,23 +25,11 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 
-struct seqniv_request_ctx {
-	struct scatterlist dst[2];
-	struct aead_request subreq;
-};
-
 struct seqiv_ctx {
 	spinlock_t lock;
 	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
 };
 
-struct seqiv_aead_ctx {
-	/* aead_geniv_ctx must be first the element */
-	struct aead_geniv_ctx geniv;
-	struct crypto_blkcipher *null;
-	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
-};
-
 static void seqiv_free(struct crypto_instance *inst);
 
 static void seqiv_complete2(struct skcipher_givcrypt_request *req, int err)
@@ -71,32 +58,6 @@ static void seqiv_complete(struct crypto_async_request *base, int err)
 	skcipher_givcrypt_complete(req, err);
 }
 
-static void seqiv_aead_complete2(struct aead_givcrypt_request *req, int err)
-{
-	struct aead_request *subreq = aead_givcrypt_reqctx(req);
-	struct crypto_aead *geniv;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	if (err)
-		goto out;
-
-	geniv = aead_givcrypt_reqtfm(req);
-	memcpy(req->areq.iv, subreq->iv, crypto_aead_ivsize(geniv));
-
-out:
-	kfree(subreq->iv);
-}
-
-static void seqiv_aead_complete(struct crypto_async_request *base, int err)
-{
-	struct aead_givcrypt_request *req = base->data;
-
-	seqiv_aead_complete2(req, err);
-	aead_givcrypt_complete(req, err);
-}
-
 static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err)
 {
 	struct aead_request *subreq = aead_request_ctx(req);
@@ -124,50 +85,6 @@ static void seqiv_aead_encrypt_complete(struct crypto_async_request *base,
 	aead_request_complete(req, err);
 }
 
-static void seqniv_aead_encrypt_complete2(struct aead_request *req, int err)
-{
-	unsigned int ivsize = 8;
-	u8 data[20];
-
-	if (err == -EINPROGRESS)
-		return;
-
-	/* Swap IV and ESP header back to correct order. */
-	scatterwalk_map_and_copy(data, req->dst, 0, req->assoclen + ivsize, 0);
-	scatterwalk_map_and_copy(data + ivsize, req->dst, 0, req->assoclen, 1);
-	scatterwalk_map_and_copy(data, req->dst, req->assoclen, ivsize, 1);
-}
-
-static void seqniv_aead_encrypt_complete(struct crypto_async_request *base,
-					int err)
-{
-	struct aead_request *req = base->data;
-
-	seqniv_aead_encrypt_complete2(req, err);
-	aead_request_complete(req, err);
-}
-
-static void seqniv_aead_decrypt_complete2(struct aead_request *req, int err)
-{
-	u8 data[4];
-
-	if (err == -EINPROGRESS)
-		return;
-
-	/* Move ESP header back to correct location. */
-	scatterwalk_map_and_copy(data, req->dst, 16, req->assoclen - 8, 0);
-	scatterwalk_map_and_copy(data, req->dst, 8, req->assoclen - 8, 1);
-}
-
-static void seqniv_aead_decrypt_complete(struct crypto_async_request *base,
-					 int err)
-{
-	struct aead_request *req = base->data;
-
-	seqniv_aead_decrypt_complete2(req, err);
-	aead_request_complete(req, err);
-}
-
 static void seqiv_geniv(struct seqiv_ctx *ctx, u8 *info, u64 seq,
 			unsigned int ivsize)
 {
@@ -227,112 +144,10 @@ static int seqiv_givencrypt(struct skcipher_givcrypt_request *req)
 	return err;
 }
 
-static int seqiv_aead_givencrypt(struct aead_givcrypt_request *req)
-{
-	struct crypto_aead *geniv = aead_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
-	struct aead_request *areq = &req->areq;
-	struct aead_request *subreq = aead_givcrypt_reqctx(req);
-	crypto_completion_t compl;
-	void *data;
-	u8 *info;
-	unsigned int ivsize;
-	int err;
-
-	aead_request_set_tfm(subreq, aead_geniv_base(geniv));
-
-	compl = areq->base.complete;
-	data = areq->base.data;
-	info = areq->iv;
-
-	ivsize = crypto_aead_ivsize(geniv);
-
-	if (unlikely(!IS_ALIGNED((unsigned long)info,
-				 crypto_aead_alignmask(geniv) + 1))) {
-		info = kmalloc(ivsize, areq->base.flags &
-				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
-								  GFP_ATOMIC);
-		if (!info)
-			return -ENOMEM;
-
-		compl = seqiv_aead_complete;
-		data = req;
-	}
-
-	aead_request_set_callback(subreq, areq->base.flags, compl, data);
-	aead_request_set_crypt(subreq, areq->src, areq->dst, areq->cryptlen,
-			       info);
-	aead_request_set_assoc(subreq, areq->assoc, areq->assoclen);
-
-	seqiv_geniv(ctx, info, req->seq, ivsize);
-	memcpy(req->giv, info, ivsize);
-
-	err = crypto_aead_encrypt(subreq);
-	if (unlikely(info != areq->iv))
-		seqiv_aead_complete2(req, err);
-	return err;
-}
-
-static int seqniv_aead_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
-	struct seqniv_request_ctx *rctx = aead_request_ctx(req);
-	struct aead_request *subreq = &rctx->subreq;
-	struct scatterlist *dst;
-	crypto_completion_t compl;
-	void *data;
-	unsigned int ivsize = 8;
-	u8 buf[20] __attribute__ ((aligned(__alignof__(u32))));
-	int err;
-
-	if (req->cryptlen < ivsize)
-		return -EINVAL;
-
-	/* ESP AD is at most 12 bytes (ESN). */
-	if (req->assoclen > 12)
-		return -EINVAL;
-
-	aead_request_set_tfm(subreq, ctx->geniv.child);
-
-	compl = seqniv_aead_encrypt_complete;
-	data = req;
-
-	if (req->src != req->dst) {
-		struct blkcipher_desc desc = {
-			.tfm = ctx->null,
-		};
-
-		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
-					       req->assoclen + req->cryptlen);
-		if (err)
-			return err;
-	}
-
-	dst = scatterwalk_ffwd(rctx->dst, req->dst, ivsize);
-
-	aead_request_set_callback(subreq, req->base.flags, compl, data);
-	aead_request_set_crypt(subreq, dst, dst,
-			       req->cryptlen - ivsize, req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
-
-	memcpy(buf, req->iv, ivsize);
-	crypto_xor(buf, ctx->salt, ivsize);
-	memcpy(req->iv, buf, ivsize);
-
-	/* Swap order of IV and ESP AD for ICV generation. */
-	scatterwalk_map_and_copy(buf + ivsize, req->dst, 0, req->assoclen, 0);
-	scatterwalk_map_and_copy(buf, req->dst, 0, req->assoclen + ivsize, 1);
-
-	err = crypto_aead_encrypt(subreq);
-	seqniv_aead_encrypt_complete2(req, err);
-	return err;
-}
-
 static int seqiv_aead_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
 	struct aead_request *subreq = aead_request_ctx(req);
 	crypto_completion_t compl;
 	void *data;
@@ -343,7 +158,7 @@ static int seqiv_aead_encrypt(struct aead_request *req)
 	if (req->cryptlen < ivsize)
 		return -EINVAL;
 
-	aead_request_set_tfm(subreq, ctx->geniv.child);
+	aead_request_set_tfm(subreq, ctx->child);
 
 	compl = req->base.complete;
 	data = req->base.data;
@@ -387,67 +202,10 @@ static int seqiv_aead_encrypt(struct aead_request *req)
 	return err;
 }
 
-static int seqniv_aead_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
-	struct seqniv_request_ctx *rctx = aead_request_ctx(req);
-	struct aead_request *subreq = &rctx->subreq;
-	struct scatterlist *dst;
-	crypto_completion_t compl;
-	void *data;
-	unsigned int ivsize = 8;
-	u8 buf[20];
-	int err;
-
-	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
-		return -EINVAL;
-
-	aead_request_set_tfm(subreq, ctx->geniv.child);
-
-	compl = req->base.complete;
-	data = req->base.data;
-
-	if (req->assoclen > 12)
-		return -EINVAL;
-	else if (req->assoclen > 8) {
-		compl = seqniv_aead_decrypt_complete;
-		data = req;
-	}
-
-	if (req->src != req->dst) {
-		struct blkcipher_desc desc = {
-			.tfm = ctx->null,
-		};
-
-		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
-					       req->assoclen + req->cryptlen);
-		if (err)
-			return err;
-	}
-
-	/* Move ESP AD forward for ICV generation. */
-	scatterwalk_map_and_copy(buf, req->dst, 0, req->assoclen + ivsize, 0);
-	memcpy(req->iv, buf + req->assoclen, ivsize);
-	scatterwalk_map_and_copy(buf, req->dst, ivsize, req->assoclen, 1);
-
-	dst = scatterwalk_ffwd(rctx->dst, req->dst, ivsize);
-
-	aead_request_set_callback(subreq, req->base.flags, compl, data);
-	aead_request_set_crypt(subreq, dst, dst,
-			       req->cryptlen - ivsize, req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
-
-	err = crypto_aead_decrypt(subreq);
-	if (req->assoclen > 8)
-		seqniv_aead_decrypt_complete2(req, err);
-	return err;
-}
-
 static int seqiv_aead_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
-	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
 	struct aead_request *subreq = aead_request_ctx(req);
 	crypto_completion_t compl;
 	void *data;
@@ -456,7 +214,7 @@ static int seqiv_aead_decrypt(struct aead_request *req)
 	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
 		return -EINVAL;
 
-	aead_request_set_tfm(subreq, ctx->geniv.child);
+	aead_request_set_tfm(subreq, ctx->child);
 
 	compl = req->base.complete;
 	data = req->base.data;
@@ -467,9 +225,6 @@ static int seqiv_aead_decrypt(struct aead_request *req)
 	aead_request_set_ad(subreq, req->assoclen + ivsize);
 
 	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
-	if (req->src != req->dst)
-		scatterwalk_map_and_copy(req->iv, req->dst,
-					 req->assoclen, ivsize, 1);
 
 	return crypto_aead_decrypt(subreq);
 }
@@ -495,85 +250,6 @@ static int seqiv_init(struct crypto_tfm *tfm)
 	return err ?: skcipher_geniv_init(tfm);
 }
 
-static int seqiv_old_aead_init(struct crypto_tfm *tfm)
-{
-	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
-	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
-				sizeof(struct aead_request));
-	err = 0;
-	if (!crypto_get_default_rng()) {
-		geniv->givencrypt = seqiv_aead_givencrypt;
-		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-					   crypto_aead_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: aead_geniv_init(tfm);
-}
-
-static int seqiv_aead_init_common(struct crypto_tfm *tfm, unsigned int reqsize)
-{
-	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
-	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
-	int err;
-
-	spin_lock_init(&ctx->geniv.lock);
-
-	crypto_aead_set_reqsize(geniv, sizeof(struct aead_request));
-
-	err = crypto_get_default_rng();
-	if (err)
-		goto out;
-
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_aead_ivsize(geniv));
-	crypto_put_default_rng();
-	if (err)
-		goto out;
-
-	ctx->null = crypto_get_default_null_skcipher();
-	err = PTR_ERR(ctx->null);
-	if (IS_ERR(ctx->null))
-		goto out;
-
-	err = aead_geniv_init(tfm);
-	if (err)
-		goto drop_null;
-
-	ctx->geniv.child = geniv->child;
-	geniv->child = geniv;
-
-out:
-	return err;
-
-drop_null:
-	crypto_put_default_null_skcipher();
-	goto out;
-}
-
-static int seqiv_aead_init(struct crypto_tfm *tfm)
-{
-	return seqiv_aead_init_common(tfm, sizeof(struct aead_request));
-}
-
-static int seqniv_aead_init(struct crypto_tfm *tfm)
-{
-	return seqiv_aead_init_common(tfm, sizeof(struct seqniv_request_ctx));
-}
-
-static void seqiv_aead_exit(struct crypto_tfm *tfm)
-{
-	struct seqiv_aead_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_aead(ctx->geniv.child);
-	crypto_put_default_null_skcipher();
-}
-
 static int seqiv_ablkcipher_create(struct crypto_template *tmpl,
 				   struct rtattr **tb)
 {
@@ -609,33 +285,6 @@ free_inst:
 	goto out;
 }
 
-static int seqiv_old_aead_create(struct crypto_template *tmpl,
-				 struct aead_instance *aead)
-{
-	struct crypto_instance *inst = aead_crypto_instance(aead);
-	int err = -EINVAL;
-
-	if (inst->alg.cra_aead.ivsize < sizeof(u64))
-		goto free_inst;
-
-	inst->alg.cra_init = seqiv_old_aead_init;
-	inst->alg.cra_exit = aead_geniv_exit;
-
-	inst->alg.cra_ctxsize = inst->alg.cra_aead.ivsize;
-	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
-
-	err = crypto_register_instance(tmpl, inst);
-	if (err)
-		goto free_inst;
-
-out:
-	return err;
-
-free_inst:
-	aead_geniv_free(aead);
-	goto out;
-}
-
 static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct aead_instance *inst;
@@ -650,15 +299,9 @@ static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
 
-	if (inst->alg.base.cra_aead.encrypt)
-		return seqiv_old_aead_create(tmpl, inst);
-
 	spawn = aead_instance_ctx(inst);
 	alg = crypto_spawn_aead_alg(spawn);
 
-	if (alg->base.cra_aead.encrypt)
-		goto done;
-
 	err = -EINVAL;
 	if (inst->alg.ivsize != sizeof(u64))
 		goto free_inst;
@@ -666,13 +309,12 @@ static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = seqiv_aead_encrypt;
 	inst->alg.decrypt = seqiv_aead_decrypt;
 
-	inst->alg.base.cra_init = seqiv_aead_init;
-	inst->alg.base.cra_exit = seqiv_aead_exit;
+	inst->alg.init = aead_init_geniv;
+	inst->alg.exit = aead_exit_geniv;
 
-	inst->alg.base.cra_ctxsize = sizeof(struct seqiv_aead_ctx);
-	inst->alg.base.cra_ctxsize += inst->alg.base.cra_aead.ivsize;
+	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
 
-done:
 	err = aead_register_instance(tmpl, inst);
 	if (err)
 		goto free_inst;
@@ -702,51 +344,6 @@ static int seqiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 	return err;
 }
 
-static int seqniv_create(struct crypto_template *tmpl, struct rtattr **tb)
-{
-	struct aead_instance *inst;
-	struct crypto_aead_spawn *spawn;
-	struct aead_alg *alg;
-	int err;
-
-	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto out;
-
-	spawn = aead_instance_ctx(inst);
-	alg = crypto_spawn_aead_alg(spawn);
-
-	if (alg->base.cra_aead.encrypt)
-		goto done;
-
-	err = -EINVAL;
-	if (inst->alg.ivsize != sizeof(u64))
-		goto free_inst;
-
-	inst->alg.encrypt = seqniv_aead_encrypt;
-	inst->alg.decrypt = seqniv_aead_decrypt;
-
-	inst->alg.base.cra_init = seqniv_aead_init;
-	inst->alg.base.cra_exit = seqiv_aead_exit;
-
-	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
-	inst->alg.base.cra_ctxsize = sizeof(struct seqiv_aead_ctx);
-	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
-
-done:
-	err = aead_register_instance(tmpl, inst);
-	if (err)
-		goto free_inst;
-
-out:
-	return err;
-
-free_inst:
-	aead_geniv_free(inst);
-	goto out;
-}
-
 static void seqiv_free(struct crypto_instance *inst)
 {
 	if ((inst->alg.cra_flags ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
@@ -762,36 +359,13 @@ static struct crypto_template seqiv_tmpl = {
 	.module = THIS_MODULE,
 };
 
-static struct crypto_template seqniv_tmpl = {
-	.name = "seqniv",
-	.create = seqniv_create,
-	.free = seqiv_free,
-	.module = THIS_MODULE,
-};
-
 static int __init seqiv_module_init(void)
 {
-	int err;
-
-	err = crypto_register_template(&seqiv_tmpl);
-	if (err)
-		goto out;
-
-	err = crypto_register_template(&seqniv_tmpl);
-	if (err)
-		goto out_undo_niv;
-
-out:
-	return err;
-
-out_undo_niv:
-	crypto_unregister_template(&seqiv_tmpl);
-	goto out;
+	return crypto_register_template(&seqiv_tmpl);
 }
 
 static void __exit seqiv_module_exit(void)
 {
-	crypto_unregister_template(&seqniv_tmpl);
 	crypto_unregister_template(&seqiv_tmpl);
 }
 
@@ -801,4 +375,3 @@ module_exit(seqiv_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Sequence Number IV Generator");
 MODULE_ALIAS_CRYPTO("seqiv");
-MODULE_ALIAS_CRYPTO("seqniv");
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
new file mode 100644
index 000000000000..dd5fc1bf6447
--- /dev/null
+++ b/crypto/skcipher.c
@@ -0,0 +1,245 @@
+/*
+ * Symmetric key cipher operations.
+ *
+ * Generic encrypt/decrypt wrapper for ciphers, handles operations across
+ * multiple page boundaries by using temporary blocks.  In user context,
+ * the kernel is given a chance to schedule us once per page.
+ *
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/skcipher.h>
+#include <linux/bug.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+static unsigned int crypto_skcipher_extsize(struct crypto_alg *alg)
+{
+	if (alg->cra_type == &crypto_blkcipher_type)
+		return sizeof(struct crypto_blkcipher *);
+
+	BUG_ON(alg->cra_type != &crypto_ablkcipher_type &&
+	       alg->cra_type != &crypto_givcipher_type);
+
+	return sizeof(struct crypto_ablkcipher *);
+}
+
+static int skcipher_setkey_blkcipher(struct crypto_skcipher *tfm,
+				     const u8 *key, unsigned int keylen)
+{
+	struct crypto_blkcipher **ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_blkcipher *blkcipher = *ctx;
+	int err;
+
+	crypto_blkcipher_clear_flags(blkcipher, ~0);
+	crypto_blkcipher_set_flags(blkcipher, crypto_skcipher_get_flags(tfm) &
+					      CRYPTO_TFM_REQ_MASK);
+	err = crypto_blkcipher_setkey(blkcipher, key, keylen);
+	crypto_skcipher_set_flags(tfm, crypto_blkcipher_get_flags(blkcipher) &
+				       CRYPTO_TFM_RES_MASK);
+
+	return err;
+}
+
+static int skcipher_crypt_blkcipher(struct skcipher_request *req,
+				    int (*crypt)(struct blkcipher_desc *,
+						 struct scatterlist *,
+						 struct scatterlist *,
+						 unsigned int))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_blkcipher **ctx = crypto_skcipher_ctx(tfm);
+	struct blkcipher_desc desc = {
+		.tfm = *ctx,
+		.info = req->iv,
+		.flags = req->base.flags,
+	};
+
+
+	return crypt(&desc, req->dst, req->src, req->cryptlen);
+}
+
+static int skcipher_encrypt_blkcipher(struct skcipher_request *req)
+{
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
+
+	return skcipher_crypt_blkcipher(req, alg->encrypt);
+}
+
+static int skcipher_decrypt_blkcipher(struct skcipher_request *req)
+{
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
+
+	return skcipher_crypt_blkcipher(req, alg->decrypt);
+}
+
+static void crypto_exit_skcipher_ops_blkcipher(struct crypto_tfm *tfm)
+{
+	struct crypto_blkcipher **ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_blkcipher(*ctx);
+}
+
+int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *calg = tfm->__crt_alg;
+	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
+	struct crypto_blkcipher **ctx = crypto_tfm_ctx(tfm);
+	struct crypto_blkcipher *blkcipher;
+	struct crypto_tfm *btfm;
+
+	if (!crypto_mod_get(calg))
+		return -EAGAIN;
+
+	btfm = __crypto_alloc_tfm(calg, CRYPTO_ALG_TYPE_BLKCIPHER,
+					CRYPTO_ALG_TYPE_MASK);
+	if (IS_ERR(btfm)) {
+		crypto_mod_put(calg);
+		return PTR_ERR(btfm);
+	}
+
+	blkcipher = __crypto_blkcipher_cast(btfm);
+	*ctx = blkcipher;
+	tfm->exit = crypto_exit_skcipher_ops_blkcipher;
+
+	skcipher->setkey = skcipher_setkey_blkcipher;
+	skcipher->encrypt = skcipher_encrypt_blkcipher;
+	skcipher->decrypt = skcipher_decrypt_blkcipher;
+
+	skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher);
+
+	return 0;
+}
+
+static int skcipher_setkey_ablkcipher(struct crypto_skcipher *tfm,
+				      const u8 *key, unsigned int keylen)
+{
+	struct crypto_ablkcipher **ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_ablkcipher *ablkcipher = *ctx;
+	int err;
+
+	crypto_ablkcipher_clear_flags(ablkcipher, ~0);
+	crypto_ablkcipher_set_flags(ablkcipher,
+				    crypto_skcipher_get_flags(tfm) &
+				    CRYPTO_TFM_REQ_MASK);
+	err = crypto_ablkcipher_setkey(ablkcipher, key, keylen);
+	crypto_skcipher_set_flags(tfm,
+				  crypto_ablkcipher_get_flags(ablkcipher) &
+				  CRYPTO_TFM_RES_MASK);
+
+	return err;
+}
+
+static int skcipher_crypt_ablkcipher(struct skcipher_request *req,
+				     int (*crypt)(struct ablkcipher_request *))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_ablkcipher **ctx = crypto_skcipher_ctx(tfm);
+	struct ablkcipher_request *subreq = skcipher_request_ctx(req);
+
+	ablkcipher_request_set_tfm(subreq, *ctx);
+	ablkcipher_request_set_callback(subreq, skcipher_request_flags(req),
+					req->base.complete, req->base.data);
+	ablkcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
+				     req->iv);
+
+	return crypt(subreq);
+}
+
+static int skcipher_encrypt_ablkcipher(struct skcipher_request *req)
+{
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher;
+
+	return skcipher_crypt_ablkcipher(req, alg->encrypt);
+}
+
+static int skcipher_decrypt_ablkcipher(struct skcipher_request *req)
+{
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher);
+	struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher;
+
+	return skcipher_crypt_ablkcipher(req, alg->decrypt);
+}
+
+static void crypto_exit_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
+{
+	struct crypto_ablkcipher **ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_ablkcipher(*ctx);
+}
+
+int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *calg = tfm->__crt_alg;
+	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
+	struct crypto_ablkcipher **ctx = crypto_tfm_ctx(tfm);
+	struct crypto_ablkcipher *ablkcipher;
+	struct crypto_tfm *abtfm;
+
+	if (!crypto_mod_get(calg))
+		return -EAGAIN;
+
+	abtfm = __crypto_alloc_tfm(calg, 0, 0);
+	if (IS_ERR(abtfm)) {
+		crypto_mod_put(calg);
+		return PTR_ERR(abtfm);
+	}
+
+	ablkcipher = __crypto_ablkcipher_cast(abtfm);
+	*ctx = ablkcipher;
+	tfm->exit = crypto_exit_skcipher_ops_ablkcipher;
+
+	skcipher->setkey = skcipher_setkey_ablkcipher;
+	skcipher->encrypt = skcipher_encrypt_ablkcipher;
+	skcipher->decrypt = skcipher_decrypt_ablkcipher;
+
+	skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+	skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) +
+			    sizeof(struct ablkcipher_request);
+
+	return 0;
+}
+
+static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
+{
+	if (tfm->__crt_alg->cra_type == &crypto_blkcipher_type)
+		return crypto_init_skcipher_ops_blkcipher(tfm);
+
+	BUG_ON(tfm->__crt_alg->cra_type != &crypto_ablkcipher_type &&
+	       tfm->__crt_alg->cra_type != &crypto_givcipher_type);
+
+	return crypto_init_skcipher_ops_ablkcipher(tfm);
+}
+
+static const struct crypto_type crypto_skcipher_type2 = {
+	.extsize = crypto_skcipher_extsize,
+	.init_tfm = crypto_skcipher_init_tfm,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_BLKCIPHER_MASK,
+	.type = CRYPTO_ALG_TYPE_BLKCIPHER,
+	.tfmsize = offsetof(struct crypto_skcipher, base),
+};
+
+struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name,
+					      u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_skcipher_type2, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_skcipher);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Symmetric key cipher type");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 9f6f10b498ba..2b00b617daab 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -73,6 +73,22 @@ static char *check[] = {
 	"lzo", "cts", "zlib", NULL
 };
 
+struct tcrypt_result {
+	struct completion completion;
+	int err;
+};
+
+static void tcrypt_complete(struct crypto_async_request *req, int err)
+{
+	struct tcrypt_result *res = req->data;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	res->err = err;
+	complete(&res->completion);
+}
+
 static int test_cipher_jiffies(struct blkcipher_desc *desc, int enc,
 			       struct scatterlist *sg, int blen, int secs)
 {
@@ -143,6 +159,20 @@ out:
 	return ret;
 }
 
+static inline int do_one_aead_op(struct aead_request *req, int ret)
+{
+	if (ret == -EINPROGRESS || ret == -EBUSY) {
+		struct tcrypt_result *tr = req->base.data;
+
+		ret = wait_for_completion_interruptible(&tr->completion);
+		if (!ret)
+			ret = tr->err;
+		reinit_completion(&tr->completion);
+	}
+
+	return ret;
+}
+
 static int test_aead_jiffies(struct aead_request *req, int enc,
 				int blen, int secs)
 {
@@ -153,9 +183,9 @@ static int test_aead_jiffies(struct aead_request *req, int enc,
 	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		if (enc)
-			ret = crypto_aead_encrypt(req);
+			ret = do_one_aead_op(req, crypto_aead_encrypt(req));
 		else
-			ret = crypto_aead_decrypt(req);
+			ret = do_one_aead_op(req, crypto_aead_decrypt(req));
 
 		if (ret)
 			return ret;
@@ -177,9 +207,9 @@ static int test_aead_cycles(struct aead_request *req, int enc, int blen)
 	/* Warm-up run. */
 	for (i = 0; i < 4; i++) {
 		if (enc)
-			ret = crypto_aead_encrypt(req);
+			ret = do_one_aead_op(req, crypto_aead_encrypt(req));
 		else
-			ret = crypto_aead_decrypt(req);
+			ret = do_one_aead_op(req, crypto_aead_decrypt(req));
 
 		if (ret)
 			goto out;
@@ -191,9 +221,9 @@ static int test_aead_cycles(struct aead_request *req, int enc, int blen)
 
 		start = get_cycles();
 		if (enc)
-			ret = crypto_aead_encrypt(req);
+			ret = do_one_aead_op(req, crypto_aead_encrypt(req));
 		else
-			ret = crypto_aead_decrypt(req);
+			ret = do_one_aead_op(req, crypto_aead_decrypt(req));
 		end = get_cycles();
 
 		if (ret)
@@ -286,6 +316,7 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 	char *axbuf[XBUFSIZE];
 	unsigned int *b_size;
 	unsigned int iv_len;
+	struct tcrypt_result result;
 
 	iv = kzalloc(MAX_IVLEN, GFP_KERNEL);
 	if (!iv)
@@ -321,6 +352,7 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 		goto out_notfm;
 	}
 
+	init_completion(&result.completion);
 	printk(KERN_INFO "\ntesting speed of %s (%s) %s\n", algo,
 			get_driver_name(crypto_aead, tfm), e);
 
@@ -331,6 +363,9 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 		goto out_noreq;
 	}
 
+	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  tcrypt_complete, &result);
+
 	i = 0;
 	do {
 		b_size = aead_sizes;
@@ -749,22 +784,6 @@ out:
 	crypto_free_hash(tfm);
 }
 
-struct tcrypt_result {
-	struct completion completion;
-	int err;
-};
-
-static void tcrypt_complete(struct crypto_async_request *req, int err)
-{
-	struct tcrypt_result *res = req->data;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	res->err = err;
-	complete(&res->completion);
-}
-
 static inline int do_one_ahash_op(struct ahash_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
@@ -1759,14 +1778,27 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 
 	case 211:
 		test_aead_speed("rfc4106(gcm(aes))", ENCRYPT, sec,
+				NULL, 0, 16, 16, aead_speed_template_20);
+		test_aead_speed("gcm(aes)", ENCRYPT, sec,
 				NULL, 0, 16, 8, aead_speed_template_20);
 		break;
 
 	case 212:
 		test_aead_speed("rfc4309(ccm(aes))", ENCRYPT, sec,
-				NULL, 0, 16, 8, aead_speed_template_19);
+				NULL, 0, 16, 16, aead_speed_template_19);
+		break;
+
+	case 213:
+		test_aead_speed("rfc7539esp(chacha20,poly1305)", ENCRYPT, sec,
+				NULL, 0, 16, 8, aead_speed_template_36);
+		break;
+
+	case 214:
+		test_cipher_speed("chacha20", ENCRYPT, sec, NULL, 0,
+				  speed_template_32);
 		break;
 
+
 	case 300:
 		if (alg) {
 			test_hash_speed(alg, sec, generic_hash_speed_template);
@@ -1855,6 +1887,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		test_hash_speed("crct10dif", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 
+	case 321:
+		test_hash_speed("poly1305", sec, poly1305_speed_template);
+		if (mode > 300 && mode < 400) break;
+
 	case 399:
 		break;
 
diff --git a/crypto/tcrypt.h b/crypto/tcrypt.h
index 6cc1b856871b..f0bfee1bb293 100644
--- a/crypto/tcrypt.h
+++ b/crypto/tcrypt.h
@@ -61,12 +61,14 @@ static u8 speed_template_32_40_48[] = {32, 40, 48, 0};
 static u8 speed_template_32_48[] = {32, 48, 0};
 static u8 speed_template_32_48_64[] = {32, 48, 64, 0};
 static u8 speed_template_32_64[] = {32, 64, 0};
+static u8 speed_template_32[] = {32, 0};
 
 /*
  * AEAD speed tests
  */
 static u8 aead_speed_template_19[] = {19, 0};
 static u8 aead_speed_template_20[] = {20, 0};
+static u8 aead_speed_template_36[] = {36, 0};
 
 /*
  * Digest speed tests
@@ -127,4 +129,22 @@ static struct hash_speed hash_speed_template_16[] = {
 	{  .blen = 0,	.plen = 0,	.klen = 0, }
 };
 
+static struct hash_speed poly1305_speed_template[] = {
+	{ .blen = 96,	.plen = 16, },
+	{ .blen = 96,	.plen = 32, },
+	{ .blen = 96,	.plen = 96, },
+	{ .blen = 288,	.plen = 16, },
+	{ .blen = 288,	.plen = 32, },
+	{ .blen = 288,	.plen = 288, },
+	{ .blen = 1056,	.plen = 32, },
+	{ .blen = 1056,	.plen = 1056, },
+	{ .blen = 2080,	.plen = 32, },
+	{ .blen = 2080,	.plen = 2080, },
+	{ .blen = 4128,	.plen = 4128, },
+	{ .blen = 8224,	.plen = 8224, },
+
+	/* End marker */
+	{  .blen = 0,	.plen = 0, }
+};
+
 #endif	/* _CRYPTO_TCRYPT_H */
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index d0a42bd3aae9..35c2de136971 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -22,6 +22,7 @@
 
 #include <crypto/aead.h>
 #include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/fips.h>
 #include <linux/module.h>
@@ -921,15 +922,15 @@ out_nobuf:
 	return ret;
 }
 
-static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
+static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 			   struct cipher_testvec *template, unsigned int tcount,
 			   const bool diff_dst, const int align_offset)
 {
 	const char *algo =
-		crypto_tfm_alg_driver_name(crypto_ablkcipher_tfm(tfm));
+		crypto_tfm_alg_driver_name(crypto_skcipher_tfm(tfm));
 	unsigned int i, j, k, n, temp;
 	char *q;
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 	struct scatterlist sg[8];
 	struct scatterlist sgout[8];
 	const char *e, *d;
@@ -958,15 +959,15 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 
 	init_completion(&result.completion);
 
-	req = ablkcipher_request_alloc(tfm, GFP_KERNEL);
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
 	if (!req) {
 		pr_err("alg: skcipher%s: Failed to allocate request for %s\n",
 		       d, algo);
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					tcrypt_complete, &result);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      tcrypt_complete, &result);
 
 	j = 0;
 	for (i = 0; i < tcount; i++) {
@@ -987,15 +988,16 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 		data += align_offset;
 		memcpy(data, template[i].input, template[i].ilen);
 
-		crypto_ablkcipher_clear_flags(tfm, ~0);
+		crypto_skcipher_clear_flags(tfm, ~0);
 		if (template[i].wk)
-			crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+			crypto_skcipher_set_flags(tfm,
+						  CRYPTO_TFM_REQ_WEAK_KEY);
 
-		ret = crypto_ablkcipher_setkey(tfm, template[i].key,
-					       template[i].klen);
+		ret = crypto_skcipher_setkey(tfm, template[i].key,
+					     template[i].klen);
 		if (!ret == template[i].fail) {
 			pr_err("alg: skcipher%s: setkey failed on test %d for %s: flags=%x\n",
-			       d, j, algo, crypto_ablkcipher_get_flags(tfm));
+			       d, j, algo, crypto_skcipher_get_flags(tfm));
 			goto out;
 		} else if (ret)
 			continue;
@@ -1007,10 +1009,10 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 			sg_init_one(&sgout[0], data, template[i].ilen);
 		}
 
-		ablkcipher_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
-					     template[i].ilen, iv);
-		ret = enc ? crypto_ablkcipher_encrypt(req) :
-			    crypto_ablkcipher_decrypt(req);
+		skcipher_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
+					   template[i].ilen, iv);
+		ret = enc ? crypto_skcipher_encrypt(req) :
+			    crypto_skcipher_decrypt(req);
 
 		switch (ret) {
 		case 0:
@@ -1054,15 +1056,16 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 			memset(iv, 0, MAX_IVLEN);
 
 		j++;
-		crypto_ablkcipher_clear_flags(tfm, ~0);
+		crypto_skcipher_clear_flags(tfm, ~0);
 		if (template[i].wk)
-			crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+			crypto_skcipher_set_flags(tfm,
+						  CRYPTO_TFM_REQ_WEAK_KEY);
 
-		ret = crypto_ablkcipher_setkey(tfm, template[i].key,
-					       template[i].klen);
+		ret = crypto_skcipher_setkey(tfm, template[i].key,
+					     template[i].klen);
 		if (!ret == template[i].fail) {
 			pr_err("alg: skcipher%s: setkey failed on chunk test %d for %s: flags=%x\n",
-			       d, j, algo, crypto_ablkcipher_get_flags(tfm));
+			       d, j, algo, crypto_skcipher_get_flags(tfm));
 			goto out;
 		} else if (ret)
 			continue;
@@ -1100,11 +1103,11 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 			temp += template[i].tap[k];
 		}
 
-		ablkcipher_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
-					     template[i].ilen, iv);
+		skcipher_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
+					   template[i].ilen, iv);
 
-		ret = enc ? crypto_ablkcipher_encrypt(req) :
-			    crypto_ablkcipher_decrypt(req);
+		ret = enc ? crypto_skcipher_encrypt(req) :
+			    crypto_skcipher_decrypt(req);
 
 		switch (ret) {
 		case 0:
@@ -1157,7 +1160,7 @@ static int __test_skcipher(struct crypto_ablkcipher *tfm, int enc,
 	ret = 0;
 
 out:
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (diff_dst)
 		testmgr_free_buf(xoutbuf);
 out_nooutbuf:
@@ -1166,7 +1169,7 @@ out_nobuf:
 	return ret;
 }
 
-static int test_skcipher(struct crypto_ablkcipher *tfm, int enc,
+static int test_skcipher(struct crypto_skcipher *tfm, int enc,
 			 struct cipher_testvec *template, unsigned int tcount)
 {
 	unsigned int alignmask;
@@ -1578,10 +1581,10 @@ out:
 static int alg_test_skcipher(const struct alg_test_desc *desc,
 			     const char *driver, u32 type, u32 mask)
 {
-	struct crypto_ablkcipher *tfm;
+	struct crypto_skcipher *tfm;
 	int err = 0;
 
-	tfm = crypto_alloc_ablkcipher(driver, type | CRYPTO_ALG_INTERNAL, mask);
+	tfm = crypto_alloc_skcipher(driver, type | CRYPTO_ALG_INTERNAL, mask);
 	if (IS_ERR(tfm)) {
 		printk(KERN_ERR "alg: skcipher: Failed to load transform for "
 		       "%s: %ld\n", driver, PTR_ERR(tfm));
@@ -1600,7 +1603,7 @@ static int alg_test_skcipher(const struct alg_test_desc *desc,
 				    desc->suite.cipher.dec.count);
 
 out:
-	crypto_free_ablkcipher(tfm);
+	crypto_free_skcipher(tfm);
 	return err;
 }
 
@@ -2476,6 +2479,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "cmac(aes)",
+		.fips_allowed = 1,
 		.test = alg_test_hash,
 		.suite = {
 			.hash = {
@@ -2485,6 +2489,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "cmac(des3_ede)",
+		.fips_allowed = 1,
 		.test = alg_test_hash,
 		.suite = {
 			.hash = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 868edf117041..64b8a8082645 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -14504,6 +14504,9 @@ static struct cipher_testvec aes_cbc_enc_tv_template[] = {
 		.result = "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
 			  "\x27\x08\x94\x2d\xbe\x77\x18\x1a",
 		.rlen   = 16,
+		.also_non_np = 1,
+		.np	= 8,
+		.tap	= { 3, 2, 3, 2, 3, 1, 1, 1 },
 	}, {
 		.key    = "\xc2\x86\x69\x6d\x88\x7c\x9a\xa0"
 			  "\x61\x1b\xbb\x3e\x20\x25\xa4\x5a",
@@ -14723,6 +14726,9 @@ static struct cipher_testvec aes_cbc_dec_tv_template[] = {
 		.ilen   = 16,
 		.result = "Single block msg",
 		.rlen   = 16,
+		.also_non_np = 1,
+		.np	= 8,
+		.tap	= { 3, 2, 3, 2, 3, 1, 1, 1 },
 	}, {
 		.key    = "\xc2\x86\x69\x6d\x88\x7c\x9a\xa0"
 			  "\x61\x1b\xbb\x3e\x20\x25\xa4\x5a",
@@ -15032,6 +15038,9 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 16,
 		.iv     = "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
 			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
+		.assoc	= "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
+			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
+		.alen	= 16,
 		.input  = "Single block msg",
 		.ilen   = 16,
 		.result = "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
@@ -15057,6 +15066,9 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 16,
 		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
 			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
+		.assoc	= "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
+			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
+		.alen	= 16,
 		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
@@ -15087,6 +15099,9 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 16,
 		.iv     = "\xc7\x82\xdc\x4c\x09\x8c\x66\xcb"
 			  "\xd9\xcd\x27\xd8\x25\x68\x2c\x81",
+		.assoc	= "\xc7\x82\xdc\x4c\x09\x8c\x66\xcb"
+			  "\xd9\xcd\x27\xd8\x25\x68\x2c\x81",
+		.alen	= 16,
 		.input  = "This is a 48-byte message (exactly 3 AES blocks)",
 		.ilen   = 48,
 		.result = "\xd0\xa0\x2b\x38\x36\x45\x17\x53"
@@ -15116,6 +15131,9 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 16,
 		.iv     = "\x8c\xe8\x2e\xef\xbe\xa0\xda\x3c"
 			  "\x44\x69\x9e\xd7\xdb\x51\xb7\xd9",
+		.assoc	= "\x8c\xe8\x2e\xef\xbe\xa0\xda\x3c"
+			  "\x44\x69\x9e\xd7\xdb\x51\xb7\xd9",
+		.alen	= 16,
 		.input  = "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
 			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
 			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
@@ -15154,8 +15172,10 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 16,
 		.iv     = "\xe9\x6e\x8c\x08\xab\x46\x57\x63"
 			  "\xfd\x09\x8d\x45\xdd\x3f\xf8\x93",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\xe9\x6e\x8c\x08\xab\x46\x57\x63"
+			  "\xfd\x09\x8d\x45\xdd\x3f\xf8\x93",
+		.alen   = 24,
 		.input  = "\x08\x00\x0e\xbd\xa7\x0a\x00\x00"
 			  "\x8e\x9c\x08\x3d\xb9\x5b\x07\x00"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
@@ -15199,6 +15219,9 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 24,
 		.iv     = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.assoc	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.alen	= 16,
 		.input  = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
@@ -15239,6 +15262,9 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 20 + 32,
 		.iv     = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.assoc	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.alen	= 16,
 		.input  = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
@@ -15374,6 +15400,9 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 16,
 		.iv     = "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
 			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
+		.assoc	= "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
+			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
+		.alen	= 16,
 		.input  = "Single block msg",
 		.ilen   = 16,
 		.result = "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
@@ -15401,6 +15430,9 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 16,
 		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
 			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
+		.assoc	= "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
+			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
+		.alen	= 16,
 		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
@@ -15433,6 +15465,9 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 16,
 		.iv     = "\xc7\x82\xdc\x4c\x09\x8c\x66\xcb"
 			  "\xd9\xcd\x27\xd8\x25\x68\x2c\x81",
+		.assoc	= "\xc7\x82\xdc\x4c\x09\x8c\x66\xcb"
+			  "\xd9\xcd\x27\xd8\x25\x68\x2c\x81",
+		.alen	= 16,
 		.input  = "This is a 48-byte message (exactly 3 AES blocks)",
 		.ilen   = 48,
 		.result = "\xd0\xa0\x2b\x38\x36\x45\x17\x53"
@@ -15464,6 +15499,9 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 16,
 		.iv     = "\x8c\xe8\x2e\xef\xbe\xa0\xda\x3c"
 			  "\x44\x69\x9e\xd7\xdb\x51\xb7\xd9",
+		.assoc	= "\x8c\xe8\x2e\xef\xbe\xa0\xda\x3c"
+			  "\x44\x69\x9e\xd7\xdb\x51\xb7\xd9",
+		.alen	= 16,
 		.input  = "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
 			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
 			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
@@ -15504,8 +15542,10 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 16,
 		.iv     = "\xe9\x6e\x8c\x08\xab\x46\x57\x63"
 			  "\xfd\x09\x8d\x45\xdd\x3f\xf8\x93",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\xe9\x6e\x8c\x08\xab\x46\x57\x63"
+			  "\xfd\x09\x8d\x45\xdd\x3f\xf8\x93",
+		.alen   = 24,
 		.input  = "\x08\x00\x0e\xbd\xa7\x0a\x00\x00"
 			  "\x8e\x9c\x08\x3d\xb9\x5b\x07\x00"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
@@ -15551,6 +15591,9 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 24,
 		.iv     = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.assoc	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.alen   = 16,
 		.input  = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
@@ -15593,6 +15636,9 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 32 + 32,
 		.iv     = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.assoc	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.alen   = 16,
 		.input  = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
@@ -15641,6 +15687,9 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 16,
 		.iv     = "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
 			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
+		.assoc	= "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
+			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
+		.alen   = 16,
 		.input  = "Single block msg",
 		.ilen   = 16,
 		.result = "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
@@ -15676,6 +15725,9 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 16,
 		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
 			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
+		.assoc	= "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
+			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
+		.alen   = 16,
 		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
@@ -15716,6 +15768,9 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 16,
 		.iv     = "\xc7\x82\xdc\x4c\x09\x8c\x66\xcb"
 			  "\xd9\xcd\x27\xd8\x25\x68\x2c\x81",
+		.assoc	= "\xc7\x82\xdc\x4c\x09\x8c\x66\xcb"
+			  "\xd9\xcd\x27\xd8\x25\x68\x2c\x81",
+		.alen   = 16,
 		.input  = "This is a 48-byte message (exactly 3 AES blocks)",
 		.ilen   = 48,
 		.result = "\xd0\xa0\x2b\x38\x36\x45\x17\x53"
@@ -15755,6 +15810,9 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 16,
 		.iv     = "\x8c\xe8\x2e\xef\xbe\xa0\xda\x3c"
 			  "\x44\x69\x9e\xd7\xdb\x51\xb7\xd9",
+		.assoc	= "\x8c\xe8\x2e\xef\xbe\xa0\xda\x3c"
+			  "\x44\x69\x9e\xd7\xdb\x51\xb7\xd9",
+		.alen   = 16,
 		.input  = "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
 			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
 			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
@@ -15803,8 +15861,10 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 16,
 		.iv     = "\xe9\x6e\x8c\x08\xab\x46\x57\x63"
 			  "\xfd\x09\x8d\x45\xdd\x3f\xf8\x93",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\xe9\x6e\x8c\x08\xab\x46\x57\x63"
+			  "\xfd\x09\x8d\x45\xdd\x3f\xf8\x93",
+		.alen   = 24,
 		.input  = "\x08\x00\x0e\xbd\xa7\x0a\x00\x00"
 			  "\x8e\x9c\x08\x3d\xb9\x5b\x07\x00"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
@@ -15858,6 +15918,9 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 24,
 		.iv     = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.assoc	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.alen   = 16,
 		.input  = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
@@ -15908,6 +15971,9 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 		.klen   = 8 + 64 + 32,
 		.iv     = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.assoc	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.alen   = 16,
 		.input  = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
@@ -15955,8 +16021,9 @@ static struct aead_testvec hmac_sha1_des_cbc_enc_tv_temp[] = {
 			  "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24",
 		.klen	= 8 + 20 + 8,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16015,8 +16082,9 @@ static struct aead_testvec hmac_sha224_des_cbc_enc_tv_temp[] = {
 			  "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24",
 		.klen	= 8 + 24 + 8,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16076,8 +16144,9 @@ static struct aead_testvec hmac_sha256_des_cbc_enc_tv_temp[] = {
 			  "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24",
 		.klen	= 8 + 32 + 8,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16140,8 +16209,9 @@ static struct aead_testvec hmac_sha384_des_cbc_enc_tv_temp[] = {
 			  "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24",
 		.klen	= 8 + 48 + 8,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16208,8 +16278,9 @@ static struct aead_testvec hmac_sha512_des_cbc_enc_tv_temp[] = {
 			  "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24",
 		.klen	= 8 + 64 + 8,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16275,8 +16346,9 @@ static struct aead_testvec hmac_sha1_des3_ede_cbc_enc_tv_temp[] = {
 			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
 		.klen	= 8 + 20 + 24,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 		  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16337,8 +16409,9 @@ static struct aead_testvec hmac_sha224_des3_ede_cbc_enc_tv_temp[] = {
 			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
 		.klen	= 8 + 24 + 24,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16400,8 +16473,9 @@ static struct aead_testvec hmac_sha256_des3_ede_cbc_enc_tv_temp[] = {
 			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
 		.klen	= 8 + 32 + 24,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16466,8 +16540,9 @@ static struct aead_testvec hmac_sha384_des3_ede_cbc_enc_tv_temp[] = {
 			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
 		.klen	= 8 + 48 + 24,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-	.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -16536,8 +16611,9 @@ static struct aead_testvec hmac_sha512_des3_ede_cbc_enc_tv_temp[] = {
 			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
 		.klen	= 8 + 64 + 24,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01",
-		.alen   = 8,
+		.assoc  = "\x00\x00\x43\x21\x00\x00\x00\x01"
+			  "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
+		.alen   = 16,
 		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
@@ -20129,149 +20205,150 @@ static struct aead_testvec aes_gcm_dec_tv_template[] = {
 };
 
 static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
-        { /* Generated using Crypto++ */
+	{ /* Generated using Crypto++ */
 		.key    = zeroed_string,
 		.klen	= 20,
-                .iv     = zeroed_string,
-                .input  = zeroed_string,
-                .ilen   = 16,
-                .assoc  = zeroed_string,
-                .alen   = 8,
+		.iv	= zeroed_string,
+		.input  = zeroed_string,
+		.ilen   = 16,
+		.assoc  = zeroed_string,
+		.alen   = 16,
 		.result	= "\x03\x88\xDA\xCE\x60\xB6\xA3\x92"
-                          "\xF3\x28\xC2\xB9\x71\xB2\xFE\x78"
-                          "\x97\xFE\x4C\x23\x37\x42\x01\xE0"
-                          "\x81\x9F\x8D\xC5\xD7\x41\xA0\x1B",
+			  "\xF3\x28\xC2\xB9\x71\xB2\xFE\x78"
+			  "\x97\xFE\x4C\x23\x37\x42\x01\xE0"
+			  "\x81\x9F\x8D\xC5\xD7\x41\xA0\x1B",
 		.rlen	= 32,
-        },{
+	},{
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x00\x00\x00\x00\x00\x01"
-                          "\x00\x00\x00\x00",
-                .input  = zeroed_string,
-                .ilen   = 16,
-                .assoc  = zeroed_string,
-                .alen   = 8,
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input  = zeroed_string,
+		.ilen   = 16,
+		.assoc  = "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen   = 16,
 		.result	= "\xC0\x0D\x8B\x42\x0F\x8F\x34\x18"
-                          "\x88\xB1\xC5\xBC\xC5\xB6\xD6\x28"
-                          "\x6A\x9D\xDF\x11\x5E\xFE\x5E\x9D"
-                          "\x2F\x70\x44\x92\xF7\xF2\xE3\xEF",
+			  "\x88\xB1\xC5\xBC\xC5\xB6\xD6\x28"
+			  "\x6A\x9D\xDF\x11\x5E\xFE\x5E\x9D"
+			  "\x2F\x70\x44\x92\xF7\xF2\xE3\xEF",
 		.rlen	= 32,
 
-        }, {
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = zeroed_string,
-                .input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .ilen   = 16,
-                .assoc  = zeroed_string,
-                .alen   = 8,
+		.iv     = zeroed_string,
+		.input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen   = 16,
+		.assoc  = zeroed_string,
+		.alen   = 16,
 		.result	= "\x4B\xB1\xB5\xE3\x25\x71\x70\xDE"
-                          "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
-                          "\x0B\x8F\x88\x69\x17\xE6\xB4\x3C"
-                          "\xB1\x68\xFD\x14\x52\x64\x61\xB2",
+			  "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
+			  "\x0B\x8F\x88\x69\x17\xE6\xB4\x3C"
+			  "\xB1\x68\xFD\x14\x52\x64\x61\xB2",
 		.rlen	= 32,
-        }, {
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = zeroed_string,
-                .input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .ilen   = 16,
-                .assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .alen   = 8,
+		.iv     = zeroed_string,
+		.input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen   = 16,
+		.assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen   = 16,
 		.result	= "\x4B\xB1\xB5\xE3\x25\x71\x70\xDE"
-                          "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
-                          "\x90\x92\xB7\xE3\x5F\xA3\x9A\x63"
-                          "\x7E\xD7\x1F\xD8\xD3\x7C\x4B\xF5",
+			  "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
+			  "\x90\x92\xB7\xE3\x5F\xA3\x9A\x63"
+			  "\x7E\xD7\x1F\xD8\xD3\x7C\x4B\xF5",
 		.rlen	= 32,
-        }, {
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x00\x00\x00\x00\x00\x01"
-                          "\x00\x00\x00\x00",
-                .input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .ilen   = 16,
-                .assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .alen   = 8,
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen   = 16,
+		.assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen   = 16,
 		.result	= "\xC1\x0C\x8A\x43\x0E\x8E\x35\x19"
-                          "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
-                          "\x64\x50\xF9\x32\x13\xFB\x74\x61"
-                          "\xF4\xED\x52\xD3\xC5\x10\x55\x3C",
+			  "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
+			  "\x64\x50\xF9\x32\x13\xFB\x74\x61"
+			  "\xF4\xED\x52\xD3\xC5\x10\x55\x3C",
 		.rlen	= 32,
-        }, {
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x00\x00\x00\x00\x00\x01"
-                          "\x00\x00\x00\x00",
-                .input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .ilen   = 64,
-                .assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .alen   = 8,
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen   = 64,
+		.assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen   = 16,
 		.result	= "\xC1\x0C\x8A\x43\x0E\x8E\x35\x19"
-                          "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
-                          "\x98\x14\xA1\x42\x37\x80\xFD\x90"
-                          "\x68\x12\x01\xA8\x91\x89\xB9\x83"
-                          "\x5B\x11\x77\x12\x9B\xFF\x24\x89"
-                          "\x94\x5F\x18\x12\xBA\x27\x09\x39"
-                          "\x99\x96\x76\x42\x15\x1C\xCD\xCB"
-                          "\xDC\xD3\xDA\x65\x73\xAF\x80\xCD"
-                          "\xD2\xB6\xC2\x4A\x76\xC2\x92\x85"
-                          "\xBD\xCF\x62\x98\x58\x14\xE5\xBD",
+			  "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
+			  "\x98\x14\xA1\x42\x37\x80\xFD\x90"
+			  "\x68\x12\x01\xA8\x91\x89\xB9\x83"
+			  "\x5B\x11\x77\x12\x9B\xFF\x24\x89"
+			  "\x94\x5F\x18\x12\xBA\x27\x09\x39"
+			  "\x99\x96\x76\x42\x15\x1C\xCD\xCB"
+			  "\xDC\xD3\xDA\x65\x73\xAF\x80\xCD"
+			  "\xD2\xB6\xC2\x4A\x76\xC2\x92\x85"
+			  "\xBD\xCF\x62\x98\x58\x14\xE5\xBD",
 		.rlen	= 80,
-        }, {
+	}, {
 		.key    = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x45\x67\x89\xab\xcd\xef"
-                          "\x00\x00\x00\x00",
-                .input  = "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff",
-                .ilen   = 192,
-                .assoc  = "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-                          "\xaa\xaa\xaa\xaa",
-                .alen   = 12,
+		.iv     = "\x00\x00\x45\x67\x89\xab\xcd\xef",
+		.input  = "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.ilen   = 192,
+		.assoc  = "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\x00\x00\x45\x67"
+			  "\x89\xab\xcd\xef",
+		.alen   = 20,
 		.result	= "\xC1\x76\x33\x85\xE2\x9B\x5F\xDE"
 			  "\xDE\x89\x3D\x42\xE7\xC9\x69\x8A"
 			  "\x44\x6D\xC3\x88\x46\x2E\xC2\x01"
@@ -20316,8 +20393,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x00\x21\x00\x01\x01\x02\x02\x01",
 		.ilen	= 72,
 		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
-			  "\x00\x00\x00\x00",
-		.alen	= 12,
+			  "\x00\x00\x00\x00\x49\x56\xED\x7E"
+			  "\x3B\x24\x4C\xFE",
+		.alen	= 20,
 		.result	= "\xFE\xCF\x53\x7E\x72\x9D\x5B\x07"
 			  "\xDC\x30\xDF\x52\x8D\xD2\x2B\x76"
 			  "\x8D\x1B\x98\x73\x66\x96\xA6\xFD"
@@ -20345,8 +20423,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x65\x72\x63\x69\x74\x79\x02\x64"
 			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
 		.ilen	= 64,
-		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
-		.alen	= 8,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
 		.result	= "\xDE\xB2\x2C\xD9\xB0\x7C\x72\xC1"
 			  "\x6E\x3A\x65\xBE\xEB\x8D\xF3\x04"
 			  "\xA5\xA5\x89\x7D\x33\xAE\x53\x0F"
@@ -20374,8 +20453,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
 			  "\x01\x02\x02\x01",
 		.ilen	= 52,
-		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02",
-		.alen	= 8,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02"
+			  "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.alen	= 16,
 		.result	= "\xFF\x42\x5C\x9B\x72\x45\x99\xDF"
 			  "\x7A\x3B\xCD\x51\x01\x94\xE0\x0D"
 			  "\x6A\x78\x10\x7F\x1B\x0B\x1C\xBF"
@@ -20401,8 +20481,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x75\x76\x77\x61\x62\x63\x64\x65"
 			  "\x66\x67\x68\x69\x01\x02\x02\x01",
 		.ilen	= 64,
-		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.result	= "\x46\x88\xDA\xF2\xF9\x73\xA3\x92"
 			  "\x73\x29\x09\xC3\x31\xD5\x6D\x60"
 			  "\xF6\x94\xAB\xAA\x41\x4B\x5E\x7F"
@@ -20430,8 +20511,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x66\x67\x68\x69\x01\x02\x02\x01",
 		.ilen	= 64,
 		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.result	= "\xFB\xA2\xCA\xA4\x85\x3C\xF9\xF0"
 			  "\xF2\x2C\xB1\x0D\x86\xDD\x83\xB0"
 			  "\xFE\xC7\x56\x91\xCF\x1A\x04\xB0"
@@ -20455,8 +20537,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x01\x02\x02\x01",
 		.ilen	= 28,
 		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.result	= "\xFB\xA2\xCA\x84\x5E\x5D\xF9\xF0"
 			  "\xF2\x2C\x3E\x6E\x86\xDD\x83\x1E"
 			  "\x1F\xC6\x57\x92\xCD\x1A\xF9\x13"
@@ -20477,8 +20560,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
 			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
 		.ilen	= 40,
-		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
-		.alen	= 8,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
 		.result	= "\xA5\xB1\xF8\x06\x60\x29\xAE\xA4"
 			  "\x0E\x59\x8B\x81\x22\xDE\x02\x42"
 			  "\x09\x38\xB3\xAB\x33\xF8\x28\xE6"
@@ -20505,8 +20589,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x23\x01\x01\x01",
 		.ilen	= 76,
 		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x01",
-		.alen	= 12,
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
 		.result	= "\x18\xA6\xFD\x42\xF7\x2C\xBF\x4A"
 			  "\xB2\xA2\xEA\x90\x1F\x73\xD8\x14"
 			  "\xE3\xE7\xF2\x43\xD9\x54\x12\xE1"
@@ -20535,8 +20620,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
 		.ilen	= 40,
 		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
-			  "\xDD\x0D\xB9\x9B",
-		.alen	= 12,
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
 		.result	= "\xF2\xD6\x9E\xCD\xBD\x5A\x0D\x5B"
 			  "\x8D\x5E\xF3\x8B\xAD\x4D\xA5\x8D"
 			  "\x1F\x27\x8F\xDE\x98\xEF\x67\x54"
@@ -20563,8 +20649,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x15\x01\x01\x01",
 		.ilen	= 76,
 		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.result	= "\xFB\xA2\xCA\xD1\x2F\xC1\xF9\xF0"
 			  "\x0D\x3C\xEB\xF3\x05\x41\x0D\xB8"
 			  "\x3D\x77\x84\xB6\x07\x32\x3D\x22"
@@ -20597,8 +20684,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
 		.ilen	= 72,
 		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
-			  "\xDD\x0D\xB9\x9B",
-		.alen	= 12,
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
 		.result	= "\xD4\xB7\xED\x86\xA1\x77\x7F\x2E"
 			  "\xA1\x3D\x69\x73\xD3\x24\xC6\x9E"
 			  "\x7B\x43\xF8\x26\xFB\x56\x83\x12"
@@ -20619,8 +20707,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
 		.input	= "\x01\x02\x02\x01",
 		.ilen	= 4,
-		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF",
-		.alen	= 8,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF"
+			  "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.alen	= 16,
 		.result	= "\x43\x7F\x86\x6B\xCB\x3F\x69\x9F"
 			  "\xE9\xB0\x82\x2B\xAC\x96\x1C\x45"
 			  "\x04\xBE\xF2\x70",
@@ -20636,8 +20725,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x62\x65\x00\x01",
 		.ilen	= 20,
 		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x01",
-		.alen	= 12,
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
 		.result	= "\x29\xC9\xFC\x69\xA1\x97\xD0\x38"
 			  "\xCC\xDD\x14\xE2\xDD\xFC\xAA\x05"
 			  "\x43\x33\x21\x64\x41\x25\x03\x52"
@@ -20661,8 +20751,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x01\x02\x02\x01",
 		.ilen	= 52,
 		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF",
-		.alen	= 12,
+			  "\xFF\xFF\xFF\xFF\x33\x30\x21\x69"
+			  "\x67\x65\x74\x6D",
+		.alen	= 20,
 		.result	= "\xF9\x7A\xB2\xAA\x35\x6D\x8E\xDC"
 			  "\xE1\x76\x44\xAC\x8C\x78\xE2\x5D"
 			  "\xD2\x4D\xED\xBB\x29\xEB\xF1\xB6"
@@ -20688,8 +20779,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x01\x02\x02\x01",
 		.ilen	= 52,
 		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.result	= "\xFB\xA2\xCA\xA8\xC6\xC5\xF9\xF0"
 			  "\xF2\x2C\xA5\x4A\x06\x12\x10\xAD"
 			  "\x3F\x6E\x57\x91\xCF\x1A\xCA\x21"
@@ -20712,8 +20804,9 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x71\x72\x73\x74\x01\x02\x02\x01",
 		.ilen	= 32,
 		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
-			  "\x00\x00\x00\x07",
-		.alen	= 12,
+			  "\x00\x00\x00\x07\x48\x55\xEC\x7D"
+			  "\x3A\x23\x4B\xFD",
+		.alen	= 20,
 		.result	= "\x74\x75\x2E\x8A\xEB\x5D\x87\x3C"
 			  "\xD7\xC0\xF4\xAC\xC3\x6C\x4B\xFF"
 			  "\x84\xB7\xD7\xB9\x8F\x0C\xA8\xB6"
@@ -20725,122 +20818,122 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 };
 
 static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
-        { /* Generated using Crypto++ */
+	{ /* Generated using Crypto++ */
 		.key    = zeroed_string,
 		.klen	= 20,
-                .iv     = zeroed_string,
+		.iv     = zeroed_string,
 		.input	= "\x03\x88\xDA\xCE\x60\xB6\xA3\x92"
-                          "\xF3\x28\xC2\xB9\x71\xB2\xFE\x78"
-                          "\x97\xFE\x4C\x23\x37\x42\x01\xE0"
-                          "\x81\x9F\x8D\xC5\xD7\x41\xA0\x1B",
+			  "\xF3\x28\xC2\xB9\x71\xB2\xFE\x78"
+			  "\x97\xFE\x4C\x23\x37\x42\x01\xE0"
+			  "\x81\x9F\x8D\xC5\xD7\x41\xA0\x1B",
 		.ilen	= 32,
-                .assoc  = zeroed_string,
-                .alen   = 8,
-                .result = zeroed_string,
-                .rlen   = 16,
+		.assoc  = zeroed_string,
+		.alen   = 16,
+		.result = zeroed_string,
+		.rlen   = 16,
 
-        },{
+	},{
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x00\x00\x00\x00\x00\x01"
-                          "\x00\x00\x00\x00",
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x01",
 		.input	= "\xC0\x0D\x8B\x42\x0F\x8F\x34\x18"
-                          "\x88\xB1\xC5\xBC\xC5\xB6\xD6\x28"
-                          "\x6A\x9D\xDF\x11\x5E\xFE\x5E\x9D"
-                          "\x2F\x70\x44\x92\xF7\xF2\xE3\xEF",
+			  "\x88\xB1\xC5\xBC\xC5\xB6\xD6\x28"
+			  "\x6A\x9D\xDF\x11\x5E\xFE\x5E\x9D"
+			  "\x2F\x70\x44\x92\xF7\xF2\xE3\xEF",
 		.ilen	= 32,
-                .assoc  = zeroed_string,
-                .alen   = 8,
-                .result = zeroed_string,
-                .rlen   = 16,
-        }, {
+		.assoc  = "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen   = 16,
+		.result = zeroed_string,
+		.rlen   = 16,
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = zeroed_string,
+		.iv     = zeroed_string,
 		.input	= "\x4B\xB1\xB5\xE3\x25\x71\x70\xDE"
-                          "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
-                          "\x0B\x8F\x88\x69\x17\xE6\xB4\x3C"
-                          "\xB1\x68\xFD\x14\x52\x64\x61\xB2",
+			  "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
+			  "\x0B\x8F\x88\x69\x17\xE6\xB4\x3C"
+			  "\xB1\x68\xFD\x14\x52\x64\x61\xB2",
 		.ilen	= 32,
-                .assoc  = zeroed_string,
-                .alen   = 8,
-                .result = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .rlen   = 16,
-        }, {
+		.assoc  = zeroed_string,
+		.alen   = 16,
+		.result = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen   = 16,
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = zeroed_string,
+		.iv     = zeroed_string,
 		.input	= "\x4B\xB1\xB5\xE3\x25\x71\x70\xDE"
-                          "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
-                          "\x90\x92\xB7\xE3\x5F\xA3\x9A\x63"
-                          "\x7E\xD7\x1F\xD8\xD3\x7C\x4B\xF5",
+			  "\x7F\xC9\x9C\xA5\x14\x19\xF2\xAC"
+			  "\x90\x92\xB7\xE3\x5F\xA3\x9A\x63"
+			  "\x7E\xD7\x1F\xD8\xD3\x7C\x4B\xF5",
 		.ilen	= 32,
-                .assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .alen   = 8,
-                .result = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .rlen   = 16,
+		.assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen   = 16,
+		.result = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen   = 16,
 
-        }, {
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x00\x00\x00\x00\x00\x01"
-                          "\x00\x00\x00\x00",
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x01",
 		.input	= "\xC1\x0C\x8A\x43\x0E\x8E\x35\x19"
-                          "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
-                          "\x64\x50\xF9\x32\x13\xFB\x74\x61"
-                          "\xF4\xED\x52\xD3\xC5\x10\x55\x3C",
+			  "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
+			  "\x64\x50\xF9\x32\x13\xFB\x74\x61"
+			  "\xF4\xED\x52\xD3\xC5\x10\x55\x3C",
 		.ilen	= 32,
-                .assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .alen   = 8,
-                .result = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .rlen   = 16,
-        }, {
+		.assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen   = 16,
+		.result = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen   = 16,
+	}, {
 		.key    = "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
 			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x00\x00\x00\x00\x00\x01"
-                          "\x00\x00\x00\x00",
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x01",
 		.input	= "\xC1\x0C\x8A\x43\x0E\x8E\x35\x19"
-                          "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
-                          "\x98\x14\xA1\x42\x37\x80\xFD\x90"
-                          "\x68\x12\x01\xA8\x91\x89\xB9\x83"
-                          "\x5B\x11\x77\x12\x9B\xFF\x24\x89"
-                          "\x94\x5F\x18\x12\xBA\x27\x09\x39"
-                          "\x99\x96\x76\x42\x15\x1C\xCD\xCB"
-                          "\xDC\xD3\xDA\x65\x73\xAF\x80\xCD"
-                          "\xD2\xB6\xC2\x4A\x76\xC2\x92\x85"
-                          "\xBD\xCF\x62\x98\x58\x14\xE5\xBD",
+			  "\x89\xB0\xC4\xBD\xC4\xB7\xD7\x29"
+			  "\x98\x14\xA1\x42\x37\x80\xFD\x90"
+			  "\x68\x12\x01\xA8\x91\x89\xB9\x83"
+			  "\x5B\x11\x77\x12\x9B\xFF\x24\x89"
+			  "\x94\x5F\x18\x12\xBA\x27\x09\x39"
+			  "\x99\x96\x76\x42\x15\x1C\xCD\xCB"
+			  "\xDC\xD3\xDA\x65\x73\xAF\x80\xCD"
+			  "\xD2\xB6\xC2\x4A\x76\xC2\x92\x85"
+			  "\xBD\xCF\x62\x98\x58\x14\xE5\xBD",
 		.ilen	= 80,
-                .assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .alen   = 8,
-                .result = "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01"
-                          "\x01\x01\x01\x01\x01\x01\x01\x01",
-                .rlen   = 64,
-        }, {
+		.assoc  = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen   = 16,
+		.result = "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen   = 64,
+	}, {
 		.key    = "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-                          "\x00\x00\x00\x00",
+			  "\x00\x00\x00\x00",
 		.klen	= 20,
-                .iv     = "\x00\x00\x45\x67\x89\xab\xcd\xef"
-                          "\x00\x00\x00\x00",
+		.iv     = "\x00\x00\x45\x67\x89\xab\xcd\xef",
 		.input	= "\xC1\x76\x33\x85\xE2\x9B\x5F\xDE"
 			  "\xDE\x89\x3D\x42\xE7\xC9\x69\x8A"
 			  "\x44\x6D\xC3\x88\x46\x2E\xC2\x01"
@@ -20868,34 +20961,35 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x37\x08\x1C\xCF\xBA\x5D\x71\x46"
 			  "\x80\x72\xB0\x4C\x82\x0D\x60\x3C",
 		.ilen	= 208,
-                .assoc  = "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-                          "\xaa\xaa\xaa\xaa",
-                .alen   = 12,
-                .result = "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff"
-                          "\xff\xff\xff\xff\xff\xff\xff\xff",
-                .rlen   = 192,
+		.assoc  = "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\x00\x00\x45\x67"
+			  "\x89\xab\xcd\xef",
+		.alen   = 20,
+		.result = "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.rlen   = 192,
 	}, {
 		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
 			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
@@ -20913,8 +21007,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x00\x21\x00\x01\x01\x02\x02\x01",
 		.rlen	= 72,
 		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
-			  "\x00\x00\x00\x00",
-		.alen	= 12,
+			  "\x00\x00\x00\x00\x49\x56\xED\x7E"
+			  "\x3B\x24\x4C\xFE",
+		.alen	= 20,
 		.input	= "\xFE\xCF\x53\x7E\x72\x9D\x5B\x07"
 			  "\xDC\x30\xDF\x52\x8D\xD2\x2B\x76"
 			  "\x8D\x1B\x98\x73\x66\x96\xA6\xFD"
@@ -20942,8 +21037,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x65\x72\x63\x69\x74\x79\x02\x64"
 			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
 		.rlen	= 64,
-		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
-		.alen	= 8,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
 		.input	= "\xDE\xB2\x2C\xD9\xB0\x7C\x72\xC1"
 			  "\x6E\x3A\x65\xBE\xEB\x8D\xF3\x04"
 			  "\xA5\xA5\x89\x7D\x33\xAE\x53\x0F"
@@ -20971,8 +21067,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
 			  "\x01\x02\x02\x01",
 		.rlen	= 52,
-		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02",
-		.alen	= 8,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02"
+			  "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.alen	= 16,
 		.input	= "\xFF\x42\x5C\x9B\x72\x45\x99\xDF"
 			  "\x7A\x3B\xCD\x51\x01\x94\xE0\x0D"
 			  "\x6A\x78\x10\x7F\x1B\x0B\x1C\xBF"
@@ -20998,8 +21095,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x75\x76\x77\x61\x62\x63\x64\x65"
 			  "\x66\x67\x68\x69\x01\x02\x02\x01",
 		.rlen	= 64,
-		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x46\x88\xDA\xF2\xF9\x73\xA3\x92"
 			  "\x73\x29\x09\xC3\x31\xD5\x6D\x60"
 			  "\xF6\x94\xAB\xAA\x41\x4B\x5E\x7F"
@@ -21027,8 +21125,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x66\x67\x68\x69\x01\x02\x02\x01",
 		.rlen	= 64,
 		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.input	= "\xFB\xA2\xCA\xA4\x85\x3C\xF9\xF0"
 			  "\xF2\x2C\xB1\x0D\x86\xDD\x83\xB0"
 			  "\xFE\xC7\x56\x91\xCF\x1A\x04\xB0"
@@ -21052,8 +21151,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x01\x02\x02\x01",
 		.rlen	= 28,
 		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.input	= "\xFB\xA2\xCA\x84\x5E\x5D\xF9\xF0"
 			  "\xF2\x2C\x3E\x6E\x86\xDD\x83\x1E"
 			  "\x1F\xC6\x57\x92\xCD\x1A\xF9\x13"
@@ -21074,8 +21174,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
 			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
 		.rlen	= 40,
-		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
-		.alen	= 8,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
 		.input	= "\xA5\xB1\xF8\x06\x60\x29\xAE\xA4"
 			  "\x0E\x59\x8B\x81\x22\xDE\x02\x42"
 			  "\x09\x38\xB3\xAB\x33\xF8\x28\xE6"
@@ -21102,8 +21203,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x23\x01\x01\x01",
 		.rlen	= 76,
 		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x01",
-		.alen	= 12,
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
 		.input	= "\x18\xA6\xFD\x42\xF7\x2C\xBF\x4A"
 			  "\xB2\xA2\xEA\x90\x1F\x73\xD8\x14"
 			  "\xE3\xE7\xF2\x43\xD9\x54\x12\xE1"
@@ -21132,8 +21234,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
 		.rlen	= 40,
 		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
-			  "\xDD\x0D\xB9\x9B",
-		.alen	= 12,
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
 		.input	= "\xF2\xD6\x9E\xCD\xBD\x5A\x0D\x5B"
 			  "\x8D\x5E\xF3\x8B\xAD\x4D\xA5\x8D"
 			  "\x1F\x27\x8F\xDE\x98\xEF\x67\x54"
@@ -21160,8 +21263,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x15\x01\x01\x01",
 		.rlen	= 76,
 		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.input	= "\xFB\xA2\xCA\xD1\x2F\xC1\xF9\xF0"
 			  "\x0D\x3C\xEB\xF3\x05\x41\x0D\xB8"
 			  "\x3D\x77\x84\xB6\x07\x32\x3D\x22"
@@ -21194,8 +21298,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
 		.rlen	= 72,
 		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
-			  "\xDD\x0D\xB9\x9B",
-		.alen	= 12,
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
 		.input	= "\xD4\xB7\xED\x86\xA1\x77\x7F\x2E"
 			  "\xA1\x3D\x69\x73\xD3\x24\xC6\x9E"
 			  "\x7B\x43\xF8\x26\xFB\x56\x83\x12"
@@ -21216,8 +21321,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
 		.result	= "\x01\x02\x02\x01",
 		.rlen	= 4,
-		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF",
-		.alen	= 8,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF"
+			  "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.alen	= 16,
 		.input	= "\x43\x7F\x86\x6B\xCB\x3F\x69\x9F"
 			  "\xE9\xB0\x82\x2B\xAC\x96\x1C\x45"
 			  "\x04\xBE\xF2\x70",
@@ -21233,8 +21339,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x62\x65\x00\x01",
 		.rlen	= 20,
 		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x01",
-		.alen	= 12,
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
 		.input	= "\x29\xC9\xFC\x69\xA1\x97\xD0\x38"
 			  "\xCC\xDD\x14\xE2\xDD\xFC\xAA\x05"
 			  "\x43\x33\x21\x64\x41\x25\x03\x52"
@@ -21258,8 +21365,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x01\x02\x02\x01",
 		.rlen	= 52,
 		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF",
-		.alen	= 12,
+			  "\xFF\xFF\xFF\xFF\x33\x30\x21\x69"
+			  "\x67\x65\x74\x6D",
+		.alen	= 20,
 		.input	= "\xF9\x7A\xB2\xAA\x35\x6D\x8E\xDC"
 			  "\xE1\x76\x44\xAC\x8C\x78\xE2\x5D"
 			  "\xD2\x4D\xED\xBB\x29\xEB\xF1\xB6"
@@ -21285,8 +21393,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x01\x02\x02\x01",
 		.rlen	= 52,
 		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
-			  "\x10\x10\x10\x10",
-		.alen	= 12,
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
 		.input	= "\xFB\xA2\xCA\xA8\xC6\xC5\xF9\xF0"
 			  "\xF2\x2C\xA5\x4A\x06\x12\x10\xAD"
 			  "\x3F\x6E\x57\x91\xCF\x1A\xCA\x21"
@@ -21309,8 +21418,9 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 			  "\x71\x72\x73\x74\x01\x02\x02\x01",
 		.rlen	= 32,
 		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
-			  "\x00\x00\x00\x07",
-		.alen	= 12,
+			  "\x00\x00\x00\x07\x48\x55\xEC\x7D"
+			  "\x3A\x23\x4B\xFD",
+		.alen	= 20,
 		.input	= "\x74\x75\x2E\x8A\xEB\x5D\x87\x3C"
 			  "\xD7\xC0\xF4\xAC\xC3\x6C\x4B\xFF"
 			  "\x84\xB7\xD7\xB9\x8F\x0C\xA8\xB6"
@@ -21538,10 +21648,7 @@ static struct aead_testvec aes_ccm_enc_tv_template[] = {
 			  "\xba",
 		.rlen	= 33,
 	}, {
-		/*
-		 * This is the same vector as aes_ccm_rfc4309_enc_tv_template[0]
-		 * below but rewritten to use the ccm algorithm directly.
-		 */
+		/* This is taken from FIPS CAVS. */
 		.key	= "\x83\xac\x54\x66\xc2\xeb\xe5\x05"
 			  "\x2e\x01\xd1\xfc\x5d\x82\x66\x2e",
 		.klen	= 16,
@@ -21559,6 +21666,142 @@ static struct aead_testvec aes_ccm_enc_tv_template[] = {
 			  "\xda\x24\xea\xd9\xa1\x39\x98\xfd"
 			  "\xa4\xbe\xd9\xf2\x1a\x6d\x22\xa8",
 		.rlen	= 48,
+	}, {
+		.key	= "\x1e\x2c\x7e\x01\x41\x9a\xef\xc0"
+			  "\x0d\x58\x96\x6e\x5c\xa2\x4b\xd3",
+		.klen	= 16,
+		.iv	= "\x03\x4f\xa3\x19\xd3\x01\x5a\xd8"
+			  "\x30\x60\x15\x56\x00\x00\x00\x00",
+		.assoc	= "\xda\xe6\x28\x9c\x45\x2d\xfd\x63"
+			  "\x5e\xda\x4c\xb6\xe6\xfc\xf9\xb7"
+			  "\x0c\x56\xcb\xe4\xe0\x05\x7a\xe1"
+			  "\x0a\x63\x09\x78\xbc\x2c\x55\xde",
+		.alen	= 32,
+		.input	= "\x87\xa3\x36\xfd\x96\xb3\x93\x78"
+			  "\xa9\x28\x63\xba\x12\xa3\x14\x85"
+			  "\x57\x1e\x06\xc9\x7b\x21\xef\x76"
+			  "\x7f\x38\x7e\x8e\x29\xa4\x3e\x7e",
+		.ilen	= 32,
+		.result	= "\x8a\x1e\x11\xf0\x02\x6b\xe2\x19"
+			  "\xfc\x70\xc4\x6d\x8e\xb7\x99\xab"
+			  "\xc5\x4b\xa2\xac\xd3\xf3\x48\xff"
+			  "\x3b\xb5\xce\x53\xef\xde\xbb\x02"
+			  "\xa9\x86\x15\x6c\x13\xfe\xda\x0a"
+			  "\x22\xb8\x29\x3d\xd8\x39\x9a\x23",
+		.rlen	= 48,
+	}, {
+		.key	= "\xf4\x6b\xc2\x75\x62\xfe\xb4\xe1"
+			  "\xa3\xf0\xff\xdd\x4e\x4b\x12\x75"
+			  "\x53\x14\x73\x66\x8d\x88\xf6\x80",
+		.klen	= 24,
+		.iv	= "\x03\xa0\x20\x35\x26\xf2\x21\x8d"
+			  "\x50\x20\xda\xe2\x00\x00\x00\x00",
+		.assoc	= "\x5b\x9e\x13\x67\x02\x5e\xef\xc1"
+			  "\x6c\xf9\xd7\x1e\x52\x8f\x7a\x47"
+			  "\xe9\xd4\xcf\x20\x14\x6e\xf0\x2d"
+			  "\xd8\x9e\x2b\x56\x10\x23\x56\xe7",
+		.alen	= 32,
+		.result	= "\x36\xea\x7a\x70\x08\xdc\x6a\xbc"
+			  "\xad\x0c\x7a\x63\xf6\x61\xfd\x9b",
+		.rlen	= 16,
+	}, {
+		.key	= "\x56\xdf\x5c\x8f\x26\x3f\x0e\x42"
+			  "\xef\x7a\xd3\xce\xfc\x84\x60\x62"
+			  "\xca\xb4\x40\xaf\x5f\xc9\xc9\x01",
+		.klen	= 24,
+		.iv	= "\x03\xd6\x3c\x8c\x86\x84\xb6\xcd"
+			  "\xef\x09\x2e\x94\x00\x00\x00\x00",
+		.assoc	= "\x02\x65\x78\x3c\xe9\x21\x30\x91"
+			  "\xb1\xb9\xda\x76\x9a\x78\x6d\x95"
+			  "\xf2\x88\x32\xa3\xf2\x50\xcb\x4c"
+			  "\xe3\x00\x73\x69\x84\x69\x87\x79",
+		.alen	= 32,
+		.input	= "\x9f\xd2\x02\x4b\x52\x49\x31\x3c"
+			  "\x43\x69\x3a\x2d\x8e\x70\xad\x7e"
+			  "\xe0\xe5\x46\x09\x80\x89\x13\xb2"
+			  "\x8c\x8b\xd9\x3f\x86\xfb\xb5\x6b",
+		.ilen	= 32,
+		.result	= "\x39\xdf\x7c\x3c\x5a\x29\xb9\x62"
+			  "\x5d\x51\xc2\x16\xd8\xbd\x06\x9f"
+			  "\x9b\x6a\x09\x70\xc1\x51\x83\xc2"
+			  "\x66\x88\x1d\x4f\x9a\xda\xe0\x1e"
+			  "\xc7\x79\x11\x58\xe5\x6b\x20\x40"
+			  "\x7a\xea\x46\x42\x8b\xe4\x6f\xe1",
+		.rlen	= 48,
+	}, {
+		.key	= "\xe0\x8d\x99\x71\x60\xd7\x97\x1a"
+			  "\xbd\x01\x99\xd5\x8a\xdf\x71\x3a"
+			  "\xd3\xdf\x24\x4b\x5e\x3d\x4b\x4e"
+			  "\x30\x7a\xb9\xd8\x53\x0a\x5e\x2b",
+		.klen	= 32,
+		.iv	= "\x03\x1e\x29\x91\xad\x8e\xc1\x53"
+			  "\x0a\xcf\x2d\xbe\x00\x00\x00\x00",
+		.assoc	= "\x19\xb6\x1f\x57\xc4\xf3\xf0\x8b"
+			  "\x78\x2b\x94\x02\x29\x0f\x42\x27"
+			  "\x6b\x75\xcb\x98\x34\x08\x7e\x79"
+			  "\xe4\x3e\x49\x0d\x84\x8b\x22\x87",
+		.alen	= 32,
+		.input	= "\xe1\xd9\xd8\x13\xeb\x3a\x75\x3f"
+			  "\x9d\xbd\x5f\x66\xbe\xdc\xbb\x66"
+			  "\xbf\x17\x99\x62\x4a\x39\x27\x1f"
+			  "\x1d\xdc\x24\xae\x19\x2f\x98\x4c",
+		.ilen	= 32,
+		.result	= "\x19\xb8\x61\x33\x45\x2b\x43\x96"
+			  "\x6f\x51\xd0\x20\x30\x7d\x9b\xc6"
+			  "\x26\x3d\xf8\xc9\x65\x16\xa8\x9f"
+			  "\xf0\x62\x17\x34\xf2\x1e\x8d\x75"
+			  "\x4e\x13\xcc\xc0\xc3\x2a\x54\x2d",
+		.rlen	= 40,
+	}, {
+		.key	= "\x7c\xc8\x18\x3b\x8d\x99\xe0\x7c"
+			  "\x45\x41\xb8\xbd\x5c\xa7\xc2\x32"
+			  "\x8a\xb8\x02\x59\xa4\xfe\xa9\x2c"
+			  "\x09\x75\x9a\x9b\x3c\x9b\x27\x39",
+		.klen	= 32,
+		.iv	= "\x03\xf9\xd9\x4e\x63\xb5\x3d\x9d"
+			  "\x43\xf6\x1e\x50",
+		.assoc	= "\x57\xf5\x6b\x8b\x57\x5c\x3d\x3b"
+			  "\x13\x02\x01\x0c\x83\x4c\x96\x35"
+			  "\x8e\xd6\x39\xcf\x7d\x14\x9b\x94"
+			  "\xb0\x39\x36\xe6\x8f\x57\xe0\x13",
+		.alen	= 32,
+		.input	= "\x3b\x6c\x29\x36\xb6\xef\x07\xa6"
+			  "\x83\x72\x07\x4f\xcf\xfa\x66\x89"
+			  "\x5f\xca\xb1\xba\xd5\x8f\x2c\x27"
+			  "\x30\xdb\x75\x09\x93\xd4\x65\xe4",
+		.ilen	= 32,
+		.result	= "\xb0\x88\x5a\x33\xaa\xe5\xc7\x1d"
+			  "\x85\x23\xc7\xc6\x2f\xf4\x1e\x3d"
+			  "\xcc\x63\x44\x25\x07\x78\x4f\x9e"
+			  "\x96\xb8\x88\xeb\xbc\x48\x1f\x06"
+			  "\x39\xaf\x39\xac\xd8\x4a\x80\x39"
+			  "\x7b\x72\x8a\xf7",
+		.rlen	= 44,
+	}, {
+		.key	= "\xab\xd0\xe9\x33\x07\x26\xe5\x83"
+			  "\x8c\x76\x95\xd4\xb6\xdc\xf3\x46"
+			  "\xf9\x8f\xad\xe3\x02\x13\x83\x77"
+			  "\x3f\xb0\xf1\xa1\xa1\x22\x0f\x2b",
+		.klen	= 32,
+		.iv	= "\x03\x24\xa7\x8b\x07\xcb\xcc\x0e"
+			  "\xe6\x33\xbf\xf5\x00\x00\x00\x00",
+		.assoc	= "\xd4\xdb\x30\x1d\x03\xfe\xfd\x5f"
+			  "\x87\xd4\x8c\xb6\xb6\xf1\x7a\x5d"
+			  "\xab\x90\x65\x8d\x8e\xca\x4d\x4f"
+			  "\x16\x0c\x40\x90\x4b\xc7\x36\x73",
+		.alen	= 32,
+		.input	= "\xf5\xc6\x7d\x48\xc1\xb7\xe6\x92"
+			  "\x97\x5a\xca\xc4\xa9\x6d\xf9\x3d"
+			  "\x6c\xde\xbc\xf1\x90\xea\x6a\xb2"
+			  "\x35\x86\x36\xaf\x5c\xfe\x4b\x3a",
+		.ilen	= 32,
+		.result	= "\x83\x6f\x40\x87\x72\xcf\xc1\x13"
+			  "\xef\xbb\x80\x21\x04\x6c\x58\x09"
+			  "\x07\x1b\xfc\xdf\xc0\x3f\x5b\xc7"
+			  "\xe0\x79\xa8\x6e\x71\x7c\x3f\xcf"
+			  "\x5c\xda\xb2\x33\xe5\x13\xe2\x0d"
+			  "\x74\xd1\xef\xb5\x0f\x3a\xb5\xf8",
+		.rlen	= 48,
 	}
 };
 
@@ -21688,186 +21931,13 @@ static struct aead_testvec aes_ccm_dec_tv_template[] = {
 			  "\x8e\x5e\x67\x01\xc9\x17\x87\x65"
 			  "\x98\x09\xd6\x7d\xbe\xdd\x18",
 		.rlen	= 23,
-	},
-};
-
-/*
- * rfc4309 refers to section 8 of rfc3610 for test vectors, but they all
- * use a 13-byte nonce, we only support an 11-byte nonce. Similarly, all of
- * Special Publication 800-38C's test vectors also use nonce lengths our
- * implementation doesn't support. The following are taken from fips cavs
- * fax files on hand at Red Hat.
- *
- * nb: actual key lengths are (klen - 3), the last 3 bytes are actually
- * part of the nonce which combine w/the iv, but need to be input this way.
- */
-static struct aead_testvec aes_ccm_rfc4309_enc_tv_template[] = {
-	{
-		.key	= "\x83\xac\x54\x66\xc2\xeb\xe5\x05"
-			  "\x2e\x01\xd1\xfc\x5d\x82\x66\x2e"
-			  "\x96\xac\x59",
-		.klen	= 19,
-		.iv	= "\x30\x07\xa1\xe2\xa2\xc7\x55\x24",
-		.alen	= 0,
-		.input	= "\x19\xc8\x81\xf6\xe9\x86\xff\x93"
-			  "\x0b\x78\x67\xe5\xbb\xb7\xfc\x6e"
-			  "\x83\x77\xb3\xa6\x0c\x8c\x9f\x9c"
-			  "\x35\x2e\xad\xe0\x62\xf9\x91\xa1",
-		.ilen	= 32,
-		.result	= "\xab\x6f\xe1\x69\x1d\x19\x99\xa8"
-			  "\x92\xa0\xc4\x6f\x7e\xe2\x8b\xb1"
-			  "\x70\xbb\x8c\xa6\x4c\x6e\x97\x8a"
-			  "\x57\x2b\xbe\x5d\x98\xa6\xb1\x32"
-			  "\xda\x24\xea\xd9\xa1\x39\x98\xfd"
-			  "\xa4\xbe\xd9\xf2\x1a\x6d\x22\xa8",
-		.rlen	= 48,
-	}, {
-		.key	= "\x1e\x2c\x7e\x01\x41\x9a\xef\xc0"
-			  "\x0d\x58\x96\x6e\x5c\xa2\x4b\xd3"
-			  "\x4f\xa3\x19",
-		.klen	= 19,
-		.iv	= "\xd3\x01\x5a\xd8\x30\x60\x15\x56",
-		.assoc	= "\xda\xe6\x28\x9c\x45\x2d\xfd\x63"
-			  "\x5e\xda\x4c\xb6\xe6\xfc\xf9\xb7"
-			  "\x0c\x56\xcb\xe4\xe0\x05\x7a\xe1"
-			  "\x0a\x63\x09\x78\xbc\x2c\x55\xde",
-		.alen	= 32,
-		.input	= "\x87\xa3\x36\xfd\x96\xb3\x93\x78"
-			  "\xa9\x28\x63\xba\x12\xa3\x14\x85"
-			  "\x57\x1e\x06\xc9\x7b\x21\xef\x76"
-			  "\x7f\x38\x7e\x8e\x29\xa4\x3e\x7e",
-		.ilen	= 32,
-		.result	= "\x8a\x1e\x11\xf0\x02\x6b\xe2\x19"
-			  "\xfc\x70\xc4\x6d\x8e\xb7\x99\xab"
-			  "\xc5\x4b\xa2\xac\xd3\xf3\x48\xff"
-			  "\x3b\xb5\xce\x53\xef\xde\xbb\x02"
-			  "\xa9\x86\x15\x6c\x13\xfe\xda\x0a"
-			  "\x22\xb8\x29\x3d\xd8\x39\x9a\x23",
-		.rlen	= 48,
-	}, {
-		.key	= "\xf4\x6b\xc2\x75\x62\xfe\xb4\xe1"
-			  "\xa3\xf0\xff\xdd\x4e\x4b\x12\x75"
-			  "\x53\x14\x73\x66\x8d\x88\xf6\x80"
-			  "\xa0\x20\x35",
-		.klen	= 27,
-		.iv	= "\x26\xf2\x21\x8d\x50\x20\xda\xe2",
-		.assoc	= "\x5b\x9e\x13\x67\x02\x5e\xef\xc1"
-			  "\x6c\xf9\xd7\x1e\x52\x8f\x7a\x47"
-			  "\xe9\xd4\xcf\x20\x14\x6e\xf0\x2d"
-			  "\xd8\x9e\x2b\x56\x10\x23\x56\xe7",
-		.alen	= 32,
-		.ilen	= 0,
-		.result	= "\x36\xea\x7a\x70\x08\xdc\x6a\xbc"
-			  "\xad\x0c\x7a\x63\xf6\x61\xfd\x9b",
-		.rlen	= 16,
-	}, {
-		.key	= "\x56\xdf\x5c\x8f\x26\x3f\x0e\x42"
-			  "\xef\x7a\xd3\xce\xfc\x84\x60\x62"
-			  "\xca\xb4\x40\xaf\x5f\xc9\xc9\x01"
-			  "\xd6\x3c\x8c",
-		.klen	= 27,
-		.iv	= "\x86\x84\xb6\xcd\xef\x09\x2e\x94",
-		.assoc	= "\x02\x65\x78\x3c\xe9\x21\x30\x91"
-			  "\xb1\xb9\xda\x76\x9a\x78\x6d\x95"
-			  "\xf2\x88\x32\xa3\xf2\x50\xcb\x4c"
-			  "\xe3\x00\x73\x69\x84\x69\x87\x79",
-		.alen	= 32,
-		.input	= "\x9f\xd2\x02\x4b\x52\x49\x31\x3c"
-			  "\x43\x69\x3a\x2d\x8e\x70\xad\x7e"
-			  "\xe0\xe5\x46\x09\x80\x89\x13\xb2"
-			  "\x8c\x8b\xd9\x3f\x86\xfb\xb5\x6b",
-		.ilen	= 32,
-		.result	= "\x39\xdf\x7c\x3c\x5a\x29\xb9\x62"
-			  "\x5d\x51\xc2\x16\xd8\xbd\x06\x9f"
-			  "\x9b\x6a\x09\x70\xc1\x51\x83\xc2"
-			  "\x66\x88\x1d\x4f\x9a\xda\xe0\x1e"
-			  "\xc7\x79\x11\x58\xe5\x6b\x20\x40"
-			  "\x7a\xea\x46\x42\x8b\xe4\x6f\xe1",
-		.rlen	= 48,
-	}, {
-		.key	= "\xe0\x8d\x99\x71\x60\xd7\x97\x1a"
-			  "\xbd\x01\x99\xd5\x8a\xdf\x71\x3a"
-			  "\xd3\xdf\x24\x4b\x5e\x3d\x4b\x4e"
-			  "\x30\x7a\xb9\xd8\x53\x0a\x5e\x2b"
-			  "\x1e\x29\x91",
-		.klen	= 35,
-		.iv	= "\xad\x8e\xc1\x53\x0a\xcf\x2d\xbe",
-		.assoc	= "\x19\xb6\x1f\x57\xc4\xf3\xf0\x8b"
-			  "\x78\x2b\x94\x02\x29\x0f\x42\x27"
-			  "\x6b\x75\xcb\x98\x34\x08\x7e\x79"
-			  "\xe4\x3e\x49\x0d\x84\x8b\x22\x87",
-		.alen	= 32,
-		.input	= "\xe1\xd9\xd8\x13\xeb\x3a\x75\x3f"
-			  "\x9d\xbd\x5f\x66\xbe\xdc\xbb\x66"
-			  "\xbf\x17\x99\x62\x4a\x39\x27\x1f"
-			  "\x1d\xdc\x24\xae\x19\x2f\x98\x4c",
-		.ilen	= 32,
-		.result	= "\x19\xb8\x61\x33\x45\x2b\x43\x96"
-			  "\x6f\x51\xd0\x20\x30\x7d\x9b\xc6"
-			  "\x26\x3d\xf8\xc9\x65\x16\xa8\x9f"
-			  "\xf0\x62\x17\x34\xf2\x1e\x8d\x75"
-			  "\x4e\x13\xcc\xc0\xc3\x2a\x54\x2d",
-		.rlen	= 40,
-	}, {
-		.key	= "\x7c\xc8\x18\x3b\x8d\x99\xe0\x7c"
-			  "\x45\x41\xb8\xbd\x5c\xa7\xc2\x32"
-			  "\x8a\xb8\x02\x59\xa4\xfe\xa9\x2c"
-			  "\x09\x75\x9a\x9b\x3c\x9b\x27\x39"
-			  "\xf9\xd9\x4e",
-		.klen	= 35,
-		.iv	= "\x63\xb5\x3d\x9d\x43\xf6\x1e\x50",
-		.assoc	= "\x57\xf5\x6b\x8b\x57\x5c\x3d\x3b"
-			  "\x13\x02\x01\x0c\x83\x4c\x96\x35"
-			  "\x8e\xd6\x39\xcf\x7d\x14\x9b\x94"
-			  "\xb0\x39\x36\xe6\x8f\x57\xe0\x13",
-		.alen	= 32,
-		.input	= "\x3b\x6c\x29\x36\xb6\xef\x07\xa6"
-			  "\x83\x72\x07\x4f\xcf\xfa\x66\x89"
-			  "\x5f\xca\xb1\xba\xd5\x8f\x2c\x27"
-			  "\x30\xdb\x75\x09\x93\xd4\x65\xe4",
-		.ilen	= 32,
-		.result	= "\xb0\x88\x5a\x33\xaa\xe5\xc7\x1d"
-			  "\x85\x23\xc7\xc6\x2f\xf4\x1e\x3d"
-			  "\xcc\x63\x44\x25\x07\x78\x4f\x9e"
-			  "\x96\xb8\x88\xeb\xbc\x48\x1f\x06"
-			  "\x39\xaf\x39\xac\xd8\x4a\x80\x39"
-			  "\x7b\x72\x8a\xf7",
-		.rlen	= 44,
 	}, {
-		.key	= "\xab\xd0\xe9\x33\x07\x26\xe5\x83"
-			  "\x8c\x76\x95\xd4\xb6\xdc\xf3\x46"
-			  "\xf9\x8f\xad\xe3\x02\x13\x83\x77"
-			  "\x3f\xb0\xf1\xa1\xa1\x22\x0f\x2b"
-			  "\x24\xa7\x8b",
-		.klen	= 35,
-		.iv	= "\x07\xcb\xcc\x0e\xe6\x33\xbf\xf5",
-		.assoc	= "\xd4\xdb\x30\x1d\x03\xfe\xfd\x5f"
-			  "\x87\xd4\x8c\xb6\xb6\xf1\x7a\x5d"
-			  "\xab\x90\x65\x8d\x8e\xca\x4d\x4f"
-			  "\x16\x0c\x40\x90\x4b\xc7\x36\x73",
-		.alen	= 32,
-		.input	= "\xf5\xc6\x7d\x48\xc1\xb7\xe6\x92"
-			  "\x97\x5a\xca\xc4\xa9\x6d\xf9\x3d"
-			  "\x6c\xde\xbc\xf1\x90\xea\x6a\xb2"
-			  "\x35\x86\x36\xaf\x5c\xfe\x4b\x3a",
-		.ilen	= 32,
-		.result	= "\x83\x6f\x40\x87\x72\xcf\xc1\x13"
-			  "\xef\xbb\x80\x21\x04\x6c\x58\x09"
-			  "\x07\x1b\xfc\xdf\xc0\x3f\x5b\xc7"
-			  "\xe0\x79\xa8\x6e\x71\x7c\x3f\xcf"
-			  "\x5c\xda\xb2\x33\xe5\x13\xe2\x0d"
-			  "\x74\xd1\xef\xb5\x0f\x3a\xb5\xf8",
-		.rlen	= 48,
-	},
-};
-
-static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
-	{
+		/* This is taken from FIPS CAVS. */
 		.key	= "\xab\x2f\x8a\x74\xb7\x1c\xd2\xb1"
-			  "\xff\x80\x2e\x48\x7d\x82\xf8\xb9"
-			  "\xc6\xfb\x7d",
-		.klen	= 19,
-		.iv	= "\x80\x0d\x13\xab\xd8\xa6\xb2\xd8",
+			  "\xff\x80\x2e\x48\x7d\x82\xf8\xb9",
+		.klen	= 16,
+		.iv	= "\x03\xc6\xfb\x7d\x80\x0d\x13\xab"
+			  "\xd8\xa6\xb2\xd8\x00\x00\x00\x00",
 		.alen	= 0,
 		.input	= "\xd5\xe8\x93\x9f\xc7\x89\x2e\x2b",
 		.ilen	= 8,
@@ -21876,10 +21946,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 		.novrfy	= 1,
 	}, {
 		.key	= "\xab\x2f\x8a\x74\xb7\x1c\xd2\xb1"
-			  "\xff\x80\x2e\x48\x7d\x82\xf8\xb9"
-			  "\xaf\x94\x87",
-		.klen	= 19,
-		.iv	= "\x78\x35\x82\x81\x7f\x88\x94\x68",
+			  "\xff\x80\x2e\x48\x7d\x82\xf8\xb9",
+		.klen	= 16,
+		.iv	= "\x03\xaf\x94\x87\x78\x35\x82\x81"
+			  "\x7f\x88\x94\x68\x00\x00\x00\x00",
 		.alen	= 0,
 		.input	= "\x41\x3c\xb8\x87\x73\xcb\xf3\xf3",
 		.ilen	= 8,
@@ -21887,10 +21957,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 		.rlen	= 0,
 	}, {
 		.key	= "\x61\x0e\x8c\xae\xe3\x23\xb6\x38"
-			  "\x76\x1c\xf6\x3a\x67\xa3\x9c\xd8"
-			  "\xc6\xfb\x7d",
-		.klen	= 19,
-		.iv	= "\x80\x0d\x13\xab\xd8\xa6\xb2\xd8",
+			  "\x76\x1c\xf6\x3a\x67\xa3\x9c\xd8",
+		.klen	= 16,
+		.iv	= "\x03\xc6\xfb\x7d\x80\x0d\x13\xab"
+			  "\xd8\xa6\xb2\xd8\x00\x00\x00\x00",
 		.assoc	= "\xf3\x94\x87\x78\x35\x82\x81\x7f"
 			  "\x88\x94\x68\xb1\x78\x6b\x2b\xd6"
 			  "\x04\x1f\x4e\xed\x78\xd5\x33\x66"
@@ -21911,10 +21981,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 		.novrfy	= 1,
 	}, {
 		.key	= "\x61\x0e\x8c\xae\xe3\x23\xb6\x38"
-			  "\x76\x1c\xf6\x3a\x67\xa3\x9c\xd8"
-			  "\x05\xe0\xc9",
-		.klen	= 19,
-		.iv	= "\x0f\xed\x34\xea\x97\xd4\x3b\xdf",
+			  "\x76\x1c\xf6\x3a\x67\xa3\x9c\xd8",
+		.klen	= 16,
+		.iv	= "\x03\x05\xe0\xc9\x0f\xed\x34\xea"
+			  "\x97\xd4\x3b\xdf\x00\x00\x00\x00",
 		.assoc	= "\x49\x5c\x50\x1f\x1d\x94\xcc\x81"
 			  "\xba\xb7\xb6\x03\xaf\xa5\xc1\xa1"
 			  "\xd8\x5c\x42\x68\xe0\x6c\xda\x89"
@@ -21935,10 +22005,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 	}, {
 		.key	= "\x39\xbb\xa7\xbe\x59\x97\x9e\x73"
 			  "\xa2\xbc\x6b\x98\xd7\x75\x7f\xe3"
-			  "\xa4\x48\x93\x39\x26\x71\x4a\xc6"
-			  "\xee\x49\x83",
-		.klen	= 27,
-		.iv	= "\xe9\xa9\xff\xe9\x57\xba\xfd\x9e",
+			  "\xa4\x48\x93\x39\x26\x71\x4a\xc6",
+		.klen	= 24,
+		.iv	= "\x03\xee\x49\x83\xe9\xa9\xff\xe9"
+			  "\x57\xba\xfd\x9e\x00\x00\x00\x00",
 		.assoc	= "\x44\xa6\x2c\x05\xe9\xe1\x43\xb1"
 			  "\x58\x7c\xf2\x5c\x6d\x39\x0a\x64"
 			  "\xa4\xf0\x13\x05\xd1\x77\x99\x67"
@@ -21951,10 +22021,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 	}, {
 		.key	= "\x58\x5d\xa0\x96\x65\x1a\x04\xd7"
 			  "\x96\xe5\xc5\x68\xaa\x95\x35\xe0"
-			  "\x29\xa0\xba\x9e\x48\x78\xd1\xba"
-			  "\xee\x49\x83",
-		.klen	= 27,
-		.iv	= "\xe9\xa9\xff\xe9\x57\xba\xfd\x9e",
+			  "\x29\xa0\xba\x9e\x48\x78\xd1\xba",
+		.klen	= 24,
+		.iv	= "\x03\xee\x49\x83\xe9\xa9\xff\xe9"
+			  "\x57\xba\xfd\x9e\x00\x00\x00\x00",
 		.assoc	= "\x44\xa6\x2c\x05\xe9\xe1\x43\xb1"
 			  "\x58\x7c\xf2\x5c\x6d\x39\x0a\x64"
 			  "\xa4\xf0\x13\x05\xd1\x77\x99\x67"
@@ -21974,10 +22044,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 	}, {
 		.key	= "\x58\x5d\xa0\x96\x65\x1a\x04\xd7"
 			  "\x96\xe5\xc5\x68\xaa\x95\x35\xe0"
-			  "\x29\xa0\xba\x9e\x48\x78\xd1\xba"
-			  "\xd1\xfc\x57",
-		.klen	= 27,
-		.iv	= "\x9c\xfe\xb8\x9c\xad\x71\xaa\x1f",
+			  "\x29\xa0\xba\x9e\x48\x78\xd1\xba",
+		.klen	= 24,
+		.iv	= "\x03\xd1\xfc\x57\x9c\xfe\xb8\x9c"
+			  "\xad\x71\xaa\x1f\x00\x00\x00\x00",
 		.assoc	= "\x86\x67\xa5\xa9\x14\x5f\x0d\xc6"
 			  "\xff\x14\xc7\x44\xbf\x6c\x3a\xc3"
 			  "\xff\xb6\x81\xbd\xe2\xd5\x06\xc7"
@@ -22000,10 +22070,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 		.key	= "\xa4\x4b\x54\x29\x0a\xb8\x6d\x01"
 			  "\x5b\x80\x2a\xcf\x25\xc4\xb7\x5c"
 			  "\x20\x2c\xad\x30\xc2\x2b\x41\xfb"
-			  "\x0e\x85\xbc\x33\xad\x0f\x2b\xff"
-			  "\xee\x49\x83",
-		.klen	= 35,
-		.iv	= "\xe9\xa9\xff\xe9\x57\xba\xfd\x9e",
+			  "\x0e\x85\xbc\x33\xad\x0f\x2b\xff",
+		.klen	= 32,
+		.iv	= "\x03\xee\x49\x83\xe9\xa9\xff\xe9"
+			  "\x57\xba\xfd\x9e\x00\x00\x00\x00",
 		.alen	= 0,
 		.input	= "\x1f\xb8\x8f\xa3\xdd\x54\x00\xf2",
 		.ilen	= 8,
@@ -22013,10 +22083,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 		.key	= "\x39\xbb\xa7\xbe\x59\x97\x9e\x73"
 			  "\xa2\xbc\x6b\x98\xd7\x75\x7f\xe3"
 			  "\xa4\x48\x93\x39\x26\x71\x4a\xc6"
-			  "\xae\x8f\x11\x4c\xc2\x9c\x4a\xbb"
-			  "\x85\x34\x66",
-		.klen	= 35,
-		.iv	= "\x42\xc8\x92\x0f\x36\x58\xe0\x6b",
+			  "\xae\x8f\x11\x4c\xc2\x9c\x4a\xbb",
+		.klen	= 32,
+		.iv	= "\x03\x85\x34\x66\x42\xc8\x92\x0f"
+			  "\x36\x58\xe0\x6b\x00\x00\x00\x00",
 		.alen	= 0,
 		.input	= "\x48\x01\x5e\x02\x24\x04\x66\x47"
 			  "\xa1\xea\x6f\xaf\xe8\xfc\xfb\xdd"
@@ -22035,10 +22105,10 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 		.key	= "\x58\x5d\xa0\x96\x65\x1a\x04\xd7"
 			  "\x96\xe5\xc5\x68\xaa\x95\x35\xe0"
 			  "\x29\xa0\xba\x9e\x48\x78\xd1\xba"
-			  "\x0d\x1a\x53\x3b\xb5\xe3\xf8\x8b"
-			  "\xcf\x76\x3f",
-		.klen	= 35,
-		.iv	= "\xd9\x95\x75\x8f\x44\x89\x40\x7b",
+			  "\x0d\x1a\x53\x3b\xb5\xe3\xf8\x8b",
+		.klen	= 32,
+		.iv	= "\x03\xcf\x76\x3f\xd9\x95\x75\x8f"
+			  "\x44\x89\x40\x7b\x00\x00\x00\x00",
 		.assoc	= "\x8f\x86\x6c\x4d\x1d\xc5\x39\x88"
 			  "\xc8\xf3\x5c\x52\x10\x63\x6f\x2b"
 			  "\x8a\x2a\xc5\x6f\x30\x23\x58\x7b"
@@ -22060,6 +22130,1240 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 };
 
 /*
+ * rfc4309 refers to section 8 of rfc3610 for test vectors, but they all
+ * use a 13-byte nonce, we only support an 11-byte nonce.  Worse,
+ * they use AD lengths which are not valid ESP header lengths.
+ *
+ * These vectors are copied/generated from the ones for rfc4106 with
+ * the key truncated by one byte..
+ */
+static struct aead_testvec aes_ccm_rfc4309_enc_tv_template[] = {
+	{ /* Generated using Crypto++ */
+		.key	= zeroed_string,
+		.klen	= 19,
+		.iv	= zeroed_string,
+		.input	= zeroed_string,
+		.ilen	= 16,
+		.assoc	= zeroed_string,
+		.alen	= 16,
+		.result	= "\x2E\x9A\xCA\x6B\xDA\x54\xFC\x6F"
+			  "\x12\x50\xE8\xDE\x81\x3C\x63\x08"
+			  "\x1A\x22\xBA\x75\xEE\xD4\xD5\xB5"
+			  "\x27\x50\x01\xAC\x03\x33\x39\xFB",
+		.rlen	= 32,
+	},{
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input	= zeroed_string,
+		.ilen	= 16,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 16,
+		.result	= "\xCF\xB9\x99\x17\xC8\x86\x0E\x7F"
+			  "\x7E\x76\xF8\xE6\xF8\xCC\x1F\x17"
+			  "\x6A\xE0\x53\x9F\x4B\x73\x7E\xDA"
+			  "\x08\x09\x4E\xC4\x1E\xAD\xC6\xB0",
+		.rlen	= 32,
+
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= zeroed_string,
+		.input	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen	= 16,
+		.assoc	= zeroed_string,
+		.alen	= 16,
+		.result	= "\x33\xDE\x73\xBC\xA6\xCE\x4E\xA6"
+			  "\x61\xF4\xF5\x41\x03\x4A\xE3\x86"
+			  "\xA1\xE2\xC2\x42\x2B\x81\x70\x40"
+			  "\xFD\x7F\x76\xD1\x03\x07\xBB\x0C",
+		.rlen	= 32,
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= zeroed_string,
+		.input	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen	= 16,
+		.assoc	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
+		.result	= "\x33\xDE\x73\xBC\xA6\xCE\x4E\xA6"
+			  "\x61\xF4\xF5\x41\x03\x4A\xE3\x86"
+			  "\x5B\xC0\x73\xE0\x2B\x73\x68\xC9"
+			  "\x2D\x8C\x58\xC2\x90\x3D\xB0\x3E",
+		.rlen	= 32,
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen	= 16,
+		.assoc	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 16,
+		.result	= "\xCE\xB8\x98\x16\xC9\x87\x0F\x7E"
+			  "\x7F\x77\xF9\xE7\xF9\xCD\x1E\x16"
+			  "\x43\x8E\x76\x57\x3B\xB4\x05\xE8"
+			  "\xA9\x9B\xBF\x25\xE0\x4F\xC0\xED",
+		.rlen	= 32,
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.ilen	= 64,
+		.assoc	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 16,
+		.result	= "\xCE\xB8\x98\x16\xC9\x87\x0F\x7E"
+			  "\x7F\x77\xF9\xE7\xF9\xCD\x1E\x16"
+			  "\x9C\xA4\x97\x83\x3F\x01\xA5\xF4"
+			  "\x43\x09\xE7\xB8\xE9\xD1\xD7\x02"
+			  "\x9B\xAB\x39\x18\xEB\x94\x34\x36"
+			  "\xE6\xC5\xC8\x9B\x00\x81\x9E\x49"
+			  "\x1D\x78\xE1\x48\xE3\xE9\xEA\x8E"
+			  "\x3A\x2B\x67\x5D\x35\x6A\x0F\xDB"
+			  "\x02\x73\xDD\xE7\x30\x4A\x30\x54"
+			  "\x1A\x9D\x09\xCA\xC8\x1C\x32\x5F",
+		.rlen	= 80,
+	}, {
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x45\x67\x89\xab\xcd\xef",
+		.input	= "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.ilen	= 192,
+		.assoc	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\x00\x00\x45\x67"
+			  "\x89\xab\xcd\xef",
+		.alen	= 20,
+		.result	= "\x64\x17\xDC\x24\x9D\x92\xBA\x5E"
+			  "\x7C\x64\x6D\x33\x46\x77\xAC\xB1"
+			  "\x5C\x9E\xE2\xC7\x27\x11\x3E\x95"
+			  "\x7D\xBE\x28\xC8\xC1\xCA\x5E\x8C"
+			  "\xB4\xE2\xDE\x9F\x53\x59\x26\xDB"
+			  "\x0C\xD4\xE4\x07\x9A\xE6\x3E\x01"
+			  "\x58\x0D\x3E\x3D\xD5\x21\xEB\x04"
+			  "\x06\x9D\x5F\xB9\x02\x49\x1A\x2B"
+			  "\xBA\xF0\x4E\x3B\x85\x50\x5B\x09"
+			  "\xFE\xEC\xFC\x54\xEC\x0C\xE2\x79"
+			  "\x8A\x2F\x5F\xD7\x05\x5D\xF1\x6D"
+			  "\x22\xEB\xD1\x09\x80\x3F\x5A\x70"
+			  "\xB2\xB9\xD3\x63\x99\xC2\x4D\x1B"
+			  "\x36\x12\x00\x89\xAA\x5D\x55\xDA"
+			  "\x1D\x5B\xD8\x3C\x5F\x09\xD2\xE6"
+			  "\x39\x41\x5C\xF0\xBE\x26\x4E\x5F"
+			  "\x2B\x50\x44\x52\xC2\x10\x7D\x38"
+			  "\x82\x64\x83\x0C\xAE\x49\xD0\xE5"
+			  "\x4F\xE5\x66\x4C\x58\x7A\xEE\x43"
+			  "\x3B\x51\xFE\xBA\x24\x8A\xFE\xDC"
+			  "\x19\x6D\x60\x66\x61\xF9\x9A\x3F"
+			  "\x75\xFC\x38\x53\x5B\xB5\xCD\x52"
+			  "\x4F\xE5\xE4\xC9\xFE\x10\xCB\x98"
+			  "\xF0\x06\x5B\x07\xAB\xBB\xF4\x0E"
+			  "\x2D\xC2\xDD\x5D\xDD\x22\x9A\xCC"
+			  "\x39\xAB\x63\xA5\x3D\x9C\x51\x8A",
+		.rlen	= 208,
+	}, { /* From draft-mcgrew-gcm-test-01 */
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x2E\x44\x3B",
+		.klen	= 19,
+		.iv	= "\x49\x56\xED\x7E\x3B\x24\x4C\xFE",
+		.input	= "\x45\x00\x00\x48\x69\x9A\x00\x00"
+			  "\x80\x11\x4D\xB7\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x9B\xF1\x56"
+			  "\x38\xD3\x01\x00\x00\x01\x00\x00"
+			  "\x00\x00\x00\x00\x04\x5F\x73\x69"
+			  "\x70\x04\x5F\x75\x64\x70\x03\x73"
+			  "\x69\x70\x09\x63\x79\x62\x65\x72"
+			  "\x63\x69\x74\x79\x02\x64\x6B\x00"
+			  "\x00\x21\x00\x01\x01\x02\x02\x01",
+		.ilen	= 72,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x00\x49\x56\xED\x7E"
+			  "\x3B\x24\x4C\xFE",
+		.alen	= 20,
+		.result	= "\x89\xBA\x3E\xEF\xE6\xD6\xCF\xDB"
+			  "\x83\x60\xF5\xBA\x3A\x56\x79\xE6"
+			  "\x7E\x0C\x53\xCF\x9E\x87\xE0\x4E"
+			  "\x1A\x26\x01\x24\xC7\x2E\x3D\xBF"
+			  "\x29\x2C\x91\xC1\xB8\xA8\xCF\xE0"
+			  "\x39\xF8\x53\x6D\x31\x22\x2B\xBF"
+			  "\x98\x81\xFC\x34\xEE\x85\x36\xCD"
+			  "\x26\xDB\x6C\x7A\x0C\x77\x8A\x35"
+			  "\x18\x85\x54\xB2\xBC\xDD\x3F\x43"
+			  "\x61\x06\x8A\xDF\x86\x3F\xB4\xAC"
+			  "\x97\xDC\xBD\xFD\x92\x10\xC5\xFF",
+		.rlen	= 88,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xCA\xFE\xBA",
+		.klen	= 19,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.input	= "\x45\x00\x00\x3E\x69\x8F\x00\x00"
+			  "\x80\x11\x4D\xCC\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x98\x00\x35"
+			  "\x00\x2A\x23\x43\xB2\xD0\x01\x00"
+			  "\x00\x01\x00\x00\x00\x00\x00\x00"
+			  "\x03\x73\x69\x70\x09\x63\x79\x62"
+			  "\x65\x72\x63\x69\x74\x79\x02\x64"
+			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
+		.ilen	= 64,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
+		.result	= "\x4B\xC2\x70\x60\x64\xD2\xF3\xC8"
+			  "\xE5\x26\x8A\xDE\xB8\x7E\x7D\x16"
+			  "\x56\xC7\xD2\x88\xBA\x8D\x58\xAF"
+			  "\xF5\x71\xB6\x37\x84\xA7\xB1\x99"
+			  "\x51\x5C\x0D\xA0\x27\xDE\xE7\x2D"
+			  "\xEF\x25\x88\x1F\x1D\x77\x11\xFF"
+			  "\xDB\xED\xEE\x56\x16\xC5\x5C\x9B"
+			  "\x00\x62\x1F\x68\x4E\x7C\xA0\x97"
+			  "\x10\x72\x7E\x53\x13\x3B\x68\xE4"
+			  "\x30\x99\x91\x79\x09\xEA\xFF\x6A",
+		.rlen	= 80,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x11\x22\x33",
+		.klen	= 35,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.input	= "\x45\x00\x00\x30\x69\xA6\x40\x00"
+			  "\x80\x06\x26\x90\xC0\xA8\x01\x02"
+			  "\x93\x89\x15\x5E\x0A\x9E\x00\x8B"
+			  "\x2D\xC5\x7E\xE0\x00\x00\x00\x00"
+			  "\x70\x02\x40\x00\x20\xBF\x00\x00"
+			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02"
+			  "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.alen	= 16,
+		.result	= "\xD6\x31\x0D\x2B\x3D\x6F\xBD\x2F"
+			  "\x58\x41\x7E\xFF\x9A\x9E\x09\xB4"
+			  "\x1A\xF7\xF6\x42\x31\xCD\xBF\xAD"
+			  "\x27\x0E\x2C\xF2\xDB\x10\xDF\x55"
+			  "\x8F\x0D\xD7\xAC\x23\xBD\x42\x10"
+			  "\xD0\xB2\xAF\xD8\x37\xAC\x6B\x0B"
+			  "\x11\xD4\x0B\x12\xEC\xB4\xB1\x92"
+			  "\x23\xA6\x10\xB0\x26\xD6\xD9\x26"
+			  "\x5A\x48\x6A\x3E",
+		.rlen	= 68,
+	}, {
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x45\x00\x00\x3C\x99\xC5\x00\x00"
+			  "\x80\x01\xCB\x7A\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x07\x5C"
+			  "\x02\x00\x44\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.ilen	= 64,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
+		.result	= "\x6B\x9A\xCA\x57\x43\x91\xFC\x6F"
+			  "\x92\x51\x23\xA4\xC1\x5B\xF0\x10"
+			  "\xF3\x13\xF4\xF8\xA1\x9A\xB4\xDC"
+			  "\x89\xC8\xF8\x42\x62\x95\xB7\xCB"
+			  "\xB8\xF5\x0F\x1B\x2E\x94\xA2\xA7"
+			  "\xBF\xFB\x8A\x92\x13\x63\xD1\x3C"
+			  "\x08\xF5\xE8\xA6\xAA\xF6\x34\xF9"
+			  "\x42\x05\xAF\xB3\xE7\x9A\xFC\xEE"
+			  "\x36\x25\xC1\x10\x12\x1C\xCA\x82"
+			  "\xEA\xE6\x63\x5A\x57\x28\xA9\x9A",
+		.rlen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x3C\x99\xC3\x00\x00"
+			  "\x80\x01\xCB\x7C\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x08\x5C"
+			  "\x02\x00\x43\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.ilen	= 64,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.result	= "\x6A\x6B\x45\x2B\x7C\x67\x52\xF6"
+			  "\x10\x60\x40\x62\x6B\x4F\x97\x8E"
+			  "\x0B\xB2\x22\x97\xCB\x21\xE0\x90"
+			  "\xA2\xE7\xD1\x41\x30\xE4\x4B\x1B"
+			  "\x79\x01\x58\x50\x01\x06\xE1\xE0"
+			  "\x2C\x83\x79\xD3\xDE\x46\x97\x1A"
+			  "\x30\xB8\xE5\xDF\xD7\x12\x56\x75"
+			  "\xD0\x95\xB7\xB8\x91\x42\xF7\xFD"
+			  "\x97\x57\xCA\xC1\x20\xD0\x86\xB9"
+			  "\x66\x9D\xB4\x2B\x96\x22\xAC\x67",
+		.rlen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x1C\x42\xA2\x00\x00"
+			  "\x80\x01\x44\x1F\x40\x67\x93\xB6"
+			  "\xE0\x00\x00\x02\x0A\x00\xF5\xFF"
+			  "\x01\x02\x02\x01",
+		.ilen	= 28,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.result	= "\x6A\x6B\x45\x0B\xA7\x06\x52\xF6"
+			  "\x10\x60\xCF\x01\x6B\x4F\x97\x20"
+			  "\xEA\xB3\x23\x94\xC9\x21\x1D\x33"
+			  "\xA1\xE5\x90\x40\x05\x37\x45\x70"
+			  "\xB5\xD6\x09\x0A\x23\x73\x33\xF9"
+			  "\x08\xB4\x22\xE4",
+		.rlen	= 44,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\xCA\xFE\xBA",
+		.klen	= 27,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.input	= "\x45\x00\x00\x28\xA4\xAD\x40\x00"
+			  "\x40\x06\x78\x80\x0A\x01\x03\x8F"
+			  "\x0A\x01\x06\x12\x80\x23\x06\xB8"
+			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
+			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
+		.ilen	= 40,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
+		.result	= "\x05\x22\x15\xD1\x52\x56\x85\x04"
+			  "\xA8\x5C\x5D\x6D\x7E\x6E\xF5\xFA"
+			  "\xEA\x16\x37\x50\xF3\xDF\x84\x3B"
+			  "\x2F\x32\x18\x57\x34\x2A\x8C\x23"
+			  "\x67\xDF\x6D\x35\x7B\x54\x0D\xFB"
+			  "\x34\xA5\x9F\x6C\x48\x30\x1E\x22"
+			  "\xFE\xB1\x22\x17\x17\x8A\xB9\x5B",
+		.rlen	= 56,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8",
+		.klen	= 19,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.input	= "\x45\x00\x00\x49\x33\xBA\x00\x00"
+			  "\x7F\x11\x91\x06\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xDD\x7B\x80\x03\x02\xD5"
+			  "\x00\x00\x4E\x20\x00\x1E\x8C\x18"
+			  "\xD7\x5B\x81\xDC\x91\xBA\xA0\x47"
+			  "\x6B\x91\xB9\x24\xB2\x80\x38\x9D"
+			  "\x92\xC9\x63\xBA\xC0\x46\xEC\x95"
+			  "\x9B\x62\x66\xC0\x47\x22\xB1\x49"
+			  "\x23\x01\x01\x01",
+		.ilen	= 76,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
+		.result	= "\x92\xD0\x53\x79\x33\x38\xD5\xF3"
+			  "\x7D\xE4\x7A\x8E\x86\x03\xC9\x90"
+			  "\x96\x35\xAB\x9C\xFB\xE8\xA3\x76"
+			  "\xE9\xE9\xE2\xD1\x2E\x11\x0E\x00"
+			  "\xFA\xCE\xB5\x9E\x02\xA7\x7B\xEA"
+			  "\x71\x9A\x58\xFB\xA5\x8A\xE1\xB7"
+			  "\x9C\x39\x9D\xE3\xB5\x6E\x69\xE6"
+			  "\x63\xC9\xDB\x05\x69\x51\x12\xAD"
+			  "\x3E\x00\x32\x73\x86\xF2\xEE\xF5"
+			  "\x0F\xE8\x81\x7E\x84\xD3\xC0\x0D"
+			  "\x76\xD6\x55\xC6\xB4\xC2\x34\xC7"
+			  "\x12\x25\x0B\xF9",
+		.rlen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C",
+		.klen	= 35,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.input	= "\x45\x08\x00\x28\x73\x2C\x00\x00"
+			  "\x40\x06\xE9\xF9\x0A\x01\x06\x12"
+			  "\x0A\x01\x03\x8F\x06\xB8\x80\x23"
+			  "\xDD\x6B\xAF\xBE\xCB\x71\x26\x02"
+			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
+		.ilen	= 40,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
+		.result	= "\xCC\x74\xB7\xD3\xB0\x38\x50\x42"
+			  "\x2C\x64\x87\x46\x1E\x34\x10\x05"
+			  "\x29\x6B\xBB\x36\xE9\x69\xAD\x92"
+			  "\x82\xA1\x10\x6A\xEB\x0F\xDC\x7D"
+			  "\x08\xBA\xF3\x91\xCA\xAA\x61\xDA"
+			  "\x62\xF4\x14\x61\x5C\x9D\xB5\xA7"
+			  "\xEE\xD7\xB9\x7E\x87\x99\x9B\x7D",
+		.rlen	= 56,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x49\x33\x3E\x00\x00"
+			  "\x7F\x11\x91\x82\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xCB\x45\x80\x03\x02\x5B"
+			  "\x00\x00\x01\xE0\x00\x1E\x8C\x18"
+			  "\xD6\x57\x59\xD5\x22\x84\xA0\x35"
+			  "\x2C\x71\x47\x5C\x88\x80\x39\x1C"
+			  "\x76\x4D\x6E\x5E\xE0\x49\x6B\x32"
+			  "\x5A\xE2\x70\xC0\x38\x99\x49\x39"
+			  "\x15\x01\x01\x01",
+		.ilen	= 76,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.result	= "\x6A\x6B\x45\x5E\xD6\x9A\x52\xF6"
+			  "\xEF\x70\x1A\x9C\xE8\xD3\x19\x86"
+			  "\xC8\x02\xF0\xB0\x03\x09\xD9\x02"
+			  "\xA0\xD2\x59\x04\xD1\x85\x2A\x24"
+			  "\x1C\x67\x3E\xD8\x68\x72\x06\x94"
+			  "\x97\xBA\x4F\x76\x8D\xB0\x44\x5B"
+			  "\x69\xBF\xD5\xE2\x3D\xF1\x0B\x0C"
+			  "\xC0\xBF\xB1\x8F\x70\x09\x9E\xCE"
+			  "\xA5\xF2\x55\x58\x84\xFA\xF9\xB5"
+			  "\x23\xF4\x84\x40\x74\x14\x8A\x6B"
+			  "\xDB\xD7\x67\xED\xA4\x93\xF3\x47"
+			  "\xCC\xF7\x46\x6F",
+		.rlen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C",
+		.klen	= 35,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.input	= "\x63\x69\x73\x63\x6F\x01\x72\x75"
+			  "\x6C\x65\x73\x01\x74\x68\x65\x01"
+			  "\x6E\x65\x74\x77\x65\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x01\x74\x68\x65"
+			  "\x74\x65\x63\x68\x6E\x6F\x6C\x6F"
+			  "\x67\x69\x65\x73\x01\x74\x68\x61"
+			  "\x74\x77\x69\x6C\x6C\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x74\x6F\x6D\x6F"
+			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
+		.ilen	= 72,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
+		.result	= "\xEA\x15\xC4\x98\xAC\x15\x22\x37"
+			  "\x00\x07\x1D\xBE\x60\x5D\x73\x16"
+			  "\x4D\x0F\xCC\xCE\x8A\xD0\x49\xD4"
+			  "\x39\xA3\xD1\xB1\x21\x0A\x92\x1A"
+			  "\x2C\xCF\x8F\x9D\xC9\x91\x0D\xB4"
+			  "\x15\xFC\xBC\xA5\xC5\xBF\x54\xE5"
+			  "\x1C\xC7\x32\x41\x07\x7B\x2C\xB6"
+			  "\x5C\x23\x7C\x93\xEA\xEF\x23\x1C"
+			  "\x73\xF4\xE7\x12\x84\x4C\x37\x0A"
+			  "\x4A\x8F\x06\x37\x48\xF9\xF9\x05"
+			  "\x55\x13\x40\xC3\xD5\x55\x3A\x3D",
+		.rlen	= 88,
+	}, {
+		.key	= "\x7D\x77\x3D\x00\xC1\x44\xC5\x25"
+			  "\xAC\x61\x9D\x18\xC8\x4A\x3F\x47"
+			  "\xD9\x66\x42",
+		.klen	= 19,
+		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.input	= "\x01\x02\x02\x01",
+		.ilen	= 4,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF"
+			  "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.alen	= 16,
+		.result	= "\x4C\x72\x63\x30\x2F\xE6\x56\xDD"
+			  "\xD0\xD8\x60\x9D\x8B\xEF\x85\x90"
+			  "\xF7\x61\x24\x62",
+		.rlen	= 20,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8",
+		.klen	= 19,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.input	= "\x74\x6F\x01\x62\x65\x01\x6F\x72"
+			  "\x01\x6E\x6F\x74\x01\x74\x6F\x01"
+			  "\x62\x65\x00\x01",
+		.ilen	= 20,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
+		.result	= "\xA3\xBF\x52\x52\x65\x83\xBA\x81"
+			  "\x03\x9B\x84\xFC\x44\x8C\xBB\x81"
+			  "\x36\xE1\x78\xBB\xA5\x49\x3A\xD0"
+			  "\xF0\x6B\x21\xAF\x98\xC0\x34\xDC"
+			  "\x17\x17\x65\xAD",
+		.rlen	= 36,
+	}, {
+		.key	= "\x6C\x65\x67\x61\x6C\x69\x7A\x65"
+			  "\x6D\x61\x72\x69\x6A\x75\x61\x6E"
+			  "\x61\x61\x6E\x64\x64\x6F\x69\x74"
+			  "\x62\x65\x66\x6F\x72\x65\x69\x61"
+			  "\x74\x75\x72",
+		.klen	= 35,
+		.iv	= "\x33\x30\x21\x69\x67\x65\x74\x6D",
+		.input	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
+			  "\xFF\xFF\xFF\xFF\x33\x30\x21\x69"
+			  "\x67\x65\x74\x6D",
+		.alen	= 20,
+		.result	= "\x96\xFD\x86\xF8\xD1\x98\xFF\x10"
+			  "\xAB\x8C\xDA\x8A\x5A\x08\x38\x1A"
+			  "\x48\x59\x80\x18\x1A\x18\x1A\x04"
+			  "\xC9\x0D\xE3\xE7\x0E\xA4\x0B\x75"
+			  "\x92\x9C\x52\x5C\x0B\xFB\xF8\xAF"
+			  "\x16\xC3\x35\xA8\xE7\xCE\x84\x04"
+			  "\xEB\x40\x6B\x7A\x8E\x75\xBB\x42"
+			  "\xE0\x63\x4B\x21\x44\xA2\x2B\x2B"
+			  "\x39\xDB\xC8\xDC",
+		.rlen	= 68,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.result	= "\x6A\x6B\x45\x27\x3F\x9E\x52\xF6"
+			  "\x10\x60\x54\x25\xEB\x80\x04\x93"
+			  "\xCA\x1B\x23\x97\xCB\x21\x2E\x01"
+			  "\xA2\xE7\x95\x41\x30\xE4\x4B\x1B"
+			  "\x79\x01\x58\x50\x01\x06\xE1\xE0"
+			  "\x2C\x83\x79\xD3\xDE\x46\x97\x1A"
+			  "\x44\xCC\x90\xBF\x00\x94\x94\x92"
+			  "\x20\x17\x0C\x1B\x55\xDE\x7E\x68"
+			  "\xF4\x95\x5D\x4F",
+		.rlen	= 68,
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x22\x43\x3C",
+		.klen	= 19,
+		.iv	= "\x48\x55\xEC\x7D\x3A\x23\x4B\xFD",
+		.input	= "\x08\x00\xC6\xCD\x02\x00\x07\x00"
+			  "\x61\x62\x63\x64\x65\x66\x67\x68"
+			  "\x69\x6A\x6B\x6C\x6D\x6E\x6F\x70"
+			  "\x71\x72\x73\x74\x01\x02\x02\x01",
+		.ilen	= 32,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x07\x48\x55\xEC\x7D"
+			  "\x3A\x23\x4B\xFD",
+		.alen	= 20,
+		.result	= "\x67\xE9\x28\xB3\x1C\xA4\x6D\x02"
+			  "\xF0\xB5\x37\xB6\x6B\x2F\xF5\x4F"
+			  "\xF8\xA3\x4C\x53\xB8\x12\x09\xBF"
+			  "\x58\x7D\xCF\x29\xA3\x41\x68\x6B"
+			  "\xCE\xE8\x79\x85\x3C\xB0\x3A\x8F"
+			  "\x16\xB0\xA1\x26\xC9\xBC\xBC\xA6",
+		.rlen	= 48,
+	}
+};
+
+static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[]	= {
+	{ /* Generated using Crypto++ */
+		.key	= zeroed_string,
+		.klen	= 19,
+		.iv	= zeroed_string,
+		.result	= zeroed_string,
+		.rlen	= 16,
+		.assoc	= zeroed_string,
+		.alen	= 16,
+		.input	= "\x2E\x9A\xCA\x6B\xDA\x54\xFC\x6F"
+			  "\x12\x50\xE8\xDE\x81\x3C\x63\x08"
+			  "\x1A\x22\xBA\x75\xEE\xD4\xD5\xB5"
+			  "\x27\x50\x01\xAC\x03\x33\x39\xFB",
+		.ilen	= 32,
+	},{
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.result	= zeroed_string,
+		.rlen	= 16,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 16,
+		.input	= "\xCF\xB9\x99\x17\xC8\x86\x0E\x7F"
+			  "\x7E\x76\xF8\xE6\xF8\xCC\x1F\x17"
+			  "\x6A\xE0\x53\x9F\x4B\x73\x7E\xDA"
+			  "\x08\x09\x4E\xC4\x1E\xAD\xC6\xB0",
+		.ilen	= 32,
+
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= zeroed_string,
+		.result	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen	= 16,
+		.assoc	= zeroed_string,
+		.alen	= 16,
+		.input	= "\x33\xDE\x73\xBC\xA6\xCE\x4E\xA6"
+			  "\x61\xF4\xF5\x41\x03\x4A\xE3\x86"
+			  "\xA1\xE2\xC2\x42\x2B\x81\x70\x40"
+			  "\xFD\x7F\x76\xD1\x03\x07\xBB\x0C",
+		.ilen	= 32,
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= zeroed_string,
+		.result	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen	= 16,
+		.assoc	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
+		.input	= "\x33\xDE\x73\xBC\xA6\xCE\x4E\xA6"
+			  "\x61\xF4\xF5\x41\x03\x4A\xE3\x86"
+			  "\x5B\xC0\x73\xE0\x2B\x73\x68\xC9"
+			  "\x2D\x8C\x58\xC2\x90\x3D\xB0\x3E",
+		.ilen	= 32,
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.result	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen	= 16,
+		.assoc	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 16,
+		.input	= "\xCE\xB8\x98\x16\xC9\x87\x0F\x7E"
+			  "\x7F\x77\xF9\xE7\xF9\xCD\x1E\x16"
+			  "\x43\x8E\x76\x57\x3B\xB4\x05\xE8"
+			  "\xA9\x9B\xBF\x25\xE0\x4F\xC0\xED",
+		.ilen	= 32,
+	}, {
+		.key	= "\xfe\xff\xe9\x92\x86\x65\x73\x1c"
+			  "\x6d\x6a\x8f\x94\x67\x30\x83\x08"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.result	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.rlen	= 64,
+		.assoc	= "\x01\x01\x01\x01\x01\x01\x01\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 16,
+		.input	= "\xCE\xB8\x98\x16\xC9\x87\x0F\x7E"
+			  "\x7F\x77\xF9\xE7\xF9\xCD\x1E\x16"
+			  "\x9C\xA4\x97\x83\x3F\x01\xA5\xF4"
+			  "\x43\x09\xE7\xB8\xE9\xD1\xD7\x02"
+			  "\x9B\xAB\x39\x18\xEB\x94\x34\x36"
+			  "\xE6\xC5\xC8\x9B\x00\x81\x9E\x49"
+			  "\x1D\x78\xE1\x48\xE3\xE9\xEA\x8E"
+			  "\x3A\x2B\x67\x5D\x35\x6A\x0F\xDB"
+			  "\x02\x73\xDD\xE7\x30\x4A\x30\x54"
+			  "\x1A\x9D\x09\xCA\xC8\x1C\x32\x5F",
+		.ilen	= 80,
+	}, {
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x45\x67\x89\xab\xcd\xef",
+		.result	= "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff"
+			  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.rlen	= 192,
+		.assoc	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\x00\x00\x45\x67"
+			  "\x89\xab\xcd\xef",
+		.alen	= 20,
+		.input	= "\x64\x17\xDC\x24\x9D\x92\xBA\x5E"
+			  "\x7C\x64\x6D\x33\x46\x77\xAC\xB1"
+			  "\x5C\x9E\xE2\xC7\x27\x11\x3E\x95"
+			  "\x7D\xBE\x28\xC8\xC1\xCA\x5E\x8C"
+			  "\xB4\xE2\xDE\x9F\x53\x59\x26\xDB"
+			  "\x0C\xD4\xE4\x07\x9A\xE6\x3E\x01"
+			  "\x58\x0D\x3E\x3D\xD5\x21\xEB\x04"
+			  "\x06\x9D\x5F\xB9\x02\x49\x1A\x2B"
+			  "\xBA\xF0\x4E\x3B\x85\x50\x5B\x09"
+			  "\xFE\xEC\xFC\x54\xEC\x0C\xE2\x79"
+			  "\x8A\x2F\x5F\xD7\x05\x5D\xF1\x6D"
+			  "\x22\xEB\xD1\x09\x80\x3F\x5A\x70"
+			  "\xB2\xB9\xD3\x63\x99\xC2\x4D\x1B"
+			  "\x36\x12\x00\x89\xAA\x5D\x55\xDA"
+			  "\x1D\x5B\xD8\x3C\x5F\x09\xD2\xE6"
+			  "\x39\x41\x5C\xF0\xBE\x26\x4E\x5F"
+			  "\x2B\x50\x44\x52\xC2\x10\x7D\x38"
+			  "\x82\x64\x83\x0C\xAE\x49\xD0\xE5"
+			  "\x4F\xE5\x66\x4C\x58\x7A\xEE\x43"
+			  "\x3B\x51\xFE\xBA\x24\x8A\xFE\xDC"
+			  "\x19\x6D\x60\x66\x61\xF9\x9A\x3F"
+			  "\x75\xFC\x38\x53\x5B\xB5\xCD\x52"
+			  "\x4F\xE5\xE4\xC9\xFE\x10\xCB\x98"
+			  "\xF0\x06\x5B\x07\xAB\xBB\xF4\x0E"
+			  "\x2D\xC2\xDD\x5D\xDD\x22\x9A\xCC"
+			  "\x39\xAB\x63\xA5\x3D\x9C\x51\x8A",
+		.ilen	= 208,
+	}, { /* From draft-mcgrew-gcm-test-01 */
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x2E\x44\x3B",
+		.klen	= 19,
+		.iv	= "\x49\x56\xED\x7E\x3B\x24\x4C\xFE",
+		.result	= "\x45\x00\x00\x48\x69\x9A\x00\x00"
+			  "\x80\x11\x4D\xB7\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x9B\xF1\x56"
+			  "\x38\xD3\x01\x00\x00\x01\x00\x00"
+			  "\x00\x00\x00\x00\x04\x5F\x73\x69"
+			  "\x70\x04\x5F\x75\x64\x70\x03\x73"
+			  "\x69\x70\x09\x63\x79\x62\x65\x72"
+			  "\x63\x69\x74\x79\x02\x64\x6B\x00"
+			  "\x00\x21\x00\x01\x01\x02\x02\x01",
+		.rlen	= 72,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x00\x49\x56\xED\x7E"
+			  "\x3B\x24\x4C\xFE",
+		.alen	= 20,
+		.input	= "\x89\xBA\x3E\xEF\xE6\xD6\xCF\xDB"
+			  "\x83\x60\xF5\xBA\x3A\x56\x79\xE6"
+			  "\x7E\x0C\x53\xCF\x9E\x87\xE0\x4E"
+			  "\x1A\x26\x01\x24\xC7\x2E\x3D\xBF"
+			  "\x29\x2C\x91\xC1\xB8\xA8\xCF\xE0"
+			  "\x39\xF8\x53\x6D\x31\x22\x2B\xBF"
+			  "\x98\x81\xFC\x34\xEE\x85\x36\xCD"
+			  "\x26\xDB\x6C\x7A\x0C\x77\x8A\x35"
+			  "\x18\x85\x54\xB2\xBC\xDD\x3F\x43"
+			  "\x61\x06\x8A\xDF\x86\x3F\xB4\xAC"
+			  "\x97\xDC\xBD\xFD\x92\x10\xC5\xFF",
+		.ilen	= 88,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xCA\xFE\xBA",
+		.klen	= 19,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.result	= "\x45\x00\x00\x3E\x69\x8F\x00\x00"
+			  "\x80\x11\x4D\xCC\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x98\x00\x35"
+			  "\x00\x2A\x23\x43\xB2\xD0\x01\x00"
+			  "\x00\x01\x00\x00\x00\x00\x00\x00"
+			  "\x03\x73\x69\x70\x09\x63\x79\x62"
+			  "\x65\x72\x63\x69\x74\x79\x02\x64"
+			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
+		.rlen	= 64,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
+		.input	= "\x4B\xC2\x70\x60\x64\xD2\xF3\xC8"
+			  "\xE5\x26\x8A\xDE\xB8\x7E\x7D\x16"
+			  "\x56\xC7\xD2\x88\xBA\x8D\x58\xAF"
+			  "\xF5\x71\xB6\x37\x84\xA7\xB1\x99"
+			  "\x51\x5C\x0D\xA0\x27\xDE\xE7\x2D"
+			  "\xEF\x25\x88\x1F\x1D\x77\x11\xFF"
+			  "\xDB\xED\xEE\x56\x16\xC5\x5C\x9B"
+			  "\x00\x62\x1F\x68\x4E\x7C\xA0\x97"
+			  "\x10\x72\x7E\x53\x13\x3B\x68\xE4"
+			  "\x30\x99\x91\x79\x09\xEA\xFF\x6A",
+		.ilen	= 80,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x11\x22\x33",
+		.klen	= 35,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.result	= "\x45\x00\x00\x30\x69\xA6\x40\x00"
+			  "\x80\x06\x26\x90\xC0\xA8\x01\x02"
+			  "\x93\x89\x15\x5E\x0A\x9E\x00\x8B"
+			  "\x2D\xC5\x7E\xE0\x00\x00\x00\x00"
+			  "\x70\x02\x40\x00\x20\xBF\x00\x00"
+			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02"
+			  "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.alen	= 16,
+		.input	= "\xD6\x31\x0D\x2B\x3D\x6F\xBD\x2F"
+			  "\x58\x41\x7E\xFF\x9A\x9E\x09\xB4"
+			  "\x1A\xF7\xF6\x42\x31\xCD\xBF\xAD"
+			  "\x27\x0E\x2C\xF2\xDB\x10\xDF\x55"
+			  "\x8F\x0D\xD7\xAC\x23\xBD\x42\x10"
+			  "\xD0\xB2\xAF\xD8\x37\xAC\x6B\x0B"
+			  "\x11\xD4\x0B\x12\xEC\xB4\xB1\x92"
+			  "\x23\xA6\x10\xB0\x26\xD6\xD9\x26"
+			  "\x5A\x48\x6A\x3E",
+		.ilen	= 68,
+	}, {
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00",
+		.klen	= 19,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.result	= "\x45\x00\x00\x3C\x99\xC5\x00\x00"
+			  "\x80\x01\xCB\x7A\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x07\x5C"
+			  "\x02\x00\x44\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.rlen	= 64,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
+		.input	= "\x6B\x9A\xCA\x57\x43\x91\xFC\x6F"
+			  "\x92\x51\x23\xA4\xC1\x5B\xF0\x10"
+			  "\xF3\x13\xF4\xF8\xA1\x9A\xB4\xDC"
+			  "\x89\xC8\xF8\x42\x62\x95\xB7\xCB"
+			  "\xB8\xF5\x0F\x1B\x2E\x94\xA2\xA7"
+			  "\xBF\xFB\x8A\x92\x13\x63\xD1\x3C"
+			  "\x08\xF5\xE8\xA6\xAA\xF6\x34\xF9"
+			  "\x42\x05\xAF\xB3\xE7\x9A\xFC\xEE"
+			  "\x36\x25\xC1\x10\x12\x1C\xCA\x82"
+			  "\xEA\xE6\x63\x5A\x57\x28\xA9\x9A",
+		.ilen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x3C\x99\xC3\x00\x00"
+			  "\x80\x01\xCB\x7C\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x08\x5C"
+			  "\x02\x00\x43\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.rlen	= 64,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.input	= "\x6A\x6B\x45\x2B\x7C\x67\x52\xF6"
+			  "\x10\x60\x40\x62\x6B\x4F\x97\x8E"
+			  "\x0B\xB2\x22\x97\xCB\x21\xE0\x90"
+			  "\xA2\xE7\xD1\x41\x30\xE4\x4B\x1B"
+			  "\x79\x01\x58\x50\x01\x06\xE1\xE0"
+			  "\x2C\x83\x79\xD3\xDE\x46\x97\x1A"
+			  "\x30\xB8\xE5\xDF\xD7\x12\x56\x75"
+			  "\xD0\x95\xB7\xB8\x91\x42\xF7\xFD"
+			  "\x97\x57\xCA\xC1\x20\xD0\x86\xB9"
+			  "\x66\x9D\xB4\x2B\x96\x22\xAC\x67",
+		.ilen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x1C\x42\xA2\x00\x00"
+			  "\x80\x01\x44\x1F\x40\x67\x93\xB6"
+			  "\xE0\x00\x00\x02\x0A\x00\xF5\xFF"
+			  "\x01\x02\x02\x01",
+		.rlen	= 28,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.input	= "\x6A\x6B\x45\x0B\xA7\x06\x52\xF6"
+			  "\x10\x60\xCF\x01\x6B\x4F\x97\x20"
+			  "\xEA\xB3\x23\x94\xC9\x21\x1D\x33"
+			  "\xA1\xE5\x90\x40\x05\x37\x45\x70"
+			  "\xB5\xD6\x09\x0A\x23\x73\x33\xF9"
+			  "\x08\xB4\x22\xE4",
+		.ilen	= 44,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\xCA\xFE\xBA",
+		.klen	= 27,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.result	= "\x45\x00\x00\x28\xA4\xAD\x40\x00"
+			  "\x40\x06\x78\x80\x0A\x01\x03\x8F"
+			  "\x0A\x01\x06\x12\x80\x23\x06\xB8"
+			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
+			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
+		.rlen	= 40,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A"
+			  "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.alen	= 16,
+		.input	= "\x05\x22\x15\xD1\x52\x56\x85\x04"
+			  "\xA8\x5C\x5D\x6D\x7E\x6E\xF5\xFA"
+			  "\xEA\x16\x37\x50\xF3\xDF\x84\x3B"
+			  "\x2F\x32\x18\x57\x34\x2A\x8C\x23"
+			  "\x67\xDF\x6D\x35\x7B\x54\x0D\xFB"
+			  "\x34\xA5\x9F\x6C\x48\x30\x1E\x22"
+			  "\xFE\xB1\x22\x17\x17\x8A\xB9\x5B",
+		.ilen	= 56,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8",
+		.klen	= 19,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.result	= "\x45\x00\x00\x49\x33\xBA\x00\x00"
+			  "\x7F\x11\x91\x06\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xDD\x7B\x80\x03\x02\xD5"
+			  "\x00\x00\x4E\x20\x00\x1E\x8C\x18"
+			  "\xD7\x5B\x81\xDC\x91\xBA\xA0\x47"
+			  "\x6B\x91\xB9\x24\xB2\x80\x38\x9D"
+			  "\x92\xC9\x63\xBA\xC0\x46\xEC\x95"
+			  "\x9B\x62\x66\xC0\x47\x22\xB1\x49"
+			  "\x23\x01\x01\x01",
+		.rlen	= 76,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
+		.input	= "\x92\xD0\x53\x79\x33\x38\xD5\xF3"
+			  "\x7D\xE4\x7A\x8E\x86\x03\xC9\x90"
+			  "\x96\x35\xAB\x9C\xFB\xE8\xA3\x76"
+			  "\xE9\xE9\xE2\xD1\x2E\x11\x0E\x00"
+			  "\xFA\xCE\xB5\x9E\x02\xA7\x7B\xEA"
+			  "\x71\x9A\x58\xFB\xA5\x8A\xE1\xB7"
+			  "\x9C\x39\x9D\xE3\xB5\x6E\x69\xE6"
+			  "\x63\xC9\xDB\x05\x69\x51\x12\xAD"
+			  "\x3E\x00\x32\x73\x86\xF2\xEE\xF5"
+			  "\x0F\xE8\x81\x7E\x84\xD3\xC0\x0D"
+			  "\x76\xD6\x55\xC6\xB4\xC2\x34\xC7"
+			  "\x12\x25\x0B\xF9",
+		.ilen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C",
+		.klen	= 35,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.result	= "\x45\x08\x00\x28\x73\x2C\x00\x00"
+			  "\x40\x06\xE9\xF9\x0A\x01\x06\x12"
+			  "\x0A\x01\x03\x8F\x06\xB8\x80\x23"
+			  "\xDD\x6B\xAF\xBE\xCB\x71\x26\x02"
+			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
+		.rlen	= 40,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
+		.input	= "\xCC\x74\xB7\xD3\xB0\x38\x50\x42"
+			  "\x2C\x64\x87\x46\x1E\x34\x10\x05"
+			  "\x29\x6B\xBB\x36\xE9\x69\xAD\x92"
+			  "\x82\xA1\x10\x6A\xEB\x0F\xDC\x7D"
+			  "\x08\xBA\xF3\x91\xCA\xAA\x61\xDA"
+			  "\x62\xF4\x14\x61\x5C\x9D\xB5\xA7"
+			  "\xEE\xD7\xB9\x7E\x87\x99\x9B\x7D",
+		.ilen	= 56,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x49\x33\x3E\x00\x00"
+			  "\x7F\x11\x91\x82\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xCB\x45\x80\x03\x02\x5B"
+			  "\x00\x00\x01\xE0\x00\x1E\x8C\x18"
+			  "\xD6\x57\x59\xD5\x22\x84\xA0\x35"
+			  "\x2C\x71\x47\x5C\x88\x80\x39\x1C"
+			  "\x76\x4D\x6E\x5E\xE0\x49\x6B\x32"
+			  "\x5A\xE2\x70\xC0\x38\x99\x49\x39"
+			  "\x15\x01\x01\x01",
+		.rlen	= 76,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.input	= "\x6A\x6B\x45\x5E\xD6\x9A\x52\xF6"
+			  "\xEF\x70\x1A\x9C\xE8\xD3\x19\x86"
+			  "\xC8\x02\xF0\xB0\x03\x09\xD9\x02"
+			  "\xA0\xD2\x59\x04\xD1\x85\x2A\x24"
+			  "\x1C\x67\x3E\xD8\x68\x72\x06\x94"
+			  "\x97\xBA\x4F\x76\x8D\xB0\x44\x5B"
+			  "\x69\xBF\xD5\xE2\x3D\xF1\x0B\x0C"
+			  "\xC0\xBF\xB1\x8F\x70\x09\x9E\xCE"
+			  "\xA5\xF2\x55\x58\x84\xFA\xF9\xB5"
+			  "\x23\xF4\x84\x40\x74\x14\x8A\x6B"
+			  "\xDB\xD7\x67\xED\xA4\x93\xF3\x47"
+			  "\xCC\xF7\x46\x6F",
+		.ilen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C",
+		.klen	= 35,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.result	= "\x63\x69\x73\x63\x6F\x01\x72\x75"
+			  "\x6C\x65\x73\x01\x74\x68\x65\x01"
+			  "\x6E\x65\x74\x77\x65\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x01\x74\x68\x65"
+			  "\x74\x65\x63\x68\x6E\x6F\x6C\x6F"
+			  "\x67\x69\x65\x73\x01\x74\x68\x61"
+			  "\x74\x77\x69\x6C\x6C\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x74\x6F\x6D\x6F"
+			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
+		.rlen	= 72,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B\x61\x6E\x64\x01"
+			  "\x69\x76\x65\x63",
+		.alen	= 20,
+		.input	= "\xEA\x15\xC4\x98\xAC\x15\x22\x37"
+			  "\x00\x07\x1D\xBE\x60\x5D\x73\x16"
+			  "\x4D\x0F\xCC\xCE\x8A\xD0\x49\xD4"
+			  "\x39\xA3\xD1\xB1\x21\x0A\x92\x1A"
+			  "\x2C\xCF\x8F\x9D\xC9\x91\x0D\xB4"
+			  "\x15\xFC\xBC\xA5\xC5\xBF\x54\xE5"
+			  "\x1C\xC7\x32\x41\x07\x7B\x2C\xB6"
+			  "\x5C\x23\x7C\x93\xEA\xEF\x23\x1C"
+			  "\x73\xF4\xE7\x12\x84\x4C\x37\x0A"
+			  "\x4A\x8F\x06\x37\x48\xF9\xF9\x05"
+			  "\x55\x13\x40\xC3\xD5\x55\x3A\x3D",
+		.ilen	= 88,
+	}, {
+		.key	= "\x7D\x77\x3D\x00\xC1\x44\xC5\x25"
+			  "\xAC\x61\x9D\x18\xC8\x4A\x3F\x47"
+			  "\xD9\x66\x42",
+		.klen	= 19,
+		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.result	= "\x01\x02\x02\x01",
+		.rlen	= 4,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF"
+			  "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.alen	= 16,
+		.input	= "\x4C\x72\x63\x30\x2F\xE6\x56\xDD"
+			  "\xD0\xD8\x60\x9D\x8B\xEF\x85\x90"
+			  "\xF7\x61\x24\x62",
+		.ilen	= 20,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8",
+		.klen	= 19,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.result	= "\x74\x6F\x01\x62\x65\x01\x6F\x72"
+			  "\x01\x6E\x6F\x74\x01\x74\x6F\x01"
+			  "\x62\x65\x00\x01",
+		.rlen	= 20,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01\xCA\xFE\xDE\xBA"
+			  "\xCE\xFA\xCE\x74",
+		.alen	= 20,
+		.input	= "\xA3\xBF\x52\x52\x65\x83\xBA\x81"
+			  "\x03\x9B\x84\xFC\x44\x8C\xBB\x81"
+			  "\x36\xE1\x78\xBB\xA5\x49\x3A\xD0"
+			  "\xF0\x6B\x21\xAF\x98\xC0\x34\xDC"
+			  "\x17\x17\x65\xAD",
+		.ilen	= 36,
+	}, {
+		.key	= "\x6C\x65\x67\x61\x6C\x69\x7A\x65"
+			  "\x6D\x61\x72\x69\x6A\x75\x61\x6E"
+			  "\x61\x61\x6E\x64\x64\x6F\x69\x74"
+			  "\x62\x65\x66\x6F\x72\x65\x69\x61"
+			  "\x74\x75\x72",
+		.klen	= 35,
+		.iv	= "\x33\x30\x21\x69\x67\x65\x74\x6D",
+		.result	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
+			  "\xFF\xFF\xFF\xFF\x33\x30\x21\x69"
+			  "\x67\x65\x74\x6D",
+		.alen	= 20,
+		.input	= "\x96\xFD\x86\xF8\xD1\x98\xFF\x10"
+			  "\xAB\x8C\xDA\x8A\x5A\x08\x38\x1A"
+			  "\x48\x59\x80\x18\x1A\x18\x1A\x04"
+			  "\xC9\x0D\xE3\xE7\x0E\xA4\x0B\x75"
+			  "\x92\x9C\x52\x5C\x0B\xFB\xF8\xAF"
+			  "\x16\xC3\x35\xA8\xE7\xCE\x84\x04"
+			  "\xEB\x40\x6B\x7A\x8E\x75\xBB\x42"
+			  "\xE0\x63\x4B\x21\x44\xA2\x2B\x2B"
+			  "\x39\xDB\xC8\xDC",
+		.ilen	= 68,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E",
+		.klen	= 19,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10\x4E\x28\x00\x00"
+			  "\xA2\xFC\xA1\xA3",
+		.alen	= 20,
+		.input	= "\x6A\x6B\x45\x27\x3F\x9E\x52\xF6"
+			  "\x10\x60\x54\x25\xEB\x80\x04\x93"
+			  "\xCA\x1B\x23\x97\xCB\x21\x2E\x01"
+			  "\xA2\xE7\x95\x41\x30\xE4\x4B\x1B"
+			  "\x79\x01\x58\x50\x01\x06\xE1\xE0"
+			  "\x2C\x83\x79\xD3\xDE\x46\x97\x1A"
+			  "\x44\xCC\x90\xBF\x00\x94\x94\x92"
+			  "\x20\x17\x0C\x1B\x55\xDE\x7E\x68"
+			  "\xF4\x95\x5D\x4F",
+		.ilen	= 68,
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x22\x43\x3C",
+		.klen	= 19,
+		.iv	= "\x48\x55\xEC\x7D\x3A\x23\x4B\xFD",
+		.result	= "\x08\x00\xC6\xCD\x02\x00\x07\x00"
+			  "\x61\x62\x63\x64\x65\x66\x67\x68"
+			  "\x69\x6A\x6B\x6C\x6D\x6E\x6F\x70"
+			  "\x71\x72\x73\x74\x01\x02\x02\x01",
+		.rlen	= 32,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x07\x48\x55\xEC\x7D"
+			  "\x3A\x23\x4B\xFD",
+		.alen	= 20,
+		.input	= "\x67\xE9\x28\xB3\x1C\xA4\x6D\x02"
+			  "\xF0\xB5\x37\xB6\x6B\x2F\xF5\x4F"
+			  "\xF8\xA3\x4C\x53\xB8\x12\x09\xBF"
+			  "\x58\x7D\xCF\x29\xA3\x41\x68\x6B"
+			  "\xCE\xE8\x79\x85\x3C\xB0\x3A\x8F"
+			  "\x16\xB0\xA1\x26\xC9\xBC\xBC\xA6",
+		.ilen	= 48,
+	}
+};
+
+/*
  * ChaCha20-Poly1305 AEAD test vectors from RFC7539 2.8.2./A.5.
  */
 #define RFC7539_ENC_TEST_VECTORS 2
@@ -22343,8 +23647,9 @@ static struct aead_testvec rfc7539esp_enc_tv_template[] = {
 		.klen	= 36,
 		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
 		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
-			  "\x00\x00\x4e\x91",
-		.alen	= 12,
+			  "\x00\x00\x4e\x91\x01\x02\x03\x04"
+			  "\x05\x06\x07\x08",
+		.alen	= 20,
 		.input	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
 			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
 			  "\x61\x72\x65\x20\x64\x72\x61\x66"
@@ -22430,8 +23735,9 @@ static struct aead_testvec rfc7539esp_dec_tv_template[] = {
 		.klen	= 36,
 		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
 		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
-			  "\x00\x00\x4e\x91",
-		.alen	= 12,
+			  "\x00\x00\x4e\x91\x01\x02\x03\x04"
+			  "\x05\x06\x07\x08",
+		.alen	= 20,
 		.input	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
 			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
 			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
@@ -30174,7 +31480,7 @@ static struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 	},
 };
 
-#define CHACHA20_ENC_TEST_VECTORS 3
+#define CHACHA20_ENC_TEST_VECTORS 4
 static struct cipher_testvec chacha20_enc_tv_template[] = {
 	{ /* RFC7539 A.2. Test Vector #1 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -30348,6 +31654,338 @@ static struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x87\xb5\x8d\xfd\x72\x8a\xfa\x36"
 			  "\x75\x7a\x79\x7a\xc1\x88\xd1",
 		.rlen	= 127,
+	}, { /* Self-made test vector for long data */
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv     = "\x1c\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.input	= "\x49\xee\xe0\xdc\x24\x90\x40\xcd"
+			  "\xc5\x40\x8f\x47\x05\xbc\xdd\x81"
+			  "\x47\xc6\x8d\xe6\xb1\x8f\xd7\xcb"
+			  "\x09\x0e\x6e\x22\x48\x1f\xbf\xb8"
+			  "\x5c\xf7\x1e\x8a\xc1\x23\xf2\xd4"
+			  "\x19\x4b\x01\x0f\x4e\xa4\x43\xce"
+			  "\x01\xc6\x67\xda\x03\x91\x18\x90"
+			  "\xa5\xa4\x8e\x45\x03\xb3\x2d\xac"
+			  "\x74\x92\xd3\x53\x47\xc8\xdd\x25"
+			  "\x53\x6c\x02\x03\x87\x0d\x11\x0c"
+			  "\x58\xe3\x12\x18\xfd\x2a\x5b\x40"
+			  "\x0c\x30\xf0\xb8\x3f\x43\xce\xae"
+			  "\x65\x3a\x7d\x7c\xf4\x54\xaa\xcc"
+			  "\x33\x97\xc3\x77\xba\xc5\x70\xde"
+			  "\xd7\xd5\x13\xa5\x65\xc4\x5f\x0f"
+			  "\x46\x1a\x0d\x97\xb5\xf3\xbb\x3c"
+			  "\x84\x0f\x2b\xc5\xaa\xea\xf2\x6c"
+			  "\xc9\xb5\x0c\xee\x15\xf3\x7d\xbe"
+			  "\x9f\x7b\x5a\xa6\xae\x4f\x83\xb6"
+			  "\x79\x49\x41\xf4\x58\x18\xcb\x86"
+			  "\x7f\x30\x0e\xf8\x7d\x44\x36\xea"
+			  "\x75\xeb\x88\x84\x40\x3c\xad\x4f"
+			  "\x6f\x31\x6b\xaa\x5d\xe5\xa5\xc5"
+			  "\x21\x66\xe9\xa7\xe3\xb2\x15\x88"
+			  "\x78\xf6\x79\xa1\x59\x47\x12\x4e"
+			  "\x9f\x9f\x64\x1a\xa0\x22\x5b\x08"
+			  "\xbe\x7c\x36\xc2\x2b\x66\x33\x1b"
+			  "\xdd\x60\x71\xf7\x47\x8c\x61\xc3"
+			  "\xda\x8a\x78\x1e\x16\xfa\x1e\x86"
+			  "\x81\xa6\x17\x2a\xa7\xb5\xc2\xe7"
+			  "\xa4\xc7\x42\xf1\xcf\x6a\xca\xb4"
+			  "\x45\xcf\xf3\x93\xf0\xe7\xea\xf6"
+			  "\xf4\xe6\x33\x43\x84\x93\xa5\x67"
+			  "\x9b\x16\x58\x58\x80\x0f\x2b\x5c"
+			  "\x24\x74\x75\x7f\x95\x81\xb7\x30"
+			  "\x7a\x33\xa7\xf7\x94\x87\x32\x27"
+			  "\x10\x5d\x14\x4c\x43\x29\xdd\x26"
+			  "\xbd\x3e\x3c\x0e\xfe\x0e\xa5\x10"
+			  "\xea\x6b\x64\xfd\x73\xc6\xed\xec"
+			  "\xa8\xc9\xbf\xb3\xba\x0b\x4d\x07"
+			  "\x70\xfc\x16\xfd\x79\x1e\xd7\xc5"
+			  "\x49\x4e\x1c\x8b\x8d\x79\x1b\xb1"
+			  "\xec\xca\x60\x09\x4c\x6a\xd5\x09"
+			  "\x49\x46\x00\x88\x22\x8d\xce\xea"
+			  "\xb1\x17\x11\xde\x42\xd2\x23\xc1"
+			  "\x72\x11\xf5\x50\x73\x04\x40\x47"
+			  "\xf9\x5d\xe7\xa7\x26\xb1\x7e\xb0"
+			  "\x3f\x58\xc1\x52\xab\x12\x67\x9d"
+			  "\x3f\x43\x4b\x68\xd4\x9c\x68\x38"
+			  "\x07\x8a\x2d\x3e\xf3\xaf\x6a\x4b"
+			  "\xf9\xe5\x31\x69\x22\xf9\xa6\x69"
+			  "\xc6\x9c\x96\x9a\x12\x35\x95\x1d"
+			  "\x95\xd5\xdd\xbe\xbf\x93\x53\x24"
+			  "\xfd\xeb\xc2\x0a\x64\xb0\x77\x00"
+			  "\x6f\x88\xc4\x37\x18\x69\x7c\xd7"
+			  "\x41\x92\x55\x4c\x03\xa1\x9a\x4b"
+			  "\x15\xe5\xdf\x7f\x37\x33\x72\xc1"
+			  "\x8b\x10\x67\xa3\x01\x57\x94\x25"
+			  "\x7b\x38\x71\x7e\xdd\x1e\xcc\x73"
+			  "\x55\xd2\x8e\xeb\x07\xdd\xf1\xda"
+			  "\x58\xb1\x47\x90\xfe\x42\x21\x72"
+			  "\xa3\x54\x7a\xa0\x40\xec\x9f\xdd"
+			  "\xc6\x84\x6e\xca\xae\xe3\x68\xb4"
+			  "\x9d\xe4\x78\xff\x57\xf2\xf8\x1b"
+			  "\x03\xa1\x31\xd9\xde\x8d\xf5\x22"
+			  "\x9c\xdd\x20\xa4\x1e\x27\xb1\x76"
+			  "\x4f\x44\x55\xe2\x9b\xa1\x9c\xfe"
+			  "\x54\xf7\x27\x1b\xf4\xde\x02\xf5"
+			  "\x1b\x55\x48\x5c\xdc\x21\x4b\x9e"
+			  "\x4b\x6e\xed\x46\x23\xdc\x65\xb2"
+			  "\xcf\x79\x5f\x28\xe0\x9e\x8b\xe7"
+			  "\x4c\x9d\x8a\xff\xc1\xa6\x28\xb8"
+			  "\x65\x69\x8a\x45\x29\xef\x74\x85"
+			  "\xde\x79\xc7\x08\xae\x30\xb0\xf4"
+			  "\xa3\x1d\x51\x41\xab\xce\xcb\xf6"
+			  "\xb5\xd8\x6d\xe0\x85\xe1\x98\xb3"
+			  "\x43\xbb\x86\x83\x0a\xa0\xf5\xb7"
+			  "\x04\x0b\xfa\x71\x1f\xb0\xf6\xd9"
+			  "\x13\x00\x15\xf0\xc7\xeb\x0d\x5a"
+			  "\x9f\xd7\xb9\x6c\x65\x14\x22\x45"
+			  "\x6e\x45\x32\x3e\x7e\x60\x1a\x12"
+			  "\x97\x82\x14\xfb\xaa\x04\x22\xfa"
+			  "\xa0\xe5\x7e\x8c\x78\x02\x48\x5d"
+			  "\x78\x33\x5a\x7c\xad\xdb\x29\xce"
+			  "\xbb\x8b\x61\xa4\xb7\x42\xe2\xac"
+			  "\x8b\x1a\xd9\x2f\x0b\x8b\x62\x21"
+			  "\x83\x35\x7e\xad\x73\xc2\xb5\x6c"
+			  "\x10\x26\x38\x07\xe5\xc7\x36\x80"
+			  "\xe2\x23\x12\x61\xf5\x48\x4b\x2b"
+			  "\xc5\xdf\x15\xd9\x87\x01\xaa\xac"
+			  "\x1e\x7c\xad\x73\x78\x18\x63\xe0"
+			  "\x8b\x9f\x81\xd8\x12\x6a\x28\x10"
+			  "\xbe\x04\x68\x8a\x09\x7c\x1b\x1c"
+			  "\x83\x66\x80\x47\x80\xe8\xfd\x35"
+			  "\x1c\x97\x6f\xae\x49\x10\x66\xcc"
+			  "\xc6\xd8\xcc\x3a\x84\x91\x20\x77"
+			  "\x72\xe4\x24\xd2\x37\x9f\xc5\xc9"
+			  "\x25\x94\x10\x5f\x40\x00\x64\x99"
+			  "\xdc\xae\xd7\x21\x09\x78\x50\x15"
+			  "\xac\x5f\xc6\x2c\xa2\x0b\xa9\x39"
+			  "\x87\x6e\x6d\xab\xde\x08\x51\x16"
+			  "\xc7\x13\xe9\xea\xed\x06\x8e\x2c"
+			  "\xf8\x37\x8c\xf0\xa6\x96\x8d\x43"
+			  "\xb6\x98\x37\xb2\x43\xed\xde\xdf"
+			  "\x89\x1a\xe7\xeb\x9d\xa1\x7b\x0b"
+			  "\x77\xb0\xe2\x75\xc0\xf1\x98\xd9"
+			  "\x80\x55\xc9\x34\x91\xd1\x59\xe8"
+			  "\x4b\x0f\xc1\xa9\x4b\x7a\x84\x06"
+			  "\x20\xa8\x5d\xfa\xd1\xde\x70\x56"
+			  "\x2f\x9e\x91\x9c\x20\xb3\x24\xd8"
+			  "\x84\x3d\xe1\x8c\x7e\x62\x52\xe5"
+			  "\x44\x4b\x9f\xc2\x93\x03\xea\x2b"
+			  "\x59\xc5\xfa\x3f\x91\x2b\xbb\x23"
+			  "\xf5\xb2\x7b\xf5\x38\xaf\xb3\xee"
+			  "\x63\xdc\x7b\xd1\xff\xaa\x8b\xab"
+			  "\x82\x6b\x37\x04\xeb\x74\xbe\x79"
+			  "\xb9\x83\x90\xef\x20\x59\x46\xff"
+			  "\xe9\x97\x3e\x2f\xee\xb6\x64\x18"
+			  "\x38\x4c\x7a\x4a\xf9\x61\xe8\x9a"
+			  "\xa1\xb5\x01\xa6\x47\xd3\x11\xd4"
+			  "\xce\xd3\x91\x49\x88\xc7\xb8\x4d"
+			  "\xb1\xb9\x07\x6d\x16\x72\xae\x46"
+			  "\x5e\x03\xa1\x4b\xb6\x02\x30\xa8"
+			  "\x3d\xa9\x07\x2a\x7c\x19\xe7\x62"
+			  "\x87\xe3\x82\x2f\x6f\xe1\x09\xd9"
+			  "\x94\x97\xea\xdd\x58\x9e\xae\x76"
+			  "\x7e\x35\xe5\xb4\xda\x7e\xf4\xde"
+			  "\xf7\x32\x87\xcd\x93\xbf\x11\x56"
+			  "\x11\xbe\x08\x74\xe1\x69\xad\xe2"
+			  "\xd7\xf8\x86\x75\x8a\x3c\xa4\xbe"
+			  "\x70\xa7\x1b\xfc\x0b\x44\x2a\x76"
+			  "\x35\xea\x5d\x85\x81\xaf\x85\xeb"
+			  "\xa0\x1c\x61\xc2\xf7\x4f\xa5\xdc"
+			  "\x02\x7f\xf6\x95\x40\x6e\x8a\x9a"
+			  "\xf3\x5d\x25\x6e\x14\x3a\x22\xc9"
+			  "\x37\x1c\xeb\x46\x54\x3f\xa5\x91"
+			  "\xc2\xb5\x8c\xfe\x53\x08\x97\x32"
+			  "\x1b\xb2\x30\x27\xfe\x25\x5d\xdc"
+			  "\x08\x87\xd0\xe5\x94\x1a\xd4\xf1"
+			  "\xfe\xd6\xb4\xa3\xe6\x74\x81\x3c"
+			  "\x1b\xb7\x31\xa7\x22\xfd\xd4\xdd"
+			  "\x20\x4e\x7c\x51\xb0\x60\x73\xb8"
+			  "\x9c\xac\x91\x90\x7e\x01\xb0\xe1"
+			  "\x8a\x2f\x75\x1c\x53\x2a\x98\x2a"
+			  "\x06\x52\x95\x52\xb2\xe9\x25\x2e"
+			  "\x4c\xe2\x5a\x00\xb2\x13\x81\x03"
+			  "\x77\x66\x0d\xa5\x99\xda\x4e\x8c"
+			  "\xac\xf3\x13\x53\x27\x45\xaf\x64"
+			  "\x46\xdc\xea\x23\xda\x97\xd1\xab"
+			  "\x7d\x6c\x30\x96\x1f\xbc\x06\x34"
+			  "\x18\x0b\x5e\x21\x35\x11\x8d\x4c"
+			  "\xe0\x2d\xe9\x50\x16\x74\x81\xa8"
+			  "\xb4\x34\xb9\x72\x42\xa6\xcc\xbc"
+			  "\xca\x34\x83\x27\x10\x5b\x68\x45"
+			  "\x8f\x52\x22\x0c\x55\x3d\x29\x7c"
+			  "\xe3\xc0\x66\x05\x42\x91\x5f\x58"
+			  "\xfe\x4a\x62\xd9\x8c\xa9\x04\x19"
+			  "\x04\xa9\x08\x4b\x57\xfc\x67\x53"
+			  "\x08\x7c\xbc\x66\x8a\xb0\xb6\x9f"
+			  "\x92\xd6\x41\x7c\x5b\x2a\x00\x79"
+			  "\x72",
+		.ilen	= 1281,
+		.result	= "\x45\xe8\xe0\xb6\x9c\xca\xfd\x87"
+			  "\xe8\x1d\x37\x96\x8a\xe3\x40\x35"
+			  "\xcf\x5e\x3a\x46\x3d\xfb\xd0\x69"
+			  "\xde\xaf\x7a\xd5\x0d\xe9\x52\xec"
+			  "\xc2\x82\xe5\x3e\x7d\xb2\x4a\xd9"
+			  "\xbb\xc3\x9f\xc0\x5d\xac\x93\x8d"
+			  "\x0e\x6f\xd3\xd7\xfb\x6a\x0d\xce"
+			  "\x92\x2c\xf7\xbb\x93\x57\xcc\xee"
+			  "\x42\x72\x6f\xc8\x4b\xd2\x76\xbf"
+			  "\xa0\xe3\x7a\x39\xf9\x5c\x8e\xfd"
+			  "\xa1\x1d\x41\xe5\x08\xc1\x1c\x11"
+			  "\x92\xfd\x39\x5c\x51\xd0\x2f\x66"
+			  "\x33\x4a\x71\x15\xfe\xee\x12\x54"
+			  "\x8c\x8f\x34\xd8\x50\x3c\x18\xa6"
+			  "\xc5\xe1\x46\x8a\xfb\x5f\x7e\x25"
+			  "\x9b\xe2\xc3\x66\x41\x2b\xb3\xa5"
+			  "\x57\x0e\x94\x17\x26\x39\xbb\x54"
+			  "\xae\x2e\x6f\x42\xfb\x4d\x89\x6f"
+			  "\x9d\xf1\x16\x2e\xe3\xe7\xfc\xe3"
+			  "\xb2\x4b\x2b\xa6\x7c\x04\x69\x3a"
+			  "\x70\x5a\xa7\xf1\x31\x64\x19\xca"
+			  "\x45\x79\xd8\x58\x23\x61\xaf\xc2"
+			  "\x52\x05\xc3\x0b\xc1\x64\x7c\x81"
+			  "\xd9\x11\xcf\xff\x02\x3d\x51\x84"
+			  "\x01\xac\xc6\x2e\x34\x2b\x09\x3a"
+			  "\xa8\x5d\x98\x0e\x89\xd9\xef\x8f"
+			  "\xd9\xd7\x7d\xdd\x63\x47\x46\x7d"
+			  "\xa1\xda\x0b\x53\x7d\x79\xcd\xc9"
+			  "\x86\xdd\x6b\x13\xa1\x9a\x70\xdd"
+			  "\x5c\xa1\x69\x3c\xe4\x5d\xe3\x8c"
+			  "\xe5\xf4\x87\x9c\x10\xcf\x0f\x0b"
+			  "\xc8\x43\xdc\xf8\x1d\x62\x5e\x5b"
+			  "\xe2\x03\x06\xc5\x71\xb6\x48\xa5"
+			  "\xf0\x0f\x2d\xd5\xa2\x73\x55\x8f"
+			  "\x01\xa7\x59\x80\x5f\x11\x6c\x40"
+			  "\xff\xb1\xf2\xc6\x7e\x01\xbb\x1c"
+			  "\x69\x9c\xc9\x3f\x71\x5f\x07\x7e"
+			  "\xdf\x6f\x99\xca\x9c\xfd\xf9\xb9"
+			  "\x49\xe7\xcc\x91\xd5\x9b\x8f\x03"
+			  "\xae\xe7\x61\x32\xef\x41\x6c\x75"
+			  "\x84\x9b\x8c\xce\x1d\x6b\x93\x21"
+			  "\x41\xec\xc6\xad\x8e\x0c\x48\xa8"
+			  "\xe2\xf5\x57\xde\xf7\x38\xfd\x4a"
+			  "\x6f\xa7\x4a\xf9\xac\x7d\xb1\x85"
+			  "\x7d\x6c\x95\x0a\x5a\xcf\x68\xd2"
+			  "\xe0\x7a\x26\xd9\xc1\x6d\x3e\xc6"
+			  "\x37\xbd\xbe\x24\x36\x77\x9f\x1b"
+			  "\xc1\x22\xf3\x79\xae\x95\x78\x66"
+			  "\x97\x11\xc0\x1a\xf1\xe8\x0d\x38"
+			  "\x09\xc2\xee\xb7\xd3\x46\x7b\x59"
+			  "\x77\x23\xe8\xb4\x92\x3d\x78\xbe"
+			  "\xe2\x25\x63\xa5\x2a\x06\x70\x92"
+			  "\x32\x63\xf9\x19\x21\x68\xe1\x0b"
+			  "\x9a\xd0\xee\x21\xdb\x1f\xe0\xde"
+			  "\x3e\x64\x02\x4d\x0e\xe0\x0a\xa9"
+			  "\xed\x19\x8c\xa8\xbf\xe3\x2e\x75"
+			  "\x24\x2b\xb0\xe5\x82\x6a\x1e\x6f"
+			  "\x71\x2a\x3a\x60\xed\x06\x0d\x17"
+			  "\xa2\xdb\x29\x1d\xae\xb2\xc4\xfb"
+			  "\x94\x04\xd8\x58\xfc\xc4\x04\x4e"
+			  "\xee\xc7\xc1\x0f\xe9\x9b\x63\x2d"
+			  "\x02\x3e\x02\x67\xe5\xd8\xbb\x79"
+			  "\xdf\xd2\xeb\x50\xe9\x0a\x02\x46"
+			  "\xdf\x68\xcf\xe7\x2b\x0a\x56\xd6"
+			  "\xf7\xbc\x44\xad\xb8\xb5\x5f\xeb"
+			  "\xbc\x74\x6b\xe8\x7e\xb0\x60\xc6"
+			  "\x0d\x96\x09\xbb\x19\xba\xe0\x3c"
+			  "\xc4\x6c\xbf\x0f\x58\xc0\x55\x62"
+			  "\x23\xa0\xff\xb5\x1c\xfd\x18\xe1"
+			  "\xcf\x6d\xd3\x52\xb4\xce\xa6\xfa"
+			  "\xaa\xfb\x1b\x0b\x42\x6d\x79\x42"
+			  "\x48\x70\x5b\x0e\xdd\x3a\xc9\x69"
+			  "\x8b\x73\x67\xf6\x95\xdb\x8c\xfb"
+			  "\xfd\xb5\x08\x47\x42\x84\x9a\xfa"
+			  "\xcc\x67\xb2\x3c\xb6\xfd\xd8\x32"
+			  "\xd6\x04\xb6\x4a\xea\x53\x4b\xf5"
+			  "\x94\x16\xad\xf0\x10\x2e\x2d\xb4"
+			  "\x8b\xab\xe5\x89\xc7\x39\x12\xf3"
+			  "\x8d\xb5\x96\x0b\x87\x5d\xa7\x7c"
+			  "\xb0\xc2\xf6\x2e\x57\x97\x2c\xdc"
+			  "\x54\x1c\x34\x72\xde\x0c\x68\x39"
+			  "\x9d\x32\xa5\x75\x92\x13\x32\xea"
+			  "\x90\x27\xbd\x5b\x1d\xb9\x21\x02"
+			  "\x1c\xcc\xba\x97\x5e\x49\x58\xe8"
+			  "\xac\x8b\xf3\xce\x3c\xf0\x00\xe9"
+			  "\x6c\xae\xe9\x77\xdf\xf4\x02\xcd"
+			  "\x55\x25\x89\x9e\x90\xf3\x6b\x8f"
+			  "\xb7\xd6\x47\x98\x26\x2f\x31\x2f"
+			  "\x8d\xbf\x54\xcd\x99\xeb\x80\xd7"
+			  "\xac\xc3\x08\xc2\xa6\x32\xf1\x24"
+			  "\x76\x7c\x4f\x78\x53\x55\xfb\x00"
+			  "\x8a\xd6\x52\x53\x25\x45\xfb\x0a"
+			  "\x6b\xb9\xbe\x3c\x5e\x11\xcc\x6a"
+			  "\xdd\xfc\xa7\xc4\x79\x4d\xbd\xfb"
+			  "\xce\x3a\xf1\x7a\xda\xeb\xfe\x64"
+			  "\x28\x3d\x0f\xee\x80\xba\x0c\xf8"
+			  "\xe9\x5b\x3a\xd4\xae\xc9\xf3\x0e"
+			  "\xe8\x5d\xc5\x5c\x0b\x20\x20\xee"
+			  "\x40\x0d\xde\x07\xa7\x14\xb4\x90"
+			  "\xb6\xbd\x3b\xae\x7d\x2b\xa7\xc7"
+			  "\xdc\x0b\x4c\x5d\x65\xb0\xd2\xc5"
+			  "\x79\x61\x23\xe0\xa2\x99\x73\x55"
+			  "\xad\xc6\xfb\xc7\x54\xb5\x98\x1f"
+			  "\x8c\x86\xc2\x3f\xbe\x5e\xea\x64"
+			  "\xa3\x60\x18\x9f\x80\xaf\x52\x74"
+			  "\x1a\xfe\x22\xc2\x92\x67\x40\x02"
+			  "\x08\xee\x67\x5b\x67\xe0\x3d\xde"
+			  "\x7a\xaf\x8e\x28\xf3\x5e\x0e\xf4"
+			  "\x48\x56\xaa\x85\x22\xd8\x36\xed"
+			  "\x3b\x3d\x68\x69\x30\xbc\x71\x23"
+			  "\xb1\x6e\x61\x03\x89\x44\x03\xf4"
+			  "\x32\xaa\x4c\x40\x9f\x69\xfb\x70"
+			  "\x91\xcc\x1f\x11\xbd\x76\x67\xe6"
+			  "\x10\x8b\x29\x39\x68\xea\x4e\x6d"
+			  "\xae\xfb\x40\xcf\xe2\xd0\x0d\x8d"
+			  "\x6f\xed\x9b\x8d\x64\x7a\x94\x8e"
+			  "\x32\x38\x78\xeb\x7d\x5f\xf9\x4d"
+			  "\x13\xbe\x21\xea\x16\xe7\x5c\xee"
+			  "\xcd\xf6\x5f\xc6\x45\xb2\x8f\x2b"
+			  "\xb5\x93\x3e\x45\xdb\xfd\xa2\x6a"
+			  "\xec\x83\x92\x99\x87\x47\xe0\x7c"
+			  "\xa2\x7b\xc4\x2a\xcd\xc0\x81\x03"
+			  "\x98\xb0\x87\xb6\x86\x13\x64\x33"
+			  "\x4c\xd7\x99\xbf\xdb\x7b\x6e\xaa"
+			  "\x76\xcc\xa0\x74\x1b\xa3\x6e\x83"
+			  "\xd4\xba\x7a\x84\x9d\x91\x71\xcd"
+			  "\x60\x2d\x56\xfd\x26\x35\xcb\xeb"
+			  "\xac\xe9\xee\xa4\xfc\x18\x5b\x91"
+			  "\xd5\xfe\x84\x45\xe0\xc7\xfd\x11"
+			  "\xe9\x00\xb6\x54\xdf\xe1\x94\xde"
+			  "\x2b\x70\x9f\x94\x7f\x15\x0e\x83"
+			  "\x63\x10\xb3\xf5\xea\xd3\xe8\xd1"
+			  "\xa5\xfc\x17\x19\x68\x9a\xbc\x17"
+			  "\x30\x43\x0a\x1a\x33\x92\xd4\x2a"
+			  "\x2e\x68\x99\xbc\x49\xf0\x68\xe3"
+			  "\xf0\x1f\xcb\xcc\xfa\xbb\x05\x56"
+			  "\x46\x84\x8b\x69\x83\x64\xc5\xe0"
+			  "\xc5\x52\x99\x07\x3c\xa6\x5c\xaf"
+			  "\xa3\xde\xd7\xdb\x43\xe6\xb7\x76"
+			  "\x4e\x4d\xd6\x71\x60\x63\x4a\x0c"
+			  "\x5f\xae\x25\x84\x22\x90\x5f\x26"
+			  "\x61\x4d\x8f\xaf\xc9\x22\xf2\x05"
+			  "\xcf\xc1\xdc\x68\xe5\x57\x8e\x24"
+			  "\x1b\x30\x59\xca\xd7\x0d\xc3\xd3"
+			  "\x52\x9e\x09\x3e\x0e\xaf\xdb\x5f"
+			  "\xc7\x2b\xde\x3a\xfd\xad\x93\x04"
+			  "\x74\x06\x89\x0e\x90\xeb\x85\xff"
+			  "\xe6\x3c\x12\x42\xf4\xfa\x80\x75"
+			  "\x5e\x4e\xd7\x2f\x93\x0b\x34\x41"
+			  "\x02\x85\x68\xd0\x03\x12\xde\x92"
+			  "\x54\x7a\x7e\xfb\x55\xe7\x88\xfb"
+			  "\xa4\xa9\xf2\xd1\xc6\x70\x06\x37"
+			  "\x25\xee\xa7\x6e\xd9\x89\x86\x50"
+			  "\x2e\x07\xdb\xfb\x2a\x86\x45\x0e"
+			  "\x91\xf4\x7c\xbb\x12\x60\xe8\x3f"
+			  "\x71\xbe\x8f\x9d\x26\xef\xd9\x89"
+			  "\xc4\x8f\xd8\xc5\x73\xd8\x84\xaa"
+			  "\x2f\xad\x22\x1e\x7e\xcf\xa2\x08"
+			  "\x23\x45\x89\x42\xa0\x30\xeb\xbf"
+			  "\xa1\xed\xad\xd5\x76\xfa\x24\x8f"
+			  "\x98",
+		.rlen	= 1281,
 	},
 };
 
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 6e973b8e3a3b..46b4a8e0f859 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -176,6 +176,8 @@ source "drivers/powercap/Kconfig"
 
 source "drivers/mcb/Kconfig"
 
+source "drivers/perf/Kconfig"
+
 source "drivers/ras/Kconfig"
 
 source "drivers/thunderbolt/Kconfig"
@@ -184,4 +186,6 @@ source "drivers/android/Kconfig"
 
 source "drivers/nvdimm/Kconfig"
 
+source "drivers/nvmem/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index b64b49f6e01b..b250b36b54f2 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -11,7 +11,7 @@ obj-y				+= bus/
 obj-$(CONFIG_GENERIC_PHY)	+= phy/
 
 # GPIO must come after pinctrl as gpios may need to mux pins etc
-obj-y				+= pinctrl/
+obj-$(CONFIG_PINCTRL)		+= pinctrl/
 obj-y				+= gpio/
 obj-y				+= pwm/
 obj-$(CONFIG_PCI)		+= pci/
@@ -161,7 +161,9 @@ obj-$(CONFIG_NTB)		+= ntb/
 obj-$(CONFIG_FMC)		+= fmc/
 obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
+obj-$(CONFIG_PERF_EVENTS)	+= perf/
 obj-$(CONFIG_RAS)		+= ras/
 obj-$(CONFIG_THUNDERBOLT)	+= thunderbolt/
 obj-$(CONFIG_CORESIGHT)		+= hwtracing/coresight/
 obj-$(CONFIG_ANDROID)		+= android/
+obj-$(CONFIG_NVMEM)		+= nvmem/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 114cf48085ab..54e9729f9634 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -189,17 +189,24 @@ config ACPI_DOCK
 	  This driver supports ACPI-controlled docking stations and removable
 	  drive bays such as the IBM Ultrabay and the Dell Module Bay.
 
-config ACPI_PROCESSOR
-	tristate "Processor"
+config ACPI_CPU_FREQ_PSS
+	bool
 	select THERMAL
+
+config ACPI_PROCESSOR_IDLE
+	bool
 	select CPU_IDLE
+
+config ACPI_PROCESSOR
+	tristate "Processor"
 	depends on X86 || IA64
+	select ACPI_PROCESSOR_IDLE
+	select ACPI_CPU_FREQ_PSS
 	default y
 	help
-	  This driver installs ACPI as the idle handler for Linux and uses
-	  ACPI C2 and C3 processor states to save power on systems that
-	  support it.  It is required by several flavors of cpufreq
-	  performance-state drivers.
+	  This driver adds support for the ACPI Processor package. It is required
+	  by several flavors of cpufreq performance-state, thermal, throttling and
+	  idle drivers.
 
 	  To compile this driver as a module, choose M here:
 	  the module will be called processor.
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 8321430d7f24..b5e7cd8a9c71 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -24,7 +24,7 @@ acpi-y				+= nvs.o
 # Power management related files
 acpi-y				+= wakeup.o
 acpi-$(CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT) += sleep.o
-acpi-y				+= device_pm.o
+acpi-y				+= device_sysfs.o device_pm.o
 acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 
 
@@ -80,8 +80,10 @@ obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
 
 # processor has its own "processor." module_param namespace
-processor-y			:= processor_driver.o processor_throttling.o
-processor-y			+= processor_idle.o processor_thermal.o
+processor-y			:= processor_driver.o
+processor-$(CONFIG_ACPI_PROCESSOR_IDLE) += processor_idle.o
+processor-$(CONFIG_ACPI_CPU_FREQ_PSS)	+= processor_throttling.o	\
+	processor_thermal.o
 processor-$(CONFIG_CPU_FREQ)	+= processor_perflib.o
 
 obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 9b5354a2cd08..f71b756b05c4 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -16,10 +16,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index 3984ea96e5f7..a450e7af877c 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -16,7 +16,6 @@
 #include <linux/clkdev.h>
 #include <linux/acpi.h>
 #include <linux/err.h>
-#include <linux/clk.h>
 #include <linux/pm.h>
 
 #include "internal.h"
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index ac0f52f6df2b..f77956c3fd45 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -17,10 +17,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 569ee090343f..f51bd0d0bc17 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/acpi.h>
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
@@ -60,6 +59,7 @@ ACPI_MODULE_NAME("acpi_lpss");
 #define LPSS_CLK_DIVIDER		BIT(2)
 #define LPSS_LTR			BIT(3)
 #define LPSS_SAVE_CTX			BIT(4)
+#define LPSS_NO_D3_DELAY		BIT(5)
 
 struct lpss_private_data;
 
@@ -156,6 +156,10 @@ static const struct lpss_device_desc byt_pwm_dev_desc = {
 	.flags = LPSS_SAVE_CTX,
 };
 
+static const struct lpss_device_desc bsw_pwm_dev_desc = {
+	.flags = LPSS_SAVE_CTX | LPSS_NO_D3_DELAY,
+};
+
 static const struct lpss_device_desc byt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.clk_con_id = "baudclk",
@@ -163,6 +167,14 @@ static const struct lpss_device_desc byt_uart_dev_desc = {
 	.setup = lpss_uart_setup,
 };
 
+static const struct lpss_device_desc bsw_uart_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX
+			| LPSS_NO_D3_DELAY,
+	.clk_con_id = "baudclk",
+	.prv_offset = 0x800,
+	.setup = lpss_uart_setup,
+};
+
 static const struct lpss_device_desc byt_spi_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x400,
@@ -178,8 +190,15 @@ static const struct lpss_device_desc byt_i2c_dev_desc = {
 	.setup = byt_i2c_setup,
 };
 
+static const struct lpss_device_desc bsw_i2c_dev_desc = {
+	.flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_NO_D3_DELAY,
+	.prv_offset = 0x800,
+	.setup = byt_i2c_setup,
+};
+
 static struct lpss_device_desc bsw_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX
+			| LPSS_NO_D3_DELAY,
 	.prv_offset = 0x400,
 	.setup = lpss_deassert_reset,
 };
@@ -214,11 +233,12 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
 	{ "INT33FC", },
 
 	/* Braswell LPSS devices */
-	{ "80862288", LPSS_ADDR(byt_pwm_dev_desc) },
-	{ "8086228A", LPSS_ADDR(byt_uart_dev_desc) },
+	{ "80862288", LPSS_ADDR(bsw_pwm_dev_desc) },
+	{ "8086228A", LPSS_ADDR(bsw_uart_dev_desc) },
 	{ "8086228E", LPSS_ADDR(bsw_spi_dev_desc) },
-	{ "808622C1", LPSS_ADDR(byt_i2c_dev_desc) },
+	{ "808622C1", LPSS_ADDR(bsw_i2c_dev_desc) },
 
+	/* Broadwell LPSS devices */
 	{ "INT3430", LPSS_ADDR(lpt_dev_desc) },
 	{ "INT3431", LPSS_ADDR(lpt_dev_desc) },
 	{ "INT3432", LPSS_ADDR(lpt_i2c_dev_desc) },
@@ -352,13 +372,16 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 				pdata->mmio_size = resource_size(rentry->res);
 			pdata->mmio_base = ioremap(rentry->res->start,
 						   pdata->mmio_size);
-			if (!pdata->mmio_base)
-				goto err_out;
 			break;
 		}
 
 	acpi_dev_free_resource_list(&resource_list);
 
+	if (!pdata->mmio_base) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
 	pdata->dev_desc = dev_desc;
 
 	if (dev_desc->setup)
@@ -555,9 +578,14 @@ static void acpi_lpss_restore_ctx(struct device *dev,
 	 * The following delay is needed or the subsequent write operations may
 	 * fail. The LPSS devices are actually PCI devices and the PCI spec
 	 * expects 10ms delay before the device can be accessed after D3 to D0
-	 * transition.
+	 * transition. However some platforms like BSW does not need this delay.
 	 */
-	msleep(10);
+	unsigned int delay = 10;	/* default 10ms delay */
+
+	if (pdata->dev_desc->flags & LPSS_NO_D3_DELAY)
+		delay = 0;
+
+	msleep(delay);
 
 	for (i = 0; i < LPSS_PRV_REG_COUNT; i++) {
 		unsigned long offset = i * sizeof(u32);
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index ee28f4d15625..6b0d3ef7309c 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -16,11 +16,6 @@
  * NON INFRINGEMENT.  See the GNU General Public License for more
  * details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- *
  * ACPI based HotPlug driver that supports Memory Hotplug
  * This driver fields notifications from firmware for memory add
  * and remove operations and alerts the VM of the affected memory
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 00b39802d7ec..ae307ff36acb 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -12,10 +12,6 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index ff6d8adc9cda..fb765524cc3d 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -153,6 +153,7 @@ static const struct acpi_device_id acpi_pnp_device_ids[] = {
 	{"AEI0250"},		/* PROLiNK 1456VH ISA PnP K56flex Fax Modem */
 	{"AEI1240"},		/* Actiontec ISA PNP 56K X2 Fax Modem */
 	{"AKY1021"},		/* Rockwell 56K ACF II Fax+Data+Voice Modem */
+	{"ALI5123"},		/* ALi Fast Infrared Controller */
 	{"AZT4001"},		/* AZT3005 PnP SOUND DEVICE */
 	{"BDP3336"},		/* Best Data Products Inc. Smart One 336F PnP Modem */
 	{"BRI0A49"},		/* Boca Complete Ofc Communicator 14.4 Data-FAX */
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 92a5f738e370..985b8a83184e 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -485,7 +485,7 @@ static const struct acpi_device_id processor_device_ids[] = {
 	{ }
 };
 
-static struct acpi_scan_handler __refdata processor_handler = {
+static struct acpi_scan_handler processor_handler = {
 	.ids = processor_device_ids,
 	.attach = acpi_processor_add,
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 8c2fe2f2f9fd..5778e8e4313a 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -17,10 +17,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile
index c1a963581dc0..fedcc16b56cc 100644
--- a/drivers/acpi/acpica/Makefile
+++ b/drivers/acpi/acpica/Makefile
@@ -11,6 +11,7 @@ obj-y	+= acpi.o
 acpi-y :=		\
 	dsargs.o	\
 	dscontrol.o	\
+	dsdebug.o	\
 	dsfield.o	\
 	dsinit.o	\
 	dsmethod.o	\
@@ -164,6 +165,7 @@ acpi-y +=		\
 	utmath.o	\
 	utmisc.o	\
 	utmutex.o	\
+	utnonansi.o	\
 	utobject.o	\
 	utosi.o		\
 	utownerid.o	\
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 43685dd36c77..eb2e926d8218 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -67,9 +67,6 @@ struct acpi_db_execute_walk {
 };
 
 #define PARAM_LIST(pl)                  pl
-#define DBTEST_OUTPUT_LEVEL(lvl)        if (acpi_gbl_db_opt_verbose)
-#define VERBOSE_PRINT(fp)               DBTEST_OUTPUT_LEVEL(lvl) {\
-			  acpi_os_printf PARAM_LIST(fp);}
 
 #define EX_NO_SINGLE_STEP               1
 #define EX_SINGLE_STEP                  2
@@ -77,10 +74,6 @@ struct acpi_db_execute_walk {
 /*
  * dbxface - external debugger interfaces
  */
-acpi_status acpi_db_initialize(void);
-
-void acpi_db_terminate(void);
-
 acpi_status
 acpi_db_single_step(struct acpi_walk_state *walk_state,
 		    union acpi_parse_object *op, u32 op_type);
@@ -102,6 +95,8 @@ void acpi_db_display_interfaces(char *action_arg, char *interface_name_arg);
 
 acpi_status acpi_db_sleep(char *object_arg);
 
+void acpi_db_trace(char *enable_arg, char *method_arg, char *once_arg);
+
 void acpi_db_display_locks(void);
 
 void acpi_db_display_resources(char *object_arg);
@@ -262,6 +257,23 @@ char *acpi_db_get_next_token(char *string,
 			     char **next, acpi_object_type * return_type);
 
 /*
+ * dbobject
+ */
+void acpi_db_decode_internal_object(union acpi_operand_object *obj_desc);
+
+void
+acpi_db_display_internal_object(union acpi_operand_object *obj_desc,
+				struct acpi_walk_state *walk_state);
+
+void acpi_db_decode_arguments(struct acpi_walk_state *walk_state);
+
+void acpi_db_decode_locals(struct acpi_walk_state *walk_state);
+
+void
+acpi_db_dump_method_info(acpi_status status,
+			 struct acpi_walk_state *walk_state);
+
+/*
  * dbstats - Generation and display of ACPI table statistics
  */
 void acpi_db_generate_statistics(union acpi_parse_object *root, u8 is_method);
diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h
index 408f04bcaab4..7094dc89eb81 100644
--- a/drivers/acpi/acpica/acdispat.h
+++ b/drivers/acpi/acpica/acdispat.h
@@ -354,4 +354,12 @@ acpi_status
 acpi_ds_result_push(union acpi_operand_object *object,
 		    struct acpi_walk_state *walk_state);
 
+/*
+ * dsdebug - parser debugging routines
+ */
+void
+acpi_ds_dump_method_stack(acpi_status status,
+			  struct acpi_walk_state *walk_state,
+			  union acpi_parse_object *op);
+
 #endif				/* _ACDISPAT_H_ */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 53f96a370762..09f37b516808 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -58,11 +58,12 @@ ACPI_GLOBAL(struct acpi_table_list, acpi_gbl_root_table_list);
 
 ACPI_GLOBAL(struct acpi_table_header *, acpi_gbl_DSDT);
 ACPI_GLOBAL(struct acpi_table_header, acpi_gbl_original_dsdt_header);
+ACPI_INIT_GLOBAL(u32, acpi_gbl_dsdt_index, ACPI_INVALID_TABLE_INDEX);
+ACPI_INIT_GLOBAL(u32, acpi_gbl_facs_index, ACPI_INVALID_TABLE_INDEX);
+ACPI_INIT_GLOBAL(u32, acpi_gbl_xfacs_index, ACPI_INVALID_TABLE_INDEX);
 
 #if (!ACPI_REDUCED_HARDWARE)
 ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_FACS);
-ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_facs32);
-ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_facs64);
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
@@ -235,6 +236,10 @@ ACPI_INIT_GLOBAL(u32, acpi_gbl_nesting_level, 0);
 
 ACPI_GLOBAL(struct acpi_thread_state *, acpi_gbl_current_walk_list);
 
+/* Maximum number of While() loop iterations before forced abort */
+
+ACPI_GLOBAL(u16, acpi_gbl_max_loop_iterations);
+
 /* Control method single step flag */
 
 ACPI_GLOBAL(u8, acpi_gbl_cm_single_step);
@@ -290,8 +295,6 @@ ACPI_GLOBAL(u32, acpi_fixed_event_count[ACPI_NUM_FIXED_EVENTS]);
 
 ACPI_GLOBAL(u32, acpi_gbl_original_dbg_level);
 ACPI_GLOBAL(u32, acpi_gbl_original_dbg_layer);
-ACPI_GLOBAL(u32, acpi_gbl_trace_dbg_level);
-ACPI_GLOBAL(u32, acpi_gbl_trace_dbg_layer);
 
 /*****************************************************************************
  *
@@ -309,9 +312,10 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_no_resource_disassembly, FALSE);
 ACPI_INIT_GLOBAL(u8, acpi_gbl_ignore_noop_operator, FALSE);
 ACPI_INIT_GLOBAL(u8, acpi_gbl_cstyle_disassembly, TRUE);
 ACPI_INIT_GLOBAL(u8, acpi_gbl_force_aml_disassembly, FALSE);
+ACPI_INIT_GLOBAL(u8, acpi_gbl_dm_opt_verbose, TRUE);
 
-ACPI_GLOBAL(u8, acpi_gbl_db_opt_disasm);
-ACPI_GLOBAL(u8, acpi_gbl_db_opt_verbose);
+ACPI_GLOBAL(u8, acpi_gbl_dm_opt_disasm);
+ACPI_GLOBAL(u8, acpi_gbl_dm_opt_listing);
 ACPI_GLOBAL(u8, acpi_gbl_num_external_methods);
 ACPI_GLOBAL(u32, acpi_gbl_resolved_external_methods);
 ACPI_GLOBAL(struct acpi_external_list *, acpi_gbl_external_list);
@@ -346,8 +350,8 @@ ACPI_GLOBAL(char, acpi_gbl_db_debug_filename[ACPI_DB_LINE_BUFFER_SIZE]);
 /*
  * Statistic globals
  */
-ACPI_GLOBAL(u16, acpi_gbl_obj_type_count[ACPI_TYPE_NS_NODE_MAX + 1]);
-ACPI_GLOBAL(u16, acpi_gbl_node_type_count[ACPI_TYPE_NS_NODE_MAX + 1]);
+ACPI_GLOBAL(u16, acpi_gbl_obj_type_count[ACPI_TOTAL_TYPES]);
+ACPI_GLOBAL(u16, acpi_gbl_node_type_count[ACPI_TOTAL_TYPES]);
 ACPI_GLOBAL(u16, acpi_gbl_obj_type_count_misc);
 ACPI_GLOBAL(u16, acpi_gbl_node_type_count_misc);
 ACPI_GLOBAL(u32, acpi_gbl_num_nodes);
diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h
index 7ac98000b46b..e820ed8f173f 100644
--- a/drivers/acpi/acpica/acinterp.h
+++ b/drivers/acpi/acpica/acinterp.h
@@ -131,6 +131,28 @@ void
 acpi_ex_do_debug_object(union acpi_operand_object *source_desc,
 			u32 level, u32 index);
 
+void
+acpi_ex_start_trace_method(struct acpi_namespace_node *method_node,
+			   union acpi_operand_object *obj_desc,
+			   struct acpi_walk_state *walk_state);
+
+void
+acpi_ex_stop_trace_method(struct acpi_namespace_node *method_node,
+			  union acpi_operand_object *obj_desc,
+			  struct acpi_walk_state *walk_state);
+
+void
+acpi_ex_start_trace_opcode(union acpi_parse_object *op,
+			   struct acpi_walk_state *walk_state);
+
+void
+acpi_ex_stop_trace_opcode(union acpi_parse_object *op,
+			  struct acpi_walk_state *walk_state);
+
+void
+acpi_ex_trace_point(acpi_trace_event_type type,
+		    u8 begin, u8 *aml, char *pathname);
+
 /*
  * exfield - ACPI AML (p-code) execution - field manipulation
  */
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index bc600969c6a1..6f708267ad8c 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -174,8 +174,12 @@ struct acpi_namespace_node {
 	 */
 #ifdef ACPI_LARGE_NAMESPACE_NODE
 	union acpi_parse_object *op;
+	void *method_locals;
+	void *method_args;
 	u32 value;
 	u32 length;
+	u8 arg_count;
+
 #endif
 };
 
@@ -209,11 +213,9 @@ struct acpi_table_list {
 #define ACPI_ROOT_ORIGIN_ALLOCATED      (1)
 #define ACPI_ROOT_ALLOW_RESIZE          (2)
 
-/* Predefined (fixed) table indexes */
+/* Predefined table indexes */
 
-#define ACPI_TABLE_INDEX_DSDT           (0)
-#define ACPI_TABLE_INDEX_FACS           (1)
-#define ACPI_TABLE_INDEX_X_FACS         (2)
+#define ACPI_INVALID_TABLE_INDEX        (0xFFFFFFFF)
 
 struct acpi_find_context {
 	char *search_for;
@@ -404,6 +406,13 @@ struct acpi_simple_repair_info {
 
 #define ACPI_NUM_RTYPES                 5	/* Number of actual object types */
 
+/* Info for running the _REG methods */
+
+struct acpi_reg_walk_info {
+	acpi_adr_space_type space_id;
+	u32 reg_run_count;
+};
+
 /*****************************************************************************
  *
  * Event typedefs and structs
@@ -715,7 +724,7 @@ union acpi_parse_value {
 	union acpi_parse_object *arg;	/* arguments and contained ops */
 };
 
-#ifdef ACPI_DISASSEMBLER
+#if defined(ACPI_DISASSEMBLER) || defined(ACPI_DEBUG_OUTPUT)
 #define ACPI_DISASM_ONLY_MEMBERS(a)     a;
 #else
 #define ACPI_DISASM_ONLY_MEMBERS(a)
@@ -726,7 +735,7 @@ union acpi_parse_value {
 	u8                              descriptor_type; /* To differentiate various internal objs */\
 	u8                              flags;          /* Type of Op */\
 	u16                             aml_opcode;     /* AML opcode */\
-	u32                             aml_offset;     /* Offset of declaration in AML */\
+	u8                              *aml;           /* Address of declaration in AML */\
 	union acpi_parse_object         *next;          /* Next op */\
 	struct acpi_namespace_node      *node;          /* For use by interpreter */\
 	union acpi_parse_value          value;          /* Value or args associated with the opcode */\
@@ -1103,6 +1112,9 @@ struct acpi_db_method_info {
 	 *   Index of current thread inside all them created.
 	 */
 	char init_args;
+#ifdef ACPI_DEBUGGER
+	acpi_object_type arg_types[4];
+#endif
 	char *arguments[4];
 	char num_threads_str[11];
 	char id_of_thread_str[11];
@@ -1119,6 +1131,10 @@ struct acpi_integrity_info {
 #define ACPI_DB_CONSOLE_OUTPUT          0x02
 #define ACPI_DB_DUPLICATE_OUTPUT        0x03
 
+struct acpi_object_info {
+	u32 types[ACPI_TOTAL_TYPES];
+};
+
 /*****************************************************************************
  *
  * Debug
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index c240bdf824f2..e85366ceb15a 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -220,6 +220,15 @@
 #define ACPI_MUL_32(a)                  _ACPI_MUL(a, 5)
 #define ACPI_MOD_32(a)                  _ACPI_MOD(a, 32)
 
+/* Test for ASCII character */
+
+#define ACPI_IS_ASCII(c)                ((c) < 0x80)
+
+/* Signed integers */
+
+#define ACPI_SIGN_POSITIVE              0
+#define ACPI_SIGN_NEGATIVE              1
+
 /*
  * Rounding macros (Power of two boundaries only)
  */
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 0dd088290d80..ea0d9076d408 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -272,17 +272,20 @@ acpi_ns_check_package(struct acpi_evaluate_info *info,
  */
 u32 acpi_ns_opens_scope(acpi_object_type type);
 
-acpi_status
-acpi_ns_build_external_path(struct acpi_namespace_node *node,
-			    acpi_size size, char *name_buffer);
-
 char *acpi_ns_get_external_pathname(struct acpi_namespace_node *node);
 
+u32
+acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
+			      char *full_path, u32 path_size, u8 no_trailing);
+
+char *acpi_ns_get_normalized_pathname(struct acpi_namespace_node *node,
+				      u8 no_trailing);
+
 char *acpi_ns_name_of_current_scope(struct acpi_walk_state *walk_state);
 
 acpi_status
 acpi_ns_handle_to_pathname(acpi_handle target_handle,
-			   struct acpi_buffer *buffer);
+			   struct acpi_buffer *buffer, u8 no_trailing);
 
 u8
 acpi_ns_pattern_match(struct acpi_namespace_node *obj_node, char *search_for);
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index c81d98d09cac..0bd02c4a5f75 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -176,6 +176,7 @@ struct acpi_object_method {
 	u8 param_count;
 	u8 sync_level;
 	union acpi_operand_object *mutex;
+	union acpi_operand_object *node;
 	u8 *aml_start;
 	union {
 		acpi_internal_method implementation;
diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h
index 0cdd2fce493a..6021ccfb0b1c 100644
--- a/drivers/acpi/acpica/acparser.h
+++ b/drivers/acpi/acpica/acparser.h
@@ -225,11 +225,11 @@ void acpi_ps_delete_parse_tree(union acpi_parse_object *root);
 /*
  * psutils - parser utilities
  */
-union acpi_parse_object *acpi_ps_create_scope_op(void);
+union acpi_parse_object *acpi_ps_create_scope_op(u8 *aml);
 
 void acpi_ps_init_op(union acpi_parse_object *op, u16 opcode);
 
-union acpi_parse_object *acpi_ps_alloc_op(u16 opcode);
+union acpi_parse_object *acpi_ps_alloc_op(u16 opcode, u8 *aml);
 
 void acpi_ps_free_op(union acpi_parse_object *op);
 
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index 44997ca02ae2..f9992dced1f9 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -85,7 +85,7 @@ struct acpi_walk_state {
 	u8 namespace_override;	/* Override existing objects */
 	u8 result_size;		/* Total elements for the result stack */
 	u8 result_count;	/* Current number of occupied elements of result stack */
-	u32 aml_offset;
+	u8 *aml;
 	u32 arg_types;
 	u32 method_breakpoint;	/* For single stepping */
 	u32 user_breakpoint;	/* User AML breakpoint */
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index 7e0b6f1bec9c..f7731f260c31 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -154,14 +154,20 @@ void acpi_tb_check_dsdt_header(void);
 struct acpi_table_header *acpi_tb_copy_dsdt(u32 table_index);
 
 void
-acpi_tb_install_table_with_override(u32 table_index,
-				    struct acpi_table_desc *new_table_desc,
-				    u8 override);
+acpi_tb_install_table_with_override(struct acpi_table_desc *new_table_desc,
+				    u8 override, u32 *table_index);
 
 acpi_status
 acpi_tb_install_fixed_table(acpi_physical_address address,
-			    char *signature, u32 table_index);
+			    char *signature, u32 *table_index);
 
 acpi_status acpi_tb_parse_root_table(acpi_physical_address rsdp_address);
 
+u8 acpi_is_valid_signature(char *signature);
+
+/*
+ * tbxfload
+ */
+acpi_status acpi_tb_load_namespace(void);
+
 #endif				/* __ACTABLES_H__ */
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 6de0d3573037..fb2aa5066f3f 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -167,6 +167,17 @@ struct acpi_pkg_info {
 #define DB_QWORD_DISPLAY    8
 
 /*
+ * utnonansi - Non-ANSI C library functions
+ */
+void acpi_ut_strupr(char *src_string);
+
+void acpi_ut_strlwr(char *src_string);
+
+int acpi_ut_stricmp(char *string1, char *string2);
+
+acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer);
+
+/*
  * utglobal - Global data structures and procedures
  */
 acpi_status acpi_ut_init_globals(void);
@@ -205,8 +216,6 @@ acpi_status acpi_ut_hardware_initialize(void);
 
 void acpi_ut_subsystem_shutdown(void);
 
-#define ACPI_IS_ASCII(c)  ((c) < 0x80)
-
 /*
  * utcopy - Object construction and conversion interfaces
  */
@@ -508,7 +517,7 @@ const struct acpi_exception_info *acpi_ut_validate_exception(acpi_status
 
 u8 acpi_ut_is_pci_root_bridge(char *id);
 
-#if (defined ACPI_ASL_COMPILER || defined ACPI_EXEC_APP)
+#if (defined ACPI_ASL_COMPILER || defined ACPI_EXEC_APP || defined ACPI_NAMES_APP)
 u8 acpi_ut_is_aml_table(struct acpi_table_header *table);
 #endif
 
@@ -567,16 +576,6 @@ acpi_ut_get_resource_end_tag(union acpi_operand_object *obj_desc, u8 **end_tag);
 /*
  * utstring - String and character utilities
  */
-void acpi_ut_strupr(char *src_string);
-
-#ifdef ACPI_ASL_COMPILER
-void acpi_ut_strlwr(char *src_string);
-
-int acpi_ut_stricmp(char *string1, char *string2);
-#endif
-
-acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer);
-
 void acpi_ut_print_string(char *string, u16 max_length);
 
 #if defined ACPI_ASL_COMPILER || defined ACPI_EXEC_APP
diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c
index 3e6989738e85..e2ab59e39162 100644
--- a/drivers/acpi/acpica/dsargs.c
+++ b/drivers/acpi/acpica/dsargs.c
@@ -86,7 +86,7 @@ acpi_ds_execute_arguments(struct acpi_namespace_node *node,
 
 	/* Allocate a new parser op to be the root of the parsed tree */
 
-	op = acpi_ps_alloc_op(AML_INT_EVAL_SUBTREE_OP);
+	op = acpi_ps_alloc_op(AML_INT_EVAL_SUBTREE_OP, aml_start);
 	if (!op) {
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
@@ -129,7 +129,7 @@ acpi_ds_execute_arguments(struct acpi_namespace_node *node,
 
 	/* Evaluate the deferred arguments */
 
-	op = acpi_ps_alloc_op(AML_INT_EVAL_SUBTREE_OP);
+	op = acpi_ps_alloc_op(AML_INT_EVAL_SUBTREE_OP, aml_start);
 	if (!op) {
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 39da9da62bbf..435fc16e2f83 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -212,7 +212,7 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state * walk_state,
 			 */
 			control_state->control.loop_count++;
 			if (control_state->control.loop_count >
-			    ACPI_MAX_LOOP_ITERATIONS) {
+			    acpi_gbl_max_loop_iterations) {
 				status = AE_AML_INFINITE_LOOP;
 				break;
 			}
diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c
new file mode 100644
index 000000000000..309556efc553
--- /dev/null
+++ b/drivers/acpi/acpica/dsdebug.c
@@ -0,0 +1,231 @@
+/******************************************************************************
+ *
+ * Module Name: dsdebug - Parser/Interpreter interface - debugging
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2015, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+#include "acdispat.h"
+#include "acnamesp.h"
+#ifdef ACPI_DISASSEMBLER
+#include "acdisasm.h"
+#endif
+#include "acinterp.h"
+
+#define _COMPONENT          ACPI_DISPATCHER
+ACPI_MODULE_NAME("dsdebug")
+
+#if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
+/* Local prototypes */
+static void
+acpi_ds_print_node_pathname(struct acpi_namespace_node *node,
+			    const char *message);
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ds_print_node_pathname
+ *
+ * PARAMETERS:  node            - Object
+ *              message         - Prefix message
+ *
+ * DESCRIPTION: Print an object's full namespace pathname
+ *              Manages allocation/freeing of a pathname buffer
+ *
+ ******************************************************************************/
+
+static void
+acpi_ds_print_node_pathname(struct acpi_namespace_node *node,
+			    const char *message)
+{
+	struct acpi_buffer buffer;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(ds_print_node_pathname);
+
+	if (!node) {
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_DISPATCH, "[NULL NAME]"));
+		return_VOID;
+	}
+
+	/* Convert handle to full pathname and print it (with supplied message) */
+
+	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
+
+	status = acpi_ns_handle_to_pathname(node, &buffer, TRUE);
+	if (ACPI_SUCCESS(status)) {
+		if (message) {
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DISPATCH, "%s ",
+					      message));
+		}
+
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_DISPATCH, "[%s] (Node %p)",
+				      (char *)buffer.pointer, node));
+		ACPI_FREE(buffer.pointer);
+	}
+
+	return_VOID;
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ds_dump_method_stack
+ *
+ * PARAMETERS:  status          - Method execution status
+ *              walk_state      - Current state of the parse tree walk
+ *              op              - Executing parse op
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Called when a method has been aborted because of an error.
+ *              Dumps the method execution stack.
+ *
+ ******************************************************************************/
+
+void
+acpi_ds_dump_method_stack(acpi_status status,
+			  struct acpi_walk_state *walk_state,
+			  union acpi_parse_object *op)
+{
+	union acpi_parse_object *next;
+	struct acpi_thread_state *thread;
+	struct acpi_walk_state *next_walk_state;
+	struct acpi_namespace_node *previous_method = NULL;
+	union acpi_operand_object *method_desc;
+
+	ACPI_FUNCTION_TRACE(ds_dump_method_stack);
+
+	/* Ignore control codes, they are not errors */
+
+	if ((status & AE_CODE_MASK) == AE_CODE_CONTROL) {
+		return_VOID;
+	}
+
+	/* We may be executing a deferred opcode */
+
+	if (walk_state->deferred_node) {
+		ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
+				  "Executing subtree for Buffer/Package/Region\n"));
+		return_VOID;
+	}
+
+	/*
+	 * If there is no Thread, we are not actually executing a method.
+	 * This can happen when the iASL compiler calls the interpreter
+	 * to perform constant folding.
+	 */
+	thread = walk_state->thread;
+	if (!thread) {
+		return_VOID;
+	}
+
+	/* Display exception and method name */
+
+	ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
+			  "\n**** Exception %s during execution of method ",
+			  acpi_format_exception(status)));
+	acpi_ds_print_node_pathname(walk_state->method_node, NULL);
+
+	/* Display stack of executing methods */
+
+	ACPI_DEBUG_PRINT_RAW((ACPI_DB_DISPATCH,
+			      "\n\nMethod Execution Stack:\n"));
+	next_walk_state = thread->walk_state_list;
+
+	/* Walk list of linked walk states */
+
+	while (next_walk_state) {
+		method_desc = next_walk_state->method_desc;
+		if (method_desc) {
+			acpi_ex_stop_trace_method((struct acpi_namespace_node *)
+						  method_desc->method.node,
+						  method_desc, walk_state);
+		}
+
+		ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
+				  "    Method [%4.4s] executing: ",
+				  acpi_ut_get_node_name(next_walk_state->
+							method_node)));
+
+		/* First method is the currently executing method */
+
+		if (next_walk_state == walk_state) {
+			if (op) {
+
+				/* Display currently executing ASL statement */
+
+				next = op->common.next;
+				op->common.next = NULL;
+
+#ifdef ACPI_DISASSEMBLER
+				acpi_dm_disassemble(next_walk_state, op,
+						    ACPI_UINT32_MAX);
+#endif
+				op->common.next = next;
+			}
+		} else {
+			/*
+			 * This method has called another method
+			 * NOTE: the method call parse subtree is already deleted at this
+			 * point, so we cannot disassemble the method invocation.
+			 */
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DISPATCH,
+					      "Call to method "));
+			acpi_ds_print_node_pathname(previous_method, NULL);
+		}
+
+		previous_method = next_walk_state->method_node;
+		next_walk_state = next_walk_state->next;
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_DISPATCH, "\n"));
+	}
+
+	return_VOID;
+}
+
+#else
+void
+acpi_ds_dump_method_stack(acpi_status status,
+			  struct acpi_walk_state *walk_state,
+			  union acpi_parse_object *op)
+{
+	return;
+}
+
+#endif
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index 95779e8ec3bb..920f1b199bc6 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -237,12 +237,22 @@ acpi_ds_initialize_objects(u32 table_index,
 		return_ACPI_STATUS(status);
 	}
 
+	/* DSDT is always the first AML table */
+
+	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT)) {
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
+				      "\nInitializing Namespace objects:\n"));
+	}
+
+	/* Summary of objects initialized */
+
 	ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
-			      "Table [%4.4s] (id %4.4X) - %4u Objects with %3u Devices, "
-			      "%3u Regions, %3u Methods (%u/%u/%u Serial/Non/Cvt)\n",
-			      table->signature, owner_id, info.object_count,
-			      info.device_count, info.op_region_count,
-			      info.method_count, info.serial_method_count,
+			      "Table [%4.4s:%8.8s] (id %.2X) - %4u Objects with %3u Devices, "
+			      "%3u Regions, %4u Methods (%u/%u/%u Serial/Non/Cvt)\n",
+			      table->signature, table->oem_table_id, owner_id,
+			      info.object_count, info.device_count,
+			      info.op_region_count, info.method_count,
+			      info.serial_method_count,
 			      info.non_serial_method_count,
 			      info.serialized_method_count));
 
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index 85bb951430d9..bc32f3194afe 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -46,11 +46,9 @@
 #include "acdispat.h"
 #include "acinterp.h"
 #include "acnamesp.h"
-#ifdef	ACPI_DISASSEMBLER
-#include "acdisasm.h"
-#endif
 #include "acparser.h"
 #include "amlcode.h"
+#include "acdebug.h"
 
 #define _COMPONENT          ACPI_DISPATCHER
 ACPI_MODULE_NAME("dsmethod")
@@ -103,7 +101,7 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 
 	/* Create/Init a root op for the method parse tree */
 
-	op = acpi_ps_alloc_op(AML_METHOD_OP);
+	op = acpi_ps_alloc_op(AML_METHOD_OP, obj_desc->method.aml_start);
 	if (!op) {
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
@@ -205,7 +203,7 @@ acpi_ds_detect_named_opcodes(struct acpi_walk_state *walk_state,
  * RETURN:      Status
  *
  * DESCRIPTION: Called on method error. Invoke the global exception handler if
- *              present, dump the method data if the disassembler is configured
+ *              present, dump the method data if the debugger is configured
  *
  *              Note: Allows the exception handler to change the status code
  *
@@ -214,6 +212,8 @@ acpi_ds_detect_named_opcodes(struct acpi_walk_state *walk_state,
 acpi_status
 acpi_ds_method_error(acpi_status status, struct acpi_walk_state * walk_state)
 {
+	u32 aml_offset;
+
 	ACPI_FUNCTION_ENTRY();
 
 	/* Ignore AE_OK and control exception codes */
@@ -234,26 +234,30 @@ acpi_ds_method_error(acpi_status status, struct acpi_walk_state * walk_state)
 		 * Handler can map the exception code to anything it wants, including
 		 * AE_OK, in which case the executing method will not be aborted.
 		 */
+		aml_offset = (u32)ACPI_PTR_DIFF(walk_state->aml,
+						walk_state->parser_state.
+						aml_start);
+
 		status = acpi_gbl_exception_handler(status,
 						    walk_state->method_node ?
 						    walk_state->method_node->
 						    name.integer : 0,
 						    walk_state->opcode,
-						    walk_state->aml_offset,
-						    NULL);
+						    aml_offset, NULL);
 		acpi_ex_enter_interpreter();
 	}
 
 	acpi_ds_clear_implicit_return(walk_state);
 
-#ifdef ACPI_DISASSEMBLER
 	if (ACPI_FAILURE(status)) {
+		acpi_ds_dump_method_stack(status, walk_state, walk_state->op);
 
-		/* Display method locals/args if disassembler is present */
+		/* Display method locals/args if debugger is present */
 
-		acpi_dm_dump_method_info(status, walk_state, walk_state->op);
-	}
+#ifdef ACPI_DEBUGGER
+		acpi_db_dump_method_info(status, walk_state);
 #endif
+	}
 
 	return (status);
 }
@@ -328,6 +332,8 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node,
 		return_ACPI_STATUS(AE_NULL_ENTRY);
 	}
 
+	acpi_ex_start_trace_method(method_node, obj_desc, walk_state);
+
 	/* Prevent wraparound of thread count */
 
 	if (obj_desc->method.thread_count == ACPI_UINT8_MAX) {
@@ -574,9 +580,7 @@ cleanup:
 	/* On error, we must terminate the method properly */
 
 	acpi_ds_terminate_control_method(obj_desc, next_walk_state);
-	if (next_walk_state) {
-		acpi_ds_delete_walk_state(next_walk_state);
-	}
+	acpi_ds_delete_walk_state(next_walk_state);
 
 	return_ACPI_STATUS(status);
 }
@@ -826,5 +830,8 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc,
 		}
 	}
 
+	acpi_ex_stop_trace_method((struct acpi_namespace_node *)method_desc->
+				  method.node, method_desc, walk_state);
+
 	return_VOID;
 }
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index ea0cc4e08f80..81d7b9863e32 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -480,8 +480,8 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state,
 	union acpi_operand_object **operand;
 	struct acpi_namespace_node *node;
 	union acpi_parse_object *next_op;
-	u32 table_index;
 	struct acpi_table_header *table;
+	u32 table_index;
 
 	ACPI_FUNCTION_TRACE_PTR(ds_eval_table_region_operands, op);
 
@@ -504,6 +504,8 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state,
 		return_ACPI_STATUS(status);
 	}
 
+	operand = &walk_state->operands[0];
+
 	/*
 	 * Resolve the Signature string, oem_id string,
 	 * and oem_table_id string operands
@@ -511,32 +513,34 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state,
 	status = acpi_ex_resolve_operands(op->common.aml_opcode,
 					  ACPI_WALK_OPERANDS, walk_state);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		goto cleanup;
 	}
 
-	operand = &walk_state->operands[0];
-
 	/* Find the ACPI table */
 
 	status = acpi_tb_find_table(operand[0]->string.pointer,
 				    operand[1]->string.pointer,
 				    operand[2]->string.pointer, &table_index);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		if (status == AE_NOT_FOUND) {
+			ACPI_ERROR((AE_INFO,
+				    "ACPI Table [%4.4s] OEM:(%s, %s) not found in RSDT/XSDT",
+				    operand[0]->string.pointer,
+				    operand[1]->string.pointer,
+				    operand[2]->string.pointer));
+		}
+		goto cleanup;
 	}
 
-	acpi_ut_remove_reference(operand[0]);
-	acpi_ut_remove_reference(operand[1]);
-	acpi_ut_remove_reference(operand[2]);
-
 	status = acpi_get_table_by_index(table_index, &table);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		goto cleanup;
 	}
 
 	obj_desc = acpi_ns_get_attached_object(node);
 	if (!obj_desc) {
-		return_ACPI_STATUS(AE_NOT_EXIST);
+		status = AE_NOT_EXIST;
+		goto cleanup;
 	}
 
 	obj_desc->region.address = ACPI_PTR_TO_PHYSADDR(table);
@@ -551,6 +555,11 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state,
 
 	obj_desc->region.flags |= AOPOBJ_DATA_VALID;
 
+cleanup:
+	acpi_ut_remove_reference(operand[0]);
+	acpi_ut_remove_reference(operand[1]);
+	acpi_ut_remove_reference(operand[2]);
+
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index 845ff44919c3..097188a6b1c1 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -388,7 +388,7 @@ acpi_ds_load1_begin_op(struct acpi_walk_state * walk_state,
 
 		/* Create a new op */
 
-		op = acpi_ps_alloc_op(walk_state->opcode);
+		op = acpi_ps_alloc_op(walk_state->opcode, walk_state->aml);
 		if (!op) {
 			return_ACPI_STATUS(AE_NO_MEMORY);
 		}
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index fcaa30c611fb..e2c08cd79aca 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -335,7 +335,7 @@ acpi_ds_load2_begin_op(struct acpi_walk_state *walk_state,
 
 		/* Create a new op */
 
-		op = acpi_ps_alloc_op(walk_state->opcode);
+		op = acpi_ps_alloc_op(walk_state->opcode, walk_state->aml);
 		if (!op) {
 			return_ACPI_STATUS(AE_NO_MEMORY);
 		}
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 2ba28a63fb68..5ee79a16fe33 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -626,9 +626,17 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 			    acpi_adr_space_type space_id)
 {
 	acpi_status status;
+	struct acpi_reg_walk_info info;
 
 	ACPI_FUNCTION_TRACE(ev_execute_reg_methods);
 
+	info.space_id = space_id;
+	info.reg_run_count = 0;
+
+	ACPI_DEBUG_PRINT_RAW((ACPI_DB_NAMES,
+			      "    Running _REG methods for SpaceId %s\n",
+			      acpi_ut_get_region_name(info.space_id)));
+
 	/*
 	 * Run all _REG methods for all Operation Regions for this space ID. This
 	 * is a separate walk in order to handle any interdependencies between
@@ -637,7 +645,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 	 */
 	status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX,
 					ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run,
-					NULL, &space_id, NULL);
+					NULL, &info, NULL);
 
 	/* Special case for EC: handle "orphan" _REG methods with no region */
 
@@ -645,6 +653,11 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 		acpi_ev_orphan_ec_reg_method(node);
 	}
 
+	ACPI_DEBUG_PRINT_RAW((ACPI_DB_NAMES,
+			      "    Executed %u _REG methods for SpaceId %s\n",
+			      info.reg_run_count,
+			      acpi_ut_get_region_name(info.space_id)));
+
 	return_ACPI_STATUS(status);
 }
 
@@ -664,10 +677,10 @@ acpi_ev_reg_run(acpi_handle obj_handle,
 {
 	union acpi_operand_object *obj_desc;
 	struct acpi_namespace_node *node;
-	acpi_adr_space_type space_id;
 	acpi_status status;
+	struct acpi_reg_walk_info *info;
 
-	space_id = *ACPI_CAST_PTR(acpi_adr_space_type, context);
+	info = ACPI_CAST_PTR(struct acpi_reg_walk_info, context);
 
 	/* Convert and validate the device handle */
 
@@ -696,13 +709,14 @@ acpi_ev_reg_run(acpi_handle obj_handle,
 
 	/* Object is a Region */
 
-	if (obj_desc->region.space_id != space_id) {
+	if (obj_desc->region.space_id != info->space_id) {
 
 		/* This region is for a different address space, just ignore it */
 
 		return (AE_OK);
 	}
 
+	info->reg_run_count++;
 	status = acpi_ev_execute_reg_method(obj_desc, ACPI_REG_CONNECT);
 	return (status);
 }
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 24a4c5c2b124..b540913c11ac 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -162,14 +162,6 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state,
 
 	ACPI_FUNCTION_TRACE(ex_load_table_op);
 
-	/* Validate lengths for the Signature, oem_id, and oem_table_id strings */
-
-	if ((operand[0]->string.length > ACPI_NAME_SIZE) ||
-	    (operand[1]->string.length > ACPI_OEM_ID_SIZE) ||
-	    (operand[2]->string.length > ACPI_OEM_TABLE_ID_SIZE)) {
-		return_ACPI_STATUS(AE_AML_STRING_LIMIT);
-	}
-
 	/* Find the ACPI table in the RSDT/XSDT */
 
 	status = acpi_tb_find_table(operand[0]->string.pointer,
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index aaeea4840aaa..ccb7219bdcee 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -486,6 +486,7 @@ acpi_ex_create_method(u8 * aml_start,
 
 	obj_desc->method.aml_start = aml_start;
 	obj_desc->method.aml_length = aml_length;
+	obj_desc->method.node = operand[0];
 
 	/*
 	 * Disassemble the method flags. Split off the arg_count, Serialized
diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c
index 815442bbd051..de92458236f5 100644
--- a/drivers/acpi/acpica/exdebug.c
+++ b/drivers/acpi/acpica/exdebug.c
@@ -43,11 +43,21 @@
 
 #include <acpi/acpi.h>
 #include "accommon.h"
+#include "acnamesp.h"
 #include "acinterp.h"
+#include "acparser.h"
 
 #define _COMPONENT          ACPI_EXECUTER
 ACPI_MODULE_NAME("exdebug")
 
+static union acpi_operand_object *acpi_gbl_trace_method_object = NULL;
+
+/* Local prototypes */
+
+#ifdef ACPI_DEBUG_OUTPUT
+static const char *acpi_ex_get_trace_event_name(acpi_trace_event_type type);
+#endif
+
 #ifndef ACPI_NO_ERROR_MESSAGES
 /*******************************************************************************
  *
@@ -70,6 +80,7 @@ ACPI_MODULE_NAME("exdebug")
  * enabled if necessary.
  *
  ******************************************************************************/
+
 void
 acpi_ex_do_debug_object(union acpi_operand_object *source_desc,
 			u32 level, u32 index)
@@ -308,3 +319,316 @@ acpi_ex_do_debug_object(union acpi_operand_object *source_desc,
 	return_VOID;
 }
 #endif
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_interpreter_trace_enabled
+ *
+ * PARAMETERS:  name                - Whether method name should be matched,
+ *                                    this should be checked before starting
+ *                                    the tracer
+ *
+ * RETURN:      TRUE if interpreter trace is enabled.
+ *
+ * DESCRIPTION: Check whether interpreter trace is enabled
+ *
+ ******************************************************************************/
+
+static u8 acpi_ex_interpreter_trace_enabled(char *name)
+{
+
+	/* Check if tracing is enabled */
+
+	if (!(acpi_gbl_trace_flags & ACPI_TRACE_ENABLED)) {
+		return (FALSE);
+	}
+
+	/*
+	 * Check if tracing is filtered:
+	 *
+	 * 1. If the tracer is started, acpi_gbl_trace_method_object should have
+	 *    been filled by the trace starter
+	 * 2. If the tracer is not started, acpi_gbl_trace_method_name should be
+	 *    matched if it is specified
+	 * 3. If the tracer is oneshot style, acpi_gbl_trace_method_name should
+	 *    not be cleared by the trace stopper during the first match
+	 */
+	if (acpi_gbl_trace_method_object) {
+		return (TRUE);
+	}
+	if (name &&
+	    (acpi_gbl_trace_method_name &&
+	     strcmp(acpi_gbl_trace_method_name, name))) {
+		return (FALSE);
+	}
+	if ((acpi_gbl_trace_flags & ACPI_TRACE_ONESHOT) &&
+	    !acpi_gbl_trace_method_name) {
+		return (FALSE);
+	}
+
+	return (TRUE);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_get_trace_event_name
+ *
+ * PARAMETERS:  type            - Trace event type
+ *
+ * RETURN:      Trace event name.
+ *
+ * DESCRIPTION: Used to obtain the full trace event name.
+ *
+ ******************************************************************************/
+
+#ifdef ACPI_DEBUG_OUTPUT
+
+static const char *acpi_ex_get_trace_event_name(acpi_trace_event_type type)
+{
+	switch (type) {
+	case ACPI_TRACE_AML_METHOD:
+
+		return "Method";
+
+	case ACPI_TRACE_AML_OPCODE:
+
+		return "Opcode";
+
+	case ACPI_TRACE_AML_REGION:
+
+		return "Region";
+
+	default:
+
+		return "";
+	}
+}
+
+#endif
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_trace_point
+ *
+ * PARAMETERS:  type                - Trace event type
+ *              begin               - TRUE if before execution
+ *              aml                 - Executed AML address
+ *              pathname            - Object path
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Internal interpreter execution trace.
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_trace_point(acpi_trace_event_type type,
+		    u8 begin, u8 *aml, char *pathname)
+{
+
+	ACPI_FUNCTION_NAME(ex_trace_point);
+
+	if (pathname) {
+		ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT,
+				  "%s %s [0x%p:%s] execution.\n",
+				  acpi_ex_get_trace_event_name(type),
+				  begin ? "Begin" : "End", aml, pathname));
+	} else {
+		ACPI_DEBUG_PRINT((ACPI_DB_TRACE_POINT,
+				  "%s %s [0x%p] execution.\n",
+				  acpi_ex_get_trace_event_name(type),
+				  begin ? "Begin" : "End", aml));
+	}
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_start_trace_method
+ *
+ * PARAMETERS:  method_node         - Node of the method
+ *              obj_desc            - The method object
+ *              walk_state          - current state, NULL if not yet executing
+ *                                    a method.
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Start control method execution trace
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_start_trace_method(struct acpi_namespace_node *method_node,
+			   union acpi_operand_object *obj_desc,
+			   struct acpi_walk_state *walk_state)
+{
+	acpi_status status;
+	char *pathname = NULL;
+	u8 enabled = FALSE;
+
+	ACPI_FUNCTION_NAME(ex_start_trace_method);
+
+	if (method_node) {
+		pathname = acpi_ns_get_normalized_pathname(method_node, TRUE);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+	if (ACPI_FAILURE(status)) {
+		goto exit;
+	}
+
+	enabled = acpi_ex_interpreter_trace_enabled(pathname);
+	if (enabled && !acpi_gbl_trace_method_object) {
+		acpi_gbl_trace_method_object = obj_desc;
+		acpi_gbl_original_dbg_level = acpi_dbg_level;
+		acpi_gbl_original_dbg_layer = acpi_dbg_layer;
+		acpi_dbg_level = ACPI_TRACE_LEVEL_ALL;
+		acpi_dbg_layer = ACPI_TRACE_LAYER_ALL;
+
+		if (acpi_gbl_trace_dbg_level) {
+			acpi_dbg_level = acpi_gbl_trace_dbg_level;
+		}
+		if (acpi_gbl_trace_dbg_layer) {
+			acpi_dbg_layer = acpi_gbl_trace_dbg_layer;
+		}
+	}
+	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+
+exit:
+	if (enabled) {
+		ACPI_TRACE_POINT(ACPI_TRACE_AML_METHOD, TRUE,
+				 obj_desc ? obj_desc->method.aml_start : NULL,
+				 pathname);
+	}
+	if (pathname) {
+		ACPI_FREE(pathname);
+	}
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_stop_trace_method
+ *
+ * PARAMETERS:  method_node         - Node of the method
+ *              obj_desc            - The method object
+ *              walk_state          - current state, NULL if not yet executing
+ *                                    a method.
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Stop control method execution trace
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_stop_trace_method(struct acpi_namespace_node *method_node,
+			  union acpi_operand_object *obj_desc,
+			  struct acpi_walk_state *walk_state)
+{
+	acpi_status status;
+	char *pathname = NULL;
+	u8 enabled;
+
+	ACPI_FUNCTION_NAME(ex_stop_trace_method);
+
+	if (method_node) {
+		pathname = acpi_ns_get_normalized_pathname(method_node, TRUE);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+	if (ACPI_FAILURE(status)) {
+		goto exit_path;
+	}
+
+	enabled = acpi_ex_interpreter_trace_enabled(NULL);
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+
+	if (enabled) {
+		ACPI_TRACE_POINT(ACPI_TRACE_AML_METHOD, FALSE,
+				 obj_desc ? obj_desc->method.aml_start : NULL,
+				 pathname);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+	if (ACPI_FAILURE(status)) {
+		goto exit_path;
+	}
+
+	/* Check whether the tracer should be stopped */
+
+	if (acpi_gbl_trace_method_object == obj_desc) {
+
+		/* Disable further tracing if type is one-shot */
+
+		if (acpi_gbl_trace_flags & ACPI_TRACE_ONESHOT) {
+			acpi_gbl_trace_method_name = NULL;
+		}
+
+		acpi_dbg_level = acpi_gbl_original_dbg_level;
+		acpi_dbg_layer = acpi_gbl_original_dbg_layer;
+		acpi_gbl_trace_method_object = NULL;
+	}
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+
+exit_path:
+	if (pathname) {
+		ACPI_FREE(pathname);
+	}
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_start_trace_opcode
+ *
+ * PARAMETERS:  op                  - The parser opcode object
+ *              walk_state          - current state, NULL if not yet executing
+ *                                    a method.
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Start opcode execution trace
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_start_trace_opcode(union acpi_parse_object *op,
+			   struct acpi_walk_state *walk_state)
+{
+
+	ACPI_FUNCTION_NAME(ex_start_trace_opcode);
+
+	if (acpi_ex_interpreter_trace_enabled(NULL) &&
+	    (acpi_gbl_trace_flags & ACPI_TRACE_OPCODE)) {
+		ACPI_TRACE_POINT(ACPI_TRACE_AML_OPCODE, TRUE,
+				 op->common.aml, op->common.aml_op_name);
+	}
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_stop_trace_opcode
+ *
+ * PARAMETERS:  op                  - The parser opcode object
+ *              walk_state          - current state, NULL if not yet executing
+ *                                    a method.
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Stop opcode execution trace
+ *
+ ******************************************************************************/
+
+void
+acpi_ex_stop_trace_opcode(union acpi_parse_object *op,
+			  struct acpi_walk_state *walk_state)
+{
+
+	ACPI_FUNCTION_NAME(ex_stop_trace_opcode);
+
+	if (acpi_ex_interpreter_trace_enabled(NULL) &&
+	    (acpi_gbl_trace_flags & ACPI_TRACE_OPCODE)) {
+		ACPI_TRACE_POINT(ACPI_TRACE_AML_OPCODE, FALSE,
+				 op->common.aml, op->common.aml_op_name);
+	}
+}
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 401e7edcd419..d836f888bb16 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -995,9 +995,8 @@ static void acpi_ex_dump_reference_obj(union acpi_operand_object *obj_desc)
 	if (obj_desc->reference.class == ACPI_REFCLASS_NAME) {
 		acpi_os_printf(" %p ", obj_desc->reference.node);
 
-		status =
-		    acpi_ns_handle_to_pathname(obj_desc->reference.node,
-					       &ret_buf);
+		status = acpi_ns_handle_to_pathname(obj_desc->reference.node,
+						    &ret_buf, TRUE);
 		if (ACPI_FAILURE(status)) {
 			acpi_os_printf(" Could not convert name to pathname\n");
 		} else {
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index c7e3b929aa85..1b372ef69308 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -126,7 +126,7 @@ acpi_ex_resolve_node_to_value(struct acpi_namespace_node **object_ptr,
 	if (!source_desc) {
 		ACPI_ERROR((AE_INFO, "No object attached to node [%4.4s] %p",
 			    node->name.ascii, node));
-		return_ACPI_STATUS(AE_AML_NO_OPERAND);
+		return_ACPI_STATUS(AE_AML_UNINITIALIZED_NODE);
 	}
 
 	/*
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index b6b7f3af29e4..7b109128b035 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -337,8 +337,9 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 			 acpi_object_type * return_type,
 			 union acpi_operand_object **return_desc)
 {
-	union acpi_operand_object *obj_desc = (void *)operand;
-	struct acpi_namespace_node *node;
+	union acpi_operand_object *obj_desc = ACPI_CAST_PTR(void, operand);
+	struct acpi_namespace_node *node =
+	    ACPI_CAST_PTR(struct acpi_namespace_node, operand);
 	acpi_object_type type;
 	acpi_status status;
 
@@ -355,9 +356,7 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 	case ACPI_DESC_TYPE_NAMED:
 
 		type = ((struct acpi_namespace_node *)obj_desc)->type;
-		obj_desc =
-		    acpi_ns_get_attached_object((struct acpi_namespace_node *)
-						obj_desc);
+		obj_desc = acpi_ns_get_attached_object(node);
 
 		/* If we had an Alias node, use the attached object for type info */
 
@@ -368,6 +367,13 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 							 acpi_namespace_node *)
 							obj_desc);
 		}
+
+		if (!obj_desc) {
+			ACPI_ERROR((AE_INFO,
+				    "[%4.4s] Node is unresolved or uninitialized",
+				    acpi_ut_get_node_name(node)));
+			return_ACPI_STATUS(AE_AML_UNINITIALIZED_NODE);
+		}
 		break;
 
 	default:
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 52dfd0d050fa..d62a61612b3f 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -160,19 +160,8 @@ acpi_set_firmware_waking_vectors(acpi_physical_address physical_address,
 
 	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vectors);
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (acpi_gbl_reduced_hardware) {
-		return_ACPI_STATUS (AE_OK);
-	}
-
-	if (acpi_gbl_facs32) {
-		(void)acpi_hw_set_firmware_waking_vectors(acpi_gbl_facs32,
-							  physical_address,
-							  physical_address64);
-	}
-	if (acpi_gbl_facs64) {
-		(void)acpi_hw_set_firmware_waking_vectors(acpi_gbl_facs64,
+	if (acpi_gbl_FACS) {
+		(void)acpi_hw_set_firmware_waking_vectors(acpi_gbl_FACS,
 							  physical_address,
 							  physical_address64);
 	}
diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c
index 80670cb32b5a..7eba578d36f3 100644
--- a/drivers/acpi/acpica/nseval.c
+++ b/drivers/acpi/acpica/nseval.c
@@ -274,6 +274,7 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info *info)
 		acpi_ex_exit_interpreter();
 
 		if (ACPI_FAILURE(status)) {
+			info->return_object = NULL;
 			goto cleanup;
 		}
 
@@ -464,7 +465,8 @@ acpi_ns_exec_module_code(union acpi_operand_object *method_obj,
 
 	status = acpi_ns_evaluate(info);
 
-	ACPI_DEBUG_PRINT((ACPI_DB_INIT, "Executed module-level code at %p\n",
+	ACPI_DEBUG_PRINT((ACPI_DB_INIT_NAMES,
+			  "Executed module-level code at %p\n",
 			  method_obj->method.aml_start));
 
 	/* Delete a possible implicit return value (in slack mode) */
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index bd6cd4a81316..14ab83668207 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -111,7 +111,21 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 	if (ACPI_SUCCESS(status)) {
 		acpi_tb_set_table_loaded_flag(table_index, TRUE);
 	} else {
-		(void)acpi_tb_release_owner_id(table_index);
+		/*
+		 * On error, delete any namespace objects created by this table.
+		 * We cannot initialize these objects, so delete them. There are
+		 * a couple of expecially bad cases:
+		 * AE_ALREADY_EXISTS - namespace collision.
+		 * AE_NOT_FOUND - the target of a Scope operator does not
+		 * exist. This target of Scope must already exist in the
+		 * namespace, as per the ACPI specification.
+		 */
+		(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+		acpi_ns_delete_namespace_by_owner(acpi_gbl_root_table_list.
+						  tables[table_index].owner_id);
+		acpi_tb_release_owner_id(table_index);
+
+		return_ACPI_STATUS(status);
 	}
 
 unlock:
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index d293d9748036..8934b4eddb73 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -51,73 +51,6 @@ ACPI_MODULE_NAME("nsnames")
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ns_build_external_path
- *
- * PARAMETERS:  node            - NS node whose pathname is needed
- *              size            - Size of the pathname
- *              *name_buffer    - Where to return the pathname
- *
- * RETURN:      Status
- *              Places the pathname into the name_buffer, in external format
- *              (name segments separated by path separators)
- *
- * DESCRIPTION: Generate a full pathaname
- *
- ******************************************************************************/
-acpi_status
-acpi_ns_build_external_path(struct acpi_namespace_node *node,
-			    acpi_size size, char *name_buffer)
-{
-	acpi_size index;
-	struct acpi_namespace_node *parent_node;
-
-	ACPI_FUNCTION_ENTRY();
-
-	/* Special case for root */
-
-	index = size - 1;
-	if (index < ACPI_NAME_SIZE) {
-		name_buffer[0] = AML_ROOT_PREFIX;
-		name_buffer[1] = 0;
-		return (AE_OK);
-	}
-
-	/* Store terminator byte, then build name backwards */
-
-	parent_node = node;
-	name_buffer[index] = 0;
-
-	while ((index > ACPI_NAME_SIZE) && (parent_node != acpi_gbl_root_node)) {
-		index -= ACPI_NAME_SIZE;
-
-		/* Put the name into the buffer */
-
-		ACPI_MOVE_32_TO_32((name_buffer + index), &parent_node->name);
-		parent_node = parent_node->parent;
-
-		/* Prefix name with the path separator */
-
-		index--;
-		name_buffer[index] = ACPI_PATH_SEPARATOR;
-	}
-
-	/* Overwrite final separator with the root prefix character */
-
-	name_buffer[index] = AML_ROOT_PREFIX;
-
-	if (index != 0) {
-		ACPI_ERROR((AE_INFO,
-			    "Could not construct external pathname; index=%u, size=%u, Path=%s",
-			    (u32) index, (u32) size, &name_buffer[size]));
-
-		return (AE_BAD_PARAMETER);
-	}
-
-	return (AE_OK);
-}
-
-/*******************************************************************************
- *
  * FUNCTION:    acpi_ns_get_external_pathname
  *
  * PARAMETERS:  node            - Namespace node whose pathname is needed
@@ -130,37 +63,13 @@ acpi_ns_build_external_path(struct acpi_namespace_node *node,
  *              for error and debug statements.
  *
  ******************************************************************************/
-
 char *acpi_ns_get_external_pathname(struct acpi_namespace_node *node)
 {
-	acpi_status status;
 	char *name_buffer;
-	acpi_size size;
 
 	ACPI_FUNCTION_TRACE_PTR(ns_get_external_pathname, node);
 
-	/* Calculate required buffer size based on depth below root */
-
-	size = acpi_ns_get_pathname_length(node);
-	if (!size) {
-		return_PTR(NULL);
-	}
-
-	/* Allocate a buffer to be returned to caller */
-
-	name_buffer = ACPI_ALLOCATE_ZEROED(size);
-	if (!name_buffer) {
-		ACPI_ERROR((AE_INFO, "Could not allocate %u bytes", (u32)size));
-		return_PTR(NULL);
-	}
-
-	/* Build the path in the allocated buffer */
-
-	status = acpi_ns_build_external_path(node, size, name_buffer);
-	if (ACPI_FAILURE(status)) {
-		ACPI_FREE(name_buffer);
-		return_PTR(NULL);
-	}
+	name_buffer = acpi_ns_get_normalized_pathname(node, FALSE);
 
 	return_PTR(name_buffer);
 }
@@ -180,33 +89,12 @@ char *acpi_ns_get_external_pathname(struct acpi_namespace_node *node)
 acpi_size acpi_ns_get_pathname_length(struct acpi_namespace_node *node)
 {
 	acpi_size size;
-	struct acpi_namespace_node *next_node;
 
 	ACPI_FUNCTION_ENTRY();
 
-	/*
-	 * Compute length of pathname as 5 * number of name segments.
-	 * Go back up the parent tree to the root
-	 */
-	size = 0;
-	next_node = node;
+	size = acpi_ns_build_normalized_path(node, NULL, 0, FALSE);
 
-	while (next_node && (next_node != acpi_gbl_root_node)) {
-		if (ACPI_GET_DESCRIPTOR_TYPE(next_node) != ACPI_DESC_TYPE_NAMED) {
-			ACPI_ERROR((AE_INFO,
-				    "Invalid Namespace Node (%p) while traversing namespace",
-				    next_node));
-			return (0);
-		}
-		size += ACPI_PATH_SEGMENT_LENGTH;
-		next_node = next_node->parent;
-	}
-
-	if (!size) {
-		size = 1;	/* Root node case */
-	}
-
-	return (size + 1);	/* +1 for null string terminator */
+	return (size);
 }
 
 /*******************************************************************************
@@ -216,6 +104,8 @@ acpi_size acpi_ns_get_pathname_length(struct acpi_namespace_node *node)
  * PARAMETERS:  target_handle           - Handle of named object whose name is
  *                                        to be found
  *              buffer                  - Where the pathname is returned
+ *              no_trailing             - Remove trailing '_' for each name
+ *                                        segment
  *
  * RETURN:      Status, Buffer is filled with pathname if status is AE_OK
  *
@@ -225,7 +115,7 @@ acpi_size acpi_ns_get_pathname_length(struct acpi_namespace_node *node)
 
 acpi_status
 acpi_ns_handle_to_pathname(acpi_handle target_handle,
-			   struct acpi_buffer * buffer)
+			   struct acpi_buffer * buffer, u8 no_trailing)
 {
 	acpi_status status;
 	struct acpi_namespace_node *node;
@@ -240,7 +130,8 @@ acpi_ns_handle_to_pathname(acpi_handle target_handle,
 
 	/* Determine size required for the caller buffer */
 
-	required_size = acpi_ns_get_pathname_length(node);
+	required_size =
+	    acpi_ns_build_normalized_path(node, NULL, 0, no_trailing);
 	if (!required_size) {
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
@@ -254,8 +145,8 @@ acpi_ns_handle_to_pathname(acpi_handle target_handle,
 
 	/* Build the path in the caller buffer */
 
-	status =
-	    acpi_ns_build_external_path(node, required_size, buffer->pointer);
+	(void)acpi_ns_build_normalized_path(node, buffer->pointer,
+					    required_size, no_trailing);
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
@@ -264,3 +155,149 @@ acpi_ns_handle_to_pathname(acpi_handle target_handle,
 			  (char *)buffer->pointer, (u32) required_size));
 	return_ACPI_STATUS(AE_OK);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_build_normalized_path
+ *
+ * PARAMETERS:  node        - Namespace node
+ *              full_path   - Where the path name is returned
+ *              path_size   - Size of returned path name buffer
+ *              no_trailing - Remove trailing '_' from each name segment
+ *
+ * RETURN:      Return 1 if the AML path is empty, otherwise returning (length
+ *              of pathname + 1) which means the 'FullPath' contains a trailing
+ *              null.
+ *
+ * DESCRIPTION: Build and return a full namespace pathname.
+ *              Note that if the size of 'FullPath' isn't large enough to
+ *              contain the namespace node's path name, the actual required
+ *              buffer length is returned, and it should be greater than
+ *              'PathSize'. So callers are able to check the returning value
+ *              to determine the buffer size of 'FullPath'.
+ *
+ ******************************************************************************/
+
+u32
+acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
+			      char *full_path, u32 path_size, u8 no_trailing)
+{
+	u32 length = 0, i;
+	char name[ACPI_NAME_SIZE];
+	u8 do_no_trailing;
+	char c, *left, *right;
+	struct acpi_namespace_node *next_node;
+
+	ACPI_FUNCTION_TRACE_PTR(ns_build_normalized_path, node);
+
+#define ACPI_PATH_PUT8(path, size, byte, length)    \
+	do {                                            \
+		if ((length) < (size))                      \
+		{                                           \
+			(path)[(length)] = (byte);              \
+		}                                           \
+		(length)++;                                 \
+	} while (0)
+
+	/*
+	 * Make sure the path_size is correct, so that we don't need to
+	 * validate both full_path and path_size.
+	 */
+	if (!full_path) {
+		path_size = 0;
+	}
+
+	if (!node) {
+		goto build_trailing_null;
+	}
+
+	next_node = node;
+	while (next_node && next_node != acpi_gbl_root_node) {
+		if (next_node != node) {
+			ACPI_PATH_PUT8(full_path, path_size,
+				       AML_DUAL_NAME_PREFIX, length);
+		}
+		ACPI_MOVE_32_TO_32(name, &next_node->name);
+		do_no_trailing = no_trailing;
+		for (i = 0; i < 4; i++) {
+			c = name[4 - i - 1];
+			if (do_no_trailing && c != '_') {
+				do_no_trailing = FALSE;
+			}
+			if (!do_no_trailing) {
+				ACPI_PATH_PUT8(full_path, path_size, c, length);
+			}
+		}
+		next_node = next_node->parent;
+	}
+	ACPI_PATH_PUT8(full_path, path_size, AML_ROOT_PREFIX, length);
+
+	/* Reverse the path string */
+
+	if (length <= path_size) {
+		left = full_path;
+		right = full_path + length - 1;
+		while (left < right) {
+			c = *left;
+			*left++ = *right;
+			*right-- = c;
+		}
+	}
+
+	/* Append the trailing null */
+
+build_trailing_null:
+	ACPI_PATH_PUT8(full_path, path_size, '\0', length);
+
+#undef ACPI_PATH_PUT8
+
+	return_UINT32(length);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_get_normalized_pathname
+ *
+ * PARAMETERS:  node            - Namespace node whose pathname is needed
+ *              no_trailing     - Remove trailing '_' from each name segment
+ *
+ * RETURN:      Pointer to storage containing the fully qualified name of
+ *              the node, In external format (name segments separated by path
+ *              separators.)
+ *
+ * DESCRIPTION: Used to obtain the full pathname to a namespace node, usually
+ *              for error and debug statements. All trailing '_' will be
+ *              removed from the full pathname if 'NoTrailing' is specified..
+ *
+ ******************************************************************************/
+
+char *acpi_ns_get_normalized_pathname(struct acpi_namespace_node *node,
+				      u8 no_trailing)
+{
+	char *name_buffer;
+	acpi_size size;
+
+	ACPI_FUNCTION_TRACE_PTR(ns_get_normalized_pathname, node);
+
+	/* Calculate required buffer size based on depth below root */
+
+	size = acpi_ns_build_normalized_path(node, NULL, 0, no_trailing);
+	if (!size) {
+		return_PTR(NULL);
+	}
+
+	/* Allocate a buffer to be returned to caller */
+
+	name_buffer = ACPI_ALLOCATE_ZEROED(size);
+	if (!name_buffer) {
+		ACPI_ERROR((AE_INFO, "Could not allocate %u bytes", (u32)size));
+		return_PTR(NULL);
+	}
+
+	/* Build the path in the allocated buffer */
+
+	(void)acpi_ns_build_normalized_path(node, name_buffer, size,
+					    no_trailing);
+
+	return_PTR(name_buffer);
+}
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index 57a4cfe547e4..3736d43b18b9 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -70,7 +70,7 @@ acpi_ns_one_complete_parse(u32 pass_number,
 {
 	union acpi_parse_object *parse_root;
 	acpi_status status;
-       u32 aml_length;
+	u32 aml_length;
 	u8 *aml_start;
 	struct acpi_walk_state *walk_state;
 	struct acpi_table_header *table;
@@ -78,6 +78,20 @@ acpi_ns_one_complete_parse(u32 pass_number,
 
 	ACPI_FUNCTION_TRACE(ns_one_complete_parse);
 
+	status = acpi_get_table_by_index(table_index, &table);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Table must consist of at least a complete header */
+
+	if (table->length < sizeof(struct acpi_table_header)) {
+		return_ACPI_STATUS(AE_BAD_HEADER);
+	}
+
+	aml_start = (u8 *)table + sizeof(struct acpi_table_header);
+	aml_length = table->length - sizeof(struct acpi_table_header);
+
 	status = acpi_tb_get_owner_id(table_index, &owner_id);
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
@@ -85,7 +99,7 @@ acpi_ns_one_complete_parse(u32 pass_number,
 
 	/* Create and init a Root Node */
 
-	parse_root = acpi_ps_create_scope_op();
+	parse_root = acpi_ps_create_scope_op(aml_start);
 	if (!parse_root) {
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
@@ -98,23 +112,12 @@ acpi_ns_one_complete_parse(u32 pass_number,
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
 
-	status = acpi_get_table_by_index(table_index, &table);
+	status = acpi_ds_init_aml_walk(walk_state, parse_root, NULL,
+				       aml_start, aml_length, NULL,
+				       (u8)pass_number);
 	if (ACPI_FAILURE(status)) {
 		acpi_ds_delete_walk_state(walk_state);
-		acpi_ps_free_op(parse_root);
-		return_ACPI_STATUS(status);
-	}
-
-	/* Table must consist of at least a complete header */
-
-	if (table->length < sizeof(struct acpi_table_header)) {
-		status = AE_BAD_HEADER;
-	} else {
-		aml_start = (u8 *) table + sizeof(struct acpi_table_header);
-		aml_length = table->length - sizeof(struct acpi_table_header);
-		status = acpi_ds_init_aml_walk(walk_state, parse_root, NULL,
-					       aml_start, aml_length, NULL,
-					       (u8) pass_number);
+		goto cleanup;
 	}
 
 	/* Found OSDT table, enable the namespace override feature */
@@ -124,11 +127,6 @@ acpi_ns_one_complete_parse(u32 pass_number,
 		walk_state->namespace_override = TRUE;
 	}
 
-	if (ACPI_FAILURE(status)) {
-		acpi_ds_delete_walk_state(walk_state);
-		goto cleanup;
-	}
-
 	/* start_node is the default location to load the table */
 
 	if (start_node && start_node != acpi_gbl_root_node) {
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index 8d8104b8bd28..de325ae04ce1 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -83,7 +83,7 @@ acpi_ns_print_node_pathname(struct acpi_namespace_node *node,
 
 	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
 
-	status = acpi_ns_handle_to_pathname(node, &buffer);
+	status = acpi_ns_handle_to_pathname(node, &buffer, TRUE);
 	if (ACPI_SUCCESS(status)) {
 		if (message) {
 			acpi_os_printf("%s ", message);
@@ -596,6 +596,23 @@ void acpi_ns_terminate(void)
 
 	ACPI_FUNCTION_TRACE(ns_terminate);
 
+#ifdef ACPI_EXEC_APP
+	{
+		union acpi_operand_object *prev;
+		union acpi_operand_object *next;
+
+		/* Delete any module-level code blocks */
+
+		next = acpi_gbl_module_code_list;
+		while (next) {
+			prev = next;
+			next = next->method.mutex;
+			prev->method.mutex = NULL;	/* Clear the Mutex (cheated) field */
+			acpi_ut_remove_reference(prev);
+		}
+	}
+#endif
+
 	/*
 	 * Free the entire namespace -- all nodes and all objects
 	 * attached to the nodes
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 9ff643b9553f..4b4d2f43d406 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -172,11 +172,15 @@ acpi_get_name(acpi_handle handle, u32 name_type, struct acpi_buffer * buffer)
 		return (status);
 	}
 
-	if (name_type == ACPI_FULL_PATHNAME) {
+	if (name_type == ACPI_FULL_PATHNAME ||
+	    name_type == ACPI_FULL_PATHNAME_NO_TRAILING) {
 
 		/* Get the full pathname (From the namespace root) */
 
-		status = acpi_ns_handle_to_pathname(handle, buffer);
+		status = acpi_ns_handle_to_pathname(handle, buffer,
+						    name_type ==
+						    ACPI_FULL_PATHNAME ? FALSE :
+						    TRUE);
 		return (status);
 	}
 
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 6d038770577b..29d8b7b01dca 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -287,7 +287,7 @@ acpi_ps_get_next_namepath(struct acpi_walk_state *walk_state,
 				  "Control Method - %p Desc %p Path=%p\n", node,
 				  method_desc, path));
 
-		name_op = acpi_ps_alloc_op(AML_INT_NAMEPATH_OP);
+		name_op = acpi_ps_alloc_op(AML_INT_NAMEPATH_OP, start);
 		if (!name_op) {
 			return_ACPI_STATUS(AE_NO_MEMORY);
 		}
@@ -484,7 +484,7 @@ acpi_ps_get_next_simple_arg(struct acpi_parse_state *parser_state,
 static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 						       *parser_state)
 {
-	u32 aml_offset;
+	u8 *aml;
 	union acpi_parse_object *field;
 	union acpi_parse_object *arg = NULL;
 	u16 opcode;
@@ -498,8 +498,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 	ACPI_FUNCTION_TRACE(ps_get_next_field);
 
-	aml_offset =
-	    (u32)ACPI_PTR_DIFF(parser_state->aml, parser_state->aml_start);
+	aml = parser_state->aml;
 
 	/* Determine field type */
 
@@ -536,13 +535,11 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 	/* Allocate a new field op */
 
-	field = acpi_ps_alloc_op(opcode);
+	field = acpi_ps_alloc_op(opcode, aml);
 	if (!field) {
 		return_PTR(NULL);
 	}
 
-	field->common.aml_offset = aml_offset;
-
 	/* Decode the field type */
 
 	switch (opcode) {
@@ -604,6 +601,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 		 * Argument for Connection operator can be either a Buffer
 		 * (resource descriptor), or a name_string.
 		 */
+		aml = parser_state->aml;
 		if (ACPI_GET8(parser_state->aml) == AML_BUFFER_OP) {
 			parser_state->aml++;
 
@@ -616,7 +614,8 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 				/* Non-empty list */
 
-				arg = acpi_ps_alloc_op(AML_INT_BYTELIST_OP);
+				arg =
+				    acpi_ps_alloc_op(AML_INT_BYTELIST_OP, aml);
 				if (!arg) {
 					acpi_ps_free_op(field);
 					return_PTR(NULL);
@@ -665,7 +664,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 			parser_state->aml = pkg_end;
 		} else {
-			arg = acpi_ps_alloc_op(AML_INT_NAMEPATH_OP);
+			arg = acpi_ps_alloc_op(AML_INT_NAMEPATH_OP, aml);
 			if (!arg) {
 				acpi_ps_free_op(field);
 				return_PTR(NULL);
@@ -730,7 +729,7 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 
 		/* Constants, strings, and namestrings are all the same size */
 
-		arg = acpi_ps_alloc_op(AML_BYTE_OP);
+		arg = acpi_ps_alloc_op(AML_BYTE_OP, parser_state->aml);
 		if (!arg) {
 			return_ACPI_STATUS(AE_NO_MEMORY);
 		}
@@ -777,7 +776,8 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 
 			/* Non-empty list */
 
-			arg = acpi_ps_alloc_op(AML_INT_BYTELIST_OP);
+			arg = acpi_ps_alloc_op(AML_INT_BYTELIST_OP,
+					       parser_state->aml);
 			if (!arg) {
 				return_ACPI_STATUS(AE_NO_MEMORY);
 			}
@@ -807,7 +807,9 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 
 			/* null_name or name_string */
 
-			arg = acpi_ps_alloc_op(AML_INT_NAMEPATH_OP);
+			arg =
+			    acpi_ps_alloc_op(AML_INT_NAMEPATH_OP,
+					     parser_state->aml);
 			if (!arg) {
 				return_ACPI_STATUS(AE_NO_MEMORY);
 			}
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index 90437227d790..03ac8c9a67ab 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -51,6 +51,7 @@
 
 #include <acpi/acpi.h>
 #include "accommon.h"
+#include "acinterp.h"
 #include "acparser.h"
 #include "acdispat.h"
 #include "amlcode.h"
@@ -125,10 +126,7 @@ acpi_ps_get_arguments(struct acpi_walk_state *walk_state,
 		 */
 		while (GET_CURRENT_ARG_TYPE(walk_state->arg_types)
 		       && !walk_state->arg_count) {
-			walk_state->aml_offset =
-			    (u32) ACPI_PTR_DIFF(walk_state->parser_state.aml,
-						walk_state->parser_state.
-						aml_start);
+			walk_state->aml = walk_state->parser_state.aml;
 
 			status =
 			    acpi_ps_get_next_arg(walk_state,
@@ -140,7 +138,6 @@ acpi_ps_get_arguments(struct acpi_walk_state *walk_state,
 			}
 
 			if (arg) {
-				arg->common.aml_offset = walk_state->aml_offset;
 				acpi_ps_append_arg(op, arg);
 			}
 
@@ -324,6 +321,8 @@ acpi_ps_link_module_code(union acpi_parse_object *parent_op,
 	union acpi_operand_object *method_obj;
 	struct acpi_namespace_node *parent_node;
 
+	ACPI_FUNCTION_TRACE(ps_link_module_code);
+
 	/* Get the tail of the list */
 
 	prev = next = acpi_gbl_module_code_list;
@@ -343,9 +342,13 @@ acpi_ps_link_module_code(union acpi_parse_object *parent_op,
 
 		method_obj = acpi_ut_create_internal_object(ACPI_TYPE_METHOD);
 		if (!method_obj) {
-			return;
+			return_VOID;
 		}
 
+		ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+				  "Create/Link new code block: %p\n",
+				  method_obj));
+
 		if (parent_op->common.node) {
 			parent_node = parent_op->common.node;
 		} else {
@@ -370,8 +373,14 @@ acpi_ps_link_module_code(union acpi_parse_object *parent_op,
 			prev->method.mutex = method_obj;
 		}
 	} else {
+		ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+				  "Appending to existing code block: %p\n",
+				  prev));
+
 		prev->method.aml_length += aml_length;
 	}
+
+	return_VOID;
 }
 
 /*******************************************************************************
@@ -494,16 +503,7 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state)
 				continue;
 			}
 
-			op->common.aml_offset = walk_state->aml_offset;
-
-			if (walk_state->op_info) {
-				ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
-						  "Opcode %4.4X [%s] Op %p Aml %p AmlOffset %5.5X\n",
-						  (u32) op->common.aml_opcode,
-						  walk_state->op_info->name, op,
-						  parser_state->aml,
-						  op->common.aml_offset));
-			}
+			acpi_ex_start_trace_opcode(op, walk_state);
 		}
 
 		/*
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index 2f5ddd806c58..e54bc2aa7a88 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -66,12 +66,11 @@ static acpi_status acpi_ps_get_aml_opcode(struct acpi_walk_state *walk_state);
 
 static acpi_status acpi_ps_get_aml_opcode(struct acpi_walk_state *walk_state)
 {
+	u32 aml_offset;
 
 	ACPI_FUNCTION_TRACE_PTR(ps_get_aml_opcode, walk_state);
 
-	walk_state->aml_offset =
-	    (u32)ACPI_PTR_DIFF(walk_state->parser_state.aml,
-			       walk_state->parser_state.aml_start);
+	walk_state->aml = walk_state->parser_state.aml;
 	walk_state->opcode = acpi_ps_peek_opcode(&(walk_state->parser_state));
 
 	/*
@@ -98,10 +97,14 @@ static acpi_status acpi_ps_get_aml_opcode(struct acpi_walk_state *walk_state)
 		/* The opcode is unrecognized. Complain and skip unknown opcodes */
 
 		if (walk_state->pass_number == 2) {
+			aml_offset = (u32)ACPI_PTR_DIFF(walk_state->aml,
+							walk_state->
+							parser_state.aml_start);
+
 			ACPI_ERROR((AE_INFO,
 				    "Unknown opcode 0x%.2X at table offset 0x%.4X, ignoring",
 				    walk_state->opcode,
-				    (u32)(walk_state->aml_offset +
+				    (u32)(aml_offset +
 					  sizeof(struct acpi_table_header))));
 
 			ACPI_DUMP_BUFFER((walk_state->parser_state.aml - 16),
@@ -115,14 +118,14 @@ static acpi_status acpi_ps_get_aml_opcode(struct acpi_walk_state *walk_state)
 			acpi_os_printf
 			    ("/*\nError: Unknown opcode 0x%.2X at table offset 0x%.4X, context:\n",
 			     walk_state->opcode,
-			     (u32)(walk_state->aml_offset +
+			     (u32)(aml_offset +
 				   sizeof(struct acpi_table_header)));
 
 			/* Dump the context surrounding the invalid opcode */
 
 			acpi_ut_dump_buffer(((u8 *)walk_state->parser_state.
 					     aml - 16), 48, DB_BYTE_DISPLAY,
-					    (walk_state->aml_offset +
+					    (aml_offset +
 					     sizeof(struct acpi_table_header) -
 					     16));
 			acpi_os_printf(" */\n");
@@ -294,7 +297,7 @@ acpi_ps_create_op(struct acpi_walk_state *walk_state,
 	/* Create Op structure and append to parent's argument list */
 
 	walk_state->op_info = acpi_ps_get_opcode_info(walk_state->opcode);
-	op = acpi_ps_alloc_op(walk_state->opcode);
+	op = acpi_ps_alloc_op(walk_state->opcode, aml_op_start);
 	if (!op) {
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index a555f7f7b9a2..98001d7f6f80 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -147,6 +147,8 @@ acpi_ps_complete_this_op(struct acpi_walk_state * walk_state,
 		return_ACPI_STATUS(AE_OK);	/* OK for now */
 	}
 
+	acpi_ex_stop_trace_opcode(op, walk_state);
+
 	/* Delete this op and the subtree below it if asked to */
 
 	if (((walk_state->parse_flags & ACPI_PARSE_TREE_MASK) !=
@@ -185,7 +187,8 @@ acpi_ps_complete_this_op(struct acpi_walk_state * walk_state,
 			 * op must be replaced by a placeholder return op
 			 */
 			replacement_op =
-			    acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP);
+			    acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP,
+					     op->common.aml);
 			if (!replacement_op) {
 				status = AE_NO_MEMORY;
 			}
@@ -209,7 +212,8 @@ acpi_ps_complete_this_op(struct acpi_walk_state * walk_state,
 			    || (op->common.parent->common.aml_opcode ==
 				AML_VAR_PACKAGE_OP)) {
 				replacement_op =
-				    acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP);
+				    acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP,
+						     op->common.aml);
 				if (!replacement_op) {
 					status = AE_NO_MEMORY;
 				}
@@ -224,7 +228,8 @@ acpi_ps_complete_this_op(struct acpi_walk_state * walk_state,
 					AML_VAR_PACKAGE_OP)) {
 					replacement_op =
 					    acpi_ps_alloc_op(op->common.
-							     aml_opcode);
+							     aml_opcode,
+							     op->common.aml);
 					if (!replacement_op) {
 						status = AE_NO_MEMORY;
 					} else {
@@ -240,7 +245,8 @@ acpi_ps_complete_this_op(struct acpi_walk_state * walk_state,
 		default:
 
 			replacement_op =
-			    acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP);
+			    acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP,
+					     op->common.aml);
 			if (!replacement_op) {
 				status = AE_NO_MEMORY;
 			}
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index 32440912023a..183cc1efbc51 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -60,11 +60,11 @@ ACPI_MODULE_NAME("psutils")
  * DESCRIPTION: Create a Scope and associated namepath op with the root name
  *
  ******************************************************************************/
-union acpi_parse_object *acpi_ps_create_scope_op(void)
+union acpi_parse_object *acpi_ps_create_scope_op(u8 *aml)
 {
 	union acpi_parse_object *scope_op;
 
-	scope_op = acpi_ps_alloc_op(AML_SCOPE_OP);
+	scope_op = acpi_ps_alloc_op(AML_SCOPE_OP, aml);
 	if (!scope_op) {
 		return (NULL);
 	}
@@ -103,6 +103,7 @@ void acpi_ps_init_op(union acpi_parse_object *op, u16 opcode)
  * FUNCTION:    acpi_ps_alloc_op
  *
  * PARAMETERS:  opcode          - Opcode that will be stored in the new Op
+ *              aml             - Address of the opcode
  *
  * RETURN:      Pointer to the new Op, null on failure
  *
@@ -112,7 +113,7 @@ void acpi_ps_init_op(union acpi_parse_object *op, u16 opcode)
  *
  ******************************************************************************/
 
-union acpi_parse_object *acpi_ps_alloc_op(u16 opcode)
+union acpi_parse_object *acpi_ps_alloc_op(u16 opcode, u8 *aml)
 {
 	union acpi_parse_object *op;
 	const struct acpi_opcode_info *op_info;
@@ -149,6 +150,7 @@ union acpi_parse_object *acpi_ps_alloc_op(u16 opcode)
 
 	if (op) {
 		acpi_ps_init_op(op, opcode);
+		op->common.aml = aml;
 		op->common.flags = flags;
 	}
 
diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c
index 841a5ea06094..4254805dd319 100644
--- a/drivers/acpi/acpica/psxface.c
+++ b/drivers/acpi/acpica/psxface.c
@@ -47,15 +47,12 @@
 #include "acdispat.h"
 #include "acinterp.h"
 #include "actables.h"
+#include "acnamesp.h"
 
 #define _COMPONENT          ACPI_PARSER
 ACPI_MODULE_NAME("psxface")
 
 /* Local Prototypes */
-static void acpi_ps_start_trace(struct acpi_evaluate_info *info);
-
-static void acpi_ps_stop_trace(struct acpi_evaluate_info *info);
-
 static void
 acpi_ps_update_parameter_list(struct acpi_evaluate_info *info, u16 action);
 
@@ -76,7 +73,7 @@ acpi_ps_update_parameter_list(struct acpi_evaluate_info *info, u16 action);
  ******************************************************************************/
 
 acpi_status
-acpi_debug_trace(char *name, u32 debug_level, u32 debug_layer, u32 flags)
+acpi_debug_trace(const char *name, u32 debug_level, u32 debug_layer, u32 flags)
 {
 	acpi_status status;
 
@@ -85,108 +82,14 @@ acpi_debug_trace(char *name, u32 debug_level, u32 debug_layer, u32 flags)
 		return (status);
 	}
 
-	/* TBDs: Validate name, allow full path or just nameseg */
-
-	acpi_gbl_trace_method_name = *ACPI_CAST_PTR(u32, name);
+	acpi_gbl_trace_method_name = name;
 	acpi_gbl_trace_flags = flags;
-
-	if (debug_level) {
-		acpi_gbl_trace_dbg_level = debug_level;
-	}
-	if (debug_layer) {
-		acpi_gbl_trace_dbg_layer = debug_layer;
-	}
+	acpi_gbl_trace_dbg_level = debug_level;
+	acpi_gbl_trace_dbg_layer = debug_layer;
+	status = AE_OK;
 
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
-	return (AE_OK);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ps_start_trace
- *
- * PARAMETERS:  info        - Method info struct
- *
- * RETURN:      None
- *
- * DESCRIPTION: Start control method execution trace
- *
- ******************************************************************************/
-
-static void acpi_ps_start_trace(struct acpi_evaluate_info *info)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_ENTRY();
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
-	if (ACPI_FAILURE(status)) {
-		return;
-	}
-
-	if ((!acpi_gbl_trace_method_name) ||
-	    (acpi_gbl_trace_method_name != info->node->name.integer)) {
-		goto exit;
-	}
-
-	acpi_gbl_original_dbg_level = acpi_dbg_level;
-	acpi_gbl_original_dbg_layer = acpi_dbg_layer;
-
-	acpi_dbg_level = 0x00FFFFFF;
-	acpi_dbg_layer = ACPI_UINT32_MAX;
-
-	if (acpi_gbl_trace_dbg_level) {
-		acpi_dbg_level = acpi_gbl_trace_dbg_level;
-	}
-	if (acpi_gbl_trace_dbg_layer) {
-		acpi_dbg_layer = acpi_gbl_trace_dbg_layer;
-	}
-
-exit:
-	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ps_stop_trace
- *
- * PARAMETERS:  info        - Method info struct
- *
- * RETURN:      None
- *
- * DESCRIPTION: Stop control method execution trace
- *
- ******************************************************************************/
-
-static void acpi_ps_stop_trace(struct acpi_evaluate_info *info)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_ENTRY();
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
-	if (ACPI_FAILURE(status)) {
-		return;
-	}
-
-	if ((!acpi_gbl_trace_method_name) ||
-	    (acpi_gbl_trace_method_name != info->node->name.integer)) {
-		goto exit;
-	}
-
-	/* Disable further tracing if type is one-shot */
-
-	if (acpi_gbl_trace_flags & 1) {
-		acpi_gbl_trace_method_name = 0;
-		acpi_gbl_trace_dbg_level = 0;
-		acpi_gbl_trace_dbg_layer = 0;
-	}
-
-	acpi_dbg_level = acpi_gbl_original_dbg_level;
-	acpi_dbg_layer = acpi_gbl_original_dbg_layer;
-
-exit:
-	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+	return (status);
 }
 
 /*******************************************************************************
@@ -212,7 +115,7 @@ exit:
  *
  ******************************************************************************/
 
-acpi_status acpi_ps_execute_method(struct acpi_evaluate_info *info)
+acpi_status acpi_ps_execute_method(struct acpi_evaluate_info * info)
 {
 	acpi_status status;
 	union acpi_parse_object *op;
@@ -243,10 +146,6 @@ acpi_status acpi_ps_execute_method(struct acpi_evaluate_info *info)
 	 */
 	acpi_ps_update_parameter_list(info, REF_INCREMENT);
 
-	/* Begin tracing if requested */
-
-	acpi_ps_start_trace(info);
-
 	/*
 	 * Execute the method. Performs parse simultaneously
 	 */
@@ -256,7 +155,7 @@ acpi_status acpi_ps_execute_method(struct acpi_evaluate_info *info)
 
 	/* Create and init a Root Node */
 
-	op = acpi_ps_create_scope_op();
+	op = acpi_ps_create_scope_op(info->obj_desc->method.aml_start);
 	if (!op) {
 		status = AE_NO_MEMORY;
 		goto cleanup;
@@ -326,10 +225,6 @@ acpi_status acpi_ps_execute_method(struct acpi_evaluate_info *info)
 cleanup:
 	acpi_ps_delete_parse_tree(op);
 
-	/* End optional tracing */
-
-	acpi_ps_stop_trace(info);
-
 	/* Take away the extra reference that we gave the parameters above */
 
 	acpi_ps_update_parameter_list(info, REF_DECREMENT);
diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c
index 3fa829e96c2a..a5344428f3ae 100644
--- a/drivers/acpi/acpica/rscreate.c
+++ b/drivers/acpi/acpica/rscreate.c
@@ -348,7 +348,8 @@ acpi_rs_create_pci_routing_table(union acpi_operand_object *package_object,
 				status =
 				    acpi_ns_handle_to_pathname((acpi_handle)
 							       node,
-							       &path_buffer);
+							       &path_buffer,
+							       FALSE);
 
 				/* +1 to include null terminator */
 
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 6253001b6375..455a0700db39 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -345,7 +345,7 @@ void acpi_tb_parse_fadt(u32 table_index)
 	/* Obtain the DSDT and FACS tables via their addresses within the FADT */
 
 	acpi_tb_install_fixed_table((acpi_physical_address) acpi_gbl_FADT.Xdsdt,
-				    ACPI_SIG_DSDT, ACPI_TABLE_INDEX_DSDT);
+				    ACPI_SIG_DSDT, &acpi_gbl_dsdt_index);
 
 	/* If Hardware Reduced flag is set, there is no FACS */
 
@@ -354,13 +354,13 @@ void acpi_tb_parse_fadt(u32 table_index)
 			acpi_tb_install_fixed_table((acpi_physical_address)
 						    acpi_gbl_FADT.facs,
 						    ACPI_SIG_FACS,
-						    ACPI_TABLE_INDEX_FACS);
+						    &acpi_gbl_facs_index);
 		}
 		if (acpi_gbl_FADT.Xfacs) {
 			acpi_tb_install_fixed_table((acpi_physical_address)
 						    acpi_gbl_FADT.Xfacs,
 						    ACPI_SIG_FACS,
-						    ACPI_TABLE_INDEX_X_FACS);
+						    &acpi_gbl_xfacs_index);
 		}
 	}
 }
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index 119c84ad9833..405529d49a1a 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -68,12 +68,25 @@ acpi_status
 acpi_tb_find_table(char *signature,
 		   char *oem_id, char *oem_table_id, u32 *table_index)
 {
-	u32 i;
 	acpi_status status;
 	struct acpi_table_header header;
+	u32 i;
 
 	ACPI_FUNCTION_TRACE(tb_find_table);
 
+	/* Validate the input table signature */
+
+	if (!acpi_is_valid_signature(signature)) {
+		return_ACPI_STATUS(AE_BAD_SIGNATURE);
+	}
+
+	/* Don't allow the OEM strings to be too long */
+
+	if ((strlen(oem_id) > ACPI_OEM_ID_SIZE) ||
+	    (strlen(oem_table_id) > ACPI_OEM_TABLE_ID_SIZE)) {
+		return_ACPI_STATUS(AE_AML_STRING_LIMIT);
+	}
+
 	/* Normalize the input strings */
 
 	memset(&header, 0, sizeof(struct acpi_table_header));
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 15ea98e0068d..6319b42420c6 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -100,9 +100,9 @@ acpi_tb_compare_tables(struct acpi_table_desc *table_desc, u32 table_index)
  *
  * FUNCTION:    acpi_tb_install_table_with_override
  *
- * PARAMETERS:  table_index             - Index into root table array
- *              new_table_desc          - New table descriptor to install
+ * PARAMETERS:  new_table_desc          - New table descriptor to install
  *              override                - Whether override should be performed
+ *              table_index             - Where the table index is returned
  *
  * RETURN:      None
  *
@@ -114,12 +114,14 @@ acpi_tb_compare_tables(struct acpi_table_desc *table_desc, u32 table_index)
  ******************************************************************************/
 
 void
-acpi_tb_install_table_with_override(u32 table_index,
-				    struct acpi_table_desc *new_table_desc,
-				    u8 override)
+acpi_tb_install_table_with_override(struct acpi_table_desc *new_table_desc,
+				    u8 override, u32 *table_index)
 {
+	u32 i;
+	acpi_status status;
 
-	if (table_index >= acpi_gbl_root_table_list.current_table_count) {
+	status = acpi_tb_get_next_table_descriptor(&i, NULL);
+	if (ACPI_FAILURE(status)) {
 		return;
 	}
 
@@ -134,8 +136,7 @@ acpi_tb_install_table_with_override(u32 table_index,
 		acpi_tb_override_table(new_table_desc);
 	}
 
-	acpi_tb_init_table_descriptor(&acpi_gbl_root_table_list.
-				      tables[table_index],
+	acpi_tb_init_table_descriptor(&acpi_gbl_root_table_list.tables[i],
 				      new_table_desc->address,
 				      new_table_desc->flags,
 				      new_table_desc->pointer);
@@ -143,9 +144,13 @@ acpi_tb_install_table_with_override(u32 table_index,
 	acpi_tb_print_table_header(new_table_desc->address,
 				   new_table_desc->pointer);
 
+	/* This synchronizes acpi_gbl_dsdt_index */
+
+	*table_index = i;
+
 	/* Set the global integer width (based upon revision of the DSDT) */
 
-	if (table_index == ACPI_TABLE_INDEX_DSDT) {
+	if (i == acpi_gbl_dsdt_index) {
 		acpi_ut_set_integer_width(new_table_desc->pointer->revision);
 	}
 }
@@ -157,7 +162,7 @@ acpi_tb_install_table_with_override(u32 table_index,
  * PARAMETERS:  address                 - Physical address of DSDT or FACS
  *              signature               - Table signature, NULL if no need to
  *                                        match
- *              table_index             - Index into root table array
+ *              table_index             - Where the table index is returned
  *
  * RETURN:      Status
  *
@@ -168,7 +173,7 @@ acpi_tb_install_table_with_override(u32 table_index,
 
 acpi_status
 acpi_tb_install_fixed_table(acpi_physical_address address,
-			    char *signature, u32 table_index)
+			    char *signature, u32 *table_index)
 {
 	struct acpi_table_desc new_table_desc;
 	acpi_status status;
@@ -200,7 +205,9 @@ acpi_tb_install_fixed_table(acpi_physical_address address,
 		goto release_and_exit;
 	}
 
-	acpi_tb_install_table_with_override(table_index, &new_table_desc, TRUE);
+	/* Add the table to the global root table list */
+
+	acpi_tb_install_table_with_override(&new_table_desc, TRUE, table_index);
 
 release_and_exit:
 
@@ -355,13 +362,8 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 
 	/* Add the table to the global root table list */
 
-	status = acpi_tb_get_next_table_descriptor(&i, NULL);
-	if (ACPI_FAILURE(status)) {
-		goto release_and_exit;
-	}
-
-	*table_index = i;
-	acpi_tb_install_table_with_override(i, &new_table_desc, override);
+	acpi_tb_install_table_with_override(&new_table_desc, override,
+					    table_index);
 
 release_and_exit:
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 568ac0e4a3c6..4337990127cc 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -68,28 +68,27 @@ acpi_tb_get_root_table_entry(u8 *table_entry, u32 table_entry_size);
 
 acpi_status acpi_tb_initialize_facs(void)
 {
+	struct acpi_table_facs *facs;
 
 	/* If Hardware Reduced flag is set, there is no FACS */
 
 	if (acpi_gbl_reduced_hardware) {
 		acpi_gbl_FACS = NULL;
 		return (AE_OK);
-	}
-
-	(void)acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
-				      ACPI_CAST_INDIRECT_PTR(struct
-							     acpi_table_header,
-							     &acpi_gbl_facs32));
-	(void)acpi_get_table_by_index(ACPI_TABLE_INDEX_X_FACS,
-				      ACPI_CAST_INDIRECT_PTR(struct
-							     acpi_table_header,
-							     &acpi_gbl_facs64));
-
-	if (acpi_gbl_facs64
-	    && (!acpi_gbl_facs32 || !acpi_gbl_use32_bit_facs_addresses)) {
-		acpi_gbl_FACS = acpi_gbl_facs64;
-	} else if (acpi_gbl_facs32) {
-		acpi_gbl_FACS = acpi_gbl_facs32;
+	} else if (acpi_gbl_FADT.Xfacs &&
+		   (!acpi_gbl_FADT.facs
+		    || !acpi_gbl_use32_bit_facs_addresses)) {
+		(void)acpi_get_table_by_index(acpi_gbl_xfacs_index,
+					      ACPI_CAST_INDIRECT_PTR(struct
+								     acpi_table_header,
+								     &facs));
+		acpi_gbl_FACS = facs;
+	} else if (acpi_gbl_FADT.facs) {
+		(void)acpi_get_table_by_index(acpi_gbl_facs_index,
+					      ACPI_CAST_INDIRECT_PTR(struct
+								     acpi_table_header,
+								     &facs));
+		acpi_gbl_FACS = facs;
 	}
 
 	/* If there is no FACS, just continue. There was already an error msg */
@@ -192,7 +191,7 @@ struct acpi_table_header *acpi_tb_copy_dsdt(u32 table_index)
 	acpi_tb_uninstall_table(table_desc);
 
 	acpi_tb_init_table_descriptor(&acpi_gbl_root_table_list.
-				      tables[ACPI_TABLE_INDEX_DSDT],
+				      tables[acpi_gbl_dsdt_index],
 				      ACPI_PTR_TO_PHYSADDR(new_table),
 				      ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL,
 				      new_table);
@@ -369,13 +368,6 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 			    table_entry_size);
 	table_entry = ACPI_ADD_PTR(u8, table, sizeof(struct acpi_table_header));
 
-	/*
-	 * First three entries in the table array are reserved for the DSDT
-	 * and 32bit/64bit FACS, which are not actually present in the
-	 * RSDT/XSDT - they come from the FADT
-	 */
-	acpi_gbl_root_table_list.current_table_count = 3;
-
 	/* Initialize the root table array from the RSDT/XSDT */
 
 	for (i = 0; i < table_count; i++) {
@@ -412,3 +404,36 @@ next_table:
 
 	return_ACPI_STATUS(AE_OK);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_is_valid_signature
+ *
+ * PARAMETERS:  signature           - Sig string to be validated
+ *
+ * RETURN:      TRUE if signature is correct length and has valid characters
+ *
+ * DESCRIPTION: Validate an ACPI table signature.
+ *
+ ******************************************************************************/
+
+u8 acpi_is_valid_signature(char *signature)
+{
+	u32 i;
+
+	/* Validate the signature length */
+
+	if (strlen(signature) != ACPI_NAME_SIZE) {
+		return (FALSE);
+	}
+
+	/* Validate each character in the signature */
+
+	for (i = 0; i < ACPI_NAME_SIZE; i++) {
+		if (!acpi_ut_valid_acpi_char(signature[i], i)) {
+			return (FALSE);
+		}
+	}
+
+	return (TRUE);
+}
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 9682d40ca6ff..55ee14ca9418 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -51,9 +51,6 @@
 #define _COMPONENT          ACPI_TABLES
 ACPI_MODULE_NAME("tbxfload")
 
-/* Local prototypes */
-static acpi_status acpi_tb_load_namespace(void);
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_load_tables
@@ -65,7 +62,6 @@ static acpi_status acpi_tb_load_namespace(void);
  * DESCRIPTION: Load the ACPI tables from the RSDT/XSDT
  *
  ******************************************************************************/
-
 acpi_status __init acpi_load_tables(void)
 {
 	acpi_status status;
@@ -75,6 +71,13 @@ acpi_status __init acpi_load_tables(void)
 	/* Load the namespace from the tables */
 
 	status = acpi_tb_load_namespace();
+
+	/* Don't let single failures abort the load */
+
+	if (status == AE_CTRL_TERMINATE) {
+		status = AE_OK;
+	}
+
 	if (ACPI_FAILURE(status)) {
 		ACPI_EXCEPTION((AE_INFO, status,
 				"While loading namespace from ACPI tables"));
@@ -97,11 +100,14 @@ ACPI_EXPORT_SYMBOL_INIT(acpi_load_tables)
  *              the RSDT/XSDT.
  *
  ******************************************************************************/
-static acpi_status acpi_tb_load_namespace(void)
+acpi_status acpi_tb_load_namespace(void)
 {
 	acpi_status status;
 	u32 i;
 	struct acpi_table_header *new_dsdt;
+	struct acpi_table_desc *table;
+	u32 tables_loaded = 0;
+	u32 tables_failed = 0;
 
 	ACPI_FUNCTION_TRACE(tb_load_namespace);
 
@@ -111,15 +117,11 @@ static acpi_status acpi_tb_load_namespace(void)
 	 * Load the namespace. The DSDT is required, but any SSDT and
 	 * PSDT tables are optional. Verify the DSDT.
 	 */
+	table = &acpi_gbl_root_table_list.tables[acpi_gbl_dsdt_index];
+
 	if (!acpi_gbl_root_table_list.current_table_count ||
-	    !ACPI_COMPARE_NAME(&
-			       (acpi_gbl_root_table_list.
-				tables[ACPI_TABLE_INDEX_DSDT].signature),
-			       ACPI_SIG_DSDT)
-	    ||
-	    ACPI_FAILURE(acpi_tb_validate_table
-			 (&acpi_gbl_root_table_list.
-			  tables[ACPI_TABLE_INDEX_DSDT]))) {
+	    !ACPI_COMPARE_NAME(table->signature.ascii, ACPI_SIG_DSDT) ||
+	    ACPI_FAILURE(acpi_tb_validate_table(table))) {
 		status = AE_NO_ACPI_TABLES;
 		goto unlock_and_exit;
 	}
@@ -130,8 +132,7 @@ static acpi_status acpi_tb_load_namespace(void)
 	 * array can change dynamically as tables are loaded at run-time. Note:
 	 * .Pointer field is not validated until after call to acpi_tb_validate_table.
 	 */
-	acpi_gbl_DSDT =
-	    acpi_gbl_root_table_list.tables[ACPI_TABLE_INDEX_DSDT].pointer;
+	acpi_gbl_DSDT = table->pointer;
 
 	/*
 	 * Optionally copy the entire DSDT to local memory (instead of simply
@@ -140,7 +141,7 @@ static acpi_status acpi_tb_load_namespace(void)
 	 * the DSDT.
 	 */
 	if (acpi_gbl_copy_dsdt_locally) {
-		new_dsdt = acpi_tb_copy_dsdt(ACPI_TABLE_INDEX_DSDT);
+		new_dsdt = acpi_tb_copy_dsdt(acpi_gbl_dsdt_index);
 		if (new_dsdt) {
 			acpi_gbl_DSDT = new_dsdt;
 		}
@@ -157,41 +158,65 @@ static acpi_status acpi_tb_load_namespace(void)
 
 	/* Load and parse tables */
 
-	status = acpi_ns_load_table(ACPI_TABLE_INDEX_DSDT, acpi_gbl_root_node);
+	status = acpi_ns_load_table(acpi_gbl_dsdt_index, acpi_gbl_root_node);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		ACPI_EXCEPTION((AE_INFO, status, "[DSDT] table load failed"));
+		tables_failed++;
+	} else {
+		tables_loaded++;
 	}
 
 	/* Load any SSDT or PSDT tables. Note: Loop leaves tables locked */
 
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) {
+		table = &acpi_gbl_root_table_list.tables[i];
+
 		if (!acpi_gbl_root_table_list.tables[i].address ||
-		    (!ACPI_COMPARE_NAME
-		     (&(acpi_gbl_root_table_list.tables[i].signature),
-		      ACPI_SIG_SSDT)
-		     &&
-		     !ACPI_COMPARE_NAME(&
-					(acpi_gbl_root_table_list.tables[i].
-					 signature), ACPI_SIG_PSDT)
-		     &&
-		     !ACPI_COMPARE_NAME(&
-					(acpi_gbl_root_table_list.tables[i].
-					 signature), ACPI_SIG_OSDT))
-		    ||
-		    ACPI_FAILURE(acpi_tb_validate_table
-				 (&acpi_gbl_root_table_list.tables[i]))) {
+		    (!ACPI_COMPARE_NAME(table->signature.ascii, ACPI_SIG_SSDT)
+		     && !ACPI_COMPARE_NAME(table->signature.ascii,
+					   ACPI_SIG_PSDT)
+		     && !ACPI_COMPARE_NAME(table->signature.ascii,
+					   ACPI_SIG_OSDT))
+		    || ACPI_FAILURE(acpi_tb_validate_table(table))) {
 			continue;
 		}
 
 		/* Ignore errors while loading tables, get as many as possible */
 
 		(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
-		(void)acpi_ns_load_table(i, acpi_gbl_root_node);
+		status = acpi_ns_load_table(i, acpi_gbl_root_node);
+		if (ACPI_FAILURE(status)) {
+			ACPI_EXCEPTION((AE_INFO, status,
+					"(%4.4s:%8.8s) while loading table",
+					table->signature.ascii,
+					table->pointer->oem_table_id));
+			tables_failed++;
+
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
+					      "Table [%4.4s:%8.8s] (id FF) - Table namespace load failed\n\n",
+					      table->signature.ascii,
+					      table->pointer->oem_table_id));
+		} else {
+			tables_loaded++;
+		}
+
 		(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 	}
 
-	ACPI_INFO((AE_INFO, "All ACPI Tables successfully acquired"));
+	if (!tables_failed) {
+		ACPI_INFO((AE_INFO,
+			   "%u ACPI AML tables successfully acquired and loaded",
+			   tables_loaded));
+	} else {
+		ACPI_ERROR((AE_INFO,
+			    "%u table load failures, %u successful",
+			    tables_failed, tables_loaded));
+
+		/* Indicate at least one failure */
+
+		status = AE_CTRL_TERMINATE;
+	}
 
 unlock_and_exit:
 	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index cd02693841db..4146229103c8 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -45,6 +45,7 @@
 
 #include <acpi/acpi.h>
 #include "accommon.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utdebug")
@@ -560,8 +561,37 @@ acpi_ut_ptr_exit(u32 line_number,
 	}
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_trace_point
+ *
+ * PARAMETERS:  type                - Trace event type
+ *              begin               - TRUE if before execution
+ *              aml                 - Executed AML address
+ *              pathname            - Object path
+ *              pointer             - Pointer to the related object
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Interpreter execution trace.
+ *
+ ******************************************************************************/
+
+void
+acpi_trace_point(acpi_trace_event_type type, u8 begin, u8 *aml, char *pathname)
+{
+
+	ACPI_FUNCTION_ENTRY();
+
+	acpi_ex_trace_point(type, begin, aml, pathname);
+
+#ifdef ACPI_USE_SYSTEM_TRACER
+	acpi_os_trace_point(type, begin, aml, pathname);
 #endif
+}
 
+ACPI_EXPORT_SYMBOL(acpi_trace_point)
+#endif
 #ifdef ACPI_APPLICATION
 /*******************************************************************************
  *
@@ -575,7 +605,6 @@ acpi_ut_ptr_exit(u32 line_number,
  * DESCRIPTION: Print error message to the console, used by applications.
  *
  ******************************************************************************/
-
 void ACPI_INTERNAL_VAR_XFACE acpi_log_error(const char *format, ...)
 {
 	va_list args;
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index 71fce389fd48..1638312e3d8f 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -209,6 +209,9 @@ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object)
 			acpi_ut_delete_object_desc(object->method.mutex);
 			object->method.mutex = NULL;
 		}
+		if (object->method.node) {
+			object->method.node = NULL;
+		}
 		break;
 
 	case ACPI_TYPE_REGION:
diff --git a/drivers/acpi/acpica/utfileio.c b/drivers/acpi/acpica/utfileio.c
index 857af824337b..75a94f52b4be 100644
--- a/drivers/acpi/acpica/utfileio.c
+++ b/drivers/acpi/acpica/utfileio.c
@@ -312,7 +312,7 @@ acpi_ut_read_table_from_file(char *filename, struct acpi_table_header ** table)
 	/* Get the entire file */
 
 	fprintf(stderr,
-		"Reading ACPI table from file %10s - Length %.8u (0x%06X)\n",
+		"Reading ACPI table from file %12s - Length %.8u (0x%06X)\n",
 		filename, file_size, file_size);
 
 	status = acpi_ut_read_table(file, table, &table_length);
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index e402e07b4846..28ab3a1d5ec1 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -204,11 +204,10 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_gbl_acpi_hardware_present = TRUE;
 	acpi_gbl_last_owner_id_index = 0;
 	acpi_gbl_next_owner_id_offset = 0;
-	acpi_gbl_trace_dbg_level = 0;
-	acpi_gbl_trace_dbg_layer = 0;
 	acpi_gbl_debugger_configuration = DEBUGGER_THREADING;
 	acpi_gbl_osi_mutex = NULL;
 	acpi_gbl_reg_methods_executed = FALSE;
+	acpi_gbl_max_loop_iterations = 0xFFFF;
 
 	/* Hardware oriented */
 
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index 71b66537f826..bd4443bdcbad 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -75,7 +75,7 @@ u8 acpi_ut_is_pci_root_bridge(char *id)
 	return (FALSE);
 }
 
-#if (defined ACPI_ASL_COMPILER || defined ACPI_EXEC_APP)
+#if (defined ACPI_ASL_COMPILER || defined ACPI_EXEC_APP || defined ACPI_NAMES_APP)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_is_aml_table
@@ -376,7 +376,7 @@ acpi_ut_display_init_pathname(u8 type,
 	/* Get the full pathname to the node */
 
 	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
-	status = acpi_ns_handle_to_pathname(obj_handle, &buffer);
+	status = acpi_ns_handle_to_pathname(obj_handle, &buffer, TRUE);
 	if (ACPI_FAILURE(status)) {
 		return;
 	}
diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c
new file mode 100644
index 000000000000..1d5f6b17b766
--- /dev/null
+++ b/drivers/acpi/acpica/utnonansi.c
@@ -0,0 +1,380 @@
+/*******************************************************************************
+ *
+ * Module Name: utnonansi - Non-ansi C library functions
+ *
+ ******************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2015, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+
+#define _COMPONENT          ACPI_UTILITIES
+ACPI_MODULE_NAME("utnonansi")
+
+/*
+ * Non-ANSI C library functions - strlwr, strupr, stricmp, and a 64-bit
+ * version of strtoul.
+ */
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_strlwr (strlwr)
+ *
+ * PARAMETERS:  src_string      - The source string to convert
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Convert a string to lowercase
+ *
+ ******************************************************************************/
+void acpi_ut_strlwr(char *src_string)
+{
+	char *string;
+
+	ACPI_FUNCTION_ENTRY();
+
+	if (!src_string) {
+		return;
+	}
+
+	/* Walk entire string, lowercasing the letters */
+
+	for (string = src_string; *string; string++) {
+		*string = (char)tolower((int)*string);
+	}
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_strupr (strupr)
+ *
+ * PARAMETERS:  src_string      - The source string to convert
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Convert a string to uppercase
+ *
+ ******************************************************************************/
+
+void acpi_ut_strupr(char *src_string)
+{
+	char *string;
+
+	ACPI_FUNCTION_ENTRY();
+
+	if (!src_string) {
+		return;
+	}
+
+	/* Walk entire string, uppercasing the letters */
+
+	for (string = src_string; *string; string++) {
+		*string = (char)toupper((int)*string);
+	}
+}
+
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_stricmp (stricmp)
+ *
+ * PARAMETERS:  string1             - first string to compare
+ *              string2             - second string to compare
+ *
+ * RETURN:      int that signifies string relationship. Zero means strings
+ *              are equal.
+ *
+ * DESCRIPTION: Case-insensitive string compare. Implementation of the
+ *              non-ANSI stricmp function.
+ *
+ ******************************************************************************/
+
+int acpi_ut_stricmp(char *string1, char *string2)
+{
+	int c1;
+	int c2;
+
+	do {
+		c1 = tolower((int)*string1);
+		c2 = tolower((int)*string2);
+
+		string1++;
+		string2++;
+	}
+	while ((c1 == c2) && (c1));
+
+	return (c1 - c2);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_strtoul64
+ *
+ * PARAMETERS:  string          - Null terminated string
+ *              base            - Radix of the string: 16 or ACPI_ANY_BASE;
+ *                                ACPI_ANY_BASE means 'in behalf of to_integer'
+ *              ret_integer     - Where the converted integer is returned
+ *
+ * RETURN:      Status and Converted value
+ *
+ * DESCRIPTION: Convert a string into an unsigned value. Performs either a
+ *              32-bit or 64-bit conversion, depending on the current mode
+ *              of the interpreter.
+ *
+ * NOTE:        Does not support Octal strings, not needed.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer)
+{
+	u32 this_digit = 0;
+	u64 return_value = 0;
+	u64 quotient;
+	u64 dividend;
+	u32 to_integer_op = (base == ACPI_ANY_BASE);
+	u32 mode32 = (acpi_gbl_integer_byte_width == 4);
+	u8 valid_digits = 0;
+	u8 sign_of0x = 0;
+	u8 term = 0;
+
+	ACPI_FUNCTION_TRACE_STR(ut_stroul64, string);
+
+	switch (base) {
+	case ACPI_ANY_BASE:
+	case 16:
+
+		break;
+
+	default:
+
+		/* Invalid Base */
+
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	if (!string) {
+		goto error_exit;
+	}
+
+	/* Skip over any white space in the buffer */
+
+	while ((*string) && (isspace((int)*string) || *string == '\t')) {
+		string++;
+	}
+
+	if (to_integer_op) {
+		/*
+		 * Base equal to ACPI_ANY_BASE means 'ToInteger operation case'.
+		 * We need to determine if it is decimal or hexadecimal.
+		 */
+		if ((*string == '0') && (tolower((int)*(string + 1)) == 'x')) {
+			sign_of0x = 1;
+			base = 16;
+
+			/* Skip over the leading '0x' */
+			string += 2;
+		} else {
+			base = 10;
+		}
+	}
+
+	/* Any string left? Check that '0x' is not followed by white space. */
+
+	if (!(*string) || isspace((int)*string) || *string == '\t') {
+		if (to_integer_op) {
+			goto error_exit;
+		} else {
+			goto all_done;
+		}
+	}
+
+	/*
+	 * Perform a 32-bit or 64-bit conversion, depending upon the current
+	 * execution mode of the interpreter
+	 */
+	dividend = (mode32) ? ACPI_UINT32_MAX : ACPI_UINT64_MAX;
+
+	/* Main loop: convert the string to a 32- or 64-bit integer */
+
+	while (*string) {
+		if (isdigit((int)*string)) {
+
+			/* Convert ASCII 0-9 to Decimal value */
+
+			this_digit = ((u8)*string) - '0';
+		} else if (base == 10) {
+
+			/* Digit is out of range; possible in to_integer case only */
+
+			term = 1;
+		} else {
+			this_digit = (u8)toupper((int)*string);
+			if (isxdigit((int)this_digit)) {
+
+				/* Convert ASCII Hex char to value */
+
+				this_digit = this_digit - 'A' + 10;
+			} else {
+				term = 1;
+			}
+		}
+
+		if (term) {
+			if (to_integer_op) {
+				goto error_exit;
+			} else {
+				break;
+			}
+		} else if ((valid_digits == 0) && (this_digit == 0)
+			   && !sign_of0x) {
+
+			/* Skip zeros */
+			string++;
+			continue;
+		}
+
+		valid_digits++;
+
+		if (sign_of0x
+		    && ((valid_digits > 16)
+			|| ((valid_digits > 8) && mode32))) {
+			/*
+			 * This is to_integer operation case.
+			 * No any restrictions for string-to-integer conversion,
+			 * see ACPI spec.
+			 */
+			goto error_exit;
+		}
+
+		/* Divide the digit into the correct position */
+
+		(void)acpi_ut_short_divide((dividend - (u64)this_digit),
+					   base, &quotient, NULL);
+
+		if (return_value > quotient) {
+			if (to_integer_op) {
+				goto error_exit;
+			} else {
+				break;
+			}
+		}
+
+		return_value *= base;
+		return_value += this_digit;
+		string++;
+	}
+
+	/* All done, normal exit */
+
+all_done:
+
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Converted value: %8.8X%8.8X\n",
+			  ACPI_FORMAT_UINT64(return_value)));
+
+	*ret_integer = return_value;
+	return_ACPI_STATUS(AE_OK);
+
+error_exit:
+	/* Base was set/validated above */
+
+	if (base == 10) {
+		return_ACPI_STATUS(AE_BAD_DECIMAL_CONSTANT);
+	} else {
+		return_ACPI_STATUS(AE_BAD_HEX_CONSTANT);
+	}
+}
+
+#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat
+ *
+ * PARAMETERS:  Adds a "DestSize" parameter to each of the standard string
+ *              functions. This is the size of the Destination buffer.
+ *
+ * RETURN:      TRUE if the operation would overflow the destination buffer.
+ *
+ * DESCRIPTION: Safe versions of standard Clib string functions. Ensure that
+ *              the result of the operation will not overflow the output string
+ *              buffer.
+ *
+ * NOTE:        These functions are typically only helpful for processing
+ *              user input and command lines. For most ACPICA code, the
+ *              required buffer length is precisely calculated before buffer
+ *              allocation, so the use of these functions is unnecessary.
+ *
+ ******************************************************************************/
+
+u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source)
+{
+
+	if (strlen(source) >= dest_size) {
+		return (TRUE);
+	}
+
+	strcpy(dest, source);
+	return (FALSE);
+}
+
+u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source)
+{
+
+	if ((strlen(dest) + strlen(source)) >= dest_size) {
+		return (TRUE);
+	}
+
+	strcat(dest, source);
+	return (FALSE);
+}
+
+u8
+acpi_ut_safe_strncat(char *dest,
+		     acpi_size dest_size,
+		     char *source, acpi_size max_transfer_length)
+{
+	acpi_size actual_transfer_length;
+
+	actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source));
+
+	if ((strlen(dest) + actual_transfer_length) >= dest_size) {
+		return (TRUE);
+	}
+
+	strncat(dest, source, max_transfer_length);
+	return (FALSE);
+}
+#endif
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 8f3c883dfe0e..4ddd105d9741 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -48,286 +48,6 @@
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utstring")
 
-/*
- * Non-ANSI C library functions - strlwr, strupr, stricmp, and a 64-bit
- * version of strtoul.
- */
-#ifdef ACPI_ASL_COMPILER
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ut_strlwr (strlwr)
- *
- * PARAMETERS:  src_string      - The source string to convert
- *
- * RETURN:      None
- *
- * DESCRIPTION: Convert string to lowercase
- *
- * NOTE: This is not a POSIX function, so it appears here, not in utclib.c
- *
- ******************************************************************************/
-void acpi_ut_strlwr(char *src_string)
-{
-	char *string;
-
-	ACPI_FUNCTION_ENTRY();
-
-	if (!src_string) {
-		return;
-	}
-
-	/* Walk entire string, lowercasing the letters */
-
-	for (string = src_string; *string; string++) {
-		*string = (char)tolower((int)*string);
-	}
-
-	return;
-}
-
-/******************************************************************************
- *
- * FUNCTION:    acpi_ut_stricmp (stricmp)
- *
- * PARAMETERS:  string1             - first string to compare
- *              string2             - second string to compare
- *
- * RETURN:      int that signifies string relationship. Zero means strings
- *              are equal.
- *
- * DESCRIPTION: Implementation of the non-ANSI stricmp function (compare
- *              strings with no case sensitivity)
- *
- ******************************************************************************/
-
-int acpi_ut_stricmp(char *string1, char *string2)
-{
-	int c1;
-	int c2;
-
-	do {
-		c1 = tolower((int)*string1);
-		c2 = tolower((int)*string2);
-
-		string1++;
-		string2++;
-	}
-	while ((c1 == c2) && (c1));
-
-	return (c1 - c2);
-}
-#endif
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ut_strupr (strupr)
- *
- * PARAMETERS:  src_string      - The source string to convert
- *
- * RETURN:      None
- *
- * DESCRIPTION: Convert string to uppercase
- *
- * NOTE: This is not a POSIX function, so it appears here, not in utclib.c
- *
- ******************************************************************************/
-
-void acpi_ut_strupr(char *src_string)
-{
-	char *string;
-
-	ACPI_FUNCTION_ENTRY();
-
-	if (!src_string) {
-		return;
-	}
-
-	/* Walk entire string, uppercasing the letters */
-
-	for (string = src_string; *string; string++) {
-		*string = (char)toupper((int)*string);
-	}
-
-	return;
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ut_strtoul64
- *
- * PARAMETERS:  string          - Null terminated string
- *              base            - Radix of the string: 16 or ACPI_ANY_BASE;
- *                                ACPI_ANY_BASE means 'in behalf of to_integer'
- *              ret_integer     - Where the converted integer is returned
- *
- * RETURN:      Status and Converted value
- *
- * DESCRIPTION: Convert a string into an unsigned value. Performs either a
- *              32-bit or 64-bit conversion, depending on the current mode
- *              of the interpreter.
- *              NOTE: Does not support Octal strings, not needed.
- *
- ******************************************************************************/
-
-acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer)
-{
-	u32 this_digit = 0;
-	u64 return_value = 0;
-	u64 quotient;
-	u64 dividend;
-	u32 to_integer_op = (base == ACPI_ANY_BASE);
-	u32 mode32 = (acpi_gbl_integer_byte_width == 4);
-	u8 valid_digits = 0;
-	u8 sign_of0x = 0;
-	u8 term = 0;
-
-	ACPI_FUNCTION_TRACE_STR(ut_stroul64, string);
-
-	switch (base) {
-	case ACPI_ANY_BASE:
-	case 16:
-
-		break;
-
-	default:
-
-		/* Invalid Base */
-
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
-	}
-
-	if (!string) {
-		goto error_exit;
-	}
-
-	/* Skip over any white space in the buffer */
-
-	while ((*string) && (isspace((int)*string) || *string == '\t')) {
-		string++;
-	}
-
-	if (to_integer_op) {
-		/*
-		 * Base equal to ACPI_ANY_BASE means 'ToInteger operation case'.
-		 * We need to determine if it is decimal or hexadecimal.
-		 */
-		if ((*string == '0') && (tolower((int)*(string + 1)) == 'x')) {
-			sign_of0x = 1;
-			base = 16;
-
-			/* Skip over the leading '0x' */
-			string += 2;
-		} else {
-			base = 10;
-		}
-	}
-
-	/* Any string left? Check that '0x' is not followed by white space. */
-
-	if (!(*string) || isspace((int)*string) || *string == '\t') {
-		if (to_integer_op) {
-			goto error_exit;
-		} else {
-			goto all_done;
-		}
-	}
-
-	/*
-	 * Perform a 32-bit or 64-bit conversion, depending upon the current
-	 * execution mode of the interpreter
-	 */
-	dividend = (mode32) ? ACPI_UINT32_MAX : ACPI_UINT64_MAX;
-
-	/* Main loop: convert the string to a 32- or 64-bit integer */
-
-	while (*string) {
-		if (isdigit((int)*string)) {
-
-			/* Convert ASCII 0-9 to Decimal value */
-
-			this_digit = ((u8)*string) - '0';
-		} else if (base == 10) {
-
-			/* Digit is out of range; possible in to_integer case only */
-
-			term = 1;
-		} else {
-			this_digit = (u8)toupper((int)*string);
-			if (isxdigit((int)this_digit)) {
-
-				/* Convert ASCII Hex char to value */
-
-				this_digit = this_digit - 'A' + 10;
-			} else {
-				term = 1;
-			}
-		}
-
-		if (term) {
-			if (to_integer_op) {
-				goto error_exit;
-			} else {
-				break;
-			}
-		} else if ((valid_digits == 0) && (this_digit == 0)
-			   && !sign_of0x) {
-
-			/* Skip zeros */
-			string++;
-			continue;
-		}
-
-		valid_digits++;
-
-		if (sign_of0x
-		    && ((valid_digits > 16)
-			|| ((valid_digits > 8) && mode32))) {
-			/*
-			 * This is to_integer operation case.
-			 * No any restrictions for string-to-integer conversion,
-			 * see ACPI spec.
-			 */
-			goto error_exit;
-		}
-
-		/* Divide the digit into the correct position */
-
-		(void)acpi_ut_short_divide((dividend - (u64)this_digit),
-					   base, &quotient, NULL);
-
-		if (return_value > quotient) {
-			if (to_integer_op) {
-				goto error_exit;
-			} else {
-				break;
-			}
-		}
-
-		return_value *= base;
-		return_value += this_digit;
-		string++;
-	}
-
-	/* All done, normal exit */
-
-all_done:
-
-	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Converted value: %8.8X%8.8X\n",
-			  ACPI_FORMAT_UINT64(return_value)));
-
-	*ret_integer = return_value;
-	return_ACPI_STATUS(AE_OK);
-
-error_exit:
-	/* Base was set/validated above */
-
-	if (base == 10) {
-		return_ACPI_STATUS(AE_BAD_DECIMAL_CONSTANT);
-	} else {
-		return_ACPI_STATUS(AE_BAD_HEX_CONSTANT);
-	}
-}
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_print_string
@@ -342,7 +62,6 @@ error_exit:
  *              sequences.
  *
  ******************************************************************************/
-
 void acpi_ut_print_string(char *string, u16 max_length)
 {
 	u32 i;
@@ -584,64 +303,3 @@ void ut_convert_backslashes(char *pathname)
 	}
 }
 #endif
-
-#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION)
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat
- *
- * PARAMETERS:  Adds a "DestSize" parameter to each of the standard string
- *              functions. This is the size of the Destination buffer.
- *
- * RETURN:      TRUE if the operation would overflow the destination buffer.
- *
- * DESCRIPTION: Safe versions of standard Clib string functions. Ensure that
- *              the result of the operation will not overflow the output string
- *              buffer.
- *
- * NOTE:        These functions are typically only helpful for processing
- *              user input and command lines. For most ACPICA code, the
- *              required buffer length is precisely calculated before buffer
- *              allocation, so the use of these functions is unnecessary.
- *
- ******************************************************************************/
-
-u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source)
-{
-
-	if (strlen(source) >= dest_size) {
-		return (TRUE);
-	}
-
-	strcpy(dest, source);
-	return (FALSE);
-}
-
-u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source)
-{
-
-	if ((strlen(dest) + strlen(source)) >= dest_size) {
-		return (TRUE);
-	}
-
-	strcat(dest, source);
-	return (FALSE);
-}
-
-u8
-acpi_ut_safe_strncat(char *dest,
-		     acpi_size dest_size,
-		     char *source, acpi_size max_transfer_length)
-{
-	acpi_size actual_transfer_length;
-
-	actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source));
-
-	if ((strlen(dest) + actual_transfer_length) >= dest_size) {
-		return (TRUE);
-	}
-
-	strncat(dest, source, max_transfer_length);
-	return (FALSE);
-}
-#endif
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 51cf52d52243..4f332815db00 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -92,13 +92,6 @@ acpi_status __init acpi_terminate(void)
 
 	acpi_ut_mutex_terminate();
 
-#ifdef ACPI_DEBUGGER
-
-	/* Shut down the debugger */
-
-	acpi_db_terminate();
-#endif
-
 	/* Now we can shutdown the OS-dependent layer */
 
 	status = acpi_os_terminate();
@@ -517,7 +510,8 @@ acpi_decode_pld_buffer(u8 *in_buffer,
 
 	/* Parameter validation */
 
-	if (!in_buffer || !return_buffer || (length < 16)) {
+	if (!in_buffer || !return_buffer
+	    || (length < ACPI_PLD_REV1_BUFFER_SIZE)) {
 		return (AE_BAD_PARAMETER);
 	}
 
@@ -567,7 +561,7 @@ acpi_decode_pld_buffer(u8 *in_buffer,
 	pld_info->rotation = ACPI_PLD_GET_ROTATION(&dword);
 	pld_info->order = ACPI_PLD_GET_ORDER(&dword);
 
-	if (length >= ACPI_PLD_BUFFER_SIZE) {
+	if (length >= ACPI_PLD_REV2_BUFFER_SIZE) {
 
 		/* Fifth 32-bit DWord (Revision 2 of _PLD) */
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 42a32a66ef22..a7137ec28447 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -124,17 +124,6 @@ acpi_status __init acpi_initialize_subsystem(void)
 		return_ACPI_STATUS(status);
 	}
 
-	/* If configured, initialize the AML debugger */
-
-#ifdef ACPI_DEBUGGER
-	status = acpi_db_initialize();
-	if (ACPI_FAILURE(status)) {
-		ACPI_EXCEPTION((AE_INFO, status,
-				"During Debugger initialization"));
-		return_ACPI_STATUS(status);
-	}
-#endif
-
 	return_ACPI_STATUS(AE_OK);
 }
 
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index a85ac07f3da3..a2c8d7adb6eb 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -24,10 +24,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index a095d4f858da..0431883653be 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -18,10 +18,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index 04ab5c9d3ced..6330f557a2c8 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -17,10 +17,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 3670bbab57a3..6682c5daf742 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -18,10 +18,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 2bfd53cbfe80..23981ac1c6c2 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -23,10 +23,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 06e9b411a0a2..20b3fcf4007c 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -21,10 +21,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b3628cc01a53..b719ab3090bb 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -18,10 +18,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 278dc4be992a..96809cd99ace 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -20,10 +20,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 513e7230e3d0..46506e7687cd 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -423,6 +419,406 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 	acpi_evaluate_ost(handle, type, ost_code, NULL);
 }
 
+static void acpi_device_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct acpi_device *device = data;
+
+	device->driver->ops.notify(device, event);
+}
+
+static void acpi_device_notify_fixed(void *data)
+{
+	struct acpi_device *device = data;
+
+	/* Fixed hardware devices have no handles */
+	acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
+}
+
+static u32 acpi_device_fixed_event(void *data)
+{
+	acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
+	return ACPI_INTERRUPT_HANDLED;
+}
+
+static int acpi_device_install_notify_handler(struct acpi_device *device)
+{
+	acpi_status status;
+
+	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
+		status =
+		    acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
+						     acpi_device_fixed_event,
+						     device);
+	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
+		status =
+		    acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
+						     acpi_device_fixed_event,
+						     device);
+	else
+		status = acpi_install_notify_handler(device->handle,
+						     ACPI_DEVICE_NOTIFY,
+						     acpi_device_notify,
+						     device);
+
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+	return 0;
+}
+
+static void acpi_device_remove_notify_handler(struct acpi_device *device)
+{
+	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
+		acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
+						acpi_device_fixed_event);
+	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
+		acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
+						acpi_device_fixed_event);
+	else
+		acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
+					   acpi_device_notify);
+}
+
+/* --------------------------------------------------------------------------
+                             Device Matching
+   -------------------------------------------------------------------------- */
+
+static struct acpi_device *acpi_primary_dev_companion(struct acpi_device *adev,
+						      const struct device *dev)
+{
+	struct mutex *physical_node_lock = &adev->physical_node_lock;
+
+	mutex_lock(physical_node_lock);
+	if (list_empty(&adev->physical_node_list)) {
+		adev = NULL;
+	} else {
+		const struct acpi_device_physical_node *node;
+
+		node = list_first_entry(&adev->physical_node_list,
+					struct acpi_device_physical_node, node);
+		if (node->dev != dev)
+			adev = NULL;
+	}
+	mutex_unlock(physical_node_lock);
+	return adev;
+}
+
+/**
+ * acpi_device_is_first_physical_node - Is given dev first physical node
+ * @adev: ACPI companion device
+ * @dev: Physical device to check
+ *
+ * Function checks if given @dev is the first physical devices attached to
+ * the ACPI companion device. This distinction is needed in some cases
+ * where the same companion device is shared between many physical devices.
+ *
+ * Note that the caller have to provide valid @adev pointer.
+ */
+bool acpi_device_is_first_physical_node(struct acpi_device *adev,
+					const struct device *dev)
+{
+	return !!acpi_primary_dev_companion(adev, dev);
+}
+
+/*
+ * acpi_companion_match() - Can we match via ACPI companion device
+ * @dev: Device in question
+ *
+ * Check if the given device has an ACPI companion and if that companion has
+ * a valid list of PNP IDs, and if the device is the first (primary) physical
+ * device associated with it.  Return the companion pointer if that's the case
+ * or NULL otherwise.
+ *
+ * If multiple physical devices are attached to a single ACPI companion, we need
+ * to be careful.  The usage scenario for this kind of relationship is that all
+ * of the physical devices in question use resources provided by the ACPI
+ * companion.  A typical case is an MFD device where all the sub-devices share
+ * the parent's ACPI companion.  In such cases we can only allow the primary
+ * (first) physical device to be matched with the help of the companion's PNP
+ * IDs.
+ *
+ * Additional physical devices sharing the ACPI companion can still use
+ * resources available from it but they will be matched normally using functions
+ * provided by their bus types (and analogously for their modalias).
+ */
+struct acpi_device *acpi_companion_match(const struct device *dev)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return NULL;
+
+	if (list_empty(&adev->pnp.ids))
+		return NULL;
+
+	return acpi_primary_dev_companion(adev, dev);
+}
+
+/**
+ * acpi_of_match_device - Match device object using the "compatible" property.
+ * @adev: ACPI device object to match.
+ * @of_match_table: List of device IDs to match against.
+ *
+ * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
+ * identifiers and a _DSD object with the "compatible" property, use that
+ * property to match against the given list of identifiers.
+ */
+static bool acpi_of_match_device(struct acpi_device *adev,
+				 const struct of_device_id *of_match_table)
+{
+	const union acpi_object *of_compatible, *obj;
+	int i, nval;
+
+	if (!adev)
+		return false;
+
+	of_compatible = adev->data.of_compatible;
+	if (!of_match_table || !of_compatible)
+		return false;
+
+	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
+		nval = of_compatible->package.count;
+		obj = of_compatible->package.elements;
+	} else { /* Must be ACPI_TYPE_STRING. */
+		nval = 1;
+		obj = of_compatible;
+	}
+	/* Now we can look for the driver DT compatible strings */
+	for (i = 0; i < nval; i++, obj++) {
+		const struct of_device_id *id;
+
+		for (id = of_match_table; id->compatible[0]; id++)
+			if (!strcasecmp(obj->string.pointer, id->compatible))
+				return true;
+	}
+
+	return false;
+}
+
+static bool __acpi_match_device_cls(const struct acpi_device_id *id,
+				    struct acpi_hardware_id *hwid)
+{
+	int i, msk, byte_shift;
+	char buf[3];
+
+	if (!id->cls)
+		return false;
+
+	/* Apply class-code bitmask, before checking each class-code byte */
+	for (i = 1; i <= 3; i++) {
+		byte_shift = 8 * (3 - i);
+		msk = (id->cls_msk >> byte_shift) & 0xFF;
+		if (!msk)
+			continue;
+
+		sprintf(buf, "%02x", (id->cls >> byte_shift) & msk);
+		if (strncmp(buf, &hwid->id[(i - 1) * 2], 2))
+			return false;
+	}
+	return true;
+}
+
+static const struct acpi_device_id *__acpi_match_device(
+	struct acpi_device *device,
+	const struct acpi_device_id *ids,
+	const struct of_device_id *of_ids)
+{
+	const struct acpi_device_id *id;
+	struct acpi_hardware_id *hwid;
+
+	/*
+	 * If the device is not present, it is unnecessary to load device
+	 * driver for it.
+	 */
+	if (!device || !device->status.present)
+		return NULL;
+
+	list_for_each_entry(hwid, &device->pnp.ids, list) {
+		/* First, check the ACPI/PNP IDs provided by the caller. */
+		for (id = ids; id->id[0] || id->cls; id++) {
+			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
+				return id;
+			else if (id->cls && __acpi_match_device_cls(id, hwid))
+				return id;
+		}
+
+		/*
+		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
+		 * "compatible" property if found.
+		 *
+		 * The id returned by the below is not valid, but the only
+		 * caller passing non-NULL of_ids here is only interested in
+		 * whether or not the return value is NULL.
+		 */
+		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
+		    && acpi_of_match_device(device, of_ids))
+			return id;
+	}
+	return NULL;
+}
+
+/**
+ * acpi_match_device - Match a struct device against a given list of ACPI IDs
+ * @ids: Array of struct acpi_device_id object to match against.
+ * @dev: The device structure to match.
+ *
+ * Check if @dev has a valid ACPI handle and if there is a struct acpi_device
+ * object for that handle and use that object to match against a given list of
+ * device IDs.
+ *
+ * Return a pointer to the first matching ID on success or %NULL on failure.
+ */
+const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
+					       const struct device *dev)
+{
+	return __acpi_match_device(acpi_companion_match(dev), ids, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_match_device);
+
+int acpi_match_device_ids(struct acpi_device *device,
+			  const struct acpi_device_id *ids)
+{
+	return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT;
+}
+EXPORT_SYMBOL(acpi_match_device_ids);
+
+bool acpi_driver_match_device(struct device *dev,
+			      const struct device_driver *drv)
+{
+	if (!drv->acpi_match_table)
+		return acpi_of_match_device(ACPI_COMPANION(dev),
+					    drv->of_match_table);
+
+	return !!__acpi_match_device(acpi_companion_match(dev),
+				     drv->acpi_match_table, drv->of_match_table);
+}
+EXPORT_SYMBOL_GPL(acpi_driver_match_device);
+
+/* --------------------------------------------------------------------------
+                              ACPI Driver Management
+   -------------------------------------------------------------------------- */
+
+/**
+ * acpi_bus_register_driver - register a driver with the ACPI bus
+ * @driver: driver being registered
+ *
+ * Registers a driver with the ACPI bus.  Searches the namespace for all
+ * devices that match the driver's criteria and binds.  Returns zero for
+ * success or a negative error status for failure.
+ */
+int acpi_bus_register_driver(struct acpi_driver *driver)
+{
+	int ret;
+
+	if (acpi_disabled)
+		return -ENODEV;
+	driver->drv.name = driver->name;
+	driver->drv.bus = &acpi_bus_type;
+	driver->drv.owner = driver->owner;
+
+	ret = driver_register(&driver->drv);
+	return ret;
+}
+
+EXPORT_SYMBOL(acpi_bus_register_driver);
+
+/**
+ * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
+ * @driver: driver to unregister
+ *
+ * Unregisters a driver with the ACPI bus.  Searches the namespace for all
+ * devices that match the driver's criteria and unbinds.
+ */
+void acpi_bus_unregister_driver(struct acpi_driver *driver)
+{
+	driver_unregister(&driver->drv);
+}
+
+EXPORT_SYMBOL(acpi_bus_unregister_driver);
+
+/* --------------------------------------------------------------------------
+                              ACPI Bus operations
+   -------------------------------------------------------------------------- */
+
+static int acpi_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_driver *acpi_drv = to_acpi_driver(drv);
+
+	return acpi_dev->flags.match_driver
+		&& !acpi_match_device_ids(acpi_dev, acpi_drv->ids);
+}
+
+static int acpi_device_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	return __acpi_device_uevent_modalias(to_acpi_device(dev), env);
+}
+
+static int acpi_device_probe(struct device *dev)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_driver *acpi_drv = to_acpi_driver(dev->driver);
+	int ret;
+
+	if (acpi_dev->handler && !acpi_is_pnp_device(acpi_dev))
+		return -EINVAL;
+
+	if (!acpi_drv->ops.add)
+		return -ENOSYS;
+
+	ret = acpi_drv->ops.add(acpi_dev);
+	if (ret)
+		return ret;
+
+	acpi_dev->driver = acpi_drv;
+	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+			  "Driver [%s] successfully bound to device [%s]\n",
+			  acpi_drv->name, acpi_dev->pnp.bus_id));
+
+	if (acpi_drv->ops.notify) {
+		ret = acpi_device_install_notify_handler(acpi_dev);
+		if (ret) {
+			if (acpi_drv->ops.remove)
+				acpi_drv->ops.remove(acpi_dev);
+
+			acpi_dev->driver = NULL;
+			acpi_dev->driver_data = NULL;
+			return ret;
+		}
+	}
+
+	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found driver [%s] for device [%s]\n",
+			  acpi_drv->name, acpi_dev->pnp.bus_id));
+	get_device(dev);
+	return 0;
+}
+
+static int acpi_device_remove(struct device * dev)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_driver *acpi_drv = acpi_dev->driver;
+
+	if (acpi_drv) {
+		if (acpi_drv->ops.notify)
+			acpi_device_remove_notify_handler(acpi_dev);
+		if (acpi_drv->ops.remove)
+			acpi_drv->ops.remove(acpi_dev);
+	}
+	acpi_dev->driver = NULL;
+	acpi_dev->driver_data = NULL;
+
+	put_device(dev);
+	return 0;
+}
+
+struct bus_type acpi_bus_type = {
+	.name		= "acpi",
+	.match		= acpi_bus_match,
+	.probe		= acpi_device_probe,
+	.remove		= acpi_device_remove,
+	.uevent		= acpi_device_uevent,
+};
+
 /* --------------------------------------------------------------------------
                              Initialization/Cleanup
    -------------------------------------------------------------------------- */
@@ -661,7 +1057,9 @@ static int __init acpi_bus_init(void)
 	 */
 	acpi_root_dir = proc_mkdir(ACPI_BUS_FILE_ROOT, NULL);
 
-	return 0;
+	result = bus_register(&acpi_bus_type);
+	if (!result)
+		return 0;
 
 	/* Mimic structured exception handling */
       error1:
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 6d5d1832a588..5c3b0918d5fd 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -16,10 +16,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/cm_sbs.c b/drivers/acpi/cm_sbs.c
index 6c9ee68e46fb..d0918d421f90 100644
--- a/drivers/acpi/cm_sbs.c
+++ b/drivers/acpi/cm_sbs.c
@@ -11,10 +11,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index c8ead9f97375..12c240903c18 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -20,10 +20,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 #include <linux/acpi.h>
diff --git a/drivers/acpi/debugfs.c b/drivers/acpi/debugfs.c
index 6b1919f6bd82..68bb305b977f 100644
--- a/drivers/acpi/debugfs.c
+++ b/drivers/acpi/debugfs.c
@@ -7,6 +7,8 @@
 #include <linux/debugfs.h>
 #include <linux/acpi.h>
 
+#include "internal.h"
+
 #define _COMPONENT		ACPI_SYSTEM_COMPONENT
 ACPI_MODULE_NAME("debugfs");
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 717afcdb5f4a..4806b7f856c4 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -231,7 +227,7 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		dev_warn(&device->dev, "Failed to change power state to %s\n",
 			 acpi_power_state_string(state));
 	} else {
-		device->power.state = state;
+		device->power.state = target_state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Device [%s] transitioned to %s\n",
 				  device->pnp.bus_id,
@@ -1123,6 +1119,14 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	if (dev->pm_domain)
 		return -EEXIST;
 
+	/*
+	 * Only attach the power domain to the first device if the
+	 * companion is shared by multiple. This is to prevent doing power
+	 * management twice.
+	 */
+	if (!acpi_device_is_first_physical_node(adev, dev))
+		return -EBUSY;
+
 	acpi_add_pm_notifier(adev, dev, acpi_pm_notify_work_func);
 	dev->pm_domain = &acpi_general_pm_domain;
 	if (power_on) {
diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c
new file mode 100644
index 000000000000..4ab4582e586b
--- /dev/null
+++ b/drivers/acpi/device_sysfs.c
@@ -0,0 +1,521 @@
+/*
+ * drivers/acpi/device_sysfs.c - ACPI device sysfs attributes and modalias.
+ *
+ * Copyright (C) 2015, Intel Corp.
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/nls.h>
+
+#include "internal.h"
+
+/**
+ * create_pnp_modalias - Create hid/cid(s) string for modalias and uevent
+ * @acpi_dev: ACPI device object.
+ * @modalias: Buffer to print into.
+ * @size: Size of the buffer.
+ *
+ * Creates hid/cid(s) string needed for modalias and uevent
+ * e.g. on a device with hid:IBM0001 and cid:ACPI0001 you get:
+ * char *modalias: "acpi:IBM0001:ACPI0001"
+ * Return: 0: no _HID and no _CID
+ *         -EINVAL: output error
+ *         -ENOMEM: output is truncated
+*/
+static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
+			       int size)
+{
+	int len;
+	int count;
+	struct acpi_hardware_id *id;
+
+	/*
+	 * Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
+	 * be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
+	 * device's list.
+	 */
+	count = 0;
+	list_for_each_entry(id, &acpi_dev->pnp.ids, list)
+		if (strcmp(id->id, ACPI_DT_NAMESPACE_HID))
+			count++;
+
+	if (!count)
+		return 0;
+
+	len = snprintf(modalias, size, "acpi:");
+	if (len <= 0)
+		return len;
+
+	size -= len;
+
+	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
+		if (!strcmp(id->id, ACPI_DT_NAMESPACE_HID))
+			continue;
+
+		count = snprintf(&modalias[len], size, "%s:", id->id);
+		if (count < 0)
+			return -EINVAL;
+
+		if (count >= size)
+			return -ENOMEM;
+
+		len += count;
+		size -= count;
+	}
+	modalias[len] = '\0';
+	return len;
+}
+
+/**
+ * create_of_modalias - Creates DT compatible string for modalias and uevent
+ * @acpi_dev: ACPI device object.
+ * @modalias: Buffer to print into.
+ * @size: Size of the buffer.
+ *
+ * Expose DT compatible modalias as of:NnameTCcompatible.  This function should
+ * only be called for devices having ACPI_DT_NAMESPACE_HID in their list of
+ * ACPI/PNP IDs.
+ */
+static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias,
+			      int size)
+{
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+	const union acpi_object *of_compatible, *obj;
+	int len, count;
+	int i, nval;
+	char *c;
+
+	acpi_get_name(acpi_dev->handle, ACPI_SINGLE_NAME, &buf);
+	/* DT strings are all in lower case */
+	for (c = buf.pointer; *c != '\0'; c++)
+		*c = tolower(*c);
+
+	len = snprintf(modalias, size, "of:N%sT", (char *)buf.pointer);
+	ACPI_FREE(buf.pointer);
+
+	if (len <= 0)
+		return len;
+
+	of_compatible = acpi_dev->data.of_compatible;
+	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
+		nval = of_compatible->package.count;
+		obj = of_compatible->package.elements;
+	} else { /* Must be ACPI_TYPE_STRING. */
+		nval = 1;
+		obj = of_compatible;
+	}
+	for (i = 0; i < nval; i++, obj++) {
+		count = snprintf(&modalias[len], size, "C%s",
+				 obj->string.pointer);
+		if (count < 0)
+			return -EINVAL;
+
+		if (count >= size)
+			return -ENOMEM;
+
+		len += count;
+		size -= count;
+	}
+	modalias[len] = '\0';
+	return len;
+}
+
+int __acpi_device_uevent_modalias(struct acpi_device *adev,
+				  struct kobj_uevent_env *env)
+{
+	int len;
+
+	if (!adev)
+		return -ENODEV;
+
+	if (list_empty(&adev->pnp.ids))
+		return 0;
+
+	if (add_uevent_var(env, "MODALIAS="))
+		return -ENOMEM;
+
+	len = create_pnp_modalias(adev, &env->buf[env->buflen - 1],
+				  sizeof(env->buf) - env->buflen);
+	if (len < 0)
+		return len;
+
+	env->buflen += len;
+	if (!adev->data.of_compatible)
+		return 0;
+
+	if (len > 0 && add_uevent_var(env, "MODALIAS="))
+		return -ENOMEM;
+
+	len = create_of_modalias(adev, &env->buf[env->buflen - 1],
+				 sizeof(env->buf) - env->buflen);
+	if (len < 0)
+		return len;
+
+	env->buflen += len;
+
+	return 0;
+}
+
+/**
+ * acpi_device_uevent_modalias - uevent modalias for ACPI-enumerated devices.
+ *
+ * Create the uevent modalias field for ACPI-enumerated devices.
+ *
+ * Because other buses do not support ACPI HIDs & CIDs, e.g. for a device with
+ * hid:IBM0001 and cid:ACPI0001 you get: "acpi:IBM0001:ACPI0001".
+ */
+int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env)
+{
+	return __acpi_device_uevent_modalias(acpi_companion_match(dev), env);
+}
+EXPORT_SYMBOL_GPL(acpi_device_uevent_modalias);
+
+static int __acpi_device_modalias(struct acpi_device *adev, char *buf, int size)
+{
+	int len, count;
+
+	if (!adev)
+		return -ENODEV;
+
+	if (list_empty(&adev->pnp.ids))
+		return 0;
+
+	len = create_pnp_modalias(adev, buf, size - 1);
+	if (len < 0) {
+		return len;
+	} else if (len > 0) {
+		buf[len++] = '\n';
+		size -= len;
+	}
+	if (!adev->data.of_compatible)
+		return len;
+
+	count = create_of_modalias(adev, buf + len, size - 1);
+	if (count < 0) {
+		return count;
+	} else if (count > 0) {
+		len += count;
+		buf[len++] = '\n';
+	}
+
+	return len;
+}
+
+/**
+ * acpi_device_modalias - modalias sysfs attribute for ACPI-enumerated devices.
+ *
+ * Create the modalias sysfs attribute for ACPI-enumerated devices.
+ *
+ * Because other buses do not support ACPI HIDs & CIDs, e.g. for a device with
+ * hid:IBM0001 and cid:ACPI0001 you get: "acpi:IBM0001:ACPI0001".
+ */
+int acpi_device_modalias(struct device *dev, char *buf, int size)
+{
+	return __acpi_device_modalias(acpi_companion_match(dev), buf, size);
+}
+EXPORT_SYMBOL_GPL(acpi_device_modalias);
+
+static ssize_t
+acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, char *buf) {
+	return __acpi_device_modalias(to_acpi_device(dev), buf, 1024);
+}
+static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL);
+
+static ssize_t real_power_state_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *adev = to_acpi_device(dev);
+	int state;
+	int ret;
+
+	ret = acpi_device_get_power(adev, &state);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%s\n", acpi_power_state_string(state));
+}
+
+static DEVICE_ATTR(real_power_state, 0444, real_power_state_show, NULL);
+
+static ssize_t power_state_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *adev = to_acpi_device(dev);
+
+	return sprintf(buf, "%s\n", acpi_power_state_string(adev->power.state));
+}
+
+static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
+
+static ssize_t
+acpi_eject_store(struct device *d, struct device_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct acpi_device *acpi_device = to_acpi_device(d);
+	acpi_object_type not_used;
+	acpi_status status;
+
+	if (!count || buf[0] != '1')
+		return -EINVAL;
+
+	if ((!acpi_device->handler || !acpi_device->handler->hotplug.enabled)
+	    && !acpi_device->driver)
+		return -ENODEV;
+
+	status = acpi_get_type(acpi_device->handle, &not_used);
+	if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable)
+		return -ENODEV;
+
+	get_device(&acpi_device->dev);
+	status = acpi_hotplug_schedule(acpi_device, ACPI_OST_EC_OSPM_EJECT);
+	if (ACPI_SUCCESS(status))
+		return count;
+
+	put_device(&acpi_device->dev);
+	acpi_evaluate_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
+			  ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL);
+	return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
+}
+
+static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store);
+
+static ssize_t
+acpi_device_hid_show(struct device *dev, struct device_attribute *attr, char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "%s\n", acpi_device_hid(acpi_dev));
+}
+static DEVICE_ATTR(hid, 0444, acpi_device_hid_show, NULL);
+
+static ssize_t acpi_device_uid_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "%s\n", acpi_dev->pnp.unique_id);
+}
+static DEVICE_ATTR(uid, 0444, acpi_device_uid_show, NULL);
+
+static ssize_t acpi_device_adr_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "0x%08x\n",
+		       (unsigned int)(acpi_dev->pnp.bus_address));
+}
+static DEVICE_ATTR(adr, 0444, acpi_device_adr_show, NULL);
+
+static ssize_t
+acpi_device_path_show(struct device *dev, struct device_attribute *attr, char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_buffer path = {ACPI_ALLOCATE_BUFFER, NULL};
+	int result;
+
+	result = acpi_get_name(acpi_dev->handle, ACPI_FULL_PATHNAME, &path);
+	if (result)
+		goto end;
+
+	result = sprintf(buf, "%s\n", (char*)path.pointer);
+	kfree(path.pointer);
+end:
+	return result;
+}
+static DEVICE_ATTR(path, 0444, acpi_device_path_show, NULL);
+
+/* sysfs file that shows description text from the ACPI _STR method */
+static ssize_t description_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	int result;
+
+	if (acpi_dev->pnp.str_obj == NULL)
+		return 0;
+
+	/*
+	 * The _STR object contains a Unicode identifier for a device.
+	 * We need to convert to utf-8 so it can be displayed.
+	 */
+	result = utf16s_to_utf8s(
+		(wchar_t *)acpi_dev->pnp.str_obj->buffer.pointer,
+		acpi_dev->pnp.str_obj->buffer.length,
+		UTF16_LITTLE_ENDIAN, buf,
+		PAGE_SIZE);
+
+	buf[result++] = '\n';
+
+	return result;
+}
+static DEVICE_ATTR(description, 0444, description_show, NULL);
+
+static ssize_t
+acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
+		     char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	acpi_status status;
+	unsigned long long sun;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return sprintf(buf, "%llu\n", sun);
+}
+static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
+
+static ssize_t status_show(struct device *dev, struct device_attribute *attr,
+				char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	acpi_status status;
+	unsigned long long sta;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "_STA", NULL, &sta);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return sprintf(buf, "%llu\n", sta);
+}
+static DEVICE_ATTR_RO(status);
+
+/**
+ * acpi_device_setup_files - Create sysfs attributes of an ACPI device.
+ * @dev: ACPI device object.
+ */
+int acpi_device_setup_files(struct acpi_device *dev)
+{
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_status status;
+	int result = 0;
+
+	/*
+	 * Devices gotten from FADT don't have a "path" attribute
+	 */
+	if (dev->handle) {
+		result = device_create_file(&dev->dev, &dev_attr_path);
+		if (result)
+			goto end;
+	}
+
+	if (!list_empty(&dev->pnp.ids)) {
+		result = device_create_file(&dev->dev, &dev_attr_hid);
+		if (result)
+			goto end;
+
+		result = device_create_file(&dev->dev, &dev_attr_modalias);
+		if (result)
+			goto end;
+	}
+
+	/*
+	 * If device has _STR, 'description' file is created
+	 */
+	if (acpi_has_method(dev->handle, "_STR")) {
+		status = acpi_evaluate_object(dev->handle, "_STR",
+					NULL, &buffer);
+		if (ACPI_FAILURE(status))
+			buffer.pointer = NULL;
+		dev->pnp.str_obj = buffer.pointer;
+		result = device_create_file(&dev->dev, &dev_attr_description);
+		if (result)
+			goto end;
+	}
+
+	if (dev->pnp.type.bus_address)
+		result = device_create_file(&dev->dev, &dev_attr_adr);
+	if (dev->pnp.unique_id)
+		result = device_create_file(&dev->dev, &dev_attr_uid);
+
+	if (acpi_has_method(dev->handle, "_SUN")) {
+		result = device_create_file(&dev->dev, &dev_attr_sun);
+		if (result)
+			goto end;
+	}
+
+	if (acpi_has_method(dev->handle, "_STA")) {
+		result = device_create_file(&dev->dev, &dev_attr_status);
+		if (result)
+			goto end;
+	}
+
+        /*
+         * If device has _EJ0, 'eject' file is created that is used to trigger
+         * hot-removal function from userland.
+         */
+	if (acpi_has_method(dev->handle, "_EJ0")) {
+		result = device_create_file(&dev->dev, &dev_attr_eject);
+		if (result)
+			return result;
+	}
+
+	if (dev->flags.power_manageable) {
+		result = device_create_file(&dev->dev, &dev_attr_power_state);
+		if (result)
+			return result;
+
+		if (dev->power.flags.power_resources)
+			result = device_create_file(&dev->dev,
+						    &dev_attr_real_power_state);
+	}
+
+end:
+	return result;
+}
+
+/**
+ * acpi_device_remove_files - Remove sysfs attributes of an ACPI device.
+ * @dev: ACPI device object.
+ */
+void acpi_device_remove_files(struct acpi_device *dev)
+{
+	if (dev->flags.power_manageable) {
+		device_remove_file(&dev->dev, &dev_attr_power_state);
+		if (dev->power.flags.power_resources)
+			device_remove_file(&dev->dev,
+					   &dev_attr_real_power_state);
+	}
+
+	/*
+	 * If device has _STR, remove 'description' file
+	 */
+	if (acpi_has_method(dev->handle, "_STR")) {
+		kfree(dev->pnp.str_obj);
+		device_remove_file(&dev->dev, &dev_attr_description);
+	}
+	/*
+	 * If device has _EJ0, remove 'eject' file.
+	 */
+	if (acpi_has_method(dev->handle, "_EJ0"))
+		device_remove_file(&dev->dev, &dev_attr_eject);
+
+	if (acpi_has_method(dev->handle, "_SUN"))
+		device_remove_file(&dev->dev, &dev_attr_sun);
+
+	if (dev->pnp.unique_id)
+		device_remove_file(&dev->dev, &dev_attr_uid);
+	if (dev->pnp.type.bus_address)
+		device_remove_file(&dev->dev, &dev_attr_adr);
+	device_remove_file(&dev->dev, &dev_attr_modalias);
+	device_remove_file(&dev->dev, &dev_attr_hid);
+	if (acpi_has_method(dev->handle, "_STA"))
+		device_remove_file(&dev->dev, &dev_attr_status);
+	if (dev->handle)
+		device_remove_file(&dev->dev, &dev_attr_path);
+}
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index a688aa243f6c..e8e128dede29 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -17,10 +17,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 9d4761d2f6b7..2614a839c60d 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -22,10 +22,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -165,8 +161,16 @@ struct transaction {
 	u8 flags;
 };
 
+struct acpi_ec_query {
+	struct transaction transaction;
+	struct work_struct work;
+	struct acpi_ec_query_handler *handler;
+};
+
 static int acpi_ec_query(struct acpi_ec *ec, u8 *data);
 static void advance_transaction(struct acpi_ec *ec);
+static void acpi_ec_event_handler(struct work_struct *work);
+static void acpi_ec_event_processor(struct work_struct *work);
 
 struct acpi_ec *boot_ec, *first_ec;
 EXPORT_SYMBOL(first_ec);
@@ -978,60 +982,90 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit)
 }
 EXPORT_SYMBOL_GPL(acpi_ec_remove_query_handler);
 
-static void acpi_ec_run(void *cxt)
+static struct acpi_ec_query *acpi_ec_create_query(u8 *pval)
 {
-	struct acpi_ec_query_handler *handler = cxt;
+	struct acpi_ec_query *q;
+	struct transaction *t;
+
+	q = kzalloc(sizeof (struct acpi_ec_query), GFP_KERNEL);
+	if (!q)
+		return NULL;
+	INIT_WORK(&q->work, acpi_ec_event_processor);
+	t = &q->transaction;
+	t->command = ACPI_EC_COMMAND_QUERY;
+	t->rdata = pval;
+	t->rlen = 1;
+	return q;
+}
+
+static void acpi_ec_delete_query(struct acpi_ec_query *q)
+{
+	if (q) {
+		if (q->handler)
+			acpi_ec_put_query_handler(q->handler);
+		kfree(q);
+	}
+}
+
+static void acpi_ec_event_processor(struct work_struct *work)
+{
+	struct acpi_ec_query *q = container_of(work, struct acpi_ec_query, work);
+	struct acpi_ec_query_handler *handler = q->handler;
 
-	if (!handler)
-		return;
 	ec_dbg_evt("Query(0x%02x) started", handler->query_bit);
 	if (handler->func)
 		handler->func(handler->data);
 	else if (handler->handle)
 		acpi_evaluate_object(handler->handle, NULL, NULL, NULL);
 	ec_dbg_evt("Query(0x%02x) stopped", handler->query_bit);
-	acpi_ec_put_query_handler(handler);
+	acpi_ec_delete_query(q);
 }
 
 static int acpi_ec_query(struct acpi_ec *ec, u8 *data)
 {
 	u8 value = 0;
 	int result;
-	acpi_status status;
 	struct acpi_ec_query_handler *handler;
-	struct transaction t = {.command = ACPI_EC_COMMAND_QUERY,
-				.wdata = NULL, .rdata = &value,
-				.wlen = 0, .rlen = 1};
+	struct acpi_ec_query *q;
+
+	q = acpi_ec_create_query(&value);
+	if (!q)
+		return -ENOMEM;
 
 	/*
 	 * Query the EC to find out which _Qxx method we need to evaluate.
 	 * Note that successful completion of the query causes the ACPI_EC_SCI
 	 * bit to be cleared (and thus clearing the interrupt source).
 	 */
-	result = acpi_ec_transaction(ec, &t);
-	if (result)
-		return result;
-	if (data)
-		*data = value;
+	result = acpi_ec_transaction(ec, &q->transaction);
 	if (!value)
-		return -ENODATA;
+		result = -ENODATA;
+	if (result)
+		goto err_exit;
 
 	mutex_lock(&ec->mutex);
 	list_for_each_entry(handler, &ec->list, node) {
 		if (value == handler->query_bit) {
-			/* have custom handler for this bit */
-			handler = acpi_ec_get_query_handler(handler);
+			q->handler = acpi_ec_get_query_handler(handler);
 			ec_dbg_evt("Query(0x%02x) scheduled",
-				   handler->query_bit);
-			status = acpi_os_execute((handler->func) ?
-				OSL_NOTIFY_HANDLER : OSL_GPE_HANDLER,
-				acpi_ec_run, handler);
-			if (ACPI_FAILURE(status))
+				   q->handler->query_bit);
+			/*
+			 * It is reported that _Qxx are evaluated in a
+			 * parallel way on Windows:
+			 * https://bugzilla.kernel.org/show_bug.cgi?id=94411
+			 */
+			if (!schedule_work(&q->work))
 				result = -EBUSY;
 			break;
 		}
 	}
 	mutex_unlock(&ec->mutex);
+
+err_exit:
+	if (result && q)
+		acpi_ec_delete_query(q);
+	if (data)
+		*data = value;
 	return result;
 }
 
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index bea0bbaafa97..e297a480e135 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -16,10 +16,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c
index a322710b5ba4..5c67a6d8f803 100644
--- a/drivers/acpi/hed.c
+++ b/drivers/acpi/hed.c
@@ -15,10 +15,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 4683a96932b9..9e426210c2a8 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -13,9 +13,6 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _ACPI_INTERNAL_H_
@@ -70,7 +67,7 @@ void acpi_scan_hotplug_enabled(struct acpi_hotplug_profile *hotplug, bool val);
 
 #ifdef CONFIG_DEBUG_FS
 extern struct dentry *acpi_debugfs_dir;
-int acpi_debugfs_init(void);
+void acpi_debugfs_init(void);
 #else
 static inline void acpi_debugfs_init(void) { return; }
 #endif
@@ -93,10 +90,21 @@ int acpi_device_add(struct acpi_device *device,
 		    void (*release)(struct device *));
 void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 			     int type, unsigned long long sta);
+int acpi_device_setup_files(struct acpi_device *dev);
+void acpi_device_remove_files(struct acpi_device *dev);
 void acpi_device_add_finalize(struct acpi_device *device);
 void acpi_free_pnp_ids(struct acpi_device_pnp *pnp);
 bool acpi_device_is_present(struct acpi_device *adev);
 bool acpi_device_is_battery(struct acpi_device *adev);
+bool acpi_device_is_first_physical_node(struct acpi_device *adev,
+					const struct device *dev);
+
+/* --------------------------------------------------------------------------
+                     Device Matching and Notification
+   -------------------------------------------------------------------------- */
+struct acpi_device *acpi_companion_match(const struct device *dev);
+int __acpi_device_uevent_modalias(struct acpi_device *adev,
+				  struct kobj_uevent_env *env);
 
 /* --------------------------------------------------------------------------
                                   Power Resource
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 2161fa178c8d..cf0fd96a7602 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/acpi.h>
 #include <linux/sort.h>
+#include <linux/pmem.h>
 #include <linux/io.h>
 #include "nfit.h"
 
@@ -305,6 +306,23 @@ static bool add_idt(struct acpi_nfit_desc *acpi_desc,
 	return true;
 }
 
+static bool add_flush(struct acpi_nfit_desc *acpi_desc,
+		struct acpi_nfit_flush_address *flush)
+{
+	struct device *dev = acpi_desc->dev;
+	struct nfit_flush *nfit_flush = devm_kzalloc(dev, sizeof(*nfit_flush),
+			GFP_KERNEL);
+
+	if (!nfit_flush)
+		return false;
+	INIT_LIST_HEAD(&nfit_flush->list);
+	nfit_flush->flush = flush;
+	list_add_tail(&nfit_flush->list, &acpi_desc->flushes);
+	dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__,
+			flush->device_handle, flush->hint_count);
+	return true;
+}
+
 static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table,
 		const void *end)
 {
@@ -338,7 +356,8 @@ static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table,
 			return err;
 		break;
 	case ACPI_NFIT_TYPE_FLUSH_ADDRESS:
-		dev_dbg(dev, "%s: flush\n", __func__);
+		if (!add_flush(acpi_desc, table))
+			return err;
 		break;
 	case ACPI_NFIT_TYPE_SMBIOS:
 		dev_dbg(dev, "%s: smbios\n", __func__);
@@ -389,6 +408,7 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
 {
 	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
 	struct nfit_memdev *nfit_memdev;
+	struct nfit_flush *nfit_flush;
 	struct nfit_dcr *nfit_dcr;
 	struct nfit_bdw *nfit_bdw;
 	struct nfit_idt *nfit_idt;
@@ -442,6 +462,14 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
 			nfit_mem->idt_bdw = nfit_idt->idt;
 			break;
 		}
+
+		list_for_each_entry(nfit_flush, &acpi_desc->flushes, list) {
+			if (nfit_flush->flush->device_handle !=
+					nfit_memdev->memdev->device_handle)
+				continue;
+			nfit_mem->nfit_flush = nfit_flush;
+			break;
+		}
 		break;
 	}
 
@@ -674,11 +702,11 @@ static ssize_t flags_show(struct device *dev,
 	u16 flags = to_nfit_memdev(dev)->flags;
 
 	return sprintf(buf, "%s%s%s%s%s\n",
-			flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save " : "",
-			flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore " : "",
-			flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush " : "",
-			flags & ACPI_NFIT_MEM_ARMED ? "arm " : "",
-			flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart " : "");
+		flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "",
+		flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore_fail " : "",
+		flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush_fail " : "",
+		flags & ACPI_NFIT_MEM_ARMED ? "not_armed " : "",
+		flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart_event " : "");
 }
 static DEVICE_ATTR_RO(flags);
 
@@ -821,12 +849,12 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		if ((mem_flags & ACPI_NFIT_MEM_FAILED_MASK) == 0)
 			continue;
 
-		dev_info(acpi_desc->dev, "%s: failed: %s%s%s%s\n",
+		dev_info(acpi_desc->dev, "%s flags:%s%s%s%s\n",
 				nvdimm_name(nvdimm),
-			mem_flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save " : "",
-			mem_flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore " : "",
-			mem_flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush " : "",
-			mem_flags & ACPI_NFIT_MEM_ARMED ? "arm " : "");
+		  mem_flags & ACPI_NFIT_MEM_SAVE_FAILED ? " save_fail" : "",
+		  mem_flags & ACPI_NFIT_MEM_RESTORE_FAILED ? " restore_fail":"",
+		  mem_flags & ACPI_NFIT_MEM_FLUSH_FAILED ? " flush_fail" : "",
+		  mem_flags & ACPI_NFIT_MEM_ARMED ? " not_armed" : "");
 
 	}
 
@@ -978,7 +1006,25 @@ static u64 to_interleave_offset(u64 offset, struct nfit_blk_mmio *mmio)
 	return mmio->base_offset + line_offset + table_offset + sub_line_offset;
 }
 
-static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
+static void wmb_blk(struct nfit_blk *nfit_blk)
+{
+
+	if (nfit_blk->nvdimm_flush) {
+		/*
+		 * The first wmb() is needed to 'sfence' all previous writes
+		 * such that they are architecturally visible for the platform
+		 * buffer flush.  Note that we've already arranged for pmem
+		 * writes to avoid the cache via arch_memcpy_to_pmem().  The
+		 * final wmb() ensures ordering for the NVDIMM flush write.
+		 */
+		wmb();
+		writeq(1, nfit_blk->nvdimm_flush);
+		wmb();
+	} else
+		wmb_pmem();
+}
+
+static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 {
 	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
 	u64 offset = nfit_blk->stat_offset + mmio->size * bw;
@@ -986,7 +1032,7 @@ static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 	if (mmio->num_lines)
 		offset = to_interleave_offset(offset, mmio);
 
-	return readq(mmio->base + offset);
+	return readl(mmio->base + offset);
 }
 
 static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
@@ -1012,7 +1058,10 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 		offset = to_interleave_offset(offset, mmio);
 
 	writeq(cmd, mmio->base + offset);
-	/* FIXME: conditionally perform read-back if mandated by firmware */
+	wmb_blk(nfit_blk);
+
+	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
+		readq(mmio->base + offset);
 }
 
 static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
@@ -1026,7 +1075,6 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 
 	base_offset = nfit_blk->bdw_offset + dpa % L1_CACHE_BYTES
 		+ lane * mmio->size;
-	/* TODO: non-temporal access, flush hints, cache management etc... */
 	write_blk_ctl(nfit_blk, lane, dpa, len, rw);
 	while (len) {
 		unsigned int c;
@@ -1045,13 +1093,19 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 		}
 
 		if (rw)
-			memcpy(mmio->aperture + offset, iobuf + copied, c);
+			memcpy_to_pmem(mmio->aperture + offset,
+					iobuf + copied, c);
 		else
-			memcpy(iobuf + copied, mmio->aperture + offset, c);
+			memcpy_from_pmem(iobuf + copied,
+					mmio->aperture + offset, c);
 
 		copied += c;
 		len -= c;
 	}
+
+	if (rw)
+		wmb_blk(nfit_blk);
+
 	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
 	return rc;
 }
@@ -1124,7 +1178,7 @@ static void nfit_spa_unmap(struct acpi_nfit_desc *acpi_desc,
 }
 
 static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
+		struct acpi_nfit_system_address *spa, enum spa_map_type type)
 {
 	resource_size_t start = spa->address;
 	resource_size_t n = spa->length;
@@ -1152,8 +1206,15 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
 	if (!res)
 		goto err_mem;
 
-	/* TODO: cacheability based on the spa type */
-	spa_map->iomem = ioremap_nocache(start, n);
+	if (type == SPA_MAP_APERTURE) {
+		/*
+		 * TODO: memremap_pmem() support, but that requires cache
+		 * flushing when the aperture is moved.
+		 */
+		spa_map->iomem = ioremap_wc(start, n);
+	} else
+		spa_map->iomem = ioremap_nocache(start, n);
+
 	if (!spa_map->iomem)
 		goto err_map;
 
@@ -1171,6 +1232,7 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
  * nfit_spa_map - interleave-aware managed-mappings of acpi_nfit_system_address ranges
  * @nvdimm_bus: NFIT-bus that provided the spa table entry
  * @nfit_spa: spa table to map
+ * @type: aperture or control region
  *
  * In the case where block-data-window apertures and
  * dimm-control-regions are interleaved they will end up sharing a
@@ -1180,12 +1242,12 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
  * unbound.
  */
 static void __iomem *nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
+		struct acpi_nfit_system_address *spa, enum spa_map_type type)
 {
 	void __iomem *iomem;
 
 	mutex_lock(&acpi_desc->spa_map_mutex);
-	iomem = __nfit_spa_map(acpi_desc, spa);
+	iomem = __nfit_spa_map(acpi_desc, spa, type);
 	mutex_unlock(&acpi_desc->spa_map_mutex);
 
 	return iomem;
@@ -1206,12 +1268,35 @@ static int nfit_blk_init_interleave(struct nfit_blk_mmio *mmio,
 	return 0;
 }
 
+static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
+		struct nvdimm *nvdimm, struct nfit_blk *nfit_blk)
+{
+	struct nd_cmd_dimm_flags flags;
+	int rc;
+
+	memset(&flags, 0, sizeof(flags));
+	rc = nd_desc->ndctl(nd_desc, nvdimm, ND_CMD_DIMM_FLAGS, &flags,
+			sizeof(flags));
+
+	if (rc >= 0 && flags.status == 0)
+		nfit_blk->dimm_flags = flags.flags;
+	else if (rc == -ENOTTY) {
+		/* fall back to a conservative default */
+		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH;
+		rc = 0;
+	} else
+		rc = -ENXIO;
+
+	return rc;
+}
+
 static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 		struct device *dev)
 {
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
+	struct nfit_flush *nfit_flush;
 	struct nfit_blk_mmio *mmio;
 	struct nfit_blk *nfit_blk;
 	struct nfit_mem *nfit_mem;
@@ -1223,8 +1308,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) {
 		dev_dbg(dev, "%s: missing%s%s%s\n", __func__,
 				nfit_mem ? "" : " nfit_mem",
-				nfit_mem->dcr ? "" : " dcr",
-				nfit_mem->bdw ? "" : " bdw");
+				(nfit_mem && nfit_mem->dcr) ? "" : " dcr",
+				(nfit_mem && nfit_mem->bdw) ? "" : " bdw");
 		return -ENXIO;
 	}
 
@@ -1237,7 +1322,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	/* map block aperture memory */
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw);
+	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
+			SPA_MAP_APERTURE);
 	if (!mmio->base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1259,7 +1345,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
 	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
 	mmio = &nfit_blk->mmio[DCR];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr);
+	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
+			SPA_MAP_CONTROL);
 	if (!mmio->base) {
 		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1277,6 +1364,24 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 		return rc;
 	}
 
+	rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk);
+	if (rc < 0) {
+		dev_dbg(dev, "%s: %s failed get DIMM flags\n",
+				__func__, nvdimm_name(nvdimm));
+		return rc;
+	}
+
+	nfit_flush = nfit_mem->nfit_flush;
+	if (nfit_flush && nfit_flush->flush->hint_count != 0) {
+		nfit_blk->nvdimm_flush = devm_ioremap_nocache(dev,
+				nfit_flush->flush->hint_address[0], 8);
+		if (!nfit_blk->nvdimm_flush)
+			return -ENOMEM;
+	}
+
+	if (!arch_has_pmem_api() && !nfit_blk->nvdimm_flush)
+		dev_warn(dev, "unable to guarantee persistence of writes\n");
+
 	if (mmio->line_size == 0)
 		return 0;
 
@@ -1459,6 +1564,7 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
 	INIT_LIST_HEAD(&acpi_desc->dcrs);
 	INIT_LIST_HEAD(&acpi_desc->bdws);
 	INIT_LIST_HEAD(&acpi_desc->idts);
+	INIT_LIST_HEAD(&acpi_desc->flushes);
 	INIT_LIST_HEAD(&acpi_desc->memdevs);
 	INIT_LIST_HEAD(&acpi_desc->dimms);
 	mutex_init(&acpi_desc->spa_map_mutex);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 81f2e8c5a79c..79b6d83875c1 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -40,6 +40,10 @@ enum nfit_uuids {
 	NFIT_UUID_MAX,
 };
 
+enum {
+	ND_BLK_DCR_LATCH = 2,
+};
+
 struct nfit_spa {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
@@ -60,6 +64,11 @@ struct nfit_idt {
 	struct list_head list;
 };
 
+struct nfit_flush {
+	struct acpi_nfit_flush_address *flush;
+	struct list_head list;
+};
+
 struct nfit_memdev {
 	struct acpi_nfit_memory_map *memdev;
 	struct list_head list;
@@ -77,6 +86,7 @@ struct nfit_mem {
 	struct acpi_nfit_system_address *spa_bdw;
 	struct acpi_nfit_interleave *idt_dcr;
 	struct acpi_nfit_interleave *idt_bdw;
+	struct nfit_flush *nfit_flush;
 	struct list_head list;
 	struct acpi_device *adev;
 	unsigned long dsm_mask;
@@ -88,6 +98,7 @@ struct acpi_nfit_desc {
 	struct mutex spa_map_mutex;
 	struct list_head spa_maps;
 	struct list_head memdevs;
+	struct list_head flushes;
 	struct list_head dimms;
 	struct list_head spas;
 	struct list_head dcrs;
@@ -109,7 +120,7 @@ struct nfit_blk {
 	struct nfit_blk_mmio {
 		union {
 			void __iomem *base;
-			void *aperture;
+			void __pmem  *aperture;
 		};
 		u64 size;
 		u64 base_offset;
@@ -123,6 +134,13 @@ struct nfit_blk {
 	u64 bdw_offset; /* post interleave offset */
 	u64 stat_offset;
 	u64 cmd_offset;
+	void __iomem *nvdimm_flush;
+	u32 dimm_flags;
+};
+
+enum spa_map_type {
+	SPA_MAP_CONTROL,
+	SPA_MAP_APERTURE,
 };
 
 struct nfit_spa_mapping {
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index acaa3b4ea504..72b6e9ef0ae9 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  */
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c262e4acd68d..739a4a6b3b9b 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -19,10 +19,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  */
@@ -47,6 +43,7 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
+#include <asm-generic/io-64-nonatomic-lo-hi.h>
 
 #include "internal.h"
 
@@ -83,6 +80,7 @@ static void *acpi_irq_context;
 static struct workqueue_struct *kacpid_wq;
 static struct workqueue_struct *kacpi_notify_wq;
 static struct workqueue_struct *kacpi_hotplug_wq;
+static bool acpi_os_initialized;
 
 /*
  * This list of permanent mappings is for memory that may be accessed from
@@ -175,10 +173,14 @@ static void __init acpi_request_region (struct acpi_generic_address *gas,
 	if (!addr || !length)
 		return;
 
-	acpi_reserve_region(addr, length, gas->space_id, 0, desc);
+	/* Resources are never freed */
+	if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+		request_region(addr, length, desc);
+	else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		request_mem_region(addr, length, desc);
 }
 
-static void __init acpi_reserve_resources(void)
+static int __init acpi_reserve_resources(void)
 {
 	acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
 		"ACPI PM1a_EVT_BLK");
@@ -207,7 +209,10 @@ static void __init acpi_reserve_resources(void)
 	if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
 		acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
 			       acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
+
+	return 0;
 }
+fs_initcall_sync(acpi_reserve_resources);
 
 void acpi_os_printf(const char *fmt, ...)
 {
@@ -940,21 +945,6 @@ acpi_status acpi_os_write_port(acpi_io_address port, u32 value, u32 width)
 
 EXPORT_SYMBOL(acpi_os_write_port);
 
-#ifdef readq
-static inline u64 read64(const volatile void __iomem *addr)
-{
-	return readq(addr);
-}
-#else
-static inline u64 read64(const volatile void __iomem *addr)
-{
-	u64 l, h;
-	l = readl(addr);
-	h = readl(addr+4);
-	return l | (h << 32);
-}
-#endif
-
 acpi_status
 acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
 {
@@ -987,7 +977,7 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
 		*(u32 *) value = readl(virt_addr);
 		break;
 	case 64:
-		*(u64 *) value = read64(virt_addr);
+		*(u64 *) value = readq(virt_addr);
 		break;
 	default:
 		BUG();
@@ -1001,19 +991,6 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
 	return AE_OK;
 }
 
-#ifdef writeq
-static inline void write64(u64 val, volatile void __iomem *addr)
-{
-	writeq(val, addr);
-}
-#else
-static inline void write64(u64 val, volatile void __iomem *addr)
-{
-	writel(val, addr);
-	writel(val>>32, addr+4);
-}
-#endif
-
 acpi_status
 acpi_os_write_memory(acpi_physical_address phys_addr, u64 value, u32 width)
 {
@@ -1042,7 +1019,7 @@ acpi_os_write_memory(acpi_physical_address phys_addr, u64 value, u32 width)
 		writel(value, virt_addr);
 		break;
 	case 64:
-		write64(value, virt_addr);
+		writeq(value, virt_addr);
 		break;
 	default:
 		BUG();
@@ -1309,6 +1286,9 @@ acpi_status acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 timeout)
 	long jiffies;
 	int ret = 0;
 
+	if (!acpi_os_initialized)
+		return AE_OK;
+
 	if (!sem || (units < 1))
 		return AE_BAD_PARAMETER;
 
@@ -1348,6 +1328,9 @@ acpi_status acpi_os_signal_semaphore(acpi_handle handle, u32 units)
 {
 	struct semaphore *sem = (struct semaphore *)handle;
 
+	if (!acpi_os_initialized)
+		return AE_OK;
+
 	if (!sem || (units < 1))
 		return AE_BAD_PARAMETER;
 
@@ -1856,13 +1839,13 @@ acpi_status __init acpi_os_initialize(void)
 		rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register);
 		pr_debug(PREFIX "%s: map reset_reg status %d\n", __func__, rv);
 	}
+	acpi_os_initialized = true;
 
 	return AE_OK;
 }
 
 acpi_status __init acpi_os_initialize1(void)
 {
-	acpi_reserve_resources();
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
 	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 304eccb0ae5c..6da0f9beab19 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -19,10 +19,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -412,7 +408,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return 0;
 	}
 
-	if (dev->irq_managed && dev->irq > 0)
+	if (pci_has_managed_irq(dev))
 		return 0;
 
 	entry = acpi_pci_irq_lookup(dev, pin);
@@ -457,8 +453,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		kfree(entry);
 		return rc;
 	}
-	dev->irq = rc;
-	dev->irq_managed = 1;
+	pci_set_managed_irq(dev, rc);
 
 	if (link)
 		snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link);
@@ -481,16 +476,8 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	u8 pin;
 
 	pin = dev->pin;
-	if (!pin || !dev->irq_managed || dev->irq <= 0)
-		return;
-
-	/* Keep IOAPIC pin configuration when suspending */
-	if (dev->dev.power.is_prepared)
+	if (!pin || !pci_has_managed_irq(dev))
 		return;
-#ifdef	CONFIG_PM
-	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
-		return;
-#endif
 
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry)
@@ -511,6 +498,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin));
 	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
-		dev->irq_managed = 0;
+		pci_reset_managed_irq(dev);
 	}
 }
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index cfd7581cc19f..3b4ea98e3ea0 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -17,10 +17,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  * TBD: 
@@ -826,6 +822,22 @@ void acpi_penalize_isa_irq(int irq, int active)
 }
 
 /*
+ * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with
+ * PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for
+ * PCI IRQs.
+ */
+void acpi_penalize_sci_irq(int irq, int trigger, int polarity)
+{
+	if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) {
+		if (trigger != ACPI_MADT_TRIGGER_LEVEL ||
+		    polarity != ACPI_MADT_POLARITY_ACTIVE_LOW)
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_ALWAYS;
+		else
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING;
+	}
+}
+
+/*
  * Over-ride default table to reserve additional IRQs for use by ISA
  * e.g. acpi_irq_isa=5
  * Useful for telling ACPI how not to interfere with your ISA sound card.
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 1b5569c092c6..393706a5261b 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -16,10 +16,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index 139d9e479370..7188e53b6b7c 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -20,10 +20,6 @@
  *  WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 93eac53b5110..fcd4ce6f78d5 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -1,8 +1,10 @@
 /*
- *  acpi_power.c - ACPI Bus Power Management ($Revision: 39 $)
+ * drivers/acpi/power.c - ACPI Power Resources management.
  *
- *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
- *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ * Copyright (C) 2001 - 2015 Intel Corp.
+ * Author: Andy Grover <andrew.grover@intel.com>
+ * Author: Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
@@ -16,10 +18,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -27,10 +25,11 @@
  * ACPI power-managed devices may be controlled in two ways:
  * 1. via "Device Specific (D-State) Control"
  * 2. via "Power Resource Control".
- * This module is used to manage devices relying on Power Resource Control.
+ * The code below deals with ACPI Power Resources control.
  * 
- * An ACPI "power resource object" describes a software controllable power
- * plane, clock plane, or other resource used by a power managed device.
+ * An ACPI "power resource object" represents a software controllable power
+ * plane, clock plane, or other resource depended on by a device.
+ *
  * A device may rely on multiple power resources, and a power resource
  * may be shared by multiple devices.
  */
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index d9f71581b79b..51e658f21e95 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -21,10 +21,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -159,38 +155,28 @@ static int acpi_cpu_soft_notify(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __refdata acpi_cpu_notifier = {
+static struct notifier_block acpi_cpu_notifier = {
 	    .notifier_call = acpi_cpu_soft_notify,
 };
 
-static int __acpi_processor_start(struct acpi_device *device)
+#ifdef CONFIG_ACPI_CPU_FREQ_PSS
+static int acpi_pss_perf_init(struct acpi_processor *pr,
+		struct acpi_device *device)
 {
-	struct acpi_processor *pr = acpi_driver_data(device);
-	acpi_status status;
 	int result = 0;
 
-	if (!pr)
-		return -ENODEV;
-
-	if (pr->flags.need_hotplug_init)
-		return 0;
-
-#ifdef CONFIG_CPU_FREQ
 	acpi_processor_ppc_has_changed(pr, 0);
-#endif
+
 	acpi_processor_get_throttling_info(pr);
 
 	if (pr->flags.throttling)
 		pr->flags.limit = 1;
 
-	if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
-		acpi_processor_power_init(pr);
-
 	pr->cdev = thermal_cooling_device_register("Processor", device,
 						   &processor_cooling_ops);
 	if (IS_ERR(pr->cdev)) {
 		result = PTR_ERR(pr->cdev);
-		goto err_power_exit;
+		return result;
 	}
 
 	dev_dbg(&device->dev, "registered as cooling_device%d\n",
@@ -204,6 +190,7 @@ static int __acpi_processor_start(struct acpi_device *device)
 			"Failed to create sysfs link 'thermal_cooling'\n");
 		goto err_thermal_unregister;
 	}
+
 	result = sysfs_create_link(&pr->cdev->device.kobj,
 				   &device->dev.kobj,
 				   "device");
@@ -213,17 +200,61 @@ static int __acpi_processor_start(struct acpi_device *device)
 		goto err_remove_sysfs_thermal;
 	}
 
-	status = acpi_install_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
-					     acpi_processor_notify, device);
-	if (ACPI_SUCCESS(status))
-		return 0;
-
 	sysfs_remove_link(&pr->cdev->device.kobj, "device");
  err_remove_sysfs_thermal:
 	sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
  err_thermal_unregister:
 	thermal_cooling_device_unregister(pr->cdev);
- err_power_exit:
+
+	return result;
+}
+
+static void acpi_pss_perf_exit(struct acpi_processor *pr,
+		struct acpi_device *device)
+{
+	if (pr->cdev) {
+		sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
+		sysfs_remove_link(&pr->cdev->device.kobj, "device");
+		thermal_cooling_device_unregister(pr->cdev);
+		pr->cdev = NULL;
+	}
+}
+#else
+static inline int acpi_pss_perf_init(struct acpi_processor *pr,
+		struct acpi_device *device)
+{
+	return 0;
+}
+
+static inline void acpi_pss_perf_exit(struct acpi_processor *pr,
+		struct acpi_device *device) {}
+#endif /* CONFIG_ACPI_CPU_FREQ_PSS */
+
+static int __acpi_processor_start(struct acpi_device *device)
+{
+	struct acpi_processor *pr = acpi_driver_data(device);
+	acpi_status status;
+	int result = 0;
+
+	if (!pr)
+		return -ENODEV;
+
+	if (pr->flags.need_hotplug_init)
+		return 0;
+
+	if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
+		acpi_processor_power_init(pr);
+
+	result = acpi_pss_perf_init(pr, device);
+	if (result)
+		goto err_power_exit;
+
+	status = acpi_install_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
+					     acpi_processor_notify, device);
+	if (ACPI_SUCCESS(status))
+		return 0;
+
+err_power_exit:
 	acpi_processor_power_exit(pr);
 	return result;
 }
@@ -252,15 +283,10 @@ static int acpi_processor_stop(struct device *dev)
 	pr = acpi_driver_data(device);
 	if (!pr)
 		return 0;
-
 	acpi_processor_power_exit(pr);
 
-	if (pr->cdev) {
-		sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
-		sysfs_remove_link(&pr->cdev->device.kobj, "device");
-		thermal_cooling_device_unregister(pr->cdev);
-		pr->cdev = NULL;
-	}
+	acpi_pss_perf_exit(pr, device);
+
 	return 0;
 }
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index d540f42c9232..175c86bee3a9 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -21,10 +21,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index cfc8aba72f86..bb01dea39fdc 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -20,10 +20,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  */
 
 #include <linux/kernel.h>
@@ -87,7 +83,7 @@ static int acpi_processor_ppc_notifier(struct notifier_block *nb,
 	if (ignore_ppc)
 		return 0;
 
-	if (event != CPUFREQ_INCOMPATIBLE)
+	if (event != CPUFREQ_ADJUST)
 		return 0;
 
 	mutex_lock(&performance_mutex);
@@ -784,9 +780,7 @@ acpi_processor_register_performance(struct acpi_processor_performance
 
 EXPORT_SYMBOL(acpi_processor_register_performance);
 
-void
-acpi_processor_unregister_performance(struct acpi_processor_performance
-				      *performance, unsigned int cpu)
+void acpi_processor_unregister_performance(unsigned int cpu)
 {
 	struct acpi_processor *pr;
 
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index e003663b2f8e..1fed84a092c2 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -19,10 +19,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 84243c32e29c..f170d746336d 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -19,10 +19,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 7836e2e980f4..6d99450549c5 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -528,13 +528,14 @@ int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
 
 	if (!val)
 		return obj->package.count;
-	else if (nval <= 0)
-		return -EINVAL;
 
 	if (nval > obj->package.count)
 		return -EOVERFLOW;
+	else if (nval <= 0)
+		return -EINVAL;
 
 	items = obj->package.elements;
+
 	switch (proptype) {
 	case DEV_PROP_U8:
 		ret = acpi_copy_property_array_u8(items, (u8 *)val, nval);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 10561ce16ed1..15d22db05054 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
@@ -26,7 +22,6 @@
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/ioport.h>
-#include <linux/list.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_X86
@@ -194,6 +189,7 @@ static bool acpi_decode_space(struct resource_win *win,
 	u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16;
 	bool wp = addr->info.mem.write_protect;
 	u64 len = attr->address_length;
+	u64 start, end, offset = 0;
 	struct resource *res = &win->res;
 
 	/*
@@ -205,9 +201,6 @@ static bool acpi_decode_space(struct resource_win *win,
 		pr_debug("ACPI: Invalid address space min_addr_fix %d, max_addr_fix %d, len %llx\n",
 			 addr->min_address_fixed, addr->max_address_fixed, len);
 
-	res->start = attr->minimum;
-	res->end = attr->maximum;
-
 	/*
 	 * For bridges that translate addresses across the bridge,
 	 * translation_offset is the offset that must be added to the
@@ -215,12 +208,22 @@ static bool acpi_decode_space(struct resource_win *win,
 	 * primary side. Non-bridge devices must list 0 for all Address
 	 * Translation offset bits.
 	 */
-	if (addr->producer_consumer == ACPI_PRODUCER) {
-		res->start += attr->translation_offset;
-		res->end += attr->translation_offset;
-	} else if (attr->translation_offset) {
+	if (addr->producer_consumer == ACPI_PRODUCER)
+		offset = attr->translation_offset;
+	else if (attr->translation_offset)
 		pr_debug("ACPI: translation_offset(%lld) is invalid for non-bridge device.\n",
 			 attr->translation_offset);
+	start = attr->minimum + offset;
+	end = attr->maximum + offset;
+
+	win->offset = offset;
+	res->start = start;
+	res->end = end;
+	if (sizeof(resource_size_t) < sizeof(u64) &&
+	    (offset != win->offset || start != res->start || end != res->end)) {
+		pr_warn("acpi resource window ([%#llx-%#llx] ignored, not CPU addressable)\n",
+			attr->minimum, attr->maximum);
+		return false;
 	}
 
 	switch (addr->resource_type) {
@@ -237,8 +240,6 @@ static bool acpi_decode_space(struct resource_win *win,
 		return false;
 	}
 
-	win->offset = attr->translation_offset;
-
 	if (addr->producer_consumer == ACPI_PRODUCER)
 		res->flags |= IORESOURCE_WINDOW;
 
@@ -622,164 +623,3 @@ int acpi_dev_filter_resource_type(struct acpi_resource *ares,
 	return (type & types) ? 0 : 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type);
-
-struct reserved_region {
-	struct list_head node;
-	u64 start;
-	u64 end;
-};
-
-static LIST_HEAD(reserved_io_regions);
-static LIST_HEAD(reserved_mem_regions);
-
-static int request_range(u64 start, u64 end, u8 space_id, unsigned long flags,
-			 char *desc)
-{
-	unsigned int length = end - start + 1;
-	struct resource *res;
-
-	res = space_id == ACPI_ADR_SPACE_SYSTEM_IO ?
-		request_region(start, length, desc) :
-		request_mem_region(start, length, desc);
-	if (!res)
-		return -EIO;
-
-	res->flags &= ~flags;
-	return 0;
-}
-
-static int add_region_before(u64 start, u64 end, u8 space_id,
-			     unsigned long flags, char *desc,
-			     struct list_head *head)
-{
-	struct reserved_region *reg;
-	int error;
-
-	reg = kmalloc(sizeof(*reg), GFP_KERNEL);
-	if (!reg)
-		return -ENOMEM;
-
-	error = request_range(start, end, space_id, flags, desc);
-	if (error) {
-		kfree(reg);
-		return error;
-	}
-
-	reg->start = start;
-	reg->end = end;
-	list_add_tail(&reg->node, head);
-	return 0;
-}
-
-/**
- * acpi_reserve_region - Reserve an I/O or memory region as a system resource.
- * @start: Starting address of the region.
- * @length: Length of the region.
- * @space_id: Identifier of address space to reserve the region from.
- * @flags: Resource flags to clear for the region after requesting it.
- * @desc: Region description (for messages).
- *
- * Reserve an I/O or memory region as a system resource to prevent others from
- * using it.  If the new region overlaps with one of the regions (in the given
- * address space) already reserved by this routine, only the non-overlapping
- * parts of it will be reserved.
- *
- * Returned is either 0 (success) or a negative error code indicating a resource
- * reservation problem.  It is the code of the first encountered error, but the
- * routine doesn't abort until it has attempted to request all of the parts of
- * the new region that don't overlap with other regions reserved previously.
- *
- * The resources requested by this routine are never released.
- */
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
-			unsigned long flags, char *desc)
-{
-	struct list_head *regions;
-	struct reserved_region *reg;
-	u64 end = start + length - 1;
-	int ret = 0, error = 0;
-
-	if (space_id == ACPI_ADR_SPACE_SYSTEM_IO)
-		regions = &reserved_io_regions;
-	else if (space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		regions = &reserved_mem_regions;
-	else
-		return -EINVAL;
-
-	if (list_empty(regions))
-		return add_region_before(start, end, space_id, flags, desc, regions);
-
-	list_for_each_entry(reg, regions, node)
-		if (reg->start == end + 1) {
-			/* The new region can be prepended to this one. */
-			ret = request_range(start, end, space_id, flags, desc);
-			if (!ret)
-				reg->start = start;
-
-			return ret;
-		} else if (reg->start > end) {
-			/* No overlap.  Add the new region here and get out. */
-			return add_region_before(start, end, space_id, flags,
-						 desc, &reg->node);
-		} else if (reg->end == start - 1) {
-			goto combine;
-		} else if (reg->end >= start) {
-			goto overlap;
-		}
-
-	/* The new region goes after the last existing one. */
-	return add_region_before(start, end, space_id, flags, desc, regions);
-
- overlap:
-	/*
-	 * The new region overlaps an existing one.
-	 *
-	 * The head part of the new region immediately preceding the existing
-	 * overlapping one can be combined with it right away.
-	 */
-	if (reg->start > start) {
-		error = request_range(start, reg->start - 1, space_id, flags, desc);
-		if (error)
-			ret = error;
-		else
-			reg->start = start;
-	}
-
- combine:
-	/*
-	 * The new region is adjacent to an existing one.  If it extends beyond
-	 * that region all the way to the next one, it is possible to combine
-	 * all three of them.
-	 */
-	while (reg->end < end) {
-		struct reserved_region *next = NULL;
-		u64 a = reg->end + 1, b = end;
-
-		if (!list_is_last(&reg->node, regions)) {
-			next = list_next_entry(reg, node);
-			if (next->start <= end)
-				b = next->start - 1;
-		}
-		error = request_range(a, b, space_id, flags, desc);
-		if (!error) {
-			if (next && next->start == b + 1) {
-				reg->end = next->end;
-				list_del(&next->node);
-				kfree(next);
-			} else {
-				reg->end = end;
-				break;
-			}
-		} else if (next) {
-			if (!ret)
-				ret = error;
-
-			reg = next;
-		} else {
-			break;
-		}
-	}
-
-	return ret ? ret : error;
-}
-EXPORT_SYMBOL_GPL(acpi_reserve_region);
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 01504c819e8f..cb3dedb1beae 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -17,10 +17,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 2649a068671d..01136b879038 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -115,264 +115,6 @@ int acpi_scan_add_handler_with_hotplug(struct acpi_scan_handler *handler,
 	return 0;
 }
 
-/**
- * create_pnp_modalias - Create hid/cid(s) string for modalias and uevent
- * @acpi_dev: ACPI device object.
- * @modalias: Buffer to print into.
- * @size: Size of the buffer.
- *
- * Creates hid/cid(s) string needed for modalias and uevent
- * e.g. on a device with hid:IBM0001 and cid:ACPI0001 you get:
- * char *modalias: "acpi:IBM0001:ACPI0001"
- * Return: 0: no _HID and no _CID
- *         -EINVAL: output error
- *         -ENOMEM: output is truncated
-*/
-static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
-			       int size)
-{
-	int len;
-	int count;
-	struct acpi_hardware_id *id;
-
-	/*
-	 * Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
-	 * be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
-	 * device's list.
-	 */
-	count = 0;
-	list_for_each_entry(id, &acpi_dev->pnp.ids, list)
-		if (strcmp(id->id, ACPI_DT_NAMESPACE_HID))
-			count++;
-
-	if (!count)
-		return 0;
-
-	len = snprintf(modalias, size, "acpi:");
-	if (len <= 0)
-		return len;
-
-	size -= len;
-
-	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
-		if (!strcmp(id->id, ACPI_DT_NAMESPACE_HID))
-			continue;
-
-		count = snprintf(&modalias[len], size, "%s:", id->id);
-		if (count < 0)
-			return -EINVAL;
-
-		if (count >= size)
-			return -ENOMEM;
-
-		len += count;
-		size -= count;
-	}
-	modalias[len] = '\0';
-	return len;
-}
-
-/**
- * create_of_modalias - Creates DT compatible string for modalias and uevent
- * @acpi_dev: ACPI device object.
- * @modalias: Buffer to print into.
- * @size: Size of the buffer.
- *
- * Expose DT compatible modalias as of:NnameTCcompatible.  This function should
- * only be called for devices having ACPI_DT_NAMESPACE_HID in their list of
- * ACPI/PNP IDs.
- */
-static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias,
-			      int size)
-{
-	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
-	const union acpi_object *of_compatible, *obj;
-	int len, count;
-	int i, nval;
-	char *c;
-
-	acpi_get_name(acpi_dev->handle, ACPI_SINGLE_NAME, &buf);
-	/* DT strings are all in lower case */
-	for (c = buf.pointer; *c != '\0'; c++)
-		*c = tolower(*c);
-
-	len = snprintf(modalias, size, "of:N%sT", (char *)buf.pointer);
-	ACPI_FREE(buf.pointer);
-
-	if (len <= 0)
-		return len;
-
-	of_compatible = acpi_dev->data.of_compatible;
-	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
-		nval = of_compatible->package.count;
-		obj = of_compatible->package.elements;
-	} else { /* Must be ACPI_TYPE_STRING. */
-		nval = 1;
-		obj = of_compatible;
-	}
-	for (i = 0; i < nval; i++, obj++) {
-		count = snprintf(&modalias[len], size, "C%s",
-				 obj->string.pointer);
-		if (count < 0)
-			return -EINVAL;
-
-		if (count >= size)
-			return -ENOMEM;
-
-		len += count;
-		size -= count;
-	}
-	modalias[len] = '\0';
-	return len;
-}
-
-/*
- * acpi_companion_match() - Can we match via ACPI companion device
- * @dev: Device in question
- *
- * Check if the given device has an ACPI companion and if that companion has
- * a valid list of PNP IDs, and if the device is the first (primary) physical
- * device associated with it.  Return the companion pointer if that's the case
- * or NULL otherwise.
- *
- * If multiple physical devices are attached to a single ACPI companion, we need
- * to be careful.  The usage scenario for this kind of relationship is that all
- * of the physical devices in question use resources provided by the ACPI
- * companion.  A typical case is an MFD device where all the sub-devices share
- * the parent's ACPI companion.  In such cases we can only allow the primary
- * (first) physical device to be matched with the help of the companion's PNP
- * IDs.
- *
- * Additional physical devices sharing the ACPI companion can still use
- * resources available from it but they will be matched normally using functions
- * provided by their bus types (and analogously for their modalias).
- */
-static struct acpi_device *acpi_companion_match(const struct device *dev)
-{
-	struct acpi_device *adev;
-	struct mutex *physical_node_lock;
-
-	adev = ACPI_COMPANION(dev);
-	if (!adev)
-		return NULL;
-
-	if (list_empty(&adev->pnp.ids))
-		return NULL;
-
-	physical_node_lock = &adev->physical_node_lock;
-	mutex_lock(physical_node_lock);
-	if (list_empty(&adev->physical_node_list)) {
-		adev = NULL;
-	} else {
-		const struct acpi_device_physical_node *node;
-
-		node = list_first_entry(&adev->physical_node_list,
-					struct acpi_device_physical_node, node);
-		if (node->dev != dev)
-			adev = NULL;
-	}
-	mutex_unlock(physical_node_lock);
-
-	return adev;
-}
-
-static int __acpi_device_uevent_modalias(struct acpi_device *adev,
-					 struct kobj_uevent_env *env)
-{
-	int len;
-
-	if (!adev)
-		return -ENODEV;
-
-	if (list_empty(&adev->pnp.ids))
-		return 0;
-
-	if (add_uevent_var(env, "MODALIAS="))
-		return -ENOMEM;
-
-	len = create_pnp_modalias(adev, &env->buf[env->buflen - 1],
-				  sizeof(env->buf) - env->buflen);
-	if (len < 0)
-		return len;
-
-	env->buflen += len;
-	if (!adev->data.of_compatible)
-		return 0;
-
-	if (len > 0 && add_uevent_var(env, "MODALIAS="))
-		return -ENOMEM;
-
-	len = create_of_modalias(adev, &env->buf[env->buflen - 1],
-				 sizeof(env->buf) - env->buflen);
-	if (len < 0)
-		return len;
-
-	env->buflen += len;
-
-	return 0;
-}
-
-/*
- * Creates uevent modalias field for ACPI enumerated devices.
- * Because the other buses does not support ACPI HIDs & CIDs.
- * e.g. for a device with hid:IBM0001 and cid:ACPI0001 you get:
- * "acpi:IBM0001:ACPI0001"
- */
-int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env)
-{
-	return __acpi_device_uevent_modalias(acpi_companion_match(dev), env);
-}
-EXPORT_SYMBOL_GPL(acpi_device_uevent_modalias);
-
-static int __acpi_device_modalias(struct acpi_device *adev, char *buf, int size)
-{
-	int len, count;
-
-	if (!adev)
-		return -ENODEV;
-
-	if (list_empty(&adev->pnp.ids))
-		return 0;
-
-	len = create_pnp_modalias(adev, buf, size - 1);
-	if (len < 0) {
-		return len;
-	} else if (len > 0) {
-		buf[len++] = '\n';
-		size -= len;
-	}
-	if (!adev->data.of_compatible)
-		return len;
-
-	count = create_of_modalias(adev, buf + len, size - 1);
-	if (count < 0) {
-		return count;
-	} else if (count > 0) {
-		len += count;
-		buf[len++] = '\n';
-	}
-
-	return len;
-}
-
-/*
- * Creates modalias sysfs attribute for ACPI enumerated devices.
- * Because the other buses does not support ACPI HIDs & CIDs.
- * e.g. for a device with hid:IBM0001 and cid:ACPI0001 you get:
- * "acpi:IBM0001:ACPI0001"
- */
-int acpi_device_modalias(struct device *dev, char *buf, int size)
-{
-	return __acpi_device_modalias(acpi_companion_match(dev), buf, size);
-}
-EXPORT_SYMBOL_GPL(acpi_device_modalias);
-
-static ssize_t
-acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, char *buf) {
-	return __acpi_device_modalias(to_acpi_device(dev), buf, 1024);
-}
-static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL);
-
 bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent)
 {
 	struct acpi_device_physical_node *pn;
@@ -701,397 +443,6 @@ void acpi_device_hotplug(struct acpi_device *adev, u32 src)
 	unlock_device_hotplug();
 }
 
-static ssize_t real_power_state_show(struct device *dev,
-				     struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *adev = to_acpi_device(dev);
-	int state;
-	int ret;
-
-	ret = acpi_device_get_power(adev, &state);
-	if (ret)
-		return ret;
-
-	return sprintf(buf, "%s\n", acpi_power_state_string(state));
-}
-
-static DEVICE_ATTR(real_power_state, 0444, real_power_state_show, NULL);
-
-static ssize_t power_state_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *adev = to_acpi_device(dev);
-
-	return sprintf(buf, "%s\n", acpi_power_state_string(adev->power.state));
-}
-
-static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
-
-static ssize_t
-acpi_eject_store(struct device *d, struct device_attribute *attr,
-		const char *buf, size_t count)
-{
-	struct acpi_device *acpi_device = to_acpi_device(d);
-	acpi_object_type not_used;
-	acpi_status status;
-
-	if (!count || buf[0] != '1')
-		return -EINVAL;
-
-	if ((!acpi_device->handler || !acpi_device->handler->hotplug.enabled)
-	    && !acpi_device->driver)
-		return -ENODEV;
-
-	status = acpi_get_type(acpi_device->handle, &not_used);
-	if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable)
-		return -ENODEV;
-
-	get_device(&acpi_device->dev);
-	status = acpi_hotplug_schedule(acpi_device, ACPI_OST_EC_OSPM_EJECT);
-	if (ACPI_SUCCESS(status))
-		return count;
-
-	put_device(&acpi_device->dev);
-	acpi_evaluate_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
-			  ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL);
-	return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
-}
-
-static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store);
-
-static ssize_t
-acpi_device_hid_show(struct device *dev, struct device_attribute *attr, char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-
-	return sprintf(buf, "%s\n", acpi_device_hid(acpi_dev));
-}
-static DEVICE_ATTR(hid, 0444, acpi_device_hid_show, NULL);
-
-static ssize_t acpi_device_uid_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-
-	return sprintf(buf, "%s\n", acpi_dev->pnp.unique_id);
-}
-static DEVICE_ATTR(uid, 0444, acpi_device_uid_show, NULL);
-
-static ssize_t acpi_device_adr_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-
-	return sprintf(buf, "0x%08x\n",
-		       (unsigned int)(acpi_dev->pnp.bus_address));
-}
-static DEVICE_ATTR(adr, 0444, acpi_device_adr_show, NULL);
-
-static ssize_t
-acpi_device_path_show(struct device *dev, struct device_attribute *attr, char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_buffer path = {ACPI_ALLOCATE_BUFFER, NULL};
-	int result;
-
-	result = acpi_get_name(acpi_dev->handle, ACPI_FULL_PATHNAME, &path);
-	if (result)
-		goto end;
-
-	result = sprintf(buf, "%s\n", (char*)path.pointer);
-	kfree(path.pointer);
-end:
-	return result;
-}
-static DEVICE_ATTR(path, 0444, acpi_device_path_show, NULL);
-
-/* sysfs file that shows description text from the ACPI _STR method */
-static ssize_t description_show(struct device *dev,
-				struct device_attribute *attr,
-				char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	int result;
-
-	if (acpi_dev->pnp.str_obj == NULL)
-		return 0;
-
-	/*
-	 * The _STR object contains a Unicode identifier for a device.
-	 * We need to convert to utf-8 so it can be displayed.
-	 */
-	result = utf16s_to_utf8s(
-		(wchar_t *)acpi_dev->pnp.str_obj->buffer.pointer,
-		acpi_dev->pnp.str_obj->buffer.length,
-		UTF16_LITTLE_ENDIAN, buf,
-		PAGE_SIZE);
-
-	buf[result++] = '\n';
-
-	return result;
-}
-static DEVICE_ATTR(description, 0444, description_show, NULL);
-
-static ssize_t
-acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
-		     char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	acpi_status status;
-	unsigned long long sun;
-
-	status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
-
-	return sprintf(buf, "%llu\n", sun);
-}
-static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
-
-static ssize_t status_show(struct device *dev, struct device_attribute *attr,
-				char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	acpi_status status;
-	unsigned long long sta;
-
-	status = acpi_evaluate_integer(acpi_dev->handle, "_STA", NULL, &sta);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
-
-	return sprintf(buf, "%llu\n", sta);
-}
-static DEVICE_ATTR_RO(status);
-
-static int acpi_device_setup_files(struct acpi_device *dev)
-{
-	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
-	int result = 0;
-
-	/*
-	 * Devices gotten from FADT don't have a "path" attribute
-	 */
-	if (dev->handle) {
-		result = device_create_file(&dev->dev, &dev_attr_path);
-		if (result)
-			goto end;
-	}
-
-	if (!list_empty(&dev->pnp.ids)) {
-		result = device_create_file(&dev->dev, &dev_attr_hid);
-		if (result)
-			goto end;
-
-		result = device_create_file(&dev->dev, &dev_attr_modalias);
-		if (result)
-			goto end;
-	}
-
-	/*
-	 * If device has _STR, 'description' file is created
-	 */
-	if (acpi_has_method(dev->handle, "_STR")) {
-		status = acpi_evaluate_object(dev->handle, "_STR",
-					NULL, &buffer);
-		if (ACPI_FAILURE(status))
-			buffer.pointer = NULL;
-		dev->pnp.str_obj = buffer.pointer;
-		result = device_create_file(&dev->dev, &dev_attr_description);
-		if (result)
-			goto end;
-	}
-
-	if (dev->pnp.type.bus_address)
-		result = device_create_file(&dev->dev, &dev_attr_adr);
-	if (dev->pnp.unique_id)
-		result = device_create_file(&dev->dev, &dev_attr_uid);
-
-	if (acpi_has_method(dev->handle, "_SUN")) {
-		result = device_create_file(&dev->dev, &dev_attr_sun);
-		if (result)
-			goto end;
-	}
-
-	if (acpi_has_method(dev->handle, "_STA")) {
-		result = device_create_file(&dev->dev, &dev_attr_status);
-		if (result)
-			goto end;
-	}
-
-        /*
-         * If device has _EJ0, 'eject' file is created that is used to trigger
-         * hot-removal function from userland.
-         */
-	if (acpi_has_method(dev->handle, "_EJ0")) {
-		result = device_create_file(&dev->dev, &dev_attr_eject);
-		if (result)
-			return result;
-	}
-
-	if (dev->flags.power_manageable) {
-		result = device_create_file(&dev->dev, &dev_attr_power_state);
-		if (result)
-			return result;
-
-		if (dev->power.flags.power_resources)
-			result = device_create_file(&dev->dev,
-						    &dev_attr_real_power_state);
-	}
-
-end:
-	return result;
-}
-
-static void acpi_device_remove_files(struct acpi_device *dev)
-{
-	if (dev->flags.power_manageable) {
-		device_remove_file(&dev->dev, &dev_attr_power_state);
-		if (dev->power.flags.power_resources)
-			device_remove_file(&dev->dev,
-					   &dev_attr_real_power_state);
-	}
-
-	/*
-	 * If device has _STR, remove 'description' file
-	 */
-	if (acpi_has_method(dev->handle, "_STR")) {
-		kfree(dev->pnp.str_obj);
-		device_remove_file(&dev->dev, &dev_attr_description);
-	}
-	/*
-	 * If device has _EJ0, remove 'eject' file.
-	 */
-	if (acpi_has_method(dev->handle, "_EJ0"))
-		device_remove_file(&dev->dev, &dev_attr_eject);
-
-	if (acpi_has_method(dev->handle, "_SUN"))
-		device_remove_file(&dev->dev, &dev_attr_sun);
-
-	if (dev->pnp.unique_id)
-		device_remove_file(&dev->dev, &dev_attr_uid);
-	if (dev->pnp.type.bus_address)
-		device_remove_file(&dev->dev, &dev_attr_adr);
-	device_remove_file(&dev->dev, &dev_attr_modalias);
-	device_remove_file(&dev->dev, &dev_attr_hid);
-	if (acpi_has_method(dev->handle, "_STA"))
-		device_remove_file(&dev->dev, &dev_attr_status);
-	if (dev->handle)
-		device_remove_file(&dev->dev, &dev_attr_path);
-}
-/* --------------------------------------------------------------------------
-			ACPI Bus operations
-   -------------------------------------------------------------------------- */
-
-/**
- * acpi_of_match_device - Match device object using the "compatible" property.
- * @adev: ACPI device object to match.
- * @of_match_table: List of device IDs to match against.
- *
- * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
- * identifiers and a _DSD object with the "compatible" property, use that
- * property to match against the given list of identifiers.
- */
-static bool acpi_of_match_device(struct acpi_device *adev,
-				 const struct of_device_id *of_match_table)
-{
-	const union acpi_object *of_compatible, *obj;
-	int i, nval;
-
-	if (!adev)
-		return false;
-
-	of_compatible = adev->data.of_compatible;
-	if (!of_match_table || !of_compatible)
-		return false;
-
-	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
-		nval = of_compatible->package.count;
-		obj = of_compatible->package.elements;
-	} else { /* Must be ACPI_TYPE_STRING. */
-		nval = 1;
-		obj = of_compatible;
-	}
-	/* Now we can look for the driver DT compatible strings */
-	for (i = 0; i < nval; i++, obj++) {
-		const struct of_device_id *id;
-
-		for (id = of_match_table; id->compatible[0]; id++)
-			if (!strcasecmp(obj->string.pointer, id->compatible))
-				return true;
-	}
-
-	return false;
-}
-
-static const struct acpi_device_id *__acpi_match_device(
-	struct acpi_device *device,
-	const struct acpi_device_id *ids,
-	const struct of_device_id *of_ids)
-{
-	const struct acpi_device_id *id;
-	struct acpi_hardware_id *hwid;
-
-	/*
-	 * If the device is not present, it is unnecessary to load device
-	 * driver for it.
-	 */
-	if (!device || !device->status.present)
-		return NULL;
-
-	list_for_each_entry(hwid, &device->pnp.ids, list) {
-		/* First, check the ACPI/PNP IDs provided by the caller. */
-		for (id = ids; id->id[0]; id++)
-			if (!strcmp((char *) id->id, hwid->id))
-				return id;
-
-		/*
-		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
-		 * "compatible" property if found.
-		 *
-		 * The id returned by the below is not valid, but the only
-		 * caller passing non-NULL of_ids here is only interested in
-		 * whether or not the return value is NULL.
-		 */
-		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
-		    && acpi_of_match_device(device, of_ids))
-			return id;
-	}
-	return NULL;
-}
-
-/**
- * acpi_match_device - Match a struct device against a given list of ACPI IDs
- * @ids: Array of struct acpi_device_id object to match against.
- * @dev: The device structure to match.
- *
- * Check if @dev has a valid ACPI handle and if there is a struct acpi_device
- * object for that handle and use that object to match against a given list of
- * device IDs.
- *
- * Return a pointer to the first matching ID on success or %NULL on failure.
- */
-const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
-					       const struct device *dev)
-{
-	return __acpi_match_device(acpi_companion_match(dev), ids, NULL);
-}
-EXPORT_SYMBOL_GPL(acpi_match_device);
-
-int acpi_match_device_ids(struct acpi_device *device,
-			  const struct acpi_device_id *ids)
-{
-	return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT;
-}
-EXPORT_SYMBOL(acpi_match_device_ids);
-
-bool acpi_driver_match_device(struct device *dev,
-			      const struct device_driver *drv)
-{
-	if (!drv->acpi_match_table)
-		return acpi_of_match_device(ACPI_COMPANION(dev),
-					    drv->of_match_table);
-
-	return !!__acpi_match_device(acpi_companion_match(dev),
-				     drv->acpi_match_table, drv->of_match_table);
-}
-EXPORT_SYMBOL_GPL(acpi_driver_match_device);
-
 static void acpi_free_power_resources_lists(struct acpi_device *device)
 {
 	int i;
@@ -1118,144 +469,6 @@ static void acpi_device_release(struct device *dev)
 	kfree(acpi_dev);
 }
 
-static int acpi_bus_match(struct device *dev, struct device_driver *drv)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = to_acpi_driver(drv);
-
-	return acpi_dev->flags.match_driver
-		&& !acpi_match_device_ids(acpi_dev, acpi_drv->ids);
-}
-
-static int acpi_device_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
-	return __acpi_device_uevent_modalias(to_acpi_device(dev), env);
-}
-
-static void acpi_device_notify(acpi_handle handle, u32 event, void *data)
-{
-	struct acpi_device *device = data;
-
-	device->driver->ops.notify(device, event);
-}
-
-static void acpi_device_notify_fixed(void *data)
-{
-	struct acpi_device *device = data;
-
-	/* Fixed hardware devices have no handles */
-	acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
-}
-
-static u32 acpi_device_fixed_event(void *data)
-{
-	acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
-	return ACPI_INTERRUPT_HANDLED;
-}
-
-static int acpi_device_install_notify_handler(struct acpi_device *device)
-{
-	acpi_status status;
-
-	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
-		status =
-		    acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						     acpi_device_fixed_event,
-						     device);
-	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
-		status =
-		    acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						     acpi_device_fixed_event,
-						     device);
-	else
-		status = acpi_install_notify_handler(device->handle,
-						     ACPI_DEVICE_NOTIFY,
-						     acpi_device_notify,
-						     device);
-
-	if (ACPI_FAILURE(status))
-		return -EINVAL;
-	return 0;
-}
-
-static void acpi_device_remove_notify_handler(struct acpi_device *device)
-{
-	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
-		acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						acpi_device_fixed_event);
-	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
-		acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						acpi_device_fixed_event);
-	else
-		acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
-					   acpi_device_notify);
-}
-
-static int acpi_device_probe(struct device *dev)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = to_acpi_driver(dev->driver);
-	int ret;
-
-	if (acpi_dev->handler && !acpi_is_pnp_device(acpi_dev))
-		return -EINVAL;
-
-	if (!acpi_drv->ops.add)
-		return -ENOSYS;
-
-	ret = acpi_drv->ops.add(acpi_dev);
-	if (ret)
-		return ret;
-
-	acpi_dev->driver = acpi_drv;
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-			  "Driver [%s] successfully bound to device [%s]\n",
-			  acpi_drv->name, acpi_dev->pnp.bus_id));
-
-	if (acpi_drv->ops.notify) {
-		ret = acpi_device_install_notify_handler(acpi_dev);
-		if (ret) {
-			if (acpi_drv->ops.remove)
-				acpi_drv->ops.remove(acpi_dev);
-
-			acpi_dev->driver = NULL;
-			acpi_dev->driver_data = NULL;
-			return ret;
-		}
-	}
-
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found driver [%s] for device [%s]\n",
-			  acpi_drv->name, acpi_dev->pnp.bus_id));
-	get_device(dev);
-	return 0;
-}
-
-static int acpi_device_remove(struct device * dev)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = acpi_dev->driver;
-
-	if (acpi_drv) {
-		if (acpi_drv->ops.notify)
-			acpi_device_remove_notify_handler(acpi_dev);
-		if (acpi_drv->ops.remove)
-			acpi_drv->ops.remove(acpi_dev);
-	}
-	acpi_dev->driver = NULL;
-	acpi_dev->driver_data = NULL;
-
-	put_device(dev);
-	return 0;
-}
-
-struct bus_type acpi_bus_type = {
-	.name		= "acpi",
-	.match		= acpi_bus_match,
-	.probe		= acpi_device_probe,
-	.remove		= acpi_device_remove,
-	.uevent		= acpi_device_uevent,
-};
-
 static void acpi_device_del(struct acpi_device *device)
 {
 	mutex_lock(&acpi_device_lock);
@@ -1503,47 +716,6 @@ struct acpi_device *acpi_get_next_child(struct device *dev,
 }
 
 /* --------------------------------------------------------------------------
-                                 Driver Management
-   -------------------------------------------------------------------------- */
-/**
- * acpi_bus_register_driver - register a driver with the ACPI bus
- * @driver: driver being registered
- *
- * Registers a driver with the ACPI bus.  Searches the namespace for all
- * devices that match the driver's criteria and binds.  Returns zero for
- * success or a negative error status for failure.
- */
-int acpi_bus_register_driver(struct acpi_driver *driver)
-{
-	int ret;
-
-	if (acpi_disabled)
-		return -ENODEV;
-	driver->drv.name = driver->name;
-	driver->drv.bus = &acpi_bus_type;
-	driver->drv.owner = driver->owner;
-
-	ret = driver_register(&driver->drv);
-	return ret;
-}
-
-EXPORT_SYMBOL(acpi_bus_register_driver);
-
-/**
- * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
- * @driver: driver to unregister
- *
- * Unregisters a driver with the ACPI bus.  Searches the namespace for all
- * devices that match the driver's criteria and unbinds.
- */
-void acpi_bus_unregister_driver(struct acpi_driver *driver)
-{
-	driver_unregister(&driver->drv);
-}
-
-EXPORT_SYMBOL(acpi_bus_unregister_driver);
-
-/* --------------------------------------------------------------------------
                                  Device Enumeration
    -------------------------------------------------------------------------- */
 static struct acpi_device *acpi_bus_get_parent(acpi_handle handle)
@@ -2101,6 +1273,8 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
 		if (info->valid & ACPI_VALID_UID)
 			pnp->unique_id = kstrdup(info->unique_id.string,
 							GFP_KERNEL);
+		if (info->valid & ACPI_VALID_CLS)
+			acpi_add_id(pnp, info->class_code.string);
 
 		kfree(info);
 
@@ -2716,12 +1890,6 @@ int __init acpi_scan_init(void)
 {
 	int result;
 
-	result = bus_register(&acpi_bus_type);
-	if (result) {
-		/* We don't want to quit even if we failed to add suspend/resume */
-		printk(KERN_ERR PREFIX "Could not register bus type\n");
-	}
-
 	acpi_pci_root_init();
 	acpi_pci_link_init();
 	acpi_processor_init();
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 0876d77b3206..40a42655227c 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -69,6 +69,8 @@ static const struct acpi_dlevel acpi_debug_levels[] = {
 	ACPI_DEBUG_INIT(ACPI_LV_INIT),
 	ACPI_DEBUG_INIT(ACPI_LV_DEBUG_OBJECT),
 	ACPI_DEBUG_INIT(ACPI_LV_INFO),
+	ACPI_DEBUG_INIT(ACPI_LV_REPAIR),
+	ACPI_DEBUG_INIT(ACPI_LV_TRACE_POINT),
 
 	ACPI_DEBUG_INIT(ACPI_LV_INIT_NAMES),
 	ACPI_DEBUG_INIT(ACPI_LV_PARSE),
@@ -162,55 +164,116 @@ static const struct kernel_param_ops param_ops_debug_level = {
 module_param_cb(debug_layer, &param_ops_debug_layer, &acpi_dbg_layer, 0644);
 module_param_cb(debug_level, &param_ops_debug_level, &acpi_dbg_level, 0644);
 
-static char trace_method_name[6];
-module_param_string(trace_method_name, trace_method_name, 6, 0644);
-static unsigned int trace_debug_layer;
-module_param(trace_debug_layer, uint, 0644);
-static unsigned int trace_debug_level;
-module_param(trace_debug_level, uint, 0644);
+static char trace_method_name[1024];
 
-static int param_set_trace_state(const char *val, struct kernel_param *kp)
+int param_set_trace_method_name(const char *val, const struct kernel_param *kp)
 {
-	int result = 0;
+	u32 saved_flags = 0;
+	bool is_abs_path = true;
 
-	if (!strncmp(val, "enable", sizeof("enable") - 1)) {
-		result = acpi_debug_trace(trace_method_name, trace_debug_level,
-					  trace_debug_layer, 0);
-		if (result)
-			result = -EBUSY;
-		goto exit;
-	}
+	if (*val != '\\')
+		is_abs_path = false;
 
-	if (!strncmp(val, "disable", sizeof("disable") - 1)) {
-		int name = 0;
-		result = acpi_debug_trace((char *)&name, trace_debug_level,
-					  trace_debug_layer, 0);
-		if (result)
-			result = -EBUSY;
-		goto exit;
+	if ((is_abs_path && strlen(val) > 1023) ||
+	    (!is_abs_path && strlen(val) > 1022)) {
+		pr_err("%s: string parameter too long\n", kp->name);
+		return -ENOSPC;
 	}
 
-	if (!strncmp(val, "1", 1)) {
-		result = acpi_debug_trace(trace_method_name, trace_debug_level,
-					  trace_debug_layer, 1);
-		if (result)
-			result = -EBUSY;
-		goto exit;
+	/*
+	 * It's not safe to update acpi_gbl_trace_method_name without
+	 * having the tracer stopped, so we save the original tracer
+	 * state and disable it.
+	 */
+	saved_flags = acpi_gbl_trace_flags;
+	(void)acpi_debug_trace(NULL,
+			       acpi_gbl_trace_dbg_level,
+			       acpi_gbl_trace_dbg_layer,
+			       0);
+
+	/* This is a hack.  We can't kmalloc in early boot. */
+	if (is_abs_path)
+		strcpy(trace_method_name, val);
+	else {
+		trace_method_name[0] = '\\';
+		strcpy(trace_method_name+1, val);
 	}
 
-	result = -EINVAL;
-exit:
-	return result;
+	/* Restore the original tracer state */
+	(void)acpi_debug_trace(trace_method_name,
+			       acpi_gbl_trace_dbg_level,
+			       acpi_gbl_trace_dbg_layer,
+			       saved_flags);
+
+	return 0;
+}
+
+static int param_get_trace_method_name(char *buffer, const struct kernel_param *kp)
+{
+	return scnprintf(buffer, PAGE_SIZE, "%s", acpi_gbl_trace_method_name);
+}
+
+static const struct kernel_param_ops param_ops_trace_method = {
+	.set = param_set_trace_method_name,
+	.get = param_get_trace_method_name,
+};
+
+static const struct kernel_param_ops param_ops_trace_attrib = {
+	.set = param_set_uint,
+	.get = param_get_uint,
+};
+
+module_param_cb(trace_method_name, &param_ops_trace_method, &trace_method_name, 0644);
+module_param_cb(trace_debug_layer, &param_ops_trace_attrib, &acpi_gbl_trace_dbg_layer, 0644);
+module_param_cb(trace_debug_level, &param_ops_trace_attrib, &acpi_gbl_trace_dbg_level, 0644);
+
+static int param_set_trace_state(const char *val, struct kernel_param *kp)
+{
+	acpi_status status;
+	const char *method = trace_method_name;
+	u32 flags = 0;
+
+/* So "xxx-once" comparison should go prior than "xxx" comparison */
+#define acpi_compare_param(val, key)	\
+	strncmp((val), (key), sizeof(key) - 1)
+
+	if (!acpi_compare_param(val, "enable")) {
+		method = NULL;
+		flags = ACPI_TRACE_ENABLED;
+	} else if (!acpi_compare_param(val, "disable"))
+		method = NULL;
+	else if (!acpi_compare_param(val, "method-once"))
+		flags = ACPI_TRACE_ENABLED | ACPI_TRACE_ONESHOT;
+	else if (!acpi_compare_param(val, "method"))
+		flags = ACPI_TRACE_ENABLED;
+	else if (!acpi_compare_param(val, "opcode-once"))
+		flags = ACPI_TRACE_ENABLED | ACPI_TRACE_ONESHOT | ACPI_TRACE_OPCODE;
+	else if (!acpi_compare_param(val, "opcode"))
+		flags = ACPI_TRACE_ENABLED | ACPI_TRACE_OPCODE;
+	else
+		return -EINVAL;
+
+	status = acpi_debug_trace(method,
+				  acpi_gbl_trace_dbg_level,
+				  acpi_gbl_trace_dbg_layer,
+				  flags);
+	if (ACPI_FAILURE(status))
+		return -EBUSY;
+
+	return 0;
 }
 
 static int param_get_trace_state(char *buffer, struct kernel_param *kp)
 {
-	if (!acpi_gbl_trace_method_name)
+	if (!(acpi_gbl_trace_flags & ACPI_TRACE_ENABLED))
 		return sprintf(buffer, "disable");
 	else {
-		if (acpi_gbl_trace_flags & 1)
-			return sprintf(buffer, "1");
-		else
+		if (acpi_gbl_trace_method_name) {
+			if (acpi_gbl_trace_flags & ACPI_TRACE_ONESHOT)
+				return sprintf(buffer, "method-once");
+			else
+				return sprintf(buffer, "method");
+		} else
 			return sprintf(buffer, "enable");
 	}
 	return 0;
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 2e19189da0ee..17a6fa01a338 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  */
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 6d4e44ea74ac..fc28b9f5aa84 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -16,10 +16,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  *  This driver fully implements the ACPI thermal policy as described in the
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 67c548ad3764..475c9079bf85 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -16,10 +16,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
  *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 815f75ef2411..2922f1f252d5 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
 #include <acpi/video.h>
 
 ACPI_MODULE_NAME("video");
@@ -41,6 +42,7 @@ void acpi_video_unregister_backlight(void);
 
 static bool backlight_notifier_registered;
 static struct notifier_block backlight_nb;
+static struct work_struct backlight_notify_work;
 
 static enum acpi_backlight_type acpi_backlight_cmdline = acpi_backlight_undef;
 static enum acpi_backlight_type acpi_backlight_dmi = acpi_backlight_undef;
@@ -262,6 +264,13 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	{ },
 };
 
+/* This uses a workqueue to avoid various locking ordering issues */
+static void acpi_video_backlight_notify_work(struct work_struct *work)
+{
+	if (acpi_video_get_backlight_type() != acpi_backlight_video)
+		acpi_video_unregister_backlight();
+}
+
 static int acpi_video_backlight_notify(struct notifier_block *nb,
 				       unsigned long val, void *bd)
 {
@@ -269,9 +278,8 @@ static int acpi_video_backlight_notify(struct notifier_block *nb,
 
 	/* A raw bl registering may change video -> native */
 	if (backlight->props.type == BACKLIGHT_RAW &&
-	    val == BACKLIGHT_REGISTERED &&
-	    acpi_video_get_backlight_type() != acpi_backlight_video)
-		acpi_video_unregister_backlight();
+	    val == BACKLIGHT_REGISTERED)
+		schedule_work(&backlight_notify_work);
 
 	return NOTIFY_OK;
 }
@@ -304,6 +312,8 @@ enum acpi_backlight_type acpi_video_get_backlight_type(void)
 		acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
 				    ACPI_UINT32_MAX, find_video, NULL,
 				    &video_caps, NULL);
+		INIT_WORK(&backlight_notify_work,
+			  acpi_video_backlight_notify_work);
 		backlight_nb.notifier_call = acpi_video_backlight_notify;
 		backlight_nb.priority = 0;
 		if (backlight_register_notifier(&backlight_nb) == 0)
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 6d17a3b65ef7..15e40ee62a94 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -48,7 +48,7 @@ config ATA_VERBOSE_ERROR
 
 config ATA_ACPI
 	bool "ATA ACPI Support"
-	depends on ACPI && PCI
+	depends on ACPI
 	default y
 	help
 	  This option adds support for ATA-related ACPI objects.
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 7e62751abfac..a46660204e3a 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -351,6 +351,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	/* JMicron 362B and 362C have an AHCI function with IDE class code */
 	{ PCI_VDEVICE(JMICRON, 0x2362), board_ahci_ign_iferr },
 	{ PCI_VDEVICE(JMICRON, 0x236f), board_ahci_ign_iferr },
+	/* May need to update quirk_jmicron_async_suspend() for additions */
 
 	/* ATI */
 	{ PCI_VDEVICE(ATI, 0x4380), board_ahci_sb600 }, /* ATI SB600 */
@@ -1451,18 +1452,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else if (pdev->vendor == 0x177d && pdev->device == 0xa01c)
 		ahci_pci_bar = AHCI_PCI_BAR_CAVIUM;
 
-	/*
-	 * The JMicron chip 361/363 contains one SATA controller and one
-	 * PATA controller,for powering on these both controllers, we must
-	 * follow the sequence one by one, otherwise one of them can not be
-	 * powered on successfully, so here we disable the async suspend
-	 * method for these chips.
-	 */
-	if (pdev->vendor == PCI_VENDOR_ID_JMICRON &&
-		(pdev->device == PCI_DEVICE_ID_JMICRON_JMB363 ||
-		pdev->device == PCI_DEVICE_ID_JMICRON_JMB361))
-		device_disable_async_suspend(&pdev->dev);
-
 	/* acquire resources */
 	rc = pcim_enable_device(pdev);
 	if (rc)
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c
index ce1e3a885981..14b7305d2ba0 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcmstb.c
@@ -92,7 +92,7 @@ static inline u32 brcm_sata_readreg(void __iomem *addr)
 	 * Other architectures (e.g., ARM) either do not support big endian, or
 	 * else leave I/O in little endian mode.
 	 */
-	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN))
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		return __raw_readl(addr);
 	else
 		return readl_relaxed(addr);
@@ -101,7 +101,7 @@ static inline u32 brcm_sata_readreg(void __iomem *addr)
 static inline void brcm_sata_writereg(u32 val, void __iomem *addr)
 {
 	/* See brcm_sata_readreg() comments */
-	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN))
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		__raw_writel(val, addr);
 	else
 		writel_relaxed(val, addr);
@@ -209,6 +209,7 @@ static void brcm_sata_init(struct brcm_ahci_priv *priv)
 			   priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int brcm_ahci_suspend(struct device *dev)
 {
 	struct ata_host *host = dev_get_drvdata(dev);
@@ -231,6 +232,7 @@ static int brcm_ahci_resume(struct device *dev)
 	brcm_sata_phys_enable(priv);
 	return ahci_platform_resume(dev);
 }
+#endif
 
 static struct scsi_host_template ahci_platform_sht = {
 	AHCI_SHT(DRV_NAME),
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 614c78f510f0..1befb114c384 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -20,6 +20,8 @@
 #include <linux/platform_device.h>
 #include <linux/libata.h>
 #include <linux/ahci_platform.h>
+#include <linux/acpi.h>
+#include <linux/pci_ids.h>
 #include "ahci.h"
 
 #define DRV_NAME "ahci"
@@ -79,12 +81,19 @@ static const struct of_device_id ahci_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, ahci_of_match);
 
+static const struct acpi_device_id ahci_acpi_match[] = {
+	{ ACPI_DEVICE_CLASS(PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff) },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, ahci_acpi_match);
+
 static struct platform_driver ahci_driver = {
 	.probe = ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = ahci_of_match,
+		.acpi_match_table = ahci_acpi_match,
 		.pm = &ahci_pm_ops,
 	},
 };
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index e83fc3d0da9c..b79cb10e289e 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -694,11 +694,11 @@ static int ata_rwcmd_protocol(struct ata_taskfile *tf, struct ata_device *dev)
  *	RETURNS:
  *	Block address read from @tf.
  */
-u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev)
+u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev)
 {
 	u64 block = 0;
 
-	if (!dev || tf->flags & ATA_TFLAG_LBA) {
+	if (tf->flags & ATA_TFLAG_LBA) {
 		if (tf->flags & ATA_TFLAG_LBA48) {
 			block |= (u64)tf->hob_lbah << 40;
 			block |= (u64)tf->hob_lbam << 32;
@@ -2147,24 +2147,6 @@ static int ata_dev_config_ncq(struct ata_device *dev,
 	return 0;
 }
 
-static void ata_dev_config_sense_reporting(struct ata_device *dev)
-{
-	unsigned int err_mask;
-
-	if (!ata_id_has_sense_reporting(dev->id))
-		return;
-
-	if (ata_id_sense_reporting_enabled(dev->id))
-		return;
-
-	err_mask = ata_dev_set_feature(dev, SETFEATURE_SENSE_DATA, 0x1);
-	if (err_mask) {
-		ata_dev_dbg(dev,
-			    "failed to enable Sense Data Reporting, Emask 0x%x\n",
-			    err_mask);
-	}
-}
-
 /**
  *	ata_dev_configure - Configure the specified ATA/ATAPI device
  *	@dev: Target device to configure
@@ -2387,7 +2369,7 @@ int ata_dev_configure(struct ata_device *dev)
 					dev->devslp_timing[i] = sata_setting[j];
 				}
 		}
-		ata_dev_config_sense_reporting(dev);
+
 		dev->cdb_len = 16;
 	}
 
@@ -2478,6 +2460,10 @@ int ata_dev_configure(struct ata_device *dev)
 		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128,
 					 dev->max_sectors);
 
+	if (dev->horkage & ATA_HORKAGE_MAX_SEC_1024)
+		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_1024,
+					 dev->max_sectors);
+
 	if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48)
 		dev->max_sectors = ATA_MAX_SECTORS_LBA48;
 
@@ -4146,6 +4132,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "Slimtype DVD A  DS8A8SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
 	{ "Slimtype DVD A  DS8A9SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
 
+	/*
+	 * Causes silent data corruption with higher max sects.
+	 * http://lkml.kernel.org/g/x49wpy40ysk.fsf@segfault.boston.devel.redhat.com
+	 */
+	{ "ST380013AS",		"3.20",		ATA_HORKAGE_MAX_SEC_1024 },
+
 	/* Devices we expect to fail diagnostics */
 
 	/* Devices where NCQ should be avoided */
@@ -4174,9 +4166,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "ST3320[68]13AS",	"SD1[5-9]",	ATA_HORKAGE_NONCQ |
 						ATA_HORKAGE_FIRMWARE_WARN },
 
-	/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
+	/* drives which fail FPDMA_AA activation (some may freeze afterwards) */
 	{ "ST1000LM024 HN-M101MBB", "2AR10001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
 	{ "ST1000LM024 HN-M101MBB", "2BA30001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+	{ "VB0250EAVER",	"HPG7",		ATA_HORKAGE_BROKEN_FPDMA_AA },
 
 	/* Blacklist entries taken from Silicon Image 3124/3132
 	   Windows driver .inf file - also several Linux problem reports */
@@ -4229,7 +4222,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
-	{ "Micron_M5[15]0*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
+	{ "Micron_M5[15]0_*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*M550*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
@@ -4237,6 +4230,11 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Samsung SSD 8*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "FCCT*M500*",			NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
+						ATA_HORKAGE_ZERO_AFTER_TRIM, },
+
+	/* devices that don't properly handle TRIM commands */
+	{ "SuperSSpeed S238*",		NULL,	ATA_HORKAGE_NOTRIM, },
 
 	/*
 	 * As defined, the DRAT (Deterministic Read After Trim) and RZAT
@@ -4501,7 +4499,8 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev)
 	else /* In the ancient relic department - skip all of this */
 		return 0;
 
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	/* On some disks, this command causes spin-up, so we need longer timeout */
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000);
 
 	DPRINTK("EXIT, err_mask=%x\n", err_mask);
 	return err_mask;
@@ -4754,6 +4753,7 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 /**
  *	ata_qc_new_init - Request an available ATA command, and initialize it
  *	@dev: Device from whom we request an available command structure
+ *	@tag: tag
  *
  *	LOCKING:
  *	None.
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 7465031a893c..cb0508af1459 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1592,8 +1592,6 @@ static int ata_eh_read_log_10h(struct ata_device *dev,
 	tf->hob_lbah = buf[10];
 	tf->nsect = buf[12];
 	tf->hob_nsect = buf[13];
-	if (ata_id_has_ncq_autosense(dev->id))
-		tf->auxiliary = buf[14] << 16 | buf[15] << 8 | buf[16];
 
 	return 0;
 }
@@ -1630,70 +1628,6 @@ unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key)
 }
 
 /**
- *	ata_eh_request_sense - perform REQUEST_SENSE_DATA_EXT
- *	@dev: device to perform REQUEST_SENSE_SENSE_DATA_EXT to
- *	@sense_buf: result sense data buffer (SCSI_SENSE_BUFFERSIZE bytes long)
- *	@dfl_sense_key: default sense key to use
- *
- *	Perform REQUEST_SENSE_DATA_EXT after the device reported CHECK
- *	SENSE.  This function is EH helper.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).
- *
- *	RETURNS:
- *	encoded sense data on success, 0 on failure or if sense data
- *	is not available.
- */
-static u32 ata_eh_request_sense(struct ata_queued_cmd *qc,
-				struct scsi_cmnd *cmd)
-{
-	struct ata_device *dev = qc->dev;
-	struct ata_taskfile tf;
-	unsigned int err_mask;
-
-	if (!cmd)
-		return 0;
-
-	DPRINTK("ATA request sense\n");
-	ata_dev_warn(dev, "request sense\n");
-	if (!ata_id_sense_reporting_enabled(dev->id)) {
-		ata_dev_warn(qc->dev, "sense data reporting disabled\n");
-		return 0;
-	}
-	ata_tf_init(dev, &tf);
-
-	tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
-	tf.flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
-	tf.command = ATA_CMD_REQ_SENSE_DATA;
-	tf.protocol = ATA_PROT_NODATA;
-
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
-	/*
-	 * ACS-4 states:
-	 * The device may set the SENSE DATA AVAILABLE bit to one in the
-	 * STATUS field and clear the ERROR bit to zero in the STATUS field
-	 * to indicate that the command returned completion without an error
-	 * and the sense data described in table 306 is available.
-	 *
-	 * IOW the 'ATA_SENSE' bit might not be set even though valid
-	 * sense data is available.
-	 * So check for both.
-	 */
-	if ((tf.command & ATA_SENSE) ||
-		tf.lbah != 0 || tf.lbam != 0 || tf.lbal != 0) {
-		ata_scsi_set_sense(cmd, tf.lbah, tf.lbam, tf.lbal);
-		qc->flags |= ATA_QCFLAG_SENSE_VALID;
-		ata_dev_warn(dev, "sense data %02x/%02x/%02x\n",
-			     tf.lbah, tf.lbam, tf.lbal);
-	} else {
-		ata_dev_warn(dev, "request sense failed stat %02x emask %x\n",
-			     tf.command, err_mask);
-	}
-	return err_mask;
-}
-
-/**
  *	atapi_eh_request_sense - perform ATAPI REQUEST_SENSE
  *	@dev: device to perform REQUEST_SENSE to
  *	@sense_buf: result sense data buffer (SCSI_SENSE_BUFFERSIZE bytes long)
@@ -1855,19 +1789,6 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
 	memcpy(&qc->result_tf, &tf, sizeof(tf));
 	qc->result_tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
 	qc->err_mask |= AC_ERR_DEV | AC_ERR_NCQ;
-	if (qc->result_tf.auxiliary) {
-		char sense_key, asc, ascq;
-
-		sense_key = (qc->result_tf.auxiliary >> 16) & 0xff;
-		asc = (qc->result_tf.auxiliary >> 8) & 0xff;
-		ascq = qc->result_tf.auxiliary & 0xff;
-		ata_dev_dbg(dev, "NCQ Autosense %02x/%02x/%02x\n",
-			    sense_key, asc, ascq);
-		ata_scsi_set_sense(qc->scsicmd, sense_key, asc, ascq);
-		ata_scsi_set_sense_information(qc->scsicmd, &qc->result_tf);
-		qc->flags |= ATA_QCFLAG_SENSE_VALID;
-	}
-
 	ehc->i.err_mask &= ~AC_ERR_DEV;
 }
 
@@ -1897,27 +1818,6 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 		return ATA_EH_RESET;
 	}
 
-	/*
-	 * Sense data reporting does not work if the
-	 * device fault bit is set.
-	 */
-	if ((stat & ATA_SENSE) && !(stat & ATA_DF) &&
-	    !(qc->flags & ATA_QCFLAG_SENSE_VALID)) {
-		if (!(qc->ap->pflags & ATA_PFLAG_FROZEN)) {
-			tmp = ata_eh_request_sense(qc, qc->scsicmd);
-			if (tmp)
-				qc->err_mask |= tmp;
-			else
-				ata_scsi_set_sense_information(qc->scsicmd, tf);
-		} else {
-			ata_dev_warn(qc->dev, "sense data available but port frozen\n");
-		}
-	}
-
-	/* Set by NCQ autosense or request sense above */
-	if (qc->flags & ATA_QCFLAG_SENSE_VALID)
-		return 0;
-
 	if (stat & (ATA_ERR | ATA_DF))
 		qc->err_mask |= AC_ERR_DEV;
 	else
@@ -2661,15 +2561,14 @@ static void ata_eh_link_report(struct ata_link *link)
 
 #ifdef CONFIG_ATA_VERBOSE_ERROR
 		if (res->command & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ |
-				    ATA_SENSE | ATA_ERR)) {
+				    ATA_ERR)) {
 			if (res->command & ATA_BUSY)
 				ata_dev_err(qc->dev, "status: { Busy }\n");
 			else
-				ata_dev_err(qc->dev, "status: { %s%s%s%s%s}\n",
+				ata_dev_err(qc->dev, "status: { %s%s%s%s}\n",
 				  res->command & ATA_DRDY ? "DRDY " : "",
 				  res->command & ATA_DF ? "DF " : "",
 				  res->command & ATA_DRQ ? "DRQ " : "",
-				  res->command & ATA_SENSE ? "SENSE " : "",
 				  res->command & ATA_ERR ? "ERR " : "");
 		}
 
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 7ccc084bf1df..85aa76116a30 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -460,6 +460,13 @@ static void sata_pmp_quirks(struct ata_port *ap)
 				       ATA_LFLAG_NO_SRST |
 				       ATA_LFLAG_ASSUME_ATA;
 		}
+	} else if (vendor == 0x11ab && devid == 0x4140) {
+		/* Marvell 4140 quirks */
+		ata_for_each_link(link, ap, EDGE) {
+			/* port 4 is for SEMB device and it doesn't like SRST */
+			if (link->pmp == 4)
+				link->flags |= ATA_LFLAG_DISABLED;
+		}
 	}
 }
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 3131adcc1f87..0d7f0da3a269 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -270,28 +270,13 @@ DEVICE_ATTR(unload_heads, S_IRUGO | S_IWUSR,
 	    ata_scsi_park_show, ata_scsi_park_store);
 EXPORT_SYMBOL_GPL(dev_attr_unload_heads);
 
-void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq)
+static void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq)
 {
-	if (!cmd)
-		return;
-
 	cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION;
 
 	scsi_build_sense_buffer(0, cmd->sense_buffer, sk, asc, ascq);
 }
 
-void ata_scsi_set_sense_information(struct scsi_cmnd *cmd,
-				    const struct ata_taskfile *tf)
-{
-	u64 information;
-
-	if (!cmd)
-		return;
-
-	information = ata_tf_read_block(tf, NULL);
-	scsi_set_sense_information(cmd->sense_buffer, information);
-}
-
 static ssize_t
 ata_scsi_em_message_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t count)
@@ -1792,9 +1777,7 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
 	    ((cdb[2] & 0x20) || need_sense)) {
 		ata_gen_passthru_sense(qc);
 	} else {
-		if (qc->flags & ATA_QCFLAG_SENSE_VALID) {
-			cmd->result = SAM_STAT_CHECK_CONDITION;
-		} else if (!need_sense) {
+		if (!need_sense) {
 			cmd->result = SAM_STAT_GOOD;
 		} else {
 			/* TODO: decide which descriptor format to use
@@ -2568,7 +2551,8 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf)
 		rbuf[14] = (lowest_aligned >> 8) & 0x3f;
 		rbuf[15] = lowest_aligned;
 
-		if (ata_id_has_trim(args->id)) {
+		if (ata_id_has_trim(args->id) &&
+		    !(dev->horkage & ATA_HORKAGE_NOTRIM)) {
 			rbuf[14] |= 0x80; /* LBPME */
 
 			if (ata_id_has_zero_after_trim(args->id) &&
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index d6c37bcd416d..e2d94972962d 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -569,6 +569,8 @@ show_ata_dev_trim(struct device *dev,
 
 	if (!ata_id_has_trim(ata_dev->id))
 		mode = "unsupported";
+	else if (ata_dev->horkage & ATA_HORKAGE_NOTRIM)
+		mode = "forced_unsupported";
 	else if (ata_dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM)
 			mode = "forced_unqueued";
 	else if (ata_fpdma_dsm_supported(ata_dev))
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index a998a175f9f1..f840ca18a7c0 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -67,8 +67,7 @@ extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag);
 extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 			   u64 block, u32 n_block, unsigned int tf_flags,
 			   unsigned int tag);
-extern u64 ata_tf_read_block(const struct ata_taskfile *tf,
-			     struct ata_device *dev);
+extern u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev);
 extern unsigned ata_exec_internal(struct ata_device *dev,
 				  struct ata_taskfile *tf, const u8 *cdb,
 				  int dma_dir, void *buf, unsigned int buflen,
@@ -138,9 +137,6 @@ extern int ata_scsi_add_hosts(struct ata_host *host,
 			      struct scsi_host_template *sht);
 extern void ata_scsi_scan_host(struct ata_port *ap, int sync);
 extern int ata_scsi_offline_dev(struct ata_device *dev);
-extern void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq);
-extern void ata_scsi_set_sense_information(struct scsi_cmnd *cmd,
-					   const struct ata_taskfile *tf);
 extern void ata_scsi_media_change_notify(struct ata_device *dev);
 extern void ata_scsi_hotplug(struct work_struct *work);
 extern void ata_schedule_scsi_eh(struct Scsi_Host *shost);
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index a9b0c820f2eb..80fe0f6fed29 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -4,7 +4,7 @@
  * Arasan Compact Flash host controller source file
  *
  * Copyright (C) 2011 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -834,7 +834,7 @@ static int arasan_cf_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	acdev->clk = clk_get(&pdev->dev, NULL);
+	acdev->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(acdev->clk)) {
 		dev_warn(&pdev->dev, "Clock not found\n");
 		return PTR_ERR(acdev->clk);
@@ -843,9 +843,8 @@ static int arasan_cf_probe(struct platform_device *pdev)
 	/* allocate host */
 	host = ata_host_alloc(&pdev->dev, 1);
 	if (!host) {
-		ret = -ENOMEM;
 		dev_warn(&pdev->dev, "alloc host fail\n");
-		goto free_clk;
+		return -ENOMEM;
 	}
 
 	ap = host->ports[0];
@@ -894,7 +893,7 @@ static int arasan_cf_probe(struct platform_device *pdev)
 
 	ret = cf_init(acdev);
 	if (ret)
-		goto free_clk;
+		return ret;
 
 	cf_card_detect(acdev, 0);
 
@@ -904,8 +903,7 @@ static int arasan_cf_probe(struct platform_device *pdev)
 		return 0;
 
 	cf_exit(acdev);
-free_clk:
-	clk_put(acdev->clk);
+
 	return ret;
 }
 
@@ -916,7 +914,6 @@ static int arasan_cf_remove(struct platform_device *pdev)
 
 	ata_host_detach(host);
 	cf_exit(acdev);
-	clk_put(acdev->clk);
 
 	return 0;
 }
@@ -968,7 +965,7 @@ static struct platform_driver arasan_cf_driver = {
 
 module_platform_driver(arasan_cf_driver);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("Arasan ATA Compact Flash driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/ata/pata_jmicron.c b/drivers/ata/pata_jmicron.c
index 47e418b8c8ba..4d1a5d2c4287 100644
--- a/drivers/ata/pata_jmicron.c
+++ b/drivers/ata/pata_jmicron.c
@@ -143,18 +143,6 @@ static int jmicron_init_one (struct pci_dev *pdev, const struct pci_device_id *i
 	};
 	const struct ata_port_info *ppi[] = { &info, NULL };
 
-	/*
-	 * The JMicron chip 361/363 contains one SATA controller and one
-	 * PATA controller,for powering on these both controllers, we must
-	 * follow the sequence one by one, otherwise one of them can not be
-	 * powered on successfully, so here we disable the async suspend
-	 * method for these chips.
-	 */
-	if (pdev->vendor == PCI_VENDOR_ID_JMICRON &&
-		(pdev->device == PCI_DEVICE_ID_JMICRON_JMB363 ||
-		pdev->device == PCI_DEVICE_ID_JMICRON_JMB361))
-		device_disable_async_suspend(&pdev->dev);
-
 	return ata_pci_bmdma_init_one(pdev, ppi, &jmicron_sht, NULL, 0);
 }
 
diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c
index 6d08446b877c..12fe0f3bb7e9 100644
--- a/drivers/ata/pata_rb532_cf.c
+++ b/drivers/ata/pata_rb532_cf.c
@@ -27,12 +27,11 @@
 #include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 
 #include <linux/libata.h>
 #include <scsi/scsi_host.h>
 
-#include <asm/gpio.h>
-
 #define DRV_NAME	"pata-rb532-cf"
 #define DRV_VERSION	"0.1.0"
 #define DRV_DESC	"PATA driver for RouterBOARD 532 Compact Flash"
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index d49a5193b7de..8804127b108c 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -861,10 +861,6 @@ MODULE_DEVICE_TABLE(of, sata_rcar_match);
 static const struct platform_device_id sata_rcar_id_table[] = {
 	{ "sata_rcar", RCAR_GEN1_SATA }, /* Deprecated by "sata-r8a7779" */
 	{ "sata-r8a7779", RCAR_GEN1_SATA },
-	{ "sata-r8a7790", RCAR_GEN2_SATA },
-	{ "sata-r8a7790-es1", RCAR_R8A7790_ES1_SATA },
-	{ "sata-r8a7791", RCAR_GEN2_SATA },
-	{ "sata-r8a7793", RCAR_GEN2_SATA },
 	{ },
 };
 MODULE_DEVICE_TABLE(platform, sata_rcar_id_table);
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 3a18a8a719b4..fab504fd9cfd 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1238,8 +1238,12 @@ static unsigned int pdc20621_prog_dimm_global(struct ata_host *host)
 	readl(mmio + PDC_SDRAM_CONTROL);
 
 	/* Turn on for ECC */
-	pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
-			  PDC_DIMM_SPD_TYPE, &spd0);
+	if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+			       PDC_DIMM_SPD_TYPE, &spd0)) {
+		pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n",
+		       PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
+		return 1;
+	}
 	if (spd0 == 0x02) {
 		data |= (0x01 << 16);
 		writel(data, mmio + PDC_SDRAM_CONTROL);
@@ -1380,8 +1384,12 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
 
 	/* ECC initiliazation. */
 
-	pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
-			  PDC_DIMM_SPD_TYPE, &spd0);
+	if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+			       PDC_DIMM_SPD_TYPE, &spd0)) {
+		pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n",
+		       PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
+		return 1;
+	}
 	if (spd0 == 0x02) {
 		void *buf;
 		VPRINTK("Start ECC initialization\n");
diff --git a/drivers/auxdisplay/ks0108.c b/drivers/auxdisplay/ks0108.c
index 5b93852392b8..816de9eaac26 100644
--- a/drivers/auxdisplay/ks0108.c
+++ b/drivers/auxdisplay/ks0108.c
@@ -23,6 +23,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -90,17 +92,19 @@ void ks0108_displaystate(unsigned char state)
 
 void ks0108_startline(unsigned char startline)
 {
-	ks0108_writedata(min(startline,(unsigned char)63) | bit(6) | bit(7));
+	ks0108_writedata(min_t(unsigned char, startline, 63) | bit(6) |
+			 bit(7));
 }
 
 void ks0108_address(unsigned char address)
 {
-	ks0108_writedata(min(address,(unsigned char)63) | bit(6));
+	ks0108_writedata(min_t(unsigned char, address, 63) | bit(6));
 }
 
 void ks0108_page(unsigned char page)
 {
-	ks0108_writedata(min(page,(unsigned char)7) | bit(3) | bit(4) | bit(5) | bit(7));
+	ks0108_writedata(min_t(unsigned char, page, 7) | bit(3) | bit(4) |
+			 bit(5) | bit(7));
 }
 
 EXPORT_SYMBOL_GPL(ks0108_writedata);
@@ -121,52 +125,71 @@ unsigned char ks0108_isinited(void)
 }
 EXPORT_SYMBOL_GPL(ks0108_isinited);
 
-/*
- * Module Init & Exit
- */
-
-static int __init ks0108_init(void)
+static void ks0108_parport_attach(struct parport *port)
 {
-	int result;
-	int ret = -EINVAL;
-
-	ks0108_parport = parport_find_base(ks0108_port);
-	if (ks0108_parport == NULL) {
-		printk(KERN_ERR KS0108_NAME ": ERROR: "
-			"parport didn't find %i port\n", ks0108_port);
-		goto none;
-	}
-
-	ks0108_pardevice = parport_register_device(ks0108_parport, KS0108_NAME,
-		NULL, NULL, NULL, PARPORT_DEV_EXCL, NULL);
-	if (ks0108_pardevice == NULL) {
-		printk(KERN_ERR KS0108_NAME ": ERROR: "
-			"parport didn't register new device\n");
-		goto none;
+	struct pardev_cb ks0108_cb;
+
+	if (port->base != ks0108_port)
+		return;
+
+	memset(&ks0108_cb, 0, sizeof(ks0108_cb));
+	ks0108_cb.flags = PARPORT_DEV_EXCL;
+	ks0108_pardevice = parport_register_dev_model(port, KS0108_NAME,
+						      &ks0108_cb, 0);
+	if (!ks0108_pardevice) {
+		pr_err("ERROR: parport didn't register new device\n");
+		return;
 	}
-
-	result = parport_claim(ks0108_pardevice);
-	if (result != 0) {
-		printk(KERN_ERR KS0108_NAME ": ERROR: "
-			"can't claim %i parport, maybe in use\n", ks0108_port);
-		ret = result;
-		goto registered;
+	if (parport_claim(ks0108_pardevice)) {
+		pr_err("could not claim access to parport %i. Aborting.\n",
+		       ks0108_port);
+		goto err_unreg_device;
 	}
 
+	ks0108_parport = port;
 	ks0108_inited = 1;
-	return 0;
+	return;
 
-registered:
+err_unreg_device:
 	parport_unregister_device(ks0108_pardevice);
-
-none:
-	return ret;
+	ks0108_pardevice = NULL;
 }
 
-static void __exit ks0108_exit(void)
+static void ks0108_parport_detach(struct parport *port)
 {
+	if (port->base != ks0108_port)
+		return;
+
+	if (!ks0108_pardevice) {
+		pr_err("%s: already unregistered.\n", KS0108_NAME);
+		return;
+	}
+
 	parport_release(ks0108_pardevice);
 	parport_unregister_device(ks0108_pardevice);
+	ks0108_pardevice = NULL;
+	ks0108_parport = NULL;
+}
+
+/*
+ * Module Init & Exit
+ */
+
+static struct parport_driver ks0108_parport_driver = {
+	.name = "ks0108",
+	.match_port = ks0108_parport_attach,
+	.detach = ks0108_parport_detach,
+	.devmodel = true,
+};
+
+static int __init ks0108_init(void)
+{
+	return parport_register_driver(&ks0108_parport_driver);
+}
+
+static void __exit ks0108_exit(void)
+{
+	parport_unregister_driver(&ks0108_parport_driver);
 }
 
 module_init(ks0108_init);
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 527d291706e8..6b2a84e7f2be 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_REGMAP)	+= regmap/
 obj-$(CONFIG_SOC_BUS) += soc.o
 obj-$(CONFIG_PINCTRL) += pinctrl.o
 obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
+obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o
 
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
 
diff --git a/drivers/base/base.h b/drivers/base/base.h
index fd3347d9f153..1782f3aa386e 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -63,7 +63,7 @@ struct driver_private {
  *	binding of drivers which were unable to get all the resources needed by
  *	the device; typically because it depends on another driver getting
  *	probed first.
- * @device - pointer back to the struct class that this structure is
+ * @device - pointer back to the struct device that this structure is
  * associated with.
  *
  * Nothing outside of the driver core should ever touch these fields.
@@ -134,6 +134,7 @@ extern int devres_release_all(struct device *dev);
 
 /* /sys/devices directory */
 extern struct kset *devices_kset;
+extern void devices_kset_move_last(struct device *dev);
 
 #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS)
 extern void module_add_driver(struct module *mod, struct device_driver *drv);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index dafae6d2f7ac..334ec7ef1960 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -534,6 +534,52 @@ static DEVICE_ATTR_RO(dev);
 struct kset *devices_kset;
 
 /**
+ * devices_kset_move_before - Move device in the devices_kset's list.
+ * @deva: Device to move.
+ * @devb: Device @deva should come before.
+ */
+static void devices_kset_move_before(struct device *deva, struct device *devb)
+{
+	if (!devices_kset)
+		return;
+	pr_debug("devices_kset: Moving %s before %s\n",
+		 dev_name(deva), dev_name(devb));
+	spin_lock(&devices_kset->list_lock);
+	list_move_tail(&deva->kobj.entry, &devb->kobj.entry);
+	spin_unlock(&devices_kset->list_lock);
+}
+
+/**
+ * devices_kset_move_after - Move device in the devices_kset's list.
+ * @deva: Device to move
+ * @devb: Device @deva should come after.
+ */
+static void devices_kset_move_after(struct device *deva, struct device *devb)
+{
+	if (!devices_kset)
+		return;
+	pr_debug("devices_kset: Moving %s after %s\n",
+		 dev_name(deva), dev_name(devb));
+	spin_lock(&devices_kset->list_lock);
+	list_move(&deva->kobj.entry, &devb->kobj.entry);
+	spin_unlock(&devices_kset->list_lock);
+}
+
+/**
+ * devices_kset_move_last - move the device to the end of devices_kset's list.
+ * @dev: device to move
+ */
+void devices_kset_move_last(struct device *dev)
+{
+	if (!devices_kset)
+		return;
+	pr_debug("devices_kset: Moving %s to end of list\n", dev_name(dev));
+	spin_lock(&devices_kset->list_lock);
+	list_move_tail(&dev->kobj.entry, &devices_kset->list);
+	spin_unlock(&devices_kset->list_lock);
+}
+
+/**
  * device_create_file - create sysfs attribute file for device.
  * @dev: device.
  * @attr: device attribute descriptor.
@@ -662,6 +708,9 @@ void device_initialize(struct device *dev)
 	INIT_LIST_HEAD(&dev->devres_head);
 	device_pm_init(dev);
 	set_dev_node(dev, -1);
+#ifdef CONFIG_GENERIC_MSI_IRQ
+	INIT_LIST_HEAD(&dev->msi_list);
+#endif
 }
 EXPORT_SYMBOL_GPL(device_initialize);
 
@@ -1252,6 +1301,19 @@ void device_unregister(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(device_unregister);
 
+static struct device *prev_device(struct klist_iter *i)
+{
+	struct klist_node *n = klist_prev(i);
+	struct device *dev = NULL;
+	struct device_private *p;
+
+	if (n) {
+		p = to_device_private_parent(n);
+		dev = p->device;
+	}
+	return dev;
+}
+
 static struct device *next_device(struct klist_iter *i)
 {
 	struct klist_node *n = klist_next(i);
@@ -1341,6 +1403,36 @@ int device_for_each_child(struct device *parent, void *data,
 EXPORT_SYMBOL_GPL(device_for_each_child);
 
 /**
+ * device_for_each_child_reverse - device child iterator in reversed order.
+ * @parent: parent struct device.
+ * @fn: function to be called for each device.
+ * @data: data for the callback.
+ *
+ * Iterate over @parent's child devices, and call @fn for each,
+ * passing it @data.
+ *
+ * We check the return of @fn each time. If it returns anything
+ * other than 0, we break out and return that value.
+ */
+int device_for_each_child_reverse(struct device *parent, void *data,
+				  int (*fn)(struct device *dev, void *data))
+{
+	struct klist_iter i;
+	struct device *child;
+	int error = 0;
+
+	if (!parent->p)
+		return 0;
+
+	klist_iter_init(&parent->p->klist_children, &i);
+	while ((child = prev_device(&i)) && !error)
+		error = fn(child, data);
+	klist_iter_exit(&i);
+	return error;
+}
+EXPORT_SYMBOL_GPL(device_for_each_child_reverse);
+
+/**
  * device_find_child - device iterator for locating a particular device.
  * @parent: parent struct device
  * @match: Callback function to check device
@@ -1923,12 +2015,15 @@ int device_move(struct device *dev, struct device *new_parent,
 		break;
 	case DPM_ORDER_DEV_AFTER_PARENT:
 		device_pm_move_after(dev, new_parent);
+		devices_kset_move_after(dev, new_parent);
 		break;
 	case DPM_ORDER_PARENT_BEFORE_DEV:
 		device_pm_move_before(new_parent, dev);
+		devices_kset_move_before(new_parent, dev);
 		break;
 	case DPM_ORDER_DEV_LAST:
 		device_pm_move_last(dev);
+		devices_kset_move_last(dev);
 		break;
 	}
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 78720e706176..91bbb1959d8d 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -41,7 +41,7 @@ static void change_cpu_under_node(struct cpu *cpu,
 	cpu->node_id = to_nid;
 }
 
-static int __ref cpu_subsys_online(struct device *dev)
+static int cpu_subsys_online(struct device *dev)
 {
 	struct cpu *cpu = container_of(dev, struct cpu, dev);
 	int cpuid = dev->id;
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index a638bbb1a27a..be0eb4639128 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -304,6 +304,14 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 			goto probe_failed;
 	}
 
+	/*
+	 * Ensure devices are listed in devices_kset in correct order
+	 * It's important to move Dev to the end of devices_kset before
+	 * calling .probe, because it could be recursive and parent Dev
+	 * should always go first
+	 */
+	devices_kset_move_last(dev);
+
 	if (dev->bus->probe) {
 		ret = dev->bus->probe(dev);
 		if (ret)
@@ -399,6 +407,8 @@ EXPORT_SYMBOL_GPL(wait_for_device_probe);
  *
  * This function must be called with @dev lock held.  When called for a
  * USB interface, @dev->parent lock must be held as well.
+ *
+ * If the device has a parent, runtime-resume the parent before driver probing.
  */
 int driver_probe_device(struct device_driver *drv, struct device *dev)
 {
@@ -410,10 +420,16 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
 		 drv->bus->name, __func__, dev_name(dev), drv->name);
 
+	if (dev->parent)
+		pm_runtime_get_sync(dev->parent);
+
 	pm_runtime_barrier(dev);
 	ret = really_probe(dev, drv);
 	pm_request_idle(dev);
 
+	if (dev->parent)
+		pm_runtime_put(dev->parent);
+
 	return ret;
 }
 
@@ -507,11 +523,17 @@ static void __device_attach_async_helper(void *_dev, async_cookie_t cookie)
 
 	device_lock(dev);
 
+	if (dev->parent)
+		pm_runtime_get_sync(dev->parent);
+
 	bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver);
 	dev_dbg(dev, "async probe completed\n");
 
 	pm_request_idle(dev);
 
+	if (dev->parent)
+		pm_runtime_put(dev->parent);
+
 	device_unlock(dev);
 
 	put_device(dev);
@@ -541,6 +563,9 @@ static int __device_attach(struct device *dev, bool allow_async)
 			.want_async = false,
 		};
 
+		if (dev->parent)
+			pm_runtime_get_sync(dev->parent);
+
 		ret = bus_for_each_drv(dev->bus, NULL, &data,
 					__device_attach_driver);
 		if (!ret && allow_async && data.have_async) {
@@ -557,6 +582,9 @@ static int __device_attach(struct device *dev, bool allow_async)
 		} else {
 			pm_request_idle(dev);
 		}
+
+		if (dev->parent)
+			pm_runtime_put(dev->parent);
 	}
 out_unlock:
 	device_unlock(dev);
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index c8a53d1e019f..875464690117 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -297,10 +297,10 @@ void * devres_get(struct device *dev, void *new_res,
 	if (!dr) {
 		add_dr(dev, &new_dr->node);
 		dr = new_dr;
-		new_dr = NULL;
+		new_res = NULL;
 	}
 	spin_unlock_irqrestore(&dev->devres_lock, flags);
-	devres_free(new_dr);
+	devres_free(new_res);
 
 	return dr->data;
 }
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 9c4288362a8e..8524450e75bd 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -443,7 +443,7 @@ static int fw_add_devm_name(struct device *dev, const char *name)
 		return -ENOMEM;
 	fwn->name = kstrdup_const(name, GFP_KERNEL);
 	if (!fwn->name) {
-		kfree(fwn);
+		devres_free(fwn);
 		return -ENOMEM;
 	}
 
@@ -563,10 +563,8 @@ static void fw_dev_release(struct device *dev)
 	kfree(fw_priv);
 }
 
-static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-
 	if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id))
 		return -ENOMEM;
 	if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout))
@@ -577,6 +575,18 @@ static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
+static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	int err = 0;
+
+	mutex_lock(&fw_lock);
+	if (fw_priv->buf)
+		err = do_firmware_uevent(fw_priv, env);
+	mutex_unlock(&fw_lock);
+	return err;
+}
+
 static struct class firmware_class = {
 	.name		= "firmware",
 	.class_attrs	= firmware_class_attrs,
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 31df474d72f4..560751bad294 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -392,6 +392,16 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;
 
+		/*
+		 * memory block could have several absent sections from start.
+		 * skip pfn range from absent section
+		 */
+		if (!pfn_present(pfn)) {
+			pfn = round_down(pfn + PAGES_PER_SECTION,
+					 PAGES_PER_SECTION) - 1;
+			continue;
+		}
+
 		page_nid = get_nid_for_pfn(pfn);
 		if (page_nid < 0)
 			continue;
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
new file mode 100644
index 000000000000..1857a5dd0816
--- /dev/null
+++ b/drivers/base/platform-msi.c
@@ -0,0 +1,282 @@
+/*
+ * MSI framework for platform devices
+ *
+ * Copyright (C) 2015 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/msi.h>
+#include <linux/slab.h>
+
+#define DEV_ID_SHIFT	24
+
+/*
+ * Internal data structure containing a (made up, but unique) devid
+ * and the callback to write the MSI message.
+ */
+struct platform_msi_priv_data {
+	irq_write_msi_msg_t	write_msg;
+	int			devid;
+};
+
+/* The devid allocator */
+static DEFINE_IDA(platform_msi_devid_ida);
+
+#ifdef GENERIC_MSI_DOMAIN_OPS
+/*
+ * Convert an msi_desc to a globaly unique identifier (per-device
+ * devid + msi_desc position in the msi_list).
+ */
+static irq_hw_number_t platform_msi_calc_hwirq(struct msi_desc *desc)
+{
+	u32 devid;
+
+	devid = desc->platform.msi_priv_data->devid;
+
+	return (devid << (32 - DEV_ID_SHIFT)) | desc->platform.msi_index;
+}
+
+static void platform_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+	arg->desc = desc;
+	arg->hwirq = platform_msi_calc_hwirq(desc);
+}
+
+static int platform_msi_init(struct irq_domain *domain,
+			     struct msi_domain_info *info,
+			     unsigned int virq, irq_hw_number_t hwirq,
+			     msi_alloc_info_t *arg)
+{
+	struct irq_data *data;
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+				      info->chip, info->chip_data);
+
+	/*
+	 * Save the MSI descriptor in handler_data so that the
+	 * irq_write_msi_msg callback can retrieve it (and the
+	 * associated device).
+	 */
+	data = irq_domain_get_irq_data(domain, virq);
+	data->handler_data = arg->desc;
+
+	return 0;
+}
+#else
+#define platform_msi_set_desc		NULL
+#define platform_msi_init		NULL
+#endif
+
+static void platform_msi_update_dom_ops(struct msi_domain_info *info)
+{
+	struct msi_domain_ops *ops = info->ops;
+
+	BUG_ON(!ops);
+
+	if (ops->msi_init == NULL)
+		ops->msi_init = platform_msi_init;
+	if (ops->set_desc == NULL)
+		ops->set_desc = platform_msi_set_desc;
+}
+
+static void platform_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct msi_desc *desc = irq_data_get_irq_handler_data(data);
+	struct platform_msi_priv_data *priv_data;
+
+	priv_data = desc->platform.msi_priv_data;
+
+	priv_data->write_msg(desc, msg);
+}
+
+static void platform_msi_update_chip_ops(struct msi_domain_info *info)
+{
+	struct irq_chip *chip = info->chip;
+
+	BUG_ON(!chip);
+	if (!chip->irq_mask)
+		chip->irq_mask = irq_chip_mask_parent;
+	if (!chip->irq_unmask)
+		chip->irq_unmask = irq_chip_unmask_parent;
+	if (!chip->irq_eoi)
+		chip->irq_eoi = irq_chip_eoi_parent;
+	if (!chip->irq_set_affinity)
+		chip->irq_set_affinity = msi_domain_set_affinity;
+	if (!chip->irq_write_msi_msg)
+		chip->irq_write_msi_msg = platform_msi_write_msg;
+}
+
+static void platform_msi_free_descs(struct device *dev)
+{
+	struct msi_desc *desc, *tmp;
+
+	list_for_each_entry_safe(desc, tmp, dev_to_msi_list(dev), list) {
+		list_del(&desc->list);
+		free_msi_entry(desc);
+	}
+}
+
+static int platform_msi_alloc_descs(struct device *dev, int nvec,
+				    struct platform_msi_priv_data *data)
+
+{
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		struct msi_desc *desc;
+
+		desc = alloc_msi_entry(dev);
+		if (!desc)
+			break;
+
+		desc->platform.msi_priv_data = data;
+		desc->platform.msi_index = i;
+		desc->nvec_used = 1;
+
+		list_add_tail(&desc->list, dev_to_msi_list(dev));
+	}
+
+	if (i != nvec) {
+		/* Clean up the mess */
+		platform_msi_free_descs(dev);
+
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * platform_msi_create_irq_domain - Create a platform MSI interrupt domain
+ * @np:		Optional device-tree node of the interrupt controller
+ * @info:	MSI domain info
+ * @parent:	Parent irq domain
+ *
+ * Updates the domain and chip ops and creates a platform MSI
+ * interrupt domain.
+ *
+ * Returns:
+ * A domain pointer or NULL in case of failure.
+ */
+struct irq_domain *platform_msi_create_irq_domain(struct device_node *np,
+						  struct msi_domain_info *info,
+						  struct irq_domain *parent)
+{
+	struct irq_domain *domain;
+
+	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
+		platform_msi_update_dom_ops(info);
+	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
+		platform_msi_update_chip_ops(info);
+
+	domain = msi_create_irq_domain(np, info, parent);
+	if (domain)
+		domain->bus_token = DOMAIN_BUS_PLATFORM_MSI;
+
+	return domain;
+}
+
+/**
+ * platform_msi_domain_alloc_irqs - Allocate MSI interrupts for @dev
+ * @dev:		The device for which to allocate interrupts
+ * @nvec:		The number of interrupts to allocate
+ * @write_msi_msg:	Callback to write an interrupt message for @dev
+ *
+ * Returns:
+ * Zero for success, or an error code in case of failure
+ */
+int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
+				   irq_write_msi_msg_t write_msi_msg)
+{
+	struct platform_msi_priv_data *priv_data;
+	int err;
+
+	/*
+	 * Limit the number of interrupts to 256 per device. Should we
+	 * need to bump this up, DEV_ID_SHIFT should be adjusted
+	 * accordingly (which would impact the max number of MSI
+	 * capable devices).
+	 */
+	if (!dev->msi_domain || !write_msi_msg || !nvec ||
+	    nvec > (1 << (32 - DEV_ID_SHIFT)))
+		return -EINVAL;
+
+	if (dev->msi_domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) {
+		dev_err(dev, "Incompatible msi_domain, giving up\n");
+		return -EINVAL;
+	}
+
+	/* Already had a helping of MSI? Greed... */
+	if (!list_empty(dev_to_msi_list(dev)))
+		return -EBUSY;
+
+	priv_data = kzalloc(sizeof(*priv_data), GFP_KERNEL);
+	if (!priv_data)
+		return -ENOMEM;
+
+	priv_data->devid = ida_simple_get(&platform_msi_devid_ida,
+					  0, 1 << DEV_ID_SHIFT, GFP_KERNEL);
+	if (priv_data->devid < 0) {
+		err = priv_data->devid;
+		goto out_free_data;
+	}
+
+	priv_data->write_msg = write_msi_msg;
+
+	err = platform_msi_alloc_descs(dev, nvec, priv_data);
+	if (err)
+		goto out_free_id;
+
+	err = msi_domain_alloc_irqs(dev->msi_domain, dev, nvec);
+	if (err)
+		goto out_free_desc;
+
+	return 0;
+
+out_free_desc:
+	platform_msi_free_descs(dev);
+out_free_id:
+	ida_simple_remove(&platform_msi_devid_ida, priv_data->devid);
+out_free_data:
+	kfree(priv_data);
+
+	return err;
+}
+
+/**
+ * platform_msi_domain_free_irqs - Free MSI interrupts for @dev
+ * @dev:	The device for which to free interrupts
+ */
+void platform_msi_domain_free_irqs(struct device *dev)
+{
+	struct msi_desc *desc;
+
+	desc = first_msi_entry(dev);
+	if (desc) {
+		struct platform_msi_priv_data *data;
+
+		data = desc->platform.msi_priv_data;
+
+		ida_simple_remove(&platform_msi_devid_ida, data->devid);
+		kfree(data);
+	}
+
+	msi_domain_free_irqs(dev->msi_domain, dev);
+	platform_msi_free_descs(dev);
+}
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 063f0ab15259..f80aaaf9f610 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -375,9 +375,7 @@ int platform_device_add(struct platform_device *pdev)
 
 	while (--i >= 0) {
 		struct resource *r = &pdev->resource[i];
-		unsigned long type = resource_type(r);
-
-		if (type == IORESOURCE_MEM || type == IORESOURCE_IO)
+		if (r->parent)
 			release_resource(r);
 	}
 
@@ -408,9 +406,7 @@ void platform_device_del(struct platform_device *pdev)
 
 		for (i = 0; i < pdev->num_resources; i++) {
 			struct resource *r = &pdev->resource[i];
-			unsigned long type = resource_type(r);
-
-			if (type == IORESOURCE_MEM || type == IORESOURCE_IO)
+			if (r->parent)
 				release_resource(r);
 		}
 	}
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index acef9f9f759a..652b5a367c1f 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -38,7 +38,7 @@ struct pm_clock_entry {
  * @dev: The device for the given clock
  * @ce: PM clock entry corresponding to the clock.
  */
-static inline int __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
+static inline void __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
 {
 	int ret;
 
@@ -50,8 +50,6 @@ static inline int __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
 			dev_err(dev, "%s: failed to enable clk %p, error %d\n",
 				__func__, ce->clk, ret);
 	}
-
-	return ret;
 }
 
 /**
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index cdd547bd67df..416720159e96 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -6,6 +6,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
@@ -19,6 +20,8 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 
+#define GENPD_RETRY_MAX_MS	250		/* Approximate */
+
 #define GENPD_DEV_CALLBACK(genpd, type, callback, dev)		\
 ({								\
 	type (*__routine)(struct device *__d); 			\
@@ -111,8 +114,12 @@ static int genpd_stop_dev(struct generic_pm_domain *genpd, struct device *dev)
 					stop_latency_ns, "stop");
 }
 
-static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev)
+static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev,
+			bool timed)
 {
+	if (!timed)
+		return GENPD_DEV_CALLBACK(genpd, int, start, dev);
+
 	return GENPD_DEV_TIMED_CALLBACK(genpd, int, start, dev,
 					start_latency_ns, "start");
 }
@@ -133,41 +140,6 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 	smp_mb__after_atomic();
 }
 
-static void genpd_acquire_lock(struct generic_pm_domain *genpd)
-{
-	DEFINE_WAIT(wait);
-
-	mutex_lock(&genpd->lock);
-	/*
-	 * Wait for the domain to transition into either the active,
-	 * or the power off state.
-	 */
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		if (genpd->status == GPD_STATE_ACTIVE
-		    || genpd->status == GPD_STATE_POWER_OFF)
-			break;
-		mutex_unlock(&genpd->lock);
-
-		schedule();
-
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-}
-
-static void genpd_release_lock(struct generic_pm_domain *genpd)
-{
-	mutex_unlock(&genpd->lock);
-}
-
-static void genpd_set_active(struct generic_pm_domain *genpd)
-{
-	if (genpd->resume_count == 0)
-		genpd->status = GPD_STATE_ACTIVE;
-}
-
 static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
 {
 	s64 usecs64;
@@ -248,35 +220,14 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
  * resume a device belonging to it.
  */
 static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
 {
 	struct gpd_link *link;
-	DEFINE_WAIT(wait);
 	int ret = 0;
 
-	/* If the domain's master is being waited for, we have to wait too. */
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		if (genpd->status != GPD_STATE_WAIT_MASTER)
-			break;
-		mutex_unlock(&genpd->lock);
-
-		schedule();
-
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-
 	if (genpd->status == GPD_STATE_ACTIVE
 	    || (genpd->prepared_count > 0 && genpd->suspend_power_off))
 		return 0;
 
-	if (genpd->status != GPD_STATE_POWER_OFF) {
-		genpd_set_active(genpd);
-		return 0;
-	}
-
 	if (genpd->cpuidle_data) {
 		cpuidle_pause_and_lock();
 		genpd->cpuidle_data->idle_state->disabled = true;
@@ -291,20 +242,8 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 	 */
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_inc(link->master);
-		genpd->status = GPD_STATE_WAIT_MASTER;
-
-		mutex_unlock(&genpd->lock);
 
 		ret = pm_genpd_poweron(link->master);
-
-		mutex_lock(&genpd->lock);
-
-		/*
-		 * The "wait for parent" status is guaranteed not to change
-		 * while the master is powering on.
-		 */
-		genpd->status = GPD_STATE_POWER_OFF;
-		wake_up_all(&genpd->status_wait_queue);
 		if (ret) {
 			genpd_sd_counter_dec(link->master);
 			goto err;
@@ -316,8 +255,7 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 		goto err;
 
  out:
-	genpd_set_active(genpd);
-
+	genpd->status = GPD_STATE_ACTIVE;
 	return 0;
 
  err:
@@ -353,20 +291,18 @@ int pm_genpd_name_poweron(const char *domain_name)
 	return genpd ? pm_genpd_poweron(genpd) : -EINVAL;
 }
 
-static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd,
-				     struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, start, dev);
-}
-
 static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
 {
 	return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev,
 					save_state_latency_ns, "state save");
 }
 
-static int genpd_restore_dev(struct generic_pm_domain *genpd, struct device *dev)
+static int genpd_restore_dev(struct generic_pm_domain *genpd,
+			struct device *dev, bool timed)
 {
+	if (!timed)
+		return GENPD_DEV_CALLBACK(genpd, int, restore_state, dev);
+
 	return GENPD_DEV_TIMED_CALLBACK(genpd, int, restore_state, dev,
 					restore_state_latency_ns,
 					"state restore");
@@ -413,89 +349,6 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 }
 
 /**
- * __pm_genpd_save_device - Save the pre-suspend state of a device.
- * @pdd: Domain data of the device to save the state of.
- * @genpd: PM domain the device belongs to.
- */
-static int __pm_genpd_save_device(struct pm_domain_data *pdd,
-				  struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
-{
-	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
-	struct device *dev = pdd->dev;
-	int ret = 0;
-
-	if (gpd_data->need_restore > 0)
-		return 0;
-
-	/*
-	 * If the value of the need_restore flag is still unknown at this point,
-	 * we trust that pm_genpd_poweroff() has verified that the device is
-	 * already runtime PM suspended.
-	 */
-	if (gpd_data->need_restore < 0) {
-		gpd_data->need_restore = 1;
-		return 0;
-	}
-
-	mutex_unlock(&genpd->lock);
-
-	genpd_start_dev(genpd, dev);
-	ret = genpd_save_dev(genpd, dev);
-	genpd_stop_dev(genpd, dev);
-
-	mutex_lock(&genpd->lock);
-
-	if (!ret)
-		gpd_data->need_restore = 1;
-
-	return ret;
-}
-
-/**
- * __pm_genpd_restore_device - Restore the pre-suspend state of a device.
- * @pdd: Domain data of the device to restore the state of.
- * @genpd: PM domain the device belongs to.
- */
-static void __pm_genpd_restore_device(struct pm_domain_data *pdd,
-				      struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
-{
-	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
-	struct device *dev = pdd->dev;
-	int need_restore = gpd_data->need_restore;
-
-	gpd_data->need_restore = 0;
-	mutex_unlock(&genpd->lock);
-
-	genpd_start_dev(genpd, dev);
-
-	/*
-	 * Call genpd_restore_dev() for recently added devices too (need_restore
-	 * is negative then).
-	 */
-	if (need_restore)
-		genpd_restore_dev(genpd, dev);
-
-	mutex_lock(&genpd->lock);
-}
-
-/**
- * genpd_abort_poweroff - Check if a PM domain power off should be aborted.
- * @genpd: PM domain to check.
- *
- * Return true if a PM domain's status changed to GPD_STATE_ACTIVE during
- * a "power off" operation, which means that a "power on" has occured in the
- * meantime, or if its resume_count field is different from zero, which means
- * that one of its devices has been resumed in the meantime.
- */
-static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
-{
-	return genpd->status == GPD_STATE_WAIT_MASTER
-		|| genpd->status == GPD_STATE_ACTIVE || genpd->resume_count > 0;
-}
-
-/**
  * genpd_queue_power_off_work - Queue up the execution of pm_genpd_poweroff().
  * @genpd: PM domait to power off.
  *
@@ -512,34 +365,26 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
  * @genpd: PM domain to power down.
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
- * have been powered down, run the runtime suspend callbacks provided by all of
- * the @genpd's devices' drivers and remove power from @genpd.
+ * have been powered down, remove power from @genpd.
  */
 static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
-	unsigned int not_suspended;
-	int ret = 0;
+	unsigned int not_suspended = 0;
 
- start:
 	/*
 	 * Do not try to power off the domain in the following situations:
 	 * (1) The domain is already in the "power off" state.
-	 * (2) The domain is waiting for its master to power up.
-	 * (3) One of the domain's devices is being resumed right now.
-	 * (4) System suspend is in progress.
+	 * (2) System suspend is in progress.
 	 */
 	if (genpd->status == GPD_STATE_POWER_OFF
-	    || genpd->status == GPD_STATE_WAIT_MASTER
-	    || genpd->resume_count > 0 || genpd->prepared_count > 0)
+	    || genpd->prepared_count > 0)
 		return 0;
 
 	if (atomic_read(&genpd->sd_count) > 0)
 		return -EBUSY;
 
-	not_suspended = 0;
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
 		enum pm_qos_flags_status stat;
 
@@ -557,41 +402,11 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 	if (not_suspended > genpd->in_progress)
 		return -EBUSY;
 
-	if (genpd->poweroff_task) {
-		/*
-		 * Another instance of pm_genpd_poweroff() is executing
-		 * callbacks, so tell it to start over and return.
-		 */
-		genpd->status = GPD_STATE_REPEAT;
-		return 0;
-	}
-
 	if (genpd->gov && genpd->gov->power_down_ok) {
 		if (!genpd->gov->power_down_ok(&genpd->domain))
 			return -EAGAIN;
 	}
 
-	genpd->status = GPD_STATE_BUSY;
-	genpd->poweroff_task = current;
-
-	list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) {
-		ret = atomic_read(&genpd->sd_count) == 0 ?
-			__pm_genpd_save_device(pdd, genpd) : -EBUSY;
-
-		if (genpd_abort_poweroff(genpd))
-			goto out;
-
-		if (ret) {
-			genpd_set_active(genpd);
-			goto out;
-		}
-
-		if (genpd->status == GPD_STATE_REPEAT) {
-			genpd->poweroff_task = NULL;
-			goto start;
-		}
-	}
-
 	if (genpd->cpuidle_data) {
 		/*
 		 * If cpuidle_data is set, cpuidle should turn the domain off
@@ -604,14 +419,14 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		cpuidle_pause_and_lock();
 		genpd->cpuidle_data->idle_state->disabled = false;
 		cpuidle_resume_and_unlock();
-		goto out;
+		return 0;
 	}
 
 	if (genpd->power_off) {
-		if (atomic_read(&genpd->sd_count) > 0) {
-			ret = -EBUSY;
-			goto out;
-		}
+		int ret;
+
+		if (atomic_read(&genpd->sd_count) > 0)
+			return -EBUSY;
 
 		/*
 		 * If sd_count > 0 at this point, one of the subdomains hasn't
@@ -622,10 +437,8 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		 * happen very often).
 		 */
 		ret = genpd_power_off(genpd, true);
-		if (ret == -EBUSY) {
-			genpd_set_active(genpd);
-			goto out;
-		}
+		if (ret)
+			return ret;
 	}
 
 	genpd->status = GPD_STATE_POWER_OFF;
@@ -635,10 +448,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		genpd_queue_power_off_work(link->master);
 	}
 
- out:
-	genpd->poweroff_task = NULL;
-	wake_up_all(&genpd->status_wait_queue);
-	return ret;
+	return 0;
 }
 
 /**
@@ -651,9 +461,9 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 	pm_genpd_poweroff(genpd);
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 }
 
 /**
@@ -667,7 +477,6 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 static int pm_genpd_runtime_suspend(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	struct generic_pm_domain_data *gpd_data;
 	bool (*stop_ok)(struct device *__dev);
 	int ret;
 
@@ -681,10 +490,16 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	if (stop_ok && !stop_ok(dev))
 		return -EBUSY;
 
-	ret = genpd_stop_dev(genpd, dev);
+	ret = genpd_save_dev(genpd, dev);
 	if (ret)
 		return ret;
 
+	ret = genpd_stop_dev(genpd, dev);
+	if (ret) {
+		genpd_restore_dev(genpd, dev, true);
+		return ret;
+	}
+
 	/*
 	 * If power.irq_safe is set, this routine will be run with interrupts
 	 * off, so it can't use mutexes.
@@ -693,16 +508,6 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	mutex_lock(&genpd->lock);
-
-	/*
-	 * If we have an unknown state of the need_restore flag, it means none
-	 * of the runtime PM callbacks has been invoked yet. Let's update the
-	 * flag to reflect that the current state is active.
-	 */
-	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	if (gpd_data->need_restore < 0)
-		gpd_data->need_restore = 0;
-
 	genpd->in_progress++;
 	pm_genpd_poweroff(genpd);
 	genpd->in_progress--;
@@ -722,8 +527,8 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 static int pm_genpd_runtime_resume(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	DEFINE_WAIT(wait);
 	int ret;
+	bool timed = true;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -732,39 +537,21 @@ static int pm_genpd_runtime_resume(struct device *dev)
 		return -EINVAL;
 
 	/* If power.irq_safe, the PM domain is never powered off. */
-	if (dev->power.irq_safe)
-		return genpd_start_dev_no_timing(genpd, dev);
+	if (dev->power.irq_safe) {
+		timed = false;
+		goto out;
+	}
 
 	mutex_lock(&genpd->lock);
 	ret = __pm_genpd_poweron(genpd);
-	if (ret) {
-		mutex_unlock(&genpd->lock);
-		return ret;
-	}
-	genpd->status = GPD_STATE_BUSY;
-	genpd->resume_count++;
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		/*
-		 * If current is the powering off task, we have been called
-		 * reentrantly from one of the device callbacks, so we should
-		 * not wait.
-		 */
-		if (!genpd->poweroff_task || genpd->poweroff_task == current)
-			break;
-		mutex_unlock(&genpd->lock);
+	mutex_unlock(&genpd->lock);
 
-		schedule();
+	if (ret)
+		return ret;
 
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-	__pm_genpd_restore_device(dev->power.subsys_data->domain_data, genpd);
-	genpd->resume_count--;
-	genpd_set_active(genpd);
-	wake_up_all(&genpd->status_wait_queue);
-	mutex_unlock(&genpd->lock);
+ out:
+	genpd_start_dev(genpd, dev, timed);
+	genpd_restore_dev(genpd, dev, timed);
 
 	return 0;
 }
@@ -880,7 +667,7 @@ static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd,
 {
 	struct gpd_link *link;
 
-	if (genpd->status != GPD_STATE_POWER_OFF)
+	if (genpd->status == GPD_STATE_ACTIVE)
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
@@ -957,14 +744,14 @@ static int pm_genpd_prepare(struct device *dev)
 	if (resume_needed(dev, genpd))
 		pm_runtime_resume(dev);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count++ == 0) {
 		genpd->suspended_count = 0;
 		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
 	}
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	if (genpd->suspend_power_off) {
 		pm_runtime_put_noidle(dev);
@@ -1099,7 +886,7 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	pm_genpd_sync_poweron(genpd, true);
 	genpd->suspended_count--;
 
-	return genpd_start_dev(genpd, dev);
+	return genpd_start_dev(genpd, dev, true);
 }
 
 /**
@@ -1227,7 +1014,7 @@ static int pm_genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev, true);
 }
 
 /**
@@ -1321,7 +1108,7 @@ static int pm_genpd_restore_noirq(struct device *dev)
 
 	pm_genpd_sync_poweron(genpd, true);
 
-	return genpd_start_dev(genpd, dev);
+	return genpd_start_dev(genpd, dev, true);
 }
 
 /**
@@ -1437,7 +1224,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 		gpd_data->td = *td;
 
 	gpd_data->base.dev = dev;
-	gpd_data->need_restore = -1;
 	gpd_data->td.constraint_changed = true;
 	gpd_data->td.effective_constraint_ns = -1;
 	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
@@ -1499,7 +1285,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1516,7 +1302,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	if (ret)
 		genpd_free_dev_data(dev, gpd_data);
@@ -1560,7 +1346,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	gpd_data = to_gpd_data(pdd);
 	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1575,14 +1361,14 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 
 	list_del_init(&pdd->list_node);
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	genpd_free_dev_data(dev, gpd_data);
 
 	return 0;
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
@@ -1603,17 +1389,9 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 	    || genpd == subdomain)
 		return -EINVAL;
 
- start:
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 	mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
-	if (subdomain->status != GPD_STATE_POWER_OFF
-	    && subdomain->status != GPD_STATE_ACTIVE) {
-		mutex_unlock(&subdomain->lock);
-		genpd_release_lock(genpd);
-		goto start;
-	}
-
 	if (genpd->status == GPD_STATE_POWER_OFF
 	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
 		ret = -EINVAL;
@@ -1641,7 +1419,7 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 
  out:
 	mutex_unlock(&subdomain->lock);
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	return ret;
 }
@@ -1689,8 +1467,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
 		return -EINVAL;
 
- start:
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	list_for_each_entry(link, &genpd->master_links, master_node) {
 		if (link->slave != subdomain)
@@ -1698,13 +1475,6 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 
 		mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
-		if (subdomain->status != GPD_STATE_POWER_OFF
-		    && subdomain->status != GPD_STATE_ACTIVE) {
-			mutex_unlock(&subdomain->lock);
-			genpd_release_lock(genpd);
-			goto start;
-		}
-
 		list_del(&link->master_node);
 		list_del(&link->slave_node);
 		kfree(link);
@@ -1717,7 +1487,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 		break;
 	}
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	return ret;
 }
@@ -1741,7 +1511,7 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 	if (IS_ERR_OR_NULL(genpd) || state < 0)
 		return -EINVAL;
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->cpuidle_data) {
 		ret = -EEXIST;
@@ -1772,7 +1542,7 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 	genpd_recalc_cpu_exit_latency(genpd);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	return ret;
 
  err:
@@ -1809,7 +1579,7 @@ int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	cpuidle_data = genpd->cpuidle_data;
 	if (!cpuidle_data) {
@@ -1827,7 +1597,7 @@ int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 	kfree(cpuidle_data);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	return ret;
 }
 
@@ -1909,9 +1679,6 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->in_progress = 0;
 	atomic_set(&genpd->sd_count, 0);
 	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
-	init_waitqueue_head(&genpd->status_wait_queue);
-	genpd->poweroff_task = NULL;
-	genpd->resume_count = 0;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
@@ -1949,6 +1716,7 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+EXPORT_SYMBOL_GPL(pm_genpd_init);
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_OF
 /*
@@ -2122,7 +1890,7 @@ EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 
 /**
  * genpd_dev_pm_detach - Detach a device from its PM domain.
- * @dev: Device to attach.
+ * @dev: Device to detach.
  * @power_off: Currently not used
  *
  * Try to locate a corresponding generic PM domain, which the device was
@@ -2131,6 +1899,7 @@ EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 {
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret = 0;
 
 	pd = pm_genpd_lookup_dev(dev);
@@ -2139,10 +1908,12 @@ static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 
 	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_remove_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
@@ -2177,12 +1948,16 @@ static void genpd_dev_pm_sync(struct device *dev)
  * Both generic and legacy Samsung-specific DT bindings are supported to keep
  * backwards compatibility with existing DTBs.
  *
- * Returns 0 on successfully attached PM domain or negative error code.
+ * Returns 0 on successfully attached PM domain or negative error code. Note
+ * that if a power-domain exists for the device, but it cannot be found or
+ * turned on, then return -EPROBE_DEFER to ensure that the device is not
+ * probed and to re-try again later.
  */
 int genpd_dev_pm_attach(struct device *dev)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret;
 
 	if (!dev->of_node)
@@ -2213,15 +1988,17 @@ int genpd_dev_pm_attach(struct device *dev)
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
 		of_node_put(dev->of_node);
-		return PTR_ERR(pd);
+		return -EPROBE_DEFER;
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_add_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
@@ -2229,14 +2006,15 @@ int genpd_dev_pm_attach(struct device *dev)
 		dev_err(dev, "failed to add to PM domain %s: %d",
 			pd->name, ret);
 		of_node_put(dev->of_node);
-		return ret;
+		goto out;
 	}
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
-	pm_genpd_poweron(pd);
+	ret = pm_genpd_poweron(pd);
 
-	return 0;
+out:
+	return ret ? -EPROBE_DEFER : 0;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -2284,9 +2062,6 @@ static int pm_genpd_summary_one(struct seq_file *s,
 {
 	static const char * const status_lookup[] = {
 		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_WAIT_MASTER] = "wait-master",
-		[GPD_STATE_BUSY] = "busy",
-		[GPD_STATE_REPEAT] = "off-in-progress",
 		[GPD_STATE_POWER_OFF] = "off"
 	};
 	struct pm_domain_data *pm_data;
@@ -2300,7 +2075,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
-	seq_printf(s, "%-30s  %-15s  ", genpd->name, status_lookup[genpd->status]);
+	seq_printf(s, "%-30s  %-15s ", genpd->name, status_lookup[genpd->status]);
 
 	/*
 	 * Modifications on the list require holding locks on both
@@ -2335,8 +2110,8 @@ static int pm_genpd_summary_show(struct seq_file *s, void *data)
 	struct generic_pm_domain *genpd;
 	int ret = 0;
 
-	seq_puts(s, "    domain                      status         slaves\n");
-	seq_puts(s, "           /device                                      runtime status\n");
+	seq_puts(s, "domain                          status          slaves\n");
+	seq_puts(s, "    /device                                             runtime status\n");
 	seq_puts(s, "----------------------------------------------------------------------\n");
 
 	ret = mutex_lock_interruptible(&gpd_list_lock);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 30b7bbfdc558..1710c26ba097 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1377,7 +1377,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
 			pm_runtime_disable(dev);
-			if (pm_runtime_suspended_if_enabled(dev))
+			if (pm_runtime_status_suspended(dev))
 				goto Complete;
 
 			pm_runtime_enable(dev);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 677fb2843553..eb254497a494 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -51,10 +52,17 @@
  *		order.
  * @dynamic:	not-created from static DT entries.
  * @available:	true/false - marks if this OPP as available or not
+ * @turbo:	true if turbo (boost) OPP
  * @rate:	Frequency in hertz
- * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
+ * @u_volt:	Target voltage in microvolts corresponding to this OPP
+ * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
+ * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
+ * @u_amp:	Maximum current drawn by the device in microamperes
+ * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
+ *		frequency from any other OPP's frequency.
  * @dev_opp:	points back to the device_opp struct this opp belongs to
  * @rcu_head:	RCU callback head used for deferred freeing
+ * @np:		OPP's device node.
  *
  * This structure stores the OPP information for a given device.
  */
@@ -63,11 +71,34 @@ struct dev_pm_opp {
 
 	bool available;
 	bool dynamic;
+	bool turbo;
 	unsigned long rate;
+
 	unsigned long u_volt;
+	unsigned long u_volt_min;
+	unsigned long u_volt_max;
+	unsigned long u_amp;
+	unsigned long clock_latency_ns;
 
 	struct device_opp *dev_opp;
 	struct rcu_head rcu_head;
+
+	struct device_node *np;
+};
+
+/**
+ * struct device_list_opp - devices managed by 'struct device_opp'
+ * @node:	list node
+ * @dev:	device to which the struct object belongs
+ * @rcu_head:	RCU callback head used for deferred freeing
+ *
+ * This is an internal data structure maintaining the list of devices that are
+ * managed by 'struct device_opp'.
+ */
+struct device_list_opp {
+	struct list_head node;
+	const struct device *dev;
+	struct rcu_head rcu_head;
 };
 
 /**
@@ -77,10 +108,12 @@ struct dev_pm_opp {
  *		list.
  *		RCU usage: nodes are not modified in the list of device_opp,
  *		however addition is possible and is secured by dev_opp_list_lock
- * @dev:	device pointer
  * @srcu_head:	notifier head to notify the OPP availability changes.
  * @rcu_head:	RCU callback head used for deferred freeing
+ * @dev_list:	list of devices that share these OPPs
  * @opp_list:	list of opps
+ * @np:		struct device_node pointer for opp's DT node.
+ * @shared_opp: OPP is shared between multiple devices.
  *
  * This is an internal data structure maintaining the link to opps attached to
  * a device. This structure is not meant to be shared to users as it is
@@ -93,10 +126,15 @@ struct dev_pm_opp {
 struct device_opp {
 	struct list_head node;
 
-	struct device *dev;
 	struct srcu_notifier_head srcu_head;
 	struct rcu_head rcu_head;
+	struct list_head dev_list;
 	struct list_head opp_list;
+
+	struct device_node *np;
+	unsigned long clock_latency_ns_max;
+	bool shared_opp;
+	struct dev_pm_opp *suspend_opp;
 };
 
 /*
@@ -110,12 +148,44 @@ static DEFINE_MUTEX(dev_opp_list_lock);
 
 #define opp_rcu_lockdep_assert()					\
 do {									\
-	rcu_lockdep_assert(rcu_read_lock_held() ||			\
-				lockdep_is_held(&dev_opp_list_lock),	\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+				!lockdep_is_held(&dev_opp_list_lock),	\
 			   "Missing rcu_read_lock() or "		\
 			   "dev_opp_list_lock protection");		\
 } while (0)
 
+static struct device_list_opp *_find_list_dev(const struct device *dev,
+					      struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_for_each_entry(list_dev, &dev_opp->dev_list, node)
+		if (list_dev->dev == dev)
+			return list_dev;
+
+	return NULL;
+}
+
+static struct device_opp *_managed_opp(const struct device_node *np)
+{
+	struct device_opp *dev_opp;
+
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) {
+		if (dev_opp->np == np) {
+			/*
+			 * Multiple devices can point to the same OPP table and
+			 * so will have same node-pointer, np.
+			 *
+			 * But the OPPs will be considered as shared only if the
+			 * OPP table contains a "opp-shared" property.
+			 */
+			return dev_opp->shared_opp ? dev_opp : NULL;
+		}
+	}
+
+	return NULL;
+}
+
 /**
  * _find_device_opp() - find device_opp struct using device pointer
  * @dev:	device pointer used to lookup device OPPs
@@ -132,21 +202,18 @@ do {									\
  */
 static struct device_opp *_find_device_opp(struct device *dev)
 {
-	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	struct device_opp *dev_opp;
 
-	if (unlikely(IS_ERR_OR_NULL(dev))) {
+	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
-		if (tmp_dev_opp->dev == dev) {
-			dev_opp = tmp_dev_opp;
-			break;
-		}
-	}
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node)
+		if (_find_list_dev(dev, dev_opp))
+			return dev_opp;
 
-	return dev_opp;
+	return ERR_PTR(-ENODEV);
 }
 
 /**
@@ -172,7 +239,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		v = tmp_opp->u_volt;
@@ -204,7 +271,7 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		f = tmp_opp->rate;
@@ -214,6 +281,66 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
 /**
+ * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not
+ * @opp: opp for which turbo mode is being verified
+ *
+ * Turbo OPPs are not for normal use, and can be enabled (under certain
+ * conditions) for short duration of times to finish high throughput work
+ * quickly. Running on them for longer times may overheat the chip.
+ *
+ * Return: true if opp is turbo opp, else false.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+
+	opp_rcu_lockdep_assert();
+
+	tmp_opp = rcu_dereference(opp);
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return false;
+	}
+
+	return tmp_opp->turbo;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
+
+/**
+ * dev_pm_opp_get_max_clock_latency() - Get max clock latency in nanoseconds
+ * @dev:	device for which we do this operation
+ *
+ * Return: This function returns the max clock latency in nanoseconds.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	unsigned long clock_latency_ns;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		clock_latency_ns = 0;
+	else
+		clock_latency_ns = dev_opp->clock_latency_ns_max;
+
+	rcu_read_unlock();
+	return clock_latency_ns;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
+
+/**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
  * @dev:	device for which we do this operation
  *
@@ -407,18 +534,57 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
+/* List-dev Helpers */
+static void _kfree_list_dev_rcu(struct rcu_head *head)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = container_of(head, struct device_list_opp, rcu_head);
+	kfree_rcu(list_dev, rcu_head);
+}
+
+static void _remove_list_dev(struct device_list_opp *list_dev,
+			     struct device_opp *dev_opp)
+{
+	list_del(&list_dev->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head,
+		  _kfree_list_dev_rcu);
+}
+
+static struct device_list_opp *_add_list_dev(const struct device *dev,
+					     struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL);
+	if (!list_dev)
+		return NULL;
+
+	/* Initialize list-dev */
+	list_dev->dev = dev;
+	list_add_rcu(&list_dev->node, &dev_opp->dev_list);
+
+	return list_dev;
+}
+
 /**
- * _add_device_opp() - Allocate a new device OPP table
+ * _add_device_opp() - Find device OPP table or allocate a new one
  * @dev:	device for which we do this operation
  *
- * New device node which uses OPPs - used when multiple devices with OPP tables
- * are maintained.
+ * It tries to find an existing table first, if it couldn't find one, it
+ * allocates a new OPP table and returns that.
  *
  * Return: valid device_opp pointer if success, else NULL.
  */
 static struct device_opp *_add_device_opp(struct device *dev)
 {
 	struct device_opp *dev_opp;
+	struct device_list_opp *list_dev;
+
+	/* Check for existing list for 'dev' first */
+	dev_opp = _find_device_opp(dev);
+	if (!IS_ERR(dev_opp))
+		return dev_opp;
 
 	/*
 	 * Allocate a new device OPP table. In the infrequent case where a new
@@ -428,7 +594,14 @@ static struct device_opp *_add_device_opp(struct device *dev)
 	if (!dev_opp)
 		return NULL;
 
-	dev_opp->dev = dev;
+	INIT_LIST_HEAD(&dev_opp->dev_list);
+
+	list_dev = _add_list_dev(dev, dev_opp);
+	if (!list_dev) {
+		kfree(dev_opp);
+		return NULL;
+	}
+
 	srcu_init_notifier_head(&dev_opp->srcu_head);
 	INIT_LIST_HEAD(&dev_opp->opp_list);
 
@@ -438,6 +611,185 @@ static struct device_opp *_add_device_opp(struct device *dev)
 }
 
 /**
+ * _kfree_device_rcu() - Free device_opp RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_device_rcu(struct rcu_head *head)
+{
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+
+	kfree_rcu(device_opp, rcu_head);
+}
+
+/**
+ * _remove_device_opp() - Removes a device OPP table
+ * @dev_opp: device OPP table to be removed.
+ *
+ * Removes/frees device OPP table it it doesn't contain any OPPs.
+ */
+static void _remove_device_opp(struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	if (!list_empty(&dev_opp->opp_list))
+		return;
+
+	list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp,
+				    node);
+
+	_remove_list_dev(list_dev, dev_opp);
+
+	/* dev_list must be empty now */
+	WARN_ON(!list_empty(&dev_opp->dev_list));
+
+	list_del_rcu(&dev_opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+		  _kfree_device_rcu);
+}
+
+/**
+ * _kfree_opp_rcu() - Free OPP RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_opp_rcu(struct rcu_head *head)
+{
+	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+
+	kfree_rcu(opp, rcu_head);
+}
+
+/**
+ * _opp_remove()  - Remove an OPP from a table definition
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @opp:	pointer to the OPP to remove
+ * @notify:	OPP_EVENT_REMOVE notification should be sent or not
+ *
+ * This function removes an opp definition from the opp list.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * It is assumed that the caller holds required mutex for an RCU updater
+ * strategy.
+ */
+static void _opp_remove(struct device_opp *dev_opp,
+			struct dev_pm_opp *opp, bool notify)
+{
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	if (notify)
+		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+	list_del_rcu(&opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+
+	_remove_device_opp(dev_opp);
+}
+
+/**
+ * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * @dev:	device for which we do this operation
+ * @freq:	OPP to remove with matching 'freq'
+ *
+ * This function removes an opp from the opp list.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+{
+	struct dev_pm_opp *opp;
+	struct device_opp *dev_opp;
+	bool found = false;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		goto unlock;
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->rate == freq) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
+			 __func__, freq);
+		goto unlock;
+	}
+
+	_opp_remove(dev_opp, opp, true);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
+static struct dev_pm_opp *_allocate_opp(struct device *dev,
+					struct device_opp **dev_opp)
+{
+	struct dev_pm_opp *opp;
+
+	/* allocate new OPP node */
+	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
+	if (!opp)
+		return NULL;
+
+	INIT_LIST_HEAD(&opp->node);
+
+	*dev_opp = _add_device_opp(dev);
+	if (!*dev_opp) {
+		kfree(opp);
+		return NULL;
+	}
+
+	return opp;
+}
+
+static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+		    struct device_opp *dev_opp)
+{
+	struct dev_pm_opp *opp;
+	struct list_head *head = &dev_opp->opp_list;
+
+	/*
+	 * Insert new OPP in order of increasing frequency and discard if
+	 * already present.
+	 *
+	 * Need to use &dev_opp->opp_list in the condition part of the 'for'
+	 * loop, don't replace it with head otherwise it will become an infinite
+	 * loop.
+	 */
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate > opp->rate) {
+			head = &opp->node;
+			continue;
+		}
+
+		if (new_opp->rate < opp->rate)
+			break;
+
+		/* Duplicate OPPs */
+		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
+			 __func__, opp->rate, opp->u_volt, opp->available,
+			 new_opp->rate, new_opp->u_volt, new_opp->available);
+
+		return opp->available && new_opp->u_volt == opp->u_volt ?
+			0 : -EEXIST;
+	}
+
+	new_opp->dev_opp = dev_opp;
+	list_add_rcu(&new_opp->node, head);
+
+	return 0;
+}
+
+/**
  * _opp_add_dynamic() - Allocate a dynamic OPP.
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
@@ -467,64 +819,29 @@ static struct device_opp *_add_device_opp(struct device *dev)
 static int _opp_add_dynamic(struct device *dev, unsigned long freq,
 			    long u_volt, bool dynamic)
 {
-	struct device_opp *dev_opp = NULL;
-	struct dev_pm_opp *opp, *new_opp;
-	struct list_head *head;
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
 	int ret;
 
-	/* allocate new OPP node */
-	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);
 
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
 	/* populate the opp table */
 	new_opp->rate = freq;
 	new_opp->u_volt = u_volt;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_opp = _add_device_opp(dev);
-		if (!dev_opp) {
-			ret = -ENOMEM;
-			goto free_opp;
-		}
-
-		head = &dev_opp->opp_list;
-		goto list_add;
-	}
-
-	/*
-	 * Insert new OPP in order of increasing frequency
-	 * and discard if already present
-	 */
-	head = &dev_opp->opp_list;
-	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
-		if (new_opp->rate <= opp->rate)
-			break;
-		else
-			head = &opp->node;
-	}
-
-	/* Duplicate OPPs ? */
-	if (new_opp->rate == opp->rate) {
-		ret = opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
-
-		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
-			 __func__, opp->rate, opp->u_volt, opp->available,
-			 new_opp->rate, new_opp->u_volt, new_opp->available);
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
 		goto free_opp;
-	}
 
-list_add:
-	new_opp->dev_opp = dev_opp;
-	list_add_rcu(&new_opp->node, head);
 	mutex_unlock(&dev_opp_list_lock);
 
 	/*
@@ -535,20 +852,52 @@ list_add:
 	return 0;
 
 free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
 	mutex_unlock(&dev_opp_list_lock);
-	kfree(new_opp);
 	return ret;
 }
 
+/* TODO: Support multiple regulators */
+static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev)
+{
+	u32 microvolt[3] = {0};
+	int count, ret;
+
+	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+	if (!count)
+		return 0;
+
+	/* There can be one or three elements here */
+	if (count != 1 && count != 3) {
+		dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
+			__func__, count);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_array(opp->np, "opp-microvolt", microvolt,
+					 count);
+	if (ret) {
+		dev_err(dev, "%s: error parsing opp-microvolt: %d\n", __func__,
+			ret);
+		return -EINVAL;
+	}
+
+	opp->u_volt = microvolt[0];
+	opp->u_volt_min = microvolt[1];
+	opp->u_volt_max = microvolt[2];
+
+	return 0;
+}
+
 /**
- * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
  * @dev:	device for which we do this operation
- * @freq:	Frequency in Hz for this OPP
- * @u_volt:	Voltage in uVolts for this OPP
+ * @np:		device node
  *
- * This function adds an opp definition to the opp list and returns status.
- * The opp is made available by default and it can be controlled using
- * dev_pm_opp_enable/disable functions.
+ * This function adds an opp definition to the opp list and returns status. The
+ * opp can be controlled using dev_pm_opp_enable/disable functions and may be
+ * removed by dev_pm_opp_remove.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -562,108 +911,119 @@ free_opp:
  * -EEXIST	Freq are same and volt are different OR
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
+ * -EINVAL	Failed parsing the OPP node
  */
-int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 {
-	return _opp_add_dynamic(dev, freq, u_volt, true);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
 
-/**
- * _kfree_opp_rcu() - Free OPP RCU handler
- * @head:	RCU head
- */
-static void _kfree_opp_rcu(struct rcu_head *head)
-{
-	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
 
-	kfree_rcu(opp, rcu_head);
-}
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
 
-/**
- * _kfree_device_rcu() - Free device_opp RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
-{
-	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+	ret = of_property_read_u64(np, "opp-hz", &rate);
+	if (ret < 0) {
+		dev_err(dev, "%s: opp-hz not found\n", __func__);
+		goto free_opp;
+	}
 
-	kfree_rcu(device_opp, rcu_head);
-}
+	/*
+	 * Rate is defined as an unsigned long in clk API, and so casting
+	 * explicitly to its type. Must be fixed once rate is 64 bit
+	 * guaranteed in clk API.
+	 */
+	new_opp->rate = (unsigned long)rate;
+	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
+
+	new_opp->np = np;
+	new_opp->dynamic = false;
+	new_opp->available = true;
+
+	if (!of_property_read_u32(np, "clock-latency-ns", &val))
+		new_opp->clock_latency_ns = val;
+
+	ret = opp_get_microvolt(new_opp, dev);
+	if (ret)
+		goto free_opp;
+
+	if (!of_property_read_u32(new_opp->np, "opp-microamp", &val))
+		new_opp->u_amp = val;
+
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (dev_opp->suspend_opp)
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, dev_opp->suspend_opp->rate,
+				 new_opp->rate);
+		else
+			dev_opp->suspend_opp = new_opp;
+	}
+
+	if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max)
+		dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	mutex_unlock(&dev_opp_list_lock);
+
+	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
+		 __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt,
+		 new_opp->u_volt_min, new_opp->u_volt_max,
+		 new_opp->clock_latency_ns);
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @dev_opp:	points back to the device_opp struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- *
- * This function removes an opp definition from the opp list.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * It is assumed that the caller holds required mutex for an RCU updater
- * strategy.
- */
-static void _opp_remove(struct device_opp *dev_opp,
-			struct dev_pm_opp *opp)
-{
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
 
-	if (list_empty(&dev_opp->opp_list)) {
-		list_del_rcu(&dev_opp->node);
-		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
-			  _kfree_device_rcu);
-	}
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	return ret;
 }
 
 /**
- * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
- * @freq:	OPP to remove with matching 'freq'
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
  *
- * This function removes an opp from the opp list.
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
  */
-void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
-	struct dev_pm_opp *opp;
-	struct device_opp *dev_opp;
-	bool found = false;
-
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
-
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
-		goto unlock;
-
-	list_for_each_entry(opp, &dev_opp->opp_list, node) {
-		if (opp->rate == freq) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
-			 __func__, freq);
-		goto unlock;
-	}
-
-	_opp_remove(dev_opp, opp);
-unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	return _opp_add_dynamic(dev, freq, u_volt, true);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
 /**
  * _opp_set_availability() - helper to set the availability of an opp
@@ -825,28 +1185,179 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
 #ifdef CONFIG_OF
 /**
- * of_init_opp_table() - Initialize opp table from device tree
+ * of_free_opp_table() - Free OPP table entries created from static DT entries
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Register the initial OPP table with the OPP library for given device.
+ * Free OPPs created using static entries present in DT.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
- *
- * Return:
- * 0		On success OR
- *		Duplicate OPPs (both freq and volt are same) and opp->available
- * -EEXIST	Freq are same and volt are different OR
- *		Duplicate OPPs (both freq and volt are same) and !opp->available
- * -ENOMEM	Memory allocation failure
- * -ENODEV	when 'operating-points' property is not found or is invalid data
- *		in device node.
- * -ENODATA	when empty 'operating-points' property is found
  */
-int of_init_opp_table(struct device *dev)
+void of_free_opp_table(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int error = PTR_ERR(dev_opp);
+
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
+		goto unlock;
+	}
+
+	/* Find if dev_opp manages a single device */
+	if (list_is_singular(&dev_opp->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+			if (!opp->dynamic)
+				_opp_remove(dev_opp, opp, true);
+		}
+	} else {
+		_remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp);
+	}
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_free_opp_table);
+
+void of_cpumask_free_opp_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		of_free_opp_table(cpu_dev);
+	}
+}
+EXPORT_SYMBOL_GPL(of_cpumask_free_opp_table);
+
+/* Returns opp descriptor node from its phandle. Caller must do of_node_put() */
+static struct device_node *
+_of_get_opp_desc_node_from_prop(struct device *dev, const struct property *prop)
+{
+	struct device_node *opp_np;
+
+	opp_np = of_find_node_by_phandle(be32_to_cpup(prop->value));
+	if (!opp_np) {
+		dev_err(dev, "%s: Prop: %s contains invalid opp desc phandle\n",
+			__func__, prop->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return opp_np;
+}
+
+/* Returns opp descriptor node for a device. Caller must do of_node_put() */
+static struct device_node *_of_get_opp_desc_node(struct device *dev)
+{
+	const struct property *prop;
+
+	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
+	if (!prop)
+		return ERR_PTR(-ENODEV);
+	if (!prop->value)
+		return ERR_PTR(-ENODATA);
+
+	/*
+	 * TODO: Support for multiple OPP tables.
+	 *
+	 * There should be only ONE phandle present in "operating-points-v2"
+	 * property.
+	 */
+	if (prop->length != sizeof(__be32)) {
+		dev_err(dev, "%s: Invalid opp desc phandle\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return _of_get_opp_desc_node_from_prop(dev, prop);
+}
+
+/* Initializes OPP tables based on new bindings */
+static int _of_init_opp_table_v2(struct device *dev,
+				 const struct property *prop)
+{
+	struct device_node *opp_np, *np;
+	struct device_opp *dev_opp;
+	int ret = 0, count = 0;
+
+	if (!prop->value)
+		return -ENODATA;
+
+	/* Get opp node */
+	opp_np = _of_get_opp_desc_node_from_prop(dev, prop);
+	if (IS_ERR(opp_np))
+		return PTR_ERR(opp_np);
+
+	dev_opp = _managed_opp(opp_np);
+	if (dev_opp) {
+		/* OPPs are already managed */
+		if (!_add_list_dev(dev, dev_opp))
+			ret = -ENOMEM;
+		goto put_opp_np;
+	}
+
+	/* We have opp-list node now, iterate over it and add OPPs */
+	for_each_available_child_of_node(opp_np, np) {
+		count++;
+
+		ret = _opp_add_static_v2(dev, np);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
+				ret);
+			goto free_table;
+		}
+	}
+
+	/* There should be one of more OPP defined */
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_np;
+	}
+
+	dev_opp = _find_device_opp(dev);
+	if (WARN_ON(IS_ERR(dev_opp))) {
+		ret = PTR_ERR(dev_opp);
+		goto free_table;
+	}
+
+	dev_opp->np = opp_np;
+	dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+
+	of_node_put(opp_np);
+	return 0;
+
+free_table:
+	of_free_opp_table(dev);
+put_opp_np:
+	of_node_put(opp_np);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on old-deprecated bindings */
+static int _of_init_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
@@ -881,47 +1392,177 @@ int of_init_opp_table(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_init_opp_table);
 
 /**
- * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * of_init_opp_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Free OPPs created using static entries present in DT.
+ * Register the initial OPP table with the OPP library for given device.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
  */
-void of_free_opp_table(struct device *dev)
+int of_init_opp_table(struct device *dev)
+{
+	const struct property *prop;
+
+	/*
+	 * OPPs have two version of bindings now. The older one is deprecated,
+	 * try for the new binding first.
+	 */
+	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
+	if (!prop) {
+		/*
+		 * Try old-deprecated bindings for backward compatibility with
+		 * older dtbs.
+		 */
+		return _of_init_opp_table_v1(dev);
+	}
+
+	return _of_init_opp_table_v2(dev, prop);
+}
+EXPORT_SYMBOL_GPL(of_init_opp_table);
+
+int of_cpumask_init_opp_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu, ret = 0;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		ret = of_init_opp_table(cpu_dev);
+		if (ret) {
+			pr_err("%s: couldn't find opp table for cpu:%d, %d\n",
+			       __func__, cpu, ret);
+
+			/* Free all other OPPs */
+			of_cpumask_free_opp_table(cpumask);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_cpumask_init_opp_table);
+
+/* Required only for V1 bindings, as v2 can manage it from DT itself */
+int set_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
 {
+	struct device_list_opp *list_dev;
 	struct device_opp *dev_opp;
-	struct dev_pm_opp *opp, *tmp;
+	struct device *dev;
+	int cpu, ret = 0;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(cpu_dev);
 	if (IS_ERR(dev_opp)) {
-		int error = PTR_ERR(dev_opp);
-		if (error != -ENODEV)
-			WARN(1, "%s: dev_opp: %d\n",
-			     IS_ERR_OR_NULL(dev) ?
-					"Invalid device" : dev_name(dev),
-			     error);
-		return;
+		ret = -EINVAL;
+		goto out_rcu_read_unlock;
 	}
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	for_each_cpu(cpu, cpumask) {
+		if (cpu == cpu_dev->id)
+			continue;
 
-	/* Free static OPPs */
-	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
-		if (!opp->dynamic)
-			_opp_remove(dev_opp, opp);
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+
+		list_dev = _add_list_dev(dev, dev_opp);
+		if (!list_dev) {
+			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
 	}
+out_rcu_read_unlock:
+	rcu_read_unlock();
 
-	mutex_unlock(&dev_opp_list_lock);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(of_free_opp_table);
+EXPORT_SYMBOL_GPL(set_cpus_sharing_opps);
+
+/*
+ * Works only for OPP v2 bindings.
+ *
+ * cpumask should be already set to mask of cpu_dev->id.
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+int of_get_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_node *np, *tmp_np;
+	struct device *tcpu_dev;
+	int cpu, ret = 0;
+
+	/* Get OPP descriptor node */
+	np = _of_get_opp_desc_node(cpu_dev);
+	if (IS_ERR(np)) {
+		dev_dbg(cpu_dev, "%s: Couldn't find opp node: %ld\n", __func__,
+			PTR_ERR(np));
+		return -ENOENT;
+	}
+
+	/* OPPs are shared ? */
+	if (!of_property_read_bool(np, "opp-shared"))
+		goto put_cpu_node;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			ret = -ENODEV;
+			goto put_cpu_node;
+		}
+
+		/* Get OPP descriptor node */
+		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		if (IS_ERR(tmp_np)) {
+			dev_err(tcpu_dev, "%s: Couldn't find opp node: %ld\n",
+				__func__, PTR_ERR(tmp_np));
+			ret = PTR_ERR(tmp_np);
+			goto put_cpu_node;
+		}
+
+		/* CPUs are sharing opp node */
+		if (np == tmp_np)
+			cpumask_set_cpu(cpu, cpumask);
+
+		of_node_put(tmp_np);
+	}
+
+put_cpu_node:
+	of_node_put(np);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_get_cpus_sharing_opps);
 #endif
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index f1a5d95e7b20..998fa6b23084 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -73,6 +73,8 @@ extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
 extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
 extern int pm_qos_sysfs_add_flags(struct device *dev);
 extern void pm_qos_sysfs_remove_flags(struct device *dev);
+extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev);
+extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev);
 
 #else /* CONFIG_PM */
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index e56d538d039e..7f3646e459cb 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -883,3 +883,40 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
+
+/**
+ * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace
+ * @dev: Device whose latency tolerance to expose
+ */
+int dev_pm_qos_expose_latency_tolerance(struct device *dev)
+{
+	int ret;
+
+	if (!dev->power.set_latency_tolerance)
+		return -EINVAL;
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	ret = pm_qos_sysfs_add_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance);
+
+/**
+ * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace
+ * @dev: Device whose latency tolerance to hide
+ */
+void dev_pm_qos_hide_latency_tolerance(struct device *dev)
+{
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	pm_qos_sysfs_remove_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	/* Remove the request from user space now */
+	pm_runtime_get_sync(dev);
+	dev_pm_qos_update_user_latency_tolerance(dev,
+		PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT);
+	pm_runtime_put(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance);
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index d2be3f9c211c..a7b46798c81d 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -738,6 +738,17 @@ void pm_qos_sysfs_remove_flags(struct device *dev)
 	sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group);
 }
 
+int pm_qos_sysfs_add_latency_tolerance(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj,
+				 &pm_qos_latency_tolerance_attr_group);
+}
+
+void pm_qos_sysfs_remove_latency_tolerance(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
+}
+
 void rpm_sysfs_remove(struct device *dev)
 {
 	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 7470004ca810..eb6e67451dec 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -45,14 +45,12 @@ static int dev_pm_attach_wake_irq(struct device *dev, int irq,
 		return -EEXIST;
 	}
 
-	dev->power.wakeirq = wirq;
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-
 	err = device_wakeup_attach_irq(dev, wirq);
-	if (err)
-		return err;
+	if (!err)
+		dev->power.wakeirq = wirq;
 
-	return 0;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+	return err;
 }
 
 /**
@@ -105,10 +103,10 @@ void dev_pm_clear_wake_irq(struct device *dev)
 		return;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
+	device_wakeup_detach_irq(dev);
 	dev->power.wakeirq = NULL;
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	device_wakeup_detach_irq(dev);
 	if (wirq->dedicated_irq)
 		free_irq(wirq->irq, wirq);
 	kfree(wirq);
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 40f71603378c..51f15bc15774 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -281,32 +281,25 @@ EXPORT_SYMBOL_GPL(device_wakeup_enable);
  * Attach a device wakeirq to the wakeup source so the device
  * wake IRQ can be configured automatically for suspend and
  * resume.
+ *
+ * Call under the device's power.lock lock.
  */
 int device_wakeup_attach_irq(struct device *dev,
 			     struct wake_irq *wakeirq)
 {
 	struct wakeup_source *ws;
-	int ret = 0;
 
-	spin_lock_irq(&dev->power.lock);
 	ws = dev->power.wakeup;
 	if (!ws) {
 		dev_err(dev, "forgot to call call device_init_wakeup?\n");
-		ret = -EINVAL;
-		goto unlock;
+		return -EINVAL;
 	}
 
-	if (ws->wakeirq) {
-		ret = -EEXIST;
-		goto unlock;
-	}
+	if (ws->wakeirq)
+		return -EEXIST;
 
 	ws->wakeirq = wakeirq;
-
-unlock:
-	spin_unlock_irq(&dev->power.lock);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -314,20 +307,16 @@ unlock:
  * @dev: Device to handle
  *
  * Removes a device wakeirq from the wakeup source.
+ *
+ * Call under the device's power.lock lock.
  */
 void device_wakeup_detach_irq(struct device *dev)
 {
 	struct wakeup_source *ws;
 
-	spin_lock_irq(&dev->power.lock);
 	ws = dev->power.wakeup;
-	if (!ws)
-		goto unlock;
-
-	ws->wakeirq = NULL;
-
-unlock:
-	spin_unlock_irq(&dev->power.lock);
+	if (ws)
+		ws->wakeirq = NULL;
 }
 
 /**
diff --git a/drivers/base/property.c b/drivers/base/property.c
index f3f6d167f3f1..ff03f2348f77 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -16,6 +16,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/property.h>
+#include <linux/etherdevice.h>
+#include <linux/phy.h>
 
 /**
  * device_add_property_set - Add a collection of properties to a device object.
@@ -27,9 +29,10 @@
  */
 void device_add_property_set(struct device *dev, struct property_set *pset)
 {
-	if (pset)
-		pset->fwnode.type = FWNODE_PDATA;
+	if (!pset)
+		return;
 
+	pset->fwnode.type = FWNODE_PDATA;
 	set_secondary_fwnode(dev, &pset->fwnode);
 }
 EXPORT_SYMBOL_GPL(device_add_property_set);
@@ -153,6 +156,7 @@ EXPORT_SYMBOL_GPL(fwnode_property_present);
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO if the property is not an array of numbers,
  *	   %-EOVERFLOW if the size of the property is not as expected.
+ *	   %-ENXIO if no suitable firmware interface is present.
  */
 int device_property_read_u8_array(struct device *dev, const char *propname,
 				  u8 *val, size_t nval)
@@ -177,6 +181,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u8_array);
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO if the property is not an array of numbers,
  *	   %-EOVERFLOW if the size of the property is not as expected.
+ *	   %-ENXIO if no suitable firmware interface is present.
  */
 int device_property_read_u16_array(struct device *dev, const char *propname,
 				   u16 *val, size_t nval)
@@ -201,6 +206,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u16_array);
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO if the property is not an array of numbers,
  *	   %-EOVERFLOW if the size of the property is not as expected.
+ *	   %-ENXIO if no suitable firmware interface is present.
  */
 int device_property_read_u32_array(struct device *dev, const char *propname,
 				   u32 *val, size_t nval)
@@ -225,6 +231,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u32_array);
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO if the property is not an array of numbers,
  *	   %-EOVERFLOW if the size of the property is not as expected.
+ *	   %-ENXIO if no suitable firmware interface is present.
  */
 int device_property_read_u64_array(struct device *dev, const char *propname,
 				   u64 *val, size_t nval)
@@ -249,6 +256,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u64_array);
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO or %-EILSEQ if the property is not an array of strings,
  *	   %-EOVERFLOW if the size of the property is not as expected.
+ *	   %-ENXIO if no suitable firmware interface is present.
  */
 int device_property_read_string_array(struct device *dev, const char *propname,
 				      const char **val, size_t nval)
@@ -270,6 +278,7 @@ EXPORT_SYMBOL_GPL(device_property_read_string_array);
  *	   %-EINVAL if given arguments are not valid,
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO or %-EILSEQ if the property type is not a string.
+ *	   %-ENXIO if no suitable firmware interface is present.
  */
 int device_property_read_string(struct device *dev, const char *propname,
 				const char **val)
@@ -291,9 +300,11 @@ EXPORT_SYMBOL_GPL(device_property_read_string);
 	else if (is_acpi_node(_fwnode_)) \
 		_ret_ = acpi_dev_prop_read(to_acpi_node(_fwnode_), _propname_, \
 					   _proptype_, _val_, _nval_); \
-	else \
+	else if (is_pset(_fwnode_)) \
 		_ret_ = pset_prop_read_array(to_pset(_fwnode_), _propname_, \
 					     _proptype_, _val_, _nval_); \
+	else \
+		_ret_ = -ENXIO; \
 	_ret_; \
 })
 
@@ -431,9 +442,10 @@ int fwnode_property_read_string_array(struct fwnode_handle *fwnode,
 	else if (is_acpi_node(fwnode))
 		return acpi_dev_prop_read(to_acpi_node(fwnode), propname,
 					  DEV_PROP_STRING, val, nval);
-
-	return pset_prop_read_array(to_pset(fwnode), propname,
-				    DEV_PROP_STRING, val, nval);
+	else if (is_pset(fwnode))
+		return pset_prop_read_array(to_pset(fwnode), propname,
+					    DEV_PROP_STRING, val, nval);
+	return -ENXIO;
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_string_array);
 
@@ -461,7 +473,8 @@ int fwnode_property_read_string(struct fwnode_handle *fwnode,
 		return acpi_dev_prop_read(to_acpi_node(fwnode), propname,
 					  DEV_PROP_STRING, val, 1);
 
-	return -ENXIO;
+	return pset_prop_read_array(to_pset(fwnode), propname,
+				    DEV_PROP_STRING, val, 1);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_string);
 
@@ -533,3 +546,79 @@ bool device_dma_is_coherent(struct device *dev)
 	return coherent;
 }
 EXPORT_SYMBOL_GPL(device_dma_is_coherent);
+
+/**
+ * device_get_phy_mode - Get phy mode for given device
+ * @dev:	Pointer to the given device
+ *
+ * The function gets phy interface string from property 'phy-mode' or
+ * 'phy-connection-type', and return its index in phy_modes table, or errno in
+ * error case.
+ */
+int device_get_phy_mode(struct device *dev)
+{
+	const char *pm;
+	int err, i;
+
+	err = device_property_read_string(dev, "phy-mode", &pm);
+	if (err < 0)
+		err = device_property_read_string(dev,
+						  "phy-connection-type", &pm);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++)
+		if (!strcasecmp(pm, phy_modes(i)))
+			return i;
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(device_get_phy_mode);
+
+static void *device_get_mac_addr(struct device *dev,
+				 const char *name, char *addr,
+				 int alen)
+{
+	int ret = device_property_read_u8_array(dev, name, addr, alen);
+
+	if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr))
+		return addr;
+	return NULL;
+}
+
+/**
+ * device_get_mac_address - Get the MAC for a given device
+ * @dev:	Pointer to the device
+ * @addr:	Address of buffer to store the MAC in
+ * @alen:	Length of the buffer pointed to by addr, should be ETH_ALEN
+ *
+ * Search the firmware node for the best MAC address to use.  'mac-address' is
+ * checked first, because that is supposed to contain to "most recent" MAC
+ * address. If that isn't set, then 'local-mac-address' is checked next,
+ * because that is the default address.  If that isn't set, then the obsolete
+ * 'address' is checked, just in case we're using an old device tree.
+ *
+ * Note that the 'address' property is supposed to contain a virtual address of
+ * the register set, but some DTS files have redefined that property to be the
+ * MAC address.
+ *
+ * All-zero MAC addresses are rejected, because those could be properties that
+ * exist in the firmware tables, but were not updated by the firmware.  For
+ * example, the DTS could define 'mac-address' and 'local-mac-address', with
+ * zero MAC addresses.  Some older U-Boots only initialized 'local-mac-address'.
+ * In this case, the real MAC is in 'local-mac-address', and 'mac-address'
+ * exists but is all zeros.
+*/
+void *device_get_mac_address(struct device *dev, char *addr, int alen)
+{
+	addr = device_get_mac_addr(dev, "mac-address", addr, alen);
+	if (addr)
+		return addr;
+
+	addr = device_get_mac_addr(dev, "local-mac-address", addr, alen);
+	if (addr)
+		return addr;
+
+	return device_get_mac_addr(dev, "address", addr, alen);
+}
+EXPORT_SYMBOL(device_get_mac_address);
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index b2b2849fc6d3..873ddf91c9d3 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -136,7 +136,7 @@ struct regmap {
 	/* if set, the HW registers are known to match map->reg_defaults */
 	bool no_sync_defaults;
 
-	struct reg_default *patch;
+	struct reg_sequence *patch;
 	int patch_regs;
 
 	/* if set, converts bulk rw to single rw */
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 81751a49d8bf..56486d92c4e7 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -296,11 +296,20 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
 	if (!blk)
 		return -ENOMEM;
 
-	present = krealloc(rbnode->cache_present,
-		    BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL);
-	if (!present) {
-		kfree(blk);
-		return -ENOMEM;
+	if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) {
+		present = krealloc(rbnode->cache_present,
+				   BITS_TO_LONGS(blklen) * sizeof(*present),
+				   GFP_KERNEL);
+		if (!present) {
+			kfree(blk);
+			return -ENOMEM;
+		}
+
+		memset(present + BITS_TO_LONGS(rbnode->blklen), 0,
+		       (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen))
+		       * sizeof(*present));
+	} else {
+		present = rbnode->cache_present;
 	}
 
 	/* insert the register value in the correct place in the rbnode block */
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 7111d04f2621..0a849eeaf952 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -34,7 +34,7 @@
 
 static int _regmap_update_bits(struct regmap *map, unsigned int reg,
 			       unsigned int mask, unsigned int val,
-			       bool *change);
+			       bool *change, bool force_write);
 
 static int _regmap_bus_reg_read(void *context, unsigned int reg,
 				unsigned int *val);
@@ -1178,7 +1178,7 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg,
 		ret = _regmap_update_bits(map, range->selector_reg,
 					  range->selector_mask,
 					  win_page << range->selector_shift,
-					  &page_chg);
+					  &page_chg, false);
 
 		map->work_buf = orig_work_buf;
 
@@ -1624,6 +1624,18 @@ int regmap_fields_write(struct regmap_field *field, unsigned int id,
 }
 EXPORT_SYMBOL_GPL(regmap_fields_write);
 
+int regmap_fields_force_write(struct regmap_field *field, unsigned int id,
+			unsigned int val)
+{
+	if (id >= field->id_size)
+		return -EINVAL;
+
+	return regmap_write_bits(field->regmap,
+				  field->reg + (field->id_offset * id),
+				  field->mask, val << field->shift);
+}
+EXPORT_SYMBOL_GPL(regmap_fields_force_write);
+
 /**
  * regmap_fields_update_bits():	Perform a read/modify/write cycle
  *                              on the register field
@@ -1743,7 +1755,7 @@ EXPORT_SYMBOL_GPL(regmap_bulk_write);
  * relative. The page register has been written if that was neccessary.
  */
 static int _regmap_raw_multi_reg_write(struct regmap *map,
-				       const struct reg_default *regs,
+				       const struct reg_sequence *regs,
 				       size_t num_regs)
 {
 	int ret;
@@ -1800,12 +1812,12 @@ static unsigned int _regmap_register_page(struct regmap *map,
 }
 
 static int _regmap_range_multi_paged_reg_write(struct regmap *map,
-					       struct reg_default *regs,
+					       struct reg_sequence *regs,
 					       size_t num_regs)
 {
 	int ret;
 	int i, n;
-	struct reg_default *base;
+	struct reg_sequence *base;
 	unsigned int this_page = 0;
 	/*
 	 * the set of registers are not neccessarily in order, but
@@ -1843,7 +1855,7 @@ static int _regmap_range_multi_paged_reg_write(struct regmap *map,
 }
 
 static int _regmap_multi_reg_write(struct regmap *map,
-				   const struct reg_default *regs,
+				   const struct reg_sequence *regs,
 				   size_t num_regs)
 {
 	int i;
@@ -1895,8 +1907,8 @@ static int _regmap_multi_reg_write(struct regmap *map,
 		struct regmap_range_node *range;
 		range = _regmap_range_lookup(map, reg);
 		if (range) {
-			size_t len = sizeof(struct reg_default)*num_regs;
-			struct reg_default *base = kmemdup(regs, len,
+			size_t len = sizeof(struct reg_sequence)*num_regs;
+			struct reg_sequence *base = kmemdup(regs, len,
 							   GFP_KERNEL);
 			if (!base)
 				return -ENOMEM;
@@ -1929,7 +1941,7 @@ static int _regmap_multi_reg_write(struct regmap *map,
  * A value of zero will be returned on success, a negative errno will be
  * returned in error cases.
  */
-int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs,
+int regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs,
 			   int num_regs)
 {
 	int ret;
@@ -1962,7 +1974,7 @@ EXPORT_SYMBOL_GPL(regmap_multi_reg_write);
  * be returned in error cases.
  */
 int regmap_multi_reg_write_bypassed(struct regmap *map,
-				    const struct reg_default *regs,
+				    const struct reg_sequence *regs,
 				    int num_regs)
 {
 	int ret;
@@ -2327,7 +2339,7 @@ EXPORT_SYMBOL_GPL(regmap_bulk_read);
 
 static int _regmap_update_bits(struct regmap *map, unsigned int reg,
 			       unsigned int mask, unsigned int val,
-			       bool *change)
+			       bool *change, bool force_write)
 {
 	int ret;
 	unsigned int tmp, orig;
@@ -2339,7 +2351,7 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg,
 	tmp = orig & ~mask;
 	tmp |= val & mask;
 
-	if (tmp != orig) {
+	if (force_write || (tmp != orig)) {
 		ret = _regmap_write(map, reg, tmp);
 		if (change)
 			*change = true;
@@ -2367,7 +2379,7 @@ int regmap_update_bits(struct regmap *map, unsigned int reg,
 	int ret;
 
 	map->lock(map->lock_arg);
-	ret = _regmap_update_bits(map, reg, mask, val, NULL);
+	ret = _regmap_update_bits(map, reg, mask, val, NULL, false);
 	map->unlock(map->lock_arg);
 
 	return ret;
@@ -2375,6 +2387,29 @@ int regmap_update_bits(struct regmap *map, unsigned int reg,
 EXPORT_SYMBOL_GPL(regmap_update_bits);
 
 /**
+ * regmap_write_bits: Perform a read/modify/write cycle on the register map
+ *
+ * @map: Register map to update
+ * @reg: Register to update
+ * @mask: Bitmask to change
+ * @val: New value for bitmask
+ *
+ * Returns zero for success, a negative number on error.
+ */
+int regmap_write_bits(struct regmap *map, unsigned int reg,
+		      unsigned int mask, unsigned int val)
+{
+	int ret;
+
+	map->lock(map->lock_arg);
+	ret = _regmap_update_bits(map, reg, mask, val, NULL, true);
+	map->unlock(map->lock_arg);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_write_bits);
+
+/**
  * regmap_update_bits_async: Perform a read/modify/write cycle on the register
  *                           map asynchronously
  *
@@ -2398,7 +2433,7 @@ int regmap_update_bits_async(struct regmap *map, unsigned int reg,
 
 	map->async = true;
 
-	ret = _regmap_update_bits(map, reg, mask, val, NULL);
+	ret = _regmap_update_bits(map, reg, mask, val, NULL, false);
 
 	map->async = false;
 
@@ -2427,7 +2462,7 @@ int regmap_update_bits_check(struct regmap *map, unsigned int reg,
 	int ret;
 
 	map->lock(map->lock_arg);
-	ret = _regmap_update_bits(map, reg, mask, val, change);
+	ret = _regmap_update_bits(map, reg, mask, val, change, false);
 	map->unlock(map->lock_arg);
 	return ret;
 }
@@ -2460,7 +2495,7 @@ int regmap_update_bits_check_async(struct regmap *map, unsigned int reg,
 
 	map->async = true;
 
-	ret = _regmap_update_bits(map, reg, mask, val, change);
+	ret = _regmap_update_bits(map, reg, mask, val, change, false);
 
 	map->async = false;
 
@@ -2552,10 +2587,10 @@ EXPORT_SYMBOL_GPL(regmap_async_complete);
  * The caller must ensure that this function cannot be called
  * concurrently with either itself or regcache_sync().
  */
-int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
+int regmap_register_patch(struct regmap *map, const struct reg_sequence *regs,
 			  int num_regs)
 {
-	struct reg_default *p;
+	struct reg_sequence *p;
 	int ret;
 	bool bypass;
 
@@ -2564,7 +2599,7 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 		return 0;
 
 	p = krealloc(map->patch,
-		     sizeof(struct reg_default) * (map->patch_regs + num_regs),
+		     sizeof(struct reg_sequence) * (map->patch_regs + num_regs),
 		     GFP_KERNEL);
 	if (p) {
 		memcpy(p + map->patch_regs, regs, num_regs * sizeof(*regs));
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index be5fffb6da24..023d448ed3fa 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -92,7 +92,7 @@ config BCMA_DRIVER_GMAC_CMN
 config BCMA_DRIVER_GPIO
 	bool "BCMA GPIO driver"
 	depends on BCMA && GPIOLIB
-	select IRQ_DOMAIN if BCMA_HOST_SOC
+	select GPIOLIB_IRQCHIP if BCMA_HOST_SOC
 	help
 	  Driver to provide access to the GPIO pins of the bcma bus.
 
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 15f2b2e242ea..38f156745d53 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -34,6 +34,7 @@ int __init bcma_bus_early_register(struct bcma_bus *bus);
 int bcma_bus_suspend(struct bcma_bus *bus);
 int bcma_bus_resume(struct bcma_bus *bus);
 #endif
+struct device *bcma_bus_get_host_dev(struct bcma_bus *bus);
 
 /* scan.c */
 void bcma_detect_chip(struct bcma_bus *bus);
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 5f6018e7cd4c..504899a72966 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -8,10 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
-#include <linux/gpio.h>
-#include <linux/irq.h>
+#include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
-#include <linux/irqdomain.h>
 #include <linux/export.h>
 #include <linux/bcma/bcma.h>
 
@@ -79,19 +77,11 @@ static void bcma_gpio_free(struct gpio_chip *chip, unsigned gpio)
 }
 
 #if IS_BUILTIN(CONFIG_BCM47XX) || IS_BUILTIN(CONFIG_ARCH_BCM_5301X)
-static int bcma_gpio_to_irq(struct gpio_chip *chip, unsigned gpio)
-{
-	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
-
-	if (cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC)
-		return irq_find_mapping(cc->irq_domain, gpio);
-	else
-		return -EINVAL;
-}
 
 static void bcma_gpio_irq_unmask(struct irq_data *d)
 {
-	struct bcma_drv_cc *cc = irq_data_get_irq_chip_data(d);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(gc);
 	int gpio = irqd_to_hwirq(d);
 	u32 val = bcma_chipco_gpio_in(cc, BIT(gpio));
 
@@ -101,7 +91,8 @@ static void bcma_gpio_irq_unmask(struct irq_data *d)
 
 static void bcma_gpio_irq_mask(struct irq_data *d)
 {
-	struct bcma_drv_cc *cc = irq_data_get_irq_chip_data(d);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(gc);
 	int gpio = irqd_to_hwirq(d);
 
 	bcma_chipco_gpio_intmask(cc, BIT(gpio), 0);
@@ -116,6 +107,7 @@ static struct irq_chip bcma_gpio_irq_chip = {
 static irqreturn_t bcma_gpio_irq_handler(int irq, void *dev_id)
 {
 	struct bcma_drv_cc *cc = dev_id;
+	struct gpio_chip *gc = &cc->gpio;
 	u32 val = bcma_cc_read32(cc, BCMA_CC_GPIOIN);
 	u32 mask = bcma_cc_read32(cc, BCMA_CC_GPIOIRQ);
 	u32 pol = bcma_cc_read32(cc, BCMA_CC_GPIOPOL);
@@ -125,81 +117,58 @@ static irqreturn_t bcma_gpio_irq_handler(int irq, void *dev_id)
 	if (!irqs)
 		return IRQ_NONE;
 
-	for_each_set_bit(gpio, &irqs, cc->gpio.ngpio)
-		generic_handle_irq(bcma_gpio_to_irq(&cc->gpio, gpio));
+	for_each_set_bit(gpio, &irqs, gc->ngpio)
+		generic_handle_irq(irq_find_mapping(gc->irqdomain, gpio));
 	bcma_chipco_gpio_polarity(cc, irqs, val & irqs);
 
 	return IRQ_HANDLED;
 }
 
-static int bcma_gpio_irq_domain_init(struct bcma_drv_cc *cc)
+static int bcma_gpio_irq_init(struct bcma_drv_cc *cc)
 {
 	struct gpio_chip *chip = &cc->gpio;
-	int gpio, hwirq, err;
+	int hwirq, err;
 
 	if (cc->core->bus->hosttype != BCMA_HOSTTYPE_SOC)
 		return 0;
 
-	cc->irq_domain = irq_domain_add_linear(NULL, chip->ngpio,
-					       &irq_domain_simple_ops, cc);
-	if (!cc->irq_domain) {
-		err = -ENODEV;
-		goto err_irq_domain;
-	}
-	for (gpio = 0; gpio < chip->ngpio; gpio++) {
-		int irq = irq_create_mapping(cc->irq_domain, gpio);
-
-		irq_set_chip_data(irq, cc);
-		irq_set_chip_and_handler(irq, &bcma_gpio_irq_chip,
-					 handle_simple_irq);
-	}
-
 	hwirq = bcma_core_irq(cc->core, 0);
 	err = request_irq(hwirq, bcma_gpio_irq_handler, IRQF_SHARED, "gpio",
 			  cc);
 	if (err)
-		goto err_req_irq;
+		return err;
 
 	bcma_chipco_gpio_intmask(cc, ~0, 0);
 	bcma_cc_set32(cc, BCMA_CC_IRQMASK, BCMA_CC_IRQ_GPIO);
 
-	return 0;
-
-err_req_irq:
-	for (gpio = 0; gpio < chip->ngpio; gpio++) {
-		int irq = irq_find_mapping(cc->irq_domain, gpio);
-
-		irq_dispose_mapping(irq);
+	err =  gpiochip_irqchip_add(chip,
+				    &bcma_gpio_irq_chip,
+				    0,
+				    handle_simple_irq,
+				    IRQ_TYPE_NONE);
+	if (err) {
+		free_irq(hwirq, cc);
+		return err;
 	}
-	irq_domain_remove(cc->irq_domain);
-err_irq_domain:
-	return err;
+
+	return 0;
 }
 
-static void bcma_gpio_irq_domain_exit(struct bcma_drv_cc *cc)
+static void bcma_gpio_irq_exit(struct bcma_drv_cc *cc)
 {
-	struct gpio_chip *chip = &cc->gpio;
-	int gpio;
-
 	if (cc->core->bus->hosttype != BCMA_HOSTTYPE_SOC)
 		return;
 
 	bcma_cc_mask32(cc, BCMA_CC_IRQMASK, ~BCMA_CC_IRQ_GPIO);
 	free_irq(bcma_core_irq(cc->core, 0), cc);
-	for (gpio = 0; gpio < chip->ngpio; gpio++) {
-		int irq = irq_find_mapping(cc->irq_domain, gpio);
-
-		irq_dispose_mapping(irq);
-	}
-	irq_domain_remove(cc->irq_domain);
 }
 #else
-static int bcma_gpio_irq_domain_init(struct bcma_drv_cc *cc)
+static int bcma_gpio_irq_init(struct bcma_drv_cc *cc)
 {
 	return 0;
 }
 
-static void bcma_gpio_irq_domain_exit(struct bcma_drv_cc *cc)
+static void bcma_gpio_irq_exit(struct bcma_drv_cc *cc)
 {
 }
 #endif
@@ -218,9 +187,8 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 	chip->set		= bcma_gpio_set_value;
 	chip->direction_input	= bcma_gpio_direction_input;
 	chip->direction_output	= bcma_gpio_direction_output;
-#if IS_BUILTIN(CONFIG_BCM47XX) || IS_BUILTIN(CONFIG_ARCH_BCM_5301X)
-	chip->to_irq		= bcma_gpio_to_irq;
-#endif
+	chip->owner		= THIS_MODULE;
+	chip->dev		= bcma_bus_get_host_dev(bus);
 #if IS_BUILTIN(CONFIG_OF)
 	if (cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC)
 		chip->of_node	= cc->core->dev.of_node;
@@ -248,13 +216,13 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 	else
 		chip->base		= -1;
 
-	err = bcma_gpio_irq_domain_init(cc);
+	err = gpiochip_add(chip);
 	if (err)
 		return err;
 
-	err = gpiochip_add(chip);
+	err = bcma_gpio_irq_init(cc);
 	if (err) {
-		bcma_gpio_irq_domain_exit(cc);
+		gpiochip_remove(chip);
 		return err;
 	}
 
@@ -263,7 +231,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 
 int bcma_gpio_unregister(struct bcma_drv_cc *cc)
 {
-	bcma_gpio_irq_domain_exit(cc);
+	bcma_gpio_irq_exit(cc);
 	gpiochip_remove(&cc->gpio);
 	return 0;
 }
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 9635f1033ce5..24882c18fcbe 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -7,11 +7,14 @@
 
 #include "bcma_private.h"
 #include <linux/module.h>
+#include <linux/mmc/sdio_func.h>
 #include <linux/platform_device.h>
+#include <linux/pci.h>
 #include <linux/bcma/bcma.h>
 #include <linux/slab.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/of_platform.h>
 
 MODULE_DESCRIPTION("Broadcom's specific AMBA driver");
 MODULE_LICENSE("GPL");
@@ -268,6 +271,28 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core)
 	}
 }
 
+struct device *bcma_bus_get_host_dev(struct bcma_bus *bus)
+{
+	switch (bus->hosttype) {
+	case BCMA_HOSTTYPE_PCI:
+		if (bus->host_pci)
+			return &bus->host_pci->dev;
+		else
+			return NULL;
+	case BCMA_HOSTTYPE_SOC:
+		if (bus->host_pdev)
+			return &bus->host_pdev->dev;
+		else
+			return NULL;
+	case BCMA_HOSTTYPE_SDIO:
+		if (bus->host_sdio)
+			return &bus->host_sdio->dev;
+		else
+			return NULL;
+	}
+	return NULL;
+}
+
 void bcma_init_bus(struct bcma_bus *bus)
 {
 	mutex_lock(&bcma_buses_mutex);
@@ -387,6 +412,7 @@ int bcma_bus_register(struct bcma_bus *bus)
 {
 	int err;
 	struct bcma_device *core;
+	struct device *dev;
 
 	/* Scan for devices (cores) */
 	err = bcma_bus_scan(bus);
@@ -409,6 +435,16 @@ int bcma_bus_register(struct bcma_bus *bus)
 		bcma_core_pci_early_init(&bus->drv_pci[0]);
 	}
 
+	dev = bcma_bus_get_host_dev(bus);
+	/* TODO: remove check for IS_BUILTIN(CONFIG_BCMA) check when
+	 * of_default_bus_match_table is exported or in some other way
+	 * accessible. This is just a temporary workaround.
+	 */
+	if (IS_BUILTIN(CONFIG_BCMA) && dev) {
+		of_platform_populate(dev->of_node, of_default_bus_match_table,
+				     NULL, dev);
+	}
+
 	/* Cores providing flash access go before SPROM init */
 	list_for_each_entry(core, &bus->cores, list) {
 		if (bcma_is_core_needed_early(core->id.id))
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 46c282fff104..dd73e1ff1759 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -395,7 +395,7 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	blk_queue_max_hw_sectors(q, 1024);
+	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
 	q->backing_dev_info.name = "aoe";
 	q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_CACHE_SIZE;
 	d->bufpool = mp;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 422b7d84f686..ad80c85e0857 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1110,7 +1110,7 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
 		d->ip.rq = NULL;
 	do {
 		bio = rq->bio;
-		bok = !fastfail && test_bit(BIO_UPTODATE, &bio->bi_flags);
+		bok = !fastfail && !bio->bi_error;
 	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size));
 
 	/* cf. http://lkml.org/lkml/2006/10/31/28 */
@@ -1172,7 +1172,7 @@ ktiocomplete(struct frame *f)
 			ahout->cmdstat, ahin->cmdstat,
 			d->aoemajor, d->aoeminor);
 noskb:		if (buf)
-			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			buf->bio->bi_error = -EIO;
 		goto out;
 	}
 
@@ -1185,7 +1185,7 @@ noskb:		if (buf)
 				"aoe: runt data size in read from",
 				(long) d->aoemajor, d->aoeminor,
 			       skb->len, n);
-			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			buf->bio->bi_error = -EIO;
 			break;
 		}
 		if (n > f->iter.bi_size) {
@@ -1193,7 +1193,7 @@ noskb:		if (buf)
 				"aoe: too-large data size in read from",
 				(long) d->aoemajor, d->aoeminor,
 				n, f->iter.bi_size);
-			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			buf->bio->bi_error = -EIO;
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
@@ -1695,7 +1695,7 @@ aoe_failbuf(struct aoedev *d, struct buf *buf)
 	if (buf == NULL)
 		return;
 	buf->iter.bi_size = 0;
-	clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+	buf->bio->bi_error = -EIO;
 	if (buf->nframesout == 0)
 		aoe_end_buf(d, buf);
 }
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index e774c50b6842..ffd1947500c6 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -170,7 +170,7 @@ aoe_failip(struct aoedev *d)
 	if (rq == NULL)
 		return;
 	while ((bio = d->ip.nxbio)) {
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
 		d->ip.nxbio = bio->bi_next;
 		n = (unsigned long) rq->special;
 		rq->special = (void *) --n;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 64ab4951e9d6..f9ab74505e69 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -331,14 +331,12 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 	struct bio_vec bvec;
 	sector_t sector;
 	struct bvec_iter iter;
-	int err = -EIO;
 
 	sector = bio->bi_iter.bi_sector;
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
-		goto out;
+		goto io_error;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
-		err = 0;
 		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
 		goto out;
 	}
@@ -349,15 +347,20 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
+		int err;
+
 		err = brd_do_bvec(brd, bvec.bv_page, len,
 					bvec.bv_offset, rw, sector);
 		if (err)
-			break;
+			goto io_error;
 		sector += len >> SECTOR_SHIFT;
 	}
 
 out:
-	bio_endio(bio, err);
+	bio_endio(bio);
+	return;
+io_error:
+	bio_io_error(bio);
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
@@ -500,7 +503,7 @@ static struct brd_device *brd_alloc(int i)
 	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
 
 	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
-	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
+	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 1318e3217cb0..b3868e7a1ffd 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -175,11 +175,11 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 	atomic_inc(&device->md_io.in_use); /* drbd_md_put_buffer() is in the completion handler */
 	device->md_io.submit_jif = jiffies;
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	else
 		submit_bio(rw, bio);
 	wait_until_done_or_force_detached(device, bdev, &device->md_io.done);
-	if (bio_flagged(bio, BIO_UPTODATE))
+	if (!bio->bi_error)
 		err = device->md_io.error;
 
  out:
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 434c77dcc99e..e5e0f19ceda0 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -941,36 +941,27 @@ static void drbd_bm_aio_ctx_destroy(struct kref *kref)
 }
 
 /* bv_page may be a copy, or may be the original */
-static void drbd_bm_endio(struct bio *bio, int error)
+static void drbd_bm_endio(struct bio *bio)
 {
 	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
 	unsigned int idx = bm_page_to_idx(bio->bi_io_vec[0].bv_page);
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
-
-
-	/* strange behavior of some lower level drivers...
-	 * fail the request by clearing the uptodate flag,
-	 * but do not return any error?!
-	 * do we want to WARN() on this? */
-	if (!error && !uptodate)
-		error = -EIO;
 
 	if ((ctx->flags & BM_AIO_COPY_PAGES) == 0 &&
 	    !bm_test_page_unchanged(b->bm_pages[idx]))
 		drbd_warn(device, "bitmap page idx %u changed during IO!\n", idx);
 
-	if (error) {
+	if (bio->bi_error) {
 		/* ctx error will hold the completed-last non-zero error code,
 		 * in case error codes differ. */
-		ctx->error = error;
+		ctx->error = bio->bi_error;
 		bm_set_page_io_err(b->bm_pages[idx]);
 		/* Not identical to on disk version of it.
 		 * Is BM_PAGE_IO_ERROR enough? */
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_err(device, "IO ERROR %d on bitmap page idx %u\n",
-					error, idx);
+					bio->bi_error, idx);
 	} else {
 		bm_clear_page_io_err(b->bm_pages[idx]);
 		dynamic_drbd_dbg(device, "bitmap page idx %u completed\n", idx);
@@ -1031,7 +1022,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
 		bio->bi_rw |= rw;
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	} else {
 		submit_bio(rw, bio);
 		/* this should not count as user activity and cause the
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index efd19c2da9c2..015c6e91b756 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1450,7 +1450,6 @@ extern void do_submit(struct work_struct *ws);
 extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long);
 extern void drbd_make_request(struct request_queue *q, struct bio *bio);
 extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
-extern int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *bvec);
 extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
@@ -1481,9 +1480,9 @@ extern int drbd_khelper(struct drbd_device *device, char *cmd);
 
 /* drbd_worker.c */
 /* bi_end_io handlers */
-extern void drbd_md_endio(struct bio *bio, int error);
-extern void drbd_peer_request_endio(struct bio *bio, int error);
-extern void drbd_request_endio(struct bio *bio, int error);
+extern void drbd_md_endio(struct bio *bio);
+extern void drbd_peer_request_endio(struct bio *bio);
+extern void drbd_request_endio(struct bio *bio);
 extern int drbd_worker(struct drbd_thread *thi);
 enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_minor);
 void drbd_resync_after_changed(struct drbd_device *device);
@@ -1604,12 +1603,13 @@ static inline void drbd_generic_make_request(struct drbd_device *device,
 	__release(local);
 	if (!bio->bi_bdev) {
 		drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n");
-		bio_endio(bio, -ENODEV);
+		bio->bi_error = -ENODEV;
+		bio_endio(bio);
 		return;
 	}
 
 	if (drbd_insert_fault(device, fault_type))
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	else
 		generic_make_request(bio);
 }
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a1518539b858..74d97f4bac34 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2774,7 +2774,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	   This triggers a max_bio_size message upon first attach or connect */
 	blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
 	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
-	blk_queue_merge_bvec(q, drbd_merge_bvec);
 	q->queue_lock = &resource->req_lock;
 
 	device->md_io.page = alloc_page(GFP_KERNEL);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 74df8cfad414..e80cbefbc2b5 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1156,14 +1156,14 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 			/* For now, don't allow more than one activity log extent worth of data
 			 * to be discarded in one go. We may need to rework drbd_al_begin_io()
 			 * to allow for even larger discard ranges */
-			q->limits.max_discard_sectors = DRBD_MAX_DISCARD_SECTORS;
+			blk_queue_max_discard_sectors(q, DRBD_MAX_DISCARD_SECTORS);
 
 			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 			/* REALLY? Is stacking secdiscard "legal"? */
 			if (blk_queue_secdiscard(b))
 				queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
 		} else {
-			q->limits.max_discard_sectors = 0;
+			blk_queue_max_discard_sectors(q, 0);
 			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 			queue_flag_clear_unlocked(QUEUE_FLAG_SECDISCARD, q);
 		}
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3907202fb9d9..211592682169 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -201,7 +201,8 @@ void start_new_tl_epoch(struct drbd_connection *connection)
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	bio_endio(m->bio, m->error);
+	m->bio->bi_error = m->error;
+	bio_endio(m->bio);
 	dec_ap_bio(device);
 }
 
@@ -1153,12 +1154,12 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 				      rw == WRITE ? DRBD_FAULT_DT_WR
 				    : rw == READ  ? DRBD_FAULT_DT_RD
 				    :               DRBD_FAULT_DT_RA))
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 		else
 			generic_make_request(bio);
 		put_ldev(device);
 	} else
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 }
 
 static void drbd_queue_write(struct drbd_device *device, struct drbd_request *req)
@@ -1191,7 +1192,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 		/* only pass the error to the upper layers.
 		 * if user cannot handle io errors, that's not our business. */
 		drbd_err(device, "could not kmalloc() req\n");
-		bio_endio(bio, -ENOMEM);
+		bio->bi_error = -ENOMEM;
+		bio_endio(bio);
 		return ERR_PTR(-ENOMEM);
 	}
 	req->start_jif = start_jif;
@@ -1497,6 +1499,8 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	struct drbd_device *device = (struct drbd_device *) q->queuedata;
 	unsigned long start_jif;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	start_jif = jiffies;
 
 	/*
@@ -1508,41 +1512,6 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	__drbd_make_request(device, bio, start_jif);
 }
 
-/* This is called by bio_add_page().
- *
- * q->max_hw_sectors and other global limits are already enforced there.
- *
- * We need to call down to our lower level device,
- * in case it has special restrictions.
- *
- * We also may need to enforce configured max-bio-bvecs limits.
- *
- * As long as the BIO is empty we have to allow at least one bvec,
- * regardless of size and offset, so no need to ask lower levels.
- */
-int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *bvec)
-{
-	struct drbd_device *device = (struct drbd_device *) q->queuedata;
-	unsigned int bio_size = bvm->bi_size;
-	int limit = DRBD_MAX_BIO_SIZE;
-	int backing_limit;
-
-	if (bio_size && get_ldev(device)) {
-		unsigned int max_hw_sectors = queue_max_hw_sectors(q);
-		struct request_queue * const b =
-			device->ldev->backing_bdev->bd_disk->queue;
-		if (b->merge_bvec_fn) {
-			bvm->bi_bdev = device->ldev->backing_bdev;
-			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
-			limit = min(limit, backing_limit);
-		}
-		put_ldev(device);
-		if ((limit >> 9) > max_hw_sectors)
-			limit = max_hw_sectors << 9;
-	}
-	return limit;
-}
-
 void request_timer_fn(unsigned long data)
 {
 	struct drbd_device *device = (struct drbd_device *) data;
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index d0fae55d871d..5578c1477ba6 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -65,12 +65,12 @@ rwlock_t global_state_lock;
 /* used for synchronous meta data and bitmap IO
  * submitted by drbd_md_sync_page_io()
  */
-void drbd_md_endio(struct bio *bio, int error)
+void drbd_md_endio(struct bio *bio)
 {
 	struct drbd_device *device;
 
 	device = bio->bi_private;
-	device->md_io.error = error;
+	device->md_io.error = bio->bi_error;
 
 	/* We grabbed an extra reference in _drbd_md_sync_page_io() to be able
 	 * to timeout on the lower level device, and eventually detach from it.
@@ -170,31 +170,20 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 /* writes on behalf of the partner, or resync writes,
  * "submitted" by the receiver.
  */
-void drbd_peer_request_endio(struct bio *bio, int error)
+void drbd_peer_request_endio(struct bio *bio)
 {
 	struct drbd_peer_request *peer_req = bio->bi_private;
 	struct drbd_device *device = peer_req->peer_device->device;
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 	int is_write = bio_data_dir(bio) == WRITE;
 	int is_discard = !!(bio->bi_rw & REQ_DISCARD);
 
-	if (error && __ratelimit(&drbd_ratelimit_state))
+	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
 				is_write ? (is_discard ? "discard" : "write")
-					: "read", error,
+					: "read", bio->bi_error,
 				(unsigned long long)peer_req->i.sector);
-	if (!error && !uptodate) {
-		if (__ratelimit(&drbd_ratelimit_state))
-			drbd_warn(device, "%s: setting error to -EIO s=%llus\n",
-					is_write ? "write" : "read",
-					(unsigned long long)peer_req->i.sector);
-		/* strange behavior of some lower level drivers...
-		 * fail the request by clearing the uptodate flag,
-		 * but do not return any error?! */
-		error = -EIO;
-	}
 
-	if (error)
+	if (bio->bi_error)
 		set_bit(__EE_WAS_ERROR, &peer_req->flags);
 
 	bio_put(bio); /* no need for the bio anymore */
@@ -208,24 +197,13 @@ void drbd_peer_request_endio(struct bio *bio, int error)
 
 /* read, readA or write requests on R_PRIMARY coming from drbd_make_request
  */
-void drbd_request_endio(struct bio *bio, int error)
+void drbd_request_endio(struct bio *bio)
 {
 	unsigned long flags;
 	struct drbd_request *req = bio->bi_private;
 	struct drbd_device *device = req->device;
 	struct bio_and_error m;
 	enum drbd_req_event what;
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
-
-	if (!error && !uptodate) {
-		drbd_warn(device, "p %s: setting error to -EIO\n",
-			 bio_data_dir(bio) == WRITE ? "write" : "read");
-		/* strange behavior of some lower level drivers...
-		 * fail the request by clearing the uptodate flag,
-		 * but do not return any error?! */
-		error = -EIO;
-	}
-
 
 	/* If this request was aborted locally before,
 	 * but now was completed "successfully",
@@ -259,14 +237,14 @@ void drbd_request_endio(struct bio *bio, int error)
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n");
 
-		if (!error)
+		if (!bio->bi_error)
 			panic("possible random memory corruption caused by delayed completion of aborted local request\n");
 	}
 
 	/* to avoid recursion in __req_mod */
-	if (unlikely(error)) {
+	if (unlikely(bio->bi_error)) {
 		if (bio->bi_rw & REQ_DISCARD)
-			what = (error == -EOPNOTSUPP)
+			what = (bio->bi_error == -EOPNOTSUPP)
 				? DISCARD_COMPLETED_NOTSUPP
 				: DISCARD_COMPLETED_WITH_ERROR;
 		else
@@ -279,7 +257,7 @@ void drbd_request_endio(struct bio *bio, int error)
 		what = COMPLETED_OK;
 
 	bio_put(req->private_bio);
-	req->private_bio = ERR_PTR(error);
+	req->private_bio = ERR_PTR(bio->bi_error);
 
 	/* not req_mod(), we need irqsave here! */
 	spin_lock_irqsave(&device->resource->req_lock, flags);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index a08cda955285..331363e7de0f 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3771,13 +3771,14 @@ struct rb0_cbdata {
 	struct completion complete;
 };
 
-static void floppy_rb0_cb(struct bio *bio, int err)
+static void floppy_rb0_cb(struct bio *bio)
 {
 	struct rb0_cbdata *cbdata = (struct rb0_cbdata *)bio->bi_private;
 	int drive = cbdata->drive;
 
-	if (err) {
-		pr_info("floppy: error %d while reading block 0\n", err);
+	if (bio->bi_error) {
+		pr_info("floppy: error %d while reading block 0\n",
+			bio->bi_error);
 		set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
 	}
 	complete(&cbdata->complete);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f7a4c9d7f721..f9889b6bc02c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -675,7 +675,7 @@ static void loop_config_discard(struct loop_device *lo)
 	    lo->lo_encrypt_key_size) {
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
-		q->limits.max_discard_sectors = 0;
+		blk_queue_max_discard_sectors(q, 0);
 		q->limits.discard_zeroes_data = 0;
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		return;
@@ -683,7 +683,7 @@ static void loop_config_discard(struct loop_device *lo)
 
 	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
-	q->limits.max_discard_sectors = UINT_MAX >> 9;
+	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
 	q->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 4a2ef09e6704..f504232c1ee7 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3756,6 +3756,14 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
 
+	/*
+	 * For flush requests, request_idx starts at the end of the
+	 * tag space.  Since we don't support FLUSH/FUA, simply return
+	 * 0 as there's nothing to be done.
+	 */
+	if (request_idx >= MTIP_MAX_COMMAND_SLOTS)
+		return 0;
+
 	cmd->command = dmam_alloc_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ,
 			&cmd->command_dma, GFP_KERNEL);
 	if (!cmd->command)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 0e385d8e9b86..293495a75d3d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -33,6 +33,7 @@
 #include <linux/net.h>
 #include <linux/kthread.h>
 #include <linux/types.h>
+#include <linux/debugfs.h>
 
 #include <asm/uaccess.h>
 #include <asm/types.h>
@@ -40,8 +41,7 @@
 #include <linux/nbd.h>
 
 struct nbd_device {
-	int flags;
-	int harderror;		/* Code of hard error			*/
+	u32 flags;
 	struct socket * sock;	/* If == NULL, device is not ready, yet	*/
 	int magic;
 
@@ -56,11 +56,24 @@ struct nbd_device {
 	struct gendisk *disk;
 	int blksize;
 	loff_t bytesize;
-	pid_t pid; /* pid of nbd-client, if attached */
 	int xmit_timeout;
-	int disconnect; /* a disconnect has been requested by user */
+	bool disconnect; /* a disconnect has been requested by user */
+
+	struct timer_list timeout_timer;
+	struct task_struct *task_recv;
+	struct task_struct *task_send;
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	struct dentry *dbg_dir;
+#endif
 };
 
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+static struct dentry *nbd_dbg_dir;
+#endif
+
+#define nbd_name(nbd) ((nbd)->disk->disk_name)
+
 #define NBD_MAGIC 0x68797548
 
 static unsigned int nbds_max = 16;
@@ -113,26 +126,36 @@ static void nbd_end_request(struct nbd_device *nbd, struct request *req)
 /*
  * Forcibly shutdown the socket causing all listeners to error
  */
-static void sock_shutdown(struct nbd_device *nbd, int lock)
+static void sock_shutdown(struct nbd_device *nbd)
 {
-	if (lock)
-		mutex_lock(&nbd->tx_lock);
-	if (nbd->sock) {
-		dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
-		kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
-		nbd->sock = NULL;
-	}
-	if (lock)
-		mutex_unlock(&nbd->tx_lock);
+	if (!nbd->sock)
+		return;
+
+	dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
+	kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
+	nbd->sock = NULL;
+	del_timer_sync(&nbd->timeout_timer);
 }
 
 static void nbd_xmit_timeout(unsigned long arg)
 {
-	struct task_struct *task = (struct task_struct *)arg;
+	struct nbd_device *nbd = (struct nbd_device *)arg;
+	struct task_struct *task;
+
+	if (list_empty(&nbd->queue_head))
+		return;
+
+	nbd->disconnect = true;
+
+	task = READ_ONCE(nbd->task_recv);
+	if (task)
+		force_sig(SIGKILL, task);
 
-	printk(KERN_WARNING "nbd: killing hung xmit (%s, pid: %d)\n",
-		task->comm, task->pid);
-	force_sig(SIGKILL, task);
+	task = READ_ONCE(nbd->task_send);
+	if (task)
+		force_sig(SIGKILL, nbd->task_send);
+
+	dev_err(nbd_to_dev(nbd), "Connection timed out, killed receiver and sender, shutting down connection\n");
 }
 
 /*
@@ -171,33 +194,12 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 		msg.msg_controllen = 0;
 		msg.msg_flags = msg_flags | MSG_NOSIGNAL;
 
-		if (send) {
-			struct timer_list ti;
-
-			if (nbd->xmit_timeout) {
-				init_timer(&ti);
-				ti.function = nbd_xmit_timeout;
-				ti.data = (unsigned long)current;
-				ti.expires = jiffies + nbd->xmit_timeout;
-				add_timer(&ti);
-			}
+		if (send)
 			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
-			if (nbd->xmit_timeout)
-				del_timer_sync(&ti);
-		} else
+		else
 			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
 						msg.msg_flags);
 
-		if (signal_pending(current)) {
-			siginfo_t info;
-			printk(KERN_WARNING "nbd (pid %d: %s) got signal %d\n",
-				task_pid_nr(current), current->comm,
-				dequeue_signal_lock(current, &current->blocked, &info));
-			result = -EINTR;
-			sock_shutdown(nbd, !send);
-			break;
-		}
-
 		if (result <= 0) {
 			if (result == 0)
 				result = -EPIPE; /* short read */
@@ -210,6 +212,9 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 	sigprocmask(SIG_SETMASK, &oldset, NULL);
 	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 
+	if (!send && nbd->xmit_timeout)
+		mod_timer(&nbd->timeout_timer, jiffies + nbd->xmit_timeout);
+
 	return result;
 }
 
@@ -333,26 +338,24 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 	if (result <= 0) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Receive control failed (result %d)\n", result);
-		goto harderror;
+		return ERR_PTR(result);
 	}
 
 	if (ntohl(reply.magic) != NBD_REPLY_MAGIC) {
 		dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n",
 				(unsigned long)ntohl(reply.magic));
-		result = -EPROTO;
-		goto harderror;
+		return ERR_PTR(-EPROTO);
 	}
 
 	req = nbd_find_request(nbd, *(struct request **)reply.handle);
 	if (IS_ERR(req)) {
 		result = PTR_ERR(req);
 		if (result != -ENOENT)
-			goto harderror;
+			return ERR_PTR(result);
 
 		dev_err(disk_to_dev(nbd->disk), "Unexpected reply (%p)\n",
 			reply.handle);
-		result = -EBADR;
-		goto harderror;
+		return ERR_PTR(-EBADR);
 	}
 
 	if (ntohl(reply.error)) {
@@ -380,18 +383,15 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 		}
 	}
 	return req;
-harderror:
-	nbd->harderror = result;
-	return NULL;
 }
 
 static ssize_t pid_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
 	struct gendisk *disk = dev_to_disk(dev);
+	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
 
-	return sprintf(buf, "%ld\n",
-		(long) ((struct nbd_device *)disk->private_data)->pid);
+	return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
 }
 
 static struct device_attribute pid_attr = {
@@ -399,7 +399,7 @@ static struct device_attribute pid_attr = {
 	.show = pid_show,
 };
 
-static int nbd_do_it(struct nbd_device *nbd)
+static int nbd_thread_recv(struct nbd_device *nbd)
 {
 	struct request *req;
 	int ret;
@@ -407,20 +407,43 @@ static int nbd_do_it(struct nbd_device *nbd)
 	BUG_ON(nbd->magic != NBD_MAGIC);
 
 	sk_set_memalloc(nbd->sock->sk);
-	nbd->pid = task_pid_nr(current);
+
+	nbd->task_recv = current;
+
 	ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (ret) {
 		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
-		nbd->pid = 0;
+		nbd->task_recv = NULL;
 		return ret;
 	}
 
-	while ((req = nbd_read_stat(nbd)) != NULL)
+	while (1) {
+		req = nbd_read_stat(nbd);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
+			break;
+		}
+
 		nbd_end_request(nbd, req);
+	}
 
 	device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
-	nbd->pid = 0;
-	return 0;
+
+	nbd->task_recv = NULL;
+
+	if (signal_pending(current)) {
+		siginfo_t info;
+
+		ret = dequeue_signal_lock(current, &current->blocked, &info);
+		dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
+			 task_pid_nr(current), current->comm, ret);
+		mutex_lock(&nbd->tx_lock);
+		sock_shutdown(nbd);
+		mutex_unlock(&nbd->tx_lock);
+		ret = -ETIMEDOUT;
+	}
+
+	return ret;
 }
 
 static void nbd_clear_que(struct nbd_device *nbd)
@@ -455,6 +478,7 @@ static void nbd_clear_que(struct nbd_device *nbd)
 		req->errors++;
 		nbd_end_request(nbd, req);
 	}
+	dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n");
 }
 
 
@@ -482,6 +506,9 @@ static void nbd_handle_req(struct nbd_device *nbd, struct request *req)
 
 	nbd->active_req = req;
 
+	if (nbd->xmit_timeout && list_empty_careful(&nbd->queue_head))
+		mod_timer(&nbd->timeout_timer, jiffies + nbd->xmit_timeout);
+
 	if (nbd_send_req(nbd, req) != 0) {
 		dev_err(disk_to_dev(nbd->disk), "Request send failed\n");
 		req->errors++;
@@ -503,11 +530,13 @@ error_out:
 	nbd_end_request(nbd, req);
 }
 
-static int nbd_thread(void *data)
+static int nbd_thread_send(void *data)
 {
 	struct nbd_device *nbd = data;
 	struct request *req;
 
+	nbd->task_send = current;
+
 	set_user_nice(current, MIN_NICE);
 	while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
 		/* wait for something to do */
@@ -515,6 +544,20 @@ static int nbd_thread(void *data)
 					 kthread_should_stop() ||
 					 !list_empty(&nbd->waiting_queue));
 
+		if (signal_pending(current)) {
+			siginfo_t info;
+			int ret;
+
+			ret = dequeue_signal_lock(current, &current->blocked,
+						  &info);
+			dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
+				 task_pid_nr(current), current->comm, ret);
+			mutex_lock(&nbd->tx_lock);
+			sock_shutdown(nbd);
+			mutex_unlock(&nbd->tx_lock);
+			break;
+		}
+
 		/* extract request */
 		if (list_empty(&nbd->waiting_queue))
 			continue;
@@ -528,6 +571,9 @@ static int nbd_thread(void *data)
 		/* handle request */
 		nbd_handle_req(nbd, req);
 	}
+
+	nbd->task_send = NULL;
+
 	return 0;
 }
 
@@ -538,7 +584,7 @@ static int nbd_thread(void *data)
  *   { printk( "Warning: Ignoring result!\n"); nbd_end_request( req ); }
  */
 
-static void do_nbd_request(struct request_queue *q)
+static void nbd_request_handler(struct request_queue *q)
 		__releases(q->queue_lock) __acquires(q->queue_lock)
 {
 	struct request *req;
@@ -574,6 +620,9 @@ static void do_nbd_request(struct request_queue *q)
 	}
 }
 
+static int nbd_dev_dbg_init(struct nbd_device *nbd);
+static void nbd_dev_dbg_close(struct nbd_device *nbd);
+
 /* Must be called with tx_lock held */
 
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
@@ -597,7 +646,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		if (!nbd->sock)
 			return -EINVAL;
 
-		nbd->disconnect = 1;
+		nbd->disconnect = true;
 
 		nbd_send_req(nbd, &sreq);
 		return 0;
@@ -625,7 +674,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 			nbd->sock = sock;
 			if (max_part > 0)
 				bdev->bd_invalidated = 1;
-			nbd->disconnect = 0; /* we're connected now */
+			nbd->disconnect = false; /* we're connected now */
 			return 0;
 		}
 		return -EINVAL;
@@ -648,6 +697,12 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 
 	case NBD_SET_TIMEOUT:
 		nbd->xmit_timeout = arg * HZ;
+		if (arg)
+			mod_timer(&nbd->timeout_timer,
+				  jiffies + nbd->xmit_timeout);
+		else
+			del_timer_sync(&nbd->timeout_timer);
+
 		return 0;
 
 	case NBD_SET_FLAGS:
@@ -666,7 +721,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		struct socket *sock;
 		int error;
 
-		if (nbd->pid)
+		if (nbd->task_recv)
 			return -EBUSY;
 		if (!nbd->sock)
 			return -EINVAL;
@@ -683,24 +738,24 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		else
 			blk_queue_flush(nbd->disk->queue, 0);
 
-		thread = kthread_run(nbd_thread, nbd, "%s",
-				     nbd->disk->disk_name);
+		thread = kthread_run(nbd_thread_send, nbd, "%s",
+				     nbd_name(nbd));
 		if (IS_ERR(thread)) {
 			mutex_lock(&nbd->tx_lock);
 			return PTR_ERR(thread);
 		}
 
-		error = nbd_do_it(nbd);
+		nbd_dev_dbg_init(nbd);
+		error = nbd_thread_recv(nbd);
+		nbd_dev_dbg_close(nbd);
 		kthread_stop(thread);
 
 		mutex_lock(&nbd->tx_lock);
-		if (error)
-			return error;
-		sock_shutdown(nbd, 0);
+
+		sock_shutdown(nbd);
 		sock = nbd->sock;
 		nbd->sock = NULL;
 		nbd_clear_que(nbd);
-		dev_warn(disk_to_dev(nbd->disk), "queue cleared\n");
 		kill_bdev(bdev);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 		set_device_ro(bdev, false);
@@ -714,7 +769,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 			blkdev_reread_part(bdev);
 		if (nbd->disconnect) /* user requested, ignore socket errors */
 			return 0;
-		return nbd->harderror;
+		return error;
 	}
 
 	case NBD_CLEAR_QUE:
@@ -758,6 +813,161 @@ static const struct block_device_operations nbd_fops =
 	.ioctl =	nbd_ioctl,
 };
 
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+
+static int nbd_dbg_tasks_show(struct seq_file *s, void *unused)
+{
+	struct nbd_device *nbd = s->private;
+
+	if (nbd->task_recv)
+		seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv));
+	if (nbd->task_send)
+		seq_printf(s, "send: %d\n", task_pid_nr(nbd->task_send));
+
+	return 0;
+}
+
+static int nbd_dbg_tasks_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nbd_dbg_tasks_show, inode->i_private);
+}
+
+static const struct file_operations nbd_dbg_tasks_ops = {
+	.open = nbd_dbg_tasks_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
+{
+	struct nbd_device *nbd = s->private;
+	u32 flags = nbd->flags;
+
+	seq_printf(s, "Hex: 0x%08x\n\n", flags);
+
+	seq_puts(s, "Known flags:\n");
+
+	if (flags & NBD_FLAG_HAS_FLAGS)
+		seq_puts(s, "NBD_FLAG_HAS_FLAGS\n");
+	if (flags & NBD_FLAG_READ_ONLY)
+		seq_puts(s, "NBD_FLAG_READ_ONLY\n");
+	if (flags & NBD_FLAG_SEND_FLUSH)
+		seq_puts(s, "NBD_FLAG_SEND_FLUSH\n");
+	if (flags & NBD_FLAG_SEND_TRIM)
+		seq_puts(s, "NBD_FLAG_SEND_TRIM\n");
+
+	return 0;
+}
+
+static int nbd_dbg_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nbd_dbg_flags_show, inode->i_private);
+}
+
+static const struct file_operations nbd_dbg_flags_ops = {
+	.open = nbd_dbg_flags_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int nbd_dev_dbg_init(struct nbd_device *nbd)
+{
+	struct dentry *dir;
+	struct dentry *f;
+
+	dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir);
+	if (IS_ERR_OR_NULL(dir)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s' (%ld)\n",
+			nbd_name(nbd), PTR_ERR(dir));
+		return PTR_ERR(dir);
+	}
+	nbd->dbg_dir = dir;
+
+	f = debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_ops);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'tasks', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'size_bytes', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_u32("timeout", 0444, dir, &nbd->xmit_timeout);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'timeout', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_u32("blocksize", 0444, dir, &nbd->blksize);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'blocksize', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	f = debugfs_create_file("flags", 0444, dir, &nbd, &nbd_dbg_flags_ops);
+	if (IS_ERR_OR_NULL(f)) {
+		dev_err(nbd_to_dev(nbd), "Failed to create debugfs file 'flags', %ld\n",
+			PTR_ERR(f));
+		return PTR_ERR(f);
+	}
+
+	return 0;
+}
+
+static void nbd_dev_dbg_close(struct nbd_device *nbd)
+{
+	debugfs_remove_recursive(nbd->dbg_dir);
+}
+
+static int nbd_dbg_init(void)
+{
+	struct dentry *dbg_dir;
+
+	dbg_dir = debugfs_create_dir("nbd", NULL);
+	if (IS_ERR(dbg_dir))
+		return PTR_ERR(dbg_dir);
+
+	nbd_dbg_dir = dbg_dir;
+
+	return 0;
+}
+
+static void nbd_dbg_close(void)
+{
+	debugfs_remove_recursive(nbd_dbg_dir);
+}
+
+#else  /* IS_ENABLED(CONFIG_DEBUG_FS) */
+
+static int nbd_dev_dbg_init(struct nbd_device *nbd)
+{
+	return 0;
+}
+
+static void nbd_dev_dbg_close(struct nbd_device *nbd)
+{
+}
+
+static int nbd_dbg_init(void)
+{
+	return 0;
+}
+
+static void nbd_dbg_close(void)
+{
+}
+
+#endif
+
 /*
  * And here should be modules and kernel interface 
  *  (Just smiley confuses emacs :-)
@@ -811,7 +1021,7 @@ static int __init nbd_init(void)
 		 * every gendisk to have its very own request_queue struct.
 		 * These structs are big so we dynamically allocate them.
 		 */
-		disk->queue = blk_init_queue(do_nbd_request, &nbd_lock);
+		disk->queue = blk_init_queue(nbd_request_handler, &nbd_lock);
 		if (!disk->queue) {
 			put_disk(disk);
 			goto out;
@@ -822,7 +1032,7 @@ static int __init nbd_init(void)
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
 		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 		disk->queue->limits.discard_granularity = 512;
-		disk->queue->limits.max_discard_sectors = UINT_MAX;
+		blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
 		disk->queue->limits.discard_zeroes_data = 0;
 		blk_queue_max_hw_sectors(disk->queue, 65536);
 		disk->queue->limits.max_sectors = 256;
@@ -835,6 +1045,8 @@ static int __init nbd_init(void)
 
 	printk(KERN_INFO "nbd: registered device at major %d\n", NBD_MAJOR);
 
+	nbd_dbg_init();
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
 		nbd_dev[i].magic = NBD_MAGIC;
@@ -842,6 +1054,9 @@ static int __init nbd_init(void)
 		spin_lock_init(&nbd_dev[i].queue_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
 		mutex_init(&nbd_dev[i].tx_lock);
+		init_timer(&nbd_dev[i].timeout_timer);
+		nbd_dev[i].timeout_timer.function = nbd_xmit_timeout;
+		nbd_dev[i].timeout_timer.data = (unsigned long)&nbd_dev[i];
 		init_waitqueue_head(&nbd_dev[i].active_wq);
 		init_waitqueue_head(&nbd_dev[i].waiting_wq);
 		nbd_dev[i].blksize = 1024;
@@ -868,6 +1083,9 @@ out:
 static void __exit nbd_cleanup(void)
 {
 	int i;
+
+	nbd_dbg_close();
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
 		nbd_dev[i].magic = 0;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 69de41a87b74..17269a3b85f2 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -222,7 +222,7 @@ static void end_cmd(struct nullb_cmd *cmd)
 		blk_end_request_all(cmd->rq, 0);
 		break;
 	case NULL_Q_BIO:
-		bio_endio(cmd->bio, 0);
+		bio_endio(cmd->bio);
 		break;
 	}
 
@@ -240,19 +240,19 @@ static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 	while ((entry = llist_del_all(&cq->list)) != NULL) {
 		entry = llist_reverse_order(entry);
 		do {
+			struct request_queue *q = NULL;
+
 			cmd = container_of(entry, struct nullb_cmd, ll_list);
 			entry = entry->next;
+			if (cmd->rq)
+				q = cmd->rq->q;
 			end_cmd(cmd);
 
-			if (cmd->rq) {
-				struct request_queue *q = cmd->rq->q;
-
-				if (!q->mq_ops && blk_queue_stopped(q)) {
-					spin_lock(q->queue_lock);
-					if (blk_queue_stopped(q))
-						blk_start_queue(q);
-					spin_unlock(q->queue_lock);
-				}
+			if (q && !q->mq_ops && blk_queue_stopped(q)) {
+				spin_lock(q->queue_lock);
+				if (blk_queue_stopped(q))
+					blk_start_queue(q);
+				spin_unlock(q->queue_lock);
 			}
 		} while (entry);
 	}
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index d1d6141920d3..b97fc3fe0916 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -72,6 +72,10 @@ module_param(nvme_char_major, int, 0);
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
 
+static bool use_cmb_sqes = true;
+module_param(use_cmb_sqes, bool, 0644);
+MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");
+
 static DEFINE_SPINLOCK(dev_list_lock);
 static LIST_HEAD(dev_list);
 static struct task_struct *nvme_thread;
@@ -103,6 +107,7 @@ struct nvme_queue {
 	char irqname[24];	/* nvme4294967295-65535\0 */
 	spinlock_t q_lock;
 	struct nvme_command *sq_cmds;
+	struct nvme_command __iomem *sq_cmds_io;
 	volatile struct nvme_completion *cqes;
 	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
@@ -379,27 +384,28 @@ static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
  *
  * Safe to use from interrupt context
  */
-static int __nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
+						struct nvme_command *cmd)
 {
 	u16 tail = nvmeq->sq_tail;
 
-	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+	if (nvmeq->sq_cmds_io)
+		memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
+	else
+		memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+
 	if (++tail == nvmeq->q_depth)
 		tail = 0;
 	writel(tail, nvmeq->q_db);
 	nvmeq->sq_tail = tail;
-
-	return 0;
 }
 
-static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
 	unsigned long flags;
-	int ret;
 	spin_lock_irqsave(&nvmeq->q_lock, flags);
-	ret = __nvme_submit_cmd(nvmeq, cmd);
+	__nvme_submit_cmd(nvmeq, cmd);
 	spin_unlock_irqrestore(&nvmeq->q_lock, flags);
-	return ret;
 }
 
 static __le64 **iod_list(struct nvme_iod *iod)
@@ -730,18 +736,16 @@ static int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod,
 static void nvme_submit_priv(struct nvme_queue *nvmeq, struct request *req,
 		struct nvme_iod *iod)
 {
-	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	struct nvme_command cmnd;
 
-	memcpy(cmnd, req->cmd, sizeof(struct nvme_command));
-	cmnd->rw.command_id = req->tag;
+	memcpy(&cmnd, req->cmd, sizeof(cmnd));
+	cmnd.rw.command_id = req->tag;
 	if (req->nr_phys_segments) {
-		cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-		cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
+		cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+		cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
 	}
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 }
 
 /*
@@ -754,45 +758,41 @@ static void nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 {
 	struct nvme_dsm_range *range =
 				(struct nvme_dsm_range *)iod_list(iod)[0];
-	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	struct nvme_command cmnd;
 
 	range->cattr = cpu_to_le32(0);
 	range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
 	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
 
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->dsm.opcode = nvme_cmd_dsm;
-	cmnd->dsm.command_id = req->tag;
-	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->dsm.prp1 = cpu_to_le64(iod->first_dma);
-	cmnd->dsm.nr = 0;
-	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
+	memset(&cmnd, 0, sizeof(cmnd));
+	cmnd.dsm.opcode = nvme_cmd_dsm;
+	cmnd.dsm.command_id = req->tag;
+	cmnd.dsm.nsid = cpu_to_le32(ns->ns_id);
+	cmnd.dsm.prp1 = cpu_to_le64(iod->first_dma);
+	cmnd.dsm.nr = 0;
+	cmnd.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 }
 
 static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 								int cmdid)
 {
-	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	struct nvme_command cmnd;
 
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->common.opcode = nvme_cmd_flush;
-	cmnd->common.command_id = cmdid;
-	cmnd->common.nsid = cpu_to_le32(ns->ns_id);
+	memset(&cmnd, 0, sizeof(cmnd));
+	cmnd.common.opcode = nvme_cmd_flush;
+	cmnd.common.command_id = cmdid;
+	cmnd.common.nsid = cpu_to_le32(ns->ns_id);
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 }
 
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 							struct nvme_ns *ns)
 {
 	struct request *req = iod_get_private(iod);
-	struct nvme_command *cmnd;
+	struct nvme_command cmnd;
 	u16 control = 0;
 	u32 dsmgmt = 0;
 
@@ -804,19 +804,16 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
-	cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
-	memset(cmnd, 0, sizeof(*cmnd));
+	memset(&cmnd, 0, sizeof(cmnd));
+	cmnd.rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd.rw.command_id = req->tag;
+	cmnd.rw.nsid = cpu_to_le32(ns->ns_id);
+	cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
+	cmnd.rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd.rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
-	cmnd->rw.command_id = req->tag;
-	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
-	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
-
-	if (blk_integrity_rq(req)) {
-		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(iod->meta_sg));
+	if (ns->ms) {
 		switch (ns->pi_type) {
 		case NVME_NS_DPS_PI_TYPE3:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD;
@@ -825,19 +822,21 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
+			cmnd.rw.reftag = cpu_to_le32(
 					nvme_block_nr(ns, blk_rq_pos(req)));
 			break;
 		}
-	} else if (ns->ms)
-		control |= NVME_RW_PRINFO_PRACT;
+		if (blk_integrity_rq(req))
+			cmnd.rw.metadata =
+				cpu_to_le64(sg_dma_address(iod->meta_sg));
+		else
+			control |= NVME_RW_PRINFO_PRACT;
+	}
 
-	cmnd->rw.control = cpu_to_le16(control);
-	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+	cmnd.rw.control = cpu_to_le16(control);
+	cmnd.rw.dsmgmt = cpu_to_le32(dsmgmt);
 
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
+	__nvme_submit_cmd(nvmeq, &cmnd);
 
 	return 0;
 }
@@ -1080,7 +1079,8 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
 	c.common.command_id = req->tag;
 
 	blk_mq_free_request(req);
-	return __nvme_submit_cmd(nvmeq, &c);
+	__nvme_submit_cmd(nvmeq, &c);
+	return 0;
 }
 
 static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
@@ -1103,7 +1103,8 @@ static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
 
 	cmd->common.command_id = req->tag;
 
-	return nvme_submit_cmd(nvmeq, cmd);
+	nvme_submit_cmd(nvmeq, cmd);
+	return 0;
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1315,12 +1316,7 @@ static void nvme_abort_req(struct request *req)
 
 	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req->tag,
 							nvmeq->qid);
-	if (nvme_submit_cmd(dev->queues[0], &cmd) < 0) {
-		dev_warn(nvmeq->q_dmadev,
-				"Could not abort I/O %d QID %d",
-				req->tag, nvmeq->qid);
-		blk_mq_free_request(abort_req);
-	}
+	nvme_submit_cmd(dev->queues[0], &cmd);
 }
 
 static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved)
@@ -1374,7 +1370,8 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
+	if (nvmeq->sq_cmds)
+		dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
 					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
 	kfree(nvmeq);
 }
@@ -1447,6 +1444,47 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
+static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
+				int entry_size)
+{
+	int q_depth = dev->q_depth;
+	unsigned q_size_aligned = roundup(q_depth * entry_size, dev->page_size);
+
+	if (q_size_aligned * nr_io_queues > dev->cmb_size) {
+		u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
+		mem_per_q = round_down(mem_per_q, dev->page_size);
+		q_depth = div_u64(mem_per_q, entry_size);
+
+		/*
+		 * Ensure the reduced q_depth is above some threshold where it
+		 * would be better to map queues in system memory with the
+		 * original depth
+		 */
+		if (q_depth < 64)
+			return -ENOMEM;
+	}
+
+	return q_depth;
+}
+
+static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
+				int qid, int depth)
+{
+	if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
+		unsigned offset = (qid - 1) *
+					roundup(SQ_SIZE(depth), dev->page_size);
+		nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
+		nvmeq->sq_cmds_io = dev->cmb + offset;
+	} else {
+		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+					&nvmeq->sq_dma_addr, GFP_KERNEL);
+		if (!nvmeq->sq_cmds)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth)
 {
@@ -1459,9 +1497,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	if (!nvmeq->cqes)
 		goto free_nvmeq;
 
-	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					&nvmeq->sq_dma_addr, GFP_KERNEL);
-	if (!nvmeq->sq_cmds)
+	if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
 		goto free_cqdma;
 
 	nvmeq->q_dmadev = dev->dev;
@@ -1696,6 +1732,12 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 		page_shift = dev_page_max;
 	}
 
+	dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
+						NVME_CAP_NSSRC(cap) : 0;
+
+	if (dev->subsystem && (readl(&dev->bar->csts) & NVME_CSTS_NSSRO))
+		writel(NVME_CSTS_NSSRO, &dev->bar->csts);
+
 	result = nvme_disable_ctrl(dev, cap);
 	if (result < 0)
 		return result;
@@ -1856,6 +1898,15 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
 	return status;
 }
 
+static int nvme_subsys_reset(struct nvme_dev *dev)
+{
+	if (!dev->subsystem)
+		return -ENOTTY;
+
+	writel(0x4E564D65, &dev->bar->nssr); /* "NVMe" */
+	return 0;
+}
+
 static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 							unsigned long arg)
 {
@@ -1935,7 +1986,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	ns->queue->limits.discard_zeroes_data = 0;
 	ns->queue->limits.discard_alignment = logical_block_size;
 	ns->queue->limits.discard_granularity = logical_block_size;
-	ns->queue->limits.max_discard_sectors = 0xffffffff;
+	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
@@ -1989,7 +2040,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 								!ns->ext)
 		nvme_init_integrity(ns);
 
-	if (ns->ms && !blk_get_integrity(disk))
+	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
 		set_capacity(disk, 0);
 	else
 		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
@@ -2020,7 +2071,10 @@ static int nvme_kthread(void *data)
 		spin_lock(&dev_list_lock);
 		list_for_each_entry_safe(dev, next, &dev_list, node) {
 			int i;
-			if (readl(&dev->bar->csts) & NVME_CSTS_CFS) {
+			u32 csts = readl(&dev->bar->csts);
+
+			if ((dev->subsystem && (csts & NVME_CSTS_NSSRO)) ||
+							csts & NVME_CSTS_CFS) {
 				if (work_busy(&dev->reset_work))
 					continue;
 				list_del_init(&dev->node);
@@ -2067,7 +2121,6 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 		goto out_free_ns;
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
-	queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, ns->queue);
 	ns->dev = dev;
 	ns->queue->queuedata = ns;
 
@@ -2081,12 +2134,16 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	list_add_tail(&ns->list, &dev->namespaces);
 
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
-	if (dev->max_hw_sectors)
+	if (dev->max_hw_sectors) {
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
+		blk_queue_max_segments(ns->queue,
+			((dev->max_hw_sectors << 9) / dev->page_size) + 1);
+	}
 	if (dev->stripe_size)
 		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
 	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
 		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
+	blk_queue_virt_boundary(ns->queue, dev->page_size - 1);
 
 	disk->major = nvme_major;
 	disk->first_minor = 0;
@@ -2108,8 +2165,17 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 		goto out_free_disk;
 
 	add_disk(ns->disk);
-	if (ns->ms)
-		revalidate_disk(ns->disk);
+	if (ns->ms) {
+		struct block_device *bd = bdget_disk(ns->disk, 0);
+		if (!bd)
+			return;
+		if (blkdev_get(bd, FMODE_READ, NULL)) {
+			bdput(bd);
+			return;
+		}
+		blkdev_reread_part(bd);
+		blkdev_put(bd, FMODE_READ);
+	}
 	return;
  out_free_disk:
 	kfree(disk);
@@ -2150,6 +2216,58 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 	return min(result & 0xffff, result >> 16) + 1;
 }
 
+static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
+{
+	u64 szu, size, offset;
+	u32 cmbloc;
+	resource_size_t bar_size;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	void __iomem *cmb;
+	dma_addr_t dma_addr;
+
+	if (!use_cmb_sqes)
+		return NULL;
+
+	dev->cmbsz = readl(&dev->bar->cmbsz);
+	if (!(NVME_CMB_SZ(dev->cmbsz)))
+		return NULL;
+
+	cmbloc = readl(&dev->bar->cmbloc);
+
+	szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
+	size = szu * NVME_CMB_SZ(dev->cmbsz);
+	offset = szu * NVME_CMB_OFST(cmbloc);
+	bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+
+	if (offset > bar_size)
+		return NULL;
+
+	/*
+	 * Controllers may support a CMB size larger than their BAR,
+	 * for example, due to being behind a bridge. Reduce the CMB to
+	 * the reported size of the BAR
+	 */
+	if (size > bar_size - offset)
+		size = bar_size - offset;
+
+	dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+	cmb = ioremap_wc(dma_addr, size);
+	if (!cmb)
+		return NULL;
+
+	dev->cmb_dma_addr = dma_addr;
+	dev->cmb_size = size;
+	return cmb;
+}
+
+static inline void nvme_release_cmb(struct nvme_dev *dev)
+{
+	if (dev->cmb) {
+		iounmap(dev->cmb);
+		dev->cmb = NULL;
+	}
+}
+
 static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 {
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
@@ -2168,6 +2286,15 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result < nr_io_queues)
 		nr_io_queues = result;
 
+	if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
+		result = nvme_cmb_qdepth(dev, nr_io_queues,
+				sizeof(struct nvme_command));
+		if (result > 0)
+			dev->q_depth = result;
+		else
+			nvme_release_cmb(dev);
+	}
+
 	size = db_bar_size(dev, nr_io_queues);
 	if (size > 8192) {
 		iounmap(dev->bar);
@@ -2335,7 +2462,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int res;
-	unsigned nn;
 	struct nvme_id_ctrl *ctrl;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
 
@@ -2345,7 +2471,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		return -EIO;
 	}
 
-	nn = le32_to_cpup(&ctrl->nn);
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
 	dev->vwc = ctrl->vwc;
@@ -2431,6 +2556,8 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
 	dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
 	dev->dbs = ((void __iomem *)dev->bar) + 4096;
+	if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
+		dev->cmb = nvme_map_cmb(dev);
 
 	return 0;
 
@@ -2811,6 +2938,8 @@ static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 	case NVME_IOCTL_RESET:
 		dev_warn(dev->dev, "resetting controller\n");
 		return nvme_reset(dev);
+	case NVME_IOCTL_SUBSYS_RESET:
+		return nvme_subsys_reset(dev);
 	default:
 		return -ENOTTY;
 	}
@@ -3136,6 +3265,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_dev_remove_admin(dev);
 	device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
 	nvme_free_queues(dev, 0);
+	nvme_release_cmb(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4c20c228184c..7be2375db7f2 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -977,7 +977,7 @@ static void pkt_make_local_copy(struct packet_data *pkt, struct bio_vec *bvec)
 	}
 }
 
-static void pkt_end_io_read(struct bio *bio, int err)
+static void pkt_end_io_read(struct bio *bio)
 {
 	struct packet_data *pkt = bio->bi_private;
 	struct pktcdvd_device *pd = pkt->pd;
@@ -985,9 +985,9 @@ static void pkt_end_io_read(struct bio *bio, int err)
 
 	pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
 		bio, (unsigned long long)pkt->sector,
-		(unsigned long long)bio->bi_iter.bi_sector, err);
+		(unsigned long long)bio->bi_iter.bi_sector, bio->bi_error);
 
-	if (err)
+	if (bio->bi_error)
 		atomic_inc(&pkt->io_errors);
 	if (atomic_dec_and_test(&pkt->io_wait)) {
 		atomic_inc(&pkt->run_sm);
@@ -996,13 +996,13 @@ static void pkt_end_io_read(struct bio *bio, int err)
 	pkt_bio_finished(pd);
 }
 
-static void pkt_end_io_packet_write(struct bio *bio, int err)
+static void pkt_end_io_packet_write(struct bio *bio)
 {
 	struct packet_data *pkt = bio->bi_private;
 	struct pktcdvd_device *pd = pkt->pd;
 	BUG_ON(!pd);
 
-	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, err);
+	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_error);
 
 	pd->stats.pkt_ended++;
 
@@ -1340,22 +1340,22 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	pkt_queue_bio(pd, pkt->w_bio);
 }
 
-static void pkt_finish_packet(struct packet_data *pkt, int uptodate)
+static void pkt_finish_packet(struct packet_data *pkt, int error)
 {
 	struct bio *bio;
 
-	if (!uptodate)
+	if (error)
 		pkt->cache_valid = 0;
 
 	/* Finish all bios corresponding to this packet */
-	while ((bio = bio_list_pop(&pkt->orig_bios)))
-		bio_endio(bio, uptodate ? 0 : -EIO);
+	while ((bio = bio_list_pop(&pkt->orig_bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 
 static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
 {
-	int uptodate;
-
 	pkt_dbg(2, pd, "pkt %d\n", pkt->id);
 
 	for (;;) {
@@ -1384,7 +1384,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			if (atomic_read(&pkt->io_wait) > 0)
 				return;
 
-			if (test_bit(BIO_UPTODATE, &pkt->w_bio->bi_flags)) {
+			if (!pkt->w_bio->bi_error) {
 				pkt_set_state(pkt, PACKET_FINISHED_STATE);
 			} else {
 				pkt_set_state(pkt, PACKET_RECOVERY_STATE);
@@ -1401,8 +1401,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			break;
 
 		case PACKET_FINISHED_STATE:
-			uptodate = test_bit(BIO_UPTODATE, &pkt->w_bio->bi_flags);
-			pkt_finish_packet(pkt, uptodate);
+			pkt_finish_packet(pkt, pkt->w_bio->bi_error);
 			return;
 
 		default:
@@ -2332,13 +2331,14 @@ static void pkt_close(struct gendisk *disk, fmode_t mode)
 }
 
 
-static void pkt_end_io_read_cloned(struct bio *bio, int err)
+static void pkt_end_io_read_cloned(struct bio *bio)
 {
 	struct packet_stacked_data *psd = bio->bi_private;
 	struct pktcdvd_device *pd = psd->pd;
 
+	psd->bio->bi_error = bio->bi_error;
 	bio_put(bio);
-	bio_endio(psd->bio, err);
+	bio_endio(psd->bio);
 	mempool_free(psd, psd_pool);
 	pkt_bio_finished(pd);
 }
@@ -2447,6 +2447,10 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 	char b[BDEVNAME_SIZE];
 	struct bio *split;
 
+	blk_queue_bounce(q, &bio);
+
+	blk_queue_split(q, &bio, q->bio_split);
+
 	pd = q->queuedata;
 	if (!pd) {
 		pr_err("%s incorrect request queue\n",
@@ -2477,8 +2481,6 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 		goto end_io;
 	}
 
-	blk_queue_bounce(q, &bio);
-
 	do {
 		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
 		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
@@ -2504,26 +2506,6 @@ end_io:
 
 
 
-static int pkt_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
-			  struct bio_vec *bvec)
-{
-	struct pktcdvd_device *pd = q->queuedata;
-	sector_t zone = get_zone(bmd->bi_sector, pd);
-	int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
-	int remaining = (pd->settings.size << 9) - used;
-	int remaining2;
-
-	/*
-	 * A bio <= PAGE_SIZE must be allowed. If it crosses a packet
-	 * boundary, pkt_make_request() will split the bio.
-	 */
-	remaining2 = PAGE_SIZE - bmd->bi_size;
-	remaining = max(remaining, remaining2);
-
-	BUG_ON(remaining < 0);
-	return remaining;
-}
-
 static void pkt_init_queue(struct pktcdvd_device *pd)
 {
 	struct request_queue *q = pd->disk->queue;
@@ -2531,7 +2513,6 @@ static void pkt_init_queue(struct pktcdvd_device *pd)
 	blk_queue_make_request(q, pkt_make_request);
 	blk_queue_logical_block_size(q, CD_FRAMESIZE);
 	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
-	blk_queue_merge_bvec(q, pkt_merge_bvec);
 	q->queuedata = pd;
 }
 
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index b1612eb16172..d89fcac59515 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -593,7 +593,8 @@ out:
 	next = bio_list_peek(&priv->list);
 	spin_unlock_irq(&priv->lock);
 
-	bio_endio(bio, error);
+	bio->bi_error = error;
+	bio_endio(bio);
 	return next;
 }
 
@@ -605,6 +606,8 @@ static void ps3vram_make_request(struct request_queue *q, struct bio *bio)
 
 	dev_dbg(&dev->core, "%s\n", __func__);
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	spin_lock_irq(&priv->lock);
 	busy = !bio_list_empty(&priv->list);
 	bio_list_add(&priv->list, bio);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d94529d5c8e9..698f761037ce 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -523,6 +523,7 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...)
 #  define rbd_assert(expr)	((void) 0)
 #endif /* !RBD_DEBUG */
 
+static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request);
 static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request);
 static void rbd_img_parent_read(struct rbd_obj_request *obj_request);
 static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
@@ -1818,6 +1819,16 @@ static void rbd_osd_stat_callback(struct rbd_obj_request *obj_request)
 	obj_request_done_set(obj_request);
 }
 
+static void rbd_osd_call_callback(struct rbd_obj_request *obj_request)
+{
+	dout("%s: obj %p\n", __func__, obj_request);
+
+	if (obj_request_img_data_test(obj_request))
+		rbd_osd_copyup_callback(obj_request);
+	else
+		obj_request_done_set(obj_request);
+}
+
 static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 				struct ceph_msg *msg)
 {
@@ -1866,6 +1877,8 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 		rbd_osd_discard_callback(obj_request);
 		break;
 	case CEPH_OSD_OP_CALL:
+		rbd_osd_call_callback(obj_request);
+		break;
 	case CEPH_OSD_OP_NOTIFY_ACK:
 	case CEPH_OSD_OP_WATCH:
 		rbd_osd_trivial_callback(obj_request);
@@ -2530,13 +2543,15 @@ out_unwind:
 }
 
 static void
-rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
+rbd_osd_copyup_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
 	u32 page_count;
 
+	dout("%s: obj %p\n", __func__, obj_request);
+
 	rbd_assert(obj_request->type == OBJ_REQUEST_BIO ||
 		obj_request->type == OBJ_REQUEST_NODATA);
 	rbd_assert(obj_request_img_data_test(obj_request));
@@ -2563,9 +2578,7 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
 	if (!obj_request->result)
 		obj_request->xferred = obj_request->length;
 
-	/* Finish up with the normal image object callback */
-
-	rbd_img_obj_callback(obj_request);
+	obj_request_done_set(obj_request);
 }
 
 static void
@@ -2650,7 +2663,6 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 
 	/* All set, send it off. */
 
-	orig_request->callback = rbd_img_obj_copyup_callback;
 	osdc = &rbd_dev->rbd_client->client->osdc;
 	img_result = rbd_obj_request_submit(osdc, orig_request);
 	if (!img_result)
@@ -3462,52 +3474,6 @@ static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
-/*
- * a queue callback. Makes sure that we don't create a bio that spans across
- * multiple osd objects. One exception would be with a single page bios,
- * which we handle later at bio_chain_clone_range()
- */
-static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
-			  struct bio_vec *bvec)
-{
-	struct rbd_device *rbd_dev = q->queuedata;
-	sector_t sector_offset;
-	sector_t sectors_per_obj;
-	sector_t obj_sector_offset;
-	int ret;
-
-	/*
-	 * Find how far into its rbd object the partition-relative
-	 * bio start sector is to offset relative to the enclosing
-	 * device.
-	 */
-	sector_offset = get_start_sect(bmd->bi_bdev) + bmd->bi_sector;
-	sectors_per_obj = 1 << (rbd_dev->header.obj_order - SECTOR_SHIFT);
-	obj_sector_offset = sector_offset & (sectors_per_obj - 1);
-
-	/*
-	 * Compute the number of bytes from that offset to the end
-	 * of the object.  Account for what's already used by the bio.
-	 */
-	ret = (int) (sectors_per_obj - obj_sector_offset) << SECTOR_SHIFT;
-	if (ret > bmd->bi_size)
-		ret -= bmd->bi_size;
-	else
-		ret = 0;
-
-	/*
-	 * Don't send back more than was asked for.  And if the bio
-	 * was empty, let the whole thing through because:  "Note
-	 * that a block device *must* allow a single page to be
-	 * added to an empty bio."
-	 */
-	rbd_assert(bvec->bv_len <= PAGE_SIZE);
-	if (ret > (int) bvec->bv_len || !bmd->bi_size)
-		ret = (int) bvec->bv_len;
-
-	return ret;
-}
-
 static void rbd_free_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk = rbd_dev->disk;
@@ -3803,10 +3769,9 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	q->limits.discard_granularity = segment_size;
 	q->limits.discard_alignment = segment_size;
-	q->limits.max_discard_sectors = segment_size / SECTOR_SIZE;
+	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
 	q->limits.discard_zeroes_data = 1;
 
-	blk_queue_merge_bvec(q, rbd_merge_bvec);
 	disk->queue = q;
 
 	q->queuedata = rbd_dev;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index ac8c62cb4875..3163e4cdc2cc 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -137,7 +137,10 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
 		if (!card->eeh_state && card->gendisk)
 			disk_stats_complete(card, meta->bio, meta->start_time);
 
-		bio_endio(meta->bio, atomic_read(&meta->error) ? -EIO : 0);
+		if (atomic_read(&meta->error))
+			bio_io_error(meta->bio);
+		else
+			bio_endio(meta->bio);
 		kmem_cache_free(bio_meta_pool, meta);
 	}
 }
@@ -148,6 +151,8 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 	struct rsxx_bio_meta *bio_meta;
 	int st = -EINVAL;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	might_sleep();
 
 	if (!card)
@@ -199,7 +204,9 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 queue_err:
 	kmem_cache_free(bio_meta_pool, bio_meta);
 req_err:
-	bio_endio(bio, st);
+	if (st)
+		bio->bi_error = st;
+	bio_endio(bio);
 }
 
 /*----------------- Device Setup -------------------*/
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 1e46eb2305c0..586f9168ffa4 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -4422,7 +4422,7 @@ static int skd_cons_disk(struct skd_device *skdev)
 	/* DISCARD Flag initialization. */
 	q->limits.discard_granularity = 8192;
 	q->limits.discard_alignment = 0;
-	q->limits.max_discard_sectors = UINT_MAX >> 9;
+	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
 	q->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 4cf81b5bf0f7..04d65790a886 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -456,7 +456,7 @@ static void process_page(unsigned long data)
 				PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
 		if (control & DMASCR_HARD_ERROR) {
 			/* error */
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 			dev_printk(KERN_WARNING, &card->dev->dev,
 				"I/O error on sector %d/%d\n",
 				le32_to_cpu(desc->local_addr)>>9,
@@ -505,7 +505,7 @@ static void process_page(unsigned long data)
 
 		return_bio = bio->bi_next;
 		bio->bi_next = NULL;
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	}
 }
 
@@ -531,6 +531,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio)
 		 (unsigned long long)bio->bi_iter.bi_sector,
 		 bio->bi_iter.bi_size);
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	spin_lock_irq(&card->lock);
 	*card->biotail = bio;
 	bio->bi_next = NULL;
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index ced96777b677..6a685aec6994 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -369,8 +369,8 @@ static void purge_persistent_gnt(struct xen_blkif *blkif)
 		return;
 	}
 
-	if (work_pending(&blkif->persistent_purge_work)) {
-		pr_alert_ratelimited("Scheduled work from previous purge is still pending, cannot purge list\n");
+	if (work_busy(&blkif->persistent_purge_work)) {
+		pr_alert_ratelimited("Scheduled work from previous purge is still busy, cannot purge list\n");
 		return;
 	}
 
@@ -1078,9 +1078,9 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
 /*
  * bio callback.
  */
-static void end_block_io_op(struct bio *bio, int error)
+static void end_block_io_op(struct bio *bio)
 {
-	__end_block_io_op(bio->bi_private, error);
+	__end_block_io_op(bio->bi_private, bio->bi_error);
 	bio_put(bio);
 }
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 6d89ed35d80c..15083539df15 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -37,6 +37,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/hdreg.h>
 #include <linux/cdrom.h>
 #include <linux/module.h>
@@ -82,7 +83,6 @@ struct blk_shadow {
 struct split_bio {
 	struct bio *bio;
 	atomic_t pending;
-	int err;
 };
 
 static DEFINE_MUTEX(blkfront_mutex);
@@ -148,6 +148,7 @@ struct blkfront_info
 	unsigned int feature_persistent:1;
 	unsigned int max_indirect_segments;
 	int is_ready;
+	struct blk_mq_tag_set tag_set;
 };
 
 static unsigned int nr_minors;
@@ -179,6 +180,7 @@ static DEFINE_SPINLOCK(minor_lock);
 	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 
 static int blkfront_setup_indirect(struct blkfront_info *info);
+static int blkfront_gather_backend_features(struct blkfront_info *info);
 
 static int get_id_from_freelist(struct blkfront_info *info)
 {
@@ -616,54 +618,41 @@ static inline bool blkif_request_flush_invalid(struct request *req,
 		 !(info->feature_flush & REQ_FUA)));
 }
 
-/*
- * do_blkif_request
- *  read a block; request is in a request queue
- */
-static void do_blkif_request(struct request_queue *rq)
+static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
+			   const struct blk_mq_queue_data *qd)
 {
-	struct blkfront_info *info = NULL;
-	struct request *req;
-	int queued;
-
-	pr_debug("Entered do_blkif_request\n");
+	struct blkfront_info *info = qd->rq->rq_disk->private_data;
 
-	queued = 0;
-
-	while ((req = blk_peek_request(rq)) != NULL) {
-		info = req->rq_disk->private_data;
-
-		if (RING_FULL(&info->ring))
-			goto wait;
+	blk_mq_start_request(qd->rq);
+	spin_lock_irq(&info->io_lock);
+	if (RING_FULL(&info->ring))
+		goto out_busy;
 
-		blk_start_request(req);
+	if (blkif_request_flush_invalid(qd->rq, info))
+		goto out_err;
 
-		if (blkif_request_flush_invalid(req, info)) {
-			__blk_end_request_all(req, -EOPNOTSUPP);
-			continue;
-		}
+	if (blkif_queue_request(qd->rq))
+		goto out_busy;
 
-		pr_debug("do_blk_req %p: cmd %p, sec %lx, "
-			 "(%u/%u) [%s]\n",
-			 req, req->cmd, (unsigned long)blk_rq_pos(req),
-			 blk_rq_cur_sectors(req), blk_rq_sectors(req),
-			 rq_data_dir(req) ? "write" : "read");
-
-		if (blkif_queue_request(req)) {
-			blk_requeue_request(rq, req);
-wait:
-			/* Avoid pointless unplugs. */
-			blk_stop_queue(rq);
-			break;
-		}
+	flush_requests(info);
+	spin_unlock_irq(&info->io_lock);
+	return BLK_MQ_RQ_QUEUE_OK;
 
-		queued++;
-	}
+out_err:
+	spin_unlock_irq(&info->io_lock);
+	return BLK_MQ_RQ_QUEUE_ERROR;
 
-	if (queued != 0)
-		flush_requests(info);
+out_busy:
+	spin_unlock_irq(&info->io_lock);
+	blk_mq_stop_hw_queue(hctx);
+	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
+static struct blk_mq_ops blkfront_mq_ops = {
+	.queue_rq = blkif_queue_rq,
+	.map_queue = blk_mq_map_queue,
+};
+
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 				unsigned int physical_sector_size,
 				unsigned int segments)
@@ -671,9 +660,22 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 	struct request_queue *rq;
 	struct blkfront_info *info = gd->private_data;
 
-	rq = blk_init_queue(do_blkif_request, &info->io_lock);
-	if (rq == NULL)
+	memset(&info->tag_set, 0, sizeof(info->tag_set));
+	info->tag_set.ops = &blkfront_mq_ops;
+	info->tag_set.nr_hw_queues = 1;
+	info->tag_set.queue_depth =  BLK_RING_SIZE(info);
+	info->tag_set.numa_node = NUMA_NO_NODE;
+	info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	info->tag_set.cmd_size = 0;
+	info->tag_set.driver_data = info;
+
+	if (blk_mq_alloc_tag_set(&info->tag_set))
+		return -1;
+	rq = blk_mq_init_queue(&info->tag_set);
+	if (IS_ERR(rq)) {
+		blk_mq_free_tag_set(&info->tag_set);
 		return -1;
+	}
 
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
 
@@ -901,19 +903,15 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 static void xlvbd_release_gendisk(struct blkfront_info *info)
 {
 	unsigned int minor, nr_minors;
-	unsigned long flags;
 
 	if (info->rq == NULL)
 		return;
 
-	spin_lock_irqsave(&info->io_lock, flags);
-
 	/* No more blkif_request(). */
-	blk_stop_queue(info->rq);
+	blk_mq_stop_hw_queues(info->rq);
 
 	/* No more gnttab callback work. */
 	gnttab_cancel_free_callback(&info->callback);
-	spin_unlock_irqrestore(&info->io_lock, flags);
 
 	/* Flush gnttab callback work. Must be done with no locks held. */
 	flush_work(&info->work);
@@ -925,20 +923,18 @@ static void xlvbd_release_gendisk(struct blkfront_info *info)
 	xlbd_release_minors(minor, nr_minors);
 
 	blk_cleanup_queue(info->rq);
+	blk_mq_free_tag_set(&info->tag_set);
 	info->rq = NULL;
 
 	put_disk(info->gd);
 	info->gd = NULL;
 }
 
+/* Must be called with io_lock holded */
 static void kick_pending_request_queues(struct blkfront_info *info)
 {
-	if (!RING_FULL(&info->ring)) {
-		/* Re-enable calldowns. */
-		blk_start_queue(info->rq);
-		/* Kick things off immediately. */
-		do_blkif_request(info->rq);
-	}
+	if (!RING_FULL(&info->ring))
+		blk_mq_start_stopped_hw_queues(info->rq, true);
 }
 
 static void blkif_restart_queue(struct work_struct *work)
@@ -963,7 +959,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 		BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
 	/* No more blkif_request(). */
 	if (info->rq)
-		blk_stop_queue(info->rq);
+		blk_mq_stop_hw_queues(info->rq);
 
 	/* Remove all persistent grants */
 	if (!list_empty(&info->grants)) {
@@ -1128,8 +1124,10 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
 				 */
-				indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
-				list_add(&indirect_page->lru, &info->indirect_pages);
+				if (!info->feature_persistent) {
+					indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
+					list_add(&indirect_page->lru, &info->indirect_pages);
+				}
 				s->indirect_grants[i]->gref = GRANT_INVALID_REF;
 				list_add_tail(&s->indirect_grants[i]->node, &info->grants);
 			}
@@ -1144,7 +1142,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 	RING_IDX i, rp;
 	unsigned long flags;
 	struct blkfront_info *info = (struct blkfront_info *)dev_id;
-	int error;
 
 	spin_lock_irqsave(&info->io_lock, flags);
 
@@ -1185,37 +1182,37 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			continue;
 		}
 
-		error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+		req->errors = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
 		switch (bret->operation) {
 		case BLKIF_OP_DISCARD:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 					   info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				req->errors = -EOPNOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
 				queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
 			}
-			__blk_end_request_all(req, error);
+			blk_mq_complete_request(req);
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				req->errors = -EOPNOTSUPP;
 			}
 			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
 				     info->shadow[id].req.u.rw.nr_segments == 0)) {
 				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				req->errors = -EOPNOTSUPP;
 			}
-			if (unlikely(error)) {
-				if (error == -EOPNOTSUPP)
-					error = 0;
+			if (unlikely(req->errors)) {
+				if (req->errors == -EOPNOTSUPP)
+					req->errors = 0;
 				info->feature_flush = 0;
 				xlvbd_flush(info);
 			}
@@ -1226,7 +1223,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
 					"request: %x\n", bret->status);
 
-			__blk_end_request_all(req, error);
+			blk_mq_complete_request(req);
 			break;
 		default:
 			BUG();
@@ -1478,16 +1475,14 @@ static int blkfront_probe(struct xenbus_device *dev,
 	return 0;
 }
 
-static void split_bio_end(struct bio *bio, int error)
+static void split_bio_end(struct bio *bio)
 {
 	struct split_bio *split_bio = bio->bi_private;
 
-	if (error)
-		split_bio->err = error;
-
 	if (atomic_dec_and_test(&split_bio->pending)) {
 		split_bio->bio->bi_phys_segments = 0;
-		bio_endio(split_bio->bio, split_bio->err);
+		split_bio->bio->bi_error = bio->bi_error;
+		bio_endio(split_bio->bio);
 		kfree(split_bio);
 	}
 	bio_put(bio);
@@ -1519,7 +1514,7 @@ static int blkif_recover(struct blkfront_info *info)
 	info->shadow_free = info->ring.req_prod_pvt;
 	info->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
 
-	rc = blkfront_setup_indirect(info);
+	rc = blkfront_gather_backend_features(info);
 	if (rc) {
 		kfree(copy);
 		return rc;
@@ -1555,28 +1550,6 @@ static int blkif_recover(struct blkfront_info *info)
 
 	kfree(copy);
 
-	/*
-	 * Empty the queue, this is important because we might have
-	 * requests in the queue with more segments than what we
-	 * can handle now.
-	 */
-	spin_lock_irq(&info->io_lock);
-	while ((req = blk_fetch_request(info->rq)) != NULL) {
-		if (req->cmd_flags &
-		    (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
-			list_add(&req->queuelist, &requests);
-			continue;
-		}
-		merge_bio.head = req->bio;
-		merge_bio.tail = req->biotail;
-		bio_list_merge(&bio_list, &merge_bio);
-		req->bio = NULL;
-		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
-			pr_alert("diskcache flush request found!\n");
-		__blk_end_request_all(req, 0);
-	}
-	spin_unlock_irq(&info->io_lock);
-
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
 
 	spin_lock_irq(&info->io_lock);
@@ -1591,9 +1564,10 @@ static int blkif_recover(struct blkfront_info *info)
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
 		BUG_ON(req->nr_phys_segments > segs);
-		blk_requeue_request(info->rq, req);
+		blk_mq_requeue_request(req);
 	}
 	spin_unlock_irq(&info->io_lock);
+	blk_mq_kick_requeue_list(info->rq);
 
 	while ((bio = bio_list_pop(&bio_list)) != NULL) {
 		/* Traverse the list of pending bios and re-queue them */
@@ -1720,20 +1694,13 @@ static void blkfront_setup_discard(struct blkfront_info *info)
 
 static int blkfront_setup_indirect(struct blkfront_info *info)
 {
-	unsigned int indirect_segments, segs;
+	unsigned int segs;
 	int err, i;
 
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-max-indirect-segments", "%u", &indirect_segments,
-			    NULL);
-	if (err) {
-		info->max_indirect_segments = 0;
+	if (info->max_indirect_segments == 0)
 		segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	} else {
-		info->max_indirect_segments = min(indirect_segments,
-						  xen_blkif_max_segments);
+	else
 		segs = info->max_indirect_segments;
-	}
 
 	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info));
 	if (err)
@@ -1797,6 +1764,68 @@ out_of_memory:
 }
 
 /*
+ * Gather all backend feature-*
+ */
+static int blkfront_gather_backend_features(struct blkfront_info *info)
+{
+	int err;
+	int barrier, flush, discard, persistent;
+	unsigned int indirect_segments;
+
+	info->feature_flush = 0;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-barrier", "%d", &barrier,
+			NULL);
+
+	/*
+	 * If there's no "feature-barrier" defined, then it means
+	 * we're dealing with a very old backend which writes
+	 * synchronously; nothing to do.
+	 *
+	 * If there are barriers, then we use flush.
+	 */
+	if (!err && barrier)
+		info->feature_flush = REQ_FLUSH | REQ_FUA;
+	/*
+	 * And if there is "feature-flush-cache" use that above
+	 * barriers.
+	 */
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-flush-cache", "%d", &flush,
+			NULL);
+
+	if (!err && flush)
+		info->feature_flush = REQ_FLUSH;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-discard", "%d", &discard,
+			NULL);
+
+	if (!err && discard)
+		blkfront_setup_discard(info);
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-persistent", "%u", &persistent,
+			NULL);
+	if (err)
+		info->feature_persistent = 0;
+	else
+		info->feature_persistent = persistent;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			    "feature-max-indirect-segments", "%u", &indirect_segments,
+			    NULL);
+	if (err)
+		info->max_indirect_segments = 0;
+	else
+		info->max_indirect_segments = min(indirect_segments,
+						  xen_blkif_max_segments);
+
+	return blkfront_setup_indirect(info);
+}
+
+/*
  * Invoked when the backend is finally 'ready' (and has told produced
  * the details about the physical device - #sectors, size, etc).
  */
@@ -1807,7 +1836,6 @@ static void blkfront_connect(struct blkfront_info *info)
 	unsigned int physical_sector_size;
 	unsigned int binfo;
 	int err;
-	int barrier, flush, discard, persistent;
 
 	switch (info->connected) {
 	case BLKIF_STATE_CONNECTED:
@@ -1864,48 +1892,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	if (err != 1)
 		physical_sector_size = sector_size;
 
-	info->feature_flush = 0;
-
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-barrier", "%d", &barrier,
-			    NULL);
-
-	/*
-	 * If there's no "feature-barrier" defined, then it means
-	 * we're dealing with a very old backend which writes
-	 * synchronously; nothing to do.
-	 *
-	 * If there are barriers, then we use flush.
-	 */
-	if (!err && barrier)
-		info->feature_flush = REQ_FLUSH | REQ_FUA;
-	/*
-	 * And if there is "feature-flush-cache" use that above
-	 * barriers.
-	 */
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-flush-cache", "%d", &flush,
-			    NULL);
-
-	if (!err && flush)
-		info->feature_flush = REQ_FLUSH;
-
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-discard", "%d", &discard,
-			    NULL);
-
-	if (!err && discard)
-		blkfront_setup_discard(info);
-
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-persistent", "%u", &persistent,
-			    NULL);
-	if (err)
-		info->feature_persistent = 0;
-	else
-		info->feature_persistent = persistent;
-
-	err = blkfront_setup_indirect(info);
+	err = blkfront_gather_backend_features(info);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
 				 info->xbdev->otherend);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fb655e8d1e3b..9c01f5bfa33f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -496,10 +496,9 @@ static void zram_meta_free(struct zram_meta *meta, u64 disksize)
 	kfree(meta);
 }
 
-static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
+static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize)
 {
 	size_t num_pages;
-	char pool_name[8];
 	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
 
 	if (!meta)
@@ -512,7 +511,6 @@ static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
 		goto out_error;
 	}
 
-	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
 	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
@@ -850,7 +848,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		zram_bio_discard(zram, index, offset, bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -883,8 +881,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 		update_position(&index, &offset, &bvec);
 	}
 
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	return;
 
 out:
@@ -901,6 +898,8 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 	if (unlikely(!zram_meta_get(zram)))
 		goto error;
 
+	blk_queue_split(queue, &bio, queue->bio_split);
+
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
@@ -1031,7 +1030,7 @@ static ssize_t disksize_store(struct device *dev,
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
+	meta = zram_meta_alloc(zram->disk->disk_name, disksize);
 	if (!meta)
 		return -ENOMEM;
 
@@ -1244,7 +1243,7 @@ static int zram_add(void)
 	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
 	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
-	zram->disk->queue->limits.max_discard_sectors = UINT_MAX;
+	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
 	/*
 	 * zram_bio_discard() will clear all logical blocks if logical block
 	 * size is identical with physical block size(PAGE_SIZE). But if it is
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 2e777071e1dc..0bd88c942a52 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -13,6 +13,10 @@ config BT_RTL
 	tristate
 	select FW_LOADER
 
+config BT_QCA
+	tristate
+	select FW_LOADER
+
 config BT_HCIBTUSB
 	tristate "HCI USB driver"
 	depends on USB
@@ -132,6 +136,7 @@ config BT_HCIUART_3WIRE
 config BT_HCIUART_INTEL
 	bool "Intel protocol support"
 	depends on BT_HCIUART
+	select BT_HCIUART_H4
 	select BT_INTEL
 	help
 	  The Intel protocol support enables Bluetooth HCI over serial
@@ -150,6 +155,19 @@ config BT_HCIUART_BCM
 
 	  Say Y here to compile support for Broadcom protocol.
 
+config BT_HCIUART_QCA
+	bool "Qualcomm Atheros protocol support"
+	depends on BT_HCIUART
+	select BT_HCIUART_H4
+	select BT_QCA
+	help
+	  The Qualcomm Atheros protocol supports HCI In-Band Sleep feature
+	  over serial port interface(H4) between controller and host.
+	  This protocol is required for UART clock control for QCA Bluetooth
+	  devices.
+
+	  Say Y here to compile support for QCA protocol.
+
 config BT_HCIBCM203X
 	tristate "HCI BCM203x USB driver"
 	depends on USB
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index f40e194e7080..07c9cf381e5a 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_BT_MRVL_SDIO)	+= btmrvl_sdio.o
 obj-$(CONFIG_BT_WILINK)		+= btwilink.o
 obj-$(CONFIG_BT_BCM)		+= btbcm.o
 obj-$(CONFIG_BT_RTL)		+= btrtl.o
+obj-$(CONFIG_BT_QCA)		+= btqca.o
 
 btmrvl-y			:= btmrvl_main.o
 btmrvl-$(CONFIG_DEBUG_FS)	+= btmrvl_debugfs.o
@@ -34,6 +35,7 @@ hci_uart-$(CONFIG_BT_HCIUART_ATH3K)	+= hci_ath.o
 hci_uart-$(CONFIG_BT_HCIUART_3WIRE)	+= hci_h5.o
 hci_uart-$(CONFIG_BT_HCIUART_INTEL)	+= hci_intel.o
 hci_uart-$(CONFIG_BT_HCIUART_BCM)	+= hci_bcm.o
+hci_uart-$(CONFIG_BT_HCIUART_QCA)	+= hci_qca.o
 hci_uart-objs				:= $(hci_uart-y)
 
 ccflags-y += -D__CHECK_ENDIAN__
diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c
index fcfb72e9e0ee..a5c4d0584389 100644
--- a/drivers/bluetooth/bfusb.c
+++ b/drivers/bluetooth/bfusb.c
@@ -492,7 +492,7 @@ static int bfusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	case HCI_SCODATA_PKT:
 		hdev->stat.sco_tx++;
 		break;
-	};
+	}
 
 	/* Prepend skb with frame type */
 	memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1);
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index 7aab65427d38..a00bb82eb7c6 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -427,7 +427,7 @@ static int bt3c_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	case HCI_SCODATA_PKT:
 		hdev->stat.sco_tx++;
 		break;
-	};
+	}
 
 	/* Prepend skb with frame type */
 	memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1);
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index 1e1a4323a71f..02ed816a18f9 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -34,6 +34,7 @@
 
 #define BDADDR_BCM20702A0 (&(bdaddr_t) {{0x00, 0xa0, 0x02, 0x70, 0x20, 0x00}})
 #define BDADDR_BCM4324B3 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb3, 0x24, 0x43}})
+#define BDADDR_BCM4330B1 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb1, 0x30, 0x43}})
 
 int btbcm_check_bdaddr(struct hci_dev *hdev)
 {
@@ -66,9 +67,13 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	 *
 	 * The address 43:24:B3:00:00:00 indicates a BCM4324B3 controller
 	 * with waiting for configuration state.
+	 *
+	 * The address 43:30:B1:00:00:00 indicates a BCM4330B1 controller
+	 * with waiting for configuration state.
 	 */
 	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) ||
-	    !bacmp(&bda->bdaddr, BDADDR_BCM4324B3)) {
+	    !bacmp(&bda->bdaddr, BDADDR_BCM4324B3) ||
+	    !bacmp(&bda->bdaddr, BDADDR_BCM4330B1)) {
 		BT_INFO("%s: BCM: Using default device address (%pMR)",
 			hdev->name, &bda->bdaddr);
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
@@ -241,6 +246,7 @@ static const struct {
 	u16 subver;
 	const char *name;
 } bcm_uart_subver_table[] = {
+	{ 0x4103, "BCM4330B1"	},	/* 002.001.003 */
 	{ 0x410e, "BCM43341B0"	},	/* 002.001.014 */
 	{ 0x4406, "BCM4324B3"	},	/* 002.004.006 */
 	{ 0x610c, "BCM4354"	},	/* 003.001.012 */
@@ -472,12 +478,11 @@ int btbcm_setup_apple(struct hci_dev *hdev)
 
 	/* Read Verbose Config Version Info */
 	skb = btbcm_read_verbose_config(hdev);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	BT_INFO("%s: BCM: chip id %u build %4.4u", hdev->name, skb->data[1],
-		get_unaligned_le16(skb->data + 5));
-	kfree_skb(skb);
+	if (!IS_ERR(skb)) {
+		BT_INFO("%s: BCM: chip id %u build %4.4u", hdev->name, skb->data[1],
+			get_unaligned_le16(skb->data + 5));
+		kfree_skb(skb);
+	}
 
 	set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
 
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 828f2f8d1568..048423fd83bf 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -89,7 +89,89 @@ int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 }
 EXPORT_SYMBOL_GPL(btintel_set_bdaddr);
 
+void btintel_hw_error(struct hci_dev *hdev, u8 code)
+{
+	struct sk_buff *skb;
+	u8 type = 0x00;
+
+	BT_ERR("%s: Hardware error 0x%2.2x", hdev->name, code);
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Reset after hardware error failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return;
+	}
+	kfree_skb(skb);
+
+	skb = __hci_cmd_sync(hdev, 0xfc22, 1, &type, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Retrieving Intel exception info failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return;
+	}
+
+	if (skb->len != 13) {
+		BT_ERR("%s: Exception info size mismatch", hdev->name);
+		kfree_skb(skb);
+		return;
+	}
+
+	BT_ERR("%s: Exception info %s", hdev->name, (char *)(skb->data + 1));
+
+	kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(btintel_hw_error);
+
+void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver)
+{
+	const char *variant;
+
+	switch (ver->fw_variant) {
+	case 0x06:
+		variant = "Bootloader";
+		break;
+	case 0x23:
+		variant = "Firmware";
+		break;
+	default:
+		return;
+	}
+
+	BT_INFO("%s: %s revision %u.%u build %u week %u %u", hdev->name,
+		variant, ver->fw_revision >> 4, ver->fw_revision & 0x0f,
+		ver->fw_build_num, ver->fw_build_ww, 2000 + ver->fw_build_yy);
+}
+EXPORT_SYMBOL_GPL(btintel_version_info);
+
+int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen,
+			const void *param)
+{
+	while (plen > 0) {
+		struct sk_buff *skb;
+		u8 cmd_param[253], fragment_len = (plen > 252) ? 252 : plen;
+
+		cmd_param[0] = fragment_type;
+		memcpy(cmd_param + 1, param, fragment_len);
+
+		skb = __hci_cmd_sync(hdev, 0xfc09, fragment_len + 1,
+				     cmd_param, HCI_INIT_TIMEOUT);
+		if (IS_ERR(skb))
+			return PTR_ERR(skb);
+
+		kfree_skb(skb);
+
+		plen -= fragment_len;
+		param += fragment_len;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btintel_secure_send);
+
 MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
 MODULE_DESCRIPTION("Bluetooth support for Intel devices ver " VERSION);
 MODULE_VERSION(VERSION);
 MODULE_LICENSE("GPL");
+MODULE_FIRMWARE("intel/ibt-11-5.sfi");
+MODULE_FIRMWARE("intel/ibt-11-5.ddc");
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 4bda6ab34f60..b278d14758d5 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -73,6 +73,11 @@ struct intel_secure_send_result {
 
 int btintel_check_bdaddr(struct hci_dev *hdev);
 int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
+void btintel_hw_error(struct hci_dev *hdev, u8 code);
+
+void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver);
+int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen,
+			const void *param);
 
 #else
 
@@ -86,4 +91,18 @@ static inline int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdadd
 	return -EOPNOTSUPP;
 }
 
+static inline void btintel_hw_error(struct hci_dev *hdev, u8 code)
+{
+}
+
+static void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver)
+{
+}
+
+static inline int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type,
+				      u32 plen, const void *param)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h
index 086f0ec89580..27a9aac25583 100644
--- a/drivers/bluetooth/btmrvl_drv.h
+++ b/drivers/bluetooth/btmrvl_drv.h
@@ -95,10 +95,10 @@ struct btmrvl_private {
 	struct btmrvl_device btmrvl_dev;
 	struct btmrvl_adapter *adapter;
 	struct btmrvl_thread main_thread;
-	int (*hw_host_to_card) (struct btmrvl_private *priv,
+	int (*hw_host_to_card)(struct btmrvl_private *priv,
 				u8 *payload, u16 nb);
-	int (*hw_wakeup_firmware) (struct btmrvl_private *priv);
-	int (*hw_process_int_status) (struct btmrvl_private *priv);
+	int (*hw_wakeup_firmware)(struct btmrvl_private *priv);
+	int (*hw_process_int_status)(struct btmrvl_private *priv);
 	void (*firmware_dump)(struct btmrvl_private *priv);
 	spinlock_t driver_lock;		/* spinlock used by driver */
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index b9a811900f6a..b9978a7ba0cc 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -1071,8 +1071,6 @@ static int btmrvl_sdio_download_fw(struct btmrvl_sdio_card *card)
 		}
 	}
 
-	sdio_release_host(card->func);
-
 	/*
 	 * winner or not, with this test the FW synchronizes when the
 	 * module can continue its initialization
@@ -1082,6 +1080,8 @@ static int btmrvl_sdio_download_fw(struct btmrvl_sdio_card *card)
 		return -ETIMEDOUT;
 	}
 
+	sdio_release_host(card->func);
+
 	return 0;
 
 done:
@@ -1376,8 +1376,7 @@ done:
 
 	/* fw_dump_data will be free in device coredump release function
 	   after 5 min*/
-	dev_coredumpv(&priv->btmrvl_dev.hcidev->dev, fw_dump_data,
-		      fw_dump_len, GFP_KERNEL);
+	dev_coredumpv(&card->func->dev, fw_dump_data, fw_dump_len, GFP_KERNEL);
 	BT_INFO("== btmrvl firmware dump to /sys/class/devcoredump end");
 }
 
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
new file mode 100644
index 000000000000..4a6208168850
--- /dev/null
+++ b/drivers/bluetooth/btqca.c
@@ -0,0 +1,392 @@
+/*
+ *  Bluetooth supports for Qualcomm Atheros chips
+ *
+ *  Copyright (c) 2015 The Linux Foundation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+#include <linux/module.h>
+#include <linux/firmware.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "btqca.h"
+
+#define VERSION "0.1"
+
+static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
+{
+	struct sk_buff *skb;
+	struct edl_event_hdr *edl;
+	struct rome_version *ver;
+	char cmd;
+	int err = 0;
+
+	BT_DBG("%s: ROME Patch Version Request", hdev->name);
+
+	cmd = EDL_PATCH_VER_REQ_CMD;
+	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN,
+				&cmd, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		BT_ERR("%s: Failed to read version of ROME (%d)", hdev->name,
+		       err);
+		return err;
+	}
+
+	if (skb->len != sizeof(*edl) + sizeof(*ver)) {
+		BT_ERR("%s: Version size mismatch len %d", hdev->name,
+		       skb->len);
+		err = -EILSEQ;
+		goto out;
+	}
+
+	edl = (struct edl_event_hdr *)(skb->data);
+	if (!edl || !edl->data) {
+		BT_ERR("%s: TLV with no header or no data", hdev->name);
+		err = -EILSEQ;
+		goto out;
+	}
+
+	if (edl->cresp != EDL_CMD_REQ_RES_EVT ||
+	    edl->rtype != EDL_APP_VER_RES_EVT) {
+		BT_ERR("%s: Wrong packet received %d %d", hdev->name,
+		       edl->cresp, edl->rtype);
+		err = -EIO;
+		goto out;
+	}
+
+	ver = (struct rome_version *)(edl->data);
+
+	BT_DBG("%s: Product:0x%08x", hdev->name, le32_to_cpu(ver->product_id));
+	BT_DBG("%s: Patch  :0x%08x", hdev->name, le16_to_cpu(ver->patch_ver));
+	BT_DBG("%s: ROM    :0x%08x", hdev->name, le16_to_cpu(ver->rome_ver));
+	BT_DBG("%s: SOC    :0x%08x", hdev->name, le32_to_cpu(ver->soc_id));
+
+	/* ROME chipset version can be decided by patch and SoC
+	 * version, combination with upper 2 bytes from SoC
+	 * and lower 2 bytes from patch will be used.
+	 */
+	*rome_version = (le32_to_cpu(ver->soc_id) << 16) |
+		        (le16_to_cpu(ver->rome_ver) & 0x0000ffff);
+
+out:
+	kfree_skb(skb);
+
+	return err;
+}
+
+static int rome_reset(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	int err;
+
+	BT_DBG("%s: ROME HCI_RESET", hdev->name);
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		BT_ERR("%s: Reset failed (%d)", hdev->name, err);
+		return err;
+	}
+
+	kfree_skb(skb);
+
+	return 0;
+}
+
+static void rome_tlv_check_data(struct rome_config *config,
+				const struct firmware *fw)
+{
+	const u8 *data;
+	u32 type_len;
+	u16 tag_id, tag_len;
+	int idx, length;
+	struct tlv_type_hdr *tlv;
+	struct tlv_type_patch *tlv_patch;
+	struct tlv_type_nvm *tlv_nvm;
+
+	tlv = (struct tlv_type_hdr *)fw->data;
+
+	type_len = le32_to_cpu(tlv->type_len);
+	length = (type_len >> 8) & 0x00ffffff;
+
+	BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff);
+	BT_DBG("Length\t\t : %d bytes", length);
+
+	switch (config->type) {
+	case TLV_TYPE_PATCH:
+		tlv_patch = (struct tlv_type_patch *)tlv->data;
+		BT_DBG("Total Length\t\t : %d bytes",
+		       le32_to_cpu(tlv_patch->total_size));
+		BT_DBG("Patch Data Length\t : %d bytes",
+		       le32_to_cpu(tlv_patch->data_length));
+		BT_DBG("Signing Format Version : 0x%x",
+		       tlv_patch->format_version);
+		BT_DBG("Signature Algorithm\t : 0x%x",
+		       tlv_patch->signature);
+		BT_DBG("Reserved\t\t : 0x%x",
+		       le16_to_cpu(tlv_patch->reserved1));
+		BT_DBG("Product ID\t\t : 0x%04x",
+		       le16_to_cpu(tlv_patch->product_id));
+		BT_DBG("Rom Build Version\t : 0x%04x",
+		       le16_to_cpu(tlv_patch->rom_build));
+		BT_DBG("Patch Version\t\t : 0x%04x",
+		       le16_to_cpu(tlv_patch->patch_version));
+		BT_DBG("Reserved\t\t : 0x%x",
+		       le16_to_cpu(tlv_patch->reserved2));
+		BT_DBG("Patch Entry Address\t : 0x%x",
+		       le32_to_cpu(tlv_patch->entry));
+		break;
+
+	case TLV_TYPE_NVM:
+		idx = 0;
+		data = tlv->data;
+		while (idx < length) {
+			tlv_nvm = (struct tlv_type_nvm *)(data + idx);
+
+			tag_id = le16_to_cpu(tlv_nvm->tag_id);
+			tag_len = le16_to_cpu(tlv_nvm->tag_len);
+
+			/* Update NVM tags as needed */
+			switch (tag_id) {
+			case EDL_TAG_ID_HCI:
+				/* HCI transport layer parameters
+				 * enabling software inband sleep
+				 * onto controller side.
+				 */
+				tlv_nvm->data[0] |= 0x80;
+
+				/* UART Baud Rate */
+				tlv_nvm->data[2] = config->user_baud_rate;
+
+				break;
+
+			case EDL_TAG_ID_DEEP_SLEEP:
+				/* Sleep enable mask
+				 * enabling deep sleep feature on controller.
+				 */
+				tlv_nvm->data[0] |= 0x01;
+
+				break;
+			}
+
+			idx += (sizeof(u16) + sizeof(u16) + 8 + tag_len);
+		}
+		break;
+
+	default:
+		BT_ERR("Unknown TLV type %d", config->type);
+		break;
+	}
+}
+
+static int rome_tlv_send_segment(struct hci_dev *hdev, int idx, int seg_size,
+				 const u8 *data)
+{
+	struct sk_buff *skb;
+	struct edl_event_hdr *edl;
+	struct tlv_seg_resp *tlv_resp;
+	u8 cmd[MAX_SIZE_PER_TLV_SEGMENT + 2];
+	int err = 0;
+
+	BT_DBG("%s: Download segment #%d size %d", hdev->name, idx, seg_size);
+
+	cmd[0] = EDL_PATCH_TLV_REQ_CMD;
+	cmd[1] = seg_size;
+	memcpy(cmd + 2, data, seg_size);
+
+	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, seg_size + 2, cmd,
+				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		BT_ERR("%s: Failed to send TLV segment (%d)", hdev->name, err);
+		return err;
+	}
+
+	if (skb->len != sizeof(*edl) + sizeof(*tlv_resp)) {
+		BT_ERR("%s: TLV response size mismatch", hdev->name);
+		err = -EILSEQ;
+		goto out;
+	}
+
+	edl = (struct edl_event_hdr *)(skb->data);
+	if (!edl || !edl->data) {
+		BT_ERR("%s: TLV with no header or no data", hdev->name);
+		err = -EILSEQ;
+		goto out;
+	}
+
+	tlv_resp = (struct tlv_seg_resp *)(edl->data);
+
+	if (edl->cresp != EDL_CMD_REQ_RES_EVT ||
+	    edl->rtype != EDL_TVL_DNLD_RES_EVT || tlv_resp->result != 0x00) {
+		BT_ERR("%s: TLV with error stat 0x%x rtype 0x%x (0x%x)",
+		       hdev->name, edl->cresp, edl->rtype, tlv_resp->result);
+		err = -EIO;
+	}
+
+out:
+	kfree_skb(skb);
+
+	return err;
+}
+
+static int rome_tlv_download_request(struct hci_dev *hdev,
+				     const struct firmware *fw)
+{
+	const u8 *buffer, *data;
+	int total_segment, remain_size;
+	int ret, i;
+
+	if (!fw || !fw->data)
+		return -EINVAL;
+
+	total_segment = fw->size / MAX_SIZE_PER_TLV_SEGMENT;
+	remain_size = fw->size % MAX_SIZE_PER_TLV_SEGMENT;
+
+	BT_DBG("%s: Total segment num %d remain size %d total size %zu",
+	       hdev->name, total_segment, remain_size, fw->size);
+
+	data = fw->data;
+	for (i = 0; i < total_segment; i++) {
+		buffer = data + i * MAX_SIZE_PER_TLV_SEGMENT;
+		ret = rome_tlv_send_segment(hdev, i, MAX_SIZE_PER_TLV_SEGMENT,
+					    buffer);
+		if (ret < 0)
+			return -EIO;
+	}
+
+	if (remain_size) {
+		buffer = data + total_segment * MAX_SIZE_PER_TLV_SEGMENT;
+		ret = rome_tlv_send_segment(hdev, total_segment, remain_size,
+					    buffer);
+		if (ret < 0)
+			return -EIO;
+	}
+
+	return 0;
+}
+
+static int rome_download_firmware(struct hci_dev *hdev,
+				  struct rome_config *config)
+{
+	const struct firmware *fw;
+	int ret;
+
+	BT_INFO("%s: ROME Downloading %s", hdev->name, config->fwname);
+
+	ret = request_firmware(&fw, config->fwname, &hdev->dev);
+	if (ret) {
+		BT_ERR("%s: Failed to request file: %s (%d)", hdev->name,
+		       config->fwname, ret);
+		return ret;
+	}
+
+	rome_tlv_check_data(config, fw);
+
+	ret = rome_tlv_download_request(hdev, fw);
+	if (ret) {
+		BT_ERR("%s: Failed to download file: %s (%d)", hdev->name,
+		       config->fwname, ret);
+	}
+
+	release_firmware(fw);
+
+	return ret;
+}
+
+int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	struct sk_buff *skb;
+	u8 cmd[9];
+	int err;
+
+	cmd[0] = EDL_NVM_ACCESS_SET_REQ_CMD;
+	cmd[1] = 0x02; 			/* TAG ID */
+	cmd[2] = sizeof(bdaddr_t);	/* size */
+	memcpy(cmd + 3, bdaddr, sizeof(bdaddr_t));
+	skb = __hci_cmd_sync_ev(hdev, EDL_NVM_ACCESS_OPCODE, sizeof(cmd), cmd,
+				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		BT_ERR("%s: Change address command failed (%d)",
+		       hdev->name, err);
+		return err;
+	}
+
+	kfree_skb(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome);
+
+int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate)
+{
+	u32 rome_ver = 0;
+	struct rome_config config;
+	int err;
+
+	BT_DBG("%s: ROME setup on UART", hdev->name);
+
+	config.user_baud_rate = baudrate;
+
+	/* Get ROME version information */
+	err = rome_patch_ver_req(hdev, &rome_ver);
+	if (err < 0 || rome_ver == 0) {
+		BT_ERR("%s: Failed to get version 0x%x", hdev->name, err);
+		return err;
+	}
+
+	BT_INFO("%s: ROME controller version 0x%08x", hdev->name, rome_ver);
+
+	/* Download rampatch file */
+	config.type = TLV_TYPE_PATCH;
+	snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin",
+		 rome_ver);
+	err = rome_download_firmware(hdev, &config);
+	if (err < 0) {
+		BT_ERR("%s: Failed to download patch (%d)", hdev->name, err);
+		return err;
+	}
+
+	/* Download NVM configuration */
+	config.type = TLV_TYPE_NVM;
+	snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin",
+		 rome_ver);
+	err = rome_download_firmware(hdev, &config);
+	if (err < 0) {
+		BT_ERR("%s: Failed to download NVM (%d)", hdev->name, err);
+		return err;
+	}
+
+	/* Perform HCI reset */
+	err = rome_reset(hdev);
+	if (err < 0) {
+		BT_ERR("%s: Failed to run HCI_RESET (%d)", hdev->name, err);
+		return err;
+	}
+
+	BT_INFO("%s: ROME setup on UART is completed", hdev->name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(qca_uart_setup_rome);
+
+MODULE_AUTHOR("Ben Young Tae Kim <ytkim@qca.qualcomm.com>");
+MODULE_DESCRIPTION("Bluetooth support for Qualcomm Atheros family ver " VERSION);
+MODULE_VERSION(VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
new file mode 100644
index 000000000000..65e994b96c47
--- /dev/null
+++ b/drivers/bluetooth/btqca.h
@@ -0,0 +1,135 @@
+/*
+ *  Bluetooth supports for Qualcomm Atheros ROME chips
+ *
+ *  Copyright (c) 2015 The Linux Foundation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#define EDL_PATCH_CMD_OPCODE		(0xFC00)
+#define EDL_NVM_ACCESS_OPCODE		(0xFC0B)
+#define EDL_PATCH_CMD_LEN		(1)
+#define EDL_PATCH_VER_REQ_CMD		(0x19)
+#define EDL_PATCH_TLV_REQ_CMD		(0x1E)
+#define EDL_NVM_ACCESS_SET_REQ_CMD	(0x01)
+#define MAX_SIZE_PER_TLV_SEGMENT	(243)
+
+#define EDL_CMD_REQ_RES_EVT		(0x00)
+#define EDL_PATCH_VER_RES_EVT		(0x19)
+#define EDL_APP_VER_RES_EVT		(0x02)
+#define EDL_TVL_DNLD_RES_EVT		(0x04)
+#define EDL_CMD_EXE_STATUS_EVT		(0x00)
+#define EDL_SET_BAUDRATE_RSP_EVT	(0x92)
+#define EDL_NVM_ACCESS_CODE_EVT		(0x0B)
+
+#define EDL_TAG_ID_HCI			(17)
+#define EDL_TAG_ID_DEEP_SLEEP		(27)
+
+enum qca_bardrate {
+	QCA_BAUDRATE_115200 	= 0,
+	QCA_BAUDRATE_57600,
+	QCA_BAUDRATE_38400,
+	QCA_BAUDRATE_19200,
+	QCA_BAUDRATE_9600,
+	QCA_BAUDRATE_230400,
+	QCA_BAUDRATE_250000,
+	QCA_BAUDRATE_460800,
+	QCA_BAUDRATE_500000,
+	QCA_BAUDRATE_720000,
+	QCA_BAUDRATE_921600,
+	QCA_BAUDRATE_1000000,
+	QCA_BAUDRATE_1250000,
+	QCA_BAUDRATE_2000000,
+	QCA_BAUDRATE_3000000,
+	QCA_BAUDRATE_4000000,
+	QCA_BAUDRATE_1600000,
+	QCA_BAUDRATE_3200000,
+	QCA_BAUDRATE_3500000,
+	QCA_BAUDRATE_AUTO 	= 0xFE,
+	QCA_BAUDRATE_RESERVED
+};
+
+enum rome_tlv_type {
+	TLV_TYPE_PATCH = 1,
+	TLV_TYPE_NVM
+};
+
+struct rome_config {
+	u8 type;
+	char fwname[64];
+	uint8_t user_baud_rate;
+};
+
+struct edl_event_hdr {
+	__u8 cresp;
+	__u8 rtype;
+	__u8 data[0];
+} __packed;
+
+struct rome_version {
+	__le32 product_id;
+	__le16 patch_ver;
+	__le16 rome_ver;
+	__le32 soc_id;
+} __packed;
+
+struct tlv_seg_resp {
+	__u8 result;
+} __packed;
+
+struct tlv_type_patch {
+	__le32 total_size;
+	__le32 data_length;
+	__u8   format_version;
+	__u8   signature;
+	__le16 reserved1;
+	__le16 product_id;
+	__le16 rom_build;
+	__le16 patch_version;
+	__le16 reserved2;
+	__le32 entry;
+} __packed;
+
+struct tlv_type_nvm {
+	__le16 tag_id;
+	__le16 tag_len;
+	__le32 reserve1;
+	__le32 reserve2;
+	__u8   data[0];
+} __packed;
+
+struct tlv_type_hdr {
+	__le32 type_len;
+	__u8   data[0];
+} __packed;
+
+#if IS_ENABLED(CONFIG_BT_QCA)
+
+int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr);
+int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate);
+
+#else
+
+static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int qca_uart_setup_rome(struct hci_dev *hdev, int speed)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b4cf8d9c9dac..b6aceaf82aa8 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -68,6 +68,9 @@ static const struct usb_device_id btusb_table[] = {
 	/* Generic Bluetooth AMP device */
 	{ USB_DEVICE_INFO(0xe0, 0x01, 0x04), .driver_info = BTUSB_AMP },
 
+	/* Generic Bluetooth USB interface */
+	{ USB_INTERFACE_INFO(0xe0, 0x01, 0x01) },
+
 	/* Apple-specific (Broadcom) devices */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x05ac, 0xff, 0x01, 0x01),
 	  .driver_info = BTUSB_BCM_APPLE },
@@ -319,6 +322,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3461), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3462), .driver_info = BTUSB_REALTEK },
 
+	/* Silicon Wave based devices */
+	{ USB_DEVICE(0x0c10, 0x0000), .driver_info = BTUSB_SWAVE },
+
 	{ }	/* Terminating entry */
 };
 
@@ -1575,7 +1581,7 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 
 	/* fw_patch_num indicates the version of patch the device currently
 	 * have. If there is no patch data in the device, it is always 0x00.
-	 * So, if it is other than 0x00, no need to patch the deivce again.
+	 * So, if it is other than 0x00, no need to patch the device again.
 	 */
 	if (ver->fw_patch_num) {
 		BT_INFO("%s: Intel device is already patched. patch num: %02x",
@@ -1878,51 +1884,6 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
 	return -EILSEQ;
 }
 
-static int btusb_intel_secure_send(struct hci_dev *hdev, u8 fragment_type,
-				   u32 plen, const void *param)
-{
-	while (plen > 0) {
-		struct sk_buff *skb;
-		u8 cmd_param[253], fragment_len = (plen > 252) ? 252 : plen;
-
-		cmd_param[0] = fragment_type;
-		memcpy(cmd_param + 1, param, fragment_len);
-
-		skb = __hci_cmd_sync(hdev, 0xfc09, fragment_len + 1,
-				     cmd_param, HCI_INIT_TIMEOUT);
-		if (IS_ERR(skb))
-			return PTR_ERR(skb);
-
-		kfree_skb(skb);
-
-		plen -= fragment_len;
-		param += fragment_len;
-	}
-
-	return 0;
-}
-
-static void btusb_intel_version_info(struct hci_dev *hdev,
-				     struct intel_version *ver)
-{
-	const char *variant;
-
-	switch (ver->fw_variant) {
-	case 0x06:
-		variant = "Bootloader";
-		break;
-	case 0x23:
-		variant = "Firmware";
-		break;
-	default:
-		return;
-	}
-
-	BT_INFO("%s: %s revision %u.%u build %u week %u %u", hdev->name,
-		variant, ver->fw_revision >> 4, ver->fw_revision & 0x0f,
-		ver->fw_build_num, ver->fw_build_ww, 2000 + ver->fw_build_yy);
-}
-
 static int btusb_setup_intel_new(struct hci_dev *hdev)
 {
 	static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01,
@@ -1984,7 +1945,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return -EINVAL;
 	}
 
-	btusb_intel_version_info(hdev, ver);
+	btintel_version_info(hdev, ver);
 
 	/* The firmware variant determines if the device is in bootloader
 	 * mode or is running operational firmware. The value 0x06 identifies
@@ -2104,7 +2065,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	/* Start the firmware download transaction with the Init fragment
 	 * represented by the 128 bytes of CSS header.
 	 */
-	err = btusb_intel_secure_send(hdev, 0x00, 128, fw->data);
+	err = btintel_secure_send(hdev, 0x00, 128, fw->data);
 	if (err < 0) {
 		BT_ERR("%s: Failed to send firmware header (%d)",
 		       hdev->name, err);
@@ -2114,7 +2075,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	/* Send the 256 bytes of public key information from the firmware
 	 * as the PKey fragment.
 	 */
-	err = btusb_intel_secure_send(hdev, 0x03, 256, fw->data + 128);
+	err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128);
 	if (err < 0) {
 		BT_ERR("%s: Failed to send firmware public key (%d)",
 		       hdev->name, err);
@@ -2124,7 +2085,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	/* Send the 256 bytes of signature information from the firmware
 	 * as the Sign fragment.
 	 */
-	err = btusb_intel_secure_send(hdev, 0x02, 256, fw->data + 388);
+	err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388);
 	if (err < 0) {
 		BT_ERR("%s: Failed to send firmware signature (%d)",
 		       hdev->name, err);
@@ -2139,7 +2100,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 
 		frag_len += sizeof(*cmd) + cmd->plen;
 
-		/* The paramter length of the secure send command requires
+		/* The parameter length of the secure send command requires
 		 * a 4 byte alignment. It happens so that the firmware file
 		 * contains proper Intel_NOP commands to align the fragments
 		 * as needed.
@@ -2148,8 +2109,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		 * firmware data buffer as a single Data fragement.
 		 */
 		if (!(frag_len % 4)) {
-			err = btusb_intel_secure_send(hdev, 0x01, frag_len,
-						      fw_ptr);
+			err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr);
 			if (err < 0) {
 				BT_ERR("%s: Failed to send firmware data (%d)",
 				       hdev->name, err);
@@ -2291,39 +2251,6 @@ done:
 	return 0;
 }
 
-static void btusb_hw_error_intel(struct hci_dev *hdev, u8 code)
-{
-	struct sk_buff *skb;
-	u8 type = 0x00;
-
-	BT_ERR("%s: Hardware error 0x%2.2x", hdev->name, code);
-
-	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb)) {
-		BT_ERR("%s: Reset after hardware error failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
-		return;
-	}
-	kfree_skb(skb);
-
-	skb = __hci_cmd_sync(hdev, 0xfc22, 1, &type, HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb)) {
-		BT_ERR("%s: Retrieving Intel exception info failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
-		return;
-	}
-
-	if (skb->len != 13) {
-		BT_ERR("%s: Exception info size mismatch", hdev->name);
-		kfree_skb(skb);
-		return;
-	}
-
-	BT_ERR("%s: Exception info %s", hdev->name, (char *)(skb->data + 1));
-
-	kfree_skb(skb);
-}
-
 static int btusb_shutdown_intel(struct hci_dev *hdev)
 {
 	struct sk_buff *skb;
@@ -2783,7 +2710,7 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info & BTUSB_INTEL_NEW) {
 		hdev->send = btusb_send_frame_intel;
 		hdev->setup = btusb_setup_intel_new;
-		hdev->hw_error = btusb_hw_error_intel;
+		hdev->hw_error = btintel_hw_error;
 		hdev->set_bdaddr = btintel_set_bdaddr;
 		set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
 	}
diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c
index 78e10f0c65b2..84135c54ed2e 100644
--- a/drivers/bluetooth/dtl1_cs.c
+++ b/drivers/bluetooth/dtl1_cs.c
@@ -182,9 +182,9 @@ static void dtl1_control(struct dtl1_info *info, struct sk_buff *skb)
 	int i;
 
 	printk(KERN_INFO "Bluetooth: Nokia control data =");
-	for (i = 0; i < skb->len; i++) {
+	for (i = 0; i < skb->len; i++)
 		printk(" %02x", skb->data[i]);
-	}
+
 	printk("\n");
 
 	/* transition to active state */
@@ -406,7 +406,7 @@ static int dtl1_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	default:
 		return -EILSEQ;
-	};
+	}
 
 	nsh.zero = 0;
 	nsh.len = skb->len;
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 23523e140a9a..835bfab88ef5 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -25,6 +25,12 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/gpio/consumer.h>
+#include <linux/tty.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -32,11 +38,37 @@
 #include "btbcm.h"
 #include "hci_uart.h"
 
+struct bcm_device {
+	struct list_head	list;
+
+	struct platform_device	*pdev;
+
+	const char		*name;
+	struct gpio_desc	*device_wakeup;
+	struct gpio_desc	*shutdown;
+
+	struct clk		*clk;
+	bool			clk_enabled;
+
+	u32			init_speed;
+
+#ifdef CONFIG_PM_SLEEP
+	struct hci_uart		*hu;
+	bool			is_suspended; /* suspend/resume flag */
+#endif
+};
+
 struct bcm_data {
-	struct sk_buff *rx_skb;
-	struct sk_buff_head txq;
+	struct sk_buff		*rx_skb;
+	struct sk_buff_head	txq;
+
+	struct bcm_device	*dev;
 };
 
+/* List of BCM BT UART devices */
+static DEFINE_SPINLOCK(bcm_device_lock);
+static LIST_HEAD(bcm_device_list);
+
 static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed)
 {
 	struct hci_dev *hdev = hu->hdev;
@@ -86,9 +118,41 @@ static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed)
 	return 0;
 }
 
+/* bcm_device_exists should be protected by bcm_device_lock */
+static bool bcm_device_exists(struct bcm_device *device)
+{
+	struct list_head *p;
+
+	list_for_each(p, &bcm_device_list) {
+		struct bcm_device *dev = list_entry(p, struct bcm_device, list);
+
+		if (device == dev)
+			return true;
+	}
+
+	return false;
+}
+
+static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
+{
+	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled)
+		clk_enable(dev->clk);
+
+	gpiod_set_value(dev->shutdown, powered);
+	gpiod_set_value(dev->device_wakeup, powered);
+
+	if (!powered && !IS_ERR(dev->clk) && dev->clk_enabled)
+		clk_disable(dev->clk);
+
+	dev->clk_enabled = powered;
+
+	return 0;
+}
+
 static int bcm_open(struct hci_uart *hu)
 {
 	struct bcm_data *bcm;
+	struct list_head *p;
 
 	BT_DBG("hu %p", hu);
 
@@ -99,6 +163,30 @@ static int bcm_open(struct hci_uart *hu)
 	skb_queue_head_init(&bcm->txq);
 
 	hu->priv = bcm;
+
+	spin_lock(&bcm_device_lock);
+	list_for_each(p, &bcm_device_list) {
+		struct bcm_device *dev = list_entry(p, struct bcm_device, list);
+
+		/* Retrieve saved bcm_device based on parent of the
+		 * platform device (saved during device probe) and
+		 * parent of tty device used by hci_uart
+		 */
+		if (hu->tty->dev->parent == dev->pdev->dev.parent) {
+			bcm->dev = dev;
+			hu->init_speed = dev->init_speed;
+#ifdef CONFIG_PM_SLEEP
+			dev->hu = hu;
+#endif
+			break;
+		}
+	}
+
+	if (bcm->dev)
+		bcm_gpio_set_power(bcm->dev, true);
+
+	spin_unlock(&bcm_device_lock);
+
 	return 0;
 }
 
@@ -108,6 +196,16 @@ static int bcm_close(struct hci_uart *hu)
 
 	BT_DBG("hu %p", hu);
 
+	/* Protect bcm->dev against removal of the device or driver */
+	spin_lock(&bcm_device_lock);
+	if (bcm_device_exists(bcm->dev)) {
+		bcm_gpio_set_power(bcm->dev, false);
+#ifdef CONFIG_PM_SLEEP
+		bcm->dev->hu = NULL;
+#endif
+	}
+	spin_unlock(&bcm_device_lock);
+
 	skb_queue_purge(&bcm->txq);
 	kfree_skb(bcm->rx_skb);
 	kfree(bcm);
@@ -232,6 +330,204 @@ static struct sk_buff *bcm_dequeue(struct hci_uart *hu)
 	return skb_dequeue(&bcm->txq);
 }
 
+#ifdef CONFIG_PM_SLEEP
+/* Platform suspend callback */
+static int bcm_suspend(struct device *dev)
+{
+	struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev));
+
+	BT_DBG("suspend (%p): is_suspended %d", bdev, bdev->is_suspended);
+
+	spin_lock(&bcm_device_lock);
+
+	if (!bdev->hu)
+		goto unlock;
+
+	if (!bdev->is_suspended) {
+		hci_uart_set_flow_control(bdev->hu, true);
+
+		/* Once this callback returns, driver suspends BT via GPIO */
+		bdev->is_suspended = true;
+	}
+
+	/* Suspend the device */
+	if (bdev->device_wakeup) {
+		gpiod_set_value(bdev->device_wakeup, false);
+		BT_DBG("suspend, delaying 15 ms");
+		mdelay(15);
+	}
+
+unlock:
+	spin_unlock(&bcm_device_lock);
+
+	return 0;
+}
+
+/* Platform resume callback */
+static int bcm_resume(struct device *dev)
+{
+	struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev));
+
+	BT_DBG("resume (%p): is_suspended %d", bdev, bdev->is_suspended);
+
+	spin_lock(&bcm_device_lock);
+
+	if (!bdev->hu)
+		goto unlock;
+
+	if (bdev->device_wakeup) {
+		gpiod_set_value(bdev->device_wakeup, true);
+		BT_DBG("resume, delaying 15 ms");
+		mdelay(15);
+	}
+
+	/* When this callback executes, the device has woken up already */
+	if (bdev->is_suspended) {
+		bdev->is_suspended = false;
+
+		hci_uart_set_flow_control(bdev->hu, false);
+	}
+
+unlock:
+	spin_unlock(&bcm_device_lock);
+
+	return 0;
+}
+#endif
+
+static const struct acpi_gpio_params device_wakeup_gpios = { 0, 0, false };
+static const struct acpi_gpio_params shutdown_gpios = { 1, 0, false };
+
+static const struct acpi_gpio_mapping acpi_bcm_default_gpios[] = {
+	{ "device-wakeup-gpios", &device_wakeup_gpios, 1 },
+	{ "shutdown-gpios", &shutdown_gpios, 1 },
+	{ },
+};
+
+#ifdef CONFIG_ACPI
+static int bcm_resource(struct acpi_resource *ares, void *data)
+{
+	struct bcm_device *dev = data;
+
+	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
+		struct acpi_resource_uart_serialbus *sb;
+
+		sb = &ares->data.uart_serial_bus;
+		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_UART)
+			dev->init_speed = sb->default_baud_rate;
+	}
+
+	/* Always tell the ACPI core to skip this resource */
+	return 1;
+}
+
+static int bcm_acpi_probe(struct bcm_device *dev)
+{
+	struct platform_device *pdev = dev->pdev;
+	const struct acpi_device_id *id;
+	struct acpi_device *adev;
+	LIST_HEAD(resources);
+	int ret;
+
+	id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev);
+	if (!id)
+		return -ENODEV;
+
+	/* Retrieve GPIO data */
+	dev->name = dev_name(&pdev->dev);
+	ret = acpi_dev_add_driver_gpios(ACPI_COMPANION(&pdev->dev),
+					acpi_bcm_default_gpios);
+	if (ret)
+		return ret;
+
+	dev->clk = devm_clk_get(&pdev->dev, NULL);
+
+	dev->device_wakeup = devm_gpiod_get_optional(&pdev->dev,
+						     "device-wakeup",
+						     GPIOD_OUT_LOW);
+	if (IS_ERR(dev->device_wakeup))
+		return PTR_ERR(dev->device_wakeup);
+
+	dev->shutdown = devm_gpiod_get_optional(&pdev->dev, "shutdown",
+						GPIOD_OUT_LOW);
+	if (IS_ERR(dev->shutdown))
+		return PTR_ERR(dev->shutdown);
+
+	/* Make sure at-least one of the GPIO is defined and that
+	 * a name is specified for this instance
+	 */
+	if ((!dev->device_wakeup && !dev->shutdown) || !dev->name) {
+		dev_err(&pdev->dev, "invalid platform data\n");
+		return -EINVAL;
+	}
+
+	/* Retrieve UART ACPI info */
+	adev = ACPI_COMPANION(&dev->pdev->dev);
+	if (!adev)
+		return 0;
+
+	acpi_dev_get_resources(adev, &resources, bcm_resource, dev);
+
+	return 0;
+}
+#else
+static int bcm_acpi_probe(struct bcm_device *dev)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_ACPI */
+
+static int bcm_probe(struct platform_device *pdev)
+{
+	struct bcm_device *dev;
+	struct acpi_device_id *pdata = pdev->dev.platform_data;
+	int ret;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->pdev = pdev;
+
+	if (ACPI_HANDLE(&pdev->dev)) {
+		ret = bcm_acpi_probe(dev);
+		if (ret)
+			return ret;
+	} else if (pdata) {
+		dev->name = pdata->id;
+	} else {
+		return -ENODEV;
+	}
+
+	platform_set_drvdata(pdev, dev);
+
+	dev_info(&pdev->dev, "%s device registered.\n", dev->name);
+
+	/* Place this instance on the device list */
+	spin_lock(&bcm_device_lock);
+	list_add_tail(&dev->list, &bcm_device_list);
+	spin_unlock(&bcm_device_lock);
+
+	bcm_gpio_set_power(dev, false);
+
+	return 0;
+}
+
+static int bcm_remove(struct platform_device *pdev)
+{
+	struct bcm_device *dev = platform_get_drvdata(pdev);
+
+	spin_lock(&bcm_device_lock);
+	list_del(&dev->list);
+	spin_unlock(&bcm_device_lock);
+
+	acpi_dev_remove_driver_gpios(ACPI_COMPANION(&pdev->dev));
+
+	dev_info(&pdev->dev, "%s device unregistered.\n", dev->name);
+
+	return 0;
+}
+
 static const struct hci_uart_proto bcm_proto = {
 	.id		= HCI_UART_BCM,
 	.name		= "BCM",
@@ -247,12 +543,38 @@ static const struct hci_uart_proto bcm_proto = {
 	.dequeue	= bcm_dequeue,
 };
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id bcm_acpi_match[] = {
+	{ "BCM2E39", 0 },
+	{ "BCM2E67", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, bcm_acpi_match);
+#endif
+
+/* Platform suspend and resume callbacks */
+static SIMPLE_DEV_PM_OPS(bcm_pm_ops, bcm_suspend, bcm_resume);
+
+static struct platform_driver bcm_driver = {
+	.probe = bcm_probe,
+	.remove = bcm_remove,
+	.driver = {
+		.name = "hci_bcm",
+		.acpi_match_table = ACPI_PTR(bcm_acpi_match),
+		.pm = &bcm_pm_ops,
+	},
+};
+
 int __init bcm_init(void)
 {
+	platform_driver_register(&bcm_driver);
+
 	return hci_uart_register_proto(&bcm_proto);
 }
 
 int __exit bcm_deinit(void)
 {
+	platform_driver_unregister(&bcm_driver);
+
 	return hci_uart_unregister_proto(&bcm_proto);
 }
diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
index 57faddc53645..eec3f28e4bb9 100644
--- a/drivers/bluetooth/hci_h4.c
+++ b/drivers/bluetooth/hci_h4.c
@@ -223,8 +223,7 @@ struct sk_buff *h4_recv_buf(struct hci_dev *hdev, struct sk_buff *skb,
 			switch ((&pkts[i])->lsize) {
 			case 0:
 				/* No variable data length */
-				(&pkts[i])->recv(hdev, skb);
-				skb = NULL;
+				dlen = 0;
 				break;
 			case 1:
 				/* Single octet variable length */
@@ -252,6 +251,12 @@ struct sk_buff *h4_recv_buf(struct hci_dev *hdev, struct sk_buff *skb,
 				kfree_skb(skb);
 				return ERR_PTR(-EILSEQ);
 			}
+
+			if (!dlen) {
+				/* No more data, complete frame */
+				(&pkts[i])->recv(hdev, skb);
+				skb = NULL;
+			}
 		} else {
 			/* Complete frame */
 			(&pkts[i])->recv(hdev, skb);
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 3455cecc9ecf..b35b238a0380 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -75,7 +75,7 @@ struct h5 {
 	size_t			rx_pending;	/* Expecting more bytes */
 	u8			rx_ack;		/* Last ack number received */
 
-	int			(*rx_func) (struct hci_uart *hu, u8 c);
+	int			(*rx_func)(struct hci_uart *hu, u8 c);
 
 	struct timer_list	timer;		/* Retransmission timer */
 
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 5dd07bf05236..cf07d1121956 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -24,8 +24,864 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/skbuff.h>
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/tty.h>
+#include <linux/platform_device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/acpi.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
 #include "hci_uart.h"
+#include "btintel.h"
+
+#define STATE_BOOTLOADER	0
+#define STATE_DOWNLOADING	1
+#define STATE_FIRMWARE_LOADED	2
+#define STATE_FIRMWARE_FAILED	3
+#define STATE_BOOTING		4
+
+struct intel_device {
+	struct list_head list;
+	struct platform_device *pdev;
+	struct gpio_desc *reset;
+};
+
+static LIST_HEAD(intel_device_list);
+static DEFINE_SPINLOCK(intel_device_list_lock);
+
+struct intel_data {
+	struct sk_buff *rx_skb;
+	struct sk_buff_head txq;
+	unsigned long flags;
+};
+
+static u8 intel_convert_speed(unsigned int speed)
+{
+	switch (speed) {
+	case 9600:
+		return 0x00;
+	case 19200:
+		return 0x01;
+	case 38400:
+		return 0x02;
+	case 57600:
+		return 0x03;
+	case 115200:
+		return 0x04;
+	case 230400:
+		return 0x05;
+	case 460800:
+		return 0x06;
+	case 921600:
+		return 0x07;
+	case 1843200:
+		return 0x08;
+	case 3250000:
+		return 0x09;
+	case 2000000:
+		return 0x0a;
+	case 3000000:
+		return 0x0b;
+	default:
+		return 0xff;
+	}
+}
+
+static int intel_wait_booting(struct hci_uart *hu)
+{
+	struct intel_data *intel = hu->priv;
+	int err;
+
+	err = wait_on_bit_timeout(&intel->flags, STATE_BOOTING,
+				  TASK_INTERRUPTIBLE,
+				  msecs_to_jiffies(1000));
+
+	if (err == 1) {
+		BT_ERR("%s: Device boot interrupted", hu->hdev->name);
+		return -EINTR;
+	}
+
+	if (err) {
+		BT_ERR("%s: Device boot timeout", hu->hdev->name);
+		return -ETIMEDOUT;
+	}
+
+	return err;
+}
+
+static int intel_set_power(struct hci_uart *hu, bool powered)
+{
+	struct list_head *p;
+	int err = -ENODEV;
+
+	spin_lock(&intel_device_list_lock);
+
+	list_for_each(p, &intel_device_list) {
+		struct intel_device *idev = list_entry(p, struct intel_device,
+						       list);
+
+		/* tty device and pdev device should share the same parent
+		 * which is the UART port.
+		 */
+		if (hu->tty->dev->parent != idev->pdev->dev.parent)
+			continue;
+
+		if (!idev->reset) {
+			err = -ENOTSUPP;
+			break;
+		}
+
+		BT_INFO("hu %p, Switching compatible pm device (%s) to %u",
+			hu, dev_name(&idev->pdev->dev), powered);
+
+		gpiod_set_value(idev->reset, powered);
+	}
+
+	spin_unlock(&intel_device_list_lock);
+
+	return err;
+}
+
+static int intel_open(struct hci_uart *hu)
+{
+	struct intel_data *intel;
+
+	BT_DBG("hu %p", hu);
+
+	intel = kzalloc(sizeof(*intel), GFP_KERNEL);
+	if (!intel)
+		return -ENOMEM;
+
+	skb_queue_head_init(&intel->txq);
+
+	hu->priv = intel;
+
+	if (!intel_set_power(hu, true))
+		set_bit(STATE_BOOTING, &intel->flags);
+
+	return 0;
+}
+
+static int intel_close(struct hci_uart *hu)
+{
+	struct intel_data *intel = hu->priv;
+
+	BT_DBG("hu %p", hu);
+
+	intel_set_power(hu, false);
+
+	skb_queue_purge(&intel->txq);
+	kfree_skb(intel->rx_skb);
+	kfree(intel);
+
+	hu->priv = NULL;
+	return 0;
+}
+
+static int intel_flush(struct hci_uart *hu)
+{
+	struct intel_data *intel = hu->priv;
+
+	BT_DBG("hu %p", hu);
+
+	skb_queue_purge(&intel->txq);
+
+	return 0;
+}
+
+static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode)
+{
+	struct sk_buff *skb;
+	struct hci_event_hdr *hdr;
+	struct hci_ev_cmd_complete *evt;
+
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = (struct hci_event_hdr *)skb_put(skb, sizeof(*hdr));
+	hdr->evt = HCI_EV_CMD_COMPLETE;
+	hdr->plen = sizeof(*evt) + 1;
+
+	evt = (struct hci_ev_cmd_complete *)skb_put(skb, sizeof(*evt));
+	evt->ncmd = 0x01;
+	evt->opcode = cpu_to_le16(opcode);
+
+	*skb_put(skb, 1) = 0x00;
+
+	bt_cb(skb)->pkt_type = HCI_EVENT_PKT;
+
+	return hci_recv_frame(hdev, skb);
+}
+
+static int intel_set_baudrate(struct hci_uart *hu, unsigned int speed)
+{
+	struct intel_data *intel = hu->priv;
+	struct hci_dev *hdev = hu->hdev;
+	u8 speed_cmd[] = { 0x06, 0xfc, 0x01, 0x00 };
+	struct sk_buff *skb;
+	int err;
+
+	/* This can be the first command sent to the chip, check
+	 * that the controller is ready.
+	 */
+	err = intel_wait_booting(hu);
+
+	clear_bit(STATE_BOOTING, &intel->flags);
+
+	/* In case of timeout, try to continue anyway */
+	if (err && err != ETIMEDOUT)
+		return err;
+
+	BT_INFO("%s: Change controller speed to %d", hdev->name, speed);
+
+	speed_cmd[3] = intel_convert_speed(speed);
+	if (speed_cmd[3] == 0xff) {
+		BT_ERR("%s: Unsupported speed", hdev->name);
+		return -EINVAL;
+	}
+
+	/* Device will not accept speed change if Intel version has not been
+	 * previously requested.
+	 */
+	skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Reading Intel version information failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+	kfree_skb(skb);
+
+	skb = bt_skb_alloc(sizeof(speed_cmd), GFP_KERNEL);
+	if (!skb) {
+		BT_ERR("%s: Failed to allocate memory for baudrate packet",
+		       hdev->name);
+		return -ENOMEM;
+	}
+
+	memcpy(skb_put(skb, sizeof(speed_cmd)), speed_cmd, sizeof(speed_cmd));
+	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
+
+	hci_uart_set_flow_control(hu, true);
+
+	skb_queue_tail(&intel->txq, skb);
+	hci_uart_tx_wakeup(hu);
+
+	/* wait 100ms to change baudrate on controller side */
+	msleep(100);
+
+	hci_uart_set_baudrate(hu, speed);
+	hci_uart_set_flow_control(hu, false);
+
+	return 0;
+}
+
+static int intel_setup(struct hci_uart *hu)
+{
+	static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01,
+					  0x00, 0x08, 0x04, 0x00 };
+	struct intel_data *intel = hu->priv;
+	struct hci_dev *hdev = hu->hdev;
+	struct sk_buff *skb;
+	struct intel_version *ver;
+	struct intel_boot_params *params;
+	const struct firmware *fw;
+	const u8 *fw_ptr;
+	char fwname[64];
+	u32 frag_len;
+	ktime_t calltime, delta, rettime;
+	unsigned long long duration;
+	unsigned int init_speed, oper_speed;
+	int speed_change = 0;
+	int err;
+
+	BT_DBG("%s", hdev->name);
+
+	hu->hdev->set_bdaddr = btintel_set_bdaddr;
+
+	calltime = ktime_get();
+
+	if (hu->init_speed)
+		init_speed = hu->init_speed;
+	else
+		init_speed = hu->proto->init_speed;
+
+	if (hu->oper_speed)
+		oper_speed = hu->oper_speed;
+	else
+		oper_speed = hu->proto->oper_speed;
+
+	if (oper_speed && init_speed && oper_speed != init_speed)
+		speed_change = 1;
+
+	/* Check that the controller is ready */
+	err = intel_wait_booting(hu);
+
+	clear_bit(STATE_BOOTING, &intel->flags);
+
+	/* In case of timeout, try to continue anyway */
+	if (err && err != ETIMEDOUT)
+		return err;
+
+	set_bit(STATE_BOOTLOADER, &intel->flags);
+
+	/* Read the Intel version information to determine if the device
+	 * is in bootloader mode or if it already has operational firmware
+	 * loaded.
+	 */
+	skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Reading Intel version information failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	if (skb->len != sizeof(*ver)) {
+		BT_ERR("%s: Intel version event size mismatch", hdev->name);
+		kfree_skb(skb);
+		return -EILSEQ;
+	}
+
+	ver = (struct intel_version *)skb->data;
+	if (ver->status) {
+		BT_ERR("%s: Intel version command failure (%02x)",
+		       hdev->name, ver->status);
+		err = -bt_to_errno(ver->status);
+		kfree_skb(skb);
+		return err;
+	}
+
+	/* The hardware platform number has a fixed value of 0x37 and
+	 * for now only accept this single value.
+	 */
+	if (ver->hw_platform != 0x37) {
+		BT_ERR("%s: Unsupported Intel hardware platform (%u)",
+		       hdev->name, ver->hw_platform);
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	/* At the moment only the hardware variant iBT 3.0 (LnP/SfP) is
+	 * supported by this firmware loading method. This check has been
+	 * put in place to ensure correct forward compatibility options
+	 * when newer hardware variants come along.
+	 */
+	if (ver->hw_variant != 0x0b) {
+		BT_ERR("%s: Unsupported Intel hardware variant (%u)",
+		       hdev->name, ver->hw_variant);
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	btintel_version_info(hdev, ver);
+
+	/* The firmware variant determines if the device is in bootloader
+	 * mode or is running operational firmware. The value 0x06 identifies
+	 * the bootloader and the value 0x23 identifies the operational
+	 * firmware.
+	 *
+	 * When the operational firmware is already present, then only
+	 * the check for valid Bluetooth device address is needed. This
+	 * determines if the device will be added as configured or
+	 * unconfigured controller.
+	 *
+	 * It is not possible to use the Secure Boot Parameters in this
+	 * case since that command is only available in bootloader mode.
+	 */
+	if (ver->fw_variant == 0x23) {
+		kfree_skb(skb);
+		clear_bit(STATE_BOOTLOADER, &intel->flags);
+		btintel_check_bdaddr(hdev);
+		return 0;
+	}
+
+	/* If the device is not in bootloader mode, then the only possible
+	 * choice is to return an error and abort the device initialization.
+	 */
+	if (ver->fw_variant != 0x06) {
+		BT_ERR("%s: Unsupported Intel firmware variant (%u)",
+		       hdev->name, ver->fw_variant);
+		kfree_skb(skb);
+		return -ENODEV;
+	}
+
+	kfree_skb(skb);
+
+	/* Read the secure boot parameters to identify the operating
+	 * details of the bootloader.
+	 */
+	skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Reading Intel boot parameters failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	if (skb->len != sizeof(*params)) {
+		BT_ERR("%s: Intel boot parameters size mismatch", hdev->name);
+		kfree_skb(skb);
+		return -EILSEQ;
+	}
+
+	params = (struct intel_boot_params *)skb->data;
+	if (params->status) {
+		BT_ERR("%s: Intel boot parameters command failure (%02x)",
+		       hdev->name, params->status);
+		err = -bt_to_errno(params->status);
+		kfree_skb(skb);
+		return err;
+	}
+
+	BT_INFO("%s: Device revision is %u", hdev->name,
+		le16_to_cpu(params->dev_revid));
+
+	BT_INFO("%s: Secure boot is %s", hdev->name,
+		params->secure_boot ? "enabled" : "disabled");
+
+	BT_INFO("%s: Minimum firmware build %u week %u %u", hdev->name,
+		params->min_fw_build_nn, params->min_fw_build_cw,
+		2000 + params->min_fw_build_yy);
+
+	/* It is required that every single firmware fragment is acknowledged
+	 * with a command complete event. If the boot parameters indicate
+	 * that this bootloader does not send them, then abort the setup.
+	 */
+	if (params->limited_cce != 0x00) {
+		BT_ERR("%s: Unsupported Intel firmware loading method (%u)",
+		       hdev->name, params->limited_cce);
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	/* If the OTP has no valid Bluetooth device address, then there will
+	 * also be no valid address for the operational firmware.
+	 */
+	if (!bacmp(&params->otp_bdaddr, BDADDR_ANY)) {
+		BT_INFO("%s: No device address configured", hdev->name);
+		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
+	}
+
+	/* With this Intel bootloader only the hardware variant and device
+	 * revision information are used to select the right firmware.
+	 *
+	 * Currently this bootloader support is limited to hardware variant
+	 * iBT 3.0 (LnP/SfP) which is identified by the value 11 (0x0b).
+	 */
+	snprintf(fwname, sizeof(fwname), "intel/ibt-11-%u.sfi",
+		 le16_to_cpu(params->dev_revid));
+
+	err = request_firmware(&fw, fwname, &hdev->dev);
+	if (err < 0) {
+		BT_ERR("%s: Failed to load Intel firmware file (%d)",
+		       hdev->name, err);
+		kfree_skb(skb);
+		return err;
+	}
+
+	BT_INFO("%s: Found device firmware: %s", hdev->name, fwname);
+
+	kfree_skb(skb);
+
+	if (fw->size < 644) {
+		BT_ERR("%s: Invalid size of firmware file (%zu)",
+		       hdev->name, fw->size);
+		err = -EBADF;
+		goto done;
+	}
+
+	set_bit(STATE_DOWNLOADING, &intel->flags);
+
+	/* Start the firmware download transaction with the Init fragment
+	 * represented by the 128 bytes of CSS header.
+	 */
+	err = btintel_secure_send(hdev, 0x00, 128, fw->data);
+	if (err < 0) {
+		BT_ERR("%s: Failed to send firmware header (%d)",
+		       hdev->name, err);
+		goto done;
+	}
+
+	/* Send the 256 bytes of public key information from the firmware
+	 * as the PKey fragment.
+	 */
+	err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128);
+	if (err < 0) {
+		BT_ERR("%s: Failed to send firmware public key (%d)",
+		       hdev->name, err);
+		goto done;
+	}
+
+	/* Send the 256 bytes of signature information from the firmware
+	 * as the Sign fragment.
+	 */
+	err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388);
+	if (err < 0) {
+		BT_ERR("%s: Failed to send firmware signature (%d)",
+		       hdev->name, err);
+		goto done;
+	}
+
+	fw_ptr = fw->data + 644;
+	frag_len = 0;
+
+	while (fw_ptr - fw->data < fw->size) {
+		struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
+
+		frag_len += sizeof(*cmd) + cmd->plen;
+
+		BT_DBG("%s: patching %td/%zu", hdev->name,
+		       (fw_ptr - fw->data), fw->size);
+
+		/* The parameter length of the secure send command requires
+		 * a 4 byte alignment. It happens so that the firmware file
+		 * contains proper Intel_NOP commands to align the fragments
+		 * as needed.
+		 *
+		 * Send set of commands with 4 byte alignment from the
+		 * firmware data buffer as a single Data fragement.
+		 */
+		if (frag_len % 4)
+			continue;
+
+		/* Send each command from the firmware data buffer as
+		 * a single Data fragment.
+		 */
+		err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr);
+		if (err < 0) {
+			BT_ERR("%s: Failed to send firmware data (%d)",
+			       hdev->name, err);
+			goto done;
+		}
+
+		fw_ptr += frag_len;
+		frag_len = 0;
+	}
+
+	set_bit(STATE_FIRMWARE_LOADED, &intel->flags);
+
+	BT_INFO("%s: Waiting for firmware download to complete", hdev->name);
+
+	/* Before switching the device into operational mode and with that
+	 * booting the loaded firmware, wait for the bootloader notification
+	 * that all fragments have been successfully received.
+	 *
+	 * When the event processing receives the notification, then the
+	 * STATE_DOWNLOADING flag will be cleared.
+	 *
+	 * The firmware loading should not take longer than 5 seconds
+	 * and thus just timeout if that happens and fail the setup
+	 * of this device.
+	 */
+	err = wait_on_bit_timeout(&intel->flags, STATE_DOWNLOADING,
+				  TASK_INTERRUPTIBLE,
+				  msecs_to_jiffies(5000));
+	if (err == 1) {
+		BT_ERR("%s: Firmware loading interrupted", hdev->name);
+		err = -EINTR;
+		goto done;
+	}
+
+	if (err) {
+		BT_ERR("%s: Firmware loading timeout", hdev->name);
+		err = -ETIMEDOUT;
+		goto done;
+	}
+
+	if (test_bit(STATE_FIRMWARE_FAILED, &intel->flags)) {
+		BT_ERR("%s: Firmware loading failed", hdev->name);
+		err = -ENOEXEC;
+		goto done;
+	}
+
+	rettime = ktime_get();
+	delta = ktime_sub(rettime, calltime);
+	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+
+	BT_INFO("%s: Firmware loaded in %llu usecs", hdev->name, duration);
+
+done:
+	release_firmware(fw);
+
+	if (err < 0)
+		return err;
+
+	/* We need to restore the default speed before Intel reset */
+	if (speed_change) {
+		err = intel_set_baudrate(hu, init_speed);
+		if (err)
+			return err;
+	}
+
+	calltime = ktime_get();
+
+	set_bit(STATE_BOOTING, &intel->flags);
+
+	skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	kfree_skb(skb);
+
+	/* The bootloader will not indicate when the device is ready. This
+	 * is done by the operational firmware sending bootup notification.
+	 *
+	 * Booting into operational firmware should not take longer than
+	 * 1 second. However if that happens, then just fail the setup
+	 * since something went wrong.
+	 */
+	BT_INFO("%s: Waiting for device to boot", hdev->name);
+
+	err = intel_wait_booting(hu);
+	if (err)
+		return err;
+
+	clear_bit(STATE_BOOTING, &intel->flags);
+
+	rettime = ktime_get();
+	delta = ktime_sub(rettime, calltime);
+	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+
+	BT_INFO("%s: Device booted in %llu usecs", hdev->name, duration);
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+	kfree_skb(skb);
+
+	if (speed_change) {
+		err = intel_set_baudrate(hu, oper_speed);
+		if (err)
+			return err;
+	}
+
+	BT_INFO("%s: Setup complete", hdev->name);
+
+	clear_bit(STATE_BOOTLOADER, &intel->flags);
+
+	return 0;
+}
+
+static int intel_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct intel_data *intel = hu->priv;
+	struct hci_event_hdr *hdr;
+
+	if (!test_bit(STATE_BOOTLOADER, &intel->flags) &&
+	    !test_bit(STATE_BOOTING, &intel->flags))
+		goto recv;
+
+	hdr = (void *)skb->data;
+
+	/* When the firmware loading completes the device sends
+	 * out a vendor specific event indicating the result of
+	 * the firmware loading.
+	 */
+	if (skb->len == 7 && hdr->evt == 0xff && hdr->plen == 0x05 &&
+	    skb->data[2] == 0x06) {
+		if (skb->data[3] != 0x00)
+			set_bit(STATE_FIRMWARE_FAILED, &intel->flags);
+
+		if (test_and_clear_bit(STATE_DOWNLOADING, &intel->flags) &&
+		    test_bit(STATE_FIRMWARE_LOADED, &intel->flags)) {
+			smp_mb__after_atomic();
+			wake_up_bit(&intel->flags, STATE_DOWNLOADING);
+		}
+
+	/* When switching to the operational firmware the device
+	 * sends a vendor specific event indicating that the bootup
+	 * completed.
+	 */
+	} else if (skb->len == 9 && hdr->evt == 0xff && hdr->plen == 0x07 &&
+		   skb->data[2] == 0x02) {
+		if (test_and_clear_bit(STATE_BOOTING, &intel->flags)) {
+			smp_mb__after_atomic();
+			wake_up_bit(&intel->flags, STATE_BOOTING);
+		}
+	}
+recv:
+	return hci_recv_frame(hdev, skb);
+}
+
+static const struct h4_recv_pkt intel_recv_pkts[] = {
+	{ H4_RECV_ACL,   .recv = hci_recv_frame },
+	{ H4_RECV_SCO,   .recv = hci_recv_frame },
+	{ H4_RECV_EVENT, .recv = intel_recv_event },
+};
+
+static int intel_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct intel_data *intel = hu->priv;
+
+	if (!test_bit(HCI_UART_REGISTERED, &hu->flags))
+		return -EUNATCH;
+
+	intel->rx_skb = h4_recv_buf(hu->hdev, intel->rx_skb, data, count,
+				    intel_recv_pkts,
+				    ARRAY_SIZE(intel_recv_pkts));
+	if (IS_ERR(intel->rx_skb)) {
+		int err = PTR_ERR(intel->rx_skb);
+		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		intel->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
+static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
+{
+	struct intel_data *intel = hu->priv;
+
+	BT_DBG("hu %p skb %p", hu, skb);
+
+	skb_queue_tail(&intel->txq, skb);
+
+	return 0;
+}
+
+static struct sk_buff *intel_dequeue(struct hci_uart *hu)
+{
+	struct intel_data *intel = hu->priv;
+	struct sk_buff *skb;
+
+	skb = skb_dequeue(&intel->txq);
+	if (!skb)
+		return skb;
+
+	if (test_bit(STATE_BOOTLOADER, &intel->flags) &&
+	    (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT)) {
+		struct hci_command_hdr *cmd = (void *)skb->data;
+		__u16 opcode = le16_to_cpu(cmd->opcode);
+
+		/* When the 0xfc01 command is issued to boot into
+		 * the operational firmware, it will actually not
+		 * send a command complete event. To keep the flow
+		 * control working inject that event here.
+		 */
+		if (opcode == 0xfc01)
+			inject_cmd_complete(hu->hdev, opcode);
+	}
+
+	/* Prepend skb with frame type */
+	memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1);
+
+	return skb;
+}
+
+static const struct hci_uart_proto intel_proto = {
+	.id		= HCI_UART_INTEL,
+	.name		= "Intel",
+	.init_speed	= 115200,
+	.oper_speed	= 3000000,
+	.open		= intel_open,
+	.close		= intel_close,
+	.flush		= intel_flush,
+	.setup		= intel_setup,
+	.set_baudrate	= intel_set_baudrate,
+	.recv		= intel_recv,
+	.enqueue	= intel_enqueue,
+	.dequeue	= intel_dequeue,
+};
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id intel_acpi_match[] = {
+	{ "INT33E1", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, intel_acpi_match);
+
+static int intel_acpi_probe(struct intel_device *idev)
+{
+	const struct acpi_device_id *id;
+
+	id = acpi_match_device(intel_acpi_match, &idev->pdev->dev);
+	if (!id)
+		return -ENODEV;
+
+	return 0;
+}
+#else
+static int intel_acpi_probe(struct intel_device *idev)
+{
+	return -ENODEV;
+}
+#endif
+
+static int intel_probe(struct platform_device *pdev)
+{
+	struct intel_device *idev;
+
+	idev = devm_kzalloc(&pdev->dev, sizeof(*idev), GFP_KERNEL);
+	if (!idev)
+		return -ENOMEM;
+
+	idev->pdev = pdev;
+
+	if (ACPI_HANDLE(&pdev->dev)) {
+		int err = intel_acpi_probe(idev);
+		if (err)
+			return err;
+	} else {
+		return -ENODEV;
+	}
+
+	idev->reset = devm_gpiod_get_optional(&pdev->dev, "reset",
+					      GPIOD_OUT_LOW);
+	if (IS_ERR(idev->reset)) {
+		dev_err(&pdev->dev, "Unable to retrieve gpio\n");
+		return PTR_ERR(idev->reset);
+	}
+
+	platform_set_drvdata(pdev, idev);
+
+	/* Place this instance on the device list */
+	spin_lock(&intel_device_list_lock);
+	list_add_tail(&idev->list, &intel_device_list);
+	spin_unlock(&intel_device_list_lock);
+
+	dev_info(&pdev->dev, "registered.\n");
+
+	return 0;
+}
+
+static int intel_remove(struct platform_device *pdev)
+{
+	struct intel_device *idev = platform_get_drvdata(pdev);
+
+	spin_lock(&intel_device_list_lock);
+	list_del(&idev->list);
+	spin_unlock(&intel_device_list_lock);
+
+	dev_info(&pdev->dev, "unregistered.\n");
+
+	return 0;
+}
+
+static struct platform_driver intel_driver = {
+	.probe = intel_probe,
+	.remove = intel_remove,
+	.driver = {
+		.name = "hci_intel",
+		.acpi_match_table = ACPI_PTR(intel_acpi_match),
+	},
+};
+
+int __init intel_init(void)
+{
+	platform_driver_register(&intel_driver);
+
+	return hci_uart_register_proto(&intel_proto);
+}
+
+int __exit intel_deinit(void)
+{
+	platform_driver_unregister(&intel_driver);
+
+	return hci_uart_unregister_proto(&intel_proto);
+}
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 177dd69fdd95..0d5a05a7c1fd 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -770,7 +770,7 @@ static int __init hci_uart_init(void)
 
 	/* Register the tty discipline */
 
-	memset(&hci_uart_ldisc, 0, sizeof (hci_uart_ldisc));
+	memset(&hci_uart_ldisc, 0, sizeof(hci_uart_ldisc));
 	hci_uart_ldisc.magic		= TTY_LDISC_MAGIC;
 	hci_uart_ldisc.name		= "n_hci";
 	hci_uart_ldisc.open		= hci_uart_tty_open;
@@ -804,9 +804,15 @@ static int __init hci_uart_init(void)
 #ifdef CONFIG_BT_HCIUART_3WIRE
 	h5_init();
 #endif
+#ifdef CONFIG_BT_HCIUART_INTEL
+	intel_init();
+#endif
 #ifdef CONFIG_BT_HCIUART_BCM
 	bcm_init();
 #endif
+#ifdef CONFIG_BT_HCIUART_QCA
+	qca_init();
+#endif
 
 	return 0;
 }
@@ -830,9 +836,15 @@ static void __exit hci_uart_exit(void)
 #ifdef CONFIG_BT_HCIUART_3WIRE
 	h5_deinit();
 #endif
+#ifdef CONFIG_BT_HCIUART_INTEL
+	intel_deinit();
+#endif
 #ifdef CONFIG_BT_HCIUART_BCM
 	bcm_deinit();
 #endif
+#ifdef CONFIG_BT_HCIUART_QCA
+	qca_deinit();
+#endif
 
 	/* Release tty registration of line discipline */
 	err = tty_unregister_ldisc(N_HCI);
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
new file mode 100644
index 000000000000..6b9b91267959
--- /dev/null
+++ b/drivers/bluetooth/hci_qca.c
@@ -0,0 +1,969 @@
+/*
+ *  Bluetooth Software UART Qualcomm protocol
+ *
+ *  HCI_IBS (HCI In-Band Sleep) is Qualcomm's power management
+ *  protocol extension to H4.
+ *
+ *  Copyright (C) 2007 Texas Instruments, Inc.
+ *  Copyright (c) 2010, 2012 The Linux Foundation. All rights reserved.
+ *
+ *  Acknowledgements:
+ *  This file is based on hci_ll.c, which was...
+ *  Written by Ohad Ben-Cohen <ohad@bencohen.org>
+ *  which was in turn based on hci_h4.c, which was written
+ *  by Maxim Krasnyansky and Marcel Holtmann.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "hci_uart.h"
+#include "btqca.h"
+
+/* HCI_IBS protocol messages */
+#define HCI_IBS_SLEEP_IND	0xFE
+#define HCI_IBS_WAKE_IND	0xFD
+#define HCI_IBS_WAKE_ACK	0xFC
+#define HCI_MAX_IBS_SIZE 	10
+
+/* Controller states */
+#define STATE_IN_BAND_SLEEP_ENABLED	1
+
+#define IBS_WAKE_RETRANS_TIMEOUT_MS 	100
+#define IBS_TX_IDLE_TIMEOUT_MS 		2000
+#define BAUDRATE_SETTLE_TIMEOUT_MS	300
+
+/* HCI_IBS transmit side sleep protocol states */
+enum tx_ibs_states {
+	HCI_IBS_TX_ASLEEP,
+	HCI_IBS_TX_WAKING,
+	HCI_IBS_TX_AWAKE,
+};
+
+/* HCI_IBS receive side sleep protocol states */
+enum rx_states {
+	HCI_IBS_RX_ASLEEP,
+	HCI_IBS_RX_AWAKE,
+};
+
+/* HCI_IBS transmit and receive side clock state vote */
+enum hci_ibs_clock_state_vote {
+	HCI_IBS_VOTE_STATS_UPDATE,
+	HCI_IBS_TX_VOTE_CLOCK_ON,
+	HCI_IBS_TX_VOTE_CLOCK_OFF,
+	HCI_IBS_RX_VOTE_CLOCK_ON,
+	HCI_IBS_RX_VOTE_CLOCK_OFF,
+};
+
+struct qca_data {
+	struct hci_uart *hu;
+	struct sk_buff *rx_skb;
+	struct sk_buff_head txq;
+	struct sk_buff_head tx_wait_q;	/* HCI_IBS wait queue	*/
+	spinlock_t hci_ibs_lock;	/* HCI_IBS state lock	*/
+	u8 tx_ibs_state;	/* HCI_IBS transmit side power state*/
+	u8 rx_ibs_state;	/* HCI_IBS receive side power state */
+	u32 tx_vote;		/* Clock must be on for TX */
+	u32 rx_vote;		/* Clock must be on for RX */
+	struct timer_list tx_idle_timer;
+	u32 tx_idle_delay;
+	struct timer_list wake_retrans_timer;
+	u32 wake_retrans;
+	struct workqueue_struct *workqueue;
+	struct work_struct ws_awake_rx;
+	struct work_struct ws_awake_device;
+	struct work_struct ws_rx_vote_off;
+	struct work_struct ws_tx_vote_off;
+	unsigned long flags;
+
+	/* For debugging purpose */
+	u64 ibs_sent_wacks;
+	u64 ibs_sent_slps;
+	u64 ibs_sent_wakes;
+	u64 ibs_recv_wacks;
+	u64 ibs_recv_slps;
+	u64 ibs_recv_wakes;
+	u64 vote_last_jif;
+	u32 vote_on_ms;
+	u32 vote_off_ms;
+	u64 tx_votes_on;
+	u64 rx_votes_on;
+	u64 tx_votes_off;
+	u64 rx_votes_off;
+	u64 votes_on;
+	u64 votes_off;
+};
+
+static void __serial_clock_on(struct tty_struct *tty)
+{
+	/* TODO: Some chipset requires to enable UART clock on client
+	 * side to save power consumption or manual work is required.
+	 * Please put your code to control UART clock here if needed
+	 */
+}
+
+static void __serial_clock_off(struct tty_struct *tty)
+{
+	/* TODO: Some chipset requires to disable UART clock on client
+	 * side to save power consumption or manual work is required.
+	 * Please put your code to control UART clock off here if needed
+	 */
+}
+
+/* serial_clock_vote needs to be called with the ibs lock held */
+static void serial_clock_vote(unsigned long vote, struct hci_uart *hu)
+{
+	struct qca_data *qca = hu->priv;
+	unsigned int diff;
+
+	bool old_vote = (qca->tx_vote | qca->rx_vote);
+	bool new_vote;
+
+	switch (vote) {
+	case HCI_IBS_VOTE_STATS_UPDATE:
+		diff = jiffies_to_msecs(jiffies - qca->vote_last_jif);
+
+		if (old_vote)
+			qca->vote_off_ms += diff;
+		else
+			qca->vote_on_ms += diff;
+		return;
+
+	case HCI_IBS_TX_VOTE_CLOCK_ON:
+		qca->tx_vote = true;
+		qca->tx_votes_on++;
+		new_vote = true;
+		break;
+
+	case HCI_IBS_RX_VOTE_CLOCK_ON:
+		qca->rx_vote = true;
+		qca->rx_votes_on++;
+		new_vote = true;
+		break;
+
+	case HCI_IBS_TX_VOTE_CLOCK_OFF:
+		qca->tx_vote = false;
+		qca->tx_votes_off++;
+		new_vote = qca->rx_vote | qca->tx_vote;
+		break;
+
+	case HCI_IBS_RX_VOTE_CLOCK_OFF:
+		qca->rx_vote = false;
+		qca->rx_votes_off++;
+		new_vote = qca->rx_vote | qca->tx_vote;
+		break;
+
+	default:
+		BT_ERR("Voting irregularity");
+		return;
+	}
+
+	if (new_vote != old_vote) {
+		if (new_vote)
+			__serial_clock_on(hu->tty);
+		else
+			__serial_clock_off(hu->tty);
+
+		BT_DBG("Vote serial clock %s(%s)", new_vote? "true" : "false",
+		       vote? "true" : "false");
+
+		diff = jiffies_to_msecs(jiffies - qca->vote_last_jif);
+
+		if (new_vote) {
+			qca->votes_on++;
+			qca->vote_off_ms += diff;
+		} else {
+			qca->votes_off++;
+			qca->vote_on_ms += diff;
+		}
+		qca->vote_last_jif = jiffies;
+	}
+}
+
+/* Builds and sends an HCI_IBS command packet.
+ * These are very simple packets with only 1 cmd byte.
+ */
+static int send_hci_ibs_cmd(u8 cmd, struct hci_uart *hu)
+{
+	int err = 0;
+	struct sk_buff *skb = NULL;
+	struct qca_data *qca = hu->priv;
+
+	BT_DBG("hu %p send hci ibs cmd 0x%x", hu, cmd);
+
+	skb = bt_skb_alloc(1, GFP_ATOMIC);
+	if (!skb) {
+		BT_ERR("Failed to allocate memory for HCI_IBS packet");
+		return -ENOMEM;
+	}
+
+	/* Assign HCI_IBS type */
+	*skb_put(skb, 1) = cmd;
+
+	skb_queue_tail(&qca->txq, skb);
+
+	return err;
+}
+
+static void qca_wq_awake_device(struct work_struct *work)
+{
+	struct qca_data *qca = container_of(work, struct qca_data,
+					    ws_awake_device);
+	struct hci_uart *hu = qca->hu;
+	unsigned long retrans_delay;
+
+	BT_DBG("hu %p wq awake device", hu);
+
+	/* Vote for serial clock */
+	serial_clock_vote(HCI_IBS_TX_VOTE_CLOCK_ON, hu);
+
+	spin_lock(&qca->hci_ibs_lock);
+
+	/* Send wake indication to device */
+	if (send_hci_ibs_cmd(HCI_IBS_WAKE_IND, hu) < 0)
+		BT_ERR("Failed to send WAKE to device");
+
+	qca->ibs_sent_wakes++;
+
+	/* Start retransmit timer */
+	retrans_delay = msecs_to_jiffies(qca->wake_retrans);
+	mod_timer(&qca->wake_retrans_timer, jiffies + retrans_delay);
+
+	spin_unlock(&qca->hci_ibs_lock);
+
+	/* Actually send the packets */
+	hci_uart_tx_wakeup(hu);
+}
+
+static void qca_wq_awake_rx(struct work_struct *work)
+{
+	struct qca_data *qca = container_of(work, struct qca_data,
+					    ws_awake_rx);
+	struct hci_uart *hu = qca->hu;
+
+	BT_DBG("hu %p wq awake rx", hu);
+
+	serial_clock_vote(HCI_IBS_RX_VOTE_CLOCK_ON, hu);
+
+	spin_lock(&qca->hci_ibs_lock);
+	qca->rx_ibs_state = HCI_IBS_RX_AWAKE;
+
+	/* Always acknowledge device wake up,
+	 * sending IBS message doesn't count as TX ON.
+	 */
+	if (send_hci_ibs_cmd(HCI_IBS_WAKE_ACK, hu) < 0)
+		BT_ERR("Failed to acknowledge device wake up");
+
+	qca->ibs_sent_wacks++;
+
+	spin_unlock(&qca->hci_ibs_lock);
+
+	/* Actually send the packets */
+	hci_uart_tx_wakeup(hu);
+}
+
+static void qca_wq_serial_rx_clock_vote_off(struct work_struct *work)
+{
+	struct qca_data *qca = container_of(work, struct qca_data,
+					    ws_rx_vote_off);
+	struct hci_uart *hu = qca->hu;
+
+	BT_DBG("hu %p rx clock vote off", hu);
+
+	serial_clock_vote(HCI_IBS_RX_VOTE_CLOCK_OFF, hu);
+}
+
+static void qca_wq_serial_tx_clock_vote_off(struct work_struct *work)
+{
+	struct qca_data *qca = container_of(work, struct qca_data,
+					    ws_tx_vote_off);
+	struct hci_uart *hu = qca->hu;
+
+	BT_DBG("hu %p tx clock vote off", hu);
+
+	/* Run HCI tx handling unlocked */
+	hci_uart_tx_wakeup(hu);
+
+	/* Now that message queued to tty driver, vote for tty clocks off.
+	 * It is up to the tty driver to pend the clocks off until tx done.
+	 */
+	serial_clock_vote(HCI_IBS_TX_VOTE_CLOCK_OFF, hu);
+}
+
+static void hci_ibs_tx_idle_timeout(unsigned long arg)
+{
+	struct hci_uart *hu = (struct hci_uart *)arg;
+	struct qca_data *qca = hu->priv;
+	unsigned long flags;
+
+	BT_DBG("hu %p idle timeout in %d state", hu, qca->tx_ibs_state);
+
+	spin_lock_irqsave_nested(&qca->hci_ibs_lock,
+				 flags, SINGLE_DEPTH_NESTING);
+
+	switch (qca->tx_ibs_state) {
+	case HCI_IBS_TX_AWAKE:
+		/* TX_IDLE, go to SLEEP */
+		if (send_hci_ibs_cmd(HCI_IBS_SLEEP_IND, hu) < 0) {
+			BT_ERR("Failed to send SLEEP to device");
+			break;
+		}
+		qca->tx_ibs_state = HCI_IBS_TX_ASLEEP;
+		qca->ibs_sent_slps++;
+		queue_work(qca->workqueue, &qca->ws_tx_vote_off);
+		break;
+
+	case HCI_IBS_TX_ASLEEP:
+	case HCI_IBS_TX_WAKING:
+		/* Fall through */
+
+	default:
+		BT_ERR("Spurrious timeout tx state %d", qca->tx_ibs_state);
+		break;
+	}
+
+	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+}
+
+static void hci_ibs_wake_retrans_timeout(unsigned long arg)
+{
+	struct hci_uart *hu = (struct hci_uart *)arg;
+	struct qca_data *qca = hu->priv;
+	unsigned long flags, retrans_delay;
+	unsigned long retransmit = 0;
+
+	BT_DBG("hu %p wake retransmit timeout in %d state",
+		hu, qca->tx_ibs_state);
+
+	spin_lock_irqsave_nested(&qca->hci_ibs_lock,
+				 flags, SINGLE_DEPTH_NESTING);
+
+	switch (qca->tx_ibs_state) {
+	case HCI_IBS_TX_WAKING:
+		/* No WAKE_ACK, retransmit WAKE */
+		retransmit = 1;
+		if (send_hci_ibs_cmd(HCI_IBS_WAKE_IND, hu) < 0) {
+			BT_ERR("Failed to acknowledge device wake up");
+			break;
+		}
+		qca->ibs_sent_wakes++;
+		retrans_delay = msecs_to_jiffies(qca->wake_retrans);
+		mod_timer(&qca->wake_retrans_timer, jiffies + retrans_delay);
+		break;
+
+	case HCI_IBS_TX_ASLEEP:
+	case HCI_IBS_TX_AWAKE:
+		/* Fall through */
+
+	default:
+		BT_ERR("Spurrious timeout tx state %d", qca->tx_ibs_state);
+		break;
+	}
+
+	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+
+	if (retransmit)
+		hci_uart_tx_wakeup(hu);
+}
+
+/* Initialize protocol */
+static int qca_open(struct hci_uart *hu)
+{
+	struct qca_data *qca;
+
+	BT_DBG("hu %p qca_open", hu);
+
+	qca = kzalloc(sizeof(struct qca_data), GFP_ATOMIC);
+	if (!qca)
+		return -ENOMEM;
+
+	skb_queue_head_init(&qca->txq);
+	skb_queue_head_init(&qca->tx_wait_q);
+	spin_lock_init(&qca->hci_ibs_lock);
+	qca->workqueue = create_singlethread_workqueue("qca_wq");
+	if (!qca->workqueue) {
+		BT_ERR("QCA Workqueue not initialized properly");
+		kfree(qca);
+		return -ENOMEM;
+	}
+
+	INIT_WORK(&qca->ws_awake_rx, qca_wq_awake_rx);
+	INIT_WORK(&qca->ws_awake_device, qca_wq_awake_device);
+	INIT_WORK(&qca->ws_rx_vote_off, qca_wq_serial_rx_clock_vote_off);
+	INIT_WORK(&qca->ws_tx_vote_off, qca_wq_serial_tx_clock_vote_off);
+
+	qca->hu = hu;
+
+	/* Assume we start with both sides asleep -- extra wakes OK */
+	qca->tx_ibs_state = HCI_IBS_TX_ASLEEP;
+	qca->rx_ibs_state = HCI_IBS_RX_ASLEEP;
+
+	/* clocks actually on, but we start votes off */
+	qca->tx_vote = false;
+	qca->rx_vote = false;
+	qca->flags = 0;
+
+	qca->ibs_sent_wacks = 0;
+	qca->ibs_sent_slps = 0;
+	qca->ibs_sent_wakes = 0;
+	qca->ibs_recv_wacks = 0;
+	qca->ibs_recv_slps = 0;
+	qca->ibs_recv_wakes = 0;
+	qca->vote_last_jif = jiffies;
+	qca->vote_on_ms = 0;
+	qca->vote_off_ms = 0;
+	qca->votes_on = 0;
+	qca->votes_off = 0;
+	qca->tx_votes_on = 0;
+	qca->tx_votes_off = 0;
+	qca->rx_votes_on = 0;
+	qca->rx_votes_off = 0;
+
+	hu->priv = qca;
+
+	init_timer(&qca->wake_retrans_timer);
+	qca->wake_retrans_timer.function = hci_ibs_wake_retrans_timeout;
+	qca->wake_retrans_timer.data = (u_long)hu;
+	qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS;
+
+	init_timer(&qca->tx_idle_timer);
+	qca->tx_idle_timer.function = hci_ibs_tx_idle_timeout;
+	qca->tx_idle_timer.data = (u_long)hu;
+	qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
+
+	BT_DBG("HCI_UART_QCA open, tx_idle_delay=%u, wake_retrans=%u",
+	       qca->tx_idle_delay, qca->wake_retrans);
+
+	return 0;
+}
+
+static void qca_debugfs_init(struct hci_dev *hdev)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct qca_data *qca = hu->priv;
+	struct dentry *ibs_dir;
+	umode_t mode;
+
+	if (!hdev->debugfs)
+		return;
+
+	ibs_dir = debugfs_create_dir("ibs", hdev->debugfs);
+
+	/* read only */
+	mode = S_IRUGO;
+	debugfs_create_u8("tx_ibs_state", mode, ibs_dir, &qca->tx_ibs_state);
+	debugfs_create_u8("rx_ibs_state", mode, ibs_dir, &qca->rx_ibs_state);
+	debugfs_create_u64("ibs_sent_sleeps", mode, ibs_dir,
+			   &qca->ibs_sent_slps);
+	debugfs_create_u64("ibs_sent_wakes", mode, ibs_dir,
+			   &qca->ibs_sent_wakes);
+	debugfs_create_u64("ibs_sent_wake_acks", mode, ibs_dir,
+			   &qca->ibs_sent_wacks);
+	debugfs_create_u64("ibs_recv_sleeps", mode, ibs_dir,
+			   &qca->ibs_recv_slps);
+	debugfs_create_u64("ibs_recv_wakes", mode, ibs_dir,
+			   &qca->ibs_recv_wakes);
+	debugfs_create_u64("ibs_recv_wake_acks", mode, ibs_dir,
+			   &qca->ibs_recv_wacks);
+	debugfs_create_bool("tx_vote", mode, ibs_dir, &qca->tx_vote);
+	debugfs_create_u64("tx_votes_on", mode, ibs_dir, &qca->tx_votes_on);
+	debugfs_create_u64("tx_votes_off", mode, ibs_dir, &qca->tx_votes_off);
+	debugfs_create_bool("rx_vote", mode, ibs_dir, &qca->rx_vote);
+	debugfs_create_u64("rx_votes_on", mode, ibs_dir, &qca->rx_votes_on);
+	debugfs_create_u64("rx_votes_off", mode, ibs_dir, &qca->rx_votes_off);
+	debugfs_create_u64("votes_on", mode, ibs_dir, &qca->votes_on);
+	debugfs_create_u64("votes_off", mode, ibs_dir, &qca->votes_off);
+	debugfs_create_u32("vote_on_ms", mode, ibs_dir, &qca->vote_on_ms);
+	debugfs_create_u32("vote_off_ms", mode, ibs_dir, &qca->vote_off_ms);
+
+	/* read/write */
+	mode = S_IRUGO | S_IWUSR;
+	debugfs_create_u32("wake_retrans", mode, ibs_dir, &qca->wake_retrans);
+	debugfs_create_u32("tx_idle_delay", mode, ibs_dir,
+			   &qca->tx_idle_delay);
+}
+
+/* Flush protocol data */
+static int qca_flush(struct hci_uart *hu)
+{
+	struct qca_data *qca = hu->priv;
+
+	BT_DBG("hu %p qca flush", hu);
+
+	skb_queue_purge(&qca->tx_wait_q);
+	skb_queue_purge(&qca->txq);
+
+	return 0;
+}
+
+/* Close protocol */
+static int qca_close(struct hci_uart *hu)
+{
+	struct qca_data *qca = hu->priv;
+
+	BT_DBG("hu %p qca close", hu);
+
+	serial_clock_vote(HCI_IBS_VOTE_STATS_UPDATE, hu);
+
+	skb_queue_purge(&qca->tx_wait_q);
+	skb_queue_purge(&qca->txq);
+	del_timer(&qca->tx_idle_timer);
+	del_timer(&qca->wake_retrans_timer);
+	destroy_workqueue(qca->workqueue);
+	qca->hu = NULL;
+
+	kfree_skb(qca->rx_skb);
+
+	hu->priv = NULL;
+
+	kfree(qca);
+
+	return 0;
+}
+
+/* Called upon a wake-up-indication from the device.
+ */
+static void device_want_to_wakeup(struct hci_uart *hu)
+{
+	unsigned long flags;
+	struct qca_data *qca = hu->priv;
+
+	BT_DBG("hu %p want to wake up", hu);
+
+	spin_lock_irqsave(&qca->hci_ibs_lock, flags);
+
+	qca->ibs_recv_wakes++;
+
+	switch (qca->rx_ibs_state) {
+	case HCI_IBS_RX_ASLEEP:
+		/* Make sure clock is on - we may have turned clock off since
+		 * receiving the wake up indicator awake rx clock.
+		 */
+		queue_work(qca->workqueue, &qca->ws_awake_rx);
+		spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+		return;
+
+	case HCI_IBS_RX_AWAKE:
+		/* Always acknowledge device wake up,
+		 * sending IBS message doesn't count as TX ON.
+		 */
+		if (send_hci_ibs_cmd(HCI_IBS_WAKE_ACK, hu) < 0) {
+			BT_ERR("Failed to acknowledge device wake up");
+			break;
+		}
+		qca->ibs_sent_wacks++;
+		break;
+
+	default:
+		/* Any other state is illegal */
+		BT_ERR("Received HCI_IBS_WAKE_IND in rx state %d",
+		       qca->rx_ibs_state);
+		break;
+	}
+
+	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+
+	/* Actually send the packets */
+	hci_uart_tx_wakeup(hu);
+}
+
+/* Called upon a sleep-indication from the device.
+ */
+static void device_want_to_sleep(struct hci_uart *hu)
+{
+	unsigned long flags;
+	struct qca_data *qca = hu->priv;
+
+	BT_DBG("hu %p want to sleep", hu);
+
+	spin_lock_irqsave(&qca->hci_ibs_lock, flags);
+
+	qca->ibs_recv_slps++;
+
+	switch (qca->rx_ibs_state) {
+	case HCI_IBS_RX_AWAKE:
+		/* Update state */
+		qca->rx_ibs_state = HCI_IBS_RX_ASLEEP;
+		/* Vote off rx clock under workqueue */
+		queue_work(qca->workqueue, &qca->ws_rx_vote_off);
+		break;
+
+	case HCI_IBS_RX_ASLEEP:
+		/* Fall through */
+
+	default:
+		/* Any other state is illegal */
+		BT_ERR("Received HCI_IBS_SLEEP_IND in rx state %d",
+		       qca->rx_ibs_state);
+		break;
+	}
+
+	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+}
+
+/* Called upon wake-up-acknowledgement from the device
+ */
+static void device_woke_up(struct hci_uart *hu)
+{
+	unsigned long flags, idle_delay;
+	struct qca_data *qca = hu->priv;
+	struct sk_buff *skb = NULL;
+
+	BT_DBG("hu %p woke up", hu);
+
+	spin_lock_irqsave(&qca->hci_ibs_lock, flags);
+
+	qca->ibs_recv_wacks++;
+
+	switch (qca->tx_ibs_state) {
+	case HCI_IBS_TX_AWAKE:
+		/* Expect one if we send 2 WAKEs */
+		BT_DBG("Received HCI_IBS_WAKE_ACK in tx state %d",
+		       qca->tx_ibs_state);
+		break;
+
+	case HCI_IBS_TX_WAKING:
+		/* Send pending packets */
+		while ((skb = skb_dequeue(&qca->tx_wait_q)))
+			skb_queue_tail(&qca->txq, skb);
+
+		/* Switch timers and change state to HCI_IBS_TX_AWAKE */
+		del_timer(&qca->wake_retrans_timer);
+		idle_delay = msecs_to_jiffies(qca->tx_idle_delay);
+		mod_timer(&qca->tx_idle_timer, jiffies + idle_delay);
+		qca->tx_ibs_state = HCI_IBS_TX_AWAKE;
+		break;
+
+	case HCI_IBS_TX_ASLEEP:
+		/* Fall through */
+
+	default:
+		BT_ERR("Received HCI_IBS_WAKE_ACK in tx state %d",
+		       qca->tx_ibs_state);
+		break;
+	}
+
+	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+
+	/* Actually send the packets */
+	hci_uart_tx_wakeup(hu);
+}
+
+/* Enqueue frame for transmittion (padding, crc, etc) may be called from
+ * two simultaneous tasklets.
+ */
+static int qca_enqueue(struct hci_uart *hu, struct sk_buff *skb)
+{
+	unsigned long flags = 0, idle_delay;
+	struct qca_data *qca = hu->priv;
+
+	BT_DBG("hu %p qca enq skb %p tx_ibs_state %d", hu, skb,
+	       qca->tx_ibs_state);
+
+	/* Prepend skb with frame type */
+	memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1);
+
+	/* Don't go to sleep in middle of patch download or
+	 * Out-Of-Band(GPIOs control) sleep is selected.
+	 */
+	if (!test_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags)) {
+		skb_queue_tail(&qca->txq, skb);
+		return 0;
+	}
+
+	spin_lock_irqsave(&qca->hci_ibs_lock, flags);
+
+	/* Act according to current state */
+	switch (qca->tx_ibs_state) {
+	case HCI_IBS_TX_AWAKE:
+		BT_DBG("Device awake, sending normally");
+		skb_queue_tail(&qca->txq, skb);
+		idle_delay = msecs_to_jiffies(qca->tx_idle_delay);
+		mod_timer(&qca->tx_idle_timer, jiffies + idle_delay);
+		break;
+
+	case HCI_IBS_TX_ASLEEP:
+		BT_DBG("Device asleep, waking up and queueing packet");
+		/* Save packet for later */
+		skb_queue_tail(&qca->tx_wait_q, skb);
+
+		qca->tx_ibs_state = HCI_IBS_TX_WAKING;
+		/* Schedule a work queue to wake up device */
+		queue_work(qca->workqueue, &qca->ws_awake_device);
+		break;
+
+	case HCI_IBS_TX_WAKING:
+		BT_DBG("Device waking up, queueing packet");
+		/* Transient state; just keep packet for later */
+		skb_queue_tail(&qca->tx_wait_q, skb);
+		break;
+
+	default:
+		BT_ERR("Illegal tx state: %d (losing packet)",
+		       qca->tx_ibs_state);
+		kfree_skb(skb);
+		break;
+	}
+
+	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
+
+	return 0;
+}
+
+static int qca_ibs_sleep_ind(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
+	BT_DBG("hu %p recv hci ibs cmd 0x%x", hu, HCI_IBS_SLEEP_IND);
+
+	device_want_to_sleep(hu);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int qca_ibs_wake_ind(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
+	BT_DBG("hu %p recv hci ibs cmd 0x%x", hu, HCI_IBS_WAKE_IND);
+
+	device_want_to_wakeup(hu);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int qca_ibs_wake_ack(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
+	BT_DBG("hu %p recv hci ibs cmd 0x%x", hu, HCI_IBS_WAKE_ACK);
+
+	device_woke_up(hu);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+#define QCA_IBS_SLEEP_IND_EVENT \
+	.type = HCI_IBS_SLEEP_IND, \
+	.hlen = 0, \
+	.loff = 0, \
+	.lsize = 0, \
+	.maxlen = HCI_MAX_IBS_SIZE
+
+#define QCA_IBS_WAKE_IND_EVENT \
+	.type = HCI_IBS_WAKE_IND, \
+	.hlen = 0, \
+	.loff = 0, \
+	.lsize = 0, \
+	.maxlen = HCI_MAX_IBS_SIZE
+
+#define QCA_IBS_WAKE_ACK_EVENT \
+	.type = HCI_IBS_WAKE_ACK, \
+	.hlen = 0, \
+	.loff = 0, \
+	.lsize = 0, \
+	.maxlen = HCI_MAX_IBS_SIZE
+
+static const struct h4_recv_pkt qca_recv_pkts[] = {
+	{ H4_RECV_ACL,             .recv = hci_recv_frame    },
+	{ H4_RECV_SCO,             .recv = hci_recv_frame    },
+	{ H4_RECV_EVENT,           .recv = hci_recv_frame    },
+	{ QCA_IBS_WAKE_IND_EVENT,  .recv = qca_ibs_wake_ind  },
+	{ QCA_IBS_WAKE_ACK_EVENT,  .recv = qca_ibs_wake_ack  },
+	{ QCA_IBS_SLEEP_IND_EVENT, .recv = qca_ibs_sleep_ind },
+};
+
+static int qca_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct qca_data *qca = hu->priv;
+
+	if (!test_bit(HCI_UART_REGISTERED, &hu->flags))
+		return -EUNATCH;
+
+	qca->rx_skb = h4_recv_buf(hu->hdev, qca->rx_skb, data, count,
+				  qca_recv_pkts, ARRAY_SIZE(qca_recv_pkts));
+	if (IS_ERR(qca->rx_skb)) {
+		int err = PTR_ERR(qca->rx_skb);
+		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		qca->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
+static struct sk_buff *qca_dequeue(struct hci_uart *hu)
+{
+	struct qca_data *qca = hu->priv;
+
+	return skb_dequeue(&qca->txq);
+}
+
+static uint8_t qca_get_baudrate_value(int speed)
+{
+	switch(speed) {
+	case 9600:
+		return QCA_BAUDRATE_9600;
+	case 19200:
+		return QCA_BAUDRATE_19200;
+	case 38400:
+		return QCA_BAUDRATE_38400;
+	case 57600:
+		return QCA_BAUDRATE_57600;
+	case 115200:
+		return QCA_BAUDRATE_115200;
+	case 230400:
+		return QCA_BAUDRATE_230400;
+	case 460800:
+		return QCA_BAUDRATE_460800;
+	case 500000:
+		return QCA_BAUDRATE_500000;
+	case 921600:
+		return QCA_BAUDRATE_921600;
+	case 1000000:
+		return QCA_BAUDRATE_1000000;
+	case 2000000:
+		return QCA_BAUDRATE_2000000;
+	case 3000000:
+		return QCA_BAUDRATE_3000000;
+	case 3500000:
+		return QCA_BAUDRATE_3500000;
+	default:
+		return QCA_BAUDRATE_115200;
+	}
+}
+
+static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct qca_data *qca = hu->priv;
+	struct sk_buff *skb;
+	u8 cmd[] = { 0x01, 0x48, 0xFC, 0x01, 0x00 };
+
+	if (baudrate > QCA_BAUDRATE_3000000)
+		return -EINVAL;
+
+	cmd[4] = baudrate;
+
+	skb = bt_skb_alloc(sizeof(cmd), GFP_ATOMIC);
+	if (!skb) {
+		BT_ERR("Failed to allocate memory for baudrate packet");
+		return -ENOMEM;
+	}
+
+	/* Assign commands to change baudrate and packet type. */
+	memcpy(skb_put(skb, sizeof(cmd)), cmd, sizeof(cmd));
+	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
+
+	skb_queue_tail(&qca->txq, skb);
+	hci_uart_tx_wakeup(hu);
+
+	/* wait 300ms to change new baudrate on controller side
+	 * controller will come back after they receive this HCI command
+	 * then host can communicate with new baudrate to controller
+	 */
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	schedule_timeout(msecs_to_jiffies(BAUDRATE_SETTLE_TIMEOUT_MS));
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	return 0;
+}
+
+static int qca_setup(struct hci_uart *hu)
+{
+	struct hci_dev *hdev = hu->hdev;
+	struct qca_data *qca = hu->priv;
+	unsigned int speed, qca_baudrate = QCA_BAUDRATE_115200;
+	int ret;
+
+	BT_INFO("%s: ROME setup", hdev->name);
+
+	/* Patch downloading has to be done without IBS mode */
+	clear_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
+
+	/* Setup initial baudrate */
+	speed = 0;
+	if (hu->init_speed)
+		speed = hu->init_speed;
+	else if (hu->proto->init_speed)
+		speed = hu->proto->init_speed;
+
+	if (speed)
+		hci_uart_set_baudrate(hu, speed);
+
+	/* Setup user speed if needed */
+	speed = 0;
+	if (hu->oper_speed)
+		speed = hu->oper_speed;
+	else if (hu->proto->oper_speed)
+		speed = hu->proto->oper_speed;
+
+	if (speed) {
+		qca_baudrate = qca_get_baudrate_value(speed);
+
+		BT_INFO("%s: Set UART speed to %d", hdev->name, speed);
+		ret = qca_set_baudrate(hdev, qca_baudrate);
+		if (ret) {
+			BT_ERR("%s: Failed to change the baud rate (%d)",
+			       hdev->name, ret);
+			return ret;
+		}
+		hci_uart_set_baudrate(hu, speed);
+	}
+
+	/* Setup patch / NVM configurations */
+	ret = qca_uart_setup_rome(hdev, qca_baudrate);
+	if (!ret) {
+		set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
+		qca_debugfs_init(hdev);
+	}
+
+	/* Setup bdaddr */
+	hu->hdev->set_bdaddr = qca_set_bdaddr_rome;
+
+	return ret;
+}
+
+static struct hci_uart_proto qca_proto = {
+	.id		= HCI_UART_QCA,
+	.name		= "QCA",
+	.init_speed	= 115200,
+	.oper_speed	= 3000000,
+	.open		= qca_open,
+	.close		= qca_close,
+	.flush		= qca_flush,
+	.setup		= qca_setup,
+	.recv		= qca_recv,
+	.enqueue	= qca_enqueue,
+	.dequeue	= qca_dequeue,
+};
+
+int __init qca_init(void)
+{
+	return hci_uart_register_proto(&qca_proto);
+}
+
+int __exit qca_deinit(void)
+{
+	return hci_uart_unregister_proto(&qca_proto);
+}
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index ce9c670956f5..495b9ef52bb0 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -35,7 +35,7 @@
 #define HCIUARTGETFLAGS		_IOR('U', 204, int)
 
 /* UART protocols */
-#define HCI_UART_MAX_PROTO	8
+#define HCI_UART_MAX_PROTO	9
 
 #define HCI_UART_H4	0
 #define HCI_UART_BCSP	1
@@ -45,6 +45,7 @@
 #define HCI_UART_ATH3K	5
 #define HCI_UART_INTEL	6
 #define HCI_UART_BCM	7
+#define HCI_UART_QCA	8
 
 #define HCI_UART_RAW_DEVICE	0
 #define HCI_UART_RESET_ON_INIT	1
@@ -167,7 +168,17 @@ int h5_init(void);
 int h5_deinit(void);
 #endif
 
+#ifdef CONFIG_BT_HCIUART_INTEL
+int intel_init(void);
+int intel_deinit(void);
+#endif
+
 #ifdef CONFIG_BT_HCIUART_BCM
 int bcm_init(void);
 int bcm_deinit(void);
 #endif
+
+#ifdef CONFIG_BT_HCIUART_QCA
+int qca_init(void);
+int qca_deinit(void);
+#endif
diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c
index ab3bde16ecb4..1c543effe062 100644
--- a/drivers/bus/mips_cdmm.c
+++ b/drivers/bus/mips_cdmm.c
@@ -332,6 +332,18 @@ static phys_addr_t mips_cdmm_cur_base(void)
 }
 
 /**
+ * mips_cdmm_phys_base() - Choose a physical base address for CDMM region.
+ *
+ * Picking a suitable physical address at which to map the CDMM region is
+ * platform specific, so this weak function can be overridden by platform
+ * code to pick a suitable value if none is configured by the bootloader.
+ */
+phys_addr_t __weak mips_cdmm_phys_base(void)
+{
+	return 0;
+}
+
+/**
  * mips_cdmm_setup() - Ensure the CDMM bus is initialised and usable.
  * @bus:	Pointer to bus information for current CPU.
  *		IS_ERR(bus) is checked, so no need for caller to check.
@@ -368,7 +380,7 @@ static int mips_cdmm_setup(struct mips_cdmm_bus *bus)
 	if (!bus->phys)
 		bus->phys = mips_cdmm_cur_base();
 	/* Otherwise, ask platform code for suggestions */
-	if (!bus->phys && mips_cdmm_phys_base)
+	if (!bus->phys)
 		bus->phys = mips_cdmm_phys_base();
 	/* Otherwise, copy what other CPUs have done */
 	if (!bus->phys)
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index c6dea3f6917b..1341a94cc779 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -1408,8 +1408,8 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 }
 EXPORT_SYMBOL(intel_gmch_probe);
 
-void intel_gtt_get(size_t *gtt_total, size_t *stolen_size,
-		   phys_addr_t *mappable_base, unsigned long *mappable_end)
+void intel_gtt_get(u64 *gtt_total, size_t *stolen_size,
+		   phys_addr_t *mappable_base, u64 *mappable_end)
 {
 	*gtt_total = intel_private.gtt_total_entries << PAGE_SHIFT;
 	*stolen_size = intel_private.stolen_size;
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index da8faf78536a..5643b65cee20 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -429,7 +429,7 @@ static int hwrng_fillfn(void *unused)
 static void start_khwrngd(void)
 {
 	hwrng_fill = kthread_run(hwrng_fillfn, NULL, "hwrng");
-	if (hwrng_fill == ERR_PTR(-ENOMEM)) {
+	if (IS_ERR(hwrng_fill)) {
 		pr_err("hwrng_fill thread creation failed");
 		hwrng_fill = NULL;
 	}
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index fdb0f9b3fe45..8069b361b8dd 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -243,17 +243,15 @@ int misc_register(struct miscdevice * misc)
  *	@misc: device to unregister
  *
  *	Unregister a miscellaneous device that was previously
- *	successfully registered with misc_register(). Success
- *	is indicated by a zero return, a negative errno code
- *	indicates an error.
+ *	successfully registered with misc_register().
  */
 
-int misc_deregister(struct miscdevice *misc)
+void misc_deregister(struct miscdevice *misc)
 {
 	int i = DYNAMIC_MINORS - misc->minor - 1;
 
 	if (WARN_ON(list_empty(&misc->list)))
-		return -EINVAL;
+		return;
 
 	mutex_lock(&misc_mtx);
 	list_del(&misc->list);
@@ -261,7 +259,6 @@ int misc_deregister(struct miscdevice *misc)
 	if (i < DYNAMIC_MINORS && i >= 0)
 		clear_bit(i, misc_minors);
 	mutex_unlock(&misc_mtx);
-	return 0;
 }
 
 EXPORT_SYMBOL(misc_register);
@@ -281,10 +278,9 @@ static char *misc_devnode(struct device *dev, umode_t *mode)
 static int __init misc_init(void)
 {
 	int err;
+	struct proc_dir_entry *ret;
 
-#ifdef CONFIG_PROC_FS
-	proc_create("misc", 0, NULL, &misc_proc_fops);
-#endif
+	ret = proc_create("misc", 0, NULL, &misc_proc_fops);
 	misc_class = class_create(THIS_MODULE, "misc");
 	err = PTR_ERR(misc_class);
 	if (IS_ERR(misc_class))
@@ -300,7 +296,8 @@ fail_printk:
 	printk("unable to get major %d for misc devices\n", MISC_MAJOR);
 	class_destroy(misc_class);
 fail_remove:
-	remove_proc_entry("misc", NULL);
+	if (ret)
+		remove_proc_entry("misc", NULL);
 	return err;
 }
 subsys_initcall(misc_init);
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 9df78e2cc45d..97c2d8d433d6 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -702,7 +702,7 @@ static void atari_proc_infos(unsigned char *nvram, struct seq_file *seq,
 		seq_printf(seq, "%ds%s\n", nvram[10],
 		    nvram[10] < 8 ? ", no memory test" : "");
 
-	vmode = (nvram[14] << 8) || nvram[15];
+	vmode = (nvram[14] << 8) | nvram[15];
 	seq_printf(seq,
 	    "Video mode       : %s colors, %d columns, %s %s monitor\n",
 	    colors[vmode & 7],
diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c
index 014c9d90d297..f5a45d887a37 100644
--- a/drivers/char/toshiba.c
+++ b/drivers/char/toshiba.c
@@ -430,7 +430,7 @@ static int tosh_probe(void)
 	int i,major,minor,day,year,month,flag;
 	unsigned char signature[7] = { 0x54,0x4f,0x53,0x48,0x49,0x42,0x41 };
 	SMMRegisters regs;
-	void __iomem *bios = ioremap_cache(0xf0000, 0x10000);
+	void __iomem *bios = ioremap(0xf0000, 0x10000);
 
 	if (!bios)
 		return -ENOMEM;
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 283f00a7f036..1082d4bb016a 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -129,8 +129,9 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev,
 
 	device_initialize(&chip->dev);
 
-	chip->cdev.owner = chip->pdev->driver->owner;
 	cdev_init(&chip->cdev, &tpm_fops);
+	chip->cdev.owner = chip->pdev->driver->owner;
+	chip->cdev.kobj.parent = &chip->dev.kobj;
 
 	return chip;
 }
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index 44f9d20c19ac..1267322595da 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -233,6 +233,14 @@ static int crb_acpi_add(struct acpi_device *device)
 		return -ENODEV;
 	}
 
+	/* At least some versions of AMI BIOS have a bug that TPM2 table has
+	 * zero address for the control area and therefore we must fail.
+	*/
+	if (!buf->control_area_pa) {
+		dev_err(dev, "TPM2 ACPI table has a zero address for the control area\n");
+		return -EINVAL;
+	}
+
 	if (buf->hdr.length < sizeof(struct acpi_tpm2)) {
 		dev_err(dev, "TPM2 ACPI table has wrong size");
 		return -EINVAL;
diff --git a/drivers/char/xillybus/xillybus_pcie.c b/drivers/char/xillybus/xillybus_pcie.c
index d8266bc2ae35..9418300214e9 100644
--- a/drivers/char/xillybus/xillybus_pcie.c
+++ b/drivers/char/xillybus/xillybus_pcie.c
@@ -193,14 +193,16 @@ static int xilly_probe(struct pci_dev *pdev,
 	}
 
 	/*
-	 * In theory, an attempt to set the DMA mask to 64 and dma_using_dac=1
-	 * is the right thing. But some unclever PCIe drivers report it's OK
-	 * when the hardware drops those 64-bit PCIe packets. So trust
-	 * nobody and use 32 bits DMA addressing in any case.
+	 * Some (old and buggy?) hardware drops 64-bit addressed PCIe packets,
+	 * even when the PCIe driver claims that a 64-bit mask is OK. On the
+	 * other hand, on some architectures, 64-bit addressing is mandatory.
+	 * So go for the 64-bit mask only when failing is the other option.
 	 */
 
 	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
 		endpoint->dma_using_dac = 0;
+	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		endpoint->dma_using_dac = 1;
 	} else {
 		dev_err(endpoint->dev, "Failed to set DMA mask. Aborting.\n");
 		return -ENODEV;
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index c4cf075a2320..d08b3e5985be 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_COMMON_CLK)	+= clk-gate.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-mux.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-composite.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-fractional-divider.o
-obj-$(CONFIG_COMMON_CLK)	+= clk-gpio-gate.o
+obj-$(CONFIG_COMMON_CLK)	+= clk-gpio.o
 ifeq ($(CONFIG_OF), y)
 obj-$(CONFIG_COMMON_CLK)	+= clk-conf.o
 endif
diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
index 152dcb3f7b5f..61566bcefa53 100644
--- a/drivers/clk/at91/clk-h32mx.c
+++ b/drivers/clk/at91/clk-h32mx.c
@@ -116,8 +116,10 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 	h32mxclk->pmc = pmc;
 
 	clk = clk_register(NULL, &h32mxclk->hw);
-	if (!clk)
+	if (!clk) {
+		kfree(h32mxclk);
 		return;
+	}
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index c2400456a044..fd7247deabdc 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -171,8 +171,10 @@ at91_clk_register_main_osc(struct at91_pmc *pmc,
 	irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
 	ret = request_irq(osc->irq, clk_main_osc_irq_handler,
 			  IRQF_TRIGGER_HIGH, name, osc);
-	if (ret)
+	if (ret) {
+		kfree(osc);
 		return ERR_PTR(ret);
+	}
 
 	if (bypass)
 		pmc_write(pmc, AT91_CKGR_MOR,
@@ -612,17 +614,12 @@ void __init of_at91sam9x5_clk_main_setup(struct device_node *np,
 	int num_parents;
 	unsigned int irq;
 	const char *name = np->name;
-	int i;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > 2)
 		return;
 
-	for (i = 0; i < num_parents; ++i) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index f98eafe9b12d..620ea323356b 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -165,12 +165,16 @@ at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq,
 	irq_set_status_flags(master->irq, IRQ_NOAUTOEN);
 	ret = request_irq(master->irq, clk_master_irq_handler,
 			  IRQF_TRIGGER_HIGH, "clk-master", master);
-	if (ret)
+	if (ret) {
+		kfree(master);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &master->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(master->irq, master);
 		kfree(master);
+	}
 
 	return clk;
 }
@@ -218,7 +222,6 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
 {
 	struct clk *clk;
 	int num_parents;
-	int i;
 	unsigned int irq;
 	const char *parent_names[MASTER_SOURCE_MAX];
 	const char *name = np->name;
@@ -228,11 +231,7 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
 	if (num_parents <= 0 || num_parents > MASTER_SOURCE_MAX)
 		return;
 
-	for (i = 0; i < num_parents; ++i) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
index df2c1afa52b4..e4d7b574f1ea 100644
--- a/drivers/clk/at91/clk-peripheral.c
+++ b/drivers/clk/at91/clk-peripheral.c
@@ -134,7 +134,7 @@ at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name,
 
 static void clk_sam9x5_peripheral_autodiv(struct clk_sam9x5_peripheral *periph)
 {
-	struct clk *parent;
+	struct clk_hw *parent;
 	unsigned long parent_rate;
 	int shift = 0;
 
@@ -142,8 +142,8 @@ static void clk_sam9x5_peripheral_autodiv(struct clk_sam9x5_peripheral *periph)
 		return;
 
 	if (periph->range.max) {
-		parent = clk_get_parent_by_index(periph->hw.clk, 0);
-		parent_rate = __clk_get_rate(parent);
+		parent = clk_hw_get_parent_by_index(&periph->hw, 0);
+		parent_rate = clk_hw_get_rate(parent);
 		if (!parent_rate)
 			return;
 
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index cbbe40377ad6..18b60f4895a6 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -346,12 +346,16 @@ at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
 	irq_set_status_flags(pll->irq, IRQ_NOAUTOEN);
 	ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH,
 			  id ? "clk-pllb" : "clk-plla", pll);
-	if (ret)
+	if (ret) {
+		kfree(pll);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(pll->irq, pll);
 		kfree(pll);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 8c86c0f7847a..14b270b85fec 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -54,46 +54,47 @@ static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
 	return parent_rate >> pres;
 }
 
-static long clk_programmable_determine_rate(struct clk_hw *hw,
-					    unsigned long rate,
-					    unsigned long min_rate,
-					    unsigned long max_rate,
-					    unsigned long *best_parent_rate,
-					    struct clk_hw **best_parent_hw)
+static int clk_programmable_determine_rate(struct clk_hw *hw,
+					   struct clk_rate_request *req)
 {
-	struct clk *parent = NULL;
+	struct clk_hw *parent;
 	long best_rate = -EINVAL;
 	unsigned long parent_rate;
 	unsigned long tmp_rate;
 	int shift;
 	int i;
 
-	for (i = 0; i < __clk_get_num_parents(hw->clk); i++) {
-		parent = clk_get_parent_by_index(hw->clk, i);
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		parent = clk_hw_get_parent_by_index(hw, i);
 		if (!parent)
 			continue;
 
-		parent_rate = __clk_get_rate(parent);
+		parent_rate = clk_hw_get_rate(parent);
 		for (shift = 0; shift < PROG_PRES_MASK; shift++) {
 			tmp_rate = parent_rate >> shift;
-			if (tmp_rate <= rate)
+			if (tmp_rate <= req->rate)
 				break;
 		}
 
-		if (tmp_rate > rate)
+		if (tmp_rate > req->rate)
 			continue;
 
-		if (best_rate < 0 || (rate - tmp_rate) < (rate - best_rate)) {
+		if (best_rate < 0 ||
+		    (req->rate - tmp_rate) < (req->rate - best_rate)) {
 			best_rate = tmp_rate;
-			*best_parent_rate = parent_rate;
-			*best_parent_hw = __clk_get_hw(parent);
+			req->best_parent_rate = parent_rate;
+			req->best_parent_hw = parent;
 		}
 
 		if (!best_rate)
 			break;
 	}
 
-	return best_rate;
+	if (best_rate < 0)
+		return best_rate;
+
+	req->rate = best_rate;
+	return 0;
 }
 
 static int clk_programmable_set_parent(struct clk_hw *hw, u8 index)
@@ -230,7 +231,6 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
 {
 	int num;
 	u32 id;
-	int i;
 	struct clk *clk;
 	int num_parents;
 	const char *parent_names[PROG_SOURCE_MAX];
@@ -241,11 +241,7 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
 	if (num_parents <= 0 || num_parents > PROG_SOURCE_MAX)
 		return;
 
-	for (i = 0; i < num_parents; ++i) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	num = of_get_child_count(np);
 	if (!num || num > (PROG_ID_MAX + 1))
diff --git a/drivers/clk/at91/clk-slow.c b/drivers/clk/at91/clk-slow.c
index 98a84a865fe1..d0d5076a9b94 100644
--- a/drivers/clk/at91/clk-slow.c
+++ b/drivers/clk/at91/clk-slow.c
@@ -10,8 +10,10 @@
  *
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/delay.h>
 #include <linux/of.h>
@@ -371,17 +373,12 @@ void __init of_at91sam9x5_clk_slow_setup(struct device_node *np,
 	const char *parent_names[2];
 	int num_parents;
 	const char *name = np->name;
-	int i;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > 2)
 		return;
 
-	for (i = 0; i < num_parents; ++i) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
@@ -449,17 +446,12 @@ void __init of_at91sam9260_clk_slow_setup(struct device_node *np,
 	const char *parent_names[2];
 	int num_parents;
 	const char *name = np->name;
-	int i;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents != 2)
 		return;
 
-	for (i = 0; i < num_parents; ++i) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
diff --git a/drivers/clk/at91/clk-smd.c b/drivers/clk/at91/clk-smd.c
index 3817ea865ca2..a7f8501cfa05 100644
--- a/drivers/clk/at91/clk-smd.c
+++ b/drivers/clk/at91/clk-smd.c
@@ -145,7 +145,6 @@ void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 					struct at91_pmc *pmc)
 {
 	struct clk *clk;
-	int i;
 	int num_parents;
 	const char *parent_names[SMD_SOURCE_MAX];
 	const char *name = np->name;
@@ -154,11 +153,7 @@ void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 	if (num_parents <= 0 || num_parents > SMD_SOURCE_MAX)
 		return;
 
-	for (i = 0; i < num_parents; i++) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
diff --git a/drivers/clk/at91/clk-system.c b/drivers/clk/at91/clk-system.c
index a76d03fd577b..58008b3e8bc1 100644
--- a/drivers/clk/at91/clk-system.c
+++ b/drivers/clk/at91/clk-system.c
@@ -130,13 +130,17 @@ at91_clk_register_system(struct at91_pmc *pmc, const char *name,
 		irq_set_status_flags(sys->irq, IRQ_NOAUTOEN);
 		ret = request_irq(sys->irq, clk_system_irq_handler,
 				IRQF_TRIGGER_HIGH, name, sys);
-		if (ret)
+		if (ret) {
+			kfree(sys);
 			return ERR_PTR(ret);
+		}
 	}
 
 	clk = clk_register(NULL, &sys->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(sys->irq, sys);
 		kfree(sys);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
index b0cbd2b1ff59..8ab8502778a2 100644
--- a/drivers/clk/at91/clk-usb.c
+++ b/drivers/clk/at91/clk-usb.c
@@ -56,47 +56,43 @@ static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw,
 	return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1));
 }
 
-static long at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw,
-					      unsigned long rate,
-					      unsigned long min_rate,
-					      unsigned long max_rate,
-					      unsigned long *best_parent_rate,
-					      struct clk_hw **best_parent_hw)
+static int at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw,
+					     struct clk_rate_request *req)
 {
-	struct clk *parent = NULL;
+	struct clk_hw *parent;
 	long best_rate = -EINVAL;
 	unsigned long tmp_rate;
 	int best_diff = -1;
 	int tmp_diff;
 	int i;
 
-	for (i = 0; i < __clk_get_num_parents(hw->clk); i++) {
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
 		int div;
 
-		parent = clk_get_parent_by_index(hw->clk, i);
+		parent = clk_hw_get_parent_by_index(hw, i);
 		if (!parent)
 			continue;
 
 		for (div = 1; div < SAM9X5_USB_MAX_DIV + 2; div++) {
 			unsigned long tmp_parent_rate;
 
-			tmp_parent_rate = rate * div;
-			tmp_parent_rate = __clk_round_rate(parent,
+			tmp_parent_rate = req->rate * div;
+			tmp_parent_rate = clk_hw_round_rate(parent,
 							   tmp_parent_rate);
 			tmp_rate = DIV_ROUND_CLOSEST(tmp_parent_rate, div);
-			if (tmp_rate < rate)
-				tmp_diff = rate - tmp_rate;
+			if (tmp_rate < req->rate)
+				tmp_diff = req->rate - tmp_rate;
 			else
-				tmp_diff = tmp_rate - rate;
+				tmp_diff = tmp_rate - req->rate;
 
 			if (best_diff < 0 || best_diff > tmp_diff) {
 				best_rate = tmp_rate;
 				best_diff = tmp_diff;
-				*best_parent_rate = tmp_parent_rate;
-				*best_parent_hw = __clk_get_hw(parent);
+				req->best_parent_rate = tmp_parent_rate;
+				req->best_parent_hw = parent;
 			}
 
-			if (!best_diff || tmp_rate < rate)
+			if (!best_diff || tmp_rate < req->rate)
 				break;
 		}
 
@@ -104,7 +100,11 @@ static long at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw,
 			break;
 	}
 
-	return best_rate;
+	if (best_rate < 0)
+		return best_rate;
+
+	req->rate = best_rate;
+	return 0;
 }
 
 static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index)
@@ -273,7 +273,7 @@ static long at91rm9200_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
 					  unsigned long *parent_rate)
 {
 	struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
-	struct clk *parent = __clk_get_parent(hw->clk);
+	struct clk_hw *parent = clk_hw_get_parent(hw);
 	unsigned long bestrate = 0;
 	int bestdiff = -1;
 	unsigned long tmprate;
@@ -287,7 +287,7 @@ static long at91rm9200_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
 			continue;
 
 		tmp_parent_rate = rate * usb->divisors[i];
-		tmp_parent_rate = __clk_round_rate(parent, tmp_parent_rate);
+		tmp_parent_rate = clk_hw_round_rate(parent, tmp_parent_rate);
 		tmprate = DIV_ROUND_CLOSEST(tmp_parent_rate, usb->divisors[i]);
 		if (tmprate < rate)
 			tmpdiff = rate - tmprate;
@@ -373,7 +373,6 @@ void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
 					struct at91_pmc *pmc)
 {
 	struct clk *clk;
-	int i;
 	int num_parents;
 	const char *parent_names[USB_SOURCE_MAX];
 	const char *name = np->name;
@@ -382,11 +381,7 @@ void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
 	if (num_parents <= 0 || num_parents > USB_SOURCE_MAX)
 		return;
 
-	for (i = 0; i < num_parents; i++) {
-		parent_names[i] = of_clk_get_parent_name(np, i);
-		if (!parent_names[i])
-			return;
-	}
+	of_clk_parent_fill(np, parent_names, num_parents);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
diff --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
index ae3263bc1476..30dd697b1668 100644
--- a/drivers/clk/at91/clk-utmi.c
+++ b/drivers/clk/at91/clk-utmi.c
@@ -118,12 +118,16 @@ at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq,
 	irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN);
 	ret = request_irq(utmi->irq, clk_utmi_irq_handler,
 			  IRQF_TRIGGER_HIGH, "clk-utmi", utmi);
-	if (ret)
+	if (ret) {
+		kfree(utmi);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &utmi->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(utmi->irq, utmi);
 		kfree(utmi);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
index 39be2be82b0a..d1844f1f3729 100644
--- a/drivers/clk/at91/pmc.c
+++ b/drivers/clk/at91/pmc.c
@@ -125,7 +125,6 @@ static int pmc_irq_map(struct irq_domain *h, unsigned int virq,
 
 	irq_set_chip_and_handler(virq, &pmc_irq,
 				 handle_level_irq);
-	set_irq_flags(virq, IRQF_VALID);
 	irq_set_chip_data(virq, pmc);
 
 	return 0;
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index eb8e5dc9076d..8b87771c69b2 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -59,71 +59,63 @@ static inline void pmc_write(struct at91_pmc *pmc, int offset, u32 value)
 int of_at91_get_clk_range(struct device_node *np, const char *propname,
 			  struct clk_range *range);
 
-extern void __init of_at91sam9260_clk_slow_setup(struct device_node *np,
-						 struct at91_pmc *pmc);
-
-extern void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np,
-						    struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np,
-						       struct at91_pmc *pmc);
-extern void __init of_at91rm9200_clk_main_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_main_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-
-extern void __init of_at91rm9200_clk_pll_setup(struct device_node *np,
-					       struct at91_pmc *pmc);
-extern void __init of_at91sam9g45_clk_pll_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-extern void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np,
-						 struct at91_pmc *pmc);
-extern void __init of_sama5d3_clk_pll_setup(struct device_node *np,
-					    struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_plldiv_setup(struct device_node *np,
-						  struct at91_pmc *pmc);
-
-extern void __init of_at91rm9200_clk_master_setup(struct device_node *np,
-						  struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_master_setup(struct device_node *np,
-						  struct at91_pmc *pmc);
-
-extern void __init of_at91rm9200_clk_sys_setup(struct device_node *np,
-					       struct at91_pmc *pmc);
-
-extern void __init of_at91rm9200_clk_periph_setup(struct device_node *np,
-						  struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_periph_setup(struct device_node *np,
-						  struct at91_pmc *pmc);
-
-extern void __init of_at91rm9200_clk_prog_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-extern void __init of_at91sam9g45_clk_prog_setup(struct device_node *np,
-						 struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_prog_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-
-#if defined(CONFIG_HAVE_AT91_UTMI)
-extern void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-#endif
-
-#if defined(CONFIG_HAVE_AT91_USB_CLK)
-extern void __init of_at91rm9200_clk_usb_setup(struct device_node *np,
-					       struct at91_pmc *pmc);
-extern void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
-					       struct at91_pmc *pmc);
-extern void __init of_at91sam9n12_clk_usb_setup(struct device_node *np,
-						struct at91_pmc *pmc);
-#endif
-
-#if defined(CONFIG_HAVE_AT91_SMD)
-extern void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
-					       struct at91_pmc *pmc);
-#endif
-
-#if defined(CONFIG_HAVE_AT91_H32MX)
-extern void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
-					      struct at91_pmc *pmc);
-#endif
+void of_at91sam9260_clk_slow_setup(struct device_node *np,
+				   struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_main_osc_setup(struct device_node *np,
+				      struct at91_pmc *pmc);
+void of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np,
+					 struct at91_pmc *pmc);
+void of_at91rm9200_clk_main_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+void of_at91sam9x5_clk_main_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_pll_setup(struct device_node *np,
+				 struct at91_pmc *pmc);
+void of_at91sam9g45_clk_pll_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+void of_at91sam9g20_clk_pllb_setup(struct device_node *np,
+				   struct at91_pmc *pmc);
+void of_sama5d3_clk_pll_setup(struct device_node *np,
+			      struct at91_pmc *pmc);
+void of_at91sam9x5_clk_plldiv_setup(struct device_node *np,
+				    struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_master_setup(struct device_node *np,
+				    struct at91_pmc *pmc);
+void of_at91sam9x5_clk_master_setup(struct device_node *np,
+				    struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_sys_setup(struct device_node *np,
+				 struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_periph_setup(struct device_node *np,
+				    struct at91_pmc *pmc);
+void of_at91sam9x5_clk_periph_setup(struct device_node *np,
+				    struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_prog_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+void of_at91sam9g45_clk_prog_setup(struct device_node *np,
+				   struct at91_pmc *pmc);
+void of_at91sam9x5_clk_prog_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+
+void of_at91sam9x5_clk_utmi_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+
+void of_at91rm9200_clk_usb_setup(struct device_node *np,
+				 struct at91_pmc *pmc);
+void of_at91sam9x5_clk_usb_setup(struct device_node *np,
+				 struct at91_pmc *pmc);
+void of_at91sam9n12_clk_usb_setup(struct device_node *np,
+				  struct at91_pmc *pmc);
+
+void of_at91sam9x5_clk_smd_setup(struct device_node *np,
+				 struct at91_pmc *pmc);
+
+void of_sama5d4_clk_h32mx_setup(struct device_node *np,
+				struct at91_pmc *pmc);
 
 #endif /* __PMC_H_ */
diff --git a/drivers/clk/bcm/clk-iproc-asiu.c b/drivers/clk/bcm/clk-iproc-asiu.c
index e19c09cd9645..f630e1bbdcfe 100644
--- a/drivers/clk/bcm/clk-iproc-asiu.c
+++ b/drivers/clk/bcm/clk-iproc-asiu.c
@@ -222,10 +222,6 @@ void __init iproc_asiu_setup(struct device_node *node,
 		struct iproc_asiu_clk *asiu_clk;
 		const char *clk_name;
 
-		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
-		if (WARN_ON(!clk_name))
-			goto err_clk_register;
-
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
 		if (WARN_ON(ret))
@@ -259,7 +255,7 @@ void __init iproc_asiu_setup(struct device_node *node,
 
 err_clk_register:
 	for (i = 0; i < num_clks; i++)
-		kfree(asiu->clks[i].name);
+		clk_unregister(asiu->clk_data.clks[i]);
 	iounmap(asiu->gate_base);
 
 err_iomap_gate:
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
index 46fb84bc2674..2dda4e8295a9 100644
--- a/drivers/clk/bcm/clk-iproc-pll.c
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -366,7 +366,7 @@ static unsigned long iproc_pll_recalc_rate(struct clk_hw *hw,
 	val = readl(pll->pll_base + ctrl->ndiv_int.offset);
 	ndiv_int = (val >> ctrl->ndiv_int.shift) &
 		bit_mask(ctrl->ndiv_int.width);
-	ndiv = ndiv_int << ctrl->ndiv_int.shift;
+	ndiv = (u64)ndiv_int << ctrl->ndiv_int.shift;
 
 	if (ctrl->flags & IPROC_CLK_PLL_HAS_NDIV_FRAC) {
 		val = readl(pll->pll_base + ctrl->ndiv_frac.offset);
@@ -374,7 +374,8 @@ static unsigned long iproc_pll_recalc_rate(struct clk_hw *hw,
 			bit_mask(ctrl->ndiv_frac.width);
 
 		if (ndiv_frac != 0)
-			ndiv = (ndiv_int << ctrl->ndiv_int.shift) | ndiv_frac;
+			ndiv = ((u64)ndiv_int << ctrl->ndiv_int.shift) |
+				ndiv_frac;
 	}
 
 	val = readl(pll->pll_base + ctrl->pdiv.offset);
@@ -655,10 +656,6 @@ void __init iproc_pll_clk_setup(struct device_node *node,
 		memset(&init, 0, sizeof(init));
 		parent_name = node->name;
 
-		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
-		if (WARN_ON(!clk_name))
-			goto err_clk_register;
-
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
 		if (WARN_ON(ret))
@@ -690,10 +687,8 @@ void __init iproc_pll_clk_setup(struct device_node *node,
 	return;
 
 err_clk_register:
-	for (i = 0; i < num_clks; i++) {
-		kfree(pll->clks[i].name);
+	for (i = 0; i < num_clks; i++)
 		clk_unregister(pll->clk_data.clks[i]);
-	}
 
 err_pll_register:
 	if (pll->asiu_base)
diff --git a/drivers/clk/bcm/clk-kona.c b/drivers/clk/bcm/clk-kona.c
index 79a98506c433..3a15347b4233 100644
--- a/drivers/clk/bcm/clk-kona.c
+++ b/drivers/clk/bcm/clk-kona.c
@@ -16,6 +16,7 @@
 
 #include <linux/delay.h>
 #include <linux/kernel.h>
+#include <linux/clk.h>
 
 /*
  * "Policies" affect the frequencies of bus clocks provided by a
@@ -1010,25 +1011,23 @@ static long kona_peri_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 	struct bcm_clk_div *div = &bcm_clk->u.peri->div;
 
 	if (!divider_exists(div))
-		return __clk_get_rate(hw->clk);
+		return clk_hw_get_rate(hw);
 
 	/* Quietly avoid a zero rate */
 	return round_rate(bcm_clk->ccu, div, &bcm_clk->u.peri->pre_div,
 				rate ? rate : 1, *parent_rate, NULL);
 }
 
-static long kona_peri_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long min_rate,
-		unsigned long max_rate,
-		unsigned long *best_parent_rate, struct clk_hw **best_parent)
+static int kona_peri_clk_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct clk *clk = hw->clk;
-	struct clk *current_parent;
+	struct clk_hw *current_parent;
 	unsigned long parent_rate;
 	unsigned long best_delta;
 	unsigned long best_rate;
 	u32 parent_count;
+	long rate;
 	u32 which;
 
 	/*
@@ -1037,18 +1036,25 @@ static long kona_peri_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
 	 */
 	WARN_ON_ONCE(bcm_clk->init_data.flags & CLK_SET_RATE_NO_REPARENT);
 	parent_count = (u32)bcm_clk->init_data.num_parents;
-	if (parent_count < 2)
-		return kona_peri_clk_round_rate(hw, rate, best_parent_rate);
+	if (parent_count < 2) {
+		rate = kona_peri_clk_round_rate(hw, req->rate,
+						&req->best_parent_rate);
+		if (rate < 0)
+			return rate;
+
+		req->rate = rate;
+		return 0;
+	}
 
 	/* Unless we can do better, stick with current parent */
-	current_parent = clk_get_parent(clk);
-	parent_rate = __clk_get_rate(current_parent);
-	best_rate = kona_peri_clk_round_rate(hw, rate, &parent_rate);
-	best_delta = abs(best_rate - rate);
+	current_parent = clk_hw_get_parent(hw);
+	parent_rate = clk_hw_get_rate(current_parent);
+	best_rate = kona_peri_clk_round_rate(hw, req->rate, &parent_rate);
+	best_delta = abs(best_rate - req->rate);
 
 	/* Check whether any other parent clock can produce a better result */
 	for (which = 0; which < parent_count; which++) {
-		struct clk *parent = clk_get_parent_by_index(clk, which);
+		struct clk_hw *parent = clk_hw_get_parent_by_index(hw, which);
 		unsigned long delta;
 		unsigned long other_rate;
 
@@ -1057,18 +1063,20 @@ static long kona_peri_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
 			continue;
 
 		/* We don't support CLK_SET_RATE_PARENT */
-		parent_rate = __clk_get_rate(parent);
-		other_rate = kona_peri_clk_round_rate(hw, rate, &parent_rate);
-		delta = abs(other_rate - rate);
+		parent_rate = clk_hw_get_rate(parent);
+		other_rate = kona_peri_clk_round_rate(hw, req->rate,
+						      &parent_rate);
+		delta = abs(other_rate - req->rate);
 		if (delta < best_delta) {
 			best_delta = delta;
 			best_rate = other_rate;
-			*best_parent = __clk_get_hw(parent);
-			*best_parent_rate = parent_rate;
+			req->best_parent_hw = parent;
+			req->best_parent_rate = parent_rate;
 		}
 	}
 
-	return best_rate;
+	req->rate = best_rate;
+	return 0;
 }
 
 static int kona_peri_clk_set_parent(struct clk_hw *hw, u8 index)
@@ -1130,7 +1138,7 @@ static int kona_peri_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (parent_rate > (unsigned long)LONG_MAX)
 		return -EINVAL;
 
-	if (rate == __clk_get_rate(hw->clk))
+	if (rate == clk_hw_get_rate(hw))
 		return 0;
 
 	if (!divider_exists(div))
@@ -1249,6 +1257,7 @@ bool __init kona_ccu_init(struct ccu_data *ccu)
 	unsigned long flags;
 	unsigned int which;
 	struct clk **clks = ccu->clk_data.clks;
+	struct kona_clk *kona_clks = ccu->kona_clks;
 	bool success = true;
 
 	flags = ccu_lock(ccu);
@@ -1259,7 +1268,7 @@ bool __init kona_ccu_init(struct ccu_data *ccu)
 
 		if (!clks[which])
 			continue;
-		bcm_clk = to_kona_clk(__clk_get_hw(clks[which]));
+		bcm_clk = &kona_clks[which];
 		success &= __kona_clk_init(bcm_clk);
 	}
 
diff --git a/drivers/clk/berlin/berlin2-pll.c b/drivers/clk/berlin/berlin2-pll.c
index f4b8d324b083..1c2294d3ba85 100644
--- a/drivers/clk/berlin/berlin2-pll.c
+++ b/drivers/clk/berlin/berlin2-pll.c
@@ -61,7 +61,7 @@ berlin2_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	fbdiv = (val >> map->fbdiv_shift) & FBDIV_MASK;
 	rfdiv = (val >> map->rfdiv_shift) & RFDIV_MASK;
 	if (rfdiv == 0) {
-		pr_warn("%s has zero rfdiv\n", __clk_get_name(hw->clk));
+		pr_warn("%s has zero rfdiv\n", clk_hw_get_name(hw));
 		rfdiv = 1;
 	}
 
@@ -70,7 +70,7 @@ berlin2_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	vcodiv = map->vcodiv[vcodivsel];
 	if (vcodiv == 0) {
 		pr_warn("%s has zero vcodiv (index %d)\n",
-			__clk_get_name(hw->clk), vcodivsel);
+			clk_hw_get_name(hw), vcodivsel);
 		vcodiv = 1;
 	}
 
diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c
index e619285c6def..3bcd42fbb55e 100644
--- a/drivers/clk/clk-axi-clkgen.c
+++ b/drivers/clk/clk-axi-clkgen.c
@@ -10,7 +10,6 @@
 
 #include <linux/platform_device.h>
 #include <linux/clk-provider.h>
-#include <linux/clk.h>
 #include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/of.h>
diff --git a/drivers/clk/clk-bcm2835.c b/drivers/clk/clk-bcm2835.c
index 6b950ca8b711..dd295e498309 100644
--- a/drivers/clk/clk-bcm2835.c
+++ b/drivers/clk/clk-bcm2835.c
@@ -32,11 +32,6 @@ void __init bcm2835_init_clocks(void)
 	struct clk *clk;
 	int ret;
 
-	clk = clk_register_fixed_rate(NULL, "sys_pclk", NULL, CLK_IS_ROOT,
-					250000000);
-	if (IS_ERR(clk))
-		pr_err("sys_pclk not registered\n");
-
 	clk = clk_register_fixed_rate(NULL, "apb_pclk", NULL, CLK_IS_ROOT,
 					126000000);
 	if (IS_ERR(clk))
diff --git a/drivers/clk/clk-cdce706.c b/drivers/clk/clk-cdce706.c
index f01164fada5d..01877f64eff6 100644
--- a/drivers/clk/clk-cdce706.c
+++ b/drivers/clk/clk-cdce706.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/i2c.h>
@@ -309,7 +310,7 @@ static long cdce706_divider_round_rate(struct clk_hw *hw, unsigned long rate,
 	if (!mul)
 		div = CDCE706_DIVIDER_DIVIDER_MAX;
 
-	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
 		unsigned long best_diff = rate;
 		unsigned long best_div = 0;
 		struct clk *gp_clk = cdce->clkin_clk[cdce->clkin[0].parent];
diff --git a/drivers/clk/clk-cdce925.c b/drivers/clk/clk-cdce925.c
index 85fafb41e6ca..089bf88ffa8d 100644
--- a/drivers/clk/clk-cdce925.c
+++ b/drivers/clk/clk-cdce925.c
@@ -10,6 +10,7 @@
  * Copyright (C) 2014, Topic Embedded Products
  * Licenced under GPL
  */
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/module.h>
diff --git a/drivers/clk/clk-clps711x.c b/drivers/clk/clk-clps711x.c
index 715eec1a9902..ff4ef4f1df62 100644
--- a/drivers/clk/clk-clps711x.c
+++ b/drivers/clk/clk-clps711x.c
@@ -9,7 +9,6 @@
  * (at your option) any later version.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/io.h>
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 616f5aef3c26..4735de0660cc 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -55,78 +55,77 @@ static unsigned long clk_composite_recalc_rate(struct clk_hw *hw,
 	return rate_ops->recalc_rate(rate_hw, parent_rate);
 }
 
-static long clk_composite_determine_rate(struct clk_hw *hw, unsigned long rate,
-					unsigned long min_rate,
-					unsigned long max_rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_p)
+static int clk_composite_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
 {
 	struct clk_composite *composite = to_clk_composite(hw);
 	const struct clk_ops *rate_ops = composite->rate_ops;
 	const struct clk_ops *mux_ops = composite->mux_ops;
 	struct clk_hw *rate_hw = composite->rate_hw;
 	struct clk_hw *mux_hw = composite->mux_hw;
-	struct clk *parent;
+	struct clk_hw *parent;
 	unsigned long parent_rate;
 	long tmp_rate, best_rate = 0;
 	unsigned long rate_diff;
 	unsigned long best_rate_diff = ULONG_MAX;
+	long rate;
 	int i;
 
 	if (rate_hw && rate_ops && rate_ops->determine_rate) {
 		__clk_hw_set_clk(rate_hw, hw);
-		return rate_ops->determine_rate(rate_hw, rate, min_rate,
-						max_rate,
-						best_parent_rate,
-						best_parent_p);
+		return rate_ops->determine_rate(rate_hw, req);
 	} else if (rate_hw && rate_ops && rate_ops->round_rate &&
 		   mux_hw && mux_ops && mux_ops->set_parent) {
-		*best_parent_p = NULL;
+		req->best_parent_hw = NULL;
 
-		if (__clk_get_flags(hw->clk) & CLK_SET_RATE_NO_REPARENT) {
-			parent = clk_get_parent(mux_hw->clk);
-			*best_parent_p = __clk_get_hw(parent);
-			*best_parent_rate = __clk_get_rate(parent);
+		if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) {
+			parent = clk_hw_get_parent(mux_hw);
+			req->best_parent_hw = parent;
+			req->best_parent_rate = clk_hw_get_rate(parent);
 
-			return rate_ops->round_rate(rate_hw, rate,
-						    best_parent_rate);
+			rate = rate_ops->round_rate(rate_hw, req->rate,
+						    &req->best_parent_rate);
+			if (rate < 0)
+				return rate;
+
+			req->rate = rate;
+			return 0;
 		}
 
-		for (i = 0; i < __clk_get_num_parents(mux_hw->clk); i++) {
-			parent = clk_get_parent_by_index(mux_hw->clk, i);
+		for (i = 0; i < clk_hw_get_num_parents(mux_hw); i++) {
+			parent = clk_hw_get_parent_by_index(mux_hw, i);
 			if (!parent)
 				continue;
 
-			parent_rate = __clk_get_rate(parent);
+			parent_rate = clk_hw_get_rate(parent);
 
-			tmp_rate = rate_ops->round_rate(rate_hw, rate,
+			tmp_rate = rate_ops->round_rate(rate_hw, req->rate,
 							&parent_rate);
 			if (tmp_rate < 0)
 				continue;
 
-			rate_diff = abs(rate - tmp_rate);
+			rate_diff = abs(req->rate - tmp_rate);
 
-			if (!rate_diff || !*best_parent_p
+			if (!rate_diff || !req->best_parent_hw
 				       || best_rate_diff > rate_diff) {
-				*best_parent_p = __clk_get_hw(parent);
-				*best_parent_rate = parent_rate;
+				req->best_parent_hw = parent;
+				req->best_parent_rate = parent_rate;
 				best_rate_diff = rate_diff;
 				best_rate = tmp_rate;
 			}
 
 			if (!rate_diff)
-				return rate;
+				return 0;
 		}
 
-		return best_rate;
+		req->rate = best_rate;
+		return 0;
 	} else if (mux_hw && mux_ops && mux_ops->determine_rate) {
 		__clk_hw_set_clk(mux_hw, hw);
-		return mux_ops->determine_rate(mux_hw, rate, min_rate,
-					       max_rate, best_parent_rate,
-					       best_parent_p);
+		return mux_ops->determine_rate(mux_hw, req);
 	} else {
 		pr_err("clk: clk_composite_determine_rate function called, but no mux or rate callback set!\n");
-		return 0;
+		return -EINVAL;
 	}
 }
 
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 706b5783c360..f24d0a19ae70 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -78,12 +78,14 @@ static unsigned int _get_table_div(const struct clk_div_table *table,
 }
 
 static unsigned int _get_div(const struct clk_div_table *table,
-			     unsigned int val, unsigned long flags)
+			     unsigned int val, unsigned long flags, u8 width)
 {
 	if (flags & CLK_DIVIDER_ONE_BASED)
 		return val;
 	if (flags & CLK_DIVIDER_POWER_OF_TWO)
 		return 1 << val;
+	if (flags & CLK_DIVIDER_MAX_AT_ZERO)
+		return val ? val : div_mask(width) + 1;
 	if (table)
 		return _get_table_div(table, val);
 	return val + 1;
@@ -101,12 +103,14 @@ static unsigned int _get_table_val(const struct clk_div_table *table,
 }
 
 static unsigned int _get_val(const struct clk_div_table *table,
-			     unsigned int div, unsigned long flags)
+			     unsigned int div, unsigned long flags, u8 width)
 {
 	if (flags & CLK_DIVIDER_ONE_BASED)
 		return div;
 	if (flags & CLK_DIVIDER_POWER_OF_TWO)
 		return __ffs(div);
+	if (flags & CLK_DIVIDER_MAX_AT_ZERO)
+		return (div == div_mask(width) + 1) ? 0 : div;
 	if (table)
 		return  _get_table_val(table, div);
 	return div - 1;
@@ -117,13 +121,14 @@ unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate,
 				  const struct clk_div_table *table,
 				  unsigned long flags)
 {
+	struct clk_divider *divider = to_clk_divider(hw);
 	unsigned int div;
 
-	div = _get_div(table, val, flags);
+	div = _get_div(table, val, flags, divider->width);
 	if (!div) {
 		WARN(!(flags & CLK_DIVIDER_ALLOW_ZERO),
 			"%s: Zero divisor and CLK_DIVIDER_ALLOW_ZERO not set\n",
-			__clk_get_name(hw->clk));
+			clk_hw_get_name(hw));
 		return parent_rate;
 	}
 
@@ -285,7 +290,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 
 	maxdiv = _get_maxdiv(table, width, flags);
 
-	if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) {
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
 		parent_rate = *best_parent_rate;
 		bestdiv = _div_round(table, parent_rate, rate, flags);
 		bestdiv = bestdiv == 0 ? 1 : bestdiv;
@@ -311,7 +316,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 			*best_parent_rate = parent_rate_saved;
 			return i;
 		}
-		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
+		parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
 					       rate * i);
 		now = DIV_ROUND_UP(parent_rate, i);
 		if (_is_best_div(rate, now, best, flags)) {
@@ -323,7 +328,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 
 	if (!bestdiv) {
 		bestdiv = _get_maxdiv(table, width, flags);
-		*best_parent_rate = __clk_round_rate(__clk_get_parent(hw->clk), 1);
+		*best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), 1);
 	}
 
 	return bestdiv;
@@ -351,7 +356,8 @@ static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
 	if (divider->flags & CLK_DIVIDER_READ_ONLY) {
 		bestdiv = readl(divider->reg) >> divider->shift;
 		bestdiv &= div_mask(divider->width);
-		bestdiv = _get_div(divider->table, bestdiv, divider->flags);
+		bestdiv = _get_div(divider->table, bestdiv, divider->flags,
+			divider->width);
 		return DIV_ROUND_UP(*prate, bestdiv);
 	}
 
@@ -370,7 +376,7 @@ int divider_get_val(unsigned long rate, unsigned long parent_rate,
 	if (!_is_valid_div(table, div, flags))
 		return -EINVAL;
 
-	value = _get_val(table, div, flags);
+	value = _get_val(table, div, flags, width);
 
 	return min_t(unsigned int, value, div_mask(width));
 }
@@ -389,6 +395,8 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (divider->lock)
 		spin_lock_irqsave(divider->lock, flags);
+	else
+		__acquire(divider->lock);
 
 	if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
 		val = div_mask(divider->width) << (divider->shift + 16);
@@ -401,6 +409,8 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (divider->lock)
 		spin_unlock_irqrestore(divider->lock, flags);
+	else
+		__release(divider->lock);
 
 	return 0;
 }
diff --git a/drivers/clk/clk-efm32gg.c b/drivers/clk/clk-efm32gg.c
index 73a8d0ff530c..bac4553f04b8 100644
--- a/drivers/clk/clk-efm32gg.c
+++ b/drivers/clk/clk-efm32gg.c
@@ -6,7 +6,6 @@
  * the terms of the GNU General Public License version 2 as published by the
  * Free Software Foundation.
  */
-#include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index fccabe497f6e..83de57aeceea 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -41,12 +41,11 @@ static long clk_factor_round_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct clk_fixed_factor *fix = to_clk_fixed_factor(hw);
 
-	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
 		unsigned long best_parent;
 
 		best_parent = (rate / fix->mult) * fix->div;
-		*prate = __clk_round_rate(__clk_get_parent(hw->clk),
-				best_parent);
+		*prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent);
 	}
 
 	return (*prate / fix->div) * fix->mult;
diff --git a/drivers/clk/clk-fractional-divider.c b/drivers/clk/clk-fractional-divider.c
index 140eb5844dc4..e85f856b8592 100644
--- a/drivers/clk/clk-fractional-divider.c
+++ b/drivers/clk/clk-fractional-divider.c
@@ -27,11 +27,15 @@ static unsigned long clk_fd_recalc_rate(struct clk_hw *hw,
 
 	if (fd->lock)
 		spin_lock_irqsave(fd->lock, flags);
+	else
+		__acquire(fd->lock);
 
 	val = clk_readl(fd->reg);
 
 	if (fd->lock)
 		spin_unlock_irqrestore(fd->lock, flags);
+	else
+		__release(fd->lock);
 
 	m = (val & fd->mmask) >> fd->mshift;
 	n = (val & fd->nmask) >> fd->nshift;
@@ -80,6 +84,8 @@ static int clk_fd_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (fd->lock)
 		spin_lock_irqsave(fd->lock, flags);
+	else
+		__acquire(fd->lock);
 
 	val = clk_readl(fd->reg);
 	val &= ~(fd->mmask | fd->nmask);
@@ -88,6 +94,8 @@ static int clk_fd_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (fd->lock)
 		spin_unlock_irqrestore(fd->lock, flags);
+	else
+		__release(fd->lock);
 
 	return 0;
 }
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
index 551dd0672794..de0b322f5f58 100644
--- a/drivers/clk/clk-gate.c
+++ b/drivers/clk/clk-gate.c
@@ -52,6 +52,8 @@ static void clk_gate_endisable(struct clk_hw *hw, int enable)
 
 	if (gate->lock)
 		spin_lock_irqsave(gate->lock, flags);
+	else
+		__acquire(gate->lock);
 
 	if (gate->flags & CLK_GATE_HIWORD_MASK) {
 		reg = BIT(gate->bit_idx + 16);
@@ -70,6 +72,8 @@ static void clk_gate_endisable(struct clk_hw *hw, int enable)
 
 	if (gate->lock)
 		spin_unlock_irqrestore(gate->lock, flags);
+	else
+		__release(gate->lock);
 }
 
 static int clk_gate_enable(struct clk_hw *hw)
diff --git a/drivers/clk/clk-gpio-gate.c b/drivers/clk/clk-gpio-gate.c
deleted file mode 100644
index f564e624fb93..000000000000
--- a/drivers/clk/clk-gpio-gate.c
+++ /dev/null
@@ -1,207 +0,0 @@
-/*
- * Copyright (C) 2013 - 2014 Texas Instruments Incorporated - http://www.ti.com
- * Author: Jyri Sarha <jsarha@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Gpio gated clock implementation
- */
-
-#include <linux/clk-provider.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
-#include <linux/of_gpio.h>
-#include <linux/err.h>
-#include <linux/device.h>
-
-/**
- * DOC: basic gpio gated clock which can be enabled and disabled
- *      with gpio output
- * Traits of this clock:
- * prepare - clk_(un)prepare only ensures parent is (un)prepared
- * enable - clk_enable and clk_disable are functional & control gpio
- * rate - inherits rate from parent.  No clk_set_rate support
- * parent - fixed parent.  No clk_set_parent support
- */
-
-#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw)
-
-static int clk_gpio_gate_enable(struct clk_hw *hw)
-{
-	struct clk_gpio *clk = to_clk_gpio(hw);
-
-	gpiod_set_value(clk->gpiod, 1);
-
-	return 0;
-}
-
-static void clk_gpio_gate_disable(struct clk_hw *hw)
-{
-	struct clk_gpio *clk = to_clk_gpio(hw);
-
-	gpiod_set_value(clk->gpiod, 0);
-}
-
-static int clk_gpio_gate_is_enabled(struct clk_hw *hw)
-{
-	struct clk_gpio *clk = to_clk_gpio(hw);
-
-	return gpiod_get_value(clk->gpiod);
-}
-
-const struct clk_ops clk_gpio_gate_ops = {
-	.enable = clk_gpio_gate_enable,
-	.disable = clk_gpio_gate_disable,
-	.is_enabled = clk_gpio_gate_is_enabled,
-};
-EXPORT_SYMBOL_GPL(clk_gpio_gate_ops);
-
-/**
- * clk_register_gpio - register a gpip clock with the clock framework
- * @dev: device that is registering this clock
- * @name: name of this clock
- * @parent_name: name of this clock's parent
- * @gpio: gpio number to gate this clock
- * @active_low: true if gpio should be set to 0 to enable clock
- * @flags: clock flags
- */
-struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
-		const char *parent_name, unsigned gpio, bool active_low,
-		unsigned long flags)
-{
-	struct clk_gpio *clk_gpio = NULL;
-	struct clk *clk = ERR_PTR(-EINVAL);
-	struct clk_init_data init = { NULL };
-	unsigned long gpio_flags;
-	int err;
-
-	if (active_low)
-		gpio_flags = GPIOF_ACTIVE_LOW | GPIOF_OUT_INIT_HIGH;
-	else
-		gpio_flags = GPIOF_OUT_INIT_LOW;
-
-	if (dev)
-		err = devm_gpio_request_one(dev, gpio, gpio_flags, name);
-	else
-		err = gpio_request_one(gpio, gpio_flags, name);
-
-	if (err) {
-		pr_err("%s: %s: Error requesting clock control gpio %u\n",
-		       __func__, name, gpio);
-		return ERR_PTR(err);
-	}
-
-	if (dev)
-		clk_gpio = devm_kzalloc(dev, sizeof(struct clk_gpio),
-					GFP_KERNEL);
-	else
-		clk_gpio = kzalloc(sizeof(struct clk_gpio), GFP_KERNEL);
-
-	if (!clk_gpio) {
-		clk = ERR_PTR(-ENOMEM);
-		goto clk_register_gpio_gate_err;
-	}
-
-	init.name = name;
-	init.ops = &clk_gpio_gate_ops;
-	init.flags = flags | CLK_IS_BASIC;
-	init.parent_names = (parent_name ? &parent_name : NULL);
-	init.num_parents = (parent_name ? 1 : 0);
-
-	clk_gpio->gpiod = gpio_to_desc(gpio);
-	clk_gpio->hw.init = &init;
-
-	clk = clk_register(dev, &clk_gpio->hw);
-
-	if (!IS_ERR(clk))
-		return clk;
-
-	if (!dev)
-		kfree(clk_gpio);
-
-clk_register_gpio_gate_err:
-	if (!dev)
-		gpio_free(gpio);
-
-	return clk;
-}
-EXPORT_SYMBOL_GPL(clk_register_gpio_gate);
-
-#ifdef CONFIG_OF
-/**
- * The clk_register_gpio_gate has to be delayed, because the EPROBE_DEFER
- * can not be handled properly at of_clk_init() call time.
- */
-
-struct clk_gpio_gate_delayed_register_data {
-	struct device_node *node;
-	struct mutex lock;
-	struct clk *clk;
-};
-
-static struct clk *of_clk_gpio_gate_delayed_register_get(
-		struct of_phandle_args *clkspec,
-		void *_data)
-{
-	struct clk_gpio_gate_delayed_register_data *data = _data;
-	struct clk *clk;
-	const char *clk_name = data->node->name;
-	const char *parent_name;
-	int gpio;
-	enum of_gpio_flags of_flags;
-
-	mutex_lock(&data->lock);
-
-	if (data->clk) {
-		mutex_unlock(&data->lock);
-		return data->clk;
-	}
-
-	gpio = of_get_named_gpio_flags(data->node, "enable-gpios", 0,
-						&of_flags);
-	if (gpio < 0) {
-		mutex_unlock(&data->lock);
-		if (gpio != -EPROBE_DEFER)
-			pr_err("%s: %s: Can't get 'enable-gpios' DT property\n",
-			       __func__, clk_name);
-		return ERR_PTR(gpio);
-	}
-
-	parent_name = of_clk_get_parent_name(data->node, 0);
-
-	clk = clk_register_gpio_gate(NULL, clk_name, parent_name, gpio,
-					of_flags & OF_GPIO_ACTIVE_LOW, 0);
-	if (IS_ERR(clk)) {
-		mutex_unlock(&data->lock);
-		return clk;
-	}
-
-	data->clk = clk;
-	mutex_unlock(&data->lock);
-
-	return clk;
-}
-
-/**
- * of_gpio_gate_clk_setup() - Setup function for gpio controlled clock
- */
-static void __init of_gpio_gate_clk_setup(struct device_node *node)
-{
-	struct clk_gpio_gate_delayed_register_data *data;
-
-	data = kzalloc(sizeof(struct clk_gpio_gate_delayed_register_data),
-		       GFP_KERNEL);
-	if (!data)
-		return;
-
-	data->node = node;
-	mutex_init(&data->lock);
-
-	of_clk_add_provider(node, of_clk_gpio_gate_delayed_register_get, data);
-}
-CLK_OF_DECLARE(gpio_gate_clk, "gpio-gate-clock", of_gpio_gate_clk_setup);
-#endif
diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c
new file mode 100644
index 000000000000..10819e248414
--- /dev/null
+++ b/drivers/clk/clk-gpio.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright (C) 2013 - 2014 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Authors:
+ *    Jyri Sarha <jsarha@ti.com>
+ *    Sergej Sawazki <ce3a@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Gpio controlled clock implementation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_gpio.h>
+#include <linux/err.h>
+#include <linux/device.h>
+
+/**
+ * DOC: basic gpio gated clock which can be enabled and disabled
+ *      with gpio output
+ * Traits of this clock:
+ * prepare - clk_(un)prepare only ensures parent is (un)prepared
+ * enable - clk_enable and clk_disable are functional & control gpio
+ * rate - inherits rate from parent.  No clk_set_rate support
+ * parent - fixed parent.  No clk_set_parent support
+ */
+
+#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw)
+
+static int clk_gpio_gate_enable(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, 1);
+
+	return 0;
+}
+
+static void clk_gpio_gate_disable(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, 0);
+}
+
+static int clk_gpio_gate_is_enabled(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	return gpiod_get_value(clk->gpiod);
+}
+
+const struct clk_ops clk_gpio_gate_ops = {
+	.enable = clk_gpio_gate_enable,
+	.disable = clk_gpio_gate_disable,
+	.is_enabled = clk_gpio_gate_is_enabled,
+};
+EXPORT_SYMBOL_GPL(clk_gpio_gate_ops);
+
+/**
+ * DOC: basic clock multiplexer which can be controlled with a gpio output
+ * Traits of this clock:
+ * prepare - clk_prepare only ensures that parents are prepared
+ * rate - rate is only affected by parent switching.  No clk_set_rate support
+ * parent - parent is adjustable through clk_set_parent
+ */
+
+static u8 clk_gpio_mux_get_parent(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	return gpiod_get_value(clk->gpiod);
+}
+
+static int clk_gpio_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, index);
+
+	return 0;
+}
+
+const struct clk_ops clk_gpio_mux_ops = {
+	.get_parent = clk_gpio_mux_get_parent,
+	.set_parent = clk_gpio_mux_set_parent,
+	.determine_rate = __clk_mux_determine_rate,
+};
+EXPORT_SYMBOL_GPL(clk_gpio_mux_ops);
+
+static struct clk *clk_register_gpio(struct device *dev, const char *name,
+		const char * const *parent_names, u8 num_parents, unsigned gpio,
+		bool active_low, unsigned long flags,
+		const struct clk_ops *clk_gpio_ops)
+{
+	struct clk_gpio *clk_gpio;
+	struct clk *clk;
+	struct clk_init_data init = {};
+	unsigned long gpio_flags;
+	int err;
+
+	if (dev)
+		clk_gpio = devm_kzalloc(dev, sizeof(*clk_gpio),	GFP_KERNEL);
+	else
+		clk_gpio = kzalloc(sizeof(*clk_gpio), GFP_KERNEL);
+
+	if (!clk_gpio)
+		return ERR_PTR(-ENOMEM);
+
+	if (active_low)
+		gpio_flags = GPIOF_ACTIVE_LOW | GPIOF_OUT_INIT_HIGH;
+	else
+		gpio_flags = GPIOF_OUT_INIT_LOW;
+
+	if (dev)
+		err = devm_gpio_request_one(dev, gpio, gpio_flags, name);
+	else
+		err = gpio_request_one(gpio, gpio_flags, name);
+	if (err) {
+		if (err != -EPROBE_DEFER)
+			pr_err("%s: %s: Error requesting clock control gpio %u\n",
+					__func__, name, gpio);
+		if (!dev)
+			kfree(clk_gpio);
+
+		return ERR_PTR(err);
+	}
+
+	init.name = name;
+	init.ops = clk_gpio_ops;
+	init.flags = flags | CLK_IS_BASIC;
+	init.parent_names = parent_names;
+	init.num_parents = num_parents;
+
+	clk_gpio->gpiod = gpio_to_desc(gpio);
+	clk_gpio->hw.init = &init;
+
+	if (dev)
+		clk = devm_clk_register(dev, &clk_gpio->hw);
+	else
+		clk = clk_register(NULL, &clk_gpio->hw);
+
+	if (!IS_ERR(clk))
+		return clk;
+
+	if (!dev) {
+		gpiod_put(clk_gpio->gpiod);
+		kfree(clk_gpio);
+	}
+
+	return clk;
+}
+
+/**
+ * clk_register_gpio_gate - register a gpio clock gate with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of this clock's parent
+ * @gpio: gpio number to gate this clock
+ * @active_low: true if gpio should be set to 0 to enable clock
+ * @flags: clock flags
+ */
+struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
+		const char *parent_name, unsigned gpio, bool active_low,
+		unsigned long flags)
+{
+	return clk_register_gpio(dev, name,
+			(parent_name ? &parent_name : NULL),
+			(parent_name ? 1 : 0), gpio, active_low, flags,
+			&clk_gpio_gate_ops);
+}
+EXPORT_SYMBOL_GPL(clk_register_gpio_gate);
+
+/**
+ * clk_register_gpio_mux - register a gpio clock mux with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_names: names of this clock's parents
+ * @num_parents: number of parents listed in @parent_names
+ * @gpio: gpio number to gate this clock
+ * @active_low: true if gpio should be set to 0 to enable clock
+ * @flags: clock flags
+ */
+struct clk *clk_register_gpio_mux(struct device *dev, const char *name,
+		const char * const *parent_names, u8 num_parents, unsigned gpio,
+		bool active_low, unsigned long flags)
+{
+	if (num_parents != 2) {
+		pr_err("mux-clock %s must have 2 parents\n", name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return clk_register_gpio(dev, name, parent_names, num_parents,
+			gpio, active_low, flags, &clk_gpio_mux_ops);
+}
+EXPORT_SYMBOL_GPL(clk_register_gpio_mux);
+
+#ifdef CONFIG_OF
+/**
+ * clk_register_get() has to be delayed, because -EPROBE_DEFER
+ * can not be handled properly at of_clk_init() call time.
+ */
+
+struct clk_gpio_delayed_register_data {
+	const char *gpio_name;
+	struct device_node *node;
+	struct mutex lock;
+	struct clk *clk;
+	struct clk *(*clk_register_get)(const char *name,
+			const char * const *parent_names, u8 num_parents,
+			unsigned gpio, bool active_low);
+};
+
+static struct clk *of_clk_gpio_delayed_register_get(
+		struct of_phandle_args *clkspec, void *_data)
+{
+	struct clk_gpio_delayed_register_data *data = _data;
+	struct clk *clk;
+	const char **parent_names;
+	int i, num_parents;
+	int gpio;
+	enum of_gpio_flags of_flags;
+
+	mutex_lock(&data->lock);
+
+	if (data->clk) {
+		mutex_unlock(&data->lock);
+		return data->clk;
+	}
+
+	gpio = of_get_named_gpio_flags(data->node, data->gpio_name, 0,
+			&of_flags);
+	if (gpio < 0) {
+		mutex_unlock(&data->lock);
+		if (gpio == -EPROBE_DEFER)
+			pr_debug("%s: %s: GPIOs not yet available, retry later\n",
+					data->node->name, __func__);
+		else
+			pr_err("%s: %s: Can't get '%s' DT property\n",
+					data->node->name, __func__,
+					data->gpio_name);
+		return ERR_PTR(gpio);
+	}
+
+	num_parents = of_clk_get_parent_count(data->node);
+
+	parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL);
+	if (!parent_names) {
+		clk = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	for (i = 0; i < num_parents; i++)
+		parent_names[i] = of_clk_get_parent_name(data->node, i);
+
+	clk = data->clk_register_get(data->node->name, parent_names,
+			num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW);
+	if (IS_ERR(clk))
+		goto out;
+
+	data->clk = clk;
+out:
+	mutex_unlock(&data->lock);
+	kfree(parent_names);
+
+	return clk;
+}
+
+static struct clk *of_clk_gpio_gate_delayed_register_get(const char *name,
+		const char * const *parent_names, u8 num_parents,
+		unsigned gpio, bool active_low)
+{
+	return clk_register_gpio_gate(NULL, name, parent_names[0],
+			gpio, active_low, 0);
+}
+
+static struct clk *of_clk_gpio_mux_delayed_register_get(const char *name,
+		const char * const *parent_names, u8 num_parents, unsigned gpio,
+		bool active_low)
+{
+	return clk_register_gpio_mux(NULL, name, parent_names, num_parents,
+			gpio, active_low, 0);
+}
+
+static void __init of_gpio_clk_setup(struct device_node *node,
+		const char *gpio_name,
+		struct clk *(*clk_register_get)(const char *name,
+				const char * const *parent_names,
+				u8 num_parents,
+				unsigned gpio, bool active_low))
+{
+	struct clk_gpio_delayed_register_data *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->node = node;
+	data->gpio_name = gpio_name;
+	data->clk_register_get = clk_register_get;
+	mutex_init(&data->lock);
+
+	of_clk_add_provider(node, of_clk_gpio_delayed_register_get, data);
+}
+
+static void __init of_gpio_gate_clk_setup(struct device_node *node)
+{
+	of_gpio_clk_setup(node, "enable-gpios",
+		of_clk_gpio_gate_delayed_register_get);
+}
+CLK_OF_DECLARE(gpio_gate_clk, "gpio-gate-clock", of_gpio_gate_clk_setup);
+
+void __init of_gpio_mux_clk_setup(struct device_node *node)
+{
+	of_gpio_clk_setup(node, "select-gpios",
+		of_clk_gpio_mux_delayed_register_get);
+}
+CLK_OF_DECLARE(gpio_mux_clk, "gpio-mux-clock", of_gpio_mux_clk_setup);
+#endif
diff --git a/drivers/clk/clk-highbank.c b/drivers/clk/clk-highbank.c
index 2e7e9d9798cb..be3a21abb185 100644
--- a/drivers/clk/clk-highbank.c
+++ b/drivers/clk/clk-highbank.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
diff --git a/drivers/clk/clk-moxart.c b/drivers/clk/clk-moxart.c
index 5181b89c3cb2..f37f719643ec 100644
--- a/drivers/clk/clk-moxart.c
+++ b/drivers/clk/clk-moxart.c
@@ -10,6 +10,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
index 6066a01b20ea..7129c86a79db 100644
--- a/drivers/clk/clk-mux.c
+++ b/drivers/clk/clk-mux.c
@@ -10,7 +10,6 @@
  * Simple multiplexer clock implementation
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -32,7 +31,7 @@
 static u8 clk_mux_get_parent(struct clk_hw *hw)
 {
 	struct clk_mux *mux = to_clk_mux(hw);
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	/*
@@ -85,6 +84,8 @@ static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
 
 	if (mux->lock)
 		spin_lock_irqsave(mux->lock, flags);
+	else
+		__acquire(mux->lock);
 
 	if (mux->flags & CLK_MUX_HIWORD_MASK) {
 		val = mux->mask << (mux->shift + 16);
@@ -97,6 +98,8 @@ static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
 
 	if (mux->lock)
 		spin_unlock_irqrestore(mux->lock, flags);
+	else
+		__release(mux->lock);
 
 	return 0;
 }
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index c9487179f25f..e4d8a991c58f 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -8,8 +8,7 @@
 #define pr_fmt(fmt) "Nomadik SRC clocks: " fmt
 
 #include <linux/bitops.h>
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/clk-provider.h>
diff --git a/drivers/clk/clk-palmas.c b/drivers/clk/clk-palmas.c
index 45a535ab48aa..8e3039f0c3f9 100644
--- a/drivers/clk/clk-palmas.c
+++ b/drivers/clk/clk-palmas.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/palmas.h>
 #include <linux/module.h>
diff --git a/drivers/clk/clk-rk808.c b/drivers/clk/clk-rk808.c
index 83902b9cd49e..0fee2f4ca258 100644
--- a/drivers/clk/clk-rk808.c
+++ b/drivers/clk/clk-rk808.c
@@ -15,7 +15,6 @@
  * more details.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/module.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 9b13a303d3f8..d266299dfdb1 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -58,21 +58,17 @@ static struct s2mps11_clk *to_s2mps11_clk(struct clk_hw *hw)
 static int s2mps11_clk_prepare(struct clk_hw *hw)
 {
 	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
-	int ret;
 
-	ret = regmap_update_bits(s2mps11->iodev->regmap_pmic,
+	return regmap_update_bits(s2mps11->iodev->regmap_pmic,
 				 s2mps11->reg,
 				 s2mps11->mask, s2mps11->mask);
-
-	return ret;
 }
 
 static void s2mps11_clk_unprepare(struct clk_hw *hw)
 {
 	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
-	int ret;
 
-	ret = regmap_update_bits(s2mps11->iodev->regmap_pmic, s2mps11->reg,
+	regmap_update_bits(s2mps11->iodev->regmap_pmic, s2mps11->reg,
 			   s2mps11->mask, ~s2mps11->mask);
 }
 
@@ -186,15 +182,15 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	struct clk_init_data *clks_init;
 	int i, ret = 0;
 
-	s2mps11_clks = devm_kzalloc(&pdev->dev, sizeof(*s2mps11_clk) *
-					S2MPS11_CLKS_NUM, GFP_KERNEL);
+	s2mps11_clks = devm_kcalloc(&pdev->dev, S2MPS11_CLKS_NUM,
+				sizeof(*s2mps11_clk), GFP_KERNEL);
 	if (!s2mps11_clks)
 		return -ENOMEM;
 
 	s2mps11_clk = s2mps11_clks;
 
-	clk_table = devm_kzalloc(&pdev->dev, sizeof(struct clk *) *
-				 S2MPS11_CLKS_NUM, GFP_KERNEL);
+	clk_table = devm_kcalloc(&pdev->dev, S2MPS11_CLKS_NUM,
+				sizeof(struct clk *), GFP_KERNEL);
 	if (!clk_table)
 		return -ENOMEM;
 
@@ -246,7 +242,7 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 					s2mps11_name(s2mps11_clk), NULL);
 		if (!s2mps11_clk->lookup) {
 			ret = -ENOMEM;
-			goto err_lup;
+			goto err_reg;
 		}
 	}
 
@@ -265,16 +261,10 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, s2mps11_clks);
 
 	return ret;
-err_lup:
-	devm_clk_unregister(&pdev->dev, s2mps11_clk->clk);
+
 err_reg:
-	while (s2mps11_clk > s2mps11_clks) {
-		if (s2mps11_clk->lookup) {
-			clkdev_drop(s2mps11_clk->lookup);
-			devm_clk_unregister(&pdev->dev, s2mps11_clk->clk);
-		}
-		s2mps11_clk--;
-	}
+	while (--i >= 0)
+		clkdev_drop(s2mps11_clks[i].lookup);
 
 	return ret;
 }
@@ -322,7 +312,7 @@ static int __init s2mps11_clk_init(void)
 }
 subsys_initcall(s2mps11_clk_init);
 
-static void __init s2mps11_clk_cleanup(void)
+static void __exit s2mps11_clk_cleanup(void)
 {
 	platform_driver_unregister(&s2mps11_clk_driver);
 }
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index e39e1e680b3c..5596c0aac22f 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -18,7 +18,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/clkdev.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -439,7 +439,7 @@ static unsigned long si5351_pll_recalc_rate(struct clk_hw *hw,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: p1 = %lu, p2 = %lu, p3 = %lu, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk),
+		__func__, clk_hw_get_name(hw),
 		hwdata->params.p1, hwdata->params.p2, hwdata->params.p3,
 		parent_rate, (unsigned long)rate);
 
@@ -497,7 +497,7 @@ static long si5351_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: a = %lu, b = %lu, c = %lu, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk), a, b, c,
+		__func__, clk_hw_get_name(hw), a, b, c,
 		*parent_rate, rate);
 
 	return rate;
@@ -521,7 +521,7 @@ static int si5351_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: p1 = %lu, p2 = %lu, p3 = %lu, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk),
+		__func__, clk_hw_get_name(hw),
 		hwdata->params.p1, hwdata->params.p2, hwdata->params.p3,
 		parent_rate, rate);
 
@@ -632,7 +632,7 @@ static unsigned long si5351_msynth_recalc_rate(struct clk_hw *hw,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: p1 = %lu, p2 = %lu, p3 = %lu, m = %lu, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk),
+		__func__, clk_hw_get_name(hw),
 		hwdata->params.p1, hwdata->params.p2, hwdata->params.p3,
 		m, parent_rate, (unsigned long)rate);
 
@@ -663,7 +663,7 @@ static long si5351_msynth_round_rate(struct clk_hw *hw, unsigned long rate,
 		divby4 = 1;
 
 	/* multisync can set pll */
-	if (__clk_get_flags(hwdata->hw.clk) & CLK_SET_RATE_PARENT) {
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
 		/*
 		 * find largest integer divider for max
 		 * vco frequency and given target rate
@@ -745,7 +745,7 @@ static long si5351_msynth_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: a = %lu, b = %lu, c = %lu, divby4 = %d, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk), a, b, c, divby4,
+		__func__, clk_hw_get_name(hw), a, b, c, divby4,
 		*parent_rate, rate);
 
 	return rate;
@@ -777,7 +777,7 @@ static int si5351_msynth_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: p1 = %lu, p2 = %lu, p3 = %lu, divby4 = %d, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk),
+		__func__, clk_hw_get_name(hw),
 		hwdata->params.p1, hwdata->params.p2, hwdata->params.p3,
 		divby4, parent_rate, rate);
 
@@ -1013,7 +1013,7 @@ static long si5351_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		rate = SI5351_CLKOUT_MIN_FREQ;
 
 	/* request frequency if multisync master */
-	if (__clk_get_flags(hwdata->hw.clk) & CLK_SET_RATE_PARENT) {
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
 		/* use r divider for frequencies below 1MHz */
 		rdiv = SI5351_OUTPUT_CLK_DIV_1;
 		while (rate < SI5351_MULTISYNTH_MIN_FREQ &&
@@ -1042,7 +1042,7 @@ static long si5351_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: rdiv = %u, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk), (1 << rdiv),
+		__func__, clk_hw_get_name(hw), (1 << rdiv),
 		*parent_rate, rate);
 
 	return rate;
@@ -1093,7 +1093,7 @@ static int si5351_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: rdiv = %u, parent_rate = %lu, rate = %lu\n",
-		__func__, __clk_get_name(hwdata->hw.clk), (1 << rdiv),
+		__func__, clk_hw_get_name(hw), (1 << rdiv),
 		parent_rate, rate);
 
 	return 0;
diff --git a/drivers/clk/clk-si570.c b/drivers/clk/clk-si570.c
index 20a5aec98b1a..cf478aa9fa5d 100644
--- a/drivers/clk/clk-si570.c
+++ b/drivers/clk/clk-si570.c
@@ -19,6 +19,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/module.h>
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index b9b12a742970..fd89e771107e 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -175,11 +175,10 @@ static long clk_apb_mul_round_rate(struct clk_hw *hw, unsigned long rate,
 	if (readl(base + STM32F4_RCC_CFGR) & BIT(am->bit_idx))
 		mult = 2;
 
-	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
 		unsigned long best_parent = rate / mult;
 
-		*prate =
-		    __clk_round_rate(__clk_get_parent(hw->clk), best_parent);
+		*prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent);
 	}
 
 	return *prate * mult;
@@ -268,7 +267,7 @@ static int stm32f4_rcc_lookup_clk_idx(u8 primary, u8 secondary)
 	memcpy(table, stm32f42xx_gate_map, sizeof(table));
 
 	/* only bits set in table can be used as indices */
-	if (WARN_ON(secondary > 8 * sizeof(table) ||
+	if (WARN_ON(secondary >= BITS_PER_BYTE * sizeof(table) ||
 		    0 == (table[BIT_ULL_WORD(secondary)] &
 			  BIT_ULL_MASK(secondary))))
 		return -EINVAL;
diff --git a/drivers/clk/clk-twl6040.c b/drivers/clk/clk-twl6040.c
index 4a755135bcd3..8e5ed649a098 100644
--- a/drivers/clk/clk-twl6040.c
+++ b/drivers/clk/clk-twl6040.c
@@ -20,7 +20,6 @@
 *
 */
 
-#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
@@ -91,7 +90,7 @@ static int twl6040_clk_probe(struct platform_device *pdev)
 	clkdata->twl6040 = twl6040;
 
 	clkdata->mcpdm_fclk.init = &wm831x_clkout_init;
-	clkdata->clk = clk_register(&pdev->dev, &clkdata->mcpdm_fclk);
+	clkdata->clk = devm_clk_register(&pdev->dev, &clkdata->mcpdm_fclk);
 	if (IS_ERR(clkdata->clk))
 		return PTR_ERR(clkdata->clk);
 
@@ -100,21 +99,11 @@ static int twl6040_clk_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int twl6040_clk_remove(struct platform_device *pdev)
-{
-	struct twl6040_clk *clkdata = platform_get_drvdata(pdev);
-
-	clk_unregister(clkdata->clk);
-
-	return 0;
-}
-
 static struct platform_driver twl6040_clk_driver = {
 	.driver = {
 		.name = "twl6040-clk",
 	},
 	.probe = twl6040_clk_probe,
-	.remove = twl6040_clk_remove,
 };
 
 module_platform_driver(twl6040_clk_driver);
diff --git a/drivers/clk/clk-u300.c b/drivers/clk/clk-u300.c
index 18bf5e576b93..95d1742dac30 100644
--- a/drivers/clk/clk-u300.c
+++ b/drivers/clk/clk-u300.c
@@ -5,8 +5,8 @@
  * Author: Linus Walleij <linus.walleij@stericsson.com>
  * Author: Jonas Aaberg <jonas.aberg@stericsson.com>
  */
-#include <linux/clk.h>
 #include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/clk-provider.h>
diff --git a/drivers/clk/clk-wm831x.c b/drivers/clk/clk-wm831x.c
index ef67719f4e52..43f9d15255f4 100644
--- a/drivers/clk/clk-wm831x.c
+++ b/drivers/clk/clk-wm831x.c
@@ -12,7 +12,6 @@
  *
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/module.h>
diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c
index f26b3ac36b27..96a6190acac2 100644
--- a/drivers/clk/clk-xgene.c
+++ b/drivers/clk/clk-xgene.c
@@ -60,7 +60,6 @@ enum xgene_pll_type {
 
 struct xgene_clk_pll {
 	struct clk_hw	hw;
-	const char	*name;
 	void __iomem	*reg;
 	spinlock_t	*lock;
 	u32		pll_offset;
@@ -75,7 +74,7 @@ static int xgene_clk_pll_is_enabled(struct clk_hw *hw)
 	u32 data;
 
 	data = xgene_clk_read(pllclk->reg + pllclk->pll_offset);
-	pr_debug("%s pll %s\n", pllclk->name,
+	pr_debug("%s pll %s\n", clk_hw_get_name(hw),
 		data & REGSPEC_RESET_F1_MASK ? "disabled" : "enabled");
 
 	return data & REGSPEC_RESET_F1_MASK ? 0 : 1;
@@ -113,7 +112,7 @@ static unsigned long xgene_clk_pll_recalc_rate(struct clk_hw *hw,
 		fref = parent_rate / nref;
 		fvco = fref * nfb;
 	}
-	pr_debug("%s pll recalc rate %ld parent %ld\n", pllclk->name,
+	pr_debug("%s pll recalc rate %ld parent %ld\n", clk_hw_get_name(hw),
 		fvco / nout, parent_rate);
 
 	return fvco / nout;
@@ -146,7 +145,6 @@ static struct clk *xgene_register_clk_pll(struct device *dev,
 	init.parent_names = parent_name ? &parent_name : NULL;
 	init.num_parents = parent_name ? 1 : 0;
 
-	apmclk->name = name;
 	apmclk->reg = reg;
 	apmclk->lock = lock;
 	apmclk->pll_offset = pll_offset;
@@ -210,7 +208,6 @@ struct xgene_dev_parameters {
 
 struct xgene_clk {
 	struct clk_hw	hw;
-	const char	*name;
 	spinlock_t	*lock;
 	struct xgene_dev_parameters	param;
 };
@@ -228,7 +225,7 @@ static int xgene_clk_enable(struct clk_hw *hw)
 		spin_lock_irqsave(pclk->lock, flags);
 
 	if (pclk->param.csr_reg != NULL) {
-		pr_debug("%s clock enabled\n", pclk->name);
+		pr_debug("%s clock enabled\n", clk_hw_get_name(hw));
 		reg = __pa(pclk->param.csr_reg);
 		/* First enable the clock */
 		data = xgene_clk_read(pclk->param.csr_reg +
@@ -237,7 +234,7 @@ static int xgene_clk_enable(struct clk_hw *hw)
 		xgene_clk_write(data, pclk->param.csr_reg +
 					pclk->param.reg_clk_offset);
 		pr_debug("%s clock PADDR base %pa clk offset 0x%08X mask 0x%08X value 0x%08X\n",
-			pclk->name, &reg,
+			clk_hw_get_name(hw), &reg,
 			pclk->param.reg_clk_offset, pclk->param.reg_clk_mask,
 			data);
 
@@ -248,7 +245,7 @@ static int xgene_clk_enable(struct clk_hw *hw)
 		xgene_clk_write(data, pclk->param.csr_reg +
 					pclk->param.reg_csr_offset);
 		pr_debug("%s CSR RESET PADDR base %pa csr offset 0x%08X mask 0x%08X value 0x%08X\n",
-			pclk->name, &reg,
+			clk_hw_get_name(hw), &reg,
 			pclk->param.reg_csr_offset, pclk->param.reg_csr_mask,
 			data);
 	}
@@ -269,7 +266,7 @@ static void xgene_clk_disable(struct clk_hw *hw)
 		spin_lock_irqsave(pclk->lock, flags);
 
 	if (pclk->param.csr_reg != NULL) {
-		pr_debug("%s clock disabled\n", pclk->name);
+		pr_debug("%s clock disabled\n", clk_hw_get_name(hw));
 		/* First put the CSR in reset */
 		data = xgene_clk_read(pclk->param.csr_reg +
 					pclk->param.reg_csr_offset);
@@ -295,10 +292,10 @@ static int xgene_clk_is_enabled(struct clk_hw *hw)
 	u32 data = 0;
 
 	if (pclk->param.csr_reg != NULL) {
-		pr_debug("%s clock checking\n", pclk->name);
+		pr_debug("%s clock checking\n", clk_hw_get_name(hw));
 		data = xgene_clk_read(pclk->param.csr_reg +
 					pclk->param.reg_clk_offset);
-		pr_debug("%s clock is %s\n", pclk->name,
+		pr_debug("%s clock is %s\n", clk_hw_get_name(hw),
 			data & pclk->param.reg_clk_mask ? "enabled" :
 							"disabled");
 	}
@@ -321,11 +318,13 @@ static unsigned long xgene_clk_recalc_rate(struct clk_hw *hw,
 		data &= (1 << pclk->param.reg_divider_width) - 1;
 
 		pr_debug("%s clock recalc rate %ld parent %ld\n",
-			pclk->name, parent_rate / data, parent_rate);
+			clk_hw_get_name(hw),
+			parent_rate / data, parent_rate);
+
 		return parent_rate / data;
 	} else {
 		pr_debug("%s clock recalc rate %ld parent %ld\n",
-			pclk->name, parent_rate, parent_rate);
+			clk_hw_get_name(hw), parent_rate, parent_rate);
 		return parent_rate;
 	}
 }
@@ -357,7 +356,7 @@ static int xgene_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		data |= divider;
 		xgene_clk_write(data, pclk->param.divider_reg +
 					pclk->param.reg_divider_offset);
-		pr_debug("%s clock set rate %ld\n", pclk->name,
+		pr_debug("%s clock set rate %ld\n", clk_hw_get_name(hw),
 			parent_rate / divider_save);
 	} else {
 		divider_save = 1;
@@ -419,7 +418,6 @@ static struct clk *xgene_register_clk(struct device *dev,
 	init.parent_names = parent_name ? &parent_name : NULL;
 	init.num_parents = parent_name ? 1 : 0;
 
-	apmclk->name = name;
 	apmclk->lock = lock;
 	apmclk->hw.init = &init;
 	apmclk->param = *parameters;
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index ddb4b541016f..43e2c3ad6c31 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -9,6 +9,7 @@
  * Standard functionality for the common clock API.  See Documentation/clk.txt
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/clk-conf.h>
 #include <linux/module.h>
@@ -56,8 +57,11 @@ struct clk_core {
 	struct clk_core		*new_parent;
 	struct clk_core		*new_child;
 	unsigned long		flags;
+	bool			orphan;
 	unsigned int		enable_count;
 	unsigned int		prepare_count;
+	unsigned long		min_rate;
+	unsigned long		max_rate;
 	unsigned long		accuracy;
 	int			phase;
 	struct hlist_head	children;
@@ -111,12 +115,14 @@ static void clk_prepare_unlock(void)
 }
 
 static unsigned long clk_enable_lock(void)
+	__acquires(enable_lock)
 {
 	unsigned long flags;
 
 	if (!spin_trylock_irqsave(&enable_lock, flags)) {
 		if (enable_owner == current) {
 			enable_refcnt++;
+			__acquire(enable_lock);
 			return flags;
 		}
 		spin_lock_irqsave(&enable_lock, flags);
@@ -129,12 +135,15 @@ static unsigned long clk_enable_lock(void)
 }
 
 static void clk_enable_unlock(unsigned long flags)
+	__releases(enable_lock)
 {
 	WARN_ON_ONCE(enable_owner != current);
 	WARN_ON_ONCE(enable_refcnt == 0);
 
-	if (--enable_refcnt)
+	if (--enable_refcnt) {
+		__release(enable_lock);
 		return;
+	}
 	enable_owner = NULL;
 	spin_unlock_irqrestore(&enable_lock, flags);
 }
@@ -269,27 +278,29 @@ const char *__clk_get_name(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(__clk_get_name);
 
+const char *clk_hw_get_name(const struct clk_hw *hw)
+{
+	return hw->core->name;
+}
+EXPORT_SYMBOL_GPL(clk_hw_get_name);
+
 struct clk_hw *__clk_get_hw(struct clk *clk)
 {
 	return !clk ? NULL : clk->core->hw;
 }
 EXPORT_SYMBOL_GPL(__clk_get_hw);
 
-u8 __clk_get_num_parents(struct clk *clk)
+unsigned int clk_hw_get_num_parents(const struct clk_hw *hw)
 {
-	return !clk ? 0 : clk->core->num_parents;
+	return hw->core->num_parents;
 }
-EXPORT_SYMBOL_GPL(__clk_get_num_parents);
+EXPORT_SYMBOL_GPL(clk_hw_get_num_parents);
 
-struct clk *__clk_get_parent(struct clk *clk)
+struct clk_hw *clk_hw_get_parent(const struct clk_hw *hw)
 {
-	if (!clk)
-		return NULL;
-
-	/* TODO: Create a per-user clk and change callers to call clk_put */
-	return !clk->core->parent ? NULL : clk->core->parent->hw->clk;
+	return hw->core->parent ? hw->core->parent->hw : NULL;
 }
-EXPORT_SYMBOL_GPL(__clk_get_parent);
+EXPORT_SYMBOL_GPL(clk_hw_get_parent);
 
 static struct clk_core *__clk_lookup_subtree(const char *name,
 					     struct clk_core *core)
@@ -348,18 +359,16 @@ static struct clk_core *clk_core_get_parent_by_index(struct clk_core *core,
 		return core->parents[index];
 }
 
-struct clk *clk_get_parent_by_index(struct clk *clk, u8 index)
+struct clk_hw *
+clk_hw_get_parent_by_index(const struct clk_hw *hw, unsigned int index)
 {
 	struct clk_core *parent;
 
-	if (!clk)
-		return NULL;
-
-	parent = clk_core_get_parent_by_index(clk->core, index);
+	parent = clk_core_get_parent_by_index(hw->core, index);
 
-	return !parent ? NULL : parent->hw->clk;
+	return !parent ? NULL : parent->hw;
 }
-EXPORT_SYMBOL_GPL(clk_get_parent_by_index);
+EXPORT_SYMBOL_GPL(clk_hw_get_parent_by_index);
 
 unsigned int __clk_get_enable_count(struct clk *clk)
 {
@@ -387,14 +396,11 @@ out:
 	return ret;
 }
 
-unsigned long __clk_get_rate(struct clk *clk)
+unsigned long clk_hw_get_rate(const struct clk_hw *hw)
 {
-	if (!clk)
-		return 0;
-
-	return clk_core_get_rate_nolock(clk->core);
+	return clk_core_get_rate_nolock(hw->core);
 }
-EXPORT_SYMBOL_GPL(__clk_get_rate);
+EXPORT_SYMBOL_GPL(clk_hw_get_rate);
 
 static unsigned long __clk_get_accuracy(struct clk_core *core)
 {
@@ -410,12 +416,15 @@ unsigned long __clk_get_flags(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(__clk_get_flags);
 
-bool __clk_is_prepared(struct clk *clk)
+unsigned long clk_hw_get_flags(const struct clk_hw *hw)
 {
-	if (!clk)
-		return false;
+	return hw->core->flags;
+}
+EXPORT_SYMBOL_GPL(clk_hw_get_flags);
 
-	return clk_core_is_prepared(clk->core);
+bool clk_hw_is_prepared(const struct clk_hw *hw)
+{
+	return clk_core_is_prepared(hw->core);
 }
 
 bool __clk_is_enabled(struct clk *clk)
@@ -436,28 +445,31 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now,
 	return now <= rate && now > best;
 }
 
-static long
-clk_mux_determine_rate_flags(struct clk_hw *hw, unsigned long rate,
-			     unsigned long min_rate,
-			     unsigned long max_rate,
-			     unsigned long *best_parent_rate,
-			     struct clk_hw **best_parent_p,
+static int
+clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req,
 			     unsigned long flags)
 {
 	struct clk_core *core = hw->core, *parent, *best_parent = NULL;
-	int i, num_parents;
-	unsigned long parent_rate, best = 0;
+	int i, num_parents, ret;
+	unsigned long best = 0;
+	struct clk_rate_request parent_req = *req;
 
 	/* if NO_REPARENT flag set, pass through to current parent */
 	if (core->flags & CLK_SET_RATE_NO_REPARENT) {
 		parent = core->parent;
-		if (core->flags & CLK_SET_RATE_PARENT)
-			best = __clk_determine_rate(parent ? parent->hw : NULL,
-						    rate, min_rate, max_rate);
-		else if (parent)
+		if (core->flags & CLK_SET_RATE_PARENT) {
+			ret = __clk_determine_rate(parent ? parent->hw : NULL,
+						   &parent_req);
+			if (ret)
+				return ret;
+
+			best = parent_req.rate;
+		} else if (parent) {
 			best = clk_core_get_rate_nolock(parent);
-		else
+		} else {
 			best = clk_core_get_rate_nolock(core);
+		}
+
 		goto out;
 	}
 
@@ -467,24 +479,33 @@ clk_mux_determine_rate_flags(struct clk_hw *hw, unsigned long rate,
 		parent = clk_core_get_parent_by_index(core, i);
 		if (!parent)
 			continue;
-		if (core->flags & CLK_SET_RATE_PARENT)
-			parent_rate = __clk_determine_rate(parent->hw, rate,
-							   min_rate,
-							   max_rate);
-		else
-			parent_rate = clk_core_get_rate_nolock(parent);
-		if (mux_is_better_rate(rate, parent_rate, best, flags)) {
+
+		if (core->flags & CLK_SET_RATE_PARENT) {
+			parent_req = *req;
+			ret = __clk_determine_rate(parent->hw, &parent_req);
+			if (ret)
+				continue;
+		} else {
+			parent_req.rate = clk_core_get_rate_nolock(parent);
+		}
+
+		if (mux_is_better_rate(req->rate, parent_req.rate,
+				       best, flags)) {
 			best_parent = parent;
-			best = parent_rate;
+			best = parent_req.rate;
 		}
 	}
 
+	if (!best_parent)
+		return -EINVAL;
+
 out:
 	if (best_parent)
-		*best_parent_p = best_parent->hw;
-	*best_parent_rate = best;
+		req->best_parent_hw = best_parent->hw;
+	req->best_parent_rate = best;
+	req->rate = best;
 
-	return best;
+	return 0;
 }
 
 struct clk *__clk_lookup(const char *name)
@@ -500,8 +521,8 @@ static void clk_core_get_boundaries(struct clk_core *core,
 {
 	struct clk *clk_user;
 
-	*min_rate = 0;
-	*max_rate = ULONG_MAX;
+	*min_rate = core->min_rate;
+	*max_rate = core->max_rate;
 
 	hlist_for_each_entry(clk_user, &core->clks, clks_node)
 		*min_rate = max(*min_rate, clk_user->min_rate);
@@ -510,33 +531,30 @@ static void clk_core_get_boundaries(struct clk_core *core,
 		*max_rate = min(*max_rate, clk_user->max_rate);
 }
 
+void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate,
+			   unsigned long max_rate)
+{
+	hw->core->min_rate = min_rate;
+	hw->core->max_rate = max_rate;
+}
+EXPORT_SYMBOL_GPL(clk_hw_set_rate_range);
+
 /*
  * Helper for finding best parent to provide a given frequency. This can be used
  * directly as a determine_rate callback (e.g. for a mux), or from a more
  * complex clock that may combine a mux with other operations.
  */
-long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate,
-			      unsigned long min_rate,
-			      unsigned long max_rate,
-			      unsigned long *best_parent_rate,
-			      struct clk_hw **best_parent_p)
+int __clk_mux_determine_rate(struct clk_hw *hw,
+			     struct clk_rate_request *req)
 {
-	return clk_mux_determine_rate_flags(hw, rate, min_rate, max_rate,
-					    best_parent_rate,
-					    best_parent_p, 0);
+	return clk_mux_determine_rate_flags(hw, req, 0);
 }
 EXPORT_SYMBOL_GPL(__clk_mux_determine_rate);
 
-long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate,
-			      unsigned long min_rate,
-			      unsigned long max_rate,
-			      unsigned long *best_parent_rate,
-			      struct clk_hw **best_parent_p)
+int __clk_mux_determine_rate_closest(struct clk_hw *hw,
+				     struct clk_rate_request *req)
 {
-	return clk_mux_determine_rate_flags(hw, rate, min_rate, max_rate,
-					    best_parent_rate,
-					    best_parent_p,
-					    CLK_MUX_ROUND_CLOSEST);
+	return clk_mux_determine_rate_flags(hw, req, CLK_MUX_ROUND_CLOSEST);
 }
 EXPORT_SYMBOL_GPL(__clk_mux_determine_rate_closest);
 
@@ -759,14 +777,11 @@ int clk_enable(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_enable);
 
-static unsigned long clk_core_round_rate_nolock(struct clk_core *core,
-						unsigned long rate,
-						unsigned long min_rate,
-						unsigned long max_rate)
+static int clk_core_round_rate_nolock(struct clk_core *core,
+				      struct clk_rate_request *req)
 {
-	unsigned long parent_rate = 0;
 	struct clk_core *parent;
-	struct clk_hw *parent_hw;
+	long rate;
 
 	lockdep_assert_held(&prepare_lock);
 
@@ -774,21 +789,30 @@ static unsigned long clk_core_round_rate_nolock(struct clk_core *core,
 		return 0;
 
 	parent = core->parent;
-	if (parent)
-		parent_rate = parent->rate;
+	if (parent) {
+		req->best_parent_hw = parent->hw;
+		req->best_parent_rate = parent->rate;
+	} else {
+		req->best_parent_hw = NULL;
+		req->best_parent_rate = 0;
+	}
 
 	if (core->ops->determine_rate) {
-		parent_hw = parent ? parent->hw : NULL;
-		return core->ops->determine_rate(core->hw, rate,
-						min_rate, max_rate,
-						&parent_rate, &parent_hw);
-	} else if (core->ops->round_rate)
-		return core->ops->round_rate(core->hw, rate, &parent_rate);
-	else if (core->flags & CLK_SET_RATE_PARENT)
-		return clk_core_round_rate_nolock(core->parent, rate, min_rate,
-						  max_rate);
-	else
-		return core->rate;
+		return core->ops->determine_rate(core->hw, req);
+	} else if (core->ops->round_rate) {
+		rate = core->ops->round_rate(core->hw, req->rate,
+					     &req->best_parent_rate);
+		if (rate < 0)
+			return rate;
+
+		req->rate = rate;
+	} else if (core->flags & CLK_SET_RATE_PARENT) {
+		return clk_core_round_rate_nolock(parent, req);
+	} else {
+		req->rate = core->rate;
+	}
+
+	return 0;
 }
 
 /**
@@ -800,38 +824,32 @@ static unsigned long clk_core_round_rate_nolock(struct clk_core *core,
  *
  * Useful for clk_ops such as .set_rate and .determine_rate.
  */
-unsigned long __clk_determine_rate(struct clk_hw *hw,
-				   unsigned long rate,
-				   unsigned long min_rate,
-				   unsigned long max_rate)
+int __clk_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
 {
-	if (!hw)
+	if (!hw) {
+		req->rate = 0;
 		return 0;
+	}
 
-	return clk_core_round_rate_nolock(hw->core, rate, min_rate, max_rate);
+	return clk_core_round_rate_nolock(hw->core, req);
 }
 EXPORT_SYMBOL_GPL(__clk_determine_rate);
 
-/**
- * __clk_round_rate - round the given rate for a clk
- * @clk: round the rate of this clock
- * @rate: the rate which is to be rounded
- *
- * Useful for clk_ops such as .set_rate
- */
-unsigned long __clk_round_rate(struct clk *clk, unsigned long rate)
+unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate)
 {
-	unsigned long min_rate;
-	unsigned long max_rate;
+	int ret;
+	struct clk_rate_request req;
 
-	if (!clk)
-		return 0;
+	clk_core_get_boundaries(hw->core, &req.min_rate, &req.max_rate);
+	req.rate = rate;
 
-	clk_core_get_boundaries(clk->core, &min_rate, &max_rate);
+	ret = clk_core_round_rate_nolock(hw->core, &req);
+	if (ret)
+		return 0;
 
-	return clk_core_round_rate_nolock(clk->core, rate, min_rate, max_rate);
+	return req.rate;
 }
-EXPORT_SYMBOL_GPL(__clk_round_rate);
+EXPORT_SYMBOL_GPL(clk_hw_round_rate);
 
 /**
  * clk_round_rate - round the given rate for a clk
@@ -844,16 +862,24 @@ EXPORT_SYMBOL_GPL(__clk_round_rate);
  */
 long clk_round_rate(struct clk *clk, unsigned long rate)
 {
-	unsigned long ret;
+	struct clk_rate_request req;
+	int ret;
 
 	if (!clk)
 		return 0;
 
 	clk_prepare_lock();
-	ret = __clk_round_rate(clk, rate);
+
+	clk_core_get_boundaries(clk->core, &req.min_rate, &req.max_rate);
+	req.rate = rate;
+
+	ret = clk_core_round_rate_nolock(clk->core, &req);
 	clk_prepare_unlock();
 
-	return ret;
+	if (ret)
+		return ret;
+
+	return req.rate;
 }
 EXPORT_SYMBOL_GPL(clk_round_rate);
 
@@ -1064,18 +1090,40 @@ static int clk_fetch_parent_index(struct clk_core *core,
 	return -EINVAL;
 }
 
+/*
+ * Update the orphan status of @core and all its children.
+ */
+static void clk_core_update_orphan_status(struct clk_core *core, bool is_orphan)
+{
+	struct clk_core *child;
+
+	core->orphan = is_orphan;
+
+	hlist_for_each_entry(child, &core->children, child_node)
+		clk_core_update_orphan_status(child, is_orphan);
+}
+
 static void clk_reparent(struct clk_core *core, struct clk_core *new_parent)
 {
+	bool was_orphan = core->orphan;
+
 	hlist_del(&core->child_node);
 
 	if (new_parent) {
+		bool becomes_orphan = new_parent->orphan;
+
 		/* avoid duplicate POST_RATE_CHANGE notifications */
 		if (new_parent->new_child == core)
 			new_parent->new_child = NULL;
 
 		hlist_add_head(&core->child_node, &new_parent->children);
+
+		if (was_orphan != becomes_orphan)
+			clk_core_update_orphan_status(core, becomes_orphan);
 	} else {
 		hlist_add_head(&core->child_node, &clk_orphan_list);
+		if (!was_orphan)
+			clk_core_update_orphan_status(core, true);
 	}
 
 	core->parent = new_parent;
@@ -1160,14 +1208,8 @@ static int __clk_set_parent(struct clk_core *core, struct clk_core *parent,
 		flags = clk_enable_lock();
 		clk_reparent(core, old_parent);
 		clk_enable_unlock(flags);
+		__clk_set_parent_after(core, old_parent, parent);
 
-		if (core->prepare_count) {
-			flags = clk_enable_lock();
-			clk_core_disable(core);
-			clk_core_disable(parent);
-			clk_enable_unlock(flags);
-			clk_core_unprepare(parent);
-		}
 		return ret;
 	}
 
@@ -1249,7 +1291,6 @@ static struct clk_core *clk_calc_new_rates(struct clk_core *core,
 {
 	struct clk_core *top = core;
 	struct clk_core *old_parent, *parent;
-	struct clk_hw *parent_hw;
 	unsigned long best_parent_rate = 0;
 	unsigned long new_rate;
 	unsigned long min_rate;
@@ -1270,20 +1311,29 @@ static struct clk_core *clk_calc_new_rates(struct clk_core *core,
 
 	/* find the closest rate and parent clk/rate */
 	if (core->ops->determine_rate) {
-		parent_hw = parent ? parent->hw : NULL;
-		ret = core->ops->determine_rate(core->hw, rate,
-					       min_rate,
-					       max_rate,
-					       &best_parent_rate,
-					       &parent_hw);
+		struct clk_rate_request req;
+
+		req.rate = rate;
+		req.min_rate = min_rate;
+		req.max_rate = max_rate;
+		if (parent) {
+			req.best_parent_hw = parent->hw;
+			req.best_parent_rate = parent->rate;
+		} else {
+			req.best_parent_hw = NULL;
+			req.best_parent_rate = 0;
+		}
+
+		ret = core->ops->determine_rate(core->hw, &req);
 		if (ret < 0)
 			return NULL;
 
-		new_rate = ret;
-		parent = parent_hw ? parent_hw->core : NULL;
+		best_parent_rate = req.best_parent_rate;
+		new_rate = req.rate;
+		parent = req.best_parent_hw ? req.best_parent_hw->core : NULL;
 	} else if (core->ops->round_rate) {
 		ret = core->ops->round_rate(core->hw, rate,
-					   &best_parent_rate);
+					    &best_parent_rate);
 		if (ret < 0)
 			return NULL;
 
@@ -1592,8 +1642,12 @@ struct clk *clk_get_parent(struct clk *clk)
 {
 	struct clk *parent;
 
+	if (!clk)
+		return NULL;
+
 	clk_prepare_lock();
-	parent = __clk_get_parent(clk);
+	/* TODO: Create a per-user clk and change callers to call clk_put */
+	parent = !clk->core->parent ? NULL : clk->core->parent->hw->clk;
 	clk_prepare_unlock();
 
 	return parent;
@@ -2324,13 +2378,17 @@ static int __clk_init(struct device *dev, struct clk *clk_user)
 	 * clocks and re-parent any that are children of the clock currently
 	 * being clk_init'd.
 	 */
-	if (core->parent)
+	if (core->parent) {
 		hlist_add_head(&core->child_node,
 				&core->parent->children);
-	else if (core->flags & CLK_IS_ROOT)
+		core->orphan = core->parent->orphan;
+	} else if (core->flags & CLK_IS_ROOT) {
 		hlist_add_head(&core->child_node, &clk_root_list);
-	else
+		core->orphan = false;
+	} else {
 		hlist_add_head(&core->child_node, &clk_orphan_list);
+		core->orphan = true;
+	}
 
 	/*
 	 * Set clk's accuracy.  The preferred method is to use
@@ -2479,6 +2537,8 @@ struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 	core->hw = hw;
 	core->flags = hw->init->flags;
 	core->num_parents = hw->init->num_parents;
+	core->min_rate = 0;
+	core->max_rate = ULONG_MAX;
 	hw->core = core;
 
 	/* allocate local copy in case parent_names is __initdata */
@@ -3054,8 +3114,6 @@ struct clock_provider {
 	struct list_head node;
 };
 
-static LIST_HEAD(clk_provider_list);
-
 /*
  * This function looks for a parent clock. If there is one, then it
  * checks that the provider for this parent clock was initialized, in
@@ -3106,14 +3164,24 @@ void __init of_clk_init(const struct of_device_id *matches)
 	struct clock_provider *clk_provider, *next;
 	bool is_init_done;
 	bool force = false;
+	LIST_HEAD(clk_provider_list);
 
 	if (!matches)
 		matches = &__clk_of_table;
 
 	/* First prepare the list of the clocks providers */
 	for_each_matching_node_and_match(np, matches, &match) {
-		struct clock_provider *parent =
-			kzalloc(sizeof(struct clock_provider),	GFP_KERNEL);
+		struct clock_provider *parent;
+
+		parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+		if (!parent) {
+			list_for_each_entry_safe(clk_provider, next,
+						 &clk_provider_list, node) {
+				list_del(&clk_provider->node);
+				kfree(clk_provider);
+			}
+			return;
+		}
 
 		parent->clk_init_cb = match->data;
 		parent->np = np;
diff --git a/drivers/clk/h8300/clk-div.c b/drivers/clk/h8300/clk-div.c
index 56f9eba91b83..1dd5d14d5dbe 100644
--- a/drivers/clk/h8300/clk-div.c
+++ b/drivers/clk/h8300/clk-div.c
@@ -4,8 +4,6 @@
  * Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/of.h>
@@ -15,7 +13,7 @@ static DEFINE_SPINLOCK(clklock);
 
 static void __init h8300_div_clk_setup(struct device_node *node)
 {
-	unsigned int num_parents;
+	int num_parents;
 	struct clk *clk;
 	const char *clk_name = node->name;
 	const char *parent_name;
diff --git a/drivers/clk/h8300/clk-h8s2678.c b/drivers/clk/h8300/clk-h8s2678.c
index 4701b093e497..2a38eb4a2552 100644
--- a/drivers/clk/h8300/clk-h8s2678.c
+++ b/drivers/clk/h8300/clk-h8s2678.c
@@ -4,8 +4,6 @@
  * Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/device.h>
@@ -28,7 +26,7 @@ static unsigned long pll_recalc_rate(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct pll_clock *pll_clock = to_pll_clock(hw);
-	int mul = 1 << (ctrl_inb((unsigned long)pll_clock->pllcr) & 3);
+	int mul = 1 << (readb(pll_clock->pllcr) & 3);
 
 	return parent_rate * mul;
 }
@@ -65,13 +63,13 @@ static int pll_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	pll = ((rate / parent_rate) / 2) & 0x03;
 	spin_lock_irqsave(&clklock, flags);
-	val = ctrl_inb((unsigned long)pll_clock->sckcr);
+	val = readb(pll_clock->sckcr);
 	val |= 0x08;
-	ctrl_outb(val, (unsigned long)pll_clock->sckcr);
-	val = ctrl_inb((unsigned long)pll_clock->pllcr);
+	writeb(val, pll_clock->sckcr);
+	val = readb(pll_clock->pllcr);
 	val &= ~0x03;
 	val |= pll;
-	ctrl_outb(val, (unsigned long)pll_clock->pllcr);
+	writeb(val, pll_clock->pllcr);
 	spin_unlock_irqrestore(&clklock, flags);
 	return 0;
 }
@@ -84,7 +82,7 @@ static const struct clk_ops pll_ops = {
 
 static void __init h8s2678_pll_clk_setup(struct device_node *node)
 {
-	unsigned int num_parents;
+	int num_parents;
 	struct clk *clk;
 	const char *clk_name = node->name;
 	const char *parent_name;
@@ -98,11 +96,9 @@ static void __init h8s2678_pll_clk_setup(struct device_node *node)
 	}
 
 
-	pll_clock = kzalloc(sizeof(struct pll_clock), GFP_KERNEL);
-	if (!pll_clock) {
-		pr_err("%s: failed to alloc memory", clk_name);
+	pll_clock = kzalloc(sizeof(*pll_clock), GFP_KERNEL);
+	if (!pll_clock)
 		return;
-	}
 
 	pll_clock->sckcr = of_iomap(node, 0);
 	if (pll_clock->sckcr == NULL) {
diff --git a/drivers/clk/hisilicon/Kconfig b/drivers/clk/hisilicon/Kconfig
index b4165ba75d9f..2c16807341dc 100644
--- a/drivers/clk/hisilicon/Kconfig
+++ b/drivers/clk/hisilicon/Kconfig
@@ -1,6 +1,6 @@
 config COMMON_CLK_HI6220
 	bool "Hi6220 Clock Driver"
-	depends on ARCH_HISI || COMPILE_TEST
+	depends on (ARCH_HISI || COMPILE_TEST) && MAILBOX
 	default ARCH_HISI
 	help
 	  Build the Hisilicon Hi6220 clock driver based on the common clock framework.
diff --git a/drivers/clk/hisilicon/Makefile b/drivers/clk/hisilicon/Makefile
index 48f0116a032a..4a1001a11f04 100644
--- a/drivers/clk/hisilicon/Makefile
+++ b/drivers/clk/hisilicon/Makefile
@@ -7,4 +7,4 @@ obj-y	+= clk.o clkgate-separated.o clkdivider-hi6220.o
 obj-$(CONFIG_ARCH_HI3xxx)	+= clk-hi3620.o
 obj-$(CONFIG_ARCH_HIP04)	+= clk-hip04.o
 obj-$(CONFIG_ARCH_HIX5HD2)	+= clk-hix5hd2.o
-obj-$(CONFIG_COMMON_CLK_HI6220)	+= clk-hi6220.o
+obj-$(CONFIG_COMMON_CLK_HI6220)	+= clk-hi6220.o clk-hi6220-stub.o
diff --git a/drivers/clk/hisilicon/clk-hi3620.c b/drivers/clk/hisilicon/clk-hi3620.c
index 715d34a5ef9b..7d03fe17d66f 100644
--- a/drivers/clk/hisilicon/clk-hi3620.c
+++ b/drivers/clk/hisilicon/clk-hi3620.c
@@ -25,13 +25,11 @@
 
 #include <linux/kernel.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/slab.h>
-#include <linux/clk.h>
 
 #include <dt-bindings/clock/hi3620-clock.h>
 
@@ -294,34 +292,29 @@ static unsigned long mmc_clk_recalc_rate(struct clk_hw *hw,
 	}
 }
 
-static long mmc_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
-			      unsigned long min_rate,
-			      unsigned long max_rate,
-			      unsigned long *best_parent_rate,
-			      struct clk_hw **best_parent_p)
+static int mmc_clk_determine_rate(struct clk_hw *hw,
+				  struct clk_rate_request *req)
 {
 	struct clk_mmc *mclk = to_mmc(hw);
-	unsigned long best = 0;
 
-	if ((rate <= 13000000) && (mclk->id == HI3620_MMC_CIUCLK1)) {
-		rate = 13000000;
-		best = 26000000;
-	} else if (rate <= 26000000) {
-		rate = 25000000;
-		best = 180000000;
-	} else if (rate <= 52000000) {
-		rate = 50000000;
-		best = 360000000;
-	} else if (rate <= 100000000) {
-		rate = 100000000;
-		best = 720000000;
+	if ((req->rate <= 13000000) && (mclk->id == HI3620_MMC_CIUCLK1)) {
+		req->rate = 13000000;
+		req->best_parent_rate = 26000000;
+	} else if (req->rate <= 26000000) {
+		req->rate = 25000000;
+		req->best_parent_rate = 180000000;
+	} else if (req->rate <= 52000000) {
+		req->rate = 50000000;
+		req->best_parent_rate = 360000000;
+	} else if (req->rate <= 100000000) {
+		req->rate = 100000000;
+		req->best_parent_rate = 720000000;
 	} else {
 		/* max is 180M */
-		rate = 180000000;
-		best = 1440000000;
+		req->rate = 180000000;
+		req->best_parent_rate = 1440000000;
 	}
-	*best_parent_rate = best;
-	return rate;
+	return -EINVAL;
 }
 
 static u32 mmc_clk_delay(u32 val, u32 para, u32 off, u32 len)
diff --git a/drivers/clk/hisilicon/clk-hi6220-stub.c b/drivers/clk/hisilicon/clk-hi6220-stub.c
new file mode 100644
index 000000000000..2c4add11c1ca
--- /dev/null
+++ b/drivers/clk/hisilicon/clk-hi6220-stub.c
@@ -0,0 +1,276 @@
+/*
+ * Hi6220 stub clock driver
+ *
+ * Copyright (c) 2015 Hisilicon Limited.
+ * Copyright (c) 2015 Linaro Limited.
+ *
+ * Author: Leo Yan <leo.yan@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mailbox_client.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+
+/* Stub clocks id */
+#define HI6220_STUB_ACPU0		0
+#define HI6220_STUB_ACPU1		1
+#define HI6220_STUB_GPU			2
+#define HI6220_STUB_DDR			5
+
+/* Mailbox message */
+#define HI6220_MBOX_MSG_LEN		8
+
+#define HI6220_MBOX_FREQ		0xA
+#define HI6220_MBOX_CMD_SET		0x3
+#define HI6220_MBOX_OBJ_AP		0x0
+
+/* CPU dynamic frequency scaling */
+#define ACPU_DFS_FREQ_MAX		0x1724
+#define ACPU_DFS_CUR_FREQ		0x17CC
+#define ACPU_DFS_FLAG			0x1B30
+#define ACPU_DFS_FREQ_REQ		0x1B34
+#define ACPU_DFS_FREQ_LMT		0x1B38
+#define ACPU_DFS_LOCK_FLAG		0xAEAEAEAE
+
+#define to_stub_clk(hw) container_of(hw, struct hi6220_stub_clk, hw)
+
+struct hi6220_stub_clk {
+	u32 id;
+
+	struct device *dev;
+	struct clk_hw hw;
+
+	struct regmap *dfs_map;
+	struct mbox_client cl;
+	struct mbox_chan *mbox;
+};
+
+struct hi6220_mbox_msg {
+	unsigned char type;
+	unsigned char cmd;
+	unsigned char obj;
+	unsigned char src;
+	unsigned char para[4];
+};
+
+union hi6220_mbox_data {
+	unsigned int data[HI6220_MBOX_MSG_LEN];
+	struct hi6220_mbox_msg msg;
+};
+
+static unsigned int hi6220_acpu_get_freq(struct hi6220_stub_clk *stub_clk)
+{
+	unsigned int freq;
+
+	regmap_read(stub_clk->dfs_map, ACPU_DFS_CUR_FREQ, &freq);
+	return freq;
+}
+
+static int hi6220_acpu_set_freq(struct hi6220_stub_clk *stub_clk,
+				unsigned int freq)
+{
+	union hi6220_mbox_data data;
+
+	/* set the frequency in sram */
+	regmap_write(stub_clk->dfs_map, ACPU_DFS_FREQ_REQ, freq);
+
+	/* compound mailbox message */
+	data.msg.type = HI6220_MBOX_FREQ;
+	data.msg.cmd  = HI6220_MBOX_CMD_SET;
+	data.msg.obj  = HI6220_MBOX_OBJ_AP;
+	data.msg.src  = HI6220_MBOX_OBJ_AP;
+
+	mbox_send_message(stub_clk->mbox, &data);
+	return 0;
+}
+
+static int hi6220_acpu_round_freq(struct hi6220_stub_clk *stub_clk,
+				  unsigned int freq)
+{
+	unsigned int limit_flag, limit_freq = UINT_MAX;
+	unsigned int max_freq;
+
+	/* check the constrained frequency */
+	regmap_read(stub_clk->dfs_map, ACPU_DFS_FLAG, &limit_flag);
+	if (limit_flag == ACPU_DFS_LOCK_FLAG)
+		regmap_read(stub_clk->dfs_map, ACPU_DFS_FREQ_LMT, &limit_freq);
+
+	/* check the supported maximum frequency */
+	regmap_read(stub_clk->dfs_map, ACPU_DFS_FREQ_MAX, &max_freq);
+
+	/* calculate the real maximum frequency */
+	max_freq = min(max_freq, limit_freq);
+
+	if (WARN_ON(freq > max_freq))
+		freq = max_freq;
+
+	return freq;
+}
+
+static unsigned long hi6220_stub_clk_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	u32 rate = 0;
+	struct hi6220_stub_clk *stub_clk = to_stub_clk(hw);
+
+	switch (stub_clk->id) {
+	case HI6220_STUB_ACPU0:
+		rate = hi6220_acpu_get_freq(stub_clk);
+
+		/* convert from kHz to Hz */
+		rate *= 1000;
+		break;
+
+	default:
+		dev_err(stub_clk->dev, "%s: un-supported clock id %d\n",
+			__func__, stub_clk->id);
+		break;
+	}
+
+	return rate;
+}
+
+static int hi6220_stub_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct hi6220_stub_clk *stub_clk = to_stub_clk(hw);
+	unsigned long new_rate = rate / 1000;  /* kHz */
+	int ret = 0;
+
+	switch (stub_clk->id) {
+	case HI6220_STUB_ACPU0:
+		ret = hi6220_acpu_set_freq(stub_clk, new_rate);
+		if (ret < 0)
+			return ret;
+
+		break;
+
+	default:
+		dev_err(stub_clk->dev, "%s: un-supported clock id %d\n",
+			__func__, stub_clk->id);
+		break;
+	}
+
+	pr_debug("%s: set rate=%ldkHz\n", __func__, new_rate);
+	return ret;
+}
+
+static long hi6220_stub_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *parent_rate)
+{
+	struct hi6220_stub_clk *stub_clk = to_stub_clk(hw);
+	unsigned long new_rate = rate / 1000;  /* kHz */
+
+	switch (stub_clk->id) {
+	case HI6220_STUB_ACPU0:
+		new_rate = hi6220_acpu_round_freq(stub_clk, new_rate);
+
+		/* convert from kHz to Hz */
+		new_rate *= 1000;
+		break;
+
+	default:
+		dev_err(stub_clk->dev, "%s: un-supported clock id %d\n",
+			__func__, stub_clk->id);
+		break;
+	}
+
+	return new_rate;
+}
+
+static const struct clk_ops hi6220_stub_clk_ops = {
+	.recalc_rate	= hi6220_stub_clk_recalc_rate,
+	.round_rate	= hi6220_stub_clk_round_rate,
+	.set_rate	= hi6220_stub_clk_set_rate,
+};
+
+static int hi6220_stub_clk_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct clk_init_data init;
+	struct hi6220_stub_clk *stub_clk;
+	struct clk *clk;
+	struct device_node *np = pdev->dev.of_node;
+	int ret;
+
+	stub_clk = devm_kzalloc(dev, sizeof(*stub_clk), GFP_KERNEL);
+	if (!stub_clk)
+		return -ENOMEM;
+
+	stub_clk->dfs_map = syscon_regmap_lookup_by_phandle(np,
+				"hisilicon,hi6220-clk-sram");
+	if (IS_ERR(stub_clk->dfs_map)) {
+		dev_err(dev, "failed to get sram regmap\n");
+		return PTR_ERR(stub_clk->dfs_map);
+	}
+
+	stub_clk->hw.init = &init;
+	stub_clk->dev = dev;
+	stub_clk->id = HI6220_STUB_ACPU0;
+
+	/* Use mailbox client with blocking mode */
+	stub_clk->cl.dev = dev;
+	stub_clk->cl.tx_done = NULL;
+	stub_clk->cl.tx_block = true;
+	stub_clk->cl.tx_tout = 500;
+	stub_clk->cl.knows_txdone = false;
+
+	/* Allocate mailbox channel */
+	stub_clk->mbox = mbox_request_channel(&stub_clk->cl, 0);
+	if (IS_ERR(stub_clk->mbox)) {
+		dev_err(dev, "failed get mailbox channel\n");
+		return PTR_ERR(stub_clk->mbox);
+	};
+
+	init.name = "acpu0";
+	init.ops = &hi6220_stub_clk_ops;
+	init.num_parents = 0;
+	init.flags = CLK_IS_ROOT;
+
+	clk = devm_clk_register(dev, &stub_clk->hw);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	if (ret) {
+		dev_err(dev, "failed to register OF clock provider\n");
+		return ret;
+	}
+
+	/* initialize buffer to zero */
+	regmap_write(stub_clk->dfs_map, ACPU_DFS_FLAG, 0x0);
+	regmap_write(stub_clk->dfs_map, ACPU_DFS_FREQ_REQ, 0x0);
+	regmap_write(stub_clk->dfs_map, ACPU_DFS_FREQ_LMT, 0x0);
+
+	dev_dbg(dev, "Registered clock '%s'\n", init.name);
+	return 0;
+}
+
+static const struct of_device_id hi6220_stub_clk_of_match[] = {
+	{ .compatible = "hisilicon,hi6220-stub-clk", },
+	{}
+};
+
+static struct platform_driver hi6220_stub_clk_driver = {
+	.driver	= {
+		.name = "hi6220-stub-clk",
+		.of_match_table = hi6220_stub_clk_of_match,
+	},
+	.probe = hi6220_stub_clk_probe,
+};
+
+static int __init hi6220_stub_clk_init(void)
+{
+	return platform_driver_register(&hi6220_stub_clk_driver);
+}
+subsys_initcall(hi6220_stub_clk_init);
diff --git a/drivers/clk/hisilicon/clk-hip04.c b/drivers/clk/hisilicon/clk-hip04.c
index 132b57a0ce09..8ca967308343 100644
--- a/drivers/clk/hisilicon/clk-hip04.c
+++ b/drivers/clk/hisilicon/clk-hip04.c
@@ -24,13 +24,11 @@
 
 #include <linux/kernel.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/slab.h>
-#include <linux/clk.h>
 
 #include <dt-bindings/clock/hip04-clock.h>
 
diff --git a/drivers/clk/hisilicon/clk.c b/drivers/clk/hisilicon/clk.c
index c90a89739b03..9f8e76676553 100644
--- a/drivers/clk/hisilicon/clk.c
+++ b/drivers/clk/hisilicon/clk.c
@@ -24,15 +24,14 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/clk-provider.h>
 #include <linux/clkdev.h>
+#include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/slab.h>
-#include <linux/clk.h>
 
 #include "clk.h"
 
@@ -45,14 +44,9 @@ struct hisi_clock_data __init *hisi_clk_init(struct device_node *np,
 	struct clk **clk_table;
 	void __iomem *base;
 
-	if (np) {
-		base = of_iomap(np, 0);
-		if (!base) {
-			pr_err("failed to map Hisilicon clock registers\n");
-			goto err;
-		}
-	} else {
-		pr_err("failed to find Hisilicon clock node in DTS\n");
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("%s: failed to map clock registers\n", __func__);
 		goto err;
 	}
 
diff --git a/drivers/clk/hisilicon/clkgate-separated.c b/drivers/clk/hisilicon/clkgate-separated.c
index b03d5a7246f9..a47812f56a17 100644
--- a/drivers/clk/hisilicon/clkgate-separated.c
+++ b/drivers/clk/hisilicon/clkgate-separated.c
@@ -25,10 +25,8 @@
 
 #include <linux/kernel.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/slab.h>
-#include <linux/clk.h>
 
 #include "clk.h"
 
diff --git a/drivers/clk/imx/Makefile b/drivers/clk/imx/Makefile
index 75fae169ce8f..1ada68abb158 100644
--- a/drivers/clk/imx/Makefile
+++ b/drivers/clk/imx/Makefile
@@ -22,5 +22,6 @@ obj-$(CONFIG_SOC_IMX5)   += clk-imx51-imx53.o
 obj-$(CONFIG_SOC_IMX6Q)  += clk-imx6q.o
 obj-$(CONFIG_SOC_IMX6SL) += clk-imx6sl.o
 obj-$(CONFIG_SOC_IMX6SX) += clk-imx6sx.o
+obj-$(CONFIG_SOC_IMX6UL) += clk-imx6ul.o
 obj-$(CONFIG_SOC_IMX7D)  += clk-imx7d.o
 obj-$(CONFIG_SOC_VF610)  += clk-vf610.o
diff --git a/drivers/clk/imx/clk-imx1.c b/drivers/clk/imx/clk-imx1.c
index c2647fa19f28..99cf802fa51f 100644
--- a/drivers/clk/imx/clk-imx1.c
+++ b/drivers/clk/imx/clk-imx1.c
@@ -15,7 +15,6 @@
  * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
  */
 
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
diff --git a/drivers/clk/imx/clk-imx21.c b/drivers/clk/imx/clk-imx21.c
index dba987e3b89f..e63188eb08ac 100644
--- a/drivers/clk/imx/clk-imx21.c
+++ b/drivers/clk/imx/clk-imx21.c
@@ -9,7 +9,6 @@
  * of the License, or (at your option) any later version.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
diff --git a/drivers/clk/imx/clk-imx31.c b/drivers/clk/imx/clk-imx31.c
index fe66c40b7be2..1f8383475bb3 100644
--- a/drivers/clk/imx/clk-imx31.c
+++ b/drivers/clk/imx/clk-imx31.c
@@ -147,7 +147,8 @@ int __init mx31_clocks_init(unsigned long fref)
 	clk_register_clkdev(clk[cspi3_gate], NULL, "imx31-cspi.2");
 	clk_register_clkdev(clk[pwm_gate], "pwm", NULL);
 	clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0");
-	clk_register_clkdev(clk[rtc_gate], NULL, "imx21-rtc");
+	clk_register_clkdev(clk[ckil], "ref", "imx21-rtc");
+	clk_register_clkdev(clk[rtc_gate], "ipg", "imx21-rtc");
 	clk_register_clkdev(clk[epit1_gate], "epit", NULL);
 	clk_register_clkdev(clk[epit2_gate], "epit", NULL);
 	clk_register_clkdev(clk[nfc], NULL, "imx27-nand.0");
diff --git a/drivers/clk/imx/clk-imx35.c b/drivers/clk/imx/clk-imx35.c
index 69138ba3dec7..8623cd4e49fd 100644
--- a/drivers/clk/imx/clk-imx35.c
+++ b/drivers/clk/imx/clk-imx35.c
@@ -66,7 +66,7 @@ static const char *std_sel[] = {"ppll", "arm"};
 static const char *ipg_per_sel[] = {"ahb_per_div", "arm_per_div"};
 
 enum mx35_clks {
-	ckih, mpll, ppll, mpll_075, arm, hsp, hsp_div, hsp_sel, ahb, ipg,
+	ckih, ckil, mpll, ppll, mpll_075, arm, hsp, hsp_div, hsp_sel, ahb, ipg,
 	arm_per_div, ahb_per_div, ipg_per, uart_sel, uart_div, esdhc_sel,
 	esdhc1_div, esdhc2_div, esdhc3_div, spdif_sel, spdif_div_pre,
 	spdif_div_post, ssi_sel, ssi1_div_pre, ssi1_div_post, ssi2_div_pre,
@@ -107,6 +107,7 @@ int __init mx35_clocks_init(void)
 	}
 
 	clk[ckih] = imx_clk_fixed("ckih", 24000000);
+	clk[ckil] = imx_clk_fixed("ckih", 32768);
 	clk[mpll] = imx_clk_pllv1(IMX_PLLV1_IMX35, "mpll", "ckih", base + MX35_CCM_MPCTL);
 	clk[ppll] = imx_clk_pllv1(IMX_PLLV1_IMX35, "ppll", "ckih", base + MX35_CCM_PPCTL);
 
@@ -258,6 +259,9 @@ int __init mx35_clocks_init(void)
 	clk_register_clkdev(clk[ipg], "ipg", "imx21-uart.1");
 	clk_register_clkdev(clk[uart3_gate], "per", "imx21-uart.2");
 	clk_register_clkdev(clk[ipg], "ipg", "imx21-uart.2");
+	/* i.mx35 has the i.mx21 type rtc */
+	clk_register_clkdev(clk[ckil], "ref", "imx21-rtc");
+	clk_register_clkdev(clk[rtc_gate], "ipg", "imx21-rtc");
 	clk_register_clkdev(clk[usb_div], "per", "mxc-ehci.0");
 	clk_register_clkdev(clk[ipg], "ipg", "mxc-ehci.0");
 	clk_register_clkdev(clk[usbotg_gate], "ahb", "mxc-ehci.0");
diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index d046f8e43de8..b2c1c047dc94 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -381,6 +381,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_ASRC]         = imx_clk_gate2_shared("asrc",         "asrc_podf",   base + 0x68, 6, &share_count_asrc);
 	clk[IMX6QDL_CLK_ASRC_IPG]     = imx_clk_gate2_shared("asrc_ipg",     "ahb",         base + 0x68, 6, &share_count_asrc);
 	clk[IMX6QDL_CLK_ASRC_MEM]     = imx_clk_gate2_shared("asrc_mem",     "ahb",         base + 0x68, 6, &share_count_asrc);
+	clk[IMX6QDL_CLK_CAAM_MEM]     = imx_clk_gate2("caam_mem",      "ahb",               base + 0x68, 8);
+	clk[IMX6QDL_CLK_CAAM_ACLK]    = imx_clk_gate2("caam_aclk",     "ahb",               base + 0x68, 10);
+	clk[IMX6QDL_CLK_CAAM_IPG]     = imx_clk_gate2("caam_ipg",      "ipg",               base + 0x68, 12);
 	clk[IMX6QDL_CLK_CAN1_IPG]     = imx_clk_gate2("can1_ipg",      "ipg",               base + 0x68, 14);
 	clk[IMX6QDL_CLK_CAN1_SERIAL]  = imx_clk_gate2("can1_serial",   "can_root",          base + 0x68, 16);
 	clk[IMX6QDL_CLK_CAN2_IPG]     = imx_clk_gate2("can2_ipg",      "ipg",               base + 0x68, 18);
@@ -494,6 +497,10 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		clk_set_parent(clk[IMX6QDL_CLK_LDB_DI1_SEL], clk[IMX6QDL_CLK_PLL5_VIDEO_DIV]);
 	}
 
+	clk_set_rate(clk[IMX6QDL_CLK_PLL3_PFD1_540M], 540000000);
+	if (clk_on_imx6dl())
+		clk_set_parent(clk[IMX6QDL_CLK_IPU1_SEL], clk[IMX6QDL_CLK_PLL3_PFD1_540M]);
+
 	clk_set_parent(clk[IMX6QDL_CLK_IPU1_DI0_PRE_SEL], clk[IMX6QDL_CLK_PLL5_VIDEO_DIV]);
 	clk_set_parent(clk[IMX6QDL_CLK_IPU1_DI1_PRE_SEL], clk[IMX6QDL_CLK_PLL5_VIDEO_DIV]);
 	clk_set_parent(clk[IMX6QDL_CLK_IPU2_DI0_PRE_SEL], clk[IMX6QDL_CLK_PLL5_VIDEO_DIV]);
diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
new file mode 100644
index 000000000000..aaa36650695f
--- /dev/null
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -0,0 +1,432 @@
+/*
+ * Copyright (C) 2015 Freescale Semiconductor, Inc.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <dt-bindings/clock/imx6ul-clock.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/types.h>
+
+#include "clk.h"
+
+#define BM_CCM_CCDR_MMDC_CH0_MASK	(0x2 << 16)
+#define CCDR	0x4
+
+static const char *pll_bypass_src_sels[] = { "osc", "dummy", };
+static const char *pll1_bypass_sels[] = { "pll1", "pll1_bypass_src", };
+static const char *pll2_bypass_sels[] = { "pll2", "pll2_bypass_src", };
+static const char *pll3_bypass_sels[] = { "pll3", "pll3_bypass_src", };
+static const char *pll4_bypass_sels[] = { "pll4", "pll4_bypass_src", };
+static const char *pll5_bypass_sels[] = { "pll5", "pll5_bypass_src", };
+static const char *pll6_bypass_sels[] = { "pll6", "pll6_bypass_src", };
+static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
+static const char *ca7_secondary_sels[] = { "pll2_pfd2_396m", "pll2_bus", };
+static const char *step_sels[] = { "osc", "ca7_secondary_sel", };
+static const char *pll1_sw_sels[] = { "pll1_sys", "step", };
+static const char *axi_alt_sels[] = { "pll2_pfd2_396m", "pll3_pfd1_540m", };
+static const char *axi_sels[] = {"periph", "axi_alt_sel", };
+static const char *periph_pre_sels[] = { "pll2_bus", "pll2_pfd2_396m", "pll2_pfd0_352m", "pll2_198m", };
+static const char *periph2_pre_sels[] = { "pll2_bus", "pll2_pfd2_396m", "pll2_pfd0_352m", "pll4_audio_div", };
+static const char *periph_clk2_sels[] = { "pll3_usb_otg", "osc", "osc", };
+static const char *periph2_clk2_sels[] = { "pll3_usb_otg", "osc", };
+static const char *periph_sels[] = { "periph_pre", "periph_clk2", };
+static const char *periph2_sels[] = { "periph2_pre", "periph2_clk2", };
+static const char *usdhc_sels[] = { "pll2_pfd2_396m", "pll2_pfd0_352m", };
+static const char *bch_sels[] = { "pll2_pfd2_396m", "pll2_pfd0_352m", };
+static const char *gpmi_sels[] = { "pll2_pfd2_396m", "pll2_pfd0_352m", };
+static const char *eim_slow_sels[] =  { "axi", "pll3_usb_otg", "pll2_pfd2_396m", "pll3_pfd0_720m", };
+static const char *spdif_sels[] = { "pll4_audio_div", "pll3_pfd2_508m", "pll5_video_div", "pll3_usb_otg", };
+static const char *sai_sels[] = { "pll3_pfd2_508m", "pll5_video_div", "pll4_audio_div", };
+static const char *lcdif_pre_sels[] = { "pll2_bus", "pll3_pfd3_454m", "pll5_video_div", "pll2_pfd0_352m", "pll2_pfd1_594m", "pll3_pfd1_540m", };
+static const char *sim_pre_sels[] = { "pll2_bus", "pll3_usb_otg", "pll5_video_div", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd2_508m", };
+static const char *ldb_di0_sels[] = { "pll5_video_div", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll2_pfd3_594m", "pll2_pfd1_594m", "pll3_pfd3_454m", };
+static const char *ldb_di0_div_sels[] = { "ldb_di0_div_3_5", "ldb_di0_div_7", };
+static const char *ldb_di1_div_sels[] = { "ldb_di1_div_3_5", "ldb_di1_div_7", };
+static const char *qspi1_sels[] = { "pll3_usb_otg", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll2_bus", "pll3_pfd3_454m", "pll3_pfd2_508m", };
+static const char *enfc_sels[] = { "pll2_pfd0_352m", "pll2_bus", "pll3_usb_otg", "pll2_pfd2_396m", "pll3_pfd3_454m", "dummy", "dummy", "dummy", };
+static const char *can_sels[] = { "pll3_60m", "osc", "pll3_80m", "dummy", };
+static const char *ecspi_sels[] = { "pll3_60m", "osc", };
+static const char *uart_sels[] = { "pll3_80m", "osc", };
+static const char *perclk_sels[] = { "ipg", "osc", };
+static const char *lcdif_sels[] = { "lcdif_podf", "ipp_di0", "ipp_di1", "ldb_di0", "ldb_di1", };
+static const char *csi_sels[] = { "osc", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", };
+static const char *sim_sels[] = { "sim_podf", "ipp_di0", "ipp_di1", "ldb_di0", "ldb_di1", };
+
+static struct clk *clks[IMX6UL_CLK_END];
+static struct clk_onecell_data clk_data;
+
+static int const clks_init_on[] __initconst = {
+	IMX6UL_CLK_AIPSTZ1, IMX6UL_CLK_AIPSTZ2, IMX6UL_CLK_AIPSTZ3,
+	IMX6UL_CLK_AXI, IMX6UL_CLK_ARM, IMX6UL_CLK_ROM,
+	IMX6UL_CLK_MMDC_P0_FAST, IMX6UL_CLK_MMDC_P0_IPG,
+};
+
+static struct clk_div_table clk_enet_ref_table[] = {
+	{ .val = 0, .div = 20, },
+	{ .val = 1, .div = 10, },
+	{ .val = 2, .div = 5, },
+	{ .val = 3, .div = 4, },
+	{ }
+};
+
+static struct clk_div_table post_div_table[] = {
+	{ .val = 2, .div = 1, },
+	{ .val = 1, .div = 2, },
+	{ .val = 0, .div = 4, },
+	{ }
+};
+
+static struct clk_div_table video_div_table[] = {
+	{ .val = 0, .div = 1, },
+	{ .val = 1, .div = 2, },
+	{ .val = 2, .div = 1, },
+	{ .val = 3, .div = 4, },
+	{ }
+};
+
+static u32 share_count_asrc;
+static u32 share_count_audio;
+static u32 share_count_sai1;
+static u32 share_count_sai2;
+static u32 share_count_sai3;
+
+static void __init imx6ul_clocks_init(struct device_node *ccm_node)
+{
+	struct device_node *np;
+	void __iomem *base;
+	int i;
+
+	clks[IMX6UL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
+
+	clks[IMX6UL_CLK_CKIL] = of_clk_get_by_name(ccm_node, "ckil");
+	clks[IMX6UL_CLK_OSC] = of_clk_get_by_name(ccm_node, "osc");
+
+	/* ipp_di clock is external input */
+	clks[IMX6UL_CLK_IPP_DI0] = of_clk_get_by_name(ccm_node, "ipp_di0");
+	clks[IMX6UL_CLK_IPP_DI1] = of_clk_get_by_name(ccm_node, "ipp_di1");
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-anatop");
+	base = of_iomap(np, 0);
+	WARN_ON(!base);
+
+	clks[IMX6UL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6UL_PLL2_BYPASS_SRC] = imx_clk_mux("pll2_bypass_src", base + 0x30, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6UL_PLL3_BYPASS_SRC] = imx_clk_mux("pll3_bypass_src", base + 0x10, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6UL_PLL4_BYPASS_SRC] = imx_clk_mux("pll4_bypass_src", base + 0x70, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6UL_PLL5_BYPASS_SRC] = imx_clk_mux("pll5_bypass_src", base + 0xa0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6UL_PLL6_BYPASS_SRC] = imx_clk_mux("pll6_bypass_src", base + 0xe0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6UL_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+
+	clks[IMX6UL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,	 "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
+	clks[IMX6UL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
+	clks[IMX6UL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,	 "pll3", "pll3_bypass_src", base + 0x10, 0x3);
+	clks[IMX6UL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,	 "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
+	clks[IMX6UL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,	 "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
+	clks[IMX6UL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,	 "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
+	clks[IMX6UL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,	 "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+
+	clks[IMX6UL_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_PLL3_BYPASS] = imx_clk_mux_flags("pll3_bypass", base + 0x10, 16, 1, pll3_bypass_sels, ARRAY_SIZE(pll3_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_PLL4_BYPASS] = imx_clk_mux_flags("pll4_bypass", base + 0x70, 16, 1, pll4_bypass_sels, ARRAY_SIZE(pll4_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_PLL5_BYPASS] = imx_clk_mux_flags("pll5_bypass", base + 0xa0, 16, 1, pll5_bypass_sels, ARRAY_SIZE(pll5_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_PLL6_BYPASS] = imx_clk_mux_flags("pll6_bypass", base + 0xe0, 16, 1, pll6_bypass_sels, ARRAY_SIZE(pll6_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_PLL7_BYPASS] = imx_clk_mux_flags("pll7_bypass", base + 0x20, 16, 1, pll7_bypass_sels, ARRAY_SIZE(pll7_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6UL_CLK_CSI_SEL] = imx_clk_mux_flags("csi_sel", base + 0x3c, 9, 2, csi_sels, ARRAY_SIZE(csi_sels), CLK_SET_RATE_PARENT);
+
+	/* Do not bypass PLLs initially */
+	clk_set_parent(clks[IMX6UL_PLL1_BYPASS], clks[IMX6UL_CLK_PLL1]);
+	clk_set_parent(clks[IMX6UL_PLL2_BYPASS], clks[IMX6UL_CLK_PLL2]);
+	clk_set_parent(clks[IMX6UL_PLL3_BYPASS], clks[IMX6UL_CLK_PLL3]);
+	clk_set_parent(clks[IMX6UL_PLL4_BYPASS], clks[IMX6UL_CLK_PLL4]);
+	clk_set_parent(clks[IMX6UL_PLL5_BYPASS], clks[IMX6UL_CLK_PLL5]);
+	clk_set_parent(clks[IMX6UL_PLL6_BYPASS], clks[IMX6UL_CLK_PLL6]);
+	clk_set_parent(clks[IMX6UL_PLL7_BYPASS], clks[IMX6UL_CLK_PLL7]);
+
+	clks[IMX6UL_CLK_PLL1_SYS]	= imx_clk_fixed_factor("pll1_sys",	"pll1_bypass", 1, 1);
+	clks[IMX6UL_CLK_PLL2_BUS]	= imx_clk_gate("pll2_bus", 	"pll2_bypass", base + 0x30, 13);
+	clks[IMX6UL_CLK_PLL3_USB_OTG]	= imx_clk_gate("pll3_usb_otg", 	"pll3_bypass", base + 0x10, 13);
+	clks[IMX6UL_CLK_PLL4_AUDIO]	= imx_clk_gate("pll4_audio", 	"pll4_bypass", base + 0x70, 13);
+	clks[IMX6UL_CLK_PLL5_VIDEO]	= imx_clk_gate("pll5_video",	"pll5_bypass", base + 0xa0, 13);
+	clks[IMX6UL_CLK_PLL6_ENET]	= imx_clk_gate("pll6_enet",	"pll6_bypass", base + 0xe0, 13);
+	clks[IMX6UL_CLK_PLL7_USB_HOST]	= imx_clk_gate("pll7_usb_host",	"pll7_bypass", base + 0x20, 13);
+
+	/*
+	 * Bit 20 is the reserved and read-only bit, we do this only for:
+	 * - Do nothing for usbphy clk_enable/disable
+	 * - Keep refcount when do usbphy clk_enable/disable, in that case,
+	 * the clk framework many need to enable/disable usbphy's parent
+	 */
+	clks[IMX6UL_CLK_USBPHY1] = imx_clk_gate("usbphy1", "pll3_usb_otg",  base + 0x10, 20);
+	clks[IMX6UL_CLK_USBPHY2] = imx_clk_gate("usbphy2", "pll7_usb_host", base + 0x20, 20);
+
+	/*
+	 * usbphy*_gate needs to be on after system boots up, and software
+	 * never needs to control it anymore.
+	 */
+	clks[IMX6UL_CLK_USBPHY1_GATE] = imx_clk_gate("usbphy1_gate", "dummy", base + 0x10, 6);
+	clks[IMX6UL_CLK_USBPHY2_GATE] = imx_clk_gate("usbphy2_gate", "dummy", base + 0x20, 6);
+
+	/*					name		   parent_name	   reg		idx */
+	clks[IMX6UL_CLK_PLL2_PFD0] = imx_clk_pfd("pll2_pfd0_352m", "pll2_bus",	   base + 0x100, 0);
+	clks[IMX6UL_CLK_PLL2_PFD1] = imx_clk_pfd("pll2_pfd1_594m", "pll2_bus",	   base + 0x100, 1);
+	clks[IMX6UL_CLK_PLL2_PFD2] = imx_clk_pfd("pll2_pfd2_396m", "pll2_bus",	   base + 0x100, 2);
+	clks[IMX6UL_CLK_PLL2_PFD3] = imx_clk_pfd("pll2_pfd3_594m", "pll2_bus",	   base + 0x100, 3);
+	clks[IMX6UL_CLK_PLL3_PFD0] = imx_clk_pfd("pll3_pfd0_720m", "pll3_usb_otg", base + 0xf0,  0);
+	clks[IMX6UL_CLK_PLL3_PFD1] = imx_clk_pfd("pll3_pfd1_540m", "pll3_usb_otg", base + 0xf0,  1);
+	clks[IMX6UL_CLK_PLL3_PFD2] = imx_clk_pfd("pll3_pfd2_508m", "pll3_usb_otg", base + 0xf0,	 2);
+	clks[IMX6UL_CLK_PLL3_PFD3] = imx_clk_pfd("pll3_pfd3_454m", "pll3_usb_otg", base + 0xf0,	 3);
+
+	clks[IMX6UL_CLK_ENET_REF] = clk_register_divider_table(NULL, "enet_ref", "pll6_enet", 0,
+			base + 0xe0, 0, 2, 0, clk_enet_ref_table, &imx_ccm_lock);
+	clks[IMX6UL_CLK_ENET2_REF] = clk_register_divider_table(NULL, "enet2_ref", "pll6_enet", 0,
+			base + 0xe0, 2, 2, 0, clk_enet_ref_table, &imx_ccm_lock);
+
+	clks[IMX6UL_CLK_ENET2_REF_125M] = imx_clk_gate("enet_ref_125m", "enet2_ref", base + 0xe0, 20);
+	clks[IMX6UL_CLK_ENET_PTP_REF] 	= imx_clk_fixed_factor("enet_ptp_ref", "pll6_enet", 1, 20);
+	clks[IMX6UL_CLK_ENET_PTP] 	= imx_clk_gate("enet_ptp", "enet_ptp_ref", base + 0xe0, 21);
+
+	clks[IMX6UL_CLK_PLL4_POST_DIV]  = clk_register_divider_table(NULL, "pll4_post_div", "pll4_audio",
+		 CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, base + 0x70, 19, 2, 0, post_div_table, &imx_ccm_lock);
+	clks[IMX6UL_CLK_PLL4_AUDIO_DIV] = clk_register_divider(NULL, "pll4_audio_div", "pll4_post_div",
+		 CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, base + 0x170, 15, 1, 0, &imx_ccm_lock);
+	clks[IMX6UL_CLK_PLL5_POST_DIV]  = clk_register_divider_table(NULL, "pll5_post_div", "pll5_video",
+		 CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, base + 0xa0, 19, 2, 0, post_div_table, &imx_ccm_lock);
+	clks[IMX6UL_CLK_PLL5_VIDEO_DIV] = clk_register_divider_table(NULL, "pll5_video_div", "pll5_post_div",
+		 CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, base + 0x170, 30, 2, 0, video_div_table, &imx_ccm_lock);
+
+	/*						   name		parent_name	 mult  div */
+	clks[IMX6UL_CLK_PLL2_198M] = imx_clk_fixed_factor("pll2_198m", "pll2_pfd2_396m", 1,	2);
+	clks[IMX6UL_CLK_PLL3_80M]  = imx_clk_fixed_factor("pll3_80m",  "pll3_usb_otg",   1, 	6);
+	clks[IMX6UL_CLK_PLL3_60M]  = imx_clk_fixed_factor("pll3_60m",  "pll3_usb_otg",   1, 	8);
+	clks[IMX6UL_CLK_GPT_3M]	   = imx_clk_fixed_factor("gpt_3m",	"osc",		 1,	8);
+
+	np = ccm_node;
+	base = of_iomap(np, 0);
+	WARN_ON(!base);
+
+	clks[IMX6UL_CA7_SECONDARY_SEL]	  = imx_clk_mux("ca7_secondary_sel", base + 0xc, 3, 1, ca7_secondary_sels, ARRAY_SIZE(ca7_secondary_sels));
+	clks[IMX6UL_CLK_STEP] 	 	  = imx_clk_mux("step", base + 0x0c, 8, 1, step_sels, ARRAY_SIZE(step_sels));
+	clks[IMX6UL_CLK_PLL1_SW] 	  = imx_clk_mux_flags("pll1_sw",   base + 0x0c, 2,  1, pll1_sw_sels, ARRAY_SIZE(pll1_sw_sels), 0);
+	clks[IMX6UL_CLK_AXI_ALT_SEL]	  = imx_clk_mux("axi_alt_sel",		base + 0x14, 7,  1, axi_alt_sels, ARRAY_SIZE(axi_alt_sels));
+	clks[IMX6UL_CLK_AXI_SEL] 	  = imx_clk_mux_flags("axi_sel", 	base + 0x14, 6,  1, axi_sels, ARRAY_SIZE(axi_sels), 0);
+	clks[IMX6UL_CLK_PERIPH_PRE] 	  = imx_clk_mux("periph_pre",       base + 0x18, 18, 2, periph_pre_sels, ARRAY_SIZE(periph_pre_sels));
+	clks[IMX6UL_CLK_PERIPH2_PRE] 	  = imx_clk_mux("periph2_pre",      base + 0x18, 21, 2, periph2_pre_sels, ARRAY_SIZE(periph2_pre_sels));
+	clks[IMX6UL_CLK_PERIPH_CLK2_SEL]  = imx_clk_mux("periph_clk2_sel",  base + 0x18, 12, 2, periph_clk2_sels, ARRAY_SIZE(periph_clk2_sels));
+	clks[IMX6UL_CLK_PERIPH2_CLK2_SEL] = imx_clk_mux("periph2_clk2_sel", base + 0x18, 20, 1, periph2_clk2_sels, ARRAY_SIZE(periph2_clk2_sels));
+	clks[IMX6UL_CLK_EIM_SLOW_SEL] 	  = imx_clk_mux("eim_slow_sel", base + 0x1c, 29, 2, eim_slow_sels, ARRAY_SIZE(eim_slow_sels));
+	clks[IMX6UL_CLK_GPMI_SEL]	  = imx_clk_mux("gpmi_sel",     base + 0x1c, 19, 1, gpmi_sels, ARRAY_SIZE(gpmi_sels));
+	clks[IMX6UL_CLK_BCH_SEL]      	  = imx_clk_mux("bch_sel", 	base + 0x1c, 18, 1, bch_sels, ARRAY_SIZE(bch_sels));
+	clks[IMX6UL_CLK_USDHC2_SEL]	  = imx_clk_mux("usdhc2_sel",   base + 0x1c, 17, 1, usdhc_sels, ARRAY_SIZE(usdhc_sels));
+	clks[IMX6UL_CLK_USDHC1_SEL]	  = imx_clk_mux("usdhc1_sel",   base + 0x1c, 16, 1, usdhc_sels, ARRAY_SIZE(usdhc_sels));
+	clks[IMX6UL_CLK_SAI3_SEL]     	  = imx_clk_mux("sai3_sel",     base + 0x1c, 14, 2, sai_sels, ARRAY_SIZE(sai_sels));
+	clks[IMX6UL_CLK_SAI2_SEL]         = imx_clk_mux("sai2_sel",     base + 0x1c, 12, 2, sai_sels, ARRAY_SIZE(sai_sels));
+	clks[IMX6UL_CLK_SAI1_SEL]    	  = imx_clk_mux("sai1_sel",     base + 0x1c, 10, 2, sai_sels, ARRAY_SIZE(sai_sels));
+	clks[IMX6UL_CLK_QSPI1_SEL] 	  = imx_clk_mux("qspi1_sel",    base + 0x1c, 7,  3, qspi1_sels, ARRAY_SIZE(qspi1_sels));
+	clks[IMX6UL_CLK_PERCLK_SEL] 	  = imx_clk_mux("perclk_sel",	base + 0x1c, 6,  1, perclk_sels, ARRAY_SIZE(perclk_sels));
+	clks[IMX6UL_CLK_CAN_SEL]      	  = imx_clk_mux("can_sel",	base + 0x20, 8,  2, can_sels, ARRAY_SIZE(can_sels));
+	clks[IMX6UL_CLK_UART_SEL]	  = imx_clk_mux("uart_sel",	base + 0x24, 6,  1, uart_sels, ARRAY_SIZE(uart_sels));
+	clks[IMX6UL_CLK_ENFC_SEL]	  = imx_clk_mux("enfc_sel",	base + 0x2c, 15, 3, enfc_sels, ARRAY_SIZE(enfc_sels));
+	clks[IMX6UL_CLK_LDB_DI0_SEL]	  = imx_clk_mux("ldb_di0_sel",	base + 0x2c, 9,  3, ldb_di0_sels, ARRAY_SIZE(ldb_di0_sels));
+	clks[IMX6UL_CLK_SPDIF_SEL]	  = imx_clk_mux("spdif_sel",	base + 0x30, 20, 2, spdif_sels, ARRAY_SIZE(spdif_sels));
+	clks[IMX6UL_CLK_SIM_PRE_SEL] 	  = imx_clk_mux("sim_pre_sel",	base + 0x34, 15, 3, sim_pre_sels, ARRAY_SIZE(sim_pre_sels));
+	clks[IMX6UL_CLK_SIM_SEL]	  = imx_clk_mux("sim_sel", 	base + 0x34, 9, 3, sim_sels, ARRAY_SIZE(sim_sels));
+	clks[IMX6UL_CLK_ECSPI_SEL]	  = imx_clk_mux("ecspi_sel",	base + 0x38, 18, 1, ecspi_sels, ARRAY_SIZE(ecspi_sels));
+	clks[IMX6UL_CLK_LCDIF_PRE_SEL]	  = imx_clk_mux("lcdif_pre_sel", base + 0x38, 15, 3, lcdif_pre_sels, ARRAY_SIZE(lcdif_pre_sels));
+	clks[IMX6UL_CLK_LCDIF_SEL]	  = imx_clk_mux("lcdif_sel", 	base + 0x38, 9, 3, lcdif_sels, ARRAY_SIZE(lcdif_sels));
+
+	clks[IMX6UL_CLK_LDB_DI0_DIV_SEL]  = imx_clk_mux("ldb_di0", base + 0x20, 10, 1, ldb_di0_div_sels, ARRAY_SIZE(ldb_di0_div_sels));
+	clks[IMX6UL_CLK_LDB_DI1_DIV_SEL]  = imx_clk_mux("ldb_di1", base + 0x20, 11, 1, ldb_di1_div_sels, ARRAY_SIZE(ldb_di1_div_sels));
+
+	clks[IMX6UL_CLK_LDB_DI0_DIV_3_5] = imx_clk_fixed_factor("ldb_di0_div_3_5", "ldb_di0_sel", 2, 7);
+	clks[IMX6UL_CLK_LDB_DI0_DIV_7]	 = imx_clk_fixed_factor("ldb_di0_div_7",   "ldb_di0_sel", 1, 7);
+	clks[IMX6UL_CLK_LDB_DI1_DIV_3_5] = imx_clk_fixed_factor("ldb_di1_div_3_5", "qspi1_sel", 2, 7);
+	clks[IMX6UL_CLK_LDB_DI1_DIV_7]	 = imx_clk_fixed_factor("ldb_di1_div_7",   "qspi1_sel", 1, 7);
+
+	clks[IMX6UL_CLK_PERIPH]  = imx_clk_busy_mux("periph",  base + 0x14, 25, 1, base + 0x48, 5, periph_sels, ARRAY_SIZE(periph_sels));
+	clks[IMX6UL_CLK_PERIPH2] = imx_clk_busy_mux("periph2", base + 0x14, 26, 1, base + 0x48, 3, periph2_sels, ARRAY_SIZE(periph2_sels));
+
+	clks[IMX6UL_CLK_PERIPH_CLK2]	= imx_clk_divider("periph_clk2",   "periph_clk2_sel",  	base + 0x14, 27, 3);
+	clks[IMX6UL_CLK_PERIPH2_CLK2]	= imx_clk_divider("periph2_clk2",  "periph2_clk2_sel", 	base + 0x14, 0,  3);
+	clks[IMX6UL_CLK_IPG]		= imx_clk_divider("ipg",	   "ahb",		base + 0x14, 8,	 2);
+	clks[IMX6UL_CLK_LCDIF_PODF]	= imx_clk_divider("lcdif_podf",	   "lcdif_pred",	base + 0x18, 23, 3);
+	clks[IMX6UL_CLK_QSPI1_PDOF] 	= imx_clk_divider("qspi1_podf",	   "qspi1_sel",		base + 0x1c, 26, 3);
+	clks[IMX6UL_CLK_EIM_SLOW_PODF]	= imx_clk_divider("eim_slow_podf", "eim_slow_sel",	base + 0x1c, 23, 3);
+	clks[IMX6UL_CLK_PERCLK]		= imx_clk_divider("perclk",	   "perclk_sel",	base + 0x1c, 0,  6);
+	clks[IMX6UL_CLK_CAN_PODF]	= imx_clk_divider("can_podf",	   "can_sel",		base + 0x20, 2,  6);
+	clks[IMX6UL_CLK_GPMI_PODF]	= imx_clk_divider("gpmi_podf",	   "gpmi_sel",		base + 0x24, 22, 3);
+	clks[IMX6UL_CLK_BCH_PODF]	= imx_clk_divider("bch_podf",	   "bch_sel",		base + 0x24, 19, 3);
+	clks[IMX6UL_CLK_USDHC2_PODF]	= imx_clk_divider("usdhc2_podf",   "usdhc2_sel",	base + 0x24, 16, 3);
+	clks[IMX6UL_CLK_USDHC1_PODF]	= imx_clk_divider("usdhc1_podf",   "usdhc1_sel",	base + 0x24, 11, 3);
+	clks[IMX6UL_CLK_UART_PODF]	= imx_clk_divider("uart_podf",	   "uart_sel",		base + 0x24, 0,  6);
+	clks[IMX6UL_CLK_SAI3_PRED]	= imx_clk_divider("sai3_pred",	   "sai3_sel",		base + 0x28, 22, 3);
+	clks[IMX6UL_CLK_SAI3_PODF]	= imx_clk_divider("sai3_podf",	   "sai3_pred",		base + 0x28, 16, 6);
+	clks[IMX6UL_CLK_SAI1_PRED]	= imx_clk_divider("sai1_pred",	   "sai1_sel",		base + 0x28, 6,	 3);
+	clks[IMX6UL_CLK_SAI1_PODF]	= imx_clk_divider("sai1_podf",	   "sai1_pred",		base + 0x28, 0,	 6);
+	clks[IMX6UL_CLK_ENFC_PRED]	= imx_clk_divider("enfc_pred",	   "enfc_sel",		base + 0x2c, 18, 3);
+	clks[IMX6UL_CLK_ENFC_PODF]	= imx_clk_divider("enfc_podf",	   "enfc_pred",		base + 0x2c, 21, 6);
+	clks[IMX6UL_CLK_SAI2_PRED]	= imx_clk_divider("sai2_pred",	   "sai2_sel",		base + 0x2c, 6,	 3);
+	clks[IMX6UL_CLK_SAI2_PODF]	= imx_clk_divider("sai2_podf",	   "sai2_pred",		base + 0x2c, 0,  6);
+	clks[IMX6UL_CLK_SPDIF_PRED]	= imx_clk_divider("spdif_pred",	   "spdif_sel",		base + 0x30, 25, 3);
+	clks[IMX6UL_CLK_SPDIF_PODF]	= imx_clk_divider("spdif_podf",	   "spdif_pred",	base + 0x30, 22, 3);
+	clks[IMX6UL_CLK_SIM_PODF]	= imx_clk_divider("sim_podf",	   "sim_pre_sel",	base + 0x34, 12, 3);
+	clks[IMX6UL_CLK_ECSPI_PODF]	= imx_clk_divider("ecspi_podf",	   "ecspi_sel",		base + 0x38, 19, 6);
+	clks[IMX6UL_CLK_LCDIF_PRED]	= imx_clk_divider("lcdif_pred",	   "lcdif_pre_sel",	base + 0x38, 12, 3);
+	clks[IMX6UL_CLK_CSI_PODF]       = imx_clk_divider("csi_podf",      "csi_sel",           base + 0x3c, 11, 3);
+
+	clks[IMX6UL_CLK_ARM]		= imx_clk_busy_divider("arm", 	    "pll1_sw",	base +	0x10, 0,  3,  base + 0x48, 16);
+	clks[IMX6UL_CLK_MMDC_PODF]	= imx_clk_busy_divider("mmdc_podf", "periph2",	base +  0x14, 3,  3,  base + 0x48, 2);
+	clks[IMX6UL_CLK_AXI_PODF]	= imx_clk_busy_divider("axi_podf",  "axi_sel",	base +  0x14, 16, 3,  base + 0x48, 0);
+	clks[IMX6UL_CLK_AHB]		= imx_clk_busy_divider("ahb",	    "periph",	base +  0x14, 10, 3,  base + 0x48, 1);
+
+	/* CCGR0 */
+	clks[IMX6UL_CLK_AIPSTZ1]	= imx_clk_gate2("aips_tz1", 	"ahb",		base + 0x68,	0);
+	clks[IMX6UL_CLK_AIPSTZ2]	= imx_clk_gate2("aips_tz2", 	"ahb",		base + 0x68,	2);
+	clks[IMX6UL_CLK_APBHDMA]	= imx_clk_gate2("apbh_dma",	"bch_podf",	base + 0x68,	4);
+	clks[IMX6UL_CLK_ASRC_IPG]	= imx_clk_gate2_shared("asrc_ipg",	"ahb",	base + 0x68,	6, &share_count_asrc);
+	clks[IMX6UL_CLK_ASRC_MEM]	= imx_clk_gate2_shared("asrc_mem",	"ahb",	base + 0x68,	6, &share_count_asrc);
+	clks[IMX6UL_CLK_CAAM_MEM]	= imx_clk_gate2("caam_mem",	"ahb",		base + 0x68,	8);
+	clks[IMX6UL_CLK_CAAM_ACLK]	= imx_clk_gate2("caam_aclk",	"ahb",		base + 0x68,	10);
+	clks[IMX6UL_CLK_CAAM_IPG]	= imx_clk_gate2("caam_ipg",	"ipg",		base + 0x68,	12);
+	clks[IMX6UL_CLK_CAN1_IPG]	= imx_clk_gate2("can1_ipg",	"ipg",		base + 0x68,	14);
+	clks[IMX6UL_CLK_CAN1_SERIAL]	= imx_clk_gate2("can1_serial",	"can_podf",	base + 0x68, 	16);
+	clks[IMX6UL_CLK_CAN2_IPG]	= imx_clk_gate2("can2_ipg",	"ipg",		base + 0x68,	18);
+	clks[IMX6UL_CLK_CAN2_SERIAL]	= imx_clk_gate2("can2_serial",	"can_podf",	base + 0x68,	20);
+	clks[IMX6UL_CLK_GPT2_BUS]	= imx_clk_gate2("gpt_bus",	"perclk",	base + 0x68,	24);
+	clks[IMX6UL_CLK_GPT2_SERIAL]	= imx_clk_gate2("gpt_serial",	"perclk",	base + 0x68,	26);
+	clks[IMX6UL_CLK_UART2_IPG]	= imx_clk_gate2("uart2_ipg",	"ipg",		base + 0x68,	28);
+	clks[IMX6UL_CLK_UART2_SERIAL]	= imx_clk_gate2("uart2_serial",	"uart_podf",	base + 0x68,	28);
+	clks[IMX6UL_CLK_AIPSTZ3]	= imx_clk_gate2("aips_tz3",	"ahb",		base + 0x68,	30);
+
+	/* CCGR1 */
+	clks[IMX6UL_CLK_ECSPI1]		= imx_clk_gate2("ecspi1",	"ecspi_podf",	base + 0x6c,	0);
+	clks[IMX6UL_CLK_ECSPI2]		= imx_clk_gate2("ecspi2",	"ecspi_podf",	base + 0x6c,	2);
+	clks[IMX6UL_CLK_ECSPI3]		= imx_clk_gate2("ecspi3",	"ecspi_podf",	base + 0x6c,	4);
+	clks[IMX6UL_CLK_ECSPI4]		= imx_clk_gate2("ecspi4",	"ecspi_podf",	base + 0x6c,	6);
+	clks[IMX6UL_CLK_ADC2]		= imx_clk_gate2("adc2",		"ipg",		base + 0x6c,	8);
+	clks[IMX6UL_CLK_UART3_IPG]	= imx_clk_gate2("uart3_ipg",	"ipg",		base + 0x6c,	10);
+	clks[IMX6UL_CLK_UART3_SERIAL]	= imx_clk_gate2("uart3_serial",	"uart_podf",	base + 0x6c,	10);
+	clks[IMX6UL_CLK_EPIT1]		= imx_clk_gate2("epit1",	"perclk",	base + 0x6c,	12);
+	clks[IMX6UL_CLK_EPIT2]		= imx_clk_gate2("epit2",	"perclk",	base + 0x6c,	14);
+	clks[IMX6UL_CLK_ADC1]		= imx_clk_gate2("adc1",		"ipg",		base + 0x6c,	16);
+	clks[IMX6UL_CLK_GPT1_BUS]	= imx_clk_gate2("gpt1_bus",	"perclk",	base + 0x6c,	20);
+	clks[IMX6UL_CLK_GPT1_SERIAL]	= imx_clk_gate2("gpt1_serial",	"perclk",	base + 0x6c,	22);
+	clks[IMX6UL_CLK_UART4_IPG]	= imx_clk_gate2("uart4_ipg",	"ipg",		base + 0x6c,	24);
+	clks[IMX6UL_CLK_UART4_SERIAL]	= imx_clk_gate2("uart4_serail",	"uart_podf",	base + 0x6c,	24);
+
+	/* CCGR2 */
+	clks[IMX6UL_CLK_CSI]		= imx_clk_gate2("csi",		"csi_podf",		base + 0x70,	2);
+	clks[IMX6UL_CLK_I2C1]		= imx_clk_gate2("i2c1",		"perclk",	base + 0x70,	6);
+	clks[IMX6UL_CLK_I2C2]		= imx_clk_gate2("i2c2",		"perclk",	base + 0x70,	8);
+	clks[IMX6UL_CLK_I2C3] 		= imx_clk_gate2("i2c3",		"perclk",	base + 0x70,	10);
+	clks[IMX6UL_CLK_OCOTP]		= imx_clk_gate2("ocotp",	"ipg",		base + 0x70,	12);
+	clks[IMX6UL_CLK_IOMUXC]		= imx_clk_gate2("iomuxc",	"lcdif_podf",	base + 0x70,	14);
+	clks[IMX6UL_CLK_LCDIF_APB]	= imx_clk_gate2("lcdif_apb",	"axi",		base + 0x70,	28);
+	clks[IMX6UL_CLK_PXP]		= imx_clk_gate2("pxp",		"axi",		base + 0x70,	30);
+
+	/* CCGR3 */
+	clks[IMX6UL_CLK_UART5_IPG]	= imx_clk_gate2("uart5_ipg",	"ipg",		base + 0x74,	2);
+	clks[IMX6UL_CLK_UART5_SERIAL]	= imx_clk_gate2("uart5_serial",	"uart_podf",	base + 0x74,	2);
+	clks[IMX6UL_CLK_ENET]		= imx_clk_gate2("enet",		"ipg",		base + 0x74,	4);
+	clks[IMX6UL_CLK_ENET_AHB]	= imx_clk_gate2("enet_ahb",	"ahb",		base + 0x74,	4);
+	clks[IMX6UL_CLK_UART6_IPG]	= imx_clk_gate2("uart6_ipg",	"ipg",		base + 0x74,	6);
+	clks[IMX6UL_CLK_UART6_SERIAL]	= imx_clk_gate2("uart6_serial",	"uart_podf",	base + 0x74,	6);
+	clks[IMX6UL_CLK_LCDIF_PIX]	= imx_clk_gate2("lcdif_pix",	"lcdif_podf",	base + 0x74,	10);
+	clks[IMX6UL_CLK_QSPI]		= imx_clk_gate2("qspi1",	"qspi1_podf",	base + 0x74,	14);
+	clks[IMX6UL_CLK_WDOG1]		= imx_clk_gate2("wdog1",	"ipg",		base + 0x74,	16);
+	clks[IMX6UL_CLK_MMDC_P0_FAST]	= imx_clk_gate("mmdc_p0_fast", "mmdc_podf", base + 0x74,	20);
+	clks[IMX6UL_CLK_MMDC_P0_IPG]	= imx_clk_gate2("mmdc_p0_ipg",	"ipg",		base + 0x74,	24);
+	clks[IMX6UL_CLK_AXI]		= imx_clk_gate("axi",	"axi_podf",	base + 0x74,	28);
+
+	/* CCGR4 */
+	clks[IMX6UL_CLK_PER_BCH]	= imx_clk_gate2("per_bch",	"bch_podf",	base + 0x78,	12);
+	clks[IMX6UL_CLK_PWM1]		= imx_clk_gate2("pwm1",		"perclk",	base + 0x78,	16);
+	clks[IMX6UL_CLK_PWM2]		= imx_clk_gate2("pwm2",		"perclk",	base + 0x78,	18);
+	clks[IMX6UL_CLK_PWM3]		= imx_clk_gate2("pwm3",		"perclk",	base + 0x78,	20);
+	clks[IMX6UL_CLK_PWM4]		= imx_clk_gate2("pwm4",		"perclk",	base + 0x78,	22);
+	clks[IMX6UL_CLK_GPMI_BCH_APB]	= imx_clk_gate2("gpmi_bch_apb",	"bch_podf",	base + 0x78,	24);
+	clks[IMX6UL_CLK_GPMI_BCH]	= imx_clk_gate2("gpmi_bch",	"gpmi_podf",	base + 0x78,	26);
+	clks[IMX6UL_CLK_GPMI_IO]	= imx_clk_gate2("gpmi_io",	"enfc_podf",	base + 0x78,	28);
+	clks[IMX6UL_CLK_GPMI_APB]	= imx_clk_gate2("gpmi_apb",	"bch_podf",	base + 0x78,	30);
+
+	/* CCGR5 */
+	clks[IMX6UL_CLK_ROM]		= imx_clk_gate2("rom",		"ahb",		base + 0x7c,	0);
+	clks[IMX6UL_CLK_SDMA]		= imx_clk_gate2("sdma",		"ahb",		base + 0x7c,	6);
+	clks[IMX6UL_CLK_WDOG2]		= imx_clk_gate2("wdog2",	"ipg",		base + 0x7c,	10);
+	clks[IMX6UL_CLK_SPBA]		= imx_clk_gate2("spba",		"ipg",		base + 0x7c,	12);
+	clks[IMX6UL_CLK_SPDIF]		= imx_clk_gate2_shared("spdif",		"spdif_podf",	base + 0x7c,	14, &share_count_audio);
+	clks[IMX6UL_CLK_SPDIF_GCLK]	= imx_clk_gate2_shared("spdif_gclk",	"ipg",		base + 0x7c,	14, &share_count_audio);
+	clks[IMX6UL_CLK_SAI3]		= imx_clk_gate2_shared("sai3",		"sai3_podf",	base + 0x7c,	22, &share_count_sai3);
+	clks[IMX6UL_CLK_SAI3_IPG]	= imx_clk_gate2_shared("sai3_ipg",	"ipg",		base + 0x7c,	22, &share_count_sai3);
+	clks[IMX6UL_CLK_UART1_IPG]	= imx_clk_gate2("uart1_ipg",	"ipg",		base + 0x7c,	24);
+	clks[IMX6UL_CLK_UART1_SERIAL]	= imx_clk_gate2("uart1_serial",	"uart_podf",	base + 0x7c,	24);
+	clks[IMX6UL_CLK_UART7_IPG]	= imx_clk_gate2("uart7_ipg",	"ipg",		base + 0x7c,	26);
+	clks[IMX6UL_CLK_UART7_SERIAL]	= imx_clk_gate2("uart7_serial",	"uart_podf",	base + 0x7c,	26);
+	clks[IMX6UL_CLK_SAI1]		= imx_clk_gate2_shared("sai1",		"sai1_podf",	base + 0x7c,	28, &share_count_sai1);
+	clks[IMX6UL_CLK_SAI1_IPG]	= imx_clk_gate2_shared("sai1_ipg",	"ipg",		base + 0x7c,	28, &share_count_sai1);
+	clks[IMX6UL_CLK_SAI2]		= imx_clk_gate2_shared("sai2",		"sai2_podf",	base + 0x7c,	30, &share_count_sai2);
+	clks[IMX6UL_CLK_SAI2_IPG]	= imx_clk_gate2_shared("sai2_ipg",	"ipg",		base + 0x7c,	30, &share_count_sai2);
+
+	/* CCGR6 */
+	clks[IMX6UL_CLK_USBOH3]		= imx_clk_gate2("usboh3",	"ipg",		 base + 0x80,	0);
+	clks[IMX6UL_CLK_USDHC1]		= imx_clk_gate2("usdhc1",	"usdhc1_podf",	 base + 0x80,	2);
+	clks[IMX6UL_CLK_USDHC2]		= imx_clk_gate2("usdhc2",	"usdhc2_podf",	 base + 0x80,	4);
+	clks[IMX6UL_CLK_SIM1]		= imx_clk_gate2("sim1",		"sim_sel",	 base + 0x80,	6);
+	clks[IMX6UL_CLK_SIM2]		= imx_clk_gate2("sim2",		"sim_sel",	 base + 0x80,	8);
+	clks[IMX6UL_CLK_EIM]		= imx_clk_gate2("eim",		"eim_slow_podf", base + 0x80,	10);
+	clks[IMX6UL_CLK_PWM8]		= imx_clk_gate2("pwm8",		"perclk",	 base + 0x80,	16);
+	clks[IMX6UL_CLK_UART8_IPG]	= imx_clk_gate2("uart8_ipg",	"ipg",		 base + 0x80,	14);
+	clks[IMX6UL_CLK_UART8_SERIAL]	= imx_clk_gate2("uart8_serial", "uart_podf",	 base + 0x80,	14);
+	clks[IMX6UL_CLK_WDOG3]		= imx_clk_gate2("wdog3",	"ipg",		 base + 0x80,	20);
+	clks[IMX6UL_CLK_I2C4]		= imx_clk_gate2("i2c4",		"perclk", 	 base + 0x80,	24);
+	clks[IMX6UL_CLK_PWM5]		= imx_clk_gate2("pwm5",		"perclk",	 base + 0x80,	26);
+	clks[IMX6UL_CLK_PWM6]		= imx_clk_gate2("pwm6",		"perclk",	 base +	0x80,	28);
+	clks[IMX6UL_CLK_PWM7]		= imx_clk_gate2("Pwm7",		"perclk",	 base + 0x80,	30);
+
+	/* mask handshake of mmdc */
+	writel_relaxed(BM_CCM_CCDR_MMDC_CH0_MASK, base + CCDR);
+
+	for (i = 0; i < ARRAY_SIZE(clks); i++)
+		if (IS_ERR(clks[i]))
+			pr_err("i.MX6UL clk %d: register failed with %ld\n", i, PTR_ERR(clks[i]));
+
+	clk_data.clks = clks;
+	clk_data.clk_num = ARRAY_SIZE(clks);
+	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+
+	/* set perclk to from OSC */
+	clk_set_parent(clks[IMX6UL_CLK_PERCLK_SEL], clks[IMX6UL_CLK_OSC]);
+
+	clk_set_rate(clks[IMX6UL_CLK_ENET_REF], 50000000);
+	clk_set_rate(clks[IMX6UL_CLK_ENET2_REF], 50000000);
+	clk_set_rate(clks[IMX6UL_CLK_CSI], 24000000);
+
+	/* keep all the clks on just for bringup */
+	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
+		clk_prepare_enable(clks[clks_init_on[i]]);
+
+	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
+		clk_prepare_enable(clks[IMX6UL_CLK_USBPHY1_GATE]);
+		clk_prepare_enable(clks[IMX6UL_CLK_USBPHY2_GATE]);
+	}
+
+	clk_set_parent(clks[IMX6UL_CLK_CAN_SEL], clks[IMX6UL_CLK_PLL3_60M]);
+	clk_set_parent(clks[IMX6UL_CLK_SIM_PRE_SEL], clks[IMX6UL_CLK_PLL3_USB_OTG]);
+
+	clk_set_parent(clks[IMX6UL_CLK_ENFC_SEL], clks[IMX6UL_CLK_PLL2_PFD2]);
+}
+
+CLK_OF_DECLARE(imx6ul, "fsl,imx6ul-ccm", imx6ul_clocks_init);
diff --git a/drivers/clk/imx/clk-pfd.c b/drivers/clk/imx/clk-pfd.c
index 0b0f6f66ec56..04a3e78ea1bc 100644
--- a/drivers/clk/imx/clk-pfd.c
+++ b/drivers/clk/imx/clk-pfd.c
@@ -10,7 +10,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/imx/clk-pllv1.c b/drivers/clk/imx/clk-pllv1.c
index c34ad8a611dd..8564e4342c7d 100644
--- a/drivers/clk/imx/clk-pllv1.c
+++ b/drivers/clk/imx/clk-pllv1.c
@@ -1,4 +1,3 @@
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/imx/clk-pllv3.c b/drivers/clk/imx/clk-pllv3.c
index f0d15fb9d783..6addf8f58b97 100644
--- a/drivers/clk/imx/clk-pllv3.c
+++ b/drivers/clk/imx/clk-pllv3.c
@@ -10,7 +10,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/io.h>
diff --git a/drivers/clk/ingenic/cgu.c b/drivers/clk/ingenic/cgu.c
index b936cdd1a13c..7cfb7b2a2ed6 100644
--- a/drivers/clk/ingenic/cgu.c
+++ b/drivers/clk/ingenic/cgu.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/delay.h>
diff --git a/drivers/clk/keystone/gate.c b/drivers/clk/keystone/gate.c
index 86f1e362eafb..aed5af23895b 100644
--- a/drivers/clk/keystone/gate.c
+++ b/drivers/clk/keystone/gate.c
@@ -10,7 +10,6 @@
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  */
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/drivers/clk/keystone/pll.c b/drivers/clk/keystone/pll.c
index 4a375ead70e9..3f553d0ae0b5 100644
--- a/drivers/clk/keystone/pll.c
+++ b/drivers/clk/keystone/pll.c
@@ -10,7 +10,6 @@
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  */
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -309,8 +308,7 @@ static void __init of_pll_mux_clk_init(struct device_node *node)
 		return;
 	}
 
-	parents[0] = of_clk_get_parent_name(node, 0);
-	parents[1] = of_clk_get_parent_name(node, 1);
+	of_clk_parent_fill(node, parents, 2);
 	if (!parents[0] || !parents[1]) {
 		pr_err("%s: missing parent clocks\n", __func__);
 		return;
diff --git a/drivers/clk/mediatek/clk-gate.h b/drivers/clk/mediatek/clk-gate.h
index 6b6780b1e9c5..11e25c992948 100644
--- a/drivers/clk/mediatek/clk-gate.h
+++ b/drivers/clk/mediatek/clk-gate.h
@@ -16,9 +16,10 @@
 #define __DRV_CLK_GATE_H
 
 #include <linux/regmap.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
+struct clk;
+
 struct mtk_clk_gate {
 	struct clk_hw	hw;
 	struct regmap	*regmap;
diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c
index 08b4b849b491..07c21e44b4b3 100644
--- a/drivers/clk/mediatek/clk-mt8135.c
+++ b/drivers/clk/mediatek/clk-mt8135.c
@@ -12,6 +12,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/mediatek/clk-mt8173.c b/drivers/clk/mediatek/clk-mt8173.c
index 4b9e04cdf7e8..90eff85f4285 100644
--- a/drivers/clk/mediatek/clk-mt8173.c
+++ b/drivers/clk/mediatek/clk-mt8173.c
@@ -12,6 +12,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
@@ -700,6 +701,22 @@ static const struct mtk_composite peri_clks[] __initconst = {
 	MUX(CLK_PERI_UART3_SEL, "uart3_ck_sel", uart_ck_sel_parents, 0x40c, 3, 1),
 };
 
+static struct clk_onecell_data *mt8173_top_clk_data __initdata;
+static struct clk_onecell_data *mt8173_pll_clk_data __initdata;
+
+static void __init mtk_clk_enable_critical(void)
+{
+	if (!mt8173_top_clk_data || !mt8173_pll_clk_data)
+		return;
+
+	clk_prepare_enable(mt8173_pll_clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+	clk_prepare_enable(mt8173_pll_clk_data->clks[CLK_APMIXED_ARMCA7PLL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_MEM_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_DDRPHYCFG_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_CCI400_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_RTC_SEL]);
+}
+
 static void __init mtk_topckgen_init(struct device_node *node)
 {
 	struct clk_onecell_data *clk_data;
@@ -712,19 +729,19 @@ static void __init mtk_topckgen_init(struct device_node *node)
 		return;
 	}
 
-	clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
+	mt8173_top_clk_data = clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
 
 	mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data);
 	mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data);
 	mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base,
 			&mt8173_clk_lock, clk_data);
 
-	clk_prepare_enable(clk_data->clks[CLK_TOP_CCI400_SEL]);
-
 	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
 	if (r)
 		pr_err("%s(): could not register clock provider: %d\n",
 			__func__, r);
+
+	mtk_clk_enable_critical();
 }
 CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8173-topckgen", mtk_topckgen_init);
 
@@ -779,8 +796,9 @@ CLK_OF_DECLARE(mtk_pericfg, "mediatek,mt8173-pericfg", mtk_pericfg_init);
 
 #define CON0_MT8173_RST_BAR	BIT(24)
 
-#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, _pd_reg, _pd_shift, \
-			_tuner_reg, _pcw_reg, _pcw_shift) { \
+#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits,	\
+			_pd_reg, _pd_shift, _tuner_reg, _pcw_reg,	\
+			_pcw_shift, _div_table) {			\
 		.id = _id,						\
 		.name = _name,						\
 		.reg = _reg,						\
@@ -795,14 +813,31 @@ CLK_OF_DECLARE(mtk_pericfg, "mediatek,mt8173-pericfg", mtk_pericfg_init);
 		.tuner_reg = _tuner_reg,				\
 		.pcw_reg = _pcw_reg,					\
 		.pcw_shift = _pcw_shift,				\
+		.div_table = _div_table,				\
 	}
 
+#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits,	\
+			_pd_reg, _pd_shift, _tuner_reg, _pcw_reg,	\
+			_pcw_shift)					\
+		PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \
+			_pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \
+			NULL)
+
+static const struct mtk_pll_div_table mmpll_div_table[] = {
+	{ .div = 0, .freq = MT8173_PLL_FMAX },
+	{ .div = 1, .freq = 1000000000 },
+	{ .div = 2, .freq = 702000000 },
+	{ .div = 3, .freq = 253500000 },
+	{ .div = 4, .freq = 126750000 },
+	{ } /* sentinel */
+};
+
 static const struct mtk_pll_data plls[] = {
 	PLL(CLK_APMIXED_ARMCA15PLL, "armca15pll", 0x200, 0x20c, 0x00000001, 0, 21, 0x204, 24, 0x0, 0x204, 0),
 	PLL(CLK_APMIXED_ARMCA7PLL, "armca7pll", 0x210, 0x21c, 0x00000001, 0, 21, 0x214, 24, 0x0, 0x214, 0),
 	PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x220, 0x22c, 0xf0000101, HAVE_RST_BAR, 21, 0x220, 4, 0x0, 0x224, 0),
 	PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x230, 0x23c, 0xfe000001, HAVE_RST_BAR, 7, 0x230, 4, 0x0, 0x234, 14),
-	PLL(CLK_APMIXED_MMPLL, "mmpll", 0x240, 0x24c, 0x00000001, 0, 21, 0x244, 24, 0x0, 0x244, 0),
+	PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x240, 0x24c, 0x00000001, 0, 21, 0x244, 24, 0x0, 0x244, 0, mmpll_div_table),
 	PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x250, 0x25c, 0x00000001, 0, 21, 0x250, 4, 0x0, 0x254, 0),
 	PLL(CLK_APMIXED_VENCPLL, "vencpll", 0x260, 0x26c, 0x00000001, 0, 21, 0x260, 4, 0x0, 0x264, 0),
 	PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x270, 0x27c, 0x00000001, 0, 21, 0x270, 4, 0x0, 0x274, 0),
@@ -818,13 +853,13 @@ static void __init mtk_apmixedsys_init(struct device_node *node)
 {
 	struct clk_onecell_data *clk_data;
 
-	clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
+	mt8173_pll_clk_data = clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
 	if (!clk_data)
 		return;
 
 	mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
 
-	clk_prepare_enable(clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+	mtk_clk_enable_critical();
 }
 CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8173-apmixedsys",
 		mtk_apmixedsys_init);
diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h
index 9dda9d8ad10b..c5cbecb3d218 100644
--- a/drivers/clk/mediatek/clk-mtk.h
+++ b/drivers/clk/mediatek/clk-mtk.h
@@ -17,9 +17,10 @@
 
 #include <linux/regmap.h>
 #include <linux/bitops.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
+struct clk;
+
 #define MAX_MUX_GATE_BIT	31
 #define INVALID_MUX_GATE_BIT	(MAX_MUX_GATE_BIT + 1)
 
@@ -134,6 +135,11 @@ struct clk_onecell_data *mtk_alloc_clk_data(unsigned int clk_num);
 
 #define HAVE_RST_BAR	BIT(0)
 
+struct mtk_pll_div_table {
+	u32 div;
+	unsigned long freq;
+};
+
 struct mtk_pll_data {
 	int id;
 	const char *name;
@@ -150,6 +156,7 @@ struct mtk_pll_data {
 	int pcwbits;
 	uint32_t pcw_reg;
 	int pcw_shift;
+	const struct mtk_pll_div_table *div_table;
 };
 
 void __init mtk_clk_register_plls(struct device_node *node,
diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c
index 44409e98c52f..622e7b6c62b4 100644
--- a/drivers/clk/mediatek/clk-pll.c
+++ b/drivers/clk/mediatek/clk-pll.c
@@ -90,20 +90,23 @@ static unsigned long __mtk_pll_recalc_rate(struct mtk_clk_pll *pll, u32 fin,
 static void mtk_pll_set_rate_regs(struct mtk_clk_pll *pll, u32 pcw,
 		int postdiv)
 {
-	u32 con1, pd, val;
+	u32 con1, val;
 	int pll_en;
 
-	/* set postdiv */
-	pd = readl(pll->pd_addr);
-	pd &= ~(POSTDIV_MASK << pll->data->pd_shift);
-	pd |= (ffs(postdiv) - 1) << pll->data->pd_shift;
-	writel(pd, pll->pd_addr);
-
 	pll_en = readl(pll->base_addr + REG_CON0) & CON0_BASE_EN;
 
-	/* set pcw */
-	val = readl(pll->pcw_addr);
+	/* set postdiv */
+	val = readl(pll->pd_addr);
+	val &= ~(POSTDIV_MASK << pll->data->pd_shift);
+	val |= (ffs(postdiv) - 1) << pll->data->pd_shift;
+
+	/* postdiv and pcw need to set at the same time if on same register */
+	if (pll->pd_addr != pll->pcw_addr) {
+		writel(val, pll->pd_addr);
+		val = readl(pll->pcw_addr);
+	}
 
+	/* set pcw */
 	val &= ~GENMASK(pll->data->pcw_shift + pll->data->pcwbits - 1,
 			pll->data->pcw_shift);
 	val |= pcw << pll->data->pcw_shift;
@@ -135,16 +138,28 @@ static void mtk_pll_calc_values(struct mtk_clk_pll *pll, u32 *pcw, u32 *postdiv,
 		u32 freq, u32 fin)
 {
 	unsigned long fmin = 1000 * MHZ;
+	const struct mtk_pll_div_table *div_table = pll->data->div_table;
 	u64 _pcw;
 	u32 val;
 
 	if (freq > pll->data->fmax)
 		freq = pll->data->fmax;
 
-	for (val = 0; val < 4; val++) {
+	if (div_table) {
+		if (freq > div_table[0].freq)
+			freq = div_table[0].freq;
+
+		for (val = 0; div_table[val + 1].freq != 0; val++) {
+			if (freq > div_table[val + 1].freq)
+				break;
+		}
 		*postdiv = 1 << val;
-		if (freq * *postdiv >= fmin)
-			break;
+	} else {
+		for (val = 0; val < 5; val++) {
+			*postdiv = 1 << val;
+			if ((u64)freq * *postdiv >= fmin)
+				break;
+		}
 	}
 
 	/* _pcw = freq * postdiv / fin * 2^pcwfbits */
diff --git a/drivers/clk/meson/clk-cpu.c b/drivers/clk/meson/clk-cpu.c
index 71ad493b94df..f7c30ea54ca8 100644
--- a/drivers/clk/meson/clk-cpu.c
+++ b/drivers/clk/meson/clk-cpu.c
@@ -35,6 +35,7 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
 #define MESON_CPU_CLK_CNTL1		0x00
diff --git a/drivers/clk/meson/clkc.c b/drivers/clk/meson/clkc.c
index b8c511c5e7a7..c83ae1367abc 100644
--- a/drivers/clk/meson/clkc.c
+++ b/drivers/clk/meson/clkc.c
@@ -15,7 +15,6 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/syscon.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/mmp/clk-apbc.c b/drivers/clk/mmp/clk-apbc.c
index 09d41c717c52..4c717db05f2d 100644
--- a/drivers/clk/mmp/clk-apbc.c
+++ b/drivers/clk/mmp/clk-apbc.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/err.h>
 #include <linux/delay.h>
diff --git a/drivers/clk/mmp/clk-apmu.c b/drivers/clk/mmp/clk-apmu.c
index cdcf2d7f321e..47b5542ce50f 100644
--- a/drivers/clk/mmp/clk-apmu.c
+++ b/drivers/clk/mmp/clk-apmu.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/err.h>
 #include <linux/delay.h>
diff --git a/drivers/clk/mmp/clk-gate.c b/drivers/clk/mmp/clk-gate.c
index adbd9d64ded2..d20cd3431ac2 100644
--- a/drivers/clk/mmp/clk-gate.c
+++ b/drivers/clk/mmp/clk-gate.c
@@ -27,7 +27,6 @@
 static int mmp_clk_gate_enable(struct clk_hw *hw)
 {
 	struct mmp_clk_gate *gate = to_clk_mmp_gate(hw);
-	struct clk *clk = hw->clk;
 	unsigned long flags = 0;
 	unsigned long rate;
 	u32 tmp;
@@ -44,7 +43,7 @@ static int mmp_clk_gate_enable(struct clk_hw *hw)
 		spin_unlock_irqrestore(gate->lock, flags);
 
 	if (gate->flags & MMP_CLK_GATE_NEED_DELAY) {
-		rate = __clk_get_rate(clk);
+		rate = clk_hw_get_rate(hw);
 		/* Need delay 2 cycles. */
 		udelay(2000000/rate);
 	}
diff --git a/drivers/clk/mmp/clk-mix.c b/drivers/clk/mmp/clk-mix.c
index de6a873175d2..c554833cffc5 100644
--- a/drivers/clk/mmp/clk-mix.c
+++ b/drivers/clk/mmp/clk-mix.c
@@ -63,7 +63,7 @@ static unsigned int _get_div(struct mmp_clk_mix *mix, unsigned int val)
 
 static unsigned int _get_mux(struct mmp_clk_mix *mix, unsigned int val)
 {
-	int num_parents = __clk_get_num_parents(mix->hw.clk);
+	int num_parents = clk_hw_get_num_parents(&mix->hw);
 	int i;
 
 	if (mix->mux_flags & CLK_MUX_INDEX_BIT)
@@ -113,15 +113,15 @@ static void _filter_clk_table(struct mmp_clk_mix *mix,
 {
 	int i;
 	struct mmp_clk_mix_clk_table *item;
-	struct clk *parent, *clk;
+	struct clk_hw *parent, *hw;
 	unsigned long parent_rate;
 
-	clk = mix->hw.clk;
+	hw = &mix->hw;
 
 	for (i = 0; i < table_size; i++) {
 		item = &table[i];
-		parent = clk_get_parent_by_index(clk, item->parent_index);
-		parent_rate = __clk_get_rate(parent);
+		parent = clk_hw_get_parent_by_index(hw, item->parent_index);
+		parent_rate = clk_hw_get_rate(parent);
 		if (parent_rate % item->rate) {
 			item->valid = 0;
 		} else {
@@ -181,7 +181,7 @@ static int _set_rate(struct mmp_clk_mix *mix, u32 mux_val, u32 div_val,
 
 		if (timeout == 0) {
 			pr_err("%s:%s cannot do frequency change\n",
-				__func__, __clk_get_name(mix->hw.clk));
+				__func__, clk_hw_get_name(&mix->hw));
 			ret = -EBUSY;
 			goto error;
 		}
@@ -201,27 +201,22 @@ error:
 	return ret;
 }
 
-static long mmp_clk_mix_determine_rate(struct clk_hw *hw, unsigned long rate,
-					unsigned long min_rate,
-					unsigned long max_rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_clk)
+static int mmp_clk_mix_determine_rate(struct clk_hw *hw,
+				      struct clk_rate_request *req)
 {
 	struct mmp_clk_mix *mix = to_clk_mix(hw);
 	struct mmp_clk_mix_clk_table *item;
-	struct clk *parent, *parent_best, *mix_clk;
+	struct clk_hw *parent, *parent_best;
 	unsigned long parent_rate, mix_rate, mix_rate_best, parent_rate_best;
 	unsigned long gap, gap_best;
 	u32 div_val_max;
 	unsigned int div;
 	int i, j;
 
-	mix_clk = hw->clk;
 
-	parent = NULL;
 	mix_rate_best = 0;
 	parent_rate_best = 0;
-	gap_best = rate;
+	gap_best = ULONG_MAX;
 	parent_best = NULL;
 
 	if (mix->table) {
@@ -229,11 +224,11 @@ static long mmp_clk_mix_determine_rate(struct clk_hw *hw, unsigned long rate,
 			item = &mix->table[i];
 			if (item->valid == 0)
 				continue;
-			parent = clk_get_parent_by_index(mix_clk,
+			parent = clk_hw_get_parent_by_index(hw,
 							item->parent_index);
-			parent_rate = __clk_get_rate(parent);
+			parent_rate = clk_hw_get_rate(parent);
 			mix_rate = parent_rate / item->divisor;
-			gap = abs(mix_rate - rate);
+			gap = abs(mix_rate - req->rate);
 			if (parent_best == NULL || gap < gap_best) {
 				parent_best = parent;
 				parent_rate_best = parent_rate;
@@ -244,14 +239,14 @@ static long mmp_clk_mix_determine_rate(struct clk_hw *hw, unsigned long rate,
 			}
 		}
 	} else {
-		for (i = 0; i < __clk_get_num_parents(mix_clk); i++) {
-			parent = clk_get_parent_by_index(mix_clk, i);
-			parent_rate = __clk_get_rate(parent);
+		for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+			parent = clk_hw_get_parent_by_index(hw, i);
+			parent_rate = clk_hw_get_rate(parent);
 			div_val_max = _get_maxdiv(mix);
 			for (j = 0; j < div_val_max; j++) {
 				div = _get_div(mix, j);
 				mix_rate = parent_rate / div;
-				gap = abs(mix_rate - rate);
+				gap = abs(mix_rate - req->rate);
 				if (parent_best == NULL || gap < gap_best) {
 					parent_best = parent;
 					parent_rate_best = parent_rate;
@@ -265,10 +260,14 @@ static long mmp_clk_mix_determine_rate(struct clk_hw *hw, unsigned long rate,
 	}
 
 found:
-	*best_parent_rate = parent_rate_best;
-	*best_parent_clk = __clk_get_hw(parent_best);
+	if (!parent_best)
+		return -EINVAL;
+
+	req->best_parent_rate = parent_rate_best;
+	req->best_parent_hw = parent_best;
+	req->rate = mix_rate_best;
 
-	return mix_rate_best;
+	return 0;
 }
 
 static int mmp_clk_mix_set_rate_and_parent(struct clk_hw *hw,
@@ -381,20 +380,19 @@ static int mmp_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct mmp_clk_mix_clk_table *item;
 	unsigned long parent_rate;
 	unsigned int best_divisor;
-	struct clk *mix_clk, *parent;
+	struct clk_hw *parent;
 	int i;
 
 	best_divisor = best_parent_rate / rate;
 
-	mix_clk = hw->clk;
 	if (mix->table) {
 		for (i = 0; i < mix->table_size; i++) {
 			item = &mix->table[i];
 			if (item->valid == 0)
 				continue;
-			parent = clk_get_parent_by_index(mix_clk,
+			parent = clk_hw_get_parent_by_index(hw,
 							item->parent_index);
-			parent_rate = __clk_get_rate(parent);
+			parent_rate = clk_hw_get_rate(parent);
 			if (parent_rate == best_parent_rate
 				&& item->divisor == best_divisor)
 				break;
@@ -407,13 +405,13 @@ static int mmp_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		else
 			return -EINVAL;
 	} else {
-		for (i = 0; i < __clk_get_num_parents(mix_clk); i++) {
-			parent = clk_get_parent_by_index(mix_clk, i);
-			parent_rate = __clk_get_rate(parent);
+		for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+			parent = clk_hw_get_parent_by_index(hw, i);
+			parent_rate = clk_hw_get_rate(parent);
 			if (parent_rate == best_parent_rate)
 				break;
 		}
-		if (i < __clk_get_num_parents(mix_clk))
+		if (i < clk_hw_get_num_parents(hw))
 			return _set_rate(mix, _get_mux_val(mix, i),
 					_get_div_val(mix, best_divisor), 1, 1);
 		else
@@ -468,20 +466,20 @@ struct clk *mmp_clk_register_mix(struct device *dev,
 	memcpy(&mix->reg_info, &config->reg_info, sizeof(config->reg_info));
 	if (config->table) {
 		table_bytes = sizeof(*config->table) * config->table_size;
-		mix->table = kzalloc(table_bytes, GFP_KERNEL);
+		mix->table = kmemdup(config->table, table_bytes, GFP_KERNEL);
 		if (!mix->table) {
 			pr_err("%s:%s: could not allocate mmp mix table\n",
 				__func__, name);
 			kfree(mix);
 			return ERR_PTR(-ENOMEM);
 		}
-		memcpy(mix->table, config->table, table_bytes);
 		mix->table_size = config->table_size;
 	}
 
 	if (config->mux_table) {
 		table_bytes = sizeof(u32) * num_parents;
-		mix->mux_table = kzalloc(table_bytes, GFP_KERNEL);
+		mix->mux_table = kmemdup(config->mux_table, table_bytes,
+					 GFP_KERNEL);
 		if (!mix->mux_table) {
 			pr_err("%s:%s: could not allocate mmp mix mux-table\n",
 				__func__, name);
@@ -489,7 +487,6 @@ struct clk *mmp_clk_register_mix(struct device *dev,
 			kfree(mix);
 			return ERR_PTR(-ENOMEM);
 		}
-		memcpy(mix->mux_table, config->mux_table, table_bytes);
 	}
 
 	mix->div_flags = config->div_flags;
diff --git a/drivers/clk/mmp/clk.c b/drivers/clk/mmp/clk.c
index cf038ef54c59..61893fe73251 100644
--- a/drivers/clk/mmp/clk.c
+++ b/drivers/clk/mmp/clk.c
@@ -1,7 +1,6 @@
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
diff --git a/drivers/clk/mvebu/clk-cpu.c b/drivers/clk/mvebu/clk-cpu.c
index 3821a88077ea..5837eb8a212f 100644
--- a/drivers/clk/mvebu/clk-cpu.c
+++ b/drivers/clk/mvebu/clk-cpu.c
@@ -10,7 +10,8 @@
  * warranty of any kind, whether express or implied.
  */
 #include <linux/kernel.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/io.h>
@@ -120,7 +121,7 @@ static int clk_cpu_on_set_rate(struct clk_hw *hwclk, unsigned long rate,
 	if (!cpuclk->pmu_dfs)
 		return -ENODEV;
 
-	cur_rate = __clk_get_rate(hwclk->clk);
+	cur_rate = clk_hw_get_rate(hwclk);
 
 	reg = readl(cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_CTRL2_OFFSET);
 	fabric_div = (reg >> SYS_CTRL_CLK_DIVIDER_CTRL2_NBCLK_RATIO_SHIFT) &
@@ -196,7 +197,6 @@ static void __init of_cpu_clk_setup(struct device_node *node)
 	for_each_node_by_type(dn, "cpu") {
 		struct clk_init_data init;
 		struct clk *clk;
-		struct clk *parent_clk;
 		char *clk_name = kzalloc(5, GFP_KERNEL);
 		int cpu, err;
 
@@ -208,9 +208,8 @@ static void __init of_cpu_clk_setup(struct device_node *node)
 			goto bail_out;
 
 		sprintf(clk_name, "cpu%d", cpu);
-		parent_clk = of_clk_get(node, 0);
 
-		cpuclk[cpu].parent_name = __clk_get_name(parent_clk);
+		cpuclk[cpu].parent_name = of_clk_get_parent_name(node, 0);
 		cpuclk[cpu].clk_name = clk_name;
 		cpuclk[cpu].cpu = cpu;
 		cpuclk[cpu].reg_base = clock_complex_base;
diff --git a/drivers/clk/mvebu/common.c b/drivers/clk/mvebu/common.c
index 15b370ff3748..4a22429cd7a2 100644
--- a/drivers/clk/mvebu/common.c
+++ b/drivers/clk/mvebu/common.c
@@ -13,8 +13,8 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
diff --git a/drivers/clk/mxs/clk-div.c b/drivers/clk/mxs/clk-div.c
index 90e1da93877e..049ee27d5a22 100644
--- a/drivers/clk/mxs/clk-div.c
+++ b/drivers/clk/mxs/clk-div.c
@@ -9,7 +9,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/mxs/clk-frac.c b/drivers/clk/mxs/clk-frac.c
index e6aa6b567d68..73f0240569ac 100644
--- a/drivers/clk/mxs/clk-frac.c
+++ b/drivers/clk/mxs/clk-frac.c
@@ -9,7 +9,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/drivers/clk/mxs/clk-imx23.c b/drivers/clk/mxs/clk-imx23.c
index 32216f9b7f03..f01876af6bb8 100644
--- a/drivers/clk/mxs/clk-imx23.c
+++ b/drivers/clk/mxs/clk-imx23.c
@@ -9,9 +9,8 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk/mxs.h>
-#include <linux/clkdev.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/init.h>
diff --git a/drivers/clk/mxs/clk-imx28.c b/drivers/clk/mxs/clk-imx28.c
index a68670868baa..6b572b759f9a 100644
--- a/drivers/clk/mxs/clk-imx28.c
+++ b/drivers/clk/mxs/clk-imx28.c
@@ -9,9 +9,9 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk/mxs.h>
 #include <linux/clkdev.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/init.h>
diff --git a/drivers/clk/mxs/clk-pll.c b/drivers/clk/mxs/clk-pll.c
index fadae41833ec..d4ca79a868e0 100644
--- a/drivers/clk/mxs/clk-pll.c
+++ b/drivers/clk/mxs/clk-pll.c
@@ -9,7 +9,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/err.h>
diff --git a/drivers/clk/mxs/clk-ref.c b/drivers/clk/mxs/clk-ref.c
index 4adeed6c2f94..495f99b7965e 100644
--- a/drivers/clk/mxs/clk-ref.c
+++ b/drivers/clk/mxs/clk-ref.c
@@ -9,7 +9,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/drivers/clk/mxs/clk.h b/drivers/clk/mxs/clk.h
index f07d821dd75d..a4590956d2a2 100644
--- a/drivers/clk/mxs/clk.h
+++ b/drivers/clk/mxs/clk.h
@@ -12,7 +12,8 @@
 #ifndef __MXS_CLK_H
 #define __MXS_CLK_H
 
-#include <linux/clk.h>
+struct clk;
+
 #include <linux/clk-provider.h>
 #include <linux/spinlock.h>
 
diff --git a/drivers/clk/nxp/clk-lpc18xx-cgu.c b/drivers/clk/nxp/clk-lpc18xx-cgu.c
index 81e9e1c788f4..e0a3cb8970ab 100644
--- a/drivers/clk/nxp/clk-lpc18xx-cgu.c
+++ b/drivers/clk/nxp/clk-lpc18xx-cgu.c
@@ -8,7 +8,6 @@
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
diff --git a/drivers/clk/pistachio/clk-pistachio.c b/drivers/clk/pistachio/clk-pistachio.c
index 8c0fe8828f99..c4ceb5eaf46c 100644
--- a/drivers/clk/pistachio/clk-pistachio.c
+++ b/drivers/clk/pistachio/clk-pistachio.c
@@ -159,9 +159,15 @@ PNAME(mux_debug) = { "mips_pll_mux", "rpu_v_pll_mux",
 		     "wifi_pll_mux", "bt_pll_mux" };
 static u32 mux_debug_idx[] = { 0x0, 0x1, 0x2, 0x4, 0x8, 0x10 };
 
-static unsigned int pistachio_critical_clks[] __initdata = {
-	CLK_MIPS,
-	CLK_PERIPH_SYS,
+static unsigned int pistachio_critical_clks_core[] __initdata = {
+	CLK_MIPS
+};
+
+static unsigned int pistachio_critical_clks_sys[] __initdata = {
+	PERIPH_CLK_SYS,
+	PERIPH_CLK_SYS_BUS,
+	PERIPH_CLK_DDR,
+	PERIPH_CLK_ROM,
 };
 
 static void __init pistachio_clk_init(struct device_node *np)
@@ -193,8 +199,8 @@ static void __init pistachio_clk_init(struct device_node *np)
 
 	pistachio_clk_register_provider(p);
 
-	pistachio_clk_force_enable(p, pistachio_critical_clks,
-				   ARRAY_SIZE(pistachio_critical_clks));
+	pistachio_clk_force_enable(p, pistachio_critical_clks_core,
+				   ARRAY_SIZE(pistachio_critical_clks_core));
 }
 CLK_OF_DECLARE(pistachio_clk, "img,pistachio-clk", pistachio_clk_init);
 
@@ -261,6 +267,9 @@ static void __init pistachio_clk_periph_init(struct device_node *np)
 				    ARRAY_SIZE(pistachio_periph_gates));
 
 	pistachio_clk_register_provider(p);
+
+	pistachio_clk_force_enable(p, pistachio_critical_clks_sys,
+				   ARRAY_SIZE(pistachio_critical_clks_sys));
 }
 CLK_OF_DECLARE(pistachio_clk_periph, "img,pistachio-clk-periph",
 	       pistachio_clk_periph_init);
diff --git a/drivers/clk/pistachio/clk-pll.c b/drivers/clk/pistachio/clk-pll.c
index e17dada0dd21..7e8daab9025b 100644
--- a/drivers/clk/pistachio/clk-pll.c
+++ b/drivers/clk/pistachio/clk-pll.c
@@ -65,6 +65,12 @@
 #define MIN_OUTPUT_FRAC			12000000UL
 #define MAX_OUTPUT_FRAC			1600000000UL
 
+/* Fractional PLL operating modes */
+enum pll_mode {
+	PLL_MODE_FRAC,
+	PLL_MODE_INT,
+};
+
 struct pistachio_clk_pll {
 	struct clk_hw hw;
 	void __iomem *base;
@@ -88,12 +94,10 @@ static inline void pll_lock(struct pistachio_clk_pll *pll)
 		cpu_relax();
 }
 
-static inline u32 do_div_round_closest(u64 dividend, u32 divisor)
+static inline u64 do_div_round_closest(u64 dividend, u64 divisor)
 {
 	dividend += divisor / 2;
-	do_div(dividend, divisor);
-
-	return dividend;
+	return div64_u64(dividend, divisor);
 }
 
 static inline struct pistachio_clk_pll *to_pistachio_pll(struct clk_hw *hw)
@@ -101,6 +105,29 @@ static inline struct pistachio_clk_pll *to_pistachio_pll(struct clk_hw *hw)
 	return container_of(hw, struct pistachio_clk_pll, hw);
 }
 
+static inline enum pll_mode pll_frac_get_mode(struct clk_hw *hw)
+{
+	struct pistachio_clk_pll *pll = to_pistachio_pll(hw);
+	u32 val;
+
+	val = pll_readl(pll, PLL_CTRL3) & PLL_FRAC_CTRL3_DSMPD;
+	return val ? PLL_MODE_INT : PLL_MODE_FRAC;
+}
+
+static inline void pll_frac_set_mode(struct clk_hw *hw, enum pll_mode mode)
+{
+	struct pistachio_clk_pll *pll = to_pistachio_pll(hw);
+	u32 val;
+
+	val = pll_readl(pll, PLL_CTRL3);
+	if (mode == PLL_MODE_INT)
+		val |= PLL_FRAC_CTRL3_DSMPD | PLL_FRAC_CTRL3_DACPD;
+	else
+		val &= ~(PLL_FRAC_CTRL3_DSMPD | PLL_FRAC_CTRL3_DACPD);
+
+	pll_writel(pll, val, PLL_CTRL3);
+}
+
 static struct pistachio_pll_rate_table *
 pll_get_params(struct pistachio_clk_pll *pll, unsigned long fref,
 	       unsigned long fout)
@@ -136,8 +163,7 @@ static int pll_gf40lp_frac_enable(struct clk_hw *hw)
 	u32 val;
 
 	val = pll_readl(pll, PLL_CTRL3);
-	val &= ~(PLL_FRAC_CTRL3_PD | PLL_FRAC_CTRL3_DACPD |
-		 PLL_FRAC_CTRL3_DSMPD | PLL_FRAC_CTRL3_FOUTPOSTDIVPD |
+	val &= ~(PLL_FRAC_CTRL3_PD | PLL_FRAC_CTRL3_FOUTPOSTDIVPD |
 		 PLL_FRAC_CTRL3_FOUT4PHASEPD | PLL_FRAC_CTRL3_FOUTVCOPD);
 	pll_writel(pll, val, PLL_CTRL3);
 
@@ -173,8 +199,8 @@ static int pll_gf40lp_frac_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct pistachio_clk_pll *pll = to_pistachio_pll(hw);
 	struct pistachio_pll_rate_table *params;
 	int enabled = pll_gf40lp_frac_is_enabled(hw);
-	u32 val, vco, old_postdiv1, old_postdiv2;
-	const char *name = __clk_get_name(hw->clk);
+	u64 val, vco, old_postdiv1, old_postdiv2;
+	const char *name = clk_hw_get_name(hw);
 
 	if (rate < MIN_OUTPUT_FRAC || rate > MAX_OUTPUT_FRAC)
 		return -EINVAL;
@@ -183,17 +209,21 @@ static int pll_gf40lp_frac_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!params || !params->refdiv)
 		return -EINVAL;
 
-	vco = params->fref * params->fbdiv / params->refdiv;
+	/* calculate vco */
+	vco = params->fref;
+	vco *= (params->fbdiv << 24) + params->frac;
+	vco = div64_u64(vco, params->refdiv << 24);
+
 	if (vco < MIN_VCO_FRAC_FRAC || vco > MAX_VCO_FRAC_FRAC)
-		pr_warn("%s: VCO %u is out of range %lu..%lu\n", name, vco,
+		pr_warn("%s: VCO %llu is out of range %lu..%lu\n", name, vco,
 			MIN_VCO_FRAC_FRAC, MAX_VCO_FRAC_FRAC);
 
-	val = params->fref / params->refdiv;
+	val = div64_u64(params->fref, params->refdiv);
 	if (val < MIN_PFD)
-		pr_warn("%s: PFD %u is too low (min %lu)\n",
+		pr_warn("%s: PFD %llu is too low (min %lu)\n",
 			name, val, MIN_PFD);
 	if (val > vco / 16)
-		pr_warn("%s: PFD %u is too high (max %u)\n",
+		pr_warn("%s: PFD %llu is too high (max %llu)\n",
 			name, val, vco / 16);
 
 	val = pll_readl(pll, PLL_CTRL1);
@@ -227,6 +257,12 @@ static int pll_gf40lp_frac_set_rate(struct clk_hw *hw, unsigned long rate,
 		(params->postdiv2 << PLL_FRAC_CTRL2_POSTDIV2_SHIFT);
 	pll_writel(pll, val, PLL_CTRL2);
 
+	/* set operating mode */
+	if (params->frac)
+		pll_frac_set_mode(hw, PLL_MODE_FRAC);
+	else
+		pll_frac_set_mode(hw, PLL_MODE_INT);
+
 	if (enabled)
 		pll_lock(pll);
 
@@ -237,8 +273,7 @@ static unsigned long pll_gf40lp_frac_recalc_rate(struct clk_hw *hw,
 						 unsigned long parent_rate)
 {
 	struct pistachio_clk_pll *pll = to_pistachio_pll(hw);
-	u32 val, prediv, fbdiv, frac, postdiv1, postdiv2;
-	u64 rate = parent_rate;
+	u64 val, prediv, fbdiv, frac, postdiv1, postdiv2, rate;
 
 	val = pll_readl(pll, PLL_CTRL1);
 	prediv = (val >> PLL_CTRL1_REFDIV_SHIFT) & PLL_CTRL1_REFDIV_MASK;
@@ -251,7 +286,13 @@ static unsigned long pll_gf40lp_frac_recalc_rate(struct clk_hw *hw,
 		PLL_FRAC_CTRL2_POSTDIV2_MASK;
 	frac = (val >> PLL_FRAC_CTRL2_FRAC_SHIFT) & PLL_FRAC_CTRL2_FRAC_MASK;
 
-	rate *= (fbdiv << 24) + frac;
+	/* get operating mode (int/frac) and calculate rate accordingly */
+	rate = parent_rate;
+	if (pll_frac_get_mode(hw) == PLL_MODE_FRAC)
+		rate *= (fbdiv << 24) + frac;
+	else
+		rate *= (fbdiv << 24);
+
 	rate = do_div_round_closest(rate, (prediv * postdiv1 * postdiv2) << 24);
 
 	return rate;
@@ -279,7 +320,7 @@ static int pll_gf40lp_laint_enable(struct clk_hw *hw)
 	u32 val;
 
 	val = pll_readl(pll, PLL_CTRL1);
-	val &= ~(PLL_INT_CTRL1_PD | PLL_INT_CTRL1_DSMPD |
+	val &= ~(PLL_INT_CTRL1_PD |
 		 PLL_INT_CTRL1_FOUTPOSTDIVPD | PLL_INT_CTRL1_FOUTVCOPD);
 	pll_writel(pll, val, PLL_CTRL1);
 
@@ -316,7 +357,7 @@ static int pll_gf40lp_laint_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct pistachio_pll_rate_table *params;
 	int enabled = pll_gf40lp_laint_is_enabled(hw);
 	u32 val, vco, old_postdiv1, old_postdiv2;
-	const char *name = __clk_get_name(hw->clk);
+	const char *name = clk_hw_get_name(hw);
 
 	if (rate < MIN_OUTPUT_LA || rate > MAX_OUTPUT_LA)
 		return -EINVAL;
@@ -325,12 +366,12 @@ static int pll_gf40lp_laint_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!params || !params->refdiv)
 		return -EINVAL;
 
-	vco = params->fref * params->fbdiv / params->refdiv;
+	vco = div_u64(params->fref * params->fbdiv, params->refdiv);
 	if (vco < MIN_VCO_LA || vco > MAX_VCO_LA)
 		pr_warn("%s: VCO %u is out of range %lu..%lu\n", name, vco,
 			MIN_VCO_LA, MAX_VCO_LA);
 
-	val = params->fref / params->refdiv;
+	val = div_u64(params->fref, params->refdiv);
 	if (val < MIN_PFD)
 		pr_warn("%s: PFD %u is too low (min %lu)\n",
 			name, val, MIN_PFD);
diff --git a/drivers/clk/pistachio/clk.c b/drivers/clk/pistachio/clk.c
index 85faa83e1bd7..698cad4f509e 100644
--- a/drivers/clk/pistachio/clk.c
+++ b/drivers/clk/pistachio/clk.c
@@ -6,6 +6,7 @@
  * version 2, as published by the Free Software Foundation.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
diff --git a/drivers/clk/pistachio/clk.h b/drivers/clk/pistachio/clk.h
index 52fabbc24624..8d45178dbde3 100644
--- a/drivers/clk/pistachio/clk.h
+++ b/drivers/clk/pistachio/clk.h
@@ -95,13 +95,13 @@ struct pistachio_fixed_factor {
 	}
 
 struct pistachio_pll_rate_table {
-	unsigned long fref;
-	unsigned long fout;
-	unsigned int refdiv;
-	unsigned int fbdiv;
-	unsigned int postdiv1;
-	unsigned int postdiv2;
-	unsigned int frac;
+	unsigned long long fref;
+	unsigned long long fout;
+	unsigned long long refdiv;
+	unsigned long long fbdiv;
+	unsigned long long postdiv1;
+	unsigned long long postdiv2;
+	unsigned long long frac;
 };
 
 enum pistachio_pll_type {
diff --git a/drivers/clk/pxa/clk-pxa25x.c b/drivers/clk/pxa/clk-pxa25x.c
index 6cd88d963a7f..542e45ef5087 100644
--- a/drivers/clk/pxa/clk-pxa25x.c
+++ b/drivers/clk/pxa/clk-pxa25x.c
@@ -79,7 +79,7 @@ unsigned int pxa25x_get_clk_frequency_khz(int info)
 			clks[3] / 1000000, (clks[3] % 1000000) / 10000);
 	}
 
-	return (unsigned int)clks[0];
+	return (unsigned int)clks[0] / KHz;
 }
 
 static unsigned long clk_pxa25x_memory_get_rate(struct clk_hw *hw,
diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c
index 9a31b77eed23..5b82d30baf9f 100644
--- a/drivers/clk/pxa/clk-pxa27x.c
+++ b/drivers/clk/pxa/clk-pxa27x.c
@@ -80,7 +80,7 @@ unsigned int pxa27x_get_clk_frequency_khz(int info)
 		pr_info("System bus clock: %ld.%02ldMHz\n",
 			clks[4] / 1000000, (clks[4] % 1000000) / 10000);
 	}
-	return (unsigned int)clks[0];
+	return (unsigned int)clks[0] / KHz;
 }
 
 bool pxa27x_is_ppll_disabled(void)
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 4b93a1efb36d..4af4eed5f89f 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -78,7 +78,7 @@ unsigned int pxa3xx_get_clk_frequency_khz(int info)
 		pr_info("System bus clock: %ld.%02ldMHz\n",
 			clks[4] / 1000000, (clks[4] % 1000000) / 10000);
 	}
-	return (unsigned int)clks[0];
+	return (unsigned int)clks[0] / KHz;
 }
 
 static unsigned long clk_pxa3xx_ac97_get_rate(struct clk_hw *hw,
@@ -126,7 +126,7 @@ PARENTS(pxa3xx_ac97_bus) = { "ring_osc_60mhz", "ac97" };
 PARENTS(pxa3xx_sbus) = { "ring_osc_60mhz", "system_bus" };
 PARENTS(pxa3xx_smemcbus) = { "ring_osc_60mhz", "smemc" };
 
-#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENA : &CKENB)
+#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENB : &CKENA)
 #define PXA3XX_CKEN(dev_id, con_id, parents, mult_lp, div_lp, mult_hp,	\
 		    div_hp, bit, is_lp, flags)				\
 	PXA_CKEN(dev_id, con_id, bit, parents, mult_lp, div_lp,		\
diff --git a/drivers/clk/qcom/clk-branch.c b/drivers/clk/qcom/clk-branch.c
index 6b4d2bcb1a53..26f7af315066 100644
--- a/drivers/clk/qcom/clk-branch.c
+++ b/drivers/clk/qcom/clk-branch.c
@@ -75,7 +75,7 @@ static int clk_branch_wait(const struct clk_branch *br, bool enabling,
 		bool (check_halt)(const struct clk_branch *, bool))
 {
 	bool voted = br->halt_check & BRANCH_VOTED;
-	const char *name = __clk_get_name(br->clkr.hw.clk);
+	const char *name = clk_hw_get_name(&br->clkr.hw);
 
 	/* Skip checking halt bit if the clock is in hardware gated mode */
 	if (clk_branch_in_hwcg_mode(br))
diff --git a/drivers/clk/qcom/clk-pll.c b/drivers/clk/qcom/clk-pll.c
index 245d5063a385..5b940d629045 100644
--- a/drivers/clk/qcom/clk-pll.c
+++ b/drivers/clk/qcom/clk-pll.c
@@ -135,19 +135,19 @@ struct pll_freq_tbl *find_freq(const struct pll_freq_tbl *f, unsigned long rate)
 	return NULL;
 }
 
-static long
-clk_pll_determine_rate(struct clk_hw *hw, unsigned long rate,
-		       unsigned long min_rate, unsigned long max_rate,
-		       unsigned long *p_rate, struct clk_hw **p)
+static int
+clk_pll_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
 	const struct pll_freq_tbl *f;
 
-	f = find_freq(pll->freq_tbl, rate);
+	f = find_freq(pll->freq_tbl, req->rate);
 	if (!f)
-		return clk_pll_recalc_rate(hw, *p_rate);
+		req->rate = clk_pll_recalc_rate(hw, req->best_parent_rate);
+	else
+		req->rate = f->freq;
 
-	return f->freq;
+	return 0;
 }
 
 static int
@@ -194,7 +194,7 @@ static int wait_for_pll(struct clk_pll *pll)
 	u32 val;
 	int count;
 	int ret;
-	const char *name = __clk_get_name(pll->clkr.hw.clk);
+	const char *name = clk_hw_get_name(&pll->clkr.hw);
 
 	/* Wait for pll to enable. */
 	for (count = 200; count > 0; count--) {
@@ -213,7 +213,7 @@ static int wait_for_pll(struct clk_pll *pll)
 static int clk_pll_vote_enable(struct clk_hw *hw)
 {
 	int ret;
-	struct clk_pll *p = to_clk_pll(__clk_get_hw(__clk_get_parent(hw->clk)));
+	struct clk_pll *p = to_clk_pll(clk_hw_get_parent(hw));
 
 	ret = clk_enable_regmap(hw);
 	if (ret)
@@ -292,3 +292,78 @@ void clk_pll_configure_sr_hpm_lp(struct clk_pll *pll, struct regmap *regmap,
 		clk_pll_set_fsm_mode(pll, regmap, 0);
 }
 EXPORT_SYMBOL_GPL(clk_pll_configure_sr_hpm_lp);
+
+static int clk_pll_sr2_enable(struct clk_hw *hw)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	int ret;
+	u32 mode;
+
+	ret = regmap_read(pll->clkr.regmap, pll->mode_reg, &mode);
+	if (ret)
+		return ret;
+
+	/* Disable PLL bypass mode. */
+	ret = regmap_update_bits(pll->clkr.regmap, pll->mode_reg, PLL_BYPASSNL,
+				 PLL_BYPASSNL);
+	if (ret)
+		return ret;
+
+	/*
+	 * H/W requires a 5us delay between disabling the bypass and
+	 * de-asserting the reset. Delay 10us just to be safe.
+	 */
+	udelay(10);
+
+	/* De-assert active-low PLL reset. */
+	ret = regmap_update_bits(pll->clkr.regmap, pll->mode_reg, PLL_RESET_N,
+				 PLL_RESET_N);
+	if (ret)
+		return ret;
+
+	ret = wait_for_pll(pll);
+	if (ret)
+		return ret;
+
+	/* Enable PLL output. */
+	return regmap_update_bits(pll->clkr.regmap, pll->mode_reg, PLL_OUTCTRL,
+				 PLL_OUTCTRL);
+}
+
+static int
+clk_pll_sr2_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long prate)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	const struct pll_freq_tbl *f;
+	bool enabled;
+	u32 mode;
+	u32 enable_mask = PLL_OUTCTRL | PLL_BYPASSNL | PLL_RESET_N;
+
+	f = find_freq(pll->freq_tbl, rate);
+	if (!f)
+		return -EINVAL;
+
+	regmap_read(pll->clkr.regmap, pll->mode_reg, &mode);
+	enabled = (mode & enable_mask) == enable_mask;
+
+	if (enabled)
+		clk_pll_disable(hw);
+
+	regmap_update_bits(pll->clkr.regmap, pll->l_reg, 0x3ff, f->l);
+	regmap_update_bits(pll->clkr.regmap, pll->m_reg, 0x7ffff, f->m);
+	regmap_update_bits(pll->clkr.regmap, pll->n_reg, 0x7ffff, f->n);
+
+	if (enabled)
+		clk_pll_sr2_enable(hw);
+
+	return 0;
+}
+
+const struct clk_ops clk_pll_sr2_ops = {
+	.enable = clk_pll_sr2_enable,
+	.disable = clk_pll_disable,
+	.set_rate = clk_pll_sr2_set_rate,
+	.recalc_rate = clk_pll_recalc_rate,
+	.determine_rate = clk_pll_determine_rate,
+};
+EXPORT_SYMBOL_GPL(clk_pll_sr2_ops);
diff --git a/drivers/clk/qcom/clk-pll.h b/drivers/clk/qcom/clk-pll.h
index c9c0cda306d0..ffd0c63bddbc 100644
--- a/drivers/clk/qcom/clk-pll.h
+++ b/drivers/clk/qcom/clk-pll.h
@@ -62,6 +62,7 @@ struct clk_pll {
 
 extern const struct clk_ops clk_pll_ops;
 extern const struct clk_ops clk_pll_vote_ops;
+extern const struct clk_ops clk_pll_sr2_ops;
 
 #define to_clk_pll(_hw) container_of(to_clk_regmap(_hw), struct clk_pll, clkr)
 
diff --git a/drivers/clk/qcom/clk-rcg.c b/drivers/clk/qcom/clk-rcg.c
index 7b3d62674203..bccedc4b5756 100644
--- a/drivers/clk/qcom/clk-rcg.c
+++ b/drivers/clk/qcom/clk-rcg.c
@@ -45,7 +45,7 @@ static u32 src_to_ns(struct src_sel *s, u8 src, u32 ns)
 static u8 clk_rcg_get_parent(struct clk_hw *hw)
 {
 	struct clk_rcg *rcg = to_clk_rcg(hw);
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 	u32 ns;
 	int i, ret;
 
@@ -59,7 +59,7 @@ static u8 clk_rcg_get_parent(struct clk_hw *hw)
 
 err:
 	pr_debug("%s: Clock %s has invalid parent, using default.\n",
-		 __func__, __clk_get_name(hw->clk));
+		 __func__, clk_hw_get_name(hw));
 	return 0;
 }
 
@@ -72,7 +72,7 @@ static int reg_to_bank(struct clk_dyn_rcg *rcg, u32 bank)
 static u8 clk_dyn_rcg_get_parent(struct clk_hw *hw)
 {
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 	u32 ns, reg;
 	int bank;
 	int i, ret;
@@ -95,7 +95,7 @@ static u8 clk_dyn_rcg_get_parent(struct clk_hw *hw)
 
 err:
 	pr_debug("%s: Clock %s has invalid parent, using default.\n",
-		 __func__, __clk_get_name(hw->clk));
+		 __func__, clk_hw_get_name(hw));
 	return 0;
 }
 
@@ -404,14 +404,12 @@ clk_dyn_rcg_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	return calc_rate(parent_rate, m, n, mode, pre_div);
 }
 
-static long _freq_tbl_determine_rate(struct clk_hw *hw,
-		const struct freq_tbl *f, unsigned long rate,
-		unsigned long min_rate, unsigned long max_rate,
-		unsigned long *p_rate, struct clk_hw **p_hw,
+static int _freq_tbl_determine_rate(struct clk_hw *hw, const struct freq_tbl *f,
+		struct clk_rate_request *req,
 		const struct parent_map *parent_map)
 {
-	unsigned long clk_flags;
-	struct clk *p;
+	unsigned long clk_flags, rate = req->rate;
+	struct clk_hw *p;
 	int index;
 
 	f = qcom_find_freq(f, rate);
@@ -422,8 +420,8 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 	if (index < 0)
 		return index;
 
-	clk_flags = __clk_get_flags(hw->clk);
-	p = clk_get_parent_by_index(hw->clk, index);
+	clk_flags = clk_hw_get_flags(hw);
+	p = clk_hw_get_parent_by_index(hw, index);
 	if (clk_flags & CLK_SET_RATE_PARENT) {
 		rate = rate * f->pre_div;
 		if (f->n) {
@@ -433,27 +431,26 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 			rate = tmp;
 		}
 	} else {
-		rate =  __clk_get_rate(p);
+		rate =  clk_hw_get_rate(p);
 	}
-	*p_hw = __clk_get_hw(p);
-	*p_rate = rate;
+	req->best_parent_hw = p;
+	req->best_parent_rate = rate;
+	req->rate = f->freq;
 
-	return f->freq;
+	return 0;
 }
 
-static long clk_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long min_rate, unsigned long max_rate,
-		unsigned long *p_rate, struct clk_hw **p)
+static int clk_rcg_determine_rate(struct clk_hw *hw,
+				  struct clk_rate_request *req)
 {
 	struct clk_rcg *rcg = to_clk_rcg(hw);
 
-	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, rate, min_rate,
-			max_rate, p_rate, p, rcg->s.parent_map);
+	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, req,
+					rcg->s.parent_map);
 }
 
-static long clk_dyn_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long min_rate, unsigned long max_rate,
-		unsigned long *p_rate, struct clk_hw **p)
+static int clk_dyn_rcg_determine_rate(struct clk_hw *hw,
+				      struct clk_rate_request *req)
 {
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
 	u32 reg;
@@ -464,24 +461,22 @@ static long clk_dyn_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
 	bank = reg_to_bank(rcg, reg);
 	s = &rcg->s[bank];
 
-	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, rate, min_rate,
-			max_rate, p_rate, p, s->parent_map);
+	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, req, s->parent_map);
 }
 
-static long clk_rcg_bypass_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long min_rate, unsigned long max_rate,
-		unsigned long *p_rate, struct clk_hw **p_hw)
+static int clk_rcg_bypass_determine_rate(struct clk_hw *hw,
+					 struct clk_rate_request *req)
 {
 	struct clk_rcg *rcg = to_clk_rcg(hw);
 	const struct freq_tbl *f = rcg->freq_tbl;
-	struct clk *p;
+	struct clk_hw *p;
 	int index = qcom_find_src_index(hw, rcg->s.parent_map, f->src);
 
-	p = clk_get_parent_by_index(hw->clk, index);
-	*p_hw = __clk_get_hw(p);
-	*p_rate = __clk_round_rate(p, rate);
+	req->best_parent_hw = p = clk_hw_get_parent_by_index(hw, index);
+	req->best_parent_rate = clk_hw_round_rate(p, req->rate);
+	req->rate = req->best_parent_rate;
 
-	return *p_rate;
+	return 0;
 }
 
 static int __clk_rcg_set_rate(struct clk_rcg *rcg, const struct freq_tbl *f)
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index b95d17fbb8d7..9aec1761fd29 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -63,7 +63,7 @@ static int clk_rcg2_is_enabled(struct clk_hw *hw)
 static u8 clk_rcg2_get_parent(struct clk_hw *hw)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 	u32 cfg;
 	int i, ret;
 
@@ -80,7 +80,7 @@ static u8 clk_rcg2_get_parent(struct clk_hw *hw)
 
 err:
 	pr_debug("%s: Clock %s has invalid parent, using default.\n",
-		 __func__, __clk_get_name(hw->clk));
+		 __func__, clk_hw_get_name(hw));
 	return 0;
 }
 
@@ -89,7 +89,7 @@ static int update_config(struct clk_rcg2 *rcg)
 	int count, ret;
 	u32 cmd;
 	struct clk_hw *hw = &rcg->clkr.hw;
-	const char *name = __clk_get_name(hw->clk);
+	const char *name = clk_hw_get_name(hw);
 
 	ret = regmap_update_bits(rcg->clkr.regmap, rcg->cmd_rcgr + CMD_REG,
 				 CMD_UPDATE, CMD_UPDATE);
@@ -176,12 +176,11 @@ clk_rcg2_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	return calc_rate(parent_rate, m, n, mode, hid_div);
 }
 
-static long _freq_tbl_determine_rate(struct clk_hw *hw,
-		const struct freq_tbl *f, unsigned long rate,
-		unsigned long *p_rate, struct clk_hw **p_hw)
+static int _freq_tbl_determine_rate(struct clk_hw *hw,
+		const struct freq_tbl *f, struct clk_rate_request *req)
 {
-	unsigned long clk_flags;
-	struct clk *p;
+	unsigned long clk_flags, rate = req->rate;
+	struct clk_hw *p;
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	int index;
 
@@ -193,8 +192,8 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 	if (index < 0)
 		return index;
 
-	clk_flags = __clk_get_flags(hw->clk);
-	p = clk_get_parent_by_index(hw->clk, index);
+	clk_flags = clk_hw_get_flags(hw);
+	p = clk_hw_get_parent_by_index(hw, index);
 	if (clk_flags & CLK_SET_RATE_PARENT) {
 		if (f->pre_div) {
 			rate /= 2;
@@ -208,21 +207,21 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 			rate = tmp;
 		}
 	} else {
-		rate =  __clk_get_rate(p);
+		rate =  clk_hw_get_rate(p);
 	}
-	*p_hw = __clk_get_hw(p);
-	*p_rate = rate;
+	req->best_parent_hw = p;
+	req->best_parent_rate = rate;
+	req->rate = f->freq;
 
-	return f->freq;
+	return 0;
 }
 
-static long clk_rcg2_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long min_rate, unsigned long max_rate,
-		unsigned long *p_rate, struct clk_hw **p)
+static int clk_rcg2_determine_rate(struct clk_hw *hw,
+				   struct clk_rate_request *req)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 
-	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, rate, p_rate, p);
+	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, req);
 }
 
 static int clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f)
@@ -374,35 +373,33 @@ static int clk_edp_pixel_set_rate_and_parent(struct clk_hw *hw,
 	return clk_edp_pixel_set_rate(hw, rate, parent_rate);
 }
 
-static long clk_edp_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
-				 unsigned long min_rate,
-				 unsigned long max_rate,
-				 unsigned long *p_rate, struct clk_hw **p)
+static int clk_edp_pixel_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	const struct freq_tbl *f = rcg->freq_tbl;
 	const struct frac_entry *frac;
 	int delta = 100000;
-	s64 src_rate = *p_rate;
 	s64 request;
 	u32 mask = BIT(rcg->hid_width) - 1;
 	u32 hid_div;
 	int index = qcom_find_src_index(hw, rcg->parent_map, f->src);
 
 	/* Force the correct parent */
-	*p = __clk_get_hw(clk_get_parent_by_index(hw->clk, index));
+	req->best_parent_hw = clk_hw_get_parent_by_index(hw, index);
+	req->best_parent_rate = clk_hw_get_rate(req->best_parent_hw);
 
-	if (src_rate == 810000000)
+	if (req->best_parent_rate == 810000000)
 		frac = frac_table_810m;
 	else
 		frac = frac_table_675m;
 
 	for (; frac->num; frac++) {
-		request = rate;
+		request = req->rate;
 		request *= frac->den;
 		request = div_s64(request, frac->num);
-		if ((src_rate < (request - delta)) ||
-		    (src_rate > (request + delta)))
+		if ((req->best_parent_rate < (request - delta)) ||
+		    (req->best_parent_rate > (request + delta)))
 			continue;
 
 		regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG,
@@ -410,8 +407,10 @@ static long clk_edp_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
 		hid_div >>= CFG_SRC_DIV_SHIFT;
 		hid_div &= mask;
 
-		return calc_rate(src_rate, frac->num, frac->den, !!frac->den,
-				 hid_div);
+		req->rate = calc_rate(req->best_parent_rate,
+				      frac->num, frac->den,
+				      !!frac->den, hid_div);
+		return 0;
 	}
 
 	return -EINVAL;
@@ -428,28 +427,28 @@ const struct clk_ops clk_edp_pixel_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_edp_pixel_ops);
 
-static long clk_byte_determine_rate(struct clk_hw *hw, unsigned long rate,
-			 unsigned long min_rate, unsigned long max_rate,
-			 unsigned long *p_rate, struct clk_hw **p_hw)
+static int clk_byte_determine_rate(struct clk_hw *hw,
+				   struct clk_rate_request *req)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	const struct freq_tbl *f = rcg->freq_tbl;
 	int index = qcom_find_src_index(hw, rcg->parent_map, f->src);
 	unsigned long parent_rate, div;
 	u32 mask = BIT(rcg->hid_width) - 1;
-	struct clk *p;
+	struct clk_hw *p;
 
-	if (rate == 0)
+	if (req->rate == 0)
 		return -EINVAL;
 
-	p = clk_get_parent_by_index(hw->clk, index);
-	*p_hw = __clk_get_hw(p);
-	*p_rate = parent_rate = __clk_round_rate(p, rate);
+	req->best_parent_hw = p = clk_hw_get_parent_by_index(hw, index);
+	req->best_parent_rate = parent_rate = clk_hw_round_rate(p, req->rate);
 
-	div = DIV_ROUND_UP((2 * parent_rate), rate) - 1;
+	div = DIV_ROUND_UP((2 * parent_rate), req->rate) - 1;
 	div = min_t(u32, div, mask);
 
-	return calc_rate(parent_rate, 0, 0, 0, div);
+	req->rate = calc_rate(parent_rate, 0, 0, 0, div);
+
+	return 0;
 }
 
 static int clk_byte_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -494,10 +493,8 @@ static const struct frac_entry frac_table_pixel[] = {
 	{ }
 };
 
-static long clk_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
-				 unsigned long min_rate,
-				 unsigned long max_rate,
-				 unsigned long *p_rate, struct clk_hw **p)
+static int clk_pixel_determine_rate(struct clk_hw *hw,
+				    struct clk_rate_request *req)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	unsigned long request, src_rate;
@@ -505,20 +502,20 @@ static long clk_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
 	const struct freq_tbl *f = rcg->freq_tbl;
 	const struct frac_entry *frac = frac_table_pixel;
 	int index = qcom_find_src_index(hw, rcg->parent_map, f->src);
-	struct clk *parent = clk_get_parent_by_index(hw->clk, index);
 
-	*p = __clk_get_hw(parent);
+	req->best_parent_hw = clk_hw_get_parent_by_index(hw, index);
 
 	for (; frac->num; frac++) {
-		request = (rate * frac->den) / frac->num;
+		request = (req->rate * frac->den) / frac->num;
 
-		src_rate = __clk_round_rate(parent, request);
+		src_rate = clk_hw_round_rate(req->best_parent_hw, request);
 		if ((src_rate < (request - delta)) ||
 			(src_rate > (request + delta)))
 			continue;
 
-		*p_rate = src_rate;
-		return (src_rate * frac->num) / frac->den;
+		req->best_parent_rate = src_rate;
+		req->rate = (src_rate * frac->num) / frac->den;
+		return 0;
 	}
 
 	return -EINVAL;
@@ -530,19 +527,16 @@ static int clk_pixel_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	struct freq_tbl f = *rcg->freq_tbl;
 	const struct frac_entry *frac = frac_table_pixel;
-	unsigned long request, src_rate;
+	unsigned long request;
 	int delta = 100000;
 	u32 mask = BIT(rcg->hid_width) - 1;
 	u32 hid_div;
-	int index = qcom_find_src_index(hw, rcg->parent_map, f.src);
-	struct clk *parent = clk_get_parent_by_index(hw->clk, index);
 
 	for (; frac->num; frac++) {
 		request = (rate * frac->den) / frac->num;
 
-		src_rate = __clk_round_rate(parent, request);
-		if ((src_rate < (request - delta)) ||
-			(src_rate > (request + delta)))
+		if ((parent_rate < (request - delta)) ||
+			(parent_rate > (request + delta)))
 			continue;
 
 		regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG,
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index f7101e330b1d..2dedceefd21d 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/module.h>
 #include <linux/regmap.h>
 #include <linux/platform_device.h>
 #include <linux/clk-provider.h>
@@ -45,7 +46,7 @@ EXPORT_SYMBOL_GPL(qcom_find_freq);
 
 int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map, u8 src)
 {
-	int i, num_parents = __clk_get_num_parents(hw->clk);
+	int i, num_parents = clk_hw_get_num_parents(hw);
 
 	for (i = 0; i < num_parents; i++)
 		if (src == map[i].src)
@@ -144,3 +145,5 @@ void qcom_cc_remove(struct platform_device *pdev)
 	reset_controller_unregister(platform_get_drvdata(pdev));
 }
 EXPORT_SYMBOL_GPL(qcom_cc_remove);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c
index 54a756b90a37..3563019b8e3c 100644
--- a/drivers/clk/qcom/gcc-apq8084.c
+++ b/drivers/clk/qcom/gcc-apq8084.c
@@ -48,7 +48,7 @@ static const struct parent_map gcc_xo_gpll0_map[] = {
 	{ P_GPLL0, 1 }
 };
 
-static const char *gcc_xo_gpll0[] = {
+static const char * const gcc_xo_gpll0[] = {
 	"xo",
 	"gpll0_vote",
 };
@@ -59,7 +59,7 @@ static const struct parent_map gcc_xo_gpll0_gpll4_map[] = {
 	{ P_GPLL4, 5 }
 };
 
-static const char *gcc_xo_gpll0_gpll4[] = {
+static const char * const gcc_xo_gpll0_gpll4[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll4_vote",
@@ -70,7 +70,7 @@ static const struct parent_map gcc_xo_sata_asic0_map[] = {
 	{ P_SATA_ASIC0_CLK, 2 }
 };
 
-static const char *gcc_xo_sata_asic0[] = {
+static const char * const gcc_xo_sata_asic0[] = {
 	"xo",
 	"sata_asic0_clk",
 };
@@ -80,7 +80,7 @@ static const struct parent_map gcc_xo_sata_rx_map[] = {
 	{ P_SATA_RX_CLK, 2}
 };
 
-static const char *gcc_xo_sata_rx[] = {
+static const char * const gcc_xo_sata_rx[] = {
 	"xo",
 	"sata_rx_clk",
 };
@@ -90,7 +90,7 @@ static const struct parent_map gcc_xo_pcie_map[] = {
 	{ P_PCIE_0_1_PIPE_CLK, 2 }
 };
 
-static const char *gcc_xo_pcie[] = {
+static const char * const gcc_xo_pcie[] = {
 	"xo",
 	"pcie_pipe",
 };
@@ -100,7 +100,7 @@ static const struct parent_map gcc_xo_pcie_sleep_map[] = {
 	{ P_SLEEP_CLK, 6 }
 };
 
-static const char *gcc_xo_pcie_sleep[] = {
+static const char * const gcc_xo_pcie_sleep[] = {
 	"xo",
 	"sleep_clk_src",
 };
@@ -2105,6 +2105,7 @@ static struct clk_branch gcc_ce1_clk = {
 				"ce1_clk_src",
 			},
 			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
 		},
 	},
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index 563969942a1d..40e480220cd3 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -188,7 +188,7 @@ static const struct parent_map gcc_pxo_pll8_map[] = {
 	{ P_PLL8, 3 }
 };
 
-static const char *gcc_pxo_pll8[] = {
+static const char * const gcc_pxo_pll8[] = {
 	"pxo",
 	"pll8_vote",
 };
@@ -199,7 +199,7 @@ static const struct parent_map gcc_pxo_pll8_cxo_map[] = {
 	{ P_CXO, 5 }
 };
 
-static const char *gcc_pxo_pll8_cxo[] = {
+static const char * const gcc_pxo_pll8_cxo[] = {
 	"pxo",
 	"pll8_vote",
 	"cxo",
@@ -215,7 +215,7 @@ static const struct parent_map gcc_pxo_pll3_sata_map[] = {
 	{ P_PLL3, 6 }
 };
 
-static const char *gcc_pxo_pll3[] = {
+static const char * const gcc_pxo_pll3[] = {
 	"pxo",
 	"pll3",
 };
@@ -226,7 +226,7 @@ static const struct parent_map gcc_pxo_pll8_pll0[] = {
 	{ P_PLL0, 2 }
 };
 
-static const char *gcc_pxo_pll8_pll0_map[] = {
+static const char * const gcc_pxo_pll8_pll0_map[] = {
 	"pxo",
 	"pll8_vote",
 	"pll0_vote",
@@ -240,7 +240,7 @@ static const struct parent_map gcc_pxo_pll8_pll14_pll18_pll0_map[] = {
 	{ P_PLL18, 1 }
 };
 
-static const char *gcc_pxo_pll8_pll14_pll18_pll0[] = {
+static const char * const gcc_pxo_pll8_pll14_pll18_pll0[] = {
 	"pxo",
 	"pll8_vote",
 	"pll0_vote",
diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c
index fc6b12da5b30..b02826ed770a 100644
--- a/drivers/clk/qcom/gcc-msm8660.c
+++ b/drivers/clk/qcom/gcc-msm8660.c
@@ -70,7 +70,7 @@ static const struct parent_map gcc_pxo_pll8_map[] = {
 	{ P_PLL8, 3 }
 };
 
-static const char *gcc_pxo_pll8[] = {
+static const char * const gcc_pxo_pll8[] = {
 	"pxo",
 	"pll8_vote",
 };
@@ -81,7 +81,7 @@ static const struct parent_map gcc_pxo_pll8_cxo_map[] = {
 	{ P_CXO, 5 }
 };
 
-static const char *gcc_pxo_pll8_cxo[] = {
+static const char * const gcc_pxo_pll8_cxo[] = {
 	"pxo",
 	"pll8_vote",
 	"cxo",
@@ -1917,7 +1917,7 @@ static struct clk_rcg usb_fs1_xcvr_fs_src = {
 	}
 };
 
-static const char *usb_fs1_xcvr_fs_src_p[] = { "usb_fs1_xcvr_fs_src" };
+static const char * const usb_fs1_xcvr_fs_src_p[] = { "usb_fs1_xcvr_fs_src" };
 
 static struct clk_branch usb_fs1_xcvr_fs_clk = {
 	.halt_reg = 0x2fcc,
@@ -1984,7 +1984,7 @@ static struct clk_rcg usb_fs2_xcvr_fs_src = {
 	}
 };
 
-static const char *usb_fs2_xcvr_fs_src_p[] = { "usb_fs2_xcvr_fs_src" };
+static const char * const usb_fs2_xcvr_fs_src_p[] = { "usb_fs2_xcvr_fs_src" };
 
 static struct clk_branch usb_fs2_xcvr_fs_clk = {
 	.halt_reg = 0x2fcc,
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index c66f7bc2ae87..22a4e1e732c0 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -51,7 +51,7 @@ static const struct parent_map gcc_xo_gpll0_map[] = {
 	{ P_GPLL0, 1 },
 };
 
-static const char *gcc_xo_gpll0[] = {
+static const char * const gcc_xo_gpll0[] = {
 	"xo",
 	"gpll0_vote",
 };
@@ -62,7 +62,7 @@ static const struct parent_map gcc_xo_gpll0_bimc_map[] = {
 	{ P_BIMC, 2 },
 };
 
-static const char *gcc_xo_gpll0_bimc[] = {
+static const char * const gcc_xo_gpll0_bimc[] = {
 	"xo",
 	"gpll0_vote",
 	"bimc_pll_vote",
@@ -75,7 +75,7 @@ static const struct parent_map gcc_xo_gpll0a_gpll1_gpll2a_map[] = {
 	{ P_GPLL2_AUX, 2 },
 };
 
-static const char *gcc_xo_gpll0a_gpll1_gpll2a[] = {
+static const char * const gcc_xo_gpll0a_gpll1_gpll2a[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll1_vote",
@@ -88,7 +88,7 @@ static const struct parent_map gcc_xo_gpll0_gpll2_map[] = {
 	{ P_GPLL2, 2 },
 };
 
-static const char *gcc_xo_gpll0_gpll2[] = {
+static const char * const gcc_xo_gpll0_gpll2[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll2_vote",
@@ -99,7 +99,7 @@ static const struct parent_map gcc_xo_gpll0a_map[] = {
 	{ P_GPLL0_AUX, 2 },
 };
 
-static const char *gcc_xo_gpll0a[] = {
+static const char * const gcc_xo_gpll0a[] = {
 	"xo",
 	"gpll0_vote",
 };
@@ -111,7 +111,7 @@ static const struct parent_map gcc_xo_gpll0_gpll1a_sleep_map[] = {
 	{ P_SLEEP_CLK, 6 },
 };
 
-static const char *gcc_xo_gpll0_gpll1a_sleep[] = {
+static const char * const gcc_xo_gpll0_gpll1a_sleep[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll1_vote",
@@ -124,7 +124,7 @@ static const struct parent_map gcc_xo_gpll0_gpll1a_map[] = {
 	{ P_GPLL1_AUX, 2 },
 };
 
-static const char *gcc_xo_gpll0_gpll1a[] = {
+static const char * const gcc_xo_gpll0_gpll1a[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll1_vote",
@@ -135,7 +135,7 @@ static const struct parent_map gcc_xo_dsibyte_map[] = {
 	{ P_DSI0_PHYPLL_BYTE, 2 },
 };
 
-static const char *gcc_xo_dsibyte[] = {
+static const char * const gcc_xo_dsibyte[] = {
 	"xo",
 	"dsi0pllbyte",
 };
@@ -146,7 +146,7 @@ static const struct parent_map gcc_xo_gpll0a_dsibyte_map[] = {
 	{ P_DSI0_PHYPLL_BYTE, 1 },
 };
 
-static const char *gcc_xo_gpll0a_dsibyte[] = {
+static const char * const gcc_xo_gpll0a_dsibyte[] = {
 	"xo",
 	"gpll0_vote",
 	"dsi0pllbyte",
@@ -158,7 +158,7 @@ static const struct parent_map gcc_xo_gpll0_dsiphy_map[] = {
 	{ P_DSI0_PHYPLL_DSI, 2 },
 };
 
-static const char *gcc_xo_gpll0_dsiphy[] = {
+static const char * const gcc_xo_gpll0_dsiphy[] = {
 	"xo",
 	"gpll0_vote",
 	"dsi0pll",
@@ -170,7 +170,7 @@ static const struct parent_map gcc_xo_gpll0a_dsiphy_map[] = {
 	{ P_DSI0_PHYPLL_DSI, 1 },
 };
 
-static const char *gcc_xo_gpll0a_dsiphy[] = {
+static const char * const gcc_xo_gpll0a_dsiphy[] = {
 	"xo",
 	"gpll0_vote",
 	"dsi0pll",
@@ -183,7 +183,7 @@ static const struct parent_map gcc_xo_gpll0a_gpll1_gpll2_map[] = {
 	{ P_GPLL2, 2 },
 };
 
-static const char *gcc_xo_gpll0a_gpll1_gpll2[] = {
+static const char * const gcc_xo_gpll0a_gpll1_gpll2[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll1_vote",
@@ -2278,7 +2278,7 @@ static struct clk_branch gcc_prng_ahb_clk = {
 	.halt_check = BRANCH_HALT_VOTED,
 	.clkr = {
 		.enable_reg = 0x45004,
-		.enable_mask = BIT(0),
+		.enable_mask = BIT(8),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_prng_ahb_clk",
 			.parent_names = (const char *[]){
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index eb6a4f9fa107..aa294b1bad34 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -125,7 +125,7 @@ static const struct parent_map gcc_pxo_pll8_map[] = {
 	{ P_PLL8, 3 }
 };
 
-static const char *gcc_pxo_pll8[] = {
+static const char * const gcc_pxo_pll8[] = {
 	"pxo",
 	"pll8_vote",
 };
@@ -136,7 +136,7 @@ static const struct parent_map gcc_pxo_pll8_cxo_map[] = {
 	{ P_CXO, 5 }
 };
 
-static const char *gcc_pxo_pll8_cxo[] = {
+static const char * const gcc_pxo_pll8_cxo[] = {
 	"pxo",
 	"pll8_vote",
 	"cxo",
@@ -148,7 +148,7 @@ static const struct parent_map gcc_pxo_pll8_pll3_map[] = {
 	{ P_PLL3, 6 }
 };
 
-static const char *gcc_pxo_pll8_pll3[] = {
+static const char * const gcc_pxo_pll8_pll3[] = {
 	"pxo",
 	"pll8_vote",
 	"pll3",
@@ -2085,7 +2085,7 @@ static struct clk_rcg usb_hsic_xcvr_fs_src = {
 	}
 };
 
-static const char *usb_hsic_xcvr_fs_src_p[] = { "usb_hsic_xcvr_fs_src" };
+static const char * const usb_hsic_xcvr_fs_src_p[] = { "usb_hsic_xcvr_fs_src" };
 
 static struct clk_branch usb_hsic_xcvr_fs_clk = {
 	.halt_reg = 0x2fc8,
@@ -2181,7 +2181,7 @@ static struct clk_rcg usb_fs1_xcvr_fs_src = {
 	}
 };
 
-static const char *usb_fs1_xcvr_fs_src_p[] = { "usb_fs1_xcvr_fs_src" };
+static const char * const usb_fs1_xcvr_fs_src_p[] = { "usb_fs1_xcvr_fs_src" };
 
 static struct clk_branch usb_fs1_xcvr_fs_clk = {
 	.halt_reg = 0x2fcc,
@@ -2248,7 +2248,7 @@ static struct clk_rcg usb_fs2_xcvr_fs_src = {
 	}
 };
 
-static const char *usb_fs2_xcvr_fs_src_p[] = { "usb_fs2_xcvr_fs_src" };
+static const char * const usb_fs2_xcvr_fs_src_p[] = { "usb_fs2_xcvr_fs_src" };
 
 static struct clk_branch usb_fs2_xcvr_fs_clk = {
 	.halt_reg = 0x2fcc,
diff --git a/drivers/clk/qcom/gcc-msm8974.c b/drivers/clk/qcom/gcc-msm8974.c
index c39d09874e74..2bcf87538f9d 100644
--- a/drivers/clk/qcom/gcc-msm8974.c
+++ b/drivers/clk/qcom/gcc-msm8974.c
@@ -44,7 +44,7 @@ static const struct parent_map gcc_xo_gpll0_map[] = {
 	{ P_GPLL0, 1 }
 };
 
-static const char *gcc_xo_gpll0[] = {
+static const char * const gcc_xo_gpll0[] = {
 	"xo",
 	"gpll0_vote",
 };
@@ -55,7 +55,7 @@ static const struct parent_map gcc_xo_gpll0_gpll4_map[] = {
 	{ P_GPLL4, 5 }
 };
 
-static const char *gcc_xo_gpll0_gpll4[] = {
+static const char * const gcc_xo_gpll0_gpll4[] = {
 	"xo",
 	"gpll0_vote",
 	"gpll4_vote",
@@ -1783,6 +1783,7 @@ static struct clk_branch gcc_ce1_clk = {
 				"ce1_clk_src",
 			},
 			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
 		},
 	},
diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c
index 47f0ac16d149..93ad42b14366 100644
--- a/drivers/clk/qcom/lcc-ipq806x.c
+++ b/drivers/clk/qcom/lcc-ipq806x.c
@@ -71,7 +71,7 @@ static const struct parent_map lcc_pxo_pll4_map[] = {
 	{ P_PLL4, 2 }
 };
 
-static const char *lcc_pxo_pll4[] = {
+static const char * const lcc_pxo_pll4[] = {
 	"pxo",
 	"pll4_vote",
 };
@@ -146,7 +146,7 @@ static struct clk_rcg mi2s_osr_src = {
 	},
 };
 
-static const char *lcc_mi2s_parents[] = {
+static const char * const lcc_mi2s_parents[] = {
 	"mi2s_osr_src",
 };
 
@@ -340,7 +340,7 @@ static struct clk_rcg spdif_src = {
 	},
 };
 
-static const char *lcc_spdif_parents[] = {
+static const char * const lcc_spdif_parents[] = {
 	"spdif_src",
 };
 
diff --git a/drivers/clk/qcom/lcc-msm8960.c b/drivers/clk/qcom/lcc-msm8960.c
index d0df9d5fc3af..ecb96c284675 100644
--- a/drivers/clk/qcom/lcc-msm8960.c
+++ b/drivers/clk/qcom/lcc-msm8960.c
@@ -57,7 +57,7 @@ static const struct parent_map lcc_pxo_pll4_map[] = {
 	{ P_PLL4, 2 }
 };
 
-static const char *lcc_pxo_pll4[] = {
+static const char * const lcc_pxo_pll4[] = {
 	"pxo",
 	"pll4_vote",
 };
@@ -127,7 +127,7 @@ static struct clk_rcg mi2s_osr_src = {
 	},
 };
 
-static const char *lcc_mi2s_parents[] = {
+static const char * const lcc_mi2s_parents[] = {
 	"mi2s_osr_src",
 };
 
@@ -233,7 +233,7 @@ static struct clk_rcg prefix##_osr_src = {			\
 	},							\
 };								\
 								\
-static const char *lcc_##prefix##_parents[] = {			\
+static const char * const lcc_##prefix##_parents[] = {		\
 	#prefix "_osr_src",					\
 };								\
 								\
@@ -445,7 +445,7 @@ static struct clk_rcg slimbus_src = {
 	},
 };
 
-static const char *lcc_slimbus_parents[] = {
+static const char * const lcc_slimbus_parents[] = {
 	"slimbus_src",
 };
 
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
index 1b17df2cb0af..f0ee6bde11af 100644
--- a/drivers/clk/qcom/mmcc-apq8084.c
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -53,7 +53,7 @@ static const struct parent_map mmcc_xo_mmpll0_mmpll1_gpll0_map[] = {
 	{ P_GPLL0, 5 }
 };
 
-static const char *mmcc_xo_mmpll0_mmpll1_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_mmpll1_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -69,7 +69,7 @@ static const struct parent_map mmcc_xo_mmpll0_dsi_hdmi_gpll0_map[] = {
 	{ P_DSI1PLL, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_dsi_hdmi_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_dsi_hdmi_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"hdmipll",
@@ -86,7 +86,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_2_gpll0_map[] = {
 	{ P_MMPLL2, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_1_2_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_1_2_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -102,7 +102,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_3_gpll0_map[] = {
 	{ P_MMPLL3, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_1_3_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_1_3_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -119,7 +119,7 @@ static const struct parent_map mmcc_xo_dsi_hdmi_edp_map[] = {
 	{ P_DSI1PLL, 2 }
 };
 
-static const char *mmcc_xo_dsi_hdmi_edp[] = {
+static const char * const mmcc_xo_dsi_hdmi_edp[] = {
 	"xo",
 	"edp_link_clk",
 	"hdmipll",
@@ -137,7 +137,7 @@ static const struct parent_map mmcc_xo_dsi_hdmi_edp_gpll0_map[] = {
 	{ P_DSI1PLL, 2 }
 };
 
-static const char *mmcc_xo_dsi_hdmi_edp_gpll0[] = {
+static const char * const mmcc_xo_dsi_hdmi_edp_gpll0[] = {
 	"xo",
 	"edp_link_clk",
 	"hdmipll",
@@ -155,7 +155,7 @@ static const struct parent_map mmcc_xo_dsibyte_hdmi_edp_gpll0_map[] = {
 	{ P_DSI1PLL_BYTE, 2 }
 };
 
-static const char *mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
+static const char * const mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
 	"xo",
 	"edp_link_clk",
 	"hdmipll",
@@ -172,7 +172,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_4_gpll0_map[] = {
 	{ P_MMPLL4, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_1_4_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_1_4_gpll0[] = {
 	"xo",
 	"mmpll0",
 	"mmpll1",
@@ -189,7 +189,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_4_gpll1_0_map[] = {
 	{ P_GPLL1, 4 }
 };
 
-static const char *mmcc_xo_mmpll0_1_4_gpll1_0[] = {
+static const char * const mmcc_xo_mmpll0_1_4_gpll1_0[] = {
 	"xo",
 	"mmpll0",
 	"mmpll1",
@@ -208,7 +208,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_4_gpll1_0_sleep_map[] = {
 	{ P_MMSLEEP, 6 }
 };
 
-static const char *mmcc_xo_mmpll0_1_4_gpll1_0_sleep[] = {
+static const char * const mmcc_xo_mmpll0_1_4_gpll1_0_sleep[] = {
 	"xo",
 	"mmpll0",
 	"mmpll1",
diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c
index 9711bca9cc06..bad02aebf959 100644
--- a/drivers/clk/qcom/mmcc-msm8960.c
+++ b/drivers/clk/qcom/mmcc-msm8960.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/regmap.h>
 #include <linux/reset-controller.h>
@@ -50,7 +51,7 @@ static const struct parent_map mmcc_pxo_pll8_pll2_map[] = {
 	{ P_PLL2, 1 }
 };
 
-static const char *mmcc_pxo_pll8_pll2[] = {
+static const char * const mmcc_pxo_pll8_pll2[] = {
 	"pxo",
 	"pll8_vote",
 	"pll2",
@@ -63,7 +64,7 @@ static const struct parent_map mmcc_pxo_pll8_pll2_pll3_map[] = {
 	{ P_PLL3, 3 }
 };
 
-static const char *mmcc_pxo_pll8_pll2_pll15[] = {
+static const char * const mmcc_pxo_pll8_pll2_pll15[] = {
 	"pxo",
 	"pll8_vote",
 	"pll2",
@@ -77,7 +78,7 @@ static const struct parent_map mmcc_pxo_pll8_pll2_pll15_map[] = {
 	{ P_PLL15, 3 }
 };
 
-static const char *mmcc_pxo_pll8_pll2_pll3[] = {
+static const char * const mmcc_pxo_pll8_pll2_pll3[] = {
 	"pxo",
 	"pll8_vote",
 	"pll2",
@@ -508,8 +509,7 @@ static int pix_rdi_set_parent(struct clk_hw *hw, u8 index)
 	int ret = 0;
 	u32 val;
 	struct clk_pix_rdi *rdi = to_clk_pix_rdi(hw);
-	struct clk *clk = hw->clk;
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 
 	/*
 	 * These clocks select three inputs via two muxes. One mux selects
@@ -520,7 +520,8 @@ static int pix_rdi_set_parent(struct clk_hw *hw, u8 index)
 	 * needs to be on at what time.
 	 */
 	for (i = 0; i < num_parents; i++) {
-		ret = clk_prepare_enable(clk_get_parent_by_index(clk, i));
+		struct clk_hw *p = clk_hw_get_parent_by_index(hw, i);
+		ret = clk_prepare_enable(p->clk);
 		if (ret)
 			goto err;
 	}
@@ -548,8 +549,10 @@ static int pix_rdi_set_parent(struct clk_hw *hw, u8 index)
 	udelay(1);
 
 err:
-	for (i--; i >= 0; i--)
-		clk_disable_unprepare(clk_get_parent_by_index(clk, i));
+	for (i--; i >= 0; i--) {
+		struct clk_hw *p = clk_hw_get_parent_by_index(hw, i);
+		clk_disable_unprepare(p->clk);
+	}
 
 	return ret;
 }
@@ -579,7 +582,7 @@ static const struct clk_ops clk_ops_pix_rdi = {
 	.determine_rate = __clk_mux_determine_rate,
 };
 
-static const char *pix_rdi_parents[] = {
+static const char * const pix_rdi_parents[] = {
 	"csi0_clk",
 	"csi1_clk",
 	"csi2_clk",
@@ -709,7 +712,7 @@ static struct clk_rcg csiphytimer_src = {
 	},
 };
 
-static const char *csixphy_timer_src[] = { "csiphytimer_src" };
+static const char * const csixphy_timer_src[] = { "csiphytimer_src" };
 
 static struct clk_branch csiphy0_timer_clk = {
 	.halt_reg = 0x01e8,
@@ -1385,7 +1388,7 @@ static const struct parent_map mmcc_pxo_hdmi_map[] = {
 	{ P_HDMI_PLL, 3 }
 };
 
-static const char *mmcc_pxo_hdmi[] = {
+static const char * const mmcc_pxo_hdmi[] = {
 	"pxo",
 	"hdmi_pll",
 };
@@ -1428,7 +1431,7 @@ static struct clk_rcg tv_src = {
 	},
 };
 
-static const char *tv_src_name[] = { "tv_src" };
+static const char * const tv_src_name[] = { "tv_src" };
 
 static struct clk_branch tv_enc_clk = {
 	.halt_reg = 0x01d4,
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index 07f4cc159ad3..0987bf443e1f 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -56,7 +56,7 @@ static const struct parent_map mmcc_xo_mmpll0_mmpll1_gpll0_map[] = {
 	{ P_GPLL0, 5 }
 };
 
-static const char *mmcc_xo_mmpll0_mmpll1_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_mmpll1_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -72,7 +72,7 @@ static const struct parent_map mmcc_xo_mmpll0_dsi_hdmi_gpll0_map[] = {
 	{ P_DSI1PLL, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_dsi_hdmi_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_dsi_hdmi_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"hdmipll",
@@ -89,7 +89,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_2_gpll0_map[] = {
 	{ P_MMPLL2, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_1_2_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_1_2_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -105,7 +105,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_3_gpll0_map[] = {
 	{ P_MMPLL3, 3 }
 };
 
-static const char *mmcc_xo_mmpll0_1_3_gpll0[] = {
+static const char * const mmcc_xo_mmpll0_1_3_gpll0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -121,7 +121,7 @@ static const struct parent_map mmcc_xo_mmpll0_1_gpll1_0_map[] = {
 	{ P_GPLL1, 4 }
 };
 
-static const char *mmcc_xo_mmpll0_1_gpll1_0[] = {
+static const char * const mmcc_xo_mmpll0_1_gpll1_0[] = {
 	"xo",
 	"mmpll0_vote",
 	"mmpll1_vote",
@@ -138,7 +138,7 @@ static const struct parent_map mmcc_xo_dsi_hdmi_edp_map[] = {
 	{ P_DSI1PLL, 2 }
 };
 
-static const char *mmcc_xo_dsi_hdmi_edp[] = {
+static const char * const mmcc_xo_dsi_hdmi_edp[] = {
 	"xo",
 	"edp_link_clk",
 	"hdmipll",
@@ -156,7 +156,7 @@ static const struct parent_map mmcc_xo_dsi_hdmi_edp_gpll0_map[] = {
 	{ P_DSI1PLL, 2 }
 };
 
-static const char *mmcc_xo_dsi_hdmi_edp_gpll0[] = {
+static const char * const mmcc_xo_dsi_hdmi_edp_gpll0[] = {
 	"xo",
 	"edp_link_clk",
 	"hdmipll",
@@ -174,7 +174,7 @@ static const struct parent_map mmcc_xo_dsibyte_hdmi_edp_gpll0_map[] = {
 	{ P_DSI1PLL_BYTE, 2 }
 };
 
-static const char *mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
+static const char * const mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
 	"xo",
 	"edp_link_clk",
 	"hdmipll",
diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index 2714097f90db..b27edd6c8183 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile
@@ -6,8 +6,10 @@ obj-y	+= clk-rockchip.o
 obj-y	+= clk.o
 obj-y	+= clk-pll.o
 obj-y	+= clk-cpu.o
+obj-y	+= clk-inverter.o
 obj-y	+= clk-mmc-phase.o
 obj-$(CONFIG_RESET_CONTROLLER)	+= softrst.o
 
 obj-y	+= clk-rk3188.o
 obj-y	+= clk-rk3288.o
+obj-y	+= clk-rk3368.o
diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c
index fb7721bd37e6..330870a6d8bf 100644
--- a/drivers/clk/rockchip/clk-cpu.c
+++ b/drivers/clk/rockchip/clk-cpu.c
@@ -35,6 +35,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/io.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include "clk.h"
 
diff --git a/drivers/clk/rockchip/clk-inverter.c b/drivers/clk/rockchip/clk-inverter.c
new file mode 100644
index 000000000000..7cbf43beb3c6
--- /dev/null
+++ b/drivers/clk/rockchip/clk-inverter.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright 2015 Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/slab.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include "clk.h"
+
+struct rockchip_inv_clock {
+	struct clk_hw	hw;
+	void __iomem	*reg;
+	int		shift;
+	int		flags;
+	spinlock_t	*lock;
+};
+
+#define to_inv_clock(_hw) container_of(_hw, struct rockchip_inv_clock, hw)
+
+#define INVERTER_MASK 0x1
+
+static int rockchip_inv_get_phase(struct clk_hw *hw)
+{
+	struct rockchip_inv_clock *inv_clock = to_inv_clock(hw);
+	u32 val;
+
+	val = readl(inv_clock->reg) >> inv_clock->shift;
+	val &= INVERTER_MASK;
+	return val ? 180 : 0;
+}
+
+static int rockchip_inv_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct rockchip_inv_clock *inv_clock = to_inv_clock(hw);
+	u32 val;
+
+	if (degrees % 180 == 0) {
+		val = !!degrees;
+	} else {
+		pr_err("%s: unsupported phase %d for %s\n",
+		       __func__, degrees, clk_hw_get_name(hw));
+		return -EINVAL;
+	}
+
+	if (inv_clock->flags & ROCKCHIP_INVERTER_HIWORD_MASK) {
+		writel(HIWORD_UPDATE(val, INVERTER_MASK, inv_clock->shift),
+		       inv_clock->reg);
+	} else {
+		unsigned long flags;
+		u32 reg;
+
+		spin_lock_irqsave(inv_clock->lock, flags);
+
+		reg = readl(inv_clock->reg);
+		reg &= ~BIT(inv_clock->shift);
+		reg |= val;
+		writel(reg, inv_clock->reg);
+
+		spin_unlock_irqrestore(inv_clock->lock, flags);
+	}
+
+	return 0;
+}
+
+static const struct clk_ops rockchip_inv_clk_ops = {
+	.get_phase	= rockchip_inv_get_phase,
+	.set_phase	= rockchip_inv_set_phase,
+};
+
+struct clk *rockchip_clk_register_inverter(const char *name,
+				const char *const *parent_names, u8 num_parents,
+				void __iomem *reg, int shift, int flags,
+				spinlock_t *lock)
+{
+	struct clk_init_data init;
+	struct rockchip_inv_clock *inv_clock;
+	struct clk *clk;
+
+	inv_clock = kmalloc(sizeof(*inv_clock), GFP_KERNEL);
+	if (!inv_clock)
+		return NULL;
+
+	init.name = name;
+	init.num_parents = num_parents;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.parent_names = parent_names;
+	init.ops = &rockchip_inv_clk_ops;
+
+	inv_clock->hw.init = &init;
+	inv_clock->reg = reg;
+	inv_clock->shift = shift;
+	inv_clock->flags = flags;
+	inv_clock->lock = lock;
+
+	clk = clk_register(NULL, &inv_clock->hw);
+	if (IS_ERR(clk))
+		goto err_free;
+
+	return clk;
+
+err_free:
+	kfree(inv_clock);
+	return NULL;
+}
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index e9f8df324e7c..9b613426e968 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -14,7 +14,10 @@
  */
 
 #include <linux/slab.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
 #include "clk.h"
 
 struct rockchip_mmc_clock {
@@ -105,7 +108,7 @@ static int rockchip_mmc_set_phase(struct clk_hw *hw, int degrees)
 	writel(HIWORD_UPDATE(raw_value, 0x07ff, mmc_clock->shift), mmc_clock->reg);
 
 	pr_debug("%s->set_phase(%d) delay_nums=%u reg[0x%p]=0x%03x actual_degrees=%d\n",
-		__clk_get_name(hw->clk), degrees, delay_num,
+		clk_hw_get_name(hw), degrees, delay_num,
 		mmc_clock->reg, raw_value>>(mmc_clock->shift),
 		rockchip_mmc_get_phase(hw)
 	);
@@ -131,6 +134,7 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 	if (!mmc_clock)
 		return NULL;
 
+	init.name = name;
 	init.num_parents = num_parents;
 	init.parent_names = parent_names;
 	init.ops = &rockchip_mmc_clk_ops;
@@ -139,9 +143,6 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 	mmc_clock->reg = reg;
 	mmc_clock->shift = shift;
 
-	if (name)
-		init.name = name;
-
 	clk = clk_register(NULL, &mmc_clock->hw);
 	if (IS_ERR(clk))
 		goto err_free;
diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index 76027261f7ed..7737a1df1e4b 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -17,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/delay.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/regmap.h>
 #include "clk.h"
@@ -121,8 +120,8 @@ static int rockchip_pll_wait_lock(struct rockchip_clk_pll *pll)
 #define RK3066_PLLCON0_NR_SHIFT		8
 #define RK3066_PLLCON1_NF_MASK		0x1fff
 #define RK3066_PLLCON1_NF_SHIFT		0
-#define RK3066_PLLCON2_BWADJ_MASK	0xfff
-#define RK3066_PLLCON2_BWADJ_SHIFT	0
+#define RK3066_PLLCON2_NB_MASK		0xfff
+#define RK3066_PLLCON2_NB_SHIFT		0
 #define RK3066_PLLCON3_RESET		(1 << 5)
 #define RK3066_PLLCON3_PWRDOWN		(1 << 1)
 #define RK3066_PLLCON3_BYPASS		(1 << 0)
@@ -137,7 +136,7 @@ static unsigned long rockchip_rk3066_pll_recalc_rate(struct clk_hw *hw,
 	pllcon = readl_relaxed(pll->reg_base + RK3066_PLLCON(3));
 	if (pllcon & RK3066_PLLCON3_BYPASS) {
 		pr_debug("%s: pll %s is bypassed\n", __func__,
-			__clk_get_name(hw->clk));
+			clk_hw_get_name(hw));
 		return prate;
 	}
 
@@ -175,13 +174,13 @@ static int rockchip_rk3066_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 	}
 
 	pr_debug("%s: changing %s from %lu to %lu with a parent rate of %lu\n",
-		 __func__, __clk_get_name(hw->clk), old_rate, drate, prate);
+		 __func__, clk_hw_get_name(hw), old_rate, drate, prate);
 
 	/* Get required rate settings from table */
 	rate = rockchip_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -208,8 +207,8 @@ static int rockchip_rk3066_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 	writel_relaxed(HIWORD_UPDATE(rate->nf - 1, RK3066_PLLCON1_NF_MASK,
 						   RK3066_PLLCON1_NF_SHIFT),
 		       pll->reg_base + RK3066_PLLCON(1));
-	writel_relaxed(HIWORD_UPDATE(rate->bwadj, RK3066_PLLCON2_BWADJ_MASK,
-						  RK3066_PLLCON2_BWADJ_SHIFT),
+	writel_relaxed(HIWORD_UPDATE(rate->nb - 1, RK3066_PLLCON2_NB_MASK,
+						   RK3066_PLLCON2_NB_SHIFT),
 		       pll->reg_base + RK3066_PLLCON(2));
 
 	/* leave reset and wait the reset_delay */
@@ -262,14 +261,14 @@ static void rockchip_rk3066_pll_init(struct clk_hw *hw)
 {
 	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
 	const struct rockchip_pll_rate_table *rate;
-	unsigned int nf, nr, no, bwadj;
+	unsigned int nf, nr, no, nb;
 	unsigned long drate;
 	u32 pllcon;
 
 	if (!(pll->flags & ROCKCHIP_PLL_SYNC_RATE))
 		return;
 
-	drate = __clk_get_rate(hw->clk);
+	drate = clk_hw_get_rate(hw);
 	rate = rockchip_get_pll_settings(pll, drate);
 
 	/* when no rate setting for the current rate, rely on clk_set_rate */
@@ -284,25 +283,25 @@ static void rockchip_rk3066_pll_init(struct clk_hw *hw)
 	nf = ((pllcon >> RK3066_PLLCON1_NF_SHIFT) & RK3066_PLLCON1_NF_MASK) + 1;
 
 	pllcon = readl_relaxed(pll->reg_base + RK3066_PLLCON(2));
-	bwadj = (pllcon >> RK3066_PLLCON2_BWADJ_SHIFT) & RK3066_PLLCON2_BWADJ_MASK;
+	nb = ((pllcon >> RK3066_PLLCON2_NB_SHIFT) & RK3066_PLLCON2_NB_MASK) + 1;
 
-	pr_debug("%s: pll %s@%lu: nr (%d:%d); no (%d:%d); nf(%d:%d), bwadj(%d:%d)\n",
-		 __func__, __clk_get_name(hw->clk), drate, rate->nr, nr,
-		rate->no, no, rate->nf, nf, rate->bwadj, bwadj);
+	pr_debug("%s: pll %s@%lu: nr (%d:%d); no (%d:%d); nf(%d:%d), nb(%d:%d)\n",
+		 __func__, clk_hw_get_name(hw), drate, rate->nr, nr,
+		rate->no, no, rate->nf, nf, rate->nb, nb);
 	if (rate->nr != nr || rate->no != no || rate->nf != nf
-					     || rate->bwadj != bwadj) {
-		struct clk *parent = __clk_get_parent(hw->clk);
+					     || rate->nb != nb) {
+		struct clk_hw *parent = clk_hw_get_parent(hw);
 		unsigned long prate;
 
 		if (!parent) {
 			pr_warn("%s: parent of %s not available\n",
-				__func__, __clk_get_name(hw->clk));
+				__func__, clk_hw_get_name(hw));
 			return;
 		}
 
 		pr_debug("%s: pll %s: rate params do not match rate table, adjusting\n",
-			 __func__, __clk_get_name(hw->clk));
-		prate = __clk_get_rate(parent);
+			 __func__, clk_hw_get_name(hw));
+		prate = clk_hw_get_rate(parent);
 		rockchip_rk3066_pll_set_rate(hw, drate, prate);
 	}
 }
@@ -354,6 +353,35 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 	if (!pll)
 		return ERR_PTR(-ENOMEM);
 
+	/* create the mux on top of the real pll */
+	pll->pll_mux_ops = &clk_mux_ops;
+	pll_mux = &pll->pll_mux;
+	pll_mux->reg = base + mode_offset;
+	pll_mux->shift = mode_shift;
+	pll_mux->mask = PLL_MODE_MASK;
+	pll_mux->flags = 0;
+	pll_mux->lock = lock;
+	pll_mux->hw.init = &init;
+
+	if (pll_type == pll_rk3066)
+		pll_mux->flags |= CLK_MUX_HIWORD_MASK;
+
+	/* the actual muxing is xin24m, pll-output, xin32k */
+	pll_parents[0] = parent_names[0];
+	pll_parents[1] = pll_name;
+	pll_parents[2] = parent_names[1];
+
+	init.name = name;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.ops = pll->pll_mux_ops;
+	init.parent_names = pll_parents;
+	init.num_parents = ARRAY_SIZE(pll_parents);
+
+	mux_clk = clk_register(NULL, &pll_mux->hw);
+	if (IS_ERR(mux_clk))
+		goto err_mux;
+
+	/* now create the actual pll */
 	init.name = pll_name;
 
 	/* keep all plls untouched for now */
@@ -399,47 +427,19 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 	pll->flags = clk_pll_flags;
 	pll->lock = lock;
 
-	/* create the mux on top of the real pll */
-	pll->pll_mux_ops = &clk_mux_ops;
-	pll_mux = &pll->pll_mux;
-	pll_mux->reg = base + mode_offset;
-	pll_mux->shift = mode_shift;
-	pll_mux->mask = PLL_MODE_MASK;
-	pll_mux->flags = 0;
-	pll_mux->lock = lock;
-	pll_mux->hw.init = &init;
-
-	if (pll_type == pll_rk3066)
-		pll_mux->flags |= CLK_MUX_HIWORD_MASK;
-
 	pll_clk = clk_register(NULL, &pll->hw);
 	if (IS_ERR(pll_clk)) {
 		pr_err("%s: failed to register pll clock %s : %ld\n",
 			__func__, name, PTR_ERR(pll_clk));
-		mux_clk = pll_clk;
 		goto err_pll;
 	}
 
-	/* the actual muxing is xin24m, pll-output, xin32k */
-	pll_parents[0] = parent_names[0];
-	pll_parents[1] = pll_name;
-	pll_parents[2] = parent_names[1];
-
-	init.name = name;
-	init.flags = CLK_SET_RATE_PARENT;
-	init.ops = pll->pll_mux_ops;
-	init.parent_names = pll_parents;
-	init.num_parents = ARRAY_SIZE(pll_parents);
-
-	mux_clk = clk_register(NULL, &pll_mux->hw);
-	if (IS_ERR(mux_clk))
-		goto err_mux;
-
 	return mux_clk;
 
-err_mux:
-	clk_unregister(pll_clk);
 err_pll:
+	clk_unregister(mux_clk);
+	mux_clk = pll_clk;
+err_mux:
 	kfree(pll);
 	return mux_clk;
 }
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index e4f9d472f1ff..ed02bbc7b11f 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -13,6 +13,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -201,7 +202,7 @@ PNAME(mux_pll_src_cpll_gpll_p)	= { "cpll", "gpll" };
 PNAME(mux_aclk_cpu_p)		= { "apll", "gpll" };
 PNAME(mux_sclk_cif0_p)		= { "cif0_pre", "xin24m" };
 PNAME(mux_sclk_i2s0_p)		= { "i2s0_pre", "i2s0_frac", "xin12m" };
-PNAME(mux_sclk_spdif_p)		= { "spdif_src", "spdif_frac", "xin12m" };
+PNAME(mux_sclk_spdif_p)		= { "spdif_pre", "spdif_frac", "xin12m" };
 PNAME(mux_sclk_uart0_p)		= { "uart0_pre", "uart0_frac", "xin24m" };
 PNAME(mux_sclk_uart1_p)		= { "uart1_pre", "uart1_frac", "xin24m" };
 PNAME(mux_sclk_uart2_p)		= { "uart2_pre", "uart2_frac", "xin24m" };
@@ -235,6 +236,7 @@ static struct rockchip_pll_clock rk3188_pll_clks[] __initdata = {
 #define MFLAGS CLK_MUX_HIWORD_MASK
 #define DFLAGS CLK_DIVIDER_HIWORD_MASK
 #define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+#define IFLAGS ROCKCHIP_INVERTER_HIWORD_MASK
 
 /* 2 ^ (val + 1) */
 static struct clk_div_table div_core_peri_t[] = {
@@ -310,6 +312,8 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 
 	GATE(0, "pclkin_cif0", "ext_cif0", 0,
 			RK2928_CLKGATE_CON(3), 3, GFLAGS),
+	INVERTER(0, "pclk_cif0", "pclkin_cif0",
+			RK2928_CLKSEL_CON(30), 8, IFLAGS),
 
 	/*
 	 * the 480m are generated inside the usb block from these clocks,
@@ -334,8 +338,10 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	COMPOSITE_FRAC(0, "hsadc_frac", "hsadc_src", 0,
 			RK2928_CLKSEL_CON(23), 0,
 			RK2928_CLKGATE_CON(2), 7, GFLAGS),
-	MUX(SCLK_HSADC, "sclk_hsadc", mux_sclk_hsadc_p, 0,
+	MUX(0, "sclk_hsadc_out", mux_sclk_hsadc_p, 0,
 			RK2928_CLKSEL_CON(22), 4, 2, MFLAGS),
+	INVERTER(SCLK_HSADC, "sclk_hsadc", "sclk_hsadc_out",
+			RK2928_CLKSEL_CON(22), 7, IFLAGS),
 
 	COMPOSITE_NOMUX(SCLK_SARADC, "sclk_saradc", "xin24m", 0,
 			RK2928_CLKSEL_CON(24), 8, 8, DFLAGS,
@@ -344,10 +350,10 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	COMPOSITE_NOMUX(0, "spdif_pre", "i2s_src", 0,
 			RK2928_CLKSEL_CON(5), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 13, GFLAGS),
-	COMPOSITE_FRAC(0, "spdif_frac", "spdif_pll", 0,
+	COMPOSITE_FRAC(0, "spdif_frac", "spdif_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(9), 0,
 			RK2928_CLKGATE_CON(0), 14, GFLAGS),
-	MUX(SCLK_SPDIF, "sclk_spdif", mux_sclk_spdif_p, 0,
+	MUX(SCLK_SPDIF, "sclk_spdif", mux_sclk_spdif_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(5), 8, 2, MFLAGS),
 
 	/*
@@ -557,6 +563,8 @@ static struct rockchip_clk_branch rk3066a_clk_branches[] __initdata = {
 
 	GATE(0, "pclkin_cif1", "ext_cif1", 0,
 			RK2928_CLKGATE_CON(3), 4, GFLAGS),
+	INVERTER(0, "pclk_cif1", "pclkin_cif1",
+			RK2928_CLKSEL_CON(30), 12, IFLAGS),
 
 	COMPOSITE(0, "aclk_gpu_src", mux_pll_src_cpll_gpll_p, 0,
 			RK2928_CLKSEL_CON(33), 8, 1, MFLAGS, 0, 5, DFLAGS,
@@ -809,7 +817,7 @@ static void __init rk3188_clk_init(struct device_node *np)
 
 		rate = pll->rate_table;
 		while (rate->rate > 0) {
-			rate->bwadj = 0;
+			rate->nb = 1;
 			rate++;
 		}
 	}
diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index 4f817ed9e6ee..9040878e3e2b 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -84,7 +84,7 @@ static struct rockchip_pll_rate_table rk3288_pll_rates[] = {
 	RK3066_PLL_RATE( 742500000, 8, 495, 2),
 	RK3066_PLL_RATE( 696000000, 1, 58, 2),
 	RK3066_PLL_RATE( 600000000, 1, 50, 2),
-	RK3066_PLL_RATE_BWADJ(594000000, 1, 198, 8, 1),
+	RK3066_PLL_RATE_NB(594000000, 1, 198, 8, 1),
 	RK3066_PLL_RATE( 552000000, 1, 46, 2),
 	RK3066_PLL_RATE( 504000000, 1, 84, 4),
 	RK3066_PLL_RATE( 500000000, 3, 125, 2),
@@ -189,7 +189,7 @@ PNAME(mux_uart1_p)	= { "uart1_src", "uart1_frac", "xin24m" };
 PNAME(mux_uart2_p)	= { "uart2_src", "uart2_frac", "xin24m" };
 PNAME(mux_uart3_p)	= { "uart3_src", "uart3_frac", "xin24m" };
 PNAME(mux_uart4_p)	= { "uart4_src", "uart4_frac", "xin24m" };
-PNAME(mux_cif_out_p)	= { "cif_src", "xin24m" };
+PNAME(mux_vip_out_p)	= { "vip_src", "xin24m" };
 PNAME(mux_mac_p)	= { "mac_pll_src", "ext_gmac" };
 PNAME(mux_hsadcout_p)	= { "hsadc_src", "ext_hsadc" };
 PNAME(mux_edp_24m_p)	= { "ext_edp_24m", "xin24m" };
@@ -223,6 +223,7 @@ static struct clk_div_table div_hclk_cpu_t[] = {
 #define MFLAGS CLK_MUX_HIWORD_MASK
 #define DFLAGS CLK_DIVIDER_HIWORD_MASK
 #define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+#define IFLAGS ROCKCHIP_INVERTER_HIWORD_MASK
 
 static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	/*
@@ -434,7 +435,7 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0,
 			RK3288_CLKSEL_CON(26), 8, 1, MFLAGS,
 			RK3288_CLKGATE_CON(3), 7, GFLAGS),
-	COMPOSITE_NOGATE(0, "sclk_vip_out", mux_cif_out_p, 0,
+	COMPOSITE_NOGATE(0, "sclk_vip_out", mux_vip_out_p, 0,
 			RK3288_CLKSEL_CON(26), 15, 1, MFLAGS, 9, 5, DFLAGS),
 
 	DIV(0, "pclk_pd_alive", "gpll", 0,
@@ -578,7 +579,7 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "mac_pll_src", mux_pll_src_npll_cpll_gpll_p, 0,
 			RK3288_CLKSEL_CON(21), 0, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3288_CLKGATE_CON(2), 5, GFLAGS),
-	MUX(SCLK_MAC, "mac_clk", mux_mac_p, 0,
+	MUX(SCLK_MAC, "mac_clk", mux_mac_p, CLK_SET_RATE_PARENT,
 			RK3288_CLKSEL_CON(21), 4, 1, MFLAGS),
 	GATE(SCLK_MACREF_OUT, "sclk_macref_out", "mac_clk", 0,
 			RK3288_CLKGATE_CON(5), 3, GFLAGS),
@@ -592,8 +593,10 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "hsadc_src", mux_pll_src_cpll_gpll_p, 0,
 			RK3288_CLKSEL_CON(22), 0, 1, MFLAGS, 8, 8, DFLAGS,
 			RK3288_CLKGATE_CON(2), 6, GFLAGS),
-	MUX(SCLK_HSADC, "sclk_hsadc_out", mux_hsadcout_p, 0,
+	MUX(0, "sclk_hsadc_out", mux_hsadcout_p, 0,
 			RK3288_CLKSEL_CON(22), 4, 1, MFLAGS),
+	INVERTER(SCLK_HSADC, "sclk_hsadc", "sclk_hsadc_out",
+			RK3288_CLKSEL_CON(22), 7, IFLAGS),
 
 	GATE(0, "jtag", "ext_jtag", 0,
 			RK3288_CLKGATE_CON(4), 14, GFLAGS),
@@ -768,13 +771,16 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	 */
 
 	GATE(0, "pclk_vip_in", "ext_vip", 0, RK3288_CLKGATE_CON(16), 0, GFLAGS),
+	INVERTER(0, "pclk_vip", "pclk_vip_in", RK3288_CLKSEL_CON(29), 4, IFLAGS),
 	GATE(0, "pclk_isp_in", "ext_isp", 0, RK3288_CLKGATE_CON(16), 3, GFLAGS),
+	INVERTER(0, "pclk_isp", "pclk_isp_in", RK3288_CLKSEL_CON(29), 3, IFLAGS),
 };
 
 static const char *const rk3288_critical_clocks[] __initconst = {
 	"aclk_cpu",
 	"aclk_peri",
 	"hclk_peri",
+	"pclk_pd_pmu",
 };
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c
new file mode 100644
index 000000000000..9c5d61e698ef
--- /dev/null
+++ b/drivers/clk/rockchip/clk-rk3368.c
@@ -0,0 +1,881 @@
+/*
+ * Copyright (c) 2015 Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <dt-bindings/clock/rk3368-cru.h>
+#include "clk.h"
+
+#define RK3368_GRF_SOC_STATUS0	0x480
+
+enum rk3368_plls {
+	apllb, aplll, dpll, cpll, gpll, npll,
+};
+
+static struct rockchip_pll_rate_table rk3368_pll_rates[] = {
+	RK3066_PLL_RATE(2208000000, 1, 92, 1),
+	RK3066_PLL_RATE(2184000000, 1, 91, 1),
+	RK3066_PLL_RATE(2160000000, 1, 90, 1),
+	RK3066_PLL_RATE(2136000000, 1, 89, 1),
+	RK3066_PLL_RATE(2112000000, 1, 88, 1),
+	RK3066_PLL_RATE(2088000000, 1, 87, 1),
+	RK3066_PLL_RATE(2064000000, 1, 86, 1),
+	RK3066_PLL_RATE(2040000000, 1, 85, 1),
+	RK3066_PLL_RATE(2016000000, 1, 84, 1),
+	RK3066_PLL_RATE(1992000000, 1, 83, 1),
+	RK3066_PLL_RATE(1968000000, 1, 82, 1),
+	RK3066_PLL_RATE(1944000000, 1, 81, 1),
+	RK3066_PLL_RATE(1920000000, 1, 80, 1),
+	RK3066_PLL_RATE(1896000000, 1, 79, 1),
+	RK3066_PLL_RATE(1872000000, 1, 78, 1),
+	RK3066_PLL_RATE(1848000000, 1, 77, 1),
+	RK3066_PLL_RATE(1824000000, 1, 76, 1),
+	RK3066_PLL_RATE(1800000000, 1, 75, 1),
+	RK3066_PLL_RATE(1776000000, 1, 74, 1),
+	RK3066_PLL_RATE(1752000000, 1, 73, 1),
+	RK3066_PLL_RATE(1728000000, 1, 72, 1),
+	RK3066_PLL_RATE(1704000000, 1, 71, 1),
+	RK3066_PLL_RATE(1680000000, 1, 70, 1),
+	RK3066_PLL_RATE(1656000000, 1, 69, 1),
+	RK3066_PLL_RATE(1632000000, 1, 68, 1),
+	RK3066_PLL_RATE(1608000000, 1, 67, 1),
+	RK3066_PLL_RATE(1560000000, 1, 65, 1),
+	RK3066_PLL_RATE(1512000000, 1, 63, 1),
+	RK3066_PLL_RATE(1488000000, 1, 62, 1),
+	RK3066_PLL_RATE(1464000000, 1, 61, 1),
+	RK3066_PLL_RATE(1440000000, 1, 60, 1),
+	RK3066_PLL_RATE(1416000000, 1, 59, 1),
+	RK3066_PLL_RATE(1392000000, 1, 58, 1),
+	RK3066_PLL_RATE(1368000000, 1, 57, 1),
+	RK3066_PLL_RATE(1344000000, 1, 56, 1),
+	RK3066_PLL_RATE(1320000000, 1, 55, 1),
+	RK3066_PLL_RATE(1296000000, 1, 54, 1),
+	RK3066_PLL_RATE(1272000000, 1, 53, 1),
+	RK3066_PLL_RATE(1248000000, 1, 52, 1),
+	RK3066_PLL_RATE(1224000000, 1, 51, 1),
+	RK3066_PLL_RATE(1200000000, 1, 50, 1),
+	RK3066_PLL_RATE(1176000000, 1, 49, 1),
+	RK3066_PLL_RATE(1128000000, 1, 47, 1),
+	RK3066_PLL_RATE(1104000000, 1, 46, 1),
+	RK3066_PLL_RATE(1008000000, 1, 84, 2),
+	RK3066_PLL_RATE( 912000000, 1, 76, 2),
+	RK3066_PLL_RATE( 888000000, 1, 74, 2),
+	RK3066_PLL_RATE( 816000000, 1, 68, 2),
+	RK3066_PLL_RATE( 792000000, 1, 66, 2),
+	RK3066_PLL_RATE( 696000000, 1, 58, 2),
+	RK3066_PLL_RATE( 672000000, 1, 56, 2),
+	RK3066_PLL_RATE( 648000000, 1, 54, 2),
+	RK3066_PLL_RATE( 624000000, 1, 52, 2),
+	RK3066_PLL_RATE( 600000000, 1, 50, 2),
+	RK3066_PLL_RATE( 576000000, 1, 48, 2),
+	RK3066_PLL_RATE( 552000000, 1, 46, 2),
+	RK3066_PLL_RATE( 528000000, 1, 88, 4),
+	RK3066_PLL_RATE( 504000000, 1, 84, 4),
+	RK3066_PLL_RATE( 480000000, 1, 80, 4),
+	RK3066_PLL_RATE( 456000000, 1, 76, 4),
+	RK3066_PLL_RATE( 408000000, 1, 68, 4),
+	RK3066_PLL_RATE( 312000000, 1, 52, 4),
+	RK3066_PLL_RATE( 252000000, 1, 84, 8),
+	RK3066_PLL_RATE( 216000000, 1, 72, 8),
+	RK3066_PLL_RATE( 126000000, 2, 84, 8),
+	RK3066_PLL_RATE(  48000000, 2, 32, 8),
+	{ /* sentinel */ },
+};
+
+PNAME(mux_pll_p)		= { "xin24m", "xin32k" };
+PNAME(mux_armclkb_p)		= { "apllb_core", "gpllb_core" };
+PNAME(mux_armclkl_p)		= { "aplll_core", "gplll_core" };
+PNAME(mux_ddrphy_p)		= { "dpll_ddr", "gpll_ddr" };
+PNAME(mux_cs_src_p)		= { "apllb_cs", "aplll_cs", "gpll_cs"};
+PNAME(mux_aclk_bus_src_p)	= { "cpll_aclk_bus", "gpll_aclk_bus" };
+
+PNAME(mux_pll_src_cpll_gpll_p)		= { "cpll", "gpll" };
+PNAME(mux_pll_src_cpll_gpll_npll_p)	= { "cpll", "gpll", "npll" };
+PNAME(mux_pll_src_npll_cpll_gpll_p)	= { "npll", "cpll", "gpll" };
+PNAME(mux_pll_src_cpll_gpll_usb_p)	= { "cpll", "gpll", "usbphy_480m" };
+PNAME(mux_pll_src_cpll_gpll_usb_usb_p)	= { "cpll", "gpll", "usbphy_480m",
+					    "usbphy_480m" };
+PNAME(mux_pll_src_cpll_gpll_usb_npll_p)	= { "cpll", "gpll", "usbphy_480m",
+					    "npll" };
+PNAME(mux_pll_src_cpll_gpll_npll_npll_p) = { "cpll", "gpll", "npll", "npll" };
+PNAME(mux_pll_src_cpll_gpll_npll_usb_p) = { "cpll", "gpll", "npll",
+					    "usbphy_480m" };
+
+PNAME(mux_i2s_8ch_pre_p)	= { "i2s_8ch_src", "i2s_8ch_frac",
+				    "ext_i2s", "xin12m" };
+PNAME(mux_i2s_8ch_clkout_p)	= { "i2s_8ch_pre", "xin12m" };
+PNAME(mux_i2s_2ch_p)		= { "i2s_2ch_src", "i2s_2ch_frac",
+				    "dummy", "xin12m" };
+PNAME(mux_spdif_8ch_p)		= { "spdif_8ch_pre", "spdif_8ch_frac",
+				    "ext_i2s", "xin12m" };
+PNAME(mux_edp_24m_p)		= { "dummy", "xin24m" };
+PNAME(mux_vip_out_p)		= { "vip_src", "xin24m" };
+PNAME(mux_usbphy480m_p)		= { "usbotg_out", "xin24m" };
+PNAME(mux_hsic_usbphy480m_p)	= { "usbotg_out", "dummy" };
+PNAME(mux_hsicphy480m_p)	= { "cpll", "gpll", "usbphy_480m" };
+PNAME(mux_uart0_p)		= { "uart0_src", "uart0_frac", "xin24m" };
+PNAME(mux_uart1_p)		= { "uart1_src", "uart1_frac", "xin24m" };
+PNAME(mux_uart2_p)		= { "uart2_src", "xin24m" };
+PNAME(mux_uart3_p)		= { "uart3_src", "uart3_frac", "xin24m" };
+PNAME(mux_uart4_p)		= { "uart4_src", "uart4_frac", "xin24m" };
+PNAME(mux_mac_p)		= { "mac_pll_src", "ext_gmac" };
+PNAME(mux_mmc_src_p)		= { "cpll", "gpll", "usbphy_480m", "xin24m" };
+
+static struct rockchip_pll_clock rk3368_pll_clks[] __initdata = {
+	[apllb] = PLL(pll_rk3066, PLL_APLLB, "apllb", mux_pll_p, 0, RK3368_PLL_CON(0),
+		     RK3368_PLL_CON(3), 8, 1, 0, rk3368_pll_rates),
+	[aplll] = PLL(pll_rk3066, PLL_APLLL, "aplll", mux_pll_p, 0, RK3368_PLL_CON(4),
+		     RK3368_PLL_CON(7), 8, 0, 0, rk3368_pll_rates),
+	[dpll] = PLL(pll_rk3066, PLL_DPLL, "dpll", mux_pll_p, 0, RK3368_PLL_CON(8),
+		     RK3368_PLL_CON(11), 8, 2, 0, NULL),
+	[cpll] = PLL(pll_rk3066, PLL_CPLL, "cpll", mux_pll_p, 0, RK3368_PLL_CON(12),
+		     RK3368_PLL_CON(15), 8, 3, ROCKCHIP_PLL_SYNC_RATE, rk3368_pll_rates),
+	[gpll] = PLL(pll_rk3066, PLL_GPLL, "gpll", mux_pll_p, 0, RK3368_PLL_CON(16),
+		     RK3368_PLL_CON(19), 8, 4, ROCKCHIP_PLL_SYNC_RATE, rk3368_pll_rates),
+	[npll] = PLL(pll_rk3066, PLL_NPLL, "npll",  mux_pll_p, 0, RK3368_PLL_CON(20),
+		     RK3368_PLL_CON(23), 8, 5, ROCKCHIP_PLL_SYNC_RATE, rk3368_pll_rates),
+};
+
+static struct clk_div_table div_ddrphy_t[] = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 3, .div = 4 },
+	{ /* sentinel */ },
+};
+
+#define MFLAGS CLK_MUX_HIWORD_MASK
+#define DFLAGS CLK_DIVIDER_HIWORD_MASK
+#define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+#define IFLAGS ROCKCHIP_INVERTER_HIWORD_MASK
+
+static const struct rockchip_cpuclk_reg_data rk3368_cpuclkb_data = {
+	.core_reg = RK3368_CLKSEL_CON(0),
+	.div_core_shift = 0,
+	.div_core_mask = 0x1f,
+	.mux_core_shift = 15,
+};
+
+static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = {
+	.core_reg = RK3368_CLKSEL_CON(2),
+	.div_core_shift = 0,
+	.div_core_mask = 0x1f,
+	.mux_core_shift = 7,
+};
+
+#define RK3368_DIV_ACLKM_MASK		0x1f
+#define RK3368_DIV_ACLKM_SHIFT		8
+#define RK3368_DIV_ATCLK_MASK		0x1f
+#define RK3368_DIV_ATCLK_SHIFT		0
+#define RK3368_DIV_PCLK_DBG_MASK	0x1f
+#define RK3368_DIV_PCLK_DBG_SHIFT	8
+
+#define RK3368_CLKSEL0(_offs, _aclkm)					\
+	{								\
+		.reg = RK3288_CLKSEL_CON(0 + _offs),			\
+		.val = HIWORD_UPDATE(_aclkm, RK3368_DIV_ACLKM_MASK,	\
+				RK3368_DIV_ACLKM_SHIFT),		\
+	}
+#define RK3368_CLKSEL1(_offs, _atclk, _pdbg)				\
+	{								\
+		.reg = RK3288_CLKSEL_CON(1 + _offs),			\
+		.val = HIWORD_UPDATE(_atclk, RK3368_DIV_ATCLK_MASK,	\
+				RK3368_DIV_ATCLK_SHIFT) |		\
+		       HIWORD_UPDATE(_pdbg, RK3368_DIV_PCLK_DBG_MASK,	\
+				RK3368_DIV_PCLK_DBG_SHIFT),		\
+	}
+
+/* cluster_b: aclkm in clksel0, rest in clksel1 */
+#define RK3368_CPUCLKB_RATE(_prate, _aclkm, _atclk, _pdbg)		\
+	{								\
+		.prate = _prate,					\
+		.divs = {						\
+			RK3368_CLKSEL0(0, _aclkm),			\
+			RK3368_CLKSEL1(0, _atclk, _pdbg),		\
+		},							\
+	}
+
+/* cluster_l: aclkm in clksel2, rest in clksel3 */
+#define RK3368_CPUCLKL_RATE(_prate, _aclkm, _atclk, _pdbg)		\
+	{								\
+		.prate = _prate,					\
+		.divs = {						\
+			RK3368_CLKSEL0(2, _aclkm),			\
+			RK3368_CLKSEL1(2, _atclk, _pdbg),		\
+		},							\
+	}
+
+static struct rockchip_cpuclk_rate_table rk3368_cpuclkb_rates[] __initdata = {
+	RK3368_CPUCLKB_RATE(1512000000, 2, 6, 6),
+	RK3368_CPUCLKB_RATE(1488000000, 2, 5, 5),
+	RK3368_CPUCLKB_RATE(1416000000, 2, 5, 5),
+	RK3368_CPUCLKB_RATE(1200000000, 2, 4, 4),
+	RK3368_CPUCLKB_RATE(1008000000, 2, 4, 4),
+	RK3368_CPUCLKB_RATE( 816000000, 2, 3, 3),
+	RK3368_CPUCLKB_RATE( 696000000, 2, 3, 3),
+	RK3368_CPUCLKB_RATE( 600000000, 2, 2, 2),
+	RK3368_CPUCLKB_RATE( 408000000, 2, 2, 2),
+	RK3368_CPUCLKB_RATE( 312000000, 2, 2, 2),
+};
+
+static struct rockchip_cpuclk_rate_table rk3368_cpuclkl_rates[] __initdata = {
+	RK3368_CPUCLKL_RATE(1512000000, 2, 7, 7),
+	RK3368_CPUCLKL_RATE(1488000000, 2, 6, 6),
+	RK3368_CPUCLKL_RATE(1416000000, 2, 6, 6),
+	RK3368_CPUCLKL_RATE(1200000000, 2, 5, 5),
+	RK3368_CPUCLKL_RATE(1008000000, 2, 5, 5),
+	RK3368_CPUCLKL_RATE( 816000000, 2, 4, 4),
+	RK3368_CPUCLKL_RATE( 696000000, 2, 3, 3),
+	RK3368_CPUCLKL_RATE( 600000000, 2, 3, 3),
+	RK3368_CPUCLKL_RATE( 408000000, 2, 2, 2),
+	RK3368_CPUCLKL_RATE( 312000000, 2, 2, 2),
+};
+
+static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 2
+	 */
+
+	MUX(SCLK_USBPHY480M, "usbphy_480m", mux_usbphy480m_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(13), 8, 1, MFLAGS),
+
+	GATE(0, "apllb_core", "apllb", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 0, GFLAGS),
+	GATE(0, "gpllb_core", "gpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 1, GFLAGS),
+
+	GATE(0, "aplll_core", "aplll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 4, GFLAGS),
+	GATE(0, "gplll_core", "gpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 5, GFLAGS),
+
+	DIV(0, "aclkm_core_b", "armclkb", 0,
+			RK3368_CLKSEL_CON(0), 8, 5, DFLAGS | CLK_DIVIDER_READ_ONLY),
+	DIV(0, "atclk_core_b", "armclkb", 0,
+			RK3368_CLKSEL_CON(1), 0, 5, DFLAGS | CLK_DIVIDER_READ_ONLY),
+	DIV(0, "pclk_dbg_b", "armclkb", 0,
+			RK3368_CLKSEL_CON(1), 8, 5, DFLAGS | CLK_DIVIDER_READ_ONLY),
+
+	DIV(0, "aclkm_core_l", "armclkl", 0,
+			RK3368_CLKSEL_CON(2), 8, 5, DFLAGS | CLK_DIVIDER_READ_ONLY),
+	DIV(0, "atclk_core_l", "armclkl", 0,
+			RK3368_CLKSEL_CON(3), 0, 5, DFLAGS | CLK_DIVIDER_READ_ONLY),
+	DIV(0, "pclk_dbg_l", "armclkl", 0,
+			RK3368_CLKSEL_CON(3), 8, 5, DFLAGS | CLK_DIVIDER_READ_ONLY),
+
+	GATE(0, "apllb_cs", "apllb", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 9, GFLAGS),
+	GATE(0, "aplll_cs", "aplll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 10, GFLAGS),
+	GATE(0, "gpll_cs", "gpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(0), 8, GFLAGS),
+	COMPOSITE_NOGATE(0, "sclk_cs_pre", mux_cs_src_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(4), 6, 2, MFLAGS, 0, 5, DFLAGS),
+	COMPOSITE_NOMUX(0, "clkin_trace", "sclk_cs_pre", CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(4), 8, 5, DFLAGS,
+			RK3368_CLKGATE_CON(0), 13, GFLAGS),
+
+	COMPOSITE(0, "aclk_cci_pre", mux_pll_src_cpll_gpll_usb_npll_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(5), 6, 2, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(0), 12, GFLAGS),
+	GATE(SCLK_PVTM_CORE, "sclk_pvtm_core", "xin24m", 0, RK3368_CLKGATE_CON(7), 10, GFLAGS),
+
+	GATE(0, "dpll_ddr", "dpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(1), 8, GFLAGS),
+	GATE(0, "gpll_ddr", "gpll", 0,
+			RK3368_CLKGATE_CON(1), 9, GFLAGS),
+	COMPOSITE_NOGATE_DIVTBL(0, "ddrphy_src", mux_ddrphy_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(13), 4, 1, MFLAGS, 0, 2, DFLAGS, div_ddrphy_t),
+
+	GATE(0, "sclk_ddr", "ddrphy_div4", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(6), 14, GFLAGS),
+	GATE(0, "sclk_ddr4x", "ddrphy_src", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(6), 15, GFLAGS),
+
+	GATE(0, "gpll_aclk_bus", "gpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(1), 10, GFLAGS),
+	GATE(0, "cpll_aclk_bus", "cpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(1), 11, GFLAGS),
+	COMPOSITE_NOGATE(0, "aclk_bus_src", mux_aclk_bus_src_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(8), 7, 1, MFLAGS, 0, 5, DFLAGS),
+
+	GATE(ACLK_BUS, "aclk_bus", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(1), 0, GFLAGS),
+	COMPOSITE_NOMUX(PCLK_BUS, "pclk_bus", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(8), 12, 3, DFLAGS,
+			RK3368_CLKGATE_CON(1), 2, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_BUS, "hclk_bus", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(8), 8, 2, DFLAGS,
+			RK3368_CLKGATE_CON(1), 1, GFLAGS),
+	COMPOSITE_NOMUX(0, "sclk_crypto", "aclk_bus_src", 0,
+			RK3368_CLKSEL_CON(10), 14, 2, DFLAGS,
+			RK3368_CLKGATE_CON(7), 2, GFLAGS),
+
+	COMPOSITE(0, "fclk_mcu_src", mux_pll_src_cpll_gpll_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(12), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(1), 3, GFLAGS),
+	/*
+	 * stclk_mcu is listed as child of fclk_mcu_src in diagram 5,
+	 * but stclk_mcu has an additional own divider in diagram 2
+	 */
+	COMPOSITE_NOMUX(0, "stclk_mcu", "fclk_mcu_src", 0,
+			RK3368_CLKSEL_CON(12), 8, 3, DFLAGS,
+			RK3368_CLKGATE_CON(13), 13, GFLAGS),
+
+	COMPOSITE(0, "i2s_8ch_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(27), 12, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(6), 1, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s_8ch_frac", "i2s_8ch_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(28), 0,
+			RK3368_CLKGATE_CON(6), 2, GFLAGS),
+	MUX(0, "i2s_8ch_pre", mux_i2s_8ch_pre_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(27), 8, 2, MFLAGS),
+	COMPOSITE_NODIV(SCLK_I2S_8CH_OUT, "i2s_8ch_clkout", mux_i2s_8ch_clkout_p, 0,
+			RK3368_CLKSEL_CON(27), 15, 1, MFLAGS,
+			RK3368_CLKGATE_CON(6), 0, GFLAGS),
+	GATE(SCLK_I2S_8CH, "sclk_i2s_8ch", "i2s_8ch_pre", CLK_SET_RATE_PARENT,
+			RK3368_CLKGATE_CON(6), 3, GFLAGS),
+	COMPOSITE(0, "spdif_8ch_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(31), 12, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(6), 4, GFLAGS),
+	COMPOSITE_FRAC(0, "spdif_8ch_frac", "spdif_8ch_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(32), 0,
+			RK3368_CLKGATE_CON(6), 5, GFLAGS),
+	COMPOSITE_NODIV(SCLK_SPDIF_8CH, "sclk_spdif_8ch", mux_spdif_8ch_p, 0,
+			RK3368_CLKSEL_CON(31), 8, 2, MFLAGS,
+			RK3368_CLKGATE_CON(6), 6, GFLAGS),
+	COMPOSITE(0, "i2s_2ch_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(53), 12, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(5), 13, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s_2ch_frac", "i2s_2ch_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(54), 0,
+			RK3368_CLKGATE_CON(5), 14, GFLAGS),
+	COMPOSITE_NODIV(SCLK_I2S_2CH, "sclk_i2s_2ch", mux_i2s_2ch_p, 0,
+			RK3368_CLKSEL_CON(53), 8, 2, MFLAGS,
+			RK3368_CLKGATE_CON(5), 15, GFLAGS),
+
+	COMPOSITE(0, "sclk_tsp", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3368_CLKSEL_CON(46), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(6), 12, GFLAGS),
+	GATE(0, "sclk_hsadc_tsp", "ext_hsadc_tsp", 0,
+			RK3368_CLKGATE_CON(13), 7, GFLAGS),
+
+	MUX(0, "uart_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(35), 12, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart2_src", "uart_src", 0,
+			RK3368_CLKSEL_CON(37), 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(2), 4, GFLAGS),
+	MUX(SCLK_UART2, "sclk_uart2", mux_uart2_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(37), 8, 1, MFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 3
+	 */
+
+	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_usb_p, 0,
+			RK3368_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(4), 6, GFLAGS),
+	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb_p, 0,
+			RK3368_CLKSEL_CON(15), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3368_CLKGATE_CON(4), 7, GFLAGS),
+
+	/*
+	 * We introduce a virtual node of hclk_vodec_pre_v to split one clock
+	 * struct with a gate and a fix divider into two node in software.
+	 */
+	GATE(0, "hclk_video_pre_v", "aclk_vdpu", 0,
+		RK3368_CLKGATE_CON(4), 8, GFLAGS),
+
+	COMPOSITE(0, "sclk_hevc_cabac_src", mux_pll_src_cpll_gpll_npll_usb_p, 0,
+			RK3368_CLKSEL_CON(17), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(5), 1, GFLAGS),
+	COMPOSITE(0, "sclk_hevc_core_src", mux_pll_src_cpll_gpll_npll_usb_p, 0,
+			RK3368_CLKSEL_CON(17), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3368_CLKGATE_CON(5), 2, GFLAGS),
+
+	COMPOSITE(0, "aclk_vio0", mux_pll_src_cpll_gpll_usb_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(19), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(4), 0, GFLAGS),
+	DIV(0, "hclk_vio", "aclk_vio0", 0,
+			RK3368_CLKSEL_CON(21), 0, 5, DFLAGS),
+
+	COMPOSITE(0, "aclk_rga_pre", mux_pll_src_cpll_gpll_usb_p, 0,
+			RK3368_CLKSEL_CON(18), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3368_CLKGATE_CON(4), 3, GFLAGS),
+	COMPOSITE(SCLK_RGA, "sclk_rga", mux_pll_src_cpll_gpll_usb_p, 0,
+			RK3368_CLKSEL_CON(18), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(4), 4, GFLAGS),
+
+	COMPOSITE(DCLK_VOP, "dclk_vop", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3368_CLKSEL_CON(20), 8, 2, MFLAGS, 0, 8, DFLAGS,
+			RK3368_CLKGATE_CON(4), 1, GFLAGS),
+
+	GATE(SCLK_VOP0_PWM, "sclk_vop0_pwm", "xin24m", 0,
+			RK3368_CLKGATE_CON(4), 2, GFLAGS),
+
+	COMPOSITE(SCLK_ISP, "sclk_isp", mux_pll_src_cpll_gpll_npll_npll_p, 0,
+			RK3368_CLKSEL_CON(22), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3368_CLKGATE_CON(4), 9, GFLAGS),
+
+	GATE(0, "pclk_isp_in", "ext_isp", 0,
+			RK3368_CLKGATE_CON(17), 2, GFLAGS),
+	INVERTER(PCLK_ISP, "pclk_isp", "pclk_isp_in",
+			RK3368_CLKSEL_CON(21), 6, IFLAGS),
+
+	GATE(0, "pclk_vip_in", "ext_vip", 0,
+			RK3368_CLKGATE_CON(16), 13, GFLAGS),
+	INVERTER(PCLK_VIP, "pclk_vip", "pclk_vip_in",
+			RK3368_CLKSEL_CON(21), 13, IFLAGS),
+
+	GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0,
+			RK3368_CLKGATE_CON(4), 13, GFLAGS),
+	GATE(SCLK_HDMI_CEC, "sclk_hdmi_cec", "xin32k", 0,
+			RK3368_CLKGATE_CON(5), 12, GFLAGS),
+
+	COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(21), 15, 1, MFLAGS,
+			RK3368_CLKGATE_CON(4), 5, GFLAGS),
+	COMPOSITE_NOGATE(0, "sclk_vip_out", mux_vip_out_p, 0,
+			RK3368_CLKSEL_CON(21), 14, 1, MFLAGS, 8, 5, DFLAGS),
+
+	COMPOSITE_NODIV(SCLK_EDP_24M, "sclk_edp_24m", mux_edp_24m_p, 0,
+			RK3368_CLKSEL_CON(23), 8, 1, MFLAGS,
+			RK3368_CLKGATE_CON(5), 4, GFLAGS),
+	COMPOSITE(SCLK_EDP, "sclk_edp", mux_pll_src_cpll_gpll_npll_npll_p, 0,
+			RK3368_CLKSEL_CON(23), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3368_CLKGATE_CON(5), 3, GFLAGS),
+
+	COMPOSITE(SCLK_HDCP, "sclk_hdcp", mux_pll_src_cpll_gpll_npll_npll_p, 0,
+			RK3368_CLKSEL_CON(55), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3368_CLKGATE_CON(5), 5, GFLAGS),
+
+	DIV(0, "pclk_pd_alive", "gpll", 0,
+			RK3368_CLKSEL_CON(10), 8, 5, DFLAGS),
+
+	/* sclk_timer has a gate in the sgrf */
+
+	COMPOSITE_NOMUX(0, "pclk_pd_pmu", "gpll", CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(10), 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(7), 9, GFLAGS),
+	GATE(SCLK_PVTM_PMU, "sclk_pvtm_pmu", "xin24m", 0,
+			RK3368_CLKGATE_CON(7), 3, GFLAGS),
+	COMPOSITE(0, "sclk_gpu_core_src", mux_pll_src_cpll_gpll_usb_npll_p, 0,
+			RK3368_CLKSEL_CON(14), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(4), 11, GFLAGS),
+	MUX(0, "aclk_gpu_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(14), 14, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_gpu_mem_pre", "aclk_gpu_src", 0,
+			RK3368_CLKSEL_CON(14), 8, 5, DFLAGS,
+			RK3368_CLKGATE_CON(5), 8, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_gpu_cfg_pre", "aclk_gpu_src", 0,
+			RK3368_CLKSEL_CON(16), 8, 5, DFLAGS,
+			RK3368_CLKGATE_CON(5), 9, GFLAGS),
+	GATE(SCLK_PVTM_GPU, "sclk_pvtm_gpu", "xin24m", 0,
+			RK3368_CLKGATE_CON(7), 11, GFLAGS),
+
+	COMPOSITE(0, "aclk_peri_src", mux_pll_src_cpll_gpll_p, CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(9), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(3), 0, GFLAGS),
+	COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0,
+			RK3368_CLKSEL_CON(9), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK3368_CLKGATE_CON(3), 3, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", CLK_IGNORE_UNUSED,
+			RK3368_CLKSEL_CON(9), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK3368_CLKGATE_CON(3), 2, GFLAGS),
+	GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(3), 1, GFLAGS),
+
+	GATE(0, "sclk_mipidsi_24m", "xin24m", 0, RK3368_CLKGATE_CON(4), 14, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 4
+	 */
+
+	COMPOSITE(SCLK_SPI0, "sclk_spi0", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(45), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(3), 7, GFLAGS),
+	COMPOSITE(SCLK_SPI1, "sclk_spi1", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(45), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			RK3368_CLKGATE_CON(3), 8, GFLAGS),
+	COMPOSITE(SCLK_SPI2, "sclk_spi2", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(46), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			RK3368_CLKGATE_CON(3), 9, GFLAGS),
+
+
+	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0,
+			RK3368_CLKSEL_CON(50), 8, 2, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(7), 12, GFLAGS),
+	COMPOSITE(SCLK_SDIO0, "sclk_sdio0", mux_mmc_src_p, 0,
+			RK3368_CLKSEL_CON(48), 8, 2, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(7), 13, GFLAGS),
+	COMPOSITE(SCLK_EMMC, "sclk_emmc", mux_mmc_src_p, 0,
+			RK3368_CLKSEL_CON(51), 8, 2, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(7), 15, GFLAGS),
+
+	MMC(SCLK_SDMMC_DRV,    "sdmmc_drv",    "sclk_sdmmc", RK3368_SDMMC_CON0, 1),
+	MMC(SCLK_SDMMC_SAMPLE, "sdmmc_sample", "sclk_sdmmc", RK3368_SDMMC_CON1, 0),
+
+	MMC(SCLK_SDIO0_DRV,    "sdio0_drv",    "sclk_sdio0", RK3368_SDIO0_CON0, 1),
+	MMC(SCLK_SDIO0_SAMPLE, "sdio0_sample", "sclk_sdio0", RK3368_SDIO0_CON1, 0),
+
+	MMC(SCLK_EMMC_DRV,     "emmc_drv",     "sclk_emmc",  RK3368_EMMC_CON0,  1),
+	MMC(SCLK_EMMC_SAMPLE,  "emmc_sample",  "sclk_emmc",  RK3368_EMMC_CON1,  0),
+
+	GATE(SCLK_OTGPHY0, "sclk_otgphy0", "xin24m", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(8), 1, GFLAGS),
+
+	/* pmu_grf_soc_con0[6] allows to select between xin32k and pvtm_pmu */
+	GATE(SCLK_OTG_ADP, "sclk_otg_adp", "xin32k", CLK_IGNORE_UNUSED,
+			RK3368_CLKGATE_CON(8), 4, GFLAGS),
+
+	/* pmu_grf_soc_con0[6] allows to select between xin32k and pvtm_pmu */
+	COMPOSITE_NOMUX(SCLK_TSADC, "sclk_tsadc", "xin32k", 0,
+			RK3368_CLKSEL_CON(25), 0, 6, DFLAGS,
+			RK3368_CLKGATE_CON(3), 5, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_SARADC, "sclk_saradc", "xin24m", 0,
+			RK3368_CLKSEL_CON(25), 8, 8, DFLAGS,
+			RK3368_CLKGATE_CON(3), 6, GFLAGS),
+
+	COMPOSITE(SCLK_NANDC0, "sclk_nandc0", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(47), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(7), 8, GFLAGS),
+
+	COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(52), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(6), 7, GFLAGS),
+
+	COMPOSITE(0, "uart0_src", mux_pll_src_cpll_gpll_usb_usb_p, 0,
+			RK3368_CLKSEL_CON(33), 12, 2, MFLAGS, 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(2), 0, GFLAGS),
+	COMPOSITE_FRAC(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(34), 0,
+			RK3368_CLKGATE_CON(2), 1, GFLAGS),
+	MUX(SCLK_UART0, "sclk_uart0", mux_uart0_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(33), 8, 2, MFLAGS),
+
+	COMPOSITE_NOMUX(0, "uart1_src", "uart_src", 0,
+			RK3368_CLKSEL_CON(35), 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(2), 2, GFLAGS),
+	COMPOSITE_FRAC(0, "uart1_frac", "uart1_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(36), 0,
+			RK3368_CLKGATE_CON(2), 3, GFLAGS),
+	MUX(SCLK_UART1, "sclk_uart1", mux_uart1_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(35), 8, 2, MFLAGS),
+
+	COMPOSITE_NOMUX(0, "uart3_src", "uart_src", 0,
+			RK3368_CLKSEL_CON(39), 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(2), 6, GFLAGS),
+	COMPOSITE_FRAC(0, "uart3_frac", "uart3_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(40), 0,
+			RK3368_CLKGATE_CON(2), 7, GFLAGS),
+	MUX(SCLK_UART3, "sclk_uart3", mux_uart3_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(39), 8, 2, MFLAGS),
+
+	COMPOSITE_NOMUX(0, "uart4_src", "uart_src", 0,
+			RK3368_CLKSEL_CON(41), 0, 7, DFLAGS,
+			RK3368_CLKGATE_CON(2), 8, GFLAGS),
+	COMPOSITE_FRAC(0, "uart4_frac", "uart4_src", CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(42), 0,
+			RK3368_CLKGATE_CON(2), 9, GFLAGS),
+	MUX(SCLK_UART4, "sclk_uart4", mux_uart4_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(41), 8, 2, MFLAGS),
+
+	COMPOSITE(0, "mac_pll_src", mux_pll_src_npll_cpll_gpll_p, 0,
+			RK3368_CLKSEL_CON(43), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3368_CLKGATE_CON(3), 4, GFLAGS),
+	MUX(SCLK_MAC, "mac_clk", mux_mac_p, CLK_SET_RATE_PARENT,
+			RK3368_CLKSEL_CON(43), 8, 1, MFLAGS),
+	GATE(SCLK_MACREF_OUT, "sclk_macref_out", "mac_clk", 0,
+			RK3368_CLKGATE_CON(7), 7, GFLAGS),
+	GATE(SCLK_MACREF, "sclk_macref", "mac_clk", 0,
+			RK3368_CLKGATE_CON(7), 6, GFLAGS),
+	GATE(SCLK_MAC_RX, "sclk_mac_rx", "mac_clk", 0,
+			RK3368_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(SCLK_MAC_TX, "sclk_mac_tx", "mac_clk", 0,
+			RK3368_CLKGATE_CON(7), 5, GFLAGS),
+
+	GATE(0, "jtag", "ext_jtag", 0,
+			RK3368_CLKGATE_CON(7), 0, GFLAGS),
+
+	COMPOSITE_NODIV(0, "hsic_usbphy_480m", mux_hsic_usbphy480m_p, 0,
+			RK3368_CLKSEL_CON(26), 8, 2, MFLAGS,
+			RK3368_CLKGATE_CON(8), 0, GFLAGS),
+	COMPOSITE_NODIV(SCLK_HSICPHY480M, "sclk_hsicphy480m", mux_hsicphy480m_p, 0,
+			RK3368_CLKSEL_CON(26), 12, 2, MFLAGS,
+			RK3368_CLKGATE_CON(8), 7, GFLAGS),
+	GATE(SCLK_HSICPHY12M, "sclk_hsicphy12m", "xin12m", 0,
+			RK3368_CLKGATE_CON(8), 6, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 5
+	 */
+
+	/* aclk_cci_pre gates */
+	GATE(0, "aclk_core_niu_cpup", "aclk_cci_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 4, GFLAGS),
+	GATE(0, "aclk_core_niu_cci", "aclk_cci_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 3, GFLAGS),
+	GATE(0, "aclk_cci400", "aclk_cci_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 2, GFLAGS),
+	GATE(0, "aclk_adb400m_pd_core_b", "aclk_cci_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 1, GFLAGS),
+	GATE(0, "aclk_adb400m_pd_core_l", "aclk_cci_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 0, GFLAGS),
+
+	/* aclkm_core_* gates */
+	GATE(0, "aclk_adb400s_pd_core_b", "aclkm_core_b", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(10), 0, GFLAGS),
+	GATE(0, "aclk_adb400s_pd_core_l", "aclkm_core_l", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(9), 0, GFLAGS),
+
+	/* armclk* gates */
+	GATE(0, "sclk_dbg_pd_core_b", "armclkb", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(10), 1, GFLAGS),
+	GATE(0, "sclk_dbg_pd_core_l", "armclkl", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(9), 1, GFLAGS),
+
+	/* sclk_cs_pre gates */
+	GATE(0, "sclk_dbg", "sclk_cs_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 7, GFLAGS),
+	GATE(0, "pclk_core_niu_sdbg", "sclk_cs_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 6, GFLAGS),
+	GATE(0, "hclk_core_niu_dbg", "sclk_cs_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(11), 5, GFLAGS),
+
+	/* aclk_bus gates */
+	GATE(0, "aclk_strc_sys", "aclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(12), 12, GFLAGS),
+	GATE(ACLK_DMAC_BUS, "aclk_dmac_bus", "aclk_bus", 0, RK3368_CLKGATE_CON(12), 11, GFLAGS),
+	GATE(0, "sclk_intmem1", "aclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(12), 6, GFLAGS),
+	GATE(0, "sclk_intmem0", "aclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(12), 5, GFLAGS),
+	GATE(0, "aclk_intmem", "aclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(12), 4, GFLAGS),
+	GATE(0, "aclk_gic400", "aclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(13), 9, GFLAGS),
+
+	/* sclk_ddr gates */
+	GATE(0, "nclk_ddrupctl", "sclk_ddr", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(13), 2, GFLAGS),
+
+	/* clk_hsadc_tsp is part of diagram2 */
+
+	/* fclk_mcu_src gates */
+	GATE(0, "hclk_noc_mcu", "fclk_mcu_src", 0, RK3368_CLKGATE_CON(13), 14, GFLAGS),
+	GATE(0, "fclk_mcu", "fclk_mcu_src", 0, RK3368_CLKGATE_CON(13), 12, GFLAGS),
+	GATE(0, "hclk_mcu", "fclk_mcu_src", 0, RK3368_CLKGATE_CON(13), 11, GFLAGS),
+
+	/* hclk_cpu gates */
+	GATE(HCLK_SPDIF, "hclk_spdif", "hclk_bus", 0, RK3368_CLKGATE_CON(12), 10, GFLAGS),
+	GATE(HCLK_ROM, "hclk_rom", "hclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(12), 9, GFLAGS),
+	GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_bus", 0, RK3368_CLKGATE_CON(12), 8, GFLAGS),
+	GATE(HCLK_I2S_8CH, "hclk_i2s_8ch", "hclk_bus", 0, RK3368_CLKGATE_CON(12), 7, GFLAGS),
+	GATE(HCLK_TSP, "hclk_tsp", "hclk_bus", 0, RK3368_CLKGATE_CON(13), 10, GFLAGS),
+	GATE(HCLK_CRYPTO, "hclk_crypto", "hclk_bus", 0, RK3368_CLKGATE_CON(13), 4, GFLAGS),
+	GATE(MCLK_CRYPTO, "mclk_crypto", "hclk_bus", 0, RK3368_CLKGATE_CON(13), 3, GFLAGS),
+
+	/* pclk_cpu gates */
+	GATE(PCLK_DDRPHY, "pclk_ddrphy", "pclk_bus", 0, RK3368_CLKGATE_CON(12), 14, GFLAGS),
+	GATE(PCLK_DDRUPCTL, "pclk_ddrupctl", "pclk_bus", 0, RK3368_CLKGATE_CON(12), 13, GFLAGS),
+	GATE(PCLK_I2C1, "pclk_i2c1", "pclk_bus", 0, RK3368_CLKGATE_CON(12), 3, GFLAGS),
+	GATE(PCLK_I2C0, "pclk_i2c0", "pclk_bus", 0, RK3368_CLKGATE_CON(12), 2, GFLAGS),
+	GATE(PCLK_MAILBOX, "pclk_mailbox", "pclk_bus", 0, RK3368_CLKGATE_CON(12), 1, GFLAGS),
+	GATE(PCLK_PWM0, "pclk_pwm0", "pclk_bus", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(12), 0, GFLAGS),
+	GATE(PCLK_SIM, "pclk_sim", "pclk_bus", 0, RK3368_CLKGATE_CON(13), 8, GFLAGS),
+	GATE(PCLK_PWM1, "pclk_pwm1", "pclk_bus", 0, RK3368_CLKGATE_CON(13), 6, GFLAGS),
+	GATE(PCLK_UART2, "pclk_uart2", "pclk_bus", 0, RK3368_CLKGATE_CON(13), 5, GFLAGS),
+	GATE(0, "pclk_efuse_256", "pclk_bus", 0, RK3368_CLKGATE_CON(13), 1, GFLAGS),
+	GATE(0, "pclk_efuse_1024", "pclk_bus", 0, RK3368_CLKGATE_CON(13), 0, GFLAGS),
+
+	/*
+	 * video clk gates
+	 * aclk_video(_pre) can actually select between parents of aclk_vdpu
+	 * and aclk_vepu by setting bit GRF_SOC_CON0[7].
+	 */
+	GATE(ACLK_VIDEO, "aclk_video", "aclk_vdpu", 0, RK3368_CLKGATE_CON(15), 0, GFLAGS),
+	GATE(SCLK_HEVC_CABAC, "sclk_hevc_cabac", "sclk_hevc_cabac_src", 0, RK3368_CLKGATE_CON(15), 3, GFLAGS),
+	GATE(SCLK_HEVC_CORE, "sclk_hevc_core", "sclk_hevc_core_src", 0, RK3368_CLKGATE_CON(15), 2, GFLAGS),
+	GATE(HCLK_VIDEO, "hclk_video", "hclk_video_pre", 0, RK3368_CLKGATE_CON(15), 1, GFLAGS),
+
+	/* aclk_rga_pre gates */
+	GATE(ACLK_VIO1_NOC, "aclk_vio1_noc", "aclk_rga_pre", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(16), 10, GFLAGS),
+	GATE(ACLK_RGA, "aclk_rga", "aclk_rga_pre", 0, RK3368_CLKGATE_CON(16), 0, GFLAGS),
+	GATE(ACLK_HDCP, "aclk_hdcp", "aclk_rga_pre", 0, RK3368_CLKGATE_CON(17), 10, GFLAGS),
+
+	/* aclk_vio0 gates */
+	GATE(ACLK_VIP, "aclk_vip", "aclk_vio0", 0, RK3368_CLKGATE_CON(16), 11, GFLAGS),
+	GATE(ACLK_VIO0_NOC, "aclk_vio0_noc", "aclk_vio0", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(16), 9, GFLAGS),
+	GATE(ACLK_VOP, "aclk_vop", "aclk_vio0", 0, RK3368_CLKGATE_CON(16), 5, GFLAGS),
+	GATE(ACLK_VOP_IEP, "aclk_vop_iep", "aclk_vio0", 0, RK3368_CLKGATE_CON(16), 4, GFLAGS),
+	GATE(ACLK_IEP, "aclk_iep", "aclk_vio0", 0, RK3368_CLKGATE_CON(16), 2, GFLAGS),
+
+	/* sclk_isp gates */
+	GATE(HCLK_ISP, "hclk_isp", "sclk_isp", 0, RK3368_CLKGATE_CON(16), 14, GFLAGS),
+	GATE(ACLK_ISP, "aclk_isp", "sclk_isp", 0, RK3368_CLKGATE_CON(17), 0, GFLAGS),
+
+	/* hclk_vio gates */
+	GATE(HCLK_VIP, "hclk_vip", "hclk_vio", 0, RK3368_CLKGATE_CON(16), 12, GFLAGS),
+	GATE(HCLK_VIO_NOC, "hclk_vio_noc", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(16), 8, GFLAGS),
+	GATE(HCLK_VIO_AHB_ARBI, "hclk_vio_ahb_arbi", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(16), 7, GFLAGS),
+	GATE(HCLK_VOP, "hclk_vop", "hclk_vio", 0, RK3368_CLKGATE_CON(16), 6, GFLAGS),
+	GATE(HCLK_IEP, "hclk_iep", "hclk_vio", 0, RK3368_CLKGATE_CON(16), 3, GFLAGS),
+	GATE(HCLK_RGA, "hclk_rga", "hclk_vio", 0, RK3368_CLKGATE_CON(16), 1, GFLAGS),
+	GATE(HCLK_VIO_HDCPMMU, "hclk_hdcpmmu", "hclk_vio", 0, RK3368_CLKGATE_CON(17), 12, GFLAGS),
+	GATE(HCLK_VIO_H2P, "hclk_vio_h2p", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 7, GFLAGS),
+
+	/*
+	 * pclk_vio gates
+	 * pclk_vio comes from the exactly same source as hclk_vio
+	 */
+	GATE(PCLK_HDCP, "pclk_hdcp", "hclk_vio", 0, RK3368_CLKGATE_CON(17), 11, GFLAGS),
+	GATE(PCLK_EDP_CTRL, "pclk_edp_ctrl", "hclk_vio", 0, RK3368_CLKGATE_CON(17), 9, GFLAGS),
+	GATE(PCLK_VIO_H2P, "pclk_vio_h2p", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 8, GFLAGS),
+	GATE(PCLK_HDMI_CTRL, "pclk_hdmi_ctrl", "hclk_vio", 0, RK3368_CLKGATE_CON(17), 6, GFLAGS),
+	GATE(PCLK_MIPI_CSI, "pclk_mipi_csi", "hclk_vio", 0, RK3368_CLKGATE_CON(17), 4, GFLAGS),
+	GATE(PCLK_MIPI_DSI0, "pclk_mipi_dsi0", "hclk_vio", 0, RK3368_CLKGATE_CON(17), 3, GFLAGS),
+
+	/* ext_vip gates in diagram3 */
+
+	/* gpu gates */
+	GATE(SCLK_GPU_CORE, "sclk_gpu_core", "sclk_gpu_core_src", 0, RK3368_CLKGATE_CON(18), 2, GFLAGS),
+	GATE(ACLK_GPU_MEM, "aclk_gpu_mem", "aclk_gpu_mem_pre", 0, RK3368_CLKGATE_CON(18), 1, GFLAGS),
+	GATE(ACLK_GPU_CFG, "aclk_gpu_cfg", "aclk_gpu_cfg_pre", 0, RK3368_CLKGATE_CON(18), 0, GFLAGS),
+
+	/* aclk_peri gates */
+	GATE(ACLK_DMAC_PERI, "aclk_dmac_peri", "aclk_peri", 0, RK3368_CLKGATE_CON(19), 3, GFLAGS),
+	GATE(0, "aclk_peri_axi_matrix", "aclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(19), 2, GFLAGS),
+	GATE(HCLK_SFC, "hclk_sfc", "aclk_peri", 0, RK3368_CLKGATE_CON(20), 15, GFLAGS),
+	GATE(ACLK_GMAC, "aclk_gmac", "aclk_peri", 0, RK3368_CLKGATE_CON(20), 13, GFLAGS),
+	GATE(0, "aclk_peri_niu", "aclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 8, GFLAGS),
+	GATE(ACLK_PERI_MMU, "aclk_peri_mmu", "aclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(21), 4, GFLAGS),
+
+	/* hclk_peri gates */
+	GATE(0, "hclk_peri_axi_matrix", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(19), 0, GFLAGS),
+	GATE(HCLK_NANDC0, "hclk_nandc0", "hclk_peri", 0, RK3368_CLKGATE_CON(20), 11, GFLAGS),
+	GATE(0, "hclk_mmc_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 10, GFLAGS),
+	GATE(0, "hclk_emem_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 9, GFLAGS),
+	GATE(0, "hclk_peri_ahb_arbi", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 7, GFLAGS),
+	GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 6, GFLAGS),
+	GATE(HCLK_HSIC, "hclk_hsic", "hclk_peri", 0, RK3368_CLKGATE_CON(20), 5, GFLAGS),
+	GATE(HCLK_HOST1, "hclk_host1", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 4, GFLAGS),
+	GATE(HCLK_HOST0, "hclk_host0", "hclk_peri", 0, RK3368_CLKGATE_CON(20), 3, GFLAGS),
+	GATE(0, "pmu_hclk_otg0", "hclk_peri", 0, RK3368_CLKGATE_CON(20), 2, GFLAGS),
+	GATE(HCLK_OTG0, "hclk_otg0", "hclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(20), 1, GFLAGS),
+	GATE(HCLK_HSADC, "hclk_hsadc", "hclk_peri", 0, RK3368_CLKGATE_CON(21), 3, GFLAGS),
+	GATE(HCLK_EMMC, "hclk_emmc", "hclk_peri", 0, RK3368_CLKGATE_CON(21), 2, GFLAGS),
+	GATE(HCLK_SDIO0, "hclk_sdio0", "hclk_peri", 0, RK3368_CLKGATE_CON(21), 1, GFLAGS),
+	GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_peri", 0, RK3368_CLKGATE_CON(21), 0, GFLAGS),
+
+	/* pclk_peri gates */
+	GATE(PCLK_SARADC, "pclk_saradc", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 15, GFLAGS),
+	GATE(PCLK_I2C5, "pclk_i2c5", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 14, GFLAGS),
+	GATE(PCLK_I2C4, "pclk_i2c4", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 13, GFLAGS),
+	GATE(PCLK_I2C3, "pclk_i2c3", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 12, GFLAGS),
+	GATE(PCLK_I2C2, "pclk_i2c2", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 11, GFLAGS),
+	GATE(PCLK_UART4, "pclk_uart4", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 10, GFLAGS),
+	GATE(PCLK_UART3, "pclk_uart3", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 9, GFLAGS),
+	GATE(PCLK_UART1, "pclk_uart1", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 8, GFLAGS),
+	GATE(PCLK_UART0, "pclk_uart0", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 7, GFLAGS),
+	GATE(PCLK_SPI2, "pclk_spi2", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 6, GFLAGS),
+	GATE(PCLK_SPI1, "pclk_spi1", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 5, GFLAGS),
+	GATE(PCLK_SPI0, "pclk_spi0", "pclk_peri", 0, RK3368_CLKGATE_CON(19), 4, GFLAGS),
+	GATE(0, "pclk_peri_axi_matrix", "pclk_peri", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(19), 1, GFLAGS),
+	GATE(PCLK_GMAC, "pclk_gmac", "pclk_peri", 0, RK3368_CLKGATE_CON(20), 14, GFLAGS),
+	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_peri", 0, RK3368_CLKGATE_CON(20), 0, GFLAGS),
+
+	/* pclk_pd_alive gates */
+	GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 8, GFLAGS),
+	GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 7, GFLAGS),
+	GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 12, GFLAGS),
+	GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 11, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 3, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 2, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 1, GFLAGS),
+
+	/*
+	 * pclk_vio gates
+	 * pclk_vio comes from the exactly same source as hclk_vio
+	 */
+	GATE(0, "pclk_dphyrx", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 8, GFLAGS),
+	GATE(0, "pclk_dphytx", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 8, GFLAGS),
+
+	/* pclk_pd_pmu gates */
+	GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 0, GFLAGS),
+	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(17), 4, GFLAGS),
+	GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 3, GFLAGS),
+	GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS),
+	GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 1, GFLAGS),
+	GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS),
+
+	/* timer gates */
+	GATE(0, "sclk_timer15", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 11, GFLAGS),
+	GATE(0, "sclk_timer14", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 10, GFLAGS),
+	GATE(0, "sclk_timer13", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 9, GFLAGS),
+	GATE(0, "sclk_timer12", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 8, GFLAGS),
+	GATE(0, "sclk_timer11", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 7, GFLAGS),
+	GATE(0, "sclk_timer10", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 6, GFLAGS),
+	GATE(0, "sclk_timer05", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 5, GFLAGS),
+	GATE(0, "sclk_timer04", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 4, GFLAGS),
+	GATE(0, "sclk_timer03", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 3, GFLAGS),
+	GATE(0, "sclk_timer02", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 2, GFLAGS),
+	GATE(0, "sclk_timer01", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 1, GFLAGS),
+	GATE(0, "sclk_timer00", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 0, GFLAGS),
+};
+
+static void __init rk3368_clk_init(struct device_node *np)
+{
+	void __iomem *reg_base;
+	struct clk *clk;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru region\n", __func__);
+		return;
+	}
+
+	rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
+
+	/* xin12m is created by a cru-internal divider */
+	clk = clk_register_fixed_factor(NULL, "xin12m", "xin24m", 0, 1, 2);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock xin12m: %ld\n",
+			__func__, PTR_ERR(clk));
+
+	/* ddrphy_div4 is created by a cru-internal divider */
+	clk = clk_register_fixed_factor(NULL, "ddrphy_div4", "ddrphy_src", 0, 1, 4);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock xin12m: %ld\n",
+			__func__, PTR_ERR(clk));
+
+	clk = clk_register_fixed_factor(NULL, "hclk_video_pre",
+					"hclk_video_pre_v", 0, 1, 4);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock hclk_vcodec_pre: %ld\n",
+			__func__, PTR_ERR(clk));
+
+	/* Watchdog pclk is controlled by sgrf_soc_con3[7]. */
+	clk = clk_register_fixed_factor(NULL, "pclk_wdt", "pclk_pd_alive", 0, 1, 1);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock pclk_wdt: %ld\n",
+			__func__, PTR_ERR(clk));
+	else
+		rockchip_clk_add_lookup(clk, PCLK_WDT);
+
+	rockchip_clk_register_plls(rk3368_pll_clks,
+				   ARRAY_SIZE(rk3368_pll_clks),
+				   RK3368_GRF_SOC_STATUS0);
+	rockchip_clk_register_branches(rk3368_clk_branches,
+				  ARRAY_SIZE(rk3368_clk_branches));
+
+	rockchip_clk_register_armclk(ARMCLKB, "armclkb",
+			mux_armclkb_p, ARRAY_SIZE(mux_armclkb_p),
+			&rk3368_cpuclkb_data, rk3368_cpuclkb_rates,
+			ARRAY_SIZE(rk3368_cpuclkb_rates));
+
+	rockchip_clk_register_armclk(ARMCLKL, "armclkl",
+			mux_armclkl_p, ARRAY_SIZE(mux_armclkl_p),
+			&rk3368_cpuclkl_data, rk3368_cpuclkl_rates,
+			ARRAY_SIZE(rk3368_cpuclkl_rates));
+
+	rockchip_register_softrst(np, 15, reg_base + RK3368_SOFTRST_CON(0),
+				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+
+	rockchip_register_restart_notifier(RK3368_GLB_SRST_FST);
+}
+CLK_OF_DECLARE(rk3368_cru, "rockchip,rk3368-cru", rk3368_clk_init);
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index 052b94db0ff9..24938815655f 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -277,6 +277,13 @@ void __init rockchip_clk_register_branches(
 				list->div_shift
 			);
 			break;
+		case branch_inverter:
+			clk = rockchip_clk_register_inverter(
+				list->name, list->parent_names,
+				list->num_parents,
+				reg_base + list->muxdiv_offset,
+				list->div_shift, list->div_flags, &clk_lock);
+			break;
 		}
 
 		/* none of the cases above matched */
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index 6b092673048a..dc8ecb2673b7 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -24,29 +24,29 @@
 #define CLK_ROCKCHIP_CLK_H
 
 #include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/clk-provider.h>
+
+struct clk;
 
 #define HIWORD_UPDATE(val, mask, shift) \
 		((val) << (shift) | (mask) << ((shift) + 16))
 
 /* register positions shared by RK2928, RK3066 and RK3188 */
-#define RK2928_PLL_CON(x)		(x * 0x4)
+#define RK2928_PLL_CON(x)		((x) * 0x4)
 #define RK2928_MODE_CON		0x40
-#define RK2928_CLKSEL_CON(x)	(x * 0x4 + 0x44)
-#define RK2928_CLKGATE_CON(x)	(x * 0x4 + 0xd0)
+#define RK2928_CLKSEL_CON(x)	((x) * 0x4 + 0x44)
+#define RK2928_CLKGATE_CON(x)	((x) * 0x4 + 0xd0)
 #define RK2928_GLB_SRST_FST		0x100
 #define RK2928_GLB_SRST_SND		0x104
-#define RK2928_SOFTRST_CON(x)	(x * 0x4 + 0x110)
+#define RK2928_SOFTRST_CON(x)	((x) * 0x4 + 0x110)
 #define RK2928_MISC_CON		0x134
 
 #define RK3288_PLL_CON(x)		RK2928_PLL_CON(x)
 #define RK3288_MODE_CON			0x50
-#define RK3288_CLKSEL_CON(x)		(x * 0x4 + 0x60)
-#define RK3288_CLKGATE_CON(x)		(x * 0x4 + 0x160)
+#define RK3288_CLKSEL_CON(x)		((x) * 0x4 + 0x60)
+#define RK3288_CLKGATE_CON(x)		((x) * 0x4 + 0x160)
 #define RK3288_GLB_SRST_FST		0x1b0
 #define RK3288_GLB_SRST_SND		0x1b4
-#define RK3288_SOFTRST_CON(x)		(x * 0x4 + 0x1b8)
+#define RK3288_SOFTRST_CON(x)		((x) * 0x4 + 0x1b8)
 #define RK3288_MISC_CON			0x1e8
 #define RK3288_SDMMC_CON0		0x200
 #define RK3288_SDMMC_CON1		0x204
@@ -57,6 +57,22 @@
 #define RK3288_EMMC_CON0		0x218
 #define RK3288_EMMC_CON1		0x21c
 
+#define RK3368_PLL_CON(x)		RK2928_PLL_CON(x)
+#define RK3368_CLKSEL_CON(x)		((x) * 0x4 + 0x100)
+#define RK3368_CLKGATE_CON(x)		((x) * 0x4 + 0x200)
+#define RK3368_GLB_SRST_FST		0x280
+#define RK3368_GLB_SRST_SND		0x284
+#define RK3368_SOFTRST_CON(x)		((x) * 0x4 + 0x300)
+#define RK3368_MISC_CON			0x380
+#define RK3368_SDMMC_CON0		0x400
+#define RK3368_SDMMC_CON1		0x404
+#define RK3368_SDIO0_CON0		0x408
+#define RK3368_SDIO0_CON1		0x40c
+#define RK3368_SDIO1_CON0		0x410
+#define RK3368_SDIO1_CON1		0x414
+#define RK3368_EMMC_CON0		0x418
+#define RK3368_EMMC_CON1		0x41c
+
 enum rockchip_pll_type {
 	pll_rk3066,
 };
@@ -67,16 +83,16 @@ enum rockchip_pll_type {
 	.nr = _nr,				\
 	.nf = _nf,				\
 	.no = _no,				\
-	.bwadj = (_nf >> 1),			\
+	.nb = ((_nf) < 2) ? 1 : (_nf) >> 1,	\
 }
 
-#define RK3066_PLL_RATE_BWADJ(_rate, _nr, _nf, _no, _bw)	\
+#define RK3066_PLL_RATE_NB(_rate, _nr, _nf, _no, _nb)		\
 {								\
 	.rate	= _rate##U,					\
 	.nr = _nr,						\
 	.nf = _nf,						\
 	.no = _no,						\
-	.bwadj = _bw,						\
+	.nb = _nb,						\
 }
 
 struct rockchip_pll_rate_table {
@@ -84,7 +100,7 @@ struct rockchip_pll_rate_table {
 	unsigned int nr;
 	unsigned int nf;
 	unsigned int no;
-	unsigned int bwadj;
+	unsigned int nb;
 };
 
 /**
@@ -182,6 +198,13 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 				const char *const *parent_names, u8 num_parents,
 				void __iomem *reg, int shift);
 
+#define ROCKCHIP_INVERTER_HIWORD_MASK	BIT(0)
+
+struct clk *rockchip_clk_register_inverter(const char *name,
+				const char *const *parent_names, u8 num_parents,
+				void __iomem *reg, int shift, int flags,
+				spinlock_t *lock);
+
 #define PNAME(x) static const char *const x[] __initconst
 
 enum rockchip_clk_branch_type {
@@ -191,6 +214,7 @@ enum rockchip_clk_branch_type {
 	branch_fraction_divider,
 	branch_gate,
 	branch_mmc,
+	branch_inverter,
 };
 
 struct rockchip_clk_branch {
@@ -308,6 +332,26 @@ struct rockchip_clk_branch {
 		.gate_offset	= -1,				\
 	}
 
+#define COMPOSITE_NOGATE_DIVTBL(_id, cname, pnames, f, mo, ms,	\
+				mw, mf, ds, dw, df, dt)		\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_composite,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.div_table	= dt,				\
+		.gate_offset	= -1,				\
+	}
+
 #define COMPOSITE_FRAC(_id, cname, pname, f, mo, df, go, gs, gf)\
 	{							\
 		.id		= _id,				\
@@ -394,6 +438,18 @@ struct rockchip_clk_branch {
 		.div_shift	= shift,			\
 	}
 
+#define INVERTER(_id, cname, pname, io, is, if)			\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_inverter,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.muxdiv_offset	= io,				\
+		.div_shift	= is,				\
+		.div_flags	= if,				\
+	}
+
 void rockchip_clk_init(struct device_node *np, void __iomem *base,
 		       unsigned long nr_clks);
 struct regmap *rockchip_clk_get_grf(void);
diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c
index 3a1fe07cfe9e..7c1e1f58e2da 100644
--- a/drivers/clk/samsung/clk-cpu.c
+++ b/drivers/clk/samsung/clk-cpu.c
@@ -33,6 +33,9 @@
 */
 
 #include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include "clk-cpu.h"
 
 #define E4210_SRC_CPU		0x0
@@ -97,8 +100,8 @@ static void wait_until_mux_stable(void __iomem *mux_reg, u32 mux_pos,
 static long exynos_cpuclk_round_rate(struct clk_hw *hw,
 			unsigned long drate, unsigned long *prate)
 {
-	struct clk *parent = __clk_get_parent(hw->clk);
-	*prate = __clk_round_rate(parent, drate);
+	struct clk_hw *parent = clk_hw_get_parent(hw);
+	*prate = clk_hw_round_rate(parent, drate);
 	return *prate;
 }
 
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 454b02ae486a..4e9584d79089 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -9,8 +9,9 @@
  * Common Clock Framework support for Audio Subsystem Clock Controller.
 */
 
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/io.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c
index 03a52228b6d1..7cd02ff37a1f 100644
--- a/drivers/clk/samsung/clk-exynos-clkout.c
+++ b/drivers/clk/samsung/clk-exynos-clkout.c
@@ -9,8 +9,8 @@
  * Clock driver for Exynos clock output
  */
 
+#include <linux/slab.h>
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-exynos3250.c b/drivers/clk/samsung/clk-exynos3250.c
index 538de66a759e..fdd41b17a24f 100644
--- a/drivers/clk/samsung/clk-exynos3250.c
+++ b/drivers/clk/samsung/clk-exynos3250.c
@@ -8,8 +8,6 @@
  * Common Clock Framework support for Exynos3250 SoC.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -19,6 +17,7 @@
 #include <dt-bindings/clock/exynos3250.h>
 
 #include "clk.h"
+#include "clk-cpu.h"
 #include "clk-pll.h"
 
 #define SRC_LEFTBUS		0x4200
@@ -319,8 +318,10 @@ static struct samsung_mux_clock mux_clks[] __initdata = {
 	MUX(CLK_MOUT_MPLL_USER_C, "mout_mpll_user_c", mout_mpll_user_p,
 	    SRC_CPU, 24, 1),
 	MUX(CLK_MOUT_HPM, "mout_hpm", mout_hpm_p, SRC_CPU, 20, 1),
-	MUX(CLK_MOUT_CORE, "mout_core", mout_core_p, SRC_CPU, 16, 1),
-	MUX(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1),
+	MUX_F(CLK_MOUT_CORE, "mout_core", mout_core_p, SRC_CPU, 16, 1,
+			CLK_SET_RATE_PARENT, 0),
+	MUX_F(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
+			CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_div_clock div_clks[] __initdata = {
@@ -772,6 +773,26 @@ static struct samsung_cmu_info cmu_info __initdata = {
 	.nr_clk_regs		= ARRAY_SIZE(exynos3250_cmu_clk_regs),
 };
 
+#define E3250_CPU_DIV0(apll, pclk_dbg, atb, corem)			\
+		(((apll) << 24) | ((pclk_dbg) << 20) | ((atb) << 16) |	\
+		((corem) << 4))
+#define E3250_CPU_DIV1(hpm, copy)					\
+		(((hpm) << 4) | ((copy) << 0))
+
+static const struct exynos_cpuclk_cfg_data e3250_armclk_d[] __initconst = {
+	{ 1000000, E3250_CPU_DIV0(1, 7, 4, 1), E3250_CPU_DIV1(7, 7), },
+	{  900000, E3250_CPU_DIV0(1, 7, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  800000, E3250_CPU_DIV0(1, 7, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  700000, E3250_CPU_DIV0(1, 7, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  600000, E3250_CPU_DIV0(1, 7, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  500000, E3250_CPU_DIV0(1, 7, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  400000, E3250_CPU_DIV0(1, 7, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  300000, E3250_CPU_DIV0(1, 5, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  200000, E3250_CPU_DIV0(1, 3, 3, 1), E3250_CPU_DIV1(7, 7), },
+	{  100000, E3250_CPU_DIV0(1, 1, 1, 1), E3250_CPU_DIV1(7, 7), },
+	{  0 },
+};
+
 static void __init exynos3250_cmu_init(struct device_node *np)
 {
 	struct samsung_clk_provider *ctx;
@@ -780,6 +801,11 @@ static void __init exynos3250_cmu_init(struct device_node *np)
 	if (!ctx)
 		return;
 
+	exynos_register_cpu_clock(ctx, CLK_ARM_CLK, "armclk",
+			mout_core_p[0], mout_core_p[1], 0x14200,
+			e3250_armclk_d, ARRAY_SIZE(e3250_armclk_d),
+			CLK_CPU_HAS_DIV1);
+
 	exynos3_core_down_clock(ctx->reg_base);
 }
 CLK_OF_DECLARE(exynos3250_cmu, "samsung,exynos3250-cmu", exynos3250_cmu_init);
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index cae2c048488d..251f48dcd12d 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -11,8 +11,8 @@
 */
 
 #include <dt-bindings/clock/exynos4.h>
+#include <linux/slab.h>
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -86,6 +86,7 @@
 #define DIV_PERIL4		0xc560
 #define DIV_PERIL5		0xc564
 #define E4X12_DIV_CAM1		0xc568
+#define E4X12_GATE_BUS_FSYS1	0xc744
 #define GATE_SCLK_CAM		0xc820
 #define GATE_IP_CAM		0xc920
 #define GATE_IP_TV		0xc924
@@ -1097,6 +1098,7 @@ static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 		0),
 	GATE(CLK_PPMUIMAGE, "ppmuimage", "aclk200", E4X12_GATE_IP_IMAGE, 9, 0,
 		0),
+	GATE(CLK_TSADC, "tsadc", "aclk133", E4X12_GATE_BUS_FSYS1, 16, 0, 0),
 	GATE(CLK_MIPI_HSI, "mipi_hsi", "aclk133", GATE_IP_FSYS, 10, 0, 0),
 	GATE(CLK_CHIPID, "chipid", "aclk100", E4X12_GATE_IP_PERIR, 0, 0, 0),
 	GATE(CLK_SYSREG, "sysreg", "aclk100", E4X12_GATE_IP_PERIR, 1,
diff --git a/drivers/clk/samsung/clk-exynos4415.c b/drivers/clk/samsung/clk-exynos4415.c
index 6c78b09c829f..92c39f6efec8 100644
--- a/drivers/clk/samsung/clk-exynos4415.c
+++ b/drivers/clk/samsung/clk-exynos4415.c
@@ -9,8 +9,6 @@
  * Common Clock Framework support for Exynos4415 SoC.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 70ec3d2608a1..55b83c7ef878 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -11,14 +11,13 @@
 */
 
 #include <dt-bindings/clock/exynos5250.h>
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
 
 #include "clk.h"
+#include "clk-cpu.h"
 
 #define APLL_LOCK		0x0
 #define APLL_CON0		0x100
@@ -748,6 +747,32 @@ static struct samsung_pll_clock exynos5250_plls[nr_plls] __initdata = {
 		VPLL_LOCK, VPLL_CON0, NULL),
 };
 
+#define E5250_CPU_DIV0(apll, pclk_dbg, atb, periph, acp, cpud)		\
+		((((apll) << 24) | ((pclk_dbg) << 20) | ((atb) << 16) |	\
+		 ((periph) << 12) | ((acp) << 8) | ((cpud) << 4)))
+#define E5250_CPU_DIV1(hpm, copy)					\
+		(((hpm) << 4) | (copy))
+
+static const struct exynos_cpuclk_cfg_data exynos5250_armclk_d[] __initconst = {
+	{ 1700000, E5250_CPU_DIV0(5, 3, 7, 7, 7, 3), E5250_CPU_DIV1(2, 0), },
+	{ 1600000, E5250_CPU_DIV0(4, 1, 7, 7, 7, 3), E5250_CPU_DIV1(2, 0), },
+	{ 1500000, E5250_CPU_DIV0(4, 1, 7, 7, 7, 2), E5250_CPU_DIV1(2, 0), },
+	{ 1400000, E5250_CPU_DIV0(4, 1, 6, 7, 7, 2), E5250_CPU_DIV1(2, 0), },
+	{ 1300000, E5250_CPU_DIV0(3, 1, 6, 7, 7, 2), E5250_CPU_DIV1(2, 0), },
+	{ 1200000, E5250_CPU_DIV0(3, 1, 5, 7, 7, 2), E5250_CPU_DIV1(2, 0), },
+	{ 1100000, E5250_CPU_DIV0(3, 1, 5, 7, 7, 3), E5250_CPU_DIV1(2, 0), },
+	{ 1000000, E5250_CPU_DIV0(2, 1, 4, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  900000, E5250_CPU_DIV0(2, 1, 4, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  800000, E5250_CPU_DIV0(2, 1, 4, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  700000, E5250_CPU_DIV0(1, 1, 3, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  600000, E5250_CPU_DIV0(1, 1, 3, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  500000, E5250_CPU_DIV0(1, 1, 2, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  400000, E5250_CPU_DIV0(1, 1, 2, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  300000, E5250_CPU_DIV0(1, 1, 1, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  200000, E5250_CPU_DIV0(1, 1, 1, 7, 7, 1), E5250_CPU_DIV1(2, 0), },
+	{  0 },
+};
+
 static const struct of_device_id ext_clk_match[] __initconst = {
 	{ .compatible = "samsung,clock-xxti", .data = (void *)0, },
 	{ },
@@ -797,6 +822,10 @@ static void __init exynos5250_clk_init(struct device_node *np)
 			ARRAY_SIZE(exynos5250_div_clks));
 	samsung_clk_register_gate(ctx, exynos5250_gate_clks,
 			ARRAY_SIZE(exynos5250_gate_clks));
+	exynos_register_cpu_clock(ctx, CLK_ARM_CLK, "armclk",
+			mout_cpu_p[0], mout_cpu_p[1], 0x200,
+			exynos5250_armclk_d, ARRAY_SIZE(exynos5250_armclk_d),
+			CLK_CPU_HAS_DIV1);
 
 	/*
 	 * Enable arm clock down (in idle) and set arm divider
diff --git a/drivers/clk/samsung/clk-exynos5260.c b/drivers/clk/samsung/clk-exynos5260.c
index 06f96eb7cf93..d1a29f6c1084 100644
--- a/drivers/clk/samsung/clk-exynos5260.c
+++ b/drivers/clk/samsung/clk-exynos5260.c
@@ -9,8 +9,6 @@
  * Common Clock Framework support for Exynos5260 SoC.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
diff --git a/drivers/clk/samsung/clk-exynos5410.c b/drivers/clk/samsung/clk-exynos5410.c
index 231475bc2b99..d5d5dcabc4a9 100644
--- a/drivers/clk/samsung/clk-exynos5410.c
+++ b/drivers/clk/samsung/clk-exynos5410.c
@@ -11,8 +11,6 @@
 
 #include <dt-bindings/clock/exynos5410.h>
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index a1d731ca8f48..389af3c15ec4 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -11,8 +11,7 @@
 */
 
 #include <dt-bindings/clock/exynos5420.h>
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 39c95649d3d0..cee062c588de 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -9,8 +9,6 @@
  * Common Clock Framework support for Exynos5443 SoC.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 
diff --git a/drivers/clk/samsung/clk-exynos5440.c b/drivers/clk/samsung/clk-exynos5440.c
index 979e81389cdd..590813871ffe 100644
--- a/drivers/clk/samsung/clk-exynos5440.c
+++ b/drivers/clk/samsung/clk-exynos5440.c
@@ -10,8 +10,6 @@
 */
 
 #include <dt-bindings/clock/exynos5440.h>
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index 03d36e847b78..8524e667097e 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -8,8 +8,6 @@
  *
 */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index bebc61b5fce1..b7dd396100d8 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -12,6 +12,8 @@
 #include <linux/errno.h>
 #include <linux/hrtimer.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/clkdev.h>
 #include "clk.h"
 #include "clk-pll.h"
 
@@ -180,7 +182,7 @@ static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -288,7 +290,7 @@ static int samsung_pll36xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -403,7 +405,7 @@ static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -455,7 +457,7 @@ static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
 
 		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
 			pr_err("%s: could not lock PLL %s\n",
-					__func__, __clk_get_name(hw->clk));
+					__func__, clk_hw_get_name(hw));
 			return -EFAULT;
 		}
 
@@ -554,7 +556,7 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -614,7 +616,7 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 
 		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
 			pr_err("%s: could not lock PLL %s\n",
-					__func__, __clk_get_name(hw->clk));
+					__func__, clk_hw_get_name(hw));
 			return -EFAULT;
 		}
 
@@ -772,7 +774,7 @@ static int samsung_s3c2410_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -1013,7 +1015,7 @@ static int samsung_pll2550xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
@@ -1111,7 +1113,7 @@ static int samsung_pll2650xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	rate = samsung_get_pll_settings(pll, drate);
 	if (!rate) {
 		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
-			drate, __clk_get_name(hw->clk));
+			drate, clk_hw_get_name(hw));
 		return -EINVAL;
 	}
 
diff --git a/drivers/clk/samsung/clk-s3c2410-dclk.c b/drivers/clk/samsung/clk-s3c2410-dclk.c
index e56df5064889..e9eb935d7616 100644
--- a/drivers/clk/samsung/clk-s3c2410-dclk.c
+++ b/drivers/clk/samsung/clk-s3c2410-dclk.c
@@ -8,6 +8,10 @@
  * Common Clock Framework support for s3c24xx external clock output.
  */
 
+#include <linux/clkdev.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
 #include "clk.h"
@@ -57,7 +61,7 @@ struct s3c24xx_clkout {
 static u8 s3c24xx_clkout_get_parent(struct clk_hw *hw)
 {
 	struct s3c24xx_clkout *clkout = to_s3c24xx_clkout(hw);
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	val = readl_relaxed(S3C24XX_MISCCR) >> clkout->shift;
diff --git a/drivers/clk/samsung/clk-s3c2410.c b/drivers/clk/samsung/clk-s3c2410.c
index 5d2f03461bc5..0945a8852299 100644
--- a/drivers/clk/samsung/clk-s3c2410.c
+++ b/drivers/clk/samsung/clk-s3c2410.c
@@ -8,8 +8,6 @@
  * Common Clock Framework support for S3C2410 and following SoCs.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-s3c2412.c b/drivers/clk/samsung/clk-s3c2412.c
index 2ceedaf8ce18..44d6a9f4f5b2 100644
--- a/drivers/clk/samsung/clk-s3c2412.c
+++ b/drivers/clk/samsung/clk-s3c2412.c
@@ -8,8 +8,6 @@
  * Common Clock Framework support for S3C2412 and S3C2413.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-s3c2443.c b/drivers/clk/samsung/clk-s3c2443.c
index 0c3c182b902a..2c0a1ea3c80c 100644
--- a/drivers/clk/samsung/clk-s3c2443.c
+++ b/drivers/clk/samsung/clk-s3c2443.c
@@ -8,8 +8,6 @@
  * Common Clock Framework support for S3C2443 and following SoCs.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c
index 0f590e5550cb..d325ed1e196b 100644
--- a/drivers/clk/samsung/clk-s3c64xx.c
+++ b/drivers/clk/samsung/clk-s3c64xx.c
@@ -8,8 +8,7 @@
  * Common Clock Framework support for all S3C64xx SoCs.
 */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-s5pv210-audss.c b/drivers/clk/samsung/clk-s5pv210-audss.c
index de4455b75e8a..eefb84b22566 100644
--- a/drivers/clk/samsung/clk-s5pv210-audss.c
+++ b/drivers/clk/samsung/clk-s5pv210-audss.c
@@ -13,8 +13,8 @@
  * Driver for Audio Subsystem Clock Controller of S5PV210-compatible SoCs.
 */
 
-#include <linux/clkdev.h>
 #include <linux/io.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
diff --git a/drivers/clk/samsung/clk-s5pv210.c b/drivers/clk/samsung/clk-s5pv210.c
index cf7e8fa7b624..759aaf342bea 100644
--- a/drivers/clk/samsung/clk-s5pv210.c
+++ b/drivers/clk/samsung/clk-s5pv210.c
@@ -11,8 +11,6 @@
  * Common Clock Framework support for all S5PC110/S5PV210 SoCs.
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -828,6 +826,8 @@ static void __init __s5pv210_clk_init(struct device_node *np,
 
 	s5pv210_clk_sleep_init();
 
+	samsung_clk_of_add_provider(np, ctx);
+
 	pr_info("%s clocks: mout_apll = %ld, mout_mpll = %ld\n"
 		"\tmout_epll = %ld, mout_vpll = %ld\n",
 		is_s5p6442 ? "S5P6442" : "S5PV210",
diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c
index 0117238391d6..f38a6c49f744 100644
--- a/drivers/clk/samsung/clk.c
+++ b/drivers/clk/samsung/clk.c
@@ -11,6 +11,10 @@
  * clock framework for Samsung platforms.
 */
 
+#include <linux/slab.h>
+#include <linux/clkdev.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
 
diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h
index b775fc29caa5..aa872d2c5105 100644
--- a/drivers/clk/samsung/clk.h
+++ b/drivers/clk/samsung/clk.h
@@ -13,10 +13,11 @@
 #ifndef __SAMSUNG_CLK_H
 #define __SAMSUNG_CLK_H
 
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include "clk-pll.h"
 
+struct clk;
+
 /**
  * struct samsung_clk_provider: information about clock provider
  * @reg_base: virtual address for the register base.
diff --git a/drivers/clk/shmobile/clk-div6.c b/drivers/clk/shmobile/clk-div6.c
index 036a692c7219..b4c8d6746f68 100644
--- a/drivers/clk/shmobile/clk-div6.c
+++ b/drivers/clk/shmobile/clk-div6.c
@@ -11,12 +11,12 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 
 #define CPG_DIV6_CKSTP		BIT(8)
 #define CPG_DIV6_DIV(d)		((d) & 0x3f)
@@ -133,13 +133,13 @@ static u8 cpg_div6_clock_get_parent(struct clk_hw *hw)
 
 	hw_index = (clk_readl(clock->reg) >> clock->src_shift) &
 		   (BIT(clock->src_width) - 1);
-	for (i = 0; i < __clk_get_num_parents(hw->clk); i++) {
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
 		if (clock->parents[i] == hw_index)
 			return i;
 	}
 
 	pr_err("%s: %s DIV6 clock set to invalid parent %u\n",
-	       __func__, __clk_get_name(hw->clk), hw_index);
+	       __func__, clk_hw_get_name(hw), hw_index);
 	return 0;
 }
 
@@ -149,7 +149,7 @@ static int cpg_div6_clock_set_parent(struct clk_hw *hw, u8 index)
 	u8 hw_index;
 	u32 mask;
 
-	if (index >= __clk_get_num_parents(hw->clk))
+	if (index >= clk_hw_get_num_parents(hw))
 		return -EINVAL;
 
 	mask = ~((BIT(clock->src_width) - 1) << clock->src_shift);
diff --git a/drivers/clk/shmobile/clk-mstp.c b/drivers/clk/shmobile/clk-mstp.c
index 2d2fe773ac81..b1df7b2f1e97 100644
--- a/drivers/clk/shmobile/clk-mstp.c
+++ b/drivers/clk/shmobile/clk-mstp.c
@@ -2,6 +2,7 @@
  * R-Car MSTP clocks
  *
  * Copyright (C) 2013 Ideas On Board SPRL
+ * Copyright (C) 2015 Glider bvba
  *
  * Contact: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
  *
@@ -10,11 +11,16 @@
  * the Free Software Foundation; version 2 of the License.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
+#include <linux/clk/shmobile.h>
+#include <linux/device.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_domain.h>
 #include <linux/spinlock.h>
 
 /*
@@ -236,3 +242,84 @@ static void __init cpg_mstp_clocks_init(struct device_node *np)
 	of_clk_add_provider(np, of_clk_src_onecell_get, &group->data);
 }
 CLK_OF_DECLARE(cpg_mstp_clks, "renesas,cpg-mstp-clocks", cpg_mstp_clocks_init);
+
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+int cpg_mstp_attach_dev(struct generic_pm_domain *domain, struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args clkspec;
+	struct clk *clk;
+	int i = 0;
+	int error;
+
+	while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i,
+					   &clkspec)) {
+		if (of_device_is_compatible(clkspec.np,
+					    "renesas,cpg-mstp-clocks"))
+			goto found;
+
+		of_node_put(clkspec.np);
+		i++;
+	}
+
+	return 0;
+
+found:
+	clk = of_clk_get_from_provider(&clkspec);
+	of_node_put(clkspec.np);
+
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	error = pm_clk_create(dev);
+	if (error) {
+		dev_err(dev, "pm_clk_create failed %d\n", error);
+		goto fail_put;
+	}
+
+	error = pm_clk_add_clk(dev, clk);
+	if (error) {
+		dev_err(dev, "pm_clk_add_clk %pC failed %d\n", clk, error);
+		goto fail_destroy;
+	}
+
+	return 0;
+
+fail_destroy:
+	pm_clk_destroy(dev);
+fail_put:
+	clk_put(clk);
+	return error;
+}
+
+void cpg_mstp_detach_dev(struct generic_pm_domain *domain, struct device *dev)
+{
+	if (!list_empty(&dev->power.subsys_data->clock_list))
+		pm_clk_destroy(dev);
+}
+
+void __init cpg_mstp_add_clk_domain(struct device_node *np)
+{
+	struct generic_pm_domain *pd;
+	u32 ncells;
+
+	if (of_property_read_u32(np, "#power-domain-cells", &ncells)) {
+		pr_warn("%s lacks #power-domain-cells\n", np->full_name);
+		return;
+	}
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return;
+
+	pd->name = np->name;
+
+	pd->flags = GENPD_FLAG_PM_CLK;
+	pm_genpd_init(pd, &simple_qos_governor, false);
+	pd->attach_dev = cpg_mstp_attach_dev;
+	pd->detach_dev = cpg_mstp_detach_dev;
+
+	of_genpd_add_provider_simple(np, pd);
+}
+#endif /* !CONFIG_PM_GENERIC_DOMAINS_OF */
diff --git a/drivers/clk/shmobile/clk-r8a73a4.c b/drivers/clk/shmobile/clk-r8a73a4.c
index 29b9a0b0012a..9326204bed9d 100644
--- a/drivers/clk/shmobile/clk-r8a73a4.c
+++ b/drivers/clk/shmobile/clk-r8a73a4.c
@@ -9,10 +9,10 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/clk/shmobile.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/shmobile/clk-r8a7740.c b/drivers/clk/shmobile/clk-r8a7740.c
index 1e2eaae21e01..1e6b1da58065 100644
--- a/drivers/clk/shmobile/clk-r8a7740.c
+++ b/drivers/clk/shmobile/clk-r8a7740.c
@@ -9,10 +9,10 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/clk/shmobile.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/shmobile/clk-r8a7778.c b/drivers/clk/shmobile/clk-r8a7778.c
index cb33b57274bf..87c1d2f2fb57 100644
--- a/drivers/clk/shmobile/clk-r8a7778.c
+++ b/drivers/clk/shmobile/clk-r8a7778.c
@@ -9,9 +9,9 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/clk/shmobile.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 
 struct r8a7778_cpg {
 	struct clk_onecell_data data;
@@ -124,6 +124,8 @@ static void __init r8a7778_cpg_clocks_init(struct device_node *np)
 	}
 
 	of_clk_add_provider(np, of_clk_src_onecell_get, &cpg->data);
+
+	cpg_mstp_add_clk_domain(np);
 }
 
 CLK_OF_DECLARE(r8a7778_cpg_clks, "renesas,r8a7778-cpg-clocks",
diff --git a/drivers/clk/shmobile/clk-r8a7779.c b/drivers/clk/shmobile/clk-r8a7779.c
index 652ecacb6daf..92275c5f2c60 100644
--- a/drivers/clk/shmobile/clk-r8a7779.c
+++ b/drivers/clk/shmobile/clk-r8a7779.c
@@ -11,12 +11,12 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/clk/shmobile.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 #include <dt-bindings/clock/r8a7779-clock.h>
@@ -168,6 +168,8 @@ static void __init r8a7779_cpg_clocks_init(struct device_node *np)
 	}
 
 	of_clk_add_provider(np, of_clk_src_onecell_get, &cpg->data);
+
+	cpg_mstp_add_clk_domain(np);
 }
 CLK_OF_DECLARE(r8a7779_cpg_clks, "renesas,r8a7779-cpg-clocks",
 	       r8a7779_cpg_clocks_init);
diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c
index acfb6d7dbd6b..745496f7ee9c 100644
--- a/drivers/clk/shmobile/clk-rcar-gen2.c
+++ b/drivers/clk/shmobile/clk-rcar-gen2.c
@@ -11,13 +11,13 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/clk/shmobile.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 struct rcar_gen2_cpg {
@@ -415,6 +415,8 @@ static void __init rcar_gen2_cpg_clocks_init(struct device_node *np)
 	}
 
 	of_clk_add_provider(np, of_clk_src_onecell_get, &cpg->data);
+
+	cpg_mstp_add_clk_domain(np);
 }
 CLK_OF_DECLARE(rcar_gen2_cpg_clks, "renesas,rcar-gen2-cpg-clocks",
 	       rcar_gen2_cpg_clocks_init);
diff --git a/drivers/clk/shmobile/clk-rz.c b/drivers/clk/shmobile/clk-rz.c
index 7e68e8630962..9766e3cb595f 100644
--- a/drivers/clk/shmobile/clk-rz.c
+++ b/drivers/clk/shmobile/clk-rz.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/clk/shmobile.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
@@ -99,5 +100,7 @@ static void __init rz_cpg_clocks_init(struct device_node *np)
 	}
 
 	of_clk_add_provider(np, of_clk_src_onecell_get, &cpg->data);
+
+	cpg_mstp_add_clk_domain(np);
 }
 CLK_OF_DECLARE(rz_cpg_clks, "renesas,rz-cpg-clocks", rz_cpg_clocks_init);
diff --git a/drivers/clk/shmobile/clk-sh73a0.c b/drivers/clk/shmobile/clk-sh73a0.c
index cd529cfe412f..8966f8bbfd72 100644
--- a/drivers/clk/shmobile/clk-sh73a0.c
+++ b/drivers/clk/shmobile/clk-sh73a0.c
@@ -9,12 +9,12 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/clk/shmobile.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 struct sh73a0_cpg {
diff --git a/drivers/clk/sirf/clk-atlas6.c b/drivers/clk/sirf/clk-atlas6.c
index d63b76ca60c3..c5eaa9d16247 100644
--- a/drivers/clk/sirf/clk-atlas6.c
+++ b/drivers/clk/sirf/clk-atlas6.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/sirf/clk-atlas7.c b/drivers/clk/sirf/clk-atlas7.c
index db8ab691dbf6..a98e21fe773a 100644
--- a/drivers/clk/sirf/clk-atlas7.c
+++ b/drivers/clk/sirf/clk-atlas7.c
@@ -358,6 +358,7 @@ static unsigned long pll_clk_recalc_rate(struct clk_hw *hw,
 	if (regctrl0 & SIRFSOC_ABPLL_CTRL0_SSEN) {
 		rate = fin;
 		rate *= 1 << 24;
+		do_div(rate, nr);
 		do_div(rate, (256 * ((ssdiv >> ssdepth) << ssdepth)
 			+ (ssmod << ssdepth)));
 	} else {
@@ -465,6 +466,9 @@ static struct clk_pll clk_sys3pll = {
  *  double resolution mode:fout = fin * finc / 2^29
  *  normal mode:fout = fin * finc / 2^28
  */
+#define DTO_RESL_DOUBLE	(1ULL << 29)
+#define DTO_RESL_NORMAL	(1ULL << 28)
+
 static int dto_clk_is_enabled(struct clk_hw *hw)
 {
 	struct clk_dto *clk = to_dtoclk(hw);
@@ -509,9 +513,9 @@ static unsigned long dto_clk_recalc_rate(struct clk_hw *hw,
 	rate *= finc;
 	if (droff & BIT(0))
 		/* Double resolution off */
-		do_div(rate, 1 << 28);
+		do_div(rate, DTO_RESL_NORMAL);
 	else
-		do_div(rate, 1 << 29);
+		do_div(rate, DTO_RESL_DOUBLE);
 
 	return rate;
 }
@@ -519,11 +523,11 @@ static unsigned long dto_clk_recalc_rate(struct clk_hw *hw,
 static long dto_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long *parent_rate)
 {
-	u64 dividend = rate * (1 << 29);
+	u64 dividend = rate * DTO_RESL_DOUBLE;
 
 	do_div(dividend, *parent_rate);
 	dividend *= *parent_rate;
-	do_div(dividend, 1 << 29);
+	do_div(dividend, DTO_RESL_DOUBLE);
 
 	return dividend;
 }
@@ -531,7 +535,7 @@ static long dto_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 static int dto_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long parent_rate)
 {
-	u64 dividend = rate * (1 << 29);
+	u64 dividend = rate * DTO_RESL_DOUBLE;
 	struct clk_dto *clk = to_dtoclk(hw);
 
 	do_div(dividend, parent_rate);
@@ -1161,7 +1165,7 @@ static struct atlas7_unit_init_data unit_list[] __initdata = {
 	{ 122, "spram1_cpudiv2", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 0, &leaf6_gate_lock },
 	{ 123, "spram2_cpudiv2", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 1, &leaf6_gate_lock },
 	{ 124, "coresight_cpudiv2", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 2, &leaf6_gate_lock },
-	{ 125, "thcpum_cpudiv4", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 3, &leaf6_gate_lock },
+	{ 125, "coresight_tpiu", "cpum_tpiu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 3, &leaf6_gate_lock },
 	{ 126, "graphic_gpu", "gpum_gpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN7_SET, 0, &leaf7_gate_lock },
 	{ 127, "vss_sdr", "gpum_sdr", 0, SIRFSOC_CLKC_LEAF_CLK_EN7_SET, 1, &leaf7_gate_lock },
 	{ 128, "thgpum_nocr", "gpum_nocr", 0, SIRFSOC_CLKC_LEAF_CLK_EN7_SET, 2, &leaf7_gate_lock },
@@ -1174,9 +1178,13 @@ static struct atlas7_unit_init_data unit_list[] __initdata = {
 	{ 135, "thbtm_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 7, &leaf8_gate_lock },
 	{ 136, "btslow", "xinw_fixdiv_btslow", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 25, &root1_gate_lock },
 	{ 137, "a7ca_btslow", "btslow", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 0, &leaf8_gate_lock },
+	{ 138, "pwm_io", "io_mux", 0, SIRFSOC_CLKC_LEAF_CLK_EN0_SET, 0, &leaf0_gate_lock },
+	{ 139, "pwm_xin", "xin", 0, SIRFSOC_CLKC_LEAF_CLK_EN0_SET, 1, &leaf0_gate_lock },
+	{ 140, "pwm_xinw", "xinw", 0, SIRFSOC_CLKC_LEAF_CLK_EN0_SET, 2, &leaf0_gate_lock },
+	{ 141, "thcgum_sys", "sys_mux", 0, SIRFSOC_CLKC_LEAF_CLK_EN0_SET, 3, &leaf0_gate_lock },
 };
 
-static struct clk *atlas7_clks[ARRAY_SIZE(unit_list)];
+static struct clk *atlas7_clks[ARRAY_SIZE(unit_list) + ARRAY_SIZE(mux_list)];
 
 static int unit_clk_is_enabled(struct clk_hw *hw)
 {
@@ -1609,6 +1617,7 @@ static void __init atlas7_clk_init(struct device_node *np)
 			       sirfsoc_clk_vbase + mux->mux_offset,
 			       mux->shift, mux->width,
 			       mux->mux_flags, NULL);
+		atlas7_clks[ARRAY_SIZE(unit_list) + i] = clk;
 		BUG_ON(!clk);
 	}
 
@@ -1620,7 +1629,7 @@ static void __init atlas7_clk_init(struct device_node *np)
 	}
 
 	clk_data.clks = atlas7_clks;
-	clk_data.clk_num = ARRAY_SIZE(unit_list);
+	clk_data.clk_num = ARRAY_SIZE(unit_list) + ARRAY_SIZE(mux_list);
 
 	ret = of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 	BUG_ON(ret);
diff --git a/drivers/clk/sirf/clk-common.c b/drivers/clk/sirf/clk-common.c
index 9fc285d784d3..77e1e2491689 100644
--- a/drivers/clk/sirf/clk-common.c
+++ b/drivers/clk/sirf/clk-common.c
@@ -7,6 +7,8 @@
  * Licensed under GPLv2 or later.
  */
 
+#include <linux/clk.h>
+
 #define KHZ     1000
 #define MHZ     (KHZ * KHZ)
 
@@ -165,10 +167,10 @@ static long cpu_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 	 * SiRF SoC has not cpu clock control,
 	 * So bypass to it's parent pll.
 	 */
-	struct clk *parent_clk = clk_get_parent(hw->clk);
-	struct clk *pll_parent_clk = clk_get_parent(parent_clk);
-	unsigned long pll_parent_rate = clk_get_rate(pll_parent_clk);
-	return pll_clk_round_rate(__clk_get_hw(parent_clk), rate, &pll_parent_rate);
+	struct clk_hw *parent_clk = clk_hw_get_parent(hw);
+	struct clk_hw *pll_parent_clk = clk_hw_get_parent(parent_clk);
+	unsigned long pll_parent_rate = clk_hw_get_rate(pll_parent_clk);
+	return pll_clk_round_rate(parent_clk, rate, &pll_parent_rate);
 }
 
 static unsigned long cpu_clk_recalc_rate(struct clk_hw *hw,
@@ -178,8 +180,8 @@ static unsigned long cpu_clk_recalc_rate(struct clk_hw *hw,
 	 * SiRF SoC has not cpu clock control,
 	 * So return the parent pll rate.
 	 */
-	struct clk *parent_clk = clk_get_parent(hw->clk);
-	return __clk_get_rate(parent_clk);
+	struct clk_hw *parent_clk = clk_hw_get_parent(hw);
+	return clk_hw_get_rate(parent_clk);
 }
 
 static struct clk_ops std_pll_ops = {
diff --git a/drivers/clk/sirf/clk-prima2.c b/drivers/clk/sirf/clk-prima2.c
index 6968e2ebcd8a..f92c40264342 100644
--- a/drivers/clk/sirf/clk-prima2.c
+++ b/drivers/clk/sirf/clk-prima2.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/socfpga/clk-gate-a10.c b/drivers/clk/socfpga/clk-gate-a10.c
index 83c6780ff4b2..1cebf253e8fd 100644
--- a/drivers/clk/socfpga/clk-gate-a10.c
+++ b/drivers/clk/socfpga/clk-gate-a10.c
@@ -13,6 +13,7 @@
  * You should have received a copy of the GNU General Public License along with
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
@@ -38,7 +39,7 @@ static unsigned long socfpga_gate_clk_recalc_rate(struct clk_hw *hwclk,
 		div = socfpgaclk->fixed_div;
 	else if (socfpgaclk->div_reg) {
 		val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
-		val &= div_mask(socfpgaclk->width);
+		val &= GENMASK(socfpgaclk->width - 1, 0);
 		div = (1 << val);
 	}
 
diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c
index 82449cd76fd7..aa7a6e6a15b6 100644
--- a/drivers/clk/socfpga/clk-gate.c
+++ b/drivers/clk/socfpga/clk-gate.c
@@ -15,8 +15,7 @@
  * Based from clk-highbank.c
  *
  */
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
@@ -106,7 +105,7 @@ static unsigned long socfpga_clk_recalc_rate(struct clk_hw *hwclk,
 		div = socfpgaclk->fixed_div;
 	else if (socfpgaclk->div_reg) {
 		val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
-		val &= div_mask(socfpgaclk->width);
+		val &= GENMASK(socfpgaclk->width - 1, 0);
 		/* Check for GPIO_DB_CLK by its offset */
 		if ((int) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET)
 			div = val + 1;
diff --git a/drivers/clk/socfpga/clk-periph-a10.c b/drivers/clk/socfpga/clk-periph-a10.c
index 9d0181b5a6a4..1f397cb72e89 100644
--- a/drivers/clk/socfpga/clk-periph-a10.c
+++ b/drivers/clk/socfpga/clk-periph-a10.c
@@ -13,6 +13,7 @@
  * You should have received a copy of the GNU General Public License along with
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -37,7 +38,7 @@ static unsigned long clk_periclk_recalc_rate(struct clk_hw *hwclk,
 		div = socfpgaclk->fixed_div;
 	} else if (socfpgaclk->div_reg) {
 		div = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
-		div &= div_mask(socfpgaclk->width);
+		div &= GENMASK(socfpgaclk->width - 1, 0);
 		div += 1;
 	} else {
 		div = ((readl(socfpgaclk->hw.reg) & 0x7ff) + 1);
diff --git a/drivers/clk/socfpga/clk-periph.c b/drivers/clk/socfpga/clk-periph.c
index 83aeaa219d14..52c883ea7706 100644
--- a/drivers/clk/socfpga/clk-periph.c
+++ b/drivers/clk/socfpga/clk-periph.c
@@ -15,8 +15,7 @@
  * Based from clk-highbank.c
  *
  */
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -36,7 +35,7 @@ static unsigned long clk_periclk_recalc_rate(struct clk_hw *hwclk,
 	} else {
 		if (socfpgaclk->div_reg) {
 			val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
-			val &= div_mask(socfpgaclk->width);
+			val &= GENMASK(socfpgaclk->width - 1, 0);
 			parent_rate /= (val + 1);
 		}
 		div = ((readl(socfpgaclk->hw.reg) & 0x1ff) + 1);
@@ -45,8 +44,17 @@ static unsigned long clk_periclk_recalc_rate(struct clk_hw *hwclk,
 	return parent_rate / div;
 }
 
+static u8 clk_periclk_get_parent(struct clk_hw *hwclk)
+{
+	u32 clk_src;
+
+	clk_src = readl(clk_mgr_base_addr + CLKMGR_DBCTRL);
+	return clk_src & 0x1;
+}
+
 static const struct clk_ops periclk_ops = {
 	.recalc_rate = clk_periclk_recalc_rate,
+	.get_parent = clk_periclk_get_parent,
 };
 
 static __init void __socfpga_periph_init(struct device_node *node,
@@ -56,7 +64,7 @@ static __init void __socfpga_periph_init(struct device_node *node,
 	struct clk *clk;
 	struct socfpga_periph_clk *periph_clk;
 	const char *clk_name = node->name;
-	const char *parent_name;
+	const char *parent_name[SOCFPGA_MAX_PARENTS];
 	struct clk_init_data init;
 	int rc;
 	u32 fixed_div;
@@ -90,9 +98,10 @@ static __init void __socfpga_periph_init(struct device_node *node,
 	init.name = clk_name;
 	init.ops = ops;
 	init.flags = 0;
-	parent_name = of_clk_get_parent_name(node, 0);
-	init.parent_names = &parent_name;
-	init.num_parents = 1;
+
+	init.num_parents = of_clk_parent_fill(node, parent_name,
+					      SOCFPGA_MAX_PARENTS);
+	init.parent_names = parent_name;
 
 	periph_clk->hw.hw.init = &init;
 
diff --git a/drivers/clk/socfpga/clk-pll-a10.c b/drivers/clk/socfpga/clk-pll-a10.c
index 1178b11babca..402d630bd531 100644
--- a/drivers/clk/socfpga/clk-pll-a10.c
+++ b/drivers/clk/socfpga/clk-pll-a10.c
@@ -13,6 +13,7 @@
  * You should have received a copy of the GNU General Public License along with
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
diff --git a/drivers/clk/socfpga/clk-pll.c b/drivers/clk/socfpga/clk-pll.c
index 8f26b5234947..c7f463172e4b 100644
--- a/drivers/clk/socfpga/clk-pll.c
+++ b/drivers/clk/socfpga/clk-pll.c
@@ -15,8 +15,7 @@
  * Based from clk-highbank.c
  *
  */
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
diff --git a/drivers/clk/socfpga/clk.h b/drivers/clk/socfpga/clk.h
index 603973ab7e29..814c7247bf73 100644
--- a/drivers/clk/socfpga/clk.h
+++ b/drivers/clk/socfpga/clk.h
@@ -18,16 +18,15 @@
 #define __SOCFPGA_CLK_H
 
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 
 /* Clock Manager offsets */
 #define CLKMGR_CTRL		0x0
 #define CLKMGR_BYPASS		0x4
+#define CLKMGR_DBCTRL		0x10
 #define CLKMGR_L4SRC		0x70
 #define CLKMGR_PERPLL_SRC	0xAC
 
 #define SOCFPGA_MAX_PARENTS		5
-#define div_mask(width) ((1 << (width)) - 1)
 
 #define streq(a, b) (strcmp((a), (b)) == 0)
 #define SYSMGR_SDMMC_CTRL_SET(smplsel, drvsel) \
diff --git a/drivers/clk/spear/clk-aux-synth.c b/drivers/clk/spear/clk-aux-synth.c
index bdfb4421c643..f271c350ef94 100644
--- a/drivers/clk/spear/clk-aux-synth.c
+++ b/drivers/clk/spear/clk-aux-synth.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk-frac-synth.c b/drivers/clk/spear/clk-frac-synth.c
index dffd4ce6c8b5..58d678b5b40a 100644
--- a/drivers/clk/spear/clk-frac-synth.c
+++ b/drivers/clk/spear/clk-frac-synth.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk-gpt-synth.c b/drivers/clk/spear/clk-gpt-synth.c
index 1afc18c4effc..1a722e99e76e 100644
--- a/drivers/clk/spear/clk-gpt-synth.c
+++ b/drivers/clk/spear/clk-gpt-synth.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk-vco-pll.c b/drivers/clk/spear/clk-vco-pll.c
index 1b9b65bca51e..dc21ca4601aa 100644
--- a/drivers/clk/spear/clk-vco-pll.c
+++ b/drivers/clk/spear/clk-vco-pll.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -87,7 +87,7 @@ static long clk_pll_round_rate_index(struct clk_hw *hw, unsigned long drate,
 	struct clk_pll *pll = to_clk_pll(hw);
 	unsigned long prev_rate, vco_prev_rate, rate = 0;
 	unsigned long vco_parent_rate =
-		__clk_get_rate(__clk_get_parent(__clk_get_parent(hw->clk)));
+		clk_hw_get_rate(clk_hw_get_parent(clk_hw_get_parent(hw)));
 
 	if (!prate) {
 		pr_err("%s: prate is must for pll clk\n", __func__);
diff --git a/drivers/clk/spear/clk.c b/drivers/clk/spear/clk.c
index 628b6d5ed3d9..157fe099ea6a 100644
--- a/drivers/clk/spear/clk.c
+++ b/drivers/clk/spear/clk.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk.h b/drivers/clk/spear/clk.h
index 931737677dfa..9834944f08b1 100644
--- a/drivers/clk/spear/clk.h
+++ b/drivers/clk/spear/clk.h
@@ -2,7 +2,7 @@
  * Clock framework definitions for SPEAr platform
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c
index 4daa5977793a..009bd1410cfa 100644
--- a/drivers/clk/spear/spear1310_clock.c
+++ b/drivers/clk/spear/spear1310_clock.c
@@ -4,14 +4,13 @@
  * SPEAr1310 machine clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c
index 5a5c6648308d..9c7abfd951ba 100644
--- a/drivers/clk/spear/spear1340_clock.c
+++ b/drivers/clk/spear/spear1340_clock.c
@@ -4,14 +4,13 @@
  * SPEAr1340 machine clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index bb5f387774e2..404a55edd613 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -2,7 +2,7 @@
  * SPEAr3xx machines clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c
index 4f649c9cb094..e24f85cd4300 100644
--- a/drivers/clk/spear/spear6xx_clock.c
+++ b/drivers/clk/spear/spear6xx_clock.c
@@ -2,14 +2,13 @@
  * SPEAr6xx machines clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/spinlock_types.h>
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index 657ca14ba709..bd355ee33766 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -5,6 +5,7 @@
  * Author:  Maxime Coquelin <maxime.coquelin@st.com> for ST-Microelectronics.
  * License terms:  GNU General Public License (GPL), version 2  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -44,7 +45,7 @@ static int flexgen_enable(struct clk_hw *hw)
 
 	clk_gate_ops.enable(fgate_hw);
 
-	pr_debug("%s: flexgen output enabled\n", __clk_get_name(hw->clk));
+	pr_debug("%s: flexgen output enabled\n", clk_hw_get_name(hw));
 	return 0;
 }
 
@@ -58,7 +59,7 @@ static void flexgen_disable(struct clk_hw *hw)
 
 	clk_gate_ops.disable(fgate_hw);
 
-	pr_debug("%s: flexgen output disabled\n", __clk_get_name(hw->clk));
+	pr_debug("%s: flexgen output disabled\n", clk_hw_get_name(hw));
 }
 
 static int flexgen_is_enabled(struct clk_hw *hw)
@@ -108,7 +109,7 @@ static long flexgen_round_rate(struct clk_hw *hw, unsigned long rate,
 	/* Round div according to exact prate and wished rate */
 	div = clk_best_div(*prate, rate);
 
-	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
 		*prate = rate * div;
 		return rate;
 	}
@@ -190,7 +191,7 @@ static struct clk *clk_register_flexgen(const char *name,
 
 	init.name = name;
 	init.ops = &flexgen_ops;
-	init.flags = CLK_IS_BASIC | flexgen_flags;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE | flexgen_flags;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
 
@@ -243,7 +244,7 @@ static const char ** __init flexgen_get_parents(struct device_node *np,
 						       int *num_parents)
 {
 	const char **parents;
-	int nparents, i;
+	int nparents;
 
 	nparents = of_clk_get_parent_count(np);
 	if (WARN_ON(nparents <= 0))
@@ -253,10 +254,8 @@ static const char ** __init flexgen_get_parents(struct device_node *np,
 	if (!parents)
 		return NULL;
 
-	for (i = 0; i < nparents; i++)
-		parents[i] = of_clk_get_parent_name(np, i);
+	*num_parents = of_clk_parent_fill(np, parents, nparents);
 
-	*num_parents = nparents;
 	return parents;
 }
 
@@ -303,6 +302,8 @@ static void __init st_of_flexgen_setup(struct device_node *np)
 	if (!rlock)
 		goto err;
 
+	spin_lock_init(rlock);
+
 	for (i = 0; i < clk_data->clk_num; i++) {
 		struct clk *clk;
 		const char *clk_name;
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index e94197f04b0b..83ccf142ff2a 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -15,6 +15,7 @@
 
 #include <linux/slab.h>
 #include <linux/of_address.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
 #include "clkgen.h"
@@ -340,7 +341,7 @@ static const struct clkgen_quadfs_data st_fs660c32_C_407 = {
 		    CLKGEN_FIELD(0x30c, 0xf, 20),
 		    CLKGEN_FIELD(0x310, 0xf, 20) },
 	.lockstatus_present = true,
-	.lock_status = CLKGEN_FIELD(0x2A0, 0x1, 24),
+	.lock_status = CLKGEN_FIELD(0x2f0, 0x1, 24),
 	.powerup_polarity = 1,
 	.standby_polarity = 1,
 	.pll_ops	= &st_quadfs_pll_c32_ops,
@@ -489,7 +490,7 @@ static int quadfs_pll_is_enabled(struct clk_hw *hw)
 	struct st_clk_quadfs_pll *pll = to_quadfs_pll(hw);
 	u32 npda = CLKGEN_READ(pll, npda);
 
-	return !!npda;
+	return pll->data->powerup_polarity ? !npda : !!npda;
 }
 
 static int clk_fs660c32_vco_get_rate(unsigned long input, struct stm_fs *fs,
@@ -512,7 +513,7 @@ static unsigned long quadfs_pll_fs660c32_recalc_rate(struct clk_hw *hw,
 	params.ndiv = CLKGEN_READ(pll, ndiv);
 	if (clk_fs660c32_vco_get_rate(parent_rate, &params, &rate))
 		pr_err("%s:%s error calculating rate\n",
-		       __clk_get_name(hw->clk), __func__);
+		       clk_hw_get_name(hw), __func__);
 
 	pll->ndiv = params.ndiv;
 
@@ -557,7 +558,7 @@ static long quadfs_pll_fs660c32_round_rate(struct clk_hw *hw, unsigned long rate
 		clk_fs660c32_vco_get_rate(*prate, &params, &rate);
 
 	pr_debug("%s: %s new rate %ld [sdiv=0x%x,md=0x%x,pe=0x%x,nsdiv3=%u]\n",
-		 __func__, __clk_get_name(hw->clk),
+		 __func__, clk_hw_get_name(hw),
 		 rate, (unsigned int)params.sdiv,
 		 (unsigned int)params.mdiv,
 		 (unsigned int)params.pe, (unsigned int)params.nsdiv);
@@ -580,7 +581,7 @@ static int quadfs_pll_fs660c32_set_rate(struct clk_hw *hw, unsigned long rate,
 		clk_fs660c32_vco_get_rate(parent_rate, &params, &hwrate);
 
 	pr_debug("%s: %s new rate %ld [ndiv=0x%x]\n",
-		 __func__, __clk_get_name(hw->clk),
+		 __func__, clk_hw_get_name(hw),
 		 hwrate, (unsigned int)params.ndiv);
 
 	if (!hwrate)
@@ -635,7 +636,7 @@ static struct clk * __init st_clk_register_quadfs_pll(
 
 	init.name = name;
 	init.ops = quadfs->pll_ops;
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
 
@@ -744,7 +745,7 @@ static int quadfs_fsynth_enable(struct clk_hw *hw)
 	struct st_clk_quadfs_fsynth *fs = to_quadfs_fsynth(hw);
 	unsigned long flags = 0;
 
-	pr_debug("%s: %s\n", __func__, __clk_get_name(hw->clk));
+	pr_debug("%s: %s\n", __func__, clk_hw_get_name(hw));
 
 	quadfs_fsynth_program_rate(fs);
 
@@ -769,12 +770,12 @@ static void quadfs_fsynth_disable(struct clk_hw *hw)
 	struct st_clk_quadfs_fsynth *fs = to_quadfs_fsynth(hw);
 	unsigned long flags = 0;
 
-	pr_debug("%s: %s\n", __func__, __clk_get_name(hw->clk));
+	pr_debug("%s: %s\n", __func__, clk_hw_get_name(hw));
 
 	if (fs->lock)
 		spin_lock_irqsave(fs->lock, flags);
 
-	CLKGEN_WRITE(fs, nsb[fs->chan], !fs->data->standby_polarity);
+	CLKGEN_WRITE(fs, nsb[fs->chan], fs->data->standby_polarity);
 
 	if (fs->lock)
 		spin_unlock_irqrestore(fs->lock, flags);
@@ -786,7 +787,7 @@ static int quadfs_fsynth_is_enabled(struct clk_hw *hw)
 	u32 nsb = CLKGEN_READ(fs, nsb[fs->chan]);
 
 	pr_debug("%s: %s enable bit = 0x%x\n",
-		 __func__, __clk_get_name(hw->clk), nsb);
+		 __func__, clk_hw_get_name(hw), nsb);
 
 	return fs->data->standby_polarity ? !nsb : !!nsb;
 }
@@ -945,10 +946,10 @@ static unsigned long quadfs_recalc_rate(struct clk_hw *hw,
 
 	if (clk_fs_get_rate(parent_rate, &params, &rate)) {
 		pr_err("%s:%s error calculating rate\n",
-		       __clk_get_name(hw->clk), __func__);
+		       clk_hw_get_name(hw), __func__);
 	}
 
-	pr_debug("%s:%s rate %lu\n", __clk_get_name(hw->clk), __func__, rate);
+	pr_debug("%s:%s rate %lu\n", clk_hw_get_name(hw), __func__, rate);
 
 	return rate;
 }
@@ -961,7 +962,7 @@ static long quadfs_round_rate(struct clk_hw *hw, unsigned long rate,
 	rate = quadfs_find_best_rate(hw, rate, *prate, &params);
 
 	pr_debug("%s: %s new rate %ld [sdiv=0x%x,md=0x%x,pe=0x%x,nsdiv3=%u]\n",
-		 __func__, __clk_get_name(hw->clk),
+		 __func__, clk_hw_get_name(hw),
 		 rate, (unsigned int)params.sdiv, (unsigned int)params.mdiv,
 			 (unsigned int)params.pe, (unsigned int)params.nsdiv);
 
@@ -1082,10 +1083,6 @@ static const struct of_device_id quadfs_of_match[] = {
 		.compatible = "st,stih407-quadfs660-D",
 		.data = &st_fs660c32_D_407
 	},
-	{
-		.compatible = "st,stih407-quadfs660-D",
-		.data = (void *)&st_fs660c32_D_407
-	},
 	{}
 };
 
diff --git a/drivers/clk/st/clkgen-mux.c b/drivers/clk/st/clkgen-mux.c
index 4fbe6e099587..4f7f6c00b219 100644
--- a/drivers/clk/st/clkgen-mux.c
+++ b/drivers/clk/st/clkgen-mux.c
@@ -15,6 +15,7 @@
 
 #include <linux/slab.h>
 #include <linux/of_address.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
 static DEFINE_SPINLOCK(clkgena_divmux_lock);
@@ -24,20 +25,17 @@ static const char ** __init clkgen_mux_get_parents(struct device_node *np,
 						       int *num_parents)
 {
 	const char **parents;
-	int nparents, i;
+	int nparents;
 
 	nparents = of_clk_get_parent_count(np);
 	if (WARN_ON(nparents <= 0))
 		return ERR_PTR(-EINVAL);
 
-	parents = kzalloc(nparents * sizeof(const char *), GFP_KERNEL);
+	parents = kcalloc(nparents, sizeof(const char *), GFP_KERNEL);
 	if (!parents)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < nparents; i++)
-		parents[i] = of_clk_get_parent_name(np, i);
-
-	*num_parents = nparents;
+	*num_parents = of_clk_parent_fill(np, parents, nparents);
 	return parents;
 }
 
@@ -141,7 +139,7 @@ static u8 clkgena_divmux_get_parent(struct clk_hw *hw)
 	genamux->muxsel = clk_mux_ops.get_parent(mux_hw);
 	if ((s8)genamux->muxsel < 0) {
 		pr_debug("%s: %s: Invalid parent, setting to default.\n",
-		      __func__, __clk_get_name(hw->clk));
+		      __func__, clk_hw_get_name(hw));
 		genamux->muxsel = 0;
 	}
 
@@ -215,7 +213,7 @@ static const struct clk_ops clkgena_divmux_ops = {
 /**
  * clk_register_genamux - register a genamux clock with the clock framework
  */
-static struct clk *clk_register_genamux(const char *name,
+static struct clk * __init clk_register_genamux(const char *name,
 				const char **parent_names, u8 num_parents,
 				void __iomem *reg,
 				const struct clkgena_divmux_data *muxdata,
@@ -237,7 +235,7 @@ static struct clk *clk_register_genamux(const char *name,
 
 	init.name = name;
 	init.ops = &clkgena_divmux_ops;
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
 
@@ -369,11 +367,10 @@ static const struct of_device_id clkgena_divmux_of_match[] = {
 	{}
 };
 
-static void __iomem * __init clkgen_get_register_base(
-				struct device_node *np)
+static void __iomem * __init clkgen_get_register_base(struct device_node *np)
 {
 	struct device_node *pnode;
-	void __iomem *reg = NULL;
+	void __iomem *reg;
 
 	pnode = of_get_parent(np);
 	if (!pnode)
@@ -398,7 +395,7 @@ static void __init st_of_clkgena_divmux_setup(struct device_node *np)
 	if (WARN_ON(!match))
 		return;
 
-	data = (struct clkgena_divmux_data *)match->data;
+	data = match->data;
 
 	reg = clkgen_get_register_base(np);
 	if (!reg)
@@ -406,18 +403,18 @@ static void __init st_of_clkgena_divmux_setup(struct device_node *np)
 
 	parents = clkgen_mux_get_parents(np, &num_parents);
 	if (IS_ERR(parents))
-		return;
+		goto err_parents;
 
 	clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
 	if (!clk_data)
-		goto err;
+		goto err_alloc;
 
 	clk_data->clk_num = data->num_outputs;
-	clk_data->clks = kzalloc(clk_data->clk_num * sizeof(struct clk *),
+	clk_data->clks = kcalloc(clk_data->clk_num, sizeof(struct clk *),
 				 GFP_KERNEL);
 
 	if (!clk_data->clks)
-		goto err;
+		goto err_alloc_clks;
 
 	for (i = 0; i < clk_data->clk_num; i++) {
 		struct clk *clk;
@@ -447,11 +444,13 @@ static void __init st_of_clkgena_divmux_setup(struct device_node *np)
 	of_clk_add_provider(np, of_clk_src_onecell_get, clk_data);
 	return;
 err:
-	if (clk_data)
-		kfree(clk_data->clks);
-
+	kfree(clk_data->clks);
+err_alloc_clks:
 	kfree(clk_data);
+err_alloc:
 	kfree(parents);
+err_parents:
+	iounmap(reg);
 }
 CLK_OF_DECLARE(clkgenadivmux, "st,clkgena-divmux", st_of_clkgena_divmux_setup);
 
@@ -491,7 +490,7 @@ static void __init st_of_clkgena_prediv_setup(struct device_node *np)
 	void __iomem *reg;
 	const char *parent_name, *clk_name;
 	struct clk *clk;
-	struct clkgena_prediv_data *data;
+	const struct clkgena_prediv_data *data;
 
 	match = of_match_node(clkgena_prediv_of_match, np);
 	if (!match) {
@@ -499,7 +498,7 @@ static void __init st_of_clkgena_prediv_setup(struct device_node *np)
 		return;
 	}
 
-	data = (struct clkgena_prediv_data *)match->data;
+	data = match->data;
 
 	reg = clkgen_get_register_base(np);
 	if (!reg)
@@ -507,17 +506,18 @@ static void __init st_of_clkgena_prediv_setup(struct device_node *np)
 
 	parent_name = of_clk_get_parent_name(np, 0);
 	if (!parent_name)
-		return;
+		goto err;
 
 	if (of_property_read_string_index(np, "clock-output-names",
 					  0, &clk_name))
-		return;
+		goto err;
 
-	clk = clk_register_divider_table(NULL, clk_name, parent_name, 0,
+	clk = clk_register_divider_table(NULL, clk_name, parent_name,
+					 CLK_GET_RATE_NOCACHE,
 					 reg + data->offset, data->shift, 1,
 					 0, data->table, NULL);
 	if (IS_ERR(clk))
-		return;
+		goto err;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 	pr_debug("%s: parent %s rate %u\n",
@@ -526,6 +526,8 @@ static void __init st_of_clkgena_prediv_setup(struct device_node *np)
 		(unsigned int)clk_get_rate(clk));
 
 	return;
+err:
+	iounmap(reg);
 }
 CLK_OF_DECLARE(clkgenaprediv, "st,clkgena-prediv", st_of_clkgena_prediv_setup);
 
@@ -582,7 +584,7 @@ static struct clkgen_mux_data stih416_a9_mux_data = {
 };
 static struct clkgen_mux_data stih407_a9_mux_data = {
 	.offset = 0x1a4,
-	.shift = 1,
+	.shift = 0,
 	.width = 2,
 };
 
@@ -629,7 +631,7 @@ static void __init st_of_clkgen_mux_setup(struct device_node *np)
 	void __iomem *reg;
 	const char **parents;
 	int num_parents;
-	struct clkgen_mux_data *data;
+	const struct clkgen_mux_data *data;
 
 	match = of_match_node(mux_of_match, np);
 	if (!match) {
@@ -637,7 +639,7 @@ static void __init st_of_clkgen_mux_setup(struct device_node *np)
 		return;
 	}
 
-	data = (struct clkgen_mux_data *)match->data;
+	data = match->data;
 
 	reg = of_iomap(np, 0);
 	if (!reg) {
@@ -649,7 +651,7 @@ static void __init st_of_clkgen_mux_setup(struct device_node *np)
 	if (IS_ERR(parents)) {
 		pr_err("%s: Failed to get parents (%ld)\n",
 				__func__, PTR_ERR(parents));
-		return;
+		goto err_parents;
 	}
 
 	clk = clk_register_mux(NULL, np->name, parents, num_parents,
@@ -665,12 +667,14 @@ static void __init st_of_clkgen_mux_setup(struct device_node *np)
 			__clk_get_name(clk_get_parent(clk)),
 			(unsigned int)clk_get_rate(clk));
 
+	kfree(parents);
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	return;
 
 err:
 	kfree(parents);
-
-	return;
+err_parents:
+	iounmap(reg);
 }
 CLK_OF_DECLARE(clkgen_mux, "st,clkgen-mux", st_of_clkgen_mux_setup);
 
@@ -706,12 +710,12 @@ static void __init st_of_clkgen_vcc_setup(struct device_node *np)
 	const char **parents;
 	int num_parents, i;
 	struct clk_onecell_data *clk_data;
-	struct clkgen_vcc_data *data;
+	const struct clkgen_vcc_data *data;
 
 	match = of_match_node(vcc_of_match, np);
 	if (WARN_ON(!match))
 		return;
-	data = (struct clkgen_vcc_data *)match->data;
+	data = match->data;
 
 	reg = of_iomap(np, 0);
 	if (!reg)
@@ -719,18 +723,18 @@ static void __init st_of_clkgen_vcc_setup(struct device_node *np)
 
 	parents = clkgen_mux_get_parents(np, &num_parents);
 	if (IS_ERR(parents))
-		return;
+		goto err_parents;
 
 	clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
 	if (!clk_data)
-		goto err;
+		goto err_alloc;
 
 	clk_data->clk_num = VCC_MAX_CHANNELS;
-	clk_data->clks = kzalloc(clk_data->clk_num * sizeof(struct clk *),
+	clk_data->clks = kcalloc(clk_data->clk_num, sizeof(struct clk *),
 				 GFP_KERNEL);
 
 	if (!clk_data->clks)
-		goto err;
+		goto err_alloc_clks;
 
 	for (i = 0; i < clk_data->clk_num; i++) {
 		struct clk *clk;
@@ -749,21 +753,21 @@ static void __init st_of_clkgen_vcc_setup(struct device_node *np)
 		if (*clk_name == '\0')
 			continue;
 
-		gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
 		if (!gate)
-			break;
+			goto err;
 
-		div = kzalloc(sizeof(struct clk_divider), GFP_KERNEL);
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
 		if (!div) {
 			kfree(gate);
-			break;
+			goto err;
 		}
 
-		mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
+		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
 		if (!mux) {
 			kfree(gate);
 			kfree(div);
-			break;
+			goto err;
 		}
 
 		gate->reg = reg + VCC_GATE_OFFSET;
@@ -786,7 +790,8 @@ static void __init st_of_clkgen_vcc_setup(struct device_node *np)
 					     &mux->hw, &clk_mux_ops,
 					     &div->hw, &clk_divider_ops,
 					     &gate->hw, &clk_gate_ops,
-					     data->clk_flags);
+					     data->clk_flags |
+					     CLK_GET_RATE_NOCACHE);
 		if (IS_ERR(clk)) {
 			kfree(gate);
 			kfree(div);
@@ -821,10 +826,12 @@ err:
 		kfree(container_of(composite->mux_hw, struct clk_mux, hw));
 	}
 
-	if (clk_data)
-		kfree(clk_data->clks);
-
+	kfree(clk_data->clks);
+err_alloc_clks:
 	kfree(clk_data);
+err_alloc:
 	kfree(parents);
+err_parents:
+	iounmap(reg);
 }
 CLK_OF_DECLARE(clkgen_vcc, "st,clkgen-vcc", st_of_clkgen_vcc_setup);
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index 106532207213..47a38a994cac 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -16,6 +16,7 @@
 
 #include <linux/slab.h>
 #include <linux/of_address.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
 #include "clkgen.h"
@@ -291,7 +292,7 @@ static unsigned long recalc_stm_pll800c65(struct clk_hw *hw,
 	res = (uint64_t)2 * (uint64_t)parent_rate * (uint64_t)ndiv;
 	rate = (unsigned long)div64_u64(res, mdiv * (1 << pdiv));
 
-	pr_debug("%s:%s rate %lu\n", __clk_get_name(hw->clk), __func__, rate);
+	pr_debug("%s:%s rate %lu\n", clk_hw_get_name(hw), __func__, rate);
 
 	return rate;
 
@@ -316,7 +317,7 @@ static unsigned long recalc_stm_pll1600c65(struct clk_hw *hw,
 	/* Note: input is divided by 1000 to avoid overflow */
 	rate = ((2 * (parent_rate / 1000) * ndiv) / mdiv) * 1000;
 
-	pr_debug("%s:%s rate %lu\n", __clk_get_name(hw->clk), __func__, rate);
+	pr_debug("%s:%s rate %lu\n", clk_hw_get_name(hw), __func__, rate);
 
 	return rate;
 }
@@ -338,7 +339,7 @@ static unsigned long recalc_stm_pll3200c32(struct clk_hw *hw,
 		/* Note: input is divided to avoid overflow */
 		rate = ((2 * (parent_rate/1000) * ndiv) / idf) * 1000;
 
-	pr_debug("%s:%s rate %lu\n", __clk_get_name(hw->clk), __func__, rate);
+	pr_debug("%s:%s rate %lu\n", clk_hw_get_name(hw), __func__, rate);
 
 	return rate;
 }
@@ -365,7 +366,7 @@ static unsigned long recalc_stm_pll1200c32(struct clk_hw *hw,
 	/* Note: input is divided by 1000 to avoid overflow */
 	rate = (((parent_rate / 1000) * ldf) / (odf * idf)) * 1000;
 
-	pr_debug("%s:%s rate %lu\n", __clk_get_name(hw->clk), __func__, rate);
+	pr_debug("%s:%s rate %lu\n", clk_hw_get_name(hw), __func__, rate);
 
 	return rate;
 }
@@ -406,7 +407,7 @@ static struct clk * __init clkgen_pll_register(const char *parent_name,
 	init.name = clk_name;
 	init.ops = pll_data->ops;
 
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents  = 1;
 
diff --git a/drivers/clk/sunxi/Makefile b/drivers/clk/sunxi/Makefile
index 058f273d6154..f5a35b82cc1a 100644
--- a/drivers/clk/sunxi/Makefile
+++ b/drivers/clk/sunxi/Makefile
@@ -6,6 +6,7 @@ obj-y += clk-sunxi.o clk-factors.o
 obj-y += clk-a10-hosc.o
 obj-y += clk-a20-gmac.o
 obj-y += clk-mod0.o
+obj-y += clk-simple-gates.o
 obj-y += clk-sun8i-mbus.o
 obj-y += clk-sun9i-core.o
 obj-y += clk-sun9i-mmc.o
diff --git a/drivers/clk/sunxi/clk-a20-gmac.c b/drivers/clk/sunxi/clk-a20-gmac.c
index 0dcf4f205fb8..1611b036421c 100644
--- a/drivers/clk/sunxi/clk-a20-gmac.c
+++ b/drivers/clk/sunxi/clk-a20-gmac.c
@@ -80,9 +80,7 @@ static void __init sun7i_a20_gmac_clk_setup(struct device_node *node)
 		goto free_mux;
 
 	/* gmac clock requires exactly 2 parents */
-	parents[0] = of_clk_get_parent_name(node, 0);
-	parents[1] = of_clk_get_parent_name(node, 1);
-	if (!parents[0] || !parents[1])
+	if (of_clk_parent_fill(node, parents, 2) != 2)
 		goto free_gate;
 
 	reg = of_iomap(node, 0);
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index 8c20190a3e9f..59428dbd607a 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -79,41 +79,42 @@ static long clk_factors_round_rate(struct clk_hw *hw, unsigned long rate,
 	return rate;
 }
 
-static long clk_factors_determine_rate(struct clk_hw *hw, unsigned long rate,
-				       unsigned long min_rate,
-				       unsigned long max_rate,
-				       unsigned long *best_parent_rate,
-				       struct clk_hw **best_parent_p)
+static int clk_factors_determine_rate(struct clk_hw *hw,
+				      struct clk_rate_request *req)
 {
-	struct clk *clk = hw->clk, *parent, *best_parent = NULL;
+	struct clk_hw *parent, *best_parent = NULL;
 	int i, num_parents;
 	unsigned long parent_rate, best = 0, child_rate, best_child_rate = 0;
 
 	/* find the parent that can help provide the fastest rate <= rate */
-	num_parents = __clk_get_num_parents(clk);
+	num_parents = clk_hw_get_num_parents(hw);
 	for (i = 0; i < num_parents; i++) {
-		parent = clk_get_parent_by_index(clk, i);
+		parent = clk_hw_get_parent_by_index(hw, i);
 		if (!parent)
 			continue;
-		if (__clk_get_flags(clk) & CLK_SET_RATE_PARENT)
-			parent_rate = __clk_round_rate(parent, rate);
+		if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)
+			parent_rate = clk_hw_round_rate(parent, req->rate);
 		else
-			parent_rate = __clk_get_rate(parent);
+			parent_rate = clk_hw_get_rate(parent);
 
-		child_rate = clk_factors_round_rate(hw, rate, &parent_rate);
+		child_rate = clk_factors_round_rate(hw, req->rate,
+						    &parent_rate);
 
-		if (child_rate <= rate && child_rate > best_child_rate) {
+		if (child_rate <= req->rate && child_rate > best_child_rate) {
 			best_parent = parent;
 			best = parent_rate;
 			best_child_rate = child_rate;
 		}
 	}
 
-	if (best_parent)
-		*best_parent_p = __clk_get_hw(best_parent);
-	*best_parent_rate = best;
+	if (!best_parent)
+		return -EINVAL;
 
-	return best_child_rate;
+	req->best_parent_hw = best_parent;
+	req->best_parent_rate = best;
+	req->rate = best_child_rate;
+
+	return 0;
 }
 
 static int clk_factors_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -174,9 +175,7 @@ struct clk *sunxi_factors_register(struct device_node *node,
 	int i = 0;
 
 	/* if we have a mux, we will have >1 parents */
-	while (i < FACTORS_MAX_PARENTS &&
-	       (parents[i] = of_clk_get_parent_name(node, i)) != NULL)
-		i++;
+	i = of_clk_parent_fill(node, parents, FACTORS_MAX_PARENTS);
 
 	/*
 	 * some factor clocks, such as pll5 and pll6, may have multiple
diff --git a/drivers/clk/sunxi/clk-mod0.c b/drivers/clk/sunxi/clk-mod0.c
index 9d028aec58e5..d167e1efb927 100644
--- a/drivers/clk/sunxi/clk-mod0.c
+++ b/drivers/clk/sunxi/clk-mod0.c
@@ -14,10 +14,11 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include "clk-factors.h"
 
diff --git a/drivers/clk/sunxi/clk-simple-gates.c b/drivers/clk/sunxi/clk-simple-gates.c
new file mode 100644
index 000000000000..6ce91180da1b
--- /dev/null
+++ b/drivers/clk/sunxi/clk-simple-gates.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright 2015 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+static DEFINE_SPINLOCK(gates_lock);
+
+static void __init sunxi_simple_gates_setup(struct device_node *node,
+					    const int protected[],
+					    int nprotected)
+{
+	struct clk_onecell_data *clk_data;
+	const char *clk_parent, *clk_name;
+	struct property *prop;
+	struct resource res;
+	void __iomem *clk_reg;
+	void __iomem *reg;
+	const __be32 *p;
+	int number, i = 0, j;
+	u8 clk_bit;
+	u32 index;
+
+	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
+	if (IS_ERR(reg))
+		return;
+
+	clk_parent = of_clk_get_parent_name(node, 0);
+
+	clk_data = kmalloc(sizeof(struct clk_onecell_data), GFP_KERNEL);
+	if (!clk_data)
+		goto err_unmap;
+
+	number = of_property_count_u32_elems(node, "clock-indices");
+	of_property_read_u32_index(node, "clock-indices", number - 1, &number);
+
+	clk_data->clks = kcalloc(number + 1, sizeof(struct clk *), GFP_KERNEL);
+	if (!clk_data->clks)
+		goto err_free_data;
+
+	of_property_for_each_u32(node, "clock-indices", prop, p, index) {
+		of_property_read_string_index(node, "clock-output-names",
+					      i, &clk_name);
+
+		clk_reg = reg + 4 * (index / 32);
+		clk_bit = index % 32;
+
+		clk_data->clks[index] = clk_register_gate(NULL, clk_name,
+							  clk_parent, 0,
+							  clk_reg,
+							  clk_bit,
+							  0, &gates_lock);
+		i++;
+
+		if (IS_ERR(clk_data->clks[index])) {
+			WARN_ON(true);
+			continue;
+		}
+
+		for (j = 0; j < nprotected; j++)
+			if (protected[j] == index)
+				clk_prepare_enable(clk_data->clks[index]);
+
+	}
+
+	clk_data->clk_num = number + 1;
+	of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+
+	return;
+
+err_free_data:
+	kfree(clk_data);
+err_unmap:
+	iounmap(reg);
+	of_address_to_resource(node, 0, &res);
+	release_mem_region(res.start, resource_size(&res));
+}
+
+static void __init sunxi_simple_gates_init(struct device_node *node)
+{
+	sunxi_simple_gates_setup(node, NULL, 0);
+}
+
+CLK_OF_DECLARE(sun4i_a10_apb0, "allwinner,sun4i-a10-apb0-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun4i_a10_apb1, "allwinner,sun4i-a10-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun4i_a10_axi, "allwinner,sun4i-a10-axi-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun5i_a10s_apb0, "allwinner,sun5i-a10s-apb0-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun5i_a10s_apb1, "allwinner,sun5i-a10s-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun5i_a13_apb0, "allwinner,sun5i-a13-apb0-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun5i_a13_apb1, "allwinner,sun5i-a13-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun6i_a31_ahb1, "allwinner,sun6i-a31-ahb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun6i_a31_apb1, "allwinner,sun6i-a31-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun6i_a31_apb2, "allwinner,sun6i-a31-apb2-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun7i_a20_apb0, "allwinner,sun7i-a20-apb0-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun7i_a20_apb1, "allwinner,sun7i-a20-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun8i_a23_ahb1, "allwinner,sun8i-a23-ahb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun8i_a23_apb1, "allwinner,sun8i-a23-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun8i_a23_apb2, "allwinner,sun8i-a23-apb2-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun9i_a80_ahb0, "allwinner,sun9i-a80-ahb0-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun9i_a80_ahb1, "allwinner,sun9i-a80-ahb1-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun9i_a80_ahb2, "allwinner,sun9i-a80-ahb2-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun9i_a80_apb0, "allwinner,sun9i-a80-apb0-gates-clk",
+	       sunxi_simple_gates_init);
+CLK_OF_DECLARE(sun9i_a80_apb1, "allwinner,sun9i-a80-apb1-gates-clk",
+	       sunxi_simple_gates_init);
+
+static const int sun4i_a10_ahb_critical_clocks[] __initconst = {
+	14,	/* ahb_sdram */
+};
+
+static void __init sun4i_a10_ahb_init(struct device_node *node)
+{
+	sunxi_simple_gates_setup(node, sun4i_a10_ahb_critical_clocks,
+				 ARRAY_SIZE(sun4i_a10_ahb_critical_clocks));
+}
+CLK_OF_DECLARE(sun4i_a10_ahb, "allwinner,sun4i-a10-ahb-gates-clk",
+	       sun4i_a10_ahb_init);
+CLK_OF_DECLARE(sun5i_a10s_ahb, "allwinner,sun5i-a10s-ahb-gates-clk",
+	       sun4i_a10_ahb_init);
+CLK_OF_DECLARE(sun5i_a13_ahb, "allwinner,sun5i-a13-ahb-gates-clk",
+	       sun4i_a10_ahb_init);
+CLK_OF_DECLARE(sun7i_a20_ahb, "allwinner,sun7i-a20-ahb-gates-clk",
+	       sun4i_a10_ahb_init);
diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c
index 63cf149195ae..806fd019c05d 100644
--- a/drivers/clk/sunxi/clk-sun6i-ar100.c
+++ b/drivers/clk/sunxi/clk-sun6i-ar100.c
@@ -44,28 +44,25 @@ static unsigned long ar100_recalc_rate(struct clk_hw *hw,
 	return (parent_rate >> shift) / (div + 1);
 }
 
-static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate,
-				 unsigned long min_rate,
-				 unsigned long max_rate,
-				 unsigned long *best_parent_rate,
-				 struct clk_hw **best_parent_clk)
+static int ar100_determine_rate(struct clk_hw *hw,
+				struct clk_rate_request *req)
 {
-	int nparents = __clk_get_num_parents(hw->clk);
+	int nparents = clk_hw_get_num_parents(hw);
 	long best_rate = -EINVAL;
 	int i;
 
-	*best_parent_clk = NULL;
+	req->best_parent_hw = NULL;
 
 	for (i = 0; i < nparents; i++) {
 		unsigned long parent_rate;
 		unsigned long tmp_rate;
-		struct clk *parent;
+		struct clk_hw *parent;
 		unsigned long div;
 		int shift;
 
-		parent = clk_get_parent_by_index(hw->clk, i);
-		parent_rate = __clk_get_rate(parent);
-		div = DIV_ROUND_UP(parent_rate, rate);
+		parent = clk_hw_get_parent_by_index(hw, i);
+		parent_rate = clk_hw_get_rate(parent);
+		div = DIV_ROUND_UP(parent_rate, req->rate);
 
 		/*
 		 * The AR100 clk contains 2 divisors:
@@ -101,14 +98,19 @@ static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate,
 			continue;
 
 		tmp_rate = (parent_rate >> shift) / div;
-		if (!*best_parent_clk || tmp_rate > best_rate) {
-			*best_parent_clk = __clk_get_hw(parent);
-			*best_parent_rate = parent_rate;
+		if (!req->best_parent_hw || tmp_rate > best_rate) {
+			req->best_parent_hw = parent;
+			req->best_parent_rate = parent_rate;
 			best_rate = tmp_rate;
 		}
 	}
 
-	return best_rate;
+	if (best_rate < 0)
+		return best_rate;
+
+	req->rate = best_rate;
+
+	return 0;
 }
 
 static int ar100_set_parent(struct clk_hw *hw, u8 index)
@@ -180,7 +182,6 @@ static int sun6i_a31_ar100_clk_probe(struct platform_device *pdev)
 	struct resource *r;
 	struct clk *clk;
 	int nparents;
-	int i;
 
 	ar100 = devm_kzalloc(&pdev->dev, sizeof(*ar100), GFP_KERNEL);
 	if (!ar100)
@@ -195,8 +196,7 @@ static int sun6i_a31_ar100_clk_probe(struct platform_device *pdev)
 	if (nparents > SUN6I_AR100_MAX_PARENTS)
 		nparents = SUN6I_AR100_MAX_PARENTS;
 
-	for (i = 0; i < nparents; i++)
-		parents[i] = of_clk_get_parent_name(np, i);
+	of_clk_parent_fill(np, parents, nparents);
 
 	of_property_read_string(np, "clock-output-names", &clk_name);
 
diff --git a/drivers/clk/sunxi/clk-sun8i-mbus.c b/drivers/clk/sunxi/clk-sun8i-mbus.c
index 14cd026064bf..bf117a636d23 100644
--- a/drivers/clk/sunxi/clk-sun8i-mbus.c
+++ b/drivers/clk/sunxi/clk-sun8i-mbus.c
@@ -14,8 +14,8 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/of_address.h>
 
 #include "clk-factors.h"
diff --git a/drivers/clk/sunxi/clk-sun9i-core.c b/drivers/clk/sunxi/clk-sun9i-core.c
index 887f4ea161bb..6c4c98324d3c 100644
--- a/drivers/clk/sunxi/clk-sun9i-core.c
+++ b/drivers/clk/sunxi/clk-sun9i-core.c
@@ -14,8 +14,8 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/log2.h>
diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c
index 710c273648d7..3436a948b796 100644
--- a/drivers/clk/sunxi/clk-sun9i-mmc.c
+++ b/drivers/clk/sunxi/clk-sun9i-mmc.c
@@ -14,14 +14,15 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/reset.h>
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 #define SUN9I_MMC_WIDTH		4
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 9a82f17d2d73..413070d07b3f 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -14,11 +14,13 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/reset-controller.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/log2.h>
 
@@ -118,42 +120,42 @@ static long sun6i_ahb1_clk_round(unsigned long rate, u8 *divp, u8 *pre_divp,
 	return (parent_rate / calcm) >> calcp;
 }
 
-static long sun6i_ahb1_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
-					  unsigned long min_rate,
-					  unsigned long max_rate,
-					  unsigned long *best_parent_rate,
-					  struct clk_hw **best_parent_clk)
+static int sun6i_ahb1_clk_determine_rate(struct clk_hw *hw,
+					 struct clk_rate_request *req)
 {
-	struct clk *clk = hw->clk, *parent, *best_parent = NULL;
+	struct clk_hw *parent, *best_parent = NULL;
 	int i, num_parents;
 	unsigned long parent_rate, best = 0, child_rate, best_child_rate = 0;
 
 	/* find the parent that can help provide the fastest rate <= rate */
-	num_parents = __clk_get_num_parents(clk);
+	num_parents = clk_hw_get_num_parents(hw);
 	for (i = 0; i < num_parents; i++) {
-		parent = clk_get_parent_by_index(clk, i);
+		parent = clk_hw_get_parent_by_index(hw, i);
 		if (!parent)
 			continue;
-		if (__clk_get_flags(clk) & CLK_SET_RATE_PARENT)
-			parent_rate = __clk_round_rate(parent, rate);
+		if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)
+			parent_rate = clk_hw_round_rate(parent, req->rate);
 		else
-			parent_rate = __clk_get_rate(parent);
+			parent_rate = clk_hw_get_rate(parent);
 
-		child_rate = sun6i_ahb1_clk_round(rate, NULL, NULL, i,
+		child_rate = sun6i_ahb1_clk_round(req->rate, NULL, NULL, i,
 						  parent_rate);
 
-		if (child_rate <= rate && child_rate > best_child_rate) {
+		if (child_rate <= req->rate && child_rate > best_child_rate) {
 			best_parent = parent;
 			best = parent_rate;
 			best_child_rate = child_rate;
 		}
 	}
 
-	if (best_parent)
-		*best_parent_clk = __clk_get_hw(best_parent);
-	*best_parent_rate = best;
+	if (!best_parent)
+		return -EINVAL;
 
-	return best_child_rate;
+	req->best_parent_hw = best_parent;
+	req->best_parent_rate = best;
+	req->rate = best_child_rate;
+
+	return 0;
 }
 
 static int sun6i_ahb1_clk_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -195,17 +197,14 @@ static void __init sun6i_ahb1_clk_setup(struct device_node *node)
 	const char *clk_name = node->name;
 	const char *parents[SUN6I_AHB1_MAX_PARENTS];
 	void __iomem *reg;
-	int i = 0;
+	int i;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
 	if (IS_ERR(reg))
 		return;
 
 	/* we have a mux, we will have >1 parents */
-	while (i < SUN6I_AHB1_MAX_PARENTS &&
-	       (parents[i] = of_clk_get_parent_name(node, i)) != NULL)
-		i++;
-
+	i = of_clk_parent_fill(node, parents, SUN6I_AHB1_MAX_PARENTS);
 	of_property_read_string(node, "clock-output-names", &clk_name);
 
 	ahb1 = kzalloc(sizeof(struct sun6i_ahb1_clk), GFP_KERNEL);
@@ -786,14 +785,11 @@ static void __init sunxi_mux_clk_setup(struct device_node *node,
 	const char *clk_name = node->name;
 	const char *parents[SUNXI_MAX_PARENTS];
 	void __iomem *reg;
-	int i = 0;
+	int i;
 
 	reg = of_iomap(node, 0);
 
-	while (i < SUNXI_MAX_PARENTS &&
-	       (parents[i] = of_clk_get_parent_name(node, i)) != NULL)
-		i++;
-
+	i = of_clk_parent_fill(node, parents, SUNXI_MAX_PARENTS);
 	of_property_read_string(node, "clock-output-names", &clk_name);
 
 	clk = clk_register_mux(NULL, clk_name, parents, i,
@@ -900,150 +896,6 @@ struct gates_data {
 	DECLARE_BITMAP(mask, SUNXI_GATES_MAX_SIZE);
 };
 
-static const struct gates_data sun4i_axi_gates_data __initconst = {
-	.mask = {1},
-};
-
-static const struct gates_data sun4i_ahb_gates_data __initconst = {
-	.mask = {0x7F77FFF, 0x14FB3F},
-};
-
-static const struct gates_data sun5i_a10s_ahb_gates_data __initconst = {
-	.mask = {0x147667e7, 0x185915},
-};
-
-static const struct gates_data sun5i_a13_ahb_gates_data __initconst = {
-	.mask = {0x107067e7, 0x185111},
-};
-
-static const struct gates_data sun6i_a31_ahb1_gates_data __initconst = {
-	.mask = {0xEDFE7F62, 0x794F931},
-};
-
-static const struct gates_data sun7i_a20_ahb_gates_data __initconst = {
-	.mask = { 0x12f77fff, 0x16ff3f },
-};
-
-static const struct gates_data sun8i_a23_ahb1_gates_data __initconst = {
-	.mask = {0x25386742, 0x2505111},
-};
-
-static const struct gates_data sun9i_a80_ahb0_gates_data __initconst = {
-	.mask = {0xF5F12B},
-};
-
-static const struct gates_data sun9i_a80_ahb1_gates_data __initconst = {
-	.mask = {0x1E20003},
-};
-
-static const struct gates_data sun9i_a80_ahb2_gates_data __initconst = {
-	.mask = {0x9B7},
-};
-
-static const struct gates_data sun4i_apb0_gates_data __initconst = {
-	.mask = {0x4EF},
-};
-
-static const struct gates_data sun5i_a10s_apb0_gates_data __initconst = {
-	.mask = {0x469},
-};
-
-static const struct gates_data sun5i_a13_apb0_gates_data __initconst = {
-	.mask = {0x61},
-};
-
-static const struct gates_data sun7i_a20_apb0_gates_data __initconst = {
-	.mask = { 0x4ff },
-};
-
-static const struct gates_data sun9i_a80_apb0_gates_data __initconst = {
-	.mask = {0xEB822},
-};
-
-static const struct gates_data sun4i_apb1_gates_data __initconst = {
-	.mask = {0xFF00F7},
-};
-
-static const struct gates_data sun5i_a10s_apb1_gates_data __initconst = {
-	.mask = {0xf0007},
-};
-
-static const struct gates_data sun5i_a13_apb1_gates_data __initconst = {
-	.mask = {0xa0007},
-};
-
-static const struct gates_data sun6i_a31_apb1_gates_data __initconst = {
-	.mask = {0x3031},
-};
-
-static const struct gates_data sun8i_a23_apb1_gates_data __initconst = {
-	.mask = {0x3021},
-};
-
-static const struct gates_data sun6i_a31_apb2_gates_data __initconst = {
-	.mask = {0x3F000F},
-};
-
-static const struct gates_data sun7i_a20_apb1_gates_data __initconst = {
-	.mask = { 0xff80ff },
-};
-
-static const struct gates_data sun9i_a80_apb1_gates_data __initconst = {
-	.mask = {0x3F001F},
-};
-
-static const struct gates_data sun8i_a23_apb2_gates_data __initconst = {
-	.mask = {0x1F0007},
-};
-
-static void __init sunxi_gates_clk_setup(struct device_node *node,
-					 struct gates_data *data)
-{
-	struct clk_onecell_data *clk_data;
-	const char *clk_parent;
-	const char *clk_name;
-	void __iomem *reg;
-	int qty;
-	int i = 0;
-	int j = 0;
-
-	reg = of_iomap(node, 0);
-
-	clk_parent = of_clk_get_parent_name(node, 0);
-
-	/* Worst-case size approximation and memory allocation */
-	qty = find_last_bit(data->mask, SUNXI_GATES_MAX_SIZE);
-	clk_data = kmalloc(sizeof(struct clk_onecell_data), GFP_KERNEL);
-	if (!clk_data)
-		return;
-	clk_data->clks = kzalloc((qty+1) * sizeof(struct clk *), GFP_KERNEL);
-	if (!clk_data->clks) {
-		kfree(clk_data);
-		return;
-	}
-
-	for_each_set_bit(i, data->mask, SUNXI_GATES_MAX_SIZE) {
-		of_property_read_string_index(node, "clock-output-names",
-					      j, &clk_name);
-
-		clk_data->clks[i] = clk_register_gate(NULL, clk_name,
-						      clk_parent, 0,
-						      reg + 4 * (i/32), i % 32,
-						      0, &clk_lock);
-		WARN_ON(IS_ERR(clk_data->clks[i]));
-		clk_register_clkdev(clk_data->clks[i], clk_name, NULL);
-
-		j++;
-	}
-
-	/* Adjust to the real max */
-	clk_data->clk_num = i;
-
-	of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
-}
-
-
-
 /**
  * sunxi_divs_clk_setup() helper data
  */
@@ -1281,34 +1133,6 @@ static const struct of_device_id clk_mux_match[] __initconst = {
 	{}
 };
 
-/* Matches for gate clocks */
-static const struct of_device_id clk_gates_match[] __initconst = {
-	{.compatible = "allwinner,sun4i-a10-axi-gates-clk", .data = &sun4i_axi_gates_data,},
-	{.compatible = "allwinner,sun4i-a10-ahb-gates-clk", .data = &sun4i_ahb_gates_data,},
-	{.compatible = "allwinner,sun5i-a10s-ahb-gates-clk", .data = &sun5i_a10s_ahb_gates_data,},
-	{.compatible = "allwinner,sun5i-a13-ahb-gates-clk", .data = &sun5i_a13_ahb_gates_data,},
-	{.compatible = "allwinner,sun6i-a31-ahb1-gates-clk", .data = &sun6i_a31_ahb1_gates_data,},
-	{.compatible = "allwinner,sun7i-a20-ahb-gates-clk", .data = &sun7i_a20_ahb_gates_data,},
-	{.compatible = "allwinner,sun8i-a23-ahb1-gates-clk", .data = &sun8i_a23_ahb1_gates_data,},
-	{.compatible = "allwinner,sun9i-a80-ahb0-gates-clk", .data = &sun9i_a80_ahb0_gates_data,},
-	{.compatible = "allwinner,sun9i-a80-ahb1-gates-clk", .data = &sun9i_a80_ahb1_gates_data,},
-	{.compatible = "allwinner,sun9i-a80-ahb2-gates-clk", .data = &sun9i_a80_ahb2_gates_data,},
-	{.compatible = "allwinner,sun4i-a10-apb0-gates-clk", .data = &sun4i_apb0_gates_data,},
-	{.compatible = "allwinner,sun5i-a10s-apb0-gates-clk", .data = &sun5i_a10s_apb0_gates_data,},
-	{.compatible = "allwinner,sun5i-a13-apb0-gates-clk", .data = &sun5i_a13_apb0_gates_data,},
-	{.compatible = "allwinner,sun7i-a20-apb0-gates-clk", .data = &sun7i_a20_apb0_gates_data,},
-	{.compatible = "allwinner,sun9i-a80-apb0-gates-clk", .data = &sun9i_a80_apb0_gates_data,},
-	{.compatible = "allwinner,sun4i-a10-apb1-gates-clk", .data = &sun4i_apb1_gates_data,},
-	{.compatible = "allwinner,sun5i-a10s-apb1-gates-clk", .data = &sun5i_a10s_apb1_gates_data,},
-	{.compatible = "allwinner,sun5i-a13-apb1-gates-clk", .data = &sun5i_a13_apb1_gates_data,},
-	{.compatible = "allwinner,sun6i-a31-apb1-gates-clk", .data = &sun6i_a31_apb1_gates_data,},
-	{.compatible = "allwinner,sun7i-a20-apb1-gates-clk", .data = &sun7i_a20_apb1_gates_data,},
-	{.compatible = "allwinner,sun8i-a23-apb1-gates-clk", .data = &sun8i_a23_apb1_gates_data,},
-	{.compatible = "allwinner,sun9i-a80-apb1-gates-clk", .data = &sun9i_a80_apb1_gates_data,},
-	{.compatible = "allwinner,sun6i-a31-apb2-gates-clk", .data = &sun6i_a31_apb2_gates_data,},
-	{.compatible = "allwinner,sun8i-a23-apb2-gates-clk", .data = &sun8i_a23_apb2_gates_data,},
-	{}
-};
 
 static void __init of_sunxi_table_clock_setup(const struct of_device_id *clk_match,
 					      void *function)
@@ -1340,9 +1164,6 @@ static void __init sunxi_init_clocks(const char *clocks[], int nclocks)
 	/* Register mux clocks */
 	of_sunxi_table_clock_setup(clk_mux_match, sunxi_mux_clk_setup);
 
-	/* Register gate clocks */
-	of_sunxi_table_clock_setup(clk_gates_match, sunxi_gates_clk_setup);
-
 	/* Protect the clocks that needs to stay on */
 	for (i = 0; i < nclocks; i++) {
 		struct clk *clk = clk_get(NULL, clocks[i]);
@@ -1354,7 +1175,6 @@ static void __init sunxi_init_clocks(const char *clocks[], int nclocks)
 
 static const char *sun4i_a10_critical_clocks[] __initdata = {
 	"pll5_ddr",
-	"ahb_sdram",
 };
 
 static void __init sun4i_a10_init_clocks(struct device_node *node)
@@ -1367,7 +1187,6 @@ CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sun4i_a10_init_clocks)
 static const char *sun5i_critical_clocks[] __initdata = {
 	"cpu",
 	"pll5_ddr",
-	"ahb_sdram",
 };
 
 static void __init sun5i_init_clocks(struct device_node *node)
@@ -1391,6 +1210,7 @@ static void __init sun6i_init_clocks(struct device_node *node)
 CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sun6i_init_clocks);
 CLK_OF_DECLARE(sun6i_a31s_clk_init, "allwinner,sun6i-a31s", sun6i_init_clocks);
 CLK_OF_DECLARE(sun8i_a23_clk_init, "allwinner,sun8i-a23", sun6i_init_clocks);
+CLK_OF_DECLARE(sun8i_a33_clk_init, "allwinner,sun8i-a33", sun6i_init_clocks);
 
 static void __init sun9i_init_clocks(struct device_node *node)
 {
diff --git a/drivers/clk/sunxi/clk-usb.c b/drivers/clk/sunxi/clk-usb.c
index 3a25f9588e67..1a72cd672839 100644
--- a/drivers/clk/sunxi/clk-usb.c
+++ b/drivers/clk/sunxi/clk-usb.c
@@ -14,11 +14,12 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/reset-controller.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 
diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile
index aec862ba7a17..826c325dc2e8 100644
--- a/drivers/clk/tegra/Makefile
+++ b/drivers/clk/tegra/Makefile
@@ -1,5 +1,6 @@
 obj-y					+= clk.o
 obj-y					+= clk-audio-sync.o
+obj-y					+= clk-dfll.o
 obj-y					+= clk-divider.o
 obj-y					+= clk-periph.o
 obj-y					+= clk-periph-gate.o
@@ -16,4 +17,6 @@ obj-$(CONFIG_ARCH_TEGRA_2x_SOC)         += clk-tegra20.o
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)         += clk-tegra30.o
 obj-$(CONFIG_ARCH_TEGRA_114_SOC)	+= clk-tegra114.o
 obj-$(CONFIG_ARCH_TEGRA_124_SOC)	+= clk-tegra124.o
+obj-$(CONFIG_ARCH_TEGRA_124_SOC)	+= clk-tegra124-dfll-fcpu.o
 obj-$(CONFIG_ARCH_TEGRA_132_SOC)	+= clk-tegra124.o
+obj-y					+= cvb.o
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
new file mode 100644
index 000000000000..c2ff859ee0e8
--- /dev/null
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -0,0 +1,1757 @@
+/*
+ * clk-dfll.c - Tegra DFLL clock source common code
+ *
+ * Copyright (C) 2012-2014 NVIDIA Corporation. All rights reserved.
+ *
+ * Aleksandr Frid <afrid@nvidia.com>
+ * Paul Walmsley <pwalmsley@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * This library is for the DVCO and DFLL IP blocks on the Tegra124
+ * SoC. These IP blocks together are also known at NVIDIA as
+ * "CL-DVFS". To try to avoid confusion, this code refers to them
+ * collectively as the "DFLL."
+ *
+ * The DFLL is a root clocksource which tolerates some amount of
+ * supply voltage noise. Tegra124 uses it to clock the fast CPU
+ * complex when the target CPU speed is above a particular rate. The
+ * DFLL can be operated in either open-loop mode or closed-loop mode.
+ * In open-loop mode, the DFLL generates an output clock appropriate
+ * to the supply voltage. In closed-loop mode, when configured with a
+ * target frequency, the DFLL minimizes supply voltage while
+ * delivering an average frequency equal to the target.
+ *
+ * Devices clocked by the DFLL must be able to tolerate frequency
+ * variation. In the case of the CPU, it's important to note that the
+ * CPU cycle time will vary. This has implications for
+ * performance-measurement code and any code that relies on the CPU
+ * cycle time to delay for a certain length of time.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm_opp.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+#include <linux/seq_file.h>
+
+#include "clk-dfll.h"
+
+/*
+ * DFLL control registers - access via dfll_{readl,writel}
+ */
+
+/* DFLL_CTRL: DFLL control register */
+#define DFLL_CTRL			0x00
+#define DFLL_CTRL_MODE_MASK		0x03
+
+/* DFLL_CONFIG: DFLL sample rate control */
+#define DFLL_CONFIG			0x04
+#define DFLL_CONFIG_DIV_MASK		0xff
+#define DFLL_CONFIG_DIV_PRESCALE	32
+
+/* DFLL_PARAMS: tuning coefficients for closed loop integrator */
+#define DFLL_PARAMS			0x08
+#define DFLL_PARAMS_CG_SCALE		(0x1 << 24)
+#define DFLL_PARAMS_FORCE_MODE_SHIFT	22
+#define DFLL_PARAMS_FORCE_MODE_MASK	(0x3 << DFLL_PARAMS_FORCE_MODE_SHIFT)
+#define DFLL_PARAMS_CF_PARAM_SHIFT	16
+#define DFLL_PARAMS_CF_PARAM_MASK	(0x3f << DFLL_PARAMS_CF_PARAM_SHIFT)
+#define DFLL_PARAMS_CI_PARAM_SHIFT	8
+#define DFLL_PARAMS_CI_PARAM_MASK	(0x7 << DFLL_PARAMS_CI_PARAM_SHIFT)
+#define DFLL_PARAMS_CG_PARAM_SHIFT	0
+#define DFLL_PARAMS_CG_PARAM_MASK	(0xff << DFLL_PARAMS_CG_PARAM_SHIFT)
+
+/* DFLL_TUNE0: delay line configuration register 0 */
+#define DFLL_TUNE0			0x0c
+
+/* DFLL_TUNE1: delay line configuration register 1 */
+#define DFLL_TUNE1			0x10
+
+/* DFLL_FREQ_REQ: target DFLL frequency control */
+#define DFLL_FREQ_REQ			0x14
+#define DFLL_FREQ_REQ_FORCE_ENABLE	(0x1 << 28)
+#define DFLL_FREQ_REQ_FORCE_SHIFT	16
+#define DFLL_FREQ_REQ_FORCE_MASK	(0xfff << DFLL_FREQ_REQ_FORCE_SHIFT)
+#define FORCE_MAX			2047
+#define FORCE_MIN			-2048
+#define DFLL_FREQ_REQ_SCALE_SHIFT	8
+#define DFLL_FREQ_REQ_SCALE_MASK	(0xff << DFLL_FREQ_REQ_SCALE_SHIFT)
+#define DFLL_FREQ_REQ_SCALE_MAX		256
+#define DFLL_FREQ_REQ_FREQ_VALID	(0x1 << 7)
+#define DFLL_FREQ_REQ_MULT_SHIFT	0
+#define DFLL_FREQ_REG_MULT_MASK		(0x7f << DFLL_FREQ_REQ_MULT_SHIFT)
+#define FREQ_MAX			127
+
+/* DFLL_DROOP_CTRL: droop prevention control */
+#define DFLL_DROOP_CTRL			0x1c
+
+/* DFLL_OUTPUT_CFG: closed loop mode control registers */
+/* NOTE: access via dfll_i2c_{readl,writel} */
+#define DFLL_OUTPUT_CFG			0x20
+#define DFLL_OUTPUT_CFG_I2C_ENABLE	(0x1 << 30)
+#define OUT_MASK			0x3f
+#define DFLL_OUTPUT_CFG_SAFE_SHIFT	24
+#define DFLL_OUTPUT_CFG_SAFE_MASK	\
+		(OUT_MASK << DFLL_OUTPUT_CFG_SAFE_SHIFT)
+#define DFLL_OUTPUT_CFG_MAX_SHIFT	16
+#define DFLL_OUTPUT_CFG_MAX_MASK	\
+		(OUT_MASK << DFLL_OUTPUT_CFG_MAX_SHIFT)
+#define DFLL_OUTPUT_CFG_MIN_SHIFT	8
+#define DFLL_OUTPUT_CFG_MIN_MASK	\
+		(OUT_MASK << DFLL_OUTPUT_CFG_MIN_SHIFT)
+#define DFLL_OUTPUT_CFG_PWM_DELTA	(0x1 << 7)
+#define DFLL_OUTPUT_CFG_PWM_ENABLE	(0x1 << 6)
+#define DFLL_OUTPUT_CFG_PWM_DIV_SHIFT	0
+#define DFLL_OUTPUT_CFG_PWM_DIV_MASK	\
+		(OUT_MASK << DFLL_OUTPUT_CFG_PWM_DIV_SHIFT)
+
+/* DFLL_OUTPUT_FORCE: closed loop mode voltage forcing control */
+#define DFLL_OUTPUT_FORCE		0x24
+#define DFLL_OUTPUT_FORCE_ENABLE	(0x1 << 6)
+#define DFLL_OUTPUT_FORCE_VALUE_SHIFT	0
+#define DFLL_OUTPUT_FORCE_VALUE_MASK	\
+		(OUT_MASK << DFLL_OUTPUT_FORCE_VALUE_SHIFT)
+
+/* DFLL_MONITOR_CTRL: internal monitor data source control */
+#define DFLL_MONITOR_CTRL		0x28
+#define DFLL_MONITOR_CTRL_FREQ		6
+
+/* DFLL_MONITOR_DATA: internal monitor data output */
+#define DFLL_MONITOR_DATA		0x2c
+#define DFLL_MONITOR_DATA_NEW_MASK	(0x1 << 16)
+#define DFLL_MONITOR_DATA_VAL_SHIFT	0
+#define DFLL_MONITOR_DATA_VAL_MASK	(0xFFFF << DFLL_MONITOR_DATA_VAL_SHIFT)
+
+/*
+ * I2C output control registers - access via dfll_i2c_{readl,writel}
+ */
+
+/* DFLL_I2C_CFG: I2C controller configuration register */
+#define DFLL_I2C_CFG			0x40
+#define DFLL_I2C_CFG_ARB_ENABLE		(0x1 << 20)
+#define DFLL_I2C_CFG_HS_CODE_SHIFT	16
+#define DFLL_I2C_CFG_HS_CODE_MASK	(0x7 << DFLL_I2C_CFG_HS_CODE_SHIFT)
+#define DFLL_I2C_CFG_PACKET_ENABLE	(0x1 << 15)
+#define DFLL_I2C_CFG_SIZE_SHIFT		12
+#define DFLL_I2C_CFG_SIZE_MASK		(0x7 << DFLL_I2C_CFG_SIZE_SHIFT)
+#define DFLL_I2C_CFG_SLAVE_ADDR_10	(0x1 << 10)
+#define DFLL_I2C_CFG_SLAVE_ADDR_SHIFT_7BIT	1
+#define DFLL_I2C_CFG_SLAVE_ADDR_SHIFT_10BIT	0
+
+/* DFLL_I2C_VDD_REG_ADDR: PMIC I2C address for closed loop mode */
+#define DFLL_I2C_VDD_REG_ADDR		0x44
+
+/* DFLL_I2C_STS: I2C controller status */
+#define DFLL_I2C_STS			0x48
+#define DFLL_I2C_STS_I2C_LAST_SHIFT	1
+#define DFLL_I2C_STS_I2C_REQ_PENDING	0x1
+
+/* DFLL_INTR_STS: DFLL interrupt status register */
+#define DFLL_INTR_STS			0x5c
+
+/* DFLL_INTR_EN: DFLL interrupt enable register */
+#define DFLL_INTR_EN			0x60
+#define DFLL_INTR_MIN_MASK		0x1
+#define DFLL_INTR_MAX_MASK		0x2
+
+/*
+ * Integrated I2C controller registers - relative to td->i2c_controller_base
+ */
+
+/* DFLL_I2C_CLK_DIVISOR: I2C controller clock divisor */
+#define DFLL_I2C_CLK_DIVISOR		0x6c
+#define DFLL_I2C_CLK_DIVISOR_MASK	0xffff
+#define DFLL_I2C_CLK_DIVISOR_FS_SHIFT	16
+#define DFLL_I2C_CLK_DIVISOR_HS_SHIFT	0
+#define DFLL_I2C_CLK_DIVISOR_PREDIV	8
+#define DFLL_I2C_CLK_DIVISOR_HSMODE_PREDIV	12
+
+/*
+ * Other constants
+ */
+
+/* MAX_DFLL_VOLTAGES: number of LUT entries in the DFLL IP block */
+#define MAX_DFLL_VOLTAGES		33
+
+/*
+ * REF_CLK_CYC_PER_DVCO_SAMPLE: the number of ref_clk cycles that the hardware
+ *    integrates the DVCO counter over - used for debug rate monitoring and
+ *    droop control
+ */
+#define REF_CLK_CYC_PER_DVCO_SAMPLE	4
+
+/*
+ * REF_CLOCK_RATE: the DFLL reference clock rate currently supported by this
+ * driver, in Hz
+ */
+#define REF_CLOCK_RATE			51000000UL
+
+#define DVCO_RATE_TO_MULT(rate, ref_rate)	((rate) / ((ref_rate) / 2))
+#define MULT_TO_DVCO_RATE(mult, ref_rate)	((mult) * ((ref_rate) / 2))
+
+/**
+ * enum dfll_ctrl_mode - DFLL hardware operating mode
+ * @DFLL_UNINITIALIZED: (uninitialized state - not in hardware bitfield)
+ * @DFLL_DISABLED: DFLL not generating an output clock
+ * @DFLL_OPEN_LOOP: DVCO running, but DFLL not adjusting voltage
+ * @DFLL_CLOSED_LOOP: DVCO running, and DFLL adjusting voltage to match
+ *		      the requested rate
+ *
+ * The integer corresponding to the last two states, minus one, is
+ * written to the DFLL hardware to change operating modes.
+ */
+enum dfll_ctrl_mode {
+	DFLL_UNINITIALIZED = 0,
+	DFLL_DISABLED = 1,
+	DFLL_OPEN_LOOP = 2,
+	DFLL_CLOSED_LOOP = 3,
+};
+
+/**
+ * enum dfll_tune_range - voltage range that the driver believes it's in
+ * @DFLL_TUNE_UNINITIALIZED: DFLL tuning not yet programmed
+ * @DFLL_TUNE_LOW: DFLL in the low-voltage range (or open-loop mode)
+ *
+ * Some DFLL tuning parameters may need to change depending on the
+ * DVCO's voltage; these states represent the ranges that the driver
+ * supports. These are software states; these values are never
+ * written into registers.
+ */
+enum dfll_tune_range {
+	DFLL_TUNE_UNINITIALIZED = 0,
+	DFLL_TUNE_LOW = 1,
+};
+
+/**
+ * struct dfll_rate_req - target DFLL rate request data
+ * @rate: target frequency, after the postscaling
+ * @dvco_target_rate: target frequency, after the postscaling
+ * @lut_index: LUT index at which voltage the dvco_target_rate will be reached
+ * @mult_bits: value to program to the MULT bits of the DFLL_FREQ_REQ register
+ * @scale_bits: value to program to the SCALE bits of the DFLL_FREQ_REQ register
+ */
+struct dfll_rate_req {
+	unsigned long rate;
+	unsigned long dvco_target_rate;
+	int lut_index;
+	u8 mult_bits;
+	u8 scale_bits;
+};
+
+struct tegra_dfll {
+	struct device			*dev;
+	struct tegra_dfll_soc_data	*soc;
+
+	void __iomem			*base;
+	void __iomem			*i2c_base;
+	void __iomem			*i2c_controller_base;
+	void __iomem			*lut_base;
+
+	struct regulator		*vdd_reg;
+	struct clk			*soc_clk;
+	struct clk			*ref_clk;
+	struct clk			*i2c_clk;
+	struct clk			*dfll_clk;
+	struct reset_control		*dvco_rst;
+	unsigned long			ref_rate;
+	unsigned long			i2c_clk_rate;
+	unsigned long			dvco_rate_min;
+
+	enum dfll_ctrl_mode		mode;
+	enum dfll_tune_range		tune_range;
+	struct dentry			*debugfs_dir;
+	struct clk_hw			dfll_clk_hw;
+	const char			*output_clock_name;
+	struct dfll_rate_req		last_req;
+	unsigned long			last_unrounded_rate;
+
+	/* Parameters from DT */
+	u32				droop_ctrl;
+	u32				sample_rate;
+	u32				force_mode;
+	u32				cf;
+	u32				ci;
+	u32				cg;
+	bool				cg_scale;
+
+	/* I2C interface parameters */
+	u32				i2c_fs_rate;
+	u32				i2c_reg;
+	u32				i2c_slave_addr;
+
+	/* i2c_lut array entries are regulator framework selectors */
+	unsigned			i2c_lut[MAX_DFLL_VOLTAGES];
+	int				i2c_lut_size;
+	u8				lut_min, lut_max, lut_safe;
+};
+
+#define clk_hw_to_dfll(_hw) container_of(_hw, struct tegra_dfll, dfll_clk_hw)
+
+/* mode_name: map numeric DFLL modes to names for friendly console messages */
+static const char * const mode_name[] = {
+	[DFLL_UNINITIALIZED] = "uninitialized",
+	[DFLL_DISABLED] = "disabled",
+	[DFLL_OPEN_LOOP] = "open_loop",
+	[DFLL_CLOSED_LOOP] = "closed_loop",
+};
+
+/*
+ * Register accessors
+ */
+
+static inline u32 dfll_readl(struct tegra_dfll *td, u32 offs)
+{
+	return __raw_readl(td->base + offs);
+}
+
+static inline void dfll_writel(struct tegra_dfll *td, u32 val, u32 offs)
+{
+	WARN_ON(offs >= DFLL_I2C_CFG);
+	__raw_writel(val, td->base + offs);
+}
+
+static inline void dfll_wmb(struct tegra_dfll *td)
+{
+	dfll_readl(td, DFLL_CTRL);
+}
+
+/* I2C output control registers - for addresses above DFLL_I2C_CFG */
+
+static inline u32 dfll_i2c_readl(struct tegra_dfll *td, u32 offs)
+{
+	return __raw_readl(td->i2c_base + offs);
+}
+
+static inline void dfll_i2c_writel(struct tegra_dfll *td, u32 val, u32 offs)
+{
+	__raw_writel(val, td->i2c_base + offs);
+}
+
+static inline void dfll_i2c_wmb(struct tegra_dfll *td)
+{
+	dfll_i2c_readl(td, DFLL_I2C_CFG);
+}
+
+/**
+ * dfll_is_running - is the DFLL currently generating a clock?
+ * @td: DFLL instance
+ *
+ * If the DFLL is currently generating an output clock signal, return
+ * true; otherwise return false.
+ */
+static bool dfll_is_running(struct tegra_dfll *td)
+{
+	return td->mode >= DFLL_OPEN_LOOP;
+}
+
+/*
+ * Runtime PM suspend/resume callbacks
+ */
+
+/**
+ * tegra_dfll_runtime_resume - enable all clocks needed by the DFLL
+ * @dev: DFLL device *
+ *
+ * Enable all clocks needed by the DFLL. Assumes that clk_prepare()
+ * has already been called on all the clocks.
+ *
+ * XXX Should also handle context restore when returning from off.
+ */
+int tegra_dfll_runtime_resume(struct device *dev)
+{
+	struct tegra_dfll *td = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_enable(td->ref_clk);
+	if (ret) {
+		dev_err(dev, "could not enable ref clock: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_enable(td->soc_clk);
+	if (ret) {
+		dev_err(dev, "could not enable register clock: %d\n", ret);
+		clk_disable(td->ref_clk);
+		return ret;
+	}
+
+	ret = clk_enable(td->i2c_clk);
+	if (ret) {
+		dev_err(dev, "could not enable i2c clock: %d\n", ret);
+		clk_disable(td->soc_clk);
+		clk_disable(td->ref_clk);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(tegra_dfll_runtime_resume);
+
+/**
+ * tegra_dfll_runtime_suspend - disable all clocks needed by the DFLL
+ * @dev: DFLL device *
+ *
+ * Disable all clocks needed by the DFLL. Assumes that other code
+ * will later call clk_unprepare().
+ */
+int tegra_dfll_runtime_suspend(struct device *dev)
+{
+	struct tegra_dfll *td = dev_get_drvdata(dev);
+
+	clk_disable(td->ref_clk);
+	clk_disable(td->soc_clk);
+	clk_disable(td->i2c_clk);
+
+	return 0;
+}
+EXPORT_SYMBOL(tegra_dfll_runtime_suspend);
+
+/*
+ * DFLL tuning operations (per-voltage-range tuning settings)
+ */
+
+/**
+ * dfll_tune_low - tune to DFLL and CPU settings valid for any voltage
+ * @td: DFLL instance
+ *
+ * Tune the DFLL oscillator parameters and the CPU clock shaper for
+ * the low-voltage range. These settings are valid for any voltage,
+ * but may not be optimal.
+ */
+static void dfll_tune_low(struct tegra_dfll *td)
+{
+	td->tune_range = DFLL_TUNE_LOW;
+
+	dfll_writel(td, td->soc->tune0_low, DFLL_TUNE0);
+	dfll_writel(td, td->soc->tune1, DFLL_TUNE1);
+	dfll_wmb(td);
+
+	if (td->soc->set_clock_trimmers_low)
+		td->soc->set_clock_trimmers_low();
+}
+
+/*
+ * Output clock scaler helpers
+ */
+
+/**
+ * dfll_scale_dvco_rate - calculate scaled rate from the DVCO rate
+ * @scale_bits: clock scaler value (bits in the DFLL_FREQ_REQ_SCALE field)
+ * @dvco_rate: the DVCO rate
+ *
+ * Apply the same scaling formula that the DFLL hardware uses to scale
+ * the DVCO rate.
+ */
+static unsigned long dfll_scale_dvco_rate(int scale_bits,
+					  unsigned long dvco_rate)
+{
+	return (u64)dvco_rate * (scale_bits + 1) / DFLL_FREQ_REQ_SCALE_MAX;
+}
+
+/*
+ * Monitor control
+ */
+
+/**
+ * dfll_calc_monitored_rate - convert DFLL_MONITOR_DATA_VAL rate into real freq
+ * @monitor_data: value read from the DFLL_MONITOR_DATA_VAL bitfield
+ * @ref_rate: DFLL reference clock rate
+ *
+ * Convert @monitor_data from DFLL_MONITOR_DATA_VAL units into cycles
+ * per second. Returns the converted value.
+ */
+static u64 dfll_calc_monitored_rate(u32 monitor_data,
+				    unsigned long ref_rate)
+{
+	return monitor_data * (ref_rate / REF_CLK_CYC_PER_DVCO_SAMPLE);
+}
+
+/**
+ * dfll_read_monitor_rate - return the DFLL's output rate from internal monitor
+ * @td: DFLL instance
+ *
+ * If the DFLL is enabled, return the last rate reported by the DFLL's
+ * internal monitoring hardware. This works in both open-loop and
+ * closed-loop mode, and takes the output scaler setting into account.
+ * Assumes that the monitor was programmed to monitor frequency before
+ * the sample period started. If the driver believes that the DFLL is
+ * currently uninitialized or disabled, it will return 0, since
+ * otherwise the DFLL monitor data register will return the last
+ * measured rate from when the DFLL was active.
+ */
+static u64 dfll_read_monitor_rate(struct tegra_dfll *td)
+{
+	u32 v, s;
+	u64 pre_scaler_rate, post_scaler_rate;
+
+	if (!dfll_is_running(td))
+		return 0;
+
+	v = dfll_readl(td, DFLL_MONITOR_DATA);
+	v = (v & DFLL_MONITOR_DATA_VAL_MASK) >> DFLL_MONITOR_DATA_VAL_SHIFT;
+	pre_scaler_rate = dfll_calc_monitored_rate(v, td->ref_rate);
+
+	s = dfll_readl(td, DFLL_FREQ_REQ);
+	s = (s & DFLL_FREQ_REQ_SCALE_MASK) >> DFLL_FREQ_REQ_SCALE_SHIFT;
+	post_scaler_rate = dfll_scale_dvco_rate(s, pre_scaler_rate);
+
+	return post_scaler_rate;
+}
+
+/*
+ * DFLL mode switching
+ */
+
+/**
+ * dfll_set_mode - change the DFLL control mode
+ * @td: DFLL instance
+ * @mode: DFLL control mode (see enum dfll_ctrl_mode)
+ *
+ * Change the DFLL's operating mode between disabled, open-loop mode,
+ * and closed-loop mode, or vice versa.
+ */
+static void dfll_set_mode(struct tegra_dfll *td,
+			  enum dfll_ctrl_mode mode)
+{
+	td->mode = mode;
+	dfll_writel(td, mode - 1, DFLL_CTRL);
+	dfll_wmb(td);
+}
+
+/*
+ * DFLL-to-I2C controller interface
+ */
+
+/**
+ * dfll_i2c_set_output_enabled - enable/disable I2C PMIC voltage requests
+ * @td: DFLL instance
+ * @enable: whether to enable or disable the I2C voltage requests
+ *
+ * Set the master enable control for I2C control value updates. If disabled,
+ * then I2C control messages are inhibited, regardless of the DFLL mode.
+ */
+static int dfll_i2c_set_output_enabled(struct tegra_dfll *td, bool enable)
+{
+	u32 val;
+
+	val = dfll_i2c_readl(td, DFLL_OUTPUT_CFG);
+
+	if (enable)
+		val |= DFLL_OUTPUT_CFG_I2C_ENABLE;
+	else
+		val &= ~DFLL_OUTPUT_CFG_I2C_ENABLE;
+
+	dfll_i2c_writel(td, val, DFLL_OUTPUT_CFG);
+	dfll_i2c_wmb(td);
+
+	return 0;
+}
+
+/**
+ * dfll_load_lut - load the voltage lookup table
+ * @td: struct tegra_dfll *
+ *
+ * Load the voltage-to-PMIC register value lookup table into the DFLL
+ * IP block memory. Look-up tables can be loaded at any time.
+ */
+static void dfll_load_i2c_lut(struct tegra_dfll *td)
+{
+	int i, lut_index;
+	u32 val;
+
+	for (i = 0; i < MAX_DFLL_VOLTAGES; i++) {
+		if (i < td->lut_min)
+			lut_index = td->lut_min;
+		else if (i > td->lut_max)
+			lut_index = td->lut_max;
+		else
+			lut_index = i;
+
+		val = regulator_list_hardware_vsel(td->vdd_reg,
+						     td->i2c_lut[lut_index]);
+		__raw_writel(val, td->lut_base + i * 4);
+	}
+
+	dfll_i2c_wmb(td);
+}
+
+/**
+ * dfll_init_i2c_if - set up the DFLL's DFLL-I2C interface
+ * @td: DFLL instance
+ *
+ * During DFLL driver initialization, program the DFLL-I2C interface
+ * with the PMU slave address, vdd register offset, and transfer mode.
+ * This data is used by the DFLL to automatically construct I2C
+ * voltage-set commands, which are then passed to the DFLL's internal
+ * I2C controller.
+ */
+static void dfll_init_i2c_if(struct tegra_dfll *td)
+{
+	u32 val;
+
+	if (td->i2c_slave_addr > 0x7f) {
+		val = td->i2c_slave_addr << DFLL_I2C_CFG_SLAVE_ADDR_SHIFT_10BIT;
+		val |= DFLL_I2C_CFG_SLAVE_ADDR_10;
+	} else {
+		val = td->i2c_slave_addr << DFLL_I2C_CFG_SLAVE_ADDR_SHIFT_7BIT;
+	}
+	val |= DFLL_I2C_CFG_SIZE_MASK;
+	val |= DFLL_I2C_CFG_ARB_ENABLE;
+	dfll_i2c_writel(td, val, DFLL_I2C_CFG);
+
+	dfll_i2c_writel(td, td->i2c_reg, DFLL_I2C_VDD_REG_ADDR);
+
+	val = DIV_ROUND_UP(td->i2c_clk_rate, td->i2c_fs_rate * 8);
+	BUG_ON(!val || (val > DFLL_I2C_CLK_DIVISOR_MASK));
+	val = (val - 1) << DFLL_I2C_CLK_DIVISOR_FS_SHIFT;
+
+	/* default hs divisor just in case */
+	val |= 1 << DFLL_I2C_CLK_DIVISOR_HS_SHIFT;
+	__raw_writel(val, td->i2c_controller_base + DFLL_I2C_CLK_DIVISOR);
+	dfll_i2c_wmb(td);
+}
+
+/**
+ * dfll_init_out_if - prepare DFLL-to-PMIC interface
+ * @td: DFLL instance
+ *
+ * During DFLL driver initialization or resume from context loss,
+ * disable the I2C command output to the PMIC, set safe voltage and
+ * output limits, and disable and clear limit interrupts.
+ */
+static void dfll_init_out_if(struct tegra_dfll *td)
+{
+	u32 val;
+
+	td->lut_min = 0;
+	td->lut_max = td->i2c_lut_size - 1;
+	td->lut_safe = td->lut_min + 1;
+
+	dfll_i2c_writel(td, 0, DFLL_OUTPUT_CFG);
+	val = (td->lut_safe << DFLL_OUTPUT_CFG_SAFE_SHIFT) |
+		(td->lut_max << DFLL_OUTPUT_CFG_MAX_SHIFT) |
+		(td->lut_min << DFLL_OUTPUT_CFG_MIN_SHIFT);
+	dfll_i2c_writel(td, val, DFLL_OUTPUT_CFG);
+	dfll_i2c_wmb(td);
+
+	dfll_writel(td, 0, DFLL_OUTPUT_FORCE);
+	dfll_i2c_writel(td, 0, DFLL_INTR_EN);
+	dfll_i2c_writel(td, DFLL_INTR_MAX_MASK | DFLL_INTR_MIN_MASK,
+			DFLL_INTR_STS);
+
+	dfll_load_i2c_lut(td);
+	dfll_init_i2c_if(td);
+}
+
+/*
+ * Set/get the DFLL's targeted output clock rate
+ */
+
+/**
+ * find_lut_index_for_rate - determine I2C LUT index for given DFLL rate
+ * @td: DFLL instance
+ * @rate: clock rate
+ *
+ * Determines the index of a I2C LUT entry for a voltage that approximately
+ * produces the given DFLL clock rate. This is used when forcing a value
+ * to the integrator during rate changes. Returns -ENOENT if a suitable
+ * LUT index is not found.
+ */
+static int find_lut_index_for_rate(struct tegra_dfll *td, unsigned long rate)
+{
+	struct dev_pm_opp *opp;
+	int i, uv;
+
+	opp = dev_pm_opp_find_freq_ceil(td->soc->dev, &rate);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+	uv = dev_pm_opp_get_voltage(opp);
+
+	for (i = 0; i < td->i2c_lut_size; i++) {
+		if (regulator_list_voltage(td->vdd_reg, td->i2c_lut[i]) == uv)
+			return i;
+	}
+
+	return -ENOENT;
+}
+
+/**
+ * dfll_calculate_rate_request - calculate DFLL parameters for a given rate
+ * @td: DFLL instance
+ * @req: DFLL-rate-request structure
+ * @rate: the desired DFLL rate
+ *
+ * Populate the DFLL-rate-request record @req fields with the scale_bits
+ * and mult_bits fields, based on the target input rate. Returns 0 upon
+ * success, or -EINVAL if the requested rate in req->rate is too high
+ * or low for the DFLL to generate.
+ */
+static int dfll_calculate_rate_request(struct tegra_dfll *td,
+				       struct dfll_rate_req *req,
+				       unsigned long rate)
+{
+	u32 val;
+
+	/*
+	 * If requested rate is below the minimum DVCO rate, active the scaler.
+	 * In the future the DVCO minimum voltage should be selected based on
+	 * chip temperature and the actual minimum rate should be calibrated
+	 * at runtime.
+	 */
+	req->scale_bits = DFLL_FREQ_REQ_SCALE_MAX - 1;
+	if (rate < td->dvco_rate_min) {
+		int scale;
+
+		scale = DIV_ROUND_CLOSEST(rate / 1000 * DFLL_FREQ_REQ_SCALE_MAX,
+					  td->dvco_rate_min / 1000);
+		if (!scale) {
+			dev_err(td->dev, "%s: Rate %lu is too low\n",
+				__func__, rate);
+			return -EINVAL;
+		}
+		req->scale_bits = scale - 1;
+		rate = td->dvco_rate_min;
+	}
+
+	/* Convert requested rate into frequency request and scale settings */
+	val = DVCO_RATE_TO_MULT(rate, td->ref_rate);
+	if (val > FREQ_MAX) {
+		dev_err(td->dev, "%s: Rate %lu is above dfll range\n",
+			__func__, rate);
+		return -EINVAL;
+	}
+	req->mult_bits = val;
+	req->dvco_target_rate = MULT_TO_DVCO_RATE(req->mult_bits, td->ref_rate);
+	req->rate = dfll_scale_dvco_rate(req->scale_bits,
+					 req->dvco_target_rate);
+	req->lut_index = find_lut_index_for_rate(td, req->dvco_target_rate);
+	if (req->lut_index < 0)
+		return req->lut_index;
+
+	return 0;
+}
+
+/**
+ * dfll_set_frequency_request - start the frequency change operation
+ * @td: DFLL instance
+ * @req: rate request structure
+ *
+ * Tell the DFLL to try to change its output frequency to the
+ * frequency represented by @req. DFLL must be in closed-loop mode.
+ */
+static void dfll_set_frequency_request(struct tegra_dfll *td,
+				       struct dfll_rate_req *req)
+{
+	u32 val = 0;
+	int force_val;
+	int coef = 128; /* FIXME: td->cg_scale? */;
+
+	force_val = (req->lut_index - td->lut_safe) * coef / td->cg;
+	force_val = clamp(force_val, FORCE_MIN, FORCE_MAX);
+
+	val |= req->mult_bits << DFLL_FREQ_REQ_MULT_SHIFT;
+	val |= req->scale_bits << DFLL_FREQ_REQ_SCALE_SHIFT;
+	val |= ((u32)force_val << DFLL_FREQ_REQ_FORCE_SHIFT) &
+		DFLL_FREQ_REQ_FORCE_MASK;
+	val |= DFLL_FREQ_REQ_FREQ_VALID | DFLL_FREQ_REQ_FORCE_ENABLE;
+
+	dfll_writel(td, val, DFLL_FREQ_REQ);
+	dfll_wmb(td);
+}
+
+/**
+ * tegra_dfll_request_rate - set the next rate for the DFLL to tune to
+ * @td: DFLL instance
+ * @rate: clock rate to target
+ *
+ * Convert the requested clock rate @rate into the DFLL control logic
+ * settings. In closed-loop mode, update new settings immediately to
+ * adjust DFLL output rate accordingly. Otherwise, just save them
+ * until the next switch to closed loop. Returns 0 upon success,
+ * -EPERM if the DFLL driver has not yet been initialized, or -EINVAL
+ * if @rate is outside the DFLL's tunable range.
+ */
+static int dfll_request_rate(struct tegra_dfll *td, unsigned long rate)
+{
+	int ret;
+	struct dfll_rate_req req;
+
+	if (td->mode == DFLL_UNINITIALIZED) {
+		dev_err(td->dev, "%s: Cannot set DFLL rate in %s mode\n",
+			__func__, mode_name[td->mode]);
+		return -EPERM;
+	}
+
+	ret = dfll_calculate_rate_request(td, &req, rate);
+	if (ret)
+		return ret;
+
+	td->last_unrounded_rate = rate;
+	td->last_req = req;
+
+	if (td->mode == DFLL_CLOSED_LOOP)
+		dfll_set_frequency_request(td, &td->last_req);
+
+	return 0;
+}
+
+/*
+ * DFLL enable/disable & open-loop <-> closed-loop transitions
+ */
+
+/**
+ * dfll_disable - switch from open-loop mode to disabled mode
+ * @td: DFLL instance
+ *
+ * Switch from OPEN_LOOP state to DISABLED state. Returns 0 upon success
+ * or -EPERM if the DFLL is not currently in open-loop mode.
+ */
+static int dfll_disable(struct tegra_dfll *td)
+{
+	if (td->mode != DFLL_OPEN_LOOP) {
+		dev_err(td->dev, "cannot disable DFLL in %s mode\n",
+			mode_name[td->mode]);
+		return -EINVAL;
+	}
+
+	dfll_set_mode(td, DFLL_DISABLED);
+	pm_runtime_put_sync(td->dev);
+
+	return 0;
+}
+
+/**
+ * dfll_enable - switch a disabled DFLL to open-loop mode
+ * @td: DFLL instance
+ *
+ * Switch from DISABLED state to OPEN_LOOP state. Returns 0 upon success
+ * or -EPERM if the DFLL is not currently disabled.
+ */
+static int dfll_enable(struct tegra_dfll *td)
+{
+	if (td->mode != DFLL_DISABLED) {
+		dev_err(td->dev, "cannot enable DFLL in %s mode\n",
+			mode_name[td->mode]);
+		return -EPERM;
+	}
+
+	pm_runtime_get_sync(td->dev);
+	dfll_set_mode(td, DFLL_OPEN_LOOP);
+
+	return 0;
+}
+
+/**
+ * dfll_set_open_loop_config - prepare to switch to open-loop mode
+ * @td: DFLL instance
+ *
+ * Prepare to switch the DFLL to open-loop mode. This switches the
+ * DFLL to the low-voltage tuning range, ensures that I2C output
+ * forcing is disabled, and disables the output clock rate scaler.
+ * The DFLL's low-voltage tuning range parameters must be
+ * characterized to keep the downstream device stable at any DVCO
+ * input voltage. No return value.
+ */
+static void dfll_set_open_loop_config(struct tegra_dfll *td)
+{
+	u32 val;
+
+	/* always tune low (safe) in open loop */
+	if (td->tune_range != DFLL_TUNE_LOW)
+		dfll_tune_low(td);
+
+	val = dfll_readl(td, DFLL_FREQ_REQ);
+	val |= DFLL_FREQ_REQ_SCALE_MASK;
+	val &= ~DFLL_FREQ_REQ_FORCE_ENABLE;
+	dfll_writel(td, val, DFLL_FREQ_REQ);
+	dfll_wmb(td);
+}
+
+/**
+ * tegra_dfll_lock - switch from open-loop to closed-loop mode
+ * @td: DFLL instance
+ *
+ * Switch from OPEN_LOOP state to CLOSED_LOOP state. Returns 0 upon success,
+ * -EINVAL if the DFLL's target rate hasn't been set yet, or -EPERM if the
+ * DFLL is not currently in open-loop mode.
+ */
+static int dfll_lock(struct tegra_dfll *td)
+{
+	struct dfll_rate_req *req = &td->last_req;
+
+	switch (td->mode) {
+	case DFLL_CLOSED_LOOP:
+		return 0;
+
+	case DFLL_OPEN_LOOP:
+		if (req->rate == 0) {
+			dev_err(td->dev, "%s: Cannot lock DFLL at rate 0\n",
+				__func__);
+			return -EINVAL;
+		}
+
+		dfll_i2c_set_output_enabled(td, true);
+		dfll_set_mode(td, DFLL_CLOSED_LOOP);
+		dfll_set_frequency_request(td, req);
+		return 0;
+
+	default:
+		BUG_ON(td->mode > DFLL_CLOSED_LOOP);
+		dev_err(td->dev, "%s: Cannot lock DFLL in %s mode\n",
+			__func__, mode_name[td->mode]);
+		return -EPERM;
+	}
+}
+
+/**
+ * tegra_dfll_unlock - switch from closed-loop to open-loop mode
+ * @td: DFLL instance
+ *
+ * Switch from CLOSED_LOOP state to OPEN_LOOP state. Returns 0 upon success,
+ * or -EPERM if the DFLL is not currently in open-loop mode.
+ */
+static int dfll_unlock(struct tegra_dfll *td)
+{
+	switch (td->mode) {
+	case DFLL_CLOSED_LOOP:
+		dfll_set_open_loop_config(td);
+		dfll_set_mode(td, DFLL_OPEN_LOOP);
+		dfll_i2c_set_output_enabled(td, false);
+		return 0;
+
+	case DFLL_OPEN_LOOP:
+		return 0;
+
+	default:
+		BUG_ON(td->mode > DFLL_CLOSED_LOOP);
+		dev_err(td->dev, "%s: Cannot unlock DFLL in %s mode\n",
+			__func__, mode_name[td->mode]);
+		return -EPERM;
+	}
+}
+
+/*
+ * Clock framework integration
+ *
+ * When the DFLL is being controlled by the CCF, always enter closed loop
+ * mode when the clk is enabled. This requires that a DFLL rate request
+ * has been set beforehand, which implies that a clk_set_rate() call is
+ * always required before a clk_enable().
+ */
+
+static int dfll_clk_is_enabled(struct clk_hw *hw)
+{
+	struct tegra_dfll *td = clk_hw_to_dfll(hw);
+
+	return dfll_is_running(td);
+}
+
+static int dfll_clk_enable(struct clk_hw *hw)
+{
+	struct tegra_dfll *td = clk_hw_to_dfll(hw);
+	int ret;
+
+	ret = dfll_enable(td);
+	if (ret)
+		return ret;
+
+	ret = dfll_lock(td);
+	if (ret)
+		dfll_disable(td);
+
+	return ret;
+}
+
+static void dfll_clk_disable(struct clk_hw *hw)
+{
+	struct tegra_dfll *td = clk_hw_to_dfll(hw);
+	int ret;
+
+	ret = dfll_unlock(td);
+	if (!ret)
+		dfll_disable(td);
+}
+
+static unsigned long dfll_clk_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct tegra_dfll *td = clk_hw_to_dfll(hw);
+
+	return td->last_unrounded_rate;
+}
+
+static long dfll_clk_round_rate(struct clk_hw *hw,
+				unsigned long rate,
+				unsigned long *parent_rate)
+{
+	struct tegra_dfll *td = clk_hw_to_dfll(hw);
+	struct dfll_rate_req req;
+	int ret;
+
+	ret = dfll_calculate_rate_request(td, &req, rate);
+	if (ret)
+		return ret;
+
+	/*
+	 * Don't return the rounded rate, since it doesn't really matter as
+	 * the output rate will be voltage controlled anyway, and cpufreq
+	 * freaks out if any rounding happens.
+	 */
+	return rate;
+}
+
+static int dfll_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate)
+{
+	struct tegra_dfll *td = clk_hw_to_dfll(hw);
+
+	return dfll_request_rate(td, rate);
+}
+
+static const struct clk_ops dfll_clk_ops = {
+	.is_enabled	= dfll_clk_is_enabled,
+	.enable		= dfll_clk_enable,
+	.disable	= dfll_clk_disable,
+	.recalc_rate	= dfll_clk_recalc_rate,
+	.round_rate	= dfll_clk_round_rate,
+	.set_rate	= dfll_clk_set_rate,
+};
+
+static struct clk_init_data dfll_clk_init_data = {
+	.flags		= CLK_IS_ROOT,
+	.ops		= &dfll_clk_ops,
+	.num_parents	= 0,
+};
+
+/**
+ * dfll_register_clk - register the DFLL output clock with the clock framework
+ * @td: DFLL instance
+ *
+ * Register the DFLL's output clock with the Linux clock framework and register
+ * the DFLL driver as an OF clock provider. Returns 0 upon success or -EINVAL
+ * or -ENOMEM upon failure.
+ */
+static int dfll_register_clk(struct tegra_dfll *td)
+{
+	int ret;
+
+	dfll_clk_init_data.name = td->output_clock_name;
+	td->dfll_clk_hw.init = &dfll_clk_init_data;
+
+	td->dfll_clk = clk_register(td->dev, &td->dfll_clk_hw);
+	if (IS_ERR(td->dfll_clk)) {
+		dev_err(td->dev, "DFLL clock registration error\n");
+		return -EINVAL;
+	}
+
+	ret = of_clk_add_provider(td->dev->of_node, of_clk_src_simple_get,
+				  td->dfll_clk);
+	if (ret) {
+		dev_err(td->dev, "of_clk_add_provider() failed\n");
+
+		clk_unregister(td->dfll_clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * dfll_unregister_clk - unregister the DFLL output clock
+ * @td: DFLL instance
+ *
+ * Unregister the DFLL's output clock from the Linux clock framework
+ * and from clkdev. No return value.
+ */
+static void dfll_unregister_clk(struct tegra_dfll *td)
+{
+	of_clk_del_provider(td->dev->of_node);
+	clk_unregister(td->dfll_clk);
+	td->dfll_clk = NULL;
+}
+
+/*
+ * Debugfs interface
+ */
+
+#ifdef CONFIG_DEBUG_FS
+
+static int attr_enable_get(void *data, u64 *val)
+{
+	struct tegra_dfll *td = data;
+
+	*val = dfll_is_running(td);
+
+	return 0;
+}
+static int attr_enable_set(void *data, u64 val)
+{
+	struct tegra_dfll *td = data;
+
+	return val ? dfll_enable(td) : dfll_disable(td);
+}
+DEFINE_SIMPLE_ATTRIBUTE(enable_fops, attr_enable_get, attr_enable_set,
+			"%llu\n");
+
+static int attr_lock_get(void *data, u64 *val)
+{
+	struct tegra_dfll *td = data;
+
+	*val = (td->mode == DFLL_CLOSED_LOOP);
+
+	return 0;
+}
+static int attr_lock_set(void *data, u64 val)
+{
+	struct tegra_dfll *td = data;
+
+	return val ? dfll_lock(td) :  dfll_unlock(td);
+}
+DEFINE_SIMPLE_ATTRIBUTE(lock_fops, attr_lock_get, attr_lock_set,
+			"%llu\n");
+
+static int attr_rate_get(void *data, u64 *val)
+{
+	struct tegra_dfll *td = data;
+
+	*val = dfll_read_monitor_rate(td);
+
+	return 0;
+}
+
+static int attr_rate_set(void *data, u64 val)
+{
+	struct tegra_dfll *td = data;
+
+	return dfll_request_rate(td, val);
+}
+DEFINE_SIMPLE_ATTRIBUTE(rate_fops, attr_rate_get, attr_rate_set, "%llu\n");
+
+static int attr_registers_show(struct seq_file *s, void *data)
+{
+	u32 val, offs;
+	struct tegra_dfll *td = s->private;
+
+	seq_puts(s, "CONTROL REGISTERS:\n");
+	for (offs = 0; offs <= DFLL_MONITOR_DATA; offs += 4) {
+		if (offs == DFLL_OUTPUT_CFG)
+			val = dfll_i2c_readl(td, offs);
+		else
+			val = dfll_readl(td, offs);
+		seq_printf(s, "[0x%02x] = 0x%08x\n", offs, val);
+	}
+
+	seq_puts(s, "\nI2C and INTR REGISTERS:\n");
+	for (offs = DFLL_I2C_CFG; offs <= DFLL_I2C_STS; offs += 4)
+		seq_printf(s, "[0x%02x] = 0x%08x\n", offs,
+			   dfll_i2c_readl(td, offs));
+	for (offs = DFLL_INTR_STS; offs <= DFLL_INTR_EN; offs += 4)
+		seq_printf(s, "[0x%02x] = 0x%08x\n", offs,
+			   dfll_i2c_readl(td, offs));
+
+	seq_puts(s, "\nINTEGRATED I2C CONTROLLER REGISTERS:\n");
+	offs = DFLL_I2C_CLK_DIVISOR;
+	seq_printf(s, "[0x%02x] = 0x%08x\n", offs,
+		   __raw_readl(td->i2c_controller_base + offs));
+
+	seq_puts(s, "\nLUT:\n");
+	for (offs = 0; offs <  4 * MAX_DFLL_VOLTAGES; offs += 4)
+		seq_printf(s, "[0x%02x] = 0x%08x\n", offs,
+			   __raw_readl(td->lut_base + offs));
+
+	return 0;
+}
+
+static int attr_registers_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, attr_registers_show, inode->i_private);
+}
+
+static const struct file_operations attr_registers_fops = {
+	.open		= attr_registers_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int dfll_debug_init(struct tegra_dfll *td)
+{
+	int ret;
+
+	if (!td || (td->mode == DFLL_UNINITIALIZED))
+		return 0;
+
+	td->debugfs_dir = debugfs_create_dir("tegra_dfll_fcpu", NULL);
+	if (!td->debugfs_dir)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+
+	if (!debugfs_create_file("enable", S_IRUGO | S_IWUSR,
+				 td->debugfs_dir, td, &enable_fops))
+		goto err_out;
+
+	if (!debugfs_create_file("lock", S_IRUGO,
+				 td->debugfs_dir, td, &lock_fops))
+		goto err_out;
+
+	if (!debugfs_create_file("rate", S_IRUGO,
+				 td->debugfs_dir, td, &rate_fops))
+		goto err_out;
+
+	if (!debugfs_create_file("registers", S_IRUGO,
+				 td->debugfs_dir, td, &attr_registers_fops))
+		goto err_out;
+
+	return 0;
+
+err_out:
+	debugfs_remove_recursive(td->debugfs_dir);
+	return ret;
+}
+
+#endif /* CONFIG_DEBUG_FS */
+
+/*
+ * DFLL initialization
+ */
+
+/**
+ * dfll_set_default_params - program non-output related DFLL parameters
+ * @td: DFLL instance
+ *
+ * During DFLL driver initialization or resume from context loss,
+ * program parameters for the closed loop integrator, DVCO tuning,
+ * voltage droop control and monitor control.
+ */
+static void dfll_set_default_params(struct tegra_dfll *td)
+{
+	u32 val;
+
+	val = DIV_ROUND_UP(td->ref_rate, td->sample_rate * 32);
+	BUG_ON(val > DFLL_CONFIG_DIV_MASK);
+	dfll_writel(td, val, DFLL_CONFIG);
+
+	val = (td->force_mode << DFLL_PARAMS_FORCE_MODE_SHIFT) |
+		(td->cf << DFLL_PARAMS_CF_PARAM_SHIFT) |
+		(td->ci << DFLL_PARAMS_CI_PARAM_SHIFT) |
+		(td->cg << DFLL_PARAMS_CG_PARAM_SHIFT) |
+		(td->cg_scale ? DFLL_PARAMS_CG_SCALE : 0);
+	dfll_writel(td, val, DFLL_PARAMS);
+
+	dfll_tune_low(td);
+	dfll_writel(td, td->droop_ctrl, DFLL_DROOP_CTRL);
+	dfll_writel(td, DFLL_MONITOR_CTRL_FREQ, DFLL_MONITOR_CTRL);
+}
+
+/**
+ * dfll_init_clks - clk_get() the DFLL source clocks
+ * @td: DFLL instance
+ *
+ * Call clk_get() on the DFLL source clocks and save the pointers for later
+ * use. Returns 0 upon success or error (see devm_clk_get) if one or more
+ * of the clocks couldn't be looked up.
+ */
+static int dfll_init_clks(struct tegra_dfll *td)
+{
+	td->ref_clk = devm_clk_get(td->dev, "ref");
+	if (IS_ERR(td->ref_clk)) {
+		dev_err(td->dev, "missing ref clock\n");
+		return PTR_ERR(td->ref_clk);
+	}
+
+	td->soc_clk = devm_clk_get(td->dev, "soc");
+	if (IS_ERR(td->soc_clk)) {
+		dev_err(td->dev, "missing soc clock\n");
+		return PTR_ERR(td->soc_clk);
+	}
+
+	td->i2c_clk = devm_clk_get(td->dev, "i2c");
+	if (IS_ERR(td->i2c_clk)) {
+		dev_err(td->dev, "missing i2c clock\n");
+		return PTR_ERR(td->i2c_clk);
+	}
+	td->i2c_clk_rate = clk_get_rate(td->i2c_clk);
+
+	return 0;
+}
+
+/**
+ * dfll_init - Prepare the DFLL IP block for use
+ * @td: DFLL instance
+ *
+ * Do everything necessary to prepare the DFLL IP block for use. The
+ * DFLL will be left in DISABLED state. Called by dfll_probe().
+ * Returns 0 upon success, or passes along the error from whatever
+ * function returned it.
+ */
+static int dfll_init(struct tegra_dfll *td)
+{
+	int ret;
+
+	td->ref_rate = clk_get_rate(td->ref_clk);
+	if (td->ref_rate != REF_CLOCK_RATE) {
+		dev_err(td->dev, "unexpected ref clk rate %lu, expecting %lu",
+			td->ref_rate, REF_CLOCK_RATE);
+		return -EINVAL;
+	}
+
+	reset_control_deassert(td->dvco_rst);
+
+	ret = clk_prepare(td->ref_clk);
+	if (ret) {
+		dev_err(td->dev, "failed to prepare ref_clk\n");
+		return ret;
+	}
+
+	ret = clk_prepare(td->soc_clk);
+	if (ret) {
+		dev_err(td->dev, "failed to prepare soc_clk\n");
+		goto di_err1;
+	}
+
+	ret = clk_prepare(td->i2c_clk);
+	if (ret) {
+		dev_err(td->dev, "failed to prepare i2c_clk\n");
+		goto di_err2;
+	}
+
+	td->last_unrounded_rate = 0;
+
+	pm_runtime_enable(td->dev);
+	pm_runtime_get_sync(td->dev);
+
+	dfll_set_mode(td, DFLL_DISABLED);
+	dfll_set_default_params(td);
+
+	if (td->soc->init_clock_trimmers)
+		td->soc->init_clock_trimmers();
+
+	dfll_set_open_loop_config(td);
+
+	dfll_init_out_if(td);
+
+	pm_runtime_put_sync(td->dev);
+
+	return 0;
+
+di_err2:
+	clk_unprepare(td->soc_clk);
+di_err1:
+	clk_unprepare(td->ref_clk);
+
+	reset_control_assert(td->dvco_rst);
+
+	return ret;
+}
+
+/*
+ * DT data fetch
+ */
+
+/*
+ * Find a PMIC voltage register-to-voltage mapping for the given voltage.
+ * An exact voltage match is required.
+ */
+static int find_vdd_map_entry_exact(struct tegra_dfll *td, int uV)
+{
+	int i, n_voltages, reg_uV;
+
+	n_voltages = regulator_count_voltages(td->vdd_reg);
+	for (i = 0; i < n_voltages; i++) {
+		reg_uV = regulator_list_voltage(td->vdd_reg, i);
+		if (reg_uV < 0)
+			break;
+
+		if (uV == reg_uV)
+			return i;
+	}
+
+	dev_err(td->dev, "no voltage map entry for %d uV\n", uV);
+	return -EINVAL;
+}
+
+/*
+ * Find a PMIC voltage register-to-voltage mapping for the given voltage,
+ * rounding up to the closest supported voltage.
+ * */
+static int find_vdd_map_entry_min(struct tegra_dfll *td, int uV)
+{
+	int i, n_voltages, reg_uV;
+
+	n_voltages = regulator_count_voltages(td->vdd_reg);
+	for (i = 0; i < n_voltages; i++) {
+		reg_uV = regulator_list_voltage(td->vdd_reg, i);
+		if (reg_uV < 0)
+			break;
+
+		if (uV <= reg_uV)
+			return i;
+	}
+
+	dev_err(td->dev, "no voltage map entry rounding to %d uV\n", uV);
+	return -EINVAL;
+}
+
+/**
+ * dfll_build_i2c_lut - build the I2C voltage register lookup table
+ * @td: DFLL instance
+ *
+ * The DFLL hardware has 33 bytes of look-up table RAM that must be filled with
+ * PMIC voltage register values that span the entire DFLL operating range.
+ * This function builds the look-up table based on the OPP table provided by
+ * the soc-specific platform driver (td->soc->opp_dev) and the PMIC
+ * register-to-voltage mapping queried from the regulator framework.
+ *
+ * On success, fills in td->i2c_lut and returns 0, or -err on failure.
+ */
+static int dfll_build_i2c_lut(struct tegra_dfll *td)
+{
+	int ret = -EINVAL;
+	int j, v, v_max, v_opp;
+	int selector;
+	unsigned long rate;
+	struct dev_pm_opp *opp;
+	int lut;
+
+	rcu_read_lock();
+
+	rate = ULONG_MAX;
+	opp = dev_pm_opp_find_freq_floor(td->soc->dev, &rate);
+	if (IS_ERR(opp)) {
+		dev_err(td->dev, "couldn't get vmax opp, empty opp table?\n");
+		goto out;
+	}
+	v_max = dev_pm_opp_get_voltage(opp);
+
+	v = td->soc->min_millivolts * 1000;
+	lut = find_vdd_map_entry_exact(td, v);
+	if (lut < 0)
+		goto out;
+	td->i2c_lut[0] = lut;
+
+	for (j = 1, rate = 0; ; rate++) {
+		opp = dev_pm_opp_find_freq_ceil(td->soc->dev, &rate);
+		if (IS_ERR(opp))
+			break;
+		v_opp = dev_pm_opp_get_voltage(opp);
+
+		if (v_opp <= td->soc->min_millivolts * 1000)
+			td->dvco_rate_min = dev_pm_opp_get_freq(opp);
+
+		for (;;) {
+			v += max(1, (v_max - v) / (MAX_DFLL_VOLTAGES - j));
+			if (v >= v_opp)
+				break;
+
+			selector = find_vdd_map_entry_min(td, v);
+			if (selector < 0)
+				goto out;
+			if (selector != td->i2c_lut[j - 1])
+				td->i2c_lut[j++] = selector;
+		}
+
+		v = (j == MAX_DFLL_VOLTAGES - 1) ? v_max : v_opp;
+		selector = find_vdd_map_entry_exact(td, v);
+		if (selector < 0)
+			goto out;
+		if (selector != td->i2c_lut[j - 1])
+			td->i2c_lut[j++] = selector;
+
+		if (v >= v_max)
+			break;
+	}
+	td->i2c_lut_size = j;
+
+	if (!td->dvco_rate_min)
+		dev_err(td->dev, "no opp above DFLL minimum voltage %d mV\n",
+			td->soc->min_millivolts);
+	else
+		ret = 0;
+
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * read_dt_param - helper function for reading required parameters from the DT
+ * @td: DFLL instance
+ * @param: DT property name
+ * @dest: output pointer for the value read
+ *
+ * Read a required numeric parameter from the DFLL device node, or complain
+ * if the property doesn't exist. Returns a boolean indicating success for
+ * easy chaining of multiple calls to this function.
+ */
+static bool read_dt_param(struct tegra_dfll *td, const char *param, u32 *dest)
+{
+	int err = of_property_read_u32(td->dev->of_node, param, dest);
+
+	if (err < 0) {
+		dev_err(td->dev, "failed to read DT parameter %s: %d\n",
+			param, err);
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * dfll_fetch_i2c_params - query PMIC I2C params from DT & regulator subsystem
+ * @td: DFLL instance
+ *
+ * Read all the parameters required for operation in I2C mode. The parameters
+ * can originate from the device tree or the regulator subsystem.
+ * Returns 0 on success or -err on failure.
+ */
+static int dfll_fetch_i2c_params(struct tegra_dfll *td)
+{
+	struct regmap *regmap;
+	struct device *i2c_dev;
+	struct i2c_client *i2c_client;
+	int vsel_reg, vsel_mask;
+	int ret;
+
+	if (!read_dt_param(td, "nvidia,i2c-fs-rate", &td->i2c_fs_rate))
+		return -EINVAL;
+
+	regmap = regulator_get_regmap(td->vdd_reg);
+	i2c_dev = regmap_get_device(regmap);
+	i2c_client = to_i2c_client(i2c_dev);
+
+	td->i2c_slave_addr = i2c_client->addr;
+
+	ret = regulator_get_hardware_vsel_register(td->vdd_reg,
+						   &vsel_reg,
+						   &vsel_mask);
+	if (ret < 0) {
+		dev_err(td->dev,
+			"regulator unsuitable for DFLL I2C operation\n");
+		return -EINVAL;
+	}
+	td->i2c_reg = vsel_reg;
+
+	ret = dfll_build_i2c_lut(td);
+	if (ret) {
+		dev_err(td->dev, "couldn't build I2C LUT\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * dfll_fetch_common_params - read DFLL parameters from the device tree
+ * @td: DFLL instance
+ *
+ * Read all the DT parameters that are common to both I2C and PWM operation.
+ * Returns 0 on success or -EINVAL on any failure.
+ */
+static int dfll_fetch_common_params(struct tegra_dfll *td)
+{
+	bool ok = true;
+
+	ok &= read_dt_param(td, "nvidia,droop-ctrl", &td->droop_ctrl);
+	ok &= read_dt_param(td, "nvidia,sample-rate", &td->sample_rate);
+	ok &= read_dt_param(td, "nvidia,force-mode", &td->force_mode);
+	ok &= read_dt_param(td, "nvidia,cf", &td->cf);
+	ok &= read_dt_param(td, "nvidia,ci", &td->ci);
+	ok &= read_dt_param(td, "nvidia,cg", &td->cg);
+	td->cg_scale = of_property_read_bool(td->dev->of_node,
+					     "nvidia,cg-scale");
+
+	if (of_property_read_string(td->dev->of_node, "clock-output-names",
+				    &td->output_clock_name)) {
+		dev_err(td->dev, "missing clock-output-names property\n");
+		ok = false;
+	}
+
+	return ok ? 0 : -EINVAL;
+}
+
+/*
+ * API exported to per-SoC platform drivers
+ */
+
+/**
+ * tegra_dfll_register - probe a Tegra DFLL device
+ * @pdev: DFLL platform_device *
+ * @soc: Per-SoC integration and characterization data for this DFLL instance
+ *
+ * Probe and initialize a DFLL device instance. Intended to be called
+ * by a SoC-specific shim driver that passes in per-SoC integration
+ * and configuration data via @soc. Returns 0 on success or -err on failure.
+ */
+int tegra_dfll_register(struct platform_device *pdev,
+			struct tegra_dfll_soc_data *soc)
+{
+	struct resource *mem;
+	struct tegra_dfll *td;
+	int ret;
+
+	if (!soc) {
+		dev_err(&pdev->dev, "no tegra_dfll_soc_data provided\n");
+		return -EINVAL;
+	}
+
+	td = devm_kzalloc(&pdev->dev, sizeof(*td), GFP_KERNEL);
+	if (!td)
+		return -ENOMEM;
+	td->dev = &pdev->dev;
+	platform_set_drvdata(pdev, td);
+
+	td->soc = soc;
+
+	td->vdd_reg = devm_regulator_get(td->dev, "vdd-cpu");
+	if (IS_ERR(td->vdd_reg)) {
+		dev_err(td->dev, "couldn't get vdd_cpu regulator\n");
+		return PTR_ERR(td->vdd_reg);
+	}
+
+	td->dvco_rst = devm_reset_control_get(td->dev, "dvco");
+	if (IS_ERR(td->dvco_rst)) {
+		dev_err(td->dev, "couldn't get dvco reset\n");
+		return PTR_ERR(td->dvco_rst);
+	}
+
+	ret = dfll_fetch_common_params(td);
+	if (ret) {
+		dev_err(td->dev, "couldn't parse device tree parameters\n");
+		return ret;
+	}
+
+	ret = dfll_fetch_i2c_params(td);
+	if (ret)
+		return ret;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem) {
+		dev_err(td->dev, "no control register resource\n");
+		return -ENODEV;
+	}
+
+	td->base = devm_ioremap(td->dev, mem->start, resource_size(mem));
+	if (!td->base) {
+		dev_err(td->dev, "couldn't ioremap DFLL control registers\n");
+		return -ENODEV;
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!mem) {
+		dev_err(td->dev, "no i2c_base resource\n");
+		return -ENODEV;
+	}
+
+	td->i2c_base = devm_ioremap(td->dev, mem->start, resource_size(mem));
+	if (!td->i2c_base) {
+		dev_err(td->dev, "couldn't ioremap i2c_base resource\n");
+		return -ENODEV;
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	if (!mem) {
+		dev_err(td->dev, "no i2c_controller_base resource\n");
+		return -ENODEV;
+	}
+
+	td->i2c_controller_base = devm_ioremap(td->dev, mem->start,
+					       resource_size(mem));
+	if (!td->i2c_controller_base) {
+		dev_err(td->dev,
+			"couldn't ioremap i2c_controller_base resource\n");
+		return -ENODEV;
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 3);
+	if (!mem) {
+		dev_err(td->dev, "no lut_base resource\n");
+		return -ENODEV;
+	}
+
+	td->lut_base = devm_ioremap(td->dev, mem->start, resource_size(mem));
+	if (!td->lut_base) {
+		dev_err(td->dev,
+			"couldn't ioremap lut_base resource\n");
+		return -ENODEV;
+	}
+
+	ret = dfll_init_clks(td);
+	if (ret) {
+		dev_err(&pdev->dev, "DFLL clock init error\n");
+		return ret;
+	}
+
+	/* Enable the clocks and set the device up */
+	ret = dfll_init(td);
+	if (ret)
+		return ret;
+
+	ret = dfll_register_clk(td);
+	if (ret) {
+		dev_err(&pdev->dev, "DFLL clk registration failed\n");
+		return ret;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	dfll_debug_init(td);
+#endif
+
+	return 0;
+}
+EXPORT_SYMBOL(tegra_dfll_register);
+
+/**
+ * tegra_dfll_unregister - release all of the DFLL driver resources for a device
+ * @pdev: DFLL platform_device *
+ *
+ * Unbind this driver from the DFLL hardware device represented by
+ * @pdev. The DFLL must be disabled for this to succeed. Returns 0
+ * upon success or -EBUSY if the DFLL is still active.
+ */
+int tegra_dfll_unregister(struct platform_device *pdev)
+{
+	struct tegra_dfll *td = platform_get_drvdata(pdev);
+
+	/* Try to prevent removal while the DFLL is active */
+	if (td->mode != DFLL_DISABLED) {
+		dev_err(&pdev->dev,
+			"must disable DFLL before removing driver\n");
+		return -EBUSY;
+	}
+
+	debugfs_remove_recursive(td->debugfs_dir);
+
+	dfll_unregister_clk(td);
+	pm_runtime_disable(&pdev->dev);
+
+	clk_unprepare(td->ref_clk);
+	clk_unprepare(td->soc_clk);
+	clk_unprepare(td->i2c_clk);
+
+	reset_control_assert(td->dvco_rst);
+
+	return 0;
+}
+EXPORT_SYMBOL(tegra_dfll_unregister);
diff --git a/drivers/clk/tegra/clk-dfll.h b/drivers/clk/tegra/clk-dfll.h
new file mode 100644
index 000000000000..2e4c0772a5dc
--- /dev/null
+++ b/drivers/clk/tegra/clk-dfll.h
@@ -0,0 +1,54 @@
+/*
+ * clk-dfll.h - prototypes and macros for the Tegra DFLL clocksource driver
+ * Copyright (C) 2013 NVIDIA Corporation.  All rights reserved.
+ *
+ * Aleksandr Frid <afrid@nvidia.com>
+ * Paul Walmsley <pwalmsley@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __DRIVERS_CLK_TEGRA_CLK_DFLL_H
+#define __DRIVERS_CLK_TEGRA_CLK_DFLL_H
+
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/types.h>
+
+/**
+ * struct tegra_dfll_soc_data - SoC-specific hooks/integration for the DFLL driver
+ * @opp_dev: struct device * that holds the OPP table for the DFLL
+ * @min_millivolts: minimum voltage (in mV) that the DFLL can operate
+ * @tune0_low: DFLL tuning register 0 (low voltage range)
+ * @tune0_high: DFLL tuning register 0 (high voltage range)
+ * @tune1: DFLL tuning register 1
+ * @assert_dvco_reset: fn ptr to place the DVCO in reset
+ * @deassert_dvco_reset: fn ptr to release the DVCO reset
+ * @set_clock_trimmers_high: fn ptr to tune clock trimmers for high voltage
+ * @set_clock_trimmers_low: fn ptr to tune clock trimmers for low voltage
+ */
+struct tegra_dfll_soc_data {
+	struct device *dev;
+	unsigned int min_millivolts;
+	u32 tune0_low;
+	u32 tune0_high;
+	u32 tune1;
+	void (*init_clock_trimmers)(void);
+	void (*set_clock_trimmers_high)(void);
+	void (*set_clock_trimmers_low)(void);
+};
+
+int tegra_dfll_register(struct platform_device *pdev,
+			struct tegra_dfll_soc_data *soc);
+int tegra_dfll_unregister(struct platform_device *pdev);
+int tegra_dfll_runtime_suspend(struct device *dev);
+int tegra_dfll_runtime_resume(struct device *dev);
+
+#endif /* __DRIVERS_CLK_TEGRA_CLK_DFLL_H */
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 59a5714dfe18..48c83efda4cf 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -19,7 +19,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/clk-provider.h>
-#include <linux/clk.h>
 
 #include "clk.h"
 
diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c
index 7649685c86bc..138a94b99b5b 100644
--- a/drivers/clk/tegra/clk-emc.c
+++ b/drivers/clk/tegra/clk-emc.c
@@ -103,7 +103,7 @@ static unsigned long emc_recalc_rate(struct clk_hw *hw,
 	 * CCF wrongly assumes that the parent won't change during set_rate,
 	 * so get the parent rate explicitly.
 	 */
-	parent_rate = __clk_get_rate(__clk_get_parent(hw->clk));
+	parent_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 
 	val = readl(tegra->clk_regs + CLK_SOURCE_EMC);
 	div = val & CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR_MASK;
@@ -116,11 +116,7 @@ static unsigned long emc_recalc_rate(struct clk_hw *hw,
  * safer since things have EMC rate floors. Also don't touch parent_rate
  * since we don't want the CCF to play with our parent clocks.
  */
-static long emc_determine_rate(struct clk_hw *hw, unsigned long rate,
-			       unsigned long min_rate,
-			       unsigned long max_rate,
-			       unsigned long *best_parent_rate,
-			       struct clk_hw **best_parent_hw)
+static int emc_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
 {
 	struct tegra_clk_emc *tegra;
 	u8 ram_code = tegra_read_ram_code();
@@ -135,22 +131,28 @@ static long emc_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 		timing = tegra->timings + i;
 
-		if (timing->rate > max_rate) {
+		if (timing->rate > req->max_rate) {
 			i = min(i, 1);
-			return tegra->timings[i - 1].rate;
+			req->rate = tegra->timings[i - 1].rate;
+			return 0;
 		}
 
-		if (timing->rate < min_rate)
+		if (timing->rate < req->min_rate)
 			continue;
 
-		if (timing->rate >= rate)
-			return timing->rate;
+		if (timing->rate >= req->rate) {
+			req->rate = timing->rate;
+			return 0;
+		}
 	}
 
-	if (timing)
-		return timing->rate;
+	if (timing) {
+		req->rate = timing->rate;
+		return 0;
+	}
 
-	return __clk_get_rate(hw->clk);
+	req->rate = clk_hw_get_rate(hw);
+	return 0;
 }
 
 static u8 emc_get_parent(struct clk_hw *hw)
@@ -312,7 +314,7 @@ static int emc_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	tegra = container_of(hw, struct tegra_clk_emc, hw);
 
-	if (__clk_get_rate(hw->clk) == rate)
+	if (clk_hw_get_rate(hw) == rate)
 		return 0;
 
 	/*
@@ -525,8 +527,8 @@ struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np,
 	if (IS_ERR(clk))
 		return clk;
 
-	tegra->prev_parent = clk_get_parent_by_index(
-		tegra->hw.clk, emc_get_parent(&tegra->hw));
+	tegra->prev_parent = clk_hw_get_parent_by_index(
+		&tegra->hw, emc_get_parent(&tegra->hw))->clk;
 	tegra->changing_timing = false;
 
 	/* Allow debugging tools to see the EMC clock */
diff --git a/drivers/clk/tegra/clk-periph-gate.c b/drivers/clk/tegra/clk-periph-gate.c
index 0aa8830ae7cc..d28d6e95020f 100644
--- a/drivers/clk/tegra/clk-periph-gate.c
+++ b/drivers/clk/tegra/clk-periph-gate.c
@@ -14,7 +14,6 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/slab.h>
 #include <linux/io.h>
diff --git a/drivers/clk/tegra/clk-periph.c b/drivers/clk/tegra/clk-periph.c
index d84ae49d0e05..ec5b6113b012 100644
--- a/drivers/clk/tegra/clk-periph.c
+++ b/drivers/clk/tegra/clk-periph.c
@@ -14,7 +14,6 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/export.h>
 #include <linux/slab.h>
diff --git a/drivers/clk/tegra/clk-pll-out.c b/drivers/clk/tegra/clk-pll-out.c
index 3598987a451d..257cae0c1488 100644
--- a/drivers/clk/tegra/clk-pll-out.c
+++ b/drivers/clk/tegra/clk-pll-out.c
@@ -20,7 +20,6 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/clk-provider.h>
-#include <linux/clk.h>
 
 #include "clk.h"
 
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index 05c6d08a6695..d6d4ecb88e94 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -18,8 +18,8 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/err.h>
-#include <linux/clk-provider.h>
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 
 #include "clk.h"
 
@@ -264,7 +264,7 @@ static int clk_pll_wait_for_lock(struct tegra_clk_pll *pll)
 	}
 
 	pr_err("%s: Timed out waiting for pll %s lock\n", __func__,
-	       __clk_get_name(pll->hw.clk));
+	       clk_hw_get_name(&pll->hw));
 
 	return -1;
 }
@@ -595,7 +595,7 @@ static int clk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (pll->params->flags & TEGRA_PLL_FIXED) {
 		if (rate != pll->params->fixed_rate) {
 			pr_err("%s: Can not change %s fixed rate %lu to %lu\n",
-				__func__, __clk_get_name(hw->clk),
+				__func__, clk_hw_get_name(hw),
 				pll->params->fixed_rate, rate);
 			return -EINVAL;
 		}
@@ -605,7 +605,7 @@ static int clk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (_get_table_rate(hw, &cfg, rate, parent_rate) &&
 	    _calc_rate(hw, &cfg, rate, parent_rate)) {
 		pr_err("%s: Failed to set %s rate %lu\n", __func__,
-		       __clk_get_name(hw->clk), rate);
+		       clk_hw_get_name(hw), rate);
 		WARN_ON(1);
 		return -EINVAL;
 	}
@@ -634,7 +634,7 @@ static long clk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	/* PLLM is used for memory; we do not change rate */
 	if (pll->params->flags & TEGRA_PLLM)
-		return __clk_get_rate(hw->clk);
+		return clk_hw_get_rate(hw);
 
 	if (_get_table_rate(hw, &cfg, rate, *prate) &&
 	    _calc_rate(hw, &cfg, rate, *prate))
@@ -663,7 +663,7 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hw,
 		if (_get_table_rate(hw, &sel, pll->params->fixed_rate,
 					parent_rate)) {
 			pr_err("Clock %s has unknown fixed frequency\n",
-			       __clk_get_name(hw->clk));
+			       clk_hw_get_name(hw));
 			BUG();
 		}
 		return pll->params->fixed_rate;
@@ -1577,7 +1577,7 @@ struct clk *tegra_clk_register_pllxc(const char *name, const char *parent_name,
 	if (!pll_params->pdiv_tohw)
 		return ERR_PTR(-EINVAL);
 
-	parent_rate = __clk_get_rate(parent);
+	parent_rate = clk_get_rate(parent);
 
 	pll_params->vco_min = _clip_vco_min(pll_params->vco_min, parent_rate);
 
@@ -1674,7 +1674,7 @@ struct clk *tegra_clk_register_pllm(const char *name, const char *parent_name,
 		return ERR_PTR(-EINVAL);
 	}
 
-	parent_rate = __clk_get_rate(parent);
+	parent_rate = clk_get_rate(parent);
 
 	pll_params->vco_min = _clip_vco_min(pll_params->vco_min, parent_rate);
 
@@ -1715,7 +1715,7 @@ struct clk *tegra_clk_register_pllc(const char *name, const char *parent_name,
 		return ERR_PTR(-EINVAL);
 	}
 
-	parent_rate = __clk_get_rate(parent);
+	parent_rate = clk_get_rate(parent);
 
 	pll_params->vco_min = _clip_vco_min(pll_params->vco_min, parent_rate);
 
@@ -1848,7 +1848,7 @@ struct clk *tegra_clk_register_pllss(const char *name, const char *parent_name,
 	val &= ~PLLSS_REF_SRC_SEL_MASK;
 	pll_writel_base(val, pll);
 
-	parent_rate = __clk_get_rate(parent);
+	parent_rate = clk_get_rate(parent);
 
 	pll_params->vco_min = _clip_vco_min(pll_params->vco_min, parent_rate);
 
diff --git a/drivers/clk/tegra/clk-super.c b/drivers/clk/tegra/clk-super.c
index 2fd924d38606..131d1b5085e2 100644
--- a/drivers/clk/tegra/clk-super.c
+++ b/drivers/clk/tegra/clk-super.c
@@ -20,7 +20,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/clk-provider.h>
-#include <linux/clk.h>
 
 #include "clk.h"
 
diff --git a/drivers/clk/tegra/clk-tegra-audio.c b/drivers/clk/tegra/clk-tegra-audio.c
index 5c38aab2c5b8..11e3ad7ad7a3 100644
--- a/drivers/clk/tegra/clk-tegra-audio.c
+++ b/drivers/clk/tegra/clk-tegra-audio.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/tegra/clk-tegra-fixed.c b/drivers/clk/tegra/clk-tegra-fixed.c
index 605676d368eb..da0b5941c89f 100644
--- a/drivers/clk/tegra/clk-tegra-fixed.c
+++ b/drivers/clk/tegra/clk-tegra-fixed.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 46af9244ba74..cb6ab830941d 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
diff --git a/drivers/clk/tegra/clk-tegra-pmc.c b/drivers/clk/tegra/clk-tegra-pmc.c
index 08b21c1ee867..91377abfefa1 100644
--- a/drivers/clk/tegra/clk-tegra-pmc.c
+++ b/drivers/clk/tegra/clk-tegra-pmc.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c
index feb3201c85ce..5b1d723932c5 100644
--- a/drivers/clk/tegra/clk-tegra-super-gen4.c
+++ b/drivers/clk/tegra/clk-tegra-super-gen4.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -44,7 +43,9 @@ static const char *sclk_parents[] = { "clk_m", "pll_c_out1", "pll_p_out4",
 
 static const char *cclk_g_parents[] = { "clk_m", "pll_c", "clk_32k", "pll_m",
 					"pll_p", "pll_p_out4", "unused",
-					"unused", "pll_x" };
+					"unused", "pll_x", "unused", "unused",
+					"unused", "unused", "unused", "unused",
+					"dfllCPU_out" };
 
 static const char *cclk_lp_parents[] = { "clk_m", "pll_c", "clk_32k", "pll_m",
 					 "pll_p", "pll_p_out4", "unused",
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index 8237d16b4075..db5871519bf5 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -15,9 +15,7 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/clkdev.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/delay.h>
diff --git a/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c b/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c
new file mode 100644
index 000000000000..61253330c12b
--- /dev/null
+++ b/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c
@@ -0,0 +1,166 @@
+/*
+ * Tegra124 DFLL FCPU clock source driver
+ *
+ * Copyright (C) 2012-2014 NVIDIA Corporation.  All rights reserved.
+ *
+ * Aleksandr Frid <afrid@nvidia.com>
+ * Paul Walmsley <pwalmsley@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <soc/tegra/fuse.h>
+
+#include "clk.h"
+#include "clk-dfll.h"
+#include "cvb.h"
+
+/* Maximum CPU frequency, indexed by CPU speedo id */
+static const unsigned long cpu_max_freq_table[] = {
+	[0] = 2014500000UL,
+	[1] = 2320500000UL,
+	[2] = 2116500000UL,
+	[3] = 2524500000UL,
+};
+
+static const struct cvb_table tegra124_cpu_cvb_tables[] = {
+	{
+		.speedo_id = -1,
+		.process_id = -1,
+		.min_millivolts = 900,
+		.max_millivolts = 1260,
+		.alignment = {
+			.step_uv = 10000, /* 10mV */
+		},
+		.speedo_scale = 100,
+		.voltage_scale = 1000,
+		.cvb_table = {
+			{204000000UL,   {1112619, -29295, 402} },
+			{306000000UL,	{1150460, -30585, 402} },
+			{408000000UL,	{1190122, -31865, 402} },
+			{510000000UL,	{1231606, -33155, 402} },
+			{612000000UL,	{1274912, -34435, 402} },
+			{714000000UL,	{1320040, -35725, 402} },
+			{816000000UL,	{1366990, -37005, 402} },
+			{918000000UL,	{1415762, -38295, 402} },
+			{1020000000UL,	{1466355, -39575, 402} },
+			{1122000000UL,	{1518771, -40865, 402} },
+			{1224000000UL,	{1573009, -42145, 402} },
+			{1326000000UL,	{1629068, -43435, 402} },
+			{1428000000UL,	{1686950, -44715, 402} },
+			{1530000000UL,	{1746653, -46005, 402} },
+			{1632000000UL,	{1808179, -47285, 402} },
+			{1734000000UL,	{1871526, -48575, 402} },
+			{1836000000UL,	{1936696, -49855, 402} },
+			{1938000000UL,	{2003687, -51145, 402} },
+			{2014500000UL,	{2054787, -52095, 402} },
+			{2116500000UL,	{2124957, -53385, 402} },
+			{2218500000UL,	{2196950, -54665, 402} },
+			{2320500000UL,	{2270765, -55955, 402} },
+			{2422500000UL,	{2346401, -57235, 402} },
+			{2524500000UL,	{2437299, -58535, 402} },
+			{0,		{      0,      0,   0} },
+		},
+		.cpu_dfll_data = {
+			.tune0_low = 0x005020ff,
+			.tune0_high = 0x005040ff,
+			.tune1 = 0x00000060,
+		}
+	},
+};
+
+static int tegra124_dfll_fcpu_probe(struct platform_device *pdev)
+{
+	int process_id, speedo_id, speedo_value;
+	struct tegra_dfll_soc_data *soc;
+	const struct cvb_table *cvb;
+
+	process_id = tegra_sku_info.cpu_process_id;
+	speedo_id = tegra_sku_info.cpu_speedo_id;
+	speedo_value = tegra_sku_info.cpu_speedo_value;
+
+	if (speedo_id >= ARRAY_SIZE(cpu_max_freq_table)) {
+		dev_err(&pdev->dev, "unknown max CPU freq for speedo_id=%d\n",
+			speedo_id);
+		return -ENODEV;
+	}
+
+	soc = devm_kzalloc(&pdev->dev, sizeof(*soc), GFP_KERNEL);
+	if (!soc)
+		return -ENOMEM;
+
+	soc->dev = get_cpu_device(0);
+	if (!soc->dev) {
+		dev_err(&pdev->dev, "no CPU0 device\n");
+		return -ENODEV;
+	}
+
+	cvb = tegra_cvb_build_opp_table(tegra124_cpu_cvb_tables,
+					ARRAY_SIZE(tegra124_cpu_cvb_tables),
+					process_id, speedo_id, speedo_value,
+					cpu_max_freq_table[speedo_id],
+					soc->dev);
+	if (IS_ERR(cvb)) {
+		dev_err(&pdev->dev, "couldn't build OPP table: %ld\n",
+			PTR_ERR(cvb));
+		return PTR_ERR(cvb);
+	}
+
+	soc->min_millivolts = cvb->min_millivolts;
+	soc->tune0_low = cvb->cpu_dfll_data.tune0_low;
+	soc->tune0_high = cvb->cpu_dfll_data.tune0_high;
+	soc->tune1 = cvb->cpu_dfll_data.tune1;
+
+	return tegra_dfll_register(pdev, soc);
+}
+
+static const struct of_device_id tegra124_dfll_fcpu_of_match[] = {
+	{ .compatible = "nvidia,tegra124-dfll", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tegra124_dfll_fcpu_of_match);
+
+static const struct dev_pm_ops tegra124_dfll_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_dfll_runtime_suspend,
+			   tegra_dfll_runtime_resume, NULL)
+};
+
+static struct platform_driver tegra124_dfll_fcpu_driver = {
+	.probe = tegra124_dfll_fcpu_probe,
+	.remove = tegra_dfll_unregister,
+	.driver = {
+		.name = "tegra124-dfll",
+		.of_match_table = tegra124_dfll_fcpu_of_match,
+		.pm = &tegra124_dfll_pm_ops,
+	},
+};
+
+static int __init tegra124_dfll_fcpu_init(void)
+{
+	return platform_driver_register(&tegra124_dfll_fcpu_driver);
+}
+module_init(tegra124_dfll_fcpu_init);
+
+static void __exit tegra124_dfll_fcpu_exit(void)
+{
+	platform_driver_unregister(&tegra124_dfll_fcpu_driver);
+}
+module_exit(tegra124_dfll_fcpu_exit);
+
+MODULE_DESCRIPTION("Tegra124 DFLL clock source driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Aleksandr Frid <afrid@nvidia.com>");
+MODULE_AUTHOR("Paul Walmsley <pwalmsley@nvidia.com>");
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index e8cca3eac007..824d75883d2b 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
@@ -24,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/clk/tegra.h>
 #include <dt-bindings/clock/tegra124-car.h>
+#include <dt-bindings/reset/tegra124-car.h>
 
 #include "clk.h"
 #include "clk-id.h"
@@ -39,6 +39,9 @@
 #define CLK_SOURCE_CSITE 0x1d4
 #define CLK_SOURCE_EMC 0x19c
 
+#define RST_DFLL_DVCO			0x2f4
+#define DVFS_DFLL_RESET_SHIFT		0
+
 #define PLLC_BASE 0x80
 #define PLLC_OUT 0x84
 #define PLLC_MISC2 0x88
@@ -94,6 +97,8 @@
 #define PMC_PLLM_WB0_OVERRIDE 0x1dc
 #define PMC_PLLM_WB0_OVERRIDE_2 0x2b0
 
+#define CCLKG_BURST_POLICY 0x368
+
 #define UTMIP_PLL_CFG2 0x488
 #define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xffff) << 6)
 #define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
@@ -126,6 +131,8 @@
 #ifdef CONFIG_PM_SLEEP
 static struct cpu_clk_suspend_context {
 	u32 clk_csite_src;
+	u32 cclkg_burst;
+	u32 cclkg_divider;
 } tegra124_cpu_clk_sctx;
 #endif
 
@@ -1319,12 +1326,22 @@ static void tegra124_cpu_clock_suspend(void)
 	tegra124_cpu_clk_sctx.clk_csite_src =
 				readl(clk_base + CLK_SOURCE_CSITE);
 	writel(3 << 30, clk_base + CLK_SOURCE_CSITE);
+
+	tegra124_cpu_clk_sctx.cclkg_burst =
+				readl(clk_base + CCLKG_BURST_POLICY);
+	tegra124_cpu_clk_sctx.cclkg_divider =
+				readl(clk_base + CCLKG_BURST_POLICY + 4);
 }
 
 static void tegra124_cpu_clock_resume(void)
 {
 	writel(tegra124_cpu_clk_sctx.clk_csite_src,
 				clk_base + CLK_SOURCE_CSITE);
+
+	writel(tegra124_cpu_clk_sctx.cclkg_burst,
+					clk_base + CCLKG_BURST_POLICY);
+	writel(tegra124_cpu_clk_sctx.cclkg_divider,
+					clk_base + CCLKG_BURST_POLICY + 4);
 }
 #endif
 
@@ -1415,6 +1432,68 @@ static void __init tegra124_clock_apply_init_table(void)
 }
 
 /**
+ * tegra124_car_barrier - wait for pending writes to the CAR to complete
+ *
+ * Wait for any outstanding writes to the CAR MMIO space from this CPU
+ * to complete before continuing execution.  No return value.
+ */
+static void tegra124_car_barrier(void)
+{
+	readl_relaxed(clk_base + RST_DFLL_DVCO);
+}
+
+/**
+ * tegra124_clock_assert_dfll_dvco_reset - assert the DFLL's DVCO reset
+ *
+ * Assert the reset line of the DFLL's DVCO.  No return value.
+ */
+static void tegra124_clock_assert_dfll_dvco_reset(void)
+{
+	u32 v;
+
+	v = readl_relaxed(clk_base + RST_DFLL_DVCO);
+	v |= (1 << DVFS_DFLL_RESET_SHIFT);
+	writel_relaxed(v, clk_base + RST_DFLL_DVCO);
+	tegra124_car_barrier();
+}
+
+/**
+ * tegra124_clock_deassert_dfll_dvco_reset - deassert the DFLL's DVCO reset
+ *
+ * Deassert the reset line of the DFLL's DVCO, allowing the DVCO to
+ * operate.  No return value.
+ */
+static void tegra124_clock_deassert_dfll_dvco_reset(void)
+{
+	u32 v;
+
+	v = readl_relaxed(clk_base + RST_DFLL_DVCO);
+	v &= ~(1 << DVFS_DFLL_RESET_SHIFT);
+	writel_relaxed(v, clk_base + RST_DFLL_DVCO);
+	tegra124_car_barrier();
+}
+
+static int tegra124_reset_assert(unsigned long id)
+{
+	if (id == TEGRA124_RST_DFLL_DVCO)
+		tegra124_clock_assert_dfll_dvco_reset();
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int tegra124_reset_deassert(unsigned long id)
+{
+	if (id == TEGRA124_RST_DFLL_DVCO)
+		tegra124_clock_deassert_dfll_dvco_reset();
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
  * tegra132_clock_apply_init_table - initialize clocks on Tegra132 SoCs
  *
  * Program an initial clock rate and enable or disable clocks needed
@@ -1499,6 +1578,8 @@ static void __init tegra124_132_clock_init_post(struct device_node *np)
 {
 	tegra_super_clk_gen4_init(clk_base, pmc_base, tegra124_clks,
 				  &pll_x_params);
+	tegra_init_special_resets(1, tegra124_reset_assert,
+				  tegra124_reset_deassert);
 	tegra_add_of_provider(np);
 
 	clks[TEGRA124_CLK_EMC] = tegra_clk_register_emc(clk_base, np,
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index 41272dcc9e22..bf004f0e4f65 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/io.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index 0af3e834dd24..fad561a5896b 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -16,7 +16,6 @@
 
 #include <linux/io.h>
 #include <linux/delay.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c
index 41cd87c67be6..2a3a4fe803d6 100644
--- a/drivers/clk/tegra/clk.c
+++ b/drivers/clk/tegra/clk.c
@@ -14,6 +14,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/clkdev.h>
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
@@ -49,7 +50,6 @@
 #define RST_DEVICES_L			0x004
 #define RST_DEVICES_H			0x008
 #define RST_DEVICES_U			0x00C
-#define RST_DFLL_DVCO			0x2F4
 #define RST_DEVICES_V			0x358
 #define RST_DEVICES_W			0x35C
 #define RST_DEVICES_X			0x28C
@@ -79,6 +79,11 @@ static struct clk **clks;
 static int clk_num;
 static struct clk_onecell_data clk_data;
 
+/* Handlers for SoC-specific reset lines */
+static int (*special_reset_assert)(unsigned long);
+static int (*special_reset_deassert)(unsigned long);
+static unsigned int num_special_reset;
+
 static struct tegra_clk_periph_regs periph_regs[] = {
 	[0] = {
 		.enb_reg = CLK_OUT_ENB_L,
@@ -152,19 +157,29 @@ static int tegra_clk_rst_assert(struct reset_controller_dev *rcdev,
 	 */
 	tegra_read_chipid();
 
-	writel_relaxed(BIT(id % 32),
-			clk_base + periph_regs[id / 32].rst_set_reg);
+	if (id < periph_banks * 32) {
+		writel_relaxed(BIT(id % 32),
+			       clk_base + periph_regs[id / 32].rst_set_reg);
+		return 0;
+	} else if (id < periph_banks * 32 + num_special_reset) {
+		return special_reset_assert(id);
+	}
 
-	return 0;
+	return -EINVAL;
 }
 
 static int tegra_clk_rst_deassert(struct reset_controller_dev *rcdev,
 		unsigned long id)
 {
-	writel_relaxed(BIT(id % 32),
-			clk_base + periph_regs[id / 32].rst_clr_reg);
+	if (id < periph_banks * 32) {
+		writel_relaxed(BIT(id % 32),
+			       clk_base + periph_regs[id / 32].rst_clr_reg);
+		return 0;
+	} else if (id < periph_banks * 32 + num_special_reset) {
+		return special_reset_deassert(id);
+	}
 
-	return 0;
+	return -EINVAL;
 }
 
 struct tegra_clk_periph_regs *get_reg_bank(int clkid)
@@ -286,10 +301,19 @@ void __init tegra_add_of_provider(struct device_node *np)
 	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 
 	rst_ctlr.of_node = np;
-	rst_ctlr.nr_resets = periph_banks * 32;
+	rst_ctlr.nr_resets = periph_banks * 32 + num_special_reset;
 	reset_controller_register(&rst_ctlr);
 }
 
+void __init tegra_init_special_resets(unsigned int num,
+				      int (*assert)(unsigned long),
+				      int (*deassert)(unsigned long))
+{
+	num_special_reset = num;
+	special_reset_assert = assert;
+	special_reset_deassert = deassert;
+}
+
 void __init tegra_register_devclks(struct tegra_devclk *dev_clks, int num)
 {
 	int i;
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index 75ddc8ff8bd4..0621887e06f7 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -591,6 +591,9 @@ struct tegra_devclk {
 	char		*con_id;
 };
 
+void tegra_init_special_resets(unsigned int num, int (*assert)(unsigned long),
+			       int (*deassert)(unsigned long));
+
 void tegra_init_from_table(struct tegra_clk_init_table *tbl,
 		struct clk *clks[], int clk_max);
 
diff --git a/drivers/clk/tegra/cvb.c b/drivers/clk/tegra/cvb.c
new file mode 100644
index 000000000000..0204e0861134
--- /dev/null
+++ b/drivers/clk/tegra/cvb.c
@@ -0,0 +1,140 @@
+/*
+ * Utility functions for parsing Tegra CVB voltage tables
+ *
+ * Copyright (C) 2012-2014 NVIDIA Corporation.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/pm_opp.h>
+
+#include "cvb.h"
+
+/* cvb_mv = ((c2 * speedo / s_scale + c1) * speedo / s_scale + c0) */
+static inline int get_cvb_voltage(int speedo, int s_scale,
+				  const struct cvb_coefficients *cvb)
+{
+	int mv;
+
+	/* apply only speedo scale: output mv = cvb_mv * v_scale */
+	mv = DIV_ROUND_CLOSEST(cvb->c2 * speedo, s_scale);
+	mv = DIV_ROUND_CLOSEST((mv + cvb->c1) * speedo, s_scale) + cvb->c0;
+	return mv;
+}
+
+static int round_cvb_voltage(int mv, int v_scale,
+			     const struct rail_alignment *align)
+{
+	/* combined: apply voltage scale and round to cvb alignment step */
+	int uv;
+	int step = (align->step_uv ? : 1000) * v_scale;
+	int offset = align->offset_uv * v_scale;
+
+	uv = max(mv * 1000, offset) - offset;
+	uv = DIV_ROUND_UP(uv, step) * align->step_uv + align->offset_uv;
+	return uv / 1000;
+}
+
+enum {
+	DOWN,
+	UP
+};
+
+static int round_voltage(int mv, const struct rail_alignment *align, int up)
+{
+	if (align->step_uv) {
+		int uv;
+
+		uv = max(mv * 1000, align->offset_uv) - align->offset_uv;
+		uv = (uv + (up ? align->step_uv - 1 : 0)) / align->step_uv;
+		return (uv * align->step_uv + align->offset_uv) / 1000;
+	}
+	return mv;
+}
+
+static int build_opp_table(const struct cvb_table *d,
+			   int speedo_value,
+			   unsigned long max_freq,
+			   struct device *opp_dev)
+{
+	int i, ret, dfll_mv, min_mv, max_mv;
+	const struct cvb_table_freq_entry *table = NULL;
+	const struct rail_alignment *align = &d->alignment;
+
+	min_mv = round_voltage(d->min_millivolts, align, UP);
+	max_mv = round_voltage(d->max_millivolts, align, DOWN);
+
+	for (i = 0; i < MAX_DVFS_FREQS; i++) {
+		table = &d->cvb_table[i];
+		if (!table->freq || (table->freq > max_freq))
+			break;
+
+		/*
+		 * FIXME after clk_round_rate/clk_determine_rate prototypes
+		 * have been updated
+		 */
+		if (table->freq & (1<<31))
+			continue;
+
+		dfll_mv = get_cvb_voltage(
+			speedo_value, d->speedo_scale, &table->coefficients);
+		dfll_mv = round_cvb_voltage(dfll_mv, d->voltage_scale, align);
+		dfll_mv = clamp(dfll_mv, min_mv, max_mv);
+
+		ret = dev_pm_opp_add(opp_dev, table->freq, dfll_mv * 1000);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * tegra_cvb_build_opp_table - build OPP table from Tegra CVB tables
+ * @cvb_tables: array of CVB tables
+ * @sz: size of the previously mentioned array
+ * @process_id: process id of the HW module
+ * @speedo_id: speedo id of the HW module
+ * @speedo_value: speedo value of the HW module
+ * @max_rate: highest safe clock rate
+ * @opp_dev: the struct device * for which the OPP table is built
+ *
+ * On Tegra, a CVB table encodes the relationship between operating voltage
+ * and safe maximal frequency for a given module (e.g. GPU or CPU). This
+ * function calculates the optimal voltage-frequency operating points
+ * for the given arguments and exports them via the OPP library for the
+ * given @opp_dev. Returns a pointer to the struct cvb_table that matched
+ * or an ERR_PTR on failure.
+ */
+const struct cvb_table *tegra_cvb_build_opp_table(
+		const struct cvb_table *cvb_tables,
+		size_t sz, int process_id,
+		int speedo_id, int speedo_value,
+		unsigned long max_rate,
+		struct device *opp_dev)
+{
+	int i, ret;
+
+	for (i = 0; i < sz; i++) {
+		const struct cvb_table *d = &cvb_tables[i];
+
+		if (d->speedo_id != -1 && d->speedo_id != speedo_id)
+			continue;
+		if (d->process_id != -1 && d->process_id != process_id)
+			continue;
+
+		ret = build_opp_table(d, speedo_value, max_rate, opp_dev);
+		return ret ? ERR_PTR(ret) : d;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
diff --git a/drivers/clk/tegra/cvb.h b/drivers/clk/tegra/cvb.h
new file mode 100644
index 000000000000..f62cdc4f4234
--- /dev/null
+++ b/drivers/clk/tegra/cvb.h
@@ -0,0 +1,67 @@
+/*
+ * Utility functions for parsing Tegra CVB voltage tables
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __DRIVERS_CLK_TEGRA_CVB_H
+#define __DRIVERS_CLK_TEGRA_CVB_H
+
+#include <linux/types.h>
+
+struct device;
+
+#define MAX_DVFS_FREQS	40
+
+struct rail_alignment {
+	int offset_uv;
+	int step_uv;
+};
+
+struct cvb_coefficients {
+	int c0;
+	int c1;
+	int c2;
+};
+
+struct cvb_table_freq_entry {
+	unsigned long freq;
+	struct cvb_coefficients coefficients;
+};
+
+struct cvb_cpu_dfll_data {
+	u32 tune0_low;
+	u32 tune0_high;
+	u32 tune1;
+};
+
+struct cvb_table {
+	int speedo_id;
+	int process_id;
+
+	int min_millivolts;
+	int max_millivolts;
+	struct rail_alignment alignment;
+
+	int speedo_scale;
+	int voltage_scale;
+	struct cvb_table_freq_entry cvb_table[MAX_DVFS_FREQS];
+	struct cvb_cpu_dfll_data cpu_dfll_data;
+};
+
+const struct cvb_table *tegra_cvb_build_opp_table(
+		const struct cvb_table *cvb_tables,
+		size_t sz, int process_id,
+		int speedo_id, int speedo_value,
+		unsigned long max_rate,
+		struct device *opp_dev);
+
+#endif
diff --git a/drivers/clk/ti/Makefile b/drivers/clk/ti/Makefile
index 105ffd0f5e79..d4ac96087ccd 100644
--- a/drivers/clk/ti/Makefile
+++ b/drivers/clk/ti/Makefile
@@ -1,16 +1,19 @@
 obj-y					+= clk.o autoidle.o clockdomain.o
 clk-common				= dpll.o composite.o divider.o gate.o \
-					  fixed-factor.o mux.o apll.o
-obj-$(CONFIG_SOC_AM33XX)		+= $(clk-common) clk-33xx.o
-obj-$(CONFIG_SOC_TI81XX)		+= $(clk-common) fapll.o clk-816x.o
+					  fixed-factor.o mux.o apll.o \
+					  clkt_dpll.o clkt_iclk.o clkt_dflt.o
+obj-$(CONFIG_SOC_AM33XX)		+= $(clk-common) clk-33xx.o dpll3xxx.o
+obj-$(CONFIG_SOC_TI81XX)		+= $(clk-common) fapll.o clk-814x.o clk-816x.o
 obj-$(CONFIG_ARCH_OMAP2)		+= $(clk-common) interface.o clk-2xxx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= $(clk-common) interface.o \
-					   clk-3xxx.o
-obj-$(CONFIG_ARCH_OMAP4)		+= $(clk-common) clk-44xx.o
-obj-$(CONFIG_SOC_OMAP5)			+= $(clk-common) clk-54xx.o
+					   clk-3xxx.o dpll3xxx.o
+obj-$(CONFIG_ARCH_OMAP4)		+= $(clk-common) clk-44xx.o \
+					   dpll3xxx.o dpll44xx.o
+obj-$(CONFIG_SOC_OMAP5)			+= $(clk-common) clk-54xx.o \
+					   dpll3xxx.o dpll44xx.o
 obj-$(CONFIG_SOC_DRA7XX)		+= $(clk-common) clk-7xx.o \
-					   clk-dra7-atl.o
-obj-$(CONFIG_SOC_AM43XX)		+= $(clk-common) clk-43xx.o
+					   clk-dra7-atl.o dpll3xxx.o dpll44xx.o
+obj-$(CONFIG_SOC_AM43XX)		+= $(clk-common) dpll3xxx.o clk-43xx.o
 
 ifdef CONFIG_ATAGS
 obj-$(CONFIG_ARCH_OMAP3)                += clk-3xxx-legacy.o
diff --git a/drivers/clk/ti/apll.c b/drivers/clk/ti/apll.c
index 49baf3831546..f3eab6e79027 100644
--- a/drivers/clk/ti/apll.c
+++ b/drivers/clk/ti/apll.c
@@ -15,6 +15,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -27,6 +28,8 @@
 #include <linux/clk/ti.h>
 #include <linux/delay.h>
 
+#include "clock.h"
+
 #define APLL_FORCE_LOCK 0x1
 #define APLL_AUTO_IDLE	0x2
 #define MAX_APLL_WAIT_TRIES		1000000
@@ -47,7 +50,7 @@ static int dra7_apll_enable(struct clk_hw *hw)
 	if (!ad)
 		return -EINVAL;
 
-	clk_name = __clk_get_name(clk->hw.clk);
+	clk_name = clk_hw_get_name(&clk->hw);
 
 	state <<= __ffs(ad->idlest_mask);
 
@@ -170,7 +173,6 @@ static void __init of_dra7_apll_setup(struct device_node *node)
 	struct clk_hw_omap *clk_hw = NULL;
 	struct clk_init_data *init = NULL;
 	const char **parent_names = NULL;
-	int i;
 
 	ad = kzalloc(sizeof(*ad), GFP_KERNEL);
 	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
@@ -195,8 +197,7 @@ static void __init of_dra7_apll_setup(struct device_node *node)
 	if (!parent_names)
 		goto cleanup;
 
-	for (i = 0; i < init->num_parents; i++)
-		parent_names[i] = of_clk_get_parent_name(node, i);
+	of_clk_parent_fill(node, parent_names, init->num_parents);
 
 	init->parent_names = parent_names;
 
@@ -272,7 +273,7 @@ static int omap2_apll_enable(struct clk_hw *hw)
 
 	if (i == MAX_APLL_WAIT_TRIES) {
 		pr_warn("%s failed to transition to locked\n",
-			__clk_get_name(clk->hw.clk));
+			clk_hw_get_name(&clk->hw));
 		return -EBUSY;
 	}
 
diff --git a/drivers/clk/ti/autoidle.c b/drivers/clk/ti/autoidle.c
index e75c64c9e81c..345af43465f0 100644
--- a/drivers/clk/ti/autoidle.c
+++ b/drivers/clk/ti/autoidle.c
@@ -22,6 +22,8 @@
 #include <linux/of_address.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 struct clk_ti_autoidle {
 	void __iomem		*reg;
 	u8			shift;
@@ -33,8 +35,41 @@ struct clk_ti_autoidle {
 #define AUTOIDLE_LOW		0x1
 
 static LIST_HEAD(autoidle_clks);
+static LIST_HEAD(clk_hw_omap_clocks);
+
+/**
+ * omap2_clk_deny_idle - disable autoidle on an OMAP clock
+ * @clk: struct clk * to disable autoidle for
+ *
+ * Disable autoidle on an OMAP clock.
+ */
+int omap2_clk_deny_idle(struct clk *clk)
+{
+	struct clk_hw_omap *c;
 
-static void ti_allow_autoidle(struct clk_ti_autoidle *clk)
+	c = to_clk_hw_omap(__clk_get_hw(clk));
+	if (c->ops && c->ops->deny_idle)
+		c->ops->deny_idle(c);
+	return 0;
+}
+
+/**
+ * omap2_clk_allow_idle - enable autoidle on an OMAP clock
+ * @clk: struct clk * to enable autoidle for
+ *
+ * Enable autoidle on an OMAP clock.
+ */
+int omap2_clk_allow_idle(struct clk *clk)
+{
+	struct clk_hw_omap *c;
+
+	c = to_clk_hw_omap(__clk_get_hw(clk));
+	if (c->ops && c->ops->allow_idle)
+		c->ops->allow_idle(c);
+	return 0;
+}
+
+static void _allow_autoidle(struct clk_ti_autoidle *clk)
 {
 	u32 val;
 
@@ -48,7 +83,7 @@ static void ti_allow_autoidle(struct clk_ti_autoidle *clk)
 	ti_clk_ll_ops->clk_writel(val, clk->reg);
 }
 
-static void ti_deny_autoidle(struct clk_ti_autoidle *clk)
+static void _deny_autoidle(struct clk_ti_autoidle *clk)
 {
 	u32 val;
 
@@ -63,31 +98,31 @@ static void ti_deny_autoidle(struct clk_ti_autoidle *clk)
 }
 
 /**
- * of_ti_clk_allow_autoidle_all - enable autoidle for all clocks
+ * _clk_generic_allow_autoidle_all - enable autoidle for all clocks
  *
  * Enables hardware autoidle for all registered DT clocks, which have
  * the feature.
  */
-void of_ti_clk_allow_autoidle_all(void)
+static void _clk_generic_allow_autoidle_all(void)
 {
 	struct clk_ti_autoidle *c;
 
 	list_for_each_entry(c, &autoidle_clks, node)
-		ti_allow_autoidle(c);
+		_allow_autoidle(c);
 }
 
 /**
- * of_ti_clk_deny_autoidle_all - disable autoidle for all clocks
+ * _clk_generic_deny_autoidle_all - disable autoidle for all clocks
  *
  * Disables hardware autoidle for all registered DT clocks, which have
  * the feature.
  */
-void of_ti_clk_deny_autoidle_all(void)
+static void _clk_generic_deny_autoidle_all(void)
 {
 	struct clk_ti_autoidle *c;
 
 	list_for_each_entry(c, &autoidle_clks, node)
-		ti_deny_autoidle(c);
+		_deny_autoidle(c);
 }
 
 /**
@@ -131,3 +166,67 @@ int __init of_ti_clk_autoidle_setup(struct device_node *node)
 
 	return 0;
 }
+
+/**
+ * omap2_init_clk_hw_omap_clocks - initialize an OMAP clock
+ * @hw: struct clk_hw * to initialize
+ *
+ * Add an OMAP clock @clk to the internal list of OMAP clocks.  Used
+ * temporarily for autoidle handling, until this support can be
+ * integrated into the common clock framework code in some way.  No
+ * return value.
+ */
+void omap2_init_clk_hw_omap_clocks(struct clk_hw *hw)
+{
+	struct clk_hw_omap *c;
+
+	if (clk_hw_get_flags(hw) & CLK_IS_BASIC)
+		return;
+
+	c = to_clk_hw_omap(hw);
+	list_add(&c->node, &clk_hw_omap_clocks);
+}
+
+/**
+ * omap2_clk_enable_autoidle_all - enable autoidle on all OMAP clocks that
+ * support it
+ *
+ * Enable clock autoidle on all OMAP clocks that have allow_idle
+ * function pointers associated with them.  This function is intended
+ * to be temporary until support for this is added to the common clock
+ * code.  Returns 0.
+ */
+int omap2_clk_enable_autoidle_all(void)
+{
+	struct clk_hw_omap *c;
+
+	list_for_each_entry(c, &clk_hw_omap_clocks, node)
+		if (c->ops && c->ops->allow_idle)
+			c->ops->allow_idle(c);
+
+	_clk_generic_allow_autoidle_all();
+
+	return 0;
+}
+
+/**
+ * omap2_clk_disable_autoidle_all - disable autoidle on all OMAP clocks that
+ * support it
+ *
+ * Disable clock autoidle on all OMAP clocks that have allow_idle
+ * function pointers associated with them.  This function is intended
+ * to be temporary until support for this is added to the common clock
+ * code.  Returns 0.
+ */
+int omap2_clk_disable_autoidle_all(void)
+{
+	struct clk_hw_omap *c;
+
+	list_for_each_entry(c, &clk_hw_omap_clocks, node)
+		if (c->ops && c->ops->deny_idle)
+			c->ops->deny_idle(c);
+
+	_clk_generic_deny_autoidle_all();
+
+	return 0;
+}
diff --git a/drivers/clk/ti/clk-2xxx.c b/drivers/clk/ti/clk-2xxx.c
index c808ab3d2bb2..657c4fe07a95 100644
--- a/drivers/clk/ti/clk-2xxx.c
+++ b/drivers/clk/ti/clk-2xxx.c
@@ -16,9 +16,11 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/clk-provider.h>
+#include <linux/clk.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 static struct ti_dt_clk omap2xxx_clks[] = {
 	DT_CLK(NULL, "func_32k_ck", "func_32k_ck"),
 	DT_CLK(NULL, "secure_32k_ck", "secure_32k_ck"),
diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c
index 028b33783d38..ef2ec64fe547 100644
--- a/drivers/clk/ti/clk-33xx.c
+++ b/drivers/clk/ti/clk-33xx.c
@@ -16,9 +16,12 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 static struct ti_dt_clk am33xx_clks[] = {
 	DT_CLK(NULL, "clk_32768_ck", "clk_32768_ck"),
 	DT_CLK(NULL, "clk_rc32k_ck", "clk_rc32k_ck"),
diff --git a/drivers/clk/ti/clk-3xxx-legacy.c b/drivers/clk/ti/clk-3xxx-legacy.c
index 0b61548d569b..0fbf8a917955 100644
--- a/drivers/clk/ti/clk-3xxx-legacy.c
+++ b/drivers/clk/ti/clk-3xxx-legacy.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 
diff --git a/drivers/clk/ti/clk-3xxx.c b/drivers/clk/ti/clk-3xxx.c
index 757636d166cf..676ee8f6d813 100644
--- a/drivers/clk/ti/clk-3xxx.c
+++ b/drivers/clk/ti/clk-3xxx.c
@@ -16,9 +16,220 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
+/*
+ * DPLL5_FREQ_FOR_USBHOST: USBHOST and USBTLL are the only clocks
+ * that are sourced by DPLL5, and both of these require this clock
+ * to be at 120 MHz for proper operation.
+ */
+#define DPLL5_FREQ_FOR_USBHOST		120000000
+
+#define OMAP3430ES2_ST_DSS_IDLE_SHIFT			1
+#define OMAP3430ES2_ST_HSOTGUSB_IDLE_SHIFT		5
+#define OMAP3430ES2_ST_SSI_IDLE_SHIFT			8
+
+#define OMAP34XX_CM_IDLEST_VAL				1
+
+/*
+ * In AM35xx IPSS, the {ICK,FCK} enable bits for modules are exported
+ * in the same register at a bit offset of 0x8. The EN_ACK for ICK is
+ * at an offset of 4 from ICK enable bit.
+ */
+#define AM35XX_IPSS_ICK_MASK			0xF
+#define AM35XX_IPSS_ICK_EN_ACK_OFFSET		0x4
+#define AM35XX_IPSS_ICK_FCK_OFFSET		0x8
+#define AM35XX_IPSS_CLK_IDLEST_VAL		0
+
+#define AM35XX_ST_IPSS_SHIFT			5
+
+/**
+ * omap3430es2_clk_ssi_find_idlest - return CM_IDLEST info for SSI
+ * @clk: struct clk * being enabled
+ * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
+ * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
+ * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
+ *
+ * The OMAP3430ES2 SSI target CM_IDLEST bit is at a different shift
+ * from the CM_{I,F}CLKEN bit.  Pass back the correct info via
+ * @idlest_reg and @idlest_bit.  No return value.
+ */
+static void omap3430es2_clk_ssi_find_idlest(struct clk_hw_omap *clk,
+					    void __iomem **idlest_reg,
+					    u8 *idlest_bit,
+					    u8 *idlest_val)
+{
+	u32 r;
+
+	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
+	*idlest_reg = (__force void __iomem *)r;
+	*idlest_bit = OMAP3430ES2_ST_SSI_IDLE_SHIFT;
+	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
+}
+
+const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait = {
+	.allow_idle	= omap2_clkt_iclk_allow_idle,
+	.deny_idle	= omap2_clkt_iclk_deny_idle,
+	.find_idlest	= omap3430es2_clk_ssi_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
+
+/**
+ * omap3430es2_clk_dss_usbhost_find_idlest - CM_IDLEST info for DSS, USBHOST
+ * @clk: struct clk * being enabled
+ * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
+ * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
+ * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
+ *
+ * Some OMAP modules on OMAP3 ES2+ chips have both initiator and
+ * target IDLEST bits.  For our purposes, we are concerned with the
+ * target IDLEST bits, which exist at a different bit position than
+ * the *CLKEN bit position for these modules (DSS and USBHOST) (The
+ * default find_idlest code assumes that they are at the same
+ * position.)  No return value.
+ */
+static void omap3430es2_clk_dss_usbhost_find_idlest(struct clk_hw_omap *clk,
+						    void __iomem **idlest_reg,
+						    u8 *idlest_bit,
+						    u8 *idlest_val)
+{
+	u32 r;
+
+	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
+	*idlest_reg = (__force void __iomem *)r;
+	/* USBHOST_IDLE has same shift */
+	*idlest_bit = OMAP3430ES2_ST_DSS_IDLE_SHIFT;
+	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
+}
+
+const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait = {
+	.find_idlest	= omap3430es2_clk_dss_usbhost_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
+
+const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait = {
+	.allow_idle	= omap2_clkt_iclk_allow_idle,
+	.deny_idle	= omap2_clkt_iclk_deny_idle,
+	.find_idlest	= omap3430es2_clk_dss_usbhost_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
+
+/**
+ * omap3430es2_clk_hsotgusb_find_idlest - return CM_IDLEST info for HSOTGUSB
+ * @clk: struct clk * being enabled
+ * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
+ * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
+ * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
+ *
+ * The OMAP3430ES2 HSOTGUSB target CM_IDLEST bit is at a different
+ * shift from the CM_{I,F}CLKEN bit.  Pass back the correct info via
+ * @idlest_reg and @idlest_bit.  No return value.
+ */
+static void omap3430es2_clk_hsotgusb_find_idlest(struct clk_hw_omap *clk,
+						 void __iomem **idlest_reg,
+						 u8 *idlest_bit,
+						 u8 *idlest_val)
+{
+	u32 r;
+
+	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
+	*idlest_reg = (__force void __iomem *)r;
+	*idlest_bit = OMAP3430ES2_ST_HSOTGUSB_IDLE_SHIFT;
+	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
+}
+
+const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait = {
+	.allow_idle	= omap2_clkt_iclk_allow_idle,
+	.deny_idle	= omap2_clkt_iclk_deny_idle,
+	.find_idlest	= omap3430es2_clk_hsotgusb_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
+
+/**
+ * am35xx_clk_find_idlest - return clock ACK info for AM35XX IPSS
+ * @clk: struct clk * being enabled
+ * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
+ * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
+ * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
+ *
+ * The interface clocks on AM35xx IPSS reflects the clock idle status
+ * in the enable register itsel at a bit offset of 4 from the enable
+ * bit. A value of 1 indicates that clock is enabled.
+ */
+static void am35xx_clk_find_idlest(struct clk_hw_omap *clk,
+				   void __iomem **idlest_reg,
+				   u8 *idlest_bit,
+				   u8 *idlest_val)
+{
+	*idlest_reg = (__force void __iomem *)(clk->enable_reg);
+	*idlest_bit = clk->enable_bit + AM35XX_IPSS_ICK_EN_ACK_OFFSET;
+	*idlest_val = AM35XX_IPSS_CLK_IDLEST_VAL;
+}
+
+/**
+ * am35xx_clk_find_companion - find companion clock to @clk
+ * @clk: struct clk * to find the companion clock of
+ * @other_reg: void __iomem ** to return the companion clock CM_*CLKEN va in
+ * @other_bit: u8 ** to return the companion clock bit shift in
+ *
+ * Some clocks don't have companion clocks.  For example, modules with
+ * only an interface clock (such as HECC) don't have a companion
+ * clock.  Right now, this code relies on the hardware exporting a bit
+ * in the correct companion register that indicates that the
+ * nonexistent 'companion clock' is active.  Future patches will
+ * associate this type of code with per-module data structures to
+ * avoid this issue, and remove the casts.  No return value.
+ */
+static void am35xx_clk_find_companion(struct clk_hw_omap *clk,
+				      void __iomem **other_reg,
+				      u8 *other_bit)
+{
+	*other_reg = (__force void __iomem *)(clk->enable_reg);
+	if (clk->enable_bit & AM35XX_IPSS_ICK_MASK)
+		*other_bit = clk->enable_bit + AM35XX_IPSS_ICK_FCK_OFFSET;
+	else
+	*other_bit = clk->enable_bit - AM35XX_IPSS_ICK_FCK_OFFSET;
+}
+
+const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait = {
+	.find_idlest	= am35xx_clk_find_idlest,
+	.find_companion	= am35xx_clk_find_companion,
+};
+
+/**
+ * am35xx_clk_ipss_find_idlest - return CM_IDLEST info for IPSS
+ * @clk: struct clk * being enabled
+ * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
+ * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
+ * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
+ *
+ * The IPSS target CM_IDLEST bit is at a different shift from the
+ * CM_{I,F}CLKEN bit.  Pass back the correct info via @idlest_reg
+ * and @idlest_bit.  No return value.
+ */
+static void am35xx_clk_ipss_find_idlest(struct clk_hw_omap *clk,
+					void __iomem **idlest_reg,
+					u8 *idlest_bit,
+					u8 *idlest_val)
+{
+	u32 r;
+
+	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
+	*idlest_reg = (__force void __iomem *)r;
+	*idlest_bit = AM35XX_ST_IPSS_SHIFT;
+	*idlest_val = OMAP34XX_CM_IDLEST_VAL;
+}
+
+const struct clk_hw_omap_ops clkhwops_am35xx_ipss_wait = {
+	.allow_idle	= omap2_clkt_iclk_allow_idle,
+	.deny_idle	= omap2_clkt_iclk_deny_idle,
+	.find_idlest	= am35xx_clk_ipss_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
 
 static struct ti_dt_clk omap3xxx_clks[] = {
 	DT_CLK(NULL, "apb_pclk", "dummy_apb_pclk"),
@@ -324,6 +535,30 @@ enum {
 	OMAP3_SOC_OMAP3630,
 };
 
+/**
+ * omap3_clk_lock_dpll5 - locks DPLL5
+ *
+ * Locks DPLL5 to a pre-defined frequency. This is required for proper
+ * operation of USB.
+ */
+void __init omap3_clk_lock_dpll5(void)
+{
+	struct clk *dpll5_clk;
+	struct clk *dpll5_m2_clk;
+
+	dpll5_clk = clk_get(NULL, "dpll5_ck");
+	clk_set_rate(dpll5_clk, DPLL5_FREQ_FOR_USBHOST);
+	clk_prepare_enable(dpll5_clk);
+
+	/* Program dpll5_m2_clk divider for no division */
+	dpll5_m2_clk = clk_get(NULL, "dpll5_m2_ck");
+	clk_prepare_enable(dpll5_m2_clk);
+	clk_set_rate(dpll5_m2_clk, DPLL5_FREQ_FOR_USBHOST);
+
+	clk_disable_unprepare(dpll5_m2_clk);
+	clk_disable_unprepare(dpll5_clk);
+}
+
 static int __init omap3xxx_dt_clk_init(int soc_type)
 {
 	if (soc_type == OMAP3_SOC_AM35XX || soc_type == OMAP3_SOC_OMAP3630 ||
diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c
index 3795fce8a830..097fc90bf19a 100644
--- a/drivers/clk/ti/clk-43xx.c
+++ b/drivers/clk/ti/clk-43xx.c
@@ -16,9 +16,12 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 static struct ti_dt_clk am43xx_clks[] = {
 	DT_CLK(NULL, "clk_32768_ck", "clk_32768_ck"),
 	DT_CLK(NULL, "clk_rc32k_ck", "clk_rc32k_ck"),
@@ -71,6 +74,7 @@ static struct ti_dt_clk am43xx_clks[] = {
 	DT_CLK(NULL, "clk_24mhz", "clk_24mhz"),
 	DT_CLK(NULL, "cpsw_125mhz_gclk", "cpsw_125mhz_gclk"),
 	DT_CLK(NULL, "cpsw_cpts_rft_clk", "cpsw_cpts_rft_clk"),
+	DT_CLK(NULL, "dpll_clksel_mac_clk", "dpll_clksel_mac_clk"),
 	DT_CLK(NULL, "gpio0_dbclk_mux_ck", "gpio0_dbclk_mux_ck"),
 	DT_CLK(NULL, "gpio0_dbclk", "gpio0_dbclk"),
 	DT_CLK(NULL, "gpio1_dbclk", "gpio1_dbclk"),
diff --git a/drivers/clk/ti/clk-44xx.c b/drivers/clk/ti/clk-44xx.c
index 581db7711f51..7a8b51b35f9f 100644
--- a/drivers/clk/ti/clk-44xx.c
+++ b/drivers/clk/ti/clk-44xx.c
@@ -16,6 +16,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 /*
  * OMAP4 ABE DPLL default frequency. In OMAP4460 TRM version V, section
  * "3.6.3.2.3 CM1_ABE Clock Generator" states that the "DPLL_ABE_X2_CLK
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 96c69a335975..59ce2fa2c104 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -17,6 +17,8 @@
 #include <linux/io.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 #define OMAP5_DPLL_ABE_DEFFREQ				98304000
 
 /*
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 63b8323df918..9b5b289e6334 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -16,11 +16,12 @@
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 #define DRA7_DPLL_ABE_DEFFREQ				180633600
 #define DRA7_DPLL_GMAC_DEFFREQ				1000000000
 #define DRA7_DPLL_USB_DEFFREQ				960000000
 
-
 static struct ti_dt_clk dra7xx_clks[] = {
 	DT_CLK(NULL, "atl_clkin0_ck", "atl_clkin0_ck"),
 	DT_CLK(NULL, "atl_clkin1_ck", "atl_clkin1_ck"),
diff --git a/drivers/clk/ti/clk-814x.c b/drivers/clk/ti/clk-814x.c
new file mode 100644
index 000000000000..e172920798ea
--- /dev/null
+++ b/drivers/clk/ti/clk-814x.c
@@ -0,0 +1,33 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/clk-provider.h>
+#include <linux/clk/ti.h>
+
+#include "clock.h"
+
+static struct ti_dt_clk dm814_clks[] = {
+	DT_CLK(NULL, "devosc_ck", "devosc_ck"),
+	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
+	DT_CLK(NULL, "sysclk4_ck", "sysclk4_ck"),
+	DT_CLK(NULL, "sysclk6_ck", "sysclk6_ck"),
+	DT_CLK(NULL, "sysclk10_ck", "sysclk10_ck"),
+	DT_CLK(NULL, "sysclk18_ck", "sysclk18_ck"),
+	DT_CLK(NULL, "timer_sys_ck", "devosc_ck"),
+	DT_CLK(NULL, "cpsw_125mhz_gclk", "cpsw_125mhz_gclk"),
+	DT_CLK(NULL, "cpsw_cpts_rft_clk", "cpsw_cpts_rft_clk"),
+	{ .node_name = NULL },
+};
+
+int __init dm814x_dt_clk_init(void)
+{
+	ti_dt_clocks_register(dm814_clks);
+	omap2_clk_disable_autoidle_all();
+	omap2_clk_enable_init_clocks(NULL, 0);
+
+	return 0;
+}
diff --git a/drivers/clk/ti/clk-816x.c b/drivers/clk/ti/clk-816x.c
index 9451e651a1ff..1dfad0c712cd 100644
--- a/drivers/clk/ti/clk-816x.c
+++ b/drivers/clk/ti/clk-816x.c
@@ -14,6 +14,8 @@
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 static struct ti_dt_clk dm816x_clks[] = {
 	DT_CLK(NULL, "sys_clkin", "sys_clkin_ck"),
 	DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"),
@@ -42,7 +44,7 @@ static const char *enable_init_clks[] = {
 	"ddr_pll_clk3",
 };
 
-int __init ti81xx_dt_clk_init(void)
+int __init dm816x_dt_clk_init(void)
 {
 	ti_dt_clocks_register(dm816x_clks);
 	omap2_clk_disable_autoidle_all();
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
index 19e543a32e2b..2e14dfb588f4 100644
--- a/drivers/clk/ti/clk-dra7-atl.c
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/slab.h>
 #include <linux/io.h>
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index 64bb5e8a3b8c..b5bcd77e8d0f 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -15,12 +15,15 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/list.h>
+#include <linux/regmap.h>
+#include <linux/bootmem.h>
 
 #include "clock.h"
 
@@ -30,6 +33,63 @@
 struct ti_clk_ll_ops *ti_clk_ll_ops;
 static struct device_node *clocks_node_ptr[CLK_MAX_MEMMAPS];
 
+static struct ti_clk_features ti_clk_features;
+
+struct clk_iomap {
+	struct regmap *regmap;
+	void __iomem *mem;
+};
+
+static struct clk_iomap *clk_memmaps[CLK_MAX_MEMMAPS];
+
+static void clk_memmap_writel(u32 val, void __iomem *reg)
+{
+	struct clk_omap_reg *r = (struct clk_omap_reg *)&reg;
+	struct clk_iomap *io = clk_memmaps[r->index];
+
+	if (io->regmap)
+		regmap_write(io->regmap, r->offset, val);
+	else
+		writel_relaxed(val, io->mem + r->offset);
+}
+
+static u32 clk_memmap_readl(void __iomem *reg)
+{
+	u32 val;
+	struct clk_omap_reg *r = (struct clk_omap_reg *)&reg;
+	struct clk_iomap *io = clk_memmaps[r->index];
+
+	if (io->regmap)
+		regmap_read(io->regmap, r->offset, &val);
+	else
+		val = readl_relaxed(io->mem + r->offset);
+
+	return val;
+}
+
+/**
+ * ti_clk_setup_ll_ops - setup low level clock operations
+ * @ops: low level clock ops descriptor
+ *
+ * Sets up low level clock operations for TI clock driver. This is used
+ * to provide various callbacks for the clock driver towards platform
+ * specific code. Returns 0 on success, -EBUSY if ll_ops have been
+ * registered already.
+ */
+int ti_clk_setup_ll_ops(struct ti_clk_ll_ops *ops)
+{
+	if (ti_clk_ll_ops) {
+		pr_err("Attempt to register ll_ops multiple times.\n");
+		return -EBUSY;
+	}
+
+	ti_clk_ll_ops = ops;
+	ops->clk_readl = clk_memmap_readl;
+	ops->clk_writel = clk_memmap_writel;
+
+	return 0;
+}
+
 /**
  * ti_dt_clocks_register - register DT alias clocks during boot
  * @oclks: list of clocks to register
@@ -134,32 +194,67 @@ void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index)
 
 	reg->offset = val;
 
-	return (void __iomem *)tmp;
+	return (__force void __iomem *)tmp;
 }
 
 /**
- * ti_dt_clk_init_provider - init master clock provider
+ * omap2_clk_provider_init - init master clock provider
  * @parent: master node
  * @index: internal index for clk_reg_ops
+ * @syscon: syscon regmap pointer for accessing clock registers
+ * @mem: iomem pointer for the clock provider memory area, only used if
+ *       syscon is not provided
  *
  * Initializes a master clock IP block. This basically sets up the
  * mapping from clocks node to the memory map index. All the clocks
  * are then initialized through the common of_clk_init call, and the
  * clocks will access their memory maps based on the node layout.
+ * Returns 0 in success.
  */
-void ti_dt_clk_init_provider(struct device_node *parent, int index)
+int __init omap2_clk_provider_init(struct device_node *parent, int index,
+				   struct regmap *syscon, void __iomem *mem)
 {
 	struct device_node *clocks;
+	struct clk_iomap *io;
 
 	/* get clocks for this parent */
 	clocks = of_get_child_by_name(parent, "clocks");
 	if (!clocks) {
 		pr_err("%s missing 'clocks' child node.\n", parent->name);
-		return;
+		return -EINVAL;
 	}
 
 	/* add clocks node info */
 	clocks_node_ptr[index] = clocks;
+
+	io = kzalloc(sizeof(*io), GFP_KERNEL);
+	if (!io)
+		return -ENOMEM;
+
+	io->regmap = syscon;
+	io->mem = mem;
+
+	clk_memmaps[index] = io;
+
+	return 0;
+}
+
+/**
+ * omap2_clk_legacy_provider_init - initialize a legacy clock provider
+ * @index: index for the clock provider
+ * @mem: iomem pointer for the clock provider memory area
+ *
+ * Initializes a legacy clock provider memory mapping.
+ */
+void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem)
+{
+	struct clk_iomap *io;
+
+	io = memblock_virt_alloc(sizeof(*io), 0);
+
+	io->mem = mem;
+
+	clk_memmaps[index] = io;
 }
 
 /**
@@ -244,11 +339,11 @@ struct clk __init *ti_clk_register_clk(struct ti_clk *setup)
 	if (!IS_ERR(clk)) {
 		setup->clk = clk;
 		if (setup->clkdm_name) {
-			if (__clk_get_flags(clk) & CLK_IS_BASIC) {
+			clk_hw = __clk_get_hw(clk);
+			if (clk_hw_get_flags(clk_hw) & CLK_IS_BASIC) {
 				pr_warn("can't setup clkdm for basic clk %s\n",
 					setup->name);
 			} else {
-				clk_hw = __clk_get_hw(clk);
 				to_clk_hw_omap(clk_hw)->clkdm_name =
 					setup->clkdm_name;
 				omap2_init_clk_clkdm(clk_hw);
@@ -311,3 +406,50 @@ int __init ti_clk_register_legacy_clks(struct ti_clk_alias *clks)
 	return 0;
 }
 #endif
+
+/**
+ * ti_clk_setup_features - setup clock features flags
+ * @features: features definition to use
+ *
+ * Initializes the clock driver features flags based on platform
+ * provided data. No return value.
+ */
+void __init ti_clk_setup_features(struct ti_clk_features *features)
+{
+	memcpy(&ti_clk_features, features, sizeof(*features));
+}
+
+/**
+ * ti_clk_get_features - get clock driver features flags
+ *
+ * Get TI clock driver features description. Returns a pointer
+ * to the current feature setup.
+ */
+const struct ti_clk_features *ti_clk_get_features(void)
+{
+	return &ti_clk_features;
+}
+
+/**
+ * omap2_clk_enable_init_clocks - prepare & enable a list of clocks
+ * @clk_names: ptr to an array of strings of clock names to enable
+ * @num_clocks: number of clock names in @clk_names
+ *
+ * Prepare and enable a list of clocks, named by @clk_names.  No
+ * return value. XXX Deprecated; only needed until these clocks are
+ * properly claimed and enabled by the drivers or core code that uses
+ * them.  XXX What code disables & calls clk_put on these clocks?
+ */
+void omap2_clk_enable_init_clocks(const char **clk_names, u8 num_clocks)
+{
+	struct clk *init_clk;
+	int i;
+
+	for (i = 0; i < num_clocks; i++) {
+		init_clk = clk_get(NULL, clk_names[i]);
+		if (WARN(IS_ERR(init_clk), "could not find init clock %s\n",
+			 clk_names[i]))
+			continue;
+		clk_prepare_enable(init_clk);
+	}
+}
diff --git a/drivers/clk/ti/clkt_dflt.c b/drivers/clk/ti/clkt_dflt.c
new file mode 100644
index 000000000000..90d7d8a21c49
--- /dev/null
+++ b/drivers/clk/ti/clkt_dflt.c
@@ -0,0 +1,316 @@
+/*
+ * Default clock type
+ *
+ * Copyright (C) 2005-2008, 2015 Texas Instruments, Inc.
+ * Copyright (C) 2004-2010 Nokia Corporation
+ *
+ * Contacts:
+ * Richard Woodruff <r-woodruff2@ti.com>
+ * Paul Walmsley
+ * Tero Kristo <t-kristo@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/clk/ti.h>
+#include <linux/delay.h>
+
+#include "clock.h"
+
+/*
+ * MAX_MODULE_ENABLE_WAIT: maximum of number of microseconds to wait
+ * for a module to indicate that it is no longer in idle
+ */
+#define MAX_MODULE_ENABLE_WAIT		100000
+
+/*
+ * CM module register offsets, used for calculating the companion
+ * register addresses.
+ */
+#define CM_FCLKEN			0x0000
+#define CM_ICLKEN			0x0010
+
+/**
+ * _wait_idlest_generic - wait for a module to leave the idle state
+ * @clk: module clock to wait for (needed for register offsets)
+ * @reg: virtual address of module IDLEST register
+ * @mask: value to mask against to determine if the module is active
+ * @idlest: idle state indicator (0 or 1) for the clock
+ * @name: name of the clock (for printk)
+ *
+ * Wait for a module to leave idle, where its idle-status register is
+ * not inside the CM module.  Returns 1 if the module left idle
+ * promptly, or 0 if the module did not leave idle before the timeout
+ * elapsed.  XXX Deprecated - should be moved into drivers for the
+ * individual IP block that the IDLEST register exists in.
+ */
+static int _wait_idlest_generic(struct clk_hw_omap *clk, void __iomem *reg,
+				u32 mask, u8 idlest, const char *name)
+{
+	int i = 0, ena = 0;
+
+	ena = (idlest) ? 0 : mask;
+
+	/* Wait until module enters enabled state */
+	for (i = 0; i < MAX_MODULE_ENABLE_WAIT; i++) {
+		if ((ti_clk_ll_ops->clk_readl(reg) & mask) == ena)
+			break;
+		udelay(1);
+	}
+
+	if (i < MAX_MODULE_ENABLE_WAIT)
+		pr_debug("omap clock: module associated with clock %s ready after %d loops\n",
+			 name, i);
+	else
+		pr_err("omap clock: module associated with clock %s didn't enable in %d tries\n",
+		       name, MAX_MODULE_ENABLE_WAIT);
+
+	return (i < MAX_MODULE_ENABLE_WAIT) ? 1 : 0;
+}
+
+/**
+ * _omap2_module_wait_ready - wait for an OMAP module to leave IDLE
+ * @clk: struct clk * belonging to the module
+ *
+ * If the necessary clocks for the OMAP hardware IP block that
+ * corresponds to clock @clk are enabled, then wait for the module to
+ * indicate readiness (i.e., to leave IDLE).  This code does not
+ * belong in the clock code and will be moved in the medium term to
+ * module-dependent code.  No return value.
+ */
+static void _omap2_module_wait_ready(struct clk_hw_omap *clk)
+{
+	void __iomem *companion_reg, *idlest_reg;
+	u8 other_bit, idlest_bit, idlest_val, idlest_reg_id;
+	s16 prcm_mod;
+	int r;
+
+	/* Not all modules have multiple clocks that their IDLEST depends on */
+	if (clk->ops->find_companion) {
+		clk->ops->find_companion(clk, &companion_reg, &other_bit);
+		if (!(ti_clk_ll_ops->clk_readl(companion_reg) &
+		      (1 << other_bit)))
+			return;
+	}
+
+	clk->ops->find_idlest(clk, &idlest_reg, &idlest_bit, &idlest_val);
+	r = ti_clk_ll_ops->cm_split_idlest_reg(idlest_reg, &prcm_mod,
+					       &idlest_reg_id);
+	if (r) {
+		/* IDLEST register not in the CM module */
+		_wait_idlest_generic(clk, idlest_reg, (1 << idlest_bit),
+				     idlest_val, clk_hw_get_name(&clk->hw));
+	} else {
+		ti_clk_ll_ops->cm_wait_module_ready(0, prcm_mod, idlest_reg_id,
+						    idlest_bit);
+	}
+}
+
+/**
+ * omap2_clk_dflt_find_companion - find companion clock to @clk
+ * @clk: struct clk * to find the companion clock of
+ * @other_reg: void __iomem ** to return the companion clock CM_*CLKEN va in
+ * @other_bit: u8 ** to return the companion clock bit shift in
+ *
+ * Note: We don't need special code here for INVERT_ENABLE for the
+ * time being since INVERT_ENABLE only applies to clocks enabled by
+ * CM_CLKEN_PLL
+ *
+ * Convert CM_ICLKEN* <-> CM_FCLKEN*.  This conversion assumes it's
+ * just a matter of XORing the bits.
+ *
+ * Some clocks don't have companion clocks.  For example, modules with
+ * only an interface clock (such as MAILBOXES) don't have a companion
+ * clock.  Right now, this code relies on the hardware exporting a bit
+ * in the correct companion register that indicates that the
+ * nonexistent 'companion clock' is active.  Future patches will
+ * associate this type of code with per-module data structures to
+ * avoid this issue, and remove the casts.  No return value.
+ */
+void omap2_clk_dflt_find_companion(struct clk_hw_omap *clk,
+				   void __iomem **other_reg, u8 *other_bit)
+{
+	u32 r;
+
+	/*
+	 * Convert CM_ICLKEN* <-> CM_FCLKEN*.  This conversion assumes
+	 * it's just a matter of XORing the bits.
+	 */
+	r = ((__force u32)clk->enable_reg ^ (CM_FCLKEN ^ CM_ICLKEN));
+
+	*other_reg = (__force void __iomem *)r;
+	*other_bit = clk->enable_bit;
+}
+
+/**
+ * omap2_clk_dflt_find_idlest - find CM_IDLEST reg va, bit shift for @clk
+ * @clk: struct clk * to find IDLEST info for
+ * @idlest_reg: void __iomem ** to return the CM_IDLEST va in
+ * @idlest_bit: u8 * to return the CM_IDLEST bit shift in
+ * @idlest_val: u8 * to return the idle status indicator
+ *
+ * Return the CM_IDLEST register address and bit shift corresponding
+ * to the module that "owns" this clock.  This default code assumes
+ * that the CM_IDLEST bit shift is the CM_*CLKEN bit shift, and that
+ * the IDLEST register address ID corresponds to the CM_*CLKEN
+ * register address ID (e.g., that CM_FCLKEN2 corresponds to
+ * CM_IDLEST2).  This is not true for all modules.  No return value.
+ */
+void omap2_clk_dflt_find_idlest(struct clk_hw_omap *clk,
+				void __iomem **idlest_reg, u8 *idlest_bit,
+				u8 *idlest_val)
+{
+	u32 r;
+
+	r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
+	*idlest_reg = (__force void __iomem *)r;
+	*idlest_bit = clk->enable_bit;
+
+	/*
+	 * 24xx uses 0 to indicate not ready, and 1 to indicate ready.
+	 * 34xx reverses this, just to keep us on our toes
+	 * AM35xx uses both, depending on the module.
+	 */
+	*idlest_val = ti_clk_get_features()->cm_idlest_val;
+}
+
+/**
+ * omap2_dflt_clk_enable - enable a clock in the hardware
+ * @hw: struct clk_hw * of the clock to enable
+ *
+ * Enable the clock @hw in the hardware.  We first call into the OMAP
+ * clockdomain code to "enable" the corresponding clockdomain if this
+ * is the first enabled user of the clockdomain.  Then program the
+ * hardware to enable the clock.  Then wait for the IP block that uses
+ * this clock to leave idle (if applicable).  Returns the error value
+ * from clkdm_clk_enable() if it terminated with an error, or -EINVAL
+ * if @hw has a null clock enable_reg, or zero upon success.
+ */
+int omap2_dflt_clk_enable(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk;
+	u32 v;
+	int ret = 0;
+	bool clkdm_control;
+
+	if (ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL)
+		clkdm_control = false;
+	else
+		clkdm_control = true;
+
+	clk = to_clk_hw_omap(hw);
+
+	if (clkdm_control && clk->clkdm) {
+		ret = ti_clk_ll_ops->clkdm_clk_enable(clk->clkdm, hw->clk);
+		if (ret) {
+			WARN(1,
+			     "%s: could not enable %s's clockdomain %s: %d\n",
+			     __func__, clk_hw_get_name(hw),
+			     clk->clkdm_name, ret);
+			return ret;
+		}
+	}
+
+	if (unlikely(!clk->enable_reg)) {
+		pr_err("%s: %s missing enable_reg\n", __func__,
+		       clk_hw_get_name(hw));
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* FIXME should not have INVERT_ENABLE bit here */
+	v = ti_clk_ll_ops->clk_readl(clk->enable_reg);
+	if (clk->flags & INVERT_ENABLE)
+		v &= ~(1 << clk->enable_bit);
+	else
+		v |= (1 << clk->enable_bit);
+	ti_clk_ll_ops->clk_writel(v, clk->enable_reg);
+	v = ti_clk_ll_ops->clk_readl(clk->enable_reg); /* OCP barrier */
+
+	if (clk->ops && clk->ops->find_idlest)
+		_omap2_module_wait_ready(clk);
+
+	return 0;
+
+err:
+	if (clkdm_control && clk->clkdm)
+		ti_clk_ll_ops->clkdm_clk_disable(clk->clkdm, hw->clk);
+	return ret;
+}
+
+/**
+ * omap2_dflt_clk_disable - disable a clock in the hardware
+ * @hw: struct clk_hw * of the clock to disable
+ *
+ * Disable the clock @hw in the hardware, and call into the OMAP
+ * clockdomain code to "disable" the corresponding clockdomain if all
+ * clocks/hwmods in that clockdomain are now disabled.  No return
+ * value.
+ */
+void omap2_dflt_clk_disable(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk;
+	u32 v;
+
+	clk = to_clk_hw_omap(hw);
+	if (!clk->enable_reg) {
+		/*
+		 * 'independent' here refers to a clock which is not
+		 * controlled by its parent.
+		 */
+		pr_err("%s: independent clock %s has no enable_reg\n",
+		       __func__, clk_hw_get_name(hw));
+		return;
+	}
+
+	v = ti_clk_ll_ops->clk_readl(clk->enable_reg);
+	if (clk->flags & INVERT_ENABLE)
+		v |= (1 << clk->enable_bit);
+	else
+		v &= ~(1 << clk->enable_bit);
+	ti_clk_ll_ops->clk_writel(v, clk->enable_reg);
+	/* No OCP barrier needed here since it is a disable operation */
+
+	if (!(ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL) &&
+	    clk->clkdm)
+		ti_clk_ll_ops->clkdm_clk_disable(clk->clkdm, hw->clk);
+}
+
+/**
+ * omap2_dflt_clk_is_enabled - is clock enabled in the hardware?
+ * @hw: struct clk_hw * to check
+ *
+ * Return 1 if the clock represented by @hw is enabled in the
+ * hardware, or 0 otherwise.  Intended for use in the struct
+ * clk_ops.is_enabled function pointer.
+ */
+int omap2_dflt_clk_is_enabled(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(clk->enable_reg);
+
+	if (clk->flags & INVERT_ENABLE)
+		v ^= BIT(clk->enable_bit);
+
+	v &= BIT(clk->enable_bit);
+
+	return v ? 1 : 0;
+}
+
+const struct clk_hw_omap_ops clkhwops_wait = {
+	.find_idlest	= omap2_clk_dflt_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
diff --git a/arch/arm/mach-omap2/clkt_dpll.c b/drivers/clk/ti/clkt_dpll.c
index f251a14cbf16..9023ca9caf84 100644
--- a/arch/arm/mach-omap2/clkt_dpll.c
+++ b/drivers/clk/ti/clkt_dpll.c
@@ -16,8 +16,10 @@
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
+#include <linux/clk/ti.h>
 
 #include <asm/div64.h>
 
@@ -74,14 +76,14 @@ static int _dpll_test_fint(struct clk_hw_omap *clk, unsigned int n)
 	dd = clk->dpll_data;
 
 	/* DPLL divider must result in a valid jitter correction val */
-	fint = __clk_get_rate(__clk_get_parent(clk->hw.clk)) / n;
+	fint = clk_hw_get_rate(clk_hw_get_parent(&clk->hw)) / n;
 
 	if (dd->flags & DPLL_J_TYPE) {
 		fint_min = OMAP3PLUS_DPLL_FINT_JTYPE_MIN;
 		fint_max = OMAP3PLUS_DPLL_FINT_JTYPE_MAX;
 	} else {
-		fint_min = ti_clk_features.fint_min;
-		fint_max = ti_clk_features.fint_max;
+		fint_min = ti_clk_get_features()->fint_min;
+		fint_max = ti_clk_get_features()->fint_max;
 	}
 
 	if (!fint_min || !fint_max) {
@@ -89,18 +91,18 @@ static int _dpll_test_fint(struct clk_hw_omap *clk, unsigned int n)
 		return DPLL_FINT_INVALID;
 	}
 
-	if (fint < ti_clk_features.fint_min) {
+	if (fint < ti_clk_get_features()->fint_min) {
 		pr_debug("rejecting n=%d due to Fint failure, lowering max_divider\n",
 			 n);
 		dd->max_divider = n;
 		ret = DPLL_FINT_UNDERFLOW;
-	} else if (fint > ti_clk_features.fint_max) {
+	} else if (fint > ti_clk_get_features()->fint_max) {
 		pr_debug("rejecting n=%d due to Fint failure, boosting min_divider\n",
 			 n);
 		dd->min_divider = n;
 		ret = DPLL_FINT_INVALID;
-	} else if (fint > ti_clk_features.fint_band1_max &&
-		   fint < ti_clk_features.fint_band2_min) {
+	} else if (fint > ti_clk_get_features()->fint_band1_max &&
+		   fint < ti_clk_get_features()->fint_band2_min) {
 		pr_debug("rejecting n=%d due to Fint failure\n", n);
 		ret = DPLL_FINT_INVALID;
 	}
@@ -183,7 +185,7 @@ static int _omap2_dpll_is_in_bypass(u32 v)
 {
 	u8 mask, val;
 
-	mask = ti_clk_features.dpll_bypass_vals;
+	mask = ti_clk_get_features()->dpll_bypass_vals;
 
 	/*
 	 * Each set bit in the mask corresponds to a bypass value equal
@@ -211,7 +213,7 @@ u8 omap2_init_dpll_parent(struct clk_hw *hw)
 	if (!dd)
 		return -EINVAL;
 
-	v = omap2_clk_readl(clk, dd->control_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->control_reg);
 	v &= dd->enable_mask;
 	v >>= __ffs(dd->enable_mask);
 
@@ -247,20 +249,20 @@ unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk)
 		return 0;
 
 	/* Return bypass rate if DPLL is bypassed */
-	v = omap2_clk_readl(clk, dd->control_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->control_reg);
 	v &= dd->enable_mask;
 	v >>= __ffs(dd->enable_mask);
 
 	if (_omap2_dpll_is_in_bypass(v))
-		return __clk_get_rate(dd->clk_bypass);
+		return clk_get_rate(dd->clk_bypass);
 
-	v = omap2_clk_readl(clk, dd->mult_div1_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->mult_div1_reg);
 	dpll_mult = v & dd->mult_mask;
 	dpll_mult >>= __ffs(dd->mult_mask);
 	dpll_div = v & dd->div1_mask;
 	dpll_div >>= __ffs(dd->div1_mask);
 
-	dpll_clk = (long long) __clk_get_rate(dd->clk_ref) * dpll_mult;
+	dpll_clk = (long long)clk_get_rate(dd->clk_ref) * dpll_mult;
 	do_div(dpll_clk, dpll_div + 1);
 
 	return dpll_clk;
@@ -281,7 +283,7 @@ unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk)
  * be rounded, or the rounded rate upon success.
  */
 long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
-		unsigned long *parent_rate)
+			   unsigned long *parent_rate)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	int m, n, r, scaled_max_m;
@@ -299,8 +301,8 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
 
 	dd = clk->dpll_data;
 
-	ref_rate = __clk_get_rate(dd->clk_ref);
-	clk_name = __clk_get_name(hw->clk);
+	ref_rate = clk_get_rate(dd->clk_ref);
+	clk_name = clk_hw_get_name(hw);
 	pr_debug("clock: %s: starting DPLL round_rate, target rate %lu\n",
 		 clk_name, target_rate);
 
@@ -310,7 +312,6 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
 	dd->last_rounded_rate = 0;
 
 	for (n = dd->min_divider; n <= dd->max_divider; n++) {
-
 		/* Is the (input clk, divider) pair valid for the DPLL? */
 		r = _dpll_test_fint(clk, n);
 		if (r == DPLL_FINT_UNDERFLOW)
@@ -367,4 +368,3 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
 
 	return dd->last_rounded_rate;
 }
-
diff --git a/drivers/clk/ti/clkt_iclk.c b/drivers/clk/ti/clkt_iclk.c
new file mode 100644
index 000000000000..38c36908cf88
--- /dev/null
+++ b/drivers/clk/ti/clkt_iclk.c
@@ -0,0 +1,101 @@
+/*
+ * OMAP2/3 interface clock control
+ *
+ * Copyright (C) 2011 Nokia Corporation
+ * Paul Walmsley
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/clk/ti.h>
+
+#include "clock.h"
+
+/* Register offsets */
+#define OMAP24XX_CM_FCLKEN2		0x04
+#define CM_AUTOIDLE			0x30
+#define CM_ICLKEN			0x10
+#define CM_IDLEST			0x20
+
+#define OMAP24XX_CM_IDLEST_VAL		0
+
+/* Private functions */
+
+/* XXX */
+void omap2_clkt_iclk_allow_idle(struct clk_hw_omap *clk)
+{
+	u32 v;
+	void __iomem *r;
+
+	r = (__force void __iomem *)
+		((__force u32)clk->enable_reg ^ (CM_AUTOIDLE ^ CM_ICLKEN));
+
+	v = ti_clk_ll_ops->clk_readl(r);
+	v |= (1 << clk->enable_bit);
+	ti_clk_ll_ops->clk_writel(v, r);
+}
+
+/* XXX */
+void omap2_clkt_iclk_deny_idle(struct clk_hw_omap *clk)
+{
+	u32 v;
+	void __iomem *r;
+
+	r = (__force void __iomem *)
+		((__force u32)clk->enable_reg ^ (CM_AUTOIDLE ^ CM_ICLKEN));
+
+	v = ti_clk_ll_ops->clk_readl(r);
+	v &= ~(1 << clk->enable_bit);
+	ti_clk_ll_ops->clk_writel(v, r);
+}
+
+/**
+ * omap2430_clk_i2chs_find_idlest - return CM_IDLEST info for 2430 I2CHS
+ * @clk: struct clk * being enabled
+ * @idlest_reg: void __iomem ** to store CM_IDLEST reg address into
+ * @idlest_bit: pointer to a u8 to store the CM_IDLEST bit shift into
+ * @idlest_val: pointer to a u8 to store the CM_IDLEST indicator
+ *
+ * OMAP2430 I2CHS CM_IDLEST bits are in CM_IDLEST1_CORE, but the
+ * CM_*CLKEN bits are in CM_{I,F}CLKEN2_CORE.  This custom function
+ * passes back the correct CM_IDLEST register address for I2CHS
+ * modules.  No return value.
+ */
+static void omap2430_clk_i2chs_find_idlest(struct clk_hw_omap *clk,
+					   void __iomem **idlest_reg,
+					   u8 *idlest_bit,
+					   u8 *idlest_val)
+{
+	u32 r;
+
+	r = ((__force u32)clk->enable_reg ^ (OMAP24XX_CM_FCLKEN2 ^ CM_IDLEST));
+	*idlest_reg = (__force void __iomem *)r;
+	*idlest_bit = clk->enable_bit;
+	*idlest_val = OMAP24XX_CM_IDLEST_VAL;
+}
+
+/* Public data */
+
+const struct clk_hw_omap_ops clkhwops_iclk = {
+	.allow_idle	= omap2_clkt_iclk_allow_idle,
+	.deny_idle	= omap2_clkt_iclk_deny_idle,
+};
+
+const struct clk_hw_omap_ops clkhwops_iclk_wait = {
+	.allow_idle	= omap2_clkt_iclk_allow_idle,
+	.deny_idle	= omap2_clkt_iclk_deny_idle,
+	.find_idlest	= omap2_clk_dflt_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
+
+/* 2430 I2CHS has non-standard IDLEST register */
+const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait = {
+	.find_idlest	= omap2430_clk_i2chs_find_idlest,
+	.find_companion	= omap2_clk_dflt_find_companion,
+};
diff --git a/drivers/clk/ti/clock.h b/drivers/clk/ti/clock.h
index 404158d2d7f8..90f3f472ae1c 100644
--- a/drivers/clk/ti/clock.h
+++ b/drivers/clk/ti/clock.h
@@ -154,6 +154,35 @@ struct ti_clk_dpll {
 	u8 recal_st_bit;
 };
 
+/* Composite clock component types */
+enum {
+	CLK_COMPONENT_TYPE_GATE = 0,
+	CLK_COMPONENT_TYPE_DIVIDER,
+	CLK_COMPONENT_TYPE_MUX,
+	CLK_COMPONENT_TYPE_MAX,
+};
+
+/**
+ * struct ti_dt_clk - OMAP DT clock alias declarations
+ * @lk: clock lookup definition
+ * @node_name: clock DT node to map to
+ */
+struct ti_dt_clk {
+	struct clk_lookup		lk;
+	char				*node_name;
+};
+
+#define DT_CLK(dev, con, name)		\
+	{				\
+		.lk = {			\
+			.dev_id = dev,	\
+			.con_id = con,	\
+		},			\
+		.node_name = name,	\
+	}
+
+typedef void (*ti_of_clk_init_cb_t)(struct clk_hw *, struct device_node *);
+
 struct clk *ti_clk_register_gate(struct ti_clk *setup);
 struct clk *ti_clk_register_interface(struct ti_clk *setup);
 struct clk *ti_clk_register_mux(struct ti_clk *setup);
@@ -169,4 +198,80 @@ void ti_clk_patch_legacy_clks(struct ti_clk **patch);
 struct clk *ti_clk_register_clk(struct ti_clk *setup);
 int ti_clk_register_legacy_clks(struct ti_clk_alias *clks);
 
+void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index);
+void ti_dt_clocks_register(struct ti_dt_clk *oclks);
+int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
+		      ti_of_clk_init_cb_t func);
+int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type);
+
+void omap2_init_clk_hw_omap_clocks(struct clk_hw *hw);
+int of_ti_clk_autoidle_setup(struct device_node *node);
+void omap2_clk_enable_init_clocks(const char **clk_names, u8 num_clocks);
+
+extern const struct clk_hw_omap_ops clkhwops_omap3_dpll;
+extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx;
+extern const struct clk_hw_omap_ops clkhwops_wait;
+extern const struct clk_hw_omap_ops clkhwops_iclk;
+extern const struct clk_hw_omap_ops clkhwops_iclk_wait;
+extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait;
+extern const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait;
+extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait;
+extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait;
+extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait;
+extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait;
+extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_wait;
+
+extern const struct clk_ops ti_clk_divider_ops;
+extern const struct clk_ops ti_clk_mux_ops;
+
+int omap2_clkops_enable_clkdm(struct clk_hw *hw);
+void omap2_clkops_disable_clkdm(struct clk_hw *hw);
+
+int omap2_dflt_clk_enable(struct clk_hw *hw);
+void omap2_dflt_clk_disable(struct clk_hw *hw);
+int omap2_dflt_clk_is_enabled(struct clk_hw *hw);
+void omap2_clk_dflt_find_companion(struct clk_hw_omap *clk,
+				   void __iomem **other_reg,
+				   u8 *other_bit);
+void omap2_clk_dflt_find_idlest(struct clk_hw_omap *clk,
+				void __iomem **idlest_reg,
+				u8 *idlest_bit, u8 *idlest_val);
+
+void omap2_clkt_iclk_allow_idle(struct clk_hw_omap *clk);
+void omap2_clkt_iclk_deny_idle(struct clk_hw_omap *clk);
+
+u8 omap2_init_dpll_parent(struct clk_hw *hw);
+int omap3_noncore_dpll_enable(struct clk_hw *hw);
+void omap3_noncore_dpll_disable(struct clk_hw *hw);
+int omap3_noncore_dpll_set_parent(struct clk_hw *hw, u8 index);
+int omap3_noncore_dpll_set_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long parent_rate);
+int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw,
+					   unsigned long rate,
+					   unsigned long parent_rate,
+					   u8 index);
+int omap3_noncore_dpll_determine_rate(struct clk_hw *hw,
+				      struct clk_rate_request *req);
+long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
+			   unsigned long *parent_rate);
+unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
+				    unsigned long parent_rate);
+
+unsigned long omap3_dpll_recalc(struct clk_hw *hw, unsigned long parent_rate);
+int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate,
+			 unsigned long parent_rate);
+int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate, u8 index);
+void omap3_clk_lock_dpll5(void);
+
+unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
+					 unsigned long parent_rate);
+long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw,
+				    unsigned long target_rate,
+				    unsigned long *parent_rate);
+int omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw,
+				       struct clk_rate_request *req);
+
+extern struct ti_clk_ll_ops *ti_clk_ll_ops;
+
 #endif
diff --git a/drivers/clk/ti/clockdomain.c b/drivers/clk/ti/clockdomain.c
index b82ef07f3403..b9bc3b8df659 100644
--- a/drivers/clk/ti/clockdomain.c
+++ b/drivers/clk/ti/clockdomain.c
@@ -15,15 +15,94 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 #undef pr_fmt
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
+/**
+ * omap2_clkops_enable_clkdm - increment usecount on clkdm of @hw
+ * @hw: struct clk_hw * of the clock being enabled
+ *
+ * Increment the usecount of the clockdomain of the clock pointed to
+ * by @hw; if the usecount is 1, the clockdomain will be "enabled."
+ * Only needed for clocks that don't use omap2_dflt_clk_enable() as
+ * their enable function pointer.  Passes along the return value of
+ * clkdm_clk_enable(), -EINVAL if @hw is not associated with a
+ * clockdomain, or 0 if clock framework-based clockdomain control is
+ * not implemented.
+ */
+int omap2_clkops_enable_clkdm(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk;
+	int ret = 0;
+
+	clk = to_clk_hw_omap(hw);
+
+	if (unlikely(!clk->clkdm)) {
+		pr_err("%s: %s: no clkdm set ?!\n", __func__,
+		       clk_hw_get_name(hw));
+		return -EINVAL;
+	}
+
+	if (unlikely(clk->enable_reg))
+		pr_err("%s: %s: should use dflt_clk_enable ?!\n", __func__,
+		       clk_hw_get_name(hw));
+
+	if (ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL) {
+		pr_err("%s: %s: clkfw-based clockdomain control disabled ?!\n",
+		       __func__, clk_hw_get_name(hw));
+		return 0;
+	}
+
+	ret = ti_clk_ll_ops->clkdm_clk_enable(clk->clkdm, hw->clk);
+	WARN(ret, "%s: could not enable %s's clockdomain %s: %d\n",
+	     __func__, clk_hw_get_name(hw), clk->clkdm_name, ret);
+
+	return ret;
+}
+
+/**
+ * omap2_clkops_disable_clkdm - decrement usecount on clkdm of @hw
+ * @hw: struct clk_hw * of the clock being disabled
+ *
+ * Decrement the usecount of the clockdomain of the clock pointed to
+ * by @hw; if the usecount is 0, the clockdomain will be "disabled."
+ * Only needed for clocks that don't use omap2_dflt_clk_disable() as their
+ * disable function pointer.  No return value.
+ */
+void omap2_clkops_disable_clkdm(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk;
+
+	clk = to_clk_hw_omap(hw);
+
+	if (unlikely(!clk->clkdm)) {
+		pr_err("%s: %s: no clkdm set ?!\n", __func__,
+		       clk_hw_get_name(hw));
+		return;
+	}
+
+	if (unlikely(clk->enable_reg))
+		pr_err("%s: %s: should use dflt_clk_disable ?!\n", __func__,
+		       clk_hw_get_name(hw));
+
+	if (ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL) {
+		pr_err("%s: %s: clkfw-based clockdomain control disabled ?!\n",
+		       __func__, clk_hw_get_name(hw));
+		return;
+	}
+
+	ti_clk_ll_ops->clkdm_clk_disable(clk->clkdm, hw->clk);
+}
+
 static void __init of_ti_clockdomain_setup(struct device_node *node)
 {
 	struct clk *clk;
@@ -41,12 +120,12 @@ static void __init of_ti_clockdomain_setup(struct device_node *node)
 			       __func__, node->full_name, i, PTR_ERR(clk));
 			continue;
 		}
-		if (__clk_get_flags(clk) & CLK_IS_BASIC) {
+		clk_hw = __clk_get_hw(clk);
+		if (clk_hw_get_flags(clk_hw) & CLK_IS_BASIC) {
 			pr_warn("can't setup clkdm for basic clk %s\n",
 				__clk_get_name(clk));
 			continue;
 		}
-		clk_hw = __clk_get_hw(clk);
 		to_clk_hw_omap(clk_hw)->clkdm_name = clkdm_name;
 		omap2_init_clk_clkdm(clk_hw);
 	}
diff --git a/drivers/clk/ti/composite.c b/drivers/clk/ti/composite.c
index 96f83cedb4b3..dbef218fe5ec 100644
--- a/drivers/clk/ti/composite.c
+++ b/drivers/clk/ti/composite.c
@@ -276,7 +276,6 @@ int __init ti_clk_add_component(struct device_node *node, struct clk_hw *hw,
 	int num_parents;
 	const char **parent_names;
 	struct component_clk *clk;
-	int i;
 
 	num_parents = of_clk_get_parent_count(node);
 
@@ -289,8 +288,7 @@ int __init ti_clk_add_component(struct device_node *node, struct clk_hw *hw,
 	if (!parent_names)
 		return -ENOMEM;
 
-	for (i = 0; i < num_parents; i++)
-		parent_names[i] = of_clk_get_parent_name(node, i);
+	of_clk_parent_fill(node, parent_names, num_parents);
 
 	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
 	if (!clk) {
diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c
index ff5f117950a9..5b1726829e6d 100644
--- a/drivers/clk/ti/divider.c
+++ b/drivers/clk/ti/divider.c
@@ -109,7 +109,7 @@ static unsigned long ti_clk_divider_recalc_rate(struct clk_hw *hw,
 	if (!div) {
 		WARN(!(divider->flags & CLK_DIVIDER_ALLOW_ZERO),
 		     "%s: Zero divisor and CLK_DIVIDER_ALLOW_ZERO not set\n",
-		     __clk_get_name(hw->clk));
+		     clk_hw_get_name(hw));
 		return parent_rate;
 	}
 
@@ -155,7 +155,7 @@ static int ti_clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 
 	maxdiv = _get_maxdiv(divider);
 
-	if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) {
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
 		parent_rate = *best_parent_rate;
 		bestdiv = DIV_ROUND_UP(parent_rate, rate);
 		bestdiv = bestdiv == 0 ? 1 : bestdiv;
@@ -181,7 +181,7 @@ static int ti_clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 			*best_parent_rate = parent_rate_saved;
 			return i;
 		}
-		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
+		parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
 				MULT_ROUND_UP(rate, i));
 		now = DIV_ROUND_UP(parent_rate, i);
 		if (now <= rate && now > best) {
@@ -194,7 +194,7 @@ static int ti_clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 	if (!bestdiv) {
 		bestdiv = _get_maxdiv(divider);
 		*best_parent_rate =
-			__clk_round_rate(__clk_get_parent(hw->clk), 1);
+			clk_hw_round_rate(clk_hw_get_parent(hw), 1);
 	}
 
 	return bestdiv;
diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c
index 2aacf7a3bcae..5519b386edc0 100644
--- a/drivers/clk/ti/dpll.c
+++ b/drivers/clk/ti/dpll.c
@@ -15,6 +15,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/slab.h>
 #include <linux/err.h>
@@ -162,7 +163,7 @@ static void __init _register_dpll(struct clk_hw *hw,
 	clk = clk_register(NULL, &clk_hw->hw);
 
 	if (!IS_ERR(clk)) {
-		omap2_init_clk_hw_omap_clocks(clk);
+		omap2_init_clk_hw_omap_clocks(&clk_hw->hw);
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 		kfree(clk_hw->hw.init->parent_names);
 		kfree(clk_hw->hw.init);
@@ -319,7 +320,7 @@ static void _register_dpll_x2(struct device_node *node,
 	if (IS_ERR(clk)) {
 		kfree(clk_hw);
 	} else {
-		omap2_init_clk_hw_omap_clocks(clk);
+		omap2_init_clk_hw_omap_clocks(&clk_hw->hw);
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 	}
 }
@@ -341,7 +342,6 @@ static void __init of_ti_dpll_setup(struct device_node *node,
 	struct clk_init_data *init = NULL;
 	const char **parent_names = NULL;
 	struct dpll_data *dd = NULL;
-	int i;
 	u8 dpll_mode = 0;
 
 	dd = kzalloc(sizeof(*dd), GFP_KERNEL);
@@ -370,8 +370,7 @@ static void __init of_ti_dpll_setup(struct device_node *node,
 	if (!parent_names)
 		goto cleanup;
 
-	for (i = 0; i < init->num_parents; i++)
-		parent_names[i] = of_clk_get_parent_name(node, i);
+	of_clk_parent_fill(node, parent_names, init->num_parents);
 
 	init->parent_names = parent_names;
 
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c
index 44e57ec225d4..f4dec00fb684 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/drivers/clk/ti/dpll3xxx.c
@@ -27,8 +27,8 @@
 #include <linux/io.h>
 #include <linux/bitops.h>
 #include <linux/clkdev.h>
+#include <linux/clk/ti.h>
 
-#include "clockdomain.h"
 #include "clock.h"
 
 /* CM_AUTOIDLE_PLL*.AUTO_* bit values */
@@ -37,6 +37,13 @@
 
 #define MAX_DPLL_WAIT_TRIES		1000000
 
+#define OMAP3XXX_EN_DPLL_LOCKED		0x7
+
+/* Forward declarations */
+static u32 omap3_dpll_autoidle_read(struct clk_hw_omap *clk);
+static void omap3_dpll_deny_idle(struct clk_hw_omap *clk);
+static void omap3_dpll_allow_idle(struct clk_hw_omap *clk);
+
 /* Private functions */
 
 /* _omap3_dpll_write_clken - write clken_bits arg to a DPLL's enable bits */
@@ -47,10 +54,10 @@ static void _omap3_dpll_write_clken(struct clk_hw_omap *clk, u8 clken_bits)
 
 	dd = clk->dpll_data;
 
-	v = omap2_clk_readl(clk, dd->control_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->control_reg);
 	v &= ~dd->enable_mask;
 	v |= clken_bits << __ffs(dd->enable_mask);
-	omap2_clk_writel(v, clk, dd->control_reg);
+	ti_clk_ll_ops->clk_writel(v, dd->control_reg);
 }
 
 /* _omap3_wait_dpll_status: wait for a DPLL to enter a specific state */
@@ -62,18 +69,18 @@ static int _omap3_wait_dpll_status(struct clk_hw_omap *clk, u8 state)
 	const char *clk_name;
 
 	dd = clk->dpll_data;
-	clk_name = __clk_get_name(clk->hw.clk);
+	clk_name = clk_hw_get_name(&clk->hw);
 
 	state <<= __ffs(dd->idlest_mask);
 
-	while (((omap2_clk_readl(clk, dd->idlest_reg) & dd->idlest_mask)
+	while (((ti_clk_ll_ops->clk_readl(dd->idlest_reg) & dd->idlest_mask)
 		!= state) && i < MAX_DPLL_WAIT_TRIES) {
 		i++;
 		udelay(1);
 	}
 
 	if (i == MAX_DPLL_WAIT_TRIES) {
-		printk(KERN_ERR "clock: %s failed transition to '%s'\n",
+		pr_err("clock: %s failed transition to '%s'\n",
 		       clk_name, (state) ? "locked" : "bypassed");
 	} else {
 		pr_debug("clock: %s transition to '%s' in %d loops\n",
@@ -91,7 +98,7 @@ static u16 _omap3_dpll_compute_freqsel(struct clk_hw_omap *clk, u8 n)
 	unsigned long fint;
 	u16 f = 0;
 
-	fint = __clk_get_rate(clk->dpll_data->clk_ref) / n;
+	fint = clk_get_rate(clk->dpll_data->clk_ref) / n;
 
 	pr_debug("clock: fint is %lu\n", fint);
 
@@ -138,13 +145,14 @@ static int _omap3_noncore_dpll_lock(struct clk_hw_omap *clk)
 	u8 state = 1;
 	int r = 0;
 
-	pr_debug("clock: locking DPLL %s\n", __clk_get_name(clk->hw.clk));
+	pr_debug("clock: locking DPLL %s\n", clk_hw_get_name(&clk->hw));
 
 	dd = clk->dpll_data;
 	state <<= __ffs(dd->idlest_mask);
 
 	/* Check if already locked */
-	if ((omap2_clk_readl(clk, dd->idlest_reg) & dd->idlest_mask) == state)
+	if ((ti_clk_ll_ops->clk_readl(dd->idlest_reg) & dd->idlest_mask) ==
+	    state)
 		goto done;
 
 	ai = omap3_dpll_autoidle_read(clk);
@@ -185,7 +193,7 @@ static int _omap3_noncore_dpll_bypass(struct clk_hw_omap *clk)
 		return -EINVAL;
 
 	pr_debug("clock: configuring DPLL %s for low-power bypass\n",
-		 __clk_get_name(clk->hw.clk));
+		 clk_hw_get_name(&clk->hw));
 
 	ai = omap3_dpll_autoidle_read(clk);
 
@@ -215,7 +223,7 @@ static int _omap3_noncore_dpll_stop(struct clk_hw_omap *clk)
 	if (!(clk->dpll_data->modes & (1 << DPLL_LOW_POWER_STOP)))
 		return -EINVAL;
 
-	pr_debug("clock: stopping DPLL %s\n", __clk_get_name(clk->hw.clk));
+	pr_debug("clock: stopping DPLL %s\n", clk_hw_get_name(&clk->hw));
 
 	ai = omap3_dpll_autoidle_read(clk);
 
@@ -243,7 +251,7 @@ static void _lookup_dco(struct clk_hw_omap *clk, u8 *dco, u16 m, u8 n)
 {
 	unsigned long fint, clkinp; /* watch out for overflow */
 
-	clkinp = __clk_get_rate(__clk_get_parent(clk->hw.clk));
+	clkinp = clk_hw_get_rate(clk_hw_get_parent(&clk->hw));
 	fint = (clkinp / n) * m;
 
 	if (fint < 1000000000)
@@ -269,7 +277,7 @@ static void _lookup_sddiv(struct clk_hw_omap *clk, u8 *sd_div, u16 m, u8 n)
 	unsigned long clkinp, sd; /* watch out for overflow */
 	int mod1, mod2;
 
-	clkinp = __clk_get_rate(__clk_get_parent(clk->hw.clk));
+	clkinp = clk_hw_get_rate(clk_hw_get_parent(&clk->hw));
 
 	/*
 	 * target sigma-delta to near 250MHz
@@ -307,15 +315,15 @@ static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 freqsel)
 	 * Set jitter correction. Jitter correction applicable for OMAP343X
 	 * only since freqsel field is no longer present on other devices.
 	 */
-	if (ti_clk_features.flags & TI_CLK_DPLL_HAS_FREQSEL) {
-		v = omap2_clk_readl(clk, dd->control_reg);
+	if (ti_clk_get_features()->flags & TI_CLK_DPLL_HAS_FREQSEL) {
+		v = ti_clk_ll_ops->clk_readl(dd->control_reg);
 		v &= ~dd->freqsel_mask;
 		v |= freqsel << __ffs(dd->freqsel_mask);
-		omap2_clk_writel(v, clk, dd->control_reg);
+		ti_clk_ll_ops->clk_writel(v, dd->control_reg);
 	}
 
 	/* Set DPLL multiplier, divider */
-	v = omap2_clk_readl(clk, dd->mult_div1_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->mult_div1_reg);
 
 	/* Handle Duty Cycle Correction */
 	if (dd->dcc_mask) {
@@ -342,11 +350,11 @@ static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 freqsel)
 		v |= sd_div << __ffs(dd->sddiv_mask);
 	}
 
-	omap2_clk_writel(v, clk, dd->mult_div1_reg);
+	ti_clk_ll_ops->clk_writel(v, dd->mult_div1_reg);
 
 	/* Set 4X multiplier and low-power mode */
 	if (dd->m4xen_mask || dd->lpmode_mask) {
-		v = omap2_clk_readl(clk, dd->control_reg);
+		v = ti_clk_ll_ops->clk_readl(dd->control_reg);
 
 		if (dd->m4xen_mask) {
 			if (dd->last_rounded_m4xen)
@@ -362,7 +370,7 @@ static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 freqsel)
 				v &= ~dd->lpmode_mask;
 		}
 
-		omap2_clk_writel(v, clk, dd->control_reg);
+		ti_clk_ll_ops->clk_writel(v, dd->control_reg);
 	}
 
 	/* We let the clock framework set the other output dividers later */
@@ -417,19 +425,19 @@ int omap3_noncore_dpll_enable(struct clk_hw *hw)
 		return -EINVAL;
 
 	if (clk->clkdm) {
-		r = clkdm_clk_enable(clk->clkdm, hw->clk);
+		r = ti_clk_ll_ops->clkdm_clk_enable(clk->clkdm, hw->clk);
 		if (r) {
 			WARN(1,
 			     "%s: could not enable %s's clockdomain %s: %d\n",
-			     __func__, __clk_get_name(hw->clk),
-			     clk->clkdm->name, r);
+			     __func__, clk_hw_get_name(hw),
+			     clk->clkdm_name, r);
 			return r;
 		}
 	}
 
-	parent = __clk_get_hw(__clk_get_parent(hw->clk));
+	parent = clk_hw_get_parent(hw);
 
-	if (__clk_get_rate(hw->clk) == __clk_get_rate(dd->clk_bypass)) {
+	if (clk_hw_get_rate(hw) == clk_get_rate(dd->clk_bypass)) {
 		WARN_ON(parent != __clk_get_hw(dd->clk_bypass));
 		r = _omap3_noncore_dpll_bypass(clk);
 	} else {
@@ -453,52 +461,46 @@ void omap3_noncore_dpll_disable(struct clk_hw *hw)
 
 	_omap3_noncore_dpll_stop(clk);
 	if (clk->clkdm)
-		clkdm_clk_disable(clk->clkdm, hw->clk);
+		ti_clk_ll_ops->clkdm_clk_disable(clk->clkdm, hw->clk);
 }
 
-
 /* Non-CORE DPLL rate set code */
 
 /**
  * omap3_noncore_dpll_determine_rate - determine rate for a DPLL
  * @hw: pointer to the clock to determine rate for
- * @rate: target rate for the DPLL
- * @best_parent_rate: pointer for returning best parent rate
- * @best_parent_clk: pointer for returning best parent clock
+ * @req: target rate request
  *
  * Determines which DPLL mode to use for reaching a desired target rate.
  * Checks whether the DPLL shall be in bypass or locked mode, and if
  * locked, calculates the M,N values for the DPLL via round-rate.
- * Returns a positive clock rate with success, negative error value
- * in failure.
+ * Returns a 0 on success, negative error value in failure.
  */
-long omap3_noncore_dpll_determine_rate(struct clk_hw *hw, unsigned long rate,
-				       unsigned long min_rate,
-				       unsigned long max_rate,
-				       unsigned long *best_parent_rate,
-				       struct clk_hw **best_parent_clk)
+int omap3_noncore_dpll_determine_rate(struct clk_hw *hw,
+				      struct clk_rate_request *req)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	struct dpll_data *dd;
 
-	if (!hw || !rate)
+	if (!req->rate)
 		return -EINVAL;
 
 	dd = clk->dpll_data;
 	if (!dd)
 		return -EINVAL;
 
-	if (__clk_get_rate(dd->clk_bypass) == rate &&
+	if (clk_get_rate(dd->clk_bypass) == req->rate &&
 	    (dd->modes & (1 << DPLL_LOW_POWER_BYPASS))) {
-		*best_parent_clk = __clk_get_hw(dd->clk_bypass);
+		req->best_parent_hw = __clk_get_hw(dd->clk_bypass);
 	} else {
-		rate = omap2_dpll_round_rate(hw, rate, best_parent_rate);
-		*best_parent_clk = __clk_get_hw(dd->clk_ref);
+		req->rate = omap2_dpll_round_rate(hw, req->rate,
+					  &req->best_parent_rate);
+		req->best_parent_hw = __clk_get_hw(dd->clk_ref);
 	}
 
-	*best_parent_rate = rate;
+	req->best_parent_rate = req->rate;
 
-	return rate;
+	return 0;
 }
 
 /**
@@ -551,21 +553,20 @@ int omap3_noncore_dpll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!dd)
 		return -EINVAL;
 
-	if (__clk_get_hw(__clk_get_parent(hw->clk)) !=
-	    __clk_get_hw(dd->clk_ref))
+	if (clk_hw_get_parent(hw) != __clk_get_hw(dd->clk_ref))
 		return -EINVAL;
 
 	if (dd->last_rounded_rate == 0)
 		return -EINVAL;
 
 	/* Freqsel is available only on OMAP343X devices */
-	if (ti_clk_features.flags & TI_CLK_DPLL_HAS_FREQSEL) {
+	if (ti_clk_get_features()->flags & TI_CLK_DPLL_HAS_FREQSEL) {
 		freqsel = _omap3_dpll_compute_freqsel(clk, dd->last_rounded_n);
 		WARN_ON(!freqsel);
 	}
 
 	pr_debug("%s: %s: set rate: locking rate to %lu.\n", __func__,
-		 __clk_get_name(hw->clk), rate);
+		 clk_hw_get_name(hw), rate);
 
 	ret = omap3_noncore_dpll_program(clk, freqsel);
 
@@ -618,7 +619,7 @@ int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw,
  * -EINVAL if passed a null pointer or if the struct clk does not
  * appear to refer to a DPLL.
  */
-u32 omap3_dpll_autoidle_read(struct clk_hw_omap *clk)
+static u32 omap3_dpll_autoidle_read(struct clk_hw_omap *clk)
 {
 	const struct dpll_data *dd;
 	u32 v;
@@ -631,7 +632,7 @@ u32 omap3_dpll_autoidle_read(struct clk_hw_omap *clk)
 	if (!dd->autoidle_reg)
 		return -EINVAL;
 
-	v = omap2_clk_readl(clk, dd->autoidle_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->autoidle_reg);
 	v &= dd->autoidle_mask;
 	v >>= __ffs(dd->autoidle_mask);
 
@@ -647,7 +648,7 @@ u32 omap3_dpll_autoidle_read(struct clk_hw_omap *clk)
  * OMAP3430.  The DPLL will enter low-power stop when its downstream
  * clocks are gated.  No return value.
  */
-void omap3_dpll_allow_idle(struct clk_hw_omap *clk)
+static void omap3_dpll_allow_idle(struct clk_hw_omap *clk)
 {
 	const struct dpll_data *dd;
 	u32 v;
@@ -665,11 +666,10 @@ void omap3_dpll_allow_idle(struct clk_hw_omap *clk)
 	 * by writing 0x5 instead of 0x1.  Add some mechanism to
 	 * optionally enter this mode.
 	 */
-	v = omap2_clk_readl(clk, dd->autoidle_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->autoidle_reg);
 	v &= ~dd->autoidle_mask;
 	v |= DPLL_AUTOIDLE_LOW_POWER_STOP << __ffs(dd->autoidle_mask);
-	omap2_clk_writel(v, clk, dd->autoidle_reg);
-
+	ti_clk_ll_ops->clk_writel(v, dd->autoidle_reg);
 }
 
 /**
@@ -678,7 +678,7 @@ void omap3_dpll_allow_idle(struct clk_hw_omap *clk)
  *
  * Disable DPLL automatic idle control.  No return value.
  */
-void omap3_dpll_deny_idle(struct clk_hw_omap *clk)
+static void omap3_dpll_deny_idle(struct clk_hw_omap *clk)
 {
 	const struct dpll_data *dd;
 	u32 v;
@@ -691,11 +691,10 @@ void omap3_dpll_deny_idle(struct clk_hw_omap *clk)
 	if (!dd->autoidle_reg)
 		return;
 
-	v = omap2_clk_readl(clk, dd->autoidle_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->autoidle_reg);
 	v &= ~dd->autoidle_mask;
 	v |= DPLL_AUTOIDLE_DISABLE << __ffs(dd->autoidle_mask);
-	omap2_clk_writel(v, clk, dd->autoidle_reg);
-
+	ti_clk_ll_ops->clk_writel(v, dd->autoidle_reg);
 }
 
 /* Clock control for DPLL outputs */
@@ -704,14 +703,12 @@ void omap3_dpll_deny_idle(struct clk_hw_omap *clk)
 static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw)
 {
 	struct clk_hw_omap *pclk = NULL;
-	struct clk *parent;
 
 	/* Walk up the parents of clk, looking for a DPLL */
 	do {
 		do {
-			parent = __clk_get_parent(hw->clk);
-			hw = __clk_get_hw(parent);
-		} while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC));
+			hw = clk_hw_get_parent(hw);
+		} while (hw && (clk_hw_get_flags(hw) & CLK_IS_BASIC));
 		if (!hw)
 			break;
 		pclk = to_clk_hw_omap(hw);
@@ -753,7 +750,7 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 
 	WARN_ON(!dd->enable_mask);
 
-	v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
+	v = ti_clk_ll_ops->clk_readl(dd->control_reg) & dd->enable_mask;
 	v >>= __ffs(dd->enable_mask);
 	if ((v != OMAP3XXX_EN_DPLL_LOCKED) || (dd->flags & DPLL_J_TYPE))
 		rate = parent_rate;
@@ -762,57 +759,59 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 	return rate;
 }
 
-int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
-					unsigned long parent_rate)
-{
-	return 0;
-}
+/* OMAP3/4 non-CORE DPLL clkops */
+const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
+	.allow_idle	= omap3_dpll_allow_idle,
+	.deny_idle	= omap3_dpll_deny_idle,
+};
 
-long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *prate)
+/**
+ * omap3_dpll4_set_rate - set rate for omap3 per-dpll
+ * @hw: clock to change
+ * @rate: target rate for clock
+ * @parent_rate: rate of the parent clock
+ *
+ * Check if the current SoC supports the per-dpll reprogram operation
+ * or not, and then do the rate change if supported. Returns -EINVAL
+ * if not supported, 0 for success, and potential error codes from the
+ * clock rate change.
+ */
+int omap3_dpll4_set_rate(struct clk_hw *hw, unsigned long rate,
+			 unsigned long parent_rate)
 {
-	const struct dpll_data *dd;
-	u32 v;
-	struct clk_hw_omap *pclk = NULL;
-
-	if (!*prate)
-		return 0;
-
-	pclk = omap3_find_clkoutx2_dpll(hw);
-
-	if (!pclk)
-		return 0;
-
-	dd = pclk->dpll_data;
-
-	/* TYPE J does not have a clkoutx2 */
-	if (dd->flags & DPLL_J_TYPE) {
-		*prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate);
-		return *prate;
+	/*
+	 * According to the 12-5 CDP code from TI, "Limitation 2.5"
+	 * on 3430ES1 prevents us from changing DPLL multipliers or dividers
+	 * on DPLL4.
+	 */
+	if (ti_clk_get_features()->flags & TI_CLK_DPLL4_DENY_REPROGRAM) {
+		pr_err("clock: DPLL4 cannot change rate due to silicon 'Limitation 2.5' on 3430ES1.\n");
+		return -EINVAL;
 	}
 
-	WARN_ON(!dd->enable_mask);
-
-	v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
-	v >>= __ffs(dd->enable_mask);
-
-	/* If in bypass, the rate is fixed to the bypass rate*/
-	if (v != OMAP3XXX_EN_DPLL_LOCKED)
-		return *prate;
-
-	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
-		unsigned long best_parent;
+	return omap3_noncore_dpll_set_rate(hw, rate, parent_rate);
+}
 
-		best_parent = (rate / 2);
-		*prate = __clk_round_rate(__clk_get_parent(hw->clk),
-				best_parent);
+/**
+ * omap3_dpll4_set_rate_and_parent - set rate and parent for omap3 per-dpll
+ * @hw: clock to change
+ * @rate: target rate for clock
+ * @parent_rate: rate of the parent clock
+ * @index: parent index, 0 - reference clock, 1 - bypass clock
+ *
+ * Check if the current SoC support the per-dpll reprogram operation
+ * or not, and then do the rate + parent change if supported. Returns
+ * -EINVAL if not supported, 0 for success, and potential error codes
+ * from the clock rate change.
+ */
+int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate, u8 index)
+{
+	if (ti_clk_get_features()->flags & TI_CLK_DPLL4_DENY_REPROGRAM) {
+		pr_err("clock: DPLL4 cannot change rate due to silicon 'Limitation 2.5' on 3430ES1.\n");
+		return -EINVAL;
 	}
 
-	return *prate * 2;
+	return omap3_noncore_dpll_set_rate_and_parent(hw, rate, parent_rate,
+						      index);
 }
-
-/* OMAP3/4 non-CORE DPLL clkops */
-const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
-	.allow_idle	= omap3_dpll_allow_idle,
-	.deny_idle	= omap3_dpll_deny_idle,
-};
diff --git a/arch/arm/mach-omap2/dpll44xx.c b/drivers/clk/ti/dpll44xx.c
index f231be05b9a6..660d7436ac24 100644
--- a/arch/arm/mach-omap2/dpll44xx.c
+++ b/drivers/clk/ti/dpll44xx.c
@@ -14,6 +14,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/bitops.h>
+#include <linux/clk/ti.h>
 
 #include "clock.h"
 
@@ -29,14 +30,14 @@
 /*
  * Bitfield declarations
  */
-#define OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK		(1 << 8)
-#define OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK		(1 << 10)
-#define OMAP4430_DPLL_REGM4XEN_MASK			(1 << 11)
+#define OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK		BIT(8)
+#define OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK		BIT(10)
+#define OMAP4430_DPLL_REGM4XEN_MASK			BIT(11)
 
 /* Static rate multiplier for OMAP4 REGM4XEN clocks */
 #define OMAP4430_REGM4XEN_MULT				4
 
-void omap4_dpllmx_allow_gatectrl(struct clk_hw_omap *clk)
+static void omap4_dpllmx_allow_gatectrl(struct clk_hw_omap *clk)
 {
 	u32 v;
 	u32 mask;
@@ -48,13 +49,13 @@ void omap4_dpllmx_allow_gatectrl(struct clk_hw_omap *clk)
 			OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK :
 			OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK;
 
-	v = omap2_clk_readl(clk, clk->clksel_reg);
+	v = ti_clk_ll_ops->clk_readl(clk->clksel_reg);
 	/* Clear the bit to allow gatectrl */
 	v &= ~mask;
-	omap2_clk_writel(v, clk, clk->clksel_reg);
+	ti_clk_ll_ops->clk_writel(v, clk->clksel_reg);
 }
 
-void omap4_dpllmx_deny_gatectrl(struct clk_hw_omap *clk)
+static void omap4_dpllmx_deny_gatectrl(struct clk_hw_omap *clk)
 {
 	u32 v;
 	u32 mask;
@@ -66,10 +67,10 @@ void omap4_dpllmx_deny_gatectrl(struct clk_hw_omap *clk)
 			OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK :
 			OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK;
 
-	v = omap2_clk_readl(clk, clk->clksel_reg);
+	v = ti_clk_ll_ops->clk_readl(clk->clksel_reg);
 	/* Set the bit to deny gatectrl */
 	v |= mask;
-	omap2_clk_writel(v, clk, clk->clksel_reg);
+	ti_clk_ll_ops->clk_writel(v, clk->clksel_reg);
 }
 
 const struct clk_hw_omap_ops clkhwops_omap4_dpllmx = {
@@ -93,7 +94,7 @@ static void omap4_dpll_lpmode_recalc(struct dpll_data *dd)
 {
 	long fint, fout;
 
-	fint = __clk_get_rate(dd->clk_ref) / (dd->last_rounded_n + 1);
+	fint = clk_get_rate(dd->clk_ref) / (dd->last_rounded_n + 1);
 	fout = fint * dd->last_rounded_m;
 
 	if ((fint < OMAP4_DPLL_LP_FINT_MAX) && (fout < OMAP4_DPLL_LP_FOUT_MAX))
@@ -112,7 +113,7 @@ static void omap4_dpll_lpmode_recalc(struct dpll_data *dd)
  * upon success, or 0 upon error.
  */
 unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
-			unsigned long parent_rate)
+					 unsigned long parent_rate)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	u32 v;
@@ -127,7 +128,7 @@ unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
 	rate = omap2_get_dpll_rate(clk);
 
 	/* regm4xen adds a multiplier of 4 to DPLL calculations */
-	v = omap2_clk_readl(clk, dd->control_reg);
+	v = ti_clk_ll_ops->clk_readl(dd->control_reg);
 	if (v & OMAP4430_DPLL_REGM4XEN_MASK)
 		rate *= OMAP4430_REGM4XEN_MULT;
 
@@ -191,42 +192,36 @@ out:
 /**
  * omap4_dpll_regm4xen_determine_rate - determine rate for a DPLL
  * @hw: pointer to the clock to determine rate for
- * @rate: target rate for the DPLL
- * @best_parent_rate: pointer for returning best parent rate
- * @best_parent_clk: pointer for returning best parent clock
+ * @req: target rate request
  *
  * Determines which DPLL mode to use for reaching a desired rate.
  * Checks whether the DPLL shall be in bypass or locked mode, and if
  * locked, calculates the M,N values for the DPLL via round-rate.
- * Returns a positive clock rate with success, negative error value
- * in failure.
+ * Returns 0 on success and a negative error value otherwise.
  */
-long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw, unsigned long rate,
-					unsigned long min_rate,
-					unsigned long max_rate,
-					unsigned long *best_parent_rate,
-					struct clk_hw **best_parent_clk)
+int omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw,
+				       struct clk_rate_request *req)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	struct dpll_data *dd;
 
-	if (!hw || !rate)
+	if (!req->rate)
 		return -EINVAL;
 
 	dd = clk->dpll_data;
 	if (!dd)
 		return -EINVAL;
 
-	if (__clk_get_rate(dd->clk_bypass) == rate &&
+	if (clk_get_rate(dd->clk_bypass) == req->rate &&
 	    (dd->modes & (1 << DPLL_LOW_POWER_BYPASS))) {
-		*best_parent_clk = __clk_get_hw(dd->clk_bypass);
+		req->best_parent_hw = __clk_get_hw(dd->clk_bypass);
 	} else {
-		rate = omap4_dpll_regm4xen_round_rate(hw, rate,
-						      best_parent_rate);
-		*best_parent_clk = __clk_get_hw(dd->clk_ref);
+		req->rate = omap4_dpll_regm4xen_round_rate(hw, req->rate,
+						&req->best_parent_rate);
+		req->best_parent_hw = __clk_get_hw(dd->clk_ref);
 	}
 
-	*best_parent_rate = rate;
+	req->best_parent_rate = req->rate;
 
-	return rate;
+	return 0;
 }
diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c
index 730aa62454a2..f4b2e9888bdf 100644
--- a/drivers/clk/ti/fapll.c
+++ b/drivers/clk/ti/fapll.c
@@ -9,6 +9,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -558,8 +559,7 @@ static void __init ti_fapll_setup(struct device_node *node)
 		goto free;
 	}
 
-	parent_name[0] = of_clk_get_parent_name(node, 0);
-	parent_name[1] = of_clk_get_parent_name(node, 1);
+	of_clk_parent_fill(node, parent_name, 2);
 	init->parent_names = parent_name;
 
 	fd->clk_ref = of_clk_get(node, 0);
diff --git a/drivers/clk/ti/fixed-factor.c b/drivers/clk/ti/fixed-factor.c
index c2c8a287408c..3cd406768909 100644
--- a/drivers/clk/ti/fixed-factor.c
+++ b/drivers/clk/ti/fixed-factor.c
@@ -22,6 +22,8 @@
 #include <linux/of_address.h>
 #include <linux/clk/ti.h>
 
+#include "clock.h"
+
 #undef pr_fmt
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
diff --git a/drivers/clk/ti/gate.c b/drivers/clk/ti/gate.c
index 0c6fdfcd5f93..5429d3534363 100644
--- a/drivers/clk/ti/gate.c
+++ b/drivers/clk/ti/gate.c
@@ -62,7 +62,7 @@ static const struct clk_ops omap_gate_clk_hsdiv_restore_ops = {
  * (Any other value different from the Read value) to the
  * corresponding CM_CLKSEL register will refresh the dividers.
  */
-static int omap36xx_gate_clk_enable_with_hsdiv_restore(struct clk_hw *clk)
+static int omap36xx_gate_clk_enable_with_hsdiv_restore(struct clk_hw *hw)
 {
 	struct clk_divider *parent;
 	struct clk_hw *parent_hw;
@@ -70,10 +70,10 @@ static int omap36xx_gate_clk_enable_with_hsdiv_restore(struct clk_hw *clk)
 	int ret;
 
 	/* Clear PWRDN bit of HSDIVIDER */
-	ret = omap2_dflt_clk_enable(clk);
+	ret = omap2_dflt_clk_enable(hw);
 
 	/* Parent is the x2 node, get parent of parent for the m2 div */
-	parent_hw = __clk_get_hw(__clk_get_parent(__clk_get_parent(clk->clk)));
+	parent_hw = clk_hw_get_parent(clk_hw_get_parent(hw));
 	parent = to_clk_divider(parent_hw);
 
 	/* Restore the dividers */
diff --git a/drivers/clk/ti/interface.c b/drivers/clk/ti/interface.c
index c76230d8dd04..e505e6f8228d 100644
--- a/drivers/clk/ti/interface.c
+++ b/drivers/clk/ti/interface.c
@@ -63,7 +63,7 @@ static struct clk *_register_interface(struct device *dev, const char *name,
 	if (IS_ERR(clk))
 		kfree(clk_hw);
 	else
-		omap2_init_clk_hw_omap_clocks(clk);
+		omap2_init_clk_hw_omap_clocks(&clk_hw->hw);
 
 	return clk;
 }
diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c
index 5cdeed538b08..69f08a1d047d 100644
--- a/drivers/clk/ti/mux.c
+++ b/drivers/clk/ti/mux.c
@@ -31,7 +31,7 @@
 static u8 ti_clk_mux_get_parent(struct clk_hw *hw)
 {
 	struct clk_mux *mux = to_clk_mux(hw);
-	int num_parents = __clk_get_num_parents(hw->clk);
+	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	/*
@@ -190,7 +190,6 @@ static void of_mux_clk_setup(struct device_node *node)
 	void __iomem *reg;
 	int num_parents;
 	const char **parent_names;
-	int i;
 	u8 clk_mux_flags = 0;
 	u32 mask = 0;
 	u32 shift = 0;
@@ -205,8 +204,7 @@ static void of_mux_clk_setup(struct device_node *node)
 	if (!parent_names)
 		goto cleanup;
 
-	for (i = 0; i < num_parents; i++)
-		parent_names[i] = of_clk_get_parent_name(node, i);
+	of_clk_parent_fill(node, parent_names, num_parents);
 
 	reg = ti_clk_get_reg_addr(node, 0);
 
diff --git a/drivers/clk/ux500/Makefile b/drivers/clk/ux500/Makefile
index 521483f0ba33..f3baef29859c 100644
--- a/drivers/clk/ux500/Makefile
+++ b/drivers/clk/ux500/Makefile
@@ -9,7 +9,6 @@ obj-y += clk-sysctrl.o
 
 # Clock definitions
 obj-y += u8500_of_clk.o
-obj-y += u8500_clk.o
 obj-y += u9540_clk.o
 obj-y += u8540_clk.o
 
diff --git a/drivers/clk/ux500/abx500-clk.c b/drivers/clk/ux500/abx500-clk.c
index 3e5e05101302..222425d08ab6 100644
--- a/drivers/clk/ux500/abx500-clk.c
+++ b/drivers/clk/ux500/abx500-clk.c
@@ -13,7 +13,6 @@
 #include <linux/platform_device.h>
 #include <linux/mfd/abx500/ab8500.h>
 #include <linux/mfd/abx500/ab8500-sysctrl.h>
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
diff --git a/drivers/clk/ux500/clk-prcmu.c b/drivers/clk/ux500/clk-prcmu.c
index bf63c96acb1a..7f343821f4e4 100644
--- a/drivers/clk/ux500/clk-prcmu.c
+++ b/drivers/clk/ux500/clk-prcmu.c
@@ -43,7 +43,7 @@ static void clk_prcmu_unprepare(struct clk_hw *hw)
 	struct clk_prcmu *clk = to_clk_prcmu(hw);
 	if (prcmu_request_clock(clk->cg_sel, false))
 		pr_err("clk_prcmu: %s failed to disable %s.\n", __func__,
-			__clk_get_name(hw->clk));
+			clk_hw_get_name(hw));
 	else
 		clk->is_prepared = 0;
 }
@@ -101,11 +101,11 @@ static int clk_prcmu_opp_prepare(struct clk_hw *hw)
 
 	if (!clk->opp_requested) {
 		err = prcmu_qos_add_requirement(PRCMU_QOS_APE_OPP,
-						(char *)__clk_get_name(hw->clk),
+						(char *)clk_hw_get_name(hw),
 						100);
 		if (err) {
 			pr_err("clk_prcmu: %s fail req APE OPP for %s.\n",
-				__func__, __clk_get_name(hw->clk));
+				__func__, clk_hw_get_name(hw));
 			return err;
 		}
 		clk->opp_requested = 1;
@@ -114,7 +114,7 @@ static int clk_prcmu_opp_prepare(struct clk_hw *hw)
 	err = prcmu_request_clock(clk->cg_sel, true);
 	if (err) {
 		prcmu_qos_remove_requirement(PRCMU_QOS_APE_OPP,
-					(char *)__clk_get_name(hw->clk));
+					(char *)clk_hw_get_name(hw));
 		clk->opp_requested = 0;
 		return err;
 	}
@@ -129,13 +129,13 @@ static void clk_prcmu_opp_unprepare(struct clk_hw *hw)
 
 	if (prcmu_request_clock(clk->cg_sel, false)) {
 		pr_err("clk_prcmu: %s failed to disable %s.\n", __func__,
-			__clk_get_name(hw->clk));
+			clk_hw_get_name(hw));
 		return;
 	}
 
 	if (clk->opp_requested) {
 		prcmu_qos_remove_requirement(PRCMU_QOS_APE_OPP,
-					(char *)__clk_get_name(hw->clk));
+					(char *)clk_hw_get_name(hw));
 		clk->opp_requested = 0;
 	}
 
@@ -151,7 +151,7 @@ static int clk_prcmu_opp_volt_prepare(struct clk_hw *hw)
 		err = prcmu_request_ape_opp_100_voltage(true);
 		if (err) {
 			pr_err("clk_prcmu: %s fail req APE OPP VOLT for %s.\n",
-				__func__, __clk_get_name(hw->clk));
+				__func__, clk_hw_get_name(hw));
 			return err;
 		}
 		clk->opp_requested = 1;
@@ -174,7 +174,7 @@ static void clk_prcmu_opp_volt_unprepare(struct clk_hw *hw)
 
 	if (prcmu_request_clock(clk->cg_sel, false)) {
 		pr_err("clk_prcmu: %s failed to disable %s.\n", __func__,
-			__clk_get_name(hw->clk));
+			clk_hw_get_name(hw));
 		return;
 	}
 
diff --git a/drivers/clk/ux500/clk-sysctrl.c b/drivers/clk/ux500/clk-sysctrl.c
index e364c9d4aa60..266ddea630d2 100644
--- a/drivers/clk/ux500/clk-sysctrl.c
+++ b/drivers/clk/ux500/clk-sysctrl.c
@@ -52,7 +52,7 @@ static void clk_sysctrl_unprepare(struct clk_hw *hw)
 	struct clk_sysctrl *clk = to_clk_sysctrl(hw);
 	if (ab8500_sysctrl_clear(clk->reg_sel[0], clk->reg_mask[0]))
 		dev_err(clk->dev, "clk_sysctrl: %s fail to clear %s.\n",
-			__func__, __clk_get_name(hw->clk));
+			__func__, clk_hw_get_name(hw));
 }
 
 static unsigned long clk_sysctrl_recalc_rate(struct clk_hw *hw,
diff --git a/drivers/clk/ux500/clk.h b/drivers/clk/ux500/clk.h
index a2bb92d85ee0..b42485da704e 100644
--- a/drivers/clk/ux500/clk.h
+++ b/drivers/clk/ux500/clk.h
@@ -10,10 +10,11 @@
 #ifndef __UX500_CLK_H
 #define __UX500_CLK_H
 
-#include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/types.h>
 
+struct clk;
+
 struct clk *clk_reg_prcc_pclk(const char *name,
 			      const char *parent_name,
 			      resource_size_t phy_base,
diff --git a/drivers/clk/ux500/u8500_clk.c b/drivers/clk/ux500/u8500_clk.c
deleted file mode 100644
index 4626b97b7d83..000000000000
--- a/drivers/clk/ux500/u8500_clk.c
+++ /dev/null
@@ -1,526 +0,0 @@
-/*
- * Clock definitions for u8500 platform.
- *
- * Copyright (C) 2012 ST-Ericsson SA
- * Author: Ulf Hansson <ulf.hansson@linaro.org>
- *
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#include <linux/clk.h>
-#include <linux/clkdev.h>
-#include <linux/clk-provider.h>
-#include <linux/mfd/dbx500-prcmu.h>
-#include <linux/platform_data/clk-ux500.h>
-#include "clk.h"
-
-void u8500_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
-		    u32 clkrst5_base, u32 clkrst6_base)
-{
-	struct prcmu_fw_version *fw_version;
-	const char *sgaclk_parent = NULL;
-	struct clk *clk;
-
-	/* Clock sources */
-	clk = clk_reg_prcmu_gate("soc0_pll", NULL, PRCMU_PLLSOC0,
-				CLK_IS_ROOT|CLK_IGNORE_UNUSED);
-	clk_register_clkdev(clk, "soc0_pll", NULL);
-
-	clk = clk_reg_prcmu_gate("soc1_pll", NULL, PRCMU_PLLSOC1,
-				CLK_IS_ROOT|CLK_IGNORE_UNUSED);
-	clk_register_clkdev(clk, "soc1_pll", NULL);
-
-	clk = clk_reg_prcmu_gate("ddr_pll", NULL, PRCMU_PLLDDR,
-				CLK_IS_ROOT|CLK_IGNORE_UNUSED);
-	clk_register_clkdev(clk, "ddr_pll", NULL);
-
-	/* FIXME: Add sys, ulp and int clocks here. */
-
-	clk = clk_register_fixed_rate(NULL, "rtc32k", "NULL",
-				CLK_IS_ROOT|CLK_IGNORE_UNUSED,
-				32768);
-	clk_register_clkdev(clk, "clk32k", NULL);
-	clk_register_clkdev(clk, "apb_pclk", "rtc-pl031");
-
-	/* PRCMU clocks */
-	fw_version = prcmu_get_fw_version();
-	if (fw_version != NULL) {
-		switch (fw_version->project) {
-		case PRCMU_FW_PROJECT_U8500_C2:
-		case PRCMU_FW_PROJECT_U8520:
-		case PRCMU_FW_PROJECT_U8420:
-			sgaclk_parent = "soc0_pll";
-			break;
-		default:
-			break;
-		}
-	}
-
-	if (sgaclk_parent)
-		clk = clk_reg_prcmu_gate("sgclk", sgaclk_parent,
-					PRCMU_SGACLK, 0);
-	else
-		clk = clk_reg_prcmu_gate("sgclk", NULL,
-					PRCMU_SGACLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "mali");
-
-	clk = clk_reg_prcmu_gate("uartclk", NULL, PRCMU_UARTCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "UART");
-
-	clk = clk_reg_prcmu_gate("msp02clk", NULL, PRCMU_MSP02CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "MSP02");
-
-	clk = clk_reg_prcmu_gate("msp1clk", NULL, PRCMU_MSP1CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "MSP1");
-
-	clk = clk_reg_prcmu_gate("i2cclk", NULL, PRCMU_I2CCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "I2C");
-
-	clk = clk_reg_prcmu_gate("slimclk", NULL, PRCMU_SLIMCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "slim");
-
-	clk = clk_reg_prcmu_gate("per1clk", NULL, PRCMU_PER1CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "PERIPH1");
-
-	clk = clk_reg_prcmu_gate("per2clk", NULL, PRCMU_PER2CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "PERIPH2");
-
-	clk = clk_reg_prcmu_gate("per3clk", NULL, PRCMU_PER3CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "PERIPH3");
-
-	clk = clk_reg_prcmu_gate("per5clk", NULL, PRCMU_PER5CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "PERIPH5");
-
-	clk = clk_reg_prcmu_gate("per6clk", NULL, PRCMU_PER6CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "PERIPH6");
-
-	clk = clk_reg_prcmu_gate("per7clk", NULL, PRCMU_PER7CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "PERIPH7");
-
-	clk = clk_reg_prcmu_scalable("lcdclk", NULL, PRCMU_LCDCLK, 0,
-				CLK_IS_ROOT|CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "lcd");
-	clk_register_clkdev(clk, "lcd", "mcde");
-
-	clk = clk_reg_prcmu_opp_gate("bmlclk", NULL, PRCMU_BMLCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "bml");
-
-	clk = clk_reg_prcmu_scalable("hsitxclk", NULL, PRCMU_HSITXCLK, 0,
-				CLK_IS_ROOT|CLK_SET_RATE_GATE);
-
-	clk = clk_reg_prcmu_scalable("hsirxclk", NULL, PRCMU_HSIRXCLK, 0,
-				CLK_IS_ROOT|CLK_SET_RATE_GATE);
-
-	clk = clk_reg_prcmu_scalable("hdmiclk", NULL, PRCMU_HDMICLK, 0,
-				CLK_IS_ROOT|CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "hdmi");
-	clk_register_clkdev(clk, "hdmi", "mcde");
-
-	clk = clk_reg_prcmu_scalable("apeatclk", NULL, PRCMU_APEATCLK, 0,
-				     CLK_IS_ROOT|CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "apeat");
-
-	clk = clk_reg_prcmu_scalable("apetraceclk", NULL, PRCMU_APETRACECLK, 0,
-				CLK_IS_ROOT|CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "apetrace");
-
-	clk = clk_reg_prcmu_gate("mcdeclk", NULL, PRCMU_MCDECLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "mcde");
-	clk_register_clkdev(clk, "mcde", "mcde");
-	clk_register_clkdev(clk, "dsisys", "dsilink.0");
-	clk_register_clkdev(clk, "dsisys", "dsilink.1");
-	clk_register_clkdev(clk, "dsisys", "dsilink.2");
-
-	clk = clk_reg_prcmu_opp_gate("ipi2cclk", NULL, PRCMU_IPI2CCLK,
-				CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "ipi2");
-
-	clk = clk_reg_prcmu_gate("dsialtclk", NULL, PRCMU_DSIALTCLK,
-				CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "dsialt");
-
-	clk = clk_reg_prcmu_gate("dmaclk", NULL, PRCMU_DMACLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "dma40.0");
-
-	clk = clk_reg_prcmu_gate("b2r2clk", NULL, PRCMU_B2R2CLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "b2r2");
-	clk_register_clkdev(clk, NULL, "b2r2_core");
-	clk_register_clkdev(clk, NULL, "U8500-B2R2.0");
-
-	clk = clk_reg_prcmu_scalable("tvclk", NULL, PRCMU_TVCLK, 0,
-				CLK_IS_ROOT|CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "tv");
-	clk_register_clkdev(clk, "tv", "mcde");
-
-	clk = clk_reg_prcmu_gate("sspclk", NULL, PRCMU_SSPCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "SSP");
-
-	clk = clk_reg_prcmu_gate("rngclk", NULL, PRCMU_RNGCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "rngclk");
-
-	clk = clk_reg_prcmu_gate("uiccclk", NULL, PRCMU_UICCCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "uicc");
-
-	clk = clk_reg_prcmu_gate("timclk", NULL, PRCMU_TIMCLK, CLK_IS_ROOT);
-	clk_register_clkdev(clk, NULL, "mtu0");
-	clk_register_clkdev(clk, NULL, "mtu1");
-
-	clk = clk_reg_prcmu_opp_volt_scalable("sdmmcclk", NULL, PRCMU_SDMMCCLK,
-					100000000,
-					CLK_IS_ROOT|CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdmmc");
-
-	clk = clk_reg_prcmu_scalable("dsi_pll", "hdmiclk",
-				PRCMU_PLLDSI, 0, CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, "dsihs2", "mcde");
-	clk_register_clkdev(clk, "dsihs2", "dsilink.2");
-
-
-	clk = clk_reg_prcmu_scalable("dsi0clk", "dsi_pll",
-				PRCMU_DSI0CLK, 0, CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, "dsihs0", "mcde");
-	clk_register_clkdev(clk, "dsihs0", "dsilink.0");
-
-	clk = clk_reg_prcmu_scalable("dsi1clk", "dsi_pll",
-				PRCMU_DSI1CLK, 0, CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, "dsihs1", "mcde");
-	clk_register_clkdev(clk, "dsihs1", "dsilink.1");
-
-	clk = clk_reg_prcmu_scalable("dsi0escclk", "tvclk",
-				PRCMU_DSI0ESCCLK, 0, CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, "dsilp0", "dsilink.0");
-	clk_register_clkdev(clk, "dsilp0", "mcde");
-
-	clk = clk_reg_prcmu_scalable("dsi1escclk", "tvclk",
-				PRCMU_DSI1ESCCLK, 0, CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, "dsilp1", "dsilink.1");
-	clk_register_clkdev(clk, "dsilp1", "mcde");
-
-	clk = clk_reg_prcmu_scalable("dsi2escclk", "tvclk",
-				PRCMU_DSI2ESCCLK, 0, CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, "dsilp2", "dsilink.2");
-	clk_register_clkdev(clk, "dsilp2", "mcde");
-
-	clk = clk_reg_prcmu_scalable_rate("armss", NULL,
-				PRCMU_ARMSS, 0, CLK_IS_ROOT|CLK_IGNORE_UNUSED);
-	clk_register_clkdev(clk, "armss", NULL);
-
-	clk = clk_register_fixed_factor(NULL, "smp_twd", "armss",
-				CLK_IGNORE_UNUSED, 1, 2);
-	clk_register_clkdev(clk, NULL, "smp_twd");
-
-	/*
-	 * FIXME: Add special handled PRCMU clocks here:
-	 * 1. clkout0yuv, use PRCMU as parent + need regulator + pinctrl.
-	 * 2. ab9540_clkout1yuv, see clkout0yuv
-	 */
-
-	/* PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p1_pclk0", "per1clk", clkrst1_base,
-				BIT(0), 0);
-	clk_register_clkdev(clk, "apb_pclk", "uart0");
-
-	clk = clk_reg_prcc_pclk("p1_pclk1", "per1clk", clkrst1_base,
-				BIT(1), 0);
-	clk_register_clkdev(clk, "apb_pclk", "uart1");
-
-	clk = clk_reg_prcc_pclk("p1_pclk2", "per1clk", clkrst1_base,
-				BIT(2), 0);
-	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.1");
-
-	clk = clk_reg_prcc_pclk("p1_pclk3", "per1clk", clkrst1_base,
-				BIT(3), 0);
-	clk_register_clkdev(clk, "apb_pclk", "msp0");
-	clk_register_clkdev(clk, "apb_pclk", "ux500-msp-i2s.0");
-
-	clk = clk_reg_prcc_pclk("p1_pclk4", "per1clk", clkrst1_base,
-				BIT(4), 0);
-	clk_register_clkdev(clk, "apb_pclk", "msp1");
-	clk_register_clkdev(clk, "apb_pclk", "ux500-msp-i2s.1");
-
-	clk = clk_reg_prcc_pclk("p1_pclk5", "per1clk", clkrst1_base,
-				BIT(5), 0);
-	clk_register_clkdev(clk, "apb_pclk", "sdi0");
-
-	clk = clk_reg_prcc_pclk("p1_pclk6", "per1clk", clkrst1_base,
-				BIT(6), 0);
-	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.2");
-
-	clk = clk_reg_prcc_pclk("p1_pclk7", "per1clk", clkrst1_base,
-				BIT(7), 0);
-	clk_register_clkdev(clk, NULL, "spi3");
-
-	clk = clk_reg_prcc_pclk("p1_pclk8", "per1clk", clkrst1_base,
-				BIT(8), 0);
-	clk_register_clkdev(clk, "apb_pclk", "slimbus0");
-
-	clk = clk_reg_prcc_pclk("p1_pclk9", "per1clk", clkrst1_base,
-				BIT(9), 0);
-	clk_register_clkdev(clk, NULL, "gpio.0");
-	clk_register_clkdev(clk, NULL, "gpio.1");
-	clk_register_clkdev(clk, NULL, "gpioblock0");
-
-	clk = clk_reg_prcc_pclk("p1_pclk10", "per1clk", clkrst1_base,
-				BIT(10), 0);
-	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.4");
-
-	clk = clk_reg_prcc_pclk("p1_pclk11", "per1clk", clkrst1_base,
-				BIT(11), 0);
-	clk_register_clkdev(clk, "apb_pclk", "msp3");
-	clk_register_clkdev(clk, "apb_pclk", "ux500-msp-i2s.3");
-
-	clk = clk_reg_prcc_pclk("p2_pclk0", "per2clk", clkrst2_base,
-				BIT(0), 0);
-	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.3");
-
-	clk = clk_reg_prcc_pclk("p2_pclk1", "per2clk", clkrst2_base,
-				BIT(1), 0);
-	clk_register_clkdev(clk, NULL, "spi2");
-
-	clk = clk_reg_prcc_pclk("p2_pclk2", "per2clk", clkrst2_base,
-				BIT(2), 0);
-	clk_register_clkdev(clk, NULL, "spi1");
-
-	clk = clk_reg_prcc_pclk("p2_pclk3", "per2clk", clkrst2_base,
-				BIT(3), 0);
-	clk_register_clkdev(clk, NULL, "pwl");
-
-	clk = clk_reg_prcc_pclk("p2_pclk4", "per2clk", clkrst2_base,
-				BIT(4), 0);
-	clk_register_clkdev(clk, "apb_pclk", "sdi4");
-
-	clk = clk_reg_prcc_pclk("p2_pclk5", "per2clk", clkrst2_base,
-				BIT(5), 0);
-	clk_register_clkdev(clk, "apb_pclk", "msp2");
-	clk_register_clkdev(clk, "apb_pclk", "ux500-msp-i2s.2");
-
-	clk = clk_reg_prcc_pclk("p2_pclk6", "per2clk", clkrst2_base,
-				BIT(6), 0);
-	clk_register_clkdev(clk, "apb_pclk", "sdi1");
-
-	clk = clk_reg_prcc_pclk("p2_pclk7", "per2clk", clkrst2_base,
-				BIT(7), 0);
-	clk_register_clkdev(clk, "apb_pclk", "sdi3");
-
-	clk = clk_reg_prcc_pclk("p2_pclk8", "per2clk", clkrst2_base,
-				BIT(8), 0);
-	clk_register_clkdev(clk, NULL, "spi0");
-
-	clk = clk_reg_prcc_pclk("p2_pclk9", "per2clk", clkrst2_base,
-				BIT(9), 0);
-	clk_register_clkdev(clk, "hsir_hclk", "ste_hsi.0");
-
-	clk = clk_reg_prcc_pclk("p2_pclk10", "per2clk", clkrst2_base,
-				BIT(10), 0);
-	clk_register_clkdev(clk, "hsit_hclk", "ste_hsi.0");
-
-	clk = clk_reg_prcc_pclk("p2_pclk11", "per2clk", clkrst2_base,
-				BIT(11), 0);
-	clk_register_clkdev(clk, NULL, "gpio.6");
-	clk_register_clkdev(clk, NULL, "gpio.7");
-	clk_register_clkdev(clk, NULL, "gpioblock1");
-
-	clk = clk_reg_prcc_pclk("p2_pclk12", "per2clk", clkrst2_base,
-				BIT(12), 0);
-
-	clk = clk_reg_prcc_pclk("p3_pclk0", "per3clk", clkrst3_base,
-				BIT(0), 0);
-	clk_register_clkdev(clk, "fsmc", NULL);
-	clk_register_clkdev(clk, NULL, "smsc911x.0");
-
-	clk = clk_reg_prcc_pclk("p3_pclk1", "per3clk", clkrst3_base,
-				BIT(1), 0);
-	clk_register_clkdev(clk, "apb_pclk", "ssp0");
-
-	clk = clk_reg_prcc_pclk("p3_pclk2", "per3clk", clkrst3_base,
-				BIT(2), 0);
-	clk_register_clkdev(clk, "apb_pclk", "ssp1");
-
-	clk = clk_reg_prcc_pclk("p3_pclk3", "per3clk", clkrst3_base,
-				BIT(3), 0);
-	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.0");
-
-	clk = clk_reg_prcc_pclk("p3_pclk4", "per3clk", clkrst3_base,
-				BIT(4), 0);
-	clk_register_clkdev(clk, "apb_pclk", "sdi2");
-
-	clk = clk_reg_prcc_pclk("p3_pclk5", "per3clk", clkrst3_base,
-				BIT(5), 0);
-	clk_register_clkdev(clk, "apb_pclk", "ske");
-	clk_register_clkdev(clk, "apb_pclk", "nmk-ske-keypad");
-
-	clk = clk_reg_prcc_pclk("p3_pclk6", "per3clk", clkrst3_base,
-				BIT(6), 0);
-	clk_register_clkdev(clk, "apb_pclk", "uart2");
-
-	clk = clk_reg_prcc_pclk("p3_pclk7", "per3clk", clkrst3_base,
-				BIT(7), 0);
-	clk_register_clkdev(clk, "apb_pclk", "sdi5");
-
-	clk = clk_reg_prcc_pclk("p3_pclk8", "per3clk", clkrst3_base,
-				BIT(8), 0);
-	clk_register_clkdev(clk, NULL, "gpio.2");
-	clk_register_clkdev(clk, NULL, "gpio.3");
-	clk_register_clkdev(clk, NULL, "gpio.4");
-	clk_register_clkdev(clk, NULL, "gpio.5");
-	clk_register_clkdev(clk, NULL, "gpioblock2");
-
-	clk = clk_reg_prcc_pclk("p5_pclk0", "per5clk", clkrst5_base,
-				BIT(0), 0);
-	clk_register_clkdev(clk, "usb", "musb-ux500.0");
-
-	clk = clk_reg_prcc_pclk("p5_pclk1", "per5clk", clkrst5_base,
-				BIT(1), 0);
-	clk_register_clkdev(clk, NULL, "gpio.8");
-	clk_register_clkdev(clk, NULL, "gpioblock3");
-
-	clk = clk_reg_prcc_pclk("p6_pclk0", "per6clk", clkrst6_base,
-				BIT(0), 0);
-	clk_register_clkdev(clk, "apb_pclk", "rng");
-
-	clk = clk_reg_prcc_pclk("p6_pclk1", "per6clk", clkrst6_base,
-				BIT(1), 0);
-	clk_register_clkdev(clk, NULL, "cryp0");
-	clk_register_clkdev(clk, NULL, "cryp1");
-
-	clk = clk_reg_prcc_pclk("p6_pclk2", "per6clk", clkrst6_base,
-				BIT(2), 0);
-	clk_register_clkdev(clk, NULL, "hash0");
-
-	clk = clk_reg_prcc_pclk("p6_pclk3", "per6clk", clkrst6_base,
-				BIT(3), 0);
-	clk_register_clkdev(clk, NULL, "pka");
-
-	clk = clk_reg_prcc_pclk("p6_pclk4", "per6clk", clkrst6_base,
-				BIT(4), 0);
-	clk_register_clkdev(clk, NULL, "hash1");
-
-	clk = clk_reg_prcc_pclk("p6_pclk5", "per6clk", clkrst6_base,
-				BIT(5), 0);
-	clk_register_clkdev(clk, NULL, "cfgreg");
-
-	clk = clk_reg_prcc_pclk("p6_pclk6", "per6clk", clkrst6_base,
-				BIT(6), 0);
-	clk_register_clkdev(clk, "apb_pclk", "mtu0");
-
-	clk = clk_reg_prcc_pclk("p6_pclk7", "per6clk", clkrst6_base,
-				BIT(7), 0);
-	clk_register_clkdev(clk, "apb_pclk", "mtu1");
-
-	/* PRCC K-clocks
-	 *
-	 * FIXME: Some drivers requires PERPIH[n| to be automatically enabled
-	 * by enabling just the K-clock, even if it is not a valid parent to
-	 * the K-clock. Until drivers get fixed we might need some kind of
-	 * "parent muxed join".
-	 */
-
-	/* Periph1 */
-	clk = clk_reg_prcc_kclk("p1_uart0_kclk", "uartclk",
-			clkrst1_base, BIT(0), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "uart0");
-
-	clk = clk_reg_prcc_kclk("p1_uart1_kclk", "uartclk",
-			clkrst1_base, BIT(1), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "uart1");
-
-	clk = clk_reg_prcc_kclk("p1_i2c1_kclk", "i2cclk",
-			clkrst1_base, BIT(2), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "nmk-i2c.1");
-
-	clk = clk_reg_prcc_kclk("p1_msp0_kclk", "msp02clk",
-			clkrst1_base, BIT(3), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "msp0");
-	clk_register_clkdev(clk, NULL, "ux500-msp-i2s.0");
-
-	clk = clk_reg_prcc_kclk("p1_msp1_kclk", "msp1clk",
-			clkrst1_base, BIT(4), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "msp1");
-	clk_register_clkdev(clk, NULL, "ux500-msp-i2s.1");
-
-	clk = clk_reg_prcc_kclk("p1_sdi0_kclk", "sdmmcclk",
-			clkrst1_base, BIT(5), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdi0");
-
-	clk = clk_reg_prcc_kclk("p1_i2c2_kclk", "i2cclk",
-			clkrst1_base, BIT(6), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "nmk-i2c.2");
-
-	clk = clk_reg_prcc_kclk("p1_slimbus0_kclk", "slimclk",
-			clkrst1_base, BIT(8), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "slimbus0");
-
-	clk = clk_reg_prcc_kclk("p1_i2c4_kclk", "i2cclk",
-			clkrst1_base, BIT(9), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "nmk-i2c.4");
-
-	clk = clk_reg_prcc_kclk("p1_msp3_kclk", "msp1clk",
-			clkrst1_base, BIT(10), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "msp3");
-	clk_register_clkdev(clk, NULL, "ux500-msp-i2s.3");
-
-	/* Periph2 */
-	clk = clk_reg_prcc_kclk("p2_i2c3_kclk", "i2cclk",
-			clkrst2_base, BIT(0), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "nmk-i2c.3");
-
-	clk = clk_reg_prcc_kclk("p2_sdi4_kclk", "sdmmcclk",
-			clkrst2_base, BIT(2), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdi4");
-
-	clk = clk_reg_prcc_kclk("p2_msp2_kclk", "msp02clk",
-			clkrst2_base, BIT(3), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "msp2");
-	clk_register_clkdev(clk, NULL, "ux500-msp-i2s.2");
-
-	clk = clk_reg_prcc_kclk("p2_sdi1_kclk", "sdmmcclk",
-			clkrst2_base, BIT(4), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdi1");
-
-	clk = clk_reg_prcc_kclk("p2_sdi3_kclk", "sdmmcclk",
-			clkrst2_base, BIT(5), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdi3");
-
-	/* Note that rate is received from parent. */
-	clk = clk_reg_prcc_kclk("p2_ssirx_kclk", "hsirxclk",
-			clkrst2_base, BIT(6),
-			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
-	clk = clk_reg_prcc_kclk("p2_ssitx_kclk", "hsitxclk",
-			clkrst2_base, BIT(7),
-			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
-
-	/* Periph3 */
-	clk = clk_reg_prcc_kclk("p3_ssp0_kclk", "sspclk",
-			clkrst3_base, BIT(1), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "ssp0");
-
-	clk = clk_reg_prcc_kclk("p3_ssp1_kclk", "sspclk",
-			clkrst3_base, BIT(2), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "ssp1");
-
-	clk = clk_reg_prcc_kclk("p3_i2c0_kclk", "i2cclk",
-			clkrst3_base, BIT(3), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "nmk-i2c.0");
-
-	clk = clk_reg_prcc_kclk("p3_sdi2_kclk", "sdmmcclk",
-			clkrst3_base, BIT(4), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdi2");
-
-	clk = clk_reg_prcc_kclk("p3_ske_kclk", "rtc32k",
-			clkrst3_base, BIT(5), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "ske");
-	clk_register_clkdev(clk, NULL, "nmk-ske-keypad");
-
-	clk = clk_reg_prcc_kclk("p3_uart2_kclk", "uartclk",
-			clkrst3_base, BIT(6), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "uart2");
-
-	clk = clk_reg_prcc_kclk("p3_sdi5_kclk", "sdmmcclk",
-			clkrst3_base, BIT(7), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "sdi5");
-
-	/* Periph6 */
-	clk = clk_reg_prcc_kclk("p3_rng_kclk", "rngclk",
-			clkrst6_base, BIT(0), CLK_SET_RATE_GATE);
-	clk_register_clkdev(clk, NULL, "rng");
-}
diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c
index e319ef912dc6..271c09644652 100644
--- a/drivers/clk/ux500/u8500_of_clk.c
+++ b/drivers/clk/ux500/u8500_of_clk.c
@@ -8,8 +8,7 @@
  */
 
 #include <linux/of.h>
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/of_address.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/platform_data/clk-ux500.h>
@@ -54,14 +53,25 @@ static const struct of_device_id u8500_clk_of_match[] = {
 	{ },
 };
 
-void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
-		       u32 clkrst5_base, u32 clkrst6_base)
+/* CLKRST4 is missing making it hard to index things */
+enum clkrst_index {
+	CLKRST1_INDEX = 0,
+	CLKRST2_INDEX,
+	CLKRST3_INDEX,
+	CLKRST5_INDEX,
+	CLKRST6_INDEX,
+	CLKRST_MAX,
+};
+
+void u8500_clk_init(void)
 {
 	struct prcmu_fw_version *fw_version;
 	struct device_node *np = NULL;
 	struct device_node *child = NULL;
 	const char *sgaclk_parent = NULL;
 	struct clk *clk, *rtc_clk, *twd_clk;
+	u32 bases[CLKRST_MAX];
+	int i;
 
 	if (of_have_populated_dt())
 		np = of_find_matching_node(NULL, u8500_clk_of_match);
@@ -69,6 +79,15 @@ void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 		pr_err("Either DT or U8500 Clock node not found\n");
 		return;
 	}
+	for (i = 0; i < ARRAY_SIZE(bases); i++) {
+		struct resource r;
+
+		if (of_address_to_resource(np, i, &r))
+			/* Not much choice but to continue */
+			pr_err("failed to get CLKRST %d base address\n",
+			       i + 1);
+		bases[i] = r.start;
+	}
 
 	/* Clock sources */
 	clk = clk_reg_prcmu_gate("soc0_pll", NULL, PRCMU_PLLSOC0,
@@ -246,179 +265,179 @@ void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 	 */
 
 	/* PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p1_pclk0", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk0", "per1clk", bases[CLKRST1_INDEX],
 				BIT(0), 0);
 	PRCC_PCLK_STORE(clk, 1, 0);
 
-	clk = clk_reg_prcc_pclk("p1_pclk1", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk1", "per1clk", bases[CLKRST1_INDEX],
 				BIT(1), 0);
 	PRCC_PCLK_STORE(clk, 1, 1);
 
-	clk = clk_reg_prcc_pclk("p1_pclk2", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk2", "per1clk", bases[CLKRST1_INDEX],
 				BIT(2), 0);
 	PRCC_PCLK_STORE(clk, 1, 2);
 
-	clk = clk_reg_prcc_pclk("p1_pclk3", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk3", "per1clk", bases[CLKRST1_INDEX],
 				BIT(3), 0);
 	PRCC_PCLK_STORE(clk, 1, 3);
 
-	clk = clk_reg_prcc_pclk("p1_pclk4", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk4", "per1clk", bases[CLKRST1_INDEX],
 				BIT(4), 0);
 	PRCC_PCLK_STORE(clk, 1, 4);
 
-	clk = clk_reg_prcc_pclk("p1_pclk5", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk5", "per1clk", bases[CLKRST1_INDEX],
 				BIT(5), 0);
 	PRCC_PCLK_STORE(clk, 1, 5);
 
-	clk = clk_reg_prcc_pclk("p1_pclk6", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk6", "per1clk", bases[CLKRST1_INDEX],
 				BIT(6), 0);
 	PRCC_PCLK_STORE(clk, 1, 6);
 
-	clk = clk_reg_prcc_pclk("p1_pclk7", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk7", "per1clk", bases[CLKRST1_INDEX],
 				BIT(7), 0);
 	PRCC_PCLK_STORE(clk, 1, 7);
 
-	clk = clk_reg_prcc_pclk("p1_pclk8", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk8", "per1clk", bases[CLKRST1_INDEX],
 				BIT(8), 0);
 	PRCC_PCLK_STORE(clk, 1, 8);
 
-	clk = clk_reg_prcc_pclk("p1_pclk9", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk9", "per1clk", bases[CLKRST1_INDEX],
 				BIT(9), 0);
 	PRCC_PCLK_STORE(clk, 1, 9);
 
-	clk = clk_reg_prcc_pclk("p1_pclk10", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk10", "per1clk", bases[CLKRST1_INDEX],
 				BIT(10), 0);
 	PRCC_PCLK_STORE(clk, 1, 10);
 
-	clk = clk_reg_prcc_pclk("p1_pclk11", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk11", "per1clk", bases[CLKRST1_INDEX],
 				BIT(11), 0);
 	PRCC_PCLK_STORE(clk, 1, 11);
 
-	clk = clk_reg_prcc_pclk("p2_pclk0", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk0", "per2clk", bases[CLKRST2_INDEX],
 				BIT(0), 0);
 	PRCC_PCLK_STORE(clk, 2, 0);
 
-	clk = clk_reg_prcc_pclk("p2_pclk1", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk1", "per2clk", bases[CLKRST2_INDEX],
 				BIT(1), 0);
 	PRCC_PCLK_STORE(clk, 2, 1);
 
-	clk = clk_reg_prcc_pclk("p2_pclk2", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk2", "per2clk", bases[CLKRST2_INDEX],
 				BIT(2), 0);
 	PRCC_PCLK_STORE(clk, 2, 2);
 
-	clk = clk_reg_prcc_pclk("p2_pclk3", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk3", "per2clk", bases[CLKRST2_INDEX],
 				BIT(3), 0);
 	PRCC_PCLK_STORE(clk, 2, 3);
 
-	clk = clk_reg_prcc_pclk("p2_pclk4", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk4", "per2clk", bases[CLKRST2_INDEX],
 				BIT(4), 0);
 	PRCC_PCLK_STORE(clk, 2, 4);
 
-	clk = clk_reg_prcc_pclk("p2_pclk5", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk5", "per2clk", bases[CLKRST2_INDEX],
 				BIT(5), 0);
 	PRCC_PCLK_STORE(clk, 2, 5);
 
-	clk = clk_reg_prcc_pclk("p2_pclk6", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk6", "per2clk", bases[CLKRST2_INDEX],
 				BIT(6), 0);
 	PRCC_PCLK_STORE(clk, 2, 6);
 
-	clk = clk_reg_prcc_pclk("p2_pclk7", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk7", "per2clk", bases[CLKRST2_INDEX],
 				BIT(7), 0);
 	PRCC_PCLK_STORE(clk, 2, 7);
 
-	clk = clk_reg_prcc_pclk("p2_pclk8", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk8", "per2clk", bases[CLKRST2_INDEX],
 				BIT(8), 0);
 	PRCC_PCLK_STORE(clk, 2, 8);
 
-	clk = clk_reg_prcc_pclk("p2_pclk9", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk9", "per2clk", bases[CLKRST2_INDEX],
 				BIT(9), 0);
 	PRCC_PCLK_STORE(clk, 2, 9);
 
-	clk = clk_reg_prcc_pclk("p2_pclk10", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk10", "per2clk", bases[CLKRST2_INDEX],
 				BIT(10), 0);
 	PRCC_PCLK_STORE(clk, 2, 10);
 
-	clk = clk_reg_prcc_pclk("p2_pclk11", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk11", "per2clk", bases[CLKRST2_INDEX],
 				BIT(11), 0);
 	PRCC_PCLK_STORE(clk, 2, 11);
 
-	clk = clk_reg_prcc_pclk("p2_pclk12", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk12", "per2clk", bases[CLKRST2_INDEX],
 				BIT(12), 0);
 	PRCC_PCLK_STORE(clk, 2, 12);
 
-	clk = clk_reg_prcc_pclk("p3_pclk0", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk0", "per3clk", bases[CLKRST3_INDEX],
 				BIT(0), 0);
 	PRCC_PCLK_STORE(clk, 3, 0);
 
-	clk = clk_reg_prcc_pclk("p3_pclk1", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk1", "per3clk", bases[CLKRST3_INDEX],
 				BIT(1), 0);
 	PRCC_PCLK_STORE(clk, 3, 1);
 
-	clk = clk_reg_prcc_pclk("p3_pclk2", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk2", "per3clk", bases[CLKRST3_INDEX],
 				BIT(2), 0);
 	PRCC_PCLK_STORE(clk, 3, 2);
 
-	clk = clk_reg_prcc_pclk("p3_pclk3", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk3", "per3clk", bases[CLKRST3_INDEX],
 				BIT(3), 0);
 	PRCC_PCLK_STORE(clk, 3, 3);
 
-	clk = clk_reg_prcc_pclk("p3_pclk4", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk4", "per3clk", bases[CLKRST3_INDEX],
 				BIT(4), 0);
 	PRCC_PCLK_STORE(clk, 3, 4);
 
-	clk = clk_reg_prcc_pclk("p3_pclk5", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk5", "per3clk", bases[CLKRST3_INDEX],
 				BIT(5), 0);
 	PRCC_PCLK_STORE(clk, 3, 5);
 
-	clk = clk_reg_prcc_pclk("p3_pclk6", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk6", "per3clk", bases[CLKRST3_INDEX],
 				BIT(6), 0);
 	PRCC_PCLK_STORE(clk, 3, 6);
 
-	clk = clk_reg_prcc_pclk("p3_pclk7", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk7", "per3clk", bases[CLKRST3_INDEX],
 				BIT(7), 0);
 	PRCC_PCLK_STORE(clk, 3, 7);
 
-	clk = clk_reg_prcc_pclk("p3_pclk8", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk8", "per3clk", bases[CLKRST3_INDEX],
 				BIT(8), 0);
 	PRCC_PCLK_STORE(clk, 3, 8);
 
-	clk = clk_reg_prcc_pclk("p5_pclk0", "per5clk", clkrst5_base,
+	clk = clk_reg_prcc_pclk("p5_pclk0", "per5clk", bases[CLKRST5_INDEX],
 				BIT(0), 0);
 	PRCC_PCLK_STORE(clk, 5, 0);
 
-	clk = clk_reg_prcc_pclk("p5_pclk1", "per5clk", clkrst5_base,
+	clk = clk_reg_prcc_pclk("p5_pclk1", "per5clk", bases[CLKRST5_INDEX],
 				BIT(1), 0);
 	PRCC_PCLK_STORE(clk, 5, 1);
 
-	clk = clk_reg_prcc_pclk("p6_pclk0", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk0", "per6clk", bases[CLKRST6_INDEX],
 				BIT(0), 0);
 	PRCC_PCLK_STORE(clk, 6, 0);
 
-	clk = clk_reg_prcc_pclk("p6_pclk1", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk1", "per6clk", bases[CLKRST6_INDEX],
 				BIT(1), 0);
 	PRCC_PCLK_STORE(clk, 6, 1);
 
-	clk = clk_reg_prcc_pclk("p6_pclk2", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk2", "per6clk", bases[CLKRST6_INDEX],
 				BIT(2), 0);
 	PRCC_PCLK_STORE(clk, 6, 2);
 
-	clk = clk_reg_prcc_pclk("p6_pclk3", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk3", "per6clk", bases[CLKRST6_INDEX],
 				BIT(3), 0);
 	PRCC_PCLK_STORE(clk, 6, 3);
 
-	clk = clk_reg_prcc_pclk("p6_pclk4", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk4", "per6clk", bases[CLKRST6_INDEX],
 				BIT(4), 0);
 	PRCC_PCLK_STORE(clk, 6, 4);
 
-	clk = clk_reg_prcc_pclk("p6_pclk5", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk5", "per6clk", bases[CLKRST6_INDEX],
 				BIT(5), 0);
 	PRCC_PCLK_STORE(clk, 6, 5);
 
-	clk = clk_reg_prcc_pclk("p6_pclk6", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk6", "per6clk", bases[CLKRST6_INDEX],
 				BIT(6), 0);
 	PRCC_PCLK_STORE(clk, 6, 6);
 
-	clk = clk_reg_prcc_pclk("p6_pclk7", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk7", "per6clk", bases[CLKRST6_INDEX],
 				BIT(7), 0);
 	PRCC_PCLK_STORE(clk, 6, 7);
 
@@ -432,109 +451,109 @@ void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 
 	/* Periph1 */
 	clk = clk_reg_prcc_kclk("p1_uart0_kclk", "uartclk",
-			clkrst1_base, BIT(0), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 0);
 
 	clk = clk_reg_prcc_kclk("p1_uart1_kclk", "uartclk",
-			clkrst1_base, BIT(1), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(1), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 1);
 
 	clk = clk_reg_prcc_kclk("p1_i2c1_kclk", "i2cclk",
-			clkrst1_base, BIT(2), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(2), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 2);
 
 	clk = clk_reg_prcc_kclk("p1_msp0_kclk", "msp02clk",
-			clkrst1_base, BIT(3), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(3), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 3);
 
 	clk = clk_reg_prcc_kclk("p1_msp1_kclk", "msp1clk",
-			clkrst1_base, BIT(4), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(4), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 4);
 
 	clk = clk_reg_prcc_kclk("p1_sdi0_kclk", "sdmmcclk",
-			clkrst1_base, BIT(5), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(5), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 5);
 
 	clk = clk_reg_prcc_kclk("p1_i2c2_kclk", "i2cclk",
-			clkrst1_base, BIT(6), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(6), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 6);
 
 	clk = clk_reg_prcc_kclk("p1_slimbus0_kclk", "slimclk",
-			clkrst1_base, BIT(8), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(8), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 8);
 
 	clk = clk_reg_prcc_kclk("p1_i2c4_kclk", "i2cclk",
-			clkrst1_base, BIT(9), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(9), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 9);
 
 	clk = clk_reg_prcc_kclk("p1_msp3_kclk", "msp1clk",
-			clkrst1_base, BIT(10), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(10), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 1, 10);
 
 	/* Periph2 */
 	clk = clk_reg_prcc_kclk("p2_i2c3_kclk", "i2cclk",
-			clkrst2_base, BIT(0), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 2, 0);
 
 	clk = clk_reg_prcc_kclk("p2_sdi4_kclk", "sdmmcclk",
-			clkrst2_base, BIT(2), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(2), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 2, 2);
 
 	clk = clk_reg_prcc_kclk("p2_msp2_kclk", "msp02clk",
-			clkrst2_base, BIT(3), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(3), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 2, 3);
 
 	clk = clk_reg_prcc_kclk("p2_sdi1_kclk", "sdmmcclk",
-			clkrst2_base, BIT(4), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(4), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 2, 4);
 
 	clk = clk_reg_prcc_kclk("p2_sdi3_kclk", "sdmmcclk",
-			clkrst2_base, BIT(5), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(5), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 2, 5);
 
 	/* Note that rate is received from parent. */
 	clk = clk_reg_prcc_kclk("p2_ssirx_kclk", "hsirxclk",
-			clkrst2_base, BIT(6),
+			bases[CLKRST2_INDEX], BIT(6),
 			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
 	PRCC_KCLK_STORE(clk, 2, 6);
 
 	clk = clk_reg_prcc_kclk("p2_ssitx_kclk", "hsitxclk",
-			clkrst2_base, BIT(7),
+			bases[CLKRST2_INDEX], BIT(7),
 			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
 	PRCC_KCLK_STORE(clk, 2, 7);
 
 	/* Periph3 */
 	clk = clk_reg_prcc_kclk("p3_ssp0_kclk", "sspclk",
-			clkrst3_base, BIT(1), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(1), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 1);
 
 	clk = clk_reg_prcc_kclk("p3_ssp1_kclk", "sspclk",
-			clkrst3_base, BIT(2), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(2), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 2);
 
 	clk = clk_reg_prcc_kclk("p3_i2c0_kclk", "i2cclk",
-			clkrst3_base, BIT(3), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(3), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 3);
 
 	clk = clk_reg_prcc_kclk("p3_sdi2_kclk", "sdmmcclk",
-			clkrst3_base, BIT(4), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(4), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 4);
 
 	clk = clk_reg_prcc_kclk("p3_ske_kclk", "rtc32k",
-			clkrst3_base, BIT(5), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(5), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 5);
 
 	clk = clk_reg_prcc_kclk("p3_uart2_kclk", "uartclk",
-			clkrst3_base, BIT(6), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(6), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 6);
 
 	clk = clk_reg_prcc_kclk("p3_sdi5_kclk", "sdmmcclk",
-			clkrst3_base, BIT(7), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(7), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 3, 7);
 
 	/* Periph6 */
 	clk = clk_reg_prcc_kclk("p3_rng_kclk", "rngclk",
-			clkrst6_base, BIT(0), CLK_SET_RATE_GATE);
+			bases[CLKRST6_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	PRCC_KCLK_STORE(clk, 6, 0);
 
 	for_each_child_of_node(np, child) {
diff --git a/drivers/clk/ux500/u8540_clk.c b/drivers/clk/ux500/u8540_clk.c
index 20c8add90d11..d7bcb7a86615 100644
--- a/drivers/clk/ux500/u8540_clk.c
+++ b/drivers/clk/ux500/u8540_clk.c
@@ -7,17 +7,51 @@
  * License terms: GNU General Public License (GPL) version 2
  */
 
-#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/platform_data/clk-ux500.h>
 #include "clk.h"
 
-void u8540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
-		    u32 clkrst5_base, u32 clkrst6_base)
+static const struct of_device_id u8540_clk_of_match[] = {
+	{ .compatible = "stericsson,u8540-clks", },
+	{ }
+};
+
+/* CLKRST4 is missing making it hard to index things */
+enum clkrst_index {
+	CLKRST1_INDEX = 0,
+	CLKRST2_INDEX,
+	CLKRST3_INDEX,
+	CLKRST5_INDEX,
+	CLKRST6_INDEX,
+	CLKRST_MAX,
+};
+
+void u8540_clk_init(void)
 {
 	struct clk *clk;
+	struct device_node *np = NULL;
+	u32 bases[CLKRST_MAX];
+	int i;
+
+	if (of_have_populated_dt())
+		np = of_find_matching_node(NULL, u8540_clk_of_match);
+	if (!np) {
+		pr_err("Either DT or U8540 Clock node not found\n");
+		return;
+	}
+	for (i = 0; i < ARRAY_SIZE(bases); i++) {
+		struct resource r;
+
+		if (of_address_to_resource(np, i, &r))
+			/* Not much choice but to continue */
+			pr_err("failed to get CLKRST %d base address\n",
+			       i + 1);
+		bases[i] = r.start;
+	}
 
 	/* Clock sources. */
 	/* Fixed ClockGen */
@@ -219,151 +253,151 @@ void u8540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 
 	/* PRCC P-clocks */
 	/* Peripheral 1 : PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p1_pclk0", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk0", "per1clk", bases[CLKRST1_INDEX],
 				BIT(0), 0);
 	clk_register_clkdev(clk, "apb_pclk", "uart0");
 
-	clk = clk_reg_prcc_pclk("p1_pclk1", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk1", "per1clk", bases[CLKRST1_INDEX],
 				BIT(1), 0);
 	clk_register_clkdev(clk, "apb_pclk", "uart1");
 
-	clk = clk_reg_prcc_pclk("p1_pclk2", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk2", "per1clk", bases[CLKRST1_INDEX],
 				BIT(2), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.1");
 
-	clk = clk_reg_prcc_pclk("p1_pclk3", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk3", "per1clk", bases[CLKRST1_INDEX],
 				BIT(3), 0);
 	clk_register_clkdev(clk, "apb_pclk", "msp0");
 	clk_register_clkdev(clk, "apb_pclk", "dbx5x0-msp-i2s.0");
 
-	clk = clk_reg_prcc_pclk("p1_pclk4", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk4", "per1clk", bases[CLKRST1_INDEX],
 				BIT(4), 0);
 	clk_register_clkdev(clk, "apb_pclk", "msp1");
 	clk_register_clkdev(clk, "apb_pclk", "dbx5x0-msp-i2s.1");
 
-	clk = clk_reg_prcc_pclk("p1_pclk5", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk5", "per1clk", bases[CLKRST1_INDEX],
 				BIT(5), 0);
 	clk_register_clkdev(clk, "apb_pclk", "sdi0");
 
-	clk = clk_reg_prcc_pclk("p1_pclk6", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk6", "per1clk", bases[CLKRST1_INDEX],
 				BIT(6), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.2");
 
-	clk = clk_reg_prcc_pclk("p1_pclk7", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk7", "per1clk", bases[CLKRST1_INDEX],
 				BIT(7), 0);
 	clk_register_clkdev(clk, NULL, "spi3");
 
-	clk = clk_reg_prcc_pclk("p1_pclk8", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk8", "per1clk", bases[CLKRST1_INDEX],
 				BIT(8), 0);
 	clk_register_clkdev(clk, "apb_pclk", "slimbus0");
 
-	clk = clk_reg_prcc_pclk("p1_pclk9", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk9", "per1clk", bases[CLKRST1_INDEX],
 				BIT(9), 0);
 	clk_register_clkdev(clk, NULL, "gpio.0");
 	clk_register_clkdev(clk, NULL, "gpio.1");
 	clk_register_clkdev(clk, NULL, "gpioblock0");
 	clk_register_clkdev(clk, "apb_pclk", "ab85xx-codec.0");
 
-	clk = clk_reg_prcc_pclk("p1_pclk10", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk10", "per1clk", bases[CLKRST1_INDEX],
 				BIT(10), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.4");
 
-	clk = clk_reg_prcc_pclk("p1_pclk11", "per1clk", clkrst1_base,
+	clk = clk_reg_prcc_pclk("p1_pclk11", "per1clk", bases[CLKRST1_INDEX],
 				BIT(11), 0);
 	clk_register_clkdev(clk, "apb_pclk", "msp3");
 	clk_register_clkdev(clk, "apb_pclk", "dbx5x0-msp-i2s.3");
 
 	/* Peripheral 2 : PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p2_pclk0", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk0", "per2clk", bases[CLKRST2_INDEX],
 				BIT(0), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.3");
 
-	clk = clk_reg_prcc_pclk("p2_pclk1", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk1", "per2clk", bases[CLKRST2_INDEX],
 				BIT(1), 0);
 	clk_register_clkdev(clk, NULL, "spi2");
 
-	clk = clk_reg_prcc_pclk("p2_pclk2", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk2", "per2clk", bases[CLKRST2_INDEX],
 				BIT(2), 0);
 	clk_register_clkdev(clk, NULL, "spi1");
 
-	clk = clk_reg_prcc_pclk("p2_pclk3", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk3", "per2clk", bases[CLKRST2_INDEX],
 				BIT(3), 0);
 	clk_register_clkdev(clk, NULL, "pwl");
 
-	clk = clk_reg_prcc_pclk("p2_pclk4", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk4", "per2clk", bases[CLKRST2_INDEX],
 				BIT(4), 0);
 	clk_register_clkdev(clk, "apb_pclk", "sdi4");
 
-	clk = clk_reg_prcc_pclk("p2_pclk5", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk5", "per2clk", bases[CLKRST2_INDEX],
 				BIT(5), 0);
 	clk_register_clkdev(clk, "apb_pclk", "msp2");
 	clk_register_clkdev(clk, "apb_pclk", "dbx5x0-msp-i2s.2");
 
-	clk = clk_reg_prcc_pclk("p2_pclk6", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk6", "per2clk", bases[CLKRST2_INDEX],
 				BIT(6), 0);
 	clk_register_clkdev(clk, "apb_pclk", "sdi1");
 
-	clk = clk_reg_prcc_pclk("p2_pclk7", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk7", "per2clk", bases[CLKRST2_INDEX],
 				BIT(7), 0);
 	clk_register_clkdev(clk, "apb_pclk", "sdi3");
 
-	clk = clk_reg_prcc_pclk("p2_pclk8", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk8", "per2clk", bases[CLKRST2_INDEX],
 				BIT(8), 0);
 	clk_register_clkdev(clk, NULL, "spi0");
 
-	clk = clk_reg_prcc_pclk("p2_pclk9", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk9", "per2clk", bases[CLKRST2_INDEX],
 				BIT(9), 0);
 	clk_register_clkdev(clk, "hsir_hclk", "ste_hsi.0");
 
-	clk = clk_reg_prcc_pclk("p2_pclk10", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk10", "per2clk", bases[CLKRST2_INDEX],
 				BIT(10), 0);
 	clk_register_clkdev(clk, "hsit_hclk", "ste_hsi.0");
 
-	clk = clk_reg_prcc_pclk("p2_pclk11", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk11", "per2clk", bases[CLKRST2_INDEX],
 				BIT(11), 0);
 	clk_register_clkdev(clk, NULL, "gpio.6");
 	clk_register_clkdev(clk, NULL, "gpio.7");
 	clk_register_clkdev(clk, NULL, "gpioblock1");
 
-	clk = clk_reg_prcc_pclk("p2_pclk12", "per2clk", clkrst2_base,
+	clk = clk_reg_prcc_pclk("p2_pclk12", "per2clk", bases[CLKRST2_INDEX],
 				BIT(12), 0);
 	clk_register_clkdev(clk, "msp4-pclk", "ab85xx-codec.0");
 
 	/* Peripheral 3 : PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p3_pclk0", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk0", "per3clk", bases[CLKRST3_INDEX],
 				BIT(0), 0);
 	clk_register_clkdev(clk, NULL, "fsmc");
 
-	clk = clk_reg_prcc_pclk("p3_pclk1", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk1", "per3clk", bases[CLKRST3_INDEX],
 				BIT(1), 0);
 	clk_register_clkdev(clk, "apb_pclk", "ssp0");
 
-	clk = clk_reg_prcc_pclk("p3_pclk2", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk2", "per3clk", bases[CLKRST3_INDEX],
 				BIT(2), 0);
 	clk_register_clkdev(clk, "apb_pclk", "ssp1");
 
-	clk = clk_reg_prcc_pclk("p3_pclk3", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk3", "per3clk", bases[CLKRST3_INDEX],
 				BIT(3), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.0");
 
-	clk = clk_reg_prcc_pclk("p3_pclk4", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk4", "per3clk", bases[CLKRST3_INDEX],
 				BIT(4), 0);
 	clk_register_clkdev(clk, "apb_pclk", "sdi2");
 
-	clk = clk_reg_prcc_pclk("p3_pclk5", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk5", "per3clk", bases[CLKRST3_INDEX],
 				BIT(5), 0);
 	clk_register_clkdev(clk, "apb_pclk", "ske");
 	clk_register_clkdev(clk, "apb_pclk", "nmk-ske-keypad");
 
-	clk = clk_reg_prcc_pclk("p3_pclk6", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk6", "per3clk", bases[CLKRST3_INDEX],
 				BIT(6), 0);
 	clk_register_clkdev(clk, "apb_pclk", "uart2");
 
-	clk = clk_reg_prcc_pclk("p3_pclk7", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk7", "per3clk", bases[CLKRST3_INDEX],
 				BIT(7), 0);
 	clk_register_clkdev(clk, "apb_pclk", "sdi5");
 
-	clk = clk_reg_prcc_pclk("p3_pclk8", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk8", "per3clk", bases[CLKRST3_INDEX],
 				BIT(8), 0);
 	clk_register_clkdev(clk, NULL, "gpio.2");
 	clk_register_clkdev(clk, NULL, "gpio.3");
@@ -371,64 +405,64 @@ void u8540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 	clk_register_clkdev(clk, NULL, "gpio.5");
 	clk_register_clkdev(clk, NULL, "gpioblock2");
 
-	clk = clk_reg_prcc_pclk("p3_pclk9", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk9", "per3clk", bases[CLKRST3_INDEX],
 				BIT(9), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.5");
 
-	clk = clk_reg_prcc_pclk("p3_pclk10", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk10", "per3clk", bases[CLKRST3_INDEX],
 				BIT(10), 0);
 	clk_register_clkdev(clk, "apb_pclk", "nmk-i2c.6");
 
-	clk = clk_reg_prcc_pclk("p3_pclk11", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk11", "per3clk", bases[CLKRST3_INDEX],
 				BIT(11), 0);
 	clk_register_clkdev(clk, "apb_pclk", "uart3");
 
-	clk = clk_reg_prcc_pclk("p3_pclk12", "per3clk", clkrst3_base,
+	clk = clk_reg_prcc_pclk("p3_pclk12", "per3clk", bases[CLKRST3_INDEX],
 				BIT(12), 0);
 	clk_register_clkdev(clk, "apb_pclk", "uart4");
 
 	/* Peripheral 5 : PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p5_pclk0", "per5clk", clkrst5_base,
+	clk = clk_reg_prcc_pclk("p5_pclk0", "per5clk", bases[CLKRST5_INDEX],
 				BIT(0), 0);
 	clk_register_clkdev(clk, "usb", "musb-ux500.0");
 	clk_register_clkdev(clk, "usbclk", "ab-iddet.0");
 
-	clk = clk_reg_prcc_pclk("p5_pclk1", "per5clk", clkrst5_base,
+	clk = clk_reg_prcc_pclk("p5_pclk1", "per5clk", bases[CLKRST5_INDEX],
 				BIT(1), 0);
 	clk_register_clkdev(clk, NULL, "gpio.8");
 	clk_register_clkdev(clk, NULL, "gpioblock3");
 
 	/* Peripheral 6 : PRCC P-clocks */
-	clk = clk_reg_prcc_pclk("p6_pclk0", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk0", "per6clk", bases[CLKRST6_INDEX],
 				BIT(0), 0);
 	clk_register_clkdev(clk, "apb_pclk", "rng");
 
-	clk = clk_reg_prcc_pclk("p6_pclk1", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk1", "per6clk", bases[CLKRST6_INDEX],
 				BIT(1), 0);
 	clk_register_clkdev(clk, NULL, "cryp0");
 	clk_register_clkdev(clk, NULL, "cryp1");
 
-	clk = clk_reg_prcc_pclk("p6_pclk2", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk2", "per6clk", bases[CLKRST6_INDEX],
 				BIT(2), 0);
 	clk_register_clkdev(clk, NULL, "hash0");
 
-	clk = clk_reg_prcc_pclk("p6_pclk3", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk3", "per6clk", bases[CLKRST6_INDEX],
 				BIT(3), 0);
 	clk_register_clkdev(clk, NULL, "pka");
 
-	clk = clk_reg_prcc_pclk("p6_pclk4", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk4", "per6clk", bases[CLKRST6_INDEX],
 				BIT(4), 0);
 	clk_register_clkdev(clk, NULL, "db8540-hash1");
 
-	clk = clk_reg_prcc_pclk("p6_pclk5", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk5", "per6clk", bases[CLKRST6_INDEX],
 				BIT(5), 0);
 	clk_register_clkdev(clk, NULL, "cfgreg");
 
-	clk = clk_reg_prcc_pclk("p6_pclk6", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk6", "per6clk", bases[CLKRST6_INDEX],
 				BIT(6), 0);
 	clk_register_clkdev(clk, "apb_pclk", "mtu0");
 
-	clk = clk_reg_prcc_pclk("p6_pclk7", "per6clk", clkrst6_base,
+	clk = clk_reg_prcc_pclk("p6_pclk7", "per6clk", bases[CLKRST6_INDEX],
 				BIT(7), 0);
 	clk_register_clkdev(clk, "apb_pclk", "mtu1");
 
@@ -442,138 +476,138 @@ void u8540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 
 	/* Peripheral 1 : PRCC K-clocks */
 	clk = clk_reg_prcc_kclk("p1_uart0_kclk", "uartclk",
-			clkrst1_base, BIT(0), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "uart0");
 
 	clk = clk_reg_prcc_kclk("p1_uart1_kclk", "uartclk",
-			clkrst1_base, BIT(1), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(1), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "uart1");
 
 	clk = clk_reg_prcc_kclk("p1_i2c1_kclk", "i2cclk",
-			clkrst1_base, BIT(2), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(2), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.1");
 
 	clk = clk_reg_prcc_kclk("p1_msp0_kclk", "msp02clk",
-			clkrst1_base, BIT(3), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(3), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "msp0");
 	clk_register_clkdev(clk, NULL, "dbx5x0-msp-i2s.0");
 
 	clk = clk_reg_prcc_kclk("p1_msp1_kclk", "msp1clk",
-			clkrst1_base, BIT(4), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(4), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "msp1");
 	clk_register_clkdev(clk, NULL, "dbx5x0-msp-i2s.1");
 
 	clk = clk_reg_prcc_kclk("p1_sdi0_kclk", "sdmmchclk",
-			clkrst1_base, BIT(5), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(5), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "sdi0");
 
 	clk = clk_reg_prcc_kclk("p1_i2c2_kclk", "i2cclk",
-			clkrst1_base, BIT(6), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(6), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.2");
 
 	clk = clk_reg_prcc_kclk("p1_slimbus0_kclk", "slimclk",
-			clkrst1_base, BIT(8), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(8), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "slimbus0");
 
 	clk = clk_reg_prcc_kclk("p1_i2c4_kclk", "i2cclk",
-			clkrst1_base, BIT(9), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(9), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.4");
 
 	clk = clk_reg_prcc_kclk("p1_msp3_kclk", "msp1clk",
-			clkrst1_base, BIT(10), CLK_SET_RATE_GATE);
+			bases[CLKRST1_INDEX], BIT(10), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "msp3");
 	clk_register_clkdev(clk, NULL, "dbx5x0-msp-i2s.3");
 
 	/* Peripheral 2 : PRCC K-clocks */
 	clk = clk_reg_prcc_kclk("p2_i2c3_kclk", "i2cclk",
-			clkrst2_base, BIT(0), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.3");
 
 	clk = clk_reg_prcc_kclk("p2_pwl_kclk", "rtc32k",
-			clkrst2_base, BIT(1), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(1), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "pwl");
 
 	clk = clk_reg_prcc_kclk("p2_sdi4_kclk", "sdmmchclk",
-			clkrst2_base, BIT(2), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(2), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "sdi4");
 
 	clk = clk_reg_prcc_kclk("p2_msp2_kclk", "msp02clk",
-			clkrst2_base, BIT(3), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(3), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "msp2");
 	clk_register_clkdev(clk, NULL, "dbx5x0-msp-i2s.2");
 
 	clk = clk_reg_prcc_kclk("p2_sdi1_kclk", "sdmmchclk",
-			clkrst2_base, BIT(4), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(4), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "sdi1");
 
 	clk = clk_reg_prcc_kclk("p2_sdi3_kclk", "sdmmcclk",
-			clkrst2_base, BIT(5), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(5), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "sdi3");
 
 	clk = clk_reg_prcc_kclk("p2_ssirx_kclk", "hsirxclk",
-			clkrst2_base, BIT(6),
+			bases[CLKRST2_INDEX], BIT(6),
 			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
 	clk_register_clkdev(clk, "hsir_hsirxclk", "ste_hsi.0");
 
 	clk = clk_reg_prcc_kclk("p2_ssitx_kclk", "hsitxclk",
-			clkrst2_base, BIT(7),
+			bases[CLKRST2_INDEX], BIT(7),
 			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
 	clk_register_clkdev(clk, "hsit_hsitxclk", "ste_hsi.0");
 
 	/* Should only be 9540, but might be added for 85xx as well */
 	clk = clk_reg_prcc_kclk("p2_msp4_kclk", "msp02clk",
-			clkrst2_base, BIT(9), CLK_SET_RATE_GATE);
+			bases[CLKRST2_INDEX], BIT(9), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "msp4");
 	clk_register_clkdev(clk, "msp4", "ab85xx-codec.0");
 
 	/* Peripheral 3 : PRCC K-clocks */
 	clk = clk_reg_prcc_kclk("p3_ssp0_kclk", "sspclk",
-			clkrst3_base, BIT(1), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(1), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "ssp0");
 
 	clk = clk_reg_prcc_kclk("p3_ssp1_kclk", "sspclk",
-			clkrst3_base, BIT(2), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(2), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "ssp1");
 
 	clk = clk_reg_prcc_kclk("p3_i2c0_kclk", "i2cclk",
-			clkrst3_base, BIT(3), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(3), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.0");
 
 	clk = clk_reg_prcc_kclk("p3_sdi2_kclk", "sdmmchclk",
-			clkrst3_base, BIT(4), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(4), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "sdi2");
 
 	clk = clk_reg_prcc_kclk("p3_ske_kclk", "rtc32k",
-			clkrst3_base, BIT(5), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(5), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "ske");
 	clk_register_clkdev(clk, NULL, "nmk-ske-keypad");
 
 	clk = clk_reg_prcc_kclk("p3_uart2_kclk", "uartclk",
-			clkrst3_base, BIT(6), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(6), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "uart2");
 
 	clk = clk_reg_prcc_kclk("p3_sdi5_kclk", "sdmmcclk",
-			clkrst3_base, BIT(7), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(7), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "sdi5");
 
 	clk = clk_reg_prcc_kclk("p3_i2c5_kclk", "i2cclk",
-			clkrst3_base, BIT(8), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(8), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.5");
 
 	clk = clk_reg_prcc_kclk("p3_i2c6_kclk", "i2cclk",
-			clkrst3_base, BIT(9), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(9), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "nmk-i2c.6");
 
 	clk = clk_reg_prcc_kclk("p3_uart3_kclk", "uartclk",
-			clkrst3_base, BIT(10), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(10), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "uart3");
 
 	clk = clk_reg_prcc_kclk("p3_uart4_kclk", "uartclk",
-			clkrst3_base, BIT(11), CLK_SET_RATE_GATE);
+			bases[CLKRST3_INDEX], BIT(11), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "uart4");
 
 	/* Peripheral 6 : PRCC K-clocks */
 	clk = clk_reg_prcc_kclk("p6_rng_kclk", "rngclk",
-			clkrst6_base, BIT(0), CLK_SET_RATE_GATE);
+			bases[CLKRST6_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "rng");
 }
diff --git a/drivers/clk/ux500/u9540_clk.c b/drivers/clk/ux500/u9540_clk.c
index 44794782e7e0..2138a4c8cbca 100644
--- a/drivers/clk/ux500/u9540_clk.c
+++ b/drivers/clk/ux500/u9540_clk.c
@@ -7,15 +7,12 @@
  * License terms: GNU General Public License (GPL) version 2
  */
 
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/platform_data/clk-ux500.h>
 #include "clk.h"
 
-void u9540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
-		    u32 clkrst5_base, u32 clkrst6_base)
+void u9540_clk_init(void)
 {
 	/* register clocks here */
 }
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index bc96f103bd7c..a3893ea2199d 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -13,8 +13,9 @@
  * ICST clock code from the ARM tree should probably be merged into this
  * file.
  */
-#include <linux/clk.h>
-#include <linux/clkdev.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/export.h>
 #include <linux/err.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
diff --git a/drivers/clk/versatile/clk-impd1.c b/drivers/clk/versatile/clk-impd1.c
index 1cc1330dc570..65c842a21c62 100644
--- a/drivers/clk/versatile/clk-impd1.c
+++ b/drivers/clk/versatile/clk-impd1.c
@@ -7,7 +7,6 @@
  * published by the Free Software Foundation.
  */
 #include <linux/clk-provider.h>
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/drivers/clk/versatile/clk-realview.c b/drivers/clk/versatile/clk-realview.c
index c8b523117fb7..86f70997d59d 100644
--- a/drivers/clk/versatile/clk-realview.c
+++ b/drivers/clk/versatile/clk-realview.c
@@ -6,7 +6,6 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -33,13 +32,13 @@ static const struct icst_params realview_oscvco_params = {
 	.idx2s		= icst307_idx2s,
 };
 
-static const struct clk_icst_desc __initdata realview_osc0_desc = {
+static const struct clk_icst_desc realview_osc0_desc __initconst = {
 	.params = &realview_oscvco_params,
 	.vco_offset = REALVIEW_SYS_OSC0_OFFSET,
 	.lock_offset = REALVIEW_SYS_LOCK_OFFSET,
 };
 
-static const struct clk_icst_desc __initdata realview_osc4_desc = {
+static const struct clk_icst_desc realview_osc4_desc __initconst = {
 	.params = &realview_oscvco_params,
 	.vco_offset = REALVIEW_SYS_OSC4_OFFSET,
 	.lock_offset = REALVIEW_SYS_LOCK_OFFSET,
diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c
index a96dd8e53fdb..a1cdef6b0f90 100644
--- a/drivers/clk/versatile/clk-sp810.c
+++ b/drivers/clk/versatile/clk-sp810.c
@@ -12,7 +12,8 @@
  */
 
 #include <linux/amba/sp810.h>
-#include <linux/clkdev.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/of.h>
@@ -32,12 +33,9 @@ struct clk_sp810_timerclken {
 
 struct clk_sp810 {
 	struct device_node *node;
-	int refclk_index, timclk_index;
 	void __iomem *base;
 	spinlock_t lock;
 	struct clk_sp810_timerclken timerclken[4];
-	struct clk *refclk;
-	struct clk *timclk;
 };
 
 static u8 clk_sp810_timerclken_get_parent(struct clk_hw *hw)
@@ -70,55 +68,7 @@ static int clk_sp810_timerclken_set_parent(struct clk_hw *hw, u8 index)
 	return 0;
 }
 
-/*
- * FIXME - setting the parent every time .prepare is invoked is inefficient.
- * This is better handled by a dedicated clock tree configuration mechanism at
- * init-time.  Revisit this later when such a mechanism exists
- */
-static int clk_sp810_timerclken_prepare(struct clk_hw *hw)
-{
-	struct clk_sp810_timerclken *timerclken = to_clk_sp810_timerclken(hw);
-	struct clk_sp810 *sp810 = timerclken->sp810;
-	struct clk *old_parent = __clk_get_parent(hw->clk);
-	struct clk *new_parent;
-
-	if (!sp810->refclk)
-		sp810->refclk = of_clk_get(sp810->node, sp810->refclk_index);
-
-	if (!sp810->timclk)
-		sp810->timclk = of_clk_get(sp810->node, sp810->timclk_index);
-
-	if (WARN_ON(IS_ERR(sp810->refclk) || IS_ERR(sp810->timclk)))
-		return -ENOENT;
-
-	/* Select fastest parent */
-	if (clk_get_rate(sp810->refclk) > clk_get_rate(sp810->timclk))
-		new_parent = sp810->refclk;
-	else
-		new_parent = sp810->timclk;
-
-	/* Switch the parent if necessary */
-	if (old_parent != new_parent) {
-		clk_prepare(new_parent);
-		clk_set_parent(hw->clk, new_parent);
-		clk_unprepare(old_parent);
-	}
-
-	return 0;
-}
-
-static void clk_sp810_timerclken_unprepare(struct clk_hw *hw)
-{
-	struct clk_sp810_timerclken *timerclken = to_clk_sp810_timerclken(hw);
-	struct clk_sp810 *sp810 = timerclken->sp810;
-
-	clk_put(sp810->timclk);
-	clk_put(sp810->refclk);
-}
-
 static const struct clk_ops clk_sp810_timerclken_ops = {
-	.prepare = clk_sp810_timerclken_prepare,
-	.unprepare = clk_sp810_timerclken_unprepare,
 	.get_parent = clk_sp810_timerclken_get_parent,
 	.set_parent = clk_sp810_timerclken_set_parent,
 };
@@ -128,8 +78,8 @@ static struct clk *clk_sp810_timerclken_of_get(struct of_phandle_args *clkspec,
 {
 	struct clk_sp810 *sp810 = data;
 
-	if (WARN_ON(clkspec->args_count != 1 || clkspec->args[0] >
-			ARRAY_SIZE(sp810->timerclken)))
+	if (WARN_ON(clkspec->args_count != 1 ||
+		    clkspec->args[0] >=	ARRAY_SIZE(sp810->timerclken)))
 		return NULL;
 
 	return sp810->timerclken[clkspec->args[0]].clk;
@@ -139,24 +89,18 @@ static void __init clk_sp810_of_setup(struct device_node *node)
 {
 	struct clk_sp810 *sp810 = kzalloc(sizeof(*sp810), GFP_KERNEL);
 	const char *parent_names[2];
+	int num = ARRAY_SIZE(parent_names);
 	char name[12];
 	struct clk_init_data init;
 	int i;
+	bool deprecated;
 
 	if (!sp810) {
 		pr_err("Failed to allocate memory for SP810!\n");
 		return;
 	}
 
-	sp810->refclk_index = of_property_match_string(node, "clock-names",
-			"refclk");
-	parent_names[0] = of_clk_get_parent_name(node, sp810->refclk_index);
-
-	sp810->timclk_index = of_property_match_string(node, "clock-names",
-			"timclk");
-	parent_names[1] = of_clk_get_parent_name(node, sp810->timclk_index);
-
-	if (!parent_names[0] || !parent_names[1]) {
+	if (of_clk_parent_fill(node, parent_names, num) != num) {
 		pr_warn("Failed to obtain parent clocks for SP810!\n");
 		return;
 	}
@@ -169,7 +113,9 @@ static void __init clk_sp810_of_setup(struct device_node *node)
 	init.ops = &clk_sp810_timerclken_ops;
 	init.flags = CLK_IS_BASIC;
 	init.parent_names = parent_names;
-	init.num_parents = ARRAY_SIZE(parent_names);
+	init.num_parents = num;
+
+	deprecated = !of_find_property(node, "assigned-clock-parents", NULL);
 
 	for (i = 0; i < ARRAY_SIZE(sp810->timerclken); i++) {
 		snprintf(name, ARRAY_SIZE(name), "timerclken%d", i);
@@ -178,6 +124,15 @@ static void __init clk_sp810_of_setup(struct device_node *node)
 		sp810->timerclken[i].channel = i;
 		sp810->timerclken[i].hw.init = &init;
 
+		/*
+		 * If DT isn't setting the parent, force it to be
+		 * the 1 MHz clock without going through the framework.
+		 * We do this before clk_register() so that it can determine
+		 * the parent and setup the tree properly.
+		 */
+		if (deprecated)
+			init.ops->set_parent(&sp810->timerclken[i].hw, 1);
+
 		sp810->timerclken[i].clk = clk_register(NULL,
 				&sp810->timerclken[i].hw);
 		WARN_ON(IS_ERR(sp810->timerclken[i].clk));
diff --git a/drivers/clk/versatile/clk-versatile.c b/drivers/clk/versatile/clk-versatile.c
index 7a4f8635bd1e..a89a927567e0 100644
--- a/drivers/clk/versatile/clk-versatile.c
+++ b/drivers/clk/versatile/clk-versatile.c
@@ -8,8 +8,6 @@
  * published by the Free Software Foundation.
  */
 #include <linux/clk-provider.h>
-#include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -35,7 +33,7 @@ static const struct icst_params cp_auxosc_params = {
 	.idx2s		= icst525_idx2s,
 };
 
-static const struct clk_icst_desc __initdata cm_auxosc_desc = {
+static const struct clk_icst_desc cm_auxosc_desc __initconst = {
 	.params = &cp_auxosc_params,
 	.vco_offset = 0x1c,
 	.lock_offset = INTEGRATOR_HDR_LOCK_OFFSET,
diff --git a/drivers/clk/zte/Makefile b/drivers/clk/zte/Makefile
index 95b707c18108..74005aa322a2 100644
--- a/drivers/clk/zte/Makefile
+++ b/drivers/clk/zte/Makefile
@@ -1,2 +1,2 @@
-obj-y := clk-pll.o
+obj-y := clk.o
 obj-$(CONFIG_SOC_ZX296702) += clk-zx296702.o
diff --git a/drivers/clk/zte/clk-zx296702.c b/drivers/clk/zte/clk-zx296702.c
index 929d033594af..ebd20d852e73 100644
--- a/drivers/clk/zte/clk-zx296702.c
+++ b/drivers/clk/zte/clk-zx296702.c
@@ -36,10 +36,21 @@ static struct clk_onecell_data lsp1clk_data;
 #define CLK_MUX1		(topcrm_base + 0x8c)
 
 #define CLK_SDMMC1		(lsp0crpm_base + 0x0c)
+#define CLK_GPIO		(lsp0crpm_base + 0x2c)
+#define CLK_SPDIF0		(lsp0crpm_base + 0x10)
+#define SPDIF0_DIV		(lsp0crpm_base + 0x14)
+#define CLK_I2S0		(lsp0crpm_base + 0x18)
+#define I2S0_DIV		(lsp0crpm_base + 0x1c)
+#define CLK_I2S1		(lsp0crpm_base + 0x20)
+#define I2S1_DIV		(lsp0crpm_base + 0x24)
+#define CLK_I2S2		(lsp0crpm_base + 0x34)
+#define I2S2_DIV		(lsp0crpm_base + 0x38)
 
 #define CLK_UART0		(lsp1crpm_base + 0x20)
 #define CLK_UART1		(lsp1crpm_base + 0x24)
 #define CLK_SDMMC0		(lsp1crpm_base + 0x2c)
+#define CLK_SPDIF1		(lsp1crpm_base + 0x30)
+#define SPDIF1_DIV		(lsp1crpm_base + 0x34)
 
 static const struct zx_pll_config pll_a9_config[] = {
 	{ .rate = 700000000, .cfg0 = 0x800405d1, .cfg1 = 0x04555555 },
@@ -72,104 +83,119 @@ static const struct clk_div_table sec_wclk_divider[] = {
 	{ /* sentinel */ }
 };
 
-static const char * matrix_aclk_sel[] = {
+static const char * const matrix_aclk_sel[] = {
 	"pll_mm0_198M",
 	"osc",
 	"clk_148M5",
 	"pll_lsp_104M",
 };
 
-static const char * a9_wclk_sel[] = {
+static const char * const a9_wclk_sel[] = {
 	"pll_a9",
 	"osc",
 	"clk_500",
 	"clk_250",
 };
 
-static const char * a9_as1_aclk_sel[] = {
+static const char * const a9_as1_aclk_sel[] = {
 	"clk_250",
 	"osc",
 	"pll_mm0_396M",
 	"pll_mac_333M",
 };
 
-static const char * a9_trace_clkin_sel[] = {
+static const char * const a9_trace_clkin_sel[] = {
 	"clk_74M25",
 	"pll_mm1_108M",
 	"clk_125",
 	"clk_148M5",
 };
 
-static const char * decppu_aclk_sel[] = {
+static const char * const decppu_aclk_sel[] = {
 	"clk_250",
 	"pll_mm0_198M",
 	"pll_lsp_104M",
 	"pll_audio_294M912",
 };
 
-static const char * vou_main_wclk_sel[] = {
+static const char * const vou_main_wclk_sel[] = {
 	"clk_148M5",
 	"clk_74M25",
 	"clk_27",
 	"pll_mm1_54M",
 };
 
-static const char * vou_scaler_wclk_sel[] = {
+static const char * const vou_scaler_wclk_sel[] = {
 	"clk_250",
 	"pll_mac_333M",
 	"pll_audio_294M912",
 	"pll_mm0_198M",
 };
 
-static const char * r2d_wclk_sel[] = {
+static const char * const r2d_wclk_sel[] = {
 	"pll_audio_294M912",
 	"pll_mac_333M",
 	"pll_a9_350M",
 	"pll_mm0_396M",
 };
 
-static const char * ddr_wclk_sel[] = {
+static const char * const ddr_wclk_sel[] = {
 	"pll_mac_333M",
 	"pll_ddr_266M",
 	"pll_audio_294M912",
 	"pll_mm0_198M",
 };
 
-static const char * nand_wclk_sel[] = {
+static const char * const nand_wclk_sel[] = {
 	"pll_lsp_104M",
 	"osc",
 };
 
-static const char * lsp_26_wclk_sel[] = {
+static const char * const lsp_26_wclk_sel[] = {
 	"pll_lsp_26M",
 	"osc",
 };
 
-static const char * vl0_sel[] = {
+static const char * const vl0_sel[] = {
 	"vou_main_channel_div",
 	"vou_aux_channel_div",
 };
 
-static const char * hdmi_sel[] = {
+static const char * const hdmi_sel[] = {
 	"vou_main_channel_wclk",
 	"vou_aux_channel_wclk",
 };
 
-static const char * sdmmc0_wclk_sel[] = {
+static const char * const sdmmc0_wclk_sel[] = {
 	"lsp1_104M_wclk",
 	"lsp1_26M_wclk",
 };
 
-static const char * sdmmc1_wclk_sel[] = {
+static const char * const sdmmc1_wclk_sel[] = {
 	"lsp0_104M_wclk",
 	"lsp0_26M_wclk",
 };
 
-static const char * uart_wclk_sel[] = {
+static const char * const uart_wclk_sel[] = {
 	"lsp1_104M_wclk",
 	"lsp1_26M_wclk",
 };
 
+static const char * const spdif0_wclk_sel[] = {
+	"lsp0_104M_wclk",
+	"lsp0_26M_wclk",
+};
+
+static const char * const spdif1_wclk_sel[] = {
+	"lsp1_104M_wclk",
+	"lsp1_26M_wclk",
+};
+
+static const char * const i2s_wclk_sel[] = {
+	"lsp0_104M_wclk",
+	"lsp0_26M_wclk",
+};
+
 static inline struct clk *zx_divtbl(const char *name, const char *parent,
 				    void __iomem *reg, u8 shift, u8 width,
 				    const struct clk_div_table *table)
@@ -185,7 +211,7 @@ static inline struct clk *zx_div(const char *name, const char *parent,
 				    reg, shift, width, 0, &reg_lock);
 }
 
-static inline struct clk *zx_mux(const char *name, const char **parents,
+static inline struct clk *zx_mux(const char *name, const char * const *parents,
 		int num_parents, void __iomem *reg, u8 shift, u8 width)
 {
 	return clk_register_mux(NULL, name, parents, num_parents,
@@ -196,7 +222,7 @@ static inline struct clk *zx_gate(const char *name, const char *parent,
 				  void __iomem *reg, u8 shift)
 {
 	return clk_register_gate(NULL, name, parent, CLK_IGNORE_UNUSED,
-				 reg, shift, 0, &reg_lock);
+				 reg, shift, CLK_SET_RATE_PARENT, &reg_lock);
 }
 
 static void __init zx296702_top_clocks_init(struct device_node *np)
@@ -585,7 +611,57 @@ static void __init zx296702_lsp0_clocks_init(struct device_node *np)
 	clk[ZX296702_SDMMC1_WCLK] =
 		zx_gate("sdmmc1_wclk", "sdmmc1_wclk_div", CLK_SDMMC1, 1);
 	clk[ZX296702_SDMMC1_PCLK] =
-		zx_gate("sdmmc1_pclk", "lsp1_apb_pclk", CLK_SDMMC1, 0);
+		zx_gate("sdmmc1_pclk", "lsp0_apb_pclk", CLK_SDMMC1, 0);
+
+	clk[ZX296702_GPIO_CLK] =
+		zx_gate("gpio_clk", "lsp0_apb_pclk", CLK_GPIO, 0);
+
+	/* SPDIF */
+	clk[ZX296702_SPDIF0_WCLK_MUX] =
+		zx_mux("spdif0_wclk_mux", spdif0_wclk_sel,
+				ARRAY_SIZE(spdif0_wclk_sel), CLK_SPDIF0, 4, 1);
+	clk[ZX296702_SPDIF0_WCLK] =
+		zx_gate("spdif0_wclk", "spdif0_wclk_mux", CLK_SPDIF0, 1);
+	clk[ZX296702_SPDIF0_PCLK] =
+		zx_gate("spdif0_pclk", "lsp0_apb_pclk", CLK_SPDIF0, 0);
+
+	clk[ZX296702_SPDIF0_DIV] =
+		clk_register_zx_audio("spdif0_div", "spdif0_wclk", 0,
+				SPDIF0_DIV);
+
+	/* I2S */
+	clk[ZX296702_I2S0_WCLK_MUX] =
+		zx_mux("i2s0_wclk_mux", i2s_wclk_sel,
+				ARRAY_SIZE(i2s_wclk_sel), CLK_I2S0, 4, 1);
+	clk[ZX296702_I2S0_WCLK] =
+		zx_gate("i2s0_wclk", "i2s0_wclk_mux", CLK_I2S0, 1);
+	clk[ZX296702_I2S0_PCLK] =
+		zx_gate("i2s0_pclk", "lsp0_apb_pclk", CLK_I2S0, 0);
+
+	clk[ZX296702_I2S0_DIV] =
+		clk_register_zx_audio("i2s0_div", "i2s0_wclk", 0, I2S0_DIV);
+
+	clk[ZX296702_I2S1_WCLK_MUX] =
+		zx_mux("i2s1_wclk_mux", i2s_wclk_sel,
+				ARRAY_SIZE(i2s_wclk_sel), CLK_I2S1, 4, 1);
+	clk[ZX296702_I2S1_WCLK] =
+		zx_gate("i2s1_wclk", "i2s1_wclk_mux", CLK_I2S1, 1);
+	clk[ZX296702_I2S1_PCLK] =
+		zx_gate("i2s1_pclk", "lsp0_apb_pclk", CLK_I2S1, 0);
+
+	clk[ZX296702_I2S1_DIV] =
+		clk_register_zx_audio("i2s1_div", "i2s1_wclk", 0, I2S1_DIV);
+
+	clk[ZX296702_I2S2_WCLK_MUX] =
+		zx_mux("i2s2_wclk_mux", i2s_wclk_sel,
+				ARRAY_SIZE(i2s_wclk_sel), CLK_I2S2, 4, 1);
+	clk[ZX296702_I2S2_WCLK] =
+		zx_gate("i2s2_wclk", "i2s2_wclk_mux", CLK_I2S2, 1);
+	clk[ZX296702_I2S2_PCLK] =
+		zx_gate("i2s2_pclk", "lsp0_apb_pclk", CLK_I2S2, 0);
+
+	clk[ZX296702_I2S2_DIV] =
+		clk_register_zx_audio("i2s2_div", "i2s2_wclk", 0, I2S2_DIV);
 
 	for (i = 0; i < ARRAY_SIZE(lsp0clk); i++) {
 		if (IS_ERR(clk[i])) {
@@ -641,6 +717,18 @@ static void __init zx296702_lsp1_clocks_init(struct device_node *np)
 	clk[ZX296702_SDMMC0_PCLK] =
 		zx_gate("sdmmc0_pclk", "lsp1_apb_pclk", CLK_SDMMC0, 0);
 
+	clk[ZX296702_SPDIF1_WCLK_MUX] =
+		zx_mux("spdif1_wclk_mux", spdif1_wclk_sel,
+				ARRAY_SIZE(spdif1_wclk_sel), CLK_SPDIF1, 4, 1);
+	clk[ZX296702_SPDIF1_WCLK] =
+		zx_gate("spdif1_wclk", "spdif1_wclk_mux", CLK_SPDIF1, 1);
+	clk[ZX296702_SPDIF1_PCLK] =
+		zx_gate("spdif1_pclk", "lsp1_apb_pclk", CLK_SPDIF1, 0);
+
+	clk[ZX296702_SPDIF1_DIV] =
+		clk_register_zx_audio("spdif1_div", "spdif1_wclk", 0,
+				SPDIF1_DIV);
+
 	for (i = 0; i < ARRAY_SIZE(lsp1clk); i++) {
 		if (IS_ERR(clk[i])) {
 			pr_err("zx296702 clk %d: register failed with %ld\n",
diff --git a/drivers/clk/zte/clk-pll.c b/drivers/clk/zte/clk.c
index c3b221ae6cd7..7c73c538c43d 100644
--- a/drivers/clk/zte/clk-pll.c
+++ b/drivers/clk/zte/clk.c
@@ -13,10 +13,12 @@
 #include <linux/iopoll.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <asm/div64.h>
 
 #include "clk.h"
 
 #define to_clk_zx_pll(_hw) container_of(_hw, struct clk_zx_pll, hw)
+#define to_clk_zx_audio(_hw) container_of(_hw, struct clk_zx_audio, hw)
 
 #define CFG0_CFG1_OFFSET 4
 #define LOCK_FLAG BIT(30)
@@ -141,8 +143,9 @@ static const struct clk_ops zx_pll_ops = {
 };
 
 struct clk *clk_register_zx_pll(const char *name, const char *parent_name,
-	unsigned long flags, void __iomem *reg_base,
-	const struct zx_pll_config *lookup_table, int count, spinlock_t *lock)
+				unsigned long flags, void __iomem *reg_base,
+				const struct zx_pll_config *lookup_table,
+				int count, spinlock_t *lock)
 {
 	struct clk_zx_pll *zx_pll;
 	struct clk *clk;
@@ -170,3 +173,137 @@ struct clk *clk_register_zx_pll(const char *name, const char *parent_name,
 
 	return clk;
 }
+
+#define BPAR 1000000
+static u32 calc_reg(u32 parent_rate, u32 rate)
+{
+	u32 sel, integ, fra_div, tmp;
+	u64 tmp64 = (u64)parent_rate * BPAR;
+
+	do_div(tmp64, rate);
+	integ = (u32)tmp64 / BPAR;
+	integ = integ >> 1;
+
+	tmp = (u32)tmp64 % BPAR;
+	sel = tmp / BPAR;
+
+	tmp = tmp % BPAR;
+	fra_div = tmp * 0xff / BPAR;
+	tmp = (sel << 24) | (integ << 16) | (0xff << 8) | fra_div;
+
+	/* Set I2S integer divider as 1. This bit is reserved for SPDIF
+	 * and do no harm.
+	 */
+	tmp |= BIT(28);
+	return tmp;
+}
+
+static u32 calc_rate(u32 reg, u32 parent_rate)
+{
+	u32 sel, integ, fra_div, tmp;
+	u64 tmp64 = (u64)parent_rate * BPAR;
+
+	tmp = reg;
+	sel = (tmp >> 24) & BIT(0);
+	integ = (tmp >> 16) & 0xff;
+	fra_div = tmp & 0xff;
+
+	tmp = fra_div * BPAR;
+	tmp = tmp / 0xff;
+	tmp += sel * BPAR;
+	tmp += 2 * integ * BPAR;
+	do_div(tmp64, tmp);
+
+	return (u32)tmp64;
+}
+
+static unsigned long zx_audio_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw);
+	u32 reg;
+
+	reg = readl_relaxed(zx_audio->reg_base);
+	return calc_rate(reg, parent_rate);
+}
+
+static long zx_audio_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *prate)
+{
+	u32 reg;
+
+	if (rate * 2 > *prate)
+		return -EINVAL;
+
+	reg = calc_reg(*prate, rate);
+	return calc_rate(reg, *prate);
+}
+
+static int zx_audio_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate)
+{
+	struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw);
+	u32 reg;
+
+	reg = calc_reg(parent_rate, rate);
+	writel_relaxed(reg, zx_audio->reg_base);
+
+	return 0;
+}
+
+#define ZX_AUDIO_EN BIT(25)
+static int zx_audio_enable(struct clk_hw *hw)
+{
+	struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw);
+	u32 reg;
+
+	reg = readl_relaxed(zx_audio->reg_base);
+	writel_relaxed(reg & ~ZX_AUDIO_EN, zx_audio->reg_base);
+	return 0;
+}
+
+static void zx_audio_disable(struct clk_hw *hw)
+{
+	struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw);
+	u32 reg;
+
+	reg = readl_relaxed(zx_audio->reg_base);
+	writel_relaxed(reg | ZX_AUDIO_EN, zx_audio->reg_base);
+}
+
+static const struct clk_ops zx_audio_ops = {
+	.recalc_rate = zx_audio_recalc_rate,
+	.round_rate = zx_audio_round_rate,
+	.set_rate = zx_audio_set_rate,
+	.enable = zx_audio_enable,
+	.disable = zx_audio_disable,
+};
+
+struct clk *clk_register_zx_audio(const char *name,
+				  const char * const parent_name,
+				  unsigned long flags,
+				  void __iomem *reg_base)
+{
+	struct clk_zx_audio *zx_audio;
+	struct clk *clk;
+	struct clk_init_data init;
+
+	zx_audio = kzalloc(sizeof(*zx_audio), GFP_KERNEL);
+	if (!zx_audio)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &zx_audio_ops;
+	init.flags = flags;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	zx_audio->reg_base = reg_base;
+	zx_audio->hw.init = &init;
+
+	clk = clk_register(NULL, &zx_audio->hw);
+	if (IS_ERR(clk))
+		kfree(zx_audio);
+
+	return clk;
+}
diff --git a/drivers/clk/zte/clk.h b/drivers/clk/zte/clk.h
index 0914a82d0535..65ae08b818d3 100644
--- a/drivers/clk/zte/clk.h
+++ b/drivers/clk/zte/clk.h
@@ -29,4 +29,13 @@ struct clk_zx_pll {
 struct clk *clk_register_zx_pll(const char *name, const char *parent_name,
 	unsigned long flags, void __iomem *reg_base,
 	const struct zx_pll_config *lookup_table, int count, spinlock_t *lock);
+
+struct clk_zx_audio {
+	struct clk_hw hw;
+	void __iomem *reg_base;
+};
+
+struct clk *clk_register_zx_audio(const char *name,
+				  const char * const parent_name,
+				  unsigned long flags, void __iomem *reg_base);
 #endif
diff --git a/drivers/clk/zynq/Makefile b/drivers/clk/zynq/Makefile
index 156d923f4fa9..0afc2e7cc5c1 100644
--- a/drivers/clk/zynq/Makefile
+++ b/drivers/clk/zynq/Makefile
@@ -1,3 +1,3 @@
 # Zynq clock specific Makefile
 
-obj-$(CONFIG_ARCH_ZYNQ)	+= clkc.o pll.o
+obj-y	+= clkc.o pll.o
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index de614384bb44..38a65c3e62fc 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/clk/zynq.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 4e57730e0be4..a7726db13abb 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -111,6 +111,10 @@ config CLKSRC_LPC32XX
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 
+config CLKSRC_PISTACHIO
+	bool
+	select CLKSRC_OF
+
 config CLKSRC_STM32
 	bool "Clocksource for STM32 SoCs" if !ARCH_STM32
 	depends on OF && ARM && (ARCH_STM32 || COMPILE_TEST)
@@ -277,7 +281,7 @@ config CLKSRC_MIPS_GIC
 
 config CLKSRC_PXA
 	def_bool y if ARCH_PXA || ARCH_SA1100
-	select CLKSRC_OF if USE_OF
+	select CLKSRC_OF if OF
 	help
 	  This enables OST0 support available on PXA and SA-11x0
 	  platforms.
@@ -293,4 +297,12 @@ config CLKSRC_IMX_GPT
 	depends on ARM && CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 
+config CLKSRC_ST_LPC
+	bool
+	depends on ARCH_STI
+	select CLKSRC_OF if OF
+	help
+	  Enable this option to use the Low Power controller timer
+	  as clocksource.
+
 endmenu
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index f228354961ca..5c00863c3e33 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
 obj-$(CONFIG_CLKSRC_QCOM)	+= qcom-timer.o
 obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
+obj-$(CONFIG_CLKSRC_PISTACHIO)	+= time-pistachio.o
 
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
 obj-$(CONFIG_ARM_GLOBAL_TIMER)		+= arm_global_timer.o
@@ -60,3 +61,4 @@ obj-$(CONFIG_ASM9260_TIMER)		+= asm9260_timer.o
 obj-$(CONFIG_H8300)			+= h8300_timer8.o
 obj-$(CONFIG_H8300_TMR16)		+= h8300_timer16.o
 obj-$(CONFIG_H8300_TPU)			+= h8300_tpu.o
+obj-$(CONFIG_CLKSRC_ST_LPC)		+= clksrc_st_lpc.o
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 0aa135ddbf80..d6e3e49399dd 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -181,44 +181,36 @@ static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id)
 	return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt);
 }
 
-static __always_inline void timer_set_mode(const int access, int mode,
-				  struct clock_event_device *clk)
+static __always_inline int timer_shutdown(const int access,
+					  struct clock_event_device *clk)
 {
 	unsigned long ctrl;
-	switch (mode) {
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
-		ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
-		break;
-	default:
-		break;
-	}
+
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+	ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+
+	return 0;
 }
 
-static void arch_timer_set_mode_virt(enum clock_event_mode mode,
-				     struct clock_event_device *clk)
+static int arch_timer_shutdown_virt(struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode, clk);
+	return timer_shutdown(ARCH_TIMER_VIRT_ACCESS, clk);
 }
 
-static void arch_timer_set_mode_phys(enum clock_event_mode mode,
-				     struct clock_event_device *clk)
+static int arch_timer_shutdown_phys(struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode, clk);
+	return timer_shutdown(ARCH_TIMER_PHYS_ACCESS, clk);
 }
 
-static void arch_timer_set_mode_virt_mem(enum clock_event_mode mode,
-					 struct clock_event_device *clk)
+static int arch_timer_shutdown_virt_mem(struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_MEM_VIRT_ACCESS, mode, clk);
+	return timer_shutdown(ARCH_TIMER_MEM_VIRT_ACCESS, clk);
 }
 
-static void arch_timer_set_mode_phys_mem(enum clock_event_mode mode,
-					 struct clock_event_device *clk)
+static int arch_timer_shutdown_phys_mem(struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_MEM_PHYS_ACCESS, mode, clk);
+	return timer_shutdown(ARCH_TIMER_MEM_PHYS_ACCESS, clk);
 }
 
 static __always_inline void set_next_event(const int access, unsigned long evt,
@@ -273,11 +265,11 @@ static void __arch_timer_setup(unsigned type,
 		clk->cpumask = cpumask_of(smp_processor_id());
 		if (arch_timer_use_virtual) {
 			clk->irq = arch_timer_ppi[VIRT_PPI];
-			clk->set_mode = arch_timer_set_mode_virt;
+			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_next_event = arch_timer_set_next_event_virt;
 		} else {
 			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
-			clk->set_mode = arch_timer_set_mode_phys;
+			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_next_event = arch_timer_set_next_event_phys;
 		}
 	} else {
@@ -286,17 +278,17 @@ static void __arch_timer_setup(unsigned type,
 		clk->rating = 400;
 		clk->cpumask = cpu_all_mask;
 		if (arch_timer_mem_use_virtual) {
-			clk->set_mode = arch_timer_set_mode_virt_mem;
+			clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
 			clk->set_next_event =
 				arch_timer_set_next_event_virt_mem;
 		} else {
-			clk->set_mode = arch_timer_set_mode_phys_mem;
+			clk->set_state_shutdown = arch_timer_shutdown_phys_mem;
 			clk->set_next_event =
 				arch_timer_set_next_event_phys_mem;
 		}
 	}
 
-	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, clk);
+	clk->set_state_shutdown(clk);
 
 	clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
 }
@@ -506,7 +498,7 @@ static void arch_timer_stop(struct clock_event_device *clk)
 			disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
 	}
 
-	clk->set_mode(CLOCK_EVT_MODE_UNUSED, clk);
+	clk->set_state_shutdown(clk);
 }
 
 static int arch_timer_cpu_notify(struct notifier_block *self,
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index e6833771a716..29ea50ac366a 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -107,26 +107,21 @@ static void gt_compare_set(unsigned long delta, int periodic)
 	writel(ctrl, gt_base + GT_CONTROL);
 }
 
-static void gt_clockevent_set_mode(enum clock_event_mode mode,
-				   struct clock_event_device *clk)
+static int gt_clockevent_shutdown(struct clock_event_device *evt)
 {
 	unsigned long ctrl;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		gt_compare_set(DIV_ROUND_CLOSEST(gt_clk_rate, HZ), 1);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl = readl(gt_base + GT_CONTROL);
-		ctrl &= ~(GT_CONTROL_COMP_ENABLE |
-				GT_CONTROL_IRQ_ENABLE | GT_CONTROL_AUTO_INC);
-		writel(ctrl, gt_base + GT_CONTROL);
-		break;
-	default:
-		break;
-	}
+	ctrl = readl(gt_base + GT_CONTROL);
+	ctrl &= ~(GT_CONTROL_COMP_ENABLE | GT_CONTROL_IRQ_ENABLE |
+		  GT_CONTROL_AUTO_INC);
+	writel(ctrl, gt_base + GT_CONTROL);
+	return 0;
+}
+
+static int gt_clockevent_set_periodic(struct clock_event_device *evt)
+{
+	gt_compare_set(DIV_ROUND_CLOSEST(gt_clk_rate, HZ), 1);
+	return 0;
 }
 
 static int gt_clockevent_set_next_event(unsigned long evt,
@@ -155,7 +150,7 @@ static irqreturn_t gt_clockevent_interrupt(int irq, void *dev_id)
 	 *	the Global Timer flag _after_ having incremented
 	 *	the Comparator register	value to a higher value.
 	 */
-	if (evt->mode == CLOCK_EVT_MODE_ONESHOT)
+	if (clockevent_state_oneshot(evt))
 		gt_compare_set(ULONG_MAX, 0);
 
 	writel_relaxed(GT_INT_STATUS_EVENT_FLAG, gt_base + GT_INT_STATUS);
@@ -171,7 +166,9 @@ static int gt_clockevents_init(struct clock_event_device *clk)
 	clk->name = "arm_global_timer";
 	clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
 		CLOCK_EVT_FEAT_PERCPU;
-	clk->set_mode = gt_clockevent_set_mode;
+	clk->set_state_shutdown = gt_clockevent_shutdown;
+	clk->set_state_periodic = gt_clockevent_set_periodic;
+	clk->set_state_oneshot = gt_clockevent_shutdown;
 	clk->set_next_event = gt_clockevent_set_next_event;
 	clk->cpumask = cpumask_of(cpu);
 	clk->rating = 300;
@@ -184,7 +181,7 @@ static int gt_clockevents_init(struct clock_event_device *clk)
 
 static void gt_clockevents_stop(struct clock_event_device *clk)
 {
-	gt_clockevent_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
+	gt_clockevent_shutdown(clk);
 	disable_percpu_irq(clk->irq);
 }
 
diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c
index 4c2ba59897e8..217438d39eb3 100644
--- a/drivers/clocksource/asm9260_timer.c
+++ b/drivers/clocksource/asm9260_timer.c
@@ -120,38 +120,52 @@ static int asm9260_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void asm9260_timer_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *evt)
+static inline void __asm9260_timer_shutdown(struct clock_event_device *evt)
 {
 	/* stop timer0 */
 	writel_relaxed(BM_C0_EN, priv.base + HW_TCR + CLR_REG);
+}
+
+static int asm9260_timer_shutdown(struct clock_event_device *evt)
+{
+	__asm9260_timer_shutdown(evt);
+	return 0;
+}
+
+static int asm9260_timer_set_oneshot(struct clock_event_device *evt)
+{
+	__asm9260_timer_shutdown(evt);
+
+	/* enable reset and stop on match */
+	writel_relaxed(BM_MCR_RES_EN(0) | BM_MCR_STOP_EN(0),
+		       priv.base + HW_MCR + SET_REG);
+	return 0;
+}
+
+static int asm9260_timer_set_periodic(struct clock_event_device *evt)
+{
+	__asm9260_timer_shutdown(evt);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* disable reset and stop on match */
-		writel_relaxed(BM_MCR_RES_EN(0) | BM_MCR_STOP_EN(0),
-				priv.base + HW_MCR + CLR_REG);
-		/* configure match count for TC0 */
-		writel_relaxed(priv.ticks_per_jiffy, priv.base + HW_MR0);
-		/* enable TC0 */
-		writel_relaxed(BM_C0_EN, priv.base + HW_TCR + SET_REG);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* enable reset and stop on match */
-		writel_relaxed(BM_MCR_RES_EN(0) | BM_MCR_STOP_EN(0),
-				priv.base + HW_MCR + SET_REG);
-		break;
-	default:
-		break;
-	}
+	/* disable reset and stop on match */
+	writel_relaxed(BM_MCR_RES_EN(0) | BM_MCR_STOP_EN(0),
+		       priv.base + HW_MCR + CLR_REG);
+	/* configure match count for TC0 */
+	writel_relaxed(priv.ticks_per_jiffy, priv.base + HW_MR0);
+	/* enable TC0 */
+	writel_relaxed(BM_C0_EN, priv.base + HW_TCR + SET_REG);
+	return 0;
 }
 
 static struct clock_event_device event_dev = {
-	.name		= DRIVER_NAME,
-	.rating		= 200,
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event	= asm9260_timer_set_next_event,
-	.set_mode	= asm9260_timer_set_mode,
+	.name			= DRIVER_NAME,
+	.rating			= 200,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= asm9260_timer_set_next_event,
+	.set_state_shutdown	= asm9260_timer_shutdown,
+	.set_state_periodic	= asm9260_timer_set_periodic,
+	.set_state_oneshot	= asm9260_timer_set_oneshot,
+	.tick_resume		= asm9260_timer_shutdown,
 };
 
 static irqreturn_t asm9260_timer_interrupt(int irq, void *dev_id)
diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index 26ed331b1aad..6f2822928963 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/drivers/clocksource/bcm2835_timer.c
@@ -54,21 +54,6 @@ static u64 notrace bcm2835_sched_read(void)
 	return readl_relaxed(system_clock);
 }
 
-static void bcm2835_time_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *evt_dev)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	default:
-		WARN(1, "%s: unhandled event mode %d\n", __func__, mode);
-		break;
-	}
-}
-
 static int bcm2835_time_set_next_event(unsigned long event,
 	struct clock_event_device *evt_dev)
 {
@@ -129,7 +114,6 @@ static void __init bcm2835_timer_init(struct device_node *node)
 	timer->evt.name = node->name;
 	timer->evt.rating = 300;
 	timer->evt.features = CLOCK_EVT_FEAT_ONESHOT;
-	timer->evt.set_mode = bcm2835_time_set_mode;
 	timer->evt.set_next_event = bcm2835_time_set_next_event;
 	timer->evt.cpumask = cpumask_of(0);
 	timer->act.name = node->name;
diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c
index f1e33d08dd83..e717e87df9bc 100644
--- a/drivers/clocksource/bcm_kona_timer.c
+++ b/drivers/clocksource/bcm_kona_timer.c
@@ -127,25 +127,18 @@ static int kona_timer_set_next_event(unsigned long clc,
 	return 0;
 }
 
-static void kona_timer_set_mode(enum clock_event_mode mode,
-			     struct clock_event_device *unused)
+static int kona_timer_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* by default mode is one shot don't do any thing */
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		kona_timer_disable_and_clear(timers.tmr_regs);
-	}
+	kona_timer_disable_and_clear(timers.tmr_regs);
+	return 0;
 }
 
 static struct clock_event_device kona_clockevent_timer = {
 	.name = "timer 1",
 	.features = CLOCK_EVT_FEAT_ONESHOT,
 	.set_next_event = kona_timer_set_next_event,
-	.set_mode = kona_timer_set_mode
+	.set_state_shutdown = kona_timer_shutdown,
+	.tick_resume = kona_timer_shutdown,
 };
 
 static void __init kona_timer_clockevents_init(void)
diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index 510c8a1d37b3..9be6018bd2b8 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -16,7 +16,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/clk-provider.h>
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
 #include <linux/of_address.h>
@@ -191,40 +190,42 @@ static int ttc_set_next_event(unsigned long cycles,
 }
 
 /**
- * ttc_set_mode - Sets the mode of timer
+ * ttc_set_{shutdown|oneshot|periodic} - Sets the state of timer
  *
- * @mode:	Mode to be set
  * @evt:	Address of clock event instance
  **/
-static void ttc_set_mode(enum clock_event_mode mode,
-					struct clock_event_device *evt)
+static int ttc_shutdown(struct clock_event_device *evt)
 {
 	struct ttc_timer_clockevent *ttce = to_ttc_timer_clkevent(evt);
 	struct ttc_timer *timer = &ttce->ttc;
 	u32 ctrl_reg;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		ttc_set_interval(timer, DIV_ROUND_CLOSEST(ttce->ttc.freq,
-						PRESCALE * HZ));
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl_reg = readl_relaxed(timer->base_addr +
-					TTC_CNT_CNTRL_OFFSET);
-		ctrl_reg |= TTC_CNT_CNTRL_DISABLE_MASK;
-		writel_relaxed(ctrl_reg,
-				timer->base_addr + TTC_CNT_CNTRL_OFFSET);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		ctrl_reg = readl_relaxed(timer->base_addr +
-					TTC_CNT_CNTRL_OFFSET);
-		ctrl_reg &= ~TTC_CNT_CNTRL_DISABLE_MASK;
-		writel_relaxed(ctrl_reg,
-				timer->base_addr + TTC_CNT_CNTRL_OFFSET);
-		break;
-	}
+	ctrl_reg = readl_relaxed(timer->base_addr + TTC_CNT_CNTRL_OFFSET);
+	ctrl_reg |= TTC_CNT_CNTRL_DISABLE_MASK;
+	writel_relaxed(ctrl_reg, timer->base_addr + TTC_CNT_CNTRL_OFFSET);
+	return 0;
+}
+
+static int ttc_set_periodic(struct clock_event_device *evt)
+{
+	struct ttc_timer_clockevent *ttce = to_ttc_timer_clkevent(evt);
+	struct ttc_timer *timer = &ttce->ttc;
+
+	ttc_set_interval(timer,
+			 DIV_ROUND_CLOSEST(ttce->ttc.freq, PRESCALE * HZ));
+	return 0;
+}
+
+static int ttc_resume(struct clock_event_device *evt)
+{
+	struct ttc_timer_clockevent *ttce = to_ttc_timer_clkevent(evt);
+	struct ttc_timer *timer = &ttce->ttc;
+	u32 ctrl_reg;
+
+	ctrl_reg = readl_relaxed(timer->base_addr + TTC_CNT_CNTRL_OFFSET);
+	ctrl_reg &= ~TTC_CNT_CNTRL_DISABLE_MASK;
+	writel_relaxed(ctrl_reg, timer->base_addr + TTC_CNT_CNTRL_OFFSET);
+	return 0;
 }
 
 static int ttc_rate_change_clocksource_cb(struct notifier_block *nb,
@@ -430,7 +431,10 @@ static void __init ttc_setup_clockevent(struct clk *clk,
 	ttcce->ce.name = "ttc_clockevent";
 	ttcce->ce.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	ttcce->ce.set_next_event = ttc_set_next_event;
-	ttcce->ce.set_mode = ttc_set_mode;
+	ttcce->ce.set_state_shutdown = ttc_shutdown;
+	ttcce->ce.set_state_periodic = ttc_set_periodic;
+	ttcce->ce.set_state_oneshot = ttc_shutdown;
+	ttcce->ce.tick_resume = ttc_resume;
 	ttcce->ce.rating = 200;
 	ttcce->ce.irq = irq;
 	ttcce->ce.cpumask = cpu_possible_mask;
diff --git a/drivers/clocksource/clksrc_st_lpc.c b/drivers/clocksource/clksrc_st_lpc.c
new file mode 100644
index 000000000000..65ec4674416d
--- /dev/null
+++ b/drivers/clocksource/clksrc_st_lpc.c
@@ -0,0 +1,131 @@
+/*
+ * Clocksource using the Low Power Timer found in the Low Power Controller (LPC)
+ *
+ * Copyright (C) 2015 STMicroelectronics – All Rights Reserved
+ *
+ * Author(s): Francesco Virlinzi <francesco.virlinzi@st.com>
+ *	      Ajit Pal Singh <ajitpal.singh@st.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+#include <dt-bindings/mfd/st-lpc.h>
+
+/* Low Power Timer */
+#define LPC_LPT_LSB_OFF		0x400
+#define LPC_LPT_MSB_OFF		0x404
+#define LPC_LPT_START_OFF	0x408
+
+static struct st_clksrc_ddata {
+	struct clk		*clk;
+	void __iomem		*base;
+} ddata;
+
+static void __init st_clksrc_reset(void)
+{
+	writel_relaxed(0, ddata.base + LPC_LPT_START_OFF);
+	writel_relaxed(0, ddata.base + LPC_LPT_MSB_OFF);
+	writel_relaxed(0, ddata.base + LPC_LPT_LSB_OFF);
+	writel_relaxed(1, ddata.base + LPC_LPT_START_OFF);
+}
+
+static u64 notrace st_clksrc_sched_clock_read(void)
+{
+	return (u64)readl_relaxed(ddata.base + LPC_LPT_LSB_OFF);
+}
+
+static int __init st_clksrc_init(void)
+{
+	unsigned long rate;
+	int ret;
+
+	st_clksrc_reset();
+
+	rate = clk_get_rate(ddata.clk);
+
+	sched_clock_register(st_clksrc_sched_clock_read, 32, rate);
+
+	ret = clocksource_mmio_init(ddata.base + LPC_LPT_LSB_OFF,
+				    "clksrc-st-lpc", rate, 300, 32,
+				    clocksource_mmio_readl_up);
+	if (ret) {
+		pr_err("clksrc-st-lpc: Failed to register clocksource\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init st_clksrc_setup_clk(struct device_node *np)
+{
+	struct clk *clk;
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk)) {
+		pr_err("clksrc-st-lpc: Failed to get LPC clock\n");
+		return PTR_ERR(clk);
+	}
+
+	if (clk_prepare_enable(clk)) {
+		pr_err("clksrc-st-lpc: Failed to enable LPC clock\n");
+		return -EINVAL;
+	}
+
+	if (!clk_get_rate(clk)) {
+		pr_err("clksrc-st-lpc: Failed to get LPC clock rate\n");
+		clk_disable_unprepare(clk);
+		return -EINVAL;
+	}
+
+	ddata.clk = clk;
+
+	return 0;
+}
+
+static void __init st_clksrc_of_register(struct device_node *np)
+{
+	int ret;
+	uint32_t mode;
+
+	ret = of_property_read_u32(np, "st,lpc-mode", &mode);
+	if (ret) {
+		pr_err("clksrc-st-lpc: An LPC mode must be provided\n");
+		return;
+	}
+
+	/* LPC can either run as a Clocksource or in RTC or WDT mode */
+	if (mode != ST_LPC_MODE_CLKSRC)
+		return;
+
+	ddata.base = of_iomap(np, 0);
+	if (!ddata.base) {
+		pr_err("clksrc-st-lpc: Unable to map iomem\n");
+		return;
+	}
+
+	if (st_clksrc_setup_clk(np)) {
+		iounmap(ddata.base);
+		return;
+	}
+
+	if (st_clksrc_init()) {
+		clk_disable_unprepare(ddata.clk);
+		clk_put(ddata.clk);
+		iounmap(ddata.base);
+		return;
+	}
+
+	pr_info("clksrc-st-lpc: clocksource initialised - running @ %luHz\n",
+		clk_get_rate(ddata.clk));
+}
+CLOCKSOURCE_OF_DECLARE(ddata, "st,stih407-lpc", st_clksrc_of_register);
diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c
index d83ec1f2fddc..cdd86e3525bb 100644
--- a/drivers/clocksource/clps711x-timer.c
+++ b/drivers/clocksource/clps711x-timer.c
@@ -61,11 +61,6 @@ static irqreturn_t clps711x_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void clps711x_clockevent_set_mode(enum clock_event_mode mode,
-					 struct clock_event_device *evt)
-{
-}
-
 static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base,
 					unsigned int irq)
 {
@@ -91,7 +86,6 @@ static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base,
 	clkevt->name = "clps711x-clockevent";
 	clkevt->rating = 300;
 	clkevt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_C3STOP;
-	clkevt->set_mode = clps711x_clockevent_set_mode;
 	clkevt->cpumask = cpumask_of(0);
 	clockevents_config_and_register(clkevt, HZ, 0, 0);
 
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index db2105290898..9a7e37cf56b0 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -42,7 +42,6 @@ MODULE_PARM_DESC(irq, "Which IRQ to use for the clock source MFGPT ticks.");
  *  256         128   .125            512.000
  */
 
-static unsigned int cs5535_tick_mode = CLOCK_EVT_MODE_SHUTDOWN;
 static struct cs5535_mfgpt_timer *cs5535_event_clock;
 
 /* Selected from the table above */
@@ -77,15 +76,17 @@ static void start_timer(struct cs5535_mfgpt_timer *timer, uint16_t delta)
 			MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2);
 }
 
-static void mfgpt_set_mode(enum clock_event_mode mode,
-		struct clock_event_device *evt)
+static int mfgpt_shutdown(struct clock_event_device *evt)
 {
 	disable_timer(cs5535_event_clock);
+	return 0;
+}
 
-	if (mode == CLOCK_EVT_MODE_PERIODIC)
-		start_timer(cs5535_event_clock, MFGPT_PERIODIC);
-
-	cs5535_tick_mode = mode;
+static int mfgpt_set_periodic(struct clock_event_device *evt)
+{
+	disable_timer(cs5535_event_clock);
+	start_timer(cs5535_event_clock, MFGPT_PERIODIC);
+	return 0;
 }
 
 static int mfgpt_next_event(unsigned long delta, struct clock_event_device *evt)
@@ -97,7 +98,10 @@ static int mfgpt_next_event(unsigned long delta, struct clock_event_device *evt)
 static struct clock_event_device cs5535_clockevent = {
 	.name = DRV_NAME,
 	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = mfgpt_set_mode,
+	.set_state_shutdown = mfgpt_shutdown,
+	.set_state_periodic = mfgpt_set_periodic,
+	.set_state_oneshot = mfgpt_shutdown,
+	.tick_resume = mfgpt_shutdown,
 	.set_next_event = mfgpt_next_event,
 	.rating = 250,
 };
@@ -113,7 +117,7 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id)
 	/* Turn off the clock (and clear the event) */
 	disable_timer(cs5535_event_clock);
 
-	if (cs5535_tick_mode == CLOCK_EVT_MODE_SHUTDOWN)
+	if (clockevent_state_shutdown(&cs5535_clockevent))
 		return IRQ_HANDLED;
 
 	/* Clear the counter */
@@ -121,7 +125,7 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id)
 
 	/* Restart the clock in periodic mode */
 
-	if (cs5535_tick_mode == CLOCK_EVT_MODE_PERIODIC)
+	if (clockevent_state_periodic(&cs5535_clockevent))
 		cs5535_mfgpt_write(cs5535_event_clock, MFGPT_REG_SETUP,
 				MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2);
 
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index 31990600fcff..776b6c86dcd5 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -16,15 +16,6 @@
 
 static DEFINE_PER_CPU(struct clock_event_device, dummy_timer_evt);
 
-static void dummy_timer_set_mode(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
-{
-	/*
-	 * Core clockevents code will call this when exchanging timer devices.
-	 * We don't need to do anything here.
-	 */
-}
-
 static void dummy_timer_setup(void)
 {
 	int cpu = smp_processor_id();
@@ -35,7 +26,6 @@ static void dummy_timer_setup(void)
 			  CLOCK_EVT_FEAT_ONESHOT |
 			  CLOCK_EVT_FEAT_DUMMY;
 	evt->rating	= 100;
-	evt->set_mode	= dummy_timer_set_mode;
 	evt->cpumask	= cpumask_of(cpu);
 
 	clockevents_register_device(evt);
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index 35a88097af3c..c76c75006ea6 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -110,71 +110,87 @@ static void apbt_enable_int(struct dw_apb_timer *timer)
 	apbt_writel(timer, ctrl, APBTMR_N_CONTROL);
 }
 
-static void apbt_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt)
+static int apbt_shutdown(struct clock_event_device *evt)
 {
+	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
 	unsigned long ctrl;
-	unsigned long period;
+
+	pr_debug("%s CPU %d state=shutdown\n", __func__,
+		 cpumask_first(evt->cpumask));
+
+	ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
+	ctrl &= ~APBTMR_CONTROL_ENABLE;
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	return 0;
+}
+
+static int apbt_set_oneshot(struct clock_event_device *evt)
+{
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
+	unsigned long ctrl;
 
-	pr_debug("%s CPU %d mode=%d\n", __func__,
-		 cpumask_first(evt->cpumask),
-		 mode);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		period = DIV_ROUND_UP(dw_ced->timer.freq, HZ);
-		ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
-		ctrl |= APBTMR_CONTROL_MODE_PERIODIC;
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-		/*
-		 * DW APB p. 46, have to disable timer before load counter,
-		 * may cause sync problem.
-		 */
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-		udelay(1);
-		pr_debug("Setting clock period %lu for HZ %d\n", period, HZ);
-		apbt_writel(&dw_ced->timer, period, APBTMR_N_LOAD_COUNT);
-		ctrl |= APBTMR_CONTROL_ENABLE;
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
-		/*
-		 * set free running mode, this mode will let timer reload max
-		 * timeout which will give time (3min on 25MHz clock) to rearm
-		 * the next event, therefore emulate the one-shot mode.
-		 */
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC;
-
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-		/* write again to set free running mode */
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-
-		/*
-		 * DW APB p. 46, load counter with all 1s before starting free
-		 * running mode.
-		 */
-		apbt_writel(&dw_ced->timer, ~0, APBTMR_N_LOAD_COUNT);
-		ctrl &= ~APBTMR_CONTROL_INT;
-		ctrl |= APBTMR_CONTROL_ENABLE;
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		apbt_enable_int(&dw_ced->timer);
-		break;
-	}
+	pr_debug("%s CPU %d state=oneshot\n", __func__,
+		 cpumask_first(evt->cpumask));
+
+	ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
+	/*
+	 * set free running mode, this mode will let timer reload max
+	 * timeout which will give time (3min on 25MHz clock) to rearm
+	 * the next event, therefore emulate the one-shot mode.
+	 */
+	ctrl &= ~APBTMR_CONTROL_ENABLE;
+	ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC;
+
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	/* write again to set free running mode */
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+
+	/*
+	 * DW APB p. 46, load counter with all 1s before starting free
+	 * running mode.
+	 */
+	apbt_writel(&dw_ced->timer, ~0, APBTMR_N_LOAD_COUNT);
+	ctrl &= ~APBTMR_CONTROL_INT;
+	ctrl |= APBTMR_CONTROL_ENABLE;
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	return 0;
+}
+
+static int apbt_set_periodic(struct clock_event_device *evt)
+{
+	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
+	unsigned long period = DIV_ROUND_UP(dw_ced->timer.freq, HZ);
+	unsigned long ctrl;
+
+	pr_debug("%s CPU %d state=periodic\n", __func__,
+		 cpumask_first(evt->cpumask));
+
+	ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
+	ctrl |= APBTMR_CONTROL_MODE_PERIODIC;
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	/*
+	 * DW APB p. 46, have to disable timer before load counter,
+	 * may cause sync problem.
+	 */
+	ctrl &= ~APBTMR_CONTROL_ENABLE;
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	udelay(1);
+	pr_debug("Setting clock period %lu for HZ %d\n", period, HZ);
+	apbt_writel(&dw_ced->timer, period, APBTMR_N_LOAD_COUNT);
+	ctrl |= APBTMR_CONTROL_ENABLE;
+	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	return 0;
+}
+
+static int apbt_resume(struct clock_event_device *evt)
+{
+	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
+
+	pr_debug("%s CPU %d state=resume\n", __func__,
+		 cpumask_first(evt->cpumask));
+
+	apbt_enable_int(&dw_ced->timer);
+	return 0;
 }
 
 static int apbt_next_event(unsigned long delta,
@@ -232,8 +248,12 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating,
 						       &dw_ced->ced);
 	dw_ced->ced.min_delta_ns = clockevent_delta2ns(5000, &dw_ced->ced);
 	dw_ced->ced.cpumask = cpumask_of(cpu);
-	dw_ced->ced.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	dw_ced->ced.set_mode = apbt_set_mode;
+	dw_ced->ced.features = CLOCK_EVT_FEAT_PERIODIC |
+				CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_DYNIRQ;
+	dw_ced->ced.set_state_shutdown = apbt_shutdown;
+	dw_ced->ced.set_state_periodic = apbt_set_periodic;
+	dw_ced->ced.set_state_oneshot = apbt_set_oneshot;
+	dw_ced->ced.tick_resume = apbt_resume;
 	dw_ced->ced.set_next_event = apbt_next_event;
 	dw_ced->ced.irq = dw_ced->timer.irq;
 	dw_ced->ced.rating = rating;
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index dc3c6ee04aaa..7a97a34dba70 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -251,33 +251,21 @@ static struct em_sti_priv *ced_to_em_sti(struct clock_event_device *ced)
 	return container_of(ced, struct em_sti_priv, ced);
 }
 
-static void em_sti_clock_event_mode(enum clock_event_mode mode,
-				    struct clock_event_device *ced)
+static int em_sti_clock_event_shutdown(struct clock_event_device *ced)
 {
 	struct em_sti_priv *p = ced_to_em_sti(ced);
+	em_sti_stop(p, USER_CLOCKEVENT);
+	return 0;
+}
 
-	/* deal with old setting first */
-	switch (ced->mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		em_sti_stop(p, USER_CLOCKEVENT);
-		break;
-	default:
-		break;
-	}
+static int em_sti_clock_event_set_oneshot(struct clock_event_device *ced)
+{
+	struct em_sti_priv *p = ced_to_em_sti(ced);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		dev_info(&p->pdev->dev, "used for oneshot clock events\n");
-		em_sti_start(p, USER_CLOCKEVENT);
-		clockevents_config(&p->ced, p->rate);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		em_sti_stop(p, USER_CLOCKEVENT);
-		break;
-	default:
-		break;
-	}
+	dev_info(&p->pdev->dev, "used for oneshot clock events\n");
+	em_sti_start(p, USER_CLOCKEVENT);
+	clockevents_config(&p->ced, p->rate);
+	return 0;
 }
 
 static int em_sti_clock_event_next(unsigned long delta,
@@ -303,11 +291,12 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
 	ced->rating = 200;
 	ced->cpumask = cpu_possible_mask;
 	ced->set_next_event = em_sti_clock_event_next;
-	ced->set_mode = em_sti_clock_event_mode;
+	ced->set_state_shutdown = em_sti_clock_event_shutdown;
+	ced->set_state_oneshot = em_sti_clock_event_set_oneshot;
 
 	dev_info(&p->pdev->dev, "used for clock events\n");
 
-	/* Register with dummy 1 Hz value, gets updated in ->set_mode() */
+	/* Register with dummy 1 Hz value, gets updated in ->set_state_oneshot() */
 	clockevents_config_and_register(ced, 1, 2, 0xffffffff);
 }
 
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 9064ff743598..029f96ab131a 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -257,15 +257,14 @@ static void exynos4_mct_comp0_stop(void)
 	exynos4_mct_write(0, EXYNOS4_MCT_G_INT_ENB);
 }
 
-static void exynos4_mct_comp0_start(enum clock_event_mode mode,
-				    unsigned long cycles)
+static void exynos4_mct_comp0_start(bool periodic, unsigned long cycles)
 {
 	unsigned int tcon;
 	cycle_t comp_cycle;
 
 	tcon = readl_relaxed(reg_base + EXYNOS4_MCT_G_TCON);
 
-	if (mode == CLOCK_EVT_MODE_PERIODIC) {
+	if (periodic) {
 		tcon |= MCT_G_TCON_COMP0_AUTO_INC;
 		exynos4_mct_write(cycles, EXYNOS4_MCT_G_COMP0_ADD_INCR);
 	}
@@ -283,38 +282,38 @@ static void exynos4_mct_comp0_start(enum clock_event_mode mode,
 static int exynos4_comp_set_next_event(unsigned long cycles,
 				       struct clock_event_device *evt)
 {
-	exynos4_mct_comp0_start(evt->mode, cycles);
+	exynos4_mct_comp0_start(false, cycles);
 
 	return 0;
 }
 
-static void exynos4_comp_set_mode(enum clock_event_mode mode,
-				  struct clock_event_device *evt)
+static int mct_set_state_shutdown(struct clock_event_device *evt)
 {
-	unsigned long cycles_per_jiffy;
 	exynos4_mct_comp0_stop();
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		cycles_per_jiffy =
-			(((unsigned long long) NSEC_PER_SEC / HZ * evt->mult) >> evt->shift);
-		exynos4_mct_comp0_start(mode, cycles_per_jiffy);
-		break;
+static int mct_set_state_periodic(struct clock_event_device *evt)
+{
+	unsigned long cycles_per_jiffy;
 
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	cycles_per_jiffy = (((unsigned long long)NSEC_PER_SEC / HZ * evt->mult)
+			    >> evt->shift);
+	exynos4_mct_comp0_stop();
+	exynos4_mct_comp0_start(true, cycles_per_jiffy);
+	return 0;
 }
 
 static struct clock_event_device mct_comp_device = {
-	.name		= "mct-comp",
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 250,
-	.set_next_event	= exynos4_comp_set_next_event,
-	.set_mode	= exynos4_comp_set_mode,
+	.name			= "mct-comp",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 250,
+	.set_next_event		= exynos4_comp_set_next_event,
+	.set_state_periodic	= mct_set_state_periodic,
+	.set_state_shutdown	= mct_set_state_shutdown,
+	.set_state_oneshot	= mct_set_state_shutdown,
+	.tick_resume		= mct_set_state_shutdown,
 };
 
 static irqreturn_t exynos4_mct_comp_isr(int irq, void *dev_id)
@@ -390,39 +389,32 @@ static int exynos4_tick_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static inline void exynos4_tick_set_mode(enum clock_event_mode mode,
-					 struct clock_event_device *evt)
+static int set_state_shutdown(struct clock_event_device *evt)
+{
+	exynos4_mct_tick_stop(this_cpu_ptr(&percpu_mct_tick));
+	return 0;
+}
+
+static int set_state_periodic(struct clock_event_device *evt)
 {
 	struct mct_clock_event_device *mevt = this_cpu_ptr(&percpu_mct_tick);
 	unsigned long cycles_per_jiffy;
 
+	cycles_per_jiffy = (((unsigned long long)NSEC_PER_SEC / HZ * evt->mult)
+			    >> evt->shift);
 	exynos4_mct_tick_stop(mevt);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		cycles_per_jiffy =
-			(((unsigned long long) NSEC_PER_SEC / HZ * evt->mult) >> evt->shift);
-		exynos4_mct_tick_start(cycles_per_jiffy, mevt);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	exynos4_mct_tick_start(cycles_per_jiffy, mevt);
+	return 0;
 }
 
 static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 {
-	struct clock_event_device *evt = &mevt->evt;
-
 	/*
 	 * This is for supporting oneshot mode.
 	 * Mct would generate interrupt periodically
 	 * without explicit stopping.
 	 */
-	if (evt->mode != CLOCK_EVT_MODE_PERIODIC)
+	if (!clockevent_state_periodic(&mevt->evt))
 		exynos4_mct_tick_stop(mevt);
 
 	/* Clear the MCT tick interrupt */
@@ -442,20 +434,21 @@ static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int exynos4_local_timer_setup(struct clock_event_device *evt)
+static int exynos4_local_timer_setup(struct mct_clock_event_device *mevt)
 {
-	struct mct_clock_event_device *mevt;
+	struct clock_event_device *evt = &mevt->evt;
 	unsigned int cpu = smp_processor_id();
 
-	mevt = container_of(evt, struct mct_clock_event_device, evt);
-
 	mevt->base = EXYNOS4_MCT_L_BASE(cpu);
 	snprintf(mevt->name, sizeof(mevt->name), "mct_tick%d", cpu);
 
 	evt->name = mevt->name;
 	evt->cpumask = cpumask_of(cpu);
 	evt->set_next_event = exynos4_tick_set_next_event;
-	evt->set_mode = exynos4_tick_set_mode;
+	evt->set_state_periodic = set_state_periodic;
+	evt->set_state_shutdown = set_state_shutdown;
+	evt->set_state_oneshot = set_state_shutdown;
+	evt->tick_resume = set_state_shutdown;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 450;
 
@@ -477,9 +470,11 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 	return 0;
 }
 
-static void exynos4_local_timer_stop(struct clock_event_device *evt)
+static void exynos4_local_timer_stop(struct mct_clock_event_device *mevt)
 {
-	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	struct clock_event_device *evt = &mevt->evt;
+
+	evt->set_state_shutdown(evt);
 	if (mct_int_type == MCT_INT_SPI) {
 		if (evt->irq != -1)
 			disable_irq_nosync(evt->irq);
@@ -500,11 +495,11 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_STARTING:
 		mevt = this_cpu_ptr(&percpu_mct_tick);
-		exynos4_local_timer_setup(&mevt->evt);
+		exynos4_local_timer_setup(mevt);
 		break;
 	case CPU_DYING:
 		mevt = this_cpu_ptr(&percpu_mct_tick);
-		exynos4_local_timer_stop(&mevt->evt);
+		exynos4_local_timer_stop(mevt);
 		break;
 	}
 
@@ -570,7 +565,7 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem
 		goto out_irq;
 
 	/* Immediately configure the timer on the boot CPU */
-	exynos4_local_timer_setup(&mevt->evt);
+	exynos4_local_timer_setup(mevt);
 	return;
 
 out_irq:
diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c
index 454227d4f895..ef434699c80a 100644
--- a/drivers/clocksource/fsl_ftm_timer.c
+++ b/drivers/clocksource/fsl_ftm_timer.c
@@ -153,19 +153,16 @@ static int ftm_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void ftm_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int ftm_set_oneshot(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		ftm_set_next_event(priv->periodic_cyc, evt);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		ftm_counter_disable(priv->clkevt_base);
-		break;
-	default:
-		return;
-	}
+	ftm_counter_disable(priv->clkevt_base);
+	return 0;
+}
+
+static int ftm_set_periodic(struct clock_event_device *evt)
+{
+	ftm_set_next_event(priv->periodic_cyc, evt);
+	return 0;
 }
 
 static irqreturn_t ftm_evt_interrupt(int irq, void *dev_id)
@@ -174,7 +171,7 @@ static irqreturn_t ftm_evt_interrupt(int irq, void *dev_id)
 
 	ftm_irq_acknowledge(priv->clkevt_base);
 
-	if (likely(evt->mode == CLOCK_EVT_MODE_ONESHOT)) {
+	if (likely(clockevent_state_oneshot(evt))) {
 		ftm_irq_disable(priv->clkevt_base);
 		ftm_counter_disable(priv->clkevt_base);
 	}
@@ -185,11 +182,13 @@ static irqreturn_t ftm_evt_interrupt(int irq, void *dev_id)
 }
 
 static struct clock_event_device ftm_clockevent = {
-	.name		= "Freescale ftm timer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= ftm_set_mode,
-	.set_next_event	= ftm_set_next_event,
-	.rating		= 300,
+	.name			= "Freescale ftm timer",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_periodic	= ftm_set_periodic,
+	.set_state_oneshot	= ftm_set_oneshot,
+	.set_next_event		= ftm_set_next_event,
+	.rating			= 300,
 };
 
 static struct irqaction ftm_timer_irq = {
diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c
index 0214cb3a7f5e..f9b3b7033a97 100644
--- a/drivers/clocksource/h8300_timer8.c
+++ b/drivers/clocksource/h8300_timer8.c
@@ -81,7 +81,7 @@ static irqreturn_t timer8_interrupt(int irq, void *dev_id)
 	p->flags |= FLAG_IRQCONTEXT;
 	ctrl_outw(p->tcora, p->mapbase + TCORA);
 	if (!(p->flags & FLAG_SKIPEVENT)) {
-		if (p->ced.mode == CLOCK_EVT_MODE_ONESHOT)
+		if (clockevent_state_oneshot(&p->ced))
 			ctrl_outw(0x0000, p->mapbase + _8TCR);
 		p->ced.event_handler(&p->ced);
 	}
@@ -169,29 +169,32 @@ static void timer8_clock_event_start(struct timer8_priv *p, int periodic)
 	timer8_set_next(p, periodic?(p->rate + HZ/2) / HZ:0x10000);
 }
 
-static void timer8_clock_event_mode(enum clock_event_mode mode,
-				    struct clock_event_device *ced)
+static int timer8_clock_event_shutdown(struct clock_event_device *ced)
+{
+	timer8_stop(ced_to_priv(ced));
+	return 0;
+}
+
+static int timer8_clock_event_periodic(struct clock_event_device *ced)
 {
 	struct timer8_priv *p = ced_to_priv(ced);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		dev_info(&p->pdev->dev, "used for periodic clock events\n");
-		timer8_stop(p);
-		timer8_clock_event_start(p, PERIODIC);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		dev_info(&p->pdev->dev, "used for oneshot clock events\n");
-		timer8_stop(p);
-		timer8_clock_event_start(p, ONESHOT);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		timer8_stop(p);
-		break;
-	default:
-		break;
-	}
+	dev_info(&p->pdev->dev, "used for periodic clock events\n");
+	timer8_stop(p);
+	timer8_clock_event_start(p, PERIODIC);
+
+	return 0;
+}
+
+static int timer8_clock_event_oneshot(struct clock_event_device *ced)
+{
+	struct timer8_priv *p = ced_to_priv(ced);
+
+	dev_info(&p->pdev->dev, "used for oneshot clock events\n");
+	timer8_stop(p);
+	timer8_clock_event_start(p, ONESHOT);
+
+	return 0;
 }
 
 static int timer8_clock_event_next(unsigned long delta,
@@ -199,7 +202,7 @@ static int timer8_clock_event_next(unsigned long delta,
 {
 	struct timer8_priv *p = ced_to_priv(ced);
 
-	BUG_ON(ced->mode != CLOCK_EVT_MODE_ONESHOT);
+	BUG_ON(!clockevent_state_oneshot(ced));
 	timer8_set_next(p, delta - 1);
 
 	return 0;
@@ -246,7 +249,9 @@ static int timer8_setup(struct timer8_priv *p,
 	p->ced.rating = 200;
 	p->ced.cpumask = cpumask_of(0);
 	p->ced.set_next_event = timer8_clock_event_next;
-	p->ced.set_mode = timer8_clock_event_mode;
+	p->ced.set_state_shutdown = timer8_clock_event_shutdown;
+	p->ced.set_state_periodic = timer8_clock_event_periodic;
+	p->ced.set_state_oneshot = timer8_clock_event_oneshot;
 
 	ret = setup_irq(irq, &p->irqaction);
 	if (ret < 0) {
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 14ee3efcc404..0efd36e483ab 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -100,44 +100,40 @@ int __init clocksource_i8253_init(void)
 #endif
 
 #ifdef CONFIG_CLKEVT_I8253
-/*
- * Initialize the PIT timer.
- *
- * This is also called after resume to bring the PIT into operation again.
- */
-static void init_pit_timer(enum clock_event_mode mode,
-			   struct clock_event_device *evt)
+static int pit_shutdown(struct clock_event_device *evt)
 {
+	if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
+		return 0;
+
 	raw_spin_lock(&i8253_lock);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* binary, mode 2, LSB/MSB, ch 0 */
-		outb_p(0x34, PIT_MODE);
-		outb_p(PIT_LATCH & 0xff , PIT_CH0);	/* LSB */
-		outb_p(PIT_LATCH >> 8 , PIT_CH0);		/* MSB */
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		if (evt->mode == CLOCK_EVT_MODE_PERIODIC ||
-		    evt->mode == CLOCK_EVT_MODE_ONESHOT) {
-			outb_p(0x30, PIT_MODE);
-			outb_p(0, PIT_CH0);
-			outb_p(0, PIT_CH0);
-		}
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* One shot setup */
-		outb_p(0x38, PIT_MODE);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
+	outb_p(0x30, PIT_MODE);
+	outb_p(0, PIT_CH0);
+	outb_p(0, PIT_CH0);
+
+	raw_spin_unlock(&i8253_lock);
+	return 0;
+}
+
+static int pit_set_oneshot(struct clock_event_device *evt)
+{
+	raw_spin_lock(&i8253_lock);
+	outb_p(0x38, PIT_MODE);
+	raw_spin_unlock(&i8253_lock);
+	return 0;
+}
+
+static int pit_set_periodic(struct clock_event_device *evt)
+{
+	raw_spin_lock(&i8253_lock);
+
+	/* binary, mode 2, LSB/MSB, ch 0 */
+	outb_p(0x34, PIT_MODE);
+	outb_p(PIT_LATCH & 0xff, PIT_CH0);	/* LSB */
+	outb_p(PIT_LATCH >> 8, PIT_CH0);	/* MSB */
+
 	raw_spin_unlock(&i8253_lock);
+	return 0;
 }
 
 /*
@@ -160,10 +156,11 @@ static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
  * it can be solely used for the global tick.
  */
 struct clock_event_device i8253_clockevent = {
-	.name		= "pit",
-	.features	= CLOCK_EVT_FEAT_PERIODIC,
-	.set_mode	= init_pit_timer,
-	.set_next_event = pit_next_event,
+	.name			= "pit",
+	.features		= CLOCK_EVT_FEAT_PERIODIC,
+	.set_state_shutdown	= pit_shutdown,
+	.set_state_periodic	= pit_set_periodic,
+	.set_next_event		= pit_next_event,
 };
 
 /*
@@ -172,8 +169,10 @@ struct clock_event_device i8253_clockevent = {
  */
 void __init clockevent_i8253_init(bool oneshot)
 {
-	if (oneshot)
+	if (oneshot) {
 		i8253_clockevent.features |= CLOCK_EVT_FEAT_ONESHOT;
+		i8253_clockevent.set_state_oneshot = pit_set_oneshot;
+	}
 	/*
 	 * Start pit with the boot cpu mask. x86 might make it global
 	 * when it is used as broadcast device later.
diff --git a/drivers/clocksource/meson6_timer.c b/drivers/clocksource/meson6_timer.c
index 5c15cba41dca..1fa22c4d2d49 100644
--- a/drivers/clocksource/meson6_timer.c
+++ b/drivers/clocksource/meson6_timer.c
@@ -67,25 +67,25 @@ static void meson6_clkevt_time_start(unsigned char timer, bool periodic)
 	writel(val | TIMER_ENABLE_BIT(timer), timer_base + TIMER_ISA_MUX);
 }
 
-static void meson6_clkevt_mode(enum clock_event_mode mode,
-			       struct clock_event_device *clk)
+static int meson6_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		meson6_clkevt_time_stop(CED_ID);
-		meson6_clkevt_time_setup(CED_ID, USEC_PER_SEC/HZ - 1);
-		meson6_clkevt_time_start(CED_ID, true);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		meson6_clkevt_time_stop(CED_ID);
-		meson6_clkevt_time_start(CED_ID, false);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		meson6_clkevt_time_stop(CED_ID);
-		break;
-	}
+	meson6_clkevt_time_stop(CED_ID);
+	return 0;
+}
+
+static int meson6_set_oneshot(struct clock_event_device *evt)
+{
+	meson6_clkevt_time_stop(CED_ID);
+	meson6_clkevt_time_start(CED_ID, false);
+	return 0;
+}
+
+static int meson6_set_periodic(struct clock_event_device *evt)
+{
+	meson6_clkevt_time_stop(CED_ID);
+	meson6_clkevt_time_setup(CED_ID, USEC_PER_SEC / HZ - 1);
+	meson6_clkevt_time_start(CED_ID, true);
+	return 0;
 }
 
 static int meson6_clkevt_next_event(unsigned long evt,
@@ -99,11 +99,15 @@ static int meson6_clkevt_next_event(unsigned long evt,
 }
 
 static struct clock_event_device meson6_clockevent = {
-	.name		= "meson6_tick",
-	.rating		= 400,
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= meson6_clkevt_mode,
-	.set_next_event	= meson6_clkevt_next_event,
+	.name			= "meson6_tick",
+	.rating			= 400,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= meson6_shutdown,
+	.set_state_periodic	= meson6_set_periodic,
+	.set_state_oneshot	= meson6_set_oneshot,
+	.tick_resume		= meson6_shutdown,
+	.set_next_event		= meson6_clkevt_next_event,
 };
 
 static irqreturn_t meson6_timer_interrupt(int irq, void *dev_id)
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index b7384b853e5a..bcd5c0d602a0 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -56,25 +56,6 @@ static int metag_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void metag_timer_set_mode(enum clock_event_mode mode,
-				 struct clock_event_device *evt)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/* We should disable the IRQ here */
-		break;
-
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_UNUSED:
-		WARN_ON(1);
-		break;
-	};
-}
-
 static cycle_t metag_clocksource_read(struct clocksource *cs)
 {
 	return __core_reg_get(TXTIMER);
@@ -129,7 +110,6 @@ static void arch_timer_setup(unsigned int cpu)
 	clk->rating = 200,
 	clk->shift = 12,
 	clk->irq = tbisig_map(TBID_SIGNUM_TRT),
-	clk->set_mode = metag_timer_set_mode,
 	clk->set_next_event = metag_timer_set_next_event,
 
 	clk->mult = div_sc(hwtimer_freq, NSEC_PER_SEC, clk->shift);
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index b81ed1a5342d..02a1945e5093 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -33,12 +33,6 @@ static int gic_next_event(unsigned long delta, struct clock_event_device *evt)
 	return res;
 }
 
-static void gic_set_clock_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
-{
-	/* Nothing to do ...  */
-}
-
 static irqreturn_t gic_compare_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *cd = dev_id;
@@ -67,7 +61,6 @@ static void gic_clockevent_cpu_init(struct clock_event_device *cd)
 	cd->irq			= gic_timer_irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= gic_next_event;
-	cd->set_mode		= gic_set_clock_mode;
 
 	clockevents_config_and_register(cd, gic_frequency, 0x300, 0x7fffffff);
 
@@ -79,6 +72,13 @@ static void gic_clockevent_cpu_exit(struct clock_event_device *cd)
 	disable_percpu_irq(gic_timer_irq);
 }
 
+static void gic_update_frequency(void *data)
+{
+	unsigned long rate = (unsigned long)data;
+
+	clockevents_update_freq(this_cpu_ptr(&gic_clockevent_device), rate);
+}
+
 static int gic_cpu_notifier(struct notifier_block *nb, unsigned long action,
 				void *data)
 {
@@ -94,18 +94,40 @@ static int gic_cpu_notifier(struct notifier_block *nb, unsigned long action,
 	return NOTIFY_OK;
 }
 
+static int gic_clk_notifier(struct notifier_block *nb, unsigned long action,
+			    void *data)
+{
+	struct clk_notifier_data *cnd = data;
+
+	if (action == POST_RATE_CHANGE)
+		on_each_cpu(gic_update_frequency, (void *)cnd->new_rate, 1);
+
+	return NOTIFY_OK;
+}
+
+
 static struct notifier_block gic_cpu_nb = {
 	.notifier_call = gic_cpu_notifier,
 };
 
+static struct notifier_block gic_clk_nb = {
+	.notifier_call = gic_clk_notifier,
+};
+
 static int gic_clockevent_init(void)
 {
+	int ret;
+
 	if (!cpu_has_counter || !gic_frequency)
 		return -ENXIO;
 
-	setup_percpu_irq(gic_timer_irq, &gic_compare_irqaction);
+	ret = setup_percpu_irq(gic_timer_irq, &gic_compare_irqaction);
+	if (ret < 0)
+		return ret;
 
-	register_cpu_notifier(&gic_cpu_nb);
+	ret = register_cpu_notifier(&gic_cpu_nb);
+	if (ret < 0)
+		pr_warn("GIC: Unable to register CPU notifier\n");
 
 	gic_clockevent_cpu_init(this_cpu_ptr(&gic_clockevent_device));
 
@@ -125,18 +147,17 @@ static struct clocksource gic_clocksource = {
 
 static void __init __gic_clocksource_init(void)
 {
+	int ret;
+
 	/* Set clocksource mask. */
 	gic_clocksource.mask = CLOCKSOURCE_MASK(gic_get_count_width());
 
 	/* Calculate a somewhat reasonable rating value. */
 	gic_clocksource.rating = 200 + gic_frequency / 10000000;
 
-	clocksource_register_hz(&gic_clocksource, gic_frequency);
-
-	gic_clockevent_init();
-
-	/* And finally start the counter */
-	gic_start_count();
+	ret = clocksource_register_hz(&gic_clocksource, gic_frequency);
+	if (ret < 0)
+		pr_warn("GIC: Unable to register clocksource\n");
 }
 
 void __init gic_clocksource_init(unsigned int frequency)
@@ -146,11 +167,16 @@ void __init gic_clocksource_init(unsigned int frequency)
 		GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_COMPARE);
 
 	__gic_clocksource_init();
+	gic_clockevent_init();
+
+	/* And finally start the counter */
+	gic_start_count();
 }
 
 static void __init gic_clocksource_of_init(struct device_node *node)
 {
 	struct clk *clk;
+	int ret;
 
 	if (WARN_ON(!gic_present || !node->parent ||
 		    !of_device_is_compatible(node->parent, "mti,gic")))
@@ -158,8 +184,13 @@ static void __init gic_clocksource_of_init(struct device_node *node)
 
 	clk = of_clk_get(node, 0);
 	if (!IS_ERR(clk)) {
+		if (clk_prepare_enable(clk) < 0) {
+			pr_err("GIC failed to enable clock\n");
+			clk_put(clk);
+			return;
+		}
+
 		gic_frequency = clk_get_rate(clk);
-		clk_put(clk);
 	} else if (of_property_read_u32(node, "clock-frequency",
 					&gic_frequency)) {
 		pr_err("GIC frequency not specified.\n");
@@ -172,6 +203,15 @@ static void __init gic_clocksource_of_init(struct device_node *node)
 	}
 
 	__gic_clocksource_init();
+
+	ret = gic_clockevent_init();
+	if (!ret && !IS_ERR(clk)) {
+		if (clk_notifier_register(clk, &gic_clk_nb) < 0)
+			pr_warn("GIC: Unable to register clock notifier\n");
+	}
+
+	/* And finally start the counter */
+	gic_start_count();
 }
 CLOCKSOURCE_OF_DECLARE(mips_gic_timer, "mti,gic-timer",
 		       gic_clocksource_of_init);
diff --git a/drivers/clocksource/moxart_timer.c b/drivers/clocksource/moxart_timer.c
index 5eb2c35932b1..19857af651c1 100644
--- a/drivers/clocksource/moxart_timer.c
+++ b/drivers/clocksource/moxart_timer.c
@@ -58,25 +58,24 @@
 static void __iomem *base;
 static unsigned int clock_count_per_tick;
 
-static void moxart_clkevt_mode(enum clock_event_mode mode,
-			       struct clock_event_device *clk)
+static int moxart_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_ONESHOT:
-		writel(TIMER1_DISABLE, base + TIMER_CR);
-		writel(~0, base + TIMER1_BASE + REG_LOAD);
-		break;
-	case CLOCK_EVT_MODE_PERIODIC:
-		writel(clock_count_per_tick, base + TIMER1_BASE + REG_LOAD);
-		writel(TIMER1_ENABLE, base + TIMER_CR);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		writel(TIMER1_DISABLE, base + TIMER_CR);
-		break;
-	}
+	writel(TIMER1_DISABLE, base + TIMER_CR);
+	return 0;
+}
+
+static int moxart_set_oneshot(struct clock_event_device *evt)
+{
+	writel(TIMER1_DISABLE, base + TIMER_CR);
+	writel(~0, base + TIMER1_BASE + REG_LOAD);
+	return 0;
+}
+
+static int moxart_set_periodic(struct clock_event_device *evt)
+{
+	writel(clock_count_per_tick, base + TIMER1_BASE + REG_LOAD);
+	writel(TIMER1_ENABLE, base + TIMER_CR);
+	return 0;
 }
 
 static int moxart_clkevt_next_event(unsigned long cycles,
@@ -95,11 +94,15 @@ static int moxart_clkevt_next_event(unsigned long cycles,
 }
 
 static struct clock_event_device moxart_clockevent = {
-	.name		= "moxart_timer",
-	.rating		= 200,
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= moxart_clkevt_mode,
-	.set_next_event	= moxart_clkevt_next_event,
+	.name			= "moxart_timer",
+	.rating			= 200,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= moxart_shutdown,
+	.set_state_periodic	= moxart_set_periodic,
+	.set_state_oneshot	= moxart_set_oneshot,
+	.tick_resume		= moxart_set_oneshot,
+	.set_next_event		= moxart_clkevt_next_event,
 };
 
 static irqreturn_t moxart_timer_interrupt(int irq, void *dev_id)
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
index 68ab42356d0e..50f0641c65b6 100644
--- a/drivers/clocksource/mtk_timer.c
+++ b/drivers/clocksource/mtk_timer.c
@@ -102,27 +102,20 @@ static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
 	       evt->gpt_base + TIMER_CTRL_REG(timer));
 }
 
-static void mtk_clkevt_mode(enum clock_event_mode mode,
-				struct clock_event_device *clk)
+static int mtk_clkevt_shutdown(struct clock_event_device *clk)
+{
+	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
+	return 0;
+}
+
+static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
 {
 	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
 
 	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
-		mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Timer is enabled in set_next_event */
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		/* No more interrupts will occur as source is disabled */
-		break;
-	}
+	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
+	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
+	return 0;
 }
 
 static int mtk_clkevt_next_event(unsigned long event,
@@ -196,7 +189,10 @@ static void __init mtk_timer_init(struct device_node *node)
 	evt->dev.name = "mtk_tick";
 	evt->dev.rating = 300;
 	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_mode = mtk_clkevt_mode;
+	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
+	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
+	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
+	evt->dev.tick_resume = mtk_clkevt_shutdown;
 	evt->dev.set_next_event = mtk_clkevt_next_event;
 	evt->dev.cpumask = cpu_possible_mask;
 
diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c
index 445b68a01dc5..f5ce2961c0d6 100644
--- a/drivers/clocksource/mxs_timer.c
+++ b/drivers/clocksource/mxs_timer.c
@@ -77,7 +77,6 @@
 #define BV_TIMROTv2_TIMCTRLn_SELECT__TICK_ALWAYS	0xf
 
 static struct clock_event_device mxs_clockevent_device;
-static enum clock_event_mode mxs_clockevent_mode = CLOCK_EVT_MODE_UNUSED;
 
 static void __iomem *mxs_timrot_base;
 static u32 timrot_major_version;
@@ -141,64 +140,49 @@ static struct irqaction mxs_timer_irq = {
 	.handler	= mxs_timer_interrupt,
 };
 
-#ifdef DEBUG
-static const char *clock_event_mode_label[] const = {
-	[CLOCK_EVT_MODE_PERIODIC] = "CLOCK_EVT_MODE_PERIODIC",
-	[CLOCK_EVT_MODE_ONESHOT]  = "CLOCK_EVT_MODE_ONESHOT",
-	[CLOCK_EVT_MODE_SHUTDOWN] = "CLOCK_EVT_MODE_SHUTDOWN",
-	[CLOCK_EVT_MODE_UNUSED]   = "CLOCK_EVT_MODE_UNUSED"
-};
-#endif /* DEBUG */
-
-static void mxs_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static void mxs_irq_clear(char *state)
 {
 	/* Disable interrupt in timer module */
 	timrot_irq_disable();
 
-	if (mode != mxs_clockevent_mode) {
-		/* Set event time into the furthest future */
-		if (timrot_is_v1())
-			__raw_writel(0xffff,
-				mxs_timrot_base + HW_TIMROT_TIMCOUNTn(1));
-		else
-			__raw_writel(0xffffffff,
-				mxs_timrot_base + HW_TIMROT_FIXED_COUNTn(1));
-
-		/* Clear pending interrupt */
-		timrot_irq_acknowledge();
-	}
+	/* Set event time into the furthest future */
+	if (timrot_is_v1())
+		__raw_writel(0xffff, mxs_timrot_base + HW_TIMROT_TIMCOUNTn(1));
+	else
+		__raw_writel(0xffffffff,
+			     mxs_timrot_base + HW_TIMROT_FIXED_COUNTn(1));
+
+	/* Clear pending interrupt */
+	timrot_irq_acknowledge();
 
 #ifdef DEBUG
-	pr_info("%s: changing mode from %s to %s\n", __func__,
-		clock_event_mode_label[mxs_clockevent_mode],
-		clock_event_mode_label[mode]);
+	pr_info("%s: changing mode to %s\n", __func__, state)
 #endif /* DEBUG */
+}
 
-	/* Remember timer mode */
-	mxs_clockevent_mode = mode;
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		pr_err("%s: Periodic mode is not implemented\n", __func__);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		timrot_irq_enable();
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		/* Left event sources disabled, no more interrupts appear */
-		break;
-	}
+static int mxs_shutdown(struct clock_event_device *evt)
+{
+	mxs_irq_clear("shutdown");
+
+	return 0;
+}
+
+static int mxs_set_oneshot(struct clock_event_device *evt)
+{
+	if (clockevent_state_oneshot(evt))
+		mxs_irq_clear("oneshot");
+	timrot_irq_enable();
+	return 0;
 }
 
 static struct clock_event_device mxs_clockevent_device = {
-	.name		= "mxs_timrot",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= mxs_set_mode,
-	.set_next_event	= timrotv2_set_next_event,
-	.rating		= 200,
+	.name			= "mxs_timrot",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= mxs_shutdown,
+	.set_state_oneshot	= mxs_set_oneshot,
+	.tick_resume		= mxs_shutdown,
+	.set_next_event		= timrotv2_set_next_event,
+	.rating			= 200,
 };
 
 static int __init mxs_clockevent_init(struct clk *timer_clk)
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
index a709cfa49d85..bc8dd443c727 100644
--- a/drivers/clocksource/nomadik-mtu.c
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -119,28 +119,27 @@ static void nmdk_clkevt_reset(void)
 	}
 }
 
-static void nmdk_clkevt_mode(enum clock_event_mode mode,
-			     struct clock_event_device *dev)
+static int nmdk_clkevt_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		clkevt_periodic = true;
-		nmdk_clkevt_reset();
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		clkevt_periodic = false;
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		writel(0, mtu_base + MTU_IMSC);
-		/* disable timer */
-		writel(0, mtu_base + MTU_CR(1));
-		/* load some high default value */
-		writel(0xffffffff, mtu_base + MTU_LR(1));
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	writel(0, mtu_base + MTU_IMSC);
+	/* disable timer */
+	writel(0, mtu_base + MTU_CR(1));
+	/* load some high default value */
+	writel(0xffffffff, mtu_base + MTU_LR(1));
+	return 0;
+}
+
+static int nmdk_clkevt_set_oneshot(struct clock_event_device *evt)
+{
+	clkevt_periodic = false;
+	return 0;
+}
+
+static int nmdk_clkevt_set_periodic(struct clock_event_device *evt)
+{
+	clkevt_periodic = true;
+	nmdk_clkevt_reset();
+	return 0;
 }
 
 static void nmdk_clksrc_reset(void)
@@ -163,13 +162,16 @@ static void nmdk_clkevt_resume(struct clock_event_device *cedev)
 }
 
 static struct clock_event_device nmdk_clkevt = {
-	.name		= "mtu_1",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC |
-	                  CLOCK_EVT_FEAT_DYNIRQ,
-	.rating		= 200,
-	.set_mode	= nmdk_clkevt_mode,
-	.set_next_event	= nmdk_clkevt_next,
-	.resume		= nmdk_clkevt_resume,
+	.name			= "mtu_1",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_DYNIRQ,
+	.rating			= 200,
+	.set_state_shutdown	= nmdk_clkevt_shutdown,
+	.set_state_periodic	= nmdk_clkevt_set_periodic,
+	.set_state_oneshot	= nmdk_clkevt_set_oneshot,
+	.set_next_event		= nmdk_clkevt_next,
+	.resume			= nmdk_clkevt_resume,
 };
 
 /*
diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c
index d9438af2bbd6..45b6a4999713 100644
--- a/drivers/clocksource/pxa_timer.c
+++ b/drivers/clocksource/pxa_timer.c
@@ -88,26 +88,12 @@ pxa_osmr0_set_next_event(unsigned long delta, struct clock_event_device *dev)
 	return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0;
 }
 
-static void
-pxa_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *dev)
+static int pxa_osmr0_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		timer_writel(timer_readl(OIER) & ~OIER_E0, OIER);
-		timer_writel(OSSR_M0, OSSR);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/* initializing, released, or preparing for suspend */
-		timer_writel(timer_readl(OIER) & ~OIER_E0, OIER);
-		timer_writel(OSSR_M0, OSSR);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		break;
-	}
+	/* initializing, released, or preparing for suspend */
+	timer_writel(timer_readl(OIER) & ~OIER_E0, OIER);
+	timer_writel(OSSR_M0, OSSR);
+	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -147,13 +133,14 @@ static void pxa_timer_resume(struct clock_event_device *cedev)
 #endif
 
 static struct clock_event_device ckevt_pxa_osmr0 = {
-	.name		= "osmr0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= pxa_osmr0_set_next_event,
-	.set_mode	= pxa_osmr0_set_mode,
-	.suspend	= pxa_timer_suspend,
-	.resume		= pxa_timer_resume,
+	.name			= "osmr0",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= pxa_osmr0_set_next_event,
+	.set_state_shutdown	= pxa_osmr0_shutdown,
+	.set_state_oneshot	= pxa_osmr0_shutdown,
+	.suspend		= pxa_timer_suspend,
+	.resume			= pxa_timer_resume,
 };
 
 static struct irqaction pxa_ost0_irq = {
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index cba2d015564c..f8e09f923651 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -47,7 +47,7 @@ static irqreturn_t msm_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evt = dev_id;
 	/* Stop the timer tick */
-	if (evt->mode == CLOCK_EVT_MODE_ONESHOT) {
+	if (clockevent_state_oneshot(evt)) {
 		u32 ctrl = readl_relaxed(event_base + TIMER_ENABLE);
 		ctrl &= ~TIMER_ENABLE_EN;
 		writel_relaxed(ctrl, event_base + TIMER_ENABLE);
@@ -75,26 +75,14 @@ static int msm_timer_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void msm_timer_set_mode(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int msm_timer_shutdown(struct clock_event_device *evt)
 {
 	u32 ctrl;
 
 	ctrl = readl_relaxed(event_base + TIMER_ENABLE);
 	ctrl &= ~(TIMER_ENABLE_EN | TIMER_ENABLE_CLR_ON_MATCH_EN);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Timer is enabled in set_next_event */
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		break;
-	}
 	writel_relaxed(ctrl, event_base + TIMER_ENABLE);
+	return 0;
 }
 
 static struct clock_event_device __percpu *msm_evt;
@@ -126,7 +114,9 @@ static int msm_local_timer_setup(struct clock_event_device *evt)
 	evt->name = "msm_timer";
 	evt->features = CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 200;
-	evt->set_mode = msm_timer_set_mode;
+	evt->set_state_shutdown = msm_timer_shutdown;
+	evt->set_state_oneshot = msm_timer_shutdown;
+	evt->tick_resume = msm_timer_shutdown;
 	evt->set_next_event = msm_timer_set_next_event;
 	evt->cpumask = cpumask_of(cpu);
 
@@ -147,7 +137,7 @@ static int msm_local_timer_setup(struct clock_event_device *evt)
 
 static void msm_local_timer_stop(struct clock_event_device *evt)
 {
-	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	evt->set_state_shutdown(evt);
 	disable_percpu_irq(evt->irq);
 }
 
diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c
index a35993bafb20..bb2c2b050964 100644
--- a/drivers/clocksource/rockchip_timer.c
+++ b/drivers/clocksource/rockchip_timer.c
@@ -82,23 +82,18 @@ static inline int rk_timer_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static inline void rk_timer_set_mode(enum clock_event_mode mode,
-				     struct clock_event_device *ce)
+static int rk_timer_shutdown(struct clock_event_device *ce)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		rk_timer_disable(ce);
-		rk_timer_update_counter(rk_timer(ce)->freq / HZ - 1, ce);
-		rk_timer_enable(ce, TIMER_MODE_FREE_RUNNING);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		rk_timer_disable(ce);
-		break;
-	}
+	rk_timer_disable(ce);
+	return 0;
+}
+
+static int rk_timer_set_periodic(struct clock_event_device *ce)
+{
+	rk_timer_disable(ce);
+	rk_timer_update_counter(rk_timer(ce)->freq / HZ - 1, ce);
+	rk_timer_enable(ce, TIMER_MODE_FREE_RUNNING);
+	return 0;
 }
 
 static irqreturn_t rk_timer_interrupt(int irq, void *dev_id)
@@ -107,7 +102,7 @@ static irqreturn_t rk_timer_interrupt(int irq, void *dev_id)
 
 	rk_timer_interrupt_clear(ce);
 
-	if (ce->mode == CLOCK_EVT_MODE_ONESHOT)
+	if (clockevent_state_oneshot(ce))
 		rk_timer_disable(ce);
 
 	ce->event_handler(ce);
@@ -161,7 +156,8 @@ static void __init rk_timer_init(struct device_node *np)
 	ce->name = TIMER_NAME;
 	ce->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	ce->set_next_event = rk_timer_set_next_event;
-	ce->set_mode = rk_timer_set_mode;
+	ce->set_state_shutdown = rk_timer_shutdown;
+	ce->set_state_periodic = rk_timer_set_periodic;
 	ce->irq = irq;
 	ce->cpumask = cpumask_of(0);
 	ce->rating = 250;
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 5645cfc90c41..bc90e13338cc 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -207,25 +207,18 @@ static int samsung_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void samsung_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int samsung_shutdown(struct clock_event_device *evt)
 {
 	samsung_time_stop(pwm.event_id);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		samsung_time_setup(pwm.event_id, pwm.clock_count_per_tick - 1);
-		samsung_time_start(pwm.event_id, true);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+static int samsung_set_periodic(struct clock_event_device *evt)
+{
+	samsung_time_stop(pwm.event_id);
+	samsung_time_setup(pwm.event_id, pwm.clock_count_per_tick - 1);
+	samsung_time_start(pwm.event_id, true);
+	return 0;
 }
 
 static void samsung_clockevent_resume(struct clock_event_device *cev)
@@ -240,12 +233,16 @@ static void samsung_clockevent_resume(struct clock_event_device *cev)
 }
 
 static struct clock_event_device time_event_device = {
-	.name		= "samsung_event_timer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= samsung_set_next_event,
-	.set_mode	= samsung_set_mode,
-	.resume		= samsung_clockevent_resume,
+	.name			= "samsung_event_timer",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= samsung_set_next_event,
+	.set_state_shutdown	= samsung_shutdown,
+	.set_state_periodic	= samsung_set_periodic,
+	.set_state_oneshot	= samsung_shutdown,
+	.tick_resume		= samsung_shutdown,
+	.resume			= samsung_clockevent_resume,
 };
 
 static irqreturn_t samsung_clock_event_isr(int irq, void *dev_id)
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index b8ff3c64cc45..ba73a6eb8d66 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -538,7 +538,7 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
 
 	if (ch->flags & FLAG_CLOCKEVENT) {
 		if (!(ch->flags & FLAG_SKIPEVENT)) {
-			if (ch->ced.mode == CLOCK_EVT_MODE_ONESHOT) {
+			if (clockevent_state_oneshot(&ch->ced)) {
 				ch->next_match_value = ch->max_match_value;
 				ch->flags |= FLAG_REPROGRAM;
 			}
@@ -554,7 +554,7 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
 		sh_cmt_clock_event_program_verify(ch, 1);
 
 		if (ch->flags & FLAG_CLOCKEVENT)
-			if ((ch->ced.mode == CLOCK_EVT_MODE_SHUTDOWN)
+			if ((clockevent_state_shutdown(&ch->ced))
 			    || (ch->match_value == ch->next_match_value))
 				ch->flags &= ~FLAG_REPROGRAM;
 	}
@@ -661,6 +661,9 @@ static void sh_cmt_clocksource_suspend(struct clocksource *cs)
 {
 	struct sh_cmt_channel *ch = cs_to_sh_cmt(cs);
 
+	if (!ch->cs_enabled)
+		return;
+
 	sh_cmt_stop(ch, FLAG_CLOCKSOURCE);
 	pm_genpd_syscore_poweroff(&ch->cmt->pdev->dev);
 }
@@ -669,6 +672,9 @@ static void sh_cmt_clocksource_resume(struct clocksource *cs)
 {
 	struct sh_cmt_channel *ch = cs_to_sh_cmt(cs);
 
+	if (!ch->cs_enabled)
+		return;
+
 	pm_genpd_syscore_poweron(&ch->cmt->pdev->dev);
 	sh_cmt_start(ch, FLAG_CLOCKSOURCE);
 }
@@ -720,39 +726,37 @@ static void sh_cmt_clock_event_start(struct sh_cmt_channel *ch, int periodic)
 		sh_cmt_set_next(ch, ch->max_match_value);
 }
 
-static void sh_cmt_clock_event_mode(enum clock_event_mode mode,
-				    struct clock_event_device *ced)
+static int sh_cmt_clock_event_shutdown(struct clock_event_device *ced)
+{
+	struct sh_cmt_channel *ch = ced_to_sh_cmt(ced);
+
+	sh_cmt_stop(ch, FLAG_CLOCKEVENT);
+	return 0;
+}
+
+static int sh_cmt_clock_event_set_state(struct clock_event_device *ced,
+					int periodic)
 {
 	struct sh_cmt_channel *ch = ced_to_sh_cmt(ced);
 
 	/* deal with old setting first */
-	switch (ced->mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
+	if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced))
 		sh_cmt_stop(ch, FLAG_CLOCKEVENT);
-		break;
-	default:
-		break;
-	}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		dev_info(&ch->cmt->pdev->dev,
-			 "ch%u: used for periodic clock events\n", ch->index);
-		sh_cmt_clock_event_start(ch, 1);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		dev_info(&ch->cmt->pdev->dev,
-			 "ch%u: used for oneshot clock events\n", ch->index);
-		sh_cmt_clock_event_start(ch, 0);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		sh_cmt_stop(ch, FLAG_CLOCKEVENT);
-		break;
-	default:
-		break;
-	}
+	dev_info(&ch->cmt->pdev->dev, "ch%u: used for %s clock events\n",
+		 ch->index, periodic ? "periodic" : "oneshot");
+	sh_cmt_clock_event_start(ch, periodic);
+	return 0;
+}
+
+static int sh_cmt_clock_event_set_oneshot(struct clock_event_device *ced)
+{
+	return sh_cmt_clock_event_set_state(ced, 0);
+}
+
+static int sh_cmt_clock_event_set_periodic(struct clock_event_device *ced)
+{
+	return sh_cmt_clock_event_set_state(ced, 1);
 }
 
 static int sh_cmt_clock_event_next(unsigned long delta,
@@ -760,7 +764,7 @@ static int sh_cmt_clock_event_next(unsigned long delta,
 {
 	struct sh_cmt_channel *ch = ced_to_sh_cmt(ced);
 
-	BUG_ON(ced->mode != CLOCK_EVT_MODE_ONESHOT);
+	BUG_ON(!clockevent_state_oneshot(ced));
 	if (likely(ch->flags & FLAG_IRQCONTEXT))
 		ch->next_match_value = delta - 1;
 	else
@@ -814,7 +818,9 @@ static int sh_cmt_register_clockevent(struct sh_cmt_channel *ch,
 	ced->rating = 125;
 	ced->cpumask = cpu_possible_mask;
 	ced->set_next_event = sh_cmt_clock_event_next;
-	ced->set_mode = sh_cmt_clock_event_mode;
+	ced->set_state_shutdown = sh_cmt_clock_event_shutdown;
+	ced->set_state_periodic = sh_cmt_clock_event_set_periodic;
+	ced->set_state_oneshot = sh_cmt_clock_event_set_oneshot;
 	ced->suspend = sh_cmt_clock_event_suspend;
 	ced->resume = sh_cmt_clock_event_resume;
 
@@ -929,9 +935,6 @@ static int sh_cmt_map_memory(struct sh_cmt_device *cmt)
 static const struct platform_device_id sh_cmt_id_table[] = {
 	{ "sh-cmt-16", (kernel_ulong_t)&sh_cmt_info[SH_CMT_16BIT] },
 	{ "sh-cmt-32", (kernel_ulong_t)&sh_cmt_info[SH_CMT_32BIT] },
-	{ "sh-cmt-32-fast", (kernel_ulong_t)&sh_cmt_info[SH_CMT_32BIT_FAST] },
-	{ "sh-cmt-48", (kernel_ulong_t)&sh_cmt_info[SH_CMT_48BIT] },
-	{ "sh-cmt-48-gen2", (kernel_ulong_t)&sh_cmt_info[SH_CMT_48BIT_GEN2] },
 	{ }
 };
 MODULE_DEVICE_TABLE(platform, sh_cmt_id_table);
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index 3d88698cf2b8..f1985da8113f 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -276,36 +276,25 @@ static struct sh_mtu2_channel *ced_to_sh_mtu2(struct clock_event_device *ced)
 	return container_of(ced, struct sh_mtu2_channel, ced);
 }
 
-static void sh_mtu2_clock_event_mode(enum clock_event_mode mode,
-				    struct clock_event_device *ced)
+static int sh_mtu2_clock_event_shutdown(struct clock_event_device *ced)
 {
 	struct sh_mtu2_channel *ch = ced_to_sh_mtu2(ced);
-	int disabled = 0;
 
-	/* deal with old setting first */
-	switch (ced->mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
+	sh_mtu2_disable(ch);
+	return 0;
+}
+
+static int sh_mtu2_clock_event_set_periodic(struct clock_event_device *ced)
+{
+	struct sh_mtu2_channel *ch = ced_to_sh_mtu2(ced);
+
+	if (clockevent_state_periodic(ced))
 		sh_mtu2_disable(ch);
-		disabled = 1;
-		break;
-	default:
-		break;
-	}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		dev_info(&ch->mtu->pdev->dev,
-			 "ch%u: used for periodic clock events\n", ch->index);
-		sh_mtu2_enable(ch);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-		if (!disabled)
-			sh_mtu2_disable(ch);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		break;
-	}
+	dev_info(&ch->mtu->pdev->dev, "ch%u: used for periodic clock events\n",
+		 ch->index);
+	sh_mtu2_enable(ch);
+	return 0;
 }
 
 static void sh_mtu2_clock_event_suspend(struct clock_event_device *ced)
@@ -327,7 +316,8 @@ static void sh_mtu2_register_clockevent(struct sh_mtu2_channel *ch,
 	ced->features = CLOCK_EVT_FEAT_PERIODIC;
 	ced->rating = 200;
 	ced->cpumask = cpu_possible_mask;
-	ced->set_mode = sh_mtu2_clock_event_mode;
+	ced->set_state_shutdown = sh_mtu2_clock_event_shutdown;
+	ced->set_state_periodic = sh_mtu2_clock_event_set_periodic;
 	ced->suspend = sh_mtu2_clock_event_suspend;
 	ced->resume = sh_mtu2_clock_event_resume;
 
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index b6b8fa3cd211..469e776ec17a 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -240,7 +240,7 @@ static irqreturn_t sh_tmu_interrupt(int irq, void *dev_id)
 	struct sh_tmu_channel *ch = dev_id;
 
 	/* disable or acknowledge interrupt */
-	if (ch->ced.mode == CLOCK_EVT_MODE_ONESHOT)
+	if (clockevent_state_oneshot(&ch->ced))
 		sh_tmu_write(ch, TCR, TCR_TPSC_CLK4);
 	else
 		sh_tmu_write(ch, TCR, TCR_UNIE | TCR_TPSC_CLK4);
@@ -358,42 +358,38 @@ static void sh_tmu_clock_event_start(struct sh_tmu_channel *ch, int periodic)
 	}
 }
 
-static void sh_tmu_clock_event_mode(enum clock_event_mode mode,
-				    struct clock_event_device *ced)
+static int sh_tmu_clock_event_shutdown(struct clock_event_device *ced)
+{
+	struct sh_tmu_channel *ch = ced_to_sh_tmu(ced);
+
+	if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced))
+		sh_tmu_disable(ch);
+	return 0;
+}
+
+static int sh_tmu_clock_event_set_state(struct clock_event_device *ced,
+					int periodic)
 {
 	struct sh_tmu_channel *ch = ced_to_sh_tmu(ced);
-	int disabled = 0;
 
 	/* deal with old setting first */
-	switch (ced->mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
+	if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced))
 		sh_tmu_disable(ch);
-		disabled = 1;
-		break;
-	default:
-		break;
-	}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		dev_info(&ch->tmu->pdev->dev,
-			 "ch%u: used for periodic clock events\n", ch->index);
-		sh_tmu_clock_event_start(ch, 1);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		dev_info(&ch->tmu->pdev->dev,
-			 "ch%u: used for oneshot clock events\n", ch->index);
-		sh_tmu_clock_event_start(ch, 0);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-		if (!disabled)
-			sh_tmu_disable(ch);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		break;
-	}
+	dev_info(&ch->tmu->pdev->dev, "ch%u: used for %s clock events\n",
+		 ch->index, periodic ? "periodic" : "oneshot");
+	sh_tmu_clock_event_start(ch, periodic);
+	return 0;
+}
+
+static int sh_tmu_clock_event_set_oneshot(struct clock_event_device *ced)
+{
+	return sh_tmu_clock_event_set_state(ced, 0);
+}
+
+static int sh_tmu_clock_event_set_periodic(struct clock_event_device *ced)
+{
+	return sh_tmu_clock_event_set_state(ced, 1);
 }
 
 static int sh_tmu_clock_event_next(unsigned long delta,
@@ -401,7 +397,7 @@ static int sh_tmu_clock_event_next(unsigned long delta,
 {
 	struct sh_tmu_channel *ch = ced_to_sh_tmu(ced);
 
-	BUG_ON(ced->mode != CLOCK_EVT_MODE_ONESHOT);
+	BUG_ON(!clockevent_state_oneshot(ced));
 
 	/* program new delta value */
 	sh_tmu_set_next(ch, delta, 0);
@@ -430,7 +426,9 @@ static void sh_tmu_register_clockevent(struct sh_tmu_channel *ch,
 	ced->rating = 200;
 	ced->cpumask = cpu_possible_mask;
 	ced->set_next_event = sh_tmu_clock_event_next;
-	ced->set_mode = sh_tmu_clock_event_mode;
+	ced->set_state_shutdown = sh_tmu_clock_event_shutdown;
+	ced->set_state_periodic = sh_tmu_clock_event_set_periodic;
+	ced->set_state_oneshot = sh_tmu_clock_event_set_oneshot;
 	ced->suspend = sh_tmu_clock_event_suspend;
 	ced->resume = sh_tmu_clock_event_resume;
 
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 1928a8912584..6f3719d73390 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -81,25 +81,25 @@ static void sun4i_clkevt_time_start(u8 timer, bool periodic)
 	       timer_base + TIMER_CTL_REG(timer));
 }
 
-static void sun4i_clkevt_mode(enum clock_event_mode mode,
-			      struct clock_event_device *clk)
+static int sun4i_clkevt_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		sun4i_clkevt_time_stop(0);
-		sun4i_clkevt_time_setup(0, ticks_per_jiffy);
-		sun4i_clkevt_time_start(0, true);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		sun4i_clkevt_time_stop(0);
-		sun4i_clkevt_time_start(0, false);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		sun4i_clkevt_time_stop(0);
-		break;
-	}
+	sun4i_clkevt_time_stop(0);
+	return 0;
+}
+
+static int sun4i_clkevt_set_oneshot(struct clock_event_device *evt)
+{
+	sun4i_clkevt_time_stop(0);
+	sun4i_clkevt_time_start(0, false);
+	return 0;
+}
+
+static int sun4i_clkevt_set_periodic(struct clock_event_device *evt)
+{
+	sun4i_clkevt_time_stop(0);
+	sun4i_clkevt_time_setup(0, ticks_per_jiffy);
+	sun4i_clkevt_time_start(0, true);
+	return 0;
 }
 
 static int sun4i_clkevt_next_event(unsigned long evt,
@@ -116,7 +116,10 @@ static struct clock_event_device sun4i_clockevent = {
 	.name = "sun4i_tick",
 	.rating = 350,
 	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = sun4i_clkevt_mode,
+	.set_state_shutdown = sun4i_clkevt_shutdown,
+	.set_state_periodic = sun4i_clkevt_set_periodic,
+	.set_state_oneshot = sun4i_clkevt_set_oneshot,
+	.tick_resume = sun4i_clkevt_shutdown,
 	.set_next_event = sun4i_clkevt_next_event,
 };
 
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 8bdbc45c6dad..d28d2fe798d5 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -91,55 +91,62 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt)
  */
 static u32 timer_clock;
 
-static void tc_mode(enum clock_event_mode m, struct clock_event_device *d)
+static int tc_shutdown(struct clock_event_device *d)
 {
 	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
 	void __iomem		*regs = tcd->regs;
 
-	if (tcd->clkevt.mode == CLOCK_EVT_MODE_PERIODIC
-			|| tcd->clkevt.mode == CLOCK_EVT_MODE_ONESHOT) {
-		__raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
-		__raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
-		clk_disable(tcd->clk);
-	}
+	__raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
+	__raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
+	clk_disable(tcd->clk);
 
-	switch (m) {
+	return 0;
+}
 
-	/* By not making the gentime core emulate periodic mode on top
-	 * of oneshot, we get lower overhead and improved accuracy.
-	 */
-	case CLOCK_EVT_MODE_PERIODIC:
-		clk_enable(tcd->clk);
+static int tc_set_oneshot(struct clock_event_device *d)
+{
+	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+	void __iomem		*regs = tcd->regs;
 
-		/* slow clock, count up to RC, then irq and restart */
-		__raw_writel(timer_clock
-				| ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
-				regs + ATMEL_TC_REG(2, CMR));
-		__raw_writel((32768 + HZ/2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
+	if (clockevent_state_oneshot(d) || clockevent_state_periodic(d))
+		tc_shutdown(d);
 
-		/* Enable clock and interrupts on RC compare */
-		__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
+	clk_enable(tcd->clk);
 
-		/* go go gadget! */
-		__raw_writel(ATMEL_TC_CLKEN | ATMEL_TC_SWTRG,
-				regs + ATMEL_TC_REG(2, CCR));
-		break;
+	/* slow clock, count up to RC, then irq and stop */
+	__raw_writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE |
+		     ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR));
+	__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
 
-	case CLOCK_EVT_MODE_ONESHOT:
-		clk_enable(tcd->clk);
+	/* set_next_event() configures and starts the timer */
+	return 0;
+}
 
-		/* slow clock, count up to RC, then irq and stop */
-		__raw_writel(timer_clock | ATMEL_TC_CPCSTOP
-				| ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
-				regs + ATMEL_TC_REG(2, CMR));
-		__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
+static int tc_set_periodic(struct clock_event_device *d)
+{
+	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+	void __iomem		*regs = tcd->regs;
 
-		/* set_next_event() configures and starts the timer */
-		break;
+	if (clockevent_state_oneshot(d) || clockevent_state_periodic(d))
+		tc_shutdown(d);
 
-	default:
-		break;
-	}
+	/* By not making the gentime core emulate periodic mode on top
+	 * of oneshot, we get lower overhead and improved accuracy.
+	 */
+	clk_enable(tcd->clk);
+
+	/* slow clock, count up to RC, then irq and restart */
+	__raw_writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
+		     regs + ATMEL_TC_REG(2, CMR));
+	__raw_writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
+
+	/* Enable clock and interrupts on RC compare */
+	__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
+
+	/* go go gadget! */
+	__raw_writel(ATMEL_TC_CLKEN | ATMEL_TC_SWTRG, regs +
+		     ATMEL_TC_REG(2, CCR));
+	return 0;
 }
 
 static int tc_next_event(unsigned long delta, struct clock_event_device *d)
@@ -154,13 +161,15 @@ static int tc_next_event(unsigned long delta, struct clock_event_device *d)
 
 static struct tc_clkevt_device clkevt = {
 	.clkevt	= {
-		.name		= "tc_clkevt",
-		.features	= CLOCK_EVT_FEAT_PERIODIC
-					| CLOCK_EVT_FEAT_ONESHOT,
+		.name			= "tc_clkevt",
+		.features		= CLOCK_EVT_FEAT_PERIODIC |
+					  CLOCK_EVT_FEAT_ONESHOT,
 		/* Should be lower than at91rm9200's system timer */
-		.rating		= 125,
-		.set_next_event	= tc_next_event,
-		.set_mode	= tc_mode,
+		.rating			= 125,
+		.set_next_event		= tc_next_event,
+		.set_state_shutdown	= tc_shutdown,
+		.set_state_periodic	= tc_set_periodic,
+		.set_state_oneshot	= tc_set_oneshot,
 	},
 };
 
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index 5a112d72fc2d..6ebda1177e79 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -72,33 +72,36 @@ static int tegra_timer_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void tegra_timer_set_mode(enum clock_event_mode mode,
-				    struct clock_event_device *evt)
+static inline void timer_shutdown(struct clock_event_device *evt)
 {
-	u32 reg;
-
 	timer_writel(0, TIMER3_BASE + TIMER_PTV);
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		reg = 0xC0000000 | ((1000000/HZ)-1);
-		timer_writel(reg, TIMER3_BASE + TIMER_PTV);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+static int tegra_timer_shutdown(struct clock_event_device *evt)
+{
+	timer_shutdown(evt);
+	return 0;
+}
+
+static int tegra_timer_set_periodic(struct clock_event_device *evt)
+{
+	u32 reg = 0xC0000000 | ((1000000 / HZ) - 1);
+
+	timer_shutdown(evt);
+	timer_writel(reg, TIMER3_BASE + TIMER_PTV);
+	return 0;
 }
 
 static struct clock_event_device tegra_clockevent = {
-	.name		= "timer0",
-	.rating		= 300,
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.set_next_event	= tegra_timer_set_next_event,
-	.set_mode	= tegra_timer_set_mode,
+	.name			= "timer0",
+	.rating			= 300,
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.set_next_event		= tegra_timer_set_next_event,
+	.set_state_shutdown	= tegra_timer_shutdown,
+	.set_state_periodic	= tegra_timer_set_periodic,
+	.set_state_oneshot	= tegra_timer_shutdown,
+	.tick_resume		= tegra_timer_shutdown,
 };
 
 static u64 notrace tegra_read_sched_clock(void)
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 0c8c5e337540..2162796fd504 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -121,33 +121,33 @@ armada_370_xp_clkevt_next_event(unsigned long delta,
 	return 0;
 }
 
-static void
-armada_370_xp_clkevt_mode(enum clock_event_mode mode,
-			  struct clock_event_device *dev)
+static int armada_370_xp_clkevt_shutdown(struct clock_event_device *evt)
 {
-	if (mode == CLOCK_EVT_MODE_PERIODIC) {
+	/*
+	 * Disable timer.
+	 */
+	local_timer_ctrl_clrset(TIMER0_EN, 0);
 
-		/*
-		 * Setup timer to fire at 1/HZ intervals.
-		 */
-		writel(ticks_per_jiffy - 1, local_base + TIMER0_RELOAD_OFF);
-		writel(ticks_per_jiffy - 1, local_base + TIMER0_VAL_OFF);
+	/*
+	 * ACK pending timer interrupt.
+	 */
+	writel(TIMER0_CLR_MASK, local_base + LCL_TIMER_EVENTS_STATUS);
+	return 0;
+}
 
-		/*
-		 * Enable timer.
-		 */
-		local_timer_ctrl_clrset(0, TIMER0_RELOAD_EN | enable_mask);
-	} else {
-		/*
-		 * Disable timer.
-		 */
-		local_timer_ctrl_clrset(TIMER0_EN, 0);
+static int armada_370_xp_clkevt_set_periodic(struct clock_event_device *evt)
+{
+	/*
+	 * Setup timer to fire at 1/HZ intervals.
+	 */
+	writel(ticks_per_jiffy - 1, local_base + TIMER0_RELOAD_OFF);
+	writel(ticks_per_jiffy - 1, local_base + TIMER0_VAL_OFF);
 
-		/*
-		 * ACK pending timer interrupt.
-		 */
-		writel(TIMER0_CLR_MASK, local_base + LCL_TIMER_EVENTS_STATUS);
-	}
+	/*
+	 * Enable timer.
+	 */
+	local_timer_ctrl_clrset(0, TIMER0_RELOAD_EN | enable_mask);
+	return 0;
 }
 
 static int armada_370_xp_clkevt_irq;
@@ -185,7 +185,10 @@ static int armada_370_xp_timer_setup(struct clock_event_device *evt)
 	evt->shift		= 32,
 	evt->rating		= 300,
 	evt->set_next_event	= armada_370_xp_clkevt_next_event,
-	evt->set_mode		= armada_370_xp_clkevt_mode,
+	evt->set_state_shutdown	= armada_370_xp_clkevt_shutdown;
+	evt->set_state_periodic	= armada_370_xp_clkevt_set_periodic;
+	evt->set_state_oneshot	= armada_370_xp_clkevt_shutdown;
+	evt->tick_resume	= armada_370_xp_clkevt_shutdown;
 	evt->irq		= armada_370_xp_clkevt_irq;
 	evt->cpumask		= cpumask_of(cpu);
 
@@ -197,7 +200,7 @@ static int armada_370_xp_timer_setup(struct clock_event_device *evt)
 
 static void armada_370_xp_timer_stop(struct clock_event_device *evt)
 {
-	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	evt->set_state_shutdown(evt);
 	disable_percpu_irq(evt->irq);
 }
 
diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c
index 5b6e3d5644c9..b06e4c2be406 100644
--- a/drivers/clocksource/time-efm32.c
+++ b/drivers/clocksource/time-efm32.c
@@ -48,40 +48,42 @@ struct efm32_clock_event_ddata {
 	unsigned periodic_top;
 };
 
-static void efm32_clock_event_set_mode(enum clock_event_mode mode,
-				       struct clock_event_device *evtdev)
+static int efm32_clock_event_shutdown(struct clock_event_device *evtdev)
 {
 	struct efm32_clock_event_ddata *ddata =
 		container_of(evtdev, struct efm32_clock_event_ddata, evtdev);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		writel_relaxed(TIMERn_CMD_STOP, ddata->base + TIMERn_CMD);
-		writel_relaxed(ddata->periodic_top, ddata->base + TIMERn_TOP);
-		writel_relaxed(TIMERn_CTRL_PRESC_1024 |
-			       TIMERn_CTRL_CLKSEL_PRESCHFPERCLK |
-			       TIMERn_CTRL_MODE_DOWN,
-			       ddata->base + TIMERn_CTRL);
-		writel_relaxed(TIMERn_CMD_START, ddata->base + TIMERn_CMD);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		writel_relaxed(TIMERn_CMD_STOP, ddata->base + TIMERn_CMD);
-		writel_relaxed(TIMERn_CTRL_PRESC_1024 |
-			       TIMERn_CTRL_CLKSEL_PRESCHFPERCLK |
-			       TIMERn_CTRL_OSMEN |
-			       TIMERn_CTRL_MODE_DOWN,
-			       ddata->base + TIMERn_CTRL);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		writel_relaxed(TIMERn_CMD_STOP, ddata->base + TIMERn_CMD);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	writel_relaxed(TIMERn_CMD_STOP, ddata->base + TIMERn_CMD);
+	return 0;
+}
+
+static int efm32_clock_event_set_oneshot(struct clock_event_device *evtdev)
+{
+	struct efm32_clock_event_ddata *ddata =
+		container_of(evtdev, struct efm32_clock_event_ddata, evtdev);
+
+	writel_relaxed(TIMERn_CMD_STOP, ddata->base + TIMERn_CMD);
+	writel_relaxed(TIMERn_CTRL_PRESC_1024 |
+		       TIMERn_CTRL_CLKSEL_PRESCHFPERCLK |
+		       TIMERn_CTRL_OSMEN |
+		       TIMERn_CTRL_MODE_DOWN,
+		       ddata->base + TIMERn_CTRL);
+	return 0;
+}
+
+static int efm32_clock_event_set_periodic(struct clock_event_device *evtdev)
+{
+	struct efm32_clock_event_ddata *ddata =
+		container_of(evtdev, struct efm32_clock_event_ddata, evtdev);
+
+	writel_relaxed(TIMERn_CMD_STOP, ddata->base + TIMERn_CMD);
+	writel_relaxed(ddata->periodic_top, ddata->base + TIMERn_TOP);
+	writel_relaxed(TIMERn_CTRL_PRESC_1024 |
+		       TIMERn_CTRL_CLKSEL_PRESCHFPERCLK |
+		       TIMERn_CTRL_MODE_DOWN,
+		       ddata->base + TIMERn_CTRL);
+	writel_relaxed(TIMERn_CMD_START, ddata->base + TIMERn_CMD);
+	return 0;
 }
 
 static int efm32_clock_event_set_next_event(unsigned long evt,
@@ -112,7 +114,9 @@ static struct efm32_clock_event_ddata clock_event_ddata = {
 	.evtdev = {
 		.name = "efm32 clockevent",
 		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-		.set_mode = efm32_clock_event_set_mode,
+		.set_state_shutdown = efm32_clock_event_shutdown,
+		.set_state_periodic = efm32_clock_event_set_periodic,
+		.set_state_oneshot = efm32_clock_event_set_oneshot,
 		.set_next_event = efm32_clock_event_set_next_event,
 		.rating = 200,
 	},
diff --git a/drivers/clocksource/time-orion.c b/drivers/clocksource/time-orion.c
index 0b3ce0399c51..0ece7427b497 100644
--- a/drivers/clocksource/time-orion.c
+++ b/drivers/clocksource/time-orion.c
@@ -60,30 +60,36 @@ static int orion_clkevt_next_event(unsigned long delta,
 	return 0;
 }
 
-static void orion_clkevt_mode(enum clock_event_mode mode,
-			      struct clock_event_device *dev)
+static int orion_clkevt_shutdown(struct clock_event_device *dev)
 {
-	if (mode == CLOCK_EVT_MODE_PERIODIC) {
-		/* setup and enable periodic timer at 1/HZ intervals */
-		writel(ticks_per_jiffy - 1, timer_base + TIMER1_RELOAD);
-		writel(ticks_per_jiffy - 1, timer_base + TIMER1_VAL);
-		atomic_io_modify(timer_base + TIMER_CTRL,
-			TIMER1_RELOAD_EN | TIMER1_EN,
-			TIMER1_RELOAD_EN | TIMER1_EN);
-	} else {
-		/* disable timer */
-		atomic_io_modify(timer_base + TIMER_CTRL,
-			TIMER1_RELOAD_EN | TIMER1_EN, 0);
-	}
+	/* disable timer */
+	atomic_io_modify(timer_base + TIMER_CTRL,
+			 TIMER1_RELOAD_EN | TIMER1_EN, 0);
+	return 0;
+}
+
+static int orion_clkevt_set_periodic(struct clock_event_device *dev)
+{
+	/* setup and enable periodic timer at 1/HZ intervals */
+	writel(ticks_per_jiffy - 1, timer_base + TIMER1_RELOAD);
+	writel(ticks_per_jiffy - 1, timer_base + TIMER1_VAL);
+	atomic_io_modify(timer_base + TIMER_CTRL,
+			 TIMER1_RELOAD_EN | TIMER1_EN,
+			 TIMER1_RELOAD_EN | TIMER1_EN);
+	return 0;
 }
 
 static struct clock_event_device orion_clkevt = {
-	.name		= "orion_event",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.shift		= 32,
-	.rating		= 300,
-	.set_next_event	= orion_clkevt_next_event,
-	.set_mode	= orion_clkevt_mode,
+	.name			= "orion_event",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.shift			= 32,
+	.rating			= 300,
+	.set_next_event		= orion_clkevt_next_event,
+	.set_state_shutdown	= orion_clkevt_shutdown,
+	.set_state_periodic	= orion_clkevt_set_periodic,
+	.set_state_oneshot	= orion_clkevt_shutdown,
+	.tick_resume		= orion_clkevt_shutdown,
 };
 
 static irqreturn_t orion_clkevt_irq_handler(int irq, void *dev_id)
diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c
new file mode 100644
index 000000000000..18d4266c2986
--- /dev/null
+++ b/drivers/clocksource/time-pistachio.c
@@ -0,0 +1,217 @@
+/*
+ * Pistachio clocksource based on general-purpose timers
+ *
+ * Copyright (C) 2015 Imagination Technologies
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/clk.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/sched_clock.h>
+#include <linux/time.h>
+
+/* Top level reg */
+#define CR_TIMER_CTRL_CFG		0x00
+#define TIMER_ME_GLOBAL			BIT(0)
+#define CR_TIMER_REV			0x10
+
+/* Timer specific registers */
+#define TIMER_CFG			0x20
+#define TIMER_ME_LOCAL			BIT(0)
+#define TIMER_RELOAD_VALUE		0x24
+#define TIMER_CURRENT_VALUE		0x28
+#define TIMER_CURRENT_OVERFLOW_VALUE	0x2C
+#define TIMER_IRQ_STATUS		0x30
+#define TIMER_IRQ_CLEAR			0x34
+#define TIMER_IRQ_MASK			0x38
+
+#define PERIP_TIMER_CONTROL		0x90
+
+/* Timer specific configuration Values */
+#define RELOAD_VALUE			0xffffffff
+
+struct pistachio_clocksource {
+	void __iomem *base;
+	raw_spinlock_t lock;
+	struct clocksource cs;
+};
+
+static struct pistachio_clocksource pcs_gpt;
+
+#define to_pistachio_clocksource(cs)	\
+	container_of(cs, struct pistachio_clocksource, cs)
+
+static inline u32 gpt_readl(void __iomem *base, u32 offset, u32 gpt_id)
+{
+	return readl(base + 0x20 * gpt_id + offset);
+}
+
+static inline void gpt_writel(void __iomem *base, u32 value, u32 offset,
+		u32 gpt_id)
+{
+	writel(value, base + 0x20 * gpt_id + offset);
+}
+
+static cycle_t pistachio_clocksource_read_cycles(struct clocksource *cs)
+{
+	struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs);
+	u32 counter, overflw;
+	unsigned long flags;
+
+	/*
+	 * The counter value is only refreshed after the overflow value is read.
+	 * And they must be read in strict order, hence raw spin lock added.
+	 */
+
+	raw_spin_lock_irqsave(&pcs->lock, flags);
+	overflw = gpt_readl(pcs->base, TIMER_CURRENT_OVERFLOW_VALUE, 0);
+	counter = gpt_readl(pcs->base, TIMER_CURRENT_VALUE, 0);
+	raw_spin_unlock_irqrestore(&pcs->lock, flags);
+
+	return ~(cycle_t)counter;
+}
+
+static u64 notrace pistachio_read_sched_clock(void)
+{
+	return pistachio_clocksource_read_cycles(&pcs_gpt.cs);
+}
+
+static void pistachio_clksrc_set_mode(struct clocksource *cs, int timeridx,
+			int enable)
+{
+	struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs);
+	u32 val;
+
+	val = gpt_readl(pcs->base, TIMER_CFG, timeridx);
+	if (enable)
+		val |= TIMER_ME_LOCAL;
+	else
+		val &= ~TIMER_ME_LOCAL;
+
+	gpt_writel(pcs->base, val, TIMER_CFG, timeridx);
+}
+
+static void pistachio_clksrc_enable(struct clocksource *cs, int timeridx)
+{
+	struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs);
+
+	/* Disable GPT local before loading reload value */
+	pistachio_clksrc_set_mode(cs, timeridx, false);
+	gpt_writel(pcs->base, RELOAD_VALUE, TIMER_RELOAD_VALUE, timeridx);
+	pistachio_clksrc_set_mode(cs, timeridx, true);
+}
+
+static void pistachio_clksrc_disable(struct clocksource *cs, int timeridx)
+{
+	/* Disable GPT local */
+	pistachio_clksrc_set_mode(cs, timeridx, false);
+}
+
+static int pistachio_clocksource_enable(struct clocksource *cs)
+{
+	pistachio_clksrc_enable(cs, 0);
+	return 0;
+}
+
+static void pistachio_clocksource_disable(struct clocksource *cs)
+{
+	pistachio_clksrc_disable(cs, 0);
+}
+
+/* Desirable clock source for pistachio platform */
+static struct pistachio_clocksource pcs_gpt = {
+	.cs =	{
+		.name		= "gptimer",
+		.rating		= 300,
+		.enable		= pistachio_clocksource_enable,
+		.disable	= pistachio_clocksource_disable,
+		.read		= pistachio_clocksource_read_cycles,
+		.mask		= CLOCKSOURCE_MASK(32),
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_SUSPEND_NONSTOP,
+		},
+};
+
+static void __init pistachio_clksrc_of_init(struct device_node *node)
+{
+	struct clk *sys_clk, *fast_clk;
+	struct regmap *periph_regs;
+	unsigned long rate;
+	int ret;
+
+	pcs_gpt.base = of_iomap(node, 0);
+	if (!pcs_gpt.base) {
+		pr_err("cannot iomap\n");
+		return;
+	}
+
+	periph_regs = syscon_regmap_lookup_by_phandle(node, "img,cr-periph");
+	if (IS_ERR(periph_regs)) {
+		pr_err("cannot get peripheral regmap (%lu)\n",
+		       PTR_ERR(periph_regs));
+		return;
+	}
+
+	/* Switch to using the fast counter clock */
+	ret = regmap_update_bits(periph_regs, PERIP_TIMER_CONTROL,
+				 0xf, 0x0);
+	if (ret)
+		return;
+
+	sys_clk = of_clk_get_by_name(node, "sys");
+	if (IS_ERR(sys_clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(sys_clk));
+		return;
+	}
+
+	fast_clk = of_clk_get_by_name(node, "fast");
+	if (IS_ERR(fast_clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(fast_clk));
+		return;
+	}
+
+	ret = clk_prepare_enable(sys_clk);
+	if (ret < 0) {
+		pr_err("failed to enable clock (%d)\n", ret);
+		return;
+	}
+
+	ret = clk_prepare_enable(fast_clk);
+	if (ret < 0) {
+		pr_err("failed to enable clock (%d)\n", ret);
+		clk_disable_unprepare(sys_clk);
+		return;
+	}
+
+	rate = clk_get_rate(fast_clk);
+
+	/* Disable irq's for clocksource usage */
+	gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 0);
+	gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 1);
+	gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 2);
+	gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 3);
+
+	/* Enable timer block */
+	writel(TIMER_ME_GLOBAL, pcs_gpt.base);
+
+	raw_spin_lock_init(&pcs_gpt.lock);
+	sched_clock_register(pistachio_read_sched_clock, 32, rate);
+	clocksource_register_hz(&pcs_gpt.cs, rate);
+}
+CLOCKSOURCE_OF_DECLARE(pistachio_gptimer, "img,pistachio-gptimer",
+		       pistachio_clksrc_of_init);
diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c
index 60f9de3438b0..27fa13680be1 100644
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -76,7 +76,7 @@ static irqreturn_t sirfsoc_timer_interrupt(int irq, void *dev_id)
 	/* clear timer interrupt */
 	writel_relaxed(BIT(cpu), sirfsoc_timer_base + SIRFSOC_TIMER_INTR_STATUS);
 
-	if (ce->mode == CLOCK_EVT_MODE_ONESHOT)
+	if (clockevent_state_oneshot(ce))
 		sirfsoc_timer_count_disable(cpu);
 
 	ce->event_handler(ce);
@@ -117,18 +117,11 @@ static int sirfsoc_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void sirfsoc_timer_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *ce)
+/* Oneshot is enabled in set_next_event */
+static int sirfsoc_timer_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* enable in set_next_event */
-		break;
-	default:
-		break;
-	}
-
 	sirfsoc_timer_count_disable(smp_processor_id());
+	return 0;
 }
 
 static void sirfsoc_clocksource_suspend(struct clocksource *cs)
@@ -193,7 +186,9 @@ static int sirfsoc_local_timer_setup(struct clock_event_device *ce)
 	ce->name = "local_timer";
 	ce->features = CLOCK_EVT_FEAT_ONESHOT;
 	ce->rating = 200;
-	ce->set_mode = sirfsoc_timer_set_mode;
+	ce->set_state_shutdown = sirfsoc_timer_shutdown;
+	ce->set_state_oneshot = sirfsoc_timer_shutdown;
+	ce->tick_resume = sirfsoc_timer_shutdown;
 	ce->set_next_event = sirfsoc_timer_set_next_event;
 	clockevents_calc_mult_shift(ce, atlas7_timer_rate, 60);
 	ce->max_delta_ns = clockevent_delta2ns(-2, ce);
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index c0304ff608b0..d911c5dca8f1 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/drivers/clocksource/timer-atmel-pit.c
@@ -90,33 +90,27 @@ static cycle_t read_pit_clk(struct clocksource *cs)
 	return elapsed;
 }
 
+static int pit_clkevt_shutdown(struct clock_event_device *dev)
+{
+	struct pit_data *data = clkevt_to_pit_data(dev);
+
+	/* disable irq, leaving the clocksource active */
+	pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN);
+	return 0;
+}
+
 /*
  * Clockevent device:  interrupts every 1/HZ (== pit_cycles * MCK/16)
  */
-static void
-pit_clkevt_mode(enum clock_event_mode mode, struct clock_event_device *dev)
+static int pit_clkevt_set_periodic(struct clock_event_device *dev)
 {
 	struct pit_data *data = clkevt_to_pit_data(dev);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* update clocksource counter */
-		data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR));
-		pit_write(data->base, AT91_PIT_MR,
-			  (data->cycle - 1) | AT91_PIT_PITEN | AT91_PIT_PITIEN);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		BUG();
-		/* FALLTHROUGH */
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		/* disable irq, leaving the clocksource active */
-		pit_write(data->base, AT91_PIT_MR,
-			  (data->cycle - 1) | AT91_PIT_PITEN);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+	/* update clocksource counter */
+	data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR));
+	pit_write(data->base, AT91_PIT_MR,
+		  (data->cycle - 1) | AT91_PIT_PITEN | AT91_PIT_PITIEN);
+	return 0;
 }
 
 static void at91sam926x_pit_suspend(struct clock_event_device *cedev)
@@ -162,7 +156,7 @@ static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	/* The PIT interrupt may be disabled, and is shared */
-	if ((data->clkevt.mode == CLOCK_EVT_MODE_PERIODIC) &&
+	if (clockevent_state_periodic(&data->clkevt) &&
 	    (pit_read(data->base, AT91_PIT_SR) & AT91_PIT_PITS)) {
 		unsigned nr_ticks;
 
@@ -208,8 +202,8 @@ static void __init at91sam926x_pit_common_init(struct pit_data *data)
 	data->clksrc.mask = CLOCKSOURCE_MASK(bits);
 	data->clksrc.name = "pit";
 	data->clksrc.rating = 175;
-	data->clksrc.read = read_pit_clk,
-	data->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	data->clksrc.read = read_pit_clk;
+	data->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
 	clocksource_register_hz(&data->clksrc, pit_rate);
 
 	/* Set up irq handler */
@@ -227,7 +221,8 @@ static void __init at91sam926x_pit_common_init(struct pit_data *data)
 	data->clkevt.rating = 100;
 	data->clkevt.cpumask = cpumask_of(0);
 
-	data->clkevt.set_mode = pit_clkevt_mode;
+	data->clkevt.set_state_shutdown = pit_clkevt_shutdown;
+	data->clkevt.set_state_periodic = pit_clkevt_set_periodic;
 	data->clkevt.resume = at91sam926x_pit_resume;
 	data->clkevt.suspend = at91sam926x_pit_suspend;
 	clockevents_register_device(&data->clkevt);
diff --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c
index 1692e17e096b..41b7b6dc1d0d 100644
--- a/drivers/clocksource/timer-atmel-st.c
+++ b/drivers/clocksource/timer-atmel-st.c
@@ -106,36 +106,47 @@ static struct clocksource clk32k = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void
-clkevt32k_mode(enum clock_event_mode mode, struct clock_event_device *dev)
+static void clkdev32k_disable_and_flush_irq(void)
 {
 	unsigned int val;
 
 	/* Disable and flush pending timer interrupts */
 	regmap_write(regmap_st, AT91_ST_IDR, AT91_ST_PITS | AT91_ST_ALMS);
 	regmap_read(regmap_st, AT91_ST_SR, &val);
-
 	last_crtr = read_CRTR();
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* PIT for periodic irqs; fixed rate of 1/HZ */
-		irqmask = AT91_ST_PITS;
-		regmap_write(regmap_st, AT91_ST_PIMR, RM9200_TIMER_LATCH);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* ALM for oneshot irqs, set by next_event()
-		 * before 32 seconds have passed
-		 */
-		irqmask = AT91_ST_ALMS;
-		regmap_write(regmap_st, AT91_ST_RTAR, last_crtr);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		irqmask = 0;
-		break;
-	}
+}
+
+static int clkevt32k_shutdown(struct clock_event_device *evt)
+{
+	clkdev32k_disable_and_flush_irq();
+	irqmask = 0;
+	regmap_write(regmap_st, AT91_ST_IER, irqmask);
+	return 0;
+}
+
+static int clkevt32k_set_oneshot(struct clock_event_device *dev)
+{
+	clkdev32k_disable_and_flush_irq();
+
+	/*
+	 * ALM for oneshot irqs, set by next_event()
+	 * before 32 seconds have passed.
+	 */
+	irqmask = AT91_ST_ALMS;
+	regmap_write(regmap_st, AT91_ST_RTAR, last_crtr);
 	regmap_write(regmap_st, AT91_ST_IER, irqmask);
+	return 0;
+}
+
+static int clkevt32k_set_periodic(struct clock_event_device *dev)
+{
+	clkdev32k_disable_and_flush_irq();
+
+	/* PIT for periodic irqs; fixed rate of 1/HZ */
+	irqmask = AT91_ST_PITS;
+	regmap_write(regmap_st, AT91_ST_PIMR, RM9200_TIMER_LATCH);
+	regmap_write(regmap_st, AT91_ST_IER, irqmask);
+	return 0;
 }
 
 static int
@@ -170,11 +181,15 @@ clkevt32k_next_event(unsigned long delta, struct clock_event_device *dev)
 }
 
 static struct clock_event_device clkevt = {
-	.name		= "at91_tick",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 150,
-	.set_next_event	= clkevt32k_next_event,
-	.set_mode	= clkevt32k_mode,
+	.name			= "at91_tick",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 150,
+	.set_next_event		= clkevt32k_next_event,
+	.set_state_shutdown	= clkevt32k_shutdown,
+	.set_state_periodic	= clkevt32k_set_periodic,
+	.set_state_oneshot	= clkevt32k_set_oneshot,
+	.tick_resume		= clkevt32k_shutdown,
 };
 
 /*
diff --git a/drivers/clocksource/timer-digicolor.c b/drivers/clocksource/timer-digicolor.c
index 7f8388cfa810..e73947f0f86d 100644
--- a/drivers/clocksource/timer-digicolor.c
+++ b/drivers/clocksource/timer-digicolor.c
@@ -87,27 +87,27 @@ static inline void dc_timer_set_count(struct clock_event_device *ce,
 	writel(count, dt->base + COUNT(dt->timer_id));
 }
 
-static void digicolor_clkevt_mode(enum clock_event_mode mode,
-				  struct clock_event_device *ce)
+static int digicolor_clkevt_shutdown(struct clock_event_device *ce)
+{
+	dc_timer_disable(ce);
+	return 0;
+}
+
+static int digicolor_clkevt_set_oneshot(struct clock_event_device *ce)
+{
+	dc_timer_disable(ce);
+	dc_timer_enable(ce, CONTROL_MODE_ONESHOT);
+	return 0;
+}
+
+static int digicolor_clkevt_set_periodic(struct clock_event_device *ce)
 {
 	struct digicolor_timer *dt = dc_timer(ce);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		dc_timer_disable(ce);
-		dc_timer_set_count(ce, dt->ticks_per_jiffy);
-		dc_timer_enable(ce, CONTROL_MODE_PERIODIC);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		dc_timer_disable(ce);
-		dc_timer_enable(ce, CONTROL_MODE_ONESHOT);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		dc_timer_disable(ce);
-		break;
-	}
+	dc_timer_disable(ce);
+	dc_timer_set_count(ce, dt->ticks_per_jiffy);
+	dc_timer_enable(ce, CONTROL_MODE_PERIODIC);
+	return 0;
 }
 
 static int digicolor_clkevt_next_event(unsigned long evt,
@@ -125,7 +125,10 @@ static struct digicolor_timer dc_timer_dev = {
 		.name = "digicolor_tick",
 		.rating = 340,
 		.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-		.set_mode = digicolor_clkevt_mode,
+		.set_state_shutdown = digicolor_clkevt_shutdown,
+		.set_state_periodic = digicolor_clkevt_set_periodic,
+		.set_state_oneshot = digicolor_clkevt_set_oneshot,
+		.tick_resume = digicolor_clkevt_shutdown,
 		.set_next_event = digicolor_clkevt_next_event,
 	},
 	.timer_id = TIMER_C,
diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c
index 879c78423546..839aba92fc39 100644
--- a/drivers/clocksource/timer-imx-gpt.c
+++ b/drivers/clocksource/timer-imx-gpt.c
@@ -83,7 +83,6 @@ struct imx_timer {
 	struct clk *clk_ipg;
 	const struct imx_gpt_data *gpt;
 	struct clock_event_device ced;
-	enum clock_event_mode cem;
 	struct irqaction act;
 };
 
@@ -212,18 +211,38 @@ static int v2_set_next_event(unsigned long evt,
 				-ETIME : 0;
 }
 
+static int mxc_shutdown(struct clock_event_device *ced)
+{
+	struct imx_timer *imxtm = to_imx_timer(ced);
+	unsigned long flags;
+	u32 tcn;
+
+	/*
+	 * The timer interrupt generation is disabled at least
+	 * for enough time to call mxc_set_next_event()
+	 */
+	local_irq_save(flags);
+
+	/* Disable interrupt in GPT module */
+	imxtm->gpt->gpt_irq_disable(imxtm);
+
+	tcn = readl_relaxed(imxtm->base + imxtm->gpt->reg_tcn);
+	/* Set event time into far-far future */
+	writel_relaxed(tcn - 3, imxtm->base + imxtm->gpt->reg_tcmp);
+
+	/* Clear pending interrupt */
+	imxtm->gpt->gpt_irq_acknowledge(imxtm);
+
 #ifdef DEBUG
-static const char *clock_event_mode_label[] = {
-	[CLOCK_EVT_MODE_PERIODIC] = "CLOCK_EVT_MODE_PERIODIC",
-	[CLOCK_EVT_MODE_ONESHOT]  = "CLOCK_EVT_MODE_ONESHOT",
-	[CLOCK_EVT_MODE_SHUTDOWN] = "CLOCK_EVT_MODE_SHUTDOWN",
-	[CLOCK_EVT_MODE_UNUSED]   = "CLOCK_EVT_MODE_UNUSED",
-	[CLOCK_EVT_MODE_RESUME]   = "CLOCK_EVT_MODE_RESUME",
-};
+	printk(KERN_INFO "%s: changing mode\n", __func__);
 #endif /* DEBUG */
 
-static void mxc_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *ced)
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+static int mxc_set_oneshot(struct clock_event_device *ced)
 {
 	struct imx_timer *imxtm = to_imx_timer(ced);
 	unsigned long flags;
@@ -237,7 +256,7 @@ static void mxc_set_mode(enum clock_event_mode mode,
 	/* Disable interrupt in GPT module */
 	imxtm->gpt->gpt_irq_disable(imxtm);
 
-	if (mode != imxtm->cem) {
+	if (!clockevent_state_oneshot(ced)) {
 		u32 tcn = readl_relaxed(imxtm->base + imxtm->gpt->reg_tcn);
 		/* Set event time into far-far future */
 		writel_relaxed(tcn - 3, imxtm->base + imxtm->gpt->reg_tcmp);
@@ -247,37 +266,19 @@ static void mxc_set_mode(enum clock_event_mode mode,
 	}
 
 #ifdef DEBUG
-	printk(KERN_INFO "mxc_set_mode: changing mode from %s to %s\n",
-		clock_event_mode_label[imxtm->cem],
-		clock_event_mode_label[mode]);
+	printk(KERN_INFO "%s: changing mode\n", __func__);
 #endif /* DEBUG */
 
-	/* Remember timer mode */
-	imxtm->cem = mode;
-	local_irq_restore(flags);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		printk(KERN_ERR"mxc_set_mode: Periodic mode is not "
-				"supported for i.MX\n");
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
 	/*
 	 * Do not put overhead of interrupt enable/disable into
 	 * mxc_set_next_event(), the core has about 4 minutes
 	 * to call mxc_set_next_event() or shutdown clock after
 	 * mode switching
 	 */
-		local_irq_save(flags);
-		imxtm->gpt->gpt_irq_enable(imxtm);
-		local_irq_restore(flags);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		/* Left event sources disabled, no more interrupts appear */
-		break;
-	}
+	imxtm->gpt->gpt_irq_enable(imxtm);
+	local_irq_restore(flags);
+
+	return 0;
 }
 
 /*
@@ -303,11 +304,11 @@ static int __init mxc_clockevent_init(struct imx_timer *imxtm)
 	struct clock_event_device *ced = &imxtm->ced;
 	struct irqaction *act = &imxtm->act;
 
-	imxtm->cem = CLOCK_EVT_MODE_UNUSED;
-
 	ced->name = "mxc_timer1";
 	ced->features = CLOCK_EVT_FEAT_ONESHOT;
-	ced->set_mode = mxc_set_mode;
+	ced->set_state_shutdown = mxc_shutdown;
+	ced->set_state_oneshot = mxc_set_oneshot;
+	ced->tick_resume = mxc_shutdown;
 	ced->set_next_event = imxtm->gpt->set_next_event;
 	ced->rating = 200;
 	ced->cpumask = cpumask_of(0);
@@ -462,6 +463,7 @@ void __init mxc_timer_init(unsigned long pbase, int irq, enum imx_gpt_type type)
 	BUG_ON(!imxtm->base);
 
 	imxtm->type = type;
+	imxtm->irq = irq;
 
 	_mxc_timer_init(imxtm);
 }
@@ -529,6 +531,7 @@ static void __init imx6dl_timer_init_dt(struct device_node *np)
 
 CLOCKSOURCE_OF_DECLARE(imx1_timer, "fsl,imx1-gpt", imx1_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx21_timer, "fsl,imx21-gpt", imx21_timer_init_dt);
+CLOCKSOURCE_OF_DECLARE(imx27_timer, "fsl,imx27-gpt", imx21_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx31_timer, "fsl,imx31-gpt", imx31_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx25_timer, "fsl,imx25-gpt", imx31_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx50_timer, "fsl,imx50-gpt", imx31_timer_init_dt);
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index a68866e0ecd4..3f59ac2180dc 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -75,33 +75,37 @@ static irqreturn_t integrator_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void clkevt_set_mode(enum clock_event_mode mode, struct clock_event_device *evt)
+static int clkevt_shutdown(struct clock_event_device *evt)
 {
 	u32 ctrl = readl(clkevt_base + TIMER_CTRL) & ~TIMER_CTRL_ENABLE;
 
 	/* Disable timer */
 	writel(ctrl, clkevt_base + TIMER_CTRL);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* Enable the timer and start the periodic tick */
-		writel(timer_reload, clkevt_base + TIMER_LOAD);
-		ctrl |= TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE;
-		writel(ctrl, clkevt_base + TIMER_CTRL);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Leave the timer disabled, .set_next_event will enable it */
-		ctrl &= ~TIMER_CTRL_PERIODIC;
-		writel(ctrl, clkevt_base + TIMER_CTRL);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-	default:
-		/* Just leave in disabled state */
-		break;
-	}
+static int clkevt_set_oneshot(struct clock_event_device *evt)
+{
+	u32 ctrl = readl(clkevt_base + TIMER_CTRL) &
+		   ~(TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC);
+
+	/* Leave the timer disabled, .set_next_event will enable it */
+	writel(ctrl, clkevt_base + TIMER_CTRL);
+	return 0;
+}
 
+static int clkevt_set_periodic(struct clock_event_device *evt)
+{
+	u32 ctrl = readl(clkevt_base + TIMER_CTRL) & ~TIMER_CTRL_ENABLE;
+
+	/* Disable timer */
+	writel(ctrl, clkevt_base + TIMER_CTRL);
+
+	/* Enable the timer and start the periodic tick */
+	writel(timer_reload, clkevt_base + TIMER_LOAD);
+	ctrl |= TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE;
+	writel(ctrl, clkevt_base + TIMER_CTRL);
+	return 0;
 }
 
 static int clkevt_set_next_event(unsigned long next, struct clock_event_device *evt)
@@ -116,11 +120,15 @@ static int clkevt_set_next_event(unsigned long next, struct clock_event_device *
 }
 
 static struct clock_event_device integrator_clockevent = {
-	.name		= "timer1",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= clkevt_set_mode,
-	.set_next_event	= clkevt_set_next_event,
-	.rating		= 300,
+	.name			= "timer1",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= clkevt_shutdown,
+	.set_state_periodic	= clkevt_set_periodic,
+	.set_state_oneshot	= clkevt_set_oneshot,
+	.tick_resume		= clkevt_shutdown,
+	.set_next_event		= clkevt_set_next_event,
+	.rating			= 300,
 };
 
 static struct irqaction integrator_timer_irq = {
diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
index 0250354f7e55..edacf3902e10 100644
--- a/drivers/clocksource/timer-keystone.c
+++ b/drivers/clocksource/timer-keystone.c
@@ -72,10 +72,10 @@ static inline void keystone_timer_barrier(void)
 
 /**
  * keystone_timer_config: configures timer to work in oneshot/periodic modes.
- * @ mode: mode to configure
+ * @ mask: mask of the mode to configure
  * @ period: cycles number to configure for
  */
-static int keystone_timer_config(u64 period, enum clock_event_mode mode)
+static int keystone_timer_config(u64 period, int mask)
 {
 	u32 tcr;
 	u32 off;
@@ -84,16 +84,7 @@ static int keystone_timer_config(u64 period, enum clock_event_mode mode)
 	off = tcr & ~(TCR_ENAMODE_MASK);
 
 	/* set enable mode */
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		tcr |= TCR_ENAMODE_ONESHOT_MASK;
-		break;
-	case CLOCK_EVT_MODE_PERIODIC:
-		tcr |= TCR_ENAMODE_PERIODIC_MASK;
-		break;
-	default:
-		return -1;
-	}
+	tcr |= mask;
 
 	/* disable timer */
 	keystone_timer_writel(off, TCR);
@@ -138,24 +129,19 @@ static irqreturn_t keystone_timer_interrupt(int irq, void *dev_id)
 static int keystone_set_next_event(unsigned long cycles,
 				  struct clock_event_device *evt)
 {
-	return keystone_timer_config(cycles, evt->mode);
+	return keystone_timer_config(cycles, TCR_ENAMODE_ONESHOT_MASK);
 }
 
-static void keystone_set_mode(enum clock_event_mode mode,
-			     struct clock_event_device *evt)
+static int keystone_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		keystone_timer_config(timer.hz_period, CLOCK_EVT_MODE_PERIODIC);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_ONESHOT:
-		keystone_timer_disable();
-		break;
-	default:
-		break;
-	}
+	keystone_timer_disable();
+	return 0;
+}
+
+static int keystone_set_periodic(struct clock_event_device *evt)
+{
+	keystone_timer_config(timer.hz_period, TCR_ENAMODE_PERIODIC_MASK);
+	return 0;
 }
 
 static void __init keystone_timer_init(struct device_node *np)
@@ -222,7 +208,9 @@ static void __init keystone_timer_init(struct device_node *np)
 	/* setup clockevent */
 	event_dev->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	event_dev->set_next_event = keystone_set_next_event;
-	event_dev->set_mode = keystone_set_mode;
+	event_dev->set_state_shutdown = keystone_shutdown;
+	event_dev->set_state_periodic = keystone_set_periodic;
+	event_dev->set_state_oneshot = keystone_shutdown;
 	event_dev->cpumask = cpu_all_mask;
 	event_dev->owner = THIS_MODULE;
 	event_dev->name = TIMER_NAME;
diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c
index ce18d570e1cd..78de982cc640 100644
--- a/drivers/clocksource/timer-prima2.c
+++ b/drivers/clocksource/timer-prima2.c
@@ -104,26 +104,21 @@ static int sirfsoc_timer_set_next_event(unsigned long delta,
 	return next - now > delta ? -ETIME : 0;
 }
 
-static void sirfsoc_timer_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *ce)
+static int sirfsoc_timer_shutdown(struct clock_event_device *evt)
 {
 	u32 val = readl_relaxed(sirfsoc_timer_base + SIRFSOC_TIMER_INT_EN);
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		WARN_ON(1);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		writel_relaxed(val | BIT(0),
-			sirfsoc_timer_base + SIRFSOC_TIMER_INT_EN);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		writel_relaxed(val & ~BIT(0),
-			sirfsoc_timer_base + SIRFSOC_TIMER_INT_EN);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
+
+	writel_relaxed(val & ~BIT(0),
+		       sirfsoc_timer_base + SIRFSOC_TIMER_INT_EN);
+	return 0;
+}
+
+static int sirfsoc_timer_set_oneshot(struct clock_event_device *evt)
+{
+	u32 val = readl_relaxed(sirfsoc_timer_base + SIRFSOC_TIMER_INT_EN);
+
+	writel_relaxed(val | BIT(0), sirfsoc_timer_base + SIRFSOC_TIMER_INT_EN);
+	return 0;
 }
 
 static void sirfsoc_clocksource_suspend(struct clocksource *cs)
@@ -157,7 +152,8 @@ static struct clock_event_device sirfsoc_clockevent = {
 	.name = "sirfsoc_clockevent",
 	.rating = 200,
 	.features = CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = sirfsoc_timer_set_mode,
+	.set_state_shutdown = sirfsoc_timer_shutdown,
+	.set_state_oneshot = sirfsoc_timer_set_oneshot,
 	.set_next_event = sirfsoc_timer_set_next_event,
 };
 
diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c
index ca02503f17d1..5f45b9adef60 100644
--- a/drivers/clocksource/timer-sp804.c
+++ b/drivers/clocksource/timer-sp804.c
@@ -133,50 +133,50 @@ static irqreturn_t sp804_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void sp804_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *evt)
+static inline void timer_shutdown(struct clock_event_device *evt)
 {
-	unsigned long ctrl = TIMER_CTRL_32BIT | TIMER_CTRL_IE;
+	writel(0, clkevt_base + TIMER_CTRL);
+}
 
-	writel(ctrl, clkevt_base + TIMER_CTRL);
+static int sp804_shutdown(struct clock_event_device *evt)
+{
+	timer_shutdown(evt);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		writel(clkevt_reload, clkevt_base + TIMER_LOAD);
-		ctrl |= TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE;
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* period set, and timer enabled in 'next_event' hook */
-		ctrl |= TIMER_CTRL_ONESHOT;
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		break;
-	}
+static int sp804_set_periodic(struct clock_event_device *evt)
+{
+	unsigned long ctrl = TIMER_CTRL_32BIT | TIMER_CTRL_IE |
+			     TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE;
 
+	timer_shutdown(evt);
+	writel(clkevt_reload, clkevt_base + TIMER_LOAD);
 	writel(ctrl, clkevt_base + TIMER_CTRL);
+	return 0;
 }
 
 static int sp804_set_next_event(unsigned long next,
 	struct clock_event_device *evt)
 {
-	unsigned long ctrl = readl(clkevt_base + TIMER_CTRL);
+	unsigned long ctrl = TIMER_CTRL_32BIT | TIMER_CTRL_IE |
+			     TIMER_CTRL_ONESHOT | TIMER_CTRL_ENABLE;
 
 	writel(next, clkevt_base + TIMER_LOAD);
-	writel(ctrl | TIMER_CTRL_ENABLE, clkevt_base + TIMER_CTRL);
+	writel(ctrl, clkevt_base + TIMER_CTRL);
 
 	return 0;
 }
 
 static struct clock_event_device sp804_clockevent = {
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
-		CLOCK_EVT_FEAT_DYNIRQ,
-	.set_mode	= sp804_set_mode,
-	.set_next_event	= sp804_set_next_event,
-	.rating		= 300,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_DYNIRQ,
+	.set_state_shutdown	= sp804_shutdown,
+	.set_state_periodic	= sp804_set_periodic,
+	.set_state_oneshot	= sp804_shutdown,
+	.tick_resume		= sp804_shutdown,
+	.set_next_event		= sp804_set_next_event,
+	.rating			= 300,
 };
 
 static struct irqaction sp804_timer_irq = {
diff --git a/drivers/clocksource/timer-stm32.c b/drivers/clocksource/timer-stm32.c
index a97e8b50701c..f3dcb76799b4 100644
--- a/drivers/clocksource/timer-stm32.c
+++ b/drivers/clocksource/timer-stm32.c
@@ -40,24 +40,25 @@ struct stm32_clock_event_ddata {
 	void __iomem *base;
 };
 
-static void stm32_clock_event_set_mode(enum clock_event_mode mode,
-				       struct clock_event_device *evtdev)
+static int stm32_clock_event_shutdown(struct clock_event_device *evtdev)
 {
 	struct stm32_clock_event_ddata *data =
 		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
 	void *base = data->base;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		writel_relaxed(data->periodic_top, base + TIM_ARR);
-		writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
-		break;
+	writel_relaxed(0, base + TIM_CR1);
+	return 0;
+}
 
-	case CLOCK_EVT_MODE_ONESHOT:
-	default:
-		writel_relaxed(0, base + TIM_CR1);
-		break;
-	}
+static int stm32_clock_event_set_periodic(struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+	void *base = data->base;
+
+	writel_relaxed(data->periodic_top, base + TIM_ARR);
+	writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
+	return 0;
 }
 
 static int stm32_clock_event_set_next_event(unsigned long evt,
@@ -88,7 +89,10 @@ static struct stm32_clock_event_ddata clock_event_ddata = {
 	.evtdev = {
 		.name = "stm32 clockevent",
 		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-		.set_mode = stm32_clock_event_set_mode,
+		.set_state_shutdown = stm32_clock_event_shutdown,
+		.set_state_periodic = stm32_clock_event_set_periodic,
+		.set_state_oneshot = stm32_clock_event_shutdown,
+		.tick_resume = stm32_clock_event_shutdown,
 		.set_next_event = stm32_clock_event_set_next_event,
 		.rating = 200,
 	},
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 0ffb4ea7c925..bca9573e036a 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -103,27 +103,31 @@ static void sun5i_clkevt_time_start(struct sun5i_timer_clkevt *ce, u8 timer, boo
 	       ce->timer.base + TIMER_CTL_REG(timer));
 }
 
-static void sun5i_clkevt_mode(enum clock_event_mode mode,
-			      struct clock_event_device *clkevt)
+static int sun5i_clkevt_shutdown(struct clock_event_device *clkevt)
 {
 	struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		sun5i_clkevt_time_stop(ce, 0);
-		sun5i_clkevt_time_setup(ce, 0, ce->timer.ticks_per_jiffy);
-		sun5i_clkevt_time_start(ce, 0, true);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		sun5i_clkevt_time_stop(ce, 0);
-		sun5i_clkevt_time_start(ce, 0, false);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	default:
-		sun5i_clkevt_time_stop(ce, 0);
-		break;
-	}
+	sun5i_clkevt_time_stop(ce, 0);
+	return 0;
+}
+
+static int sun5i_clkevt_set_oneshot(struct clock_event_device *clkevt)
+{
+	struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt);
+
+	sun5i_clkevt_time_stop(ce, 0);
+	sun5i_clkevt_time_start(ce, 0, false);
+	return 0;
+}
+
+static int sun5i_clkevt_set_periodic(struct clock_event_device *clkevt)
+{
+	struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt);
+
+	sun5i_clkevt_time_stop(ce, 0);
+	sun5i_clkevt_time_setup(ce, 0, ce->timer.ticks_per_jiffy);
+	sun5i_clkevt_time_start(ce, 0, true);
+	return 0;
 }
 
 static int sun5i_clkevt_next_event(unsigned long evt,
@@ -286,7 +290,10 @@ static int __init sun5i_setup_clockevent(struct device_node *node, void __iomem
 	ce->clkevt.name = node->name;
 	ce->clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	ce->clkevt.set_next_event = sun5i_clkevt_next_event;
-	ce->clkevt.set_mode = sun5i_clkevt_mode;
+	ce->clkevt.set_state_shutdown = sun5i_clkevt_shutdown;
+	ce->clkevt.set_state_periodic = sun5i_clkevt_set_periodic;
+	ce->clkevt.set_state_oneshot = sun5i_clkevt_set_oneshot;
+	ce->clkevt.tick_resume = sun5i_clkevt_shutdown;
 	ce->clkevt.rating = 340;
 	ce->clkevt.irq = irq;
 	ce->clkevt.cpumask = cpu_possible_mask;
diff --git a/drivers/clocksource/timer-u300.c b/drivers/clocksource/timer-u300.c
index 5dcf756970e7..1744b243898a 100644
--- a/drivers/clocksource/timer-u300.c
+++ b/drivers/clocksource/timer-u300.c
@@ -187,85 +187,82 @@ struct u300_clockevent_data {
 	unsigned ticks_per_jiffy;
 };
 
+static int u300_shutdown(struct clock_event_device *evt)
+{
+	/* Disable interrupts on GP1 */
+	writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
+	       u300_timer_base + U300_TIMER_APP_GPT1IE);
+	/* Disable GP1 */
+	writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
+	       u300_timer_base + U300_TIMER_APP_DGPT1);
+	return 0;
+}
+
 /*
- * The u300_set_mode() function is always called first, if we
- * have oneshot timer active, the oneshot scheduling function
+ * If we have oneshot timer active, the oneshot scheduling function
  * u300_set_next_event() is called immediately after.
  */
-static void u300_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt)
+static int u300_set_oneshot(struct clock_event_device *evt)
+{
+	/* Just return; here? */
+	/*
+	 * The actual event will be programmed by the next event hook,
+	 * so we just set a dummy value somewhere at the end of the
+	 * universe here.
+	 */
+	/* Disable interrupts on GPT1 */
+	writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
+	       u300_timer_base + U300_TIMER_APP_GPT1IE);
+	/* Disable GP1 while we're reprogramming it. */
+	writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
+	       u300_timer_base + U300_TIMER_APP_DGPT1);
+	/*
+	 * Expire far in the future, u300_set_next_event() will be
+	 * called soon...
+	 */
+	writel(0xFFFFFFFF, u300_timer_base + U300_TIMER_APP_GPT1TC);
+	/* We run one shot per tick here! */
+	writel(U300_TIMER_APP_SGPT1M_MODE_ONE_SHOT,
+	       u300_timer_base + U300_TIMER_APP_SGPT1M);
+	/* Enable interrupts for this timer */
+	writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
+	       u300_timer_base + U300_TIMER_APP_GPT1IE);
+	/* Enable timer */
+	writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
+	       u300_timer_base + U300_TIMER_APP_EGPT1);
+	return 0;
+}
+
+static int u300_set_periodic(struct clock_event_device *evt)
 {
 	struct u300_clockevent_data *cevdata =
 		container_of(evt, struct u300_clockevent_data, cevd);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		/* Disable interrupts on GPT1 */
-		writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-		       u300_timer_base + U300_TIMER_APP_GPT1IE);
-		/* Disable GP1 while we're reprogramming it. */
-		writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-		       u300_timer_base + U300_TIMER_APP_DGPT1);
-		/*
-		 * Set the periodic mode to a certain number of ticks per
-		 * jiffy.
-		 */
-		writel(cevdata->ticks_per_jiffy,
-		       u300_timer_base + U300_TIMER_APP_GPT1TC);
-		/*
-		 * Set continuous mode, so the timer keeps triggering
-		 * interrupts.
-		 */
-		writel(U300_TIMER_APP_SGPT1M_MODE_CONTINUOUS,
-		       u300_timer_base + U300_TIMER_APP_SGPT1M);
-		/* Enable timer interrupts */
-		writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
-		       u300_timer_base + U300_TIMER_APP_GPT1IE);
-		/* Then enable the OS timer again */
-		writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
-		       u300_timer_base + U300_TIMER_APP_EGPT1);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Just break; here? */
-		/*
-		 * The actual event will be programmed by the next event hook,
-		 * so we just set a dummy value somewhere at the end of the
-		 * universe here.
-		 */
-		/* Disable interrupts on GPT1 */
-		writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-		       u300_timer_base + U300_TIMER_APP_GPT1IE);
-		/* Disable GP1 while we're reprogramming it. */
-		writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-		       u300_timer_base + U300_TIMER_APP_DGPT1);
-		/*
-		 * Expire far in the future, u300_set_next_event() will be
-		 * called soon...
-		 */
-		writel(0xFFFFFFFF, u300_timer_base + U300_TIMER_APP_GPT1TC);
-		/* We run one shot per tick here! */
-		writel(U300_TIMER_APP_SGPT1M_MODE_ONE_SHOT,
-		       u300_timer_base + U300_TIMER_APP_SGPT1M);
-		/* Enable interrupts for this timer */
-		writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
-		       u300_timer_base + U300_TIMER_APP_GPT1IE);
-		/* Enable timer */
-		writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
-		       u300_timer_base + U300_TIMER_APP_EGPT1);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/* Disable interrupts on GP1 */
-		writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-		       u300_timer_base + U300_TIMER_APP_GPT1IE);
-		/* Disable GP1 */
-		writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-		       u300_timer_base + U300_TIMER_APP_DGPT1);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		/* Ignore this call */
-		break;
-	}
+	/* Disable interrupts on GPT1 */
+	writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
+	       u300_timer_base + U300_TIMER_APP_GPT1IE);
+	/* Disable GP1 while we're reprogramming it. */
+	writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
+	       u300_timer_base + U300_TIMER_APP_DGPT1);
+	/*
+	 * Set the periodic mode to a certain number of ticks per
+	 * jiffy.
+	 */
+	writel(cevdata->ticks_per_jiffy,
+	       u300_timer_base + U300_TIMER_APP_GPT1TC);
+	/*
+	 * Set continuous mode, so the timer keeps triggering
+	 * interrupts.
+	 */
+	writel(U300_TIMER_APP_SGPT1M_MODE_CONTINUOUS,
+	       u300_timer_base + U300_TIMER_APP_SGPT1M);
+	/* Enable timer interrupts */
+	writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
+	       u300_timer_base + U300_TIMER_APP_GPT1IE);
+	/* Then enable the OS timer again */
+	writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
+	       u300_timer_base + U300_TIMER_APP_EGPT1);
+	return 0;
 }
 
 /*
@@ -309,13 +306,15 @@ static int u300_set_next_event(unsigned long cycles,
 static struct u300_clockevent_data u300_clockevent_data = {
 	/* Use general purpose timer 1 as clock event */
 	.cevd = {
-		.name		= "GPT1",
+		.name			= "GPT1",
 		/* Reasonably fast and accurate clock event */
-		.rating		= 300,
-		.features	= CLOCK_EVT_FEAT_PERIODIC |
-			CLOCK_EVT_FEAT_ONESHOT,
-		.set_next_event	= u300_set_next_event,
-		.set_mode	= u300_set_mode,
+		.rating			= 300,
+		.features		= CLOCK_EVT_FEAT_PERIODIC |
+					  CLOCK_EVT_FEAT_ONESHOT,
+		.set_next_event		= u300_set_next_event,
+		.set_state_shutdown	= u300_shutdown,
+		.set_state_periodic	= u300_set_periodic,
+		.set_state_oneshot	= u300_set_oneshot,
 	},
 };
 
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
index b45ac6229b57..f07ba9932171 100644
--- a/drivers/clocksource/vf_pit_timer.c
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -86,20 +86,16 @@ static int pit_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void pit_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int pit_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		pit_set_next_event(cycle_per_jiffy, evt);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		pit_timer_disable();
-		break;
-	default:
-		break;
-	}
+	pit_timer_disable();
+	return 0;
+}
+
+static int pit_set_periodic(struct clock_event_device *evt)
+{
+	pit_set_next_event(cycle_per_jiffy, evt);
+	return 0;
 }
 
 static irqreturn_t pit_timer_interrupt(int irq, void *dev_id)
@@ -114,7 +110,7 @@ static irqreturn_t pit_timer_interrupt(int irq, void *dev_id)
 	 * and start the counter again. So software need to disable the timer
 	 * to stop the counter loop in ONESHOT mode.
 	 */
-	if (likely(evt->mode == CLOCK_EVT_MODE_ONESHOT))
+	if (likely(clockevent_state_oneshot(evt)))
 		pit_timer_disable();
 
 	evt->event_handler(evt);
@@ -125,7 +121,8 @@ static irqreturn_t pit_timer_interrupt(int irq, void *dev_id)
 static struct clock_event_device clockevent_pit = {
 	.name		= "VF pit timer",
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= pit_set_mode,
+	.set_state_shutdown = pit_shutdown,
+	.set_state_periodic = pit_set_periodic,
 	.set_next_event	= pit_set_next_event,
 	.rating		= 300,
 };
diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c
index 1098ed3b9b89..a92e94b40b5b 100644
--- a/drivers/clocksource/vt8500_timer.c
+++ b/drivers/clocksource/vt8500_timer.c
@@ -88,29 +88,20 @@ static int vt8500_timer_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void vt8500_timer_set_mode(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int vt8500_shutdown(struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		writel(readl(regbase + TIMER_CTRL_VAL) | 1,
-			regbase + TIMER_CTRL_VAL);
-		writel(0, regbase + TIMER_IER_VAL);
-		break;
-	}
+	writel(readl(regbase + TIMER_CTRL_VAL) | 1, regbase + TIMER_CTRL_VAL);
+	writel(0, regbase + TIMER_IER_VAL);
+	return 0;
 }
 
 static struct clock_event_device clockevent = {
-	.name           = "vt8500_timer",
-	.features       = CLOCK_EVT_FEAT_ONESHOT,
-	.rating         = 200,
-	.set_next_event = vt8500_timer_set_next_event,
-	.set_mode       = vt8500_timer_set_mode,
+	.name			= "vt8500_timer",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= vt8500_timer_set_next_event,
+	.set_state_shutdown	= vt8500_shutdown,
+	.set_state_oneshot	= vt8500_shutdown,
 };
 
 static irqreturn_t vt8500_timer_interrupt(int irq, void *dev_id)
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
index 7ce442148c3f..ceaa6133f9c2 100644
--- a/drivers/clocksource/zevio-timer.c
+++ b/drivers/clocksource/zevio-timer.c
@@ -76,32 +76,28 @@ static int zevio_timer_set_event(unsigned long delta,
 	return 0;
 }
 
-static void zevio_timer_set_mode(enum clock_event_mode mode,
-				 struct clock_event_device *dev)
+static int zevio_timer_shutdown(struct clock_event_device *dev)
 {
 	struct zevio_timer *timer = container_of(dev, struct zevio_timer,
 						 clkevt);
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* Enable timer interrupts */
-		writel(TIMER_INTR_MSK, timer->interrupt_regs + IO_INTR_MSK);
-		writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		/* Disable timer interrupts */
-		writel(0, timer->interrupt_regs + IO_INTR_MSK);
-		writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
-		/* Stop timer */
-		writel(CNTL_STOP_TIMER, timer->timer1 + IO_CONTROL);
-		break;
-	case CLOCK_EVT_MODE_PERIODIC:
-	default:
-		/* Unsupported */
-		break;
-	}
+	/* Disable timer interrupts */
+	writel(0, timer->interrupt_regs + IO_INTR_MSK);
+	writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
+	/* Stop timer */
+	writel(CNTL_STOP_TIMER, timer->timer1 + IO_CONTROL);
+	return 0;
+}
+
+static int zevio_timer_set_oneshot(struct clock_event_device *dev)
+{
+	struct zevio_timer *timer = container_of(dev, struct zevio_timer,
+						 clkevt);
+
+	/* Enable timer interrupts */
+	writel(TIMER_INTR_MSK, timer->interrupt_regs + IO_INTR_MSK);
+	writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
+	return 0;
 }
 
 static irqreturn_t zevio_timer_interrupt(int irq, void *dev_id)
@@ -162,7 +158,9 @@ static int __init zevio_timer_add(struct device_node *node)
 	if (timer->interrupt_regs && irqnr) {
 		timer->clkevt.name		= timer->clockevent_name;
 		timer->clkevt.set_next_event	= zevio_timer_set_event;
-		timer->clkevt.set_mode		= zevio_timer_set_mode;
+		timer->clkevt.set_state_shutdown = zevio_timer_shutdown;
+		timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot;
+		timer->clkevt.tick_resume	= zevio_timer_set_oneshot;
 		timer->clkevt.rating		= 200;
 		timer->clkevt.cpumask		= cpu_all_mask;
 		timer->clkevt.features		= CLOCK_EVT_FEAT_ONESHOT;
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index cc8a71c267b8..77aa34eae92c 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -130,6 +130,13 @@ config ARM_KIRKWOOD_CPUFREQ
 	  This adds the CPUFreq driver for Marvell Kirkwood
 	  SoCs.
 
+config ARM_MT8173_CPUFREQ
+	bool "Mediatek MT8173 CPUFreq support"
+	depends on ARCH_MEDIATEK && REGULATOR
+	select PM_OPP
+	help
+	  This adds the CPUFreq driver support for Mediatek MT8173 SoC.
+
 config ARM_OMAP2PLUS_CPUFREQ
 	bool "TI OMAP2+"
 	depends on ARCH_OMAP2PLUS
@@ -247,12 +254,19 @@ config ARM_SPEAR_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
 
-config ARM_TEGRA_CPUFREQ
-	bool "TEGRA CPUFreq support"
+config ARM_TEGRA20_CPUFREQ
+	bool "Tegra20 CPUFreq support"
 	depends on ARCH_TEGRA
 	default y
 	help
-	  This adds the CPUFreq driver support for TEGRA SOCs.
+	  This adds the CPUFreq driver support for Tegra20 SOCs.
+
+config ARM_TEGRA124_CPUFREQ
+	tristate "Tegra124 CPUFreq support"
+	depends on ARCH_TEGRA && CPUFREQ_DT
+	default y
+	help
+	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
 config ARM_PXA2xx_CPUFREQ
 	tristate "Intel PXA2xx CPUfreq driver"
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 2169bf792db7..60a57ca5b22d 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_ARM_HISI_ACPU_CPUFREQ)	+= hisi-acpu-cpufreq.o
 obj-$(CONFIG_ARM_IMX6Q_CPUFREQ)		+= imx6q-cpufreq.o
 obj-$(CONFIG_ARM_INTEGRATOR)		+= integrator-cpufreq.o
 obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ)	+= kirkwood-cpufreq.o
+obj-$(CONFIG_ARM_MT8173_CPUFREQ)	+= mt8173-cpufreq.o
 obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o
 obj-$(CONFIG_PXA3xx)			+= pxa3xx-cpufreq.o
@@ -76,7 +77,8 @@ obj-$(CONFIG_ARM_S5PV210_CPUFREQ)	+= s5pv210-cpufreq.o
 obj-$(CONFIG_ARM_SA1100_CPUFREQ)	+= sa1100-cpufreq.o
 obj-$(CONFIG_ARM_SA1110_CPUFREQ)	+= sa1110-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
-obj-$(CONFIG_ARM_TEGRA_CPUFREQ)		+= tegra-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
 
 ##################################################################################
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 0136dfcdabf0..15b921a9248c 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -65,18 +65,21 @@ enum {
 #define MSR_K7_HWCR_CPB_DIS	(1ULL << 25)
 
 struct acpi_cpufreq_data {
-	struct acpi_processor_performance *acpi_data;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int resume;
 	unsigned int cpu_feature;
+	unsigned int acpi_perf_cpu;
 	cpumask_var_t freqdomain_cpus;
 };
 
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
-
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
+static inline struct acpi_processor_performance *to_perf_data(struct acpi_cpufreq_data *data)
+{
+	return per_cpu_ptr(acpi_perf_data, data->acpi_perf_cpu);
+}
+
 static struct cpufreq_driver acpi_cpufreq_driver;
 
 static unsigned int acpi_pstate_strict;
@@ -144,7 +147,7 @@ static int _store_boost(int val)
 
 static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 
 	return cpufreq_show_cpus(data->freqdomain_cpus, buf);
 }
@@ -202,7 +205,7 @@ static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
 	struct acpi_processor_performance *perf;
 	int i;
 
-	perf = data->acpi_data;
+	perf = to_perf_data(data);
 
 	for (i = 0; i < perf->state_count; i++) {
 		if (value == perf->states[i].status)
@@ -221,7 +224,7 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
 	else
 		msr &= INTEL_MSR_RANGE;
 
-	perf = data->acpi_data;
+	perf = to_perf_data(data);
 
 	cpufreq_for_each_entry(pos, data->freq_table)
 		if (msr == perf->states[pos->driver_data].status)
@@ -327,7 +330,8 @@ static void drv_write(struct drv_cmd *cmd)
 	put_cpu();
 }
 
-static u32 get_cur_val(const struct cpumask *mask)
+static u32
+get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
 {
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
@@ -335,7 +339,7 @@ static u32 get_cur_val(const struct cpumask *mask)
 	if (unlikely(cpumask_empty(mask)))
 		return 0;
 
-	switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
+	switch (data->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
@@ -346,7 +350,7 @@ static u32 get_cur_val(const struct cpumask *mask)
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
+		perf = to_perf_data(data);
 		cmd.addr.io.port = perf->control_register.address;
 		cmd.addr.io.bit_width = perf->control_register.bit_width;
 		break;
@@ -364,19 +368,24 @@ static u32 get_cur_val(const struct cpumask *mask)
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
+	struct acpi_cpufreq_data *data;
+	struct cpufreq_policy *policy;
 	unsigned int freq;
 	unsigned int cached_freq;
 
 	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
 
-	if (unlikely(data == NULL ||
-		     data->acpi_data == NULL || data->freq_table == NULL)) {
+	policy = cpufreq_cpu_get(cpu);
+	if (unlikely(!policy))
 		return 0;
-	}
 
-	cached_freq = data->freq_table[data->acpi_data->state].frequency;
-	freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
+	data = policy->driver_data;
+	cpufreq_cpu_put(policy);
+	if (unlikely(!data || !data->freq_table))
+		return 0;
+
+	cached_freq = data->freq_table[to_perf_data(data)->state].frequency;
+	freq = extract_freq(get_cur_val(cpumask_of(cpu), data), data);
 	if (freq != cached_freq) {
 		/*
 		 * The dreaded BIOS frequency change behind our back.
@@ -397,7 +406,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 	unsigned int i;
 
 	for (i = 0; i < 100; i++) {
-		cur_freq = extract_freq(get_cur_val(mask), data);
+		cur_freq = extract_freq(get_cur_val(mask, data), data);
 		if (cur_freq == freq)
 			return 1;
 		udelay(10);
@@ -408,18 +417,17 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 			       unsigned int index)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	int result = 0;
 
-	if (unlikely(data == NULL ||
-	     data->acpi_data == NULL || data->freq_table == NULL)) {
+	if (unlikely(data == NULL || data->freq_table == NULL)) {
 		return -ENODEV;
 	}
 
-	perf = data->acpi_data;
+	perf = to_perf_data(data);
 	next_perf_state = data->freq_table[index].driver_data;
 	if (perf->state == next_perf_state) {
 		if (unlikely(data->resume)) {
@@ -482,8 +490,9 @@ out:
 static unsigned long
 acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
 {
-	struct acpi_processor_performance *perf = data->acpi_data;
+	struct acpi_processor_performance *perf;
 
+	perf = to_perf_data(data);
 	if (cpu_khz) {
 		/* search the closest match to cpu_khz */
 		unsigned int i;
@@ -672,17 +681,17 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_free;
 	}
 
-	data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
-	per_cpu(acfreq_data, cpu) = data;
+	perf = per_cpu_ptr(acpi_perf_data, cpu);
+	data->acpi_perf_cpu = cpu;
+	policy->driver_data = data;
 
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
 		acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
 
-	result = acpi_processor_register_performance(data->acpi_data, cpu);
+	result = acpi_processor_register_performance(perf, cpu);
 	if (result)
 		goto err_free_mask;
 
-	perf = data->acpi_data;
 	policy->shared_type = perf->shared_type;
 
 	/*
@@ -838,26 +847,25 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 err_freqfree:
 	kfree(data->freq_table);
 err_unreg:
-	acpi_processor_unregister_performance(perf, cpu);
+	acpi_processor_unregister_performance(cpu);
 err_free_mask:
 	free_cpumask_var(data->freqdomain_cpus);
 err_free:
 	kfree(data);
-	per_cpu(acfreq_data, cpu) = NULL;
+	policy->driver_data = NULL;
 
 	return result;
 }
 
 static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 
 	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
-		per_cpu(acfreq_data, policy->cpu) = NULL;
-		acpi_processor_unregister_performance(data->acpi_data,
-						      policy->cpu);
+		policy->driver_data = NULL;
+		acpi_processor_unregister_performance(data->acpi_perf_cpu);
 		free_cpumask_var(data->freqdomain_cpus);
 		kfree(data->freq_table);
 		kfree(data);
@@ -868,7 +876,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 
 static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 
 	pr_debug("acpi_cpufreq_resume\n");
 
@@ -880,7 +888,9 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 static struct freq_attr *acpi_cpufreq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	&freqdomain_cpus,
-	NULL,	/* this is a placeholder for cpb, do not remove */
+#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
+	&cpb,
+#endif
 	NULL,
 };
 
@@ -953,17 +963,16 @@ static int __init acpi_cpufreq_init(void)
 	 * only if configured. This is considered legacy code, which
 	 * will probably be removed at some point in the future.
 	 */
-	if (check_amd_hwpstate_cpu(0)) {
-		struct freq_attr **iter;
-
-		pr_debug("adding sysfs entry for cpb\n");
+	if (!check_amd_hwpstate_cpu(0)) {
+		struct freq_attr **attr;
 
-		for (iter = acpi_cpufreq_attr; *iter != NULL; iter++)
-			;
+		pr_debug("CPB unsupported, do not expose it\n");
 
-		/* make sure there is a terminator behind it */
-		if (iter[1] == NULL)
-			*iter = &cpb;
+		for (attr = acpi_cpufreq_attr; *attr; attr++)
+			if (*attr == &cpb) {
+				*attr = NULL;
+				break;
+			}
 	}
 #endif
 	acpi_cpufreq_boost_init();
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 528a82bf5038..c3583cdfadbd 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -36,6 +36,12 @@ struct private_data {
 	unsigned int voltage_tolerance; /* in percentage */
 };
 
+static struct freq_attr *cpufreq_dt_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,   /* Extra space for boost-attr if required */
+	NULL,
+};
+
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct dev_pm_opp *opp;
@@ -184,7 +190,6 @@ try_again:
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct cpufreq_dt_platform_data *pd;
 	struct cpufreq_frequency_table *freq_table;
 	struct device_node *np;
 	struct private_data *priv;
@@ -193,6 +198,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct clk *cpu_clk;
 	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
+	bool need_update = false;
 	int ret;
 
 	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
@@ -208,8 +214,47 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_put_reg_clk;
 	}
 
-	/* OPPs might be populated at runtime, don't check for error here */
-	of_init_opp_table(cpu_dev);
+	/* Get OPP-sharing information from "operating-points-v2" bindings */
+	ret = of_get_cpus_sharing_opps(cpu_dev, policy->cpus);
+	if (ret) {
+		/*
+		 * operating-points-v2 not supported, fallback to old method of
+		 * finding shared-OPPs for backward compatibility.
+		 */
+		if (ret == -ENOENT)
+			need_update = true;
+		else
+			goto out_node_put;
+	}
+
+	/*
+	 * Initialize OPP tables for all policy->cpus. They will be shared by
+	 * all CPUs which have marked their CPUs shared with OPP bindings.
+	 *
+	 * For platforms not using operating-points-v2 bindings, we do this
+	 * before updating policy->cpus. Otherwise, we will end up creating
+	 * duplicate OPPs for policy->cpus.
+	 *
+	 * OPPs might be populated at runtime, don't check for error here
+	 */
+	of_cpumask_init_opp_table(policy->cpus);
+
+	if (need_update) {
+		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
+
+		if (!pd || !pd->independent_clocks)
+			cpumask_setall(policy->cpus);
+
+		/*
+		 * OPP tables are initialized only for policy->cpu, do it for
+		 * others as well.
+		 */
+		set_cpus_sharing_opps(cpu_dev, policy->cpus);
+
+		of_property_read_u32(np, "clock-latency", &transition_latency);
+	} else {
+		transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev);
+	}
 
 	/*
 	 * But we need OPP table to function so if it is not there let's
@@ -230,7 +275,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
 
-	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+	if (!transition_latency)
 		transition_latency = CPUFREQ_ETERNAL;
 
 	if (!IS_ERR(cpu_reg)) {
@@ -291,11 +336,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_cpufreq_table;
 	}
 
-	policy->cpuinfo.transition_latency = transition_latency;
+	/* Support turbo/boost mode */
+	if (policy_has_boost_freq(policy)) {
+		/* This gets disabled by core on driver unregister */
+		ret = cpufreq_enable_boost_support();
+		if (ret)
+			goto out_free_cpufreq_table;
+		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+	}
 
-	pd = cpufreq_get_driver_data();
-	if (!pd || !pd->independent_clocks)
-		cpumask_setall(policy->cpus);
+	policy->cpuinfo.transition_latency = transition_latency;
 
 	of_node_put(np);
 
@@ -306,7 +356,8 @@ out_free_cpufreq_table:
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	of_free_opp_table(cpu_dev);
+	of_cpumask_free_opp_table(policy->cpus);
+out_node_put:
 	of_node_put(np);
 out_put_reg_clk:
 	clk_put(cpu_clk);
@@ -322,7 +373,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	of_free_opp_table(priv->cpu_dev);
+	of_cpumask_free_opp_table(policy->related_cpus);
 	clk_put(policy->clk);
 	if (!IS_ERR(priv->cpu_reg))
 		regulator_put(priv->cpu_reg);
@@ -367,7 +418,7 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.exit = cpufreq_exit,
 	.ready = cpufreq_ready,
 	.name = "cpufreq-dt",
-	.attr = cpufreq_generic_attr,
+	.attr = cpufreq_dt_attr,
 };
 
 static int dt_cpufreq_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b612411655f9..b3d9368339af 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -112,12 +112,6 @@ static inline bool has_target(void)
 	return cpufreq_driver->target_index || cpufreq_driver->target;
 }
 
-/*
- * rwsem to guarantee that cpufreq driver module doesn't unload during critical
- * sections
- */
-static DECLARE_RWSEM(cpufreq_rwsem);
-
 /* internal prototypes */
 static int __cpufreq_governor(struct cpufreq_policy *policy,
 		unsigned int event);
@@ -169,6 +163,15 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
+struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+
+	return policy && !policy_is_inactive(policy) ?
+		policy->freq_table : NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
+
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -268,10 +271,6 @@ EXPORT_SYMBOL_GPL(cpufreq_generic_get);
  * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be
  * freed as that depends on the kobj count.
  *
- * It also takes a read-lock of 'cpufreq_rwsem' and doesn't put it back if a
- * valid policy is found. This is done to make sure the driver doesn't get
- * unregistered while the policy is being used.
- *
  * Return: A valid policy on success, otherwise NULL on failure.
  */
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
@@ -282,9 +281,6 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 	if (WARN_ON(cpu >= nr_cpu_ids))
 		return NULL;
 
-	if (!down_read_trylock(&cpufreq_rwsem))
-		return NULL;
-
 	/* get the cpufreq driver */
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
 
@@ -297,9 +293,6 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (!policy)
-		up_read(&cpufreq_rwsem);
-
 	return policy;
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
@@ -311,13 +304,10 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
  *
  * This decrements the kobject reference count incremented earlier by calling
  * cpufreq_cpu_get().
- *
- * It also drops the read-lock of 'cpufreq_rwsem' taken at cpufreq_cpu_get().
  */
 void cpufreq_cpu_put(struct cpufreq_policy *policy)
 {
 	kobject_put(&policy->kobj);
-	up_read(&cpufreq_rwsem);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
@@ -530,9 +520,6 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 {
 	int err = -EINVAL;
 
-	if (!cpufreq_driver)
-		goto out;
-
 	if (cpufreq_driver->setpolicy) {
 		if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
 			*policy = CPUFREQ_POLICY_PERFORMANCE;
@@ -567,7 +554,6 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 
 		mutex_unlock(&cpufreq_governor_mutex);
 	}
-out:
 	return err;
 }
 
@@ -616,9 +602,7 @@ static ssize_t store_##file_name					\
 	int ret, temp;							\
 	struct cpufreq_policy new_policy;				\
 									\
-	ret = cpufreq_get_policy(&new_policy, policy->cpu);		\
-	if (ret)							\
-		return -EINVAL;						\
+	memcpy(&new_policy, policy, sizeof(*policy));			\
 									\
 	ret = sscanf(buf, "%u", &new_policy.object);			\
 	if (ret != 1)							\
@@ -672,9 +656,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 	char	str_governor[16];
 	struct cpufreq_policy new_policy;
 
-	ret = cpufreq_get_policy(&new_policy, policy->cpu);
-	if (ret)
-		return ret;
+	memcpy(&new_policy, policy, sizeof(*policy));
 
 	ret = sscanf(buf, "%15s", str_governor);
 	if (ret != 1)
@@ -685,14 +667,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 		return -EINVAL;
 
 	ret = cpufreq_set_policy(policy, &new_policy);
-
-	policy->user_policy.policy = policy->policy;
-	policy->user_policy.governor = policy->governor;
-
-	if (ret)
-		return ret;
-	else
-		return count;
+	return ret ? ret : count;
 }
 
 /**
@@ -842,9 +817,6 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret;
 
-	if (!down_read_trylock(&cpufreq_rwsem))
-		return -EINVAL;
-
 	down_read(&policy->rwsem);
 
 	if (fattr->show)
@@ -853,7 +825,6 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 		ret = -EIO;
 
 	up_read(&policy->rwsem);
-	up_read(&cpufreq_rwsem);
 
 	return ret;
 }
@@ -870,9 +841,6 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	if (!cpu_online(policy->cpu))
 		goto unlock;
 
-	if (!down_read_trylock(&cpufreq_rwsem))
-		goto unlock;
-
 	down_write(&policy->rwsem);
 
 	/* Updating inactive policies is invalid, so avoid doing that. */
@@ -888,8 +856,6 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 
 unlock_policy_rwsem:
 	up_write(&policy->rwsem);
-
-	up_read(&cpufreq_rwsem);
 unlock:
 	put_online_cpus();
 
@@ -993,7 +959,7 @@ static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
 	int ret = 0;
 
 	/* Some related CPUs might not be present (physically hotplugged) */
-	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+	for_each_cpu(j, policy->real_cpus) {
 		if (j == policy->kobj_cpu)
 			continue;
 
@@ -1010,7 +976,7 @@ static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
 	unsigned int j;
 
 	/* Some related CPUs might not be present (physically hotplugged) */
-	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+	for_each_cpu(j, policy->real_cpus) {
 		if (j == policy->kobj_cpu)
 			continue;
 
@@ -1018,8 +984,7 @@ static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
 	}
 }
 
-static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
-				     struct device *dev)
+static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
 {
 	struct freq_attr **drv_attr;
 	int ret = 0;
@@ -1051,11 +1016,10 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 	return cpufreq_add_dev_symlink(policy);
 }
 
-static void cpufreq_init_policy(struct cpufreq_policy *policy)
+static int cpufreq_init_policy(struct cpufreq_policy *policy)
 {
 	struct cpufreq_governor *gov = NULL;
 	struct cpufreq_policy new_policy;
-	int ret = 0;
 
 	memcpy(&new_policy, policy, sizeof(*policy));
 
@@ -1074,16 +1038,10 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy)
 		cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
 
 	/* set default policy */
-	ret = cpufreq_set_policy(policy, &new_policy);
-	if (ret) {
-		pr_debug("setting policy failed\n");
-		if (cpufreq_driver->exit)
-			cpufreq_driver->exit(policy);
-	}
+	return cpufreq_set_policy(policy, &new_policy);
 }
 
-static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
-				  unsigned int cpu, struct device *dev)
+static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 {
 	int ret = 0;
 
@@ -1117,32 +1075,15 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 	return 0;
 }
 
-static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
-{
-	struct cpufreq_policy *policy;
-	unsigned long flags;
-
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
-	policy = per_cpu(cpufreq_cpu_data, cpu);
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	if (likely(policy)) {
-		/* Policy should be inactive here */
-		WARN_ON(!policy_is_inactive(policy));
-
-		down_write(&policy->rwsem);
-		policy->cpu = cpu;
-		up_write(&policy->rwsem);
-	}
-
-	return policy;
-}
-
-static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev)
+static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 {
+	struct device *dev = get_cpu_device(cpu);
 	struct cpufreq_policy *policy;
 	int ret;
 
+	if (WARN_ON(!dev))
+		return NULL;
+
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
 	if (!policy)
 		return NULL;
@@ -1153,11 +1094,14 @@ static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev)
 	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
 		goto err_free_cpumask;
 
+	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
+		goto err_free_rcpumask;
+
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj,
 				   "cpufreq");
 	if (ret) {
 		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
-		goto err_free_rcpumask;
+		goto err_free_real_cpus;
 	}
 
 	INIT_LIST_HEAD(&policy->policy_list);
@@ -1167,13 +1111,15 @@ static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev)
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
-	policy->cpu = dev->id;
+	policy->cpu = cpu;
 
 	/* Set this once on allocation */
-	policy->kobj_cpu = dev->id;
+	policy->kobj_cpu = cpu;
 
 	return policy;
 
+err_free_real_cpus:
+	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
 	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
@@ -1224,61 +1170,40 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	cpufreq_policy_put_kobj(policy, notify);
+	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
 	free_cpumask_var(policy->cpus);
 	kfree(policy);
 }
 
-/**
- * cpufreq_add_dev - add a CPU device
- *
- * Adds the cpufreq interface for a CPU device.
- *
- * The Oracle says: try running cpufreq registration/unregistration concurrently
- * with with cpu hotplugging and all hell will break loose. Tried to clean this
- * mess up, but more thorough testing is needed. - Mathieu
- */
-static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+static int cpufreq_online(unsigned int cpu)
 {
-	unsigned int j, cpu = dev->id;
-	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
+	bool new_policy;
 	unsigned long flags;
-	bool recover_policy = !sif;
-
-	pr_debug("adding CPU %u\n", cpu);
-
-	/*
-	 * Only possible if 'cpu' wasn't physically present earlier and we are
-	 * here from subsys_interface add callback. A hotplug notifier will
-	 * follow and we will handle it like logical CPU hotplug then. For now,
-	 * just create the sysfs link.
-	 */
-	if (cpu_is_offline(cpu))
-		return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu);
+	unsigned int j;
+	int ret;
 
-	if (!down_read_trylock(&cpufreq_rwsem))
-		return 0;
+	pr_debug("%s: bringing CPU%u online\n", __func__, cpu);
 
 	/* Check if this CPU already has a policy to manage it */
 	policy = per_cpu(cpufreq_cpu_data, cpu);
-	if (policy && !policy_is_inactive(policy)) {
+	if (policy) {
 		WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus));
-		ret = cpufreq_add_policy_cpu(policy, cpu, dev);
-		up_read(&cpufreq_rwsem);
-		return ret;
-	}
+		if (!policy_is_inactive(policy))
+			return cpufreq_add_policy_cpu(policy, cpu);
 
-	/*
-	 * Restore the saved policy when doing light-weight init and fall back
-	 * to the full init if that fails.
-	 */
-	policy = recover_policy ? cpufreq_policy_restore(cpu) : NULL;
-	if (!policy) {
-		recover_policy = false;
-		policy = cpufreq_policy_alloc(dev);
+		/* This is the only online CPU for the policy.  Start over. */
+		new_policy = false;
+		down_write(&policy->rwsem);
+		policy->cpu = cpu;
+		policy->governor = NULL;
+		up_write(&policy->rwsem);
+	} else {
+		new_policy = true;
+		policy = cpufreq_policy_alloc(cpu);
 		if (!policy)
-			goto nomem_out;
+			return -ENOMEM;
 	}
 
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
@@ -1289,13 +1214,17 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	ret = cpufreq_driver->init(policy);
 	if (ret) {
 		pr_debug("initialization failed\n");
-		goto err_set_policy_cpu;
+		goto out_free_policy;
 	}
 
 	down_write(&policy->rwsem);
 
-	/* related cpus should atleast have policy->cpus */
-	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+	if (new_policy) {
+		/* related_cpus should at least include policy->cpus. */
+		cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+		/* Remember CPUs present at the policy creation time. */
+		cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
+	}
 
 	/*
 	 * affected cpus must always be the one, which are online. We aren't
@@ -1303,7 +1232,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	 */
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
-	if (!recover_policy) {
+	if (new_policy) {
 		policy->user_policy.min = policy->min;
 		policy->user_policy.max = policy->max;
 
@@ -1317,7 +1246,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
 			pr_err("%s: ->get() failed\n", __func__);
-			goto err_get_freq;
+			goto out_exit_policy;
 		}
 	}
 
@@ -1364,10 +1293,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
 
-	if (!recover_policy) {
-		ret = cpufreq_add_dev_interface(policy, dev);
+	if (new_policy) {
+		ret = cpufreq_add_dev_interface(policy);
 		if (ret)
-			goto err_out_unregister;
+			goto out_exit_policy;
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
 
@@ -1376,18 +1305,19 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
-	cpufreq_init_policy(policy);
-
-	if (!recover_policy) {
-		policy->user_policy.policy = policy->policy;
-		policy->user_policy.governor = policy->governor;
+	ret = cpufreq_init_policy(policy);
+	if (ret) {
+		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
+		       __func__, cpu, ret);
+		/* cpufreq_policy_free() will notify based on this */
+		new_policy = false;
+		goto out_exit_policy;
 	}
+
 	up_write(&policy->rwsem);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 
-	up_read(&cpufreq_rwsem);
-
 	/* Callback for handling stuff after policy is ready */
 	if (cpufreq_driver->ready)
 		cpufreq_driver->ready(policy);
@@ -1396,25 +1326,47 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 
 	return 0;
 
-err_out_unregister:
-err_get_freq:
+out_exit_policy:
 	up_write(&policy->rwsem);
 
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
-err_set_policy_cpu:
-	cpufreq_policy_free(policy, recover_policy);
-nomem_out:
-	up_read(&cpufreq_rwsem);
+out_free_policy:
+	cpufreq_policy_free(policy, !new_policy);
+	return ret;
+}
+
+/**
+ * cpufreq_add_dev - the cpufreq interface for a CPU device.
+ * @dev: CPU device.
+ * @sif: Subsystem interface structure pointer (not used)
+ */
+static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+{
+	unsigned cpu = dev->id;
+	int ret;
+
+	dev_dbg(dev, "%s: adding CPU%u\n", __func__, cpu);
+
+	if (cpu_online(cpu)) {
+		ret = cpufreq_online(cpu);
+	} else {
+		/*
+		 * A hotplug notifier will follow and we will handle it as CPU
+		 * online then.  For now, just create the sysfs link, unless
+		 * there is no policy or the link is already present.
+		 */
+		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+
+		ret = policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus)
+			? add_cpu_dev_symlink(policy, cpu) : 0;
+	}
 
 	return ret;
 }
 
-static int __cpufreq_remove_dev_prepare(struct device *dev,
-					struct subsys_interface *sif)
+static void cpufreq_offline_prepare(unsigned int cpu)
 {
-	unsigned int cpu = dev->id;
-	int ret = 0;
 	struct cpufreq_policy *policy;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
@@ -1422,15 +1374,13 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
-		return -EINVAL;
+		return;
 	}
 
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-		if (ret) {
+		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret)
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
-		}
 	}
 
 	down_write(&policy->rwsem);
@@ -1449,7 +1399,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 	/* Start governor again for active policy */
 	if (!policy_is_inactive(policy)) {
 		if (has_target()) {
-			ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+			int ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
 			if (!ret)
 				ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
@@ -1459,33 +1409,26 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 	} else if (cpufreq_driver->stop_cpu) {
 		cpufreq_driver->stop_cpu(policy);
 	}
-
-	return ret;
 }
 
-static int __cpufreq_remove_dev_finish(struct device *dev,
-				       struct subsys_interface *sif)
+static void cpufreq_offline_finish(unsigned int cpu)
 {
-	unsigned int cpu = dev->id;
-	int ret;
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
-		return -EINVAL;
+		return;
 	}
 
 	/* Only proceed for inactive policies */
 	if (!policy_is_inactive(policy))
-		return 0;
+		return;
 
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		if (ret) {
+		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
-			return ret;
-		}
 	}
 
 	/*
@@ -1495,12 +1438,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 	 */
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
-
-	/* Free the policy only if the driver is getting removed. */
-	if (sif)
-		cpufreq_policy_free(policy, true);
-
-	return 0;
 }
 
 /**
@@ -1508,45 +1445,42 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
  *
  * Removes the cpufreq interface for a CPU device.
  */
-static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
+static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id;
-	int ret;
-
-	/*
-	 * Only possible if 'cpu' is getting physically removed now. A hotplug
-	 * notifier should have already been called and we just need to remove
-	 * link or free policy here.
-	 */
-	if (cpu_is_offline(cpu)) {
-		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-		struct cpumask mask;
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
-		if (!policy)
-			return 0;
+	if (!policy)
+		return;
 
-		cpumask_copy(&mask, policy->related_cpus);
-		cpumask_clear_cpu(cpu, &mask);
+	if (cpu_online(cpu)) {
+		cpufreq_offline_prepare(cpu);
+		cpufreq_offline_finish(cpu);
+	}
 
-		/*
-		 * Free policy only if all policy->related_cpus are removed
-		 * physically.
-		 */
-		if (cpumask_intersects(&mask, cpu_present_mask)) {
-			remove_cpu_dev_symlink(policy, cpu);
-			return 0;
-		}
+	cpumask_clear_cpu(cpu, policy->real_cpus);
 
+	if (cpumask_empty(policy->real_cpus)) {
 		cpufreq_policy_free(policy, true);
-		return 0;
+		return;
 	}
 
-	ret = __cpufreq_remove_dev_prepare(dev, sif);
+	if (cpu != policy->kobj_cpu) {
+		remove_cpu_dev_symlink(policy, cpu);
+	} else {
+		/*
+		 * The CPU owning the policy object is going away.  Move it to
+		 * another suitable CPU.
+		 */
+		unsigned int new_cpu = cpumask_first(policy->real_cpus);
+		struct device *new_dev = get_cpu_device(new_cpu);
 
-	if (!ret)
-		ret = __cpufreq_remove_dev_finish(dev, sif);
+		dev_dbg(dev, "%s: Moving policy object to CPU%u\n", __func__, new_cpu);
 
-	return ret;
+		sysfs_remove_link(&new_dev->kobj, "cpufreq");
+		policy->kobj_cpu = new_cpu;
+		WARN_ON(kobject_move(&policy->kobj, &new_dev->kobj));
+	}
 }
 
 static void handle_update(struct work_struct *work)
@@ -2235,7 +2169,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
 
-	if (new_policy->min > policy->max || new_policy->max < policy->min)
+	/*
+	* This check works well when we store new min/max freq attributes,
+	* because new_policy is a copy of policy with one field updated.
+	*/
+	if (new_policy->min > new_policy->max)
 		return -EINVAL;
 
 	/* verify the cpu speed can be set within this limit */
@@ -2247,10 +2185,6 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 			CPUFREQ_ADJUST, new_policy);
 
-	/* adjust if necessary - hardware incompatibility*/
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_INCOMPATIBLE, new_policy);
-
 	/*
 	 * verify the cpu speed can be set within this limit, which might be
 	 * different to the first one
@@ -2284,16 +2218,31 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	old_gov = policy->governor;
 	/* end old governor */
 	if (old_gov) {
-		__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret) {
+			/* This can happen due to race with other operations */
+			pr_debug("%s: Failed to Stop Governor: %s (%d)\n",
+				 __func__, old_gov->name, ret);
+			return ret;
+		}
+
 		up_write(&policy->rwsem);
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		down_write(&policy->rwsem);
+
+		if (ret) {
+			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
+			       __func__, old_gov->name, ret);
+			return ret;
+		}
 	}
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
-		if (!__cpufreq_governor(policy, CPUFREQ_GOV_START))
+	ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	if (!ret) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		if (!ret)
 			goto out;
 
 		up_write(&policy->rwsem);
@@ -2305,11 +2254,13 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
-		__cpufreq_governor(policy, CPUFREQ_GOV_START);
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+			policy->governor = NULL;
+		else
+			__cpufreq_governor(policy, CPUFREQ_GOV_START);
 	}
 
-	return -EINVAL;
+	return ret;
 
  out:
 	pr_debug("governor: change or update limits\n");
@@ -2338,8 +2289,6 @@ int cpufreq_update_policy(unsigned int cpu)
 	memcpy(&new_policy, policy, sizeof(*policy));
 	new_policy.min = policy->user_policy.min;
 	new_policy.max = policy->user_policy.max;
-	new_policy.policy = policy->user_policy.policy;
-	new_policy.governor = policy->user_policy.governor;
 
 	/*
 	 * BIOS might change freq behind our back
@@ -2375,27 +2324,23 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
-	struct device *dev;
 
-	dev = get_cpu_device(cpu);
-	if (dev) {
-		switch (action & ~CPU_TASKS_FROZEN) {
-		case CPU_ONLINE:
-			cpufreq_add_dev(dev, NULL);
-			break;
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		cpufreq_online(cpu);
+		break;
 
-		case CPU_DOWN_PREPARE:
-			__cpufreq_remove_dev_prepare(dev, NULL);
-			break;
+	case CPU_DOWN_PREPARE:
+		cpufreq_offline_prepare(cpu);
+		break;
 
-		case CPU_POST_DEAD:
-			__cpufreq_remove_dev_finish(dev, NULL);
-			break;
+	case CPU_POST_DEAD:
+		cpufreq_offline_finish(cpu);
+		break;
 
-		case CPU_DOWN_FAILED:
-			cpufreq_add_dev(dev, NULL);
-			break;
-		}
+	case CPU_DOWN_FAILED:
+		cpufreq_online(cpu);
+		break;
 	}
 	return NOTIFY_OK;
 }
@@ -2465,6 +2410,49 @@ int cpufreq_boost_supported(void)
 }
 EXPORT_SYMBOL_GPL(cpufreq_boost_supported);
 
+static int create_boost_sysfs_file(void)
+{
+	int ret;
+
+	if (!cpufreq_boost_supported())
+		return 0;
+
+	/*
+	 * Check if driver provides function to enable boost -
+	 * if not, use cpufreq_boost_set_sw as default
+	 */
+	if (!cpufreq_driver->set_boost)
+		cpufreq_driver->set_boost = cpufreq_boost_set_sw;
+
+	ret = cpufreq_sysfs_create_file(&boost.attr);
+	if (ret)
+		pr_err("%s: cannot register global BOOST sysfs file\n",
+		       __func__);
+
+	return ret;
+}
+
+static void remove_boost_sysfs_file(void)
+{
+	if (cpufreq_boost_supported())
+		cpufreq_sysfs_remove_file(&boost.attr);
+}
+
+int cpufreq_enable_boost_support(void)
+{
+	if (!cpufreq_driver)
+		return -EINVAL;
+
+	if (cpufreq_boost_supported())
+		return 0;
+
+	cpufreq_driver->boost_supported = true;
+
+	/* This will get removed on driver unregister */
+	return create_boost_sysfs_file();
+}
+EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support);
+
 int cpufreq_boost_enabled(void)
 {
 	return cpufreq_driver->boost_enabled;
@@ -2503,10 +2491,14 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
 
+	/* Protect against concurrent CPU online/offline. */
+	get_online_cpus();
+
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	if (cpufreq_driver) {
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-		return -EEXIST;
+		ret = -EEXIST;
+		goto out;
 	}
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
@@ -2514,21 +2506,9 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
-	if (cpufreq_boost_supported()) {
-		/*
-		 * Check if driver provides function to enable boost -
-		 * if not, use cpufreq_boost_set_sw as default
-		 */
-		if (!cpufreq_driver->set_boost)
-			cpufreq_driver->set_boost = cpufreq_boost_set_sw;
-
-		ret = cpufreq_sysfs_create_file(&boost.attr);
-		if (ret) {
-			pr_err("%s: cannot register global BOOST sysfs file\n",
-			       __func__);
-			goto err_null_driver;
-		}
-	}
+	ret = create_boost_sysfs_file();
+	if (ret)
+		goto err_null_driver;
 
 	ret = subsys_interface_register(&cpufreq_interface);
 	if (ret)
@@ -2545,17 +2525,19 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	register_hotcpu_notifier(&cpufreq_cpu_notifier);
 	pr_debug("driver %s up and running\n", driver_data->name);
 
-	return 0;
+out:
+	put_online_cpus();
+	return ret;
+
 err_if_unreg:
 	subsys_interface_unregister(&cpufreq_interface);
 err_boost_unreg:
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
+	remove_boost_sysfs_file();
 err_null_driver:
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	cpufreq_driver = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	return ret;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_driver);
 
@@ -2576,19 +2558,18 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 
 	pr_debug("unregistering driver %s\n", driver->name);
 
+	/* Protect against concurrent cpu hotplug */
+	get_online_cpus();
 	subsys_interface_unregister(&cpufreq_interface);
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
-
+	remove_boost_sysfs_file();
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
 
-	down_write(&cpufreq_rwsem);
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
 	cpufreq_driver = NULL;
 
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	up_write(&cpufreq_rwsem);
+	put_online_cpus();
 
 	return 0;
 }
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index c86a10c30912..84a1506950a7 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -47,7 +47,7 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
 static void cs_check_cpu(int cpu, unsigned int load)
 {
 	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
 	struct dbs_data *dbs_data = policy->governor_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 
@@ -102,26 +102,15 @@ static void cs_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static void cs_dbs_timer(struct work_struct *work)
+static unsigned int cs_dbs_timer(struct cpu_dbs_info *cdbs,
+				 struct dbs_data *dbs_data, bool modify_all)
 {
-	struct cs_cpu_dbs_info_s *dbs_info = container_of(work,
-			struct cs_cpu_dbs_info_s, cdbs.work.work);
-	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
-	struct cs_cpu_dbs_info_s *core_dbs_info = &per_cpu(cs_cpu_dbs_info,
-			cpu);
-	struct dbs_data *dbs_data = dbs_info->cdbs.cur_policy->governor_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	int delay = delay_for_sampling_rate(cs_tuners->sampling_rate);
-	bool modify_all = true;
 
-	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
-	if (!need_load_eval(&core_dbs_info->cdbs, cs_tuners->sampling_rate))
-		modify_all = false;
-	else
-		dbs_check_cpu(dbs_data, cpu);
+	if (modify_all)
+		dbs_check_cpu(dbs_data, cdbs->shared->policy->cpu);
 
-	gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy, delay, modify_all);
-	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
+	return delay_for_sampling_rate(cs_tuners->sampling_rate);
 }
 
 static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
@@ -135,7 +124,7 @@ static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 	if (!dbs_info->enable)
 		return 0;
 
-	policy = dbs_info->cdbs.cur_policy;
+	policy = dbs_info->cdbs.shared->policy;
 
 	/*
 	 * we only care if our internally tracked freq moves outside the 'valid'
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 57a39f8a92b7..939197ffa4ac 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -32,10 +32,10 @@ static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
 
 void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 {
-	struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	struct cpufreq_policy *policy;
+	struct cpufreq_policy *policy = cdbs->shared->policy;
 	unsigned int sampling_rate;
 	unsigned int max_load = 0;
 	unsigned int ignore_nice;
@@ -60,11 +60,9 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		ignore_nice = cs_tuners->ignore_nice_load;
 	}
 
-	policy = cdbs->cur_policy;
-
 	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_common_info *j_cdbs;
+		struct cpu_dbs_info *j_cdbs;
 		u64 cur_wall_time, cur_idle_time;
 		unsigned int idle_time, wall_time;
 		unsigned int load;
@@ -163,9 +161,9 @@ EXPORT_SYMBOL_GPL(dbs_check_cpu);
 static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
 		unsigned int delay)
 {
-	struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
 
-	mod_delayed_work_on(cpu, system_wq, &cdbs->work, delay);
+	mod_delayed_work_on(cpu, system_wq, &cdbs->dwork, delay);
 }
 
 void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
@@ -199,33 +197,63 @@ EXPORT_SYMBOL_GPL(gov_queue_work);
 static inline void gov_cancel_work(struct dbs_data *dbs_data,
 		struct cpufreq_policy *policy)
 {
-	struct cpu_dbs_common_info *cdbs;
+	struct cpu_dbs_info *cdbs;
 	int i;
 
 	for_each_cpu(i, policy->cpus) {
 		cdbs = dbs_data->cdata->get_cpu_cdbs(i);
-		cancel_delayed_work_sync(&cdbs->work);
+		cancel_delayed_work_sync(&cdbs->dwork);
 	}
 }
 
 /* Will return if we need to evaluate cpu load again or not */
-bool need_load_eval(struct cpu_dbs_common_info *cdbs,
-		unsigned int sampling_rate)
+static bool need_load_eval(struct cpu_common_dbs_info *shared,
+			   unsigned int sampling_rate)
 {
-	if (policy_is_shared(cdbs->cur_policy)) {
+	if (policy_is_shared(shared->policy)) {
 		ktime_t time_now = ktime_get();
-		s64 delta_us = ktime_us_delta(time_now, cdbs->time_stamp);
+		s64 delta_us = ktime_us_delta(time_now, shared->time_stamp);
 
 		/* Do nothing if we recently have sampled */
 		if (delta_us < (s64)(sampling_rate / 2))
 			return false;
 		else
-			cdbs->time_stamp = time_now;
+			shared->time_stamp = time_now;
 	}
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(need_load_eval);
+
+static void dbs_timer(struct work_struct *work)
+{
+	struct cpu_dbs_info *cdbs = container_of(work, struct cpu_dbs_info,
+						 dwork.work);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+	struct cpufreq_policy *policy = shared->policy;
+	struct dbs_data *dbs_data = policy->governor_data;
+	unsigned int sampling_rate, delay;
+	bool modify_all = true;
+
+	mutex_lock(&shared->timer_mutex);
+
+	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+
+		sampling_rate = cs_tuners->sampling_rate;
+	} else {
+		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+
+		sampling_rate = od_tuners->sampling_rate;
+	}
+
+	if (!need_load_eval(cdbs->shared, sampling_rate))
+		modify_all = false;
+
+	delay = dbs_data->cdata->gov_dbs_timer(cdbs, dbs_data, modify_all);
+	gov_queue_work(dbs_data, policy, delay, modify_all);
+
+	mutex_unlock(&shared->timer_mutex);
+}
 
 static void set_sampling_rate(struct dbs_data *dbs_data,
 		unsigned int sampling_rate)
@@ -239,6 +267,37 @@ static void set_sampling_rate(struct dbs_data *dbs_data,
 	}
 }
 
+static int alloc_common_dbs_info(struct cpufreq_policy *policy,
+				 struct common_dbs_data *cdata)
+{
+	struct cpu_common_dbs_info *shared;
+	int j;
+
+	/* Allocate memory for the common information for policy->cpus */
+	shared = kzalloc(sizeof(*shared), GFP_KERNEL);
+	if (!shared)
+		return -ENOMEM;
+
+	/* Set shared for all CPUs, online+offline */
+	for_each_cpu(j, policy->related_cpus)
+		cdata->get_cpu_cdbs(j)->shared = shared;
+
+	return 0;
+}
+
+static void free_common_dbs_info(struct cpufreq_policy *policy,
+				 struct common_dbs_data *cdata)
+{
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+	int j;
+
+	for_each_cpu(j, policy->cpus)
+		cdata->get_cpu_cdbs(j)->shared = NULL;
+
+	kfree(shared);
+}
+
 static int cpufreq_governor_init(struct cpufreq_policy *policy,
 				 struct dbs_data *dbs_data,
 				 struct common_dbs_data *cdata)
@@ -246,9 +305,18 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy,
 	unsigned int latency;
 	int ret;
 
+	/* State should be equivalent to EXIT */
+	if (policy->governor_data)
+		return -EBUSY;
+
 	if (dbs_data) {
 		if (WARN_ON(have_governor_per_policy()))
 			return -EINVAL;
+
+		ret = alloc_common_dbs_info(policy, cdata);
+		if (ret)
+			return ret;
+
 		dbs_data->usage_count++;
 		policy->governor_data = dbs_data;
 		return 0;
@@ -258,12 +326,16 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy,
 	if (!dbs_data)
 		return -ENOMEM;
 
+	ret = alloc_common_dbs_info(policy, cdata);
+	if (ret)
+		goto free_dbs_data;
+
 	dbs_data->cdata = cdata;
 	dbs_data->usage_count = 1;
 
 	ret = cdata->init(dbs_data, !policy->governor->initialized);
 	if (ret)
-		goto free_dbs_data;
+		goto free_common_dbs_info;
 
 	/* policy latency is in ns. Convert it to us first */
 	latency = policy->cpuinfo.transition_latency / 1000;
@@ -300,15 +372,22 @@ put_kobj:
 	}
 cdata_exit:
 	cdata->exit(dbs_data, !policy->governor->initialized);
+free_common_dbs_info:
+	free_common_dbs_info(policy, cdata);
 free_dbs_data:
 	kfree(dbs_data);
 	return ret;
 }
 
-static void cpufreq_governor_exit(struct cpufreq_policy *policy,
-				  struct dbs_data *dbs_data)
+static int cpufreq_governor_exit(struct cpufreq_policy *policy,
+				 struct dbs_data *dbs_data)
 {
 	struct common_dbs_data *cdata = dbs_data->cdata;
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
+
+	/* State should be equivalent to INIT */
+	if (!cdbs->shared || cdbs->shared->policy)
+		return -EBUSY;
 
 	policy->governor_data = NULL;
 	if (!--dbs_data->usage_count) {
@@ -323,6 +402,9 @@ static void cpufreq_governor_exit(struct cpufreq_policy *policy,
 		cdata->exit(dbs_data, policy->governor->initialized == 1);
 		kfree(dbs_data);
 	}
+
+	free_common_dbs_info(policy, cdata);
+	return 0;
 }
 
 static int cpufreq_governor_start(struct cpufreq_policy *policy,
@@ -330,12 +412,17 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 {
 	struct common_dbs_data *cdata = dbs_data->cdata;
 	unsigned int sampling_rate, ignore_nice, j, cpu = policy->cpu;
-	struct cpu_dbs_common_info *cpu_cdbs = cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
 	int io_busy = 0;
 
 	if (!policy->cur)
 		return -EINVAL;
 
+	/* State should be equivalent to INIT */
+	if (!shared || shared->policy)
+		return -EBUSY;
+
 	if (cdata->governor == GOV_CONSERVATIVE) {
 		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 
@@ -349,12 +436,14 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 		io_busy = od_tuners->io_is_busy;
 	}
 
+	shared->policy = policy;
+	shared->time_stamp = ktime_get();
+	mutex_init(&shared->timer_mutex);
+
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_common_info *j_cdbs = cdata->get_cpu_cdbs(j);
+		struct cpu_dbs_info *j_cdbs = cdata->get_cpu_cdbs(j);
 		unsigned int prev_load;
 
-		j_cdbs->cpu = j;
-		j_cdbs->cur_policy = policy;
 		j_cdbs->prev_cpu_idle =
 			get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
 
@@ -366,8 +455,7 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 		if (ignore_nice)
 			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-		mutex_init(&j_cdbs->timer_mutex);
-		INIT_DEFERRABLE_WORK(&j_cdbs->work, cdata->gov_dbs_timer);
+		INIT_DEFERRABLE_WORK(&j_cdbs->dwork, dbs_timer);
 	}
 
 	if (cdata->governor == GOV_CONSERVATIVE) {
@@ -386,20 +474,24 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 		od_ops->powersave_bias_init_cpu(cpu);
 	}
 
-	/* Initiate timer time stamp */
-	cpu_cdbs->time_stamp = ktime_get();
-
 	gov_queue_work(dbs_data, policy, delay_for_sampling_rate(sampling_rate),
 		       true);
 	return 0;
 }
 
-static void cpufreq_governor_stop(struct cpufreq_policy *policy,
-				  struct dbs_data *dbs_data)
+static int cpufreq_governor_stop(struct cpufreq_policy *policy,
+				 struct dbs_data *dbs_data)
 {
 	struct common_dbs_data *cdata = dbs_data->cdata;
 	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_common_info *cpu_cdbs = cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+
+	/* State should be equivalent to START */
+	if (!shared || !shared->policy)
+		return -EBUSY;
+
+	gov_cancel_work(dbs_data, policy);
 
 	if (cdata->governor == GOV_CONSERVATIVE) {
 		struct cs_cpu_dbs_info_s *cs_dbs_info =
@@ -408,38 +500,40 @@ static void cpufreq_governor_stop(struct cpufreq_policy *policy,
 		cs_dbs_info->enable = 0;
 	}
 
-	gov_cancel_work(dbs_data, policy);
-
-	mutex_destroy(&cpu_cdbs->timer_mutex);
-	cpu_cdbs->cur_policy = NULL;
+	shared->policy = NULL;
+	mutex_destroy(&shared->timer_mutex);
+	return 0;
 }
 
-static void cpufreq_governor_limits(struct cpufreq_policy *policy,
-				    struct dbs_data *dbs_data)
+static int cpufreq_governor_limits(struct cpufreq_policy *policy,
+				   struct dbs_data *dbs_data)
 {
 	struct common_dbs_data *cdata = dbs_data->cdata;
 	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_common_info *cpu_cdbs = cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
 
-	if (!cpu_cdbs->cur_policy)
-		return;
+	/* State should be equivalent to START */
+	if (!cdbs->shared || !cdbs->shared->policy)
+		return -EBUSY;
 
-	mutex_lock(&cpu_cdbs->timer_mutex);
-	if (policy->max < cpu_cdbs->cur_policy->cur)
-		__cpufreq_driver_target(cpu_cdbs->cur_policy, policy->max,
+	mutex_lock(&cdbs->shared->timer_mutex);
+	if (policy->max < cdbs->shared->policy->cur)
+		__cpufreq_driver_target(cdbs->shared->policy, policy->max,
 					CPUFREQ_RELATION_H);
-	else if (policy->min > cpu_cdbs->cur_policy->cur)
-		__cpufreq_driver_target(cpu_cdbs->cur_policy, policy->min,
+	else if (policy->min > cdbs->shared->policy->cur)
+		__cpufreq_driver_target(cdbs->shared->policy, policy->min,
 					CPUFREQ_RELATION_L);
 	dbs_check_cpu(dbs_data, cpu);
-	mutex_unlock(&cpu_cdbs->timer_mutex);
+	mutex_unlock(&cdbs->shared->timer_mutex);
+
+	return 0;
 }
 
 int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			 struct common_dbs_data *cdata, unsigned int event)
 {
 	struct dbs_data *dbs_data;
-	int ret = 0;
+	int ret;
 
 	/* Lock governor to block concurrent initialization of governor */
 	mutex_lock(&cdata->mutex);
@@ -449,7 +543,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	else
 		dbs_data = cdata->gdbs_data;
 
-	if (WARN_ON(!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT))) {
+	if (!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT)) {
 		ret = -EINVAL;
 		goto unlock;
 	}
@@ -459,17 +553,19 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		ret = cpufreq_governor_init(policy, dbs_data, cdata);
 		break;
 	case CPUFREQ_GOV_POLICY_EXIT:
-		cpufreq_governor_exit(policy, dbs_data);
+		ret = cpufreq_governor_exit(policy, dbs_data);
 		break;
 	case CPUFREQ_GOV_START:
 		ret = cpufreq_governor_start(policy, dbs_data);
 		break;
 	case CPUFREQ_GOV_STOP:
-		cpufreq_governor_stop(policy, dbs_data);
+		ret = cpufreq_governor_stop(policy, dbs_data);
 		break;
 	case CPUFREQ_GOV_LIMITS:
-		cpufreq_governor_limits(policy, dbs_data);
+		ret = cpufreq_governor_limits(policy, dbs_data);
 		break;
+	default:
+		ret = -EINVAL;
 	}
 
 unlock:
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 34736f5e869d..50f171796632 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -109,7 +109,7 @@ store_one(_gov, file_name)
 
 /* create helper routines */
 #define define_get_cpu_dbs_routines(_dbs_info)				\
-static struct cpu_dbs_common_info *get_cpu_cdbs(int cpu)		\
+static struct cpu_dbs_info *get_cpu_cdbs(int cpu)			\
 {									\
 	return &per_cpu(_dbs_info, cpu).cdbs;				\
 }									\
@@ -128,9 +128,20 @@ static void *get_cpu_dbs_info_s(int cpu)				\
  * cs_*: Conservative governor
  */
 
+/* Common to all CPUs of a policy */
+struct cpu_common_dbs_info {
+	struct cpufreq_policy *policy;
+	/*
+	 * percpu mutex that serializes governor limit change with dbs_timer
+	 * invocation. We do not want dbs_timer to run when user is changing
+	 * the governor or limits.
+	 */
+	struct mutex timer_mutex;
+	ktime_t time_stamp;
+};
+
 /* Per cpu structures */
-struct cpu_dbs_common_info {
-	int cpu;
+struct cpu_dbs_info {
 	u64 prev_cpu_idle;
 	u64 prev_cpu_wall;
 	u64 prev_cpu_nice;
@@ -141,19 +152,12 @@ struct cpu_dbs_common_info {
 	 * wake-up from idle.
 	 */
 	unsigned int prev_load;
-	struct cpufreq_policy *cur_policy;
-	struct delayed_work work;
-	/*
-	 * percpu mutex that serializes governor limit change with gov_dbs_timer
-	 * invocation. We do not want gov_dbs_timer to run when user is changing
-	 * the governor or limits.
-	 */
-	struct mutex timer_mutex;
-	ktime_t time_stamp;
+	struct delayed_work dwork;
+	struct cpu_common_dbs_info *shared;
 };
 
 struct od_cpu_dbs_info_s {
-	struct cpu_dbs_common_info cdbs;
+	struct cpu_dbs_info cdbs;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int freq_lo;
 	unsigned int freq_lo_jiffies;
@@ -163,7 +167,7 @@ struct od_cpu_dbs_info_s {
 };
 
 struct cs_cpu_dbs_info_s {
-	struct cpu_dbs_common_info cdbs;
+	struct cpu_dbs_info cdbs;
 	unsigned int down_skip;
 	unsigned int requested_freq;
 	unsigned int enable:1;
@@ -204,9 +208,11 @@ struct common_dbs_data {
 	 */
 	struct dbs_data *gdbs_data;
 
-	struct cpu_dbs_common_info *(*get_cpu_cdbs)(int cpu);
+	struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
 	void *(*get_cpu_dbs_info_s)(int cpu);
-	void (*gov_dbs_timer)(struct work_struct *work);
+	unsigned int (*gov_dbs_timer)(struct cpu_dbs_info *cdbs,
+				      struct dbs_data *dbs_data,
+				      bool modify_all);
 	void (*gov_check_cpu)(int cpu, unsigned int load);
 	int (*init)(struct dbs_data *dbs_data, bool notify);
 	void (*exit)(struct dbs_data *dbs_data, bool notify);
@@ -265,8 +271,6 @@ static ssize_t show_sampling_rate_min_gov_pol				\
 extern struct mutex cpufreq_governor_lock;
 
 void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
-bool need_load_eval(struct cpu_dbs_common_info *cdbs,
-		unsigned int sampling_rate);
 int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		struct common_dbs_data *cdata, unsigned int event);
 void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 3c1e10f2304c..1fa9088c84a8 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -155,7 +155,7 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 static void od_check_cpu(int cpu, unsigned int load)
 {
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
 	struct dbs_data *dbs_data = policy->governor_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
@@ -191,46 +191,40 @@ static void od_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static void od_dbs_timer(struct work_struct *work)
+static unsigned int od_dbs_timer(struct cpu_dbs_info *cdbs,
+				 struct dbs_data *dbs_data, bool modify_all)
 {
-	struct od_cpu_dbs_info_s *dbs_info =
-		container_of(work, struct od_cpu_dbs_info_s, cdbs.work.work);
-	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
-	struct od_cpu_dbs_info_s *core_dbs_info = &per_cpu(od_cpu_dbs_info,
+	struct cpufreq_policy *policy = cdbs->shared->policy;
+	unsigned int cpu = policy->cpu;
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
 			cpu);
-	struct dbs_data *dbs_data = dbs_info->cdbs.cur_policy->governor_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	int delay = 0, sample_type = core_dbs_info->sample_type;
-	bool modify_all = true;
+	int delay = 0, sample_type = dbs_info->sample_type;
 
-	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
-	if (!need_load_eval(&core_dbs_info->cdbs, od_tuners->sampling_rate)) {
-		modify_all = false;
+	if (!modify_all)
 		goto max_delay;
-	}
 
 	/* Common NORMAL_SAMPLE setup */
-	core_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	dbs_info->sample_type = OD_NORMAL_SAMPLE;
 	if (sample_type == OD_SUB_SAMPLE) {
-		delay = core_dbs_info->freq_lo_jiffies;
-		__cpufreq_driver_target(core_dbs_info->cdbs.cur_policy,
-				core_dbs_info->freq_lo, CPUFREQ_RELATION_H);
+		delay = dbs_info->freq_lo_jiffies;
+		__cpufreq_driver_target(policy, dbs_info->freq_lo,
+					CPUFREQ_RELATION_H);
 	} else {
 		dbs_check_cpu(dbs_data, cpu);
-		if (core_dbs_info->freq_lo) {
+		if (dbs_info->freq_lo) {
 			/* Setup timer for SUB_SAMPLE */
-			core_dbs_info->sample_type = OD_SUB_SAMPLE;
-			delay = core_dbs_info->freq_hi_jiffies;
+			dbs_info->sample_type = OD_SUB_SAMPLE;
+			delay = dbs_info->freq_hi_jiffies;
 		}
 	}
 
 max_delay:
 	if (!delay)
 		delay = delay_for_sampling_rate(od_tuners->sampling_rate
-				* core_dbs_info->rate_mult);
+				* dbs_info->rate_mult);
 
-	gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy, delay, modify_all);
-	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
+	return delay;
 }
 
 /************************** sysfs interface ************************/
@@ -273,27 +267,27 @@ static void update_sampling_rate(struct dbs_data *dbs_data,
 		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 		cpufreq_cpu_put(policy);
 
-		mutex_lock(&dbs_info->cdbs.timer_mutex);
+		mutex_lock(&dbs_info->cdbs.shared->timer_mutex);
 
-		if (!delayed_work_pending(&dbs_info->cdbs.work)) {
-			mutex_unlock(&dbs_info->cdbs.timer_mutex);
+		if (!delayed_work_pending(&dbs_info->cdbs.dwork)) {
+			mutex_unlock(&dbs_info->cdbs.shared->timer_mutex);
 			continue;
 		}
 
 		next_sampling = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->cdbs.work.timer.expires;
+		appointed_at = dbs_info->cdbs.dwork.timer.expires;
 
 		if (time_before(next_sampling, appointed_at)) {
 
-			mutex_unlock(&dbs_info->cdbs.timer_mutex);
-			cancel_delayed_work_sync(&dbs_info->cdbs.work);
-			mutex_lock(&dbs_info->cdbs.timer_mutex);
+			mutex_unlock(&dbs_info->cdbs.shared->timer_mutex);
+			cancel_delayed_work_sync(&dbs_info->cdbs.dwork);
+			mutex_lock(&dbs_info->cdbs.shared->timer_mutex);
 
-			gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy,
-					usecs_to_jiffies(new_rate), true);
+			gov_queue_work(dbs_data, policy,
+				       usecs_to_jiffies(new_rate), true);
 
 		}
-		mutex_unlock(&dbs_info->cdbs.timer_mutex);
+		mutex_unlock(&dbs_info->cdbs.shared->timer_mutex);
 	}
 }
 
@@ -556,13 +550,16 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
+		struct cpu_common_dbs_info *shared;
+
 		if (cpumask_test_cpu(cpu, &done))
 			continue;
 
-		policy = per_cpu(od_cpu_dbs_info, cpu).cdbs.cur_policy;
-		if (!policy)
+		shared = per_cpu(od_cpu_dbs_info, cpu).cdbs.shared;
+		if (!shared)
 			continue;
 
+		policy = shared->policy;
 		cpumask_or(&done, &done, policy->cpus);
 
 		if (policy->governor != &cpufreq_gov_ondemand)
diff --git a/drivers/cpufreq/cpufreq_opp.c b/drivers/cpufreq/cpufreq_opp.c
index 773bcde893c0..0f5e6d5f6da0 100644
--- a/drivers/cpufreq/cpufreq_opp.c
+++ b/drivers/cpufreq/cpufreq_opp.c
@@ -75,6 +75,10 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		}
 		freq_table[i].driver_data = i;
 		freq_table[i].frequency = rate / 1000;
+
+		/* Is Boost/turbo opp ? */
+		if (dev_pm_opp_is_turbo(opp))
+			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
 	}
 
 	freq_table[i].driver_data = i;
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index a0d2a423cea9..4085244c8a67 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -78,7 +78,7 @@ static int eps_acpi_init(void)
 static int eps_acpi_exit(struct cpufreq_policy *policy)
 {
 	if (eps_acpi_cpu_perf) {
-		acpi_processor_unregister_performance(eps_acpi_cpu_perf, 0);
+		acpi_processor_unregister_performance(0);
 		free_cpumask_var(eps_acpi_cpu_perf->shared_cpu_map);
 		kfree(eps_acpi_cpu_perf);
 		eps_acpi_cpu_perf = NULL;
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index ae5b2bd3a978..fa3dd840a837 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -180,7 +180,7 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 		ret = exynos5250_cpufreq_init(exynos_info);
 	} else {
 		pr_err("%s: Unknown SoC type\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
 	}
 
 	if (ret)
@@ -188,12 +188,14 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 
 	if (exynos_info->set_freq == NULL) {
 		dev_err(&pdev->dev, "No set_freq function (ERR)\n");
+		ret = -EINVAL;
 		goto err_vdd_arm;
 	}
 
 	arm_regulator = regulator_get(NULL, "vdd_arm");
 	if (IS_ERR(arm_regulator)) {
 		dev_err(&pdev->dev, "failed to get resource vdd_arm\n");
+		ret = -EINVAL;
 		goto err_vdd_arm;
 	}
 
@@ -225,7 +227,7 @@ err_cpufreq_reg:
 	regulator_put(arm_regulator);
 err_vdd_arm:
 	kfree(exynos_info);
-	return -EINVAL;
+	return ret;
 }
 
 static struct platform_driver exynos_cpufreq_platdrv = {
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index df14766a8e06..a8f1daffc9bc 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -18,6 +18,21 @@
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
 
+bool policy_has_boost_freq(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+
+	if (!table)
+		return false;
+
+	cpufreq_for_each_valid_entry(pos, table)
+		if (pos->flags & CPUFREQ_BOOST_FREQ)
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(policy_has_boost_freq);
+
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table)
 {
@@ -297,15 +312,6 @@ int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu);
-
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	return policy ? policy->freq_table : NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq frequency table helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index c30aaa6a54e8..0202429f1c5b 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -29,7 +29,6 @@ MODULE_LICENSE("GPL");
 
 struct cpufreq_acpi_io {
 	struct acpi_processor_performance	acpi_data;
-	struct cpufreq_frequency_table		*freq_table;
 	unsigned int				resume;
 };
 
@@ -221,6 +220,7 @@ acpi_cpufreq_cpu_init (
 	unsigned int		cpu = policy->cpu;
 	struct cpufreq_acpi_io	*data;
 	unsigned int		result = 0;
+	struct cpufreq_frequency_table *freq_table;
 
 	pr_debug("acpi_cpufreq_cpu_init\n");
 
@@ -254,10 +254,10 @@ acpi_cpufreq_cpu_init (
 	}
 
 	/* alloc freq_table */
-	data->freq_table = kzalloc(sizeof(*data->freq_table) *
+	freq_table = kzalloc(sizeof(*freq_table) *
 	                           (data->acpi_data.state_count + 1),
 	                           GFP_KERNEL);
-	if (!data->freq_table) {
+	if (!freq_table) {
 		result = -ENOMEM;
 		goto err_unreg;
 	}
@@ -276,14 +276,14 @@ acpi_cpufreq_cpu_init (
 	for (i = 0; i <= data->acpi_data.state_count; i++)
 	{
 		if (i < data->acpi_data.state_count) {
-			data->freq_table[i].frequency =
+			freq_table[i].frequency =
 			      data->acpi_data.states[i].core_frequency * 1000;
 		} else {
-			data->freq_table[i].frequency = CPUFREQ_TABLE_END;
+			freq_table[i].frequency = CPUFREQ_TABLE_END;
 		}
 	}
 
-	result = cpufreq_table_validate_and_show(policy, data->freq_table);
+	result = cpufreq_table_validate_and_show(policy, freq_table);
 	if (result) {
 		goto err_freqfree;
 	}
@@ -311,9 +311,9 @@ acpi_cpufreq_cpu_init (
 	return (result);
 
  err_freqfree:
-	kfree(data->freq_table);
+	kfree(freq_table);
  err_unreg:
-	acpi_processor_unregister_performance(&data->acpi_data, cpu);
+	acpi_processor_unregister_performance(cpu);
  err_free:
 	kfree(data);
 	acpi_io_data[cpu] = NULL;
@@ -332,8 +332,8 @@ acpi_cpufreq_cpu_exit (
 
 	if (data) {
 		acpi_io_data[policy->cpu] = NULL;
-		acpi_processor_unregister_performance(&data->acpi_data,
-		                                      policy->cpu);
+		acpi_processor_unregister_performance(policy->cpu);
+		kfree(policy->freq_table);
 		kfree(data);
 	}
 
diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c
index 129e266f7621..2faa4216bf2a 100644
--- a/drivers/cpufreq/integrator-cpufreq.c
+++ b/drivers/cpufreq/integrator-cpufreq.c
@@ -98,11 +98,10 @@ static int integrator_set_target(struct cpufreq_policy *policy,
 	/* get current setting */
 	cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET);
 
-	if (machine_is_integrator()) {
+	if (machine_is_integrator())
 		vco.s = (cm_osc >> 8) & 7;
-	} else if (machine_is_cintegrator()) {
+	else if (machine_is_cintegrator())
 		vco.s = 1;
-	}
 	vco.v = cm_osc & 255;
 	vco.r = 22;
 	freqs.old = icst_hz(&cclk_params, vco) / 1000;
@@ -163,11 +162,10 @@ static unsigned int integrator_get(unsigned int cpu)
 	/* detect memory etc. */
 	cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET);
 
-	if (machine_is_integrator()) {
+	if (machine_is_integrator())
 		vco.s = (cm_osc >> 8) & 7;
-	} else {
+	else
 		vco.s = 1;
-	}
 	vco.v = cm_osc & 255;
 	vco.r = 22;
 
@@ -203,7 +201,7 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev)
 	struct resource *res;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-        if (!res)
+	if (!res)
 		return -ENODEV;
 
 	cm_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
@@ -234,6 +232,6 @@ static struct platform_driver integrator_cpufreq_driver = {
 module_platform_driver_probe(integrator_cpufreq_driver,
 			     integrator_cpufreq_probe);
 
-MODULE_AUTHOR ("Russell M. King");
-MODULE_DESCRIPTION ("cpufreq driver for ARM Integrator CPUs");
-MODULE_LICENSE ("GPL");
+MODULE_AUTHOR("Russell M. King");
+MODULE_DESCRIPTION("cpufreq driver for ARM Integrator CPUs");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 15ada47bb720..cddc61939a86 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -484,12 +484,11 @@ static void __init intel_pstate_sysfs_expose_params(void)
 }
 /************************** sysfs end ************************/
 
-static void intel_pstate_hwp_enable(void)
+static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
-	hwp_active++;
 	pr_info("intel_pstate: HWP enabled\n");
 
-	wrmsrl( MSR_PM_ENABLE, 0x1);
+	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
 static int byt_get_min_pstate(void)
@@ -522,7 +521,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	int32_t vid_fp;
 	u32 vid;
 
-	val = pstate << 8;
+	val = (u64)pstate << 8;
 	if (limits.no_turbo && !limits.turbo_disabled)
 		val |= (u64)1 << 32;
 
@@ -611,7 +610,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 
-	val = pstate << 8;
+	val = (u64)pstate << 8;
 	if (limits.no_turbo && !limits.turbo_disabled)
 		val |= (u64)1 << 32;
 
@@ -681,6 +680,7 @@ static struct cpu_defaults knl_params = {
 		.get_max = core_get_max_pstate,
 		.get_min = core_get_min_pstate,
 		.get_turbo = knl_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
 	},
 };
@@ -765,7 +765,7 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
-	tsc = native_read_tsc();
+	tsc = rdtsc();
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
@@ -908,6 +908,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x4c, byt_params),
 	ICPU(0x4e, core_params),
 	ICPU(0x4f, core_params),
+	ICPU(0x5e, core_params),
 	ICPU(0x56, core_params),
 	ICPU(0x57, knl_params),
 	{}
@@ -932,6 +933,10 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu = all_cpu_data[cpunum];
 
 	cpu->cpu = cpunum;
+
+	if (hwp_active)
+		intel_pstate_hwp_enable(cpu);
+
 	intel_pstate_get_cpu_pstates(cpu);
 
 	init_timer_deferrable(&cpu->timer);
@@ -1169,6 +1174,10 @@ static struct hw_vendor_info vendor_info[] = {
 	{1, "ORACLE", "X4270M3 ", PPC},
 	{1, "ORACLE", "X4270M2 ", PPC},
 	{1, "ORACLE", "X4170M2 ", PPC},
+	{1, "ORACLE", "X4170 M3", PPC},
+	{1, "ORACLE", "X4275 M3", PPC},
+	{1, "ORACLE", "X6-2    ", PPC},
+	{1, "ORACLE", "Sudbury ", PPC},
 	{0, "", ""},
 };
 
@@ -1245,7 +1254,7 @@ static int __init intel_pstate_init(void)
 		return -ENOMEM;
 
 	if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp)
-		intel_pstate_hwp_enable();
+		hwp_active++;
 
 	if (!hwp_active && hwp_only)
 		goto out;
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index fc897babab55..cd593c1f66dc 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -3,7 +3,7 @@
  *
  * The 2E revision of loongson processor not support this feature.
  *
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -20,7 +20,7 @@
 #include <asm/clock.h>
 #include <asm/idle.h>
 
-#include <asm/mach-loongson/loongson.h>
+#include <asm/mach-loongson64/loongson.h>
 
 static uint nowait;
 
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
new file mode 100644
index 000000000000..49caed293a3b
--- /dev/null
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -0,0 +1,527 @@
+/*
+ * Copyright (c) 2015 Linaro Ltd.
+ * Author: Pi-Cheng Chen <pi-cheng.chen@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/cpu_cooling.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#define MIN_VOLT_SHIFT		(100000)
+#define MAX_VOLT_SHIFT		(200000)
+#define MAX_VOLT_LIMIT		(1150000)
+#define VOLT_TOL		(10000)
+
+/*
+ * The struct mtk_cpu_dvfs_info holds necessary information for doing CPU DVFS
+ * on each CPU power/clock domain of Mediatek SoCs. Each CPU cluster in
+ * Mediatek SoCs has two voltage inputs, Vproc and Vsram. In some cases the two
+ * voltage inputs need to be controlled under a hardware limitation:
+ * 100mV < Vsram - Vproc < 200mV
+ *
+ * When scaling the clock frequency of a CPU clock domain, the clock source
+ * needs to be switched to another stable PLL clock temporarily until
+ * the original PLL becomes stable at target frequency.
+ */
+struct mtk_cpu_dvfs_info {
+	struct device *cpu_dev;
+	struct regulator *proc_reg;
+	struct regulator *sram_reg;
+	struct clk *cpu_clk;
+	struct clk *inter_clk;
+	struct thermal_cooling_device *cdev;
+	int intermediate_voltage;
+	bool need_voltage_tracking;
+};
+
+static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
+					int new_vproc)
+{
+	struct regulator *proc_reg = info->proc_reg;
+	struct regulator *sram_reg = info->sram_reg;
+	int old_vproc, old_vsram, new_vsram, vsram, vproc, ret;
+
+	old_vproc = regulator_get_voltage(proc_reg);
+	old_vsram = regulator_get_voltage(sram_reg);
+	/* Vsram should not exceed the maximum allowed voltage of SoC. */
+	new_vsram = min(new_vproc + MIN_VOLT_SHIFT, MAX_VOLT_LIMIT);
+
+	if (old_vproc < new_vproc) {
+		/*
+		 * When scaling up voltages, Vsram and Vproc scale up step
+		 * by step. At each step, set Vsram to (Vproc + 200mV) first,
+		 * then set Vproc to (Vsram - 100mV).
+		 * Keep doing it until Vsram and Vproc hit target voltages.
+		 */
+		do {
+			old_vsram = regulator_get_voltage(sram_reg);
+			old_vproc = regulator_get_voltage(proc_reg);
+
+			vsram = min(new_vsram, old_vproc + MAX_VOLT_SHIFT);
+
+			if (vsram + VOLT_TOL >= MAX_VOLT_LIMIT) {
+				vsram = MAX_VOLT_LIMIT;
+
+				/*
+				 * If the target Vsram hits the maximum voltage,
+				 * try to set the exact voltage value first.
+				 */
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram);
+				if (ret)
+					ret = regulator_set_voltage(sram_reg,
+							vsram - VOLT_TOL,
+							vsram);
+
+				vproc = new_vproc;
+			} else {
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram + VOLT_TOL);
+
+				vproc = vsram - MIN_VOLT_SHIFT;
+			}
+			if (ret)
+				return ret;
+
+			ret = regulator_set_voltage(proc_reg, vproc,
+						    vproc + VOLT_TOL);
+			if (ret) {
+				regulator_set_voltage(sram_reg, old_vsram,
+						      old_vsram);
+				return ret;
+			}
+		} while (vproc < new_vproc || vsram < new_vsram);
+	} else if (old_vproc > new_vproc) {
+		/*
+		 * When scaling down voltages, Vsram and Vproc scale down step
+		 * by step. At each step, set Vproc to (Vsram - 200mV) first,
+		 * then set Vproc to (Vproc + 100mV).
+		 * Keep doing it until Vsram and Vproc hit target voltages.
+		 */
+		do {
+			old_vproc = regulator_get_voltage(proc_reg);
+			old_vsram = regulator_get_voltage(sram_reg);
+
+			vproc = max(new_vproc, old_vsram - MAX_VOLT_SHIFT);
+			ret = regulator_set_voltage(proc_reg, vproc,
+						    vproc + VOLT_TOL);
+			if (ret)
+				return ret;
+
+			if (vproc == new_vproc)
+				vsram = new_vsram;
+			else
+				vsram = max(new_vsram, vproc + MIN_VOLT_SHIFT);
+
+			if (vsram + VOLT_TOL >= MAX_VOLT_LIMIT) {
+				vsram = MAX_VOLT_LIMIT;
+
+				/*
+				 * If the target Vsram hits the maximum voltage,
+				 * try to set the exact voltage value first.
+				 */
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram);
+				if (ret)
+					ret = regulator_set_voltage(sram_reg,
+							vsram - VOLT_TOL,
+							vsram);
+			} else {
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram + VOLT_TOL);
+			}
+
+			if (ret) {
+				regulator_set_voltage(proc_reg, old_vproc,
+						      old_vproc);
+				return ret;
+			}
+		} while (vproc > new_vproc + VOLT_TOL ||
+			 vsram > new_vsram + VOLT_TOL);
+	}
+
+	return 0;
+}
+
+static int mtk_cpufreq_set_voltage(struct mtk_cpu_dvfs_info *info, int vproc)
+{
+	if (info->need_voltage_tracking)
+		return mtk_cpufreq_voltage_tracking(info, vproc);
+	else
+		return regulator_set_voltage(info->proc_reg, vproc,
+					     vproc + VOLT_TOL);
+}
+
+static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
+				  unsigned int index)
+{
+	struct cpufreq_frequency_table *freq_table = policy->freq_table;
+	struct clk *cpu_clk = policy->clk;
+	struct clk *armpll = clk_get_parent(cpu_clk);
+	struct mtk_cpu_dvfs_info *info = policy->driver_data;
+	struct device *cpu_dev = info->cpu_dev;
+	struct dev_pm_opp *opp;
+	long freq_hz, old_freq_hz;
+	int vproc, old_vproc, inter_vproc, target_vproc, ret;
+
+	inter_vproc = info->intermediate_voltage;
+
+	old_freq_hz = clk_get_rate(cpu_clk);
+	old_vproc = regulator_get_voltage(info->proc_reg);
+
+	freq_hz = freq_table[index].frequency * 1000;
+
+	rcu_read_lock();
+	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
+		pr_err("cpu%d: failed to find OPP for %ld\n",
+		       policy->cpu, freq_hz);
+		return PTR_ERR(opp);
+	}
+	vproc = dev_pm_opp_get_voltage(opp);
+	rcu_read_unlock();
+
+	/*
+	 * If the new voltage or the intermediate voltage is higher than the
+	 * current voltage, scale up voltage first.
+	 */
+	target_vproc = (inter_vproc > vproc) ? inter_vproc : vproc;
+	if (old_vproc < target_vproc) {
+		ret = mtk_cpufreq_set_voltage(info, target_vproc);
+		if (ret) {
+			pr_err("cpu%d: failed to scale up voltage!\n",
+			       policy->cpu);
+			mtk_cpufreq_set_voltage(info, old_vproc);
+			return ret;
+		}
+	}
+
+	/* Reparent the CPU clock to intermediate clock. */
+	ret = clk_set_parent(cpu_clk, info->inter_clk);
+	if (ret) {
+		pr_err("cpu%d: failed to re-parent cpu clock!\n",
+		       policy->cpu);
+		mtk_cpufreq_set_voltage(info, old_vproc);
+		WARN_ON(1);
+		return ret;
+	}
+
+	/* Set the original PLL to target rate. */
+	ret = clk_set_rate(armpll, freq_hz);
+	if (ret) {
+		pr_err("cpu%d: failed to scale cpu clock rate!\n",
+		       policy->cpu);
+		clk_set_parent(cpu_clk, armpll);
+		mtk_cpufreq_set_voltage(info, old_vproc);
+		return ret;
+	}
+
+	/* Set parent of CPU clock back to the original PLL. */
+	ret = clk_set_parent(cpu_clk, armpll);
+	if (ret) {
+		pr_err("cpu%d: failed to re-parent cpu clock!\n",
+		       policy->cpu);
+		mtk_cpufreq_set_voltage(info, inter_vproc);
+		WARN_ON(1);
+		return ret;
+	}
+
+	/*
+	 * If the new voltage is lower than the intermediate voltage or the
+	 * original voltage, scale down to the new voltage.
+	 */
+	if (vproc < inter_vproc || vproc < old_vproc) {
+		ret = mtk_cpufreq_set_voltage(info, vproc);
+		if (ret) {
+			pr_err("cpu%d: failed to scale down voltage!\n",
+			       policy->cpu);
+			clk_set_parent(cpu_clk, info->inter_clk);
+			clk_set_rate(armpll, old_freq_hz);
+			clk_set_parent(cpu_clk, armpll);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	struct mtk_cpu_dvfs_info *info = policy->driver_data;
+	struct device_node *np = of_node_get(info->cpu_dev->of_node);
+
+	if (WARN_ON(!np))
+		return;
+
+	if (of_find_property(np, "#cooling-cells", NULL)) {
+		info->cdev = of_cpufreq_cooling_register(np,
+							 policy->related_cpus);
+
+		if (IS_ERR(info->cdev)) {
+			dev_err(info->cpu_dev,
+				"running cpufreq without cooling device: %ld\n",
+				PTR_ERR(info->cdev));
+
+			info->cdev = NULL;
+		}
+	}
+
+	of_node_put(np);
+}
+
+static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
+{
+	struct device *cpu_dev;
+	struct regulator *proc_reg = ERR_PTR(-ENODEV);
+	struct regulator *sram_reg = ERR_PTR(-ENODEV);
+	struct clk *cpu_clk = ERR_PTR(-ENODEV);
+	struct clk *inter_clk = ERR_PTR(-ENODEV);
+	struct dev_pm_opp *opp;
+	unsigned long rate;
+	int ret;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", cpu);
+		return -ENODEV;
+	}
+
+	cpu_clk = clk_get(cpu_dev, "cpu");
+	if (IS_ERR(cpu_clk)) {
+		if (PTR_ERR(cpu_clk) == -EPROBE_DEFER)
+			pr_warn("cpu clk for cpu%d not ready, retry.\n", cpu);
+		else
+			pr_err("failed to get cpu clk for cpu%d\n", cpu);
+
+		ret = PTR_ERR(cpu_clk);
+		return ret;
+	}
+
+	inter_clk = clk_get(cpu_dev, "intermediate");
+	if (IS_ERR(inter_clk)) {
+		if (PTR_ERR(inter_clk) == -EPROBE_DEFER)
+			pr_warn("intermediate clk for cpu%d not ready, retry.\n",
+				cpu);
+		else
+			pr_err("failed to get intermediate clk for cpu%d\n",
+			       cpu);
+
+		ret = PTR_ERR(inter_clk);
+		goto out_free_resources;
+	}
+
+	proc_reg = regulator_get_exclusive(cpu_dev, "proc");
+	if (IS_ERR(proc_reg)) {
+		if (PTR_ERR(proc_reg) == -EPROBE_DEFER)
+			pr_warn("proc regulator for cpu%d not ready, retry.\n",
+				cpu);
+		else
+			pr_err("failed to get proc regulator for cpu%d\n",
+			       cpu);
+
+		ret = PTR_ERR(proc_reg);
+		goto out_free_resources;
+	}
+
+	/* Both presence and absence of sram regulator are valid cases. */
+	sram_reg = regulator_get_exclusive(cpu_dev, "sram");
+
+	ret = of_init_opp_table(cpu_dev);
+	if (ret) {
+		pr_warn("no OPP table for cpu%d\n", cpu);
+		goto out_free_resources;
+	}
+
+	/* Search a safe voltage for intermediate frequency. */
+	rate = clk_get_rate(inter_clk);
+	rcu_read_lock();
+	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
+		pr_err("failed to get intermediate opp for cpu%d\n", cpu);
+		ret = PTR_ERR(opp);
+		goto out_free_opp_table;
+	}
+	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
+	rcu_read_unlock();
+
+	info->cpu_dev = cpu_dev;
+	info->proc_reg = proc_reg;
+	info->sram_reg = IS_ERR(sram_reg) ? NULL : sram_reg;
+	info->cpu_clk = cpu_clk;
+	info->inter_clk = inter_clk;
+
+	/*
+	 * If SRAM regulator is present, software "voltage tracking" is needed
+	 * for this CPU power domain.
+	 */
+	info->need_voltage_tracking = !IS_ERR(sram_reg);
+
+	return 0;
+
+out_free_opp_table:
+	of_free_opp_table(cpu_dev);
+
+out_free_resources:
+	if (!IS_ERR(proc_reg))
+		regulator_put(proc_reg);
+	if (!IS_ERR(sram_reg))
+		regulator_put(sram_reg);
+	if (!IS_ERR(cpu_clk))
+		clk_put(cpu_clk);
+	if (!IS_ERR(inter_clk))
+		clk_put(inter_clk);
+
+	return ret;
+}
+
+static void mtk_cpu_dvfs_info_release(struct mtk_cpu_dvfs_info *info)
+{
+	if (!IS_ERR(info->proc_reg))
+		regulator_put(info->proc_reg);
+	if (!IS_ERR(info->sram_reg))
+		regulator_put(info->sram_reg);
+	if (!IS_ERR(info->cpu_clk))
+		clk_put(info->cpu_clk);
+	if (!IS_ERR(info->inter_clk))
+		clk_put(info->inter_clk);
+
+	of_free_opp_table(info->cpu_dev);
+}
+
+static int mtk_cpufreq_init(struct cpufreq_policy *policy)
+{
+	struct mtk_cpu_dvfs_info *info;
+	struct cpufreq_frequency_table *freq_table;
+	int ret;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	ret = mtk_cpu_dvfs_info_init(info, policy->cpu);
+	if (ret) {
+		pr_err("%s failed to initialize dvfs info for cpu%d\n",
+		       __func__, policy->cpu);
+		goto out_free_dvfs_info;
+	}
+
+	ret = dev_pm_opp_init_cpufreq_table(info->cpu_dev, &freq_table);
+	if (ret) {
+		pr_err("failed to init cpufreq table for cpu%d: %d\n",
+		       policy->cpu, ret);
+		goto out_release_dvfs_info;
+	}
+
+	ret = cpufreq_table_validate_and_show(policy, freq_table);
+	if (ret) {
+		pr_err("%s: invalid frequency table: %d\n", __func__, ret);
+		goto out_free_cpufreq_table;
+	}
+
+	/* CPUs in the same cluster share a clock and power domain. */
+	cpumask_copy(policy->cpus, &cpu_topology[policy->cpu].core_sibling);
+	policy->driver_data = info;
+	policy->clk = info->cpu_clk;
+
+	return 0;
+
+out_free_cpufreq_table:
+	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &freq_table);
+
+out_release_dvfs_info:
+	mtk_cpu_dvfs_info_release(info);
+
+out_free_dvfs_info:
+	kfree(info);
+
+	return ret;
+}
+
+static int mtk_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct mtk_cpu_dvfs_info *info = policy->driver_data;
+
+	cpufreq_cooling_unregister(info->cdev);
+	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &policy->freq_table);
+	mtk_cpu_dvfs_info_release(info);
+	kfree(info);
+
+	return 0;
+}
+
+static struct cpufreq_driver mt8173_cpufreq_driver = {
+	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify = cpufreq_generic_frequency_table_verify,
+	.target_index = mtk_cpufreq_set_target,
+	.get = cpufreq_generic_get,
+	.init = mtk_cpufreq_init,
+	.exit = mtk_cpufreq_exit,
+	.ready = mtk_cpufreq_ready,
+	.name = "mtk-cpufreq",
+	.attr = cpufreq_generic_attr,
+};
+
+static int mt8173_cpufreq_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = cpufreq_register_driver(&mt8173_cpufreq_driver);
+	if (ret)
+		pr_err("failed to register mtk cpufreq driver\n");
+
+	return ret;
+}
+
+static struct platform_driver mt8173_cpufreq_platdrv = {
+	.driver = {
+		.name	= "mt8173-cpufreq",
+	},
+	.probe		= mt8173_cpufreq_probe,
+};
+
+static int mt8173_cpufreq_driver_init(void)
+{
+	struct platform_device *pdev;
+	int err;
+
+	if (!of_machine_is_compatible("mediatek,mt8173"))
+		return -ENODEV;
+
+	err = platform_driver_register(&mt8173_cpufreq_platdrv);
+	if (err)
+		return err;
+
+	/*
+	 * Since there's no place to hold device registration code and no
+	 * device tree based way to match cpufreq driver yet, both the driver
+	 * and the device registration codes are put here to handle defer
+	 * probing.
+	 */
+	pdev = platform_device_register_simple("mt8173-cpufreq", -1, NULL, 0);
+	if (IS_ERR(pdev)) {
+		pr_err("failed to register mtk-cpufreq platform device\n");
+		return PTR_ERR(pdev);
+	}
+
+	return 0;
+}
+device_initcall(mt8173_cpufreq_driver_init);
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 37c5742482d8..c1ae1999770a 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -421,7 +421,7 @@ static int powernow_acpi_init(void)
 	return 0;
 
 err2:
-	acpi_processor_unregister_performance(acpi_processor_perf, 0);
+	acpi_processor_unregister_performance(0);
 err1:
 	free_cpumask_var(acpi_processor_perf->shared_cpu_map);
 err05:
@@ -661,7 +661,7 @@ static int powernow_cpu_exit(struct cpufreq_policy *policy)
 {
 #ifdef CONFIG_X86_POWERNOW_K7_ACPI
 	if (acpi_processor_perf) {
-		acpi_processor_unregister_performance(acpi_processor_perf, 0);
+		acpi_processor_unregister_performance(0);
 		free_cpumask_var(acpi_processor_perf->shared_cpu_map);
 		kfree(acpi_processor_perf);
 	}
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 5c035d04d827..0b5bf135b090 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -795,7 +795,7 @@ err_out_mem:
 	kfree(powernow_table);
 
 err_out:
-	acpi_processor_unregister_performance(&data->acpi_data, data->cpu);
+	acpi_processor_unregister_performance(data->cpu);
 
 	/* data->acpi_data.state_count informs us at ->exit()
 	 * whether ACPI was used */
@@ -863,8 +863,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
 {
 	if (data->acpi_data.state_count)
-		acpi_processor_unregister_performance(&data->acpi_data,
-				data->cpu);
+		acpi_processor_unregister_performance(data->cpu);
 	free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
 
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index ebef0d8279c7..64994e10638e 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -27,20 +27,31 @@
 #include <linux/smp.h>
 #include <linux/of.h>
 #include <linux/reboot.h>
+#include <linux/slab.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
 #include <asm/reg.h>
 #include <asm/smp.h> /* Required for cpu_sibling_mask() in UP configs */
+#include <asm/opal.h>
 
 #define POWERNV_MAX_PSTATES	256
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
 #define PMSR_SPR_EM_DISABLE	(1UL << 31)
 #define PMSR_MAX(x)		((x >> 32) & 0xFF)
-#define PMSR_LP(x)		((x >> 48) & 0xFF)
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
-static bool rebooting, throttled;
+static bool rebooting, throttled, occ_reset;
+
+static struct chip {
+	unsigned int id;
+	bool throttled;
+	cpumask_t mask;
+	struct work_struct throttle;
+	bool restore;
+} *chips;
+
+static int nr_chips;
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -298,28 +309,35 @@ static inline unsigned int get_nominal_index(void)
 	return powernv_pstate_info.max - powernv_pstate_info.nominal;
 }
 
-static void powernv_cpufreq_throttle_check(unsigned int cpu)
+static void powernv_cpufreq_throttle_check(void *data)
 {
+	unsigned int cpu = smp_processor_id();
 	unsigned long pmsr;
-	int pmsr_pmax, pmsr_lp;
+	int pmsr_pmax, i;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 
+	for (i = 0; i < nr_chips; i++)
+		if (chips[i].id == cpu_to_chip_id(cpu))
+			break;
+
 	/* Check for Pmax Capping */
 	pmsr_pmax = (s8)PMSR_MAX(pmsr);
 	if (pmsr_pmax != powernv_pstate_info.max) {
-		throttled = true;
-		pr_info("CPU %d Pmax is reduced to %d\n", cpu, pmsr_pmax);
-		pr_info("Max allowed Pstate is capped\n");
+		if (chips[i].throttled)
+			goto next;
+		chips[i].throttled = true;
+		pr_info("CPU %d on Chip %u has Pmax reduced to %d\n", cpu,
+			chips[i].id, pmsr_pmax);
+	} else if (chips[i].throttled) {
+		chips[i].throttled = false;
+		pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu,
+			chips[i].id, pmsr_pmax);
 	}
 
-	/*
-	 * Check for Psafe by reading LocalPstate
-	 * or check if Psafe_mode_active is set in PMSR.
-	 */
-	pmsr_lp = (s8)PMSR_LP(pmsr);
-	if ((pmsr_lp < powernv_pstate_info.min) ||
-				(pmsr & PMSR_PSAFE_ENABLE)) {
+	/* Check if Psafe_mode_active is set in PMSR. */
+next:
+	if (pmsr & PMSR_PSAFE_ENABLE) {
 		throttled = true;
 		pr_info("Pstate set to safe frequency\n");
 	}
@@ -350,7 +368,7 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 		return 0;
 
 	if (!throttled)
-		powernv_cpufreq_throttle_check(smp_processor_id());
+		powernv_cpufreq_throttle_check(NULL);
 
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
@@ -395,6 +413,119 @@ static struct notifier_block powernv_cpufreq_reboot_nb = {
 	.notifier_call = powernv_cpufreq_reboot_notifier,
 };
 
+void powernv_cpufreq_work_fn(struct work_struct *work)
+{
+	struct chip *chip = container_of(work, struct chip, throttle);
+	unsigned int cpu;
+	cpumask_var_t mask;
+
+	smp_call_function_any(&chip->mask,
+			      powernv_cpufreq_throttle_check, NULL, 0);
+
+	if (!chip->restore)
+		return;
+
+	chip->restore = false;
+	cpumask_copy(mask, &chip->mask);
+	for_each_cpu_and(cpu, mask, cpu_online_mask) {
+		int index, tcpu;
+		struct cpufreq_policy policy;
+
+		cpufreq_get_policy(&policy, cpu);
+		cpufreq_frequency_table_target(&policy, policy.freq_table,
+					       policy.cur,
+					       CPUFREQ_RELATION_C, &index);
+		powernv_cpufreq_target_index(&policy, index);
+		for_each_cpu(tcpu, policy.cpus)
+			cpumask_clear_cpu(tcpu, mask);
+	}
+}
+
+static char throttle_reason[][30] = {
+					"No throttling",
+					"Power Cap",
+					"Processor Over Temperature",
+					"Power Supply Failure",
+					"Over Current",
+					"OCC Reset"
+				     };
+
+static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
+				   unsigned long msg_type, void *_msg)
+{
+	struct opal_msg *msg = _msg;
+	struct opal_occ_msg omsg;
+	int i;
+
+	if (msg_type != OPAL_MSG_OCC)
+		return 0;
+
+	omsg.type = be64_to_cpu(msg->params[0]);
+
+	switch (omsg.type) {
+	case OCC_RESET:
+		occ_reset = true;
+		pr_info("OCC (On Chip Controller - enforces hard thermal/power limits) Resetting\n");
+		/*
+		 * powernv_cpufreq_throttle_check() is called in
+		 * target() callback which can detect the throttle state
+		 * for governors like ondemand.
+		 * But static governors will not call target() often thus
+		 * report throttling here.
+		 */
+		if (!throttled) {
+			throttled = true;
+			pr_crit("CPU frequency is throttled for duration\n");
+		}
+
+		break;
+	case OCC_LOAD:
+		pr_info("OCC Loading, CPU frequency is throttled until OCC is started\n");
+		break;
+	case OCC_THROTTLE:
+		omsg.chip = be64_to_cpu(msg->params[1]);
+		omsg.throttle_status = be64_to_cpu(msg->params[2]);
+
+		if (occ_reset) {
+			occ_reset = false;
+			throttled = false;
+			pr_info("OCC Active, CPU frequency is no longer throttled\n");
+
+			for (i = 0; i < nr_chips; i++) {
+				chips[i].restore = true;
+				schedule_work(&chips[i].throttle);
+			}
+
+			return 0;
+		}
+
+		if (omsg.throttle_status &&
+		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS)
+			pr_info("OCC: Chip %u Pmax reduced due to %s\n",
+				(unsigned int)omsg.chip,
+				throttle_reason[omsg.throttle_status]);
+		else if (!omsg.throttle_status)
+			pr_info("OCC: Chip %u %s\n", (unsigned int)omsg.chip,
+				throttle_reason[omsg.throttle_status]);
+		else
+			return 0;
+
+		for (i = 0; i < nr_chips; i++)
+			if (chips[i].id == omsg.chip) {
+				if (!omsg.throttle_status)
+					chips[i].restore = true;
+				schedule_work(&chips[i].throttle);
+			}
+	}
+	return 0;
+}
+
+static struct notifier_block powernv_cpufreq_opal_nb = {
+	.notifier_call	= powernv_cpufreq_occ_msg,
+	.next		= NULL,
+	.priority	= 0,
+};
+
 static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
 	struct powernv_smp_call_data freq_data;
@@ -414,6 +545,36 @@ static struct cpufreq_driver powernv_cpufreq_driver = {
 	.attr		= powernv_cpu_freq_attr,
 };
 
+static int init_chip_info(void)
+{
+	unsigned int chip[256];
+	unsigned int cpu, i;
+	unsigned int prev_chip_id = UINT_MAX;
+
+	for_each_possible_cpu(cpu) {
+		unsigned int id = cpu_to_chip_id(cpu);
+
+		if (prev_chip_id != id) {
+			prev_chip_id = id;
+			chip[nr_chips++] = id;
+		}
+	}
+
+	chips = kmalloc_array(nr_chips, sizeof(struct chip), GFP_KERNEL);
+	if (!chips)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_chips; i++) {
+		chips[i].id = chip[i];
+		chips[i].throttled = false;
+		cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
+		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
+		chips[i].restore = false;
+	}
+
+	return 0;
+}
+
 static int __init powernv_cpufreq_init(void)
 {
 	int rc = 0;
@@ -429,7 +590,13 @@ static int __init powernv_cpufreq_init(void)
 		return rc;
 	}
 
+	/* Populate chip info */
+	rc = init_chip_info();
+	if (rc)
+		return rc;
+
 	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
+	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
 	return cpufreq_register_driver(&powernv_cpufreq_driver);
 }
 module_init(powernv_cpufreq_init);
@@ -437,6 +604,8 @@ module_init(powernv_cpufreq_init);
 static void __exit powernv_cpufreq_exit(void)
 {
 	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
+	opal_message_notifier_unregister(OPAL_MSG_OCC,
+					 &powernv_cpufreq_opal_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
 }
 module_exit(powernv_cpufreq_exit);
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index d29e8da396a0..7969f7690498 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -97,8 +97,8 @@ static int pmi_notifier(struct notifier_block *nb,
 	struct cpufreq_frequency_table *cbe_freqs;
 	u8 node;
 
-	/* Should this really be called for CPUFREQ_ADJUST, CPUFREQ_INCOMPATIBLE
-	 * and CPUFREQ_NOTIFY policy events?)
+	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
+	 * policy events?)
 	 */
 	if (event == CPUFREQ_START)
 		return 0;
diff --git a/drivers/cpufreq/sfi-cpufreq.c b/drivers/cpufreq/sfi-cpufreq.c
index ffa3389e535b..992ce6f9abec 100644
--- a/drivers/cpufreq/sfi-cpufreq.c
+++ b/drivers/cpufreq/sfi-cpufreq.c
@@ -45,12 +45,10 @@ static int sfi_parse_freq(struct sfi_table_header *table)
 	pentry = (struct sfi_freq_table_entry *)sb->pentry;
 	totallen = num_freq_table_entries * sizeof(*pentry);
 
-	sfi_cpufreq_array = kzalloc(totallen, GFP_KERNEL);
+	sfi_cpufreq_array = kmemdup(pentry, totallen, GFP_KERNEL);
 	if (!sfi_cpufreq_array)
 		return -ENOMEM;
 
-	memcpy(sfi_cpufreq_array, pentry, totallen);
-
 	return 0;
 }
 
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 4ab7a2156672..15d3214aaa00 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -386,7 +386,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 	unsigned int prev_speed;
 	unsigned int ret = 0;
 	unsigned long flags;
-	struct timeval tv1, tv2;
+	ktime_t tv1, tv2;
 
 	if ((!processor) || (!low_speed) || (!high_speed) || (!set_state))
 		return -EINVAL;
@@ -415,14 +415,14 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 	/* start latency measurement */
 	if (transition_latency)
-		do_gettimeofday(&tv1);
+		tv1 = ktime_get();
 
 	/* switch to high state */
 	set_state(SPEEDSTEP_HIGH);
 
 	/* end latency measurement */
 	if (transition_latency)
-		do_gettimeofday(&tv2);
+		tv2 = ktime_get();
 
 	*high_speed = speedstep_get_frequency(processor);
 	if (!*high_speed) {
@@ -442,8 +442,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 		set_state(SPEEDSTEP_LOW);
 
 	if (transition_latency) {
-		*transition_latency = (tv2.tv_sec - tv1.tv_sec) * USEC_PER_SEC +
-			tv2.tv_usec - tv1.tv_usec;
+		*transition_latency = ktime_to_us(ktime_sub(tv2, tv1));
 		pr_debug("transition latency is %u uSec\n", *transition_latency);
 
 		/* convert uSec to nSec and add 20% for safety reasons */
diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c
new file mode 100644
index 000000000000..20bcceb58ccc
--- /dev/null
+++ b/drivers/cpufreq/tegra124-cpufreq.c
@@ -0,0 +1,214 @@
+/*
+ * Tegra 124 cpufreq driver
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpufreq-dt.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/regulator/consumer.h>
+#include <linux/types.h>
+
+struct tegra124_cpufreq_priv {
+	struct regulator *vdd_cpu_reg;
+	struct clk *cpu_clk;
+	struct clk *pllp_clk;
+	struct clk *pllx_clk;
+	struct clk *dfll_clk;
+	struct platform_device *cpufreq_dt_pdev;
+};
+
+static int tegra124_cpu_switch_to_dfll(struct tegra124_cpufreq_priv *priv)
+{
+	struct clk *orig_parent;
+	int ret;
+
+	ret = clk_set_rate(priv->dfll_clk, clk_get_rate(priv->cpu_clk));
+	if (ret)
+		return ret;
+
+	orig_parent = clk_get_parent(priv->cpu_clk);
+	clk_set_parent(priv->cpu_clk, priv->pllp_clk);
+
+	ret = clk_prepare_enable(priv->dfll_clk);
+	if (ret)
+		goto out;
+
+	clk_set_parent(priv->cpu_clk, priv->dfll_clk);
+
+	return 0;
+
+out:
+	clk_set_parent(priv->cpu_clk, orig_parent);
+
+	return ret;
+}
+
+static void tegra124_cpu_switch_to_pllx(struct tegra124_cpufreq_priv *priv)
+{
+	clk_set_parent(priv->cpu_clk, priv->pllp_clk);
+	clk_disable_unprepare(priv->dfll_clk);
+	regulator_sync_voltage(priv->vdd_cpu_reg);
+	clk_set_parent(priv->cpu_clk, priv->pllx_clk);
+}
+
+static struct cpufreq_dt_platform_data cpufreq_dt_pd = {
+	.independent_clocks = false,
+};
+
+static int tegra124_cpufreq_probe(struct platform_device *pdev)
+{
+	struct tegra124_cpufreq_priv *priv;
+	struct device_node *np;
+	struct device *cpu_dev;
+	struct platform_device_info cpufreq_dt_devinfo = {};
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev)
+		return -ENODEV;
+
+	np = of_cpu_device_node_get(0);
+	if (!np)
+		return -ENODEV;
+
+	priv->vdd_cpu_reg = regulator_get(cpu_dev, "vdd-cpu");
+	if (IS_ERR(priv->vdd_cpu_reg)) {
+		ret = PTR_ERR(priv->vdd_cpu_reg);
+		goto out_put_np;
+	}
+
+	priv->cpu_clk = of_clk_get_by_name(np, "cpu_g");
+	if (IS_ERR(priv->cpu_clk)) {
+		ret = PTR_ERR(priv->cpu_clk);
+		goto out_put_vdd_cpu_reg;
+	}
+
+	priv->dfll_clk = of_clk_get_by_name(np, "dfll");
+	if (IS_ERR(priv->dfll_clk)) {
+		ret = PTR_ERR(priv->dfll_clk);
+		goto out_put_cpu_clk;
+	}
+
+	priv->pllx_clk = of_clk_get_by_name(np, "pll_x");
+	if (IS_ERR(priv->pllx_clk)) {
+		ret = PTR_ERR(priv->pllx_clk);
+		goto out_put_dfll_clk;
+	}
+
+	priv->pllp_clk = of_clk_get_by_name(np, "pll_p");
+	if (IS_ERR(priv->pllp_clk)) {
+		ret = PTR_ERR(priv->pllp_clk);
+		goto out_put_pllx_clk;
+	}
+
+	ret = tegra124_cpu_switch_to_dfll(priv);
+	if (ret)
+		goto out_put_pllp_clk;
+
+	cpufreq_dt_devinfo.name = "cpufreq-dt";
+	cpufreq_dt_devinfo.parent = &pdev->dev;
+	cpufreq_dt_devinfo.data = &cpufreq_dt_pd;
+	cpufreq_dt_devinfo.size_data = sizeof(cpufreq_dt_pd);
+
+	priv->cpufreq_dt_pdev =
+		platform_device_register_full(&cpufreq_dt_devinfo);
+	if (IS_ERR(priv->cpufreq_dt_pdev)) {
+		ret = PTR_ERR(priv->cpufreq_dt_pdev);
+		goto out_switch_to_pllx;
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+out_switch_to_pllx:
+	tegra124_cpu_switch_to_pllx(priv);
+out_put_pllp_clk:
+	clk_put(priv->pllp_clk);
+out_put_pllx_clk:
+	clk_put(priv->pllx_clk);
+out_put_dfll_clk:
+	clk_put(priv->dfll_clk);
+out_put_cpu_clk:
+	clk_put(priv->cpu_clk);
+out_put_vdd_cpu_reg:
+	regulator_put(priv->vdd_cpu_reg);
+out_put_np:
+	of_node_put(np);
+
+	return ret;
+}
+
+static int tegra124_cpufreq_remove(struct platform_device *pdev)
+{
+	struct tegra124_cpufreq_priv *priv = platform_get_drvdata(pdev);
+
+	platform_device_unregister(priv->cpufreq_dt_pdev);
+	tegra124_cpu_switch_to_pllx(priv);
+
+	clk_put(priv->pllp_clk);
+	clk_put(priv->pllx_clk);
+	clk_put(priv->dfll_clk);
+	clk_put(priv->cpu_clk);
+	regulator_put(priv->vdd_cpu_reg);
+
+	return 0;
+}
+
+static struct platform_driver tegra124_cpufreq_platdrv = {
+	.driver.name	= "cpufreq-tegra124",
+	.probe		= tegra124_cpufreq_probe,
+	.remove		= tegra124_cpufreq_remove,
+};
+
+static int __init tegra_cpufreq_init(void)
+{
+	int ret;
+	struct platform_device *pdev;
+
+	if (!of_machine_is_compatible("nvidia,tegra124"))
+		return -ENODEV;
+
+	/*
+	 * Platform driver+device required for handling EPROBE_DEFER with
+	 * the regulator and the DFLL clock
+	 */
+	ret = platform_driver_register(&tegra124_cpufreq_platdrv);
+	if (ret)
+		return ret;
+
+	pdev = platform_device_register_simple("cpufreq-tegra124", -1, NULL, 0);
+	if (IS_ERR(pdev)) {
+		platform_driver_unregister(&tegra124_cpufreq_platdrv);
+		return PTR_ERR(pdev);
+	}
+
+	return 0;
+}
+module_init(tegra_cpufreq_init);
+
+MODULE_AUTHOR("Tuomas Tynkkynen <ttynkkynen@nvidia.com>");
+MODULE_DESCRIPTION("cpufreq driver for NVIDIA Tegra124");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra20-cpufreq.c
index 8084c7f7e206..8084c7f7e206 100644
--- a/drivers/cpufreq/tegra-cpufreq.c
+++ b/drivers/cpufreq/tegra20-cpufreq.c
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 7936dce4b878..1523e2d745eb 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -176,14 +176,12 @@ void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a)
 
 /**
  * cpuidle_state_is_coupled - check if a state is part of a coupled set
- * @dev: struct cpuidle_device for the current cpu
  * @drv: struct cpuidle_driver for the platform
  * @state: index of the target state in drv->states
  *
  * Returns true if the target state is coupled with cpus besides this one
  */
-bool cpuidle_state_is_coupled(struct cpuidle_device *dev,
-	struct cpuidle_driver *drv, int state)
+bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state)
 {
 	return drv->states[state].flags & CPUIDLE_FLAG_COUPLED;
 }
@@ -473,7 +471,7 @@ int cpuidle_enter_state_coupled(struct cpuidle_device *dev,
 			return entered_state;
 		}
 		entered_state = cpuidle_enter_state(dev, drv,
-			dev->safe_state_index);
+			drv->safe_state_index);
 		local_irq_disable();
 	}
 
@@ -521,7 +519,7 @@ retry:
 		}
 
 		entered_state = cpuidle_enter_state(dev, drv,
-			dev->safe_state_index);
+			drv->safe_state_index);
 		local_irq_disable();
 	}
 
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index c13feec89ea1..ea9728fde9b3 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -25,16 +25,21 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/platform_device.h>
+#include <linux/psci.h>
+
 #include <asm/cpuidle.h>
 #include <asm/suspend.h>
-#include <asm/psci.h>
+
+#include <uapi/linux/psci.h>
+
+#define CALXEDA_IDLE_PARAM \
+	((0 << PSCI_0_2_POWER_STATE_ID_SHIFT) | \
+	 (0 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) | \
+	 (PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT))
 
 static int calxeda_idle_finish(unsigned long val)
 {
-	const struct psci_power_state ps = {
-		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
-	};
-	return psci_ops.cpu_suspend(ps, __pa(cpu_resume));
+	return psci_ops.cpu_suspend(CALXEDA_IDLE_PARAM, __pa(cpu_resume));
 }
 
 static int calxeda_pwrdown_idle(struct cpuidle_device *dev,
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index e8e2775c3821..17a6dc0e2111 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -112,20 +112,27 @@ int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 static void enter_freeze_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {
-	tick_freeze();
+	/*
+	 * trace_suspend_resume() called by tick_freeze() for the last CPU
+	 * executing it contains RCU usage regarded as invalid in the idle
+	 * context, so tell RCU about that.
+	 */
+	RCU_NONIDLE(tick_freeze());
 	/*
 	 * The state used here cannot be a "coupled" one, because the "coupled"
 	 * cpuidle mechanism enables interrupts and doing that with timekeeping
 	 * suspended is generally unsafe.
 	 */
+	stop_critical_timings();
 	drv->states[index].enter_freeze(dev, drv, index);
 	WARN_ON(!irqs_disabled());
 	/*
 	 * timekeeping_resume() that will be called by tick_unfreeze() for the
-	 * last CPU executing it calls functions containing RCU read-side
+	 * first CPU executing it calls functions containing RCU read-side
 	 * critical sections, so tell RCU about that.
 	 */
 	RCU_NONIDLE(tick_unfreeze());
+	start_critical_timings();
 }
 
 /**
@@ -190,7 +197,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	trace_cpu_idle_rcuidle(index, dev->cpu);
 	time_start = ktime_get();
 
+	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
+	start_critical_timings();
 
 	time_end = ktime_get();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
@@ -205,7 +214,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		tick_broadcast_exit();
 	}
 
-	if (!cpuidle_state_is_coupled(dev, drv, entered_state))
+	if (!cpuidle_state_is_coupled(drv, entered_state))
 		local_irq_enable();
 
 	diff = ktime_to_us(ktime_sub(time_end, time_start));
@@ -254,7 +263,7 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		  int index)
 {
-	if (cpuidle_state_is_coupled(dev, drv, index))
+	if (cpuidle_state_is_coupled(drv, index))
 		return cpuidle_enter_state_coupled(dev, drv, index);
 	return cpuidle_enter_state(dev, drv, index);
 }
diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h
index ee97e9672ecf..178c5ad3d568 100644
--- a/drivers/cpuidle/cpuidle.h
+++ b/drivers/cpuidle/cpuidle.h
@@ -34,15 +34,14 @@ extern int cpuidle_add_sysfs(struct cpuidle_device *dev);
 extern void cpuidle_remove_sysfs(struct cpuidle_device *dev);
 
 #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
-bool cpuidle_state_is_coupled(struct cpuidle_device *dev,
-		struct cpuidle_driver *drv, int state);
+bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state);
 int cpuidle_enter_state_coupled(struct cpuidle_device *dev,
 		struct cpuidle_driver *drv, int next_state);
 int cpuidle_coupled_register_device(struct cpuidle_device *dev);
 void cpuidle_coupled_unregister_device(struct cpuidle_device *dev);
 #else
-static inline bool cpuidle_state_is_coupled(struct cpuidle_device *dev,
-		struct cpuidle_driver *drv, int state)
+static inline
+bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state)
 {
 	return false;
 }
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 4044125fb5d5..07bc7aa6b224 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -480,4 +480,21 @@ config CRYPTO_DEV_IMGTEC_HASH
 	  hardware hash accelerator. Supporting MD5/SHA1/SHA224/SHA256
 	  hashing algorithms.
 
+config CRYPTO_DEV_SUN4I_SS
+	tristate "Support for Allwinner Security System cryptographic accelerator"
+	depends on ARCH_SUNXI
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	select CRYPTO_AES
+	select CRYPTO_DES
+	select CRYPTO_BLKCIPHER
+	help
+	  Some Allwinner SoC have a crypto accelerator named
+	  Security System. Select this if you want to use it.
+	  The Security System handle AES/DES/3DES ciphers in CBC mode
+	  and SHA1 and MD5 hash algorithms.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sun4i-ss.
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index e35c07a8da85..c3ced6fbd1b8 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -28,3 +28,4 @@ obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
 obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
 obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
+obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sunxi-ss/
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 3b28e8c3de28..192a8fa325c1 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -1113,7 +1113,7 @@ static irqreturn_t crypto4xx_ce_interrupt_handler(int irq, void *data)
 	struct device *dev = (struct device *)data;
 	struct crypto4xx_core_device *core_dev = dev_get_drvdata(dev);
 
-	if (core_dev->dev->ce_base == 0)
+	if (!core_dev->dev->ce_base)
 		return 0;
 
 	writel(PPC4XX_INTERRUPT_CLR,
diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c
index d9af9403ab6c..2f0b3337505d 100644
--- a/drivers/crypto/bfin_crc.c
+++ b/drivers/crypto/bfin_crc.c
@@ -370,8 +370,7 @@ static int bfin_crypto_crc_handle_queue(struct bfin_crypto_crc *crc,
 			sg_init_table(ctx->bufsl, nsg);
 			sg_set_buf(ctx->bufsl, ctx->buflast, ctx->buflast_len);
 			if (nsg > 1)
-				scatterwalk_sg_chain(ctx->bufsl, nsg,
-						req->src);
+				sg_chain(ctx->bufsl, nsg, req->src);
 			ctx->sg = ctx->bufsl;
 		} else
 			ctx->sg = req->src;
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index e286e285aa8a..5652a53415dc 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -1,6 +1,6 @@
 config CRYPTO_DEV_FSL_CAAM
 	tristate "Freescale CAAM-Multicore driver backend"
-	depends on FSL_SOC
+	depends on FSL_SOC || ARCH_MXC
 	help
 	  Enables the driver module for Freescale's Cryptographic Accelerator
 	  and Assurance Module (CAAM), also known as the SEC version 4 (SEC4).
@@ -112,6 +112,14 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API
 	  To compile this as a module, choose M here: the module
 	  will be called caamrng.
 
+config CRYPTO_DEV_FSL_CAAM_IMX
+	def_bool SOC_IMX6 || SOC_IMX7D
+	depends on CRYPTO_DEV_FSL_CAAM
+
+config CRYPTO_DEV_FSL_CAAM_LE
+	def_bool CRYPTO_DEV_FSL_CAAM_IMX || SOC_LS1021A
+	depends on CRYPTO_DEV_FSL_CAAM
+
 config CRYPTO_DEV_FSL_CAAM_DEBUG
 	bool "Enable debug output in CAAM driver"
 	depends on CRYPTO_DEV_FSL_CAAM
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index daca933a82ec..ba79d638f782 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -68,27 +68,29 @@
 #define AEAD_DESC_JOB_IO_LEN		(DESC_JOB_IO_LEN + CAAM_CMD_SZ * 2)
 #define GCM_DESC_JOB_IO_LEN		(AEAD_DESC_JOB_IO_LEN + \
 					 CAAM_CMD_SZ * 4)
+#define AUTHENC_DESC_JOB_IO_LEN		(AEAD_DESC_JOB_IO_LEN + \
+					 CAAM_CMD_SZ * 5)
 
 /* length of descriptors text */
 #define DESC_AEAD_BASE			(4 * CAAM_CMD_SZ)
-#define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
-#define DESC_AEAD_DEC_LEN		(DESC_AEAD_BASE + 18 * CAAM_CMD_SZ)
-#define DESC_AEAD_GIVENC_LEN		(DESC_AEAD_ENC_LEN + 7 * CAAM_CMD_SZ)
+#define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 11 * CAAM_CMD_SZ)
+#define DESC_AEAD_DEC_LEN		(DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
+#define DESC_AEAD_GIVENC_LEN		(DESC_AEAD_ENC_LEN + 9 * CAAM_CMD_SZ)
 
 /* Note: Nonce is counted in enckeylen */
-#define DESC_AEAD_CTR_RFC3686_LEN	(6 * CAAM_CMD_SZ)
+#define DESC_AEAD_CTR_RFC3686_LEN	(4 * CAAM_CMD_SZ)
 
 #define DESC_AEAD_NULL_BASE		(3 * CAAM_CMD_SZ)
-#define DESC_AEAD_NULL_ENC_LEN		(DESC_AEAD_NULL_BASE + 14 * CAAM_CMD_SZ)
-#define DESC_AEAD_NULL_DEC_LEN		(DESC_AEAD_NULL_BASE + 17 * CAAM_CMD_SZ)
+#define DESC_AEAD_NULL_ENC_LEN		(DESC_AEAD_NULL_BASE + 11 * CAAM_CMD_SZ)
+#define DESC_AEAD_NULL_DEC_LEN		(DESC_AEAD_NULL_BASE + 13 * CAAM_CMD_SZ)
 
 #define DESC_GCM_BASE			(3 * CAAM_CMD_SZ)
 #define DESC_GCM_ENC_LEN		(DESC_GCM_BASE + 16 * CAAM_CMD_SZ)
 #define DESC_GCM_DEC_LEN		(DESC_GCM_BASE + 12 * CAAM_CMD_SZ)
 
 #define DESC_RFC4106_BASE		(3 * CAAM_CMD_SZ)
-#define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 10 * CAAM_CMD_SZ)
-#define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 10 * CAAM_CMD_SZ)
+#define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 13 * CAAM_CMD_SZ)
+#define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 13 * CAAM_CMD_SZ)
 
 #define DESC_RFC4543_BASE		(3 * CAAM_CMD_SZ)
 #define DESC_RFC4543_ENC_LEN		(DESC_RFC4543_BASE + 11 * CAAM_CMD_SZ)
@@ -111,6 +113,20 @@
 #endif
 static struct list_head alg_list;
 
+struct caam_alg_entry {
+	int class1_alg_type;
+	int class2_alg_type;
+	int alg_op;
+	bool rfc3686;
+	bool geniv;
+};
+
+struct caam_aead_alg {
+	struct aead_alg aead;
+	struct caam_alg_entry caam;
+	bool registered;
+};
+
 /* Set DK bit in class 1 operation if shared */
 static inline void append_dec_op1(u32 *desc, u32 type)
 {
@@ -145,18 +161,6 @@ static inline void aead_append_src_dst(u32 *desc, u32 msg_type)
 }
 
 /*
- * For aead encrypt and decrypt, read iv for both classes
- */
-static inline void aead_append_ld_iv(u32 *desc, int ivsize, int ivoffset)
-{
-	append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
-			LDST_SRCDST_BYTE_CONTEXT |
-			(ivoffset << LDST_OFFSET_SHIFT));
-	append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_CLASS2INFIFO |
-		    (ivoffset << MOVE_OFFSET_SHIFT) | ivsize);
-}
-
-/*
  * For ablkcipher encrypt and decrypt, read from req->src and
  * write to req->dst
  */
@@ -170,13 +174,6 @@ static inline void ablkcipher_append_src_dst(u32 *desc)
 }
 
 /*
- * If all data, including src (with assoc and iv) or dst (with iv only) are
- * contiguous
- */
-#define GIV_SRC_CONTIG		1
-#define GIV_DST_CONTIG		(1 << 1)
-
-/*
  * per-session context
  */
 struct caam_ctx {
@@ -259,7 +256,6 @@ static void init_sh_desc_key_aead(u32 *desc, struct caam_ctx *ctx,
 
 static int aead_null_set_sh_desc(struct crypto_aead *aead)
 {
-	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
@@ -270,11 +266,11 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptors
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_AEAD_NULL_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_AEAD_NULL_ENC_LEN + AEAD_DESC_JOB_IO_LEN +
 	    ctx->split_key_pad_len <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* old_aead_encrypt shared descriptor */
+	/* aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 
 	init_sh_desc(desc, HDR_SHARE_SERIAL);
@@ -291,20 +287,10 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 			   KEY_DEST_MDHA_SPLIT | KEY_ENC);
 	set_jump_tgt_here(desc, key_jump_cmd);
 
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/*
-	 * NULL encryption; IV is zero
-	 * assoclen = (assoclen + cryptlen) - cryptlen
-	 */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* read assoc before reading payload */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
-			     KEY_VLF);
+	/* assoclen + cryptlen = seqinlen */
+	append_math_sub(desc, REG3, SEQINLEN, REG0, CAAM_CMD_SZ);
 
-	/* Prepare to read and write cryptlen bytes */
+	/* Prepare to read and write cryptlen + assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
@@ -363,7 +349,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	desc = ctx->sh_desc_dec;
 
-	/* old_aead_decrypt shared descriptor */
+	/* aead_decrypt shared descriptor */
 	init_sh_desc(desc, HDR_SHARE_SERIAL);
 
 	/* Skip if already shared */
@@ -382,18 +368,10 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class2_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* assoclen + cryptlen = seqinlen - ivsize - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + ivsize);
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
+	/* assoclen + cryptlen = seqoutlen */
 	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
 
-	/* read assoc before reading payload */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
-			     KEY_VLF);
-
-	/* Prepare to read and write cryptlen bytes */
+	/* Prepare to read and write cryptlen + assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG2, CAAM_CMD_SZ);
 
@@ -450,10 +428,10 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 static int aead_set_sh_desc(struct crypto_aead *aead)
 {
+	struct caam_aead_alg *alg = container_of(crypto_aead_alg(aead),
+						 struct caam_aead_alg, aead);
 	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	struct crypto_tfm *ctfm = crypto_aead_tfm(aead);
-	const char *alg_name = crypto_tfm_alg_name(ctfm);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline;
 	u32 geniv, moveiv;
@@ -461,11 +439,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	u32 *desc;
 	const bool ctr_mode = ((ctx->class1_alg_type & OP_ALG_AAI_MASK) ==
 			       OP_ALG_AAI_CTR_MOD128);
-	const bool is_rfc3686 = (ctr_mode &&
-				 (strstr(alg_name, "rfc3686") != NULL));
-
-	if (!ctx->authsize)
-		return 0;
+	const bool is_rfc3686 = alg->caam.rfc3686;
 
 	/* NULL encryption / decryption */
 	if (!ctx->enckeylen)
@@ -486,18 +460,21 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	if (is_rfc3686)
 		ctx1_iv_off = 16 + CTR_RFC3686_NONCE_SIZE;
 
+	if (alg->caam.geniv)
+		goto skip_enc;
+
 	/*
 	 * Job Descriptor and Shared Descriptors
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_AEAD_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_AEAD_ENC_LEN + AUTHENC_DESC_JOB_IO_LEN +
 	    ctx->split_key_pad_len + ctx->enckeylen +
 	    (is_rfc3686 ? DESC_AEAD_CTR_RFC3686_LEN : 0) <=
 	    CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* old_aead_encrypt shared descriptor */
+	/* aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 
 	/* Note: Context registers are saved. */
@@ -507,19 +484,16 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class2_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, ivsize);
+	/* Read and write assoclen bytes */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, VARSEQINLEN, REG2, REG3, CAAM_CMD_SZ);
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* read assoc before reading payload */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
-			     KEY_VLF);
-	aead_append_ld_iv(desc, ivsize, ctx1_iv_off);
+				      FIFOLDST_VLF);
 
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
@@ -534,8 +508,8 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
 	/* Read and write cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 	aead_append_src_dst(desc, FIFOLD_TYPE_MSG1OUT2);
 
 	/* Write ICV */
@@ -555,18 +529,19 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
+skip_enc:
 	/*
 	 * Job Descriptor and Shared Descriptors
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_AEAD_DEC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_AEAD_DEC_LEN + AUTHENC_DESC_JOB_IO_LEN +
 	    ctx->split_key_pad_len + ctx->enckeylen +
 	    (is_rfc3686 ? DESC_AEAD_CTR_RFC3686_LEN : 0) <=
 	    CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* old_aead_decrypt shared descriptor */
+	/* aead_decrypt shared descriptor */
 	desc = ctx->sh_desc_dec;
 
 	/* Note: Context registers are saved. */
@@ -576,19 +551,17 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class2_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* assoclen + cryptlen = seqinlen - ivsize - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + ivsize);
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
+	/* Read and write assoclen bytes */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* read assoc before reading payload */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
 
-	aead_append_ld_iv(desc, ivsize, ctx1_iv_off);
-
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
 		append_load_imm_u32(desc, be32_to_cpu(1), LDST_IMM |
@@ -605,8 +578,8 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		append_dec_op1(desc, ctx->class1_alg_type);
 
 	/* Read and write cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG2, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 	aead_append_src_dst(desc, FIFOLD_TYPE_MSG);
 
 	/* Load ICV */
@@ -626,12 +599,15 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
+	if (!alg->caam.geniv)
+		goto skip_givenc;
+
 	/*
 	 * Job Descriptor and Shared Descriptors
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_AEAD_GIVENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_AEAD_GIVENC_LEN + AUTHENC_DESC_JOB_IO_LEN +
 	    ctx->split_key_pad_len + ctx->enckeylen +
 	    (is_rfc3686 ? DESC_AEAD_CTR_RFC3686_LEN : 0) <=
 	    CAAM_DESC_BYTES_MAX)
@@ -643,6 +619,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* Note: Context registers are saved. */
 	init_sh_desc_key_aead(desc, ctx, keys_fit_inline, is_rfc3686);
 
+	if (is_rfc3686)
+		goto copy_iv;
+
 	/* Generate IV */
 	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
 		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
@@ -656,6 +635,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		    (ivsize << MOVE_LEN_SHIFT));
 	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
 
+copy_iv:
 	/* Copy IV to class 1 context */
 	append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_OUTFIFO |
 		    (ctx1_iv_off << MOVE_OFFSET_SHIFT) |
@@ -668,8 +648,12 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* ivsize + cryptlen = seqoutlen - authsize */
 	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
 
-	/* assoclen = seqinlen - (ivsize + cryptlen) */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
+	/* Read and write assoclen bytes */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* read assoc before reading payload */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
@@ -710,9 +694,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_seq_store(desc, ctx->authsize, LDST_CLASS_2_CCB |
 			 LDST_SRCDST_BYTE_CONTEXT);
 
-	ctx->sh_desc_givenc_dma = dma_map_single(jrdev, desc,
-						 desc_bytes(desc),
-						 DMA_TO_DEVICE);
+	ctx->sh_desc_enc_dma = dma_map_single(jrdev, desc,
+					      desc_bytes(desc),
+					      DMA_TO_DEVICE);
 	if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
 		dev_err(jrdev, "unable to map shared descriptor\n");
 		return -ENOMEM;
@@ -723,6 +707,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
+skip_givenc:
 	return 0;
 }
 
@@ -976,22 +961,28 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_sub_imm_u32(desc, VARSEQINLEN, REG3, IMM, 8);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* Skip assoc data */
-	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
-
 	/* Read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
-	/* cryptlen = seqoutlen - assoclen */
-	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+	/* Skip IV */
+	append_seq_fifo_load(desc, 8, FIFOLD_CLASS_SKIP);
 
 	/* Will read cryptlen bytes */
 	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
+	/* Workaround for erratum A-005473 (simultaneous SEQ FIFO skips) */
+	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_MSG);
+
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
+
+	/* cryptlen = seqoutlen - assoclen */
+	append_math_sub(desc, VARSEQOUTLEN, VARSEQINLEN, REG0, CAAM_CMD_SZ);
+
 	/* Write encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
 
@@ -1044,21 +1035,27 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_sub_imm_u32(desc, VARSEQINLEN, REG3, IMM, 8);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* Skip assoc data */
-	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
-
 	/* Read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
-	/* Will write cryptlen bytes */
-	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+	/* Skip IV */
+	append_seq_fifo_load(desc, 8, FIFOLD_CLASS_SKIP);
 
 	/* Will read cryptlen bytes */
-	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG3, CAAM_CMD_SZ);
+
+	/* Workaround for erratum A-005473 (simultaneous SEQ FIFO skips) */
+	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_MSG);
+
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
+
+	/* Will write cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* Store payload data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -1793,22 +1790,6 @@ static void aead_unmap(struct device *dev,
 		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
-static void old_aead_unmap(struct device *dev,
-			   struct aead_edesc *edesc,
-			   struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	int ivsize = crypto_aead_ivsize(aead);
-
-	dma_unmap_sg_chained(dev, req->assoc, edesc->assoc_nents,
-			     DMA_TO_DEVICE, edesc->assoc_chained);
-
-	caam_unmap(dev, req->src, req->dst,
-		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
-		   edesc->dst_chained, edesc->iv_dma, ivsize,
-		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
-}
-
 static void ablkcipher_unmap(struct device *dev,
 			     struct ablkcipher_edesc *edesc,
 			     struct ablkcipher_request *req)
@@ -1844,45 +1825,6 @@ static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	aead_request_complete(req, err);
 }
 
-static void old_aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
-				  void *context)
-{
-	struct aead_request *req = context;
-	struct aead_edesc *edesc;
-#ifdef DEBUG
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	int ivsize = crypto_aead_ivsize(aead);
-
-	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
-#endif
-
-	edesc = (struct aead_edesc *)((char *)desc -
-		 offsetof(struct aead_edesc, hw_desc));
-
-	if (err)
-		caam_jr_strstatus(jrdev, err);
-
-	old_aead_unmap(jrdev, edesc, req);
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->assoc),
-		       req->assoclen , 1);
-	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src) - ivsize,
-		       edesc->src_nents ? 100 : ivsize, 1);
-	print_hex_dump(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
-		       edesc->src_nents ? 100 : req->cryptlen +
-		       ctx->authsize + 4, 1);
-#endif
-
-	kfree(edesc);
-
-	aead_request_complete(req, err);
-}
-
 static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 				   void *context)
 {
@@ -1911,62 +1853,6 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	aead_request_complete(req, err);
 }
 
-static void old_aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
-				  void *context)
-{
-	struct aead_request *req = context;
-	struct aead_edesc *edesc;
-#ifdef DEBUG
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	int ivsize = crypto_aead_ivsize(aead);
-
-	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
-#endif
-
-	edesc = (struct aead_edesc *)((char *)desc -
-		 offsetof(struct aead_edesc, hw_desc));
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, req->iv,
-		       ivsize, 1);
-	print_hex_dump(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->dst),
-		       req->cryptlen - ctx->authsize, 1);
-#endif
-
-	if (err)
-		caam_jr_strstatus(jrdev, err);
-
-	old_aead_unmap(jrdev, edesc, req);
-
-	/*
-	 * verify hw auth check passed else return -EBADMSG
-	 */
-	if ((err & JRSTA_CCBERR_ERRID_MASK) == JRSTA_CCBERR_ERRID_ICVCHK)
-		err = -EBADMSG;
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "iphdrout@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       ((char *)sg_virt(req->assoc) - sizeof(struct iphdr)),
-		       sizeof(struct iphdr) + req->assoclen +
-		       ((req->cryptlen > 1500) ? 1500 : req->cryptlen) +
-		       ctx->authsize + 36, 1);
-	if (!err && edesc->sec4_sg_bytes) {
-		struct scatterlist *sg = sg_last(req->src, edesc->src_nents);
-		print_hex_dump(KERN_ERR, "sglastout@"__stringify(__LINE__)": ",
-			       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(sg),
-			sg->length + ctx->authsize + 16, 1);
-	}
-#endif
-
-	kfree(edesc);
-
-	aead_request_complete(req, err);
-}
-
 static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 				   void *context)
 {
@@ -2035,91 +1921,6 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 /*
  * Fill in aead job descriptor
  */
-static void old_init_aead_job(u32 *sh_desc, dma_addr_t ptr,
-			      struct aead_edesc *edesc,
-			      struct aead_request *req,
-			      bool all_contig, bool encrypt)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	int ivsize = crypto_aead_ivsize(aead);
-	int authsize = ctx->authsize;
-	u32 *desc = edesc->hw_desc;
-	u32 out_options = 0, in_options;
-	dma_addr_t dst_dma, src_dma;
-	int len, sec4_sg_index = 0;
-	bool is_gcm = false;
-
-#ifdef DEBUG
-	debug("assoclen %d cryptlen %d authsize %d\n",
-	      req->assoclen, req->cryptlen, authsize);
-	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->assoc),
-		       req->assoclen , 1);
-	print_hex_dump(KERN_ERR, "presciv@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, req->iv,
-		       edesc->src_nents ? 100 : ivsize, 1);
-	print_hex_dump(KERN_ERR, "src    @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
-			edesc->src_nents ? 100 : req->cryptlen, 1);
-	print_hex_dump(KERN_ERR, "shrdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sh_desc,
-		       desc_bytes(sh_desc), 1);
-#endif
-
-	if (((ctx->class1_alg_type & OP_ALG_ALGSEL_MASK) ==
-	      OP_ALG_ALGSEL_AES) &&
-	    ((ctx->class1_alg_type & OP_ALG_AAI_MASK) == OP_ALG_AAI_GCM))
-		is_gcm = true;
-
-	len = desc_len(sh_desc);
-	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
-
-	if (all_contig) {
-		if (is_gcm)
-			src_dma = edesc->iv_dma;
-		else
-			src_dma = sg_dma_address(req->assoc);
-		in_options = 0;
-	} else {
-		src_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += (edesc->assoc_nents ? : 1) + 1 +
-				 (edesc->src_nents ? : 1);
-		in_options = LDST_SGF;
-	}
-
-	append_seq_in_ptr(desc, src_dma, req->assoclen + ivsize + req->cryptlen,
-			  in_options);
-
-	if (likely(req->src == req->dst)) {
-		if (all_contig) {
-			dst_dma = sg_dma_address(req->src);
-		} else {
-			dst_dma = src_dma + sizeof(struct sec4_sg_entry) *
-				  ((edesc->assoc_nents ? : 1) + 1);
-			out_options = LDST_SGF;
-		}
-	} else {
-		if (!edesc->dst_nents) {
-			dst_dma = sg_dma_address(req->dst);
-		} else {
-			dst_dma = edesc->sec4_sg_dma +
-				  sec4_sg_index *
-				  sizeof(struct sec4_sg_entry);
-			out_options = LDST_SGF;
-		}
-	}
-	if (encrypt)
-		append_seq_out_ptr(desc, dst_dma, req->cryptlen + authsize,
-				   out_options);
-	else
-		append_seq_out_ptr(desc, dst_dma, req->cryptlen - authsize,
-				   out_options);
-}
-
-/*
- * Fill in aead job descriptor
- */
 static void init_aead_job(struct aead_request *req,
 			  struct aead_edesc *edesc,
 			  bool all_contig, bool encrypt)
@@ -2208,80 +2009,43 @@ static void init_gcm_job(struct aead_request *req,
 	/* End of blank commands */
 }
 
-/*
- * Fill in aead givencrypt job descriptor
- */
-static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
-			      struct aead_edesc *edesc,
-			      struct aead_request *req,
-			      int contig)
+static void init_authenc_job(struct aead_request *req,
+			     struct aead_edesc *edesc,
+			     bool all_contig, bool encrypt)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_aead_alg *alg = container_of(crypto_aead_alg(aead),
+						 struct caam_aead_alg, aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	int ivsize = crypto_aead_ivsize(aead);
-	int authsize = ctx->authsize;
+	const bool ctr_mode = ((ctx->class1_alg_type & OP_ALG_AAI_MASK) ==
+			       OP_ALG_AAI_CTR_MOD128);
+	const bool is_rfc3686 = alg->caam.rfc3686;
 	u32 *desc = edesc->hw_desc;
-	u32 out_options = 0, in_options;
-	dma_addr_t dst_dma, src_dma;
-	int len, sec4_sg_index = 0;
-	bool is_gcm = false;
-
-#ifdef DEBUG
-	debug("assoclen %d cryptlen %d authsize %d\n",
-	      req->assoclen, req->cryptlen, authsize);
-	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->assoc),
-		       req->assoclen , 1);
-	print_hex_dump(KERN_ERR, "presciv@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, req->iv, ivsize, 1);
-	print_hex_dump(KERN_ERR, "src    @"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
-			edesc->src_nents > 1 ? 100 : req->cryptlen, 1);
-	print_hex_dump(KERN_ERR, "shrdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sh_desc,
-		       desc_bytes(sh_desc), 1);
-#endif
+	u32 ivoffset = 0;
 
-	if (((ctx->class1_alg_type & OP_ALG_ALGSEL_MASK) ==
-	      OP_ALG_ALGSEL_AES) &&
-	    ((ctx->class1_alg_type & OP_ALG_AAI_MASK) == OP_ALG_AAI_GCM))
-		is_gcm = true;
-
-	len = desc_len(sh_desc);
-	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
+	/*
+	 * AES-CTR needs to load IV in CONTEXT1 reg
+	 * at an offset of 128bits (16bytes)
+	 * CONTEXT1[255:128] = IV
+	 */
+	if (ctr_mode)
+		ivoffset = 16;
 
-	if (contig & GIV_SRC_CONTIG) {
-		if (is_gcm)
-			src_dma = edesc->iv_dma;
-		else
-			src_dma = sg_dma_address(req->assoc);
-		in_options = 0;
-	} else {
-		src_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += edesc->assoc_nents + 1 + edesc->src_nents;
-		in_options = LDST_SGF;
-	}
-	append_seq_in_ptr(desc, src_dma, req->assoclen + ivsize + req->cryptlen,
-			  in_options);
+	/*
+	 * RFC3686 specific:
+	 *	CONTEXT1[255:128] = {NONCE, IV, COUNTER}
+	 */
+	if (is_rfc3686)
+		ivoffset = 16 + CTR_RFC3686_NONCE_SIZE;
 
-	if (contig & GIV_DST_CONTIG) {
-		dst_dma = edesc->iv_dma;
-	} else {
-		if (likely(req->src == req->dst)) {
-			dst_dma = src_dma + sizeof(struct sec4_sg_entry) *
-				  (edesc->assoc_nents +
-				   (is_gcm ? 1 + edesc->src_nents : 0));
-			out_options = LDST_SGF;
-		} else {
-			dst_dma = edesc->sec4_sg_dma +
-				  sec4_sg_index *
-				  sizeof(struct sec4_sg_entry);
-			out_options = LDST_SGF;
-		}
-	}
+	init_aead_job(req, edesc, all_contig, encrypt);
 
-	append_seq_out_ptr(desc, dst_dma, ivsize + req->cryptlen + authsize,
-			   out_options);
+	if (ivsize && (is_rfc3686 || !(alg->caam.geniv && encrypt)))
+		append_load_as_imm(desc, req->iv, ivsize,
+				   LDST_CLASS_1_CCB |
+				   LDST_SRCDST_BYTE_CONTEXT |
+				   (ivoffset << LDST_OFFSET_SHIFT));
 }
 
 /*
@@ -2392,150 +2156,6 @@ static void init_ablkcipher_giv_job(u32 *sh_desc, dma_addr_t ptr,
 /*
  * allocate and map the aead extended descriptor
  */
-static struct aead_edesc *old_aead_edesc_alloc(struct aead_request *req,
-					       int desc_bytes,
-					       bool *all_contig_ptr,
-					       bool encrypt)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	struct device *jrdev = ctx->jrdev;
-	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
-		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
-	int assoc_nents, src_nents, dst_nents = 0;
-	struct aead_edesc *edesc;
-	dma_addr_t iv_dma = 0;
-	int sgc;
-	bool all_contig = true;
-	bool assoc_chained = false, src_chained = false, dst_chained = false;
-	int ivsize = crypto_aead_ivsize(aead);
-	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
-	unsigned int authsize = ctx->authsize;
-	bool is_gcm = false;
-
-	assoc_nents = sg_count(req->assoc, req->assoclen, &assoc_chained);
-
-	if (unlikely(req->dst != req->src)) {
-		src_nents = sg_count(req->src, req->cryptlen, &src_chained);
-		dst_nents = sg_count(req->dst,
-				     req->cryptlen +
-					(encrypt ? authsize : (-authsize)),
-				     &dst_chained);
-	} else {
-		src_nents = sg_count(req->src,
-				     req->cryptlen +
-					(encrypt ? authsize : 0),
-				     &src_chained);
-	}
-
-	sgc = dma_map_sg_chained(jrdev, req->assoc, assoc_nents ? : 1,
-				 DMA_TO_DEVICE, assoc_chained);
-	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
-					 DMA_BIDIRECTIONAL, src_chained);
-	} else {
-		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
-					 DMA_TO_DEVICE, src_chained);
-		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
-					 DMA_FROM_DEVICE, dst_chained);
-	}
-
-	iv_dma = dma_map_single(jrdev, req->iv, ivsize, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, iv_dma)) {
-		dev_err(jrdev, "unable to map IV\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (((ctx->class1_alg_type & OP_ALG_ALGSEL_MASK) ==
-	      OP_ALG_ALGSEL_AES) &&
-	    ((ctx->class1_alg_type & OP_ALG_AAI_MASK) == OP_ALG_AAI_GCM))
-		is_gcm = true;
-
-	/*
-	 * Check if data are contiguous.
-	 * GCM expected input sequence: IV, AAD, text
-	 * All other - expected input sequence: AAD, IV, text
-	 */
-	if (is_gcm)
-		all_contig = (!assoc_nents &&
-			      iv_dma + ivsize == sg_dma_address(req->assoc) &&
-			      !src_nents && sg_dma_address(req->assoc) +
-			      req->assoclen == sg_dma_address(req->src));
-	else
-		all_contig = (!assoc_nents && sg_dma_address(req->assoc) +
-			      req->assoclen == iv_dma && !src_nents &&
-			      iv_dma + ivsize == sg_dma_address(req->src));
-	if (!all_contig) {
-		assoc_nents = assoc_nents ? : 1;
-		src_nents = src_nents ? : 1;
-		sec4_sg_len = assoc_nents + 1 + src_nents;
-	}
-
-	sec4_sg_len += dst_nents;
-
-	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
-
-	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct aead_edesc) + desc_bytes +
-			sec4_sg_bytes, GFP_DMA | flags);
-	if (!edesc) {
-		dev_err(jrdev, "could not allocate extended descriptor\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	edesc->assoc_nents = assoc_nents;
-	edesc->assoc_chained = assoc_chained;
-	edesc->src_nents = src_nents;
-	edesc->src_chained = src_chained;
-	edesc->dst_nents = dst_nents;
-	edesc->dst_chained = dst_chained;
-	edesc->iv_dma = iv_dma;
-	edesc->sec4_sg_bytes = sec4_sg_bytes;
-	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
-			 desc_bytes;
-	*all_contig_ptr = all_contig;
-
-	sec4_sg_index = 0;
-	if (!all_contig) {
-		if (!is_gcm) {
-			sg_to_sec4_sg_len(req->assoc, req->assoclen,
-					  edesc->sec4_sg + sec4_sg_index);
-			sec4_sg_index += assoc_nents;
-		}
-
-		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
-				   iv_dma, ivsize, 0);
-		sec4_sg_index += 1;
-
-		if (is_gcm) {
-			sg_to_sec4_sg_len(req->assoc, req->assoclen,
-					  edesc->sec4_sg + sec4_sg_index);
-			sec4_sg_index += assoc_nents;
-		}
-
-		sg_to_sec4_sg_last(req->src,
-				   src_nents,
-				   edesc->sec4_sg +
-				   sec4_sg_index, 0);
-		sec4_sg_index += src_nents;
-	}
-	if (dst_nents) {
-		sg_to_sec4_sg_last(req->dst, dst_nents,
-				   edesc->sec4_sg + sec4_sg_index, 0);
-	}
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
-		dev_err(jrdev, "unable to map S/G table\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return edesc;
-}
-
-/*
- * allocate and map the aead extended descriptor
- */
 static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 					   int desc_bytes, bool *all_contig_ptr,
 					   bool encrypt)
@@ -2579,8 +2199,8 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kzalloc(sizeof(struct aead_edesc) + desc_bytes +
-			sec4_sg_bytes, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return ERR_PTR(-ENOMEM);
@@ -2685,7 +2305,15 @@ static int gcm_encrypt(struct aead_request *req)
 	return ret;
 }
 
-static int old_aead_encrypt(struct aead_request *req)
+static int ipsec_gcm_encrypt(struct aead_request *req)
+{
+	if (req->assoclen < 8)
+		return -EINVAL;
+
+	return gcm_encrypt(req);
+}
+
+static int aead_encrypt(struct aead_request *req)
 {
 	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -2696,14 +2324,13 @@ static int old_aead_encrypt(struct aead_request *req)
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = old_aead_edesc_alloc(req, DESC_JOB_IO_LEN *
-				     CAAM_CMD_SZ, &all_contig, true);
+	edesc = aead_edesc_alloc(req, AUTHENC_DESC_JOB_IO_LEN,
+				 &all_contig, true);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	/* Create and submit job descriptor */
-	old_init_aead_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req,
-			  all_contig, true);
+	init_authenc_job(req, edesc, all_contig, true);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -2711,11 +2338,11 @@ static int old_aead_encrypt(struct aead_request *req)
 #endif
 
 	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, old_aead_encrypt_done, req);
+	ret = caam_jr_enqueue(jrdev, desc, aead_encrypt_done, req);
 	if (!ret) {
 		ret = -EINPROGRESS;
 	} else {
-		old_aead_unmap(jrdev, edesc, req);
+		aead_unmap(jrdev, edesc, req);
 		kfree(edesc);
 	}
 
@@ -2757,7 +2384,15 @@ static int gcm_decrypt(struct aead_request *req)
 	return ret;
 }
 
-static int old_aead_decrypt(struct aead_request *req)
+static int ipsec_gcm_decrypt(struct aead_request *req)
+{
+	if (req->assoclen < 8)
+		return -EINVAL;
+
+	return gcm_decrypt(req);
+}
+
+static int aead_decrypt(struct aead_request *req)
 {
 	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -2768,20 +2403,19 @@ static int old_aead_decrypt(struct aead_request *req)
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = old_aead_edesc_alloc(req, DESC_JOB_IO_LEN *
-				     CAAM_CMD_SZ, &all_contig, false);
+	edesc = aead_edesc_alloc(req, AUTHENC_DESC_JOB_IO_LEN,
+				 &all_contig, false);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "dec src@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
-		       req->cryptlen, 1);
+		       req->assoclen + req->cryptlen, 1);
 #endif
 
 	/* Create and submit job descriptor*/
-	old_init_aead_job(ctx->sh_desc_dec,
-			  ctx->sh_desc_dec_dma, edesc, req, all_contig, false);
+	init_authenc_job(req, edesc, all_contig, false);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -2789,232 +2423,29 @@ static int old_aead_decrypt(struct aead_request *req)
 #endif
 
 	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, old_aead_decrypt_done, req);
+	ret = caam_jr_enqueue(jrdev, desc, aead_decrypt_done, req);
 	if (!ret) {
 		ret = -EINPROGRESS;
 	} else {
-		old_aead_unmap(jrdev, edesc, req);
+		aead_unmap(jrdev, edesc, req);
 		kfree(edesc);
 	}
 
 	return ret;
 }
 
-/*
- * allocate and map the aead extended descriptor for aead givencrypt
- */
-static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
-					       *greq, int desc_bytes,
-					       u32 *contig_ptr)
-{
-	struct aead_request *req = &greq->areq;
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	struct device *jrdev = ctx->jrdev;
-	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
-		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
-	int assoc_nents, src_nents, dst_nents = 0;
-	struct aead_edesc *edesc;
-	dma_addr_t iv_dma = 0;
-	int sgc;
-	u32 contig = GIV_SRC_CONTIG | GIV_DST_CONTIG;
-	int ivsize = crypto_aead_ivsize(aead);
-	bool assoc_chained = false, src_chained = false, dst_chained = false;
-	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
-	bool is_gcm = false;
-
-	assoc_nents = sg_count(req->assoc, req->assoclen, &assoc_chained);
-	src_nents = sg_count(req->src, req->cryptlen, &src_chained);
-
-	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->cryptlen + ctx->authsize,
-				     &dst_chained);
-
-	sgc = dma_map_sg_chained(jrdev, req->assoc, assoc_nents ? : 1,
-				 DMA_TO_DEVICE, assoc_chained);
-	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
-					 DMA_BIDIRECTIONAL, src_chained);
-	} else {
-		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
-					 DMA_TO_DEVICE, src_chained);
-		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
-					 DMA_FROM_DEVICE, dst_chained);
-	}
-
-	iv_dma = dma_map_single(jrdev, greq->giv, ivsize, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, iv_dma)) {
-		dev_err(jrdev, "unable to map IV\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (((ctx->class1_alg_type & OP_ALG_ALGSEL_MASK) ==
-	      OP_ALG_ALGSEL_AES) &&
-	    ((ctx->class1_alg_type & OP_ALG_AAI_MASK) == OP_ALG_AAI_GCM))
-		is_gcm = true;
-
-	/*
-	 * Check if data are contiguous.
-	 * GCM expected input sequence: IV, AAD, text
-	 * All other - expected input sequence: AAD, IV, text
-	 */
-
-	if (is_gcm) {
-		if (assoc_nents || iv_dma + ivsize !=
-		    sg_dma_address(req->assoc) || src_nents ||
-		    sg_dma_address(req->assoc) + req->assoclen !=
-		    sg_dma_address(req->src))
-			contig &= ~GIV_SRC_CONTIG;
-	} else {
-		if (assoc_nents ||
-		    sg_dma_address(req->assoc) + req->assoclen != iv_dma ||
-		    src_nents || iv_dma + ivsize != sg_dma_address(req->src))
-			contig &= ~GIV_SRC_CONTIG;
-	}
-
-	if (dst_nents || iv_dma + ivsize != sg_dma_address(req->dst))
-		contig &= ~GIV_DST_CONTIG;
-
-	if (!(contig & GIV_SRC_CONTIG)) {
-		assoc_nents = assoc_nents ? : 1;
-		src_nents = src_nents ? : 1;
-		sec4_sg_len += assoc_nents + 1 + src_nents;
-		if (req->src == req->dst &&
-		    (src_nents || iv_dma + ivsize != sg_dma_address(req->src)))
-			contig &= ~GIV_DST_CONTIG;
-	}
-
-	/*
-	 * Add new sg entries for GCM output sequence.
-	 * Expected output sequence: IV, encrypted text.
-	 */
-	if (is_gcm && req->src == req->dst && !(contig & GIV_DST_CONTIG))
-		sec4_sg_len += 1 + src_nents;
-
-	if (unlikely(req->src != req->dst)) {
-		dst_nents = dst_nents ? : 1;
-		sec4_sg_len += 1 + dst_nents;
-	}
-
-	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
-
-	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct aead_edesc) + desc_bytes +
-			sec4_sg_bytes, GFP_DMA | flags);
-	if (!edesc) {
-		dev_err(jrdev, "could not allocate extended descriptor\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	edesc->assoc_nents = assoc_nents;
-	edesc->assoc_chained = assoc_chained;
-	edesc->src_nents = src_nents;
-	edesc->src_chained = src_chained;
-	edesc->dst_nents = dst_nents;
-	edesc->dst_chained = dst_chained;
-	edesc->iv_dma = iv_dma;
-	edesc->sec4_sg_bytes = sec4_sg_bytes;
-	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
-			 desc_bytes;
-	*contig_ptr = contig;
-
-	sec4_sg_index = 0;
-	if (!(contig & GIV_SRC_CONTIG)) {
-		if (!is_gcm) {
-			sg_to_sec4_sg_len(req->assoc, req->assoclen,
-					  edesc->sec4_sg + sec4_sg_index);
-			sec4_sg_index += assoc_nents;
-		}
-
-		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
-				   iv_dma, ivsize, 0);
-		sec4_sg_index += 1;
-
-		if (is_gcm) {
-			sg_to_sec4_sg_len(req->assoc, req->assoclen,
-					  edesc->sec4_sg + sec4_sg_index);
-			sec4_sg_index += assoc_nents;
-		}
-
-		sg_to_sec4_sg_last(req->src, src_nents,
-				   edesc->sec4_sg +
-				   sec4_sg_index, 0);
-		sec4_sg_index += src_nents;
-	}
-
-	if (is_gcm && req->src == req->dst && !(contig & GIV_DST_CONTIG)) {
-		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
-				   iv_dma, ivsize, 0);
-		sec4_sg_index += 1;
-		sg_to_sec4_sg_last(req->src, src_nents,
-				   edesc->sec4_sg + sec4_sg_index, 0);
-	}
-
-	if (unlikely(req->src != req->dst && !(contig & GIV_DST_CONTIG))) {
-		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
-				   iv_dma, ivsize, 0);
-		sec4_sg_index += 1;
-		sg_to_sec4_sg_last(req->dst, dst_nents,
-				   edesc->sec4_sg + sec4_sg_index, 0);
-	}
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
-		dev_err(jrdev, "unable to map S/G table\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return edesc;
-}
-
-static int old_aead_givencrypt(struct aead_givcrypt_request *areq)
+static int aead_givdecrypt(struct aead_request *req)
 {
-	struct aead_request *req = &areq->areq;
-	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct caam_ctx *ctx = crypto_aead_ctx(aead);
-	struct device *jrdev = ctx->jrdev;
-	u32 contig;
-	u32 *desc;
-	int ret = 0;
-
-	/* allocate extended descriptor */
-	edesc = aead_giv_edesc_alloc(areq, DESC_JOB_IO_LEN *
-				     CAAM_CMD_SZ, &contig);
-
-	if (IS_ERR(edesc))
-		return PTR_ERR(edesc);
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "giv src@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
-		       req->cryptlen, 1);
-#endif
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 
-	/* Create and submit job descriptor*/
-	init_aead_giv_job(ctx->sh_desc_givenc,
-			  ctx->sh_desc_givenc_dma, edesc, req, contig);
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
-		       desc_bytes(edesc->hw_desc), 1);
-#endif
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, old_aead_encrypt_done, req);
-	if (!ret) {
-		ret = -EINPROGRESS;
-	} else {
-		old_aead_unmap(jrdev, edesc, req);
-		kfree(edesc);
-	}
+	req->cryptlen -= ivsize;
+	req->assoclen += ivsize;
 
-	return ret;
-}
-
-static int aead_null_givencrypt(struct aead_givcrypt_request *areq)
-{
-	return old_aead_encrypt(&areq->areq);
+	return aead_decrypt(req);
 }
 
 /*
@@ -3072,8 +2503,8 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 			sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct ablkcipher_edesc) + desc_bytes +
-			sec4_sg_bytes, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return ERR_PTR(-ENOMEM);
@@ -3251,8 +2682,8 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 			sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(*edesc) + desc_bytes +
-			sec4_sg_bytes, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return ERR_PTR(-ENOMEM);
@@ -3347,7 +2778,6 @@ struct caam_alg_template {
 	u32 type;
 	union {
 		struct ablkcipher_alg ablkcipher;
-		struct old_aead_alg aead;
 	} template_u;
 	u32 class1_alg_type;
 	u32 class2_alg_type;
@@ -3355,753 +2785,1426 @@ struct caam_alg_template {
 };
 
 static struct caam_alg_template driver_algs[] = {
+	/* ablkcipher descriptor */
+	{
+		.name = "cbc(aes)",
+		.driver_name = "cbc-aes-caam",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+	},
+	{
+		.name = "cbc(des3_ede)",
+		.driver_name = "cbc-3des-caam",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+	},
+	{
+		.name = "cbc(des)",
+		.driver_name = "cbc-des-caam",
+		.blocksize = DES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = DES_BLOCK_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+	},
+	{
+		.name = "ctr(aes)",
+		.driver_name = "ctr-aes-caam",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.geniv = "chainiv",
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
+	},
+	{
+		.name = "rfc3686(ctr(aes))",
+		.driver_name = "rfc3686-ctr-aes-caam",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = AES_MIN_KEY_SIZE +
+				       CTR_RFC3686_NONCE_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE +
+				       CTR_RFC3686_NONCE_SIZE,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
+	}
+};
+
+static struct caam_aead_alg driver_aeads[] = {
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4106(gcm(aes))",
+				.cra_driver_name = "rfc4106-gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4106_setkey,
+			.setauthsize = rfc4106_setauthsize,
+			.encrypt = ipsec_gcm_encrypt,
+			.decrypt = ipsec_gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4543(gcm(aes))",
+				.cra_driver_name = "rfc4543-gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4543_setkey,
+			.setauthsize = rfc4543_setauthsize,
+			.encrypt = ipsec_gcm_encrypt,
+			.decrypt = ipsec_gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	/* Galois Counter Mode */
+	{
+		.aead = {
+			.base = {
+				.cra_name = "gcm(aes)",
+				.cra_driver_name = "gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = gcm_setkey,
+			.setauthsize = gcm_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 12,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
 	/* single-pass ipsec_esp descriptor */
 	{
-		.name = "authenc(hmac(md5),ecb(cipher_null))",
-		.driver_name = "authenc-hmac-md5-ecb-cipher_null-caam",
-		.blocksize = NULL_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),"
+					    "ecb(cipher_null))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "ecb-cipher_null-caam",
+				.cra_blocksize = NULL_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = aead_null_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = NULL_IV_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
-			},
-		.class1_alg_type = 0,
-		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha1),ecb(cipher_null))",
-		.driver_name = "authenc-hmac-sha1-ecb-cipher_null-caam",
-		.blocksize = NULL_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "ecb(cipher_null))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "ecb-cipher_null-caam",
+				.cra_blocksize = NULL_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = aead_null_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = NULL_IV_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
-			},
-		.class1_alg_type = 0,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha224),ecb(cipher_null))",
-		.driver_name = "authenc-hmac-sha224-ecb-cipher_null-caam",
-		.blocksize = NULL_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "ecb(cipher_null))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "ecb-cipher_null-caam",
+				.cra_blocksize = NULL_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = aead_null_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = NULL_IV_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
-			},
-		.class1_alg_type = 0,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha256),ecb(cipher_null))",
-		.driver_name = "authenc-hmac-sha256-ecb-cipher_null-caam",
-		.blocksize = NULL_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "ecb(cipher_null))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "ecb-cipher_null-caam",
+				.cra_blocksize = NULL_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = aead_null_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = NULL_IV_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
-			},
-		.class1_alg_type = 0,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha384),ecb(cipher_null))",
-		.driver_name = "authenc-hmac-sha384-ecb-cipher_null-caam",
-		.blocksize = NULL_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),"
+					    "ecb(cipher_null))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "ecb-cipher_null-caam",
+				.cra_blocksize = NULL_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = aead_null_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = NULL_IV_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
-			},
-		.class1_alg_type = 0,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha512),ecb(cipher_null))",
-		.driver_name = "authenc-hmac-sha512-ecb-cipher_null-caam",
-		.blocksize = NULL_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),"
+					    "ecb(cipher_null))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "ecb-cipher_null-caam",
+				.cra_blocksize = NULL_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = aead_null_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = NULL_IV_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
-			},
-		.class1_alg_type = 0,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(md5),cbc(aes))",
-		.driver_name = "authenc-hmac-md5-cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(md5),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-hmac-md5-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha1),cbc(aes))",
-		.driver_name = "authenc-hmac-sha1-cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha1),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha1-cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha224),cbc(aes))",
-		.driver_name = "authenc-hmac-sha224-cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha224),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha224-cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha256),cbc(aes))",
-		.driver_name = "authenc-hmac-sha256-cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha256),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha256-cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha384),cbc(aes))",
-		.driver_name = "authenc-hmac-sha384-cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha384),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha384-cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
-
 	{
-		.name = "authenc(hmac(sha512),cbc(aes))",
-		.driver_name = "authenc-hmac-sha512-cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha512),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha512-cbc-aes-caam",
+				.cra_blocksize = AES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(md5),cbc(des3_ede))",
-		.driver_name = "authenc-hmac-md5-cbc-des3_ede-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(md5),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-hmac-md5-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		}
 	},
 	{
-		.name = "authenc(hmac(sha1),cbc(des3_ede))",
-		.driver_name = "authenc-hmac-sha1-cbc-des3_ede-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha1),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha1-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha224),cbc(des3_ede))",
-		.driver_name = "authenc-hmac-sha224-cbc-des3_ede-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha224),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha224-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha256),cbc(des3_ede))",
-		.driver_name = "authenc-hmac-sha256-cbc-des3_ede-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha256),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha256-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha384),cbc(des3_ede))",
-		.driver_name = "authenc-hmac-sha384-cbc-des3_ede-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha384),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha384-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha512),cbc(des3_ede))",
-		.driver_name = "authenc-hmac-sha512-cbc-des3_ede-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha512),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha512-"
+						   "cbc-des3_ede-caam",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(md5),cbc(des))",
-		.driver_name = "authenc-hmac-md5-cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(md5),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-hmac-md5-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha1),cbc(des))",
-		.driver_name = "authenc-hmac-sha1-cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha1),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha1-cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha224),cbc(des))",
-		.driver_name = "authenc-hmac-sha224-cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha224),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha224-cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha256),cbc(des))",
-		.driver_name = "authenc-hmac-sha256-cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha256),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha256-cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha384),cbc(des))",
-		.driver_name = "authenc-hmac-sha384-cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha384),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha384-cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha512),cbc(des))",
-		.driver_name = "authenc-hmac-sha512-cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+		},
 	},
 	{
-		.name = "authenc(hmac(md5),rfc3686(ctr(aes)))",
-		.driver_name = "authenc-hmac-md5-rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha512),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha512-cbc-des-caam",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
-			.ivsize = CTR_RFC3686_IV_SIZE,
-			.maxauthsize = MD5_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha1),rfc3686(ctr(aes)))",
-		.driver_name = "authenc-hmac-sha1-rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),"
+					    "rfc3686(ctr(aes)))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
-			.maxauthsize = SHA1_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha224),rfc3686(ctr(aes)))",
-		.driver_name = "authenc-hmac-sha224-rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "seqiv(authenc("
+					    "hmac(md5),rfc3686(ctr(aes))))",
+				.cra_driver_name = "seqiv-authenc-hmac-md5-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
-			.maxauthsize = SHA224_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha256),rfc3686(ctr(aes)))",
-		.driver_name = "authenc-hmac-sha256-rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "rfc3686(ctr(aes)))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
-			.maxauthsize = SHA256_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha384),rfc3686(ctr(aes)))",
-		.driver_name = "authenc-hmac-sha384-rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "seqiv(authenc("
+					    "hmac(sha1),rfc3686(ctr(aes))))",
+				.cra_driver_name = "seqiv-authenc-hmac-sha1-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
-			.maxauthsize = SHA384_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "authenc(hmac(sha512),rfc3686(ctr(aes)))",
-		.driver_name = "authenc-hmac-sha512-rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "rfc3686(ctr(aes)))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
+			},
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = old_aead_encrypt,
-			.decrypt = old_aead_decrypt,
-			.givencrypt = old_aead_givencrypt,
-			.geniv = "<built-in>",
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
-			.maxauthsize = SHA512_DIGEST_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-		.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
-				   OP_ALG_AAI_HMAC_PRECOMP,
-		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+		},
 	},
-	/* ablkcipher descriptor */
 	{
-		.name = "cbc(aes)",
-		.driver_name = "cbc-aes-caam",
-		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
-		.template_ablkcipher = {
-			.setkey = ablkcipher_setkey,
-			.encrypt = ablkcipher_encrypt,
-			.decrypt = ablkcipher_decrypt,
-			.givencrypt = ablkcipher_givencrypt,
-			.geniv = "<built-in>",
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
+		.aead = {
+			.base = {
+				.cra_name = "seqiv(authenc("
+					    "hmac(sha224),rfc3686(ctr(aes))))",
+				.cra_driver_name = "seqiv-authenc-hmac-sha224-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "cbc(des3_ede)",
-		.driver_name = "cbc-3des-caam",
-		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
-		.template_ablkcipher = {
-			.setkey = ablkcipher_setkey,
-			.encrypt = ablkcipher_encrypt,
-			.decrypt = ablkcipher_decrypt,
-			.givencrypt = ablkcipher_givencrypt,
-			.geniv = "<built-in>",
-			.min_keysize = DES3_EDE_KEY_SIZE,
-			.max_keysize = DES3_EDE_KEY_SIZE,
-			.ivsize = DES3_EDE_BLOCK_SIZE,
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "rfc3686(ctr(aes)))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+		},
 	},
 	{
-		.name = "cbc(des)",
-		.driver_name = "cbc-des-caam",
-		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
-		.template_ablkcipher = {
-			.setkey = ablkcipher_setkey,
-			.encrypt = ablkcipher_encrypt,
-			.decrypt = ablkcipher_decrypt,
-			.givencrypt = ablkcipher_givencrypt,
-			.geniv = "<built-in>",
-			.min_keysize = DES_KEY_SIZE,
-			.max_keysize = DES_KEY_SIZE,
-			.ivsize = DES_BLOCK_SIZE,
+		.aead = {
+			.base = {
+				.cra_name = "seqiv(authenc(hmac(sha256),"
+					    "rfc3686(ctr(aes))))",
+				.cra_driver_name = "seqiv-authenc-hmac-sha256-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+			.geniv = true,
+		},
 	},
 	{
-		.name = "ctr(aes)",
-		.driver_name = "ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.template_ablkcipher = {
-			.setkey = ablkcipher_setkey,
-			.encrypt = ablkcipher_encrypt,
-			.decrypt = ablkcipher_decrypt,
-			.geniv = "chainiv",
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),"
+					    "rfc3686(ctr(aes)))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "rfc3686-ctr-aes-caam",
+				.cra_blocksize = 1,
 			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-	},
-	{
-		.name = "rfc3686(ctr(aes))",
-		.driver_name = "rfc3686-ctr-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
-		.template_ablkcipher = {
-			.setkey = ablkcipher_setkey,
-			.encrypt = ablkcipher_encrypt,
-			.decrypt = ablkcipher_decrypt,
-			.givencrypt = ablkcipher_givencrypt,
-			.geniv = "<built-in>",
-			.min_keysize = AES_MIN_KEY_SIZE +
-				       CTR_RFC3686_NONCE_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE +
-				       CTR_RFC3686_NONCE_SIZE,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
-	}
-};
-
-struct caam_alg_entry {
-	int class1_alg_type;
-	int class2_alg_type;
-	int alg_op;
-};
-
-struct caam_aead_alg {
-	struct aead_alg aead;
-	struct caam_alg_entry caam;
-	bool registered;
-};
-
-static struct caam_aead_alg driver_aeads[] = {
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+		},
+	},
 	{
 		.aead = {
 			.base = {
-				.cra_name = "rfc4106(gcm(aes))",
-				.cra_driver_name = "rfc4106-gcm-aes-caam",
+				.cra_name = "seqiv(authenc(hmac(sha384),"
+					    "rfc3686(ctr(aes))))",
+				.cra_driver_name = "seqiv-authenc-hmac-sha384-"
+						   "rfc3686-ctr-aes-caam",
 				.cra_blocksize = 1,
 			},
-			.setkey = rfc4106_setkey,
-			.setauthsize = rfc4106_setauthsize,
-			.encrypt = gcm_encrypt,
-			.decrypt = gcm_decrypt,
-			.ivsize = 8,
-			.maxauthsize = AES_BLOCK_SIZE,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
 		.caam = {
-			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+			.geniv = true,
 		},
 	},
 	{
 		.aead = {
 			.base = {
-				.cra_name = "rfc4543(gcm(aes))",
-				.cra_driver_name = "rfc4543-gcm-aes-caam",
+				.cra_name = "authenc(hmac(sha512),"
+					    "rfc3686(ctr(aes)))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "rfc3686-ctr-aes-caam",
 				.cra_blocksize = 1,
 			},
-			.setkey = rfc4543_setkey,
-			.setauthsize = rfc4543_setauthsize,
-			.encrypt = gcm_encrypt,
-			.decrypt = gcm_decrypt,
-			.ivsize = 8,
-			.maxauthsize = AES_BLOCK_SIZE,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
 		.caam = {
-			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
 		},
 	},
-	/* Galois Counter Mode */
 	{
 		.aead = {
 			.base = {
-				.cra_name = "gcm(aes)",
-				.cra_driver_name = "gcm-aes-caam",
+				.cra_name = "seqiv(authenc(hmac(sha512),"
+					    "rfc3686(ctr(aes))))",
+				.cra_driver_name = "seqiv-authenc-hmac-sha512-"
+						   "rfc3686-ctr-aes-caam",
 				.cra_blocksize = 1,
 			},
-			.setkey = gcm_setkey,
-			.setauthsize = gcm_setauthsize,
-			.encrypt = gcm_encrypt,
-			.decrypt = gcm_decrypt,
-			.ivsize = 12,
-			.maxauthsize = AES_BLOCK_SIZE,
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_givdecrypt,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
 		.caam = {
-			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+			.class1_alg_type = OP_ALG_ALGSEL_AES |
+					   OP_ALG_AAI_CTR_MOD128,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+			.rfc3686 = true,
+			.geniv = true,
 		},
 	},
 };
@@ -4211,7 +4314,7 @@ static struct caam_crypto_alg *caam_alg_alloc(struct caam_alg_template
 	struct caam_crypto_alg *t_alg;
 	struct crypto_alg *alg;
 
-	t_alg = kzalloc(sizeof(struct caam_crypto_alg), GFP_KERNEL);
+	t_alg = kzalloc(sizeof(*t_alg), GFP_KERNEL);
 	if (!t_alg) {
 		pr_err("failed to allocate t_alg\n");
 		return ERR_PTR(-ENOMEM);
@@ -4240,10 +4343,6 @@ static struct caam_crypto_alg *caam_alg_alloc(struct caam_alg_template
 		alg->cra_type = &crypto_ablkcipher_type;
 		alg->cra_ablkcipher = template->template_ablkcipher;
 		break;
-	case CRYPTO_ALG_TYPE_AEAD:
-		alg->cra_type = &crypto_aead_type;
-		alg->cra_aead = template->template_aead;
-		break;
 	}
 
 	t_alg->caam.class1_alg_type = template->class1_alg_type;
@@ -4271,8 +4370,10 @@ static int __init caam_algapi_init(void)
 	struct device_node *dev_node;
 	struct platform_device *pdev;
 	struct device *ctrldev;
-	void *priv;
+	struct caam_drv_private *priv;
 	int i = 0, err = 0;
+	u32 cha_vid, cha_inst, des_inst, aes_inst, md_inst;
+	unsigned int md_limit = SHA512_DIGEST_SIZE;
 	bool registered = false;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
@@ -4302,16 +4403,39 @@ static int __init caam_algapi_init(void)
 
 	INIT_LIST_HEAD(&alg_list);
 
-	/* register crypto algorithms the device supports */
+	/*
+	 * Register crypto algorithms the device supports.
+	 * First, detect presence and attributes of DES, AES, and MD blocks.
+	 */
+	cha_vid = rd_reg32(&priv->ctrl->perfmon.cha_id_ls);
+	cha_inst = rd_reg32(&priv->ctrl->perfmon.cha_num_ls);
+	des_inst = (cha_inst & CHA_ID_LS_DES_MASK) >> CHA_ID_LS_DES_SHIFT;
+	aes_inst = (cha_inst & CHA_ID_LS_AES_MASK) >> CHA_ID_LS_AES_SHIFT;
+	md_inst = (cha_inst & CHA_ID_LS_MD_MASK) >> CHA_ID_LS_MD_SHIFT;
+
+	/* If MD is present, limit digest size based on LP256 */
+	if (md_inst && ((cha_vid & CHA_ID_LS_MD_MASK) == CHA_ID_LS_MD_LP256))
+		md_limit = SHA256_DIGEST_SIZE;
+
 	for (i = 0; i < ARRAY_SIZE(driver_algs); i++) {
-		/* TODO: check if h/w supports alg */
 		struct caam_crypto_alg *t_alg;
+		struct caam_alg_template *alg = driver_algs + i;
+		u32 alg_sel = alg->class1_alg_type & OP_ALG_ALGSEL_MASK;
+
+		/* Skip DES algorithms if not supported by device */
+		if (!des_inst &&
+		    ((alg_sel == OP_ALG_ALGSEL_3DES) ||
+		     (alg_sel == OP_ALG_ALGSEL_DES)))
+				continue;
+
+		/* Skip AES algorithms if not supported by device */
+		if (!aes_inst && (alg_sel == OP_ALG_ALGSEL_AES))
+				continue;
 
-		t_alg = caam_alg_alloc(&driver_algs[i]);
+		t_alg = caam_alg_alloc(alg);
 		if (IS_ERR(t_alg)) {
 			err = PTR_ERR(t_alg);
-			pr_warn("%s alg allocation failed\n",
-				driver_algs[i].driver_name);
+			pr_warn("%s alg allocation failed\n", alg->driver_name);
 			continue;
 		}
 
@@ -4329,6 +4453,37 @@ static int __init caam_algapi_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
 		struct caam_aead_alg *t_alg = driver_aeads + i;
+		u32 c1_alg_sel = t_alg->caam.class1_alg_type &
+				 OP_ALG_ALGSEL_MASK;
+		u32 c2_alg_sel = t_alg->caam.class2_alg_type &
+				 OP_ALG_ALGSEL_MASK;
+		u32 alg_aai = t_alg->caam.class1_alg_type & OP_ALG_AAI_MASK;
+
+		/* Skip DES algorithms if not supported by device */
+		if (!des_inst &&
+		    ((c1_alg_sel == OP_ALG_ALGSEL_3DES) ||
+		     (c1_alg_sel == OP_ALG_ALGSEL_DES)))
+				continue;
+
+		/* Skip AES algorithms if not supported by device */
+		if (!aes_inst && (c1_alg_sel == OP_ALG_ALGSEL_AES))
+				continue;
+
+		/*
+		 * Check support for AES algorithms not available
+		 * on LP devices.
+		 */
+		if ((cha_vid & CHA_ID_LS_AES_MASK) == CHA_ID_LS_AES_LP)
+			if (alg_aai == OP_ALG_AAI_GCM)
+				continue;
+
+		/*
+		 * Skip algorithms requiring message digests
+		 * if MD or MD size is not supported by device.
+		 */
+		if (c2_alg_sel &&
+		    (!md_inst || (t_alg->aead.maxauthsize > md_limit)))
+				continue;
 
 		caam_aead_alg_init(t_alg);
 
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index dae1e8099969..94433b9fc200 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -127,7 +127,7 @@ struct caam_hash_state {
 	int buflen_0;
 	u8 buf_1[CAAM_MAX_HASH_BLOCK_SIZE] ____cacheline_aligned;
 	int buflen_1;
-	u8 caam_ctx[MAX_CTX_LEN];
+	u8 caam_ctx[MAX_CTX_LEN] ____cacheline_aligned;
 	int (*update)(struct ahash_request *req);
 	int (*final)(struct ahash_request *req);
 	int (*finup)(struct ahash_request *req);
@@ -807,7 +807,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 		 * allocate space for base edesc and hw desc commands,
 		 * link tables
 		 */
-		edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+		edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN +
 				sec4_sg_bytes, GFP_DMA | flags);
 		if (!edesc) {
 			dev_err(jrdev,
@@ -829,7 +829,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 		state->buf_dma = try_buf_map_to_sec4_sg(jrdev,
 							edesc->sec4_sg + 1,
 							buf, state->buf_dma,
-							*buflen, last_buflen);
+							*next_buflen, *buflen);
 
 		if (src_nents) {
 			src_map_to_sec4_sg(jrdev, req->src, src_nents,
@@ -909,17 +909,18 @@ static int ahash_final_ctx(struct ahash_request *req)
 			  state->buflen_1;
 	u32 *sh_desc = ctx->sh_desc_fin, *desc;
 	dma_addr_t ptr = ctx->sh_desc_fin_dma;
-	int sec4_sg_bytes;
+	int sec4_sg_bytes, sec4_sg_src_index;
 	int digestsize = crypto_ahash_digestsize(ahash);
 	struct ahash_edesc *edesc;
 	int ret = 0;
 	int sh_len;
 
-	sec4_sg_bytes = (1 + (buflen ? 1 : 0)) * sizeof(struct sec4_sg_entry);
+	sec4_sg_src_index = 1 + (buflen ? 1 : 0);
+	sec4_sg_bytes = sec4_sg_src_index * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
-			sec4_sg_bytes, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN + sec4_sg_bytes,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return -ENOMEM;
@@ -942,7 +943,7 @@ static int ahash_final_ctx(struct ahash_request *req)
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
 						last_buflen);
-	(edesc->sec4_sg + sec4_sg_bytes - 1)->len |= SEC4_SG_LEN_FIN;
+	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |= SEC4_SG_LEN_FIN;
 
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
@@ -1005,8 +1006,8 @@ static int ahash_finup_ctx(struct ahash_request *req)
 			 sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
-			sec4_sg_bytes, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN + sec4_sg_bytes,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return -ENOMEM;
@@ -1091,8 +1092,8 @@ static int ahash_digest(struct ahash_request *req)
 	sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct ahash_edesc) + sec4_sg_bytes +
-			DESC_JOB_IO_LEN, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + sec4_sg_bytes + DESC_JOB_IO_LEN,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return -ENOMEM;
@@ -1165,8 +1166,7 @@ static int ahash_final_no_ctx(struct ahash_request *req)
 	int sh_len;
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN,
-			GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN, GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return -ENOMEM;
@@ -1245,7 +1245,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		 * allocate space for base edesc and hw desc commands,
 		 * link tables
 		 */
-		edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+		edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN +
 				sec4_sg_bytes, GFP_DMA | flags);
 		if (!edesc) {
 			dev_err(jrdev,
@@ -1353,8 +1353,8 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 			 sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
-			sec4_sg_bytes, GFP_DMA | flags);
+	edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN + sec4_sg_bytes,
+			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return -ENOMEM;
@@ -1448,7 +1448,7 @@ static int ahash_update_first(struct ahash_request *req)
 		 * allocate space for base edesc and hw desc commands,
 		 * link tables
 		 */
-		edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+		edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN +
 				sec4_sg_bytes, GFP_DMA | flags);
 		if (!edesc) {
 			dev_err(jrdev,
@@ -1842,7 +1842,7 @@ caam_hash_alloc(struct caam_hash_template *template,
 	struct ahash_alg *halg;
 	struct crypto_alg *alg;
 
-	t_alg = kzalloc(sizeof(struct caam_hash_alg), GFP_KERNEL);
+	t_alg = kzalloc(sizeof(*t_alg), GFP_KERNEL);
 	if (!t_alg) {
 		pr_err("failed to allocate t_alg\n");
 		return ERR_PTR(-ENOMEM);
@@ -1884,8 +1884,10 @@ static int __init caam_algapi_hash_init(void)
 	struct device_node *dev_node;
 	struct platform_device *pdev;
 	struct device *ctrldev;
-	void *priv;
 	int i = 0, err = 0;
+	struct caam_drv_private *priv;
+	unsigned int md_limit = SHA512_DIGEST_SIZE;
+	u32 cha_inst, cha_vid;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
 	if (!dev_node) {
@@ -1911,19 +1913,40 @@ static int __init caam_algapi_hash_init(void)
 	if (!priv)
 		return -ENODEV;
 
+	/*
+	 * Register crypto algorithms the device supports.  First, identify
+	 * presence and attributes of MD block.
+	 */
+	cha_vid = rd_reg32(&priv->ctrl->perfmon.cha_id_ls);
+	cha_inst = rd_reg32(&priv->ctrl->perfmon.cha_num_ls);
+
+	/*
+	 * Skip registration of any hashing algorithms if MD block
+	 * is not present.
+	 */
+	if (!((cha_inst & CHA_ID_LS_MD_MASK) >> CHA_ID_LS_MD_SHIFT))
+		return -ENODEV;
+
+	/* Limit digest size based on LP256 */
+	if ((cha_vid & CHA_ID_LS_MD_MASK) == CHA_ID_LS_MD_LP256)
+		md_limit = SHA256_DIGEST_SIZE;
+
 	INIT_LIST_HEAD(&hash_list);
 
 	/* register crypto algorithms the device supports */
 	for (i = 0; i < ARRAY_SIZE(driver_hash); i++) {
-		/* TODO: check if h/w supports alg */
 		struct caam_hash_alg *t_alg;
+		struct caam_hash_template *alg = driver_hash + i;
+
+		/* If MD size is not supported by device, skip registration */
+		if (alg->template_ahash.halg.digestsize > md_limit)
+			continue;
 
 		/* register hmac version */
-		t_alg = caam_hash_alloc(&driver_hash[i], true);
+		t_alg = caam_hash_alloc(alg, true);
 		if (IS_ERR(t_alg)) {
 			err = PTR_ERR(t_alg);
-			pr_warn("%s alg allocation failed\n",
-				driver_hash[i].driver_name);
+			pr_warn("%s alg allocation failed\n", alg->driver_name);
 			continue;
 		}
 
@@ -1936,11 +1959,10 @@ static int __init caam_algapi_hash_init(void)
 			list_add_tail(&t_alg->entry, &hash_list);
 
 		/* register unkeyed version */
-		t_alg = caam_hash_alloc(&driver_hash[i], false);
+		t_alg = caam_hash_alloc(alg, false);
 		if (IS_ERR(t_alg)) {
 			err = PTR_ERR(t_alg);
-			pr_warn("%s alg allocation failed\n",
-				driver_hash[i].driver_name);
+			pr_warn("%s alg allocation failed\n", alg->driver_name);
 			continue;
 		}
 
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index 5095337205b8..9b92af2c7241 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -108,6 +108,10 @@ static void rng_done(struct device *jrdev, u32 *desc, u32 err, void *context)
 
 	atomic_set(&bd->empty, BUF_NOT_EMPTY);
 	complete(&bd->filled);
+
+	/* Buffer refilled, invalidate cache */
+	dma_sync_single_for_cpu(jrdev, bd->addr, RN_BUF_SIZE, DMA_FROM_DEVICE);
+
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "rng refreshed buf@: ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, bd->buf, RN_BUF_SIZE, 1);
@@ -311,7 +315,7 @@ static int __init caam_rng_init(void)
 	struct device_node *dev_node;
 	struct platform_device *pdev;
 	struct device *ctrldev;
-	void *priv;
+	struct caam_drv_private *priv;
 	int err;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
@@ -338,20 +342,32 @@ static int __init caam_rng_init(void)
 	if (!priv)
 		return -ENODEV;
 
+	/* Check for an instantiated RNG before registration */
+	if (!(rd_reg32(&priv->ctrl->perfmon.cha_num_ls) & CHA_ID_LS_RNG_MASK))
+		return -ENODEV;
+
 	dev = caam_jr_alloc();
 	if (IS_ERR(dev)) {
 		pr_err("Job Ring Device allocation for transform failed\n");
 		return PTR_ERR(dev);
 	}
-	rng_ctx = kmalloc(sizeof(struct caam_rng_ctx), GFP_DMA);
-	if (!rng_ctx)
-		return -ENOMEM;
+	rng_ctx = kmalloc(sizeof(*rng_ctx), GFP_DMA);
+	if (!rng_ctx) {
+		err = -ENOMEM;
+		goto free_caam_alloc;
+	}
 	err = caam_init_rng(rng_ctx, dev);
 	if (err)
-		return err;
+		goto free_rng_ctx;
 
 	dev_info(dev, "registering rng-caam\n");
 	return hwrng_register(&caam_rng);
+
+free_rng_ctx:
+	kfree(rng_ctx);
+free_caam_alloc:
+	caam_jr_free(dev);
+	return err;
 }
 
 module_init(caam_rng_init);
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index f57f395db33f..b6955ecdfb3f 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/debugfs.h>
 #include <linux/circ_buf.h>
+#include <linux/clk.h>
 #include <net/xfrm.h>
 
 #include <crypto/algapi.h>
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index efacab7539ef..8abb4bc548cc 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -16,6 +16,24 @@
 #include "error.h"
 
 /*
+ * i.MX targets tend to have clock control subsystems that can
+ * enable/disable clocking to our device.
+ */
+#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+static inline struct clk *caam_drv_identify_clk(struct device *dev,
+						char *clk_name)
+{
+	return devm_clk_get(dev, clk_name);
+}
+#else
+static inline struct clk *caam_drv_identify_clk(struct device *dev,
+						char *clk_name)
+{
+	return NULL;
+}
+#endif
+
+/*
  * Descriptor to instantiate RNG State Handle 0 in normal mode and
  * load the JDKEK, TDKEK and TDSK registers
  */
@@ -121,7 +139,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		flags |= DECO_JQCR_FOUR;
 
 	/* Instruct the DECO to execute it */
-	wr_reg32(&deco->jr_ctl_hi, flags);
+	setbits32(&deco->jr_ctl_hi, flags);
 
 	timeout = 10000000;
 	do {
@@ -175,7 +193,7 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask,
 {
 	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctrldev);
 	struct caam_ctrl __iomem *ctrl;
-	u32 *desc, status, rdsta_val;
+	u32 *desc, status = 0, rdsta_val;
 	int ret = 0, sh_idx;
 
 	ctrl = (struct caam_ctrl __iomem *)ctrlpriv->ctrl;
@@ -207,7 +225,8 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask,
 		 * CAAM eras), then try again.
 		 */
 		rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK;
-		if (status || !(rdsta_val & (1 << sh_idx)))
+		if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) ||
+		    !(rdsta_val & (1 << sh_idx)))
 			ret = -EAGAIN;
 		if (ret)
 			break;
@@ -279,7 +298,7 @@ static int caam_remove(struct platform_device *pdev)
 	struct device *ctrldev;
 	struct caam_drv_private *ctrlpriv;
 	struct caam_ctrl __iomem *ctrl;
-	int ring, ret = 0;
+	int ring;
 
 	ctrldev = &pdev->dev;
 	ctrlpriv = dev_get_drvdata(ctrldev);
@@ -303,7 +322,13 @@ static int caam_remove(struct platform_device *pdev)
 	/* Unmap controller region */
 	iounmap(ctrl);
 
-	return ret;
+	/* shut clocks off before finalizing shutdown */
+	clk_disable_unprepare(ctrlpriv->caam_ipg);
+	clk_disable_unprepare(ctrlpriv->caam_mem);
+	clk_disable_unprepare(ctrlpriv->caam_aclk);
+	clk_disable_unprepare(ctrlpriv->caam_emi_slow);
+
+	return 0;
 }
 
 /*
@@ -370,14 +395,14 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 int caam_get_era(void)
 {
 	struct device_node *caam_node;
-	for_each_compatible_node(caam_node, NULL, "fsl,sec-v4.0") {
-		const uint32_t *prop = (uint32_t *)of_get_property(caam_node,
-				"fsl,sec-era",
-				NULL);
-		return prop ? *prop : -ENOTSUPP;
-	}
+	int ret;
+	u32 prop;
 
-	return -ENOTSUPP;
+	caam_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	ret = of_property_read_u32(caam_node, "fsl,sec-era", &prop);
+	of_node_put(caam_node);
+
+	return IS_ERR_VALUE(ret) ? -ENOTSUPP : prop;
 }
 EXPORT_SYMBOL(caam_get_era);
 
@@ -390,6 +415,7 @@ static int caam_probe(struct platform_device *pdev)
 	struct device_node *nprop, *np;
 	struct caam_ctrl __iomem *ctrl;
 	struct caam_drv_private *ctrlpriv;
+	struct clk *clk;
 #ifdef CONFIG_DEBUG_FS
 	struct caam_perfmon *perfmon;
 #endif
@@ -398,8 +424,7 @@ static int caam_probe(struct platform_device *pdev)
 	int pg_size;
 	int BLOCK_OFFSET = 0;
 
-	ctrlpriv = devm_kzalloc(&pdev->dev, sizeof(struct caam_drv_private),
-				GFP_KERNEL);
+	ctrlpriv = devm_kzalloc(&pdev->dev, sizeof(*ctrlpriv), GFP_KERNEL);
 	if (!ctrlpriv)
 		return -ENOMEM;
 
@@ -408,12 +433,76 @@ static int caam_probe(struct platform_device *pdev)
 	ctrlpriv->pdev = pdev;
 	nprop = pdev->dev.of_node;
 
+	/* Enable clocking */
+	clk = caam_drv_identify_clk(&pdev->dev, "ipg");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(&pdev->dev,
+			"can't identify CAAM ipg clk: %d\n", ret);
+		return ret;
+	}
+	ctrlpriv->caam_ipg = clk;
+
+	clk = caam_drv_identify_clk(&pdev->dev, "mem");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(&pdev->dev,
+			"can't identify CAAM mem clk: %d\n", ret);
+		return ret;
+	}
+	ctrlpriv->caam_mem = clk;
+
+	clk = caam_drv_identify_clk(&pdev->dev, "aclk");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(&pdev->dev,
+			"can't identify CAAM aclk clk: %d\n", ret);
+		return ret;
+	}
+	ctrlpriv->caam_aclk = clk;
+
+	clk = caam_drv_identify_clk(&pdev->dev, "emi_slow");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(&pdev->dev,
+			"can't identify CAAM emi_slow clk: %d\n", ret);
+		return ret;
+	}
+	ctrlpriv->caam_emi_slow = clk;
+
+	ret = clk_prepare_enable(ctrlpriv->caam_ipg);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can't enable CAAM ipg clock: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(ctrlpriv->caam_mem);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can't enable CAAM secure mem clock: %d\n",
+			ret);
+		goto disable_caam_ipg;
+	}
+
+	ret = clk_prepare_enable(ctrlpriv->caam_aclk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can't enable CAAM aclk clock: %d\n", ret);
+		goto disable_caam_mem;
+	}
+
+	ret = clk_prepare_enable(ctrlpriv->caam_emi_slow);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can't enable CAAM emi slow clock: %d\n",
+			ret);
+		goto disable_caam_aclk;
+	}
+
 	/* Get configuration properties from device tree */
 	/* First, get register page */
 	ctrl = of_iomap(nprop, 0);
 	if (ctrl == NULL) {
 		dev_err(dev, "caam: of_iomap() failed\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto disable_caam_emi_slow;
 	}
 	/* Finding the page size for using the CTPR_MS register */
 	comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ms);
@@ -444,8 +533,9 @@ static int caam_probe(struct platform_device *pdev)
 	 * Enable DECO watchdogs and, if this is a PHYS_ADDR_T_64BIT kernel,
 	 * long pointers in master configuration register
 	 */
-	setbits32(&ctrl->mcr, MCFGR_WDENABLE |
-		  (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0));
+	clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH |
+		      MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ?
+					MCFGR_LONG_PTR : 0));
 
 	/*
 	 *  Read the Compile Time paramters and SCFGR to determine
@@ -492,12 +582,11 @@ static int caam_probe(struct platform_device *pdev)
 		    of_device_is_compatible(np, "fsl,sec4.0-job-ring"))
 			rspec++;
 
-	ctrlpriv->jrpdev = devm_kzalloc(&pdev->dev,
-					sizeof(struct platform_device *) * rspec,
-					GFP_KERNEL);
+	ctrlpriv->jrpdev = devm_kcalloc(&pdev->dev, rspec,
+					sizeof(*ctrlpriv->jrpdev), GFP_KERNEL);
 	if (ctrlpriv->jrpdev == NULL) {
-		iounmap(ctrl);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto iounmap_ctrl;
 	}
 
 	ring = 0;
@@ -537,8 +626,8 @@ static int caam_probe(struct platform_device *pdev)
 	/* If no QI and no rings specified, quit and go home */
 	if ((!ctrlpriv->qi_present) && (!ctrlpriv->total_jobrs)) {
 		dev_err(dev, "no queues configured, terminating\n");
-		caam_remove(pdev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto caam_remove;
 	}
 
 	cha_vid_ls = rd_reg32(&ctrl->perfmon.cha_id_ls);
@@ -595,8 +684,7 @@ static int caam_probe(struct platform_device *pdev)
 		} while ((ret == -EAGAIN) && (ent_delay < RTSDCTL_ENT_DLY_MAX));
 		if (ret) {
 			dev_err(dev, "failed to instantiate RNG");
-			caam_remove(pdev);
-			return ret;
+			goto caam_remove;
 		}
 		/*
 		 * Set handles init'ed by this module as the complement of the
@@ -700,6 +788,20 @@ static int caam_probe(struct platform_device *pdev)
 						 &ctrlpriv->ctl_tdsk_wrap);
 #endif
 	return 0;
+
+caam_remove:
+	caam_remove(pdev);
+iounmap_ctrl:
+	iounmap(ctrl);
+disable_caam_emi_slow:
+	clk_disable_unprepare(ctrlpriv->caam_emi_slow);
+disable_caam_aclk:
+	clk_disable_unprepare(ctrlpriv->caam_aclk);
+disable_caam_mem:
+	clk_disable_unprepare(ctrlpriv->caam_mem);
+disable_caam_ipg:
+	clk_disable_unprepare(ctrlpriv->caam_ipg);
+	return ret;
 }
 
 static struct of_device_id caam_match[] = {
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index d397ff9d56fd..983d663ef671 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -8,12 +8,29 @@
 #ifndef DESC_H
 #define DESC_H
 
+/*
+ * 16-byte hardware scatter/gather table
+ * An 8-byte table exists in the hardware spec, but has never been
+ * implemented to date. The 8/16 option is selected at RTL-compile-time.
+ * and this selection is visible in the Compile Time Parameters Register
+ */
+
+#define SEC4_SG_LEN_EXT		0x80000000	/* Entry points to table */
+#define SEC4_SG_LEN_FIN		0x40000000	/* Last ent in table */
+#define SEC4_SG_BPID_MASK	0x000000ff
+#define SEC4_SG_BPID_SHIFT	16
+#define SEC4_SG_LEN_MASK	0x3fffffff	/* Excludes EXT and FINAL */
+#define SEC4_SG_OFFS_MASK	0x00001fff
+
 struct sec4_sg_entry {
+#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+	u32 rsvd1;
+	dma_addr_t ptr;
+#else
 	u64 ptr;
-#define SEC4_SG_LEN_FIN 0x40000000
-#define SEC4_SG_LEN_EXT 0x80000000
+#endif /* CONFIG_CRYPTO_DEV_FSL_CAAM_IMX */
 	u32 len;
-	u8 reserved;
+	u8 rsvd2;
 	u8 buf_pool_id;
 	u16 offset;
 };
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index 9f79fd7bd4d7..98d07de24fc4 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -367,7 +367,7 @@ do { \
 	if (upper) \
 		append_u64(desc, data); \
 	else \
-		append_u32(desc, data); \
+		append_u32(desc, lower_32_bits(data)); \
 } while (0)
 
 #define append_math_add_imm_u64(desc, dest, src0, src1, data) \
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 89b94cc9e7a2..e2bcacc1a921 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -91,6 +91,11 @@ struct caam_drv_private {
 				   Handles of the RNG4 block are initialized
 				   by this driver */
 
+	struct clk *caam_ipg;
+	struct clk *caam_mem;
+	struct clk *caam_aclk;
+	struct clk *caam_emi_slow;
+
 	/*
 	 * debugfs entries for developer view into driver/device
 	 * variables at runtime.
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index b8b5d47acd7a..f7e0d8d4c3da 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -202,6 +202,13 @@ static void caam_jr_dequeue(unsigned long devarg)
 		userdesc = jrp->entinfo[sw_idx].desc_addr_virt;
 		userstatus = jrp->outring[hw_idx].jrstatus;
 
+		/*
+		 * Make sure all information from the job has been obtained
+		 * before telling CAAM that the job has been removed from the
+		 * output ring.
+		 */
+		mb();
+
 		/* set done */
 		wr_reg32(&jrp->rregs->outring_rmvd, 1);
 
@@ -351,12 +358,23 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 
 	jrp->inpring[jrp->inp_ring_write_index] = desc_dma;
 
+	/*
+	 * Guarantee that the descriptor's DMA address has been written to
+	 * the next slot in the ring before the write index is updated, since
+	 * other cores may update this index independently.
+	 */
 	smp_wmb();
 
 	jrp->inp_ring_write_index = (jrp->inp_ring_write_index + 1) &
 				    (JOBR_DEPTH - 1);
 	jrp->head = (head + 1) & (JOBR_DEPTH - 1);
 
+	/*
+	 * Ensure that all job information has been written before
+	 * notifying CAAM that a new job was added to the input ring.
+	 */
+	wmb();
+
 	wr_reg32(&jrp->rregs->inpring_jobadd, 1);
 
 	spin_unlock_bh(&jrp->inplock);
@@ -392,18 +410,17 @@ static int caam_jr_init(struct device *dev)
 		goto out_free_irq;
 
 	error = -ENOMEM;
-	jrp->inpring = dma_alloc_coherent(dev, sizeof(dma_addr_t) * JOBR_DEPTH,
-					  &inpbusaddr, GFP_KERNEL);
+	jrp->inpring = dma_alloc_coherent(dev, sizeof(*jrp->inpring) *
+					  JOBR_DEPTH, &inpbusaddr, GFP_KERNEL);
 	if (!jrp->inpring)
 		goto out_free_irq;
 
-	jrp->outring = dma_alloc_coherent(dev, sizeof(struct jr_outentry) *
+	jrp->outring = dma_alloc_coherent(dev, sizeof(*jrp->outring) *
 					  JOBR_DEPTH, &outbusaddr, GFP_KERNEL);
 	if (!jrp->outring)
 		goto out_free_inpring;
 
-	jrp->entinfo = kzalloc(sizeof(struct caam_jrentry_info) * JOBR_DEPTH,
-			       GFP_KERNEL);
+	jrp->entinfo = kcalloc(JOBR_DEPTH, sizeof(*jrp->entinfo), GFP_KERNEL);
 	if (!jrp->entinfo)
 		goto out_free_outring;
 
@@ -461,8 +478,7 @@ static int caam_jr_probe(struct platform_device *pdev)
 	int error;
 
 	jrdev = &pdev->dev;
-	jrpriv = devm_kmalloc(jrdev, sizeof(struct caam_drv_private_jr),
-			      GFP_KERNEL);
+	jrpriv = devm_kmalloc(jrdev, sizeof(*jrpriv), GFP_KERNEL);
 	if (!jrpriv)
 		return -ENOMEM;
 
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 672c97489505..a8a79975682f 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -65,9 +65,31 @@
  *
  */
 
+#ifdef CONFIG_ARM
+/* These are common macros for Power, put here for ARM */
+#define setbits32(_addr, _v) writel((readl(_addr) | (_v)), (_addr))
+#define clrbits32(_addr, _v) writel((readl(_addr) & ~(_v)), (_addr))
+
+#define out_arch(type, endian, a, v)	__raw_write##type(cpu_to_##endian(v), a)
+#define in_arch(type, endian, a)	endian##_to_cpu(__raw_read##type(a))
+
+#define out_le32(a, v)	out_arch(l, le32, a, v)
+#define in_le32(a)	in_arch(l, le32, a)
+
+#define out_be32(a, v)	out_arch(l, be32, a, v)
+#define in_be32(a)	in_arch(l, be32, a)
+
+#define clrsetbits(type, addr, clear, set) \
+	out_##type((addr), (in_##type(addr) & ~(clear)) | (set))
+
+#define clrsetbits_be32(addr, clear, set) clrsetbits(be32, addr, clear, set)
+#define clrsetbits_le32(addr, clear, set) clrsetbits(le32, addr, clear, set)
+#endif
+
 #ifdef __BIG_ENDIAN
 #define wr_reg32(reg, data) out_be32(reg, data)
 #define rd_reg32(reg) in_be32(reg)
+#define clrsetbits_32(addr, clear, set) clrsetbits_be32(addr, clear, set)
 #ifdef CONFIG_64BIT
 #define wr_reg64(reg, data) out_be64(reg, data)
 #define rd_reg64(reg) in_be64(reg)
@@ -76,6 +98,7 @@
 #ifdef __LITTLE_ENDIAN
 #define wr_reg32(reg, data) __raw_writel(data, reg)
 #define rd_reg32(reg) __raw_readl(reg)
+#define clrsetbits_32(addr, clear, set) clrsetbits_le32(addr, clear, set)
 #ifdef CONFIG_64BIT
 #define wr_reg64(reg, data) __raw_writeq(data, reg)
 #define rd_reg64(reg) __raw_readq(reg)
@@ -85,20 +108,31 @@
 
 /*
  * The only users of these wr/rd_reg64 functions is the Job Ring (JR).
- * The DMA address registers in the JR are a pair of 32-bit registers.
- * The layout is:
+ * The DMA address registers in the JR are handled differently depending on
+ * platform:
+ *
+ * 1. All BE CAAM platforms and i.MX platforms (LE CAAM):
  *
  *    base + 0x0000 : most-significant 32 bits
  *    base + 0x0004 : least-significant 32 bits
  *
  * The 32-bit version of this core therefore has to write to base + 0x0004
- * to set the 32-bit wide DMA address. This seems to be independent of the
- * endianness of the written/read data.
+ * to set the 32-bit wide DMA address.
+ *
+ * 2. All other LE CAAM platforms (LS1021A etc.)
+ *    base + 0x0000 : least-significant 32 bits
+ *    base + 0x0004 : most-significant 32 bits
  */
 
 #ifndef CONFIG_64BIT
+#if !defined(CONFIG_CRYPTO_DEV_FSL_CAAM_LE) || \
+	defined(CONFIG_CRYPTO_DEV_FSL_CAAM_IMX)
 #define REG64_MS32(reg) ((u32 __iomem *)(reg))
 #define REG64_LS32(reg) ((u32 __iomem *)(reg) + 1)
+#else
+#define REG64_MS32(reg) ((u32 __iomem *)(reg) + 1)
+#define REG64_LS32(reg) ((u32 __iomem *)(reg))
+#endif
 
 static inline void wr_reg64(u64 __iomem *reg, u64 data)
 {
@@ -133,18 +167,28 @@ struct jr_outentry {
 #define CHA_NUM_MS_DECONUM_SHIFT	24
 #define CHA_NUM_MS_DECONUM_MASK	(0xfull << CHA_NUM_MS_DECONUM_SHIFT)
 
-/* CHA Version IDs */
+/*
+ * CHA version IDs / instantiation bitfields
+ * Defined for use with the cha_id fields in perfmon, but the same shift/mask
+ * selectors can be used to pull out the number of instantiated blocks within
+ * cha_num fields in perfmon because the locations are the same.
+ */
 #define CHA_ID_LS_AES_SHIFT	0
-#define CHA_ID_LS_AES_MASK		(0xfull << CHA_ID_LS_AES_SHIFT)
+#define CHA_ID_LS_AES_MASK	(0xfull << CHA_ID_LS_AES_SHIFT)
+#define CHA_ID_LS_AES_LP	(0x3ull << CHA_ID_LS_AES_SHIFT)
+#define CHA_ID_LS_AES_HP	(0x4ull << CHA_ID_LS_AES_SHIFT)
 
 #define CHA_ID_LS_DES_SHIFT	4
-#define CHA_ID_LS_DES_MASK		(0xfull << CHA_ID_LS_DES_SHIFT)
+#define CHA_ID_LS_DES_MASK	(0xfull << CHA_ID_LS_DES_SHIFT)
 
 #define CHA_ID_LS_ARC4_SHIFT	8
 #define CHA_ID_LS_ARC4_MASK	(0xfull << CHA_ID_LS_ARC4_SHIFT)
 
 #define CHA_ID_LS_MD_SHIFT	12
 #define CHA_ID_LS_MD_MASK	(0xfull << CHA_ID_LS_MD_SHIFT)
+#define CHA_ID_LS_MD_LP256	(0x0ull << CHA_ID_LS_MD_SHIFT)
+#define CHA_ID_LS_MD_LP512	(0x1ull << CHA_ID_LS_MD_SHIFT)
+#define CHA_ID_LS_MD_HP		(0x2ull << CHA_ID_LS_MD_SHIFT)
 
 #define CHA_ID_LS_RNG_SHIFT	16
 #define CHA_ID_LS_RNG_MASK	(0xfull << CHA_ID_LS_RNG_SHIFT)
@@ -395,10 +439,16 @@ struct caam_ctrl {
 /* AXI read cache control */
 #define MCFGR_ARCACHE_SHIFT	12
 #define MCFGR_ARCACHE_MASK	(0xf << MCFGR_ARCACHE_SHIFT)
+#define MCFGR_ARCACHE_BUFF	(0x1 << MCFGR_ARCACHE_SHIFT)
+#define MCFGR_ARCACHE_CACH	(0x2 << MCFGR_ARCACHE_SHIFT)
+#define MCFGR_ARCACHE_RALL	(0x4 << MCFGR_ARCACHE_SHIFT)
 
 /* AXI write cache control */
 #define MCFGR_AWCACHE_SHIFT	8
 #define MCFGR_AWCACHE_MASK	(0xf << MCFGR_AWCACHE_SHIFT)
+#define MCFGR_AWCACHE_BUFF	(0x1 << MCFGR_AWCACHE_SHIFT)
+#define MCFGR_AWCACHE_CACH	(0x2 << MCFGR_AWCACHE_SHIFT)
+#define MCFGR_AWCACHE_WALL	(0x8 << MCFGR_AWCACHE_SHIFT)
 
 /* AXI pipeline depth */
 #define MCFGR_AXIPIPE_SHIFT	4
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index b68b74cc7b77..18cd6d1f5870 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -15,7 +15,6 @@ static inline void dma_to_sec4_sg_one(struct sec4_sg_entry *sec4_sg_ptr,
 {
 	sec4_sg_ptr->ptr = dma;
 	sec4_sg_ptr->len = len;
-	sec4_sg_ptr->reserved = 0;
 	sec4_sg_ptr->buf_pool_id = 0;
 	sec4_sg_ptr->offset = offset;
 #ifdef DEBUG
@@ -106,9 +105,15 @@ static inline void dma_unmap_sg_chained(
 {
 	if (unlikely(chained)) {
 		int i;
+		struct scatterlist *tsg = sg;
+
+		/*
+		 * Use a local copy of the sg pointer to avoid moving the
+		 * head of the list pointed to by sg as we walk the list.
+		 */
 		for (i = 0; i < nents; i++) {
-			dma_unmap_sg(dev, sg, 1, dir);
-			sg = sg_next(sg);
+			dma_unmap_sg(dev, tsg, 1, dir);
+			tsg = sg_next(tsg);
 		}
 	} else if (nents) {
 		dma_unmap_sg(dev, sg, nents, dir);
@@ -119,19 +124,23 @@ static inline int dma_map_sg_chained(
 	struct device *dev, struct scatterlist *sg, unsigned int nents,
 	enum dma_data_direction dir, bool chained)
 {
-	struct scatterlist *first = sg;
-
 	if (unlikely(chained)) {
 		int i;
+		struct scatterlist *tsg = sg;
+
+		/*
+		 * Use a local copy of the sg pointer to avoid moving the
+		 * head of the list pointed to by sg as we walk the list.
+		 */
 		for (i = 0; i < nents; i++) {
-			if (!dma_map_sg(dev, sg, 1, dir)) {
-				dma_unmap_sg_chained(dev, first, i, dir,
+			if (!dma_map_sg(dev, tsg, 1, dir)) {
+				dma_unmap_sg_chained(dev, sg, i, dir,
 						     chained);
 				nents = 0;
 				break;
 			}
 
-			sg = sg_next(sg);
+			tsg = sg_next(tsg);
 		}
 	} else
 		nents = dma_map_sg(dev, sg, nents, dir);
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
index f2e6de361fd1..bb241c3ab6b9 100644
--- a/drivers/crypto/ccp/ccp-platform.c
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -216,6 +216,7 @@ static const struct acpi_device_id ccp_acpi_match[] = {
 	{ "AMDI0C00", 0 },
 	{ },
 };
+MODULE_DEVICE_TABLE(acpi, ccp_acpi_match);
 #endif
 
 #ifdef CONFIG_OF
@@ -223,6 +224,7 @@ static const struct of_device_id ccp_of_match[] = {
 	{ .compatible = "amd,ccp-seattle-v1a" },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, ccp_of_match);
 #endif
 
 static struct platform_driver ccp_platform_driver = {
diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c
index ad47d0d61098..68e8aa90fe01 100644
--- a/drivers/crypto/img-hash.c
+++ b/drivers/crypto/img-hash.c
@@ -334,7 +334,7 @@ static int img_hash_dma_init(struct img_hash_dev *hdev)
 
 	hdev->dma_lch = dma_request_slave_channel(hdev->dev, "tx");
 	if (!hdev->dma_lch) {
-		dev_err(hdev->dev, "Couldn't aquire a slave DMA channel.\n");
+		dev_err(hdev->dev, "Couldn't acquire a slave DMA channel.\n");
 		return -EBUSY;
 	}
 	dma_conf.direction = DMA_MEM_TO_DEV;
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 7ba495f75370..8f2790353281 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -156,7 +156,8 @@ struct ablk_ctx {
 };
 
 struct aead_ctx {
-	struct buffer_desc *buffer;
+	struct buffer_desc *src;
+	struct buffer_desc *dst;
 	struct scatterlist ivlist;
 	/* used when the hmac is not on one sg entry */
 	u8 *hmac_virt;
@@ -198,6 +199,15 @@ struct ixp_alg {
 	int registered;
 };
 
+struct ixp_aead_alg {
+	struct aead_alg crypto;
+	const struct ix_hash_algo *hash;
+	u32 cfg_enc;
+	u32 cfg_dec;
+
+	int registered;
+};
+
 static const struct ix_hash_algo hash_alg_md5 = {
 	.cfgword	= 0xAA010004,
 	.icv		= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
@@ -339,11 +349,11 @@ static void finish_scattered_hmac(struct crypt_ctl *crypt)
 	struct aead_ctx *req_ctx = aead_request_ctx(req);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	int authsize = crypto_aead_authsize(tfm);
-	int decryptlen = req->cryptlen - authsize;
+	int decryptlen = req->assoclen + req->cryptlen - authsize;
 
 	if (req_ctx->encrypt) {
 		scatterwalk_map_and_copy(req_ctx->hmac_virt,
-			req->src, decryptlen, authsize, 1);
+			req->dst, decryptlen, authsize, 1);
 	}
 	dma_pool_free(buffer_pool, req_ctx->hmac_virt, crypt->icv_rev_aes);
 }
@@ -364,7 +374,8 @@ static void one_packet(dma_addr_t phys)
 		struct aead_request *req = crypt->data.aead_req;
 		struct aead_ctx *req_ctx = aead_request_ctx(req);
 
-		free_buf_chain(dev, req_ctx->buffer, crypt->src_buf);
+		free_buf_chain(dev, req_ctx->src, crypt->src_buf);
+		free_buf_chain(dev, req_ctx->dst, crypt->dst_buf);
 		if (req_ctx->hmac_virt) {
 			finish_scattered_hmac(crypt);
 		}
@@ -573,11 +584,10 @@ static int init_tfm_ablk(struct crypto_tfm *tfm)
 	return init_tfm(tfm);
 }
 
-static int init_tfm_aead(struct crypto_tfm *tfm)
+static int init_tfm_aead(struct crypto_aead *tfm)
 {
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
-				sizeof(struct aead_ctx));
-	return init_tfm(tfm);
+	crypto_aead_set_reqsize(tfm, sizeof(struct aead_ctx));
+	return init_tfm(crypto_aead_tfm(tfm));
 }
 
 static void exit_tfm(struct crypto_tfm *tfm)
@@ -587,6 +597,11 @@ static void exit_tfm(struct crypto_tfm *tfm)
 	free_sa_dir(&ctx->decrypt);
 }
 
+static void exit_tfm_aead(struct crypto_aead *tfm)
+{
+	exit_tfm(crypto_aead_tfm(tfm));
+}
+
 static int register_chain_var(struct crypto_tfm *tfm, u8 xpad, u32 target,
 		int init_len, u32 ctx_addr, const u8 *key, int key_len)
 {
@@ -905,7 +920,6 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt)
 		crypt->mode |= NPE_OP_NOT_IN_PLACE;
 		/* This was never tested by Intel
 		 * for more than one dst buffer, I think. */
-		BUG_ON(req->dst->length < nbytes);
 		req_ctx->dst = NULL;
 		if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook,
 					flags, DMA_FROM_DEVICE))
@@ -970,24 +984,6 @@ static int ablk_rfc3686_crypt(struct ablkcipher_request *req)
 	return ret;
 }
 
-static int hmac_inconsistent(struct scatterlist *sg, unsigned start,
-		unsigned int nbytes)
-{
-	int offset = 0;
-
-	if (!nbytes)
-		return 0;
-
-	for (;;) {
-		if (start < offset + sg->length)
-			break;
-
-		offset += sg->length;
-		sg = sg_next(sg);
-	}
-	return (start + nbytes > offset + sg->length);
-}
-
 static int aead_perform(struct aead_request *req, int encrypt,
 		int cryptoffset, int eff_cryptlen, u8 *iv)
 {
@@ -1003,6 +999,8 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	struct device *dev = &pdev->dev;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
 				GFP_KERNEL : GFP_ATOMIC;
+	enum dma_data_direction src_direction = DMA_BIDIRECTIONAL;
+	unsigned int lastlen;
 
 	if (qmgr_stat_full(SEND_QID))
 		return -EAGAIN;
@@ -1031,35 +1029,55 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	crypt->crypt_len = eff_cryptlen;
 
 	crypt->auth_offs = 0;
-	crypt->auth_len = req->assoclen + ivsize + cryptlen;
+	crypt->auth_len = req->assoclen + cryptlen;
 	BUG_ON(ivsize && !req->iv);
 	memcpy(crypt->iv, req->iv, ivsize);
 
+	req_ctx->dst = NULL;
+
 	if (req->src != req->dst) {
-		BUG(); /* -ENOTSUP because of my laziness */
+		struct buffer_desc dst_hook;
+
+		crypt->mode |= NPE_OP_NOT_IN_PLACE;
+		src_direction = DMA_TO_DEVICE;
+
+		buf = chainup_buffers(dev, req->dst, crypt->auth_len,
+				      &dst_hook, flags, DMA_FROM_DEVICE);
+		req_ctx->dst = dst_hook.next;
+		crypt->dst_buf = dst_hook.phys_next;
+
+		if (!buf)
+			goto free_buf_dst;
+
+		if (encrypt) {
+			lastlen = buf->buf_len;
+			if (lastlen >= authsize)
+				crypt->icv_rev_aes = buf->phys_addr +
+						     buf->buf_len - authsize;
+		}
 	}
 
-	/* ASSOC data */
-	buf = chainup_buffers(dev, req->assoc, req->assoclen, &src_hook,
-		flags, DMA_TO_DEVICE);
-	req_ctx->buffer = src_hook.next;
+	buf = chainup_buffers(dev, req->src, crypt->auth_len,
+			      &src_hook, flags, src_direction);
+	req_ctx->src = src_hook.next;
 	crypt->src_buf = src_hook.phys_next;
 	if (!buf)
-		goto out;
-	/* IV */
-	sg_init_table(&req_ctx->ivlist, 1);
-	sg_set_buf(&req_ctx->ivlist, iv, ivsize);
-	buf = chainup_buffers(dev, &req_ctx->ivlist, ivsize, buf, flags,
-			DMA_BIDIRECTIONAL);
-	if (!buf)
-		goto free_chain;
-	if (unlikely(hmac_inconsistent(req->src, cryptlen, authsize))) {
+		goto free_buf_src;
+
+	if (!encrypt || !req_ctx->dst) {
+		lastlen = buf->buf_len;
+		if (lastlen >= authsize)
+			crypt->icv_rev_aes = buf->phys_addr +
+					     buf->buf_len - authsize;
+	}
+
+	if (unlikely(lastlen < authsize)) {
 		/* The 12 hmac bytes are scattered,
 		 * we need to copy them into a safe buffer */
 		req_ctx->hmac_virt = dma_pool_alloc(buffer_pool, flags,
 				&crypt->icv_rev_aes);
 		if (unlikely(!req_ctx->hmac_virt))
-			goto free_chain;
+			goto free_buf_src;
 		if (!encrypt) {
 			scatterwalk_map_and_copy(req_ctx->hmac_virt,
 				req->src, cryptlen, authsize, 0);
@@ -1068,27 +1086,16 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	} else {
 		req_ctx->hmac_virt = NULL;
 	}
-	/* Crypt */
-	buf = chainup_buffers(dev, req->src, cryptlen + authsize, buf, flags,
-			DMA_BIDIRECTIONAL);
-	if (!buf)
-		goto free_hmac_virt;
-	if (!req_ctx->hmac_virt) {
-		crypt->icv_rev_aes = buf->phys_addr + buf->buf_len - authsize;
-	}
 
 	crypt->ctl_flags |= CTL_FLAG_PERFORM_AEAD;
 	qmgr_put_entry(SEND_QID, crypt_virt2phys(crypt));
 	BUG_ON(qmgr_stat_overflow(SEND_QID));
 	return -EINPROGRESS;
-free_hmac_virt:
-	if (req_ctx->hmac_virt) {
-		dma_pool_free(buffer_pool, req_ctx->hmac_virt,
-				crypt->icv_rev_aes);
-	}
-free_chain:
-	free_buf_chain(dev, req_ctx->buffer, crypt->src_buf);
-out:
+
+free_buf_src:
+	free_buf_chain(dev, req_ctx->src, crypt->src_buf);
+free_buf_dst:
+	free_buf_chain(dev, req_ctx->dst, crypt->dst_buf);
 	crypt->ctl_flags = CTL_FLAG_UNUSED;
 	return -ENOMEM;
 }
@@ -1174,40 +1181,12 @@ badkey:
 
 static int aead_encrypt(struct aead_request *req)
 {
-	unsigned ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(req));
-	return aead_perform(req, 1, req->assoclen + ivsize,
-			req->cryptlen, req->iv);
+	return aead_perform(req, 1, req->assoclen, req->cryptlen, req->iv);
 }
 
 static int aead_decrypt(struct aead_request *req)
 {
-	unsigned ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(req));
-	return aead_perform(req, 0, req->assoclen + ivsize,
-			req->cryptlen, req->iv);
-}
-
-static int aead_givencrypt(struct aead_givcrypt_request *req)
-{
-	struct crypto_aead *tfm = aead_givcrypt_reqtfm(req);
-	struct ixp_ctx *ctx = crypto_aead_ctx(tfm);
-	unsigned len, ivsize = crypto_aead_ivsize(tfm);
-	__be64 seq;
-
-	/* copied from eseqiv.c */
-	if (!ctx->salted) {
-		get_random_bytes(ctx->salt, ivsize);
-		ctx->salted = 1;
-	}
-	memcpy(req->areq.iv, ctx->salt, ivsize);
-	len = ivsize;
-	if (ivsize > sizeof(u64)) {
-		memset(req->giv, 0, ivsize - sizeof(u64));
-		len = sizeof(u64);
-	}
-	seq = cpu_to_be64(req->seq);
-	memcpy(req->giv + ivsize - len, &seq, len);
-	return aead_perform(&req->areq, 1, req->areq.assoclen,
-			req->areq.cryptlen +ivsize, req->giv);
+	return aead_perform(req, 0, req->assoclen, req->cryptlen, req->iv);
 }
 
 static struct ixp_alg ixp4xx_algos[] = {
@@ -1320,80 +1299,77 @@ static struct ixp_alg ixp4xx_algos[] = {
 	},
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_CTR,
 	.cfg_dec = CIPH_ENCR | MOD_AES | MOD_CTR,
-}, {
+} };
+
+static struct ixp_aead_alg ixp4xx_aeads[] = {
+{
 	.crypto	= {
-		.cra_name	= "authenc(hmac(md5),cbc(des))",
-		.cra_blocksize	= DES_BLOCK_SIZE,
-		.cra_u		= { .aead = {
-			.ivsize		= DES_BLOCK_SIZE,
-			.maxauthsize	= MD5_DIGEST_SIZE,
-			}
-		}
+		.base = {
+			.cra_name	= "authenc(hmac(md5),cbc(des))",
+			.cra_blocksize	= DES_BLOCK_SIZE,
+		},
+		.ivsize		= DES_BLOCK_SIZE,
+		.maxauthsize	= MD5_DIGEST_SIZE,
 	},
 	.hash = &hash_alg_md5,
 	.cfg_enc = CIPH_ENCR | MOD_DES | MOD_CBC_ENC | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_DES | MOD_CBC_DEC | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "authenc(hmac(md5),cbc(des3_ede))",
-		.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-		.cra_u		= { .aead = {
-			.ivsize		= DES3_EDE_BLOCK_SIZE,
-			.maxauthsize	= MD5_DIGEST_SIZE,
-			}
-		}
+		.base = {
+			.cra_name	= "authenc(hmac(md5),cbc(des3_ede))",
+			.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+		},
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.maxauthsize	= MD5_DIGEST_SIZE,
 	},
 	.hash = &hash_alg_md5,
 	.cfg_enc = CIPH_ENCR | MOD_3DES | MOD_CBC_ENC | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_3DES | MOD_CBC_DEC | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "authenc(hmac(sha1),cbc(des))",
-		.cra_blocksize	= DES_BLOCK_SIZE,
-		.cra_u		= { .aead = {
+		.base = {
+			.cra_name	= "authenc(hmac(sha1),cbc(des))",
+			.cra_blocksize	= DES_BLOCK_SIZE,
+		},
 			.ivsize		= DES_BLOCK_SIZE,
 			.maxauthsize	= SHA1_DIGEST_SIZE,
-			}
-		}
 	},
 	.hash = &hash_alg_sha1,
 	.cfg_enc = CIPH_ENCR | MOD_DES | MOD_CBC_ENC | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_DES | MOD_CBC_DEC | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "authenc(hmac(sha1),cbc(des3_ede))",
-		.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-		.cra_u		= { .aead = {
-			.ivsize		= DES3_EDE_BLOCK_SIZE,
-			.maxauthsize	= SHA1_DIGEST_SIZE,
-			}
-		}
+		.base = {
+			.cra_name	= "authenc(hmac(sha1),cbc(des3_ede))",
+			.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+		},
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.maxauthsize	= SHA1_DIGEST_SIZE,
 	},
 	.hash = &hash_alg_sha1,
 	.cfg_enc = CIPH_ENCR | MOD_3DES | MOD_CBC_ENC | KEYLEN_192,
 	.cfg_dec = CIPH_DECR | MOD_3DES | MOD_CBC_DEC | KEYLEN_192,
 }, {
 	.crypto	= {
-		.cra_name	= "authenc(hmac(md5),cbc(aes))",
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_u		= { .aead = {
-			.ivsize		= AES_BLOCK_SIZE,
-			.maxauthsize	= MD5_DIGEST_SIZE,
-			}
-		}
+		.base = {
+			.cra_name	= "authenc(hmac(md5),cbc(aes))",
+			.cra_blocksize	= AES_BLOCK_SIZE,
+		},
+		.ivsize		= AES_BLOCK_SIZE,
+		.maxauthsize	= MD5_DIGEST_SIZE,
 	},
 	.hash = &hash_alg_md5,
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_CBC_ENC,
 	.cfg_dec = CIPH_DECR | MOD_AES | MOD_CBC_DEC,
 }, {
 	.crypto	= {
-		.cra_name	= "authenc(hmac(sha1),cbc(aes))",
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_u		= { .aead = {
-			.ivsize		= AES_BLOCK_SIZE,
-			.maxauthsize	= SHA1_DIGEST_SIZE,
-			}
-		}
+		.base = {
+			.cra_name	= "authenc(hmac(sha1),cbc(aes))",
+			.cra_blocksize	= AES_BLOCK_SIZE,
+		},
+		.ivsize		= AES_BLOCK_SIZE,
+		.maxauthsize	= SHA1_DIGEST_SIZE,
 	},
 	.hash = &hash_alg_sha1,
 	.cfg_enc = CIPH_ENCR | MOD_AES | MOD_CBC_ENC,
@@ -1437,32 +1413,20 @@ static int __init ixp_module_init(void)
 		if (!support_aes && (ixp4xx_algos[i].cfg_enc & MOD_AES)) {
 			continue;
 		}
-		if (!ixp4xx_algos[i].hash) {
-			/* block ciphers */
-			cra->cra_type = &crypto_ablkcipher_type;
-			cra->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-					 CRYPTO_ALG_KERN_DRIVER_ONLY |
-					 CRYPTO_ALG_ASYNC;
-			if (!cra->cra_ablkcipher.setkey)
-				cra->cra_ablkcipher.setkey = ablk_setkey;
-			if (!cra->cra_ablkcipher.encrypt)
-				cra->cra_ablkcipher.encrypt = ablk_encrypt;
-			if (!cra->cra_ablkcipher.decrypt)
-				cra->cra_ablkcipher.decrypt = ablk_decrypt;
-			cra->cra_init = init_tfm_ablk;
-		} else {
-			/* authenc */
-			cra->cra_type = &crypto_aead_type;
-			cra->cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					 CRYPTO_ALG_KERN_DRIVER_ONLY |
-					 CRYPTO_ALG_ASYNC;
-			cra->cra_aead.setkey = aead_setkey;
-			cra->cra_aead.setauthsize = aead_setauthsize;
-			cra->cra_aead.encrypt = aead_encrypt;
-			cra->cra_aead.decrypt = aead_decrypt;
-			cra->cra_aead.givencrypt = aead_givencrypt;
-			cra->cra_init = init_tfm_aead;
-		}
+
+		/* block ciphers */
+		cra->cra_type = &crypto_ablkcipher_type;
+		cra->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+				 CRYPTO_ALG_KERN_DRIVER_ONLY |
+				 CRYPTO_ALG_ASYNC;
+		if (!cra->cra_ablkcipher.setkey)
+			cra->cra_ablkcipher.setkey = ablk_setkey;
+		if (!cra->cra_ablkcipher.encrypt)
+			cra->cra_ablkcipher.encrypt = ablk_encrypt;
+		if (!cra->cra_ablkcipher.decrypt)
+			cra->cra_ablkcipher.decrypt = ablk_decrypt;
+		cra->cra_init = init_tfm_ablk;
+
 		cra->cra_ctxsize = sizeof(struct ixp_ctx);
 		cra->cra_module = THIS_MODULE;
 		cra->cra_alignmask = 3;
@@ -1474,6 +1438,38 @@ static int __init ixp_module_init(void)
 		else
 			ixp4xx_algos[i].registered = 1;
 	}
+
+	for (i = 0; i < ARRAY_SIZE(ixp4xx_aeads); i++) {
+		struct aead_alg *cra = &ixp4xx_aeads[i].crypto;
+
+		if (snprintf(cra->base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+			     "%s"IXP_POSTFIX, cra->base.cra_name) >=
+		    CRYPTO_MAX_ALG_NAME)
+			continue;
+		if (!support_aes && (ixp4xx_algos[i].cfg_enc & MOD_AES))
+			continue;
+
+		/* authenc */
+		cra->base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY |
+				      CRYPTO_ALG_ASYNC;
+		cra->setkey = aead_setkey;
+		cra->setauthsize = aead_setauthsize;
+		cra->encrypt = aead_encrypt;
+		cra->decrypt = aead_decrypt;
+		cra->init = init_tfm_aead;
+		cra->exit = exit_tfm_aead;
+
+		cra->base.cra_ctxsize = sizeof(struct ixp_ctx);
+		cra->base.cra_module = THIS_MODULE;
+		cra->base.cra_alignmask = 3;
+		cra->base.cra_priority = 300;
+
+		if (crypto_register_aead(cra))
+			printk(KERN_ERR "Failed to register '%s'\n",
+				cra->base.cra_driver_name);
+		else
+			ixp4xx_aeads[i].registered = 1;
+	}
 	return 0;
 }
 
@@ -1482,6 +1478,11 @@ static void __exit ixp_module_exit(void)
 	int num = ARRAY_SIZE(ixp4xx_algos);
 	int i;
 
+	for (i = 0; i < ARRAY_SIZE(ixp4xx_aeads); i++) {
+		if (ixp4xx_aeads[i].registered)
+			crypto_unregister_aead(&ixp4xx_aeads[i].crypto);
+	}
+
 	for (i=0; i< num; i++) {
 		if (ixp4xx_algos[i].registered)
 			crypto_unregister_alg(&ixp4xx_algos[i].crypto);
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index 1c6f98dd88f4..0643e3366e33 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -533,7 +533,6 @@ static struct platform_driver marvell_cesa = {
 	.probe		= mv_cesa_probe,
 	.remove		= mv_cesa_remove,
 	.driver		= {
-		.owner	= THIS_MODULE,
 		.name	= "marvell-cesa",
 		.of_match_table = mv_cesa_of_match_table,
 	},
diff --git a/drivers/crypto/nx/Kconfig b/drivers/crypto/nx/Kconfig
index e421c96c763a..ad7552a6998c 100644
--- a/drivers/crypto/nx/Kconfig
+++ b/drivers/crypto/nx/Kconfig
@@ -14,11 +14,14 @@ config CRYPTO_DEV_NX_ENCRYPT
 config CRYPTO_DEV_NX_COMPRESS
 	tristate "Compression acceleration support"
 	default y
+	select CRYPTO_ALGAPI
+	select 842_DECOMPRESS
 	help
 	  Support for PowerPC Nest (NX) compression acceleration. This
 	  module supports acceleration for compressing memory with the 842
-	  algorithm.  One of the platform drivers must be selected also.
-	  If you choose 'M' here, this module will be called nx_compress.
+	  algorithm using the cryptographic API.  One of the platform
+	  drivers must be selected also.  If you choose 'M' here, this
+	  module will be called nx_compress.
 
 if CRYPTO_DEV_NX_COMPRESS
 
@@ -42,14 +45,4 @@ config CRYPTO_DEV_NX_COMPRESS_POWERNV
 	  algorithm.  This supports NX hardware on the PowerNV platform.
 	  If you choose 'M' here, this module will be called nx_compress_powernv.
 
-config CRYPTO_DEV_NX_COMPRESS_CRYPTO
-	tristate "Compression acceleration cryptographic interface"
-	select CRYPTO_ALGAPI
-	select 842_DECOMPRESS
-	default y
-	help
-	  Support for PowerPC Nest (NX) accelerators using the cryptographic
-	  API.  If you choose 'M' here, this module will be called
-	  nx_compress_crypto.
-
 endif
diff --git a/drivers/crypto/nx/Makefile b/drivers/crypto/nx/Makefile
index e1684f5adb11..b727821c8ed4 100644
--- a/drivers/crypto/nx/Makefile
+++ b/drivers/crypto/nx/Makefile
@@ -10,12 +10,8 @@ nx-crypto-objs := nx.o \
 		  nx-sha256.o \
 		  nx-sha512.o
 
-obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS) += nx-compress.o nx-compress-platform.o
-obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_PSERIES) += nx-compress-pseries.o
-obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_POWERNV) += nx-compress-powernv.o
-obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_CRYPTO) += nx-compress-crypto.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_PSERIES) += nx-compress-pseries.o nx-compress.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_POWERNV) += nx-compress-powernv.o nx-compress.o
 nx-compress-objs := nx-842.o
-nx-compress-platform-objs := nx-842-platform.o
 nx-compress-pseries-objs := nx-842-pseries.o
 nx-compress-powernv-objs := nx-842-powernv.o
-nx-compress-crypto-objs := nx-842-crypto.o
diff --git a/drivers/crypto/nx/nx-842-crypto.c b/drivers/crypto/nx/nx-842-crypto.c
deleted file mode 100644
index d53a1dcd7b4e..000000000000
--- a/drivers/crypto/nx/nx-842-crypto.c
+++ /dev/null
@@ -1,580 +0,0 @@
-/*
- * Cryptographic API for the NX-842 hardware compression.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Copyright (C) IBM Corporation, 2011-2015
- *
- * Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
- *                   Seth Jennings <sjenning@linux.vnet.ibm.com>
- *
- * Rewrite: Dan Streetman <ddstreet@ieee.org>
- *
- * This is an interface to the NX-842 compression hardware in PowerPC
- * processors.  Most of the complexity of this drvier is due to the fact that
- * the NX-842 compression hardware requires the input and output data buffers
- * to be specifically aligned, to be a specific multiple in length, and within
- * specific minimum and maximum lengths.  Those restrictions, provided by the
- * nx-842 driver via nx842_constraints, mean this driver must use bounce
- * buffers and headers to correct misaligned in or out buffers, and to split
- * input buffers that are too large.
- *
- * This driver will fall back to software decompression if the hardware
- * decompression fails, so this driver's decompression should never fail as
- * long as the provided compressed buffer is valid.  Any compressed buffer
- * created by this driver will have a header (except ones where the input
- * perfectly matches the constraints); so users of this driver cannot simply
- * pass a compressed buffer created by this driver over to the 842 software
- * decompression library.  Instead, users must use this driver to decompress;
- * if the hardware fails or is unavailable, the compressed buffer will be
- * parsed and the header removed, and the raw 842 buffer(s) passed to the 842
- * software decompression library.
- *
- * This does not fall back to software compression, however, since the caller
- * of this function is specifically requesting hardware compression; if the
- * hardware compression fails, the caller can fall back to software
- * compression, and the raw 842 compressed buffer that the software compressor
- * creates can be passed to this driver for hardware decompression; any
- * buffer without our specific header magic is assumed to be a raw 842 buffer
- * and passed directly to the hardware.  Note that the software compression
- * library will produce a compressed buffer that is incompatible with the
- * hardware decompressor if the original input buffer length is not a multiple
- * of 8; if such a compressed buffer is passed to this driver for
- * decompression, the hardware will reject it and this driver will then pass
- * it over to the software library for decompression.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/crypto.h>
-#include <linux/vmalloc.h>
-#include <linux/sw842.h>
-#include <linux/ratelimit.h>
-
-#include "nx-842.h"
-
-/* The first 5 bits of this magic are 0x1f, which is an invalid 842 5-bit
- * template (see lib/842/842.h), so this magic number will never appear at
- * the start of a raw 842 compressed buffer.  That is important, as any buffer
- * passed to us without this magic is assumed to be a raw 842 compressed
- * buffer, and passed directly to the hardware to decompress.
- */
-#define NX842_CRYPTO_MAGIC	(0xf842)
-#define NX842_CRYPTO_GROUP_MAX	(0x20)
-#define NX842_CRYPTO_HEADER_SIZE(g)				\
-	(sizeof(struct nx842_crypto_header) +			\
-	 sizeof(struct nx842_crypto_header_group) * (g))
-#define NX842_CRYPTO_HEADER_MAX_SIZE				\
-	NX842_CRYPTO_HEADER_SIZE(NX842_CRYPTO_GROUP_MAX)
-
-/* bounce buffer size */
-#define BOUNCE_BUFFER_ORDER	(2)
-#define BOUNCE_BUFFER_SIZE					\
-	((unsigned int)(PAGE_SIZE << BOUNCE_BUFFER_ORDER))
-
-/* try longer on comp because we can fallback to sw decomp if hw is busy */
-#define COMP_BUSY_TIMEOUT	(250) /* ms */
-#define DECOMP_BUSY_TIMEOUT	(50) /* ms */
-
-struct nx842_crypto_header_group {
-	__be16 padding;			/* unused bytes at start of group */
-	__be32 compressed_length;	/* compressed bytes in group */
-	__be32 uncompressed_length;	/* bytes after decompression */
-} __packed;
-
-struct nx842_crypto_header {
-	__be16 magic;		/* NX842_CRYPTO_MAGIC */
-	__be16 ignore;		/* decompressed end bytes to ignore */
-	u8 groups;		/* total groups in this header */
-	struct nx842_crypto_header_group group[];
-} __packed;
-
-struct nx842_crypto_param {
-	u8 *in;
-	unsigned int iremain;
-	u8 *out;
-	unsigned int oremain;
-	unsigned int ototal;
-};
-
-static int update_param(struct nx842_crypto_param *p,
-			unsigned int slen, unsigned int dlen)
-{
-	if (p->iremain < slen)
-		return -EOVERFLOW;
-	if (p->oremain < dlen)
-		return -ENOSPC;
-
-	p->in += slen;
-	p->iremain -= slen;
-	p->out += dlen;
-	p->oremain -= dlen;
-	p->ototal += dlen;
-
-	return 0;
-}
-
-struct nx842_crypto_ctx {
-	u8 *wmem;
-	u8 *sbounce, *dbounce;
-
-	struct nx842_crypto_header header;
-	struct nx842_crypto_header_group group[NX842_CRYPTO_GROUP_MAX];
-};
-
-static int nx842_crypto_init(struct crypto_tfm *tfm)
-{
-	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	ctx->wmem = kmalloc(nx842_workmem_size(), GFP_KERNEL);
-	ctx->sbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
-	ctx->dbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
-	if (!ctx->wmem || !ctx->sbounce || !ctx->dbounce) {
-		kfree(ctx->wmem);
-		free_page((unsigned long)ctx->sbounce);
-		free_page((unsigned long)ctx->dbounce);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void nx842_crypto_exit(struct crypto_tfm *tfm)
-{
-	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	kfree(ctx->wmem);
-	free_page((unsigned long)ctx->sbounce);
-	free_page((unsigned long)ctx->dbounce);
-}
-
-static int read_constraints(struct nx842_constraints *c)
-{
-	int ret;
-
-	ret = nx842_constraints(c);
-	if (ret) {
-		pr_err_ratelimited("could not get nx842 constraints : %d\n",
-				   ret);
-		return ret;
-	}
-
-	/* limit maximum, to always have enough bounce buffer to decompress */
-	if (c->maximum > BOUNCE_BUFFER_SIZE) {
-		c->maximum = BOUNCE_BUFFER_SIZE;
-		pr_info_once("limiting nx842 maximum to %x\n", c->maximum);
-	}
-
-	return 0;
-}
-
-static int nx842_crypto_add_header(struct nx842_crypto_header *hdr, u8 *buf)
-{
-	int s = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
-
-	/* compress should have added space for header */
-	if (s > be16_to_cpu(hdr->group[0].padding)) {
-		pr_err("Internal error: no space for header\n");
-		return -EINVAL;
-	}
-
-	memcpy(buf, hdr, s);
-
-	print_hex_dump_debug("header ", DUMP_PREFIX_OFFSET, 16, 1, buf, s, 0);
-
-	return 0;
-}
-
-static int compress(struct nx842_crypto_ctx *ctx,
-		    struct nx842_crypto_param *p,
-		    struct nx842_crypto_header_group *g,
-		    struct nx842_constraints *c,
-		    u16 *ignore,
-		    unsigned int hdrsize)
-{
-	unsigned int slen = p->iremain, dlen = p->oremain, tmplen;
-	unsigned int adj_slen = slen;
-	u8 *src = p->in, *dst = p->out;
-	int ret, dskip = 0;
-	ktime_t timeout;
-
-	if (p->iremain == 0)
-		return -EOVERFLOW;
-
-	if (p->oremain == 0 || hdrsize + c->minimum > dlen)
-		return -ENOSPC;
-
-	if (slen % c->multiple)
-		adj_slen = round_up(slen, c->multiple);
-	if (slen < c->minimum)
-		adj_slen = c->minimum;
-	if (slen > c->maximum)
-		adj_slen = slen = c->maximum;
-	if (adj_slen > slen || (u64)src % c->alignment) {
-		adj_slen = min(adj_slen, BOUNCE_BUFFER_SIZE);
-		slen = min(slen, BOUNCE_BUFFER_SIZE);
-		if (adj_slen > slen)
-			memset(ctx->sbounce + slen, 0, adj_slen - slen);
-		memcpy(ctx->sbounce, src, slen);
-		src = ctx->sbounce;
-		slen = adj_slen;
-		pr_debug("using comp sbounce buffer, len %x\n", slen);
-	}
-
-	dst += hdrsize;
-	dlen -= hdrsize;
-
-	if ((u64)dst % c->alignment) {
-		dskip = (int)(PTR_ALIGN(dst, c->alignment) - dst);
-		dst += dskip;
-		dlen -= dskip;
-	}
-	if (dlen % c->multiple)
-		dlen = round_down(dlen, c->multiple);
-	if (dlen < c->minimum) {
-nospc:
-		dst = ctx->dbounce;
-		dlen = min(p->oremain, BOUNCE_BUFFER_SIZE);
-		dlen = round_down(dlen, c->multiple);
-		dskip = 0;
-		pr_debug("using comp dbounce buffer, len %x\n", dlen);
-	}
-	if (dlen > c->maximum)
-		dlen = c->maximum;
-
-	tmplen = dlen;
-	timeout = ktime_add_ms(ktime_get(), COMP_BUSY_TIMEOUT);
-	do {
-		dlen = tmplen; /* reset dlen, if we're retrying */
-		ret = nx842_compress(src, slen, dst, &dlen, ctx->wmem);
-		/* possibly we should reduce the slen here, instead of
-		 * retrying with the dbounce buffer?
-		 */
-		if (ret == -ENOSPC && dst != ctx->dbounce)
-			goto nospc;
-	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
-	if (ret)
-		return ret;
-
-	dskip += hdrsize;
-
-	if (dst == ctx->dbounce)
-		memcpy(p->out + dskip, dst, dlen);
-
-	g->padding = cpu_to_be16(dskip);
-	g->compressed_length = cpu_to_be32(dlen);
-	g->uncompressed_length = cpu_to_be32(slen);
-
-	if (p->iremain < slen) {
-		*ignore = slen - p->iremain;
-		slen = p->iremain;
-	}
-
-	pr_debug("compress slen %x ignore %x dlen %x padding %x\n",
-		 slen, *ignore, dlen, dskip);
-
-	return update_param(p, slen, dskip + dlen);
-}
-
-static int nx842_crypto_compress(struct crypto_tfm *tfm,
-				 const u8 *src, unsigned int slen,
-				 u8 *dst, unsigned int *dlen)
-{
-	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct nx842_crypto_header *hdr = &ctx->header;
-	struct nx842_crypto_param p;
-	struct nx842_constraints c;
-	unsigned int groups, hdrsize, h;
-	int ret, n;
-	bool add_header;
-	u16 ignore = 0;
-
-	p.in = (u8 *)src;
-	p.iremain = slen;
-	p.out = dst;
-	p.oremain = *dlen;
-	p.ototal = 0;
-
-	*dlen = 0;
-
-	ret = read_constraints(&c);
-	if (ret)
-		return ret;
-
-	groups = min_t(unsigned int, NX842_CRYPTO_GROUP_MAX,
-		       DIV_ROUND_UP(p.iremain, c.maximum));
-	hdrsize = NX842_CRYPTO_HEADER_SIZE(groups);
-
-	/* skip adding header if the buffers meet all constraints */
-	add_header = (p.iremain % c.multiple	||
-		      p.iremain < c.minimum	||
-		      p.iremain > c.maximum	||
-		      (u64)p.in % c.alignment	||
-		      p.oremain % c.multiple	||
-		      p.oremain < c.minimum	||
-		      p.oremain > c.maximum	||
-		      (u64)p.out % c.alignment);
-
-	hdr->magic = cpu_to_be16(NX842_CRYPTO_MAGIC);
-	hdr->groups = 0;
-	hdr->ignore = 0;
-
-	while (p.iremain > 0) {
-		n = hdr->groups++;
-		if (hdr->groups > NX842_CRYPTO_GROUP_MAX)
-			return -ENOSPC;
-
-		/* header goes before first group */
-		h = !n && add_header ? hdrsize : 0;
-
-		if (ignore)
-			pr_warn("interal error, ignore is set %x\n", ignore);
-
-		ret = compress(ctx, &p, &hdr->group[n], &c, &ignore, h);
-		if (ret)
-			return ret;
-	}
-
-	if (!add_header && hdr->groups > 1) {
-		pr_err("Internal error: No header but multiple groups\n");
-		return -EINVAL;
-	}
-
-	/* ignore indicates the input stream needed to be padded */
-	hdr->ignore = cpu_to_be16(ignore);
-	if (ignore)
-		pr_debug("marked %d bytes as ignore\n", ignore);
-
-	if (add_header)
-		ret = nx842_crypto_add_header(hdr, dst);
-	if (ret)
-		return ret;
-
-	*dlen = p.ototal;
-
-	pr_debug("compress total slen %x dlen %x\n", slen, *dlen);
-
-	return 0;
-}
-
-static int decompress(struct nx842_crypto_ctx *ctx,
-		      struct nx842_crypto_param *p,
-		      struct nx842_crypto_header_group *g,
-		      struct nx842_constraints *c,
-		      u16 ignore,
-		      bool usehw)
-{
-	unsigned int slen = be32_to_cpu(g->compressed_length);
-	unsigned int required_len = be32_to_cpu(g->uncompressed_length);
-	unsigned int dlen = p->oremain, tmplen;
-	unsigned int adj_slen = slen;
-	u8 *src = p->in, *dst = p->out;
-	u16 padding = be16_to_cpu(g->padding);
-	int ret, spadding = 0, dpadding = 0;
-	ktime_t timeout;
-
-	if (!slen || !required_len)
-		return -EINVAL;
-
-	if (p->iremain <= 0 || padding + slen > p->iremain)
-		return -EOVERFLOW;
-
-	if (p->oremain <= 0 || required_len - ignore > p->oremain)
-		return -ENOSPC;
-
-	src += padding;
-
-	if (!usehw)
-		goto usesw;
-
-	if (slen % c->multiple)
-		adj_slen = round_up(slen, c->multiple);
-	if (slen < c->minimum)
-		adj_slen = c->minimum;
-	if (slen > c->maximum)
-		goto usesw;
-	if (slen < adj_slen || (u64)src % c->alignment) {
-		/* we can append padding bytes because the 842 format defines
-		 * an "end" template (see lib/842/842_decompress.c) and will
-		 * ignore any bytes following it.
-		 */
-		if (slen < adj_slen)
-			memset(ctx->sbounce + slen, 0, adj_slen - slen);
-		memcpy(ctx->sbounce, src, slen);
-		src = ctx->sbounce;
-		spadding = adj_slen - slen;
-		slen = adj_slen;
-		pr_debug("using decomp sbounce buffer, len %x\n", slen);
-	}
-
-	if (dlen % c->multiple)
-		dlen = round_down(dlen, c->multiple);
-	if (dlen < required_len || (u64)dst % c->alignment) {
-		dst = ctx->dbounce;
-		dlen = min(required_len, BOUNCE_BUFFER_SIZE);
-		pr_debug("using decomp dbounce buffer, len %x\n", dlen);
-	}
-	if (dlen < c->minimum)
-		goto usesw;
-	if (dlen > c->maximum)
-		dlen = c->maximum;
-
-	tmplen = dlen;
-	timeout = ktime_add_ms(ktime_get(), DECOMP_BUSY_TIMEOUT);
-	do {
-		dlen = tmplen; /* reset dlen, if we're retrying */
-		ret = nx842_decompress(src, slen, dst, &dlen, ctx->wmem);
-	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
-	if (ret) {
-usesw:
-		/* reset everything, sw doesn't have constraints */
-		src = p->in + padding;
-		slen = be32_to_cpu(g->compressed_length);
-		spadding = 0;
-		dst = p->out;
-		dlen = p->oremain;
-		dpadding = 0;
-		if (dlen < required_len) { /* have ignore bytes */
-			dst = ctx->dbounce;
-			dlen = BOUNCE_BUFFER_SIZE;
-		}
-		pr_info_ratelimited("using software 842 decompression\n");
-		ret = sw842_decompress(src, slen, dst, &dlen);
-	}
-	if (ret)
-		return ret;
-
-	slen -= spadding;
-
-	dlen -= ignore;
-	if (ignore)
-		pr_debug("ignoring last %x bytes\n", ignore);
-
-	if (dst == ctx->dbounce)
-		memcpy(p->out, dst, dlen);
-
-	pr_debug("decompress slen %x padding %x dlen %x ignore %x\n",
-		 slen, padding, dlen, ignore);
-
-	return update_param(p, slen + padding, dlen);
-}
-
-static int nx842_crypto_decompress(struct crypto_tfm *tfm,
-				   const u8 *src, unsigned int slen,
-				   u8 *dst, unsigned int *dlen)
-{
-	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct nx842_crypto_header *hdr;
-	struct nx842_crypto_param p;
-	struct nx842_constraints c;
-	int n, ret, hdr_len;
-	u16 ignore = 0;
-	bool usehw = true;
-
-	p.in = (u8 *)src;
-	p.iremain = slen;
-	p.out = dst;
-	p.oremain = *dlen;
-	p.ototal = 0;
-
-	*dlen = 0;
-
-	if (read_constraints(&c))
-		usehw = false;
-
-	hdr = (struct nx842_crypto_header *)src;
-
-	/* If it doesn't start with our header magic number, assume it's a raw
-	 * 842 compressed buffer and pass it directly to the hardware driver
-	 */
-	if (be16_to_cpu(hdr->magic) != NX842_CRYPTO_MAGIC) {
-		struct nx842_crypto_header_group g = {
-			.padding =		0,
-			.compressed_length =	cpu_to_be32(p.iremain),
-			.uncompressed_length =	cpu_to_be32(p.oremain),
-		};
-
-		ret = decompress(ctx, &p, &g, &c, 0, usehw);
-		if (ret)
-			return ret;
-
-		*dlen = p.ototal;
-
-		return 0;
-	}
-
-	if (!hdr->groups) {
-		pr_err("header has no groups\n");
-		return -EINVAL;
-	}
-	if (hdr->groups > NX842_CRYPTO_GROUP_MAX) {
-		pr_err("header has too many groups %x, max %x\n",
-		       hdr->groups, NX842_CRYPTO_GROUP_MAX);
-		return -EINVAL;
-	}
-
-	hdr_len = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
-	if (hdr_len > slen)
-		return -EOVERFLOW;
-
-	memcpy(&ctx->header, src, hdr_len);
-	hdr = &ctx->header;
-
-	for (n = 0; n < hdr->groups; n++) {
-		/* ignore applies to last group */
-		if (n + 1 == hdr->groups)
-			ignore = be16_to_cpu(hdr->ignore);
-
-		ret = decompress(ctx, &p, &hdr->group[n], &c, ignore, usehw);
-		if (ret)
-			return ret;
-	}
-
-	*dlen = p.ototal;
-
-	pr_debug("decompress total slen %x dlen %x\n", slen, *dlen);
-
-	return 0;
-}
-
-static struct crypto_alg alg = {
-	.cra_name		= "842",
-	.cra_driver_name	= "842-nx",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
-	.cra_ctxsize		= sizeof(struct nx842_crypto_ctx),
-	.cra_module		= THIS_MODULE,
-	.cra_init		= nx842_crypto_init,
-	.cra_exit		= nx842_crypto_exit,
-	.cra_u			= { .compress = {
-	.coa_compress		= nx842_crypto_compress,
-	.coa_decompress		= nx842_crypto_decompress } }
-};
-
-static int __init nx842_crypto_mod_init(void)
-{
-	return crypto_register_alg(&alg);
-}
-module_init(nx842_crypto_mod_init);
-
-static void __exit nx842_crypto_mod_exit(void)
-{
-	crypto_unregister_alg(&alg);
-}
-module_exit(nx842_crypto_mod_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("IBM PowerPC Nest (NX) 842 Hardware Compression Interface");
-MODULE_ALIAS_CRYPTO("842");
-MODULE_ALIAS_CRYPTO("842-nx");
-MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/drivers/crypto/nx/nx-842-platform.c b/drivers/crypto/nx/nx-842-platform.c
deleted file mode 100644
index 664f13dd06ed..000000000000
--- a/drivers/crypto/nx/nx-842-platform.c
+++ /dev/null
@@ -1,84 +0,0 @@
-
-#include "nx-842.h"
-
-/* this is needed, separate from the main nx-842.c driver, because that main
- * driver loads the platform drivers during its init(), and it expects one
- * (or none) of the platform drivers to set this pointer to its driver.
- * That means this pointer can't be in the main nx-842 driver, because it
- * wouldn't be accessible until after the main driver loaded, which wouldn't
- * be possible as it's waiting for the platform driver to load.  So place it
- * here.
- */
-static struct nx842_driver *driver;
-static DEFINE_SPINLOCK(driver_lock);
-
-struct nx842_driver *nx842_platform_driver(void)
-{
-	return driver;
-}
-EXPORT_SYMBOL_GPL(nx842_platform_driver);
-
-bool nx842_platform_driver_set(struct nx842_driver *_driver)
-{
-	bool ret = false;
-
-	spin_lock(&driver_lock);
-
-	if (!driver) {
-		driver = _driver;
-		ret = true;
-	} else
-		WARN(1, "can't set platform driver, already set to %s\n",
-		     driver->name);
-
-	spin_unlock(&driver_lock);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nx842_platform_driver_set);
-
-/* only call this from the platform driver exit function */
-void nx842_platform_driver_unset(struct nx842_driver *_driver)
-{
-	spin_lock(&driver_lock);
-
-	if (driver == _driver)
-		driver = NULL;
-	else if (driver)
-		WARN(1, "can't unset platform driver %s, currently set to %s\n",
-		     _driver->name, driver->name);
-	else
-		WARN(1, "can't unset platform driver, already unset\n");
-
-	spin_unlock(&driver_lock);
-}
-EXPORT_SYMBOL_GPL(nx842_platform_driver_unset);
-
-bool nx842_platform_driver_get(void)
-{
-	bool ret = false;
-
-	spin_lock(&driver_lock);
-
-	if (driver)
-		ret = try_module_get(driver->owner);
-
-	spin_unlock(&driver_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nx842_platform_driver_get);
-
-void nx842_platform_driver_put(void)
-{
-	spin_lock(&driver_lock);
-
-	if (driver)
-		module_put(driver->owner);
-
-	spin_unlock(&driver_lock);
-}
-EXPORT_SYMBOL_GPL(nx842_platform_driver_put);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
-MODULE_DESCRIPTION("842 H/W Compression platform driver");
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 33b3b0abf4ae..3750e13d8721 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -26,6 +26,8 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
 MODULE_DESCRIPTION("842 H/W Compression driver for IBM PowerNV processors");
+MODULE_ALIAS_CRYPTO("842");
+MODULE_ALIAS_CRYPTO("842-nx");
 
 #define WORKMEM_ALIGN	(CRB_ALIGN)
 #define CSB_WAIT_MAX	(5000) /* ms */
@@ -344,7 +346,8 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 	}
 
 	/* successful completion */
-	pr_debug_ratelimited("Processed %u bytes in %lu us\n", csb->count,
+	pr_debug_ratelimited("Processed %u bytes in %lu us\n",
+			     be32_to_cpu(csb->count),
 			     (unsigned long)ktime_us_delta(now, start));
 
 	return 0;
@@ -581,9 +584,29 @@ static struct nx842_driver nx842_powernv_driver = {
 	.decompress =	nx842_powernv_decompress,
 };
 
+static int nx842_powernv_crypto_init(struct crypto_tfm *tfm)
+{
+	return nx842_crypto_init(tfm, &nx842_powernv_driver);
+}
+
+static struct crypto_alg nx842_powernv_alg = {
+	.cra_name		= "842",
+	.cra_driver_name	= "842-nx",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct nx842_crypto_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_init		= nx842_powernv_crypto_init,
+	.cra_exit		= nx842_crypto_exit,
+	.cra_u			= { .compress = {
+	.coa_compress		= nx842_crypto_compress,
+	.coa_decompress		= nx842_crypto_decompress } }
+};
+
 static __init int nx842_powernv_init(void)
 {
 	struct device_node *dn;
+	int ret;
 
 	/* verify workmem size/align restrictions */
 	BUILD_BUG_ON(WORKMEM_ALIGN % CRB_ALIGN);
@@ -594,17 +617,14 @@ static __init int nx842_powernv_init(void)
 	BUILD_BUG_ON(DDE_BUFFER_ALIGN % DDE_BUFFER_SIZE_MULT);
 	BUILD_BUG_ON(DDE_BUFFER_SIZE_MULT % DDE_BUFFER_LAST_MULT);
 
-	pr_info("loading\n");
-
 	for_each_compatible_node(dn, NULL, "ibm,power-nx")
 		nx842_powernv_probe(dn);
 
-	if (!nx842_ct) {
-		pr_err("no coprocessors found\n");
+	if (!nx842_ct)
 		return -ENODEV;
-	}
 
-	if (!nx842_platform_driver_set(&nx842_powernv_driver)) {
+	ret = crypto_register_alg(&nx842_powernv_alg);
+	if (ret) {
 		struct nx842_coproc *coproc, *n;
 
 		list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
@@ -612,11 +632,9 @@ static __init int nx842_powernv_init(void)
 			kfree(coproc);
 		}
 
-		return -EEXIST;
+		return ret;
 	}
 
-	pr_info("loaded\n");
-
 	return 0;
 }
 module_init(nx842_powernv_init);
@@ -625,13 +643,11 @@ static void __exit nx842_powernv_exit(void)
 {
 	struct nx842_coproc *coproc, *n;
 
-	nx842_platform_driver_unset(&nx842_powernv_driver);
+	crypto_unregister_alg(&nx842_powernv_alg);
 
 	list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
 		list_del(&coproc->list);
 		kfree(coproc);
 	}
-
-	pr_info("unloaded\n");
 }
 module_exit(nx842_powernv_exit);
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 3040a6091bf2..f4cbde03c6ad 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -29,6 +29,8 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Robert Jennings <rcj@linux.vnet.ibm.com>");
 MODULE_DESCRIPTION("842 H/W Compression driver for IBM Power processors");
+MODULE_ALIAS_CRYPTO("842");
+MODULE_ALIAS_CRYPTO("842-nx");
 
 static struct nx842_constraints nx842_pseries_constraints = {
 	.alignment =	DDE_BUFFER_ALIGN,
@@ -99,11 +101,6 @@ struct nx842_workmem {
 #define NX842_HW_PAGE_SIZE	(4096)
 #define NX842_HW_PAGE_MASK	(~(NX842_HW_PAGE_SIZE-1))
 
-enum nx842_status {
-	UNAVAILABLE,
-	AVAILABLE
-};
-
 struct ibm_nx842_counters {
 	atomic64_t comp_complete;
 	atomic64_t comp_failed;
@@ -121,7 +118,6 @@ static struct nx842_devdata {
 	unsigned int max_sg_len;
 	unsigned int max_sync_size;
 	unsigned int max_sync_sg;
-	enum nx842_status status;
 } __rcu *devdata;
 static DEFINE_SPINLOCK(devdata_mutex);
 
@@ -230,9 +226,12 @@ static int nx842_validate_result(struct device *dev,
 	switch (csb->completion_code) {
 	case 0:	/* Completed without error */
 		break;
-	case 64: /* Target bytes > Source bytes during compression */
+	case 64: /* Compression ok, but output larger than input */
+		dev_dbg(dev, "%s: output size larger than input size\n",
+					__func__);
+		break;
 	case 13: /* Output buffer too small */
-		dev_dbg(dev, "%s: Compression output larger than input\n",
+		dev_dbg(dev, "%s: Out of space in output buffer\n",
 					__func__);
 		return -ENOSPC;
 	case 66: /* Input data contains an illegal template field */
@@ -537,41 +536,36 @@ static int nx842_OF_set_defaults(struct nx842_devdata *devdata)
 		devdata->max_sync_size = 0;
 		devdata->max_sync_sg = 0;
 		devdata->max_sg_len = 0;
-		devdata->status = UNAVAILABLE;
 		return 0;
 	} else
 		return -ENOENT;
 }
 
 /**
- * nx842_OF_upd_status -- Update the device info from OF status prop
+ * nx842_OF_upd_status -- Check the device info from OF status prop
  *
  * The status property indicates if the accelerator is enabled.  If the
  * device is in the OF tree it indicates that the hardware is present.
  * The status field indicates if the device is enabled when the status
  * is 'okay'.  Otherwise the device driver will be disabled.
  *
- * @devdata - struct nx842_devdata to update
  * @prop - struct property point containing the maxsyncop for the update
  *
  * Returns:
  *  0 - Device is available
- *  -EINVAL - Device is not available
+ *  -ENODEV - Device is not available
  */
-static int nx842_OF_upd_status(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
+static int nx842_OF_upd_status(struct property *prop)
+{
 	const char *status = (const char *)prop->value;
 
-	if (!strncmp(status, "okay", (size_t)prop->length)) {
-		devdata->status = AVAILABLE;
-	} else {
-		dev_info(devdata->dev, "%s: status '%s' is not 'okay'\n",
-				__func__, status);
-		devdata->status = UNAVAILABLE;
-	}
+	if (!strncmp(status, "okay", (size_t)prop->length))
+		return 0;
+	if (!strncmp(status, "disabled", (size_t)prop->length))
+		return -ENODEV;
+	dev_info(devdata->dev, "%s: unknown status '%s'\n", __func__, status);
 
-	return ret;
+	return -EINVAL;
 }
 
 /**
@@ -735,6 +729,10 @@ static int nx842_OF_upd(struct property *new_prop)
 	int ret = 0;
 	unsigned long flags;
 
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
+	if (!new_devdata)
+		return -ENOMEM;
+
 	spin_lock_irqsave(&devdata_mutex, flags);
 	old_devdata = rcu_dereference_check(devdata,
 			lockdep_is_held(&devdata_mutex));
@@ -744,16 +742,10 @@ static int nx842_OF_upd(struct property *new_prop)
 	if (!old_devdata || !of_node) {
 		pr_err("%s: device is not available\n", __func__);
 		spin_unlock_irqrestore(&devdata_mutex, flags);
+		kfree(new_devdata);
 		return -ENODEV;
 	}
 
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
-	if (!new_devdata) {
-		dev_err(old_devdata->dev, "%s: Could not allocate memory for device data\n", __func__);
-		ret = -ENOMEM;
-		goto error_out;
-	}
-
 	memcpy(new_devdata, old_devdata, sizeof(*old_devdata));
 	new_devdata->counters = old_devdata->counters;
 
@@ -777,7 +769,7 @@ static int nx842_OF_upd(struct property *new_prop)
 		goto out;
 
 	/* Perform property updates */
-	ret = nx842_OF_upd_status(new_devdata, status);
+	ret = nx842_OF_upd_status(status);
 	if (ret)
 		goto error_out;
 
@@ -970,13 +962,43 @@ static struct nx842_driver nx842_pseries_driver = {
 	.decompress =	nx842_pseries_decompress,
 };
 
-static int __init nx842_probe(struct vio_dev *viodev,
-				  const struct vio_device_id *id)
+static int nx842_pseries_crypto_init(struct crypto_tfm *tfm)
+{
+	return nx842_crypto_init(tfm, &nx842_pseries_driver);
+}
+
+static struct crypto_alg nx842_pseries_alg = {
+	.cra_name		= "842",
+	.cra_driver_name	= "842-nx",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct nx842_crypto_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_init		= nx842_pseries_crypto_init,
+	.cra_exit		= nx842_crypto_exit,
+	.cra_u			= { .compress = {
+	.coa_compress		= nx842_crypto_compress,
+	.coa_decompress		= nx842_crypto_decompress } }
+};
+
+static int nx842_probe(struct vio_dev *viodev,
+		       const struct vio_device_id *id)
 {
 	struct nx842_devdata *old_devdata, *new_devdata = NULL;
 	unsigned long flags;
 	int ret = 0;
 
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
+	if (!new_devdata)
+		return -ENOMEM;
+
+	new_devdata->counters = kzalloc(sizeof(*new_devdata->counters),
+			GFP_NOFS);
+	if (!new_devdata->counters) {
+		kfree(new_devdata);
+		return -ENOMEM;
+	}
+
 	spin_lock_irqsave(&devdata_mutex, flags);
 	old_devdata = rcu_dereference_check(devdata,
 			lockdep_is_held(&devdata_mutex));
@@ -989,21 +1011,6 @@ static int __init nx842_probe(struct vio_dev *viodev,
 
 	dev_set_drvdata(&viodev->dev, NULL);
 
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
-	if (!new_devdata) {
-		dev_err(&viodev->dev, "%s: Could not allocate memory for device data\n", __func__);
-		ret = -ENOMEM;
-		goto error_unlock;
-	}
-
-	new_devdata->counters = kzalloc(sizeof(*new_devdata->counters),
-			GFP_NOFS);
-	if (!new_devdata->counters) {
-		dev_err(&viodev->dev, "%s: Could not allocate memory for performance counters\n", __func__);
-		ret = -ENOMEM;
-		goto error_unlock;
-	}
-
 	new_devdata->vdev = viodev;
 	new_devdata->dev = &viodev->dev;
 	nx842_OF_set_defaults(new_devdata);
@@ -1016,9 +1023,12 @@ static int __init nx842_probe(struct vio_dev *viodev,
 	of_reconfig_notifier_register(&nx842_of_nb);
 
 	ret = nx842_OF_upd(NULL);
-	if (ret && ret != -ENODEV) {
-		dev_err(&viodev->dev, "could not parse device tree. %d\n", ret);
-		ret = -1;
+	if (ret)
+		goto error;
+
+	ret = crypto_register_alg(&nx842_pseries_alg);
+	if (ret) {
+		dev_err(&viodev->dev, "could not register comp alg: %d\n", ret);
 		goto error;
 	}
 
@@ -1043,7 +1053,7 @@ error:
 	return ret;
 }
 
-static int __exit nx842_remove(struct vio_dev *viodev)
+static int nx842_remove(struct vio_dev *viodev)
 {
 	struct nx842_devdata *old_devdata;
 	unsigned long flags;
@@ -1051,6 +1061,8 @@ static int __exit nx842_remove(struct vio_dev *viodev)
 	pr_info("Removing IBM Power 842 compression device\n");
 	sysfs_remove_group(&viodev->dev.kobj, &nx842_attribute_group);
 
+	crypto_unregister_alg(&nx842_pseries_alg);
+
 	spin_lock_irqsave(&devdata_mutex, flags);
 	old_devdata = rcu_dereference_check(devdata,
 			lockdep_is_held(&devdata_mutex));
@@ -1074,18 +1086,16 @@ static struct vio_device_id nx842_vio_driver_ids[] = {
 static struct vio_driver nx842_vio_driver = {
 	.name = KBUILD_MODNAME,
 	.probe = nx842_probe,
-	.remove = __exit_p(nx842_remove),
+	.remove = nx842_remove,
 	.get_desired_dma = nx842_get_desired_dma,
 	.id_table = nx842_vio_driver_ids,
 };
 
-static int __init nx842_init(void)
+static int __init nx842_pseries_init(void)
 {
 	struct nx842_devdata *new_devdata;
 	int ret;
 
-	pr_info("Registering IBM Power 842 compression driver\n");
-
 	if (!of_find_compatible_node(NULL, NULL, "ibm,compression"))
 		return -ENODEV;
 
@@ -1095,7 +1105,6 @@ static int __init nx842_init(void)
 		pr_err("Could not allocate memory for device data\n");
 		return -ENOMEM;
 	}
-	new_devdata->status = UNAVAILABLE;
 	RCU_INIT_POINTER(devdata, new_devdata);
 
 	ret = vio_register_driver(&nx842_vio_driver);
@@ -1106,24 +1115,18 @@ static int __init nx842_init(void)
 		return ret;
 	}
 
-	if (!nx842_platform_driver_set(&nx842_pseries_driver)) {
-		vio_unregister_driver(&nx842_vio_driver);
-		kfree(new_devdata);
-		return -EEXIST;
-	}
-
 	return 0;
 }
 
-module_init(nx842_init);
+module_init(nx842_pseries_init);
 
-static void __exit nx842_exit(void)
+static void __exit nx842_pseries_exit(void)
 {
 	struct nx842_devdata *old_devdata;
 	unsigned long flags;
 
-	pr_info("Exiting IBM Power 842 compression driver\n");
-	nx842_platform_driver_unset(&nx842_pseries_driver);
+	crypto_unregister_alg(&nx842_pseries_alg);
+
 	spin_lock_irqsave(&devdata_mutex, flags);
 	old_devdata = rcu_dereference_check(devdata,
 			lockdep_is_held(&devdata_mutex));
@@ -1136,5 +1139,5 @@ static void __exit nx842_exit(void)
 	vio_unregister_driver(&nx842_vio_driver);
 }
 
-module_exit(nx842_exit);
+module_exit(nx842_pseries_exit);
 
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 6e5e0d60d0c8..046c1c45411b 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -1,10 +1,5 @@
 /*
- * Driver frontend for IBM Power 842 compression accelerator
- *
- * Copyright (C) 2015 Dan Streetman, IBM Corp
- *
- * Designer of the Power data compression engine:
- *   Bulent Abali <abali@us.ibm.com>
+ * Cryptographic API for the NX-842 hardware compression.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -15,89 +10,522 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
+ *
+ * Copyright (C) IBM Corporation, 2011-2015
+ *
+ * Designer of the Power data compression engine:
+ *   Bulent Abali <abali@us.ibm.com>
+ *
+ * Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *                   Seth Jennings <sjenning@linux.vnet.ibm.com>
+ *
+ * Rewrite: Dan Streetman <ddstreet@ieee.org>
+ *
+ * This is an interface to the NX-842 compression hardware in PowerPC
+ * processors.  Most of the complexity of this drvier is due to the fact that
+ * the NX-842 compression hardware requires the input and output data buffers
+ * to be specifically aligned, to be a specific multiple in length, and within
+ * specific minimum and maximum lengths.  Those restrictions, provided by the
+ * nx-842 driver via nx842_constraints, mean this driver must use bounce
+ * buffers and headers to correct misaligned in or out buffers, and to split
+ * input buffers that are too large.
+ *
+ * This driver will fall back to software decompression if the hardware
+ * decompression fails, so this driver's decompression should never fail as
+ * long as the provided compressed buffer is valid.  Any compressed buffer
+ * created by this driver will have a header (except ones where the input
+ * perfectly matches the constraints); so users of this driver cannot simply
+ * pass a compressed buffer created by this driver over to the 842 software
+ * decompression library.  Instead, users must use this driver to decompress;
+ * if the hardware fails or is unavailable, the compressed buffer will be
+ * parsed and the header removed, and the raw 842 buffer(s) passed to the 842
+ * software decompression library.
+ *
+ * This does not fall back to software compression, however, since the caller
+ * of this function is specifically requesting hardware compression; if the
+ * hardware compression fails, the caller can fall back to software
+ * compression, and the raw 842 compressed buffer that the software compressor
+ * creates can be passed to this driver for hardware decompression; any
+ * buffer without our specific header magic is assumed to be a raw 842 buffer
+ * and passed directly to the hardware.  Note that the software compression
+ * library will produce a compressed buffer that is incompatible with the
+ * hardware decompressor if the original input buffer length is not a multiple
+ * of 8; if such a compressed buffer is passed to this driver for
+ * decompression, the hardware will reject it and this driver will then pass
+ * it over to the software library for decompression.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include "nx-842.h"
+#include <linux/vmalloc.h>
+#include <linux/sw842.h>
+#include <linux/spinlock.h>
 
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
-MODULE_DESCRIPTION("842 H/W Compression driver for IBM Power processors");
+#include "nx-842.h"
 
-/**
- * nx842_constraints
- *
- * This provides the driver's constraints.  Different nx842 implementations
- * may have varying requirements.  The constraints are:
- *   @alignment:	All buffers should be aligned to this
- *   @multiple:		All buffer lengths should be a multiple of this
- *   @minimum:		Buffer lengths must not be less than this amount
- *   @maximum:		Buffer lengths must not be more than this amount
- *
- * The constraints apply to all buffers and lengths, both input and output,
- * for both compression and decompression, except for the minimum which
- * only applies to compression input and decompression output; the
- * compressed data can be less than the minimum constraint.  It can be
- * assumed that compressed data will always adhere to the multiple
- * constraint.
- *
- * The driver may succeed even if these constraints are violated;
- * however the driver can return failure or suffer reduced performance
- * if any constraint is not met.
+/* The first 5 bits of this magic are 0x1f, which is an invalid 842 5-bit
+ * template (see lib/842/842.h), so this magic number will never appear at
+ * the start of a raw 842 compressed buffer.  That is important, as any buffer
+ * passed to us without this magic is assumed to be a raw 842 compressed
+ * buffer, and passed directly to the hardware to decompress.
  */
-int nx842_constraints(struct nx842_constraints *c)
+#define NX842_CRYPTO_MAGIC	(0xf842)
+#define NX842_CRYPTO_HEADER_SIZE(g)				\
+	(sizeof(struct nx842_crypto_header) +			\
+	 sizeof(struct nx842_crypto_header_group) * (g))
+#define NX842_CRYPTO_HEADER_MAX_SIZE				\
+	NX842_CRYPTO_HEADER_SIZE(NX842_CRYPTO_GROUP_MAX)
+
+/* bounce buffer size */
+#define BOUNCE_BUFFER_ORDER	(2)
+#define BOUNCE_BUFFER_SIZE					\
+	((unsigned int)(PAGE_SIZE << BOUNCE_BUFFER_ORDER))
+
+/* try longer on comp because we can fallback to sw decomp if hw is busy */
+#define COMP_BUSY_TIMEOUT	(250) /* ms */
+#define DECOMP_BUSY_TIMEOUT	(50) /* ms */
+
+struct nx842_crypto_param {
+	u8 *in;
+	unsigned int iremain;
+	u8 *out;
+	unsigned int oremain;
+	unsigned int ototal;
+};
+
+static int update_param(struct nx842_crypto_param *p,
+			unsigned int slen, unsigned int dlen)
 {
-	memcpy(c, nx842_platform_driver()->constraints, sizeof(*c));
+	if (p->iremain < slen)
+		return -EOVERFLOW;
+	if (p->oremain < dlen)
+		return -ENOSPC;
+
+	p->in += slen;
+	p->iremain -= slen;
+	p->out += dlen;
+	p->oremain -= dlen;
+	p->ototal += dlen;
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nx842_constraints);
 
-/**
- * nx842_workmem_size
- *
- * Get the amount of working memory the driver requires.
- */
-size_t nx842_workmem_size(void)
+int nx842_crypto_init(struct crypto_tfm *tfm, struct nx842_driver *driver)
 {
-	return nx842_platform_driver()->workmem_size;
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	spin_lock_init(&ctx->lock);
+	ctx->driver = driver;
+	ctx->wmem = kmalloc(driver->workmem_size, GFP_KERNEL);
+	ctx->sbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
+	ctx->dbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
+	if (!ctx->wmem || !ctx->sbounce || !ctx->dbounce) {
+		kfree(ctx->wmem);
+		free_page((unsigned long)ctx->sbounce);
+		free_page((unsigned long)ctx->dbounce);
+		return -ENOMEM;
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(nx842_workmem_size);
+EXPORT_SYMBOL_GPL(nx842_crypto_init);
 
-int nx842_compress(const unsigned char *in, unsigned int ilen,
-		   unsigned char *out, unsigned int *olen, void *wmem)
+void nx842_crypto_exit(struct crypto_tfm *tfm)
 {
-	return nx842_platform_driver()->compress(in, ilen, out, olen, wmem);
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	kfree(ctx->wmem);
+	free_page((unsigned long)ctx->sbounce);
+	free_page((unsigned long)ctx->dbounce);
 }
-EXPORT_SYMBOL_GPL(nx842_compress);
+EXPORT_SYMBOL_GPL(nx842_crypto_exit);
 
-int nx842_decompress(const unsigned char *in, unsigned int ilen,
-		     unsigned char *out, unsigned int *olen, void *wmem)
+static void check_constraints(struct nx842_constraints *c)
 {
-	return nx842_platform_driver()->decompress(in, ilen, out, olen, wmem);
+	/* limit maximum, to always have enough bounce buffer to decompress */
+	if (c->maximum > BOUNCE_BUFFER_SIZE)
+		c->maximum = BOUNCE_BUFFER_SIZE;
 }
-EXPORT_SYMBOL_GPL(nx842_decompress);
 
-static __init int nx842_init(void)
+static int nx842_crypto_add_header(struct nx842_crypto_header *hdr, u8 *buf)
 {
-	request_module("nx-compress-powernv");
-	request_module("nx-compress-pseries");
+	int s = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
 
-	/* we prevent loading if there's no platform driver, and we get the
-	 * module that set it so it won't unload, so we don't need to check
-	 * if it's set in any of the above functions
-	 */
-	if (!nx842_platform_driver_get()) {
-		pr_err("no nx842 driver found.\n");
-		return -ENODEV;
+	/* compress should have added space for header */
+	if (s > be16_to_cpu(hdr->group[0].padding)) {
+		pr_err("Internal error: no space for header\n");
+		return -EINVAL;
 	}
 
+	memcpy(buf, hdr, s);
+
+	print_hex_dump_debug("header ", DUMP_PREFIX_OFFSET, 16, 1, buf, s, 0);
+
 	return 0;
 }
-module_init(nx842_init);
 
-static void __exit nx842_exit(void)
+static int compress(struct nx842_crypto_ctx *ctx,
+		    struct nx842_crypto_param *p,
+		    struct nx842_crypto_header_group *g,
+		    struct nx842_constraints *c,
+		    u16 *ignore,
+		    unsigned int hdrsize)
+{
+	unsigned int slen = p->iremain, dlen = p->oremain, tmplen;
+	unsigned int adj_slen = slen;
+	u8 *src = p->in, *dst = p->out;
+	int ret, dskip = 0;
+	ktime_t timeout;
+
+	if (p->iremain == 0)
+		return -EOVERFLOW;
+
+	if (p->oremain == 0 || hdrsize + c->minimum > dlen)
+		return -ENOSPC;
+
+	if (slen % c->multiple)
+		adj_slen = round_up(slen, c->multiple);
+	if (slen < c->minimum)
+		adj_slen = c->minimum;
+	if (slen > c->maximum)
+		adj_slen = slen = c->maximum;
+	if (adj_slen > slen || (u64)src % c->alignment) {
+		adj_slen = min(adj_slen, BOUNCE_BUFFER_SIZE);
+		slen = min(slen, BOUNCE_BUFFER_SIZE);
+		if (adj_slen > slen)
+			memset(ctx->sbounce + slen, 0, adj_slen - slen);
+		memcpy(ctx->sbounce, src, slen);
+		src = ctx->sbounce;
+		slen = adj_slen;
+		pr_debug("using comp sbounce buffer, len %x\n", slen);
+	}
+
+	dst += hdrsize;
+	dlen -= hdrsize;
+
+	if ((u64)dst % c->alignment) {
+		dskip = (int)(PTR_ALIGN(dst, c->alignment) - dst);
+		dst += dskip;
+		dlen -= dskip;
+	}
+	if (dlen % c->multiple)
+		dlen = round_down(dlen, c->multiple);
+	if (dlen < c->minimum) {
+nospc:
+		dst = ctx->dbounce;
+		dlen = min(p->oremain, BOUNCE_BUFFER_SIZE);
+		dlen = round_down(dlen, c->multiple);
+		dskip = 0;
+		pr_debug("using comp dbounce buffer, len %x\n", dlen);
+	}
+	if (dlen > c->maximum)
+		dlen = c->maximum;
+
+	tmplen = dlen;
+	timeout = ktime_add_ms(ktime_get(), COMP_BUSY_TIMEOUT);
+	do {
+		dlen = tmplen; /* reset dlen, if we're retrying */
+		ret = ctx->driver->compress(src, slen, dst, &dlen, ctx->wmem);
+		/* possibly we should reduce the slen here, instead of
+		 * retrying with the dbounce buffer?
+		 */
+		if (ret == -ENOSPC && dst != ctx->dbounce)
+			goto nospc;
+	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
+	if (ret)
+		return ret;
+
+	dskip += hdrsize;
+
+	if (dst == ctx->dbounce)
+		memcpy(p->out + dskip, dst, dlen);
+
+	g->padding = cpu_to_be16(dskip);
+	g->compressed_length = cpu_to_be32(dlen);
+	g->uncompressed_length = cpu_to_be32(slen);
+
+	if (p->iremain < slen) {
+		*ignore = slen - p->iremain;
+		slen = p->iremain;
+	}
+
+	pr_debug("compress slen %x ignore %x dlen %x padding %x\n",
+		 slen, *ignore, dlen, dskip);
+
+	return update_param(p, slen, dskip + dlen);
+}
+
+int nx842_crypto_compress(struct crypto_tfm *tfm,
+			  const u8 *src, unsigned int slen,
+			  u8 *dst, unsigned int *dlen)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_crypto_header *hdr = &ctx->header;
+	struct nx842_crypto_param p;
+	struct nx842_constraints c = *ctx->driver->constraints;
+	unsigned int groups, hdrsize, h;
+	int ret, n;
+	bool add_header;
+	u16 ignore = 0;
+
+	check_constraints(&c);
+
+	p.in = (u8 *)src;
+	p.iremain = slen;
+	p.out = dst;
+	p.oremain = *dlen;
+	p.ototal = 0;
+
+	*dlen = 0;
+
+	groups = min_t(unsigned int, NX842_CRYPTO_GROUP_MAX,
+		       DIV_ROUND_UP(p.iremain, c.maximum));
+	hdrsize = NX842_CRYPTO_HEADER_SIZE(groups);
+
+	spin_lock_bh(&ctx->lock);
+
+	/* skip adding header if the buffers meet all constraints */
+	add_header = (p.iremain % c.multiple	||
+		      p.iremain < c.minimum	||
+		      p.iremain > c.maximum	||
+		      (u64)p.in % c.alignment	||
+		      p.oremain % c.multiple	||
+		      p.oremain < c.minimum	||
+		      p.oremain > c.maximum	||
+		      (u64)p.out % c.alignment);
+
+	hdr->magic = cpu_to_be16(NX842_CRYPTO_MAGIC);
+	hdr->groups = 0;
+	hdr->ignore = 0;
+
+	while (p.iremain > 0) {
+		n = hdr->groups++;
+		ret = -ENOSPC;
+		if (hdr->groups > NX842_CRYPTO_GROUP_MAX)
+			goto unlock;
+
+		/* header goes before first group */
+		h = !n && add_header ? hdrsize : 0;
+
+		if (ignore)
+			pr_warn("interal error, ignore is set %x\n", ignore);
+
+		ret = compress(ctx, &p, &hdr->group[n], &c, &ignore, h);
+		if (ret)
+			goto unlock;
+	}
+
+	if (!add_header && hdr->groups > 1) {
+		pr_err("Internal error: No header but multiple groups\n");
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	/* ignore indicates the input stream needed to be padded */
+	hdr->ignore = cpu_to_be16(ignore);
+	if (ignore)
+		pr_debug("marked %d bytes as ignore\n", ignore);
+
+	if (add_header)
+		ret = nx842_crypto_add_header(hdr, dst);
+	if (ret)
+		goto unlock;
+
+	*dlen = p.ototal;
+
+	pr_debug("compress total slen %x dlen %x\n", slen, *dlen);
+
+unlock:
+	spin_unlock_bh(&ctx->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nx842_crypto_compress);
+
+static int decompress(struct nx842_crypto_ctx *ctx,
+		      struct nx842_crypto_param *p,
+		      struct nx842_crypto_header_group *g,
+		      struct nx842_constraints *c,
+		      u16 ignore)
 {
-	nx842_platform_driver_put();
+	unsigned int slen = be32_to_cpu(g->compressed_length);
+	unsigned int required_len = be32_to_cpu(g->uncompressed_length);
+	unsigned int dlen = p->oremain, tmplen;
+	unsigned int adj_slen = slen;
+	u8 *src = p->in, *dst = p->out;
+	u16 padding = be16_to_cpu(g->padding);
+	int ret, spadding = 0, dpadding = 0;
+	ktime_t timeout;
+
+	if (!slen || !required_len)
+		return -EINVAL;
+
+	if (p->iremain <= 0 || padding + slen > p->iremain)
+		return -EOVERFLOW;
+
+	if (p->oremain <= 0 || required_len - ignore > p->oremain)
+		return -ENOSPC;
+
+	src += padding;
+
+	if (slen % c->multiple)
+		adj_slen = round_up(slen, c->multiple);
+	if (slen < c->minimum)
+		adj_slen = c->minimum;
+	if (slen > c->maximum)
+		goto usesw;
+	if (slen < adj_slen || (u64)src % c->alignment) {
+		/* we can append padding bytes because the 842 format defines
+		 * an "end" template (see lib/842/842_decompress.c) and will
+		 * ignore any bytes following it.
+		 */
+		if (slen < adj_slen)
+			memset(ctx->sbounce + slen, 0, adj_slen - slen);
+		memcpy(ctx->sbounce, src, slen);
+		src = ctx->sbounce;
+		spadding = adj_slen - slen;
+		slen = adj_slen;
+		pr_debug("using decomp sbounce buffer, len %x\n", slen);
+	}
+
+	if (dlen % c->multiple)
+		dlen = round_down(dlen, c->multiple);
+	if (dlen < required_len || (u64)dst % c->alignment) {
+		dst = ctx->dbounce;
+		dlen = min(required_len, BOUNCE_BUFFER_SIZE);
+		pr_debug("using decomp dbounce buffer, len %x\n", dlen);
+	}
+	if (dlen < c->minimum)
+		goto usesw;
+	if (dlen > c->maximum)
+		dlen = c->maximum;
+
+	tmplen = dlen;
+	timeout = ktime_add_ms(ktime_get(), DECOMP_BUSY_TIMEOUT);
+	do {
+		dlen = tmplen; /* reset dlen, if we're retrying */
+		ret = ctx->driver->decompress(src, slen, dst, &dlen, ctx->wmem);
+	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
+	if (ret) {
+usesw:
+		/* reset everything, sw doesn't have constraints */
+		src = p->in + padding;
+		slen = be32_to_cpu(g->compressed_length);
+		spadding = 0;
+		dst = p->out;
+		dlen = p->oremain;
+		dpadding = 0;
+		if (dlen < required_len) { /* have ignore bytes */
+			dst = ctx->dbounce;
+			dlen = BOUNCE_BUFFER_SIZE;
+		}
+		pr_info_ratelimited("using software 842 decompression\n");
+		ret = sw842_decompress(src, slen, dst, &dlen);
+	}
+	if (ret)
+		return ret;
+
+	slen -= spadding;
+
+	dlen -= ignore;
+	if (ignore)
+		pr_debug("ignoring last %x bytes\n", ignore);
+
+	if (dst == ctx->dbounce)
+		memcpy(p->out, dst, dlen);
+
+	pr_debug("decompress slen %x padding %x dlen %x ignore %x\n",
+		 slen, padding, dlen, ignore);
+
+	return update_param(p, slen + padding, dlen);
 }
-module_exit(nx842_exit);
+
+int nx842_crypto_decompress(struct crypto_tfm *tfm,
+			    const u8 *src, unsigned int slen,
+			    u8 *dst, unsigned int *dlen)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_crypto_header *hdr;
+	struct nx842_crypto_param p;
+	struct nx842_constraints c = *ctx->driver->constraints;
+	int n, ret, hdr_len;
+	u16 ignore = 0;
+
+	check_constraints(&c);
+
+	p.in = (u8 *)src;
+	p.iremain = slen;
+	p.out = dst;
+	p.oremain = *dlen;
+	p.ototal = 0;
+
+	*dlen = 0;
+
+	hdr = (struct nx842_crypto_header *)src;
+
+	spin_lock_bh(&ctx->lock);
+
+	/* If it doesn't start with our header magic number, assume it's a raw
+	 * 842 compressed buffer and pass it directly to the hardware driver
+	 */
+	if (be16_to_cpu(hdr->magic) != NX842_CRYPTO_MAGIC) {
+		struct nx842_crypto_header_group g = {
+			.padding =		0,
+			.compressed_length =	cpu_to_be32(p.iremain),
+			.uncompressed_length =	cpu_to_be32(p.oremain),
+		};
+
+		ret = decompress(ctx, &p, &g, &c, 0);
+		if (ret)
+			goto unlock;
+
+		goto success;
+	}
+
+	if (!hdr->groups) {
+		pr_err("header has no groups\n");
+		ret = -EINVAL;
+		goto unlock;
+	}
+	if (hdr->groups > NX842_CRYPTO_GROUP_MAX) {
+		pr_err("header has too many groups %x, max %x\n",
+		       hdr->groups, NX842_CRYPTO_GROUP_MAX);
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	hdr_len = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
+	if (hdr_len > slen) {
+		ret = -EOVERFLOW;
+		goto unlock;
+	}
+
+	memcpy(&ctx->header, src, hdr_len);
+	hdr = &ctx->header;
+
+	for (n = 0; n < hdr->groups; n++) {
+		/* ignore applies to last group */
+		if (n + 1 == hdr->groups)
+			ignore = be16_to_cpu(hdr->ignore);
+
+		ret = decompress(ctx, &p, &hdr->group[n], &c, ignore);
+		if (ret)
+			goto unlock;
+	}
+
+success:
+	*dlen = p.ototal;
+
+	pr_debug("decompress total slen %x dlen %x\n", slen, *dlen);
+
+	ret = 0;
+
+unlock:
+	spin_unlock_bh(&ctx->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nx842_crypto_decompress);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IBM PowerPC Nest (NX) 842 Hardware Compression Driver");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/drivers/crypto/nx/nx-842.h b/drivers/crypto/nx/nx-842.h
index ac0ea79d0f8b..a4eee3bba937 100644
--- a/drivers/crypto/nx/nx-842.h
+++ b/drivers/crypto/nx/nx-842.h
@@ -3,8 +3,9 @@
 #define __NX_842_H__
 
 #include <linux/kernel.h>
+#include <linux/init.h>
 #include <linux/module.h>
-#include <linux/sw842.h>
+#include <linux/crypto.h>
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/io.h>
@@ -104,6 +105,25 @@ static inline unsigned long nx842_get_pa(void *addr)
 #define GET_FIELD(v, m)		(((v) & (m)) >> MASK_LSH(m))
 #define SET_FIELD(v, m, val)	(((v) & ~(m)) | (((val) << MASK_LSH(m)) & (m)))
 
+/**
+ * This provides the driver's constraints.  Different nx842 implementations
+ * may have varying requirements.  The constraints are:
+ *   @alignment:	All buffers should be aligned to this
+ *   @multiple:		All buffer lengths should be a multiple of this
+ *   @minimum:		Buffer lengths must not be less than this amount
+ *   @maximum:		Buffer lengths must not be more than this amount
+ *
+ * The constraints apply to all buffers and lengths, both input and output,
+ * for both compression and decompression, except for the minimum which
+ * only applies to compression input and decompression output; the
+ * compressed data can be less than the minimum constraint.  It can be
+ * assumed that compressed data will always adhere to the multiple
+ * constraint.
+ *
+ * The driver may succeed even if these constraints are violated;
+ * however the driver can return failure or suffer reduced performance
+ * if any constraint is not met.
+ */
 struct nx842_constraints {
 	int alignment;
 	int multiple;
@@ -126,19 +146,40 @@ struct nx842_driver {
 			  void *wrkmem);
 };
 
-struct nx842_driver *nx842_platform_driver(void);
-bool nx842_platform_driver_set(struct nx842_driver *driver);
-void nx842_platform_driver_unset(struct nx842_driver *driver);
-bool nx842_platform_driver_get(void);
-void nx842_platform_driver_put(void);
+struct nx842_crypto_header_group {
+	__be16 padding;			/* unused bytes at start of group */
+	__be32 compressed_length;	/* compressed bytes in group */
+	__be32 uncompressed_length;	/* bytes after decompression */
+} __packed;
+
+struct nx842_crypto_header {
+	__be16 magic;		/* NX842_CRYPTO_MAGIC */
+	__be16 ignore;		/* decompressed end bytes to ignore */
+	u8 groups;		/* total groups in this header */
+	struct nx842_crypto_header_group group[];
+} __packed;
 
-size_t nx842_workmem_size(void);
+#define NX842_CRYPTO_GROUP_MAX	(0x20)
 
-int nx842_constraints(struct nx842_constraints *constraints);
+struct nx842_crypto_ctx {
+	spinlock_t lock;
+
+	u8 *wmem;
+	u8 *sbounce, *dbounce;
+
+	struct nx842_crypto_header header;
+	struct nx842_crypto_header_group group[NX842_CRYPTO_GROUP_MAX];
+
+	struct nx842_driver *driver;
+};
 
-int nx842_compress(const unsigned char *in, unsigned int in_len,
-		   unsigned char *out, unsigned int *out_len, void *wrkmem);
-int nx842_decompress(const unsigned char *in, unsigned int in_len,
-		     unsigned char *out, unsigned int *out_len, void *wrkmem);
+int nx842_crypto_init(struct crypto_tfm *tfm, struct nx842_driver *driver);
+void nx842_crypto_exit(struct crypto_tfm *tfm);
+int nx842_crypto_compress(struct crypto_tfm *tfm,
+			  const u8 *src, unsigned int slen,
+			  u8 *dst, unsigned int *dlen);
+int nx842_crypto_decompress(struct crypto_tfm *tfm,
+			    const u8 *src, unsigned int slen,
+			    u8 *dst, unsigned int *dlen);
 
 #endif /* __NX_842_H__ */
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index 67f80813a06f..73ef49922788 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -94,8 +94,6 @@ static int ccm_aes_nx_setauthsize(struct crypto_aead *tfm,
 		return -EINVAL;
 	}
 
-	crypto_aead_crt(tfm)->authsize = authsize;
-
 	return 0;
 }
 
@@ -111,8 +109,6 @@ static int ccm4309_aes_nx_setauthsize(struct crypto_aead *tfm,
 		return -EINVAL;
 	}
 
-	crypto_aead_crt(tfm)->authsize = authsize;
-
 	return 0;
 }
 
@@ -174,6 +170,7 @@ static int generate_pat(u8                   *iv,
 			struct nx_crypto_ctx *nx_ctx,
 			unsigned int          authsize,
 			unsigned int          nbytes,
+			unsigned int	      assoclen,
 			u8                   *out)
 {
 	struct nx_sg *nx_insg = nx_ctx->in_sg;
@@ -200,16 +197,16 @@ static int generate_pat(u8                   *iv,
 	 * greater than 2^32.
 	 */
 
-	if (!req->assoclen) {
+	if (!assoclen) {
 		b0 = nx_ctx->csbcpb->cpb.aes_ccm.in_pat_or_b0;
-	} else if (req->assoclen <= 14) {
+	} else if (assoclen <= 14) {
 		/* if associated data is 14 bytes or less, we do 1 GCM
 		 * operation on 2 AES blocks, B0 (stored in the csbcpb) and B1,
 		 * which is fed in through the source buffers here */
 		b0 = nx_ctx->csbcpb->cpb.aes_ccm.in_pat_or_b0;
 		b1 = nx_ctx->priv.ccm.iauth_tag;
-		iauth_len = req->assoclen;
-	} else if (req->assoclen <= 65280) {
+		iauth_len = assoclen;
+	} else if (assoclen <= 65280) {
 		/* if associated data is less than (2^16 - 2^8), we construct
 		 * B1 differently and feed in the associated data to a CCA
 		 * operation */
@@ -223,7 +220,7 @@ static int generate_pat(u8                   *iv,
 	}
 
 	/* generate B0 */
-	rc = generate_b0(iv, req->assoclen, authsize, nbytes, b0);
+	rc = generate_b0(iv, assoclen, authsize, nbytes, b0);
 	if (rc)
 		return rc;
 
@@ -233,22 +230,22 @@ static int generate_pat(u8                   *iv,
 	 */
 	if (b1) {
 		memset(b1, 0, 16);
-		if (req->assoclen <= 65280) {
-			*(u16 *)b1 = (u16)req->assoclen;
-			scatterwalk_map_and_copy(b1 + 2, req->assoc, 0,
+		if (assoclen <= 65280) {
+			*(u16 *)b1 = assoclen;
+			scatterwalk_map_and_copy(b1 + 2, req->src, 0,
 					 iauth_len, SCATTERWALK_FROM_SG);
 		} else {
 			*(u16 *)b1 = (u16)(0xfffe);
-			*(u32 *)&b1[2] = (u32)req->assoclen;
-			scatterwalk_map_and_copy(b1 + 6, req->assoc, 0,
+			*(u32 *)&b1[2] = assoclen;
+			scatterwalk_map_and_copy(b1 + 6, req->src, 0,
 					 iauth_len, SCATTERWALK_FROM_SG);
 		}
 	}
 
 	/* now copy any remaining AAD to scatterlist and call nx... */
-	if (!req->assoclen) {
+	if (!assoclen) {
 		return rc;
-	} else if (req->assoclen <= 14) {
+	} else if (assoclen <= 14) {
 		unsigned int len = 16;
 
 		nx_insg = nx_build_sg_list(nx_insg, b1, &len, nx_ctx->ap->sglen);
@@ -280,7 +277,7 @@ static int generate_pat(u8                   *iv,
 			return rc;
 
 		atomic_inc(&(nx_ctx->stats->aes_ops));
-		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
+		atomic64_add(assoclen, &nx_ctx->stats->aes_bytes);
 
 	} else {
 		unsigned int processed = 0, to_process;
@@ -294,15 +291,15 @@ static int generate_pat(u8                   *iv,
 				nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
 		do {
-			to_process = min_t(u32, req->assoclen - processed,
+			to_process = min_t(u32, assoclen - processed,
 					   nx_ctx->ap->databytelen);
 
 			nx_insg = nx_walk_and_build(nx_ctx->in_sg,
 						    nx_ctx->ap->sglen,
-						    req->assoc, processed,
+						    req->src, processed,
 						    &to_process);
 
-			if ((to_process + processed) < req->assoclen) {
+			if ((to_process + processed) < assoclen) {
 				NX_CPB_FDM(nx_ctx->csbcpb_aead) |=
 					NX_FDM_INTERMEDIATE;
 			} else {
@@ -328,11 +325,10 @@ static int generate_pat(u8                   *iv,
 			NX_CPB_FDM(nx_ctx->csbcpb_aead) |= NX_FDM_CONTINUATION;
 
 			atomic_inc(&(nx_ctx->stats->aes_ops));
-			atomic64_add(req->assoclen,
-					&(nx_ctx->stats->aes_bytes));
+			atomic64_add(assoclen, &nx_ctx->stats->aes_bytes);
 
 			processed += to_process;
-		} while (processed < req->assoclen);
+		} while (processed < assoclen);
 
 		result = nx_ctx->csbcpb_aead->cpb.aes_cca.out_pat_or_b0;
 	}
@@ -343,7 +339,8 @@ static int generate_pat(u8                   *iv,
 }
 
 static int ccm_nx_decrypt(struct aead_request   *req,
-			  struct blkcipher_desc *desc)
+			  struct blkcipher_desc *desc,
+			  unsigned int assoclen)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
@@ -360,10 +357,10 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 
 	/* copy out the auth tag to compare with later */
 	scatterwalk_map_and_copy(priv->oauth_tag,
-				 req->src, nbytes, authsize,
+				 req->src, nbytes + req->assoclen, authsize,
 				 SCATTERWALK_FROM_SG);
 
-	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes,
+	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes, assoclen,
 			  csbcpb->cpb.aes_ccm.in_pat_or_b0);
 	if (rc)
 		goto out;
@@ -383,8 +380,8 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 		NX_CPB_FDM(nx_ctx->csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 
 		rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src,
-					&to_process, processed,
-					csbcpb->cpb.aes_ccm.iv_or_ctr);
+				       &to_process, processed + req->assoclen,
+				       csbcpb->cpb.aes_ccm.iv_or_ctr);
 		if (rc)
 			goto out;
 
@@ -420,7 +417,8 @@ out:
 }
 
 static int ccm_nx_encrypt(struct aead_request   *req,
-			  struct blkcipher_desc *desc)
+			  struct blkcipher_desc *desc,
+			  unsigned int assoclen)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
@@ -432,7 +430,7 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes,
+	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes, assoclen,
 			  csbcpb->cpb.aes_ccm.in_pat_or_b0);
 	if (rc)
 		goto out;
@@ -451,7 +449,7 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
 
 		rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src,
-					&to_process, processed,
+				       &to_process, processed + req->assoclen,
 				       csbcpb->cpb.aes_ccm.iv_or_ctr);
 		if (rc)
 			goto out;
@@ -483,7 +481,7 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 
 	/* copy out the auth tag */
 	scatterwalk_map_and_copy(csbcpb->cpb.aes_ccm.out_pat_or_mac,
-				 req->dst, nbytes, authsize,
+				 req->dst, nbytes + req->assoclen, authsize,
 				 SCATTERWALK_TO_SG);
 
 out:
@@ -494,17 +492,17 @@ out:
 static int ccm4309_aes_nx_encrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct blkcipher_desc desc;
-	u8 *iv = nx_ctx->priv.ccm.iv;
+	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
 	memcpy(iv + 4, req->iv, 8);
 
 	desc.info = iv;
-	desc.tfm = (struct crypto_blkcipher *)req->base.tfm;
 
-	return ccm_nx_encrypt(req, &desc);
+	return ccm_nx_encrypt(req, &desc, req->assoclen - 8);
 }
 
 static int ccm_aes_nx_encrypt(struct aead_request *req)
@@ -513,29 +511,28 @@ static int ccm_aes_nx_encrypt(struct aead_request *req)
 	int rc;
 
 	desc.info = req->iv;
-	desc.tfm = (struct crypto_blkcipher *)req->base.tfm;
 
 	rc = crypto_ccm_check_iv(desc.info);
 	if (rc)
 		return rc;
 
-	return ccm_nx_encrypt(req, &desc);
+	return ccm_nx_encrypt(req, &desc, req->assoclen);
 }
 
 static int ccm4309_aes_nx_decrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct blkcipher_desc desc;
-	u8 *iv = nx_ctx->priv.ccm.iv;
+	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
 	memcpy(iv + 4, req->iv, 8);
 
 	desc.info = iv;
-	desc.tfm = (struct crypto_blkcipher *)req->base.tfm;
 
-	return ccm_nx_decrypt(req, &desc);
+	return ccm_nx_decrypt(req, &desc, req->assoclen - 8);
 }
 
 static int ccm_aes_nx_decrypt(struct aead_request *req)
@@ -544,13 +541,12 @@ static int ccm_aes_nx_decrypt(struct aead_request *req)
 	int rc;
 
 	desc.info = req->iv;
-	desc.tfm = (struct crypto_blkcipher *)req->base.tfm;
 
 	rc = crypto_ccm_check_iv(desc.info);
 	if (rc)
 		return rc;
 
-	return ccm_nx_decrypt(req, &desc);
+	return ccm_nx_decrypt(req, &desc, req->assoclen);
 }
 
 /* tell the block cipher walk routines that this is a stream cipher by
@@ -558,47 +554,42 @@ static int ccm_aes_nx_decrypt(struct aead_request *req)
  * during encrypt/decrypt doesn't solve this problem, because it calls
  * blkcipher_walk_done under the covers, which doesn't use walk->blocksize,
  * but instead uses this tfm->blocksize. */
-struct crypto_alg nx_ccm_aes_alg = {
-	.cra_name        = "ccm(aes)",
-	.cra_driver_name = "ccm-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_AEAD |
-			   CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_aead_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_ccm_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_aead = {
-		.ivsize      = AES_BLOCK_SIZE,
-		.maxauthsize = AES_BLOCK_SIZE,
-		.setkey      = ccm_aes_nx_set_key,
-		.setauthsize = ccm_aes_nx_setauthsize,
-		.encrypt     = ccm_aes_nx_encrypt,
-		.decrypt     = ccm_aes_nx_decrypt,
-	}
+struct aead_alg nx_ccm_aes_alg = {
+	.base = {
+		.cra_name        = "ccm(aes)",
+		.cra_driver_name = "ccm-aes-nx",
+		.cra_priority    = 300,
+		.cra_flags       = CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize   = 1,
+		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
+		.cra_module      = THIS_MODULE,
+	},
+	.init        = nx_crypto_ctx_aes_ccm_init,
+	.exit        = nx_crypto_ctx_aead_exit,
+	.ivsize      = AES_BLOCK_SIZE,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.setkey      = ccm_aes_nx_set_key,
+	.setauthsize = ccm_aes_nx_setauthsize,
+	.encrypt     = ccm_aes_nx_encrypt,
+	.decrypt     = ccm_aes_nx_decrypt,
 };
 
-struct crypto_alg nx_ccm4309_aes_alg = {
-	.cra_name        = "rfc4309(ccm(aes))",
-	.cra_driver_name = "rfc4309-ccm-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_AEAD |
-			   CRYPTO_ALG_NEED_FALLBACK,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_nivaead_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_ccm_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_aead = {
-		.ivsize      = 8,
-		.maxauthsize = AES_BLOCK_SIZE,
-		.setkey      = ccm4309_aes_nx_set_key,
-		.setauthsize = ccm4309_aes_nx_setauthsize,
-		.encrypt     = ccm4309_aes_nx_encrypt,
-		.decrypt     = ccm4309_aes_nx_decrypt,
-		.geniv       = "seqiv",
-	}
+struct aead_alg nx_ccm4309_aes_alg = {
+	.base = {
+		.cra_name        = "rfc4309(ccm(aes))",
+		.cra_driver_name = "rfc4309-ccm-aes-nx",
+		.cra_priority    = 300,
+		.cra_flags       = CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize   = 1,
+		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
+		.cra_module      = THIS_MODULE,
+	},
+	.init        = nx_crypto_ctx_aes_ccm_init,
+	.exit        = nx_crypto_ctx_aead_exit,
+	.ivsize      = 8,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.setkey      = ccm4309_aes_nx_set_key,
+	.setauthsize = ccm4309_aes_nx_setauthsize,
+	.encrypt     = ccm4309_aes_nx_encrypt,
+	.decrypt     = ccm4309_aes_nx_decrypt,
 };
diff --git a/drivers/crypto/nx/nx-aes-ctr.c b/drivers/crypto/nx/nx-aes-ctr.c
index 2617cd4d54dd..898c0a280511 100644
--- a/drivers/crypto/nx/nx-aes-ctr.c
+++ b/drivers/crypto/nx/nx-aes-ctr.c
@@ -72,7 +72,7 @@ static int ctr3686_aes_nx_set_key(struct crypto_tfm *tfm,
 	if (key_len < CTR_RFC3686_NONCE_SIZE)
 		return -EINVAL;
 
-	memcpy(nx_ctx->priv.ctr.iv,
+	memcpy(nx_ctx->priv.ctr.nonce,
 	       in_key + key_len - CTR_RFC3686_NONCE_SIZE,
 	       CTR_RFC3686_NONCE_SIZE);
 
@@ -131,39 +131,19 @@ static int ctr3686_aes_nx_crypt(struct blkcipher_desc *desc,
 				unsigned int           nbytes)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 *iv = nx_ctx->priv.ctr.iv;
+	u8 iv[16];
 
+	memcpy(iv, nx_ctx->priv.ctr.nonce, CTR_RFC3686_IV_SIZE);
 	memcpy(iv + CTR_RFC3686_NONCE_SIZE,
 	       desc->info, CTR_RFC3686_IV_SIZE);
 	iv[12] = iv[13] = iv[14] = 0;
 	iv[15] = 1;
 
-	desc->info = nx_ctx->priv.ctr.iv;
+	desc->info = iv;
 
 	return ctr_aes_nx_crypt(desc, dst, src, nbytes);
 }
 
-struct crypto_alg nx_ctr_aes_alg = {
-	.cra_name        = "ctr(aes)",
-	.cra_driver_name = "ctr-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_blkcipher_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_ctr_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_blkcipher = {
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.ivsize      = AES_BLOCK_SIZE,
-		.setkey      = ctr_aes_nx_set_key,
-		.encrypt     = ctr_aes_nx_crypt,
-		.decrypt     = ctr_aes_nx_crypt,
-	}
-};
-
 struct crypto_alg nx_ctr3686_aes_alg = {
 	.cra_name        = "rfc3686(ctr(aes))",
 	.cra_driver_name = "rfc3686-ctr-aes-nx",
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index 08ac6d48688c..eee624f589b6 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -21,11 +21,9 @@
 
 #include <crypto/internal/aead.h>
 #include <crypto/aes.h>
-#include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <asm/vio.h>
 
 #include "nx_csbcpb.h"
@@ -36,7 +34,7 @@ static int gcm_aes_nx_set_key(struct crypto_aead *tfm,
 			      const u8           *in_key,
 			      unsigned int        key_len)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&tfm->base);
+	struct nx_crypto_ctx *nx_ctx = crypto_aead_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_csbcpb *csbcpb_aead = nx_ctx->csbcpb_aead;
 
@@ -75,7 +73,7 @@ static int gcm4106_aes_nx_set_key(struct crypto_aead *tfm,
 				  const u8           *in_key,
 				  unsigned int        key_len)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&tfm->base);
+	struct nx_crypto_ctx *nx_ctx = crypto_aead_ctx(tfm);
 	char *nonce = nx_ctx->priv.gcm.nonce;
 	int rc;
 
@@ -110,13 +108,14 @@ static int gcm4106_aes_nx_setauthsize(struct crypto_aead *tfm,
 
 static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 		  struct aead_request   *req,
-		  u8                    *out)
+		  u8                    *out,
+		  unsigned int assoclen)
 {
 	int rc;
 	struct nx_csbcpb *csbcpb_aead = nx_ctx->csbcpb_aead;
 	struct scatter_walk walk;
 	struct nx_sg *nx_sg = nx_ctx->in_sg;
-	unsigned int nbytes = req->assoclen;
+	unsigned int nbytes = assoclen;
 	unsigned int processed = 0, to_process;
 	unsigned int max_sg_len;
 
@@ -167,7 +166,7 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 		NX_CPB_FDM(csbcpb_aead) |= NX_FDM_CONTINUATION;
 
 		atomic_inc(&(nx_ctx->stats->aes_ops));
-		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
+		atomic64_add(assoclen, &(nx_ctx->stats->aes_bytes));
 
 		processed += to_process;
 	} while (processed < nbytes);
@@ -177,13 +176,15 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 	return rc;
 }
 
-static int gmac(struct aead_request *req, struct blkcipher_desc *desc)
+static int gmac(struct aead_request *req, struct blkcipher_desc *desc,
+		unsigned int assoclen)
 {
 	int rc;
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_crypto_ctx *nx_ctx =
+		crypto_aead_ctx(crypto_aead_reqtfm(req));
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_sg *nx_sg;
-	unsigned int nbytes = req->assoclen;
+	unsigned int nbytes = assoclen;
 	unsigned int processed = 0, to_process;
 	unsigned int max_sg_len;
 
@@ -238,7 +239,7 @@ static int gmac(struct aead_request *req, struct blkcipher_desc *desc)
 		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
 		atomic_inc(&(nx_ctx->stats->aes_ops));
-		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
+		atomic64_add(assoclen, &(nx_ctx->stats->aes_bytes));
 
 		processed += to_process;
 	} while (processed < nbytes);
@@ -253,7 +254,8 @@ static int gcm_empty(struct aead_request *req, struct blkcipher_desc *desc,
 		     int enc)
 {
 	int rc;
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_crypto_ctx *nx_ctx =
+		crypto_aead_ctx(crypto_aead_reqtfm(req));
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	char out[AES_BLOCK_SIZE];
 	struct nx_sg *in_sg, *out_sg;
@@ -314,9 +316,12 @@ out:
 	return rc;
 }
 
-static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
+static int gcm_aes_nx_crypt(struct aead_request *req, int enc,
+			    unsigned int assoclen)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_crypto_ctx *nx_ctx =
+		crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct blkcipher_desc desc;
 	unsigned int nbytes = req->cryptlen;
@@ -326,15 +331,15 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	desc.info = nx_ctx->priv.gcm.iv;
+	desc.info = rctx->iv;
 	/* initialize the counter */
 	*(u32 *)(desc.info + NX_GCM_CTR_OFFSET) = 1;
 
 	if (nbytes == 0) {
-		if (req->assoclen == 0)
+		if (assoclen == 0)
 			rc = gcm_empty(req, &desc, enc);
 		else
-			rc = gmac(req, &desc);
+			rc = gmac(req, &desc, assoclen);
 		if (rc)
 			goto out;
 		else
@@ -342,9 +347,10 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 	}
 
 	/* Process associated data */
-	csbcpb->cpb.aes_gcm.bit_length_aad = req->assoclen * 8;
-	if (req->assoclen) {
-		rc = nx_gca(nx_ctx, req, csbcpb->cpb.aes_gcm.in_pat_or_aad);
+	csbcpb->cpb.aes_gcm.bit_length_aad = assoclen * 8;
+	if (assoclen) {
+		rc = nx_gca(nx_ctx, req, csbcpb->cpb.aes_gcm.in_pat_or_aad,
+			    assoclen);
 		if (rc)
 			goto out;
 	}
@@ -362,7 +368,6 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 		to_process = nbytes - processed;
 
 		csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
-		desc.tfm = (struct crypto_blkcipher *) req->base.tfm;
 		rc = nx_build_sg_lists(nx_ctx, &desc, req->dst,
 				       req->src, &to_process,
 				       processed + req->assoclen,
@@ -424,46 +429,56 @@ out:
 
 static int gcm_aes_nx_encrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 
 	memcpy(iv, req->iv, 12);
 
-	return gcm_aes_nx_crypt(req, 1);
+	return gcm_aes_nx_crypt(req, 1, req->assoclen);
 }
 
 static int gcm_aes_nx_decrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 
 	memcpy(iv, req->iv, 12);
 
-	return gcm_aes_nx_crypt(req, 0);
+	return gcm_aes_nx_crypt(req, 0, req->assoclen);
 }
 
 static int gcm4106_aes_nx_encrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_crypto_ctx *nx_ctx =
+		crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 	char *nonce = nx_ctx->priv.gcm.nonce;
 
 	memcpy(iv, nonce, NX_GCM4106_NONCE_LEN);
 	memcpy(iv + NX_GCM4106_NONCE_LEN, req->iv, 8);
 
-	return gcm_aes_nx_crypt(req, 1);
+	if (req->assoclen < 8)
+		return -EINVAL;
+
+	return gcm_aes_nx_crypt(req, 1, req->assoclen - 8);
 }
 
 static int gcm4106_aes_nx_decrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_crypto_ctx *nx_ctx =
+		crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 	char *nonce = nx_ctx->priv.gcm.nonce;
 
 	memcpy(iv, nonce, NX_GCM4106_NONCE_LEN);
 	memcpy(iv + NX_GCM4106_NONCE_LEN, req->iv, 8);
 
-	return gcm_aes_nx_crypt(req, 0);
+	if (req->assoclen < 8)
+		return -EINVAL;
+
+	return gcm_aes_nx_crypt(req, 0, req->assoclen - 8);
 }
 
 /* tell the block cipher walk routines that this is a stream cipher by
diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c
index 8c2faffab4a3..c2f7d4befb55 100644
--- a/drivers/crypto/nx/nx-aes-xcbc.c
+++ b/drivers/crypto/nx/nx-aes-xcbc.c
@@ -42,6 +42,7 @@ static int nx_xcbc_set_key(struct crypto_shash *desc,
 			   unsigned int         key_len)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_shash_ctx(desc);
+	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 
 	switch (key_len) {
 	case AES_KEYSIZE_128:
@@ -51,7 +52,7 @@ static int nx_xcbc_set_key(struct crypto_shash *desc,
 		return -EINVAL;
 	}
 
-	memcpy(nx_ctx->priv.xcbc.key, in_key, key_len);
+	memcpy(csbcpb->cpb.aes_xcbc.key, in_key, key_len);
 
 	return 0;
 }
@@ -148,32 +149,29 @@ out:
 	return rc;
 }
 
-static int nx_xcbc_init(struct shash_desc *desc)
+static int nx_crypto_ctx_aes_xcbc_init2(struct crypto_tfm *tfm)
 {
-	struct xcbc_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
-	struct nx_sg *out_sg;
-	int len;
+	int err;
 
-	nx_ctx_init(nx_ctx, HCOP_FC_AES);
+	err = nx_crypto_ctx_aes_xcbc_init(tfm);
+	if (err)
+		return err;
 
-	memset(sctx, 0, sizeof *sctx);
+	nx_ctx_init(nx_ctx, HCOP_FC_AES);
 
 	NX_CPB_SET_KEY_SIZE(csbcpb, NX_KS_AES_128);
 	csbcpb->cpb.hdr.mode = NX_MODE_AES_XCBC_MAC;
 
-	memcpy(csbcpb->cpb.aes_xcbc.key, nx_ctx->priv.xcbc.key, AES_BLOCK_SIZE);
-	memset(nx_ctx->priv.xcbc.key, 0, sizeof *nx_ctx->priv.xcbc.key);
-
-	len = AES_BLOCK_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, nx_ctx->ap->sglen);
+	return 0;
+}
 
-	if (len != AES_BLOCK_SIZE)
-		return -EINVAL;
+static int nx_xcbc_init(struct shash_desc *desc)
+{
+	struct xcbc_state *sctx = shash_desc_ctx(desc);
 
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+	memset(sctx, 0, sizeof *sctx);
 
 	return 0;
 }
@@ -186,6 +184,7 @@ static int nx_xcbc_update(struct shash_desc *desc,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u32 to_process = 0, leftover, total;
 	unsigned int max_sg_len;
 	unsigned long irq_flags;
@@ -213,6 +212,17 @@ static int nx_xcbc_update(struct shash_desc *desc,
 	max_sg_len = min_t(u64, max_sg_len,
 				nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = AES_BLOCK_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, nx_ctx->ap->sglen);
+
+	if (data_len != AES_BLOCK_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
 	do {
 		to_process = total - to_process;
 		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
@@ -235,8 +245,10 @@ static int nx_xcbc_update(struct shash_desc *desc,
 						(u8 *) sctx->buffer,
 						&data_len,
 						max_sg_len);
-			if (data_len != sctx->count)
-				return -EINVAL;
+			if (data_len != sctx->count) {
+				rc = -EINVAL;
+				goto out;
+			}
 		}
 
 		data_len = to_process - sctx->count;
@@ -245,8 +257,10 @@ static int nx_xcbc_update(struct shash_desc *desc,
 					&data_len,
 					max_sg_len);
 
-		if (data_len != to_process - sctx->count)
-			return -EINVAL;
+		if (data_len != to_process - sctx->count) {
+			rc = -EINVAL;
+			goto out;
+		}
 
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
 					sizeof(struct nx_sg);
@@ -325,15 +339,19 @@ static int nx_xcbc_final(struct shash_desc *desc, u8 *out)
 	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)sctx->buffer,
 				 &len, nx_ctx->ap->sglen);
 
-	if (len != sctx->count)
-		return -EINVAL;
+	if (len != sctx->count) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	len = AES_BLOCK_SIZE;
 	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len,
 				  nx_ctx->ap->sglen);
 
-	if (len != AES_BLOCK_SIZE)
-		return -EINVAL;
+	if (len != AES_BLOCK_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
@@ -372,7 +390,7 @@ struct shash_alg nx_shash_aes_xcbc_alg = {
 		.cra_blocksize   = AES_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_aes_xcbc_init,
+		.cra_init        = nx_crypto_ctx_aes_xcbc_init2,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 4e91bdb83c59..becb738c897b 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -29,34 +29,28 @@
 #include "nx.h"
 
 
-static int nx_sha256_init(struct shash_desc *desc)
+static int nx_crypto_ctx_sha256_init(struct crypto_tfm *tfm)
 {
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
-	struct nx_sg *out_sg;
-	int len;
-	u32 max_sg_len;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	int err;
 
-	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
+	err = nx_crypto_ctx_sha_init(tfm);
+	if (err)
+		return err;
 
-	memset(sctx, 0, sizeof *sctx);
+	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
 	nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA256];
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA256);
 
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+	return 0;
+}
 
-	len = SHA256_DIGEST_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, max_sg_len);
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+static int nx_sha256_init(struct shash_desc *desc) {
+	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (len != SHA256_DIGEST_SIZE)
-		return -EINVAL;
+	memset(sctx, 0, sizeof *sctx);
 
 	sctx->state[0] = __cpu_to_be32(SHA256_H0);
 	sctx->state[1] = __cpu_to_be32(SHA256_H1);
@@ -77,7 +71,7 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
-	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u64 to_process = 0, leftover, total;
 	unsigned long irq_flags;
 	int rc = 0;
@@ -102,24 +96,28 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
-	in_sg = nx_ctx->in_sg;
 	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
 			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = SHA256_DIGEST_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &data_len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	if (data_len != SHA256_DIGEST_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	do {
-		/*
-		 * to_process: the SHA256_BLOCK_SIZE data chunk to process in
-		 * this update. This value is also restricted by the sg list
-		 * limits.
-		 */
-		to_process = total - to_process;
-		to_process = to_process & ~(SHA256_BLOCK_SIZE - 1);
+		int used_sgs = 0;
+		struct nx_sg *in_sg = nx_ctx->in_sg;
 
 		if (buf_len) {
 			data_len = buf_len;
-			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+			in_sg = nx_build_sg_list(in_sg,
 						 (u8 *) sctx->buf,
 						 &data_len,
 						 max_sg_len);
@@ -128,15 +126,27 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 				rc = -EINVAL;
 				goto out;
 			}
+			used_sgs = in_sg - nx_ctx->in_sg;
 		}
 
+		/* to_process: SHA256_BLOCK_SIZE aligned chunk to be
+		 * processed in this iteration. This value is restricted
+		 * by sg list limits and number of sgs we already used
+		 * for leftover data. (see above)
+		 * In ideal case, we could allow NX_PAGE_SIZE * max_sg_len,
+		 * but because data may not be aligned, we need to account
+		 * for that too. */
+		to_process = min_t(u64, total,
+			(max_sg_len - 1 - used_sgs) * NX_PAGE_SIZE);
+		to_process = to_process & ~(SHA256_BLOCK_SIZE - 1);
+
 		data_len = to_process - buf_len;
 		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
 					 &data_len, max_sg_len);
 
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 
-		to_process = (data_len + buf_len);
+		to_process = data_len + buf_len;
 		leftover = total - to_process;
 
 		/*
@@ -282,7 +292,7 @@ struct shash_alg nx_shash_sha256_alg = {
 		.cra_blocksize   = SHA256_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_sha_init,
+		.cra_init        = nx_crypto_ctx_sha256_init,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index e6a58d2ee628..b6e183d58d73 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -28,34 +28,29 @@
 #include "nx.h"
 
 
-static int nx_sha512_init(struct shash_desc *desc)
+static int nx_crypto_ctx_sha512_init(struct crypto_tfm *tfm)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
-	struct nx_sg *out_sg;
-	int len;
-	u32 max_sg_len;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	int err;
 
-	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
+	err = nx_crypto_ctx_sha_init(tfm);
+	if (err)
+		return err;
 
-	memset(sctx, 0, sizeof *sctx);
+	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
 	nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA512];
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA512);
 
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+	return 0;
+}
 
-	len = SHA512_DIGEST_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, max_sg_len);
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+static int nx_sha512_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (len != SHA512_DIGEST_SIZE)
-		return -EINVAL;
+	memset(sctx, 0, sizeof *sctx);
 
 	sctx->state[0] = __cpu_to_be64(SHA512_H0);
 	sctx->state[1] = __cpu_to_be64(SHA512_H1);
@@ -76,7 +71,7 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
-	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u64 to_process, leftover = 0, total;
 	unsigned long irq_flags;
 	int rc = 0;
@@ -101,25 +96,28 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
-	in_sg = nx_ctx->in_sg;
 	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
 			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = SHA512_DIGEST_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &data_len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	if (data_len != SHA512_DIGEST_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	do {
-		/*
-		 * to_process: the SHA512_BLOCK_SIZE data chunk to process in
-		 * this update. This value is also restricted by the sg list
-		 * limits.
-		 */
-		to_process = total - leftover;
-		to_process = to_process & ~(SHA512_BLOCK_SIZE - 1);
-		leftover = total - to_process;
+		int used_sgs = 0;
+		struct nx_sg *in_sg = nx_ctx->in_sg;
 
 		if (buf_len) {
 			data_len = buf_len;
-			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+			in_sg = nx_build_sg_list(in_sg,
 						 (u8 *) sctx->buf,
 						 &data_len, max_sg_len);
 
@@ -127,8 +125,20 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 				rc = -EINVAL;
 				goto out;
 			}
+			used_sgs = in_sg - nx_ctx->in_sg;
 		}
 
+		/* to_process: SHA512_BLOCK_SIZE aligned chunk to be
+		 * processed in this iteration. This value is restricted
+		 * by sg list limits and number of sgs we already used
+		 * for leftover data. (see above)
+		 * In ideal case, we could allow NX_PAGE_SIZE * max_sg_len,
+		 * but because data may not be aligned, we need to account
+		 * for that too. */
+		to_process = min_t(u64, total,
+			(max_sg_len - 1 - used_sgs) * NX_PAGE_SIZE);
+		to_process = to_process & ~(SHA512_BLOCK_SIZE - 1);
+
 		data_len = to_process - buf_len;
 		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
 					 &data_len, max_sg_len);
@@ -140,7 +150,7 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 			goto out;
 		}
 
-		to_process = (data_len + buf_len);
+		to_process = data_len + buf_len;
 		leftover = total - to_process;
 
 		/*
@@ -288,7 +298,7 @@ struct shash_alg nx_shash_sha512_alg = {
 		.cra_blocksize   = SHA512_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_sha_init,
+		.cra_init        = nx_crypto_ctx_sha512_init,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index f6198f29a4a8..0794f1cc0018 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -596,13 +596,9 @@ static int nx_register_algs(void)
 	if (rc)
 		goto out_unreg_ecb;
 
-	rc = nx_register_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
-	if (rc)
-		goto out_unreg_cbc;
-
 	rc = nx_register_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 	if (rc)
-		goto out_unreg_ctr;
+		goto out_unreg_cbc;
 
 	rc = nx_register_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 	if (rc)
@@ -612,11 +608,11 @@ static int nx_register_algs(void)
 	if (rc)
 		goto out_unreg_gcm;
 
-	rc = nx_register_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+	rc = nx_register_aead(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 	if (rc)
 		goto out_unreg_gcm4106;
 
-	rc = nx_register_alg(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+	rc = nx_register_aead(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 	if (rc)
 		goto out_unreg_ccm;
 
@@ -644,17 +640,15 @@ out_unreg_s256:
 	nx_unregister_shash(&nx_shash_sha256_alg, NX_FC_SHA, NX_MODE_SHA,
 			    NX_PROPS_SHA256);
 out_unreg_ccm4309:
-	nx_unregister_alg(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+	nx_unregister_aead(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 out_unreg_ccm:
-	nx_unregister_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+	nx_unregister_aead(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 out_unreg_gcm4106:
 	nx_unregister_aead(&nx_gcm4106_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_gcm:
 	nx_unregister_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_ctr3686:
 	nx_unregister_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
-out_unreg_ctr:
-	nx_unregister_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 out_unreg_cbc:
 	nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 out_unreg_ecb:
@@ -711,14 +705,16 @@ static int nx_crypto_ctx_init(struct nx_crypto_ctx *nx_ctx, u32 fc, u32 mode)
 }
 
 /* entry points from the crypto tfm initializers */
-int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm)
+int nx_crypto_ctx_aes_ccm_init(struct crypto_aead *tfm)
 {
-	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
+	crypto_aead_set_reqsize(tfm, sizeof(struct nx_ccm_rctx));
+	return nx_crypto_ctx_init(crypto_aead_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_CCM);
 }
 
 int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm)
 {
+	crypto_aead_set_reqsize(tfm, sizeof(struct nx_gcm_rctx));
 	return nx_crypto_ctx_init(crypto_aead_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_GCM);
 }
@@ -810,16 +806,15 @@ static int nx_remove(struct vio_dev *viodev)
 				    NX_FC_SHA, NX_MODE_SHA, NX_PROPS_SHA256);
 		nx_unregister_shash(&nx_shash_sha256_alg,
 				    NX_FC_SHA, NX_MODE_SHA, NX_PROPS_SHA512);
-		nx_unregister_alg(&nx_ccm4309_aes_alg,
-				  NX_FC_AES, NX_MODE_AES_CCM);
-		nx_unregister_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+		nx_unregister_aead(&nx_ccm4309_aes_alg,
+				   NX_FC_AES, NX_MODE_AES_CCM);
+		nx_unregister_aead(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 		nx_unregister_aead(&nx_gcm4106_aes_alg,
 				   NX_FC_AES, NX_MODE_AES_GCM);
 		nx_unregister_aead(&nx_gcm_aes_alg,
 				   NX_FC_AES, NX_MODE_AES_GCM);
 		nx_unregister_alg(&nx_ctr3686_aes_alg,
 				  NX_FC_AES, NX_MODE_AES_CTR);
-		nx_unregister_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 		nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 		nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 	}
diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h
index de3ea8738146..9347878d4f30 100644
--- a/drivers/crypto/nx/nx.h
+++ b/drivers/crypto/nx/nx.h
@@ -2,6 +2,8 @@
 #ifndef __NX_H__
 #define __NX_H__
 
+#include <crypto/ctr.h>
+
 #define NX_NAME		"nx-crypto"
 #define NX_STRING	"IBM Power7+ Nest Accelerator Crypto Driver"
 #define NX_VERSION	"1.0"
@@ -91,8 +93,11 @@ struct nx_crypto_driver {
 
 #define NX_GCM4106_NONCE_LEN		(4)
 #define NX_GCM_CTR_OFFSET		(12)
-struct nx_gcm_priv {
+struct nx_gcm_rctx {
 	u8 iv[16];
+};
+
+struct nx_gcm_priv {
 	u8 iauth_tag[16];
 	u8 nonce[NX_GCM4106_NONCE_LEN];
 };
@@ -100,8 +105,11 @@ struct nx_gcm_priv {
 #define NX_CCM_AES_KEY_LEN		(16)
 #define NX_CCM4309_AES_KEY_LEN		(19)
 #define NX_CCM4309_NONCE_LEN		(3)
-struct nx_ccm_priv {
+struct nx_ccm_rctx {
 	u8 iv[16];
+};
+
+struct nx_ccm_priv {
 	u8 b0[16];
 	u8 iauth_tag[16];
 	u8 oauth_tag[16];
@@ -113,7 +121,7 @@ struct nx_xcbc_priv {
 };
 
 struct nx_ctr_priv {
-	u8 iv[16];
+	u8 nonce[CTR_RFC3686_NONCE_SIZE];
 };
 
 struct nx_crypto_ctx {
@@ -141,8 +149,10 @@ struct nx_crypto_ctx {
 	} priv;
 };
 
+struct crypto_aead;
+
 /* prototypes */
-int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm);
+int nx_crypto_ctx_aes_ccm_init(struct crypto_aead *tfm);
 int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm);
 int nx_crypto_ctx_aes_xcbc_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_ctr_init(struct crypto_tfm *tfm);
@@ -179,10 +189,9 @@ extern struct crypto_alg nx_cbc_aes_alg;
 extern struct crypto_alg nx_ecb_aes_alg;
 extern struct aead_alg nx_gcm_aes_alg;
 extern struct aead_alg nx_gcm4106_aes_alg;
-extern struct crypto_alg nx_ctr_aes_alg;
 extern struct crypto_alg nx_ctr3686_aes_alg;
-extern struct crypto_alg nx_ccm_aes_alg;
-extern struct crypto_alg nx_ccm4309_aes_alg;
+extern struct aead_alg nx_ccm_aes_alg;
+extern struct aead_alg nx_ccm4309_aes_alg;
 extern struct shash_alg nx_shash_aes_xcbc_alg;
 extern struct shash_alg nx_shash_sha512_alg;
 extern struct shash_alg nx_shash_sha256_alg;
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index 9a28b7e07c71..eba23147c0ee 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -52,29 +52,30 @@
 #define AES_REG_IV(dd, x)		((dd)->pdata->iv_ofs + ((x) * 0x04))
 
 #define AES_REG_CTRL(dd)		((dd)->pdata->ctrl_ofs)
-#define AES_REG_CTRL_CTR_WIDTH_MASK	(3 << 7)
-#define AES_REG_CTRL_CTR_WIDTH_32		(0 << 7)
-#define AES_REG_CTRL_CTR_WIDTH_64		(1 << 7)
-#define AES_REG_CTRL_CTR_WIDTH_96		(2 << 7)
-#define AES_REG_CTRL_CTR_WIDTH_128		(3 << 7)
-#define AES_REG_CTRL_CTR		(1 << 6)
-#define AES_REG_CTRL_CBC		(1 << 5)
-#define AES_REG_CTRL_KEY_SIZE		(3 << 3)
-#define AES_REG_CTRL_DIRECTION		(1 << 2)
-#define AES_REG_CTRL_INPUT_READY	(1 << 1)
-#define AES_REG_CTRL_OUTPUT_READY	(1 << 0)
+#define AES_REG_CTRL_CTR_WIDTH_MASK	GENMASK(8, 7)
+#define AES_REG_CTRL_CTR_WIDTH_32	0
+#define AES_REG_CTRL_CTR_WIDTH_64	BIT(7)
+#define AES_REG_CTRL_CTR_WIDTH_96	BIT(8)
+#define AES_REG_CTRL_CTR_WIDTH_128	GENMASK(8, 7)
+#define AES_REG_CTRL_CTR		BIT(6)
+#define AES_REG_CTRL_CBC		BIT(5)
+#define AES_REG_CTRL_KEY_SIZE		GENMASK(4, 3)
+#define AES_REG_CTRL_DIRECTION		BIT(2)
+#define AES_REG_CTRL_INPUT_READY	BIT(1)
+#define AES_REG_CTRL_OUTPUT_READY	BIT(0)
+#define AES_REG_CTRL_MASK		GENMASK(24, 2)
 
 #define AES_REG_DATA_N(dd, x)		((dd)->pdata->data_ofs + ((x) * 0x04))
 
 #define AES_REG_REV(dd)			((dd)->pdata->rev_ofs)
 
 #define AES_REG_MASK(dd)		((dd)->pdata->mask_ofs)
-#define AES_REG_MASK_SIDLE		(1 << 6)
-#define AES_REG_MASK_START		(1 << 5)
-#define AES_REG_MASK_DMA_OUT_EN		(1 << 3)
-#define AES_REG_MASK_DMA_IN_EN		(1 << 2)
-#define AES_REG_MASK_SOFTRESET		(1 << 1)
-#define AES_REG_AUTOIDLE		(1 << 0)
+#define AES_REG_MASK_SIDLE		BIT(6)
+#define AES_REG_MASK_START		BIT(5)
+#define AES_REG_MASK_DMA_OUT_EN		BIT(3)
+#define AES_REG_MASK_DMA_IN_EN		BIT(2)
+#define AES_REG_MASK_SOFTRESET		BIT(1)
+#define AES_REG_AUTOIDLE		BIT(0)
 
 #define AES_REG_LENGTH_N(x)		(0x54 + ((x) * 0x04))
 
@@ -254,7 +255,7 @@ static int omap_aes_write_ctrl(struct omap_aes_dev *dd)
 {
 	unsigned int key32;
 	int i, err;
-	u32 val, mask = 0;
+	u32 val;
 
 	err = omap_aes_hw_init(dd);
 	if (err)
@@ -274,17 +275,13 @@ static int omap_aes_write_ctrl(struct omap_aes_dev *dd)
 	val = FLD_VAL(((dd->ctx->keylen >> 3) - 1), 4, 3);
 	if (dd->flags & FLAGS_CBC)
 		val |= AES_REG_CTRL_CBC;
-	if (dd->flags & FLAGS_CTR) {
+	if (dd->flags & FLAGS_CTR)
 		val |= AES_REG_CTRL_CTR | AES_REG_CTRL_CTR_WIDTH_128;
-		mask = AES_REG_CTRL_CTR | AES_REG_CTRL_CTR_WIDTH_MASK;
-	}
+
 	if (dd->flags & FLAGS_ENCRYPT)
 		val |= AES_REG_CTRL_DIRECTION;
 
-	mask |= AES_REG_CTRL_CBC | AES_REG_CTRL_DIRECTION |
-			AES_REG_CTRL_KEY_SIZE;
-
-	omap_aes_write_mask(dd, AES_REG_CTRL(dd), val, mask);
+	omap_aes_write_mask(dd, AES_REG_CTRL(dd), val, AES_REG_CTRL_MASK);
 
 	return 0;
 }
@@ -558,6 +555,9 @@ static int omap_aes_check_aligned(struct scatterlist *sg, int total)
 {
 	int len = 0;
 
+	if (!IS_ALIGNED(total, AES_BLOCK_SIZE))
+		return -EINVAL;
+
 	while (sg) {
 		if (!IS_ALIGNED(sg->offset, 4))
 			return -1;
@@ -577,9 +577,10 @@ static int omap_aes_check_aligned(struct scatterlist *sg, int total)
 static int omap_aes_copy_sgs(struct omap_aes_dev *dd)
 {
 	void *buf_in, *buf_out;
-	int pages;
+	int pages, total;
 
-	pages = get_order(dd->total);
+	total = ALIGN(dd->total, AES_BLOCK_SIZE);
+	pages = get_order(total);
 
 	buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
 	buf_out = (void *)__get_free_pages(GFP_ATOMIC, pages);
@@ -594,11 +595,11 @@ static int omap_aes_copy_sgs(struct omap_aes_dev *dd)
 	sg_copy_buf(buf_in, dd->in_sg, 0, dd->total, 0);
 
 	sg_init_table(&dd->in_sgl, 1);
-	sg_set_buf(&dd->in_sgl, buf_in, dd->total);
+	sg_set_buf(&dd->in_sgl, buf_in, total);
 	dd->in_sg = &dd->in_sgl;
 
 	sg_init_table(&dd->out_sgl, 1);
-	sg_set_buf(&dd->out_sgl, buf_out, dd->total);
+	sg_set_buf(&dd->out_sgl, buf_out, total);
 	dd->out_sg = &dd->out_sgl;
 
 	return 0;
@@ -611,7 +612,7 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 	struct omap_aes_ctx *ctx;
 	struct omap_aes_reqctx *rctx;
 	unsigned long flags;
-	int err, ret = 0;
+	int err, ret = 0, len;
 
 	spin_lock_irqsave(&dd->lock, flags);
 	if (req)
@@ -650,8 +651,9 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 		dd->sgs_copied = 0;
 	}
 
-	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, dd->total);
-	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, dd->total);
+	len = ALIGN(dd->total, AES_BLOCK_SIZE);
+	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, len);
+	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, len);
 	BUG_ON(dd->in_sg_len < 0 || dd->out_sg_len < 0);
 
 	rctx = ablkcipher_request_ctx(req);
@@ -678,7 +680,7 @@ static void omap_aes_done_task(unsigned long data)
 {
 	struct omap_aes_dev *dd = (struct omap_aes_dev *)data;
 	void *buf_in, *buf_out;
-	int pages;
+	int pages, len;
 
 	pr_debug("enter done_task\n");
 
@@ -697,7 +699,8 @@ static void omap_aes_done_task(unsigned long data)
 
 		sg_copy_buf(buf_out, dd->orig_out, 0, dd->total_save, 1);
 
-		pages = get_order(dd->total_save);
+		len = ALIGN(dd->total_save, AES_BLOCK_SIZE);
+		pages = get_order(len);
 		free_pages((unsigned long)buf_in, pages);
 		free_pages((unsigned long)buf_out, pages);
 	}
@@ -726,11 +729,6 @@ static int omap_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 		  !!(mode & FLAGS_ENCRYPT),
 		  !!(mode & FLAGS_CBC));
 
-	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
-		pr_err("request size is not exact amount of AES blocks\n");
-		return -EINVAL;
-	}
-
 	dd = omap_aes_find_dev(ctx);
 	if (!dd)
 		return -ENODEV;
@@ -833,7 +831,7 @@ static struct crypto_alg algs_ecb_cbc[] = {
 {
 	.cra_name		= "ecb(aes)",
 	.cra_driver_name	= "ecb-aes-omap",
-	.cra_priority		= 100,
+	.cra_priority		= 300,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
 				  CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
@@ -855,7 +853,7 @@ static struct crypto_alg algs_ecb_cbc[] = {
 {
 	.cra_name		= "cbc(aes)",
 	.cra_driver_name	= "cbc-aes-omap",
-	.cra_priority		= 100,
+	.cra_priority		= 300,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
 				  CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
@@ -881,7 +879,7 @@ static struct crypto_alg algs_ctr[] = {
 {
 	.cra_name		= "ctr(aes)",
 	.cra_driver_name	= "ctr-aes-omap",
-	.cra_priority		= 100,
+	.cra_priority		= 300,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
 				  CRYPTO_ALG_KERN_DRIVER_ONLY |
 				  CRYPTO_ALG_ASYNC,
@@ -1046,9 +1044,7 @@ static irqreturn_t omap_aes_irq(int irq, void *dev_id)
 			}
 		}
 
-		dd->total -= AES_BLOCK_SIZE;
-
-		BUG_ON(dd->total < 0);
+		dd->total -= min_t(size_t, AES_BLOCK_SIZE, dd->total);
 
 		/* Clear IRQ status */
 		status &= ~AES_REG_IRQ_DATA_OUT;
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index 46307098f8ba..0a70e46d5416 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -536,9 +536,6 @@ static int omap_des_crypt_dma_stop(struct omap_des_dev *dd)
 	dmaengine_terminate_all(dd->dma_lch_in);
 	dmaengine_terminate_all(dd->dma_lch_out);
 
-	dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
-	dma_unmap_sg(dd->dev, dd->out_sg, dd->out_sg_len, DMA_FROM_DEVICE);
-
 	return err;
 }
 
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index b2024c95a3cf..48adb2a0903e 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -588,7 +588,7 @@ static int omap_sham_xmit_dma(struct omap_sham_dev *dd, dma_addr_t dma_addr,
 		 * the dmaengine may try to DMA the incorrect amount of data.
 		 */
 		sg_init_table(&ctx->sgl, 1);
-		ctx->sgl.page_link = ctx->sg->page_link;
+		sg_assign_page(&ctx->sgl, sg_page(ctx->sg));
 		ctx->sgl.offset = ctx->sg->offset;
 		sg_dma_len(&ctx->sgl) = len32;
 		sg_dma_address(&ctx->sgl) = sg_dma_address(ctx->sg);
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 4f56f3681abd..da36de26a4dc 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -99,11 +99,16 @@ struct spacc_req {
 	dma_addr_t			src_addr, dst_addr;
 	struct spacc_ddt		*src_ddt, *dst_ddt;
 	void				(*complete)(struct spacc_req *req);
+};
 
-	/* AEAD specific bits. */
-	u8				*giv;
-	size_t				giv_len;
-	dma_addr_t			giv_pa;
+struct spacc_aead {
+	unsigned long			ctrl_default;
+	unsigned long			type;
+	struct aead_alg			alg;
+	struct spacc_engine		*engine;
+	struct list_head		entry;
+	int				key_offs;
+	int				iv_offs;
 };
 
 struct spacc_engine {
@@ -121,6 +126,9 @@ struct spacc_engine {
 	struct spacc_alg		*algs;
 	unsigned			num_algs;
 	struct list_head		registered_algs;
+	struct spacc_aead		*aeads;
+	unsigned			num_aeads;
+	struct list_head		registered_aeads;
 	size_t				cipher_pg_sz;
 	size_t				hash_pg_sz;
 	const char			*name;
@@ -174,8 +182,6 @@ struct spacc_aead_ctx {
 	u8				cipher_key_len;
 	u8				hash_key_len;
 	struct crypto_aead		*sw_cipher;
-	size_t				auth_size;
-	u8				salt[AES_BLOCK_SIZE];
 };
 
 static int spacc_ablk_submit(struct spacc_req *req);
@@ -185,6 +191,11 @@ static inline struct spacc_alg *to_spacc_alg(struct crypto_alg *alg)
 	return alg ? container_of(alg, struct spacc_alg, alg) : NULL;
 }
 
+static inline struct spacc_aead *to_spacc_aead(struct aead_alg *alg)
+{
+	return container_of(alg, struct spacc_aead, alg);
+}
+
 static inline int spacc_fifo_cmd_full(struct spacc_engine *engine)
 {
 	u32 fifo_stat = readl(engine->regs + SPA_FIFO_STAT_REG_OFFSET);
@@ -310,120 +321,117 @@ out:
 	return NULL;
 }
 
-static int spacc_aead_make_ddts(struct spacc_req *req, u8 *giv)
+static int spacc_aead_make_ddts(struct aead_request *areq)
 {
-	struct aead_request *areq = container_of(req->req, struct aead_request,
-						 base);
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct spacc_req *req = aead_request_ctx(areq);
 	struct spacc_engine *engine = req->engine;
 	struct spacc_ddt *src_ddt, *dst_ddt;
-	unsigned ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(areq));
-	unsigned nents = sg_count(areq->src, areq->cryptlen);
 	unsigned total;
-	dma_addr_t iv_addr;
+	unsigned int src_nents, dst_nents;
 	struct scatterlist *cur;
-	int i, dst_ents, src_ents, assoc_ents;
-	u8 *iv = giv ? giv : areq->iv;
+	int i, dst_ents, src_ents;
+
+	total = areq->assoclen + areq->cryptlen;
+	if (req->is_encrypt)
+		total += crypto_aead_authsize(aead);
+
+	src_nents = sg_count(areq->src, total);
+	if (src_nents + 1 > MAX_DDT_LEN)
+		return -E2BIG;
+
+	dst_nents = 0;
+	if (areq->src != areq->dst) {
+		dst_nents = sg_count(areq->dst, total);
+		if (src_nents + 1 > MAX_DDT_LEN)
+			return -E2BIG;
+	}
 
 	src_ddt = dma_pool_alloc(engine->req_pool, GFP_ATOMIC, &req->src_addr);
 	if (!src_ddt)
-		return -ENOMEM;
+		goto err;
 
 	dst_ddt = dma_pool_alloc(engine->req_pool, GFP_ATOMIC, &req->dst_addr);
-	if (!dst_ddt) {
-		dma_pool_free(engine->req_pool, src_ddt, req->src_addr);
-		return -ENOMEM;
-	}
+	if (!dst_ddt)
+		goto err_free_src;
 
 	req->src_ddt = src_ddt;
 	req->dst_ddt = dst_ddt;
 
-	assoc_ents = dma_map_sg(engine->dev, areq->assoc,
-		sg_count(areq->assoc, areq->assoclen), DMA_TO_DEVICE);
-	if (areq->src != areq->dst) {
-		src_ents = dma_map_sg(engine->dev, areq->src, nents,
+	if (dst_nents) {
+		src_ents = dma_map_sg(engine->dev, areq->src, src_nents,
 				      DMA_TO_DEVICE);
-		dst_ents = dma_map_sg(engine->dev, areq->dst, nents,
+		if (!src_ents)
+			goto err_free_dst;
+
+		dst_ents = dma_map_sg(engine->dev, areq->dst, dst_nents,
 				      DMA_FROM_DEVICE);
+
+		if (!dst_ents) {
+			dma_unmap_sg(engine->dev, areq->src, src_nents,
+				     DMA_TO_DEVICE);
+			goto err_free_dst;
+		}
 	} else {
-		src_ents = dma_map_sg(engine->dev, areq->src, nents,
+		src_ents = dma_map_sg(engine->dev, areq->src, src_nents,
 				      DMA_BIDIRECTIONAL);
-		dst_ents = 0;
+		if (!src_ents)
+			goto err_free_dst;
+		dst_ents = src_ents;
 	}
 
 	/*
-	 * Map the IV/GIV. For the GIV it needs to be bidirectional as it is
-	 * formed by the crypto block and sent as the ESP IV for IPSEC.
+	 * Now map in the payload for the source and destination and terminate
+	 * with the NULL pointers.
 	 */
-	iv_addr = dma_map_single(engine->dev, iv, ivsize,
-				 giv ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE);
-	req->giv_pa = iv_addr;
+	for_each_sg(areq->src, cur, src_ents, i)
+		ddt_set(src_ddt++, sg_dma_address(cur), sg_dma_len(cur));
 
-	/*
-	 * Map the associated data. For decryption we don't copy the
-	 * associated data.
-	 */
-	total = areq->assoclen;
-	for_each_sg(areq->assoc, cur, assoc_ents, i) {
+	/* For decryption we need to skip the associated data. */
+	total = req->is_encrypt ? 0 : areq->assoclen;
+	for_each_sg(areq->dst, cur, dst_ents, i) {
 		unsigned len = sg_dma_len(cur);
 
-		if (len > total)
-			len = total;
-
-		total -= len;
+		if (len <= total) {
+			total -= len;
+			continue;
+		}
 
-		ddt_set(src_ddt++, sg_dma_address(cur), len);
-		if (req->is_encrypt)
-			ddt_set(dst_ddt++, sg_dma_address(cur), len);
+		ddt_set(dst_ddt++, sg_dma_address(cur) + total, len - total);
 	}
-	ddt_set(src_ddt++, iv_addr, ivsize);
-
-	if (giv || req->is_encrypt)
-		ddt_set(dst_ddt++, iv_addr, ivsize);
-
-	/*
-	 * Now map in the payload for the source and destination and terminate
-	 * with the NULL pointers.
-	 */
-	for_each_sg(areq->src, cur, src_ents, i) {
-		ddt_set(src_ddt++, sg_dma_address(cur), sg_dma_len(cur));
-		if (areq->src == areq->dst)
-			ddt_set(dst_ddt++, sg_dma_address(cur),
-				sg_dma_len(cur));
-	}
-
-	for_each_sg(areq->dst, cur, dst_ents, i)
-		ddt_set(dst_ddt++, sg_dma_address(cur),
-			sg_dma_len(cur));
 
 	ddt_set(src_ddt, 0, 0);
 	ddt_set(dst_ddt, 0, 0);
 
 	return 0;
+
+err_free_dst:
+	dma_pool_free(engine->req_pool, dst_ddt, req->dst_addr);
+err_free_src:
+	dma_pool_free(engine->req_pool, src_ddt, req->src_addr);
+err:
+	return -ENOMEM;
 }
 
 static void spacc_aead_free_ddts(struct spacc_req *req)
 {
 	struct aead_request *areq = container_of(req->req, struct aead_request,
 						 base);
-	struct spacc_alg *alg = to_spacc_alg(req->req->tfm->__crt_alg);
-	struct spacc_ablk_ctx *aead_ctx = crypto_tfm_ctx(req->req->tfm);
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	unsigned total = areq->assoclen + areq->cryptlen +
+			 (req->is_encrypt ? crypto_aead_authsize(aead) : 0);
+	struct spacc_aead_ctx *aead_ctx = crypto_aead_ctx(aead);
 	struct spacc_engine *engine = aead_ctx->generic.engine;
-	unsigned ivsize = alg->alg.cra_aead.ivsize;
-	unsigned nents = sg_count(areq->src, areq->cryptlen);
+	unsigned nents = sg_count(areq->src, total);
 
 	if (areq->src != areq->dst) {
 		dma_unmap_sg(engine->dev, areq->src, nents, DMA_TO_DEVICE);
 		dma_unmap_sg(engine->dev, areq->dst,
-			     sg_count(areq->dst, areq->cryptlen),
+			     sg_count(areq->dst, total),
 			     DMA_FROM_DEVICE);
 	} else
 		dma_unmap_sg(engine->dev, areq->src, nents, DMA_BIDIRECTIONAL);
 
-	dma_unmap_sg(engine->dev, areq->assoc,
-		     sg_count(areq->assoc, areq->assoclen), DMA_TO_DEVICE);
-
-	dma_unmap_single(engine->dev, req->giv_pa, ivsize, DMA_BIDIRECTIONAL);
-
 	dma_pool_free(engine->req_pool, req->src_ddt, req->src_addr);
 	dma_pool_free(engine->req_pool, req->dst_ddt, req->dst_addr);
 }
@@ -438,65 +446,22 @@ static void spacc_free_ddt(struct spacc_req *req, struct spacc_ddt *ddt,
 	dma_pool_free(req->engine->req_pool, ddt, ddt_addr);
 }
 
-/*
- * Set key for a DES operation in an AEAD cipher. This also performs weak key
- * checking if required.
- */
-static int spacc_aead_des_setkey(struct crypto_aead *aead, const u8 *key,
-				 unsigned int len)
-{
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 tmp[DES_EXPKEY_WORDS];
-
-	if (unlikely(!des_ekey(tmp, key)) &&
-	    (crypto_aead_get_flags(aead)) & CRYPTO_TFM_REQ_WEAK_KEY) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		return -EINVAL;
-	}
-
-	memcpy(ctx->cipher_key, key, len);
-	ctx->cipher_key_len = len;
-
-	return 0;
-}
-
-/* Set the key for the AES block cipher component of the AEAD transform. */
-static int spacc_aead_aes_setkey(struct crypto_aead *aead, const u8 *key,
-				 unsigned int len)
-{
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	/*
-	 * IPSec engine only supports 128 and 256 bit AES keys. If we get a
-	 * request for any other size (192 bits) then we need to do a software
-	 * fallback.
-	 */
-	if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256) {
-		/*
-		 * Set the fallback transform to use the same request flags as
-		 * the hardware transform.
-		 */
-		ctx->sw_cipher->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-		ctx->sw_cipher->base.crt_flags |=
-			tfm->crt_flags & CRYPTO_TFM_REQ_MASK;
-		return crypto_aead_setkey(ctx->sw_cipher, key, len);
-	}
-
-	memcpy(ctx->cipher_key, key, len);
-	ctx->cipher_key_len = len;
-
-	return 0;
-}
-
 static int spacc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 			     unsigned int keylen)
 {
 	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
-	struct spacc_alg *alg = to_spacc_alg(tfm->base.__crt_alg);
 	struct crypto_authenc_keys keys;
-	int err = -EINVAL;
+	int err;
+
+	crypto_aead_clear_flags(ctx->sw_cipher, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(ctx->sw_cipher, crypto_aead_get_flags(tfm) &
+					      CRYPTO_TFM_REQ_MASK);
+	err = crypto_aead_setkey(ctx->sw_cipher, key, keylen);
+	crypto_aead_clear_flags(tfm, CRYPTO_TFM_RES_MASK);
+	crypto_aead_set_flags(tfm, crypto_aead_get_flags(ctx->sw_cipher) &
+				   CRYPTO_TFM_RES_MASK);
+	if (err)
+		return err;
 
 	if (crypto_authenc_extractkeys(&keys, key, keylen) != 0)
 		goto badkey;
@@ -507,14 +472,8 @@ static int spacc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 	if (keys.authkeylen > sizeof(ctx->hash_ctx))
 		goto badkey;
 
-	if ((alg->ctrl_default & SPACC_CRYPTO_ALG_MASK) ==
-	    SPA_CTRL_CIPH_ALG_AES)
-		err = spacc_aead_aes_setkey(tfm, keys.enckey, keys.enckeylen);
-	else
-		err = spacc_aead_des_setkey(tfm, keys.enckey, keys.enckeylen);
-
-	if (err)
-		goto badkey;
+	memcpy(ctx->cipher_key, keys.enckey, keys.enckeylen);
+	ctx->cipher_key_len = keys.enckeylen;
 
 	memcpy(ctx->hash_ctx, keys.authkey, keys.authkeylen);
 	ctx->hash_key_len = keys.authkeylen;
@@ -531,9 +490,7 @@ static int spacc_aead_setauthsize(struct crypto_aead *tfm,
 {
 	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(crypto_aead_tfm(tfm));
 
-	ctx->auth_size = authsize;
-
-	return 0;
+	return crypto_aead_setauthsize(ctx->sw_cipher, authsize);
 }
 
 /*
@@ -541,15 +498,13 @@ static int spacc_aead_setauthsize(struct crypto_aead *tfm,
  * be completed in hardware because the hardware may not support certain key
  * sizes. In these cases we need to complete the request in software.
  */
-static int spacc_aead_need_fallback(struct spacc_req *req)
+static int spacc_aead_need_fallback(struct aead_request *aead_req)
 {
-	struct aead_request *aead_req;
-	struct crypto_tfm *tfm = req->req->tfm;
-	struct crypto_alg *alg = req->req->tfm->__crt_alg;
-	struct spacc_alg *spacc_alg = to_spacc_alg(alg);
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct spacc_aead *spacc_alg = to_spacc_aead(alg);
+	struct spacc_aead_ctx *ctx = crypto_aead_ctx(aead);
 
-	aead_req = container_of(req->req, struct aead_request, base);
 	/*
 	 * If we have a non-supported key-length, then we need to do a
 	 * software fallback.
@@ -568,22 +523,17 @@ static int spacc_aead_do_fallback(struct aead_request *req, unsigned alg_type,
 {
 	struct crypto_tfm *old_tfm = crypto_aead_tfm(crypto_aead_reqtfm(req));
 	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(old_tfm);
-	int err;
+	struct aead_request *subreq = aead_request_ctx(req);
 
-	if (ctx->sw_cipher) {
-		/*
-		 * Change the request to use the software fallback transform,
-		 * and once the ciphering has completed, put the old transform
-		 * back into the request.
-		 */
-		aead_request_set_tfm(req, ctx->sw_cipher);
-		err = is_encrypt ? crypto_aead_encrypt(req) :
-		    crypto_aead_decrypt(req);
-		aead_request_set_tfm(req, __crypto_aead_cast(old_tfm));
-	} else
-		err = -EINVAL;
+	aead_request_set_tfm(subreq, ctx->sw_cipher);
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
+			       req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
 
-	return err;
+	return is_encrypt ? crypto_aead_encrypt(subreq) :
+			    crypto_aead_decrypt(subreq);
 }
 
 static void spacc_aead_complete(struct spacc_req *req)
@@ -594,18 +544,19 @@ static void spacc_aead_complete(struct spacc_req *req)
 
 static int spacc_aead_submit(struct spacc_req *req)
 {
-	struct crypto_tfm *tfm = req->req->tfm;
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_alg *alg = req->req->tfm->__crt_alg;
-	struct spacc_alg *spacc_alg = to_spacc_alg(alg);
-	struct spacc_engine *engine = ctx->generic.engine;
-	u32 ctrl, proc_len, assoc_len;
 	struct aead_request *aead_req =
 		container_of(req->req, struct aead_request, base);
+	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
+	unsigned int authsize = crypto_aead_authsize(aead);
+	struct spacc_aead_ctx *ctx = crypto_aead_ctx(aead);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct spacc_aead *spacc_alg = to_spacc_aead(alg);
+	struct spacc_engine *engine = ctx->generic.engine;
+	u32 ctrl, proc_len, assoc_len;
 
 	req->result = -EINPROGRESS;
 	req->ctx_id = spacc_load_ctx(&ctx->generic, ctx->cipher_key,
-		ctx->cipher_key_len, aead_req->iv, alg->cra_aead.ivsize,
+		ctx->cipher_key_len, aead_req->iv, crypto_aead_ivsize(aead),
 		ctx->hash_ctx, ctx->hash_key_len);
 
 	/* Set the source and destination DDT pointers. */
@@ -617,25 +568,15 @@ static int spacc_aead_submit(struct spacc_req *req)
 	proc_len = aead_req->cryptlen + assoc_len;
 
 	/*
-	 * If we aren't generating an IV, then we need to include the IV in the
-	 * associated data so that it is included in the hash.
-	 */
-	if (!req->giv) {
-		assoc_len += crypto_aead_ivsize(crypto_aead_reqtfm(aead_req));
-		proc_len += crypto_aead_ivsize(crypto_aead_reqtfm(aead_req));
-	} else
-		proc_len += req->giv_len;
-
-	/*
 	 * If we are decrypting, we need to take the length of the ICV out of
 	 * the processing length.
 	 */
 	if (!req->is_encrypt)
-		proc_len -= ctx->auth_size;
+		proc_len -= authsize;
 
 	writel(proc_len, engine->regs + SPA_PROC_LEN_REG_OFFSET);
 	writel(assoc_len, engine->regs + SPA_AAD_LEN_REG_OFFSET);
-	writel(ctx->auth_size, engine->regs + SPA_ICV_LEN_REG_OFFSET);
+	writel(authsize, engine->regs + SPA_ICV_LEN_REG_OFFSET);
 	writel(0, engine->regs + SPA_ICV_OFFSET_REG_OFFSET);
 	writel(0, engine->regs + SPA_AUX_INFO_REG_OFFSET);
 
@@ -674,32 +615,29 @@ static void spacc_push(struct spacc_engine *engine)
 /*
  * Setup an AEAD request for processing. This will configure the engine, load
  * the context and then start the packet processing.
- *
- * @giv Pointer to destination address for a generated IV. If the
- *	request does not need to generate an IV then this should be set to NULL.
  */
-static int spacc_aead_setup(struct aead_request *req, u8 *giv,
+static int spacc_aead_setup(struct aead_request *req,
 			    unsigned alg_type, bool is_encrypt)
 {
-	struct crypto_alg *alg = req->base.tfm->__crt_alg;
-	struct spacc_engine *engine = to_spacc_alg(alg)->engine;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct spacc_engine *engine = to_spacc_aead(alg)->engine;
 	struct spacc_req *dev_req = aead_request_ctx(req);
-	int err = -EINPROGRESS;
+	int err;
 	unsigned long flags;
-	unsigned ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(req));
 
-	dev_req->giv		= giv;
-	dev_req->giv_len	= ivsize;
 	dev_req->req		= &req->base;
 	dev_req->is_encrypt	= is_encrypt;
 	dev_req->result		= -EBUSY;
 	dev_req->engine		= engine;
 	dev_req->complete	= spacc_aead_complete;
 
-	if (unlikely(spacc_aead_need_fallback(dev_req)))
+	if (unlikely(spacc_aead_need_fallback(req) ||
+		     ((err = spacc_aead_make_ddts(req)) == -E2BIG)))
 		return spacc_aead_do_fallback(req, alg_type, is_encrypt);
 
-	spacc_aead_make_ddts(dev_req, dev_req->giv);
+	if (err)
+		goto out;
 
 	err = -EINPROGRESS;
 	spin_lock_irqsave(&engine->hw_lock, flags);
@@ -728,70 +666,44 @@ out:
 static int spacc_aead_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
-	struct spacc_alg *alg = to_spacc_alg(tfm->__crt_alg);
+	struct spacc_aead *alg = to_spacc_aead(crypto_aead_alg(aead));
 
-	return spacc_aead_setup(req, NULL, alg->type, 1);
-}
-
-static int spacc_aead_givencrypt(struct aead_givcrypt_request *req)
-{
-	struct crypto_aead *tfm = aead_givcrypt_reqtfm(req);
-	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
-	size_t ivsize = crypto_aead_ivsize(tfm);
-	struct spacc_alg *alg = to_spacc_alg(tfm->base.__crt_alg);
-	unsigned len;
-	__be64 seq;
-
-	memcpy(req->areq.iv, ctx->salt, ivsize);
-	len = ivsize;
-	if (ivsize > sizeof(u64)) {
-		memset(req->giv, 0, ivsize - sizeof(u64));
-		len = sizeof(u64);
-	}
-	seq = cpu_to_be64(req->seq);
-	memcpy(req->giv + ivsize - len, &seq, len);
-
-	return spacc_aead_setup(&req->areq, req->giv, alg->type, 1);
+	return spacc_aead_setup(req, alg->type, 1);
 }
 
 static int spacc_aead_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
-	struct spacc_alg *alg = to_spacc_alg(tfm->__crt_alg);
+	struct spacc_aead  *alg = to_spacc_aead(crypto_aead_alg(aead));
 
-	return spacc_aead_setup(req, NULL, alg->type, 0);
+	return spacc_aead_setup(req, alg->type, 0);
 }
 
 /*
  * Initialise a new AEAD context. This is responsible for allocating the
  * fallback cipher and initialising the context.
  */
-static int spacc_aead_cra_init(struct crypto_tfm *tfm)
+static int spacc_aead_cra_init(struct crypto_aead *tfm)
 {
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct spacc_alg *spacc_alg = to_spacc_alg(alg);
+	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct spacc_aead *spacc_alg = to_spacc_aead(alg);
 	struct spacc_engine *engine = spacc_alg->engine;
 
 	ctx->generic.flags = spacc_alg->type;
 	ctx->generic.engine = engine;
-	ctx->sw_cipher = crypto_alloc_aead(alg->cra_name, 0,
-					   CRYPTO_ALG_ASYNC |
+	ctx->sw_cipher = crypto_alloc_aead(alg->base.cra_name, 0,
 					   CRYPTO_ALG_NEED_FALLBACK);
-	if (IS_ERR(ctx->sw_cipher)) {
-		dev_warn(engine->dev, "failed to allocate fallback for %s\n",
-			 alg->cra_name);
-		ctx->sw_cipher = NULL;
-	}
+	if (IS_ERR(ctx->sw_cipher))
+		return PTR_ERR(ctx->sw_cipher);
 	ctx->generic.key_offs = spacc_alg->key_offs;
 	ctx->generic.iv_offs = spacc_alg->iv_offs;
 
-	get_random_bytes(ctx->salt, sizeof(ctx->salt));
-
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
-				sizeof(struct spacc_req));
+	crypto_aead_set_reqsize(
+		tfm,
+		max(sizeof(struct spacc_req),
+		    sizeof(struct aead_request) +
+		    crypto_aead_reqsize(ctx->sw_cipher)));
 
 	return 0;
 }
@@ -800,13 +712,11 @@ static int spacc_aead_cra_init(struct crypto_tfm *tfm)
  * Destructor for an AEAD context. This is called when the transform is freed
  * and must free the fallback cipher.
  */
-static void spacc_aead_cra_exit(struct crypto_tfm *tfm)
+static void spacc_aead_cra_exit(struct crypto_aead *tfm)
 {
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
 
-	if (ctx->sw_cipher)
-		crypto_free_aead(ctx->sw_cipher);
-	ctx->sw_cipher = NULL;
+	crypto_free_aead(ctx->sw_cipher);
 }
 
 /*
@@ -1458,180 +1368,188 @@ static struct spacc_alg ipsec_engine_algs[] = {
 			.cra_exit = spacc_ablk_cra_exit,
 		},
 	},
+};
+
+static struct spacc_aead ipsec_engine_aeads[] = {
 	{
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_SHA | SPA_CTRL_HASH_MODE_HMAC,
+		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
+				SPA_CTRL_CIPH_MODE_CBC |
+				SPA_CTRL_HASH_ALG_SHA |
+				SPA_CTRL_HASH_MODE_HMAC,
 		.key_offs = 0,
 		.iv_offs = AES_MAX_KEY_SIZE,
 		.alg = {
-			.cra_name = "authenc(hmac(sha1),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha1-cbc-aes-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-			.cra_type = &crypto_aead_type,
-			.cra_module = THIS_MODULE,
-			.cra_aead = {
-				.setkey = spacc_aead_setkey,
-				.setauthsize = spacc_aead_setauthsize,
-				.encrypt = spacc_aead_encrypt,
-				.decrypt = spacc_aead_decrypt,
-				.givencrypt = spacc_aead_givencrypt,
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA1_DIGEST_SIZE,
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-aes-picoxcell",
+				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
+				.cra_module = THIS_MODULE,
 			},
-			.cra_init = spacc_aead_cra_init,
-			.cra_exit = spacc_aead_cra_exit,
+			.setkey = spacc_aead_setkey,
+			.setauthsize = spacc_aead_setauthsize,
+			.encrypt = spacc_aead_encrypt,
+			.decrypt = spacc_aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+			.init = spacc_aead_cra_init,
+			.exit = spacc_aead_cra_exit,
 		},
 	},
 	{
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_CBC |
+		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
+				SPA_CTRL_CIPH_MODE_CBC |
 				SPA_CTRL_HASH_ALG_SHA256 |
 				SPA_CTRL_HASH_MODE_HMAC,
 		.key_offs = 0,
 		.iv_offs = AES_MAX_KEY_SIZE,
 		.alg = {
-			.cra_name = "authenc(hmac(sha256),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha256-cbc-aes-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-			.cra_type = &crypto_aead_type,
-			.cra_module = THIS_MODULE,
-			.cra_aead = {
-				.setkey = spacc_aead_setkey,
-				.setauthsize = spacc_aead_setauthsize,
-				.encrypt = spacc_aead_encrypt,
-				.decrypt = spacc_aead_decrypt,
-				.givencrypt = spacc_aead_givencrypt,
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA256_DIGEST_SIZE,
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-aes-picoxcell",
+				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
+				.cra_module = THIS_MODULE,
 			},
-			.cra_init = spacc_aead_cra_init,
-			.cra_exit = spacc_aead_cra_exit,
+			.setkey = spacc_aead_setkey,
+			.setauthsize = spacc_aead_setauthsize,
+			.encrypt = spacc_aead_encrypt,
+			.decrypt = spacc_aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+			.init = spacc_aead_cra_init,
+			.exit = spacc_aead_cra_exit,
 		},
 	},
 	{
 		.key_offs = 0,
 		.iv_offs = AES_MAX_KEY_SIZE,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_MD5 | SPA_CTRL_HASH_MODE_HMAC,
+		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
+				SPA_CTRL_CIPH_MODE_CBC |
+				SPA_CTRL_HASH_ALG_MD5 |
+				SPA_CTRL_HASH_MODE_HMAC,
 		.alg = {
-			.cra_name = "authenc(hmac(md5),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-md5-cbc-aes-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-			.cra_type = &crypto_aead_type,
-			.cra_module = THIS_MODULE,
-			.cra_aead = {
-				.setkey = spacc_aead_setkey,
-				.setauthsize = spacc_aead_setauthsize,
-				.encrypt = spacc_aead_encrypt,
-				.decrypt = spacc_aead_decrypt,
-				.givencrypt = spacc_aead_givencrypt,
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = MD5_DIGEST_SIZE,
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-aes-picoxcell",
+				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
+				.cra_module = THIS_MODULE,
 			},
-			.cra_init = spacc_aead_cra_init,
-			.cra_exit = spacc_aead_cra_exit,
+			.setkey = spacc_aead_setkey,
+			.setauthsize = spacc_aead_setauthsize,
+			.encrypt = spacc_aead_encrypt,
+			.decrypt = spacc_aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+			.init = spacc_aead_cra_init,
+			.exit = spacc_aead_cra_exit,
 		},
 	},
 	{
 		.key_offs = DES_BLOCK_SIZE,
 		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_SHA | SPA_CTRL_HASH_MODE_HMAC,
+		.ctrl_default = SPA_CTRL_CIPH_ALG_DES |
+				SPA_CTRL_CIPH_MODE_CBC |
+				SPA_CTRL_HASH_ALG_SHA |
+				SPA_CTRL_HASH_MODE_HMAC,
 		.alg = {
-			.cra_name = "authenc(hmac(sha1),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha1-cbc-3des-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-			.cra_type = &crypto_aead_type,
-			.cra_module = THIS_MODULE,
-			.cra_aead = {
-				.setkey = spacc_aead_setkey,
-				.setauthsize = spacc_aead_setauthsize,
-				.encrypt = spacc_aead_encrypt,
-				.decrypt = spacc_aead_decrypt,
-				.givencrypt = spacc_aead_givencrypt,
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA1_DIGEST_SIZE,
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-3des-picoxcell",
+				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
+				.cra_module = THIS_MODULE,
 			},
-			.cra_init = spacc_aead_cra_init,
-			.cra_exit = spacc_aead_cra_exit,
+			.setkey = spacc_aead_setkey,
+			.setauthsize = spacc_aead_setauthsize,
+			.encrypt = spacc_aead_encrypt,
+			.decrypt = spacc_aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+			.init = spacc_aead_cra_init,
+			.exit = spacc_aead_cra_exit,
 		},
 	},
 	{
 		.key_offs = DES_BLOCK_SIZE,
 		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_CBC |
+		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
+				SPA_CTRL_CIPH_MODE_CBC |
 				SPA_CTRL_HASH_ALG_SHA256 |
 				SPA_CTRL_HASH_MODE_HMAC,
 		.alg = {
-			.cra_name = "authenc(hmac(sha256),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha256-cbc-3des-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-			.cra_type = &crypto_aead_type,
-			.cra_module = THIS_MODULE,
-			.cra_aead = {
-				.setkey = spacc_aead_setkey,
-				.setauthsize = spacc_aead_setauthsize,
-				.encrypt = spacc_aead_encrypt,
-				.decrypt = spacc_aead_decrypt,
-				.givencrypt = spacc_aead_givencrypt,
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA256_DIGEST_SIZE,
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-3des-picoxcell",
+				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
+				.cra_module = THIS_MODULE,
 			},
-			.cra_init = spacc_aead_cra_init,
-			.cra_exit = spacc_aead_cra_exit,
+			.setkey = spacc_aead_setkey,
+			.setauthsize = spacc_aead_setauthsize,
+			.encrypt = spacc_aead_encrypt,
+			.decrypt = spacc_aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+			.init = spacc_aead_cra_init,
+			.exit = spacc_aead_cra_exit,
 		},
 	},
 	{
 		.key_offs = DES_BLOCK_SIZE,
 		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_MD5 | SPA_CTRL_HASH_MODE_HMAC,
+		.ctrl_default = SPA_CTRL_CIPH_ALG_DES |
+				SPA_CTRL_CIPH_MODE_CBC |
+				SPA_CTRL_HASH_ALG_MD5 |
+				SPA_CTRL_HASH_MODE_HMAC,
 		.alg = {
-			.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-md5-cbc-3des-picoxcell",
-			.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD |
-					CRYPTO_ALG_ASYNC |
-					CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-			.cra_type = &crypto_aead_type,
-			.cra_module = THIS_MODULE,
-			.cra_aead = {
-				.setkey = spacc_aead_setkey,
-				.setauthsize = spacc_aead_setauthsize,
-				.encrypt = spacc_aead_encrypt,
-				.decrypt = spacc_aead_decrypt,
-				.givencrypt = spacc_aead_givencrypt,
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = MD5_DIGEST_SIZE,
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-3des-picoxcell",
+				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
+				.cra_module = THIS_MODULE,
 			},
-			.cra_init = spacc_aead_cra_init,
-			.cra_exit = spacc_aead_cra_exit,
+			.setkey = spacc_aead_setkey,
+			.setauthsize = spacc_aead_setauthsize,
+			.encrypt = spacc_aead_encrypt,
+			.decrypt = spacc_aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+			.init = spacc_aead_cra_init,
+			.exit = spacc_aead_cra_exit,
 		},
 	},
 };
@@ -1707,6 +1625,8 @@ static int spacc_probe(struct platform_device *pdev)
 		engine->fifo_sz		= SPACC_CRYPTO_IPSEC_FIFO_SZ;
 		engine->algs		= ipsec_engine_algs;
 		engine->num_algs	= ARRAY_SIZE(ipsec_engine_algs);
+		engine->aeads		= ipsec_engine_aeads;
+		engine->num_aeads	= ARRAY_SIZE(ipsec_engine_aeads);
 	} else if (spacc_is_compatible(pdev, "picochip,spacc-l2")) {
 		engine->max_ctxs	= SPACC_CRYPTO_L2_MAX_CTXS;
 		engine->cipher_pg_sz	= SPACC_CRYPTO_L2_CIPHER_PG_SZ;
@@ -1815,17 +1735,40 @@ static int spacc_probe(struct platform_device *pdev)
 				engine->algs[i].alg.cra_name);
 	}
 
+	INIT_LIST_HEAD(&engine->registered_aeads);
+	for (i = 0; i < engine->num_aeads; ++i) {
+		engine->aeads[i].engine = engine;
+		err = crypto_register_aead(&engine->aeads[i].alg);
+		if (!err) {
+			list_add_tail(&engine->aeads[i].entry,
+				      &engine->registered_aeads);
+			ret = 0;
+		}
+		if (err)
+			dev_err(engine->dev, "failed to register alg \"%s\"\n",
+				engine->aeads[i].alg.base.cra_name);
+		else
+			dev_dbg(engine->dev, "registered alg \"%s\"\n",
+				engine->aeads[i].alg.base.cra_name);
+	}
+
 	return ret;
 }
 
 static int spacc_remove(struct platform_device *pdev)
 {
+	struct spacc_aead *aead, *an;
 	struct spacc_alg *alg, *next;
 	struct spacc_engine *engine = platform_get_drvdata(pdev);
 
 	del_timer_sync(&engine->packet_timeout);
 	device_remove_file(&pdev->dev, &dev_attr_stat_irq_thresh);
 
+	list_for_each_entry_safe(aead, an, &engine->registered_aeads, entry) {
+		list_del(&aead->entry);
+		crypto_unregister_aead(&aead->alg);
+	}
+
 	list_for_each_entry_safe(alg, next, &engine->registered_algs, entry) {
 		list_del(&alg->entry);
 		crypto_unregister_alg(&alg->alg);
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 6fdb9e8b22a7..eefccf7b8be7 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -3,11 +3,13 @@ config CRYPTO_DEV_QAT
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_AKCIPHER
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
 	select FW_LOADER
+	select ASN1
 
 config CRYPTO_DEV_QAT_DH895xCC
 	tristate "Support for Intel(R) DH895xCC"
@@ -19,3 +21,16 @@ config CRYPTO_DEV_QAT_DH895xCC
 
 	  To compile this as a module, choose M here: the module
 	  will be called qat_dh895xcc.
+
+config CRYPTO_DEV_QAT_DH895xCCVF
+	tristate "Support for Intel(R) DH895xCC Virtual Function"
+	depends on X86 && PCI
+	select PCI_IOV
+	select CRYPTO_DEV_QAT
+
+	help
+	  Support for Intel(R) DH895xcc with Intel(R) QuickAssist Technology
+	  Virtual Function for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_dh895xccvf.
diff --git a/drivers/crypto/qat/Makefile b/drivers/crypto/qat/Makefile
index d11481be225e..a3ce0b70e32f 100644
--- a/drivers/crypto/qat/Makefile
+++ b/drivers/crypto/qat/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat_common/
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc/
+obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCCVF) += qat_dh895xccvf/
diff --git a/drivers/crypto/qat/qat_common/.gitignore b/drivers/crypto/qat/qat_common/.gitignore
new file mode 100644
index 000000000000..ee328374dba8
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/.gitignore
@@ -0,0 +1 @@
+*-asn1.[ch]
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index e0424dc382fe..df20a9de1c58 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -1,3 +1,6 @@
+$(obj)/qat_rsakey-asn1.o: $(obj)/qat_rsakey-asn1.c $(obj)/qat_rsakey-asn1.h
+clean-files += qat_rsakey-asn1.c qat_rsakey-asn1.h
+
 obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o
 intel_qat-objs := adf_cfg.o \
 	adf_ctl_drv.o \
@@ -6,9 +9,14 @@ intel_qat-objs := adf_cfg.o \
 	adf_accel_engine.o \
 	adf_aer.o \
 	adf_transport.o \
+	adf_admin.o \
+	adf_hw_arbiter.o \
 	qat_crypto.o \
 	qat_algs.o \
+	qat_rsakey-asn1.o \
+	qat_asym_algs.o \
 	qat_uclo.o \
 	qat_hal.o
 
 intel_qat-$(CONFIG_DEBUG_FS) += adf_transport_debug.o
+intel_qat-$(CONFIG_PCI_IOV) += adf_sriov.o adf_pf2vf_msg.o
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index 5fe902967620..ca853d50b4b7 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -46,13 +46,17 @@
 */
 #ifndef ADF_ACCEL_DEVICES_H_
 #define ADF_ACCEL_DEVICES_H_
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/io.h>
+#include <linux/ratelimit.h>
 #include "adf_cfg_common.h"
 
 #define ADF_DH895XCC_DEVICE_NAME "dh895xcc"
+#define ADF_DH895XCCVF_DEVICE_NAME "dh895xccvf"
 #define ADF_DH895XCC_PCI_DEVICE_ID 0x435
+#define ADF_DH895XCCIOV_PCI_DEVICE_ID 0x443
 #define ADF_PCI_MAX_BARS 3
 #define ADF_DEVICE_NAME_LENGTH 32
 #define ADF_ETR_MAX_RINGS_PER_BANK 16
@@ -79,6 +83,7 @@ struct adf_bar {
 struct adf_accel_msix {
 	struct msix_entry *entries;
 	char **names;
+	u32 num_entries;
 } __packed;
 
 struct adf_accel_pci {
@@ -99,6 +104,7 @@ enum dev_sku_info {
 	DEV_SKU_2,
 	DEV_SKU_3,
 	DEV_SKU_4,
+	DEV_SKU_VF,
 	DEV_SKU_UNKNOWN,
 };
 
@@ -113,6 +119,8 @@ static inline const char *get_sku_info(enum dev_sku_info info)
 		return "SKU3";
 	case DEV_SKU_4:
 		return "SKU4";
+	case DEV_SKU_VF:
+		return "SKUVF";
 	case DEV_SKU_UNKNOWN:
 	default:
 		break;
@@ -135,23 +143,29 @@ struct adf_hw_device_data {
 	struct adf_hw_device_class *dev_class;
 	uint32_t (*get_accel_mask)(uint32_t fuse);
 	uint32_t (*get_ae_mask)(uint32_t fuse);
+	uint32_t (*get_sram_bar_id)(struct adf_hw_device_data *self);
 	uint32_t (*get_misc_bar_id)(struct adf_hw_device_data *self);
 	uint32_t (*get_etr_bar_id)(struct adf_hw_device_data *self);
 	uint32_t (*get_num_aes)(struct adf_hw_device_data *self);
 	uint32_t (*get_num_accels)(struct adf_hw_device_data *self);
+	uint32_t (*get_pf2vf_offset)(uint32_t i);
+	uint32_t (*get_vintmsk_offset)(uint32_t i);
 	enum dev_sku_info (*get_sku)(struct adf_hw_device_data *self);
-	void (*hw_arb_ring_enable)(struct adf_etr_ring_data *ring);
-	void (*hw_arb_ring_disable)(struct adf_etr_ring_data *ring);
 	int (*alloc_irq)(struct adf_accel_dev *accel_dev);
 	void (*free_irq)(struct adf_accel_dev *accel_dev);
 	void (*enable_error_correction)(struct adf_accel_dev *accel_dev);
 	int (*init_admin_comms)(struct adf_accel_dev *accel_dev);
 	void (*exit_admin_comms)(struct adf_accel_dev *accel_dev);
+	int (*send_admin_init)(struct adf_accel_dev *accel_dev);
 	int (*init_arb)(struct adf_accel_dev *accel_dev);
 	void (*exit_arb)(struct adf_accel_dev *accel_dev);
+	void (*get_arb_mapping)(struct adf_accel_dev *accel_dev,
+				const uint32_t **cfg);
+	void (*disable_iov)(struct adf_accel_dev *accel_dev);
 	void (*enable_ints)(struct adf_accel_dev *accel_dev);
+	int (*enable_vf2pf_comms)(struct adf_accel_dev *accel_dev);
 	const char *fw_name;
-	uint32_t pci_dev_id;
+	const char *fw_mmp_name;
 	uint32_t fuses;
 	uint32_t accel_capabilities_mask;
 	uint16_t accel_mask;
@@ -163,6 +177,7 @@ struct adf_hw_device_data {
 	uint8_t num_accel;
 	uint8_t num_logical_accel;
 	uint8_t num_engines;
+	uint8_t min_iov_compat_ver;
 } __packed;
 
 /* CSR write macro */
@@ -184,6 +199,16 @@ struct icp_qat_fw_loader_handle;
 struct adf_fw_loader_data {
 	struct icp_qat_fw_loader_handle *fw_loader;
 	const struct firmware *uof_fw;
+	const struct firmware *mmp_fw;
+};
+
+struct adf_accel_vf_info {
+	struct adf_accel_dev *accel_dev;
+	struct tasklet_struct vf2pf_bh_tasklet;
+	struct mutex pf2vf_lock; /* protect CSR access for PF2VF messages */
+	struct ratelimit_state vf2pf_ratelimit;
+	u32 vf_nr;
+	bool init;
 };
 
 struct adf_accel_dev {
@@ -199,6 +224,21 @@ struct adf_accel_dev {
 	struct list_head list;
 	struct module *owner;
 	struct adf_accel_pci accel_pci_dev;
+	union {
+		struct {
+			/* vf_info is non-zero when SR-IOV is init'ed */
+			struct adf_accel_vf_info *vf_info;
+		} pf;
+		struct {
+			char *irq_name;
+			struct tasklet_struct pf2vf_bh_tasklet;
+			struct mutex vf2pf_lock; /* protect CSR access */
+			struct completion iov_msg_completion;
+			uint8_t compatible;
+			uint8_t pf_version;
+		} vf;
+	};
+	bool is_vf;
 	uint8_t accel_id;
 } __packed;
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_accel_engine.c b/drivers/crypto/qat/qat_common/adf_accel_engine.c
index fdda8e7ae302..20b08bdcb146 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_engine.c
+++ b/drivers/crypto/qat/qat_common/adf_accel_engine.c
@@ -55,24 +55,36 @@ int adf_ae_fw_load(struct adf_accel_dev *accel_dev)
 {
 	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
 	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
-	void *uof_addr;
-	uint32_t uof_size;
+	void *uof_addr, *mmp_addr;
+	u32 uof_size, mmp_size;
 
+	if (!hw_device->fw_name)
+		return 0;
+
+	if (request_firmware(&loader_data->mmp_fw, hw_device->fw_mmp_name,
+			     &accel_dev->accel_pci_dev.pci_dev->dev)) {
+		dev_err(&GET_DEV(accel_dev), "Failed to load MMP firmware %s\n",
+			hw_device->fw_mmp_name);
+		return -EFAULT;
+	}
 	if (request_firmware(&loader_data->uof_fw, hw_device->fw_name,
 			     &accel_dev->accel_pci_dev.pci_dev->dev)) {
-		dev_err(&GET_DEV(accel_dev), "Failed to load firmware %s\n",
+		dev_err(&GET_DEV(accel_dev), "Failed to load UOF firmware %s\n",
 			hw_device->fw_name);
-		return -EFAULT;
+		goto out_err;
 	}
 
 	uof_size = loader_data->uof_fw->size;
 	uof_addr = (void *)loader_data->uof_fw->data;
+	mmp_size = loader_data->mmp_fw->size;
+	mmp_addr = (void *)loader_data->mmp_fw->data;
+	qat_uclo_wr_mimage(loader_data->fw_loader, mmp_addr, mmp_size);
 	if (qat_uclo_map_uof_obj(loader_data->fw_loader, uof_addr, uof_size)) {
 		dev_err(&GET_DEV(accel_dev), "Failed to map UOF\n");
 		goto out_err;
 	}
 	if (qat_uclo_wr_all_uimage(loader_data->fw_loader)) {
-		dev_err(&GET_DEV(accel_dev), "Failed to map UOF\n");
+		dev_err(&GET_DEV(accel_dev), "Failed to load UOF\n");
 		goto out_err;
 	}
 	return 0;
@@ -85,11 +97,17 @@ out_err:
 void adf_ae_fw_release(struct adf_accel_dev *accel_dev)
 {
 	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+
+	if (!hw_device->fw_name)
+		return;
 
 	qat_uclo_del_uof_obj(loader_data->fw_loader);
 	qat_hal_deinit(loader_data->fw_loader);
 	release_firmware(loader_data->uof_fw);
+	release_firmware(loader_data->mmp_fw);
 	loader_data->uof_fw = NULL;
+	loader_data->mmp_fw = NULL;
 	loader_data->fw_loader = NULL;
 }
 
@@ -99,6 +117,9 @@ int adf_ae_start(struct adf_accel_dev *accel_dev)
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	uint32_t ae_ctr, ae, max_aes = GET_MAX_ACCELENGINES(accel_dev);
 
+	if (!hw_data->fw_name)
+		return 0;
+
 	for (ae = 0, ae_ctr = 0; ae < max_aes; ae++) {
 		if (hw_data->ae_mask & (1 << ae)) {
 			qat_hal_start(loader_data->fw_loader, ae, 0xFF);
@@ -117,6 +138,9 @@ int adf_ae_stop(struct adf_accel_dev *accel_dev)
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	uint32_t ae_ctr, ae, max_aes = GET_MAX_ACCELENGINES(accel_dev);
 
+	if (!hw_data->fw_name)
+		return 0;
+
 	for (ae = 0, ae_ctr = 0; ae < max_aes; ae++) {
 		if (hw_data->ae_mask & (1 << ae)) {
 			qat_hal_stop(loader_data->fw_loader, ae, 0xFF);
@@ -143,6 +167,10 @@ static int adf_ae_reset(struct adf_accel_dev *accel_dev, int ae)
 int adf_ae_init(struct adf_accel_dev *accel_dev)
 {
 	struct adf_fw_loader_data *loader_data;
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+
+	if (!hw_device->fw_name)
+		return 0;
 
 	loader_data = kzalloc(sizeof(*loader_data), GFP_KERNEL);
 	if (!loader_data)
@@ -166,6 +194,10 @@ int adf_ae_init(struct adf_accel_dev *accel_dev)
 int adf_ae_shutdown(struct adf_accel_dev *accel_dev)
 {
 	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+
+	if (!hw_device->fw_name)
+		return 0;
 
 	qat_hal_deinit(loader_data->fw_loader);
 	kfree(accel_dev->fw_loader);
diff --git a/drivers/crypto/qat/qat_common/adf_admin.c b/drivers/crypto/qat/qat_common/adf_admin.c
new file mode 100644
index 000000000000..147d755fed97
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_admin.c
@@ -0,0 +1,290 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include "adf_accel_devices.h"
+#include "icp_qat_fw_init_admin.h"
+
+/* Admin Messages Registers */
+#define ADF_DH895XCC_ADMINMSGUR_OFFSET (0x3A000 + 0x574)
+#define ADF_DH895XCC_ADMINMSGLR_OFFSET (0x3A000 + 0x578)
+#define ADF_DH895XCC_MAILBOX_BASE_OFFSET 0x20970
+#define ADF_DH895XCC_MAILBOX_STRIDE 0x1000
+#define ADF_ADMINMSG_LEN 32
+
+static const u8 const_tab[1024] = {
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x21, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x03, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x01,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x13, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x02, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x13,
+0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x23, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x33, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x01, 0x23, 0x45, 0x67, 0x89, 0xab, 0xcd, 0xef, 0xfe, 0xdc, 0xba, 0x98, 0x76,
+0x54, 0x32, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x67, 0x45, 0x23, 0x01, 0xef, 0xcd, 0xab,
+0x89, 0x98, 0xba, 0xdc, 0xfe, 0x10, 0x32, 0x54, 0x76, 0xc3, 0xd2, 0xe1, 0xf0,
+0x00, 0x00, 0x00, 0x00, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x40, 0x00, 0x00, 0x00, 0x00, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc1, 0x05, 0x9e,
+0xd8, 0x36, 0x7c, 0xd5, 0x07, 0x30, 0x70, 0xdd, 0x17, 0xf7, 0x0e, 0x59, 0x39,
+0xff, 0xc0, 0x0b, 0x31, 0x68, 0x58, 0x15, 0x11, 0x64, 0xf9, 0x8f, 0xa7, 0xbe,
+0xfa, 0x4f, 0xa4, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6a, 0x09, 0xe6, 0x67, 0xbb, 0x67, 0xae,
+0x85, 0x3c, 0x6e, 0xf3, 0x72, 0xa5, 0x4f, 0xf5, 0x3a, 0x51, 0x0e, 0x52, 0x7f,
+0x9b, 0x05, 0x68, 0x8c, 0x1f, 0x83, 0xd9, 0xab, 0x5b, 0xe0, 0xcd, 0x19, 0x05,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xcb, 0xbb, 0x9d, 0x5d, 0xc1, 0x05, 0x9e, 0xd8, 0x62, 0x9a, 0x29,
+0x2a, 0x36, 0x7c, 0xd5, 0x07, 0x91, 0x59, 0x01, 0x5a, 0x30, 0x70, 0xdd, 0x17,
+0x15, 0x2f, 0xec, 0xd8, 0xf7, 0x0e, 0x59, 0x39, 0x67, 0x33, 0x26, 0x67, 0xff,
+0xc0, 0x0b, 0x31, 0x8e, 0xb4, 0x4a, 0x87, 0x68, 0x58, 0x15, 0x11, 0xdb, 0x0c,
+0x2e, 0x0d, 0x64, 0xf9, 0x8f, 0xa7, 0x47, 0xb5, 0x48, 0x1d, 0xbe, 0xfa, 0x4f,
+0xa4, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x6a, 0x09, 0xe6, 0x67, 0xf3, 0xbc, 0xc9, 0x08, 0xbb,
+0x67, 0xae, 0x85, 0x84, 0xca, 0xa7, 0x3b, 0x3c, 0x6e, 0xf3, 0x72, 0xfe, 0x94,
+0xf8, 0x2b, 0xa5, 0x4f, 0xf5, 0x3a, 0x5f, 0x1d, 0x36, 0xf1, 0x51, 0x0e, 0x52,
+0x7f, 0xad, 0xe6, 0x82, 0xd1, 0x9b, 0x05, 0x68, 0x8c, 0x2b, 0x3e, 0x6c, 0x1f,
+0x1f, 0x83, 0xd9, 0xab, 0xfb, 0x41, 0xbd, 0x6b, 0x5b, 0xe0, 0xcd, 0x19, 0x13,
+0x7e, 0x21, 0x79, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
+
+struct adf_admin_comms {
+	dma_addr_t phy_addr;
+	dma_addr_t const_tbl_addr;
+	void *virt_addr;
+	void __iomem *mailbox_addr;
+	struct mutex lock;	/* protects adf_admin_comms struct */
+};
+
+static int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev, u32 ae,
+				  void *in, void *out)
+{
+	struct adf_admin_comms *admin = accel_dev->admin;
+	int offset = ae * ADF_ADMINMSG_LEN * 2;
+	void __iomem *mailbox = admin->mailbox_addr;
+	int mb_offset = ae * ADF_DH895XCC_MAILBOX_STRIDE;
+	int times, received;
+
+	mutex_lock(&admin->lock);
+
+	if (ADF_CSR_RD(mailbox, mb_offset) == 1) {
+		mutex_unlock(&admin->lock);
+		return -EAGAIN;
+	}
+
+	memcpy(admin->virt_addr + offset, in, ADF_ADMINMSG_LEN);
+	ADF_CSR_WR(mailbox, mb_offset, 1);
+	received = 0;
+	for (times = 0; times < 50; times++) {
+		msleep(20);
+		if (ADF_CSR_RD(mailbox, mb_offset) == 0) {
+			received = 1;
+			break;
+		}
+	}
+	if (received)
+		memcpy(out, admin->virt_addr + offset +
+		       ADF_ADMINMSG_LEN, ADF_ADMINMSG_LEN);
+	else
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send admin msg to accelerator\n");
+
+	mutex_unlock(&admin->lock);
+	return received ? 0 : -EFAULT;
+}
+
+static int adf_send_admin_cmd(struct adf_accel_dev *accel_dev, int cmd)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct icp_qat_fw_init_admin_req req;
+	struct icp_qat_fw_init_admin_resp resp;
+	int i;
+
+	memset(&req, 0, sizeof(struct icp_qat_fw_init_admin_req));
+	req.init_admin_cmd_id = cmd;
+
+	if (cmd == ICP_QAT_FW_CONSTANTS_CFG) {
+		req.init_cfg_sz = 1024;
+		req.init_cfg_ptr = accel_dev->admin->const_tbl_addr;
+	}
+	for (i = 0; i < hw_device->get_num_aes(hw_device); i++) {
+		memset(&resp, 0, sizeof(struct icp_qat_fw_init_admin_resp));
+		if (adf_put_admin_msg_sync(accel_dev, i, &req, &resp) ||
+		    resp.init_resp_hdr.status)
+			return -EFAULT;
+	}
+	return 0;
+}
+
+/**
+ * adf_send_admin_init() - Function sends init message to FW
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Function sends admin init message to the FW
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int adf_send_admin_init(struct adf_accel_dev *accel_dev)
+{
+	int ret = adf_send_admin_cmd(accel_dev, ICP_QAT_FW_INIT_ME);
+
+	if (ret)
+		return ret;
+	return adf_send_admin_cmd(accel_dev, ICP_QAT_FW_CONSTANTS_CFG);
+}
+EXPORT_SYMBOL_GPL(adf_send_admin_init);
+
+int adf_init_admin_comms(struct adf_accel_dev *accel_dev)
+{
+	struct adf_admin_comms *admin;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+		&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *csr = pmisc->virt_addr;
+	void __iomem *mailbox = csr + ADF_DH895XCC_MAILBOX_BASE_OFFSET;
+	u64 reg_val;
+
+	admin = kzalloc_node(sizeof(*accel_dev->admin), GFP_KERNEL,
+			     dev_to_node(&GET_DEV(accel_dev)));
+	if (!admin)
+		return -ENOMEM;
+	admin->virt_addr = dma_zalloc_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
+					       &admin->phy_addr, GFP_KERNEL);
+	if (!admin->virt_addr) {
+		dev_err(&GET_DEV(accel_dev), "Failed to allocate dma buff\n");
+		kfree(admin);
+		return -ENOMEM;
+	}
+
+	admin->const_tbl_addr = dma_map_single(&GET_DEV(accel_dev),
+					       (void *) const_tab, 1024,
+					       DMA_TO_DEVICE);
+
+	if (unlikely(dma_mapping_error(&GET_DEV(accel_dev),
+				       admin->const_tbl_addr))) {
+		dma_free_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
+				  admin->virt_addr, admin->phy_addr);
+		kfree(admin);
+		return -ENOMEM;
+	}
+	reg_val = (u64)admin->phy_addr;
+	ADF_CSR_WR(csr, ADF_DH895XCC_ADMINMSGUR_OFFSET, reg_val >> 32);
+	ADF_CSR_WR(csr, ADF_DH895XCC_ADMINMSGLR_OFFSET, reg_val);
+	mutex_init(&admin->lock);
+	admin->mailbox_addr = mailbox;
+	accel_dev->admin = admin;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_init_admin_comms);
+
+void adf_exit_admin_comms(struct adf_accel_dev *accel_dev)
+{
+	struct adf_admin_comms *admin = accel_dev->admin;
+
+	if (!admin)
+		return;
+
+	if (admin->virt_addr)
+		dma_free_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
+				  admin->virt_addr, admin->phy_addr);
+
+	dma_unmap_single(&GET_DEV(accel_dev), admin->const_tbl_addr, 1024,
+			 DMA_TO_DEVICE);
+	mutex_destroy(&admin->lock);
+	kfree(admin);
+	accel_dev->admin = NULL;
+}
+EXPORT_SYMBOL_GPL(adf_exit_admin_comms);
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index 2dbc733b8ab2..a57b4194de28 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -91,6 +91,9 @@ static void adf_dev_restore(struct adf_accel_dev *accel_dev)
 	dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
 		 accel_dev->accel_id);
 
+	if (!parent)
+		parent = pdev;
+
 	if (!pci_wait_for_pending_transaction(pdev))
 		dev_info(&GET_DEV(accel_dev),
 			 "Transaction still in progress. Proceeding\n");
@@ -206,7 +209,7 @@ static struct pci_error_handlers adf_err_handler = {
  * QAT acceleration device accel_dev.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf)
 {
diff --git a/drivers/crypto/qat/qat_common/adf_cfg.c b/drivers/crypto/qat/qat_common/adf_cfg.c
index ab65bc274561..d0879790561f 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg.c
+++ b/drivers/crypto/qat/qat_common/adf_cfg.c
@@ -123,7 +123,7 @@ static const struct file_operations qat_dev_cfg_fops = {
  * The table stores device specific config values.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_cfg_dev_add(struct adf_accel_dev *accel_dev)
 {
@@ -178,6 +178,9 @@ void adf_cfg_dev_remove(struct adf_accel_dev *accel_dev)
 {
 	struct adf_cfg_device_data *dev_cfg_data = accel_dev->cfg;
 
+	if (!dev_cfg_data)
+		return;
+
 	down_write(&dev_cfg_data->lock);
 	adf_cfg_section_del_all(&dev_cfg_data->sec_list);
 	up_write(&dev_cfg_data->lock);
@@ -276,7 +279,7 @@ static int adf_cfg_key_val_get(struct adf_accel_dev *accel_dev,
  * in the given acceleration device
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev,
 				const char *section_name,
@@ -327,7 +330,7 @@ EXPORT_SYMBOL_GPL(adf_cfg_add_key_value_param);
  * will be stored.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_cfg_section_add(struct adf_accel_dev *accel_dev, const char *name)
 {
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_common.h b/drivers/crypto/qat/qat_common/adf_cfg_common.h
index 88b82187ac35..c697fb1cdfb5 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_common.h
+++ b/drivers/crypto/qat/qat_common/adf_cfg_common.h
@@ -60,7 +60,7 @@
 #define ADF_CFG_NO_DEVICE 0xFF
 #define ADF_CFG_AFFINITY_WHATEVER 0xFF
 #define MAX_DEVICE_NAME_SIZE 32
-#define ADF_MAX_DEVICES 32
+#define ADF_MAX_DEVICES (32 * 32)
 
 enum adf_cfg_val_type {
 	ADF_DEC,
@@ -71,6 +71,7 @@ enum adf_cfg_val_type {
 enum adf_device_type {
 	DEV_UNKNOWN = 0,
 	DEV_DH895XCC,
+	DEV_DH895XCCVF,
 };
 
 struct adf_dev_status_info {
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 27e16c09230b..7836dffc3d47 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -54,8 +54,8 @@
 #include "icp_qat_hal.h"
 
 #define ADF_MAJOR_VERSION	0
-#define ADF_MINOR_VERSION	1
-#define ADF_BUILD_VERSION	3
+#define ADF_MINOR_VERSION	2
+#define ADF_BUILD_VERSION	0
 #define ADF_DRV_VERSION		__stringify(ADF_MAJOR_VERSION) "." \
 				__stringify(ADF_MINOR_VERSION) "." \
 				__stringify(ADF_BUILD_VERSION)
@@ -91,9 +91,13 @@ struct service_hndl {
 	unsigned long start_status;
 	char *name;
 	struct list_head list;
-	int admin;
 };
 
+static inline int get_current_node(void)
+{
+	return topology_physical_package_id(smp_processor_id());
+}
+
 int adf_service_register(struct service_hndl *service);
 int adf_service_unregister(struct service_hndl *service);
 
@@ -102,13 +106,24 @@ int adf_dev_start(struct adf_accel_dev *accel_dev);
 int adf_dev_stop(struct adf_accel_dev *accel_dev);
 void adf_dev_shutdown(struct adf_accel_dev *accel_dev);
 
+void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
+void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
+int adf_iov_putmsg(struct adf_accel_dev *accel_dev, u32 msg, u8 vf_nr);
+void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev);
+int adf_enable_vf2pf_comms(struct adf_accel_dev *accel_dev);
+void adf_vf2pf_req_hndl(struct adf_accel_vf_info *vf_info);
+void adf_devmgr_update_class_index(struct adf_hw_device_data *hw_data);
+void adf_clean_vf_map(bool);
+
 int adf_ctl_dev_register(void);
 void adf_ctl_dev_unregister(void);
 int adf_processes_dev_register(void);
 void adf_processes_dev_unregister(void);
 
-int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev);
-void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev);
+int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev,
+		       struct adf_accel_dev *pf);
+void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev,
+		       struct adf_accel_dev *pf);
 struct list_head *adf_devmgr_get_head(void);
 struct adf_accel_dev *adf_devmgr_get_dev_by_id(uint32_t id);
 struct adf_accel_dev *adf_devmgr_get_first(void);
@@ -130,6 +145,12 @@ int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf);
 void adf_disable_aer(struct adf_accel_dev *accel_dev);
 int adf_init_aer(void);
 void adf_exit_aer(void);
+int adf_init_admin_comms(struct adf_accel_dev *accel_dev);
+void adf_exit_admin_comms(struct adf_accel_dev *accel_dev);
+int adf_send_admin_init(struct adf_accel_dev *accel_dev);
+int adf_init_arb(struct adf_accel_dev *accel_dev);
+void adf_exit_arb(struct adf_accel_dev *accel_dev);
+void adf_update_ring_arb(struct adf_etr_ring_data *ring);
 
 int adf_dev_get(struct adf_accel_dev *accel_dev);
 void adf_dev_put(struct adf_accel_dev *accel_dev);
@@ -141,10 +162,13 @@ int qat_crypto_unregister(void);
 struct qat_crypto_instance *qat_crypto_get_instance_node(int node);
 void qat_crypto_put_instance(struct qat_crypto_instance *inst);
 void qat_alg_callback(void *resp);
+void qat_alg_asym_callback(void *resp);
 int qat_algs_init(void);
 void qat_algs_exit(void);
 int qat_algs_register(void);
 int qat_algs_unregister(void);
+int qat_asym_algs_register(void);
+void qat_asym_algs_unregister(void);
 
 int qat_hal_init(struct adf_accel_dev *accel_dev);
 void qat_hal_deinit(struct icp_qat_fw_loader_handle *handle);
@@ -196,4 +220,23 @@ int qat_uclo_wr_all_uimage(struct icp_qat_fw_loader_handle *handle);
 void qat_uclo_del_uof_obj(struct icp_qat_fw_loader_handle *handle);
 int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
 			 void *addr_ptr, int mem_size);
+void qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle,
+			void *addr_ptr, int mem_size);
+#if defined(CONFIG_PCI_IOV)
+int adf_sriov_configure(struct pci_dev *pdev, int numvfs);
+void adf_disable_sriov(struct adf_accel_dev *accel_dev);
+void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
+				  uint32_t vf_mask);
+void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
+				 uint32_t vf_mask);
+#else
+static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
+{
+	return 0;
+}
+
+static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev)
+{
+}
+#endif
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index e056b9e9bf8a..cd8a12af8ec5 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -398,10 +398,9 @@ static int adf_ctl_ioctl_get_status(struct file *fp, unsigned int cmd,
 	}
 
 	accel_dev = adf_devmgr_get_dev_by_id(dev_info.accel_id);
-	if (!accel_dev) {
-		pr_err("QAT: Device %d not found\n", dev_info.accel_id);
+	if (!accel_dev)
 		return -ENODEV;
-	}
+
 	hw_data = accel_dev->hw_device;
 	dev_info.state = adf_dev_started(accel_dev) ? DEV_UP : DEV_DOWN;
 	dev_info.num_ae = hw_data->get_num_aes(hw_data);
@@ -495,6 +494,7 @@ static void __exit adf_unregister_ctl_device_driver(void)
 	adf_exit_aer();
 	qat_crypto_unregister();
 	qat_algs_exit();
+	adf_clean_vf_map(false);
 	mutex_destroy(&adf_ctl_lock);
 }
 
diff --git a/drivers/crypto/qat/qat_common/adf_dev_mgr.c b/drivers/crypto/qat/qat_common/adf_dev_mgr.c
index 3f0ff9e7d840..8dfdb8f90797 100644
--- a/drivers/crypto/qat/qat_common/adf_dev_mgr.c
+++ b/drivers/crypto/qat/qat_common/adf_dev_mgr.c
@@ -50,21 +50,125 @@
 #include "adf_common_drv.h"
 
 static LIST_HEAD(accel_table);
+static LIST_HEAD(vfs_table);
 static DEFINE_MUTEX(table_lock);
 static uint32_t num_devices;
 
+struct vf_id_map {
+	u32 bdf;
+	u32 id;
+	u32 fake_id;
+	bool attached;
+	struct list_head list;
+};
+
+static int adf_get_vf_id(struct adf_accel_dev *vf)
+{
+	return ((7 * (PCI_SLOT(accel_to_pci_dev(vf)->devfn) - 1)) +
+		PCI_FUNC(accel_to_pci_dev(vf)->devfn) +
+		(PCI_SLOT(accel_to_pci_dev(vf)->devfn) - 1));
+}
+
+static int adf_get_vf_num(struct adf_accel_dev *vf)
+{
+	return (accel_to_pci_dev(vf)->bus->number << 8) | adf_get_vf_id(vf);
+}
+
+static struct vf_id_map *adf_find_vf(u32 bdf)
+{
+	struct list_head *itr;
+
+	list_for_each(itr, &vfs_table) {
+		struct vf_id_map *ptr =
+			list_entry(itr, struct vf_id_map, list);
+
+		if (ptr->bdf == bdf)
+			return ptr;
+	}
+	return NULL;
+}
+
+static int adf_get_vf_real_id(u32 fake)
+{
+	struct list_head *itr;
+
+	list_for_each(itr, &vfs_table) {
+		struct vf_id_map *ptr =
+			list_entry(itr, struct vf_id_map, list);
+		if (ptr->fake_id == fake)
+			return ptr->id;
+	}
+	return -1;
+}
+
+/**
+ * adf_clean_vf_map() - Cleans VF id mapings
+ *
+ * Function cleans internal ids for virtual functions.
+ * @vf: flag indicating whether mappings is cleaned
+ *	for vfs only or for vfs and pfs
+ */
+void adf_clean_vf_map(bool vf)
+{
+	struct vf_id_map *map;
+	struct list_head *ptr, *tmp;
+
+	mutex_lock(&table_lock);
+	list_for_each_safe(ptr, tmp, &vfs_table) {
+		map = list_entry(ptr, struct vf_id_map, list);
+		if (map->bdf != -1)
+			num_devices--;
+
+		if (vf && map->bdf == -1)
+			continue;
+
+		list_del(ptr);
+		kfree(map);
+	}
+	mutex_unlock(&table_lock);
+}
+EXPORT_SYMBOL_GPL(adf_clean_vf_map);
+
+/**
+ * adf_devmgr_update_class_index() - Update internal index
+ * @hw_data:  Pointer to internal device data.
+ *
+ * Function updates internal dev index for VFs
+ */
+void adf_devmgr_update_class_index(struct adf_hw_device_data *hw_data)
+{
+	struct adf_hw_device_class *class = hw_data->dev_class;
+	struct list_head *itr;
+	int i = 0;
+
+	list_for_each(itr, &accel_table) {
+		struct adf_accel_dev *ptr =
+				list_entry(itr, struct adf_accel_dev, list);
+
+		if (ptr->hw_device->dev_class == class)
+			ptr->hw_device->instance_id = i++;
+
+		if (i == class->instances)
+				break;
+	}
+}
+EXPORT_SYMBOL_GPL(adf_devmgr_update_class_index);
+
 /**
  * adf_devmgr_add_dev() - Add accel_dev to the acceleration framework
  * @accel_dev:  Pointer to acceleration device.
+ * @pf:		Corresponding PF if the accel_dev is a VF
  *
  * Function adds acceleration device to the acceleration framework.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
-int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev)
+int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev,
+		       struct adf_accel_dev *pf)
 {
 	struct list_head *itr;
+	int ret = 0;
 
 	if (num_devices == ADF_MAX_DEVICES) {
 		dev_err(&GET_DEV(accel_dev), "Only support up to %d devices\n",
@@ -73,20 +177,77 @@ int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev)
 	}
 
 	mutex_lock(&table_lock);
-	list_for_each(itr, &accel_table) {
-		struct adf_accel_dev *ptr =
+	atomic_set(&accel_dev->ref_count, 0);
+
+	/* PF on host or VF on guest */
+	if (!accel_dev->is_vf || (accel_dev->is_vf && !pf)) {
+		struct vf_id_map *map;
+
+		list_for_each(itr, &accel_table) {
+			struct adf_accel_dev *ptr =
 				list_entry(itr, struct adf_accel_dev, list);
 
-		if (ptr == accel_dev) {
-			mutex_unlock(&table_lock);
-			return -EEXIST;
+			if (ptr == accel_dev) {
+				ret = -EEXIST;
+				goto unlock;
+			}
 		}
+
+		list_add_tail(&accel_dev->list, &accel_table);
+		accel_dev->accel_id = num_devices++;
+
+		map = kzalloc(sizeof(*map), GFP_KERNEL);
+		if (!map) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
+		map->bdf = ~0;
+		map->id = accel_dev->accel_id;
+		map->fake_id = map->id;
+		map->attached = true;
+		list_add_tail(&map->list, &vfs_table);
+	} else if (accel_dev->is_vf && pf) {
+		/* VF on host */
+		struct adf_accel_vf_info *vf_info;
+		struct vf_id_map *map;
+
+		vf_info = pf->pf.vf_info + adf_get_vf_id(accel_dev);
+
+		map = adf_find_vf(adf_get_vf_num(accel_dev));
+		if (map) {
+			struct vf_id_map *next;
+
+			accel_dev->accel_id = map->id;
+			list_add_tail(&accel_dev->list, &accel_table);
+			map->fake_id++;
+			map->attached = true;
+			next = list_next_entry(map, list);
+			while (next && &next->list != &vfs_table) {
+				next->fake_id++;
+				next = list_next_entry(next, list);
+			}
+
+			ret = 0;
+			goto unlock;
+		}
+
+		map = kzalloc(sizeof(*map), GFP_KERNEL);
+		if (!map) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
+
+		accel_dev->accel_id = num_devices++;
+		list_add_tail(&accel_dev->list, &accel_table);
+		map->bdf = adf_get_vf_num(accel_dev);
+		map->id = accel_dev->accel_id;
+		map->fake_id = map->id;
+		map->attached = true;
+		list_add_tail(&map->list, &vfs_table);
 	}
-	atomic_set(&accel_dev->ref_count, 0);
-	list_add_tail(&accel_dev->list, &accel_table);
-	accel_dev->accel_id = num_devices++;
+unlock:
 	mutex_unlock(&table_lock);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(adf_devmgr_add_dev);
 
@@ -98,17 +259,37 @@ struct list_head *adf_devmgr_get_head(void)
 /**
  * adf_devmgr_rm_dev() - Remove accel_dev from the acceleration framework.
  * @accel_dev:  Pointer to acceleration device.
+ * @pf:		Corresponding PF if the accel_dev is a VF
  *
  * Function removes acceleration device from the acceleration framework.
  * To be used by QAT device specific drivers.
  *
  * Return: void
  */
-void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev)
+void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev,
+		       struct adf_accel_dev *pf)
 {
 	mutex_lock(&table_lock);
+	if (!accel_dev->is_vf || (accel_dev->is_vf && !pf)) {
+		num_devices--;
+	} else if (accel_dev->is_vf && pf) {
+		struct vf_id_map *map, *next;
+
+		map = adf_find_vf(adf_get_vf_num(accel_dev));
+		if (!map) {
+			dev_err(&GET_DEV(accel_dev), "Failed to find VF map\n");
+			goto unlock;
+		}
+		map->fake_id--;
+		map->attached = false;
+		next = list_next_entry(map, list);
+		while (next && &next->list != &vfs_table) {
+			next->fake_id--;
+			next = list_next_entry(next, list);
+		}
+	}
+unlock:
 	list_del(&accel_dev->list);
-	num_devices--;
 	mutex_unlock(&table_lock);
 }
 EXPORT_SYMBOL_GPL(adf_devmgr_rm_dev);
@@ -154,17 +335,24 @@ EXPORT_SYMBOL_GPL(adf_devmgr_pci_to_accel_dev);
 struct adf_accel_dev *adf_devmgr_get_dev_by_id(uint32_t id)
 {
 	struct list_head *itr;
+	int real_id;
 
 	mutex_lock(&table_lock);
+	real_id = adf_get_vf_real_id(id);
+	if (real_id < 0)
+		goto unlock;
+
+	id = real_id;
+
 	list_for_each(itr, &accel_table) {
 		struct adf_accel_dev *ptr =
 				list_entry(itr, struct adf_accel_dev, list);
-
 		if (ptr->accel_id == id) {
 			mutex_unlock(&table_lock);
 			return ptr;
 		}
 	}
+unlock:
 	mutex_unlock(&table_lock);
 	return NULL;
 }
@@ -180,21 +368,52 @@ int adf_devmgr_verify_id(uint32_t id)
 	return -ENODEV;
 }
 
-void adf_devmgr_get_num_dev(uint32_t *num)
+static int adf_get_num_dettached_vfs(void)
 {
 	struct list_head *itr;
+	int vfs = 0;
 
-	*num = 0;
-	list_for_each(itr, &accel_table) {
-		(*num)++;
+	mutex_lock(&table_lock);
+	list_for_each(itr, &vfs_table) {
+		struct vf_id_map *ptr =
+			list_entry(itr, struct vf_id_map, list);
+		if (ptr->bdf != ~0 && !ptr->attached)
+			vfs++;
 	}
+	mutex_unlock(&table_lock);
+	return vfs;
+}
+
+void adf_devmgr_get_num_dev(uint32_t *num)
+{
+	*num = num_devices - adf_get_num_dettached_vfs();
 }
 
+/**
+ * adf_dev_in_use() - Check whether accel_dev is currently in use
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 1 when device is in use, 0 otherwise.
+ */
 int adf_dev_in_use(struct adf_accel_dev *accel_dev)
 {
 	return atomic_read(&accel_dev->ref_count) != 0;
 }
+EXPORT_SYMBOL_GPL(adf_dev_in_use);
 
+/**
+ * adf_dev_get() - Increment accel_dev reference count
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Increment the accel_dev refcount and if this is the first time
+ * incrementing it during this period the accel_dev is in use,
+ * increment the module refcount too.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 when successful, EFAULT when fail to bump module refcount
+ */
 int adf_dev_get(struct adf_accel_dev *accel_dev)
 {
 	if (atomic_add_return(1, &accel_dev->ref_count) == 1)
@@ -202,19 +421,50 @@ int adf_dev_get(struct adf_accel_dev *accel_dev)
 			return -EFAULT;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(adf_dev_get);
 
+/**
+ * adf_dev_put() - Decrement accel_dev reference count
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Decrement the accel_dev refcount and if this is the last time
+ * decrementing it during this period the accel_dev is in use,
+ * decrement the module refcount too.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: void
+ */
 void adf_dev_put(struct adf_accel_dev *accel_dev)
 {
 	if (atomic_sub_return(1, &accel_dev->ref_count) == 0)
 		module_put(accel_dev->owner);
 }
+EXPORT_SYMBOL_GPL(adf_dev_put);
 
+/**
+ * adf_devmgr_in_reset() - Check whether device is in reset
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 1 when the device is being reset, 0 otherwise.
+ */
 int adf_devmgr_in_reset(struct adf_accel_dev *accel_dev)
 {
 	return test_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
 }
+EXPORT_SYMBOL_GPL(adf_devmgr_in_reset);
 
+/**
+ * adf_dev_started() - Check whether device has started
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 1 when the device has started, 0 otherwise
+ */
 int adf_dev_started(struct adf_accel_dev *accel_dev)
 {
 	return test_bit(ADF_STATUS_STARTED, &accel_dev->status);
 }
+EXPORT_SYMBOL_GPL(adf_dev_started);
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_hw_arbiter.c b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
index 1864bdb36f8f..6849422e04bb 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_hw_arbiter.c
+++ b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
@@ -44,9 +44,8 @@
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
-#include <adf_accel_devices.h>
-#include <adf_transport_internal.h>
-#include "adf_drv.h"
+#include "adf_accel_devices.h"
+#include "adf_transport_internal.h"
 
 #define ADF_ARB_NUM 4
 #define ADF_ARB_REQ_RING_NUM 8
@@ -58,7 +57,6 @@
 #define ADF_ARB_RO_EN_OFFSET 0x090
 #define ADF_ARB_WQCFG_OFFSET 0x100
 #define ADF_ARB_WRK_2_SER_MAP_OFFSET 0x180
-#define ADF_ARB_WRK_2_SER_MAP 10
 #define ADF_ARB_RINGSRVARBEN_OFFSET 0x19C
 
 #define WRITE_CSR_ARB_RINGSRVARBEN(csr_addr, index, value) \
@@ -89,10 +87,11 @@
 
 int adf_init_arb(struct adf_accel_dev *accel_dev)
 {
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	void __iomem *csr = accel_dev->transport->banks[0].csr_addr;
-	uint32_t arb_cfg = 0x1 << 31 | 0x4 << 4 | 0x1;
-	uint32_t arb, i;
-	const uint32_t *thd_2_arb_cfg;
+	u32 arb_cfg = 0x1 << 31 | 0x4 << 4 | 0x1;
+	u32 arb, i;
+	const u32 *thd_2_arb_cfg;
 
 	/* Service arb configured for 32 bytes responses and
 	 * ring flow control check enabled. */
@@ -109,30 +108,39 @@ int adf_init_arb(struct adf_accel_dev *accel_dev)
 		WRITE_CSR_ARB_RESPORDERING(csr, i, 0xFFFFFFFF);
 
 	/* Setup worker queue registers */
-	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+	for (i = 0; i < hw_data->num_engines; i++)
 		WRITE_CSR_ARB_WQCFG(csr, i, i);
 
 	/* Map worker threads to service arbiters */
-	adf_get_arbiter_mapping(accel_dev, &thd_2_arb_cfg);
+	hw_data->get_arb_mapping(accel_dev, &thd_2_arb_cfg);
 
 	if (!thd_2_arb_cfg)
 		return -EFAULT;
 
-	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+	for (i = 0; i < hw_data->num_engines; i++)
 		WRITE_CSR_ARB_WRK_2_SER_MAP(csr, i, *(thd_2_arb_cfg + i));
 
 	return 0;
 }
-
-void adf_update_ring_arb_enable(struct adf_etr_ring_data *ring)
+EXPORT_SYMBOL_GPL(adf_init_arb);
+
+/**
+ * adf_update_ring_arb() - update ring arbitration rgister
+ * @accel_dev:  Pointer to ring data.
+ *
+ * Function enables or disables rings for/from arbitration.
+ */
+void adf_update_ring_arb(struct adf_etr_ring_data *ring)
 {
 	WRITE_CSR_ARB_RINGSRVARBEN(ring->bank->csr_addr,
 				   ring->bank->bank_number,
 				   ring->bank->ring_mask & 0xFF);
 }
+EXPORT_SYMBOL_GPL(adf_update_ring_arb);
 
 void adf_exit_arb(struct adf_accel_dev *accel_dev)
 {
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	void __iomem *csr;
 	unsigned int i;
 
@@ -146,14 +154,15 @@ void adf_exit_arb(struct adf_accel_dev *accel_dev)
 		WRITE_CSR_ARB_SARCONFIG(csr, i, 0);
 
 	/* Shutdown work queue */
-	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+	for (i = 0; i < hw_data->num_engines; i++)
 		WRITE_CSR_ARB_WQCFG(csr, i, 0);
 
 	/* Unmap worker threads to service arbiters */
-	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+	for (i = 0; i < hw_data->num_engines; i++)
 		WRITE_CSR_ARB_WRK_2_SER_MAP(csr, i, 0);
 
 	/* Disable arbitration on all rings */
 	for (i = 0; i < GET_MAX_BANKS(accel_dev); i++)
 		WRITE_CSR_ARB_RINGSRVARBEN(csr, i, 0);
 }
+EXPORT_SYMBOL_GPL(adf_exit_arb);
diff --git a/drivers/crypto/qat/qat_common/adf_init.c b/drivers/crypto/qat/qat_common/adf_init.c
index 245f43237a2d..ac37a89965ac 100644
--- a/drivers/crypto/qat/qat_common/adf_init.c
+++ b/drivers/crypto/qat/qat_common/adf_init.c
@@ -69,7 +69,7 @@ static void adf_service_add(struct service_hndl *service)
  * Function adds the acceleration service to the acceleration framework.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_service_register(struct service_hndl *service)
 {
@@ -94,7 +94,7 @@ static void adf_service_remove(struct service_hndl *service)
  * Function remove the acceleration service from the acceleration framework.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_service_unregister(struct service_hndl *service)
 {
@@ -114,7 +114,7 @@ EXPORT_SYMBOL_GPL(adf_service_unregister);
  * Initialize the ring data structures and the admin comms and arbitration
  * services.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_dev_init(struct adf_accel_dev *accel_dev)
 {
@@ -177,20 +177,6 @@ int adf_dev_init(struct adf_accel_dev *accel_dev)
 	 */
 	list_for_each(list_itr, &service_table) {
 		service = list_entry(list_itr, struct service_hndl, list);
-		if (!service->admin)
-			continue;
-		if (service->event_hld(accel_dev, ADF_EVENT_INIT)) {
-			dev_err(&GET_DEV(accel_dev),
-				"Failed to initialise service %s\n",
-				service->name);
-			return -EFAULT;
-		}
-		set_bit(accel_dev->accel_id, &service->init_status);
-	}
-	list_for_each(list_itr, &service_table) {
-		service = list_entry(list_itr, struct service_hndl, list);
-		if (service->admin)
-			continue;
 		if (service->event_hld(accel_dev, ADF_EVENT_INIT)) {
 			dev_err(&GET_DEV(accel_dev),
 				"Failed to initialise service %s\n",
@@ -201,6 +187,7 @@ int adf_dev_init(struct adf_accel_dev *accel_dev)
 	}
 
 	hw_data->enable_error_correction(accel_dev);
+	hw_data->enable_vf2pf_comms(accel_dev);
 
 	return 0;
 }
@@ -214,10 +201,11 @@ EXPORT_SYMBOL_GPL(adf_dev_init);
  * is ready to be used.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_dev_start(struct adf_accel_dev *accel_dev)
 {
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	struct service_hndl *service;
 	struct list_head *list_itr;
 
@@ -229,22 +217,13 @@ int adf_dev_start(struct adf_accel_dev *accel_dev)
 	}
 	set_bit(ADF_STATUS_AE_STARTED, &accel_dev->status);
 
-	list_for_each(list_itr, &service_table) {
-		service = list_entry(list_itr, struct service_hndl, list);
-		if (!service->admin)
-			continue;
-		if (service->event_hld(accel_dev, ADF_EVENT_START)) {
-			dev_err(&GET_DEV(accel_dev),
-				"Failed to start service %s\n",
-				service->name);
-			return -EFAULT;
-		}
-		set_bit(accel_dev->accel_id, &service->start_status);
+	if (hw_data->send_admin_init(accel_dev)) {
+		dev_err(&GET_DEV(accel_dev), "Failed to send init message\n");
+		return -EFAULT;
 	}
+
 	list_for_each(list_itr, &service_table) {
 		service = list_entry(list_itr, struct service_hndl, list);
-		if (service->admin)
-			continue;
 		if (service->event_hld(accel_dev, ADF_EVENT_START)) {
 			dev_err(&GET_DEV(accel_dev),
 				"Failed to start service %s\n",
@@ -257,7 +236,8 @@ int adf_dev_start(struct adf_accel_dev *accel_dev)
 	clear_bit(ADF_STATUS_STARTING, &accel_dev->status);
 	set_bit(ADF_STATUS_STARTED, &accel_dev->status);
 
-	if (qat_algs_register()) {
+	if (!list_empty(&accel_dev->crypto_list) &&
+	    (qat_algs_register() || qat_asym_algs_register())) {
 		dev_err(&GET_DEV(accel_dev),
 			"Failed to register crypto algs\n");
 		set_bit(ADF_STATUS_STARTING, &accel_dev->status);
@@ -276,7 +256,7 @@ EXPORT_SYMBOL_GPL(adf_dev_start);
  * is shuting down.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_dev_stop(struct adf_accel_dev *accel_dev)
 {
@@ -292,14 +272,15 @@ int adf_dev_stop(struct adf_accel_dev *accel_dev)
 	clear_bit(ADF_STATUS_STARTING, &accel_dev->status);
 	clear_bit(ADF_STATUS_STARTED, &accel_dev->status);
 
-	if (qat_algs_unregister())
+	if (!list_empty(&accel_dev->crypto_list) && qat_algs_unregister())
 		dev_err(&GET_DEV(accel_dev),
 			"Failed to unregister crypto algs\n");
 
+	if (!list_empty(&accel_dev->crypto_list))
+		qat_asym_algs_unregister();
+
 	list_for_each(list_itr, &service_table) {
 		service = list_entry(list_itr, struct service_hndl, list);
-		if (service->admin)
-			continue;
 		if (!test_bit(accel_dev->accel_id, &service->start_status))
 			continue;
 		ret = service->event_hld(accel_dev, ADF_EVENT_STOP);
@@ -310,19 +291,6 @@ int adf_dev_stop(struct adf_accel_dev *accel_dev)
 			clear_bit(accel_dev->accel_id, &service->start_status);
 		}
 	}
-	list_for_each(list_itr, &service_table) {
-		service = list_entry(list_itr, struct service_hndl, list);
-		if (!service->admin)
-			continue;
-		if (!test_bit(accel_dev->accel_id, &service->start_status))
-			continue;
-		if (service->event_hld(accel_dev, ADF_EVENT_STOP))
-			dev_err(&GET_DEV(accel_dev),
-				"Failed to shutdown service %s\n",
-				service->name);
-		else
-			clear_bit(accel_dev->accel_id, &service->start_status);
-	}
 
 	if (wait)
 		msleep(100);
@@ -373,21 +341,6 @@ void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
 
 	list_for_each(list_itr, &service_table) {
 		service = list_entry(list_itr, struct service_hndl, list);
-		if (service->admin)
-			continue;
-		if (!test_bit(accel_dev->accel_id, &service->init_status))
-			continue;
-		if (service->event_hld(accel_dev, ADF_EVENT_SHUTDOWN))
-			dev_err(&GET_DEV(accel_dev),
-				"Failed to shutdown service %s\n",
-				service->name);
-		else
-			clear_bit(accel_dev->accel_id, &service->init_status);
-	}
-	list_for_each(list_itr, &service_table) {
-		service = list_entry(list_itr, struct service_hndl, list);
-		if (!service->admin)
-			continue;
 		if (!test_bit(accel_dev->accel_id, &service->init_status))
 			continue;
 		if (service->event_hld(accel_dev, ADF_EVENT_SHUTDOWN))
@@ -413,6 +366,7 @@ void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
 	if (hw_data->exit_admin_comms)
 		hw_data->exit_admin_comms(accel_dev);
 
+	hw_data->disable_iov(accel_dev);
 	adf_cleanup_etr_data(accel_dev);
 }
 EXPORT_SYMBOL_GPL(adf_dev_shutdown);
@@ -424,17 +378,6 @@ int adf_dev_restarting_notify(struct adf_accel_dev *accel_dev)
 
 	list_for_each(list_itr, &service_table) {
 		service = list_entry(list_itr, struct service_hndl, list);
-		if (service->admin)
-			continue;
-		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTING))
-			dev_err(&GET_DEV(accel_dev),
-				"Failed to restart service %s.\n",
-				service->name);
-	}
-	list_for_each(list_itr, &service_table) {
-		service = list_entry(list_itr, struct service_hndl, list);
-		if (!service->admin)
-			continue;
 		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTING))
 			dev_err(&GET_DEV(accel_dev),
 				"Failed to restart service %s.\n",
@@ -450,17 +393,6 @@ int adf_dev_restarted_notify(struct adf_accel_dev *accel_dev)
 
 	list_for_each(list_itr, &service_table) {
 		service = list_entry(list_itr, struct service_hndl, list);
-		if (service->admin)
-			continue;
-		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTED))
-			dev_err(&GET_DEV(accel_dev),
-				"Failed to restart service %s.\n",
-				service->name);
-	}
-	list_for_each(list_itr, &service_table) {
-		service = list_entry(list_itr, struct service_hndl, list);
-		if (!service->admin)
-			continue;
 		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTED))
 			dev_err(&GET_DEV(accel_dev),
 				"Failed to restart service %s.\n",
diff --git a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
new file mode 100644
index 000000000000..5fdbad809343
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
@@ -0,0 +1,438 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+
+#include <linux/pci.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "adf_pf2vf_msg.h"
+
+#define ADF_DH895XCC_EP_OFFSET	0x3A000
+#define ADF_DH895XCC_ERRMSK3	(ADF_DH895XCC_EP_OFFSET + 0x1C)
+#define ADF_DH895XCC_ERRMSK3_VF2PF_L_MASK(vf_mask) ((vf_mask & 0xFFFF) << 9)
+#define ADF_DH895XCC_ERRMSK5	(ADF_DH895XCC_EP_OFFSET + 0xDC)
+#define ADF_DH895XCC_ERRMSK5_VF2PF_U_MASK(vf_mask) (vf_mask >> 16)
+
+/**
+ * adf_enable_pf2vf_interrupts() - Enable PF to VF interrupts
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function enables PF to VF interrupts
+ */
+void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	void __iomem *pmisc_bar_addr =
+		pci_info->pci_bars[hw_data->get_misc_bar_id(hw_data)].virt_addr;
+
+	ADF_CSR_WR(pmisc_bar_addr, hw_data->get_vintmsk_offset(0), 0x0);
+}
+EXPORT_SYMBOL_GPL(adf_enable_pf2vf_interrupts);
+
+/**
+ * adf_disable_pf2vf_interrupts() - Disable PF to VF interrupts
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function disables PF to VF interrupts
+ */
+void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	void __iomem *pmisc_bar_addr =
+		pci_info->pci_bars[hw_data->get_misc_bar_id(hw_data)].virt_addr;
+
+	ADF_CSR_WR(pmisc_bar_addr, hw_data->get_vintmsk_offset(0), 0x2);
+}
+EXPORT_SYMBOL_GPL(adf_disable_pf2vf_interrupts);
+
+void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
+				 u32 vf_mask)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *pmisc_addr = pmisc->virt_addr;
+	u32 reg;
+
+	/* Enable VF2PF Messaging Ints - VFs 1 through 16 per vf_mask[15:0] */
+	if (vf_mask & 0xFFFF) {
+		reg = ADF_CSR_RD(pmisc_addr, ADF_DH895XCC_ERRMSK3);
+		reg &= ~ADF_DH895XCC_ERRMSK3_VF2PF_L_MASK(vf_mask);
+		ADF_CSR_WR(pmisc_addr, ADF_DH895XCC_ERRMSK3, reg);
+	}
+
+	/* Enable VF2PF Messaging Ints - VFs 17 through 32 per vf_mask[31:16] */
+	if (vf_mask >> 16) {
+		reg = ADF_CSR_RD(pmisc_addr, ADF_DH895XCC_ERRMSK5);
+		reg &= ~ADF_DH895XCC_ERRMSK5_VF2PF_U_MASK(vf_mask);
+		ADF_CSR_WR(pmisc_addr, ADF_DH895XCC_ERRMSK5, reg);
+	}
+}
+
+/**
+ * adf_disable_pf2vf_interrupts() - Disable VF to PF interrupts
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function disables VF to PF interrupts
+ */
+void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *pmisc_addr = pmisc->virt_addr;
+	u32 reg;
+
+	/* Disable VF2PF interrupts for VFs 1 through 16 per vf_mask[15:0] */
+	if (vf_mask & 0xFFFF) {
+		reg = ADF_CSR_RD(pmisc_addr, ADF_DH895XCC_ERRMSK3) |
+			ADF_DH895XCC_ERRMSK3_VF2PF_L_MASK(vf_mask);
+		ADF_CSR_WR(pmisc_addr, ADF_DH895XCC_ERRMSK3, reg);
+	}
+
+	/* Disable VF2PF interrupts for VFs 17 through 32 per vf_mask[31:16] */
+	if (vf_mask >> 16) {
+		reg = ADF_CSR_RD(pmisc_addr, ADF_DH895XCC_ERRMSK5) |
+			ADF_DH895XCC_ERRMSK5_VF2PF_U_MASK(vf_mask);
+		ADF_CSR_WR(pmisc_addr, ADF_DH895XCC_ERRMSK5, reg);
+	}
+}
+EXPORT_SYMBOL_GPL(adf_disable_vf2pf_interrupts);
+
+static int __adf_iov_putmsg(struct adf_accel_dev *accel_dev, u32 msg, u8 vf_nr)
+{
+	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	void __iomem *pmisc_bar_addr =
+		pci_info->pci_bars[hw_data->get_misc_bar_id(hw_data)].virt_addr;
+	u32 val, pf2vf_offset, count = 0;
+	u32 local_in_use_mask, local_in_use_pattern;
+	u32 remote_in_use_mask, remote_in_use_pattern;
+	struct mutex *lock;	/* lock preventing concurrent acces of CSR */
+	u32 int_bit;
+	int ret = 0;
+
+	if (accel_dev->is_vf) {
+		pf2vf_offset = hw_data->get_pf2vf_offset(0);
+		lock = &accel_dev->vf.vf2pf_lock;
+		local_in_use_mask = ADF_VF2PF_IN_USE_BY_VF_MASK;
+		local_in_use_pattern = ADF_VF2PF_IN_USE_BY_VF;
+		remote_in_use_mask = ADF_PF2VF_IN_USE_BY_PF_MASK;
+		remote_in_use_pattern = ADF_PF2VF_IN_USE_BY_PF;
+		int_bit = ADF_VF2PF_INT;
+	} else {
+		pf2vf_offset = hw_data->get_pf2vf_offset(vf_nr);
+		lock = &accel_dev->pf.vf_info[vf_nr].pf2vf_lock;
+		local_in_use_mask = ADF_PF2VF_IN_USE_BY_PF_MASK;
+		local_in_use_pattern = ADF_PF2VF_IN_USE_BY_PF;
+		remote_in_use_mask = ADF_VF2PF_IN_USE_BY_VF_MASK;
+		remote_in_use_pattern = ADF_VF2PF_IN_USE_BY_VF;
+		int_bit = ADF_PF2VF_INT;
+	}
+
+	mutex_lock(lock);
+
+	/* Check if PF2VF CSR is in use by remote function */
+	val = ADF_CSR_RD(pmisc_bar_addr, pf2vf_offset);
+	if ((val & remote_in_use_mask) == remote_in_use_pattern) {
+		dev_dbg(&GET_DEV(accel_dev),
+			"PF2VF CSR in use by remote function\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* Attempt to get ownership of PF2VF CSR */
+	msg &= ~local_in_use_mask;
+	msg |= local_in_use_pattern;
+	ADF_CSR_WR(pmisc_bar_addr, pf2vf_offset, msg);
+
+	/* Wait in case remote func also attempting to get ownership */
+	msleep(ADF_IOV_MSG_COLLISION_DETECT_DELAY);
+
+	val = ADF_CSR_RD(pmisc_bar_addr, pf2vf_offset);
+	if ((val & local_in_use_mask) != local_in_use_pattern) {
+		dev_dbg(&GET_DEV(accel_dev),
+			"PF2VF CSR in use by remote - collision detected\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/*
+	 * This function now owns the PV2VF CSR.  The IN_USE_BY pattern must
+	 * remain in the PF2VF CSR for all writes including ACK from remote
+	 * until this local function relinquishes the CSR.  Send the message
+	 * by interrupting the remote.
+	 */
+	ADF_CSR_WR(pmisc_bar_addr, pf2vf_offset, msg | int_bit);
+
+	/* Wait for confirmation from remote func it received the message */
+	do {
+		msleep(ADF_IOV_MSG_ACK_DELAY);
+		val = ADF_CSR_RD(pmisc_bar_addr, pf2vf_offset);
+	} while ((val & int_bit) && (count++ < ADF_IOV_MSG_ACK_MAX_RETRY));
+
+	if (val & int_bit) {
+		dev_dbg(&GET_DEV(accel_dev), "ACK not received from remote\n");
+		val &= ~int_bit;
+		ret = -EIO;
+	}
+
+	/* Finished with PF2VF CSR; relinquish it and leave msg in CSR */
+	ADF_CSR_WR(pmisc_bar_addr, pf2vf_offset, val & ~local_in_use_mask);
+out:
+	mutex_unlock(lock);
+	return ret;
+}
+
+/**
+ * adf_iov_putmsg() - send PF2VF message
+ * @accel_dev:  Pointer to acceleration device.
+ * @msg:	Message to send
+ * @vf_nr:	VF number to which the message will be sent
+ *
+ * Function sends a messge from the PF to a VF
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int adf_iov_putmsg(struct adf_accel_dev *accel_dev, u32 msg, u8 vf_nr)
+{
+	u32 count = 0;
+	int ret;
+
+	do {
+		ret = __adf_iov_putmsg(accel_dev, msg, vf_nr);
+		if (ret)
+			msleep(ADF_IOV_MSG_RETRY_DELAY);
+	} while (ret && (count++ < ADF_IOV_MSG_MAX_RETRIES));
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_iov_putmsg);
+
+void adf_vf2pf_req_hndl(struct adf_accel_vf_info *vf_info)
+{
+	struct adf_accel_dev *accel_dev = vf_info->accel_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	int bar_id = hw_data->get_misc_bar_id(hw_data);
+	struct adf_bar *pmisc = &GET_BARS(accel_dev)[bar_id];
+	void __iomem *pmisc_addr = pmisc->virt_addr;
+	u32 msg, resp = 0, vf_nr = vf_info->vf_nr;
+
+	/* Read message from the VF */
+	msg = ADF_CSR_RD(pmisc_addr, hw_data->get_pf2vf_offset(vf_nr));
+
+	/* To ACK, clear the VF2PFINT bit */
+	msg &= ~ADF_VF2PF_INT;
+	ADF_CSR_WR(pmisc_addr, hw_data->get_pf2vf_offset(vf_nr), msg);
+
+	if (!(msg & ADF_VF2PF_MSGORIGIN_SYSTEM))
+		/* Ignore legacy non-system (non-kernel) VF2PF messages */
+		goto err;
+
+	switch ((msg & ADF_VF2PF_MSGTYPE_MASK) >> ADF_VF2PF_MSGTYPE_SHIFT) {
+	case ADF_VF2PF_MSGTYPE_COMPAT_VER_REQ:
+		{
+		u8 vf_compat_ver = msg >> ADF_VF2PF_COMPAT_VER_REQ_SHIFT;
+
+		resp = (ADF_PF2VF_MSGORIGIN_SYSTEM |
+			 (ADF_PF2VF_MSGTYPE_VERSION_RESP <<
+			  ADF_PF2VF_MSGTYPE_SHIFT) |
+			 (ADF_PFVF_COMPATIBILITY_VERSION <<
+			  ADF_PF2VF_VERSION_RESP_VERS_SHIFT));
+
+		dev_dbg(&GET_DEV(accel_dev),
+			"Compatibility Version Request from VF%d vers=%u\n",
+			vf_nr + 1, vf_compat_ver);
+
+		if (vf_compat_ver < hw_data->min_iov_compat_ver) {
+			dev_err(&GET_DEV(accel_dev),
+				"VF (vers %d) incompatible with PF (vers %d)\n",
+				vf_compat_ver, ADF_PFVF_COMPATIBILITY_VERSION);
+			resp |= ADF_PF2VF_VF_INCOMPATIBLE <<
+				ADF_PF2VF_VERSION_RESP_RESULT_SHIFT;
+		} else if (vf_compat_ver > ADF_PFVF_COMPATIBILITY_VERSION) {
+			dev_err(&GET_DEV(accel_dev),
+				"VF (vers %d) compat with PF (vers %d) unkn.\n",
+				vf_compat_ver, ADF_PFVF_COMPATIBILITY_VERSION);
+			resp |= ADF_PF2VF_VF_COMPAT_UNKNOWN <<
+				ADF_PF2VF_VERSION_RESP_RESULT_SHIFT;
+		} else {
+			dev_dbg(&GET_DEV(accel_dev),
+				"VF (vers %d) compatible with PF (vers %d)\n",
+				vf_compat_ver, ADF_PFVF_COMPATIBILITY_VERSION);
+			resp |= ADF_PF2VF_VF_COMPATIBLE <<
+				ADF_PF2VF_VERSION_RESP_RESULT_SHIFT;
+		}
+		}
+		break;
+	case ADF_VF2PF_MSGTYPE_VERSION_REQ:
+		dev_dbg(&GET_DEV(accel_dev),
+			"Legacy VersionRequest received from VF%d 0x%x\n",
+			vf_nr + 1, msg);
+		resp = (ADF_PF2VF_MSGORIGIN_SYSTEM |
+			 (ADF_PF2VF_MSGTYPE_VERSION_RESP <<
+			  ADF_PF2VF_MSGTYPE_SHIFT) |
+			 (ADF_PFVF_COMPATIBILITY_VERSION <<
+			  ADF_PF2VF_VERSION_RESP_VERS_SHIFT));
+		resp |= ADF_PF2VF_VF_COMPATIBLE <<
+			ADF_PF2VF_VERSION_RESP_RESULT_SHIFT;
+		/* Set legacy major and minor version num */
+		resp |= 1 << ADF_PF2VF_MAJORVERSION_SHIFT |
+			1 << ADF_PF2VF_MINORVERSION_SHIFT;
+		break;
+	case ADF_VF2PF_MSGTYPE_INIT:
+		{
+		dev_dbg(&GET_DEV(accel_dev),
+			"Init message received from VF%d 0x%x\n",
+			vf_nr + 1, msg);
+		vf_info->init = true;
+		}
+		break;
+	case ADF_VF2PF_MSGTYPE_SHUTDOWN:
+		{
+		dev_dbg(&GET_DEV(accel_dev),
+			"Shutdown message received from VF%d 0x%x\n",
+			vf_nr + 1, msg);
+		vf_info->init = false;
+		}
+		break;
+	default:
+		goto err;
+	}
+
+	if (resp && adf_iov_putmsg(accel_dev, resp, vf_nr))
+		dev_err(&GET_DEV(accel_dev), "Failed to send response to VF\n");
+
+	/* re-enable interrupt on PF from this VF */
+	adf_enable_vf2pf_interrupts(accel_dev, (1 << vf_nr));
+	return;
+err:
+	dev_dbg(&GET_DEV(accel_dev), "Unknown message from VF%d (0x%x);\n",
+		vf_nr + 1, msg);
+}
+
+void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_vf_info *vf;
+	u32 msg = (ADF_PF2VF_MSGORIGIN_SYSTEM |
+		(ADF_PF2VF_MSGTYPE_RESTARTING << ADF_PF2VF_MSGTYPE_SHIFT));
+	int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev));
+
+	for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) {
+		if (vf->init && adf_iov_putmsg(accel_dev, msg, i))
+			dev_err(&GET_DEV(accel_dev),
+				"Failed to send restarting msg to VF%d\n", i);
+	}
+}
+
+static int adf_vf2pf_request_version(struct adf_accel_dev *accel_dev)
+{
+	unsigned long timeout = msecs_to_jiffies(ADF_IOV_MSG_RESP_TIMEOUT);
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	u32 msg = 0;
+	int ret;
+
+	msg = ADF_VF2PF_MSGORIGIN_SYSTEM;
+	msg |= ADF_VF2PF_MSGTYPE_COMPAT_VER_REQ << ADF_VF2PF_MSGTYPE_SHIFT;
+	msg |= ADF_PFVF_COMPATIBILITY_VERSION << ADF_VF2PF_COMPAT_VER_REQ_SHIFT;
+	BUILD_BUG_ON(ADF_PFVF_COMPATIBILITY_VERSION > 255);
+
+	/* Send request from VF to PF */
+	ret = adf_iov_putmsg(accel_dev, msg, 0);
+	if (ret) {
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Compatibility Version Request.\n");
+		return ret;
+	}
+
+	/* Wait for response */
+	if (!wait_for_completion_timeout(&accel_dev->vf.iov_msg_completion,
+					 timeout)) {
+		dev_err(&GET_DEV(accel_dev),
+			"IOV request/response message timeout expired\n");
+		return -EIO;
+	}
+
+	/* Response from PF received, check compatibility */
+	switch (accel_dev->vf.compatible) {
+	case ADF_PF2VF_VF_COMPATIBLE:
+		break;
+	case ADF_PF2VF_VF_COMPAT_UNKNOWN:
+		/* VF is newer than PF and decides whether it is compatible */
+		if (accel_dev->vf.pf_version >= hw_data->min_iov_compat_ver)
+			break;
+		/* fall through */
+	case ADF_PF2VF_VF_INCOMPATIBLE:
+		dev_err(&GET_DEV(accel_dev),
+			"PF (vers %d) and VF (vers %d) are not compatible\n",
+			accel_dev->vf.pf_version,
+			ADF_PFVF_COMPATIBILITY_VERSION);
+		return -EINVAL;
+	default:
+		dev_err(&GET_DEV(accel_dev),
+			"Invalid response from PF; assume not compatible\n");
+		return -EINVAL;
+	}
+	return ret;
+}
+
+/**
+ * adf_enable_vf2pf_comms() - Function enables communication from vf to pf
+ *
+ * @accel_dev: Pointer to acceleration device virtual function.
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int adf_enable_vf2pf_comms(struct adf_accel_dev *accel_dev)
+{
+	adf_enable_pf2vf_interrupts(accel_dev);
+	return adf_vf2pf_request_version(accel_dev);
+}
+EXPORT_SYMBOL_GPL(adf_enable_vf2pf_comms);
diff --git a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.h b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.h
new file mode 100644
index 000000000000..5acd531a11ff
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.h
@@ -0,0 +1,146 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_PF2VF_MSG_H
+#define ADF_PF2VF_MSG_H
+
+/*
+ * PF<->VF Messaging
+ * The PF has an array of 32-bit PF2VF registers, one for each VF.  The
+ * PF can access all these registers; each VF can access only the one
+ * register associated with that particular VF.
+ *
+ * The register functionally is split into two parts:
+ * The bottom half is for PF->VF messages. In particular when the first
+ * bit of this register (bit 0) gets set an interrupt will be triggered
+ * in the respective VF.
+ * The top half is for VF->PF messages. In particular when the first bit
+ * of this half of register (bit 16) gets set an interrupt will be triggered
+ * in the PF.
+ *
+ * The remaining bits within this register are available to encode messages.
+ * and implement a collision control mechanism to prevent concurrent use of
+ * the PF2VF register by both the PF and VF.
+ *
+ *  31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16
+ *  _______________________________________________
+ * |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |
+ * +-----------------------------------------------+
+ *  \___________________________/ \_________/ ^   ^
+ *                ^                    ^      |   |
+ *                |                    |      |   VF2PF Int
+ *                |                    |      Message Origin
+ *                |                    Message Type
+ *                Message-specific Data/Reserved
+ *
+ *  15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+ *  _______________________________________________
+ * |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |
+ * +-----------------------------------------------+
+ *  \___________________________/ \_________/ ^   ^
+ *                ^                    ^      |   |
+ *                |                    |      |   PF2VF Int
+ *                |                    |      Message Origin
+ *                |                    Message Type
+ *                Message-specific Data/Reserved
+ *
+ * Message Origin (Should always be 1)
+ * A legacy out-of-tree QAT driver allowed for a set of messages not supported
+ * by this driver; these had a Msg Origin of 0 and are ignored by this driver.
+ *
+ * When a PF or VF attempts to send a message in the lower or upper 16 bits,
+ * respectively, the other 16 bits are written to first with a defined
+ * IN_USE_BY pattern as part of a collision control scheme (see adf_iov_putmsg).
+ */
+
+#define ADF_PFVF_COMPATIBILITY_VERSION		0x1	/* PF<->VF compat */
+
+/* PF->VF messages */
+#define ADF_PF2VF_INT				BIT(0)
+#define ADF_PF2VF_MSGORIGIN_SYSTEM		BIT(1)
+#define ADF_PF2VF_MSGTYPE_MASK			0x0000003C
+#define ADF_PF2VF_MSGTYPE_SHIFT			2
+#define ADF_PF2VF_MSGTYPE_RESTARTING		0x01
+#define ADF_PF2VF_MSGTYPE_VERSION_RESP		0x02
+#define ADF_PF2VF_IN_USE_BY_PF			0x6AC20000
+#define ADF_PF2VF_IN_USE_BY_PF_MASK		0xFFFE0000
+
+/* PF->VF Version Response */
+#define ADF_PF2VF_VERSION_RESP_VERS_MASK	0x00003FC0
+#define ADF_PF2VF_VERSION_RESP_VERS_SHIFT	6
+#define ADF_PF2VF_VERSION_RESP_RESULT_MASK	0x0000C000
+#define ADF_PF2VF_VERSION_RESP_RESULT_SHIFT	14
+#define ADF_PF2VF_MINORVERSION_SHIFT		6
+#define ADF_PF2VF_MAJORVERSION_SHIFT		10
+#define ADF_PF2VF_VF_COMPATIBLE			1
+#define ADF_PF2VF_VF_INCOMPATIBLE		2
+#define ADF_PF2VF_VF_COMPAT_UNKNOWN		3
+
+/* VF->PF messages */
+#define ADF_VF2PF_IN_USE_BY_VF			0x00006AC2
+#define ADF_VF2PF_IN_USE_BY_VF_MASK		0x0000FFFE
+#define ADF_VF2PF_INT				BIT(16)
+#define ADF_VF2PF_MSGORIGIN_SYSTEM		BIT(17)
+#define ADF_VF2PF_MSGTYPE_MASK			0x003C0000
+#define ADF_VF2PF_MSGTYPE_SHIFT			18
+#define ADF_VF2PF_MSGTYPE_INIT			0x3
+#define ADF_VF2PF_MSGTYPE_SHUTDOWN		0x4
+#define ADF_VF2PF_MSGTYPE_VERSION_REQ		0x5
+#define ADF_VF2PF_MSGTYPE_COMPAT_VER_REQ	0x6
+
+/* VF->PF Compatible Version Request */
+#define ADF_VF2PF_COMPAT_VER_REQ_SHIFT		22
+
+/* Collision detection */
+#define ADF_IOV_MSG_COLLISION_DETECT_DELAY	10
+#define ADF_IOV_MSG_ACK_DELAY			2
+#define ADF_IOV_MSG_ACK_MAX_RETRY		100
+#define ADF_IOV_MSG_RETRY_DELAY			5
+#define ADF_IOV_MSG_MAX_RETRIES			3
+#define ADF_IOV_MSG_RESP_TIMEOUT	(ADF_IOV_MSG_ACK_DELAY * \
+					 ADF_IOV_MSG_ACK_MAX_RETRY + \
+					 ADF_IOV_MSG_COLLISION_DETECT_DELAY)
+#endif /* ADF_IOV_MSG_H */
diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c
new file mode 100644
index 000000000000..2f77a4a8cecb
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_sriov.c
@@ -0,0 +1,309 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/workqueue.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include "adf_common_drv.h"
+#include "adf_cfg.h"
+#include "adf_pf2vf_msg.h"
+
+static struct workqueue_struct *pf2vf_resp_wq;
+
+#define ME2FUNCTION_MAP_A_OFFSET	(0x3A400 + 0x190)
+#define ME2FUNCTION_MAP_A_NUM_REGS	96
+
+#define ME2FUNCTION_MAP_B_OFFSET	(0x3A400 + 0x310)
+#define ME2FUNCTION_MAP_B_NUM_REGS	12
+
+#define ME2FUNCTION_MAP_REG_SIZE	4
+#define ME2FUNCTION_MAP_VALID		BIT(7)
+
+#define READ_CSR_ME2FUNCTION_MAP_A(pmisc_bar_addr, index)		\
+	ADF_CSR_RD(pmisc_bar_addr, ME2FUNCTION_MAP_A_OFFSET +		\
+		   ME2FUNCTION_MAP_REG_SIZE * index)
+
+#define WRITE_CSR_ME2FUNCTION_MAP_A(pmisc_bar_addr, index, value)	\
+	ADF_CSR_WR(pmisc_bar_addr, ME2FUNCTION_MAP_A_OFFSET +		\
+		   ME2FUNCTION_MAP_REG_SIZE * index, value)
+
+#define READ_CSR_ME2FUNCTION_MAP_B(pmisc_bar_addr, index)		\
+	ADF_CSR_RD(pmisc_bar_addr, ME2FUNCTION_MAP_B_OFFSET +		\
+		   ME2FUNCTION_MAP_REG_SIZE * index)
+
+#define WRITE_CSR_ME2FUNCTION_MAP_B(pmisc_bar_addr, index, value)	\
+	ADF_CSR_WR(pmisc_bar_addr, ME2FUNCTION_MAP_B_OFFSET +		\
+		   ME2FUNCTION_MAP_REG_SIZE * index, value)
+
+struct adf_pf2vf_resp {
+	struct work_struct pf2vf_resp_work;
+	struct adf_accel_vf_info *vf_info;
+};
+
+static void adf_iov_send_resp(struct work_struct *work)
+{
+	struct adf_pf2vf_resp *pf2vf_resp =
+		container_of(work, struct adf_pf2vf_resp, pf2vf_resp_work);
+
+	adf_vf2pf_req_hndl(pf2vf_resp->vf_info);
+	kfree(pf2vf_resp);
+}
+
+static void adf_vf2pf_bh_handler(void *data)
+{
+	struct adf_accel_vf_info *vf_info = (struct adf_accel_vf_info *)data;
+	struct adf_pf2vf_resp *pf2vf_resp;
+
+	pf2vf_resp = kzalloc(sizeof(*pf2vf_resp), GFP_ATOMIC);
+	if (!pf2vf_resp)
+		return;
+
+	pf2vf_resp->vf_info = vf_info;
+	INIT_WORK(&pf2vf_resp->pf2vf_resp_work, adf_iov_send_resp);
+	queue_work(pf2vf_resp_wq, &pf2vf_resp->pf2vf_resp_work);
+}
+
+static int adf_enable_sriov(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	int totalvfs = pci_sriov_get_totalvfs(pdev);
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *pmisc_addr = pmisc->virt_addr;
+	struct adf_accel_vf_info *vf_info;
+	int i;
+	u32 reg;
+
+	/* Workqueue for PF2VF responses */
+	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
+	if (!pf2vf_resp_wq)
+		return -ENOMEM;
+
+	for (i = 0, vf_info = accel_dev->pf.vf_info; i < totalvfs;
+	     i++, vf_info++) {
+		/* This ptr will be populated when VFs will be created */
+		vf_info->accel_dev = accel_dev;
+		vf_info->vf_nr = i;
+
+		tasklet_init(&vf_info->vf2pf_bh_tasklet,
+			     (void *)adf_vf2pf_bh_handler,
+			     (unsigned long)vf_info);
+		mutex_init(&vf_info->pf2vf_lock);
+		ratelimit_state_init(&vf_info->vf2pf_ratelimit,
+				     DEFAULT_RATELIMIT_INTERVAL,
+				     DEFAULT_RATELIMIT_BURST);
+	}
+
+	/* Set Valid bits in ME Thread to PCIe Function Mapping Group A */
+	for (i = 0; i < ME2FUNCTION_MAP_A_NUM_REGS; i++) {
+		reg = READ_CSR_ME2FUNCTION_MAP_A(pmisc_addr, i);
+		reg |= ME2FUNCTION_MAP_VALID;
+		WRITE_CSR_ME2FUNCTION_MAP_A(pmisc_addr, i, reg);
+	}
+
+	/* Set Valid bits in ME Thread to PCIe Function Mapping Group B */
+	for (i = 0; i < ME2FUNCTION_MAP_B_NUM_REGS; i++) {
+		reg = READ_CSR_ME2FUNCTION_MAP_B(pmisc_addr, i);
+		reg |= ME2FUNCTION_MAP_VALID;
+		WRITE_CSR_ME2FUNCTION_MAP_B(pmisc_addr, i, reg);
+	}
+
+	/* Enable VF to PF interrupts for all VFs */
+	adf_enable_vf2pf_interrupts(accel_dev, GENMASK_ULL(totalvfs - 1, 0));
+
+	/*
+	 * Due to the hardware design, when SR-IOV and the ring arbiter
+	 * are enabled all the VFs supported in hardware must be enabled in
+	 * order for all the hardware resources (i.e. bundles) to be usable.
+	 * When SR-IOV is enabled, each of the VFs will own one bundle.
+	 */
+	return pci_enable_sriov(pdev, totalvfs);
+}
+
+/**
+ * adf_disable_sriov() - Disable SRIOV for the device
+ * @pdev:  Pointer to pci device.
+ *
+ * Function disables SRIOV for the pci device.
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+void adf_disable_sriov(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *pmisc_addr = pmisc->virt_addr;
+	int totalvfs = pci_sriov_get_totalvfs(accel_to_pci_dev(accel_dev));
+	struct adf_accel_vf_info *vf;
+	u32 reg;
+	int i;
+
+	if (!accel_dev->pf.vf_info)
+		return;
+
+	adf_pf2vf_notify_restarting(accel_dev);
+
+	pci_disable_sriov(accel_to_pci_dev(accel_dev));
+
+	/* Disable VF to PF interrupts */
+	adf_disable_vf2pf_interrupts(accel_dev, 0xFFFFFFFF);
+
+	/* Clear Valid bits in ME Thread to PCIe Function Mapping Group A */
+	for (i = 0; i < ME2FUNCTION_MAP_A_NUM_REGS; i++) {
+		reg = READ_CSR_ME2FUNCTION_MAP_A(pmisc_addr, i);
+		reg &= ~ME2FUNCTION_MAP_VALID;
+		WRITE_CSR_ME2FUNCTION_MAP_A(pmisc_addr, i, reg);
+	}
+
+	/* Clear Valid bits in ME Thread to PCIe Function Mapping Group B */
+	for (i = 0; i < ME2FUNCTION_MAP_B_NUM_REGS; i++) {
+		reg = READ_CSR_ME2FUNCTION_MAP_B(pmisc_addr, i);
+		reg &= ~ME2FUNCTION_MAP_VALID;
+		WRITE_CSR_ME2FUNCTION_MAP_B(pmisc_addr, i, reg);
+	}
+
+	for (i = 0, vf = accel_dev->pf.vf_info; i < totalvfs; i++, vf++) {
+		tasklet_disable(&vf->vf2pf_bh_tasklet);
+		tasklet_kill(&vf->vf2pf_bh_tasklet);
+		mutex_destroy(&vf->pf2vf_lock);
+	}
+
+	kfree(accel_dev->pf.vf_info);
+	accel_dev->pf.vf_info = NULL;
+
+	if (pf2vf_resp_wq) {
+		destroy_workqueue(pf2vf_resp_wq);
+		pf2vf_resp_wq = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(adf_disable_sriov);
+
+/**
+ * adf_sriov_configure() - Enable SRIOV for the device
+ * @pdev:  Pointer to pci device.
+ *
+ * Function enables SRIOV for the pci device.
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+	int totalvfs = pci_sriov_get_totalvfs(pdev);
+	unsigned long val;
+	int ret;
+
+	if (!accel_dev) {
+		dev_err(&pdev->dev, "Failed to find accel_dev\n");
+		return -EFAULT;
+	}
+
+	if (!iommu_present(&pci_bus_type)) {
+		dev_err(&pdev->dev,
+			"IOMMU must be enabled for SR-IOV to work\n");
+		return -EINVAL;
+	}
+
+	if (accel_dev->pf.vf_info) {
+		dev_info(&pdev->dev, "Already enabled for this device\n");
+		return -EINVAL;
+	}
+
+	if (adf_dev_started(accel_dev)) {
+		if (adf_devmgr_in_reset(accel_dev) ||
+		    adf_dev_in_use(accel_dev)) {
+			dev_err(&GET_DEV(accel_dev), "Device busy\n");
+			return -EBUSY;
+		}
+
+		if (adf_dev_stop(accel_dev)) {
+			dev_err(&GET_DEV(accel_dev),
+				"Failed to stop qat_dev%d\n",
+				accel_dev->accel_id);
+			return -EFAULT;
+		}
+
+		adf_dev_shutdown(accel_dev);
+	}
+
+	if (adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC))
+		return -EFAULT;
+	val = 0;
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					ADF_NUM_CY, (void *)&val, ADF_DEC))
+		return -EFAULT;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+
+	/* Allocate memory for VF info structs */
+	accel_dev->pf.vf_info = kcalloc(totalvfs,
+					sizeof(struct adf_accel_vf_info),
+					GFP_KERNEL);
+	if (!accel_dev->pf.vf_info)
+		return -ENOMEM;
+
+	if (adf_dev_init(accel_dev)) {
+		dev_err(&GET_DEV(accel_dev), "Failed to init qat_dev%d\n",
+			accel_dev->accel_id);
+		return -EFAULT;
+	}
+
+	if (adf_dev_start(accel_dev)) {
+		dev_err(&GET_DEV(accel_dev), "Failed to start qat_dev%d\n",
+			accel_dev->accel_id);
+		return -EFAULT;
+	}
+
+	ret = adf_enable_sriov(accel_dev);
+	if (ret)
+		return ret;
+
+	return numvfs;
+}
+EXPORT_SYMBOL_GPL(adf_sriov_configure);
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c
index db2926bff8a5..3865ae8d96d9 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.c
+++ b/drivers/crypto/qat/qat_common/adf_transport.c
@@ -264,6 +264,10 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 		dev_err(&GET_DEV(accel_dev), "Can't get ring number\n");
 		return -EFAULT;
 	}
+	if (ring_num >= ADF_ETR_MAX_RINGS_PER_BANK) {
+		dev_err(&GET_DEV(accel_dev), "Invalid ring number\n");
+		return -EFAULT;
+	}
 
 	bank = &transport_data->banks[bank_num];
 	if (adf_reserve_ring(bank, ring_num)) {
@@ -285,7 +289,7 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 		goto err;
 
 	/* Enable HW arbitration for the given ring */
-	accel_dev->hw_device->hw_arb_ring_enable(ring);
+	adf_update_ring_arb(ring);
 
 	if (adf_ring_debugfs_add(ring, ring_name)) {
 		dev_err(&GET_DEV(accel_dev),
@@ -302,14 +306,13 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 err:
 	adf_cleanup_ring(ring);
 	adf_unreserve_ring(bank, ring_num);
-	accel_dev->hw_device->hw_arb_ring_disable(ring);
+	adf_update_ring_arb(ring);
 	return ret;
 }
 
 void adf_remove_ring(struct adf_etr_ring_data *ring)
 {
 	struct adf_etr_bank_data *bank = ring->bank;
-	struct adf_accel_dev *accel_dev = bank->accel_dev;
 
 	/* Disable interrupts for the given ring */
 	adf_disable_ring_irq(bank, ring->ring_number);
@@ -322,7 +325,7 @@ void adf_remove_ring(struct adf_etr_ring_data *ring)
 	adf_ring_debugfs_rm(ring);
 	adf_unreserve_ring(bank, ring->ring_number);
 	/* Disable HW arbitration for the given ring */
-	accel_dev->hw_device->hw_arb_ring_disable(ring);
+	adf_update_ring_arb(ring);
 	adf_cleanup_ring(ring);
 }
 
@@ -463,7 +466,7 @@ err:
  * acceleration device accel_dev.
  * To be used by QAT device specific drivers.
  *
- * Return: 0 on success, error code othewise.
+ * Return: 0 on success, error code otherwise.
  */
 int adf_init_etr_data(struct adf_accel_dev *accel_dev)
 {
diff --git a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h b/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
index 160c9a36c919..6ad7e4e1edca 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
+++ b/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
@@ -97,8 +97,9 @@
 #define ADF_RING_SIZE_IN_BYTES_TO_SIZE(SIZE) ((1 << (SIZE - 1)) >> 7)
 
 /* Minimum ring bufer size for memory allocation */
-#define ADF_RING_SIZE_BYTES_MIN(SIZE) ((SIZE < ADF_RING_SIZE_4K) ? \
-				ADF_RING_SIZE_4K : SIZE)
+#define ADF_RING_SIZE_BYTES_MIN(SIZE) \
+	((SIZE < ADF_SIZE_TO_RING_SIZE_IN_BYTES(ADF_RING_SIZE_4K)) ? \
+		ADF_SIZE_TO_RING_SIZE_IN_BYTES(ADF_RING_SIZE_4K) : SIZE)
 #define ADF_RING_SIZE_MODULO(SIZE) (SIZE + 0x6)
 #define ADF_SIZE_TO_POW(SIZE) ((((SIZE & 0x4) >> 1) | ((SIZE & 0x4) >> 2) | \
 				SIZE) & ~0x4)
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw.h b/drivers/crypto/qat/qat_common/icp_qat_fw.h
index f1e30e24a419..46747f01b1d1 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw.h
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw.h
@@ -249,6 +249,8 @@ struct icp_qat_fw_comn_resp {
 
 #define QAT_COMN_RESP_CRYPTO_STATUS_BITPOS 7
 #define QAT_COMN_RESP_CRYPTO_STATUS_MASK 0x1
+#define QAT_COMN_RESP_PKE_STATUS_BITPOS 6
+#define QAT_COMN_RESP_PKE_STATUS_MASK 0x1
 #define QAT_COMN_RESP_CMP_STATUS_BITPOS 5
 #define QAT_COMN_RESP_CMP_STATUS_MASK 0x1
 #define QAT_COMN_RESP_XLAT_STATUS_BITPOS 4
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_pke.h b/drivers/crypto/qat/qat_common/icp_qat_fw_pke.h
new file mode 100644
index 000000000000..0d7a9b51ce9f
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw_pke.h
@@ -0,0 +1,112 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+	* Redistributions of source code must retain the above copyright
+	  notice, this list of conditions and the following disclaimer.
+	* Redistributions in binary form must reproduce the above copyright
+	  notice, this list of conditions and the following disclaimer in
+	  the documentation and/or other materials provided with the
+	  distribution.
+	* Neither the name of Intel Corporation nor the names of its
+	  contributors may be used to endorse or promote products derived
+	  from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef _ICP_QAT_FW_PKE_
+#define _ICP_QAT_FW_PKE_
+
+#include "icp_qat_fw.h"
+
+struct icp_qat_fw_req_hdr_pke_cd_pars {
+	u64 content_desc_addr;
+	u32 content_desc_resrvd;
+	u32 func_id;
+};
+
+struct icp_qat_fw_req_pke_mid {
+	u64 opaque;
+	u64 src_data_addr;
+	u64 dest_data_addr;
+};
+
+struct icp_qat_fw_req_pke_hdr {
+	u8 resrvd1;
+	u8 resrvd2;
+	u8 service_type;
+	u8 hdr_flags;
+	u16 comn_req_flags;
+	u16 resrvd4;
+	struct icp_qat_fw_req_hdr_pke_cd_pars cd_pars;
+};
+
+struct icp_qat_fw_pke_request {
+	struct icp_qat_fw_req_pke_hdr pke_hdr;
+	struct icp_qat_fw_req_pke_mid pke_mid;
+	u8 output_param_count;
+	u8 input_param_count;
+	u16 resrvd1;
+	u32 resrvd2;
+	u64 next_req_adr;
+};
+
+struct icp_qat_fw_resp_pke_hdr {
+	u8 resrvd1;
+	u8 resrvd2;
+	u8 response_type;
+	u8 hdr_flags;
+	u16 comn_resp_flags;
+	u16 resrvd4;
+};
+
+struct icp_qat_fw_pke_resp {
+	struct icp_qat_fw_resp_pke_hdr pke_resp_hdr;
+	u64 opaque;
+	u64 src_data_addr;
+	u64 dest_data_addr;
+};
+
+#define ICP_QAT_FW_PKE_HDR_VALID_FLAG_BITPOS              7
+#define ICP_QAT_FW_PKE_HDR_VALID_FLAG_MASK                0x1
+#define ICP_QAT_FW_PKE_RESP_PKE_STAT_GET(status_word) \
+	QAT_FIELD_GET(((status_word >> ICP_QAT_FW_COMN_ONE_BYTE_SHIFT) & \
+		ICP_QAT_FW_COMN_SINGLE_BYTE_MASK), \
+		QAT_COMN_RESP_PKE_STATUS_BITPOS, \
+		QAT_COMN_RESP_PKE_STATUS_MASK)
+
+#define ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(hdr_t, val) \
+	QAT_FIELD_SET((hdr_t.hdr_flags), (val), \
+		ICP_QAT_FW_PKE_HDR_VALID_FLAG_BITPOS, \
+		ICP_QAT_FW_PKE_HDR_VALID_FLAG_MASK)
+#endif
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 067402c7c2a9..2bd913aceaeb 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -53,7 +53,6 @@
 #include <crypto/hash.h>
 #include <crypto/algapi.h>
 #include <crypto/authenc.h>
-#include <crypto/rng.h>
 #include <linux/dma-mapping.h>
 #include "adf_accel_devices.h"
 #include "adf_transport.h"
@@ -73,7 +72,8 @@
 				       ICP_QAT_HW_CIPHER_KEY_CONVERT, \
 				       ICP_QAT_HW_CIPHER_DECRYPT)
 
-static atomic_t active_dev;
+static DEFINE_MUTEX(algs_lock);
+static unsigned int active_devs;
 
 struct qat_alg_buf {
 	uint32_t len;
@@ -112,9 +112,6 @@ struct qat_alg_aead_ctx {
 	struct crypto_shash *hash_tfm;
 	enum icp_qat_hw_auth_algo qat_hash_alg;
 	struct qat_crypto_instance *inst;
-	struct crypto_tfm *tfm;
-	uint8_t salt[AES_BLOCK_SIZE];
-	spinlock_t lock;	/* protects qat_alg_aead_ctx struct */
 };
 
 struct qat_alg_ablkcipher_ctx {
@@ -129,11 +126,6 @@ struct qat_alg_ablkcipher_ctx {
 	spinlock_t lock;	/* protects qat_alg_ablkcipher_ctx struct */
 };
 
-static int get_current_node(void)
-{
-	return cpu_data(current_thread_info()->cpu).phys_proc_id;
-}
-
 static int qat_get_inter_state_size(enum icp_qat_hw_auth_algo qat_hash_alg)
 {
 	switch (qat_hash_alg) {
@@ -277,12 +269,12 @@ static void qat_alg_init_common_hdr(struct icp_qat_fw_comn_req_hdr *header)
 				       ICP_QAT_FW_LA_NO_UPDATE_STATE);
 }
 
-static int qat_alg_aead_init_enc_session(struct qat_alg_aead_ctx *ctx,
+static int qat_alg_aead_init_enc_session(struct crypto_aead *aead_tfm,
 					 int alg,
 					 struct crypto_authenc_keys *keys)
 {
-	struct crypto_aead *aead_tfm = __crypto_aead_cast(ctx->tfm);
-	unsigned int digestsize = crypto_aead_crt(aead_tfm)->authsize;
+	struct qat_alg_aead_ctx *ctx = crypto_aead_ctx(aead_tfm);
+	unsigned int digestsize = crypto_aead_authsize(aead_tfm);
 	struct qat_enc *enc_ctx = &ctx->enc_cd->qat_enc_cd;
 	struct icp_qat_hw_cipher_algo_blk *cipher = &enc_ctx->cipher;
 	struct icp_qat_hw_auth_algo_blk *hash =
@@ -357,12 +349,12 @@ static int qat_alg_aead_init_enc_session(struct qat_alg_aead_ctx *ctx,
 	return 0;
 }
 
-static int qat_alg_aead_init_dec_session(struct qat_alg_aead_ctx *ctx,
+static int qat_alg_aead_init_dec_session(struct crypto_aead *aead_tfm,
 					 int alg,
 					 struct crypto_authenc_keys *keys)
 {
-	struct crypto_aead *aead_tfm = __crypto_aead_cast(ctx->tfm);
-	unsigned int digestsize = crypto_aead_crt(aead_tfm)->authsize;
+	struct qat_alg_aead_ctx *ctx = crypto_aead_ctx(aead_tfm);
+	unsigned int digestsize = crypto_aead_authsize(aead_tfm);
 	struct qat_dec *dec_ctx = &ctx->dec_cd->qat_dec_cd;
 	struct icp_qat_hw_auth_algo_blk *hash = &dec_ctx->hash;
 	struct icp_qat_hw_cipher_algo_blk *cipher =
@@ -514,30 +506,27 @@ static int qat_alg_validate_key(int key_len, int *alg)
 	return 0;
 }
 
-static int qat_alg_aead_init_sessions(struct qat_alg_aead_ctx *ctx,
+static int qat_alg_aead_init_sessions(struct crypto_aead *tfm,
 				      const uint8_t *key, unsigned int keylen)
 {
 	struct crypto_authenc_keys keys;
 	int alg;
 
-	if (crypto_rng_get_bytes(crypto_default_rng, ctx->salt, AES_BLOCK_SIZE))
-		return -EFAULT;
-
 	if (crypto_authenc_extractkeys(&keys, key, keylen))
 		goto bad_key;
 
 	if (qat_alg_validate_key(keys.enckeylen, &alg))
 		goto bad_key;
 
-	if (qat_alg_aead_init_enc_session(ctx, alg, &keys))
+	if (qat_alg_aead_init_enc_session(tfm, alg, &keys))
 		goto error;
 
-	if (qat_alg_aead_init_dec_session(ctx, alg, &keys))
+	if (qat_alg_aead_init_dec_session(tfm, alg, &keys))
 		goto error;
 
 	return 0;
 bad_key:
-	crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 	return -EINVAL;
 error:
 	return -EFAULT;
@@ -566,7 +555,6 @@ static int qat_alg_aead_setkey(struct crypto_aead *tfm, const uint8_t *key,
 	struct qat_alg_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct device *dev;
 
-	spin_lock(&ctx->lock);
 	if (ctx->enc_cd) {
 		/* rekeying */
 		dev = &GET_DEV(ctx->inst->accel_dev);
@@ -580,7 +568,6 @@ static int qat_alg_aead_setkey(struct crypto_aead *tfm, const uint8_t *key,
 		struct qat_crypto_instance *inst =
 				qat_crypto_get_instance_node(node);
 		if (!inst) {
-			spin_unlock(&ctx->lock);
 			return -EINVAL;
 		}
 
@@ -590,19 +577,16 @@ static int qat_alg_aead_setkey(struct crypto_aead *tfm, const uint8_t *key,
 						  &ctx->enc_cd_paddr,
 						  GFP_ATOMIC);
 		if (!ctx->enc_cd) {
-			spin_unlock(&ctx->lock);
 			return -ENOMEM;
 		}
 		ctx->dec_cd = dma_zalloc_coherent(dev, sizeof(*ctx->dec_cd),
 						  &ctx->dec_cd_paddr,
 						  GFP_ATOMIC);
 		if (!ctx->dec_cd) {
-			spin_unlock(&ctx->lock);
 			goto out_free_enc;
 		}
 	}
-	spin_unlock(&ctx->lock);
-	if (qat_alg_aead_init_sessions(ctx, key, keylen))
+	if (qat_alg_aead_init_sessions(tfm, key, keylen))
 		goto out_free_all;
 
 	return 0;
@@ -653,22 +637,20 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 }
 
 static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
-			       struct scatterlist *assoc, int assoclen,
 			       struct scatterlist *sgl,
-			       struct scatterlist *sglout, uint8_t *iv,
-			       uint8_t ivlen,
+			       struct scatterlist *sglout,
 			       struct qat_crypto_request *qat_req)
 {
 	struct device *dev = &GET_DEV(inst->accel_dev);
-	int i, bufs = 0, sg_nctr = 0;
-	int n = sg_nents(sgl), assoc_n = sg_nents(assoc);
+	int i, sg_nctr = 0;
+	int n = sg_nents(sgl);
 	struct qat_alg_buf_list *bufl;
 	struct qat_alg_buf_list *buflout = NULL;
 	dma_addr_t blp;
 	dma_addr_t bloutp = 0;
 	struct scatterlist *sg;
 	size_t sz_out, sz = sizeof(struct qat_alg_buf_list) +
-			((1 + n + assoc_n) * sizeof(struct qat_alg_buf));
+			((1 + n) * sizeof(struct qat_alg_buf));
 
 	if (unlikely(!n))
 		return -EINVAL;
@@ -682,35 +664,8 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 	if (unlikely(dma_mapping_error(dev, blp)))
 		goto err;
 
-	for_each_sg(assoc, sg, assoc_n, i) {
-		if (!sg->length)
-			continue;
-
-		if (!(assoclen > 0))
-			break;
-
-		bufl->bufers[bufs].addr =
-			dma_map_single(dev, sg_virt(sg),
-				       min_t(int, assoclen, sg->length),
-				       DMA_BIDIRECTIONAL);
-		bufl->bufers[bufs].len = min_t(int, assoclen, sg->length);
-		if (unlikely(dma_mapping_error(dev, bufl->bufers[bufs].addr)))
-			goto err;
-		bufs++;
-		assoclen -= sg->length;
-	}
-
-	if (ivlen) {
-		bufl->bufers[bufs].addr = dma_map_single(dev, iv, ivlen,
-							 DMA_BIDIRECTIONAL);
-		bufl->bufers[bufs].len = ivlen;
-		if (unlikely(dma_mapping_error(dev, bufl->bufers[bufs].addr)))
-			goto err;
-		bufs++;
-	}
-
 	for_each_sg(sgl, sg, n, i) {
-		int y = sg_nctr + bufs;
+		int y = sg_nctr;
 
 		if (!sg->length)
 			continue;
@@ -723,7 +678,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 			goto err;
 		sg_nctr++;
 	}
-	bufl->num_bufs = sg_nctr + bufs;
+	bufl->num_bufs = sg_nctr;
 	qat_req->buf.bl = bufl;
 	qat_req->buf.blp = blp;
 	qat_req->buf.sz = sz;
@@ -733,7 +688,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 
 		n = sg_nents(sglout);
 		sz_out = sizeof(struct qat_alg_buf_list) +
-			((1 + n + assoc_n) * sizeof(struct qat_alg_buf));
+			((1 + n) * sizeof(struct qat_alg_buf));
 		sg_nctr = 0;
 		buflout = kzalloc_node(sz_out, GFP_ATOMIC,
 				       dev_to_node(&GET_DEV(inst->accel_dev)));
@@ -743,14 +698,8 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 		if (unlikely(dma_mapping_error(dev, bloutp)))
 			goto err;
 		bufers = buflout->bufers;
-		/* For out of place operation dma map only data and
-		 * reuse assoc mapping and iv */
-		for (i = 0; i < bufs; i++) {
-			bufers[i].len = bufl->bufers[i].len;
-			bufers[i].addr = bufl->bufers[i].addr;
-		}
 		for_each_sg(sglout, sg, n, i) {
-			int y = sg_nctr + bufs;
+			int y = sg_nctr;
 
 			if (!sg->length)
 				continue;
@@ -763,7 +712,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 			bufers[y].len = sg->length;
 			sg_nctr++;
 		}
-		buflout->num_bufs = sg_nctr + bufs;
+		buflout->num_bufs = sg_nctr;
 		buflout->num_mapped_bufs = sg_nctr;
 		qat_req->buf.blout = buflout;
 		qat_req->buf.bloutp = bloutp;
@@ -777,7 +726,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 err:
 	dev_err(dev, "Failed to map buf for dma\n");
 	sg_nctr = 0;
-	for (i = 0; i < n + bufs; i++)
+	for (i = 0; i < n; i++)
 		if (!dma_mapping_error(dev, bufl->bufers[i].addr))
 			dma_unmap_single(dev, bufl->bufers[i].addr,
 					 bufl->bufers[i].len,
@@ -788,7 +737,7 @@ err:
 	kfree(bufl);
 	if (sgl != sglout && buflout) {
 		n = sg_nents(sglout);
-		for (i = bufs; i < n + bufs; i++)
+		for (i = 0; i < n; i++)
 			if (!dma_mapping_error(dev, buflout->bufers[i].addr))
 				dma_unmap_single(dev, buflout->bufers[i].addr,
 						 buflout->bufers[i].len,
@@ -848,12 +797,10 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	struct icp_qat_fw_la_cipher_req_params *cipher_param;
 	struct icp_qat_fw_la_auth_req_params *auth_param;
 	struct icp_qat_fw_la_bulk_req *msg;
-	int digst_size = crypto_aead_crt(aead_tfm)->authsize;
+	int digst_size = crypto_aead_authsize(aead_tfm);
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->assoclen,
-				  areq->src, areq->dst, areq->iv,
-				  AES_BLOCK_SIZE, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -867,12 +814,11 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	qat_req->req.comn_mid.dest_data_addr = qat_req->buf.bloutp;
 	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
 	cipher_param->cipher_length = areq->cryptlen - digst_size;
-	cipher_param->cipher_offset = areq->assoclen + AES_BLOCK_SIZE;
+	cipher_param->cipher_offset = areq->assoclen;
 	memcpy(cipher_param->u.cipher_IV_array, areq->iv, AES_BLOCK_SIZE);
 	auth_param = (void *)((uint8_t *)cipher_param + sizeof(*cipher_param));
 	auth_param->auth_off = 0;
-	auth_param->auth_len = areq->assoclen +
-				cipher_param->cipher_length + AES_BLOCK_SIZE;
+	auth_param->auth_len = areq->assoclen + cipher_param->cipher_length;
 	do {
 		ret = adf_send_message(ctx->inst->sym_tx, (uint32_t *)msg);
 	} while (ret == -EAGAIN && ctr++ < 10);
@@ -884,8 +830,7 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	return -EINPROGRESS;
 }
 
-static int qat_alg_aead_enc_internal(struct aead_request *areq, uint8_t *iv,
-				     int enc_iv)
+static int qat_alg_aead_enc(struct aead_request *areq)
 {
 	struct crypto_aead *aead_tfm = crypto_aead_reqtfm(areq);
 	struct crypto_tfm *tfm = crypto_aead_tfm(aead_tfm);
@@ -894,11 +839,10 @@ static int qat_alg_aead_enc_internal(struct aead_request *areq, uint8_t *iv,
 	struct icp_qat_fw_la_cipher_req_params *cipher_param;
 	struct icp_qat_fw_la_auth_req_params *auth_param;
 	struct icp_qat_fw_la_bulk_req *msg;
+	uint8_t *iv = areq->iv;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->assoclen,
-				  areq->src, areq->dst, iv, AES_BLOCK_SIZE,
-				  qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -913,16 +857,12 @@ static int qat_alg_aead_enc_internal(struct aead_request *areq, uint8_t *iv,
 	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
 	auth_param = (void *)((uint8_t *)cipher_param + sizeof(*cipher_param));
 
-	if (enc_iv) {
-		cipher_param->cipher_length = areq->cryptlen + AES_BLOCK_SIZE;
-		cipher_param->cipher_offset = areq->assoclen;
-	} else {
-		memcpy(cipher_param->u.cipher_IV_array, iv, AES_BLOCK_SIZE);
-		cipher_param->cipher_length = areq->cryptlen;
-		cipher_param->cipher_offset = areq->assoclen + AES_BLOCK_SIZE;
-	}
+	memcpy(cipher_param->u.cipher_IV_array, iv, AES_BLOCK_SIZE);
+	cipher_param->cipher_length = areq->cryptlen;
+	cipher_param->cipher_offset = areq->assoclen;
+
 	auth_param->auth_off = 0;
-	auth_param->auth_len = areq->assoclen + areq->cryptlen + AES_BLOCK_SIZE;
+	auth_param->auth_len = areq->assoclen + areq->cryptlen;
 
 	do {
 		ret = adf_send_message(ctx->inst->sym_tx, (uint32_t *)msg);
@@ -935,25 +875,6 @@ static int qat_alg_aead_enc_internal(struct aead_request *areq, uint8_t *iv,
 	return -EINPROGRESS;
 }
 
-static int qat_alg_aead_enc(struct aead_request *areq)
-{
-	return qat_alg_aead_enc_internal(areq, areq->iv, 0);
-}
-
-static int qat_alg_aead_genivenc(struct aead_givcrypt_request *req)
-{
-	struct crypto_aead *aead_tfm = crypto_aead_reqtfm(&req->areq);
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead_tfm);
-	struct qat_alg_aead_ctx *ctx = crypto_tfm_ctx(tfm);
-	__be64 seq;
-
-	memcpy(req->giv, ctx->salt, AES_BLOCK_SIZE);
-	seq = cpu_to_be64(req->seq);
-	memcpy(req->giv + AES_BLOCK_SIZE - sizeof(uint64_t),
-	       &seq, sizeof(uint64_t));
-	return qat_alg_aead_enc_internal(&req->areq, req->giv, 1);
-}
-
 static int qat_alg_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 				     const uint8_t *key,
 				     unsigned int keylen)
@@ -1025,8 +946,7 @@ static int qat_alg_ablkcipher_encrypt(struct ablkcipher_request *req)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, 0, req->src, req->dst,
-				  NULL, 0, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, req->src, req->dst, qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -1063,8 +983,7 @@ static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, 0, req->src, req->dst,
-				  NULL, 0, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, req->src, req->dst, qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -1091,47 +1010,43 @@ static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
 	return -EINPROGRESS;
 }
 
-static int qat_alg_aead_init(struct crypto_tfm *tfm,
+static int qat_alg_aead_init(struct crypto_aead *tfm,
 			     enum icp_qat_hw_auth_algo hash,
 			     const char *hash_name)
 {
-	struct qat_alg_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_alg_aead_ctx *ctx = crypto_aead_ctx(tfm);
 
 	ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0);
 	if (IS_ERR(ctx->hash_tfm))
-		return -EFAULT;
-	spin_lock_init(&ctx->lock);
+		return PTR_ERR(ctx->hash_tfm);
 	ctx->qat_hash_alg = hash;
-	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
-		sizeof(struct aead_request) +
-		sizeof(struct qat_crypto_request));
-	ctx->tfm = tfm;
+	crypto_aead_set_reqsize(tfm, sizeof(struct aead_request) +
+				     sizeof(struct qat_crypto_request));
 	return 0;
 }
 
-static int qat_alg_aead_sha1_init(struct crypto_tfm *tfm)
+static int qat_alg_aead_sha1_init(struct crypto_aead *tfm)
 {
 	return qat_alg_aead_init(tfm, ICP_QAT_HW_AUTH_ALGO_SHA1, "sha1");
 }
 
-static int qat_alg_aead_sha256_init(struct crypto_tfm *tfm)
+static int qat_alg_aead_sha256_init(struct crypto_aead *tfm)
 {
 	return qat_alg_aead_init(tfm, ICP_QAT_HW_AUTH_ALGO_SHA256, "sha256");
 }
 
-static int qat_alg_aead_sha512_init(struct crypto_tfm *tfm)
+static int qat_alg_aead_sha512_init(struct crypto_aead *tfm)
 {
 	return qat_alg_aead_init(tfm, ICP_QAT_HW_AUTH_ALGO_SHA512, "sha512");
 }
 
-static void qat_alg_aead_exit(struct crypto_tfm *tfm)
+static void qat_alg_aead_exit(struct crypto_aead *tfm)
 {
-	struct qat_alg_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_alg_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev;
 
-	if (!IS_ERR(ctx->hash_tfm))
-		crypto_free_shash(ctx->hash_tfm);
+	crypto_free_shash(ctx->hash_tfm);
 
 	if (!inst)
 		return;
@@ -1188,73 +1103,61 @@ static void qat_alg_ablkcipher_exit(struct crypto_tfm *tfm)
 	qat_crypto_put_instance(inst);
 }
 
-static struct crypto_alg qat_algs[] = { {
-	.cra_name = "authenc(hmac(sha1),cbc(aes))",
-	.cra_driver_name = "qat_aes_cbc_hmac_sha1",
-	.cra_priority = 4001,
-	.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct qat_alg_aead_ctx),
-	.cra_alignmask = 0,
-	.cra_type = &crypto_aead_type,
-	.cra_module = THIS_MODULE,
-	.cra_init = qat_alg_aead_sha1_init,
-	.cra_exit = qat_alg_aead_exit,
-	.cra_u = {
-		.aead = {
-			.setkey = qat_alg_aead_setkey,
-			.decrypt = qat_alg_aead_dec,
-			.encrypt = qat_alg_aead_enc,
-			.givencrypt = qat_alg_aead_genivenc,
-			.ivsize = AES_BLOCK_SIZE,
-			.maxauthsize = SHA1_DIGEST_SIZE,
-		},
+
+static struct aead_alg qat_aeads[] = { {
+	.base = {
+		.cra_name = "authenc(hmac(sha1),cbc(aes))",
+		.cra_driver_name = "qat_aes_cbc_hmac_sha1",
+		.cra_priority = 4001,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct qat_alg_aead_ctx),
+		.cra_module = THIS_MODULE,
 	},
+	.init = qat_alg_aead_sha1_init,
+	.exit = qat_alg_aead_exit,
+	.setkey = qat_alg_aead_setkey,
+	.decrypt = qat_alg_aead_dec,
+	.encrypt = qat_alg_aead_enc,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA1_DIGEST_SIZE,
 }, {
-	.cra_name = "authenc(hmac(sha256),cbc(aes))",
-	.cra_driver_name = "qat_aes_cbc_hmac_sha256",
-	.cra_priority = 4001,
-	.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct qat_alg_aead_ctx),
-	.cra_alignmask = 0,
-	.cra_type = &crypto_aead_type,
-	.cra_module = THIS_MODULE,
-	.cra_init = qat_alg_aead_sha256_init,
-	.cra_exit = qat_alg_aead_exit,
-	.cra_u = {
-		.aead = {
-			.setkey = qat_alg_aead_setkey,
-			.decrypt = qat_alg_aead_dec,
-			.encrypt = qat_alg_aead_enc,
-			.givencrypt = qat_alg_aead_genivenc,
-			.ivsize = AES_BLOCK_SIZE,
-			.maxauthsize = SHA256_DIGEST_SIZE,
-		},
+	.base = {
+		.cra_name = "authenc(hmac(sha256),cbc(aes))",
+		.cra_driver_name = "qat_aes_cbc_hmac_sha256",
+		.cra_priority = 4001,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct qat_alg_aead_ctx),
+		.cra_module = THIS_MODULE,
 	},
+	.init = qat_alg_aead_sha256_init,
+	.exit = qat_alg_aead_exit,
+	.setkey = qat_alg_aead_setkey,
+	.decrypt = qat_alg_aead_dec,
+	.encrypt = qat_alg_aead_enc,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA256_DIGEST_SIZE,
 }, {
-	.cra_name = "authenc(hmac(sha512),cbc(aes))",
-	.cra_driver_name = "qat_aes_cbc_hmac_sha512",
-	.cra_priority = 4001,
-	.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize = sizeof(struct qat_alg_aead_ctx),
-	.cra_alignmask = 0,
-	.cra_type = &crypto_aead_type,
-	.cra_module = THIS_MODULE,
-	.cra_init = qat_alg_aead_sha512_init,
-	.cra_exit = qat_alg_aead_exit,
-	.cra_u = {
-		.aead = {
-			.setkey = qat_alg_aead_setkey,
-			.decrypt = qat_alg_aead_dec,
-			.encrypt = qat_alg_aead_enc,
-			.givencrypt = qat_alg_aead_genivenc,
-			.ivsize = AES_BLOCK_SIZE,
-			.maxauthsize = SHA512_DIGEST_SIZE,
-		},
+	.base = {
+		.cra_name = "authenc(hmac(sha512),cbc(aes))",
+		.cra_driver_name = "qat_aes_cbc_hmac_sha512",
+		.cra_priority = 4001,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct qat_alg_aead_ctx),
+		.cra_module = THIS_MODULE,
 	},
-}, {
+	.init = qat_alg_aead_sha512_init,
+	.exit = qat_alg_aead_exit,
+	.setkey = qat_alg_aead_setkey,
+	.decrypt = qat_alg_aead_dec,
+	.encrypt = qat_alg_aead_enc,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA512_DIGEST_SIZE,
+} };
+
+static struct crypto_alg qat_algs[] = { {
 	.cra_name = "cbc(aes)",
 	.cra_driver_name = "qat_aes_cbc",
 	.cra_priority = 4001,
@@ -1280,35 +1183,54 @@ static struct crypto_alg qat_algs[] = { {
 
 int qat_algs_register(void)
 {
-	if (atomic_add_return(1, &active_dev) == 1) {
-		int i;
+	int ret = 0, i;
 
-		for (i = 0; i < ARRAY_SIZE(qat_algs); i++)
-			qat_algs[i].cra_flags =
-				(qat_algs[i].cra_type == &crypto_aead_type) ?
-				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC :
-				CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC;
+	mutex_lock(&algs_lock);
+	if (++active_devs != 1)
+		goto unlock;
 
-		return crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
-	}
-	return 0;
+	for (i = 0; i < ARRAY_SIZE(qat_algs); i++)
+		qat_algs[i].cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC;
+
+	ret = crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	if (ret)
+		goto unlock;
+
+	for (i = 0; i < ARRAY_SIZE(qat_aeads); i++)
+		qat_aeads[i].base.cra_flags = CRYPTO_ALG_ASYNC;
+
+	ret = crypto_register_aeads(qat_aeads, ARRAY_SIZE(qat_aeads));
+	if (ret)
+		goto unreg_algs;
+
+unlock:
+	mutex_unlock(&algs_lock);
+	return ret;
+
+unreg_algs:
+	crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	goto unlock;
 }
 
 int qat_algs_unregister(void)
 {
-	if (atomic_sub_return(1, &active_dev) == 0)
-		return crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	mutex_lock(&algs_lock);
+	if (--active_devs != 0)
+		goto unlock;
+
+	crypto_unregister_aeads(qat_aeads, ARRAY_SIZE(qat_aeads));
+	crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+
+unlock:
+	mutex_unlock(&algs_lock);
 	return 0;
 }
 
 int qat_algs_init(void)
 {
-	atomic_set(&active_dev, 0);
-	crypto_get_default_rng();
 	return 0;
 }
 
 void qat_algs_exit(void)
 {
-	crypto_put_default_rng();
 }
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
new file mode 100644
index 000000000000..e87f51023ba4
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -0,0 +1,652 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+	* Redistributions of source code must retain the above copyright
+	  notice, this list of conditions and the following disclaimer.
+	* Redistributions in binary form must reproduce the above copyright
+	  notice, this list of conditions and the following disclaimer in
+	  the documentation and/or other materials provided with the
+	  distribution.
+	* Neither the name of Intel Corporation nor the names of its
+	  contributors may be used to endorse or promote products derived
+	  from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+
+#include <linux/module.h>
+#include <crypto/internal/rsa.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/akcipher.h>
+#include <linux/dma-mapping.h>
+#include <linux/fips.h>
+#include "qat_rsakey-asn1.h"
+#include "icp_qat_fw_pke.h"
+#include "adf_accel_devices.h"
+#include "adf_transport.h"
+#include "adf_common_drv.h"
+#include "qat_crypto.h"
+
+static DEFINE_MUTEX(algs_lock);
+static unsigned int active_devs;
+
+struct qat_rsa_input_params {
+	union {
+		struct {
+			dma_addr_t m;
+			dma_addr_t e;
+			dma_addr_t n;
+		} enc;
+		struct {
+			dma_addr_t c;
+			dma_addr_t d;
+			dma_addr_t n;
+		} dec;
+		u64 in_tab[8];
+	};
+} __packed __aligned(64);
+
+struct qat_rsa_output_params {
+	union {
+		struct {
+			dma_addr_t c;
+		} enc;
+		struct {
+			dma_addr_t m;
+		} dec;
+		u64 out_tab[8];
+	};
+} __packed __aligned(64);
+
+struct qat_rsa_ctx {
+	char *n;
+	char *e;
+	char *d;
+	dma_addr_t dma_n;
+	dma_addr_t dma_e;
+	dma_addr_t dma_d;
+	unsigned int key_sz;
+	struct qat_crypto_instance *inst;
+} __packed __aligned(64);
+
+struct qat_rsa_request {
+	struct qat_rsa_input_params in;
+	struct qat_rsa_output_params out;
+	dma_addr_t phy_in;
+	dma_addr_t phy_out;
+	char *src_align;
+	struct icp_qat_fw_pke_request req;
+	struct qat_rsa_ctx *ctx;
+	int err;
+} __aligned(64);
+
+static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp)
+{
+	struct akcipher_request *areq = (void *)(__force long)resp->opaque;
+	struct qat_rsa_request *req = PTR_ALIGN(akcipher_request_ctx(areq), 64);
+	struct device *dev = &GET_DEV(req->ctx->inst->accel_dev);
+	int err = ICP_QAT_FW_PKE_RESP_PKE_STAT_GET(
+				resp->pke_resp_hdr.comn_resp_flags);
+	char *ptr = areq->dst;
+
+	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
+
+	if (req->src_align)
+		dma_free_coherent(dev, req->ctx->key_sz, req->src_align,
+				  req->in.enc.m);
+	else
+		dma_unmap_single(dev, req->in.enc.m, req->ctx->key_sz,
+				 DMA_TO_DEVICE);
+
+	dma_unmap_single(dev, req->out.enc.c, req->ctx->key_sz,
+			 DMA_FROM_DEVICE);
+	dma_unmap_single(dev, req->phy_in, sizeof(struct qat_rsa_input_params),
+			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, req->phy_out,
+			 sizeof(struct qat_rsa_output_params),
+			 DMA_TO_DEVICE);
+
+	areq->dst_len = req->ctx->key_sz;
+	/* Need to set the corect length of the output */
+	while (!(*ptr) && areq->dst_len) {
+		areq->dst_len--;
+		ptr++;
+	}
+
+	if (areq->dst_len != req->ctx->key_sz)
+		memmove(areq->dst, ptr, areq->dst_len);
+
+	akcipher_request_complete(areq, err);
+}
+
+void qat_alg_asym_callback(void *_resp)
+{
+	struct icp_qat_fw_pke_resp *resp = _resp;
+
+	qat_rsa_cb(resp);
+}
+
+#define PKE_RSA_EP_512 0x1c161b21
+#define PKE_RSA_EP_1024 0x35111bf7
+#define PKE_RSA_EP_1536 0x4d111cdc
+#define PKE_RSA_EP_2048 0x6e111dba
+#define PKE_RSA_EP_3072 0x7d111ea3
+#define PKE_RSA_EP_4096 0xa5101f7e
+
+static unsigned long qat_rsa_enc_fn_id(unsigned int len)
+{
+	unsigned int bitslen = len << 3;
+
+	switch (bitslen) {
+	case 512:
+		return PKE_RSA_EP_512;
+	case 1024:
+		return PKE_RSA_EP_1024;
+	case 1536:
+		return PKE_RSA_EP_1536;
+	case 2048:
+		return PKE_RSA_EP_2048;
+	case 3072:
+		return PKE_RSA_EP_3072;
+	case 4096:
+		return PKE_RSA_EP_4096;
+	default:
+		return 0;
+	};
+}
+
+#define PKE_RSA_DP1_512 0x1c161b3c
+#define PKE_RSA_DP1_1024 0x35111c12
+#define PKE_RSA_DP1_1536 0x4d111cf7
+#define PKE_RSA_DP1_2048 0x6e111dda
+#define PKE_RSA_DP1_3072 0x7d111ebe
+#define PKE_RSA_DP1_4096 0xa5101f98
+
+static unsigned long qat_rsa_dec_fn_id(unsigned int len)
+{
+	unsigned int bitslen = len << 3;
+
+	switch (bitslen) {
+	case 512:
+		return PKE_RSA_DP1_512;
+	case 1024:
+		return PKE_RSA_DP1_1024;
+	case 1536:
+		return PKE_RSA_DP1_1536;
+	case 2048:
+		return PKE_RSA_DP1_2048;
+	case 3072:
+		return PKE_RSA_DP1_3072;
+	case 4096:
+		return PKE_RSA_DP1_4096;
+	default:
+		return 0;
+	};
+}
+
+static int qat_rsa_enc(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	struct qat_rsa_request *qat_req =
+			PTR_ALIGN(akcipher_request_ctx(req), 64);
+	struct icp_qat_fw_pke_request *msg = &qat_req->req;
+	int ret, ctr = 0;
+
+	if (unlikely(!ctx->n || !ctx->e))
+		return -EINVAL;
+
+	if (req->dst_len < ctx->key_sz) {
+		req->dst_len = ctx->key_sz;
+		return -EOVERFLOW;
+	}
+	memset(msg, '\0', sizeof(*msg));
+	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
+					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
+	msg->pke_hdr.cd_pars.func_id = qat_rsa_enc_fn_id(ctx->key_sz);
+	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
+		return -EINVAL;
+
+	qat_req->ctx = ctx;
+	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
+	msg->pke_hdr.comn_req_flags =
+		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
+					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
+
+	qat_req->in.enc.e = ctx->dma_e;
+	qat_req->in.enc.n = ctx->dma_n;
+	ret = -ENOMEM;
+
+	/*
+	 * src can be of any size in valid range, but HW expects it to be the
+	 * same as modulo n so in case it is different we need to allocate a
+	 * new buf and copy src data.
+	 * In other case we just need to map the user provided buffer.
+	 */
+	if (req->src_len < ctx->key_sz) {
+		int shift = ctx->key_sz - req->src_len;
+
+		qat_req->src_align = dma_zalloc_coherent(dev, ctx->key_sz,
+							 &qat_req->in.enc.m,
+							 GFP_KERNEL);
+		if (unlikely(!qat_req->src_align))
+			return ret;
+
+		memcpy(qat_req->src_align + shift, req->src, req->src_len);
+	} else {
+		qat_req->src_align = NULL;
+		qat_req->in.enc.m = dma_map_single(dev, req->src, req->src_len,
+					   DMA_TO_DEVICE);
+	}
+	qat_req->in.in_tab[3] = 0;
+	qat_req->out.enc.c = dma_map_single(dev, req->dst, req->dst_len,
+					    DMA_FROM_DEVICE);
+	qat_req->out.out_tab[1] = 0;
+	qat_req->phy_in = dma_map_single(dev, &qat_req->in.enc.m,
+					 sizeof(struct qat_rsa_input_params),
+					 DMA_TO_DEVICE);
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.enc.c,
+					  sizeof(struct qat_rsa_output_params),
+					    DMA_TO_DEVICE);
+
+	if (unlikely((!qat_req->src_align &&
+		      dma_mapping_error(dev, qat_req->in.enc.m)) ||
+		     dma_mapping_error(dev, qat_req->out.enc.c) ||
+		     dma_mapping_error(dev, qat_req->phy_in) ||
+		     dma_mapping_error(dev, qat_req->phy_out)))
+		goto unmap;
+
+	msg->pke_mid.src_data_addr = qat_req->phy_in;
+	msg->pke_mid.dest_data_addr = qat_req->phy_out;
+	msg->pke_mid.opaque = (uint64_t)(__force long)req;
+	msg->input_param_count = 3;
+	msg->output_param_count = 1;
+	do {
+		ret = adf_send_message(ctx->inst->pke_tx, (uint32_t *)msg);
+	} while (ret == -EBUSY && ctr++ < 100);
+
+	if (!ret)
+		return -EINPROGRESS;
+unmap:
+	if (qat_req->src_align)
+		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
+				  qat_req->in.enc.m);
+	else
+		if (!dma_mapping_error(dev, qat_req->in.enc.m))
+			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
+					 DMA_TO_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->out.enc.c))
+		dma_unmap_single(dev, qat_req->out.enc.c, ctx->key_sz,
+				 DMA_FROM_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_rsa_input_params),
+				 DMA_TO_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_rsa_output_params),
+				 DMA_TO_DEVICE);
+	return ret;
+}
+
+static int qat_rsa_dec(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	struct qat_rsa_request *qat_req =
+			PTR_ALIGN(akcipher_request_ctx(req), 64);
+	struct icp_qat_fw_pke_request *msg = &qat_req->req;
+	int ret, ctr = 0;
+
+	if (unlikely(!ctx->n || !ctx->d))
+		return -EINVAL;
+
+	if (req->dst_len < ctx->key_sz) {
+		req->dst_len = ctx->key_sz;
+		return -EOVERFLOW;
+	}
+	memset(msg, '\0', sizeof(*msg));
+	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
+					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
+	msg->pke_hdr.cd_pars.func_id = qat_rsa_dec_fn_id(ctx->key_sz);
+	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
+		return -EINVAL;
+
+	qat_req->ctx = ctx;
+	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
+	msg->pke_hdr.comn_req_flags =
+		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
+					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
+
+	qat_req->in.dec.d = ctx->dma_d;
+	qat_req->in.dec.n = ctx->dma_n;
+	ret = -ENOMEM;
+
+	/*
+	 * src can be of any size in valid range, but HW expects it to be the
+	 * same as modulo n so in case it is different we need to allocate a
+	 * new buf and copy src data.
+	 * In other case we just need to map the user provided buffer.
+	 */
+	if (req->src_len < ctx->key_sz) {
+		int shift = ctx->key_sz - req->src_len;
+
+		qat_req->src_align = dma_zalloc_coherent(dev, ctx->key_sz,
+							 &qat_req->in.dec.c,
+							 GFP_KERNEL);
+		if (unlikely(!qat_req->src_align))
+			return ret;
+
+		memcpy(qat_req->src_align + shift, req->src, req->src_len);
+	} else {
+		qat_req->src_align = NULL;
+		qat_req->in.dec.c = dma_map_single(dev, req->src, req->src_len,
+						   DMA_TO_DEVICE);
+	}
+	qat_req->in.in_tab[3] = 0;
+	qat_req->out.dec.m = dma_map_single(dev, req->dst, req->dst_len,
+					    DMA_FROM_DEVICE);
+	qat_req->out.out_tab[1] = 0;
+	qat_req->phy_in = dma_map_single(dev, &qat_req->in.dec.c,
+					 sizeof(struct qat_rsa_input_params),
+					 DMA_TO_DEVICE);
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.dec.m,
+					  sizeof(struct qat_rsa_output_params),
+					    DMA_TO_DEVICE);
+
+	if (unlikely((!qat_req->src_align &&
+		      dma_mapping_error(dev, qat_req->in.dec.c)) ||
+		     dma_mapping_error(dev, qat_req->out.dec.m) ||
+		     dma_mapping_error(dev, qat_req->phy_in) ||
+		     dma_mapping_error(dev, qat_req->phy_out)))
+		goto unmap;
+
+	msg->pke_mid.src_data_addr = qat_req->phy_in;
+	msg->pke_mid.dest_data_addr = qat_req->phy_out;
+	msg->pke_mid.opaque = (uint64_t)(__force long)req;
+	msg->input_param_count = 3;
+	msg->output_param_count = 1;
+	do {
+		ret = adf_send_message(ctx->inst->pke_tx, (uint32_t *)msg);
+	} while (ret == -EBUSY && ctr++ < 100);
+
+	if (!ret)
+		return -EINPROGRESS;
+unmap:
+	if (qat_req->src_align)
+		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
+				  qat_req->in.dec.c);
+	else
+		if (!dma_mapping_error(dev, qat_req->in.dec.c))
+			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
+					 DMA_TO_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->out.dec.m))
+		dma_unmap_single(dev, qat_req->out.dec.m, ctx->key_sz,
+				 DMA_FROM_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_rsa_input_params),
+				 DMA_TO_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_rsa_output_params),
+				 DMA_TO_DEVICE);
+	return ret;
+}
+
+int qat_rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
+		  const void *value, size_t vlen)
+{
+	struct qat_rsa_ctx *ctx = context;
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	const char *ptr = value;
+	int ret;
+
+	while (!*ptr && vlen) {
+		ptr++;
+		vlen--;
+	}
+
+	ctx->key_sz = vlen;
+	ret = -EINVAL;
+	/* In FIPS mode only allow key size 2K & 3K */
+	if (fips_enabled && (ctx->key_sz != 256 && ctx->key_sz != 384)) {
+		pr_err("QAT: RSA: key size not allowed in FIPS mode\n");
+		goto err;
+	}
+	/* invalid key size provided */
+	if (!qat_rsa_enc_fn_id(ctx->key_sz))
+		goto err;
+
+	ret = -ENOMEM;
+	ctx->n = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_n, GFP_KERNEL);
+	if (!ctx->n)
+		goto err;
+
+	memcpy(ctx->n, ptr, ctx->key_sz);
+	return 0;
+err:
+	ctx->key_sz = 0;
+	ctx->n = NULL;
+	return ret;
+}
+
+int qat_rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
+		  const void *value, size_t vlen)
+{
+	struct qat_rsa_ctx *ctx = context;
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	const char *ptr = value;
+
+	while (!*ptr && vlen) {
+		ptr++;
+		vlen--;
+	}
+
+	if (!ctx->key_sz || !vlen || vlen > ctx->key_sz) {
+		ctx->e = NULL;
+		return -EINVAL;
+	}
+
+	ctx->e = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_e, GFP_KERNEL);
+	if (!ctx->e) {
+		ctx->e = NULL;
+		return -ENOMEM;
+	}
+	memcpy(ctx->e + (ctx->key_sz - vlen), ptr, vlen);
+	return 0;
+}
+
+int qat_rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
+		  const void *value, size_t vlen)
+{
+	struct qat_rsa_ctx *ctx = context;
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	const char *ptr = value;
+	int ret;
+
+	while (!*ptr && vlen) {
+		ptr++;
+		vlen--;
+	}
+
+	ret = -EINVAL;
+	if (!ctx->key_sz || !vlen || vlen > ctx->key_sz)
+		goto err;
+
+	/* In FIPS mode only allow key size 2K & 3K */
+	if (fips_enabled && (vlen != 256 && vlen != 384)) {
+		pr_err("QAT: RSA: key size not allowed in FIPS mode\n");
+		goto err;
+	}
+
+	ret = -ENOMEM;
+	ctx->d = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_d, GFP_KERNEL);
+	if (!ctx->n)
+		goto err;
+
+	memcpy(ctx->d + (ctx->key_sz - vlen), ptr, vlen);
+	return 0;
+err:
+	ctx->d = NULL;
+	return ret;
+}
+
+static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
+			  unsigned int keylen)
+{
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+	int ret;
+
+	/* Free the old key if any */
+	if (ctx->n)
+		dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n);
+	if (ctx->e)
+		dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e);
+	if (ctx->d) {
+		memset(ctx->d, '\0', ctx->key_sz);
+		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
+	}
+
+	ctx->n = NULL;
+	ctx->e = NULL;
+	ctx->d = NULL;
+	ret = asn1_ber_decoder(&qat_rsakey_decoder, ctx, key, keylen);
+	if (ret < 0)
+		goto free;
+
+	if (!ctx->n || !ctx->e) {
+		/* invalid key provided */
+		ret = -EINVAL;
+		goto free;
+	}
+
+	return 0;
+free:
+	if (ctx->d) {
+		memset(ctx->d, '\0', ctx->key_sz);
+		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
+		ctx->d = NULL;
+	}
+	if (ctx->e) {
+		dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e);
+		ctx->e = NULL;
+	}
+	if (ctx->n) {
+		dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n);
+		ctx->n = NULL;
+		ctx->key_sz = 0;
+	}
+	return ret;
+}
+
+static int qat_rsa_init_tfm(struct crypto_akcipher *tfm)
+{
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst =
+			qat_crypto_get_instance_node(get_current_node());
+
+	if (!inst)
+		return -EINVAL;
+
+	ctx->key_sz = 0;
+	ctx->inst = inst;
+	return 0;
+}
+
+static void qat_rsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+
+	if (ctx->n)
+		dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n);
+	if (ctx->e)
+		dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e);
+	if (ctx->d) {
+		memset(ctx->d, '\0', ctx->key_sz);
+		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
+	}
+	qat_crypto_put_instance(ctx->inst);
+	ctx->n = NULL;
+	ctx->d = NULL;
+	ctx->d = NULL;
+}
+
+static struct akcipher_alg rsa = {
+	.encrypt = qat_rsa_enc,
+	.decrypt = qat_rsa_dec,
+	.sign = qat_rsa_dec,
+	.verify = qat_rsa_enc,
+	.setkey = qat_rsa_setkey,
+	.init = qat_rsa_init_tfm,
+	.exit = qat_rsa_exit_tfm,
+	.reqsize = sizeof(struct qat_rsa_request) + 64,
+	.base = {
+		.cra_name = "rsa",
+		.cra_driver_name = "qat-rsa",
+		.cra_priority = 1000,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct qat_rsa_ctx),
+	},
+};
+
+int qat_asym_algs_register(void)
+{
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (++active_devs == 1) {
+		rsa.base.cra_flags = 0;
+		ret = crypto_register_akcipher(&rsa);
+	}
+	mutex_unlock(&algs_lock);
+	return ret;
+}
+
+void qat_asym_algs_unregister(void)
+{
+	mutex_lock(&algs_lock);
+	if (--active_devs == 0)
+		crypto_unregister_akcipher(&rsa);
+	mutex_unlock(&algs_lock);
+}
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.c b/drivers/crypto/qat/qat_common/qat_crypto.c
index 3bd705ca5973..07c2f9f9d1fc 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.c
+++ b/drivers/crypto/qat/qat_common/qat_crypto.c
@@ -88,12 +88,6 @@ static int qat_crypto_free_instances(struct adf_accel_dev *accel_dev)
 		if (inst->pke_rx)
 			adf_remove_ring(inst->pke_rx);
 
-		if (inst->rnd_tx)
-			adf_remove_ring(inst->rnd_tx);
-
-		if (inst->rnd_rx)
-			adf_remove_ring(inst->rnd_rx);
-
 		list_del(list_ptr);
 		kfree(inst);
 	}
@@ -109,9 +103,11 @@ struct qat_crypto_instance *qat_crypto_get_instance_node(int node)
 
 	list_for_each(itr, adf_devmgr_get_head()) {
 		accel_dev = list_entry(itr, struct adf_accel_dev, list);
+
 		if ((node == dev_to_node(&GET_DEV(accel_dev)) ||
 		     dev_to_node(&GET_DEV(accel_dev)) < 0) &&
-		    adf_dev_started(accel_dev))
+		    adf_dev_started(accel_dev) &&
+		    !list_empty(&accel_dev->crypto_list))
 			break;
 		accel_dev = NULL;
 	}
@@ -158,7 +154,6 @@ static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
 
 	INIT_LIST_HEAD(&accel_dev->crypto_list);
 	strlcpy(key, ADF_NUM_CY, sizeof(key));
-
 	if (adf_cfg_get_param_value(accel_dev, SEC, key, val))
 		return -EFAULT;
 
@@ -187,7 +182,9 @@ static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
 
 		if (kstrtoul(val, 10, &num_msg_sym))
 			goto err;
+
 		num_msg_sym = num_msg_sym >> 1;
+
 		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
 		if (adf_cfg_get_param_value(accel_dev, SEC, key, val))
 			goto err;
@@ -202,11 +199,6 @@ static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
 				    msg_size, key, NULL, 0, &inst->sym_tx))
 			goto err;
 
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_TX, i);
-		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
-				    msg_size, key, NULL, 0, &inst->rnd_tx))
-			goto err;
-
 		msg_size = msg_size >> 1;
 		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
 		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
@@ -220,15 +212,9 @@ static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
 				    &inst->sym_rx))
 			goto err;
 
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_RX, i);
-		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
-				    msg_size, key, qat_alg_callback, 0,
-				    &inst->rnd_rx))
-			goto err;
-
 		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
 		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
-				    msg_size, key, qat_alg_callback, 0,
+				    msg_size, key, qat_alg_asym_callback, 0,
 				    &inst->pke_rx))
 			goto err;
 	}
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/qat/qat_common/qat_crypto.h
index d503007b49e6..dc0273fe3620 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.h
+++ b/drivers/crypto/qat/qat_common/qat_crypto.h
@@ -57,8 +57,6 @@ struct qat_crypto_instance {
 	struct adf_etr_ring_data *sym_rx;
 	struct adf_etr_ring_data *pke_tx;
 	struct adf_etr_ring_data *pke_rx;
-	struct adf_etr_ring_data *rnd_tx;
-	struct adf_etr_ring_data *rnd_rx;
 	struct adf_accel_dev *accel_dev;
 	struct list_head list;
 	unsigned long state;
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
index 274ff7e9de6e..8e711d1c3084 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -671,7 +671,6 @@ static int qat_hal_clear_gpr(struct icp_qat_fw_loader_handle *handle)
 #define ICP_DH895XCC_CAP_OFFSET     (ICP_DH895XCC_AE_OFFSET + 0x10000)
 #define LOCAL_TO_XFER_REG_OFFSET    0x800
 #define ICP_DH895XCC_EP_OFFSET      0x3a000
-#define ICP_DH895XCC_PMISC_BAR 1
 int qat_hal_init(struct adf_accel_dev *accel_dev)
 {
 	unsigned char ae;
@@ -679,21 +678,24 @@ int qat_hal_init(struct adf_accel_dev *accel_dev)
 	struct icp_qat_fw_loader_handle *handle;
 	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
-	struct adf_bar *bar =
+	struct adf_bar *misc_bar =
 			&pci_info->pci_bars[hw_data->get_misc_bar_id(hw_data)];
+	struct adf_bar *sram_bar =
+			&pci_info->pci_bars[hw_data->get_sram_bar_id(hw_data)];
 
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
 	if (!handle)
 		return -ENOMEM;
 
-	handle->hal_cap_g_ctl_csr_addr_v = bar->virt_addr +
+	handle->hal_cap_g_ctl_csr_addr_v = misc_bar->virt_addr +
 						ICP_DH895XCC_CAP_OFFSET;
-	handle->hal_cap_ae_xfer_csr_addr_v = bar->virt_addr +
+	handle->hal_cap_ae_xfer_csr_addr_v = misc_bar->virt_addr +
 						ICP_DH895XCC_AE_OFFSET;
-	handle->hal_ep_csr_addr_v = bar->virt_addr + ICP_DH895XCC_EP_OFFSET;
+	handle->hal_ep_csr_addr_v = misc_bar->virt_addr +
+				    ICP_DH895XCC_EP_OFFSET;
 	handle->hal_cap_ae_local_csr_addr_v =
 		handle->hal_cap_ae_xfer_csr_addr_v + LOCAL_TO_XFER_REG_OFFSET;
-
+	handle->hal_sram_addr_v = sram_bar->virt_addr;
 	handle->hal_handle = kzalloc(sizeof(*handle->hal_handle), GFP_KERNEL);
 	if (!handle->hal_handle)
 		goto out_hal_handle;
diff --git a/drivers/crypto/qat/qat_common/qat_rsakey.asn1 b/drivers/crypto/qat/qat_common/qat_rsakey.asn1
new file mode 100644
index 000000000000..97b0e02b600a
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_rsakey.asn1
@@ -0,0 +1,5 @@
+RsaKey ::= SEQUENCE {
+	n INTEGER ({ qat_rsa_get_n }),
+	e INTEGER ({ qat_rsa_get_e }),
+	d INTEGER ({ qat_rsa_get_d })
+}
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index 1e27f9f7fddf..c48f181e8941 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -359,28 +359,7 @@ static int qat_uclo_init_umem_seg(struct icp_qat_fw_loader_handle *handle,
 static int qat_uclo_init_ae_memory(struct icp_qat_fw_loader_handle *handle,
 				   struct icp_qat_uof_initmem *init_mem)
 {
-	unsigned int i;
-	struct icp_qat_uof_memvar_attr *mem_val_attr;
-
-	mem_val_attr =
-		(struct icp_qat_uof_memvar_attr *)((unsigned long)init_mem +
-		sizeof(struct icp_qat_uof_initmem));
-
 	switch (init_mem->region) {
-	case ICP_QAT_UOF_SRAM_REGION:
-		if ((init_mem->addr + init_mem->num_in_bytes) >
-		    ICP_DH895XCC_PESRAM_BAR_SIZE) {
-			pr_err("QAT: initmem on SRAM is out of range");
-			return -EINVAL;
-		}
-		for (i = 0; i < init_mem->val_attr_num; i++) {
-			qat_uclo_wr_sram_by_words(handle,
-						  init_mem->addr +
-						  mem_val_attr->offset_in_byte,
-						  &mem_val_attr->value, 4);
-			mem_val_attr++;
-		}
-		break;
 	case ICP_QAT_UOF_LMEM_REGION:
 		if (qat_uclo_init_lmem_seg(handle, init_mem))
 			return -EINVAL;
@@ -990,6 +969,12 @@ out_err:
 	return -EFAULT;
 }
 
+void qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle,
+			void *addr_ptr, int mem_size)
+{
+	qat_uclo_wr_sram_by_words(handle, 0, addr_ptr, ALIGN(mem_size, 4));
+}
+
 int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
 			 void *addr_ptr, int mem_size)
 {
diff --git a/drivers/crypto/qat/qat_dh895xcc/Makefile b/drivers/crypto/qat/qat_dh895xcc/Makefile
index 25171c557043..8c79c543740f 100644
--- a/drivers/crypto/qat/qat_dh895xcc/Makefile
+++ b/drivers/crypto/qat/qat_dh895xcc/Makefile
@@ -2,7 +2,4 @@ ccflags-y := -I$(src)/../qat_common
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc.o
 qat_dh895xcc-objs := adf_drv.o \
 		adf_isr.o \
-		adf_dh895xcc_hw_data.o \
-		adf_hw_arbiter.o \
-		qat_admin.o \
-		adf_admin.o
+		adf_dh895xcc_hw_data.o
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_admin.c b/drivers/crypto/qat/qat_dh895xcc/adf_admin.c
deleted file mode 100644
index e4666065c399..000000000000
--- a/drivers/crypto/qat/qat_dh895xcc/adf_admin.c
+++ /dev/null
@@ -1,145 +0,0 @@
-/*
-  This file is provided under a dual BSD/GPLv2 license.  When using or
-  redistributing this file, you may do so under either license.
-
-  GPL LICENSE SUMMARY
-  Copyright(c) 2014 Intel Corporation.
-  This program is free software; you can redistribute it and/or modify
-  it under the terms of version 2 of the GNU General Public License as
-  published by the Free Software Foundation.
-
-  This program is distributed in the hope that it will be useful, but
-  WITHOUT ANY WARRANTY; without even the implied warranty of
-  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-  General Public License for more details.
-
-  Contact Information:
-  qat-linux@intel.com
-
-  BSD LICENSE
-  Copyright(c) 2014 Intel Corporation.
-  Redistribution and use in source and binary forms, with or without
-  modification, are permitted provided that the following conditions
-  are met:
-
-    * Redistributions of source code must retain the above copyright
-      notice, this list of conditions and the following disclaimer.
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in
-      the documentation and/or other materials provided with the
-      distribution.
-    * Neither the name of Intel Corporation nor the names of its
-      contributors may be used to endorse or promote products derived
-      from this software without specific prior written permission.
-
-  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-*/
-#include <linux/types.h>
-#include <linux/mutex.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <linux/dma-mapping.h>
-#include <adf_accel_devices.h>
-#include "adf_drv.h"
-#include "adf_dh895xcc_hw_data.h"
-
-#define ADF_ADMINMSG_LEN 32
-
-struct adf_admin_comms {
-	dma_addr_t phy_addr;
-	void *virt_addr;
-	void __iomem *mailbox_addr;
-	struct mutex lock;	/* protects adf_admin_comms struct */
-};
-
-int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev,
-			   uint32_t ae, void *in, void *out)
-{
-	struct adf_admin_comms *admin = accel_dev->admin;
-	int offset = ae * ADF_ADMINMSG_LEN * 2;
-	void __iomem *mailbox = admin->mailbox_addr;
-	int mb_offset = ae * ADF_DH895XCC_MAILBOX_STRIDE;
-	int times, received;
-
-	mutex_lock(&admin->lock);
-
-	if (ADF_CSR_RD(mailbox, mb_offset) == 1) {
-		mutex_unlock(&admin->lock);
-		return -EAGAIN;
-	}
-
-	memcpy(admin->virt_addr + offset, in, ADF_ADMINMSG_LEN);
-	ADF_CSR_WR(mailbox, mb_offset, 1);
-	received = 0;
-	for (times = 0; times < 50; times++) {
-		msleep(20);
-		if (ADF_CSR_RD(mailbox, mb_offset) == 0) {
-			received = 1;
-			break;
-		}
-	}
-	if (received)
-		memcpy(out, admin->virt_addr + offset +
-		       ADF_ADMINMSG_LEN, ADF_ADMINMSG_LEN);
-	else
-		dev_err(&GET_DEV(accel_dev),
-			"Failed to send admin msg to accelerator\n");
-
-	mutex_unlock(&admin->lock);
-	return received ? 0 : -EFAULT;
-}
-
-int adf_init_admin_comms(struct adf_accel_dev *accel_dev)
-{
-	struct adf_admin_comms *admin;
-	struct adf_bar *pmisc = &GET_BARS(accel_dev)[ADF_DH895XCC_PMISC_BAR];
-	void __iomem *csr = pmisc->virt_addr;
-	void __iomem *mailbox = csr + ADF_DH895XCC_MAILBOX_BASE_OFFSET;
-	uint64_t reg_val;
-
-	admin = kzalloc_node(sizeof(*accel_dev->admin), GFP_KERNEL,
-			     dev_to_node(&GET_DEV(accel_dev)));
-	if (!admin)
-		return -ENOMEM;
-	admin->virt_addr = dma_zalloc_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
-					       &admin->phy_addr, GFP_KERNEL);
-	if (!admin->virt_addr) {
-		dev_err(&GET_DEV(accel_dev), "Failed to allocate dma buff\n");
-		kfree(admin);
-		return -ENOMEM;
-	}
-	reg_val = (uint64_t)admin->phy_addr;
-	ADF_CSR_WR(csr, ADF_DH895XCC_ADMINMSGUR_OFFSET, reg_val >> 32);
-	ADF_CSR_WR(csr, ADF_DH895XCC_ADMINMSGLR_OFFSET, reg_val);
-	mutex_init(&admin->lock);
-	admin->mailbox_addr = mailbox;
-	accel_dev->admin = admin;
-	return 0;
-}
-
-void adf_exit_admin_comms(struct adf_accel_dev *accel_dev)
-{
-	struct adf_admin_comms *admin = accel_dev->admin;
-
-	if (!admin)
-		return;
-
-	if (admin->virt_addr)
-		dma_free_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
-				  admin->virt_addr, admin->phy_addr);
-
-	mutex_destroy(&admin->lock);
-	kfree(admin);
-	accel_dev->admin = NULL;
-}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
index b1386922d7a2..ff54257eced4 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -45,8 +45,9 @@
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
 #include <adf_accel_devices.h>
+#include <adf_pf2vf_msg.h>
+#include <adf_common_drv.h>
 #include "adf_dh895xcc_hw_data.h"
-#include "adf_common_drv.h"
 #include "adf_drv.h"
 
 /* Worker thread to service arbiter mappings based on dev SKUs */
@@ -117,6 +118,11 @@ static uint32_t get_etr_bar_id(struct adf_hw_device_data *self)
 	return ADF_DH895XCC_ETR_BAR;
 }
 
+static uint32_t get_sram_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCC_SRAM_BAR;
+}
+
 static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 {
 	int sku = (self->fuses & ADF_DH895XCC_FUSECTL_SKU_MASK)
@@ -156,6 +162,16 @@ void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
 	}
 }
 
+static uint32_t get_pf2vf_offset(uint32_t i)
+{
+	return ADF_DH895XCC_PF2VF_OFFSET(i);
+}
+
+static uint32_t get_vintmsk_offset(uint32_t i)
+{
+	return ADF_DH895XCC_VINTMSK_OFFSET(i);
+}
+
 static void adf_enable_error_correction(struct adf_accel_dev *accel_dev)
 {
 	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
@@ -192,18 +208,23 @@ static void adf_enable_ints(struct adf_accel_dev *accel_dev)
 
 	/* Enable bundle and misc interrupts */
 	ADF_CSR_WR(addr, ADF_DH895XCC_SMIAPF0_MASK_OFFSET,
-		   ADF_DH895XCC_SMIA0_MASK);
+		   accel_dev->pf.vf_info ? 0 :
+			GENMASK_ULL(GET_MAX_BANKS(accel_dev) - 1, 0));
 	ADF_CSR_WR(addr, ADF_DH895XCC_SMIAPF1_MASK_OFFSET,
 		   ADF_DH895XCC_SMIA1_MASK);
 }
 
+static int adf_pf_enable_vf2pf_comms(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
 void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data)
 {
 	hw_data->dev_class = &dh895xcc_class;
 	hw_data->instance_id = dh895xcc_class.instances++;
 	hw_data->num_banks = ADF_DH895XCC_ETR_MAX_BANKS;
 	hw_data->num_accel = ADF_DH895XCC_MAX_ACCELERATORS;
-	hw_data->pci_dev_id = ADF_DH895XCC_PCI_DEVICE_ID;
 	hw_data->num_logical_accel = 1;
 	hw_data->num_engines = ADF_DH895XCC_MAX_ACCELENGINES;
 	hw_data->tx_rx_gap = ADF_DH895XCC_RX_RINGS_OFFSET;
@@ -211,21 +232,28 @@ void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data)
 	hw_data->alloc_irq = adf_isr_resource_alloc;
 	hw_data->free_irq = adf_isr_resource_free;
 	hw_data->enable_error_correction = adf_enable_error_correction;
-	hw_data->hw_arb_ring_enable = adf_update_ring_arb_enable;
-	hw_data->hw_arb_ring_disable = adf_update_ring_arb_enable;
 	hw_data->get_accel_mask = get_accel_mask;
 	hw_data->get_ae_mask = get_ae_mask;
 	hw_data->get_num_accels = get_num_accels;
 	hw_data->get_num_aes = get_num_aes;
 	hw_data->get_etr_bar_id = get_etr_bar_id;
 	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_pf2vf_offset = get_pf2vf_offset;
+	hw_data->get_vintmsk_offset = get_vintmsk_offset;
+	hw_data->get_sram_bar_id = get_sram_bar_id;
 	hw_data->get_sku = get_sku;
 	hw_data->fw_name = ADF_DH895XCC_FW;
+	hw_data->fw_mmp_name = ADF_DH895XCC_MMP;
 	hw_data->init_admin_comms = adf_init_admin_comms;
 	hw_data->exit_admin_comms = adf_exit_admin_comms;
+	hw_data->disable_iov = adf_disable_sriov;
+	hw_data->send_admin_init = adf_send_admin_init;
 	hw_data->init_arb = adf_init_arb;
 	hw_data->exit_arb = adf_exit_arb;
+	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
+	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
 void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data)
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
index 25269a9f24a2..88dffb297346 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
@@ -48,6 +48,7 @@
 #define ADF_DH895x_HW_DATA_H_
 
 /* PCIe configuration space */
+#define ADF_DH895XCC_SRAM_BAR 0
 #define ADF_DH895XCC_PMISC_BAR 1
 #define ADF_DH895XCC_ETR_BAR 2
 #define ADF_DH895XCC_RX_RINGS_OFFSET 8
@@ -79,10 +80,11 @@
 #define ADF_DH895XCC_CERRSSMSH(i) (i * 0x4000 + 0x10)
 #define ADF_DH895XCC_ERRSSMSH_EN BIT(3)
 
-/* Admin Messages Registers */
-#define ADF_DH895XCC_ADMINMSGUR_OFFSET (0x3A000 + 0x574)
-#define ADF_DH895XCC_ADMINMSGLR_OFFSET (0x3A000 + 0x578)
-#define ADF_DH895XCC_MAILBOX_BASE_OFFSET 0x20970
-#define ADF_DH895XCC_MAILBOX_STRIDE 0x1000
+#define ADF_DH895XCC_ERRSOU3	(0x3A000 + 0x00C)
+#define ADF_DH895XCC_ERRSOU5	(0x3A000 + 0x0D8)
+#define ADF_DH895XCC_PF2VF_OFFSET(i)	(0x3A000 + 0x280 + ((i) * 0x04))
+#define ADF_DH895XCC_VINTMSK_OFFSET(i)	(0x3A000 + 0x200 + ((i) * 0x04))
+/* FW names */
 #define ADF_DH895XCC_FW "qat_895xcc.bin"
+#define ADF_DH895XCC_MMP "qat_mmp.bin"
 #endif
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
index 1bde45b7a3c5..f8dd14f232c8 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -82,16 +82,21 @@ static struct pci_driver adf_driver = {
 	.id_table = adf_pci_tbl,
 	.name = adf_driver_name,
 	.probe = adf_probe,
-	.remove = adf_remove
+	.remove = adf_remove,
+	.sriov_configure = adf_sriov_configure,
 };
 
+static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev)
+{
+	pci_release_regions(accel_dev->accel_pci_dev.pci_dev);
+	pci_disable_device(accel_dev->accel_pci_dev.pci_dev);
+}
+
 static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
 {
 	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
 	int i;
 
-	adf_dev_shutdown(accel_dev);
-
 	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
 
@@ -100,7 +105,7 @@ static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
 	}
 
 	if (accel_dev->hw_device) {
-		switch (accel_dev->hw_device->pci_dev_id) {
+		switch (accel_pci_dev->pci_dev->device) {
 		case ADF_DH895XCC_PCI_DEVICE_ID:
 			adf_clean_hw_data_dh895xcc(accel_dev->hw_device);
 			break;
@@ -108,13 +113,11 @@ static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
 			break;
 		}
 		kfree(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
 	}
 	adf_cfg_dev_remove(accel_dev);
 	debugfs_remove(accel_dev->debugfs_dir);
-	adf_devmgr_rm_dev(accel_dev);
-	pci_release_regions(accel_pci_dev->pci_dev);
-	pci_disable_device(accel_pci_dev->pci_dev);
-	kfree(accel_dev);
+	adf_devmgr_rm_dev(accel_dev, NULL);
 }
 
 static int adf_dev_configure(struct adf_accel_dev *accel_dev)
@@ -167,12 +170,6 @@ static int adf_dev_configure(struct adf_accel_dev *accel_dev)
 						key, (void *)&val, ADF_DEC))
 			goto err;
 
-		val = 4;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_TX, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
 		val = 8;
 		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
 		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
@@ -185,12 +182,6 @@ static int adf_dev_configure(struct adf_accel_dev *accel_dev)
 						key, (void *)&val, ADF_DEC))
 			goto err;
 
-		val = 12;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_RX, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
 		val = ADF_COALESCING_DEF_TIME;
 		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
 		if (adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
@@ -217,7 +208,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret;
+	int ret, bar_mask;
 
 	switch (ent->device) {
 	case ADF_DH895XCC_PCI_DEVICE_ID:
@@ -241,10 +232,12 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&accel_dev->crypto_list);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
 
 	/* Add accel device to accel table.
 	 * This should be called before adf_cleanup_accel is called */
-	if (adf_devmgr_add_dev(accel_dev)) {
+	if (adf_devmgr_add_dev(accel_dev, NULL)) {
 		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
 		kfree(accel_dev);
 		return -EFAULT;
@@ -267,7 +260,6 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	default:
 		return -ENODEV;
 	}
-	accel_pci_dev = &accel_dev->accel_pci_dev;
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
 	pci_read_config_dword(pdev, ADF_DH895XCC_FUSECTL_OFFSET,
 			      &hw_data->fuses);
@@ -276,7 +268,6 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
 	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
 	accel_pci_dev->sku = hw_data->get_sku(hw_data);
-	accel_pci_dev->pci_dev = pdev;
 	/* If the device has no acceleration engines then ignore it. */
 	if (!hw_data->accel_mask || !hw_data->ae_mask ||
 	    ((~hw_data->ae_mask) & 0x01)) {
@@ -286,11 +277,14 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* Create dev top level debugfs entry */
-	snprintf(name, sizeof(name), "%s%s_dev%d", ADF_DEVICE_NAME_PREFIX,
-		 hw_data->dev_class->name, hw_data->instance_id);
+	snprintf(name, sizeof(name), "%s%s_%02x:%02d.%02d",
+		 ADF_DEVICE_NAME_PREFIX, hw_data->dev_class->name,
+		 pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+
 	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
 	if (!accel_dev->debugfs_dir) {
-		dev_err(&pdev->dev, "Could not create debugfs dir\n");
+		dev_err(&pdev->dev, "Could not create debugfs dir %s\n", name);
 		ret = -EINVAL;
 		goto out_err;
 	}
@@ -313,7 +307,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
 			dev_err(&pdev->dev, "No usable DMA configuration\n");
 			ret = -EFAULT;
-			goto out_err;
+			goto out_err_disable;
 		} else {
 			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
 		}
@@ -324,7 +318,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (pci_request_regions(pdev, adf_driver_name)) {
 		ret = -EFAULT;
-		goto out_err;
+		goto out_err_disable;
 	}
 
 	/* Read accelerator capabilities mask */
@@ -332,19 +326,21 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			      &hw_data->accel_capabilities_mask);
 
 	/* Find and map all the device's BARS */
-	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
-		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+	i = 0;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+			 ADF_PCI_MAX_BARS * 2) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
-		bar_nr = i * 2;
 		bar->base_addr = pci_resource_start(pdev, bar_nr);
 		if (!bar->base_addr)
 			break;
 		bar->size = pci_resource_len(pdev, bar_nr);
 		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
 		if (!bar->virt_addr) {
-			dev_err(&pdev->dev, "Failed to map BAR %d\n", i);
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", bar_nr);
 			ret = -EFAULT;
-			goto out_err;
+			goto out_err_free_reg;
 		}
 	}
 	pci_set_master(pdev);
@@ -352,32 +348,40 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (adf_enable_aer(accel_dev, &adf_driver)) {
 		dev_err(&pdev->dev, "Failed to enable aer\n");
 		ret = -EFAULT;
-		goto out_err;
+		goto out_err_free_reg;
 	}
 
 	if (pci_save_state(pdev)) {
 		dev_err(&pdev->dev, "Failed to save pci state\n");
 		ret = -ENOMEM;
-		goto out_err;
+		goto out_err_free_reg;
 	}
 
 	ret = adf_dev_configure(accel_dev);
 	if (ret)
-		goto out_err;
+		goto out_err_free_reg;
 
 	ret = adf_dev_init(accel_dev);
 	if (ret)
-		goto out_err;
+		goto out_err_dev_shutdown;
 
 	ret = adf_dev_start(accel_dev);
-	if (ret) {
-		adf_dev_stop(accel_dev);
-		goto out_err;
-	}
+	if (ret)
+		goto out_err_dev_stop;
 
-	return 0;
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_stop(accel_dev);
+out_err_dev_shutdown:
+	adf_dev_shutdown(accel_dev);
+out_err_free_reg:
+	pci_release_regions(accel_pci_dev->pci_dev);
+out_err_disable:
+	pci_disable_device(accel_pci_dev->pci_dev);
 out_err:
 	adf_cleanup_accel(accel_dev);
+	kfree(accel_dev);
 	return ret;
 }
 
@@ -391,15 +395,17 @@ static void adf_remove(struct pci_dev *pdev)
 	}
 	if (adf_dev_stop(accel_dev))
 		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+
+	adf_dev_shutdown(accel_dev);
 	adf_disable_aer(accel_dev);
 	adf_cleanup_accel(accel_dev);
+	adf_cleanup_pci_dev(accel_dev);
+	kfree(accel_dev);
 }
 
 static int __init adfdrv_init(void)
 {
 	request_module("intel_qat");
-	if (qat_admin_register())
-		return -EFAULT;
 
 	if (pci_register_driver(&adf_driver)) {
 		pr_err("QAT: Driver initialization failed\n");
@@ -411,7 +417,6 @@ static int __init adfdrv_init(void)
 static void __exit adfdrv_release(void)
 {
 	pci_unregister_driver(&adf_driver);
-	qat_admin_unregister();
 }
 
 module_init(adfdrv_init);
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h b/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
index a2fbb6ce75cd..85ff245bd1d8 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
@@ -53,15 +53,6 @@ void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
 void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
 int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
 void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
-void adf_update_ring_arb_enable(struct adf_etr_ring_data *ring);
 void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
 			     uint32_t const **arb_map_config);
-int adf_init_admin_comms(struct adf_accel_dev *accel_dev);
-void adf_exit_admin_comms(struct adf_accel_dev *accel_dev);
-int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev,
-			   uint32_t ae, void *in, void *out);
-int qat_admin_register(void);
-int qat_admin_unregister(void);
-int adf_init_arb(struct adf_accel_dev *accel_dev);
-void adf_exit_arb(struct adf_accel_dev *accel_dev);
 #endif
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_isr.c b/drivers/crypto/qat/qat_dh895xcc/adf_isr.c
index 0d03c109c2d3..5570f78795c1 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_isr.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_isr.c
@@ -59,21 +59,30 @@
 #include <adf_transport_access_macros.h>
 #include <adf_transport_internal.h>
 #include "adf_drv.h"
+#include "adf_dh895xcc_hw_data.h"
 
 static int adf_enable_msix(struct adf_accel_dev *accel_dev)
 {
 	struct adf_accel_pci *pci_dev_info = &accel_dev->accel_pci_dev;
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
-	uint32_t msix_num_entries = hw_data->num_banks + 1;
-	int i;
-
-	for (i = 0; i < msix_num_entries; i++)
-		pci_dev_info->msix_entries.entries[i].entry = i;
+	u32 msix_num_entries = 1;
+
+	/* If SR-IOV is disabled, add entries for each bank */
+	if (!accel_dev->pf.vf_info) {
+		int i;
+
+		msix_num_entries += hw_data->num_banks;
+		for (i = 0; i < msix_num_entries; i++)
+			pci_dev_info->msix_entries.entries[i].entry = i;
+	} else {
+		pci_dev_info->msix_entries.entries[0].entry =
+			hw_data->num_banks;
+	}
 
 	if (pci_enable_msix_exact(pci_dev_info->pci_dev,
 				  pci_dev_info->msix_entries.entries,
 				  msix_num_entries)) {
-		dev_err(&GET_DEV(accel_dev), "Failed to enable MSIX IRQ\n");
+		dev_err(&GET_DEV(accel_dev), "Failed to enable MSI-X IRQ(s)\n");
 		return -EFAULT;
 	}
 	return 0;
@@ -97,9 +106,58 @@ static irqreturn_t adf_msix_isr_ae(int irq, void *dev_ptr)
 {
 	struct adf_accel_dev *accel_dev = dev_ptr;
 
-	dev_info(&GET_DEV(accel_dev), "qat_dev%d spurious AE interrupt\n",
-		 accel_dev->accel_id);
-	return IRQ_HANDLED;
+#ifdef CONFIG_PCI_IOV
+	/* If SR-IOV is enabled (vf_info is non-NULL), check for VF->PF ints */
+	if (accel_dev->pf.vf_info) {
+		void __iomem *pmisc_bar_addr =
+		    (&GET_BARS(accel_dev)[ADF_DH895XCC_PMISC_BAR])->virt_addr;
+		u32 vf_mask;
+
+		/* Get the interrupt sources triggered by VFs */
+		vf_mask = ((ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCC_ERRSOU5) &
+			    0x0000FFFF) << 16) |
+			  ((ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCC_ERRSOU3) &
+			    0x01FFFE00) >> 9);
+
+		if (vf_mask) {
+			struct adf_accel_vf_info *vf_info;
+			bool irq_handled = false;
+			int i;
+
+			/* Disable VF2PF interrupts for VFs with pending ints */
+			adf_disable_vf2pf_interrupts(accel_dev, vf_mask);
+
+			/*
+			 * Schedule tasklets to handle VF2PF interrupt BHs
+			 * unless the VF is malicious and is attempting to
+			 * flood the host OS with VF2PF interrupts.
+			 */
+			for_each_set_bit(i, (const unsigned long *)&vf_mask,
+					 (sizeof(vf_mask) * BITS_PER_BYTE)) {
+				vf_info = accel_dev->pf.vf_info + i;
+
+				if (!__ratelimit(&vf_info->vf2pf_ratelimit)) {
+					dev_info(&GET_DEV(accel_dev),
+						 "Too many ints from VF%d\n",
+						  vf_info->vf_nr + 1);
+					continue;
+				}
+
+				/* Tasklet will re-enable ints from this VF */
+				tasklet_hi_schedule(&vf_info->vf2pf_bh_tasklet);
+				irq_handled = true;
+			}
+
+			if (irq_handled)
+				return IRQ_HANDLED;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	dev_dbg(&GET_DEV(accel_dev), "qat_dev%d spurious AE interrupt\n",
+		accel_dev->accel_id);
+
+	return IRQ_NONE;
 }
 
 static int adf_request_irqs(struct adf_accel_dev *accel_dev)
@@ -108,28 +166,32 @@ static int adf_request_irqs(struct adf_accel_dev *accel_dev)
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	struct msix_entry *msixe = pci_dev_info->msix_entries.entries;
 	struct adf_etr_data *etr_data = accel_dev->transport;
-	int ret, i;
+	int ret, i = 0;
 	char *name;
 
-	/* Request msix irq for all banks */
-	for (i = 0; i < hw_data->num_banks; i++) {
-		struct adf_etr_bank_data *bank = &etr_data->banks[i];
-		unsigned int cpu, cpus = num_online_cpus();
-
-		name = *(pci_dev_info->msix_entries.names + i);
-		snprintf(name, ADF_MAX_MSIX_VECTOR_NAME,
-			 "qat%d-bundle%d", accel_dev->accel_id, i);
-		ret = request_irq(msixe[i].vector,
-				  adf_msix_isr_bundle, 0, name, bank);
-		if (ret) {
-			dev_err(&GET_DEV(accel_dev),
-				"failed to enable irq %d for %s\n",
-				msixe[i].vector, name);
-			return ret;
+	/* Request msix irq for all banks unless SR-IOV enabled */
+	if (!accel_dev->pf.vf_info) {
+		for (i = 0; i < hw_data->num_banks; i++) {
+			struct adf_etr_bank_data *bank = &etr_data->banks[i];
+			unsigned int cpu, cpus = num_online_cpus();
+
+			name = *(pci_dev_info->msix_entries.names + i);
+			snprintf(name, ADF_MAX_MSIX_VECTOR_NAME,
+				 "qat%d-bundle%d", accel_dev->accel_id, i);
+			ret = request_irq(msixe[i].vector,
+					  adf_msix_isr_bundle, 0, name, bank);
+			if (ret) {
+				dev_err(&GET_DEV(accel_dev),
+					"failed to enable irq %d for %s\n",
+					msixe[i].vector, name);
+				return ret;
+			}
+
+			cpu = ((accel_dev->accel_id * hw_data->num_banks) +
+			       i) % cpus;
+			irq_set_affinity_hint(msixe[i].vector,
+					      get_cpu_mask(cpu));
 		}
-
-		cpu = ((accel_dev->accel_id * hw_data->num_banks) + i) % cpus;
-		irq_set_affinity_hint(msixe[i].vector, get_cpu_mask(cpu));
 	}
 
 	/* Request msix irq for AE */
@@ -152,11 +214,13 @@ static void adf_free_irqs(struct adf_accel_dev *accel_dev)
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	struct msix_entry *msixe = pci_dev_info->msix_entries.entries;
 	struct adf_etr_data *etr_data = accel_dev->transport;
-	int i;
+	int i = 0;
 
-	for (i = 0; i < hw_data->num_banks; i++) {
-		irq_set_affinity_hint(msixe[i].vector, NULL);
-		free_irq(msixe[i].vector, &etr_data->banks[i]);
+	if (pci_dev_info->msix_entries.num_entries > 1) {
+		for (i = 0; i < hw_data->num_banks; i++) {
+			irq_set_affinity_hint(msixe[i].vector, NULL);
+			free_irq(msixe[i].vector, &etr_data->banks[i]);
+		}
 	}
 	irq_set_affinity_hint(msixe[i].vector, NULL);
 	free_irq(msixe[i].vector, accel_dev);
@@ -168,7 +232,11 @@ static int adf_isr_alloc_msix_entry_table(struct adf_accel_dev *accel_dev)
 	char **names;
 	struct msix_entry *entries;
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
-	uint32_t msix_num_entries = hw_data->num_banks + 1;
+	u32 msix_num_entries = 1;
+
+	/* If SR-IOV is disabled (vf_info is NULL), add entries for each bank */
+	if (!accel_dev->pf.vf_info)
+		msix_num_entries += hw_data->num_banks;
 
 	entries = kzalloc_node(msix_num_entries * sizeof(*entries),
 			       GFP_KERNEL, dev_to_node(&GET_DEV(accel_dev)));
@@ -185,6 +253,7 @@ static int adf_isr_alloc_msix_entry_table(struct adf_accel_dev *accel_dev)
 		if (!(*(names + i)))
 			goto err;
 	}
+	accel_dev->accel_pci_dev.msix_entries.num_entries = msix_num_entries;
 	accel_dev->accel_pci_dev.msix_entries.entries = entries;
 	accel_dev->accel_pci_dev.msix_entries.names = names;
 	return 0;
@@ -198,13 +267,11 @@ err:
 
 static void adf_isr_free_msix_entry_table(struct adf_accel_dev *accel_dev)
 {
-	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
-	uint32_t msix_num_entries = hw_data->num_banks + 1;
 	char **names = accel_dev->accel_pci_dev.msix_entries.names;
 	int i;
 
 	kfree(accel_dev->accel_pci_dev.msix_entries.entries);
-	for (i = 0; i < msix_num_entries; i++)
+	for (i = 0; i < accel_dev->accel_pci_dev.msix_entries.num_entries; i++)
 		kfree(*(names + i));
 	kfree(names);
 }
diff --git a/drivers/crypto/qat/qat_dh895xccvf/Makefile b/drivers/crypto/qat/qat_dh895xccvf/Makefile
new file mode 100644
index 000000000000..85399fcbbad4
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xccvf/Makefile
@@ -0,0 +1,5 @@
+ccflags-y := -I$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCCVF) += qat_dh895xccvf.o
+qat_dh895xccvf-objs := adf_drv.o \
+		adf_isr.o \
+		adf_dh895xccvf_hw_data.o
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
new file mode 100644
index 000000000000..a9a27eff41fb
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
@@ -0,0 +1,172 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include <adf_pf2vf_msg.h>
+#include <adf_common_drv.h>
+#include "adf_dh895xccvf_hw_data.h"
+#include "adf_drv.h"
+
+static struct adf_hw_device_class dh895xcciov_class = {
+	.name = ADF_DH895XCCVF_DEVICE_NAME,
+	.type = DEV_DH895XCCVF,
+	.instances = 0
+};
+
+static u32 get_accel_mask(u32 fuse)
+{
+	return ADF_DH895XCCIOV_ACCELERATORS_MASK;
+}
+
+static u32 get_ae_mask(u32 fuse)
+{
+	return ADF_DH895XCCIOV_ACCELENGINES_MASK;
+}
+
+static u32 get_num_accels(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCCIOV_MAX_ACCELERATORS;
+}
+
+static u32 get_num_aes(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCCIOV_MAX_ACCELENGINES;
+}
+
+static u32 get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCCIOV_PMISC_BAR;
+}
+
+static u32 get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCCIOV_ETR_BAR;
+}
+
+static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
+{
+	return DEV_SKU_VF;
+}
+
+static u32 get_pf2vf_offset(u32 i)
+{
+	return ADF_DH895XCCIOV_PF2VF_OFFSET;
+}
+
+static u32 get_vintmsk_offset(u32 i)
+{
+	return ADF_DH895XCCIOV_VINTMSK_OFFSET;
+}
+
+static int adf_vf_int_noop(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+static void adf_vf_void_noop(struct adf_accel_dev *accel_dev)
+{
+}
+
+static int adf_vf2pf_init(struct adf_accel_dev *accel_dev)
+{
+	u32 msg = (ADF_VF2PF_MSGORIGIN_SYSTEM |
+		(ADF_VF2PF_MSGTYPE_INIT << ADF_VF2PF_MSGTYPE_SHIFT));
+
+	if (adf_iov_putmsg(accel_dev, msg, 0)) {
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Init event to PF\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void adf_vf2pf_shutdown(struct adf_accel_dev *accel_dev)
+{
+	u32 msg = (ADF_VF2PF_MSGORIGIN_SYSTEM |
+	    (ADF_VF2PF_MSGTYPE_SHUTDOWN << ADF_VF2PF_MSGTYPE_SHIFT));
+
+	if (adf_iov_putmsg(accel_dev, msg, 0))
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Shutdown event to PF\n");
+}
+
+void adf_init_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class = &dh895xcciov_class;
+	hw_data->instance_id = dh895xcciov_class.instances++;
+	hw_data->num_banks = ADF_DH895XCCIOV_ETR_MAX_BANKS;
+	hw_data->num_accel = ADF_DH895XCCIOV_MAX_ACCELERATORS;
+	hw_data->num_logical_accel = 1;
+	hw_data->num_engines = ADF_DH895XCCIOV_MAX_ACCELENGINES;
+	hw_data->tx_rx_gap = ADF_DH895XCCIOV_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_DH895XCCIOV_TX_RINGS_MASK;
+	hw_data->alloc_irq = adf_vf_isr_resource_alloc;
+	hw_data->free_irq = adf_vf_isr_resource_free;
+	hw_data->enable_error_correction = adf_vf_void_noop;
+	hw_data->init_admin_comms = adf_vf_int_noop;
+	hw_data->exit_admin_comms = adf_vf_void_noop;
+	hw_data->send_admin_init = adf_vf2pf_init;
+	hw_data->init_arb = adf_vf_int_noop;
+	hw_data->exit_arb = adf_vf_void_noop;
+	hw_data->disable_iov = adf_vf2pf_shutdown;
+	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = get_num_accels;
+	hw_data->get_num_aes = get_num_aes;
+	hw_data->get_etr_bar_id = get_etr_bar_id;
+	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_pf2vf_offset = get_pf2vf_offset;
+	hw_data->get_vintmsk_offset = get_vintmsk_offset;
+	hw_data->get_sku = get_sku;
+	hw_data->enable_ints = adf_vf_void_noop;
+	hw_data->enable_vf2pf_comms = adf_enable_vf2pf_comms;
+	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+}
+
+void adf_clean_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+}
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
new file mode 100644
index 000000000000..8f6babfef629
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
@@ -0,0 +1,68 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_DH895XVF_HW_DATA_H_
+#define ADF_DH895XVF_HW_DATA_H_
+
+#define ADF_DH895XCCIOV_PMISC_BAR 1
+#define ADF_DH895XCCIOV_ACCELERATORS_MASK 0x1
+#define ADF_DH895XCCIOV_ACCELENGINES_MASK 0x1
+#define ADF_DH895XCCIOV_MAX_ACCELERATORS 1
+#define ADF_DH895XCCIOV_MAX_ACCELENGINES 1
+#define ADF_DH895XCCIOV_RX_RINGS_OFFSET 8
+#define ADF_DH895XCCIOV_TX_RINGS_MASK 0xFF
+#define ADF_DH895XCCIOV_ETR_BAR 0
+#define ADF_DH895XCCIOV_ETR_MAX_BANKS 1
+
+#define ADF_DH895XCCIOV_PF2VF_OFFSET	0x200
+#define ADF_DH895XCC_PF2VF_PF2VFINT	BIT(0)
+
+#define ADF_DH895XCCIOV_VINTSOU_OFFSET	0x204
+#define ADF_DH895XCC_VINTSOU_BUN	BIT(0)
+#define ADF_DH895XCC_VINTSOU_PF2VF	BIT(1)
+
+#define ADF_DH895XCCIOV_VINTMSK_OFFSET	0x208
+#endif
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
new file mode 100644
index 000000000000..789426f21882
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
@@ -0,0 +1,393 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include <adf_transport_access_macros.h>
+#include "adf_dh895xccvf_hw_data.h"
+#include "adf_drv.h"
+
+static const char adf_driver_name[] = ADF_DH895XCCVF_DEVICE_NAME;
+
+#define ADF_SYSTEM_DEVICE(device_id) \
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	ADF_SYSTEM_DEVICE(ADF_DH895XCCIOV_PCI_DEVICE_ID),
+	{0,}
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static int adf_probe(struct pci_dev *dev, const struct pci_device_id *ent);
+static void adf_remove(struct pci_dev *dev);
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = adf_driver_name,
+	.probe = adf_probe,
+	.remove = adf_remove,
+};
+
+static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev)
+{
+	pci_release_regions(accel_dev->accel_pci_dev.pci_dev);
+	pci_disable_device(accel_dev->accel_pci_dev.pci_dev);
+}
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
+	struct adf_accel_dev *pf;
+	int i;
+
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		if (bar->virt_addr)
+			pci_iounmap(accel_pci_dev->pci_dev, bar->virt_addr);
+	}
+
+	if (accel_dev->hw_device) {
+		switch (accel_pci_dev->pci_dev->device) {
+		case ADF_DH895XCCIOV_PCI_DEVICE_ID:
+			adf_clean_hw_data_dh895xcciov(accel_dev->hw_device);
+			break;
+		default:
+			break;
+		}
+		kfree(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
+	}
+	adf_cfg_dev_remove(accel_dev);
+	debugfs_remove(accel_dev->debugfs_dir);
+	pf = adf_devmgr_pci_to_accel_dev(accel_pci_dev->pci_dev->physfn);
+	adf_devmgr_rm_dev(accel_dev, pf);
+}
+
+static int adf_dev_configure(struct adf_accel_dev *accel_dev)
+{
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	unsigned long val, bank = 0;
+
+	if (adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC))
+		goto err;
+	if (adf_cfg_section_add(accel_dev, "Accelerator0"))
+		goto err;
+
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_BANK_NUM, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, key,
+					(void *)&bank, ADF_DEC))
+		goto err;
+
+	val = bank;
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, key,
+					(void *)&val, ADF_DEC))
+		goto err;
+
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, 0);
+
+	val = 128;
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, key,
+					(void *)&val, ADF_DEC))
+		goto err;
+
+	val = 512;
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					key, (void *)&val, ADF_DEC))
+		goto err;
+
+	val = 0;
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					key, (void *)&val, ADF_DEC))
+		goto err;
+
+	val = 2;
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					key, (void *)&val, ADF_DEC))
+		goto err;
+
+	val = 8;
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					key, (void *)&val, ADF_DEC))
+		goto err;
+
+	val = 10;
+	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, 0);
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					key, (void *)&val, ADF_DEC))
+			goto err;
+
+	val = ADF_COALESCING_DEF_TIME;
+	snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT,
+		 (int)bank);
+	if (adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
+					key, (void *)&val, ADF_DEC))
+		goto err;
+
+	val = 1;
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					ADF_NUM_CY, (void *)&val, ADF_DEC))
+		goto err;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+	return 0;
+err:
+	dev_err(&GET_DEV(accel_dev), "Failed to configure QAT accel dev\n");
+	return -EINVAL;
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_dev *pf;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	char name[ADF_DEVICE_NAME_LENGTH];
+	unsigned int i, bar_nr;
+	int ret, bar_mask;
+
+	switch (ent->device) {
+	case ADF_DH895XCCIOV_PCI_DEVICE_ID:
+		break;
+	default:
+		dev_err(&pdev->dev, "Invalid device 0x%x.\n", ent->device);
+		return -ENODEV;
+	}
+
+	accel_dev = kzalloc_node(sizeof(*accel_dev), GFP_KERNEL,
+				 dev_to_node(&pdev->dev));
+	if (!accel_dev)
+		return -ENOMEM;
+
+	accel_dev->is_vf = true;
+	pf = adf_devmgr_pci_to_accel_dev(pdev->physfn);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
+
+	/* Add accel device to accel table */
+	if (adf_devmgr_add_dev(accel_dev, pf)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		kfree(accel_dev);
+		return -EFAULT;
+	}
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and configure device configuration structure */
+	hw_data = kzalloc_node(sizeof(*hw_data), GFP_KERNEL,
+			       dev_to_node(&pdev->dev));
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+	accel_dev->hw_device = hw_data;
+	switch (ent->device) {
+	case ADF_DH895XCCIOV_PCI_DEVICE_ID:
+		adf_init_hw_data_dh895xcciov(accel_dev->hw_device);
+		break;
+	default:
+		ret = -ENODEV;
+		goto out_err;
+	}
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+
+	/* Create dev top level debugfs entry */
+	snprintf(name, sizeof(name), "%s%s_%02x:%02d.%02d",
+		 ADF_DEVICE_NAME_PREFIX, hw_data->dev_class->name,
+		 pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+
+	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
+	if (!accel_dev->debugfs_dir) {
+		dev_err(&pdev->dev, "Could not create debugfs dir %s\n", name);
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* enable PCI device */
+	if (pci_enable_device(pdev)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* set dma identifier */
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
+			dev_err(&pdev->dev, "No usable DMA configuration\n");
+			ret = -EFAULT;
+			goto out_err_disable;
+		} else {
+			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		}
+
+	} else {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	}
+
+	if (pci_request_regions(pdev, adf_driver_name)) {
+		ret = -EFAULT;
+		goto out_err_disable;
+	}
+
+	/* Find and map all the device's BARS */
+	i = 0;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+			 ADF_PCI_MAX_BARS * 2) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
+
+		bar->base_addr = pci_resource_start(pdev, bar_nr);
+		if (!bar->base_addr)
+			break;
+		bar->size = pci_resource_len(pdev, bar_nr);
+		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", bar_nr);
+			ret = -EFAULT;
+			goto out_err_free_reg;
+		}
+	}
+	pci_set_master(pdev);
+	/* Completion for VF2PF request/response message exchange */
+	init_completion(&accel_dev->vf.iov_msg_completion);
+
+	ret = adf_dev_configure(accel_dev);
+	if (ret)
+		goto out_err_free_reg;
+
+	ret = adf_dev_init(accel_dev);
+	if (ret)
+		goto out_err_dev_shutdown;
+
+	ret = adf_dev_start(accel_dev);
+	if (ret)
+		goto out_err_dev_stop;
+
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_stop(accel_dev);
+out_err_dev_shutdown:
+	adf_dev_shutdown(accel_dev);
+out_err_free_reg:
+	pci_release_regions(accel_pci_dev->pci_dev);
+out_err_disable:
+	pci_disable_device(accel_pci_dev->pci_dev);
+out_err:
+	adf_cleanup_accel(accel_dev);
+	kfree(accel_dev);
+	return ret;
+}
+
+static void adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	if (adf_dev_stop(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+
+	adf_dev_shutdown(accel_dev);
+	adf_cleanup_accel(accel_dev);
+	adf_cleanup_pci_dev(accel_dev);
+	kfree(accel_dev);
+}
+
+static int __init adfdrv_init(void)
+{
+	request_module("intel_qat");
+
+	if (pci_register_driver(&adf_driver)) {
+		pr_err("QAT: Driver initialization failed\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void __exit adfdrv_release(void)
+{
+	pci_unregister_driver(&adf_driver);
+	adf_clean_vf_map(true);
+}
+
+module_init(adfdrv_init);
+module_exit(adfdrv_release);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_dh895xcc/qat_admin.c b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.h
index 55b7a8e48bad..e270e4a63d14 100644
--- a/drivers/crypto/qat/qat_dh895xcc/qat_admin.c
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.h
@@ -44,64 +44,14 @@
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
-#include <icp_qat_fw_init_admin.h>
+#ifndef ADF_DH895xVF_DRV_H_
+#define ADF_DH895xVF_DRV_H_
 #include <adf_accel_devices.h>
-#include <adf_common_drv.h>
-#include "adf_drv.h"
-
-static struct service_hndl qat_admin;
-
-static int qat_send_admin_cmd(struct adf_accel_dev *accel_dev, int cmd)
-{
-	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
-	struct icp_qat_fw_init_admin_req req;
-	struct icp_qat_fw_init_admin_resp resp;
-	int i;
-
-	memset(&req, 0, sizeof(struct icp_qat_fw_init_admin_req));
-	req.init_admin_cmd_id = cmd;
-	for (i = 0; i < hw_device->get_num_aes(hw_device); i++) {
-		memset(&resp, 0, sizeof(struct icp_qat_fw_init_admin_resp));
-		if (adf_put_admin_msg_sync(accel_dev, i, &req, &resp) ||
-		    resp.init_resp_hdr.status)
-			return -EFAULT;
-	}
-	return 0;
-}
-
-static int qat_admin_start(struct adf_accel_dev *accel_dev)
-{
-	return qat_send_admin_cmd(accel_dev, ICP_QAT_FW_INIT_ME);
-}
-
-static int qat_admin_event_handler(struct adf_accel_dev *accel_dev,
-				   enum adf_event event)
-{
-	int ret;
-
-	switch (event) {
-	case ADF_EVENT_START:
-		ret = qat_admin_start(accel_dev);
-		break;
-	case ADF_EVENT_STOP:
-	case ADF_EVENT_INIT:
-	case ADF_EVENT_SHUTDOWN:
-	default:
-		ret = 0;
-	}
-	return ret;
-}
-
-int qat_admin_register(void)
-{
-	memset(&qat_admin, 0, sizeof(struct service_hndl));
-	qat_admin.event_hld = qat_admin_event_handler;
-	qat_admin.name = "qat_admin";
-	qat_admin.admin = 1;
-	return adf_service_register(&qat_admin);
-}
-
-int qat_admin_unregister(void)
-{
-	return adf_service_unregister(&qat_admin);
-}
+#include <adf_transport.h>
+
+void adf_init_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data);
+int adf_vf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
+void adf_vf_isr_resource_free(struct adf_accel_dev *accel_dev);
+void adf_update_ring_arb_enable(struct adf_etr_ring_data *ring);
+#endif
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_isr.c b/drivers/crypto/qat/qat_dh895xccvf/adf_isr.c
new file mode 100644
index 000000000000..87c5d8adb125
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_isr.c
@@ -0,0 +1,258 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include <adf_cfg_strings.h>
+#include <adf_cfg_common.h>
+#include <adf_transport_access_macros.h>
+#include <adf_transport_internal.h>
+#include <adf_pf2vf_msg.h>
+#include "adf_drv.h"
+#include "adf_dh895xccvf_hw_data.h"
+
+static int adf_enable_msi(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *pci_dev_info = &accel_dev->accel_pci_dev;
+	int stat = pci_enable_msi(pci_dev_info->pci_dev);
+
+	if (stat) {
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to enable MSI interrupts\n");
+		return stat;
+	}
+
+	accel_dev->vf.irq_name = kzalloc(ADF_MAX_MSIX_VECTOR_NAME, GFP_KERNEL);
+	if (!accel_dev->vf.irq_name)
+		return -ENOMEM;
+
+	return stat;
+}
+
+static void adf_disable_msi(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+
+	kfree(accel_dev->vf.irq_name);
+	pci_disable_msi(pdev);
+}
+
+static void adf_pf2vf_bh_handler(void *data)
+{
+	struct adf_accel_dev *accel_dev = data;
+	void __iomem *pmisc_bar_addr =
+		(&GET_BARS(accel_dev)[ADF_DH895XCCIOV_PMISC_BAR])->virt_addr;
+	u32 msg;
+
+	/* Read the message from PF */
+	msg = ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCCIOV_PF2VF_OFFSET);
+
+	if (!(msg & ADF_PF2VF_MSGORIGIN_SYSTEM))
+		/* Ignore legacy non-system (non-kernel) PF2VF messages */
+		goto err;
+
+	switch ((msg & ADF_PF2VF_MSGTYPE_MASK) >> ADF_PF2VF_MSGTYPE_SHIFT) {
+	case ADF_PF2VF_MSGTYPE_RESTARTING:
+		dev_dbg(&GET_DEV(accel_dev),
+			"Restarting msg received from PF 0x%x\n", msg);
+		adf_dev_stop(accel_dev);
+		break;
+	case ADF_PF2VF_MSGTYPE_VERSION_RESP:
+		dev_dbg(&GET_DEV(accel_dev),
+			"Version resp received from PF 0x%x\n", msg);
+		accel_dev->vf.pf_version =
+			(msg & ADF_PF2VF_VERSION_RESP_VERS_MASK) >>
+			ADF_PF2VF_VERSION_RESP_VERS_SHIFT;
+		accel_dev->vf.compatible =
+			(msg & ADF_PF2VF_VERSION_RESP_RESULT_MASK) >>
+			ADF_PF2VF_VERSION_RESP_RESULT_SHIFT;
+		complete(&accel_dev->vf.iov_msg_completion);
+		break;
+	default:
+		goto err;
+	}
+
+	/* To ack, clear the PF2VFINT bit */
+	msg &= ~ADF_DH895XCC_PF2VF_PF2VFINT;
+	ADF_CSR_WR(pmisc_bar_addr, ADF_DH895XCCIOV_PF2VF_OFFSET, msg);
+
+	/* Re-enable PF2VF interrupts */
+	adf_enable_pf2vf_interrupts(accel_dev);
+	return;
+err:
+	dev_err(&GET_DEV(accel_dev),
+		"Unknown message from PF (0x%x); leaving PF2VF ints disabled\n",
+		msg);
+}
+
+static int adf_setup_pf2vf_bh(struct adf_accel_dev *accel_dev)
+{
+	tasklet_init(&accel_dev->vf.pf2vf_bh_tasklet,
+		     (void *)adf_pf2vf_bh_handler, (unsigned long)accel_dev);
+
+	mutex_init(&accel_dev->vf.vf2pf_lock);
+	return 0;
+}
+
+static void adf_cleanup_pf2vf_bh(struct adf_accel_dev *accel_dev)
+{
+	tasklet_disable(&accel_dev->vf.pf2vf_bh_tasklet);
+	tasklet_kill(&accel_dev->vf.pf2vf_bh_tasklet);
+	mutex_destroy(&accel_dev->vf.vf2pf_lock);
+}
+
+static irqreturn_t adf_isr(int irq, void *privdata)
+{
+	struct adf_accel_dev *accel_dev = privdata;
+	void __iomem *pmisc_bar_addr =
+		(&GET_BARS(accel_dev)[ADF_DH895XCCIOV_PMISC_BAR])->virt_addr;
+	u32 v_int;
+
+	/* Read VF INT source CSR to determine the source of VF interrupt */
+	v_int = ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCCIOV_VINTSOU_OFFSET);
+
+	/* Check for PF2VF interrupt */
+	if (v_int & ADF_DH895XCC_VINTSOU_PF2VF) {
+		/* Disable PF to VF interrupt */
+		adf_disable_pf2vf_interrupts(accel_dev);
+
+		/* Schedule tasklet to handle interrupt BH */
+		tasklet_hi_schedule(&accel_dev->vf.pf2vf_bh_tasklet);
+		return IRQ_HANDLED;
+	}
+
+	/* Check bundle interrupt */
+	if (v_int & ADF_DH895XCC_VINTSOU_BUN) {
+		struct adf_etr_data *etr_data = accel_dev->transport;
+		struct adf_etr_bank_data *bank = &etr_data->banks[0];
+
+		/* Disable Flag and Coalesce Ring Interrupts */
+		WRITE_CSR_INT_FLAG_AND_COL(bank->csr_addr, bank->bank_number,
+					   0);
+		tasklet_hi_schedule(&bank->resp_handler);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int adf_request_msi_irq(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	unsigned int cpu;
+	int ret;
+
+	snprintf(accel_dev->vf.irq_name, ADF_MAX_MSIX_VECTOR_NAME,
+		 "qat_%02x:%02d.%02d", pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+	ret = request_irq(pdev->irq, adf_isr, 0, accel_dev->vf.irq_name,
+			  (void *)accel_dev);
+	if (ret) {
+		dev_err(&GET_DEV(accel_dev), "failed to enable irq for %s\n",
+			accel_dev->vf.irq_name);
+		return ret;
+	}
+	cpu = accel_dev->accel_id % num_online_cpus();
+	irq_set_affinity_hint(pdev->irq, get_cpu_mask(cpu));
+
+	return ret;
+}
+
+static int adf_setup_bh(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *priv_data = accel_dev->transport;
+
+	tasklet_init(&priv_data->banks[0].resp_handler, adf_response_handler,
+		     (unsigned long)priv_data->banks);
+	return 0;
+}
+
+static void adf_cleanup_bh(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *priv_data = accel_dev->transport;
+
+	tasklet_disable(&priv_data->banks[0].resp_handler);
+	tasklet_kill(&priv_data->banks[0].resp_handler);
+}
+
+void adf_vf_isr_resource_free(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+
+	irq_set_affinity_hint(pdev->irq, NULL);
+	free_irq(pdev->irq, (void *)accel_dev);
+	adf_cleanup_bh(accel_dev);
+	adf_cleanup_pf2vf_bh(accel_dev);
+	adf_disable_msi(accel_dev);
+}
+
+int adf_vf_isr_resource_alloc(struct adf_accel_dev *accel_dev)
+{
+	if (adf_enable_msi(accel_dev))
+		goto err_out;
+
+	if (adf_setup_pf2vf_bh(accel_dev))
+		goto err_out;
+
+	if (adf_setup_bh(accel_dev))
+		goto err_out;
+
+	if (adf_request_msi_irq(accel_dev))
+		goto err_out;
+
+	return 0;
+err_out:
+	adf_vf_isr_resource_free(accel_dev);
+	return -EFAULT;
+}
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index 5c5df1d17f90..be2f5049256a 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -296,7 +296,7 @@ static int qce_ahash_update(struct ahash_request *req)
 	if (rctx->buflen) {
 		sg_init_table(rctx->sg, 2);
 		sg_set_buf(rctx->sg, rctx->tmpbuf, rctx->buflen);
-		scatterwalk_sg_chain(rctx->sg, 2, req->src);
+		sg_chain(rctx->sg, 2, req->src);
 		req->src = rctx->sg;
 	}
 
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 397a500b3d8a..820dc3acb28c 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -999,7 +999,7 @@ static int sahara_sha_prepare_request(struct ahash_request *req)
 		sg_init_table(rctx->in_sg_chain, 2);
 		sg_set_buf(rctx->in_sg_chain, rctx->rembuf, rctx->buf_cnt);
 
-		scatterwalk_sg_chain(rctx->in_sg_chain, 2, req->src);
+		sg_chain(rctx->in_sg_chain, 2, req->src);
 
 		rctx->total = req->nbytes + rctx->buf_cnt;
 		rctx->in_sg = rctx->in_sg_chain;
@@ -1516,7 +1516,7 @@ static int sahara_probe(struct platform_device *pdev)
 	}
 
 	/* Allocate HW descriptors */
-	dev->hw_desc[0] = dma_alloc_coherent(&pdev->dev,
+	dev->hw_desc[0] = dmam_alloc_coherent(&pdev->dev,
 			SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc),
 			&dev->hw_phys_desc[0], GFP_KERNEL);
 	if (!dev->hw_desc[0]) {
@@ -1528,34 +1528,31 @@ static int sahara_probe(struct platform_device *pdev)
 				sizeof(struct sahara_hw_desc);
 
 	/* Allocate space for iv and key */
-	dev->key_base = dma_alloc_coherent(&pdev->dev, 2 * AES_KEYSIZE_128,
+	dev->key_base = dmam_alloc_coherent(&pdev->dev, 2 * AES_KEYSIZE_128,
 				&dev->key_phys_base, GFP_KERNEL);
 	if (!dev->key_base) {
 		dev_err(&pdev->dev, "Could not allocate memory for key\n");
-		err = -ENOMEM;
-		goto err_key;
+		return -ENOMEM;
 	}
 	dev->iv_base = dev->key_base + AES_KEYSIZE_128;
 	dev->iv_phys_base = dev->key_phys_base + AES_KEYSIZE_128;
 
 	/* Allocate space for context: largest digest + message length field */
-	dev->context_base = dma_alloc_coherent(&pdev->dev,
+	dev->context_base = dmam_alloc_coherent(&pdev->dev,
 					SHA256_DIGEST_SIZE + 4,
 					&dev->context_phys_base, GFP_KERNEL);
 	if (!dev->context_base) {
 		dev_err(&pdev->dev, "Could not allocate memory for MDHA context\n");
-		err = -ENOMEM;
-		goto err_key;
+		return -ENOMEM;
 	}
 
 	/* Allocate space for HW links */
-	dev->hw_link[0] = dma_alloc_coherent(&pdev->dev,
+	dev->hw_link[0] = dmam_alloc_coherent(&pdev->dev,
 			SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
 			&dev->hw_phys_link[0], GFP_KERNEL);
 	if (!dev->hw_link[0]) {
 		dev_err(&pdev->dev, "Could not allocate hw links\n");
-		err = -ENOMEM;
-		goto err_link;
+		return -ENOMEM;
 	}
 	for (i = 1; i < SAHARA_MAX_HW_LINK; i++) {
 		dev->hw_phys_link[i] = dev->hw_phys_link[i - 1] +
@@ -1572,15 +1569,14 @@ static int sahara_probe(struct platform_device *pdev)
 
 	dev->kthread = kthread_run(sahara_queue_manage, dev, "sahara_crypto");
 	if (IS_ERR(dev->kthread)) {
-		err = PTR_ERR(dev->kthread);
-		goto err_link;
+		return PTR_ERR(dev->kthread);
 	}
 
 	init_completion(&dev->dma_completion);
 
 	err = clk_prepare_enable(dev->clk_ipg);
 	if (err)
-		goto err_link;
+		return err;
 	err = clk_prepare_enable(dev->clk_ahb);
 	if (err)
 		goto clk_ipg_disable;
@@ -1620,25 +1616,11 @@ static int sahara_probe(struct platform_device *pdev)
 	return 0;
 
 err_algs:
-	dma_free_coherent(&pdev->dev,
-			  SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
-			  dev->hw_link[0], dev->hw_phys_link[0]);
 	kthread_stop(dev->kthread);
 	dev_ptr = NULL;
 	clk_disable_unprepare(dev->clk_ahb);
 clk_ipg_disable:
 	clk_disable_unprepare(dev->clk_ipg);
-err_link:
-	dma_free_coherent(&pdev->dev,
-			  2 * AES_KEYSIZE_128,
-			  dev->key_base, dev->key_phys_base);
-	dma_free_coherent(&pdev->dev,
-			  SHA256_DIGEST_SIZE,
-			  dev->context_base, dev->context_phys_base);
-err_key:
-	dma_free_coherent(&pdev->dev,
-			  SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc),
-			  dev->hw_desc[0], dev->hw_phys_desc[0]);
 
 	return err;
 }
@@ -1647,16 +1629,6 @@ static int sahara_remove(struct platform_device *pdev)
 {
 	struct sahara_dev *dev = platform_get_drvdata(pdev);
 
-	dma_free_coherent(&pdev->dev,
-			  SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
-			  dev->hw_link[0], dev->hw_phys_link[0]);
-	dma_free_coherent(&pdev->dev,
-			  2 * AES_KEYSIZE_128,
-			  dev->key_base, dev->key_phys_base);
-	dma_free_coherent(&pdev->dev,
-			  SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc),
-			  dev->hw_desc[0], dev->hw_phys_desc[0]);
-
 	kthread_stop(dev->kthread);
 
 	sahara_unregister_algs(dev);
diff --git a/drivers/crypto/sunxi-ss/Makefile b/drivers/crypto/sunxi-ss/Makefile
new file mode 100644
index 000000000000..8f4c7a273141
--- /dev/null
+++ b/drivers/crypto/sunxi-ss/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sun4i-ss.o
+sun4i-ss-y += sun4i-ss-core.o sun4i-ss-hash.o sun4i-ss-cipher.o
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
new file mode 100644
index 000000000000..e070c316e8b7
--- /dev/null
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -0,0 +1,542 @@
+/*
+ * sun4i-ss-cipher.c - hardware cryptographic accelerator for Allwinner A20 SoC
+ *
+ * Copyright (C) 2013-2015 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * This file add support for AES cipher with 128,192,256 bits
+ * keysize in CBC and ECB mode.
+ * Add support also for DES and 3DES in CBC and ECB mode.
+ *
+ * You could find the datasheet in Documentation/arm/sunxi/README
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include "sun4i-ss.h"
+
+static int sun4i_ss_opti_poll(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_ss_ctx *ss = op->ss;
+	unsigned int ivsize = crypto_ablkcipher_ivsize(tfm);
+	struct sun4i_cipher_req_ctx *ctx = ablkcipher_request_ctx(areq);
+	u32 mode = ctx->mode;
+	/* when activating SS, the default FIFO space is SS_RX_DEFAULT(32) */
+	u32 rx_cnt = SS_RX_DEFAULT;
+	u32 tx_cnt = 0;
+	u32 spaces;
+	u32 v;
+	int i, err = 0;
+	unsigned int ileft = areq->nbytes;
+	unsigned int oleft = areq->nbytes;
+	unsigned int todo;
+	struct sg_mapping_iter mi, mo;
+	unsigned int oi, oo; /* offset for in and out */
+
+	if (areq->nbytes == 0)
+		return 0;
+
+	if (!areq->info) {
+		dev_err_ratelimited(ss->dev, "ERROR: Empty IV\n");
+		return -EINVAL;
+	}
+
+	if (!areq->src || !areq->dst) {
+		dev_err_ratelimited(ss->dev, "ERROR: Some SGs are NULL\n");
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&ss->slock);
+
+	for (i = 0; i < op->keylen; i += 4)
+		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
+
+	if (areq->info) {
+		for (i = 0; i < 4 && i < ivsize / 4; i++) {
+			v = *(u32 *)(areq->info + i * 4);
+			writel(v, ss->base + SS_IV0 + i * 4);
+		}
+	}
+	writel(mode, ss->base + SS_CTL);
+
+	sg_miter_start(&mi, areq->src, sg_nents(areq->src),
+		       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+	sg_miter_start(&mo, areq->dst, sg_nents(areq->dst),
+		       SG_MITER_TO_SG | SG_MITER_ATOMIC);
+	sg_miter_next(&mi);
+	sg_miter_next(&mo);
+	if (!mi.addr || !mo.addr) {
+		dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
+		err = -EINVAL;
+		goto release_ss;
+	}
+
+	ileft = areq->nbytes / 4;
+	oleft = areq->nbytes / 4;
+	oi = 0;
+	oo = 0;
+	do {
+		todo = min3(rx_cnt, ileft, (mi.length - oi) / 4);
+		if (todo > 0) {
+			ileft -= todo;
+			writesl(ss->base + SS_RXFIFO, mi.addr + oi, todo);
+			oi += todo * 4;
+		}
+		if (oi == mi.length) {
+			sg_miter_next(&mi);
+			oi = 0;
+		}
+
+		spaces = readl(ss->base + SS_FCSR);
+		rx_cnt = SS_RXFIFO_SPACES(spaces);
+		tx_cnt = SS_TXFIFO_SPACES(spaces);
+
+		todo = min3(tx_cnt, oleft, (mo.length - oo) / 4);
+		if (todo > 0) {
+			oleft -= todo;
+			readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo);
+			oo += todo * 4;
+		}
+		if (oo == mo.length) {
+			sg_miter_next(&mo);
+			oo = 0;
+		}
+	} while (mo.length > 0);
+
+	if (areq->info) {
+		for (i = 0; i < 4 && i < ivsize / 4; i++) {
+			v = readl(ss->base + SS_IV0 + i * 4);
+			*(u32 *)(areq->info + i * 4) = v;
+		}
+	}
+
+release_ss:
+	sg_miter_stop(&mi);
+	sg_miter_stop(&mo);
+	writel(0, ss->base + SS_CTL);
+	spin_unlock_bh(&ss->slock);
+	return err;
+}
+
+/* Generic function that support SG with size not multiple of 4 */
+static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_ss_ctx *ss = op->ss;
+	int no_chunk = 1;
+	struct scatterlist *in_sg = areq->src;
+	struct scatterlist *out_sg = areq->dst;
+	unsigned int ivsize = crypto_ablkcipher_ivsize(tfm);
+	struct sun4i_cipher_req_ctx *ctx = ablkcipher_request_ctx(areq);
+	u32 mode = ctx->mode;
+	/* when activating SS, the default FIFO space is SS_RX_DEFAULT(32) */
+	u32 rx_cnt = SS_RX_DEFAULT;
+	u32 tx_cnt = 0;
+	u32 v;
+	u32 spaces;
+	int i, err = 0;
+	unsigned int ileft = areq->nbytes;
+	unsigned int oleft = areq->nbytes;
+	unsigned int todo;
+	struct sg_mapping_iter mi, mo;
+	unsigned int oi, oo;	/* offset for in and out */
+	char buf[4 * SS_RX_MAX];/* buffer for linearize SG src */
+	char bufo[4 * SS_TX_MAX]; /* buffer for linearize SG dst */
+	unsigned int ob = 0;	/* offset in buf */
+	unsigned int obo = 0;	/* offset in bufo*/
+	unsigned int obl = 0;	/* length of data in bufo */
+
+	if (areq->nbytes == 0)
+		return 0;
+
+	if (!areq->info) {
+		dev_err_ratelimited(ss->dev, "ERROR: Empty IV\n");
+		return -EINVAL;
+	}
+
+	if (!areq->src || !areq->dst) {
+		dev_err_ratelimited(ss->dev, "ERROR: Some SGs are NULL\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * if we have only SGs with size multiple of 4,
+	 * we can use the SS optimized function
+	 */
+	while (in_sg && no_chunk == 1) {
+		if ((in_sg->length % 4) != 0)
+			no_chunk = 0;
+		in_sg = sg_next(in_sg);
+	}
+	while (out_sg && no_chunk == 1) {
+		if ((out_sg->length % 4) != 0)
+			no_chunk = 0;
+		out_sg = sg_next(out_sg);
+	}
+
+	if (no_chunk == 1)
+		return sun4i_ss_opti_poll(areq);
+
+	spin_lock_bh(&ss->slock);
+
+	for (i = 0; i < op->keylen; i += 4)
+		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
+
+	if (areq->info) {
+		for (i = 0; i < 4 && i < ivsize / 4; i++) {
+			v = *(u32 *)(areq->info + i * 4);
+			writel(v, ss->base + SS_IV0 + i * 4);
+		}
+	}
+	writel(mode, ss->base + SS_CTL);
+
+	sg_miter_start(&mi, areq->src, sg_nents(areq->src),
+		       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+	sg_miter_start(&mo, areq->dst, sg_nents(areq->dst),
+		       SG_MITER_TO_SG | SG_MITER_ATOMIC);
+	sg_miter_next(&mi);
+	sg_miter_next(&mo);
+	if (!mi.addr || !mo.addr) {
+		dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
+		err = -EINVAL;
+		goto release_ss;
+	}
+	ileft = areq->nbytes;
+	oleft = areq->nbytes;
+	oi = 0;
+	oo = 0;
+
+	while (oleft > 0) {
+		if (ileft > 0) {
+			/*
+			 * todo is the number of consecutive 4byte word that we
+			 * can read from current SG
+			 */
+			todo = min3(rx_cnt, ileft / 4, (mi.length - oi) / 4);
+			if (todo > 0 && ob == 0) {
+				writesl(ss->base + SS_RXFIFO, mi.addr + oi,
+					todo);
+				ileft -= todo * 4;
+				oi += todo * 4;
+			} else {
+				/*
+				 * not enough consecutive bytes, so we need to
+				 * linearize in buf. todo is in bytes
+				 * After that copy, if we have a multiple of 4
+				 * we need to be able to write all buf in one
+				 * pass, so it is why we min() with rx_cnt
+				 */
+				todo = min3(rx_cnt * 4 - ob, ileft,
+					    mi.length - oi);
+				memcpy(buf + ob, mi.addr + oi, todo);
+				ileft -= todo;
+				oi += todo;
+				ob += todo;
+				if (ob % 4 == 0) {
+					writesl(ss->base + SS_RXFIFO, buf,
+						ob / 4);
+					ob = 0;
+				}
+			}
+			if (oi == mi.length) {
+				sg_miter_next(&mi);
+				oi = 0;
+			}
+		}
+
+		spaces = readl(ss->base + SS_FCSR);
+		rx_cnt = SS_RXFIFO_SPACES(spaces);
+		tx_cnt = SS_TXFIFO_SPACES(spaces);
+		dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u %u\n",
+			mode,
+			oi, mi.length, ileft, areq->nbytes, rx_cnt,
+			oo, mo.length, oleft, areq->nbytes, tx_cnt,
+			todo, ob);
+
+		if (tx_cnt == 0)
+			continue;
+		/* todo in 4bytes word */
+		todo = min3(tx_cnt, oleft / 4, (mo.length - oo) / 4);
+		if (todo > 0) {
+			readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo);
+			oleft -= todo * 4;
+			oo += todo * 4;
+			if (oo == mo.length) {
+				sg_miter_next(&mo);
+				oo = 0;
+			}
+		} else {
+			/*
+			 * read obl bytes in bufo, we read at maximum for
+			 * emptying the device
+			 */
+			readsl(ss->base + SS_TXFIFO, bufo, tx_cnt);
+			obl = tx_cnt * 4;
+			obo = 0;
+			do {
+				/*
+				 * how many bytes we can copy ?
+				 * no more than remaining SG size
+				 * no more than remaining buffer
+				 * no need to test against oleft
+				 */
+				todo = min(mo.length - oo, obl - obo);
+				memcpy(mo.addr + oo, bufo + obo, todo);
+				oleft -= todo;
+				obo += todo;
+				oo += todo;
+				if (oo == mo.length) {
+					sg_miter_next(&mo);
+					oo = 0;
+				}
+			} while (obo < obl);
+			/* bufo must be fully used here */
+		}
+	}
+	if (areq->info) {
+		for (i = 0; i < 4 && i < ivsize / 4; i++) {
+			v = readl(ss->base + SS_IV0 + i * 4);
+			*(u32 *)(areq->info + i * 4) = v;
+		}
+	}
+
+release_ss:
+	sg_miter_stop(&mi);
+	sg_miter_stop(&mo);
+	writel(0, ss->base + SS_CTL);
+	spin_unlock_bh(&ss->slock);
+
+	return err;
+}
+
+/* CBC AES */
+int sun4i_ss_cbc_aes_encrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_AES | SS_CBC | SS_ENABLED | SS_ENCRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_cbc_aes_decrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_AES | SS_CBC | SS_ENABLED | SS_DECRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+/* ECB AES */
+int sun4i_ss_ecb_aes_encrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_AES | SS_ECB | SS_ENABLED | SS_ENCRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_ecb_aes_decrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_AES | SS_ECB | SS_ENABLED | SS_DECRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+/* CBC DES */
+int sun4i_ss_cbc_des_encrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_DES | SS_CBC | SS_ENABLED | SS_ENCRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_cbc_des_decrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_DES | SS_CBC | SS_ENABLED | SS_DECRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+/* ECB DES */
+int sun4i_ss_ecb_des_encrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_DES | SS_ECB | SS_ENABLED | SS_ENCRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_ecb_des_decrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_DES | SS_ECB | SS_ENABLED | SS_DECRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+/* CBC 3DES */
+int sun4i_ss_cbc_des3_encrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_3DES | SS_CBC | SS_ENABLED | SS_ENCRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_cbc_des3_decrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_3DES | SS_CBC | SS_ENABLED | SS_DECRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+/* ECB 3DES */
+int sun4i_ss_ecb_des3_encrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_3DES | SS_ECB | SS_ENABLED | SS_ENCRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_ecb_des3_decrypt(struct ablkcipher_request *areq)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *rctx = ablkcipher_request_ctx(areq);
+
+	rctx->mode = SS_OP_3DES | SS_ECB | SS_ENABLED | SS_DECRYPTION |
+		op->keymode;
+	return sun4i_ss_cipher_poll(areq);
+}
+
+int sun4i_ss_cipher_init(struct crypto_tfm *tfm)
+{
+	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct sun4i_ss_alg_template *algt;
+
+	memset(op, 0, sizeof(struct sun4i_tfm_ctx));
+
+	algt = container_of(alg, struct sun4i_ss_alg_template, alg.crypto);
+	op->ss = algt->ss;
+
+	tfm->crt_ablkcipher.reqsize = sizeof(struct sun4i_cipher_req_ctx);
+
+	return 0;
+}
+
+/* check and set the AES key, prepare the mode to be used */
+int sun4i_ss_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_ss_ctx *ss = op->ss;
+
+	switch (keylen) {
+	case 128 / 8:
+		op->keymode = SS_AES_128BITS;
+		break;
+	case 192 / 8:
+		op->keymode = SS_AES_192BITS;
+		break;
+	case 256 / 8:
+		op->keymode = SS_AES_256BITS;
+		break;
+	default:
+		dev_err(ss->dev, "ERROR: Invalid keylen %u\n", keylen);
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	op->keylen = keylen;
+	memcpy(op->key, key, keylen);
+	return 0;
+}
+
+/* check and set the DES key, prepare the mode to be used */
+int sun4i_ss_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_ss_ctx *ss = op->ss;
+	u32 flags;
+	u32 tmp[DES_EXPKEY_WORDS];
+	int ret;
+
+	if (unlikely(keylen != DES_KEY_SIZE)) {
+		dev_err(ss->dev, "Invalid keylen %u\n", keylen);
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	flags = crypto_ablkcipher_get_flags(tfm);
+
+	ret = des_ekey(tmp, key);
+	if (unlikely(ret == 0) && (flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_WEAK_KEY);
+		dev_dbg(ss->dev, "Weak key %u\n", keylen);
+		return -EINVAL;
+	}
+
+	op->keylen = keylen;
+	memcpy(op->key, key, keylen);
+	return 0;
+}
+
+/* check and set the 3DES key, prepare the mode to be used */
+int sun4i_ss_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			 unsigned int keylen)
+{
+	struct sun4i_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
+	struct sun4i_ss_ctx *ss = op->ss;
+
+	if (unlikely(keylen != 3 * DES_KEY_SIZE)) {
+		dev_err(ss->dev, "Invalid keylen %u\n", keylen);
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	op->keylen = keylen;
+	memcpy(op->key, key, keylen);
+	return 0;
+}
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
new file mode 100644
index 000000000000..eab6fe227fa0
--- /dev/null
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -0,0 +1,425 @@
+/*
+ * sun4i-ss-core.c - hardware cryptographic accelerator for Allwinner A20 SoC
+ *
+ * Copyright (C) 2013-2015 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * Core file which registers crypto algorithms supported by the SS.
+ *
+ * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <crypto/scatterwalk.h>
+#include <linux/scatterlist.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/reset.h>
+
+#include "sun4i-ss.h"
+
+static struct sun4i_ss_alg_template ss_algs[] = {
+{       .type = CRYPTO_ALG_TYPE_AHASH,
+	.mode = SS_OP_MD5,
+	.alg.hash = {
+		.init = sun4i_hash_init,
+		.update = sun4i_hash_update,
+		.final = sun4i_hash_final,
+		.finup = sun4i_hash_finup,
+		.digest = sun4i_hash_digest,
+		.export = sun4i_hash_export_md5,
+		.import = sun4i_hash_import_md5,
+		.halg = {
+			.digestsize = MD5_DIGEST_SIZE,
+			.base = {
+				.cra_name = "md5",
+				.cra_driver_name = "md5-sun4i-ss",
+				.cra_priority = 300,
+				.cra_alignmask = 3,
+				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
+				.cra_module = THIS_MODULE,
+				.cra_type = &crypto_ahash_type,
+				.cra_init = sun4i_hash_crainit
+			}
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_AHASH,
+	.mode = SS_OP_SHA1,
+	.alg.hash = {
+		.init = sun4i_hash_init,
+		.update = sun4i_hash_update,
+		.final = sun4i_hash_final,
+		.finup = sun4i_hash_finup,
+		.digest = sun4i_hash_digest,
+		.export = sun4i_hash_export_sha1,
+		.import = sun4i_hash_import_sha1,
+		.halg = {
+			.digestsize = SHA1_DIGEST_SIZE,
+			.base = {
+				.cra_name = "sha1",
+				.cra_driver_name = "sha1-sun4i-ss",
+				.cra_priority = 300,
+				.cra_alignmask = 3,
+				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_blocksize = SHA1_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
+				.cra_module = THIS_MODULE,
+				.cra_type = &crypto_ahash_type,
+				.cra_init = sun4i_hash_crainit
+			}
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.alg.crypto = {
+		.cra_name = "cbc(aes)",
+		.cra_driver_name = "cbc-aes-sun4i-ss",
+		.cra_priority = 300,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
+		.cra_module = THIS_MODULE,
+		.cra_alignmask = 3,
+		.cra_type = &crypto_ablkcipher_type,
+		.cra_init = sun4i_ss_cipher_init,
+		.cra_ablkcipher = {
+			.min_keysize	= AES_MIN_KEY_SIZE,
+			.max_keysize	= AES_MAX_KEY_SIZE,
+			.ivsize		= AES_BLOCK_SIZE,
+			.setkey         = sun4i_ss_aes_setkey,
+			.encrypt        = sun4i_ss_cbc_aes_encrypt,
+			.decrypt        = sun4i_ss_cbc_aes_decrypt,
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.alg.crypto = {
+		.cra_name = "ecb(aes)",
+		.cra_driver_name = "ecb-aes-sun4i-ss",
+		.cra_priority = 300,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
+		.cra_module = THIS_MODULE,
+		.cra_alignmask = 3,
+		.cra_type = &crypto_ablkcipher_type,
+		.cra_init = sun4i_ss_cipher_init,
+		.cra_ablkcipher = {
+			.min_keysize	= AES_MIN_KEY_SIZE,
+			.max_keysize	= AES_MAX_KEY_SIZE,
+			.ivsize		= AES_BLOCK_SIZE,
+			.setkey         = sun4i_ss_aes_setkey,
+			.encrypt        = sun4i_ss_ecb_aes_encrypt,
+			.decrypt        = sun4i_ss_ecb_aes_decrypt,
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.alg.crypto = {
+		.cra_name = "cbc(des)",
+		.cra_driver_name = "cbc-des-sun4i-ss",
+		.cra_priority = 300,
+		.cra_blocksize = DES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.cra_ctxsize = sizeof(struct sun4i_req_ctx),
+		.cra_module = THIS_MODULE,
+		.cra_alignmask = 3,
+		.cra_type = &crypto_ablkcipher_type,
+		.cra_init = sun4i_ss_cipher_init,
+		.cra_u.ablkcipher = {
+			.min_keysize    = DES_KEY_SIZE,
+			.max_keysize    = DES_KEY_SIZE,
+			.ivsize         = DES_BLOCK_SIZE,
+			.setkey         = sun4i_ss_des_setkey,
+			.encrypt        = sun4i_ss_cbc_des_encrypt,
+			.decrypt        = sun4i_ss_cbc_des_decrypt,
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.alg.crypto = {
+		.cra_name = "ecb(des)",
+		.cra_driver_name = "ecb-des-sun4i-ss",
+		.cra_priority = 300,
+		.cra_blocksize = DES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.cra_ctxsize = sizeof(struct sun4i_req_ctx),
+		.cra_module = THIS_MODULE,
+		.cra_alignmask = 3,
+		.cra_type = &crypto_ablkcipher_type,
+		.cra_init = sun4i_ss_cipher_init,
+		.cra_u.ablkcipher = {
+			.min_keysize    = DES_KEY_SIZE,
+			.max_keysize    = DES_KEY_SIZE,
+			.setkey         = sun4i_ss_des_setkey,
+			.encrypt        = sun4i_ss_ecb_des_encrypt,
+			.decrypt        = sun4i_ss_ecb_des_decrypt,
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.alg.crypto = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "cbc-des3-sun4i-ss",
+			.cra_priority = 300,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
+			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 3,
+			.cra_type = &crypto_ablkcipher_type,
+			.cra_init = sun4i_ss_cipher_init,
+			.cra_u.ablkcipher = {
+				.min_keysize    = DES3_EDE_KEY_SIZE,
+				.max_keysize    = DES3_EDE_KEY_SIZE,
+				.ivsize         = DES3_EDE_BLOCK_SIZE,
+				.setkey         = sun4i_ss_des3_setkey,
+				.encrypt        = sun4i_ss_cbc_des3_encrypt,
+				.decrypt        = sun4i_ss_cbc_des3_decrypt,
+		}
+	}
+},
+{       .type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.alg.crypto = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "ecb-des3-sun4i-ss",
+			.cra_priority = 300,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
+			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 3,
+			.cra_type = &crypto_ablkcipher_type,
+			.cra_init = sun4i_ss_cipher_init,
+			.cra_u.ablkcipher = {
+				.min_keysize    = DES3_EDE_KEY_SIZE,
+				.max_keysize    = DES3_EDE_KEY_SIZE,
+				.ivsize         = DES3_EDE_BLOCK_SIZE,
+				.setkey         = sun4i_ss_des3_setkey,
+				.encrypt        = sun4i_ss_ecb_des3_encrypt,
+				.decrypt        = sun4i_ss_ecb_des3_decrypt,
+		}
+	}
+},
+};
+
+static int sun4i_ss_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	u32 v;
+	int err, i;
+	unsigned long cr;
+	const unsigned long cr_ahb = 24 * 1000 * 1000;
+	const unsigned long cr_mod = 150 * 1000 * 1000;
+	struct sun4i_ss_ctx *ss;
+
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	ss = devm_kzalloc(&pdev->dev, sizeof(*ss), GFP_KERNEL);
+	if (!ss)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ss->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ss->base)) {
+		dev_err(&pdev->dev, "Cannot request MMIO\n");
+		return PTR_ERR(ss->base);
+	}
+
+	ss->ssclk = devm_clk_get(&pdev->dev, "mod");
+	if (IS_ERR(ss->ssclk)) {
+		err = PTR_ERR(ss->ssclk);
+		dev_err(&pdev->dev, "Cannot get SS clock err=%d\n", err);
+		return err;
+	}
+	dev_dbg(&pdev->dev, "clock ss acquired\n");
+
+	ss->busclk = devm_clk_get(&pdev->dev, "ahb");
+	if (IS_ERR(ss->busclk)) {
+		err = PTR_ERR(ss->busclk);
+		dev_err(&pdev->dev, "Cannot get AHB SS clock err=%d\n", err);
+		return err;
+	}
+	dev_dbg(&pdev->dev, "clock ahb_ss acquired\n");
+
+	ss->reset = devm_reset_control_get_optional(&pdev->dev, "ahb");
+	if (IS_ERR(ss->reset)) {
+		if (PTR_ERR(ss->reset) == -EPROBE_DEFER)
+			return PTR_ERR(ss->reset);
+		dev_info(&pdev->dev, "no reset control found\n");
+		ss->reset = NULL;
+	}
+
+	/* Enable both clocks */
+	err = clk_prepare_enable(ss->busclk);
+	if (err != 0) {
+		dev_err(&pdev->dev, "Cannot prepare_enable busclk\n");
+		return err;
+	}
+	err = clk_prepare_enable(ss->ssclk);
+	if (err != 0) {
+		dev_err(&pdev->dev, "Cannot prepare_enable ssclk\n");
+		goto error_ssclk;
+	}
+
+	/*
+	 * Check that clock have the correct rates given in the datasheet
+	 * Try to set the clock to the maximum allowed
+	 */
+	err = clk_set_rate(ss->ssclk, cr_mod);
+	if (err != 0) {
+		dev_err(&pdev->dev, "Cannot set clock rate to ssclk\n");
+		goto error_clk;
+	}
+
+	/* Deassert reset if we have a reset control */
+	if (ss->reset) {
+		err = reset_control_deassert(ss->reset);
+		if (err) {
+			dev_err(&pdev->dev, "Cannot deassert reset control\n");
+			goto error_clk;
+		}
+	}
+
+	/*
+	 * The only impact on clocks below requirement are bad performance,
+	 * so do not print "errors"
+	 * warn on Overclocked clocks
+	 */
+	cr = clk_get_rate(ss->busclk);
+	if (cr >= cr_ahb)
+		dev_dbg(&pdev->dev, "Clock bus %lu (%lu MHz) (must be >= %lu)\n",
+			cr, cr / 1000000, cr_ahb);
+	else
+		dev_warn(&pdev->dev, "Clock bus %lu (%lu MHz) (must be >= %lu)\n",
+			 cr, cr / 1000000, cr_ahb);
+
+	cr = clk_get_rate(ss->ssclk);
+	if (cr <= cr_mod)
+		if (cr < cr_mod)
+			dev_warn(&pdev->dev, "Clock ss %lu (%lu MHz) (must be <= %lu)\n",
+				 cr, cr / 1000000, cr_mod);
+		else
+			dev_dbg(&pdev->dev, "Clock ss %lu (%lu MHz) (must be <= %lu)\n",
+				cr, cr / 1000000, cr_mod);
+	else
+		dev_warn(&pdev->dev, "Clock ss is at %lu (%lu MHz) (must be <= %lu)\n",
+			 cr, cr / 1000000, cr_mod);
+
+	/*
+	 * Datasheet named it "Die Bonding ID"
+	 * I expect to be a sort of Security System Revision number.
+	 * Since the A80 seems to have an other version of SS
+	 * this info could be useful
+	 */
+	writel(SS_ENABLED, ss->base + SS_CTL);
+	v = readl(ss->base + SS_CTL);
+	v >>= 16;
+	v &= 0x07;
+	dev_info(&pdev->dev, "Die ID %d\n", v);
+	writel(0, ss->base + SS_CTL);
+
+	ss->dev = &pdev->dev;
+
+	spin_lock_init(&ss->slock);
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		ss_algs[i].ss = ss;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_ABLKCIPHER:
+			err = crypto_register_alg(&ss_algs[i].alg.crypto);
+			if (err != 0) {
+				dev_err(ss->dev, "Fail to register %s\n",
+					ss_algs[i].alg.crypto.cra_name);
+				goto error_alg;
+			}
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			err = crypto_register_ahash(&ss_algs[i].alg.hash);
+			if (err != 0) {
+				dev_err(ss->dev, "Fail to register %s\n",
+					ss_algs[i].alg.hash.halg.base.cra_name);
+				goto error_alg;
+			}
+			break;
+		}
+	}
+	platform_set_drvdata(pdev, ss);
+	return 0;
+error_alg:
+	i--;
+	for (; i >= 0; i--) {
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_ABLKCIPHER:
+			crypto_unregister_alg(&ss_algs[i].alg.crypto);
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			crypto_unregister_ahash(&ss_algs[i].alg.hash);
+			break;
+		}
+	}
+	if (ss->reset)
+		reset_control_assert(ss->reset);
+error_clk:
+	clk_disable_unprepare(ss->ssclk);
+error_ssclk:
+	clk_disable_unprepare(ss->busclk);
+	return err;
+}
+
+static int sun4i_ss_remove(struct platform_device *pdev)
+{
+	int i;
+	struct sun4i_ss_ctx *ss = platform_get_drvdata(pdev);
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_ABLKCIPHER:
+			crypto_unregister_alg(&ss_algs[i].alg.crypto);
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			crypto_unregister_ahash(&ss_algs[i].alg.hash);
+			break;
+		}
+	}
+
+	writel(0, ss->base + SS_CTL);
+	if (ss->reset)
+		reset_control_assert(ss->reset);
+	clk_disable_unprepare(ss->busclk);
+	clk_disable_unprepare(ss->ssclk);
+	return 0;
+}
+
+static const struct of_device_id a20ss_crypto_of_match_table[] = {
+	{ .compatible = "allwinner,sun4i-a10-crypto" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, a20ss_crypto_of_match_table);
+
+static struct platform_driver sun4i_ss_driver = {
+	.probe          = sun4i_ss_probe,
+	.remove         = sun4i_ss_remove,
+	.driver         = {
+		.name           = "sun4i-ss",
+		.of_match_table	= a20ss_crypto_of_match_table,
+	},
+};
+
+module_platform_driver(sun4i_ss_driver);
+
+MODULE_DESCRIPTION("Allwinner Security System cryptographic accelerator");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Corentin LABBE <clabbe.montjoie@gmail.com>");
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
new file mode 100644
index 000000000000..ff8031498809
--- /dev/null
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
@@ -0,0 +1,492 @@
+/*
+ * sun4i-ss-hash.c - hardware cryptographic accelerator for Allwinner A20 SoC
+ *
+ * Copyright (C) 2013-2015 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * This file add support for MD5 and SHA1.
+ *
+ * You could find the datasheet in Documentation/arm/sunxi/README
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include "sun4i-ss.h"
+#include <linux/scatterlist.h>
+
+/* This is a totally arbitrary value */
+#define SS_TIMEOUT 100
+
+int sun4i_hash_crainit(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct sun4i_req_ctx));
+	return 0;
+}
+
+/* sun4i_hash_init: initialize request context */
+int sun4i_hash_init(struct ahash_request *areq)
+{
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct ahash_alg *alg = __crypto_ahash_alg(tfm->base.__crt_alg);
+	struct sun4i_ss_alg_template *algt;
+	struct sun4i_ss_ctx *ss;
+
+	memset(op, 0, sizeof(struct sun4i_req_ctx));
+
+	algt = container_of(alg, struct sun4i_ss_alg_template, alg.hash);
+	ss = algt->ss;
+	op->ss = algt->ss;
+	op->mode = algt->mode;
+
+	return 0;
+}
+
+int sun4i_hash_export_md5(struct ahash_request *areq, void *out)
+{
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	struct md5_state *octx = out;
+	int i;
+
+	octx->byte_count = op->byte_count + op->len;
+
+	memcpy(octx->block, op->buf, op->len);
+
+	if (op->byte_count > 0) {
+		for (i = 0; i < 4; i++)
+			octx->hash[i] = op->hash[i];
+	} else {
+		octx->hash[0] = SHA1_H0;
+		octx->hash[1] = SHA1_H1;
+		octx->hash[2] = SHA1_H2;
+		octx->hash[3] = SHA1_H3;
+	}
+
+	return 0;
+}
+
+int sun4i_hash_import_md5(struct ahash_request *areq, const void *in)
+{
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	const struct md5_state *ictx = in;
+	int i;
+
+	sun4i_hash_init(areq);
+
+	op->byte_count = ictx->byte_count & ~0x3F;
+	op->len = ictx->byte_count & 0x3F;
+
+	memcpy(op->buf, ictx->block, op->len);
+
+	for (i = 0; i < 4; i++)
+		op->hash[i] = ictx->hash[i];
+
+	return 0;
+}
+
+int sun4i_hash_export_sha1(struct ahash_request *areq, void *out)
+{
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	struct sha1_state *octx = out;
+	int i;
+
+	octx->count = op->byte_count + op->len;
+
+	memcpy(octx->buffer, op->buf, op->len);
+
+	if (op->byte_count > 0) {
+		for (i = 0; i < 5; i++)
+			octx->state[i] = op->hash[i];
+	} else {
+		octx->state[0] = SHA1_H0;
+		octx->state[1] = SHA1_H1;
+		octx->state[2] = SHA1_H2;
+		octx->state[3] = SHA1_H3;
+		octx->state[4] = SHA1_H4;
+	}
+
+	return 0;
+}
+
+int sun4i_hash_import_sha1(struct ahash_request *areq, const void *in)
+{
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	const struct sha1_state *ictx = in;
+	int i;
+
+	sun4i_hash_init(areq);
+
+	op->byte_count = ictx->count & ~0x3F;
+	op->len = ictx->count & 0x3F;
+
+	memcpy(op->buf, ictx->buffer, op->len);
+
+	for (i = 0; i < 5; i++)
+		op->hash[i] = ictx->state[i];
+
+	return 0;
+}
+
+/*
+ * sun4i_hash_update: update hash engine
+ *
+ * Could be used for both SHA1 and MD5
+ * Write data by step of 32bits and put then in the SS.
+ *
+ * Since we cannot leave partial data and hash state in the engine,
+ * we need to get the hash state at the end of this function.
+ * We can get the hash state every 64 bytes
+ *
+ * So the first work is to get the number of bytes to write to SS modulo 64
+ * The extra bytes will go to a temporary buffer op->buf storing op->len bytes
+ *
+ * So at the begin of update()
+ * if op->len + areq->nbytes < 64
+ * => all data will be written to wait buffer (op->buf) and end=0
+ * if not, write all data from op->buf to the device and position end to
+ * complete to 64bytes
+ *
+ * example 1:
+ * update1 60o => op->len=60
+ * update2 60o => need one more word to have 64 bytes
+ * end=4
+ * so write all data from op->buf and one word of SGs
+ * write remaining data in op->buf
+ * final state op->len=56
+ */
+int sun4i_hash_update(struct ahash_request *areq)
+{
+	u32 v, ivmode = 0;
+	unsigned int i = 0;
+	/*
+	 * i is the total bytes read from SGs, to be compared to areq->nbytes
+	 * i is important because we cannot rely on SG length since the sum of
+	 * SG->length could be greater than areq->nbytes
+	 */
+
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	struct sun4i_ss_ctx *ss = op->ss;
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	unsigned int in_i = 0; /* advancement in the current SG */
+	unsigned int end;
+	/*
+	 * end is the position when we need to stop writing to the device,
+	 * to be compared to i
+	 */
+	int in_r, err = 0;
+	unsigned int todo;
+	u32 spaces, rx_cnt = SS_RX_DEFAULT;
+	size_t copied = 0;
+	struct sg_mapping_iter mi;
+
+	dev_dbg(ss->dev, "%s %s bc=%llu len=%u mode=%x wl=%u h0=%0x",
+		__func__, crypto_tfm_alg_name(areq->base.tfm),
+		op->byte_count, areq->nbytes, op->mode,
+		op->len, op->hash[0]);
+
+	if (areq->nbytes == 0)
+		return 0;
+
+	/* protect against overflow */
+	if (areq->nbytes > UINT_MAX - op->len) {
+		dev_err(ss->dev, "Cannot process too large request\n");
+		return -EINVAL;
+	}
+
+	if (op->len + areq->nbytes < 64) {
+		/* linearize data to op->buf */
+		copied = sg_pcopy_to_buffer(areq->src, sg_nents(areq->src),
+					    op->buf + op->len, areq->nbytes, 0);
+		op->len += copied;
+		return 0;
+	}
+
+	end = ((areq->nbytes + op->len) / 64) * 64 - op->len;
+
+	if (end > areq->nbytes || areq->nbytes - end > 63) {
+		dev_err(ss->dev, "ERROR: Bound error %u %u\n",
+			end, areq->nbytes);
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&ss->slock);
+
+	/*
+	 * if some data have been processed before,
+	 * we need to restore the partial hash state
+	 */
+	if (op->byte_count > 0) {
+		ivmode = SS_IV_ARBITRARY;
+		for (i = 0; i < 5; i++)
+			writel(op->hash[i], ss->base + SS_IV0 + i * 4);
+	}
+	/* Enable the device */
+	writel(op->mode | SS_ENABLED | ivmode, ss->base + SS_CTL);
+
+	i = 0;
+	sg_miter_start(&mi, areq->src, sg_nents(areq->src),
+		       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+	sg_miter_next(&mi);
+	in_i = 0;
+
+	do {
+		/*
+		 * we need to linearize in two case:
+		 * - the buffer is already used
+		 * - the SG does not have enough byte remaining ( < 4)
+		 */
+		if (op->len > 0 || (mi.length - in_i) < 4) {
+			/*
+			 * if we have entered here we have two reason to stop
+			 * - the buffer is full
+			 * - reach the end
+			 */
+			while (op->len < 64 && i < end) {
+				/* how many bytes we can read from current SG */
+				in_r = min3(mi.length - in_i, end - i,
+					    64 - op->len);
+				memcpy(op->buf + op->len, mi.addr + in_i, in_r);
+				op->len += in_r;
+				i += in_r;
+				in_i += in_r;
+				if (in_i == mi.length) {
+					sg_miter_next(&mi);
+					in_i = 0;
+				}
+			}
+			if (op->len > 3 && (op->len % 4) == 0) {
+				/* write buf to the device */
+				writesl(ss->base + SS_RXFIFO, op->buf,
+					op->len / 4);
+				op->byte_count += op->len;
+				op->len = 0;
+			}
+		}
+		if (mi.length - in_i > 3 && i < end) {
+			/* how many bytes we can read from current SG */
+			in_r = min3(mi.length - in_i, areq->nbytes - i,
+				    ((mi.length - in_i) / 4) * 4);
+			/* how many bytes we can write in the device*/
+			todo = min3((u32)(end - i) / 4, rx_cnt, (u32)in_r / 4);
+			writesl(ss->base + SS_RXFIFO, mi.addr + in_i, todo);
+			op->byte_count += todo * 4;
+			i += todo * 4;
+			in_i += todo * 4;
+			rx_cnt -= todo;
+			if (rx_cnt == 0) {
+				spaces = readl(ss->base + SS_FCSR);
+				rx_cnt = SS_RXFIFO_SPACES(spaces);
+			}
+			if (in_i == mi.length) {
+				sg_miter_next(&mi);
+				in_i = 0;
+			}
+		}
+	} while (i < end);
+	/* final linear */
+	if ((areq->nbytes - i) < 64) {
+		while (i < areq->nbytes && in_i < mi.length && op->len < 64) {
+			/* how many bytes we can read from current SG */
+			in_r = min3(mi.length - in_i, areq->nbytes - i,
+				    64 - op->len);
+			memcpy(op->buf + op->len, mi.addr + in_i, in_r);
+			op->len += in_r;
+			i += in_r;
+			in_i += in_r;
+			if (in_i == mi.length) {
+				sg_miter_next(&mi);
+				in_i = 0;
+			}
+		}
+	}
+
+	sg_miter_stop(&mi);
+
+	writel(op->mode | SS_ENABLED | SS_DATA_END, ss->base + SS_CTL);
+	i = 0;
+	do {
+		v = readl(ss->base + SS_CTL);
+		i++;
+	} while (i < SS_TIMEOUT && (v & SS_DATA_END) > 0);
+	if (i >= SS_TIMEOUT) {
+		dev_err_ratelimited(ss->dev,
+				    "ERROR: hash end timeout %d>%d ctl=%x len=%u\n",
+				    i, SS_TIMEOUT, v, areq->nbytes);
+		err = -EIO;
+		goto release_ss;
+	}
+
+	/* get the partial hash only if something was written */
+	for (i = 0; i < crypto_ahash_digestsize(tfm) / 4; i++)
+		op->hash[i] = readl(ss->base + SS_MD0 + i * 4);
+
+release_ss:
+	writel(0, ss->base + SS_CTL);
+	spin_unlock_bh(&ss->slock);
+	return err;
+}
+
+/*
+ * sun4i_hash_final: finalize hashing operation
+ *
+ * If we have some remaining bytes, we write them.
+ * Then ask the SS for finalizing the hashing operation
+ *
+ * I do not check RX FIFO size in this function since the size is 32
+ * after each enabling and this function neither write more than 32 words.
+ */
+int sun4i_hash_final(struct ahash_request *areq)
+{
+	u32 v, ivmode = 0;
+	unsigned int i;
+	unsigned int j = 0;
+	int zeros, err = 0;
+	unsigned int index, padlen;
+	__be64 bits;
+	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
+	struct sun4i_ss_ctx *ss = op->ss;
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	u32 bf[32];
+	u32 wb = 0;
+	unsigned int nwait, nbw = 0;
+
+	dev_dbg(ss->dev, "%s: byte=%llu len=%u mode=%x wl=%u h=%x",
+		__func__, op->byte_count, areq->nbytes, op->mode,
+		op->len, op->hash[0]);
+
+	spin_lock_bh(&ss->slock);
+
+	/*
+	 * if we have already written something,
+	 * restore the partial hash state
+	 */
+	if (op->byte_count > 0) {
+		ivmode = SS_IV_ARBITRARY;
+		for (i = 0; i < crypto_ahash_digestsize(tfm) / 4; i++)
+			writel(op->hash[i], ss->base + SS_IV0 + i * 4);
+	}
+	writel(op->mode | SS_ENABLED | ivmode, ss->base + SS_CTL);
+
+	/* write the remaining words of the wait buffer */
+	if (op->len > 0) {
+		nwait = op->len / 4;
+		if (nwait > 0) {
+			writesl(ss->base + SS_RXFIFO, op->buf, nwait);
+			op->byte_count += 4 * nwait;
+		}
+		nbw = op->len - 4 * nwait;
+		wb = *(u32 *)(op->buf + nwait * 4);
+		wb &= (0xFFFFFFFF >> (4 - nbw) * 8);
+	}
+
+	/* write the remaining bytes of the nbw buffer */
+	if (nbw > 0) {
+		wb |= ((1 << 7) << (nbw * 8));
+		bf[j++] = wb;
+	} else {
+		bf[j++] = 1 << 7;
+	}
+
+	/*
+	 * number of space to pad to obtain 64o minus 8(size) minus 4 (final 1)
+	 * I take the operations from other MD5/SHA1 implementations
+	 */
+
+	/* we have already send 4 more byte of which nbw data */
+	if (op->mode == SS_OP_MD5) {
+		index = (op->byte_count + 4) & 0x3f;
+		op->byte_count += nbw;
+		if (index > 56)
+			zeros = (120 - index) / 4;
+		else
+			zeros = (56 - index) / 4;
+	} else {
+		op->byte_count += nbw;
+		index = op->byte_count & 0x3f;
+		padlen = (index < 56) ? (56 - index) : ((64 + 56) - index);
+		zeros = (padlen - 1) / 4;
+	}
+
+	memset(bf + j, 0, 4 * zeros);
+	j += zeros;
+
+	/* write the length of data */
+	if (op->mode == SS_OP_SHA1) {
+		bits = cpu_to_be64(op->byte_count << 3);
+		bf[j++] = bits & 0xffffffff;
+		bf[j++] = (bits >> 32) & 0xffffffff;
+	} else {
+		bf[j++] = (op->byte_count << 3) & 0xffffffff;
+		bf[j++] = (op->byte_count >> 29) & 0xffffffff;
+	}
+	writesl(ss->base + SS_RXFIFO, bf, j);
+
+	/* Tell the SS to stop the hashing */
+	writel(op->mode | SS_ENABLED | SS_DATA_END, ss->base + SS_CTL);
+
+	/*
+	 * Wait for SS to finish the hash.
+	 * The timeout could happen only in case of bad overcloking
+	 * or driver bug.
+	 */
+	i = 0;
+	do {
+		v = readl(ss->base + SS_CTL);
+		i++;
+	} while (i < SS_TIMEOUT && (v & SS_DATA_END) > 0);
+	if (i >= SS_TIMEOUT) {
+		dev_err_ratelimited(ss->dev,
+				    "ERROR: hash end timeout %d>%d ctl=%x len=%u\n",
+				    i, SS_TIMEOUT, v, areq->nbytes);
+		err = -EIO;
+		goto release_ss;
+	}
+
+	/* Get the hash from the device */
+	if (op->mode == SS_OP_SHA1) {
+		for (i = 0; i < 5; i++) {
+			v = cpu_to_be32(readl(ss->base + SS_MD0 + i * 4));
+			memcpy(areq->result + i * 4, &v, 4);
+		}
+	} else {
+		for (i = 0; i < 4; i++) {
+			v = readl(ss->base + SS_MD0 + i * 4);
+			memcpy(areq->result + i * 4, &v, 4);
+		}
+	}
+
+release_ss:
+	writel(0, ss->base + SS_CTL);
+	spin_unlock_bh(&ss->slock);
+	return err;
+}
+
+/* sun4i_hash_finup: finalize hashing operation after an update */
+int sun4i_hash_finup(struct ahash_request *areq)
+{
+	int err;
+
+	err = sun4i_hash_update(areq);
+	if (err != 0)
+		return err;
+
+	return sun4i_hash_final(areq);
+}
+
+/* combo of init/update/final functions */
+int sun4i_hash_digest(struct ahash_request *areq)
+{
+	int err;
+
+	err = sun4i_hash_init(areq);
+	if (err != 0)
+		return err;
+
+	err = sun4i_hash_update(areq);
+	if (err != 0)
+		return err;
+
+	return sun4i_hash_final(areq);
+}
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss.h b/drivers/crypto/sunxi-ss/sun4i-ss.h
new file mode 100644
index 000000000000..8e9c05f6e4d4
--- /dev/null
+++ b/drivers/crypto/sunxi-ss/sun4i-ss.h
@@ -0,0 +1,201 @@
+/*
+ * sun4i-ss.h - hardware cryptographic accelerator for Allwinner A20 SoC
+ *
+ * Copyright (C) 2013-2015 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * Support AES cipher with 128,192,256 bits keysize.
+ * Support MD5 and SHA1 hash algorithms.
+ * Support DES and 3DES
+ *
+ * You could find the datasheet in Documentation/arm/sunxi/README
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <crypto/scatterwalk.h>
+#include <linux/scatterlist.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <crypto/md5.h>
+#include <crypto/sha.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+#include <crypto/aes.h>
+#include <crypto/des.h>
+#include <crypto/internal/rng.h>
+
+#define SS_CTL            0x00
+#define SS_KEY0           0x04
+#define SS_KEY1           0x08
+#define SS_KEY2           0x0C
+#define SS_KEY3           0x10
+#define SS_KEY4           0x14
+#define SS_KEY5           0x18
+#define SS_KEY6           0x1C
+#define SS_KEY7           0x20
+
+#define SS_IV0            0x24
+#define SS_IV1            0x28
+#define SS_IV2            0x2C
+#define SS_IV3            0x30
+
+#define SS_FCSR           0x44
+
+#define SS_MD0            0x4C
+#define SS_MD1            0x50
+#define SS_MD2            0x54
+#define SS_MD3            0x58
+#define SS_MD4            0x5C
+
+#define SS_RXFIFO         0x200
+#define SS_TXFIFO         0x204
+
+/* SS_CTL configuration values */
+
+/* PRNG generator mode - bit 15 */
+#define SS_PRNG_ONESHOT		(0 << 15)
+#define SS_PRNG_CONTINUE	(1 << 15)
+
+/* IV mode for hash */
+#define SS_IV_ARBITRARY		(1 << 14)
+
+/* SS operation mode - bits 12-13 */
+#define SS_ECB			(0 << 12)
+#define SS_CBC			(1 << 12)
+#define SS_CTS			(3 << 12)
+
+/* Counter width for CNT mode - bits 10-11 */
+#define SS_CNT_16BITS		(0 << 10)
+#define SS_CNT_32BITS		(1 << 10)
+#define SS_CNT_64BITS		(2 << 10)
+
+/* Key size for AES - bits 8-9 */
+#define SS_AES_128BITS		(0 << 8)
+#define SS_AES_192BITS		(1 << 8)
+#define SS_AES_256BITS		(2 << 8)
+
+/* Operation direction - bit 7 */
+#define SS_ENCRYPTION		(0 << 7)
+#define SS_DECRYPTION		(1 << 7)
+
+/* SS Method - bits 4-6 */
+#define SS_OP_AES		(0 << 4)
+#define SS_OP_DES		(1 << 4)
+#define SS_OP_3DES		(2 << 4)
+#define SS_OP_SHA1		(3 << 4)
+#define SS_OP_MD5		(4 << 4)
+#define SS_OP_PRNG		(5 << 4)
+
+/* Data end bit - bit 2 */
+#define SS_DATA_END		(1 << 2)
+
+/* PRNG start bit - bit 1 */
+#define SS_PRNG_START		(1 << 1)
+
+/* SS Enable bit - bit 0 */
+#define SS_DISABLED		(0 << 0)
+#define SS_ENABLED		(1 << 0)
+
+/* SS_FCSR configuration values */
+/* RX FIFO status - bit 30 */
+#define SS_RXFIFO_FREE		(1 << 30)
+
+/* RX FIFO empty spaces - bits 24-29 */
+#define SS_RXFIFO_SPACES(val)	(((val) >> 24) & 0x3f)
+
+/* TX FIFO status - bit 22 */
+#define SS_TXFIFO_AVAILABLE	(1 << 22)
+
+/* TX FIFO available spaces - bits 16-21 */
+#define SS_TXFIFO_SPACES(val)	(((val) >> 16) & 0x3f)
+
+#define SS_RX_MAX	32
+#define SS_RX_DEFAULT	SS_RX_MAX
+#define SS_TX_MAX	33
+
+#define SS_RXFIFO_EMP_INT_PENDING	(1 << 10)
+#define SS_TXFIFO_AVA_INT_PENDING	(1 << 8)
+#define SS_RXFIFO_EMP_INT_ENABLE	(1 << 2)
+#define SS_TXFIFO_AVA_INT_ENABLE	(1 << 0)
+
+struct sun4i_ss_ctx {
+	void __iomem *base;
+	int irq;
+	struct clk *busclk;
+	struct clk *ssclk;
+	struct reset_control *reset;
+	struct device *dev;
+	struct resource *res;
+	spinlock_t slock; /* control the use of the device */
+};
+
+struct sun4i_ss_alg_template {
+	u32 type;
+	u32 mode;
+	union {
+		struct crypto_alg crypto;
+		struct ahash_alg hash;
+	} alg;
+	struct sun4i_ss_ctx *ss;
+};
+
+struct sun4i_tfm_ctx {
+	u32 key[AES_MAX_KEY_SIZE / 4];/* divided by sizeof(u32) */
+	u32 keylen;
+	u32 keymode;
+	struct sun4i_ss_ctx *ss;
+};
+
+struct sun4i_cipher_req_ctx {
+	u32 mode;
+};
+
+struct sun4i_req_ctx {
+	u32 mode;
+	u64 byte_count; /* number of bytes "uploaded" to the device */
+	u32 hash[5]; /* for storing SS_IVx register */
+	char buf[64];
+	unsigned int len;
+	struct sun4i_ss_ctx *ss;
+};
+
+int sun4i_hash_crainit(struct crypto_tfm *tfm);
+int sun4i_hash_init(struct ahash_request *areq);
+int sun4i_hash_update(struct ahash_request *areq);
+int sun4i_hash_final(struct ahash_request *areq);
+int sun4i_hash_finup(struct ahash_request *areq);
+int sun4i_hash_digest(struct ahash_request *areq);
+int sun4i_hash_export_md5(struct ahash_request *areq, void *out);
+int sun4i_hash_import_md5(struct ahash_request *areq, const void *in);
+int sun4i_hash_export_sha1(struct ahash_request *areq, void *out);
+int sun4i_hash_import_sha1(struct ahash_request *areq, const void *in);
+
+int sun4i_ss_cbc_aes_encrypt(struct ablkcipher_request *areq);
+int sun4i_ss_cbc_aes_decrypt(struct ablkcipher_request *areq);
+int sun4i_ss_ecb_aes_encrypt(struct ablkcipher_request *areq);
+int sun4i_ss_ecb_aes_decrypt(struct ablkcipher_request *areq);
+
+int sun4i_ss_cbc_des_encrypt(struct ablkcipher_request *areq);
+int sun4i_ss_cbc_des_decrypt(struct ablkcipher_request *areq);
+int sun4i_ss_ecb_des_encrypt(struct ablkcipher_request *areq);
+int sun4i_ss_ecb_des_decrypt(struct ablkcipher_request *areq);
+
+int sun4i_ss_cbc_des3_encrypt(struct ablkcipher_request *areq);
+int sun4i_ss_cbc_des3_decrypt(struct ablkcipher_request *areq);
+int sun4i_ss_ecb_des3_encrypt(struct ablkcipher_request *areq);
+int sun4i_ss_ecb_des3_decrypt(struct ablkcipher_request *areq);
+
+int sun4i_ss_cipher_init(struct crypto_tfm *tfm);
+int sun4i_ss_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int keylen);
+int sun4i_ss_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int keylen);
+int sun4i_ss_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			 unsigned int keylen);
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 83aca95a95bc..3b20a1bce703 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -766,6 +766,7 @@ static int talitos_rng_init(struct hwrng *rng)
 static int talitos_register_rng(struct device *dev)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
+	int err;
 
 	priv->rng.name		= dev_driver_string(dev),
 	priv->rng.init		= talitos_rng_init,
@@ -773,14 +774,22 @@ static int talitos_register_rng(struct device *dev)
 	priv->rng.data_read	= talitos_rng_data_read,
 	priv->rng.priv		= (unsigned long)dev;
 
-	return hwrng_register(&priv->rng);
+	err = hwrng_register(&priv->rng);
+	if (!err)
+		priv->rng_registered = true;
+
+	return err;
 }
 
 static void talitos_unregister_rng(struct device *dev)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 
+	if (!priv->rng_registered)
+		return;
+
 	hwrng_unregister(&priv->rng);
+	priv->rng_registered = false;
 }
 
 /*
@@ -799,7 +808,6 @@ struct talitos_ctx {
 	unsigned int keylen;
 	unsigned int enckeylen;
 	unsigned int authkeylen;
-	unsigned int authsize;
 };
 
 #define HASH_MAX_BLOCK_SIZE		SHA512_BLOCK_SIZE
@@ -819,16 +827,6 @@ struct talitos_ahash_req_ctx {
 	struct scatterlist *psrc;
 };
 
-static int aead_setauthsize(struct crypto_aead *authenc,
-			    unsigned int authsize)
-{
-	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
-
-	ctx->authsize = authsize;
-
-	return 0;
-}
-
 static int aead_setkey(struct crypto_aead *authenc,
 		       const u8 *key, unsigned int keylen)
 {
@@ -857,12 +855,11 @@ badkey:
 
 /*
  * talitos_edesc - s/w-extended descriptor
- * @assoc_nents: number of segments in associated data scatterlist
  * @src_nents: number of segments in input scatterlist
  * @dst_nents: number of segments in output scatterlist
- * @assoc_chained: whether assoc is chained or not
  * @src_chained: whether src is chained or not
  * @dst_chained: whether dst is chained or not
+ * @icv_ool: whether ICV is out-of-line
  * @iv_dma: dma address of iv for checking continuity and link table
  * @dma_len: length of dma mapped link_tbl space
  * @dma_link_tbl: bus physical address of link_tbl/buf
@@ -875,12 +872,11 @@ badkey:
  * of link_tbl data
  */
 struct talitos_edesc {
-	int assoc_nents;
 	int src_nents;
 	int dst_nents;
-	bool assoc_chained;
 	bool src_chained;
 	bool dst_chained;
+	bool icv_ool;
 	dma_addr_t iv_dma;
 	int dma_len;
 	dma_addr_t dma_link_tbl;
@@ -952,14 +948,6 @@ static void ipsec_esp_unmap(struct device *dev,
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[0], DMA_TO_DEVICE);
 
-	if (edesc->assoc_chained)
-		talitos_unmap_sg_chain(dev, areq->assoc, DMA_TO_DEVICE);
-	else if (areq->assoclen)
-		/* assoc_nents counts also for IV in non-contiguous cases */
-		dma_unmap_sg(dev, areq->assoc,
-			     edesc->assoc_nents ? edesc->assoc_nents - 1 : 1,
-			     DMA_TO_DEVICE);
-
 	talitos_sg_unmap(dev, edesc, areq->src, areq->dst);
 
 	if (edesc->dma_len)
@@ -976,7 +964,7 @@ static void ipsec_esp_encrypt_done(struct device *dev,
 {
 	struct aead_request *areq = context;
 	struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
+	unsigned int authsize = crypto_aead_authsize(authenc);
 	struct talitos_edesc *edesc;
 	struct scatterlist *sg;
 	void *icvdata;
@@ -986,13 +974,12 @@ static void ipsec_esp_encrypt_done(struct device *dev,
 	ipsec_esp_unmap(dev, edesc, areq);
 
 	/* copy the generated ICV to dst */
-	if (edesc->dst_nents) {
+	if (edesc->icv_ool) {
 		icvdata = &edesc->link_tbl[edesc->src_nents +
-					   edesc->dst_nents + 2 +
-					   edesc->assoc_nents];
+					   edesc->dst_nents + 2];
 		sg = sg_last(areq->dst, edesc->dst_nents);
-		memcpy((char *)sg_virt(sg) + sg->length - ctx->authsize,
-		       icvdata, ctx->authsize);
+		memcpy((char *)sg_virt(sg) + sg->length - authsize,
+		       icvdata, authsize);
 	}
 
 	kfree(edesc);
@@ -1006,10 +993,10 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev,
 {
 	struct aead_request *req = context;
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
-	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
+	unsigned int authsize = crypto_aead_authsize(authenc);
 	struct talitos_edesc *edesc;
 	struct scatterlist *sg;
-	void *icvdata;
+	char *oicv, *icv;
 
 	edesc = container_of(desc, struct talitos_edesc, desc);
 
@@ -1017,16 +1004,18 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev,
 
 	if (!err) {
 		/* auth check */
-		if (edesc->dma_len)
-			icvdata = &edesc->link_tbl[edesc->src_nents +
-						   edesc->dst_nents + 2 +
-						   edesc->assoc_nents];
-		else
-			icvdata = &edesc->link_tbl[0];
-
 		sg = sg_last(req->dst, edesc->dst_nents ? : 1);
-		err = memcmp(icvdata, (char *)sg_virt(sg) + sg->length -
-			     ctx->authsize, ctx->authsize) ? -EBADMSG : 0;
+		icv = (char *)sg_virt(sg) + sg->length - authsize;
+
+		if (edesc->dma_len) {
+			oicv = (char *)&edesc->link_tbl[edesc->src_nents +
+							edesc->dst_nents + 2];
+			if (edesc->icv_ool)
+				icv = oicv + authsize;
+		} else
+			oicv = (char *)&edesc->link_tbl[0];
+
+		err = memcmp(oicv, icv, authsize) ? -EBADMSG : 0;
 	}
 
 	kfree(edesc);
@@ -1059,53 +1048,69 @@ static void ipsec_esp_decrypt_hwauth_done(struct device *dev,
  * convert scatterlist to SEC h/w link table format
  * stop at cryptlen bytes
  */
-static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
-			   int cryptlen, struct talitos_ptr *link_tbl_ptr)
+static int sg_to_link_tbl_offset(struct scatterlist *sg, int sg_count,
+				 unsigned int offset, int cryptlen,
+				 struct talitos_ptr *link_tbl_ptr)
 {
 	int n_sg = sg_count;
+	int count = 0;
 
-	while (sg && n_sg--) {
-		to_talitos_ptr(link_tbl_ptr, sg_dma_address(sg), 0);
-		link_tbl_ptr->len = cpu_to_be16(sg_dma_len(sg));
-		link_tbl_ptr->j_extent = 0;
-		link_tbl_ptr++;
-		cryptlen -= sg_dma_len(sg);
-		sg = sg_next(sg);
-	}
+	while (cryptlen && sg && n_sg--) {
+		unsigned int len = sg_dma_len(sg);
+
+		if (offset >= len) {
+			offset -= len;
+			goto next;
+		}
+
+		len -= offset;
+
+		if (len > cryptlen)
+			len = cryptlen;
 
-	/* adjust (decrease) last one (or two) entry's len to cryptlen */
-	link_tbl_ptr--;
-	while (be16_to_cpu(link_tbl_ptr->len) <= (-cryptlen)) {
-		/* Empty this entry, and move to previous one */
-		cryptlen += be16_to_cpu(link_tbl_ptr->len);
-		link_tbl_ptr->len = 0;
-		sg_count--;
-		link_tbl_ptr--;
+		to_talitos_ptr(link_tbl_ptr + count,
+			       sg_dma_address(sg) + offset, 0);
+		link_tbl_ptr[count].len = cpu_to_be16(len);
+		link_tbl_ptr[count].j_extent = 0;
+		count++;
+		cryptlen -= len;
+		offset = 0;
+
+next:
+		sg = sg_next(sg);
 	}
-	link_tbl_ptr->len = cpu_to_be16(be16_to_cpu(link_tbl_ptr->len)
-					+ cryptlen);
 
 	/* tag end of link table */
-	link_tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
+	if (count > 0)
+		link_tbl_ptr[count - 1].j_extent = DESC_PTR_LNKTBL_RETURN;
 
-	return sg_count;
+	return count;
+}
+
+static inline int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
+				 int cryptlen,
+				 struct talitos_ptr *link_tbl_ptr)
+{
+	return sg_to_link_tbl_offset(sg, sg_count, 0, cryptlen,
+				     link_tbl_ptr);
 }
 
 /*
  * fill in and submit ipsec_esp descriptor
  */
 static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
-		     u64 seq, void (*callback) (struct device *dev,
-						struct talitos_desc *desc,
-						void *context, int error))
+		     void (*callback)(struct device *dev,
+				      struct talitos_desc *desc,
+				      void *context, int error))
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	unsigned int authsize = crypto_aead_authsize(aead);
 	struct talitos_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *dev = ctx->dev;
 	struct talitos_desc *desc = &edesc->desc;
 	unsigned int cryptlen = areq->cryptlen;
-	unsigned int authsize = ctx->authsize;
 	unsigned int ivsize = crypto_aead_ivsize(aead);
+	int tbl_off = 0;
 	int sg_count, ret;
 	int sg_link_tbl_len;
 
@@ -1113,36 +1118,27 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	map_single_talitos_ptr(dev, &desc->ptr[0], ctx->authkeylen, &ctx->key,
 			       DMA_TO_DEVICE);
 
+	sg_count = talitos_map_sg(dev, areq->src, edesc->src_nents ?: 1,
+				  (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
+							   : DMA_TO_DEVICE,
+				  edesc->src_chained);
+
 	/* hmac data */
-	desc->ptr[1].len = cpu_to_be16(areq->assoclen + ivsize);
-	if (edesc->assoc_nents) {
-		int tbl_off = edesc->src_nents + edesc->dst_nents + 2;
-		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
+	desc->ptr[1].len = cpu_to_be16(areq->assoclen);
+	if (sg_count > 1 &&
+	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0,
+					 areq->assoclen,
+					 &edesc->link_tbl[tbl_off])) > 1) {
+		tbl_off += ret;
 
 		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
 			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
 
-		/* assoc_nents - 1 entries for assoc, 1 for IV */
-		sg_count = sg_to_link_tbl(areq->assoc, edesc->assoc_nents - 1,
-					  areq->assoclen, tbl_ptr);
-
-		/* add IV to link table */
-		tbl_ptr += sg_count - 1;
-		tbl_ptr->j_extent = 0;
-		tbl_ptr++;
-		to_talitos_ptr(tbl_ptr, edesc->iv_dma, 0);
-		tbl_ptr->len = cpu_to_be16(ivsize);
-		tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
-
 		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
 	} else {
-		if (areq->assoclen)
-			to_talitos_ptr(&desc->ptr[1],
-				       sg_dma_address(areq->assoc), 0);
-		else
-			to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, 0);
+		to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0);
 		desc->ptr[1].j_extent = 0;
 	}
 
@@ -1150,8 +1146,6 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, 0);
 	desc->ptr[2].len = cpu_to_be16(ivsize);
 	desc->ptr[2].j_extent = 0;
-	/* Sync needed for the aead_givencrypt case */
-	dma_sync_single_for_device(dev, edesc->iv_dma, ivsize, DMA_TO_DEVICE);
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
@@ -1167,33 +1161,24 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	desc->ptr[4].len = cpu_to_be16(cryptlen);
 	desc->ptr[4].j_extent = authsize;
 
-	sg_count = talitos_map_sg(dev, areq->src, edesc->src_nents ? : 1,
-				  (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
-							   : DMA_TO_DEVICE,
-				  edesc->src_chained);
-
-	if (sg_count == 1) {
+	sg_link_tbl_len = cryptlen;
+	if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
+		sg_link_tbl_len += authsize;
+
+	if (sg_count > 1 &&
+	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen,
+					 sg_link_tbl_len,
+					 &edesc->link_tbl[tbl_off])) > 1) {
+		tbl_off += ret;
+		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
+		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
+					      tbl_off *
+					      sizeof(struct talitos_ptr), 0);
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len,
+					   DMA_BIDIRECTIONAL);
+	} else
 		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0);
-	} else {
-		sg_link_tbl_len = cryptlen;
-
-		if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
-			sg_link_tbl_len = cryptlen + authsize;
-
-		sg_count = sg_to_link_tbl(areq->src, sg_count, sg_link_tbl_len,
-					  &edesc->link_tbl[0]);
-		if (sg_count > 1) {
-			desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl, 0);
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		} else {
-			/* Only one segment now, so no link tbl needed */
-			to_talitos_ptr(&desc->ptr[4],
-				       sg_dma_address(areq->src), 0);
-		}
-	}
 
 	/* cipher out */
 	desc->ptr[5].len = cpu_to_be16(cryptlen);
@@ -1204,16 +1189,17 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					  edesc->dst_nents ? : 1,
 					  DMA_FROM_DEVICE, edesc->dst_chained);
 
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0);
-	} else {
-		int tbl_off = edesc->src_nents + 1;
+	edesc->icv_ool = false;
+
+	if (sg_count > 1 &&
+	    (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count,
+					      areq->assoclen, cryptlen,
+					      &edesc->link_tbl[tbl_off])) >
+	    1) {
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
 			       tbl_off * sizeof(struct talitos_ptr), 0);
-		sg_count = sg_to_link_tbl(areq->dst, sg_count, cryptlen,
-					  tbl_ptr);
 
 		/* Add an entry to the link table for ICV data */
 		tbl_ptr += sg_count - 1;
@@ -1224,13 +1210,16 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 		/* icv data follows link tables */
 		to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl +
-			       (tbl_off + edesc->dst_nents + 1 +
-				edesc->assoc_nents) *
-			       sizeof(struct talitos_ptr), 0);
+					(edesc->src_nents + edesc->dst_nents +
+					 2) * sizeof(struct talitos_ptr) +
+					authsize, 0);
 		desc->ptr[5].j_extent |= DESC_PTR_LNKTBL_JUMP;
 		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
-	}
+
+		edesc->icv_ool = true;
+	} else
+		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0);
 
 	/* iv out */
 	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
@@ -1268,7 +1257,6 @@ static int sg_count(struct scatterlist *sg_list, int nbytes, bool *chained)
  * allocate and map the extended descriptor
  */
 static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
-						 struct scatterlist *assoc,
 						 struct scatterlist *src,
 						 struct scatterlist *dst,
 						 u8 *iv,
@@ -1281,8 +1269,8 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 						 bool encrypt)
 {
 	struct talitos_edesc *edesc;
-	int assoc_nents = 0, src_nents, dst_nents, alloc_len, dma_len;
-	bool assoc_chained = false, src_chained = false, dst_chained = false;
+	int src_nents, dst_nents, alloc_len, dma_len;
+	bool src_chained = false, dst_chained = false;
 	dma_addr_t iv_dma = 0;
 	gfp_t flags = cryptoflags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		      GFP_ATOMIC;
@@ -1298,48 +1286,35 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	if (ivsize)
 		iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE);
 
-	if (assoclen) {
-		/*
-		 * Currently it is assumed that iv is provided whenever assoc
-		 * is.
-		 */
-		BUG_ON(!iv);
-
-		assoc_nents = sg_count(assoc, assoclen, &assoc_chained);
-		talitos_map_sg(dev, assoc, assoc_nents, DMA_TO_DEVICE,
-			       assoc_chained);
-		assoc_nents = (assoc_nents == 1) ? 0 : assoc_nents;
-
-		if (assoc_nents || sg_dma_address(assoc) + assoclen != iv_dma)
-			assoc_nents = assoc_nents ? assoc_nents + 1 : 2;
-	}
-
 	if (!dst || dst == src) {
-		src_nents = sg_count(src, cryptlen + authsize, &src_chained);
+		src_nents = sg_count(src, assoclen + cryptlen + authsize,
+				     &src_chained);
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_nents = dst ? src_nents : 0;
 	} else { /* dst && dst != src*/
-		src_nents = sg_count(src, cryptlen + (encrypt ? 0 : authsize),
+		src_nents = sg_count(src, assoclen + cryptlen +
+					  (encrypt ? 0 : authsize),
 				     &src_chained);
 		src_nents = (src_nents == 1) ? 0 : src_nents;
-		dst_nents = sg_count(dst, cryptlen + (encrypt ? authsize : 0),
+		dst_nents = sg_count(dst, assoclen + cryptlen +
+					  (encrypt ? authsize : 0),
 				     &dst_chained);
 		dst_nents = (dst_nents == 1) ? 0 : dst_nents;
 	}
 
 	/*
 	 * allocate space for base edesc plus the link tables,
-	 * allowing for two separate entries for ICV and generated ICV (+ 2),
-	 * and the ICV data itself
+	 * allowing for two separate entries for AD and generated ICV (+ 2),
+	 * and space for two sets of ICVs (stashed and generated)
 	 */
 	alloc_len = sizeof(struct talitos_edesc);
-	if (assoc_nents || src_nents || dst_nents) {
+	if (src_nents || dst_nents) {
 		if (is_sec1)
 			dma_len = (src_nents ? cryptlen : 0) +
 				  (dst_nents ? cryptlen : 0);
 		else
-			dma_len = (src_nents + dst_nents + 2 + assoc_nents) *
-				  sizeof(struct talitos_ptr) + authsize;
+			dma_len = (src_nents + dst_nents + 2) *
+				  sizeof(struct talitos_ptr) + authsize * 2;
 		alloc_len += dma_len;
 	} else {
 		dma_len = 0;
@@ -1348,13 +1323,6 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 
 	edesc = kmalloc(alloc_len, GFP_DMA | flags);
 	if (!edesc) {
-		if (assoc_chained)
-			talitos_unmap_sg_chain(dev, assoc, DMA_TO_DEVICE);
-		else if (assoclen)
-			dma_unmap_sg(dev, assoc,
-				     assoc_nents ? assoc_nents - 1 : 1,
-				     DMA_TO_DEVICE);
-
 		if (iv_dma)
 			dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE);
 
@@ -1362,10 +1330,8 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	edesc->assoc_nents = assoc_nents;
 	edesc->src_nents = src_nents;
 	edesc->dst_nents = dst_nents;
-	edesc->assoc_chained = assoc_chained;
 	edesc->src_chained = src_chained;
 	edesc->dst_chained = dst_chained;
 	edesc->iv_dma = iv_dma;
@@ -1382,12 +1348,13 @@ static struct talitos_edesc *aead_edesc_alloc(struct aead_request *areq, u8 *iv,
 					      int icv_stashing, bool encrypt)
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
+	unsigned int authsize = crypto_aead_authsize(authenc);
 	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
 	unsigned int ivsize = crypto_aead_ivsize(authenc);
 
-	return talitos_edesc_alloc(ctx->dev, areq->assoc, areq->src, areq->dst,
+	return talitos_edesc_alloc(ctx->dev, areq->src, areq->dst,
 				   iv, areq->assoclen, areq->cryptlen,
-				   ctx->authsize, ivsize, icv_stashing,
+				   authsize, ivsize, icv_stashing,
 				   areq->base.flags, encrypt);
 }
 
@@ -1405,14 +1372,14 @@ static int aead_encrypt(struct aead_request *req)
 	/* set encrypt */
 	edesc->desc.hdr = ctx->desc_hdr_template | DESC_HDR_MODE0_ENCRYPT;
 
-	return ipsec_esp(edesc, req, 0, ipsec_esp_encrypt_done);
+	return ipsec_esp(edesc, req, ipsec_esp_encrypt_done);
 }
 
 static int aead_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
+	unsigned int authsize = crypto_aead_authsize(authenc);
 	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
-	unsigned int authsize = ctx->authsize;
 	struct talitos_private *priv = dev_get_drvdata(ctx->dev);
 	struct talitos_edesc *edesc;
 	struct scatterlist *sg;
@@ -1437,7 +1404,7 @@ static int aead_decrypt(struct aead_request *req)
 		/* reset integrity check result bits */
 		edesc->desc.hdr_lo = 0;
 
-		return ipsec_esp(edesc, req, 0, ipsec_esp_decrypt_hwauth_done);
+		return ipsec_esp(edesc, req, ipsec_esp_decrypt_hwauth_done);
 	}
 
 	/* Have to check the ICV with software */
@@ -1445,40 +1412,16 @@ static int aead_decrypt(struct aead_request *req)
 
 	/* stash incoming ICV for later cmp with ICV generated by the h/w */
 	if (edesc->dma_len)
-		icvdata = &edesc->link_tbl[edesc->src_nents +
-					   edesc->dst_nents + 2 +
-					   edesc->assoc_nents];
+		icvdata = (char *)&edesc->link_tbl[edesc->src_nents +
+						   edesc->dst_nents + 2];
 	else
 		icvdata = &edesc->link_tbl[0];
 
 	sg = sg_last(req->src, edesc->src_nents ? : 1);
 
-	memcpy(icvdata, (char *)sg_virt(sg) + sg->length - ctx->authsize,
-	       ctx->authsize);
+	memcpy(icvdata, (char *)sg_virt(sg) + sg->length - authsize, authsize);
 
-	return ipsec_esp(edesc, req, 0, ipsec_esp_decrypt_swauth_done);
-}
-
-static int aead_givencrypt(struct aead_givcrypt_request *req)
-{
-	struct aead_request *areq = &req->areq;
-	struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
-	struct talitos_edesc *edesc;
-
-	/* allocate extended descriptor */
-	edesc = aead_edesc_alloc(areq, req->giv, 0, true);
-	if (IS_ERR(edesc))
-		return PTR_ERR(edesc);
-
-	/* set encrypt */
-	edesc->desc.hdr = ctx->desc_hdr_template | DESC_HDR_MODE0_ENCRYPT;
-
-	memcpy(req->giv, ctx->iv, crypto_aead_ivsize(authenc));
-	/* avoid consecutive packets going out with same IV */
-	*(__be64 *)req->giv ^= cpu_to_be64(req->seq);
-
-	return ipsec_esp(edesc, areq, req->seq, ipsec_esp_encrypt_done);
+	return ipsec_esp(edesc, req, ipsec_esp_decrypt_swauth_done);
 }
 
 static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
@@ -1710,7 +1653,7 @@ static struct talitos_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request *
 	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
 	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
 
-	return talitos_edesc_alloc(ctx->dev, NULL, areq->src, areq->dst,
+	return talitos_edesc_alloc(ctx->dev, areq->src, areq->dst,
 				   areq->info, 0, areq->nbytes, 0, ivsize, 0,
 				   areq->base.flags, encrypt);
 }
@@ -1895,7 +1838,7 @@ static struct talitos_edesc *ahash_edesc_alloc(struct ahash_request *areq,
 	struct talitos_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
 
-	return talitos_edesc_alloc(ctx->dev, NULL, req_ctx->psrc, NULL, NULL, 0,
+	return talitos_edesc_alloc(ctx->dev, req_ctx->psrc, NULL, NULL, 0,
 				   nbytes, 0, 0, 0, areq->base.flags, false);
 }
 
@@ -1986,7 +1929,7 @@ static int ahash_process_req(struct ahash_request *areq, unsigned int nbytes)
 		sg_init_table(req_ctx->bufsl, nsg);
 		sg_set_buf(req_ctx->bufsl, req_ctx->buf, req_ctx->nbuf);
 		if (nsg > 1)
-			scatterwalk_sg_chain(req_ctx->bufsl, 2, areq->src);
+			sg_chain(req_ctx->bufsl, 2, areq->src);
 		req_ctx->psrc = req_ctx->bufsl;
 	} else
 		req_ctx->psrc = areq->src;
@@ -2161,6 +2104,7 @@ struct talitos_alg_template {
 	union {
 		struct crypto_alg crypto;
 		struct ahash_alg hash;
+		struct aead_alg aead;
 	} alg;
 	__be32 desc_hdr_template;
 };
@@ -2168,15 +2112,16 @@ struct talitos_alg_template {
 static struct talitos_alg_template driver_algs[] = {
 	/* AEAD algorithms.  These use a single-pass ipsec_esp descriptor */
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha1),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha1-cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA1_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_AESU |
@@ -2187,15 +2132,17 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha1),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha1-cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA1_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2207,15 +2154,16 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
 	{       .type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha224),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha224-cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA224_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 				     DESC_HDR_SEL0_AESU |
@@ -2226,15 +2174,17 @@ static struct talitos_alg_template driver_algs[] = {
 				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha224),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha224-cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA224_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2246,15 +2196,16 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha256),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha256-cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA256_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_AESU |
@@ -2265,15 +2216,17 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha256),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha256-cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA256_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2285,15 +2238,16 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha384),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha384-cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA384_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_AESU |
@@ -2304,15 +2258,17 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEUB_SHA384_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha384),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha384-cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA384_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2324,15 +2280,16 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEUB_SHA384_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha512),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-sha512-cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = SHA512_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_AESU |
@@ -2343,15 +2300,17 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEUB_SHA512_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(sha512),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-sha512-cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = SHA512_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2363,15 +2322,16 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEUB_SHA512_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(md5),cbc(aes))",
-			.cra_driver_name = "authenc-hmac-md5-cbc-aes-talitos",
-			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = AES_BLOCK_SIZE,
-				.maxauthsize = MD5_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_AESU |
@@ -2382,15 +2342,16 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_MD5_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
-		.alg.crypto = {
-			.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
-			.cra_driver_name = "authenc-hmac-md5-cbc-3des-talitos",
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-			.cra_aead = {
-				.ivsize = DES3_EDE_BLOCK_SIZE,
-				.maxauthsize = MD5_DIGEST_SIZE,
-			}
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2658,15 +2619,9 @@ static int talitos_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static int talitos_cra_init_aead(struct crypto_tfm *tfm)
+static int talitos_cra_init_aead(struct crypto_aead *tfm)
 {
-	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	talitos_cra_init(tfm);
-
-	/* random first IV */
-	get_random_bytes(ctx->iv, TALITOS_MAX_IV_LENGTH);
-
+	talitos_cra_init(crypto_aead_tfm(tfm));
 	return 0;
 }
 
@@ -2713,9 +2668,9 @@ static int talitos_remove(struct platform_device *ofdev)
 	list_for_each_entry_safe(t_alg, n, &priv->alg_list, entry) {
 		switch (t_alg->algt.type) {
 		case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		case CRYPTO_ALG_TYPE_AEAD:
-			crypto_unregister_alg(&t_alg->algt.alg.crypto);
 			break;
+		case CRYPTO_ALG_TYPE_AEAD:
+			crypto_unregister_aead(&t_alg->algt.alg.aead);
 		case CRYPTO_ALG_TYPE_AHASH:
 			crypto_unregister_ahash(&t_alg->algt.alg.hash);
 			break;
@@ -2727,7 +2682,7 @@ static int talitos_remove(struct platform_device *ofdev)
 	if (hw_supports(dev, DESC_HDR_SEL0_RNG))
 		talitos_unregister_rng(dev);
 
-	for (i = 0; i < priv->num_channels; i++)
+	for (i = 0; priv->chan && i < priv->num_channels; i++)
 		kfree(priv->chan[i].fifo);
 
 	kfree(priv->chan);
@@ -2774,15 +2729,11 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		alg->cra_ablkcipher.geniv = "eseqiv";
 		break;
 	case CRYPTO_ALG_TYPE_AEAD:
-		alg = &t_alg->algt.alg.crypto;
-		alg->cra_init = talitos_cra_init_aead;
-		alg->cra_type = &crypto_aead_type;
-		alg->cra_aead.setkey = aead_setkey;
-		alg->cra_aead.setauthsize = aead_setauthsize;
-		alg->cra_aead.encrypt = aead_encrypt;
-		alg->cra_aead.decrypt = aead_decrypt;
-		alg->cra_aead.givencrypt = aead_givencrypt;
-		alg->cra_aead.geniv = "<built-in>";
+		alg = &t_alg->algt.alg.aead.base;
+		t_alg->algt.alg.aead.init = talitos_cra_init_aead;
+		t_alg->algt.alg.aead.setkey = aead_setkey;
+		t_alg->algt.alg.aead.encrypt = aead_encrypt;
+		t_alg->algt.alg.aead.decrypt = aead_decrypt;
 		break;
 	case CRYPTO_ALG_TYPE_AHASH:
 		alg = &t_alg->algt.alg.hash.halg.base;
@@ -3041,7 +2992,7 @@ static int talitos_probe(struct platform_device *ofdev)
 	for (i = 0; i < ARRAY_SIZE(driver_algs); i++) {
 		if (hw_supports(dev, driver_algs[i].desc_hdr_template)) {
 			struct talitos_crypto_alg *t_alg;
-			char *name = NULL;
+			struct crypto_alg *alg = NULL;
 
 			t_alg = talitos_alg_alloc(dev, &driver_algs[i]);
 			if (IS_ERR(t_alg)) {
@@ -3053,21 +3004,26 @@ static int talitos_probe(struct platform_device *ofdev)
 
 			switch (t_alg->algt.type) {
 			case CRYPTO_ALG_TYPE_ABLKCIPHER:
-			case CRYPTO_ALG_TYPE_AEAD:
 				err = crypto_register_alg(
 						&t_alg->algt.alg.crypto);
-				name = t_alg->algt.alg.crypto.cra_driver_name;
+				alg = &t_alg->algt.alg.crypto;
 				break;
+
+			case CRYPTO_ALG_TYPE_AEAD:
+				err = crypto_register_aead(
+					&t_alg->algt.alg.aead);
+				alg = &t_alg->algt.alg.aead.base;
+				break;
+
 			case CRYPTO_ALG_TYPE_AHASH:
 				err = crypto_register_ahash(
 						&t_alg->algt.alg.hash);
-				name =
-				 t_alg->algt.alg.hash.halg.base.cra_driver_name;
+				alg = &t_alg->algt.alg.hash.halg.base;
 				break;
 			}
 			if (err) {
 				dev_err(dev, "%s alg registration failed\n",
-					name);
+					alg->cra_driver_name);
 				kfree(t_alg);
 			} else
 				list_add_tail(&t_alg->entry, &priv->alg_list);
diff --git a/drivers/crypto/talitos.h b/drivers/crypto/talitos.h
index 314daf55e7f7..0090f3211d68 100644
--- a/drivers/crypto/talitos.h
+++ b/drivers/crypto/talitos.h
@@ -52,12 +52,7 @@ struct talitos_ptr {
 	__be32 ptr;     /* address */
 };
 
-static const struct talitos_ptr zero_entry = {
-	.len = 0,
-	.j_extent = 0,
-	.eptr = 0,
-	.ptr = 0
-};
+static const struct talitos_ptr zero_entry;
 
 /* descriptor */
 struct talitos_desc {
@@ -154,6 +149,7 @@ struct talitos_private {
 
 	/* hwrng device */
 	struct hwrng rng;
+	bool rng_registered;
 };
 
 extern int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index e79e567e43aa..263af709e536 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -84,6 +84,7 @@ static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
 	preempt_disable();
 	pagefault_disable();
 	enable_kernel_altivec();
+	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
 	pagefault_enable();
@@ -103,6 +104,7 @@ static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 		preempt_disable();
 		pagefault_disable();
 		enable_kernel_altivec();
+		enable_kernel_vsx();
 		aes_p8_encrypt(src, dst, &ctx->enc_key);
 		pagefault_enable();
 		preempt_enable();
@@ -119,6 +121,7 @@ static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 		preempt_disable();
 		pagefault_disable();
 		enable_kernel_altivec();
+		enable_kernel_vsx();
 		aes_p8_decrypt(src, dst, &ctx->dec_key);
 		pagefault_enable();
 		preempt_enable();
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 7299995c78ec..0b8fe2ec5315 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -85,6 +85,7 @@ static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
 	preempt_disable();
 	pagefault_disable();
 	enable_kernel_altivec();
+	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
 	pagefault_enable();
@@ -115,6 +116,7 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
 		preempt_disable();
 		pagefault_disable();
 		enable_kernel_altivec();
+		enable_kernel_vsx();
 
 		blkcipher_walk_init(&walk, dst, src, nbytes);
 		ret = blkcipher_walk_virt(desc, &walk);
@@ -155,6 +157,7 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
 		preempt_disable();
 		pagefault_disable();
 		enable_kernel_altivec();
+		enable_kernel_vsx();
 
 		blkcipher_walk_init(&walk, dst, src, nbytes);
 		ret = blkcipher_walk_virt(desc, &walk);
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 7adae42a7b79..ee1306cd8f59 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -82,6 +82,7 @@ static int p8_aes_ctr_setkey(struct crypto_tfm *tfm, const u8 *key,
 
 	pagefault_disable();
 	enable_kernel_altivec();
+	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	pagefault_enable();
 
@@ -100,6 +101,7 @@ static void p8_aes_ctr_final(struct p8_aes_ctr_ctx *ctx,
 
 	pagefault_disable();
 	enable_kernel_altivec();
+	enable_kernel_vsx();
 	aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
 	pagefault_enable();
 
@@ -113,6 +115,7 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
 			    struct scatterlist *src, unsigned int nbytes)
 {
 	int ret;
+	u64 inc;
 	struct blkcipher_walk walk;
 	struct p8_aes_ctr_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
@@ -131,6 +134,7 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
 		while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
 			pagefault_disable();
 			enable_kernel_altivec();
+			enable_kernel_vsx();
 			aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr,
 						    walk.dst.virt.addr,
 						    (nbytes &
@@ -140,7 +144,12 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
 						    walk.iv);
 			pagefault_enable();
 
-			crypto_inc(walk.iv, AES_BLOCK_SIZE);
+			/* We need to update IV mostly for last bytes/round */
+			inc = (nbytes & AES_BLOCK_MASK) / AES_BLOCK_SIZE;
+			if (inc > 0)
+				while (inc--)
+					crypto_inc(walk.iv, AES_BLOCK_SIZE);
+
 			nbytes &= AES_BLOCK_SIZE - 1;
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
 		}
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index 6c5c20c6108e..228053921b3f 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1437,28 +1437,28 @@ Load_ctr32_enc_key:
 	?vperm		v31,v31,$out0,$keyperm
 	lvx		v25,$x10,$key_		# pre-load round[2]
 
-	vadduwm		$two,$one,$one
+	vadduqm		$two,$one,$one
 	subi		$inp,$inp,15		# undo "caller"
 	$SHL		$len,$len,4
 
-	vadduwm		$out1,$ivec,$one	# counter values ...
-	vadduwm		$out2,$ivec,$two
+	vadduqm		$out1,$ivec,$one	# counter values ...
+	vadduqm		$out2,$ivec,$two
 	vxor		$out0,$ivec,$rndkey0	# ... xored with rndkey[0]
 	 le?li		$idx,8
-	vadduwm		$out3,$out1,$two
+	vadduqm		$out3,$out1,$two
 	vxor		$out1,$out1,$rndkey0
 	 le?lvsl	$inpperm,0,$idx
-	vadduwm		$out4,$out2,$two
+	vadduqm		$out4,$out2,$two
 	vxor		$out2,$out2,$rndkey0
 	 le?vspltisb	$tmp,0x0f
-	vadduwm		$out5,$out3,$two
+	vadduqm		$out5,$out3,$two
 	vxor		$out3,$out3,$rndkey0
 	 le?vxor	$inpperm,$inpperm,$tmp	# transform for lvx_u/stvx_u
-	vadduwm		$out6,$out4,$two
+	vadduqm		$out6,$out4,$two
 	vxor		$out4,$out4,$rndkey0
-	vadduwm		$out7,$out5,$two
+	vadduqm		$out7,$out5,$two
 	vxor		$out5,$out5,$rndkey0
-	vadduwm		$ivec,$out6,$two	# next counter value
+	vadduqm		$ivec,$out6,$two	# next counter value
 	vxor		$out6,$out6,$rndkey0
 	vxor		$out7,$out7,$rndkey0
 
@@ -1594,27 +1594,27 @@ Loop_ctr32_enc8x_middle:
 
 	vcipherlast	$in0,$out0,$in0
 	vcipherlast	$in1,$out1,$in1
-	 vadduwm	$out1,$ivec,$one	# counter values ...
+	 vadduqm	$out1,$ivec,$one	# counter values ...
 	vcipherlast	$in2,$out2,$in2
-	 vadduwm	$out2,$ivec,$two
+	 vadduqm	$out2,$ivec,$two
 	 vxor		$out0,$ivec,$rndkey0	# ... xored with rndkey[0]
 	vcipherlast	$in3,$out3,$in3
-	 vadduwm	$out3,$out1,$two
+	 vadduqm	$out3,$out1,$two
 	 vxor		$out1,$out1,$rndkey0
 	vcipherlast	$in4,$out4,$in4
-	 vadduwm	$out4,$out2,$two
+	 vadduqm	$out4,$out2,$two
 	 vxor		$out2,$out2,$rndkey0
 	vcipherlast	$in5,$out5,$in5
-	 vadduwm	$out5,$out3,$two
+	 vadduqm	$out5,$out3,$two
 	 vxor		$out3,$out3,$rndkey0
 	vcipherlast	$in6,$out6,$in6
-	 vadduwm	$out6,$out4,$two
+	 vadduqm	$out6,$out4,$two
 	 vxor		$out4,$out4,$rndkey0
 	vcipherlast	$in7,$out7,$in7
-	 vadduwm	$out7,$out5,$two
+	 vadduqm	$out7,$out5,$two
 	 vxor		$out5,$out5,$rndkey0
 	le?vperm	$in0,$in0,$in0,$inpperm
-	 vadduwm	$ivec,$out6,$two	# next counter value
+	 vadduqm	$ivec,$out6,$two	# next counter value
 	 vxor		$out6,$out6,$rndkey0
 	le?vperm	$in1,$in1,$in1,$inpperm
 	 vxor		$out7,$out7,$rndkey0
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index b5e29002b666..2183a2e77641 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -119,6 +119,7 @@ static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
 	preempt_disable();
 	pagefault_disable();
 	enable_kernel_altivec();
+	enable_kernel_vsx();
 	enable_kernel_fp();
 	gcm_init_p8(ctx->htable, (const u64 *) key);
 	pagefault_enable();
@@ -149,6 +150,7 @@ static int p8_ghash_update(struct shash_desc *desc,
 			preempt_disable();
 			pagefault_disable();
 			enable_kernel_altivec();
+			enable_kernel_vsx();
 			enable_kernel_fp();
 			gcm_ghash_p8(dctx->shash, ctx->htable,
 				     dctx->buffer, GHASH_DIGEST_SIZE);
@@ -163,6 +165,7 @@ static int p8_ghash_update(struct shash_desc *desc,
 			preempt_disable();
 			pagefault_disable();
 			enable_kernel_altivec();
+			enable_kernel_vsx();
 			enable_kernel_fp();
 			gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
 			pagefault_enable();
@@ -193,6 +196,7 @@ static int p8_ghash_final(struct shash_desc *desc, u8 *out)
 			preempt_disable();
 			pagefault_disable();
 			enable_kernel_altivec();
+			enable_kernel_vsx();
 			enable_kernel_fp();
 			gcm_ghash_p8(dctx->shash, ctx->htable,
 				     dctx->buffer, GHASH_DIGEST_SIZE);
diff --git a/drivers/crypto/vmx/ghashp8-ppc.pl b/drivers/crypto/vmx/ghashp8-ppc.pl
index 0a6f899839dd..d8429cb71f02 100644
--- a/drivers/crypto/vmx/ghashp8-ppc.pl
+++ b/drivers/crypto/vmx/ghashp8-ppc.pl
@@ -61,6 +61,12 @@ $code=<<___;
 	mtspr		256,r0
 	li		r10,0x30
 	lvx_u		$H,0,r4			# load H
+	le?xor		r7,r7,r7
+	le?addi		r7,r7,0x8		# need a vperm start with 08
+	le?lvsr		5,0,r7
+	le?vspltisb	6,0x0f
+	le?vxor		5,5,6			# set a b-endian mask
+	le?vperm	$H,$H,$H,5
 
 	vspltisb	$xC2,-16		# 0xf0
 	vspltisb	$t0,1			# one
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index a59188494af8..b9997335f193 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -169,6 +169,7 @@ my $vpmsumd	= sub { vcrypto_op(@_, 1224); };
 my $vpmsubh	= sub { vcrypto_op(@_, 1096); };
 my $vpmsumw	= sub { vcrypto_op(@_, 1160); };
 my $vaddudm	= sub { vcrypto_op(@_, 192);  };
+my $vadduqm	= sub { vcrypto_op(@_, 256);  };
 
 my $mtsle	= sub {
     my ($f, $arg) = @_;
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 7d99d13bacd8..f9901f52a225 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -1,7 +1,7 @@
 /*
  * exynos_ppmu.c - EXYNOS PPMU (Platform Performance Monitoring Unit) support
  *
- * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2014-2015 Samsung Electronics Co., Ltd.
  * Author : Chanwoo Choi <cw00.choi@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -82,6 +82,15 @@ struct __exynos_ppmu_events {
 	PPMU_EVENT(mscl),
 	PPMU_EVENT(fimd0x),
 	PPMU_EVENT(fimd1x),
+
+	/* Only for Exynos5433 SoCs */
+	PPMU_EVENT(d0-cpu),
+	PPMU_EVENT(d0-general),
+	PPMU_EVENT(d0-rt),
+	PPMU_EVENT(d1-cpu),
+	PPMU_EVENT(d1-general),
+	PPMU_EVENT(d1-rt),
+
 	{ /* sentinel */ },
 };
 
@@ -96,6 +105,9 @@ static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev)
 	return -EINVAL;
 }
 
+/*
+ * The devfreq-event ops structure for PPMU v1.1
+ */
 static int exynos_ppmu_disable(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
@@ -200,10 +212,158 @@ static const struct devfreq_event_ops exynos_ppmu_ops = {
 	.get_event = exynos_ppmu_get_event,
 };
 
+/*
+ * The devfreq-event ops structure for PPMU v2.0
+ */
+static int exynos_ppmu_v2_disable(struct devfreq_event_dev *edev)
+{
+	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	u32 pmnc, clear;
+
+	/* Disable all counters */
+	clear = (PPMU_CCNT_MASK | PPMU_PMCNT0_MASK | PPMU_PMCNT1_MASK
+		| PPMU_PMCNT2_MASK | PPMU_PMCNT3_MASK);
+
+	__raw_writel(clear, info->ppmu.base + PPMU_V2_FLAG);
+	__raw_writel(clear, info->ppmu.base + PPMU_V2_INTENC);
+	__raw_writel(clear, info->ppmu.base + PPMU_V2_CNTENC);
+	__raw_writel(clear, info->ppmu.base + PPMU_V2_CNT_RESET);
+
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG0);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG1);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG2);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_RESULT);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CNT_AUTO);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV0_TYPE);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV1_TYPE);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV2_TYPE);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV3_TYPE);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_ID_V);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_ID_A);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_OTHERS_V);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_OTHERS_A);
+	__raw_writel(0x0, info->ppmu.base + PPMU_V2_INTERRUPT_RESET);
+
+	/* Disable PPMU */
+	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
+	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+
+	return 0;
+}
+
+static int exynos_ppmu_v2_set_event(struct devfreq_event_dev *edev)
+{
+	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int id = exynos_ppmu_find_ppmu_id(edev);
+	u32 pmnc, cntens;
+
+	/* Enable all counters */
+	cntens = __raw_readl(info->ppmu.base + PPMU_V2_CNTENS);
+	cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
+	__raw_writel(cntens, info->ppmu.base + PPMU_V2_CNTENS);
+
+	/* Set the event of Read/Write data count  */
+	switch (id) {
+	case PPMU_PMNCNT0:
+	case PPMU_PMNCNT1:
+	case PPMU_PMNCNT2:
+		__raw_writel(PPMU_V2_RO_DATA_CNT | PPMU_V2_WO_DATA_CNT,
+				info->ppmu.base + PPMU_V2_CH_EVx_TYPE(id));
+		break;
+	case PPMU_PMNCNT3:
+		__raw_writel(PPMU_V2_EVT3_RW_DATA_CNT,
+				info->ppmu.base + PPMU_V2_CH_EVx_TYPE(id));
+		break;
+	}
+
+	/* Reset cycle counter/performance counter and enable PPMU */
+	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	pmnc &= ~(PPMU_PMNC_ENABLE_MASK
+			| PPMU_PMNC_COUNTER_RESET_MASK
+			| PPMU_PMNC_CC_RESET_MASK
+			| PPMU_PMNC_CC_DIVIDER_MASK
+			| PPMU_V2_PMNC_START_MODE_MASK);
+	pmnc |= (PPMU_ENABLE << PPMU_PMNC_ENABLE_SHIFT);
+	pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT);
+	pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT);
+	pmnc |= (PPMU_V2_MODE_MANUAL << PPMU_V2_PMNC_START_MODE_SHIFT);
+	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+
+	return 0;
+}
+
+static int exynos_ppmu_v2_get_event(struct devfreq_event_dev *edev,
+				    struct devfreq_event_data *edata)
+{
+	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int id = exynos_ppmu_find_ppmu_id(edev);
+	u32 pmnc, cntenc;
+	u32 pmcnt_high, pmcnt_low;
+	u64 load_count = 0;
+
+	/* Disable PPMU */
+	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
+	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+
+	/* Read cycle count and performance count */
+	edata->total_count = __raw_readl(info->ppmu.base + PPMU_V2_CCNT);
+
+	switch (id) {
+	case PPMU_PMNCNT0:
+	case PPMU_PMNCNT1:
+	case PPMU_PMNCNT2:
+		load_count = __raw_readl(info->ppmu.base + PPMU_V2_PMNCT(id));
+		break;
+	case PPMU_PMNCNT3:
+		pmcnt_high = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_HIGH);
+		pmcnt_low = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_LOW);
+		load_count = (u64)((pmcnt_high & 0xff) << 32) + (u64)pmcnt_low;
+		break;
+	}
+	edata->load_count = load_count;
+
+	/* Disable all counters */
+	cntenc = __raw_readl(info->ppmu.base + PPMU_V2_CNTENC);
+	cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
+	__raw_writel(cntenc, info->ppmu.base + PPMU_V2_CNTENC);
+
+	dev_dbg(&edev->dev, "%25s (load: %ld / %ld)\n", edev->desc->name,
+					edata->load_count, edata->total_count);
+	return 0;
+}
+
+static const struct devfreq_event_ops exynos_ppmu_v2_ops = {
+	.disable = exynos_ppmu_v2_disable,
+	.set_event = exynos_ppmu_v2_set_event,
+	.get_event = exynos_ppmu_v2_get_event,
+};
+
+static const struct of_device_id exynos_ppmu_id_match[] = {
+	{
+		.compatible = "samsung,exynos-ppmu",
+		.data = (void *)&exynos_ppmu_ops,
+	}, {
+		.compatible = "samsung,exynos-ppmu-v2",
+		.data = (void *)&exynos_ppmu_v2_ops,
+	},
+	{ /* sentinel */ },
+};
+
+static struct devfreq_event_ops *exynos_bus_get_ops(struct device_node *np)
+{
+	const struct of_device_id *match;
+
+	match = of_match_node(exynos_ppmu_id_match, np);
+	return (struct devfreq_event_ops *)match->data;
+}
+
 static int of_get_devfreq_events(struct device_node *np,
 				 struct exynos_ppmu *info)
 {
 	struct devfreq_event_desc *desc;
+	struct devfreq_event_ops *event_ops;
 	struct device *dev = info->dev;
 	struct device_node *events_np, *node;
 	int i, j, count;
@@ -214,6 +374,7 @@ static int of_get_devfreq_events(struct device_node *np,
 			"failed to get child node of devfreq-event devices\n");
 		return -EINVAL;
 	}
+	event_ops = exynos_bus_get_ops(np);
 
 	count = of_get_child_count(events_np);
 	desc = devm_kzalloc(dev, sizeof(*desc) * count, GFP_KERNEL);
@@ -238,7 +399,7 @@ static int of_get_devfreq_events(struct device_node *np,
 			continue;
 		}
 
-		desc[j].ops = &exynos_ppmu_ops;
+		desc[j].ops = event_ops;
 		desc[j].driver_data = info;
 
 		of_property_read_string(node, "event-name", &desc[j].name);
@@ -354,11 +515,6 @@ static int exynos_ppmu_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id exynos_ppmu_id_match[] = {
-	{ .compatible = "samsung,exynos-ppmu", },
-	{ /* sentinel */ },
-};
-
 static struct platform_driver exynos_ppmu_driver = {
 	.probe	= exynos_ppmu_probe,
 	.remove	= exynos_ppmu_remove,
diff --git a/drivers/devfreq/event/exynos-ppmu.h b/drivers/devfreq/event/exynos-ppmu.h
index 4e831d48c138..05774c449137 100644
--- a/drivers/devfreq/event/exynos-ppmu.h
+++ b/drivers/devfreq/event/exynos-ppmu.h
@@ -26,6 +26,9 @@ enum ppmu_counter {
 	PPMU_PMNCNT_MAX,
 };
 
+/***
+ * PPMUv1.1 Definitions
+ */
 enum ppmu_event_type {
 	PPMU_RO_BUSY_CYCLE_CNT	= 0x0,
 	PPMU_WO_BUSY_CYCLE_CNT	= 0x1,
@@ -90,4 +93,71 @@ enum ppmu_reg {
 #define PPMU_PMNCT(x)			(PPMU_PMCNT0 + (0x10 * x))
 #define PPMU_BEVTxSEL(x)		(PPMU_BEVT0SEL + (0x100 * x))
 
+/***
+ * PPMU_V2.0 definitions
+ */
+enum ppmu_v2_mode {
+	PPMU_V2_MODE_MANUAL = 0,
+	PPMU_V2_MODE_AUTO = 1,
+	PPMU_V2_MODE_CIG = 2,	/* CIG (Conditional Interrupt Generation) */
+};
+
+enum ppmu_v2_event_type {
+	PPMU_V2_RO_DATA_CNT	= 0x4,
+	PPMU_V2_WO_DATA_CNT	= 0x5,
+
+	PPMU_V2_EVT3_RW_DATA_CNT = 0x22,	/* Only for Event3 */
+};
+
+enum ppmu_V2_reg {
+	/* PPC control register */
+	PPMU_V2_PMNC		= 0x04,
+	PPMU_V2_CNTENS		= 0x08,
+	PPMU_V2_CNTENC		= 0x0c,
+	PPMU_V2_INTENS		= 0x10,
+	PPMU_V2_INTENC		= 0x14,
+	PPMU_V2_FLAG		= 0x18,
+
+	/* Cycle Counter and Performance Event Counter Register */
+	PPMU_V2_CCNT		= 0x48,
+	PPMU_V2_PMCNT0		= 0x34,
+	PPMU_V2_PMCNT1		= 0x38,
+	PPMU_V2_PMCNT2		= 0x3c,
+	PPMU_V2_PMCNT3_LOW	= 0x40,
+	PPMU_V2_PMCNT3_HIGH	= 0x44,
+
+	/* Bus Event Generator */
+	PPMU_V2_CIG_CFG0		= 0x1c,
+	PPMU_V2_CIG_CFG1		= 0x20,
+	PPMU_V2_CIG_CFG2		= 0x24,
+	PPMU_V2_CIG_RESULT	= 0x28,
+	PPMU_V2_CNT_RESET	= 0x2c,
+	PPMU_V2_CNT_AUTO		= 0x30,
+	PPMU_V2_CH_EV0_TYPE	= 0x200,
+	PPMU_V2_CH_EV1_TYPE	= 0x204,
+	PPMU_V2_CH_EV2_TYPE	= 0x208,
+	PPMU_V2_CH_EV3_TYPE	= 0x20c,
+	PPMU_V2_SM_ID_V		= 0x220,
+	PPMU_V2_SM_ID_A		= 0x224,
+	PPMU_V2_SM_OTHERS_V	= 0x228,
+	PPMU_V2_SM_OTHERS_A	= 0x22c,
+	PPMU_V2_INTERRUPT_RESET	= 0x260,
+};
+
+/* PMNC register */
+#define PPMU_V2_PMNC_START_MODE_SHIFT	20
+#define PPMU_V2_PMNC_START_MODE_MASK	(0x3 << PPMU_V2_PMNC_START_MODE_SHIFT)
+
+#define PPMU_PMNC_CC_RESET_SHIFT	2
+#define PPMU_PMNC_COUNTER_RESET_SHIFT	1
+#define PPMU_PMNC_ENABLE_SHIFT		0
+#define PPMU_PMNC_START_MODE_MASK	BIT(16)
+#define PPMU_PMNC_CC_DIVIDER_MASK	BIT(3)
+#define PPMU_PMNC_CC_RESET_MASK		BIT(2)
+#define PPMU_PMNC_COUNTER_RESET_MASK	BIT(1)
+#define PPMU_PMNC_ENABLE_MASK		BIT(0)
+
+#define PPMU_V2_PMNCT(x)		(PPMU_V2_PMCNT0 + (0x4 * x))
+#define PPMU_V2_CH_EVx_TYPE(x)		(PPMU_V2_CH_EV0_TYPE + (0x4 * x))
+
 #endif /* __EXYNOS_PPMU_H__ */
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 88d474b78076..b4584757dae0 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -33,27 +33,29 @@ if DMADEVICES
 
 comment "DMA Devices"
 
-config INTEL_MIC_X100_DMA
-	tristate "Intel MIC X100 DMA Driver"
-	depends on 64BIT && X86 && INTEL_MIC_BUS
-	select DMA_ENGINE
-	help
-	  This enables DMA support for the Intel Many Integrated Core
-	  (MIC) family of PCIe form factor coprocessor X100 devices that
-	  run a 64 bit Linux OS. This driver will be used by both MIC
-	  host and card drivers.
-
-	  If you are building host kernel with a MIC device or a card
-	  kernel for a MIC device, then say M (recommended) or Y, else
-	  say N. If unsure say N.
+#core
+config ASYNC_TX_ENABLE_CHANNEL_SWITCH
+	bool
 
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
+config ARCH_HAS_ASYNC_TX_FIND_CHANNEL
+	bool
 
-config ASYNC_TX_ENABLE_CHANNEL_SWITCH
+config DMA_ENGINE
 	bool
 
+config DMA_VIRTUAL_CHANNELS
+	tristate
+
+config DMA_ACPI
+	def_bool y
+	depends on ACPI
+
+config DMA_OF
+	def_bool y
+	depends on OF
+	select DMA_ENGINE
+
+#devices
 config AMBA_PL08X
 	bool "ARM PrimeCell PL080 or PL081 support"
 	depends on ARM_AMBA
@@ -63,29 +65,15 @@ config AMBA_PL08X
 	  Platform has a PL08x DMAC device
 	  which can provide DMA engine support
 
-config INTEL_IOATDMA
-	tristate "Intel I/OAT DMA support"
-	depends on PCI && X86
+config AMCC_PPC440SPE_ADMA
+	tristate "AMCC PPC440SPe ADMA support"
+	depends on 440SPe || 440SP
 	select DMA_ENGINE
 	select DMA_ENGINE_RAID
-	select DCA
-	help
-	  Enable support for the Intel(R) I/OAT DMA engine present
-	  in recent Intel Xeon chipsets.
-
-	  Say Y here if you have such a chipset.
-
-	  If unsure, say N.
-
-config INTEL_IOP_ADMA
-	tristate "Intel IOP ADMA support"
-	depends on ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX
-	select DMA_ENGINE
+	select ARCH_HAS_ASYNC_TX_FIND_CHANNEL
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	help
-	  Enable support for the Intel(R) IOP Series RAID engines.
-
-source "drivers/dma/dw/Kconfig"
+	  Enable support for the AMCC PPC440SPe RAID engines.
 
 config AT_HDMAC
 	tristate "Atmel AHB DMA support"
@@ -101,6 +89,89 @@ config AT_XDMAC
 	help
 	  Support the Atmel XDMA controller.
 
+config AXI_DMAC
+	tristate "Analog Devices AXI-DMAC DMA support"
+	depends on MICROBLAZE || NIOS2 || ARCH_ZYNQ || ARCH_SOCFPGA || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Analog Devices AXI-DMAC peripheral. This DMA
+	  controller is often used in Analog Device's reference designs for FPGA
+	  platforms.
+
+config COH901318
+	bool "ST-Ericsson COH901318 DMA support"
+	select DMA_ENGINE
+	depends on ARCH_U300
+	help
+	  Enable support for ST-Ericsson COH 901 318 DMA.
+
+config DMA_BCM2835
+	tristate "BCM2835 DMA engine support"
+	depends on ARCH_BCM2835
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+
+config DMA_JZ4740
+	tristate "JZ4740 DMA support"
+	depends on MACH_JZ4740
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+
+config DMA_JZ4780
+	tristate "JZ4780 DMA support"
+	depends on MACH_JZ4780
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  This selects support for the DMA controller in Ingenic JZ4780 SoCs.
+	  If you have a board based on such a SoC and wish to use DMA for
+	  devices which can use the DMA controller, say Y or M here.
+
+config DMA_OMAP
+	tristate "OMAP DMA support"
+	depends on ARCH_OMAP
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select TI_DMA_CROSSBAR if SOC_DRA7XX
+
+config DMA_SA11X0
+	tristate "SA-11x0 DMA support"
+	depends on ARCH_SA1100
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the DMA engine found on Intel StrongARM SA-1100 and
+	  SA-1110 SoCs.  This DMA engine can only be used with on-chip
+	  devices.
+
+config DMA_SUN4I
+	tristate "Allwinner A10 DMA SoCs support"
+	depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I
+	default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I)
+	select DMA_ENGINE
+	select DMA_OF
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the DMA controller present in the sun4i,
+	  sun5i and sun7i Allwinner ARM SoCs.
+
+config DMA_SUN6I
+	tristate "Allwinner A31 SoCs DMA support"
+	depends on MACH_SUN6I || MACH_SUN8I || COMPILE_TEST
+	depends on RESET_CONTROLLER
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the DMA engine first found in Allwinner A31 SoCs.
+
+config EP93XX_DMA
+	bool "Cirrus Logic EP93xx DMA support"
+	depends on ARCH_EP93XX
+	select DMA_ENGINE
+	help
+	  Enable support for the Cirrus Logic EP93xx M2P/M2M DMA controller.
+
 config FSL_DMA
 	tristate "Freescale Elo series DMA support"
 	depends on FSL_SOC
@@ -112,6 +183,16 @@ config FSL_DMA
 	  EloPlus is on mpc85xx and mpc86xx and Pxxx parts, and the Elo3 is on
 	  some Txxx and Bxxx parts.
 
+config FSL_EDMA
+	tristate "Freescale eDMA engine support"
+	depends on OF
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the Freescale eDMA engine with programmable channel
+	  multiplexing capability for DMA request sources(slot).
+	  This module can be found on Freescale Vybrid and LS-1 SoCs.
+
 config FSL_RAID
         tristate "Freescale RAID engine Support"
         depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH
@@ -123,153 +204,175 @@ config FSL_RAID
           the capability to offload memcpy, xor and pq computation
 	  for raid5/6.
 
-source "drivers/dma/hsu/Kconfig"
-
-config MPC512X_DMA
-	tristate "Freescale MPC512x built-in DMA engine support"
-	depends on PPC_MPC512x || PPC_MPC831x
+config IMG_MDC_DMA
+	tristate "IMG MDC support"
+	depends on MIPS || COMPILE_TEST
+	depends on MFD_SYSCON
 	select DMA_ENGINE
-	---help---
-	  Enable support for the Freescale MPC512x built-in DMA engine.
-
-source "drivers/dma/bestcomm/Kconfig"
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the IMG multi-threaded DMA controller (MDC).
 
-config MV_XOR
-	bool "Marvell XOR engine support"
-	depends on PLAT_ORION
+config IMX_DMA
+	tristate "i.MX DMA support"
+	depends on ARCH_MXC
 	select DMA_ENGINE
-	select DMA_ENGINE_RAID
-	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
-	---help---
-	  Enable support for the Marvell XOR engine.
+	help
+	  Support the i.MX DMA engine. This engine is integrated into
+	  Freescale i.MX1/21/27 chips.
 
-config MX3_IPU
-	bool "MX3x Image Processing Unit support"
+config IMX_SDMA
+	tristate "i.MX SDMA support"
 	depends on ARCH_MXC
 	select DMA_ENGINE
-	default y
 	help
-	  If you plan to use the Image Processing unit in the i.MX3x, say
-	  Y here. If unsure, select Y.
+	  Support the i.MX SDMA engine. This engine is integrated into
+	  Freescale i.MX25/31/35/51/53/6 chips.
 
-config MX3_IPU_IRQS
-	int "Number of dynamically mapped interrupts for IPU"
-	depends on MX3_IPU
-	range 2 137
-	default 4
+config IDMA64
+	tristate "Intel integrated DMA 64-bit support"
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
 	help
-	  Out of 137 interrupt sources on i.MX31 IPU only very few are used.
-	  To avoid bloating the irq_desc[] array we allocate a sufficient
-	  number of IRQ slots and map them dynamically to specific sources.
+	  Enable DMA support for Intel Low Power Subsystem such as found on
+	  Intel Skylake PCH.
 
-config PXA_DMA
-	bool "PXA DMA support"
-	depends on (ARCH_MMP || ARCH_PXA)
+config INTEL_IOATDMA
+	tristate "Intel I/OAT DMA support"
+	depends on PCI && X86_64
 	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
+	select DMA_ENGINE_RAID
+	select DCA
 	help
-	  Support the DMA engine for PXA. It is also compatible with MMP PDMA
-	  platform. The internal DMA IP of all PXA variants is supported, with
-	  16 to 32 channels for peripheral to memory or memory to memory
-	  transfers.
+	  Enable support for the Intel(R) I/OAT DMA engine present
+	  in recent Intel Xeon chipsets.
 
-config TXX9_DMAC
-	tristate "Toshiba TXx9 SoC DMA support"
-	depends on MACH_TX49XX || MACH_TX39XX
+	  Say Y here if you have such a chipset.
+
+	  If unsure, say N.
+
+config INTEL_IOP_ADMA
+	tristate "Intel IOP ADMA support"
+	depends on ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX
 	select DMA_ENGINE
+	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	help
-	  Support the TXx9 SoC internal DMA controller.  This can be
-	  integrated in chips such as the Toshiba TX4927/38/39.
+	  Enable support for the Intel(R) IOP Series RAID engines.
 
-config TEGRA20_APB_DMA
-	bool "NVIDIA Tegra20 APB DMA support"
-	depends on ARCH_TEGRA
+config INTEL_MIC_X100_DMA
+	tristate "Intel MIC X100 DMA Driver"
+	depends on 64BIT && X86 && INTEL_MIC_BUS
 	select DMA_ENGINE
 	help
-	  Support for the NVIDIA Tegra20 APB DMA controller driver. The
-	  DMA controller is having multiple DMA channel which can be
-	  configured for different peripherals like audio, UART, SPI,
-	  I2C etc which is in APB bus.
-	  This DMA controller transfers data from memory to peripheral fifo
-	  or vice versa. It does not support memory to memory data transfer.
+	  This enables DMA support for the Intel Many Integrated Core
+	  (MIC) family of PCIe form factor coprocessor X100 devices that
+	  run a 64 bit Linux OS. This driver will be used by both MIC
+	  host and card drivers.
 
-config S3C24XX_DMAC
-	tristate "Samsung S3C24XX DMA support"
-	depends on ARCH_S3C24XX
+	  If you are building host kernel with a MIC device or a card
+	  kernel for a MIC device, then say M (recommended) or Y, else
+	  say N. If unsure say N.
+
+	  More information about the Intel MIC family as well as the Linux
+	  OS and tools for MIC to use with this driver are available from
+	  <http://software.intel.com/en-us/mic-developer>.
+
+config K3_DMA
+	tristate "Hisilicon K3 DMA support"
+	depends on ARCH_HI3xxx
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  Support for the Samsung S3C24XX DMA controller driver. The
-	  DMA controller is having multiple DMA channels which can be
-	  configured for different peripherals like audio, UART, SPI.
-	  The DMA controller can transfer data from memory to peripheral,
-	  periphal to memory, periphal to periphal and memory to memory.
+	  Support the DMA engine for Hisilicon K3 platform
+	  devices.
 
-source "drivers/dma/sh/Kconfig"
+config LPC18XX_DMAMUX
+	bool "NXP LPC18xx/43xx DMA MUX for PL080"
+	depends on ARCH_LPC18XX || COMPILE_TEST
+	depends on OF && AMBA_PL08X
+	select MFD_SYSCON
+	help
+	  Enable support for DMA on NXP LPC18xx/43xx platforms
+	  with PL080 and multiplexed DMA request lines.
 
-config COH901318
-	bool "ST-Ericsson COH901318 DMA support"
+config MMP_PDMA
+	bool "MMP PDMA support"
+	depends on (ARCH_MMP || ARCH_PXA)
 	select DMA_ENGINE
-	depends on ARCH_U300
 	help
-	  Enable support for ST-Ericsson COH 901 318 DMA.
+	  Support the MMP PDMA engine for PXA and MMP platform.
 
-config STE_DMA40
-	bool "ST-Ericsson DMA40 support"
-	depends on ARCH_U8500
+config MMP_TDMA
+	bool "MMP Two-Channel DMA support"
+	depends on ARCH_MMP
 	select DMA_ENGINE
+	select MMP_SRAM
 	help
-	  Support for ST-Ericsson DMA40 controller
+	  Support the MMP Two-Channel DMA engine.
+	  This engine used for MMP Audio DMA and pxa910 SQU.
+	  It needs sram driver under mach-mmp.
 
-config AMCC_PPC440SPE_ADMA
-	tristate "AMCC PPC440SPe ADMA support"
-	depends on 440SPe || 440SP
+config MOXART_DMA
+	tristate "MOXART DMA support"
+	depends on ARCH_MOXART
 	select DMA_ENGINE
-	select DMA_ENGINE_RAID
-	select ARCH_HAS_ASYNC_TX_FIND_CHANNEL
-	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+	select DMA_OF
+	select DMA_VIRTUAL_CHANNELS
 	help
-	  Enable support for the AMCC PPC440SPe RAID engines.
+	  Enable support for the MOXA ART SoC DMA controller.
+ 
+	  Say Y here if you enabled MMP ADMA, otherwise say N.
 
-config TIMB_DMA
-	tristate "Timberdale FPGA DMA support"
-	depends on MFD_TIMBERDALE
+config MPC512X_DMA
+	tristate "Freescale MPC512x built-in DMA engine support"
+	depends on PPC_MPC512x || PPC_MPC831x
 	select DMA_ENGINE
-	help
-	  Enable support for the Timberdale FPGA DMA engine.
+	---help---
+	  Enable support for the Freescale MPC512x built-in DMA engine.
 
-config SIRF_DMA
-	tristate "CSR SiRFprimaII/SiRFmarco DMA support"
-	depends on ARCH_SIRF
+config MV_XOR
+	bool "Marvell XOR engine support"
+	depends on PLAT_ORION
 	select DMA_ENGINE
-	help
-	  Enable support for the CSR SiRFprimaII DMA engine.
+	select DMA_ENGINE_RAID
+	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+	---help---
+	  Enable support for the Marvell XOR engine.
 
-config TI_EDMA
-	bool "TI EDMA support"
-	depends on ARCH_DAVINCI || ARCH_OMAP || ARCH_KEYSTONE
+config MXS_DMA
+	bool "MXS DMA support"
+	depends on SOC_IMX23 || SOC_IMX28 || SOC_IMX6Q
+	select STMP_DEVICE
 	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	select TI_PRIV_EDMA
-	default n
 	help
-	  Enable support for the TI EDMA controller. This DMA
-	  engine is found on TI DaVinci and AM33xx parts.
+	  Support the MXS DMA engine. This engine including APBH-DMA
+	  and APBX-DMA is integrated into Freescale i.MX23/28/MX6Q/MX6DL chips.
 
-config TI_DMA_CROSSBAR
-	bool
+config MX3_IPU
+	bool "MX3x Image Processing Unit support"
+	depends on ARCH_MXC
+	select DMA_ENGINE
+	default y
+	help
+	  If you plan to use the Image Processing unit in the i.MX3x, say
+	  Y here. If unsure, select Y.
 
-config ARCH_HAS_ASYNC_TX_FIND_CHANNEL
-	bool
+config MX3_IPU_IRQS
+	int "Number of dynamically mapped interrupts for IPU"
+	depends on MX3_IPU
+	range 2 137
+	default 4
+	help
+	  Out of 137 interrupt sources on i.MX31 IPU only very few are used.
+	  To avoid bloating the irq_desc[] array we allocate a sufficient
+	  number of IRQ slots and map them dynamically to specific sources.
 
-config PL330_DMA
-	tristate "DMA API Driver for PL330"
+config NBPFAXI_DMA
+	tristate "Renesas Type-AXI NBPF DMA support"
 	select DMA_ENGINE
-	depends on ARM_AMBA
+	depends on ARM || COMPILE_TEST
 	help
-	  Select if your platform has one or more PL330 DMACs.
-	  You need to provide platform specific settings via
-	  platform_data for a dma-pl330 device.
+	  Support for "Type-AXI" NBPF DMA IPs from Renesas
 
 config PCH_DMA
 	tristate "Intel EG20T PCH / LAPIS Semicon IOH(ML7213/ML7223/ML7831) DMA"
@@ -285,72 +388,87 @@ config PCH_DMA
 	  ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
 	  ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
 
-config IMX_SDMA
-	tristate "i.MX SDMA support"
-	depends on ARCH_MXC
+config PL330_DMA
+	tristate "DMA API Driver for PL330"
 	select DMA_ENGINE
+	depends on ARM_AMBA
 	help
-	  Support the i.MX SDMA engine. This engine is integrated into
-	  Freescale i.MX25/31/35/51/53/6 chips.
+	  Select if your platform has one or more PL330 DMACs.
+	  You need to provide platform specific settings via
+	  platform_data for a dma-pl330 device.
 
-config IMX_DMA
-	tristate "i.MX DMA support"
-	depends on ARCH_MXC
+config PXA_DMA
+	bool "PXA DMA support"
+	depends on (ARCH_MMP || ARCH_PXA)
 	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
 	help
-	  Support the i.MX DMA engine. This engine is integrated into
-	  Freescale i.MX1/21/27 chips.
+	  Support the DMA engine for PXA. It is also compatible with MMP PDMA
+	  platform. The internal DMA IP of all PXA variants is supported, with
+	  16 to 32 channels for peripheral to memory or memory to memory
+	  transfers.
 
-config MXS_DMA
-	bool "MXS DMA support"
-	depends on SOC_IMX23 || SOC_IMX28 || SOC_IMX6Q
-	select STMP_DEVICE
+config QCOM_BAM_DMA
+	tristate "QCOM BAM DMA support"
+	depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM)
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	---help---
+	  Enable support for the QCOM BAM DMA controller.  This controller
+	  provides DMA capabilities for a variety of on-chip devices.
+
+config SIRF_DMA
+	tristate "CSR SiRFprimaII/SiRFmarco DMA support"
+	depends on ARCH_SIRF
 	select DMA_ENGINE
 	help
-	  Support the MXS DMA engine. This engine including APBH-DMA
-	  and APBX-DMA is integrated into Freescale i.MX23/28/MX6Q/MX6DL chips.
+	  Enable support for the CSR SiRFprimaII DMA engine.
 
-config EP93XX_DMA
-	bool "Cirrus Logic EP93xx DMA support"
-	depends on ARCH_EP93XX
+config STE_DMA40
+	bool "ST-Ericsson DMA40 support"
+	depends on ARCH_U8500
 	select DMA_ENGINE
 	help
-	  Enable support for the Cirrus Logic EP93xx M2P/M2M DMA controller.
+	  Support for ST-Ericsson DMA40 controller
 
-config DMA_SA11X0
-	tristate "SA-11x0 DMA support"
-	depends on ARCH_SA1100
+config S3C24XX_DMAC
+	tristate "Samsung S3C24XX DMA support"
+	depends on ARCH_S3C24XX
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  Support the DMA engine found on Intel StrongARM SA-1100 and
-	  SA-1110 SoCs.  This DMA engine can only be used with on-chip
-	  devices.
+	  Support for the Samsung S3C24XX DMA controller driver. The
+	  DMA controller is having multiple DMA channels which can be
+	  configured for different peripherals like audio, UART, SPI.
+	  The DMA controller can transfer data from memory to peripheral,
+	  periphal to memory, periphal to periphal and memory to memory.
 
-config MMP_TDMA
-	bool "MMP Two-Channel DMA support"
-	depends on ARCH_MMP
+config TXX9_DMAC
+	tristate "Toshiba TXx9 SoC DMA support"
+	depends on MACH_TX49XX || MACH_TX39XX
 	select DMA_ENGINE
-	select MMP_SRAM
 	help
-	  Support the MMP Two-Channel DMA engine.
-	  This engine used for MMP Audio DMA and pxa910 SQU.
-	  It needs sram driver under mach-mmp.
-
-	  Say Y here if you enabled MMP ADMA, otherwise say N.
+	  Support the TXx9 SoC internal DMA controller.  This can be
+	  integrated in chips such as the Toshiba TX4927/38/39.
 
-config DMA_OMAP
-	tristate "OMAP DMA support"
-	depends on ARCH_OMAP
+config TEGRA20_APB_DMA
+	bool "NVIDIA Tegra20 APB DMA support"
+	depends on ARCH_TEGRA
 	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	select TI_DMA_CROSSBAR if SOC_DRA7XX
+	help
+	  Support for the NVIDIA Tegra20 APB DMA controller driver. The
+	  DMA controller is having multiple DMA channel which can be
+	  configured for different peripherals like audio, UART, SPI,
+	  I2C etc which is in APB bus.
+	  This DMA controller transfers data from memory to peripheral fifo
+	  or vice versa. It does not support memory to memory data transfer.
 
-config DMA_BCM2835
-	tristate "BCM2835 DMA engine support"
-	depends on ARCH_BCM2835
+config TIMB_DMA
+	tristate "Timberdale FPGA DMA support"
+	depends on MFD_TIMBERDALE
 	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Timberdale FPGA DMA engine.
 
 config TI_CPPI41
 	tristate "AM33xx CPPI41 DMA support"
@@ -360,56 +478,28 @@ config TI_CPPI41
 	  The Communications Port Programming Interface (CPPI) 4.1 DMA engine
 	  is currently used by the USB driver on AM335x platforms.
 
-config MMP_PDMA
-	bool "MMP PDMA support"
-	depends on (ARCH_MMP || ARCH_PXA)
-	select DMA_ENGINE
-	help
-	  Support the MMP PDMA engine for PXA and MMP platform.
-
-config DMA_JZ4740
-	tristate "JZ4740 DMA support"
-	depends on MACH_JZ4740
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-
-config DMA_JZ4780
-	tristate "JZ4780 DMA support"
-	depends on MACH_JZ4780
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  This selects support for the DMA controller in Ingenic JZ4780 SoCs.
-	  If you have a board based on such a SoC and wish to use DMA for
-	  devices which can use the DMA controller, say Y or M here.
+config TI_DMA_CROSSBAR
+	bool
 
-config K3_DMA
-	tristate "Hisilicon K3 DMA support"
-	depends on ARCH_HI3xxx
+config TI_EDMA
+	bool "TI EDMA support"
+	depends on ARCH_DAVINCI || ARCH_OMAP || ARCH_KEYSTONE
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
+	select TI_PRIV_EDMA
+	default n
 	help
-	  Support the DMA engine for Hisilicon K3 platform
-	  devices.
+	  Enable support for the TI EDMA controller. This DMA
+	  engine is found on TI DaVinci and AM33xx parts.
 
-config MOXART_DMA
-	tristate "MOXART DMA support"
-	depends on ARCH_MOXART
-	select DMA_ENGINE
-	select DMA_OF
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Enable support for the MOXA ART SoC DMA controller.
- 
-config FSL_EDMA
-	tristate "Freescale eDMA engine support"
-	depends on OF
+config XGENE_DMA
+	tristate "APM X-Gene DMA support"
+	depends on ARCH_XGENE || COMPILE_TEST
 	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
+	select DMA_ENGINE_RAID
+	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	help
-	  Support the Freescale eDMA engine with programmable channel
-	  multiplexing capability for DMA request sources(slot).
-	  This module can be found on Freescale Vybrid and LS-1 SoCs.
+	  Enable support for the APM X-Gene SoC DMA engine.
 
 config XILINX_VDMA
 	tristate "Xilinx AXI VDMA Engine"
@@ -425,55 +515,25 @@ config XILINX_VDMA
 	  channels, Memory Mapped to Stream (MM2S) and Stream to
 	  Memory Mapped (S2MM) for the data transfers.
 
-config DMA_SUN6I
-	tristate "Allwinner A31 SoCs DMA support"
-	depends on MACH_SUN6I || MACH_SUN8I || COMPILE_TEST
-	depends on RESET_CONTROLLER
+config ZX_DMA
+	tristate "ZTE ZX296702 DMA support"
+	depends on ARCH_ZX
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  Support for the DMA engine first found in Allwinner A31 SoCs.
+	  Support the DMA engine for ZTE ZX296702 platform devices.
 
-config NBPFAXI_DMA
-	tristate "Renesas Type-AXI NBPF DMA support"
-	select DMA_ENGINE
-	depends on ARM || COMPILE_TEST
-	help
-	  Support for "Type-AXI" NBPF DMA IPs from Renesas
 
-config IMG_MDC_DMA
-	tristate "IMG MDC support"
-	depends on MIPS || COMPILE_TEST
-	depends on MFD_SYSCON
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Enable support for the IMG multi-threaded DMA controller (MDC).
-
-config XGENE_DMA
-	tristate "APM X-Gene DMA support"
-	depends on ARCH_XGENE || COMPILE_TEST
-	select DMA_ENGINE
-	select DMA_ENGINE_RAID
-	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
-	help
-	  Enable support for the APM X-Gene SoC DMA engine.
-
-config DMA_ENGINE
-	bool
+# driver files
+source "drivers/dma/bestcomm/Kconfig"
 
-config DMA_VIRTUAL_CHANNELS
-	tristate
+source "drivers/dma/dw/Kconfig"
 
-config DMA_ACPI
-	def_bool y
-	depends on ACPI
+source "drivers/dma/hsu/Kconfig"
 
-config DMA_OF
-	def_bool y
-	depends on OF
-	select DMA_ENGINE
+source "drivers/dma/sh/Kconfig"
 
+# clients
 comment "DMA Clients"
 	depends on DMA_ENGINE
 
@@ -498,13 +558,4 @@ config DMATEST
 config DMA_ENGINE_RAID
 	bool
 
-config QCOM_BAM_DMA
-	tristate "QCOM BAM DMA support"
-	depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM)
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	---help---
-	  Enable support for the QCOM BAM DMA controller.  This controller
-	  provides DMA capabilities for a variety of on-chip devices.
-
 endif
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 6a4d6f2827da..7711a7180726 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -1,58 +1,69 @@
+#dmaengine debug flags
 subdir-ccflags-$(CONFIG_DMADEVICES_DEBUG)  := -DDEBUG
 subdir-ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG
 
+#core
 obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
 obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o
 obj-$(CONFIG_DMA_ACPI) += acpi-dma.o
 obj-$(CONFIG_DMA_OF) += of-dma.o
 
+#dmatest
 obj-$(CONFIG_DMATEST) += dmatest.o
-obj-$(CONFIG_INTEL_IOATDMA) += ioat/
-obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
-obj-$(CONFIG_FSL_DMA) += fsldma.o
-obj-$(CONFIG_HSU_DMA) += hsu/
-obj-$(CONFIG_MPC512X_DMA) += mpc512x_dma.o
-obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
-obj-$(CONFIG_MV_XOR) += mv_xor.o
-obj-$(CONFIG_DW_DMAC_CORE) += dw/
+
+#devices
+obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
+obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
-obj-$(CONFIG_MX3_IPU) += ipu/
-obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
-obj-$(CONFIG_RENESAS_DMA) += sh/
+obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o
 obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
-obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
-obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
+obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
+obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o
+obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o
+obj-$(CONFIG_DMA_OMAP) += omap-dma.o
+obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
+obj-$(CONFIG_DMA_SUN4I) += sun4i-dma.o
+obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o
+obj-$(CONFIG_DW_DMAC_CORE) += dw/
+obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
+obj-$(CONFIG_FSL_DMA) += fsldma.o
+obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
+obj-$(CONFIG_FSL_RAID) += fsl_raid.o
+obj-$(CONFIG_HSU_DMA) += hsu/
+obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
 obj-$(CONFIG_IMX_DMA) += imx-dma.o
+obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
+obj-$(CONFIG_IDMA64) += idma64.o
+obj-$(CONFIG_INTEL_IOATDMA) += ioat/
+obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
+obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
+obj-$(CONFIG_K3_DMA) += k3dma.o
+obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
+obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
+obj-$(CONFIG_MOXART_DMA) += moxart-dma.o
+obj-$(CONFIG_MPC512X_DMA) += mpc512x_dma.o
+obj-$(CONFIG_MV_XOR) += mv_xor.o
 obj-$(CONFIG_MXS_DMA) += mxs-dma.o
+obj-$(CONFIG_MX3_IPU) += ipu/
+obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
+obj-$(CONFIG_PCH_DMA) += pch_dma.o
+obj-$(CONFIG_PL330_DMA) += pl330.o
+obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
 obj-$(CONFIG_PXA_DMA) += pxa_dma.o
-obj-$(CONFIG_TIMB_DMA) += timb_dma.o
+obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
+obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
-obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
-obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
 obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
-obj-$(CONFIG_PL330_DMA) += pl330.o
-obj-$(CONFIG_PCH_DMA) += pch_dma.o
-obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
-obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
-obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
-obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
-obj-$(CONFIG_DMA_OMAP) += omap-dma.o
-obj-$(CONFIG_TI_DMA_CROSSBAR) += ti-dma-crossbar.o
-obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
-obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
-obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o
-obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o
+obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
+obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
+obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_TI_CPPI41) += cppi41.o
-obj-$(CONFIG_K3_DMA) += k3dma.o
-obj-$(CONFIG_MOXART_DMA) += moxart-dma.o
-obj-$(CONFIG_FSL_RAID) += fsl_raid.o
-obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
-obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
-obj-y += xilinx/
-obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
-obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
-obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o
-obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
+obj-$(CONFIG_TI_DMA_CROSSBAR) += ti-dma-crossbar.o
+obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
+obj-$(CONFIG_ZX_DMA) += zx296702_dma.o
+
+obj-y += xilinx/
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 5de3cf453f35..9b42c0588550 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -83,6 +83,8 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
@@ -2030,10 +2032,188 @@ static inline void init_pl08x_debugfs(struct pl08x_driver_data *pl08x)
 }
 #endif
 
+#ifdef CONFIG_OF
+static struct dma_chan *pl08x_find_chan_id(struct pl08x_driver_data *pl08x,
+					 u32 id)
+{
+	struct pl08x_dma_chan *chan;
+
+	list_for_each_entry(chan, &pl08x->slave.channels, vc.chan.device_node) {
+		if (chan->signal == id)
+			return &chan->vc.chan;
+	}
+
+	return NULL;
+}
+
+static struct dma_chan *pl08x_of_xlate(struct of_phandle_args *dma_spec,
+				       struct of_dma *ofdma)
+{
+	struct pl08x_driver_data *pl08x = ofdma->of_dma_data;
+	struct pl08x_channel_data *data;
+	struct pl08x_dma_chan *chan;
+	struct dma_chan *dma_chan;
+
+	if (!pl08x)
+		return NULL;
+
+	if (dma_spec->args_count != 2)
+		return NULL;
+
+	dma_chan = pl08x_find_chan_id(pl08x, dma_spec->args[0]);
+	if (dma_chan)
+		return dma_get_slave_channel(dma_chan);
+
+	chan = devm_kzalloc(pl08x->slave.dev, sizeof(*chan) + sizeof(*data),
+			    GFP_KERNEL);
+	if (!chan)
+		return NULL;
+
+	data = (void *)&chan[1];
+	data->bus_id = "(none)";
+	data->periph_buses = dma_spec->args[1];
+
+	chan->cd = data;
+	chan->host = pl08x;
+	chan->slave = true;
+	chan->name = data->bus_id;
+	chan->state = PL08X_CHAN_IDLE;
+	chan->signal = dma_spec->args[0];
+	chan->vc.desc_free = pl08x_desc_free;
+
+	vchan_init(&chan->vc, &pl08x->slave);
+
+	return dma_get_slave_channel(&chan->vc.chan);
+}
+
+static int pl08x_of_probe(struct amba_device *adev,
+			  struct pl08x_driver_data *pl08x,
+			  struct device_node *np)
+{
+	struct pl08x_platform_data *pd;
+	u32 cctl_memcpy = 0;
+	u32 val;
+	int ret;
+
+	pd = devm_kzalloc(&adev->dev, sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return -ENOMEM;
+
+	/* Eligible bus masters for fetching LLIs */
+	if (of_property_read_bool(np, "lli-bus-interface-ahb1"))
+		pd->lli_buses |= PL08X_AHB1;
+	if (of_property_read_bool(np, "lli-bus-interface-ahb2"))
+		pd->lli_buses |= PL08X_AHB2;
+	if (!pd->lli_buses) {
+		dev_info(&adev->dev, "no bus masters for LLIs stated, assume all\n");
+		pd->lli_buses |= PL08X_AHB1 | PL08X_AHB2;
+	}
+
+	/* Eligible bus masters for memory access */
+	if (of_property_read_bool(np, "mem-bus-interface-ahb1"))
+		pd->mem_buses |= PL08X_AHB1;
+	if (of_property_read_bool(np, "mem-bus-interface-ahb2"))
+		pd->mem_buses |= PL08X_AHB2;
+	if (!pd->mem_buses) {
+		dev_info(&adev->dev, "no bus masters for memory stated, assume all\n");
+		pd->mem_buses |= PL08X_AHB1 | PL08X_AHB2;
+	}
+
+	/* Parse the memcpy channel properties */
+	ret = of_property_read_u32(np, "memcpy-burst-size", &val);
+	if (ret) {
+		dev_info(&adev->dev, "no memcpy burst size specified, using 1 byte\n");
+		val = 1;
+	}
+	switch (val) {
+	default:
+		dev_err(&adev->dev, "illegal burst size for memcpy, set to 1\n");
+		/* Fall through */
+	case 1:
+		cctl_memcpy |= PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 4:
+		cctl_memcpy |= PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 8:
+		cctl_memcpy |= PL080_BSIZE_8 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_8 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 16:
+		cctl_memcpy |= PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 32:
+		cctl_memcpy |= PL080_BSIZE_32 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_32 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 64:
+		cctl_memcpy |= PL080_BSIZE_64 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_64 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 128:
+		cctl_memcpy |= PL080_BSIZE_128 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_128 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	case 256:
+		cctl_memcpy |= PL080_BSIZE_256 << PL080_CONTROL_SB_SIZE_SHIFT |
+			       PL080_BSIZE_256 << PL080_CONTROL_DB_SIZE_SHIFT;
+		break;
+	}
+
+	ret = of_property_read_u32(np, "memcpy-bus-width", &val);
+	if (ret) {
+		dev_info(&adev->dev, "no memcpy bus width specified, using 8 bits\n");
+		val = 8;
+	}
+	switch (val) {
+	default:
+		dev_err(&adev->dev, "illegal bus width for memcpy, set to 8 bits\n");
+		/* Fall through */
+	case 8:
+		cctl_memcpy |= PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT |
+			       PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT;
+		break;
+	case 16:
+		cctl_memcpy |= PL080_WIDTH_16BIT << PL080_CONTROL_SWIDTH_SHIFT |
+			       PL080_WIDTH_16BIT << PL080_CONTROL_DWIDTH_SHIFT;
+		break;
+	case 32:
+		cctl_memcpy |= PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT |
+			       PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT;
+		break;
+	}
+
+	/* This is currently the only thing making sense */
+	cctl_memcpy |= PL080_CONTROL_PROT_SYS;
+
+	/* Set up memcpy channel */
+	pd->memcpy_channel.bus_id = "memcpy";
+	pd->memcpy_channel.cctl_memcpy = cctl_memcpy;
+	/* Use the buses that can access memory, obviously */
+	pd->memcpy_channel.periph_buses = pd->mem_buses;
+
+	pl08x->pd = pd;
+
+	return of_dma_controller_register(adev->dev.of_node, pl08x_of_xlate,
+					  pl08x);
+}
+#else
+static inline int pl08x_of_probe(struct amba_device *adev,
+				 struct pl08x_driver_data *pl08x,
+				 struct device_node *np)
+{
+	return -EINVAL;
+}
+#endif
+
 static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	struct pl08x_driver_data *pl08x;
 	const struct vendor_data *vd = id->data;
+	struct device_node *np = adev->dev.of_node;
 	u32 tsfr_size;
 	int ret = 0;
 	int i;
@@ -2093,9 +2273,15 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	/* Get the platform data */
 	pl08x->pd = dev_get_platdata(&adev->dev);
 	if (!pl08x->pd) {
-		dev_err(&adev->dev, "no platform data supplied\n");
-		ret = -EINVAL;
-		goto out_no_platdata;
+		if (np) {
+			ret = pl08x_of_probe(adev, pl08x, np);
+			if (ret)
+				goto out_no_platdata;
+		} else {
+			dev_err(&adev->dev, "no platform data supplied\n");
+			ret = -EINVAL;
+			goto out_no_platdata;
+		}
 	}
 
 	/* Assign useful pointers to the driver state */
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 59892126d175..58d406230d89 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -48,6 +48,8 @@
 	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
 	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+#define ATC_MAX_DSCR_TRIALS	10
+
 /*
  * Initial number of descriptors to allocate for each channel. This could
  * be increased during dma usage.
@@ -285,28 +287,19 @@ static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan,
  *
  * @current_len: the number of bytes left before reading CTRLA
  * @ctrla: the value of CTRLA
- * @desc: the descriptor containing the transfer width
  */
-static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
-					struct at_desc *desc)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla)
 {
-	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
-}
+	u32 btsize = (ctrla & ATC_BTSIZE_MAX);
+	u32 src_width = ATC_REG_TO_SRC_WIDTH(ctrla);
 
-/**
- * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
- * to the current value of CTRLA.
- *
- * @current_len: the number of bytes left before reading CTRLA
- * @atchan: the channel to read CTRLA for
- * @desc: the descriptor containing the transfer width
- */
-static inline int atc_calc_bytes_left_from_reg(int current_len,
-			struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	u32 ctrla = channel_readl(atchan, CTRLA);
-
-	return atc_calc_bytes_left(current_len, ctrla, desc);
+	/*
+	 * According to the datasheet, when reading the Control A Register
+	 * (ctrla), the Buffer Transfer Size (btsize) bitfield refers to the
+	 * number of transfers completed on the Source Interface.
+	 * So btsize is always a number of source width transfers.
+	 */
+	return current_len - (btsize << src_width);
 }
 
 /**
@@ -320,7 +313,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr;
+	u32 ctrla, dscr, trials;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -346,15 +339,82 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		 * the channel's DSCR register and compare it against the value
 		 * of the hardware linked list structure of each child
 		 * descriptor.
+		 *
+		 * The CTRLA register provides us with the amount of data
+		 * already read from the source for the current child
+		 * descriptor. So we can compute a more accurate residue by also
+		 * removing the number of bytes corresponding to this amount of
+		 * data.
+		 *
+		 * However, the DSCR and CTRLA registers cannot be read both
+		 * atomically. Hence a race condition may occur: the first read
+		 * register may refer to one child descriptor whereas the second
+		 * read may refer to a later child descriptor in the list
+		 * because of the DMA transfer progression inbetween the two
+		 * reads.
+		 *
+		 * One solution could have been to pause the DMA transfer, read
+		 * the DSCR and CTRLA then resume the DMA transfer. Nonetheless,
+		 * this approach presents some drawbacks:
+		 * - If the DMA transfer is paused, RX overruns or TX underruns
+		 *   are more likey to occur depending on the system latency.
+		 *   Taking the USART driver as an example, it uses a cyclic DMA
+		 *   transfer to read data from the Receive Holding Register
+		 *   (RHR) to avoid RX overruns since the RHR is not protected
+		 *   by any FIFO on most Atmel SoCs. So pausing the DMA transfer
+		 *   to compute the residue would break the USART driver design.
+		 * - The atc_pause() function masks interrupts but we'd rather
+		 *   avoid to do so for system latency purpose.
+		 *
+		 * Then we'd rather use another solution: the DSCR is read a
+		 * first time, the CTRLA is read in turn, next the DSCR is read
+		 * a second time. If the two consecutive read values of the DSCR
+		 * are the same then we assume both refers to the very same
+		 * child descriptor as well as the CTRLA value read inbetween
+		 * does. For cyclic tranfers, the assumption is that a full loop
+		 * is "not so fast".
+		 * If the two DSCR values are different, we read again the CTRLA
+		 * then the DSCR till two consecutive read values from DSCR are
+		 * equal or till the maxium trials is reach.
+		 * This algorithm is very unlikely not to find a stable value for
+		 * DSCR.
 		 */
 
-		ctrla = channel_readl(atchan, CTRLA);
-		rmb(); /* ensure CTRLA is read before DSCR */
 		dscr = channel_readl(atchan, DSCR);
+		rmb(); /* ensure DSCR is read before CTRLA */
+		ctrla = channel_readl(atchan, CTRLA);
+		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+			u32 new_dscr;
+
+			rmb(); /* ensure DSCR is read after CTRLA */
+			new_dscr = channel_readl(atchan, DSCR);
+
+			/*
+			 * If the DSCR register value has not changed inside the
+			 * DMA controller since the previous read, we assume
+			 * that both the dscr and ctrla values refers to the
+			 * very same descriptor.
+			 */
+			if (likely(new_dscr == dscr))
+				break;
+
+			/*
+			 * DSCR has changed inside the DMA controller, so the
+			 * previouly read value of CTRLA may refer to an already
+			 * processed descriptor hence could be outdated.
+			 * We need to update ctrla to match the current
+			 * descriptor.
+			 */
+			dscr = new_dscr;
+			rmb(); /* ensure DSCR is read before CTRLA */
+			ctrla = channel_readl(atchan, CTRLA);
+		}
+		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
 		if (desc_first->lli.dscr == dscr)
-			return atc_calc_bytes_left(ret, ctrla, desc_first);
+			return atc_calc_bytes_left(ret, ctrla);
 
 		ret -= desc_first->len;
 		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
@@ -365,16 +425,14 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		}
 
 		/*
-		 * For the last descriptor in the chain we can calculate
+		 * For the current descriptor in the chain we can calculate
 		 * the remaining bytes using the channel's register.
-		 * Note that the transfer width of the first and last
-		 * descriptor may differ.
 		 */
-		if (!desc->lli.dscr)
-			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	} else {
 		/* single transfer */
-		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+		ctrla = channel_readl(atchan, CTRLA);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	}
 
 	return ret;
@@ -390,6 +448,7 @@ static void
 atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 {
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
+	struct at_dma			*atdma = to_at_dma(atchan->chan_common.device);
 
 	dev_vdbg(chan2dev(&atchan->chan_common),
 		"descriptor %u complete\n", txd->cookie);
@@ -398,6 +457,13 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	if (!atc_chan_is_cyclic(atchan))
 		dma_cookie_complete(txd);
 
+	/* If the transfer was a memset, free our temporary buffer */
+	if (desc->memset) {
+		dma_pool_free(atdma->memset_pool, desc->memset_vaddr,
+			      desc->memset_paddr);
+		desc->memset = false;
+	}
+
 	/* move children to free_list */
 	list_splice_init(&desc->tx_list, &atchan->free_list);
 	/* move myself to free_list */
@@ -659,14 +725,14 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 	size_t			len = 0;
 	int			i;
 
+	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
+		return NULL;
+
 	dev_info(chan2dev(chan),
 		 "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
 		__func__, xt->src_start, xt->dst_start, xt->numf,
 		xt->frame_size, flags);
 
-	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
-		return NULL;
-
 	/*
 	 * The controller can only "skip" X bytes every Y bytes, so we
 	 * need to make sure we are given a template that fit that
@@ -726,7 +792,6 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 
 	desc->txd.cookie = -EBUSY;
 	desc->total_len = desc->len = len;
-	desc->tx_width = dwidth;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -804,10 +869,6 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	first->txd.cookie = -EBUSY;
 	first->total_len = len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = src_width;
-	prev->tx_width = src_width;
-
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
 
@@ -820,6 +881,93 @@ err_desc_get:
 	return NULL;
 }
 
+/**
+ * atc_prep_dma_memset - prepare a memcpy operation
+ * @chan: the channel to prepare operation on
+ * @dest: operation virtual destination address
+ * @value: value to set memory buffer to
+ * @len: operation length
+ * @flags: tx descriptor status flags
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
+		    size_t len, unsigned long flags)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	struct at_desc		*desc = NULL;
+	size_t			xfer_count;
+	u32			ctrla;
+	u32			ctrlb;
+
+	dev_vdbg(chan2dev(chan), "%s: d0x%x v0x%x l0x%zx f0x%lx\n", __func__,
+		dest, value, len, flags);
+
+	if (unlikely(!len)) {
+		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
+		return NULL;
+	}
+
+	if (!is_dma_fill_aligned(chan->device, dest, 0, len)) {
+		dev_dbg(chan2dev(chan), "%s: buffer is not aligned\n",
+			__func__);
+		return NULL;
+	}
+
+	xfer_count = len >> 2;
+	if (xfer_count > ATC_BTSIZE_MAX) {
+		dev_err(chan2dev(chan), "%s: buffer is too big\n",
+			__func__);
+		return NULL;
+	}
+
+	ctrlb =   ATC_DEFAULT_CTRLB | ATC_IEN
+		| ATC_SRC_ADDR_MODE_FIXED
+		| ATC_DST_ADDR_MODE_INCR
+		| ATC_FC_MEM2MEM;
+
+	ctrla = ATC_SRC_WIDTH(2) |
+		ATC_DST_WIDTH(2);
+
+	desc = atc_desc_get(atchan);
+	if (!desc) {
+		dev_err(chan2dev(chan), "%s: can't get a descriptor\n",
+			__func__);
+		return NULL;
+	}
+
+	desc->memset_vaddr = dma_pool_alloc(atdma->memset_pool, GFP_ATOMIC,
+					    &desc->memset_paddr);
+	if (!desc->memset_vaddr) {
+		dev_err(chan2dev(chan), "%s: couldn't allocate buffer\n",
+			__func__);
+		goto err_put_desc;
+	}
+
+	*desc->memset_vaddr = value;
+	desc->memset = true;
+
+	desc->lli.saddr = desc->memset_paddr;
+	desc->lli.daddr = dest;
+	desc->lli.ctrla = ctrla | xfer_count;
+	desc->lli.ctrlb = ctrlb;
+
+	desc->txd.cookie = -EBUSY;
+	desc->len = len;
+	desc->total_len = len;
+
+	/* set end-of-link on the descriptor */
+	set_desc_eol(desc);
+
+	desc->txd.flags = flags;
+
+	return &desc->txd;
+
+err_put_desc:
+	atc_desc_put(atchan, desc);
+	return NULL;
+}
+
 
 /**
  * atc_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
@@ -956,10 +1104,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	first->txd.cookie = -EBUSY;
 	first->total_len = total_len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = reg_width;
-	prev->tx_width = reg_width;
-
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
 
@@ -1077,12 +1221,6 @@ atc_prep_dma_sg(struct dma_chan *chan,
 		desc->txd.cookie = 0;
 		desc->len = len;
 
-		/*
-		 * Although we only need the transfer width for the first and
-		 * the last descriptor, its easier to set it to all descriptors.
-		 */
-		desc->tx_width = src_width;
-
 		atc_desc_chain(&first, &prev, desc);
 
 		/* update the lengths and addresses for the next loop cycle */
@@ -1256,7 +1394,6 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
 	first->total_len = buf_len;
-	first->tx_width = reg_width;
 
 	return &first->txd;
 
@@ -1713,6 +1850,8 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SG, at91sam9rl_config.cap_mask);
 	dma_cap_set(DMA_INTERLEAVE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_MEMCPY, at91sam9g45_config.cap_mask);
+	dma_cap_set(DMA_MEMSET, at91sam9g45_config.cap_mask);
+	dma_cap_set(DMA_PRIVATE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SLAVE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SG, at91sam9g45_config.cap_mask);
 
@@ -1776,7 +1915,16 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	if (!atdma->dma_desc_pool) {
 		dev_err(&pdev->dev, "No memory for descriptors dma pool\n");
 		err = -ENOMEM;
-		goto err_pool_create;
+		goto err_desc_pool_create;
+	}
+
+	/* create a pool of consistent memory blocks for memset blocks */
+	atdma->memset_pool = dma_pool_create("at_hdmac_memset_pool",
+					     &pdev->dev, sizeof(int), 4, 0);
+	if (!atdma->memset_pool) {
+		dev_err(&pdev->dev, "No memory for memset dma pool\n");
+		err = -ENOMEM;
+		goto err_memset_pool_create;
 	}
 
 	/* clear any pending interrupt */
@@ -1822,6 +1970,11 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
 
+	if (dma_has_cap(DMA_MEMSET, atdma->dma_common.cap_mask)) {
+		atdma->dma_common.device_prep_dma_memset = atc_prep_dma_memset;
+		atdma->dma_common.fill_align = DMAENGINE_ALIGN_4_BYTES;
+	}
+
 	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)) {
 		atdma->dma_common.device_prep_slave_sg = atc_prep_slave_sg;
 		/* controller can do slave DMA: can trigger cyclic transfers */
@@ -1842,8 +1995,9 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
 
-	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s%s), %d channels\n",
+	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s%s%s), %d channels\n",
 	  dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask) ? "cpy " : "",
+	  dma_has_cap(DMA_MEMSET, atdma->dma_common.cap_mask) ? "set " : "",
 	  dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)  ? "slave " : "",
 	  dma_has_cap(DMA_SG, atdma->dma_common.cap_mask)  ? "sg-cpy " : "",
 	  plat_dat->nr_channels);
@@ -1868,8 +2022,10 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 err_of_dma_controller_register:
 	dma_async_device_unregister(&atdma->dma_common);
+	dma_pool_destroy(atdma->memset_pool);
+err_memset_pool_create:
 	dma_pool_destroy(atdma->dma_desc_pool);
-err_pool_create:
+err_desc_pool_create:
 	free_irq(platform_get_irq(pdev, 0), atdma);
 err_irq:
 	clk_disable_unprepare(atdma->clk);
@@ -1894,6 +2050,7 @@ static int at_dma_remove(struct platform_device *pdev)
 	at_dma_off(atdma);
 	dma_async_device_unregister(&atdma->dma_common);
 
+	dma_pool_destroy(atdma->memset_pool);
 	dma_pool_destroy(atdma->dma_desc_pool);
 	free_irq(platform_get_irq(pdev, 0), atdma);
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index bc8d5ebedd19..c3bebbe899ac 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -112,6 +112,7 @@
 #define		ATC_SRC_WIDTH_BYTE	(0x0 << 24)
 #define		ATC_SRC_WIDTH_HALFWORD	(0x1 << 24)
 #define		ATC_SRC_WIDTH_WORD	(0x2 << 24)
+#define		ATC_REG_TO_SRC_WIDTH(r)	(((r) >> 24) & 0x3)
 #define	ATC_DST_WIDTH_MASK	(0x3 << 28)	/* Destination Single Transfer Size */
 #define		ATC_DST_WIDTH(x)	((x) << 28)
 #define		ATC_DST_WIDTH_BYTE	(0x0 << 28)
@@ -182,7 +183,6 @@ struct at_lli {
  * @txd: support for the async_tx api
  * @desc_node: node on the channed descriptors list
  * @len: descriptor byte count
- * @tx_width: transfer width
  * @total_len: total transaction byte count
  */
 struct at_desc {
@@ -194,13 +194,17 @@ struct at_desc {
 	struct dma_async_tx_descriptor	txd;
 	struct list_head		desc_node;
 	size_t				len;
-	u32				tx_width;
 	size_t				total_len;
 
 	/* Interleaved data */
 	size_t				boundary;
 	size_t				dst_hole;
 	size_t				src_hole;
+
+	/* Memset temporary buffer */
+	bool				memset;
+	dma_addr_t			memset_paddr;
+	int				*memset_vaddr;
 };
 
 static inline struct at_desc *
@@ -331,6 +335,7 @@ struct at_dma {
 	u8			all_chan_mask;
 
 	struct dma_pool		*dma_desc_pool;
+	struct dma_pool		*memset_pool;
 	/* AT THE END channels table */
 	struct at_dma_chan	chan[0];
 };
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index cf1213de7865..a165b4bfd330 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -359,18 +359,19 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
 	 * descriptor view 2 since some fields of the configuration register
 	 * depend on transfer size and src/dest addresses.
 	 */
-	if (at_xdmac_chan_is_cyclic(atchan)) {
+	if (at_xdmac_chan_is_cyclic(atchan))
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
-		at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
-	} else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) {
+	else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3)
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV3;
-	} else {
-		/*
-		 * No need to write AT_XDMAC_CC reg, it will be done when the
-		 * descriptor is fecthed.
-		 */
+	else
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV2;
-	}
+	/*
+	 * Even if the register will be updated from the configuration in the
+	 * descriptor when using view 2 or higher, the PROT bit won't be set
+	 * properly. This bit can be modified only by using the channel
+	 * configuration register.
+	 */
+	at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
 
 	reg |= AT_XDMAC_CNDC_NDDUP
 	       | AT_XDMAC_CNDC_NDSUP
@@ -624,12 +625,12 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		       unsigned int sg_len, enum dma_transfer_direction direction,
 		       unsigned long flags, void *context)
 {
-	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
-	struct at_xdmac_desc	*first = NULL, *prev = NULL;
-	struct scatterlist	*sg;
-	int			i;
-	unsigned int		xfer_size = 0;
-	unsigned long		irqflags;
+	struct at_xdmac_chan		*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac_desc		*first = NULL, *prev = NULL;
+	struct scatterlist		*sg;
+	int				i;
+	unsigned int			xfer_size = 0;
+	unsigned long			irqflags;
 	struct dma_async_tx_descriptor	*ret = NULL;
 
 	if (!sgl)
@@ -681,15 +682,16 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			desc->lld.mbr_sa = mem;
 			desc->lld.mbr_da = atchan->sconfig.dst_addr;
 		}
-		desc->lld.mbr_cfg = atchan->cfg;
-		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
+		dwidth = at_xdmac_get_dwidth(atchan->cfg);
 		fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
-			       ? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
+			       ? dwidth
 			       : AT_XDMAC_CC_DWIDTH_BYTE;
 		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2			/* next descriptor view */
 			| AT_XDMAC_MBR_UBC_NDEN					/* next descriptor dst parameter update */
 			| AT_XDMAC_MBR_UBC_NSEN					/* next descriptor src parameter update */
 			| (len >> fixed_dwidth);				/* microblock length */
+		desc->lld.mbr_cfg = (atchan->cfg & ~AT_XDMAC_CC_DWIDTH_MASK) |
+				    AT_XDMAC_CC_DWIDTH(fixed_dwidth);
 		dev_dbg(chan2dev(chan),
 			 "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
 			 __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc);
@@ -795,10 +797,7 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		list_add_tail(&desc->desc_node, &first->descs_list);
 	}
 
-	prev->lld.mbr_nda = first->tx_dma_desc.phys;
-	dev_dbg(chan2dev(chan),
-		"%s: chain lld: prev=0x%p, mbr_nda=%pad\n",
-		__func__, prev, &prev->lld.mbr_nda);
+	at_xdmac_queue_desc(chan, prev, first);
 	first->tx_dma_desc.flags = flags;
 	first->xfer_size = buf_len;
 	first->direction = direction;
@@ -1133,7 +1132,7 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_INCREMENTED_AM
+	u32			chan_cc = AT_XDMAC_CC_DAM_UBS_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1201,6 +1200,168 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 	return &desc->tx_dma_desc;
 }
 
+static struct dma_async_tx_descriptor *
+at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl,
+			    unsigned int sg_len, int value,
+			    unsigned long flags)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac_desc	*desc, *pdesc = NULL,
+				*ppdesc = NULL, *first = NULL;
+	struct scatterlist	*sg, *psg = NULL, *ppsg = NULL;
+	size_t			stride = 0, pstride = 0, len = 0;
+	int			i;
+
+	if (!sgl)
+		return NULL;
+
+	dev_dbg(chan2dev(chan), "%s: sg_len=%d, value=0x%x, flags=0x%lx\n",
+		__func__, sg_len, value, flags);
+
+	/* Prepare descriptors. */
+	for_each_sg(sgl, sg, sg_len, i) {
+		dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
+			__func__, sg_dma_address(sg), sg_dma_len(sg),
+			value, flags);
+		desc = at_xdmac_memset_create_desc(chan, atchan,
+						   sg_dma_address(sg),
+						   sg_dma_len(sg),
+						   value);
+		if (!desc && first)
+			list_splice_init(&first->descs_list,
+					 &atchan->free_descs_list);
+
+		if (!first)
+			first = desc;
+
+		/* Update our strides */
+		pstride = stride;
+		if (psg)
+			stride = sg_dma_address(sg) -
+				(sg_dma_address(psg) + sg_dma_len(psg));
+
+		/*
+		 * The scatterlist API gives us only the address and
+		 * length of each elements.
+		 *
+		 * Unfortunately, we don't have the stride, which we
+		 * will need to compute.
+		 *
+		 * That make us end up in a situation like this one:
+		 *    len    stride    len    stride    len
+		 * +-------+        +-------+        +-------+
+		 * |  N-2  |        |  N-1  |        |   N   |
+		 * +-------+        +-------+        +-------+
+		 *
+		 * We need all these three elements (N-2, N-1 and N)
+		 * to actually take the decision on whether we need to
+		 * queue N-1 or reuse N-2.
+		 *
+		 * We will only consider N if it is the last element.
+		 */
+		if (ppdesc && pdesc) {
+			if ((stride == pstride) &&
+			    (sg_dma_len(ppsg) == sg_dma_len(psg))) {
+				dev_dbg(chan2dev(chan),
+					"%s: desc 0x%p can be merged with desc 0x%p\n",
+					__func__, pdesc, ppdesc);
+
+				/*
+				 * Increment the block count of the
+				 * N-2 descriptor
+				 */
+				at_xdmac_increment_block_count(chan, ppdesc);
+				ppdesc->lld.mbr_dus = stride;
+
+				/*
+				 * Put back the N-1 descriptor in the
+				 * free descriptor list
+				 */
+				list_add_tail(&pdesc->desc_node,
+					      &atchan->free_descs_list);
+
+				/*
+				 * Make our N-1 descriptor pointer
+				 * point to the N-2 since they were
+				 * actually merged.
+				 */
+				pdesc = ppdesc;
+
+			/*
+			 * Rule out the case where we don't have
+			 * pstride computed yet (our second sg
+			 * element)
+			 *
+			 * We also want to catch the case where there
+			 * would be a negative stride,
+			 */
+			} else if (pstride ||
+				   sg_dma_address(sg) < sg_dma_address(psg)) {
+				/*
+				 * Queue the N-1 descriptor after the
+				 * N-2
+				 */
+				at_xdmac_queue_desc(chan, ppdesc, pdesc);
+
+				/*
+				 * Add the N-1 descriptor to the list
+				 * of the descriptors used for this
+				 * transfer
+				 */
+				list_add_tail(&desc->desc_node,
+					      &first->descs_list);
+				dev_dbg(chan2dev(chan),
+					"%s: add desc 0x%p to descs_list 0x%p\n",
+					__func__, desc, first);
+			}
+		}
+
+		/*
+		 * If we are the last element, just see if we have the
+		 * same size than the previous element.
+		 *
+		 * If so, we can merge it with the previous descriptor
+		 * since we don't care about the stride anymore.
+		 */
+		if ((i == (sg_len - 1)) &&
+		    sg_dma_len(ppsg) == sg_dma_len(psg)) {
+			dev_dbg(chan2dev(chan),
+				"%s: desc 0x%p can be merged with desc 0x%p\n",
+				__func__, desc, pdesc);
+
+			/*
+			 * Increment the block count of the N-1
+			 * descriptor
+			 */
+			at_xdmac_increment_block_count(chan, pdesc);
+			pdesc->lld.mbr_dus = stride;
+
+			/*
+			 * Put back the N descriptor in the free
+			 * descriptor list
+			 */
+			list_add_tail(&desc->desc_node,
+				      &atchan->free_descs_list);
+		}
+
+		/* Update our descriptors */
+		ppdesc = pdesc;
+		pdesc = desc;
+
+		/* Update our scatter pointers */
+		ppsg = psg;
+		psg = sg;
+
+		len += sg_dma_len(sg);
+	}
+
+	first->tx_dma_desc.cookie = -EBUSY;
+	first->tx_dma_desc.flags = flags;
+	first->xfer_size = len;
+
+	return &first->tx_dma_desc;
+}
+
 static enum dma_status
 at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		struct dma_tx_state *txstate)
@@ -1734,6 +1895,7 @@ static int at_xdmac_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_INTERLEAVE, atxdmac->dma.cap_mask);
 	dma_cap_set(DMA_MEMCPY, atxdmac->dma.cap_mask);
 	dma_cap_set(DMA_MEMSET, atxdmac->dma.cap_mask);
+	dma_cap_set(DMA_MEMSET_SG, atxdmac->dma.cap_mask);
 	dma_cap_set(DMA_SLAVE, atxdmac->dma.cap_mask);
 	/*
 	 * Without DMA_PRIVATE the driver is not able to allocate more than
@@ -1749,6 +1911,7 @@ static int at_xdmac_probe(struct platform_device *pdev)
 	atxdmac->dma.device_prep_interleaved_dma	= at_xdmac_prep_interleaved;
 	atxdmac->dma.device_prep_dma_memcpy		= at_xdmac_prep_dma_memcpy;
 	atxdmac->dma.device_prep_dma_memset		= at_xdmac_prep_dma_memset;
+	atxdmac->dma.device_prep_dma_memset_sg		= at_xdmac_prep_dma_memset_sg;
 	atxdmac->dma.device_prep_slave_sg		= at_xdmac_prep_slave_sg;
 	atxdmac->dma.device_config			= at_xdmac_device_config;
 	atxdmac->dma.device_pause			= at_xdmac_device_pause;
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index fd22dd36985f..c340ca9bd2b5 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -2730,7 +2730,7 @@ static int __init coh901318_probe(struct platform_device *pdev)
 	 * This controller can only access address at even 32bit boundaries,
 	 * i.e. 2^2
 	 */
-	base->dma_memcpy.copy_align = 2;
+	base->dma_memcpy.copy_align = DMAENGINE_ALIGN_4_BYTES;
 	err = dma_async_device_register(&base->dma_memcpy);
 
 	if (err)
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
new file mode 100644
index 000000000000..5b2395e7e04d
--- /dev/null
+++ b/drivers/dma/dma-axi-dmac.c
@@ -0,0 +1,691 @@
+/*
+ * Driver for the Analog Devices AXI-DMAC core
+ *
+ * Copyright 2013-2015 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <dt-bindings/dma/axi-dmac.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+/*
+ * The AXI-DMAC is a soft IP core that is used in FPGA designs. The core has
+ * various instantiation parameters which decided the exact feature set support
+ * by the core.
+ *
+ * Each channel of the core has a source interface and a destination interface.
+ * The number of channels and the type of the channel interfaces is selected at
+ * configuration time. A interface can either be a connected to a central memory
+ * interconnect, which allows access to system memory, or it can be connected to
+ * a dedicated bus which is directly connected to a data port on a peripheral.
+ * Given that those are configuration options of the core that are selected when
+ * it is instantiated this means that they can not be changed by software at
+ * runtime. By extension this means that each channel is uni-directional. It can
+ * either be device to memory or memory to device, but not both. Also since the
+ * device side is a dedicated data bus only connected to a single peripheral
+ * there is no address than can or needs to be configured for the device side.
+ */
+
+#define AXI_DMAC_REG_IRQ_MASK		0x80
+#define AXI_DMAC_REG_IRQ_PENDING	0x84
+#define AXI_DMAC_REG_IRQ_SOURCE		0x88
+
+#define AXI_DMAC_REG_CTRL		0x400
+#define AXI_DMAC_REG_TRANSFER_ID	0x404
+#define AXI_DMAC_REG_START_TRANSFER	0x408
+#define AXI_DMAC_REG_FLAGS		0x40c
+#define AXI_DMAC_REG_DEST_ADDRESS	0x410
+#define AXI_DMAC_REG_SRC_ADDRESS	0x414
+#define AXI_DMAC_REG_X_LENGTH		0x418
+#define AXI_DMAC_REG_Y_LENGTH		0x41c
+#define AXI_DMAC_REG_DEST_STRIDE	0x420
+#define AXI_DMAC_REG_SRC_STRIDE		0x424
+#define AXI_DMAC_REG_TRANSFER_DONE	0x428
+#define AXI_DMAC_REG_ACTIVE_TRANSFER_ID 0x42c
+#define AXI_DMAC_REG_STATUS		0x430
+#define AXI_DMAC_REG_CURRENT_SRC_ADDR	0x434
+#define AXI_DMAC_REG_CURRENT_DEST_ADDR	0x438
+
+#define AXI_DMAC_CTRL_ENABLE		BIT(0)
+#define AXI_DMAC_CTRL_PAUSE		BIT(1)
+
+#define AXI_DMAC_IRQ_SOT		BIT(0)
+#define AXI_DMAC_IRQ_EOT		BIT(1)
+
+#define AXI_DMAC_FLAG_CYCLIC		BIT(0)
+
+struct axi_dmac_sg {
+	dma_addr_t src_addr;
+	dma_addr_t dest_addr;
+	unsigned int x_len;
+	unsigned int y_len;
+	unsigned int dest_stride;
+	unsigned int src_stride;
+	unsigned int id;
+};
+
+struct axi_dmac_desc {
+	struct virt_dma_desc vdesc;
+	bool cyclic;
+
+	unsigned int num_submitted;
+	unsigned int num_completed;
+	unsigned int num_sgs;
+	struct axi_dmac_sg sg[];
+};
+
+struct axi_dmac_chan {
+	struct virt_dma_chan vchan;
+
+	struct axi_dmac_desc *next_desc;
+	struct list_head active_descs;
+	enum dma_transfer_direction direction;
+
+	unsigned int src_width;
+	unsigned int dest_width;
+	unsigned int src_type;
+	unsigned int dest_type;
+
+	unsigned int max_length;
+	unsigned int align_mask;
+
+	bool hw_cyclic;
+	bool hw_2d;
+};
+
+struct axi_dmac {
+	void __iomem *base;
+	int irq;
+
+	struct clk *clk;
+
+	struct dma_device dma_dev;
+	struct axi_dmac_chan chan;
+
+	struct device_dma_parameters dma_parms;
+};
+
+static struct axi_dmac *chan_to_axi_dmac(struct axi_dmac_chan *chan)
+{
+	return container_of(chan->vchan.chan.device, struct axi_dmac,
+		dma_dev);
+}
+
+static struct axi_dmac_chan *to_axi_dmac_chan(struct dma_chan *c)
+{
+	return container_of(c, struct axi_dmac_chan, vchan.chan);
+}
+
+static struct axi_dmac_desc *to_axi_dmac_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct axi_dmac_desc, vdesc);
+}
+
+static void axi_dmac_write(struct axi_dmac *axi_dmac, unsigned int reg,
+	unsigned int val)
+{
+	writel(val, axi_dmac->base + reg);
+}
+
+static int axi_dmac_read(struct axi_dmac *axi_dmac, unsigned int reg)
+{
+	return readl(axi_dmac->base + reg);
+}
+
+static int axi_dmac_src_is_mem(struct axi_dmac_chan *chan)
+{
+	return chan->src_type == AXI_DMAC_BUS_TYPE_AXI_MM;
+}
+
+static int axi_dmac_dest_is_mem(struct axi_dmac_chan *chan)
+{
+	return chan->dest_type == AXI_DMAC_BUS_TYPE_AXI_MM;
+}
+
+static bool axi_dmac_check_len(struct axi_dmac_chan *chan, unsigned int len)
+{
+	if (len == 0 || len > chan->max_length)
+		return false;
+	if ((len & chan->align_mask) != 0) /* Not aligned */
+		return false;
+	return true;
+}
+
+static bool axi_dmac_check_addr(struct axi_dmac_chan *chan, dma_addr_t addr)
+{
+	if ((addr & chan->align_mask) != 0) /* Not aligned */
+		return false;
+	return true;
+}
+
+static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
+{
+	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+	struct virt_dma_desc *vdesc;
+	struct axi_dmac_desc *desc;
+	struct axi_dmac_sg *sg;
+	unsigned int flags = 0;
+	unsigned int val;
+
+	val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
+	if (val) /* Queue is full, wait for the next SOT IRQ */
+		return;
+
+	desc = chan->next_desc;
+
+	if (!desc) {
+		vdesc = vchan_next_desc(&chan->vchan);
+		if (!vdesc)
+			return;
+		list_move_tail(&vdesc->node, &chan->active_descs);
+		desc = to_axi_dmac_desc(vdesc);
+	}
+	sg = &desc->sg[desc->num_submitted];
+
+	desc->num_submitted++;
+	if (desc->num_submitted == desc->num_sgs)
+		chan->next_desc = NULL;
+	else
+		chan->next_desc = desc;
+
+	sg->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
+
+	if (axi_dmac_dest_is_mem(chan)) {
+		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->dest_addr);
+		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->dest_stride);
+	}
+
+	if (axi_dmac_src_is_mem(chan)) {
+		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->src_addr);
+		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->src_stride);
+	}
+
+	/*
+	 * If the hardware supports cyclic transfers and there is no callback to
+	 * call, enable hw cyclic mode to avoid unnecessary interrupts.
+	 */
+	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback)
+		flags |= AXI_DMAC_FLAG_CYCLIC;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->x_len - 1);
+	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->y_len - 1);
+	axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, flags);
+	axi_dmac_write(dmac, AXI_DMAC_REG_START_TRANSFER, 1);
+}
+
+static struct axi_dmac_desc *axi_dmac_active_desc(struct axi_dmac_chan *chan)
+{
+	return list_first_entry_or_null(&chan->active_descs,
+		struct axi_dmac_desc, vdesc.node);
+}
+
+static void axi_dmac_transfer_done(struct axi_dmac_chan *chan,
+	unsigned int completed_transfers)
+{
+	struct axi_dmac_desc *active;
+	struct axi_dmac_sg *sg;
+
+	active = axi_dmac_active_desc(chan);
+	if (!active)
+		return;
+
+	if (active->cyclic) {
+		vchan_cyclic_callback(&active->vdesc);
+	} else {
+		do {
+			sg = &active->sg[active->num_completed];
+			if (!(BIT(sg->id) & completed_transfers))
+				break;
+			active->num_completed++;
+			if (active->num_completed == active->num_sgs) {
+				list_del(&active->vdesc.node);
+				vchan_cookie_complete(&active->vdesc);
+				active = axi_dmac_active_desc(chan);
+			}
+		} while (active);
+	}
+}
+
+static irqreturn_t axi_dmac_interrupt_handler(int irq, void *devid)
+{
+	struct axi_dmac *dmac = devid;
+	unsigned int pending;
+
+	pending = axi_dmac_read(dmac, AXI_DMAC_REG_IRQ_PENDING);
+	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_PENDING, pending);
+
+	spin_lock(&dmac->chan.vchan.lock);
+	/* One or more transfers have finished */
+	if (pending & AXI_DMAC_IRQ_EOT) {
+		unsigned int completed;
+
+		completed = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_DONE);
+		axi_dmac_transfer_done(&dmac->chan, completed);
+	}
+	/* Space has become available in the descriptor queue */
+	if (pending & AXI_DMAC_IRQ_SOT)
+		axi_dmac_start_transfer(&dmac->chan);
+	spin_unlock(&dmac->chan.vchan.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int axi_dmac_terminate_all(struct dma_chan *c)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, 0);
+	chan->next_desc = NULL;
+	vchan_get_all_descriptors(&chan->vchan, &head);
+	list_splice_tail_init(&chan->active_descs, &head);
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&chan->vchan, &head);
+
+	return 0;
+}
+
+static void axi_dmac_issue_pending(struct dma_chan *c)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+	unsigned long flags;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, AXI_DMAC_CTRL_ENABLE);
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	if (vchan_issue_pending(&chan->vchan))
+		axi_dmac_start_transfer(chan);
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+}
+
+static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
+{
+	struct axi_dmac_desc *desc;
+
+	desc = kzalloc(sizeof(struct axi_dmac_desc) +
+		sizeof(struct axi_dmac_sg) * num_sgs, GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->num_sgs = num_sgs;
+
+	return desc;
+}
+
+static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
+	struct dma_chan *c, struct scatterlist *sgl,
+	unsigned int sg_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+	struct axi_dmac_desc *desc;
+	struct scatterlist *sg;
+	unsigned int i;
+
+	if (direction != chan->direction)
+		return NULL;
+
+	desc = axi_dmac_alloc_desc(sg_len);
+	if (!desc)
+		return NULL;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		if (!axi_dmac_check_addr(chan, sg_dma_address(sg)) ||
+		    !axi_dmac_check_len(chan, sg_dma_len(sg))) {
+			kfree(desc);
+			return NULL;
+		}
+
+		if (direction == DMA_DEV_TO_MEM)
+			desc->sg[i].dest_addr = sg_dma_address(sg);
+		else
+			desc->sg[i].src_addr = sg_dma_address(sg);
+		desc->sg[i].x_len = sg_dma_len(sg);
+		desc->sg[i].y_len = 1;
+	}
+
+	desc->cyclic = false;
+
+	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
+}
+
+static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
+	struct dma_chan *c, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+	struct axi_dmac_desc *desc;
+	unsigned int num_periods, i;
+
+	if (direction != chan->direction)
+		return NULL;
+
+	if (!axi_dmac_check_len(chan, buf_len) ||
+	    !axi_dmac_check_addr(chan, buf_addr))
+		return NULL;
+
+	if (period_len == 0 || buf_len % period_len)
+		return NULL;
+
+	num_periods = buf_len / period_len;
+
+	desc = axi_dmac_alloc_desc(num_periods);
+	if (!desc)
+		return NULL;
+
+	for (i = 0; i < num_periods; i++) {
+		if (direction == DMA_DEV_TO_MEM)
+			desc->sg[i].dest_addr = buf_addr;
+		else
+			desc->sg[i].src_addr = buf_addr;
+		desc->sg[i].x_len = period_len;
+		desc->sg[i].y_len = 1;
+		buf_addr += period_len;
+	}
+
+	desc->cyclic = true;
+
+	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
+}
+
+static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
+	struct dma_chan *c, struct dma_interleaved_template *xt,
+	unsigned long flags)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+	struct axi_dmac_desc *desc;
+	size_t dst_icg, src_icg;
+
+	if (xt->frame_size != 1)
+		return NULL;
+
+	if (xt->dir != chan->direction)
+		return NULL;
+
+	if (axi_dmac_src_is_mem(chan)) {
+		if (!xt->src_inc || !axi_dmac_check_addr(chan, xt->src_start))
+			return NULL;
+	}
+
+	if (axi_dmac_dest_is_mem(chan)) {
+		if (!xt->dst_inc || !axi_dmac_check_addr(chan, xt->dst_start))
+			return NULL;
+	}
+
+	dst_icg = dmaengine_get_dst_icg(xt, &xt->sgl[0]);
+	src_icg = dmaengine_get_src_icg(xt, &xt->sgl[0]);
+
+	if (chan->hw_2d) {
+		if (!axi_dmac_check_len(chan, xt->sgl[0].size) ||
+		    !axi_dmac_check_len(chan, xt->numf))
+			return NULL;
+		if (xt->sgl[0].size + dst_icg > chan->max_length ||
+		    xt->sgl[0].size + src_icg > chan->max_length)
+			return NULL;
+	} else {
+		if (dst_icg != 0 || src_icg != 0)
+			return NULL;
+		if (chan->max_length / xt->sgl[0].size < xt->numf)
+			return NULL;
+		if (!axi_dmac_check_len(chan, xt->sgl[0].size * xt->numf))
+			return NULL;
+	}
+
+	desc = axi_dmac_alloc_desc(1);
+	if (!desc)
+		return NULL;
+
+	if (axi_dmac_src_is_mem(chan)) {
+		desc->sg[0].src_addr = xt->src_start;
+		desc->sg[0].src_stride = xt->sgl[0].size + src_icg;
+	}
+
+	if (axi_dmac_dest_is_mem(chan)) {
+		desc->sg[0].dest_addr = xt->dst_start;
+		desc->sg[0].dest_stride = xt->sgl[0].size + dst_icg;
+	}
+
+	if (chan->hw_2d) {
+		desc->sg[0].x_len = xt->sgl[0].size;
+		desc->sg[0].y_len = xt->numf;
+	} else {
+		desc->sg[0].x_len = xt->sgl[0].size * xt->numf;
+		desc->sg[0].y_len = 1;
+	}
+
+	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
+}
+
+static void axi_dmac_free_chan_resources(struct dma_chan *c)
+{
+	vchan_free_chan_resources(to_virt_chan(c));
+}
+
+static void axi_dmac_desc_free(struct virt_dma_desc *vdesc)
+{
+	kfree(container_of(vdesc, struct axi_dmac_desc, vdesc));
+}
+
+/*
+ * The configuration stored in the devicetree matches the configuration
+ * parameters of the peripheral instance and allows the driver to know which
+ * features are implemented and how it should behave.
+ */
+static int axi_dmac_parse_chan_dt(struct device_node *of_chan,
+	struct axi_dmac_chan *chan)
+{
+	u32 val;
+	int ret;
+
+	ret = of_property_read_u32(of_chan, "reg", &val);
+	if (ret)
+		return ret;
+
+	/* We only support 1 channel for now */
+	if (val != 0)
+		return -EINVAL;
+
+	ret = of_property_read_u32(of_chan, "adi,source-bus-type", &val);
+	if (ret)
+		return ret;
+	if (val > AXI_DMAC_BUS_TYPE_FIFO)
+		return -EINVAL;
+	chan->src_type = val;
+
+	ret = of_property_read_u32(of_chan, "adi,destination-bus-type", &val);
+	if (ret)
+		return ret;
+	if (val > AXI_DMAC_BUS_TYPE_FIFO)
+		return -EINVAL;
+	chan->dest_type = val;
+
+	ret = of_property_read_u32(of_chan, "adi,source-bus-width", &val);
+	if (ret)
+		return ret;
+	chan->src_width = val / 8;
+
+	ret = of_property_read_u32(of_chan, "adi,destination-bus-width", &val);
+	if (ret)
+		return ret;
+	chan->dest_width = val / 8;
+
+	ret = of_property_read_u32(of_chan, "adi,length-width", &val);
+	if (ret)
+		return ret;
+
+	if (val >= 32)
+		chan->max_length = UINT_MAX;
+	else
+		chan->max_length = (1ULL << val) - 1;
+
+	chan->align_mask = max(chan->dest_width, chan->src_width) - 1;
+
+	if (axi_dmac_dest_is_mem(chan) && axi_dmac_src_is_mem(chan))
+		chan->direction = DMA_MEM_TO_MEM;
+	else if (!axi_dmac_dest_is_mem(chan) && axi_dmac_src_is_mem(chan))
+		chan->direction = DMA_MEM_TO_DEV;
+	else if (axi_dmac_dest_is_mem(chan) && !axi_dmac_src_is_mem(chan))
+		chan->direction = DMA_DEV_TO_MEM;
+	else
+		chan->direction = DMA_DEV_TO_DEV;
+
+	chan->hw_cyclic = of_property_read_bool(of_chan, "adi,cyclic");
+	chan->hw_2d = of_property_read_bool(of_chan, "adi,2d");
+
+	return 0;
+}
+
+static int axi_dmac_probe(struct platform_device *pdev)
+{
+	struct device_node *of_channels, *of_chan;
+	struct dma_device *dma_dev;
+	struct axi_dmac *dmac;
+	struct resource *res;
+	int ret;
+
+	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
+	if (!dmac)
+		return -ENOMEM;
+
+	dmac->irq = platform_get_irq(pdev, 0);
+	if (dmac->irq <= 0)
+		return -EINVAL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dmac->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dmac->base))
+		return PTR_ERR(dmac->base);
+
+	dmac->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(dmac->clk))
+		return PTR_ERR(dmac->clk);
+
+	INIT_LIST_HEAD(&dmac->chan.active_descs);
+
+	of_channels = of_get_child_by_name(pdev->dev.of_node, "adi,channels");
+	if (of_channels == NULL)
+		return -ENODEV;
+
+	for_each_child_of_node(of_channels, of_chan) {
+		ret = axi_dmac_parse_chan_dt(of_chan, &dmac->chan);
+		if (ret) {
+			of_node_put(of_chan);
+			of_node_put(of_channels);
+			return -EINVAL;
+		}
+	}
+	of_node_put(of_channels);
+
+	pdev->dev.dma_parms = &dmac->dma_parms;
+	dma_set_max_seg_size(&pdev->dev, dmac->chan.max_length);
+
+	dma_dev = &dmac->dma_dev;
+	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, dma_dev->cap_mask);
+	dma_dev->device_free_chan_resources = axi_dmac_free_chan_resources;
+	dma_dev->device_tx_status = dma_cookie_status;
+	dma_dev->device_issue_pending = axi_dmac_issue_pending;
+	dma_dev->device_prep_slave_sg = axi_dmac_prep_slave_sg;
+	dma_dev->device_prep_dma_cyclic = axi_dmac_prep_dma_cyclic;
+	dma_dev->device_prep_interleaved_dma = axi_dmac_prep_interleaved;
+	dma_dev->device_terminate_all = axi_dmac_terminate_all;
+	dma_dev->dev = &pdev->dev;
+	dma_dev->chancnt = 1;
+	dma_dev->src_addr_widths = BIT(dmac->chan.src_width);
+	dma_dev->dst_addr_widths = BIT(dmac->chan.dest_width);
+	dma_dev->directions = BIT(dmac->chan.direction);
+	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	INIT_LIST_HEAD(&dma_dev->channels);
+
+	dmac->chan.vchan.desc_free = axi_dmac_desc_free;
+	vchan_init(&dmac->chan.vchan, dma_dev);
+
+	ret = clk_prepare_enable(dmac->clk);
+	if (ret < 0)
+		return ret;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, 0x00);
+
+	ret = dma_async_device_register(dma_dev);
+	if (ret)
+		goto err_clk_disable;
+
+	ret = of_dma_controller_register(pdev->dev.of_node,
+		of_dma_xlate_by_chan_id, dma_dev);
+	if (ret)
+		goto err_unregister_device;
+
+	ret = request_irq(dmac->irq, axi_dmac_interrupt_handler, 0,
+		dev_name(&pdev->dev), dmac);
+	if (ret)
+		goto err_unregister_of;
+
+	platform_set_drvdata(pdev, dmac);
+
+	return 0;
+
+err_unregister_of:
+	of_dma_controller_free(pdev->dev.of_node);
+err_unregister_device:
+	dma_async_device_unregister(&dmac->dma_dev);
+err_clk_disable:
+	clk_disable_unprepare(dmac->clk);
+
+	return ret;
+}
+
+static int axi_dmac_remove(struct platform_device *pdev)
+{
+	struct axi_dmac *dmac = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	free_irq(dmac->irq, dmac);
+	tasklet_kill(&dmac->chan.vchan.task);
+	dma_async_device_unregister(&dmac->dma_dev);
+	clk_disable_unprepare(dmac->clk);
+
+	return 0;
+}
+
+static const struct of_device_id axi_dmac_of_match_table[] = {
+	{ .compatible = "adi,axi-dmac-1.00.a" },
+	{ },
+};
+
+static struct platform_driver axi_dmac_driver = {
+	.driver = {
+		.name = "dma-axi-dmac",
+		.of_match_table = axi_dmac_of_match_table,
+	},
+	.probe = axi_dmac_probe,
+	.remove = axi_dmac_remove,
+};
+module_platform_driver(axi_dmac_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("DMA controller driver for the AXI-DMAC controller");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 26d2f0e09ea3..dade7c47ff18 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -145,7 +145,8 @@ struct jz4780_dma_dev {
 	struct jz4780_dma_chan chan[JZ_DMA_NR_CHANNELS];
 };
 
-struct jz4780_dma_data {
+struct jz4780_dma_filter_data {
+	struct device_node *of_node;
 	uint32_t transfer_type;
 	int channel;
 };
@@ -214,11 +215,25 @@ static void jz4780_dma_desc_free(struct virt_dma_desc *vdesc)
 	kfree(desc);
 }
 
-static uint32_t jz4780_dma_transfer_size(unsigned long val, int *ord)
+static uint32_t jz4780_dma_transfer_size(unsigned long val, uint32_t *shift)
 {
-	*ord = ffs(val) - 1;
+	int ord = ffs(val) - 1;
 
-	switch (*ord) {
+	/*
+	 * 8 byte transfer sizes unsupported so fall back on 4. If it's larger
+	 * than the maximum, just limit it. It is perfectly safe to fall back
+	 * in this way since we won't exceed the maximum burst size supported
+	 * by the device, the only effect is reduced efficiency. This is better
+	 * than refusing to perform the request at all.
+	 */
+	if (ord == 3)
+		ord = 2;
+	else if (ord > 7)
+		ord = 7;
+
+	*shift = ord;
+
+	switch (ord) {
 	case 0:
 		return JZ_DMA_SIZE_1_BYTE;
 	case 1:
@@ -231,20 +246,17 @@ static uint32_t jz4780_dma_transfer_size(unsigned long val, int *ord)
 		return JZ_DMA_SIZE_32_BYTE;
 	case 6:
 		return JZ_DMA_SIZE_64_BYTE;
-	case 7:
-		return JZ_DMA_SIZE_128_BYTE;
 	default:
-		return -EINVAL;
+		return JZ_DMA_SIZE_128_BYTE;
 	}
 }
 
-static uint32_t jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
+static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 	struct jz4780_dma_hwdesc *desc, dma_addr_t addr, size_t len,
 	enum dma_transfer_direction direction)
 {
 	struct dma_slave_config *config = &jzchan->config;
 	uint32_t width, maxburst, tsz;
-	int ord;
 
 	if (direction == DMA_MEM_TO_DEV) {
 		desc->dcm = JZ_DMA_DCM_SAI;
@@ -271,8 +283,8 @@ static uint32_t jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 	 * divisible by the transfer size, and we must not use more than the
 	 * maximum burst specified by the user.
 	 */
-	tsz = jz4780_dma_transfer_size(addr | len | (width * maxburst), &ord);
-	jzchan->transfer_shift = ord;
+	tsz = jz4780_dma_transfer_size(addr | len | (width * maxburst),
+				       &jzchan->transfer_shift);
 
 	switch (width) {
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:
@@ -289,12 +301,14 @@ static uint32_t jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 	desc->dcm |= width << JZ_DMA_DCM_SP_SHIFT;
 	desc->dcm |= width << JZ_DMA_DCM_DP_SHIFT;
 
-	desc->dtc = len >> ord;
+	desc->dtc = len >> jzchan->transfer_shift;
+	return 0;
 }
 
 static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
 	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
 	struct jz4780_dma_desc *desc;
@@ -307,12 +321,11 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
 
 	for (i = 0; i < sg_len; i++) {
 		err = jz4780_dma_setup_hwdesc(jzchan, &desc->desc[i],
-					sg_dma_address(&sgl[i]),
-					sg_dma_len(&sgl[i]),
-					direction);
+					      sg_dma_address(&sgl[i]),
+					      sg_dma_len(&sgl[i]),
+					      direction);
 		if (err < 0)
-			return ERR_PTR(err);
-
+			return NULL;
 
 		desc->desc[i].dcm |= JZ_DMA_DCM_TIE;
 
@@ -354,9 +367,9 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic(
 
 	for (i = 0; i < periods; i++) {
 		err = jz4780_dma_setup_hwdesc(jzchan, &desc->desc[i], buf_addr,
-					period_len, direction);
+					      period_len, direction);
 		if (err < 0)
-			return ERR_PTR(err);
+			return NULL;
 
 		buf_addr += period_len;
 
@@ -390,15 +403,13 @@ struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
 	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
 	struct jz4780_dma_desc *desc;
 	uint32_t tsz;
-	int ord;
 
 	desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY);
 	if (!desc)
 		return NULL;
 
-	tsz = jz4780_dma_transfer_size(dest | src | len, &ord);
-	if (tsz < 0)
-		return ERR_PTR(tsz);
+	tsz = jz4780_dma_transfer_size(dest | src | len,
+				       &jzchan->transfer_shift);
 
 	desc->desc[0].dsa = src;
 	desc->desc[0].dta = dest;
@@ -407,7 +418,7 @@ struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
 			    tsz << JZ_DMA_DCM_TSZ_SHIFT |
 			    JZ_DMA_WIDTH_32_BIT << JZ_DMA_DCM_SP_SHIFT |
 			    JZ_DMA_WIDTH_32_BIT << JZ_DMA_DCM_DP_SHIFT;
-	desc->desc[0].dtc = len >> ord;
+	desc->desc[0].dtc = len >> jzchan->transfer_shift;
 
 	return vchan_tx_prep(&jzchan->vchan, &desc->vdesc, flags);
 }
@@ -484,8 +495,9 @@ static void jz4780_dma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&jzchan->vchan.lock, flags);
 }
 
-static int jz4780_dma_terminate_all(struct jz4780_dma_chan *jzchan)
+static int jz4780_dma_terminate_all(struct dma_chan *chan)
 {
+	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
 	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
 	unsigned long flags;
 	LIST_HEAD(head);
@@ -507,9 +519,11 @@ static int jz4780_dma_terminate_all(struct jz4780_dma_chan *jzchan)
 	return 0;
 }
 
-static int jz4780_dma_slave_config(struct jz4780_dma_chan *jzchan,
-	const struct dma_slave_config *config)
+static int jz4780_dma_config(struct dma_chan *chan,
+	struct dma_slave_config *config)
 {
+	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
+
 	if ((config->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
 	   || (config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES))
 		return -EINVAL;
@@ -567,8 +581,8 @@ static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan,
 		txstate->residue = 0;
 
 	if (vdesc && jzchan->desc && vdesc == &jzchan->desc->vdesc
-		&& jzchan->desc->status & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT))
-			status = DMA_ERROR;
+	    && jzchan->desc->status & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT))
+		status = DMA_ERROR;
 
 	spin_unlock_irqrestore(&jzchan->vchan.lock, flags);
 	return status;
@@ -671,7 +685,10 @@ static bool jz4780_dma_filter_fn(struct dma_chan *chan, void *param)
 {
 	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
 	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
-	struct jz4780_dma_data *data = param;
+	struct jz4780_dma_filter_data *data = param;
+
+	if (jzdma->dma_device.dev->of_node != data->of_node)
+		return false;
 
 	if (data->channel > -1) {
 		if (data->channel != jzchan->id)
@@ -690,11 +707,12 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
 {
 	struct jz4780_dma_dev *jzdma = ofdma->of_dma_data;
 	dma_cap_mask_t mask = jzdma->dma_device.cap_mask;
-	struct jz4780_dma_data data;
+	struct jz4780_dma_filter_data data;
 
 	if (dma_spec->args_count != 2)
 		return NULL;
 
+	data.of_node = ofdma->of_node;
 	data.transfer_type = dma_spec->args[0];
 	data.channel = dma_spec->args[1];
 
@@ -713,9 +731,14 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
 				data.channel);
 			return NULL;
 		}
-	}
 
-	return dma_request_channel(mask, jz4780_dma_filter_fn, &data);
+		jzdma->chan[data.channel].transfer_type = data.transfer_type;
+
+		return dma_get_slave_channel(
+			&jzdma->chan[data.channel].vchan.chan);
+	} else {
+		return dma_request_channel(mask, jz4780_dma_filter_fn, &data);
+	}
 }
 
 static int jz4780_dma_probe(struct platform_device *pdev)
@@ -743,23 +766,26 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	if (IS_ERR(jzdma->base))
 		return PTR_ERR(jzdma->base);
 
-	jzdma->irq = platform_get_irq(pdev, 0);
-	if (jzdma->irq < 0) {
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
 		dev_err(dev, "failed to get IRQ: %d\n", ret);
-		return jzdma->irq;
+		return ret;
 	}
 
-	ret = devm_request_irq(dev, jzdma->irq, jz4780_dma_irq_handler, 0,
-			       dev_name(dev), jzdma);
+	jzdma->irq = ret;
+
+	ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev),
+			  jzdma);
 	if (ret) {
 		dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq);
-		return -EINVAL;
+		return ret;
 	}
 
 	jzdma->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(jzdma->clk)) {
 		dev_err(dev, "failed to get clock\n");
-		return PTR_ERR(jzdma->clk);
+		ret = PTR_ERR(jzdma->clk);
+		goto err_free_irq;
 	}
 
 	clk_prepare_enable(jzdma->clk);
@@ -775,13 +801,13 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_CYCLIC, dd->cap_mask);
 
 	dd->dev = dev;
-	dd->copy_align = 2; /* 2^2 = 4 byte alignment */
+	dd->copy_align = DMAENGINE_ALIGN_4_BYTES;
 	dd->device_alloc_chan_resources = jz4780_dma_alloc_chan_resources;
 	dd->device_free_chan_resources = jz4780_dma_free_chan_resources;
 	dd->device_prep_slave_sg = jz4780_dma_prep_slave_sg;
 	dd->device_prep_dma_cyclic = jz4780_dma_prep_dma_cyclic;
 	dd->device_prep_dma_memcpy = jz4780_dma_prep_dma_memcpy;
-	dd->device_config = jz4780_dma_slave_config;
+	dd->device_config = jz4780_dma_config;
 	dd->device_terminate_all = jz4780_dma_terminate_all;
 	dd->device_tx_status = jz4780_dma_tx_status;
 	dd->device_issue_pending = jz4780_dma_issue_pending;
@@ -790,7 +816,6 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	dd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	dd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
-
 	/*
 	 * Enable DMA controller, mark all channels as not programmable.
 	 * Also set the FMSC bit - it increases MSC performance, so it makes
@@ -832,15 +857,24 @@ err_unregister_dev:
 
 err_disable_clk:
 	clk_disable_unprepare(jzdma->clk);
+
+err_free_irq:
+	free_irq(jzdma->irq, jzdma);
 	return ret;
 }
 
 static int jz4780_dma_remove(struct platform_device *pdev)
 {
 	struct jz4780_dma_dev *jzdma = platform_get_drvdata(pdev);
+	int i;
 
 	of_dma_controller_free(pdev->dev.of_node);
-	devm_free_irq(&pdev->dev, jzdma->irq, jzdma);
+
+	free_irq(jzdma->irq, jzdma);
+
+	for (i = 0; i < JZ_DMA_NR_CHANNELS; i++)
+		tasklet_kill(&jzdma->chan[i].vchan.task);
+
 	dma_async_device_unregister(&jzdma->dma_device);
 	return 0;
 }
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 4a4cce15f25d..3ff284c8e3d5 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -689,6 +689,10 @@ struct dma_chan *dma_request_slave_channel(struct device *dev,
 	struct dma_chan *ch = dma_request_slave_channel_reason(dev, name);
 	if (IS_ERR(ch))
 		return NULL;
+
+	dma_cap_set(DMA_PRIVATE, ch->device->cap_mask);
+	ch->device->privatecnt++;
+
 	return ch;
 }
 EXPORT_SYMBOL_GPL(dma_request_slave_channel);
diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index 36e02f0f645e..e00c9b022964 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -6,6 +6,9 @@ config DW_DMAC_CORE
 	tristate
 	select DMA_ENGINE
 
+config DW_DMAC_BIG_ENDIAN_IO
+	bool
+
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA platform driver"
 	select DW_DMAC_CORE
@@ -23,6 +26,3 @@ config DW_DMAC_PCI
 	  Support the Synopsys DesignWare AHB DMA controller on the
 	  platfroms that enumerate it as a PCI device. For example,
 	  Intel Medfield has integrated this GPDMA controller.
-
-config DW_DMAC_BIG_ENDIAN_IO
-	bool
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 1022c2e1a2b0..cf1c87fa1edd 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1746,4 +1746,4 @@ EXPORT_SYMBOL_GPL(dw_dma_enable);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver");
 MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 88853af69489..3e5d4f193005 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -1000,7 +1000,7 @@ static void edma_dma_init(struct edma_cc *ecc, struct dma_device *dma,
 	 * code using dma memcpy must make sure alignment of
 	 * length is at dma->copy_align boundary.
 	 */
-	dma->copy_align = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	dma->copy_align = DMAENGINE_ALIGN_4_BYTES;
 
 	INIT_LIST_HEAD(&dma->channels);
 }
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index f42f71e37e73..7669c7dd1e34 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -99,21 +99,13 @@ static void hsu_dma_chan_start(struct hsu_dma_chan *hsuc)
 
 static void hsu_dma_stop_channel(struct hsu_dma_chan *hsuc)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&hsuc->lock, flags);
 	hsu_chan_disable(hsuc);
 	hsu_chan_writel(hsuc, HSU_CH_DCR, 0);
-	spin_unlock_irqrestore(&hsuc->lock, flags);
 }
 
 static void hsu_dma_start_channel(struct hsu_dma_chan *hsuc)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&hsuc->lock, flags);
 	hsu_dma_chan_start(hsuc);
-	spin_unlock_irqrestore(&hsuc->lock, flags);
 }
 
 static void hsu_dma_start_transfer(struct hsu_dma_chan *hsuc)
@@ -139,9 +131,9 @@ static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc)
 	unsigned long flags;
 	u32 sr;
 
-	spin_lock_irqsave(&hsuc->lock, flags);
+	spin_lock_irqsave(&hsuc->vchan.lock, flags);
 	sr = hsu_chan_readl(hsuc, HSU_CH_SR);
-	spin_unlock_irqrestore(&hsuc->lock, flags);
+	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 
 	return sr;
 }
@@ -273,14 +265,11 @@ static size_t hsu_dma_active_desc_size(struct hsu_dma_chan *hsuc)
 	struct hsu_dma_desc *desc = hsuc->desc;
 	size_t bytes = hsu_dma_desc_size(desc);
 	int i;
-	unsigned long flags;
 
-	spin_lock_irqsave(&hsuc->lock, flags);
 	i = desc->active % HSU_DMA_CHAN_NR_DESC;
 	do {
 		bytes += hsu_chan_readl(hsuc, HSU_CH_DxTSR(i));
 	} while (--i >= 0);
-	spin_unlock_irqrestore(&hsuc->lock, flags);
 
 	return bytes;
 }
@@ -327,24 +316,6 @@ static int hsu_dma_slave_config(struct dma_chan *chan,
 	return 0;
 }
 
-static void hsu_dma_chan_deactivate(struct hsu_dma_chan *hsuc)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&hsuc->lock, flags);
-	hsu_chan_disable(hsuc);
-	spin_unlock_irqrestore(&hsuc->lock, flags);
-}
-
-static void hsu_dma_chan_activate(struct hsu_dma_chan *hsuc)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&hsuc->lock, flags);
-	hsu_chan_enable(hsuc);
-	spin_unlock_irqrestore(&hsuc->lock, flags);
-}
-
 static int hsu_dma_pause(struct dma_chan *chan)
 {
 	struct hsu_dma_chan *hsuc = to_hsu_dma_chan(chan);
@@ -352,7 +323,7 @@ static int hsu_dma_pause(struct dma_chan *chan)
 
 	spin_lock_irqsave(&hsuc->vchan.lock, flags);
 	if (hsuc->desc && hsuc->desc->status == DMA_IN_PROGRESS) {
-		hsu_dma_chan_deactivate(hsuc);
+		hsu_chan_disable(hsuc);
 		hsuc->desc->status = DMA_PAUSED;
 	}
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
@@ -368,7 +339,7 @@ static int hsu_dma_resume(struct dma_chan *chan)
 	spin_lock_irqsave(&hsuc->vchan.lock, flags);
 	if (hsuc->desc && hsuc->desc->status == DMA_PAUSED) {
 		hsuc->desc->status = DMA_IN_PROGRESS;
-		hsu_dma_chan_activate(hsuc);
+		hsu_chan_enable(hsuc);
 	}
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 
@@ -441,8 +412,6 @@ int hsu_dma_probe(struct hsu_dma_chip *chip)
 
 		hsuc->direction = (i & 0x1) ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV;
 		hsuc->reg = addr + i * HSU_DMA_CHAN_LENGTH;
-
-		spin_lock_init(&hsuc->lock);
 	}
 
 	dma_cap_set(DMA_SLAVE, hsu->dma.cap_mask);
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index 0275233cf550..eeb9fff66967 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -78,7 +78,6 @@ struct hsu_dma_chan {
 	struct virt_dma_chan vchan;
 
 	void __iomem *reg;
-	spinlock_t lock;
 
 	/* hardware configuration */
 	enum dma_transfer_direction direction;
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
new file mode 100644
index 000000000000..18c14e1f1414
--- /dev/null
+++ b/drivers/dma/idma64.c
@@ -0,0 +1,710 @@
+/*
+ * Core driver for the Intel integrated DMA 64-bit
+ *
+ * Copyright (C) 2015 Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "idma64.h"
+
+/* Platform driver name */
+#define DRV_NAME		"idma64"
+
+/* For now we support only two channels */
+#define IDMA64_NR_CHAN		2
+
+/* ---------------------------------------------------------------------- */
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void idma64_off(struct idma64 *idma64)
+{
+	unsigned short count = 100;
+
+	dma_writel(idma64, CFG, 0);
+
+	channel_clear_bit(idma64, MASK(XFER), idma64->all_chan_mask);
+	channel_clear_bit(idma64, MASK(BLOCK), idma64->all_chan_mask);
+	channel_clear_bit(idma64, MASK(SRC_TRAN), idma64->all_chan_mask);
+	channel_clear_bit(idma64, MASK(DST_TRAN), idma64->all_chan_mask);
+	channel_clear_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
+
+	do {
+		cpu_relax();
+	} while (dma_readl(idma64, CFG) & IDMA64_CFG_DMA_EN && --count);
+}
+
+static void idma64_on(struct idma64 *idma64)
+{
+	dma_writel(idma64, CFG, IDMA64_CFG_DMA_EN);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void idma64_chan_init(struct idma64 *idma64, struct idma64_chan *idma64c)
+{
+	u32 cfghi = IDMA64C_CFGH_SRC_PER(1) | IDMA64C_CFGH_DST_PER(0);
+	u32 cfglo = 0;
+
+	/* Enforce FIFO drain when channel is suspended */
+	cfglo |= IDMA64C_CFGL_CH_DRAIN;
+
+	/* Set default burst alignment */
+	cfglo |= IDMA64C_CFGL_DST_BURST_ALIGN | IDMA64C_CFGL_SRC_BURST_ALIGN;
+
+	channel_writel(idma64c, CFG_LO, cfglo);
+	channel_writel(idma64c, CFG_HI, cfghi);
+
+	/* Enable interrupts */
+	channel_set_bit(idma64, MASK(XFER), idma64c->mask);
+	channel_set_bit(idma64, MASK(ERROR), idma64c->mask);
+
+	/*
+	 * Enforce the controller to be turned on.
+	 *
+	 * The iDMA is turned off in ->probe() and looses context during system
+	 * suspend / resume cycle. That's why we have to enable it each time we
+	 * use it.
+	 */
+	idma64_on(idma64);
+}
+
+static void idma64_chan_stop(struct idma64 *idma64, struct idma64_chan *idma64c)
+{
+	channel_clear_bit(idma64, CH_EN, idma64c->mask);
+}
+
+static void idma64_chan_start(struct idma64 *idma64, struct idma64_chan *idma64c)
+{
+	struct idma64_desc *desc = idma64c->desc;
+	struct idma64_hw_desc *hw = &desc->hw[0];
+
+	channel_writeq(idma64c, SAR, 0);
+	channel_writeq(idma64c, DAR, 0);
+
+	channel_writel(idma64c, CTL_HI, IDMA64C_CTLH_BLOCK_TS(~0UL));
+	channel_writel(idma64c, CTL_LO, IDMA64C_CTLL_LLP_S_EN | IDMA64C_CTLL_LLP_D_EN);
+
+	channel_writeq(idma64c, LLP, hw->llp);
+
+	channel_set_bit(idma64, CH_EN, idma64c->mask);
+}
+
+static void idma64_stop_transfer(struct idma64_chan *idma64c)
+{
+	struct idma64 *idma64 = to_idma64(idma64c->vchan.chan.device);
+
+	idma64_chan_stop(idma64, idma64c);
+}
+
+static void idma64_start_transfer(struct idma64_chan *idma64c)
+{
+	struct idma64 *idma64 = to_idma64(idma64c->vchan.chan.device);
+	struct virt_dma_desc *vdesc;
+
+	/* Get the next descriptor */
+	vdesc = vchan_next_desc(&idma64c->vchan);
+	if (!vdesc) {
+		idma64c->desc = NULL;
+		return;
+	}
+
+	list_del(&vdesc->node);
+	idma64c->desc = to_idma64_desc(vdesc);
+
+	/* Configure the channel */
+	idma64_chan_init(idma64, idma64c);
+
+	/* Start the channel with a new descriptor */
+	idma64_chan_start(idma64, idma64c);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void idma64_chan_irq(struct idma64 *idma64, unsigned short c,
+		u32 status_err, u32 status_xfer)
+{
+	struct idma64_chan *idma64c = &idma64->chan[c];
+	struct idma64_desc *desc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	desc = idma64c->desc;
+	if (desc) {
+		if (status_err & (1 << c)) {
+			dma_writel(idma64, CLEAR(ERROR), idma64c->mask);
+			desc->status = DMA_ERROR;
+		} else if (status_xfer & (1 << c)) {
+			dma_writel(idma64, CLEAR(XFER), idma64c->mask);
+			desc->status = DMA_COMPLETE;
+			vchan_cookie_complete(&desc->vdesc);
+			idma64_start_transfer(idma64c);
+		}
+
+		/* idma64_start_transfer() updates idma64c->desc */
+		if (idma64c->desc == NULL || desc->status == DMA_ERROR)
+			idma64_stop_transfer(idma64c);
+	}
+	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+}
+
+static irqreturn_t idma64_irq(int irq, void *dev)
+{
+	struct idma64 *idma64 = dev;
+	u32 status = dma_readl(idma64, STATUS_INT);
+	u32 status_xfer;
+	u32 status_err;
+	unsigned short i;
+
+	dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status);
+
+	/* Check if we have any interrupt from the DMA controller */
+	if (!status)
+		return IRQ_NONE;
+
+	/* Disable interrupts */
+	channel_clear_bit(idma64, MASK(XFER), idma64->all_chan_mask);
+	channel_clear_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
+
+	status_xfer = dma_readl(idma64, RAW(XFER));
+	status_err = dma_readl(idma64, RAW(ERROR));
+
+	for (i = 0; i < idma64->dma.chancnt; i++)
+		idma64_chan_irq(idma64, i, status_err, status_xfer);
+
+	/* Re-enable interrupts */
+	channel_set_bit(idma64, MASK(XFER), idma64->all_chan_mask);
+	channel_set_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
+
+	return IRQ_HANDLED;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct idma64_desc *idma64_alloc_desc(unsigned int ndesc)
+{
+	struct idma64_desc *desc;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->hw = kcalloc(ndesc, sizeof(*desc->hw), GFP_NOWAIT);
+	if (!desc->hw) {
+		kfree(desc);
+		return NULL;
+	}
+
+	return desc;
+}
+
+static void idma64_desc_free(struct idma64_chan *idma64c,
+		struct idma64_desc *desc)
+{
+	struct idma64_hw_desc *hw;
+
+	if (desc->ndesc) {
+		unsigned int i = desc->ndesc;
+
+		do {
+			hw = &desc->hw[--i];
+			dma_pool_free(idma64c->pool, hw->lli, hw->llp);
+		} while (i);
+	}
+
+	kfree(desc->hw);
+	kfree(desc);
+}
+
+static void idma64_vdesc_free(struct virt_dma_desc *vdesc)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(vdesc->tx.chan);
+
+	idma64_desc_free(idma64c, to_idma64_desc(vdesc));
+}
+
+static u64 idma64_hw_desc_fill(struct idma64_hw_desc *hw,
+		struct dma_slave_config *config,
+		enum dma_transfer_direction direction, u64 llp)
+{
+	struct idma64_lli *lli = hw->lli;
+	u64 sar, dar;
+	u32 ctlhi = IDMA64C_CTLH_BLOCK_TS(hw->len);
+	u32 ctllo = IDMA64C_CTLL_LLP_S_EN | IDMA64C_CTLL_LLP_D_EN;
+	u32 src_width, dst_width;
+
+	if (direction == DMA_MEM_TO_DEV) {
+		sar = hw->phys;
+		dar = config->dst_addr;
+		ctllo |= IDMA64C_CTLL_DST_FIX | IDMA64C_CTLL_SRC_INC |
+			 IDMA64C_CTLL_FC_M2P;
+		src_width = min_t(u32, 2, __fls(sar | hw->len));
+		dst_width = __fls(config->dst_addr_width);
+	} else {	/* DMA_DEV_TO_MEM */
+		sar = config->src_addr;
+		dar = hw->phys;
+		ctllo |= IDMA64C_CTLL_DST_INC | IDMA64C_CTLL_SRC_FIX |
+			 IDMA64C_CTLL_FC_P2M;
+		src_width = __fls(config->src_addr_width);
+		dst_width = min_t(u32, 2, __fls(dar | hw->len));
+	}
+
+	lli->sar = sar;
+	lli->dar = dar;
+
+	lli->ctlhi = ctlhi;
+	lli->ctllo = ctllo |
+		     IDMA64C_CTLL_SRC_MSIZE(config->src_maxburst) |
+		     IDMA64C_CTLL_DST_MSIZE(config->dst_maxburst) |
+		     IDMA64C_CTLL_DST_WIDTH(dst_width) |
+		     IDMA64C_CTLL_SRC_WIDTH(src_width);
+
+	lli->llp = llp;
+	return hw->llp;
+}
+
+static void idma64_desc_fill(struct idma64_chan *idma64c,
+		struct idma64_desc *desc)
+{
+	struct dma_slave_config *config = &idma64c->config;
+	struct idma64_hw_desc *hw = &desc->hw[desc->ndesc - 1];
+	struct idma64_lli *lli = hw->lli;
+	u64 llp = 0;
+	unsigned int i = desc->ndesc;
+
+	/* Fill the hardware descriptors and link them to a list */
+	do {
+		hw = &desc->hw[--i];
+		llp = idma64_hw_desc_fill(hw, config, desc->direction, llp);
+		desc->length += hw->len;
+	} while (i);
+
+	/* Trigger interrupt after last block */
+	lli->ctllo |= IDMA64C_CTLL_INT_EN;
+}
+
+static struct dma_async_tx_descriptor *idma64_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+	struct idma64_desc *desc;
+	struct scatterlist *sg;
+	unsigned int i;
+
+	desc = idma64_alloc_desc(sg_len);
+	if (!desc)
+		return NULL;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		struct idma64_hw_desc *hw = &desc->hw[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		hw->lli = dma_pool_alloc(idma64c->pool, GFP_NOWAIT, &hw->llp);
+		if (!hw->lli) {
+			desc->ndesc = i;
+			idma64_desc_free(idma64c, desc);
+			return NULL;
+		}
+
+		hw->phys = sg_dma_address(sg);
+		hw->len = sg_dma_len(sg);
+	}
+
+	desc->ndesc = sg_len;
+	desc->direction = direction;
+	desc->status = DMA_IN_PROGRESS;
+
+	idma64_desc_fill(idma64c, desc);
+	return vchan_tx_prep(&idma64c->vchan, &desc->vdesc, flags);
+}
+
+static void idma64_issue_pending(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	if (vchan_issue_pending(&idma64c->vchan) && !idma64c->desc)
+		idma64_start_transfer(idma64c);
+	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+}
+
+static size_t idma64_active_desc_size(struct idma64_chan *idma64c)
+{
+	struct idma64_desc *desc = idma64c->desc;
+	struct idma64_hw_desc *hw;
+	size_t bytes = desc->length;
+	u64 llp;
+	u32 ctlhi;
+	unsigned int i = 0;
+
+	llp = channel_readq(idma64c, LLP);
+	do {
+		hw = &desc->hw[i];
+	} while ((hw->llp != llp) && (++i < desc->ndesc));
+
+	if (!i)
+		return bytes;
+
+	do {
+		bytes -= desc->hw[--i].len;
+	} while (i);
+
+	ctlhi = channel_readl(idma64c, CTL_HI);
+	return bytes - IDMA64C_CTLH_BLOCK_TS(ctlhi);
+}
+
+static enum dma_status idma64_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *state)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+	struct virt_dma_desc *vdesc;
+	enum dma_status status;
+	size_t bytes;
+	unsigned long flags;
+
+	status = dma_cookie_status(chan, cookie, state);
+	if (status == DMA_COMPLETE)
+		return status;
+
+	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	vdesc = vchan_find_desc(&idma64c->vchan, cookie);
+	if (idma64c->desc && cookie == idma64c->desc->vdesc.tx.cookie) {
+		bytes = idma64_active_desc_size(idma64c);
+		dma_set_residue(state, bytes);
+		status = idma64c->desc->status;
+	} else if (vdesc) {
+		bytes = to_idma64_desc(vdesc)->length;
+		dma_set_residue(state, bytes);
+	}
+	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+
+	return status;
+}
+
+static void convert_burst(u32 *maxburst)
+{
+	if (*maxburst)
+		*maxburst = __fls(*maxburst);
+	else
+		*maxburst = 0;
+}
+
+static int idma64_slave_config(struct dma_chan *chan,
+		struct dma_slave_config *config)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+
+	/* Check if chan will be configured for slave transfers */
+	if (!is_slave_direction(config->direction))
+		return -EINVAL;
+
+	memcpy(&idma64c->config, config, sizeof(idma64c->config));
+
+	convert_burst(&idma64c->config.src_maxburst);
+	convert_burst(&idma64c->config.dst_maxburst);
+
+	return 0;
+}
+
+static void idma64_chan_deactivate(struct idma64_chan *idma64c)
+{
+	unsigned short count = 100;
+	u32 cfglo;
+
+	cfglo = channel_readl(idma64c, CFG_LO);
+	channel_writel(idma64c, CFG_LO, cfglo | IDMA64C_CFGL_CH_SUSP);
+	do {
+		udelay(1);
+		cfglo = channel_readl(idma64c, CFG_LO);
+	} while (!(cfglo & IDMA64C_CFGL_FIFO_EMPTY) && --count);
+}
+
+static void idma64_chan_activate(struct idma64_chan *idma64c)
+{
+	u32 cfglo;
+
+	cfglo = channel_readl(idma64c, CFG_LO);
+	channel_writel(idma64c, CFG_LO, cfglo & ~IDMA64C_CFGL_CH_SUSP);
+}
+
+static int idma64_pause(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	if (idma64c->desc && idma64c->desc->status == DMA_IN_PROGRESS) {
+		idma64_chan_deactivate(idma64c);
+		idma64c->desc->status = DMA_PAUSED;
+	}
+	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+
+	return 0;
+}
+
+static int idma64_resume(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	if (idma64c->desc && idma64c->desc->status == DMA_PAUSED) {
+		idma64c->desc->status = DMA_IN_PROGRESS;
+		idma64_chan_activate(idma64c);
+	}
+	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+
+	return 0;
+}
+
+static int idma64_terminate_all(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	idma64_chan_deactivate(idma64c);
+	idma64_stop_transfer(idma64c);
+	if (idma64c->desc) {
+		idma64_vdesc_free(&idma64c->desc->vdesc);
+		idma64c->desc = NULL;
+	}
+	vchan_get_all_descriptors(&idma64c->vchan, &head);
+	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&idma64c->vchan, &head);
+	return 0;
+}
+
+static int idma64_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+
+	/* Create a pool of consistent memory blocks for hardware descriptors */
+	idma64c->pool = dma_pool_create(dev_name(chan2dev(chan)),
+					chan->device->dev,
+					sizeof(struct idma64_lli), 8, 0);
+	if (!idma64c->pool) {
+		dev_err(chan2dev(chan), "No memory for descriptors\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void idma64_free_chan_resources(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+
+	vchan_free_chan_resources(to_virt_chan(chan));
+	dma_pool_destroy(idma64c->pool);
+	idma64c->pool = NULL;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#define IDMA64_BUSWIDTHS				\
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE)		|	\
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES)		|	\
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
+
+static int idma64_probe(struct idma64_chip *chip)
+{
+	struct idma64 *idma64;
+	unsigned short nr_chan = IDMA64_NR_CHAN;
+	unsigned short i;
+	int ret;
+
+	idma64 = devm_kzalloc(chip->dev, sizeof(*idma64), GFP_KERNEL);
+	if (!idma64)
+		return -ENOMEM;
+
+	idma64->regs = chip->regs;
+	chip->idma64 = idma64;
+
+	idma64->chan = devm_kcalloc(chip->dev, nr_chan, sizeof(*idma64->chan),
+				    GFP_KERNEL);
+	if (!idma64->chan)
+		return -ENOMEM;
+
+	idma64->all_chan_mask = (1 << nr_chan) - 1;
+
+	/* Turn off iDMA controller */
+	idma64_off(idma64);
+
+	ret = devm_request_irq(chip->dev, chip->irq, idma64_irq, IRQF_SHARED,
+			       dev_name(chip->dev), idma64);
+	if (ret)
+		return ret;
+
+	INIT_LIST_HEAD(&idma64->dma.channels);
+	for (i = 0; i < nr_chan; i++) {
+		struct idma64_chan *idma64c = &idma64->chan[i];
+
+		idma64c->vchan.desc_free = idma64_vdesc_free;
+		vchan_init(&idma64c->vchan, &idma64->dma);
+
+		idma64c->regs = idma64->regs + i * IDMA64_CH_LENGTH;
+		idma64c->mask = BIT(i);
+	}
+
+	dma_cap_set(DMA_SLAVE, idma64->dma.cap_mask);
+	dma_cap_set(DMA_PRIVATE, idma64->dma.cap_mask);
+
+	idma64->dma.device_alloc_chan_resources = idma64_alloc_chan_resources;
+	idma64->dma.device_free_chan_resources = idma64_free_chan_resources;
+
+	idma64->dma.device_prep_slave_sg = idma64_prep_slave_sg;
+
+	idma64->dma.device_issue_pending = idma64_issue_pending;
+	idma64->dma.device_tx_status = idma64_tx_status;
+
+	idma64->dma.device_config = idma64_slave_config;
+	idma64->dma.device_pause = idma64_pause;
+	idma64->dma.device_resume = idma64_resume;
+	idma64->dma.device_terminate_all = idma64_terminate_all;
+
+	idma64->dma.src_addr_widths = IDMA64_BUSWIDTHS;
+	idma64->dma.dst_addr_widths = IDMA64_BUSWIDTHS;
+	idma64->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	idma64->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	idma64->dma.dev = chip->dev;
+
+	ret = dma_async_device_register(&idma64->dma);
+	if (ret)
+		return ret;
+
+	dev_info(chip->dev, "Found Intel integrated DMA 64-bit\n");
+	return 0;
+}
+
+static int idma64_remove(struct idma64_chip *chip)
+{
+	struct idma64 *idma64 = chip->idma64;
+	unsigned short i;
+
+	dma_async_device_unregister(&idma64->dma);
+
+	/*
+	 * Explicitly call devm_request_irq() to avoid the side effects with
+	 * the scheduled tasklets.
+	 */
+	devm_free_irq(chip->dev, chip->irq, idma64);
+
+	for (i = 0; i < idma64->dma.chancnt; i++) {
+		struct idma64_chan *idma64c = &idma64->chan[i];
+
+		tasklet_kill(&idma64c->vchan.task);
+	}
+
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int idma64_platform_probe(struct platform_device *pdev)
+{
+	struct idma64_chip *chip;
+	struct device *dev = &pdev->dev;
+	struct resource *mem;
+	int ret;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->irq = platform_get_irq(pdev, 0);
+	if (chip->irq < 0)
+		return chip->irq;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	chip->regs = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(chip->regs))
+		return PTR_ERR(chip->regs);
+
+	ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret)
+		return ret;
+
+	chip->dev = dev;
+
+	ret = idma64_probe(chip);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, chip);
+	return 0;
+}
+
+static int idma64_platform_remove(struct platform_device *pdev)
+{
+	struct idma64_chip *chip = platform_get_drvdata(pdev);
+
+	return idma64_remove(chip);
+}
+
+#ifdef CONFIG_PM_SLEEP
+
+static int idma64_pm_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct idma64_chip *chip = platform_get_drvdata(pdev);
+
+	idma64_off(chip->idma64);
+	return 0;
+}
+
+static int idma64_pm_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct idma64_chip *chip = platform_get_drvdata(pdev);
+
+	idma64_on(chip->idma64);
+	return 0;
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct dev_pm_ops idma64_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(idma64_pm_suspend, idma64_pm_resume)
+};
+
+static struct platform_driver idma64_platform_driver = {
+	.probe		= idma64_platform_probe,
+	.remove		= idma64_platform_remove,
+	.driver = {
+		.name	= DRV_NAME,
+		.pm	= &idma64_dev_pm_ops,
+	},
+};
+
+module_platform_driver(idma64_platform_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("iDMA64 core driver");
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/dma/idma64.h b/drivers/dma/idma64.h
new file mode 100644
index 000000000000..a4d99685a7c4
--- /dev/null
+++ b/drivers/dma/idma64.h
@@ -0,0 +1,233 @@
+/*
+ * Driver for the Intel integrated DMA 64-bit
+ *
+ * Copyright (C) 2015 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __DMA_IDMA64_H__
+#define __DMA_IDMA64_H__
+
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include "virt-dma.h"
+
+/* Channel registers */
+
+#define IDMA64_CH_SAR		0x00	/* Source Address Register */
+#define IDMA64_CH_DAR		0x08	/* Destination Address Register */
+#define IDMA64_CH_LLP		0x10	/* Linked List Pointer */
+#define IDMA64_CH_CTL_LO	0x18	/* Control Register Low */
+#define IDMA64_CH_CTL_HI	0x1c	/* Control Register High */
+#define IDMA64_CH_SSTAT		0x20
+#define IDMA64_CH_DSTAT		0x28
+#define IDMA64_CH_SSTATAR	0x30
+#define IDMA64_CH_DSTATAR	0x38
+#define IDMA64_CH_CFG_LO	0x40	/* Configuration Register Low */
+#define IDMA64_CH_CFG_HI	0x44	/* Configuration Register High */
+#define IDMA64_CH_SGR		0x48
+#define IDMA64_CH_DSR		0x50
+
+#define IDMA64_CH_LENGTH	0x58
+
+/* Bitfields in CTL_LO */
+#define IDMA64C_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
+#define IDMA64C_CTLL_DST_WIDTH(x)	((x) << 1)	/* bytes per element */
+#define IDMA64C_CTLL_SRC_WIDTH(x)	((x) << 4)
+#define IDMA64C_CTLL_DST_INC		(0 << 8)	/* DAR update/not */
+#define IDMA64C_CTLL_DST_FIX		(1 << 8)
+#define IDMA64C_CTLL_SRC_INC		(0 << 10)	/* SAR update/not */
+#define IDMA64C_CTLL_SRC_FIX		(1 << 10)
+#define IDMA64C_CTLL_DST_MSIZE(x)	((x) << 11)	/* burst, #elements */
+#define IDMA64C_CTLL_SRC_MSIZE(x)	((x) << 14)
+#define IDMA64C_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
+#define IDMA64C_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
+#define IDMA64C_CTLL_LLP_D_EN		(1 << 27)	/* dest block chain */
+#define IDMA64C_CTLL_LLP_S_EN		(1 << 28)	/* src block chain */
+
+/* Bitfields in CTL_HI */
+#define IDMA64C_CTLH_BLOCK_TS(x)	((x) & ((1 << 17) - 1))
+#define IDMA64C_CTLH_DONE		(1 << 17)
+
+/* Bitfields in CFG_LO */
+#define IDMA64C_CFGL_DST_BURST_ALIGN	(1 << 0)	/* dst burst align */
+#define IDMA64C_CFGL_SRC_BURST_ALIGN	(1 << 1)	/* src burst align */
+#define IDMA64C_CFGL_CH_SUSP		(1 << 8)
+#define IDMA64C_CFGL_FIFO_EMPTY		(1 << 9)
+#define IDMA64C_CFGL_CH_DRAIN		(1 << 10)	/* drain FIFO */
+#define IDMA64C_CFGL_DST_OPT_BL		(1 << 20)	/* optimize dst burst length */
+#define IDMA64C_CFGL_SRC_OPT_BL		(1 << 21)	/* optimize src burst length */
+
+/* Bitfields in CFG_HI */
+#define IDMA64C_CFGH_SRC_PER(x)		((x) << 0)	/* src peripheral */
+#define IDMA64C_CFGH_DST_PER(x)		((x) << 4)	/* dst peripheral */
+#define IDMA64C_CFGH_RD_ISSUE_THD(x)	((x) << 8)
+#define IDMA64C_CFGH_RW_ISSUE_THD(x)	((x) << 18)
+
+/* Interrupt registers */
+
+#define IDMA64_INT_XFER		0x00
+#define IDMA64_INT_BLOCK	0x08
+#define IDMA64_INT_SRC_TRAN	0x10
+#define IDMA64_INT_DST_TRAN	0x18
+#define IDMA64_INT_ERROR	0x20
+
+#define IDMA64_RAW(x)		(0x2c0 + IDMA64_INT_##x)	/* r */
+#define IDMA64_STATUS(x)	(0x2e8 + IDMA64_INT_##x)	/* r (raw & mask) */
+#define IDMA64_MASK(x)		(0x310 + IDMA64_INT_##x)	/* rw (set = irq enabled) */
+#define IDMA64_CLEAR(x)		(0x338 + IDMA64_INT_##x)	/* w (ack, affects "raw") */
+
+/* Common registers */
+
+#define IDMA64_STATUS_INT	0x360	/* r */
+#define IDMA64_CFG		0x398
+#define IDMA64_CH_EN		0x3a0
+
+/* Bitfields in CFG */
+#define IDMA64_CFG_DMA_EN		(1 << 0)
+
+/* Hardware descriptor for Linked LIst transfers */
+struct idma64_lli {
+	u64		sar;
+	u64		dar;
+	u64		llp;
+	u32		ctllo;
+	u32		ctlhi;
+	u32		sstat;
+	u32		dstat;
+};
+
+struct idma64_hw_desc {
+	struct idma64_lli *lli;
+	dma_addr_t llp;
+	dma_addr_t phys;
+	unsigned int len;
+};
+
+struct idma64_desc {
+	struct virt_dma_desc vdesc;
+	enum dma_transfer_direction direction;
+	struct idma64_hw_desc *hw;
+	unsigned int ndesc;
+	size_t length;
+	enum dma_status status;
+};
+
+static inline struct idma64_desc *to_idma64_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct idma64_desc, vdesc);
+}
+
+struct idma64_chan {
+	struct virt_dma_chan vchan;
+
+	void __iomem *regs;
+
+	/* hardware configuration */
+	enum dma_transfer_direction direction;
+	unsigned int mask;
+	struct dma_slave_config config;
+
+	void *pool;
+	struct idma64_desc *desc;
+};
+
+static inline struct idma64_chan *to_idma64_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct idma64_chan, vchan.chan);
+}
+
+#define channel_set_bit(idma64, reg, mask)	\
+	dma_writel(idma64, reg, ((mask) << 8) | (mask))
+#define channel_clear_bit(idma64, reg, mask)	\
+	dma_writel(idma64, reg, ((mask) << 8) | 0)
+
+static inline u32 idma64c_readl(struct idma64_chan *idma64c, int offset)
+{
+	return readl(idma64c->regs + offset);
+}
+
+static inline void idma64c_writel(struct idma64_chan *idma64c, int offset,
+				  u32 value)
+{
+	writel(value, idma64c->regs + offset);
+}
+
+#define channel_readl(idma64c, reg)		\
+	idma64c_readl(idma64c, IDMA64_CH_##reg)
+#define channel_writel(idma64c, reg, value)	\
+	idma64c_writel(idma64c, IDMA64_CH_##reg, (value))
+
+static inline u64 idma64c_readq(struct idma64_chan *idma64c, int offset)
+{
+	u64 l, h;
+
+	l = idma64c_readl(idma64c, offset);
+	h = idma64c_readl(idma64c, offset + 4);
+
+	return l | (h << 32);
+}
+
+static inline void idma64c_writeq(struct idma64_chan *idma64c, int offset,
+				  u64 value)
+{
+	idma64c_writel(idma64c, offset, value);
+	idma64c_writel(idma64c, offset + 4, value >> 32);
+}
+
+#define channel_readq(idma64c, reg)		\
+	idma64c_readq(idma64c, IDMA64_CH_##reg)
+#define channel_writeq(idma64c, reg, value)	\
+	idma64c_writeq(idma64c, IDMA64_CH_##reg, (value))
+
+struct idma64 {
+	struct dma_device dma;
+
+	void __iomem *regs;
+
+	/* channels */
+	unsigned short all_chan_mask;
+	struct idma64_chan *chan;
+};
+
+static inline struct idma64 *to_idma64(struct dma_device *ddev)
+{
+	return container_of(ddev, struct idma64, dma);
+}
+
+static inline u32 idma64_readl(struct idma64 *idma64, int offset)
+{
+	return readl(idma64->regs + offset);
+}
+
+static inline void idma64_writel(struct idma64 *idma64, int offset, u32 value)
+{
+	writel(value, idma64->regs + offset);
+}
+
+#define dma_readl(idma64, reg)			\
+	idma64_readl(idma64, IDMA64_##reg)
+#define dma_writel(idma64, reg, value)		\
+	idma64_writel(idma64, IDMA64_##reg, (value))
+
+/**
+ * struct idma64_chip - representation of DesignWare DMA controller hardware
+ * @dev:		struct device of the DMA controller
+ * @irq:		irq line
+ * @regs:		memory mapped I/O space
+ * @idma64:		struct idma64 that is filed by idma64_probe()
+ */
+struct idma64_chip {
+	struct device	*dev;
+	int		irq;
+	void __iomem	*regs;
+	struct idma64	*idma64;
+};
+
+#endif /* __DMA_IDMA64_H__ */
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 865501fcc67d..48d85f8b95fe 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -1083,8 +1083,12 @@ static int __init imxdma_probe(struct platform_device *pdev)
 	if (IS_ERR(imxdma->dma_ahb))
 		return PTR_ERR(imxdma->dma_ahb);
 
-	clk_prepare_enable(imxdma->dma_ipg);
-	clk_prepare_enable(imxdma->dma_ahb);
+	ret = clk_prepare_enable(imxdma->dma_ipg);
+	if (ret)
+		return ret;
+	ret = clk_prepare_enable(imxdma->dma_ahb);
+	if (ret)
+		goto disable_dma_ipg_clk;
 
 	/* reset DMA module */
 	imx_dmav1_writel(imxdma, DCR_DRST, DMA_DCR);
@@ -1094,20 +1098,20 @@ static int __init imxdma_probe(struct platform_device *pdev)
 				       dma_irq_handler, 0, "DMA", imxdma);
 		if (ret) {
 			dev_warn(imxdma->dev, "Can't register IRQ for DMA\n");
-			goto err;
+			goto disable_dma_ahb_clk;
 		}
 
 		irq_err = platform_get_irq(pdev, 1);
 		if (irq_err < 0) {
 			ret = irq_err;
-			goto err;
+			goto disable_dma_ahb_clk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, irq_err,
 				       imxdma_err_handler, 0, "DMA", imxdma);
 		if (ret) {
 			dev_warn(imxdma->dev, "Can't register ERRIRQ for DMA\n");
-			goto err;
+			goto disable_dma_ahb_clk;
 		}
 	}
 
@@ -1144,7 +1148,7 @@ static int __init imxdma_probe(struct platform_device *pdev)
 				dev_warn(imxdma->dev, "Can't register IRQ %d "
 					 "for DMA channel %d\n",
 					 irq + i, i);
-				goto err;
+				goto disable_dma_ahb_clk;
 			}
 			init_timer(&imxdmac->watchdog);
 			imxdmac->watchdog.function = &imxdma_watchdog;
@@ -1183,14 +1187,14 @@ static int __init imxdma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, imxdma);
 
-	imxdma->dma_device.copy_align = 2; /* 2^2 = 4 bytes alignment */
+	imxdma->dma_device.copy_align = DMAENGINE_ALIGN_4_BYTES;
 	imxdma->dma_device.dev->dma_parms = &imxdma->dma_parms;
 	dma_set_max_seg_size(imxdma->dma_device.dev, 0xffffff);
 
 	ret = dma_async_device_register(&imxdma->dma_device);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to register\n");
-		goto err;
+		goto disable_dma_ahb_clk;
 	}
 
 	if (pdev->dev.of_node) {
@@ -1206,9 +1210,10 @@ static int __init imxdma_probe(struct platform_device *pdev)
 
 err_of_dma_controller:
 	dma_async_device_unregister(&imxdma->dma_device);
-err:
-	clk_disable_unprepare(imxdma->dma_ipg);
+disable_dma_ahb_clk:
 	clk_disable_unprepare(imxdma->dma_ahb);
+disable_dma_ipg_clk:
+	clk_disable_unprepare(imxdma->dma_ipg);
 	return ret;
 }
 
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 77b6aab04f47..9d375bc7590a 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -35,12 +35,16 @@
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 
 #include <asm/irq.h>
 #include <linux/platform_data/dma-imx-sdma.h>
 #include <linux/platform_data/dma-imx.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 
 #include "dmaengine.h"
 
@@ -124,6 +128,56 @@
 #define CHANGE_ENDIANNESS   0x80
 
 /*
+ *  p_2_p watermark_level description
+ *	Bits		Name			Description
+ *	0-7		Lower WML		Lower watermark level
+ *	8		PS			1: Pad Swallowing
+ *						0: No Pad Swallowing
+ *	9		PA			1: Pad Adding
+ *						0: No Pad Adding
+ *	10		SPDIF			If this bit is set both source
+ *						and destination are on SPBA
+ *	11		Source Bit(SP)		1: Source on SPBA
+ *						0: Source on AIPS
+ *	12		Destination Bit(DP)	1: Destination on SPBA
+ *						0: Destination on AIPS
+ *	13-15		---------		MUST BE 0
+ *	16-23		Higher WML		HWML
+ *	24-27		N			Total number of samples after
+ *						which Pad adding/Swallowing
+ *						must be done. It must be odd.
+ *	28		Lower WML Event(LWE)	SDMA events reg to check for
+ *						LWML event mask
+ *						0: LWE in EVENTS register
+ *						1: LWE in EVENTS2 register
+ *	29		Higher WML Event(HWE)	SDMA events reg to check for
+ *						HWML event mask
+ *						0: HWE in EVENTS register
+ *						1: HWE in EVENTS2 register
+ *	30		---------		MUST BE 0
+ *	31		CONT			1: Amount of samples to be
+ *						transferred is unknown and
+ *						script will keep on
+ *						transferring samples as long as
+ *						both events are detected and
+ *						script must be manually stopped
+ *						by the application
+ *						0: The amount of samples to be
+ *						transferred is equal to the
+ *						count field of mode word
+ */
+#define SDMA_WATERMARK_LEVEL_LWML	0xFF
+#define SDMA_WATERMARK_LEVEL_PS		BIT(8)
+#define SDMA_WATERMARK_LEVEL_PA		BIT(9)
+#define SDMA_WATERMARK_LEVEL_SPDIF	BIT(10)
+#define SDMA_WATERMARK_LEVEL_SP		BIT(11)
+#define SDMA_WATERMARK_LEVEL_DP		BIT(12)
+#define SDMA_WATERMARK_LEVEL_HWML	(0xFF << 16)
+#define SDMA_WATERMARK_LEVEL_LWE	BIT(28)
+#define SDMA_WATERMARK_LEVEL_HWE	BIT(29)
+#define SDMA_WATERMARK_LEVEL_CONT	BIT(31)
+
+/*
  * Mode/Count of data node descriptors - IPCv2
  */
 struct sdma_mode_count {
@@ -259,8 +313,9 @@ struct sdma_channel {
 	struct sdma_buffer_descriptor	*bd;
 	dma_addr_t			bd_phys;
 	unsigned int			pc_from_device, pc_to_device;
+	unsigned int			device_to_device;
 	unsigned long			flags;
-	dma_addr_t			per_address;
+	dma_addr_t			per_address, per_address2;
 	unsigned long			event_mask[2];
 	unsigned long			watermark_level;
 	u32				shp_addr, per_addr;
@@ -328,6 +383,8 @@ struct sdma_engine {
 	u32				script_number;
 	struct sdma_script_start_addrs	*script_addrs;
 	const struct sdma_driver_data	*drvdata;
+	u32				spba_start_addr;
+	u32				spba_end_addr;
 };
 
 static struct sdma_driver_data sdma_imx31 = {
@@ -705,6 +762,7 @@ static void sdma_get_pc(struct sdma_channel *sdmac,
 
 	sdmac->pc_from_device = 0;
 	sdmac->pc_to_device = 0;
+	sdmac->device_to_device = 0;
 
 	switch (peripheral_type) {
 	case IMX_DMATYPE_MEMORY:
@@ -780,6 +838,7 @@ static void sdma_get_pc(struct sdma_channel *sdmac,
 
 	sdmac->pc_from_device = per_2_emi;
 	sdmac->pc_to_device = emi_2_per;
+	sdmac->device_to_device = per_2_per;
 }
 
 static int sdma_load_context(struct sdma_channel *sdmac)
@@ -792,11 +851,12 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 	int ret;
 	unsigned long flags;
 
-	if (sdmac->direction == DMA_DEV_TO_MEM) {
+	if (sdmac->direction == DMA_DEV_TO_MEM)
 		load_address = sdmac->pc_from_device;
-	} else {
+	else if (sdmac->direction == DMA_DEV_TO_DEV)
+		load_address = sdmac->device_to_device;
+	else
 		load_address = sdmac->pc_to_device;
-	}
 
 	if (load_address < 0)
 		return load_address;
@@ -851,6 +911,46 @@ static int sdma_disable_channel(struct dma_chan *chan)
 	return 0;
 }
 
+static void sdma_set_watermarklevel_for_p2p(struct sdma_channel *sdmac)
+{
+	struct sdma_engine *sdma = sdmac->sdma;
+
+	int lwml = sdmac->watermark_level & SDMA_WATERMARK_LEVEL_LWML;
+	int hwml = (sdmac->watermark_level & SDMA_WATERMARK_LEVEL_HWML) >> 16;
+
+	set_bit(sdmac->event_id0 % 32, &sdmac->event_mask[1]);
+	set_bit(sdmac->event_id1 % 32, &sdmac->event_mask[0]);
+
+	if (sdmac->event_id0 > 31)
+		sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_LWE;
+
+	if (sdmac->event_id1 > 31)
+		sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_HWE;
+
+	/*
+	 * If LWML(src_maxburst) > HWML(dst_maxburst), we need
+	 * swap LWML and HWML of INFO(A.3.2.5.1), also need swap
+	 * r0(event_mask[1]) and r1(event_mask[0]).
+	 */
+	if (lwml > hwml) {
+		sdmac->watermark_level &= ~(SDMA_WATERMARK_LEVEL_LWML |
+						SDMA_WATERMARK_LEVEL_HWML);
+		sdmac->watermark_level |= hwml;
+		sdmac->watermark_level |= lwml << 16;
+		swap(sdmac->event_mask[0], sdmac->event_mask[1]);
+	}
+
+	if (sdmac->per_address2 >= sdma->spba_start_addr &&
+			sdmac->per_address2 <= sdma->spba_end_addr)
+		sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_SP;
+
+	if (sdmac->per_address >= sdma->spba_start_addr &&
+			sdmac->per_address <= sdma->spba_end_addr)
+		sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_DP;
+
+	sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_CONT;
+}
+
 static int sdma_config_channel(struct dma_chan *chan)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
@@ -869,6 +969,12 @@ static int sdma_config_channel(struct dma_chan *chan)
 		sdma_event_enable(sdmac, sdmac->event_id0);
 	}
 
+	if (sdmac->event_id1) {
+		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
+			return -EINVAL;
+		sdma_event_enable(sdmac, sdmac->event_id1);
+	}
+
 	switch (sdmac->peripheral_type) {
 	case IMX_DMATYPE_DSP:
 		sdma_config_ownership(sdmac, false, true, true);
@@ -887,19 +993,17 @@ static int sdma_config_channel(struct dma_chan *chan)
 			(sdmac->peripheral_type != IMX_DMATYPE_DSP)) {
 		/* Handle multiple event channels differently */
 		if (sdmac->event_id1) {
-			sdmac->event_mask[1] = BIT(sdmac->event_id1 % 32);
-			if (sdmac->event_id1 > 31)
-				__set_bit(31, &sdmac->watermark_level);
-			sdmac->event_mask[0] = BIT(sdmac->event_id0 % 32);
-			if (sdmac->event_id0 > 31)
-				__set_bit(30, &sdmac->watermark_level);
-		} else {
+			if (sdmac->peripheral_type == IMX_DMATYPE_ASRC_SP ||
+			    sdmac->peripheral_type == IMX_DMATYPE_ASRC)
+				sdma_set_watermarklevel_for_p2p(sdmac);
+		} else
 			__set_bit(sdmac->event_id0, sdmac->event_mask);
-		}
+
 		/* Watermark Level */
 		sdmac->watermark_level |= sdmac->watermark_level;
 		/* Address */
 		sdmac->shp_addr = sdmac->per_address;
+		sdmac->per_addr = sdmac->per_address2;
 	} else {
 		sdmac->watermark_level = 0; /* FIXME: M3_BASE_ADDRESS */
 	}
@@ -987,17 +1091,22 @@ static int sdma_alloc_chan_resources(struct dma_chan *chan)
 
 	sdmac->peripheral_type = data->peripheral_type;
 	sdmac->event_id0 = data->dma_request;
+	sdmac->event_id1 = data->dma_request2;
 
-	clk_enable(sdmac->sdma->clk_ipg);
-	clk_enable(sdmac->sdma->clk_ahb);
+	ret = clk_enable(sdmac->sdma->clk_ipg);
+	if (ret)
+		return ret;
+	ret = clk_enable(sdmac->sdma->clk_ahb);
+	if (ret)
+		goto disable_clk_ipg;
 
 	ret = sdma_request_channel(sdmac);
 	if (ret)
-		return ret;
+		goto disable_clk_ahb;
 
 	ret = sdma_set_channel_priority(sdmac, prio);
 	if (ret)
-		return ret;
+		goto disable_clk_ahb;
 
 	dma_async_tx_descriptor_init(&sdmac->desc, chan);
 	sdmac->desc.tx_submit = sdma_tx_submit;
@@ -1005,6 +1114,12 @@ static int sdma_alloc_chan_resources(struct dma_chan *chan)
 	sdmac->desc.flags = DMA_CTRL_ACK;
 
 	return 0;
+
+disable_clk_ahb:
+	clk_disable(sdmac->sdma->clk_ahb);
+disable_clk_ipg:
+	clk_disable(sdmac->sdma->clk_ipg);
+	return ret;
 }
 
 static void sdma_free_chan_resources(struct dma_chan *chan)
@@ -1221,6 +1336,14 @@ static int sdma_config(struct dma_chan *chan,
 		sdmac->watermark_level = dmaengine_cfg->src_maxburst *
 			dmaengine_cfg->src_addr_width;
 		sdmac->word_size = dmaengine_cfg->src_addr_width;
+	} else if (dmaengine_cfg->direction == DMA_DEV_TO_DEV) {
+		sdmac->per_address2 = dmaengine_cfg->src_addr;
+		sdmac->per_address = dmaengine_cfg->dst_addr;
+		sdmac->watermark_level = dmaengine_cfg->src_maxburst &
+			SDMA_WATERMARK_LEVEL_LWML;
+		sdmac->watermark_level |= (dmaengine_cfg->dst_maxburst << 16) &
+			SDMA_WATERMARK_LEVEL_HWML;
+		sdmac->word_size = dmaengine_cfg->dst_addr_width;
 	} else {
 		sdmac->per_address = dmaengine_cfg->dst_addr;
 		sdmac->watermark_level = dmaengine_cfg->dst_maxburst *
@@ -1337,6 +1460,72 @@ err_firmware:
 	release_firmware(fw);
 }
 
+#define EVENT_REMAP_CELLS 3
+
+static int __init sdma_event_remap(struct sdma_engine *sdma)
+{
+	struct device_node *np = sdma->dev->of_node;
+	struct device_node *gpr_np = of_parse_phandle(np, "gpr", 0);
+	struct property *event_remap;
+	struct regmap *gpr;
+	char propname[] = "fsl,sdma-event-remap";
+	u32 reg, val, shift, num_map, i;
+	int ret = 0;
+
+	if (IS_ERR(np) || IS_ERR(gpr_np))
+		goto out;
+
+	event_remap = of_find_property(np, propname, NULL);
+	num_map = event_remap ? (event_remap->length / sizeof(u32)) : 0;
+	if (!num_map) {
+		dev_warn(sdma->dev, "no event needs to be remapped\n");
+		goto out;
+	} else if (num_map % EVENT_REMAP_CELLS) {
+		dev_err(sdma->dev, "the property %s must modulo %d\n",
+				propname, EVENT_REMAP_CELLS);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	gpr = syscon_node_to_regmap(gpr_np);
+	if (IS_ERR(gpr)) {
+		dev_err(sdma->dev, "failed to get gpr regmap\n");
+		ret = PTR_ERR(gpr);
+		goto out;
+	}
+
+	for (i = 0; i < num_map; i += EVENT_REMAP_CELLS) {
+		ret = of_property_read_u32_index(np, propname, i, &reg);
+		if (ret) {
+			dev_err(sdma->dev, "failed to read property %s index %d\n",
+					propname, i);
+			goto out;
+		}
+
+		ret = of_property_read_u32_index(np, propname, i + 1, &shift);
+		if (ret) {
+			dev_err(sdma->dev, "failed to read property %s index %d\n",
+					propname, i + 1);
+			goto out;
+		}
+
+		ret = of_property_read_u32_index(np, propname, i + 2, &val);
+		if (ret) {
+			dev_err(sdma->dev, "failed to read property %s index %d\n",
+					propname, i + 2);
+			goto out;
+		}
+
+		regmap_update_bits(gpr, reg, BIT(shift), val << shift);
+	}
+
+out:
+	if (!IS_ERR(gpr_np))
+		of_node_put(gpr_np);
+
+	return ret;
+}
+
 static int sdma_get_firmware(struct sdma_engine *sdma,
 		const char *fw_name)
 {
@@ -1354,8 +1543,12 @@ static int sdma_init(struct sdma_engine *sdma)
 	int i, ret;
 	dma_addr_t ccb_phys;
 
-	clk_enable(sdma->clk_ipg);
-	clk_enable(sdma->clk_ahb);
+	ret = clk_enable(sdma->clk_ipg);
+	if (ret)
+		return ret;
+	ret = clk_enable(sdma->clk_ahb);
+	if (ret)
+		goto disable_clk_ipg;
 
 	/* Be sure SDMA has not started yet */
 	writel_relaxed(0, sdma->regs + SDMA_H_C0PTR);
@@ -1411,8 +1604,9 @@ static int sdma_init(struct sdma_engine *sdma)
 	return 0;
 
 err_dma_alloc:
-	clk_disable(sdma->clk_ipg);
 	clk_disable(sdma->clk_ahb);
+disable_clk_ipg:
+	clk_disable(sdma->clk_ipg);
 	dev_err(sdma->dev, "initialisation failed with %d\n", ret);
 	return ret;
 }
@@ -1444,6 +1638,14 @@ static struct dma_chan *sdma_xlate(struct of_phandle_args *dma_spec,
 	data.dma_request = dma_spec->args[0];
 	data.peripheral_type = dma_spec->args[1];
 	data.priority = dma_spec->args[2];
+	/*
+	 * init dma_request2 to zero, which is not used by the dts.
+	 * For P2P, dma_request2 is init from dma_request_channel(),
+	 * chan->private will point to the imx_dma_data, and in
+	 * device_alloc_chan_resources(), imx_dma_data.dma_request2 will
+	 * be set to sdmac->event_id1.
+	 */
+	data.dma_request2 = 0;
 
 	return dma_request_channel(mask, sdma_filter_fn, &data);
 }
@@ -1453,10 +1655,12 @@ static int sdma_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id =
 			of_match_device(sdma_dt_ids, &pdev->dev);
 	struct device_node *np = pdev->dev.of_node;
+	struct device_node *spba_bus;
 	const char *fw_name;
 	int ret;
 	int irq;
 	struct resource *iores;
+	struct resource spba_res;
 	struct sdma_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int i;
 	struct sdma_engine *sdma;
@@ -1551,6 +1755,10 @@ static int sdma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_init;
 
+	ret = sdma_event_remap(sdma);
+	if (ret)
+		goto err_init;
+
 	if (sdma->drvdata->script_addrs)
 		sdma_add_scripts(sdma, sdma->drvdata->script_addrs);
 	if (pdata && pdata->script_addrs)
@@ -1608,6 +1816,14 @@ static int sdma_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "failed to register controller\n");
 			goto err_register;
 		}
+
+		spba_bus = of_find_compatible_node(NULL, NULL, "fsl,spba-bus");
+		ret = of_address_to_resource(spba_bus, 0, &spba_res);
+		if (!ret) {
+			sdma->spba_start_addr = spba_res.start;
+			sdma->spba_end_addr = spba_res.end;
+		}
+		of_node_put(spba_bus);
 	}
 
 	dev_info(sdma->dev, "initialized\n");
diff --git a/drivers/dma/ioat/Makefile b/drivers/dma/ioat/Makefile
index 0ff7270af25b..cf5fedbe2b75 100644
--- a/drivers/dma/ioat/Makefile
+++ b/drivers/dma/ioat/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
-ioatdma-y := pci.o dma.o dma_v2.o dma_v3.o dca.o
+ioatdma-y := init.o dma.o prep.o dca.o sysfs.o
diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c
index ea1e107ae884..2cb7c308d5c7 100644
--- a/drivers/dma/ioat/dca.c
+++ b/drivers/dma/ioat/dca.c
@@ -31,7 +31,6 @@
 
 #include "dma.h"
 #include "registers.h"
-#include "dma_v2.h"
 
 /*
  * Bit 7 of a tag map entry is the "valid" bit, if it is set then bits 0:6
@@ -71,14 +70,6 @@ static inline int dca2_tag_map_valid(u8 *tag_map)
 #define APICID_BIT(x)		(DCA_TAG_MAP_VALID | (x))
 #define IOAT_TAG_MAP_LEN	8
 
-static u8 ioat_tag_map_BNB[IOAT_TAG_MAP_LEN] = {
-	1, APICID_BIT(1), APICID_BIT(2), APICID_BIT(2), };
-static u8 ioat_tag_map_SCNB[IOAT_TAG_MAP_LEN] = {
-	1, APICID_BIT(1), APICID_BIT(2), APICID_BIT(2), };
-static u8 ioat_tag_map_CNB[IOAT_TAG_MAP_LEN] = {
-	1, APICID_BIT(1), APICID_BIT(3), APICID_BIT(4), APICID_BIT(2), };
-static u8 ioat_tag_map_UNISYS[IOAT_TAG_MAP_LEN] = { 0 };
-
 /* pack PCI B/D/F into a u16 */
 static inline u16 dcaid_from_pcidev(struct pci_dev *pci)
 {
@@ -126,96 +117,6 @@ struct ioat_dca_priv {
 	struct ioat_dca_slot 	 req_slots[0];
 };
 
-/* 5000 series chipset DCA Port Requester ID Table Entry Format
- * [15:8]	PCI-Express Bus Number
- * [7:3]	PCI-Express Device Number
- * [2:0]	PCI-Express Function Number
- *
- * 5000 series chipset DCA control register format
- * [7:1]	Reserved (0)
- * [0]		Ignore Function Number
- */
-
-static int ioat_dca_add_requester(struct dca_provider *dca, struct device *dev)
-{
-	struct ioat_dca_priv *ioatdca = dca_priv(dca);
-	struct pci_dev *pdev;
-	int i;
-	u16 id;
-
-	/* This implementation only supports PCI-Express */
-	if (!dev_is_pci(dev))
-		return -ENODEV;
-	pdev = to_pci_dev(dev);
-	id = dcaid_from_pcidev(pdev);
-
-	if (ioatdca->requester_count == ioatdca->max_requesters)
-		return -ENODEV;
-
-	for (i = 0; i < ioatdca->max_requesters; i++) {
-		if (ioatdca->req_slots[i].pdev == NULL) {
-			/* found an empty slot */
-			ioatdca->requester_count++;
-			ioatdca->req_slots[i].pdev = pdev;
-			ioatdca->req_slots[i].rid = id;
-			writew(id, ioatdca->dca_base + (i * 4));
-			/* make sure the ignore function bit is off */
-			writeb(0, ioatdca->dca_base + (i * 4) + 2);
-			return i;
-		}
-	}
-	/* Error, ioatdma->requester_count is out of whack */
-	return -EFAULT;
-}
-
-static int ioat_dca_remove_requester(struct dca_provider *dca,
-				     struct device *dev)
-{
-	struct ioat_dca_priv *ioatdca = dca_priv(dca);
-	struct pci_dev *pdev;
-	int i;
-
-	/* This implementation only supports PCI-Express */
-	if (!dev_is_pci(dev))
-		return -ENODEV;
-	pdev = to_pci_dev(dev);
-
-	for (i = 0; i < ioatdca->max_requesters; i++) {
-		if (ioatdca->req_slots[i].pdev == pdev) {
-			writew(0, ioatdca->dca_base + (i * 4));
-			ioatdca->req_slots[i].pdev = NULL;
-			ioatdca->req_slots[i].rid = 0;
-			ioatdca->requester_count--;
-			return i;
-		}
-	}
-	return -ENODEV;
-}
-
-static u8 ioat_dca_get_tag(struct dca_provider *dca,
-			   struct device *dev,
-			   int cpu)
-{
-	struct ioat_dca_priv *ioatdca = dca_priv(dca);
-	int i, apic_id, bit, value;
-	u8 entry, tag;
-
-	tag = 0;
-	apic_id = cpu_physical_id(cpu);
-
-	for (i = 0; i < IOAT_TAG_MAP_LEN; i++) {
-		entry = ioatdca->tag_map[i];
-		if (entry & DCA_TAG_MAP_VALID) {
-			bit = entry & ~DCA_TAG_MAP_VALID;
-			value = (apic_id & (1 << bit)) ? 1 : 0;
-		} else {
-			value = entry ? 1 : 0;
-		}
-		tag |= (value << i);
-	}
-	return tag;
-}
-
 static int ioat_dca_dev_managed(struct dca_provider *dca,
 				struct device *dev)
 {
@@ -231,260 +132,7 @@ static int ioat_dca_dev_managed(struct dca_provider *dca,
 	return 0;
 }
 
-static struct dca_ops ioat_dca_ops = {
-	.add_requester		= ioat_dca_add_requester,
-	.remove_requester	= ioat_dca_remove_requester,
-	.get_tag		= ioat_dca_get_tag,
-	.dev_managed		= ioat_dca_dev_managed,
-};
-
-
-struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
-{
-	struct dca_provider *dca;
-	struct ioat_dca_priv *ioatdca;
-	u8 *tag_map = NULL;
-	int i;
-	int err;
-	u8 version;
-	u8 max_requesters;
-
-	if (!system_has_dca_enabled(pdev))
-		return NULL;
-
-	/* I/OAT v1 systems must have a known tag_map to support DCA */
-	switch (pdev->vendor) {
-	case PCI_VENDOR_ID_INTEL:
-		switch (pdev->device) {
-		case PCI_DEVICE_ID_INTEL_IOAT:
-			tag_map = ioat_tag_map_BNB;
-			break;
-		case PCI_DEVICE_ID_INTEL_IOAT_CNB:
-			tag_map = ioat_tag_map_CNB;
-			break;
-		case PCI_DEVICE_ID_INTEL_IOAT_SCNB:
-			tag_map = ioat_tag_map_SCNB;
-			break;
-		}
-		break;
-	case PCI_VENDOR_ID_UNISYS:
-		switch (pdev->device) {
-		case PCI_DEVICE_ID_UNISYS_DMA_DIRECTOR:
-			tag_map = ioat_tag_map_UNISYS;
-			break;
-		}
-		break;
-	}
-	if (tag_map == NULL)
-		return NULL;
-
-	version = readb(iobase + IOAT_VER_OFFSET);
-	if (version == IOAT_VER_3_0)
-		max_requesters = IOAT3_DCA_MAX_REQ;
-	else
-		max_requesters = IOAT_DCA_MAX_REQ;
-
-	dca = alloc_dca_provider(&ioat_dca_ops,
-			sizeof(*ioatdca) +
-			(sizeof(struct ioat_dca_slot) * max_requesters));
-	if (!dca)
-		return NULL;
-
-	ioatdca = dca_priv(dca);
-	ioatdca->max_requesters = max_requesters;
-	ioatdca->dca_base = iobase + 0x54;
-
-	/* copy over the APIC ID to DCA tag mapping */
-	for (i = 0; i < IOAT_TAG_MAP_LEN; i++)
-		ioatdca->tag_map[i] = tag_map[i];
-
-	err = register_dca_provider(dca, &pdev->dev);
-	if (err) {
-		free_dca_provider(dca);
-		return NULL;
-	}
-
-	return dca;
-}
-
-
-static int ioat2_dca_add_requester(struct dca_provider *dca, struct device *dev)
-{
-	struct ioat_dca_priv *ioatdca = dca_priv(dca);
-	struct pci_dev *pdev;
-	int i;
-	u16 id;
-	u16 global_req_table;
-
-	/* This implementation only supports PCI-Express */
-	if (!dev_is_pci(dev))
-		return -ENODEV;
-	pdev = to_pci_dev(dev);
-	id = dcaid_from_pcidev(pdev);
-
-	if (ioatdca->requester_count == ioatdca->max_requesters)
-		return -ENODEV;
-
-	for (i = 0; i < ioatdca->max_requesters; i++) {
-		if (ioatdca->req_slots[i].pdev == NULL) {
-			/* found an empty slot */
-			ioatdca->requester_count++;
-			ioatdca->req_slots[i].pdev = pdev;
-			ioatdca->req_slots[i].rid = id;
-			global_req_table =
-			      readw(ioatdca->dca_base + IOAT_DCA_GREQID_OFFSET);
-			writel(id | IOAT_DCA_GREQID_VALID,
-			       ioatdca->iobase + global_req_table + (i * 4));
-			return i;
-		}
-	}
-	/* Error, ioatdma->requester_count is out of whack */
-	return -EFAULT;
-}
-
-static int ioat2_dca_remove_requester(struct dca_provider *dca,
-				      struct device *dev)
-{
-	struct ioat_dca_priv *ioatdca = dca_priv(dca);
-	struct pci_dev *pdev;
-	int i;
-	u16 global_req_table;
-
-	/* This implementation only supports PCI-Express */
-	if (!dev_is_pci(dev))
-		return -ENODEV;
-	pdev = to_pci_dev(dev);
-
-	for (i = 0; i < ioatdca->max_requesters; i++) {
-		if (ioatdca->req_slots[i].pdev == pdev) {
-			global_req_table =
-			      readw(ioatdca->dca_base + IOAT_DCA_GREQID_OFFSET);
-			writel(0, ioatdca->iobase + global_req_table + (i * 4));
-			ioatdca->req_slots[i].pdev = NULL;
-			ioatdca->req_slots[i].rid = 0;
-			ioatdca->requester_count--;
-			return i;
-		}
-	}
-	return -ENODEV;
-}
-
-static u8 ioat2_dca_get_tag(struct dca_provider *dca,
-			    struct device *dev,
-			    int cpu)
-{
-	u8 tag;
-
-	tag = ioat_dca_get_tag(dca, dev, cpu);
-	tag = (~tag) & 0x1F;
-	return tag;
-}
-
-static struct dca_ops ioat2_dca_ops = {
-	.add_requester		= ioat2_dca_add_requester,
-	.remove_requester	= ioat2_dca_remove_requester,
-	.get_tag		= ioat2_dca_get_tag,
-	.dev_managed		= ioat_dca_dev_managed,
-};
-
-static int ioat2_dca_count_dca_slots(void __iomem *iobase, u16 dca_offset)
-{
-	int slots = 0;
-	u32 req;
-	u16 global_req_table;
-
-	global_req_table = readw(iobase + dca_offset + IOAT_DCA_GREQID_OFFSET);
-	if (global_req_table == 0)
-		return 0;
-	do {
-		req = readl(iobase + global_req_table + (slots * sizeof(u32)));
-		slots++;
-	} while ((req & IOAT_DCA_GREQID_LASTID) == 0);
-
-	return slots;
-}
-
-struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase)
-{
-	struct dca_provider *dca;
-	struct ioat_dca_priv *ioatdca;
-	int slots;
-	int i;
-	int err;
-	u32 tag_map;
-	u16 dca_offset;
-	u16 csi_fsb_control;
-	u16 pcie_control;
-	u8 bit;
-
-	if (!system_has_dca_enabled(pdev))
-		return NULL;
-
-	dca_offset = readw(iobase + IOAT_DCAOFFSET_OFFSET);
-	if (dca_offset == 0)
-		return NULL;
-
-	slots = ioat2_dca_count_dca_slots(iobase, dca_offset);
-	if (slots == 0)
-		return NULL;
-
-	dca = alloc_dca_provider(&ioat2_dca_ops,
-				 sizeof(*ioatdca)
-				      + (sizeof(struct ioat_dca_slot) * slots));
-	if (!dca)
-		return NULL;
-
-	ioatdca = dca_priv(dca);
-	ioatdca->iobase = iobase;
-	ioatdca->dca_base = iobase + dca_offset;
-	ioatdca->max_requesters = slots;
-
-	/* some bios might not know to turn these on */
-	csi_fsb_control = readw(ioatdca->dca_base + IOAT_FSB_CAP_ENABLE_OFFSET);
-	if ((csi_fsb_control & IOAT_FSB_CAP_ENABLE_PREFETCH) == 0) {
-		csi_fsb_control |= IOAT_FSB_CAP_ENABLE_PREFETCH;
-		writew(csi_fsb_control,
-		       ioatdca->dca_base + IOAT_FSB_CAP_ENABLE_OFFSET);
-	}
-	pcie_control = readw(ioatdca->dca_base + IOAT_PCI_CAP_ENABLE_OFFSET);
-	if ((pcie_control & IOAT_PCI_CAP_ENABLE_MEMWR) == 0) {
-		pcie_control |= IOAT_PCI_CAP_ENABLE_MEMWR;
-		writew(pcie_control,
-		       ioatdca->dca_base + IOAT_PCI_CAP_ENABLE_OFFSET);
-	}
-
-
-	/* TODO version, compatibility and configuration checks */
-
-	/* copy out the APIC to DCA tag map */
-	tag_map = readl(ioatdca->dca_base + IOAT_APICID_TAG_MAP_OFFSET);
-	for (i = 0; i < 5; i++) {
-		bit = (tag_map >> (4 * i)) & 0x0f;
-		if (bit < 8)
-			ioatdca->tag_map[i] = bit | DCA_TAG_MAP_VALID;
-		else
-			ioatdca->tag_map[i] = 0;
-	}
-
-	if (!dca2_tag_map_valid(ioatdca->tag_map)) {
-		WARN_TAINT_ONCE(1, TAINT_FIRMWARE_WORKAROUND,
-				"%s %s: APICID_TAG_MAP set incorrectly by BIOS, disabling DCA\n",
-				dev_driver_string(&pdev->dev),
-				dev_name(&pdev->dev));
-		free_dca_provider(dca);
-		return NULL;
-	}
-
-	err = register_dca_provider(dca, &pdev->dev);
-	if (err) {
-		free_dca_provider(dca);
-		return NULL;
-	}
-
-	return dca;
-}
-
-static int ioat3_dca_add_requester(struct dca_provider *dca, struct device *dev)
+static int ioat_dca_add_requester(struct dca_provider *dca, struct device *dev)
 {
 	struct ioat_dca_priv *ioatdca = dca_priv(dca);
 	struct pci_dev *pdev;
@@ -518,7 +166,7 @@ static int ioat3_dca_add_requester(struct dca_provider *dca, struct device *dev)
 	return -EFAULT;
 }
 
-static int ioat3_dca_remove_requester(struct dca_provider *dca,
+static int ioat_dca_remove_requester(struct dca_provider *dca,
 				      struct device *dev)
 {
 	struct ioat_dca_priv *ioatdca = dca_priv(dca);
@@ -545,7 +193,7 @@ static int ioat3_dca_remove_requester(struct dca_provider *dca,
 	return -ENODEV;
 }
 
-static u8 ioat3_dca_get_tag(struct dca_provider *dca,
+static u8 ioat_dca_get_tag(struct dca_provider *dca,
 			    struct device *dev,
 			    int cpu)
 {
@@ -576,14 +224,14 @@ static u8 ioat3_dca_get_tag(struct dca_provider *dca,
 	return tag;
 }
 
-static struct dca_ops ioat3_dca_ops = {
-	.add_requester		= ioat3_dca_add_requester,
-	.remove_requester	= ioat3_dca_remove_requester,
-	.get_tag		= ioat3_dca_get_tag,
+static struct dca_ops ioat_dca_ops = {
+	.add_requester		= ioat_dca_add_requester,
+	.remove_requester	= ioat_dca_remove_requester,
+	.get_tag		= ioat_dca_get_tag,
 	.dev_managed		= ioat_dca_dev_managed,
 };
 
-static int ioat3_dca_count_dca_slots(void *iobase, u16 dca_offset)
+static int ioat_dca_count_dca_slots(void *iobase, u16 dca_offset)
 {
 	int slots = 0;
 	u32 req;
@@ -618,7 +266,7 @@ static inline int dca3_tag_map_invalid(u8 *tag_map)
 		(tag_map[4] == DCA_TAG_MAP_VALID));
 }
 
-struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase)
+struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 {
 	struct dca_provider *dca;
 	struct ioat_dca_priv *ioatdca;
@@ -645,11 +293,11 @@ struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 	if (dca_offset == 0)
 		return NULL;
 
-	slots = ioat3_dca_count_dca_slots(iobase, dca_offset);
+	slots = ioat_dca_count_dca_slots(iobase, dca_offset);
 	if (slots == 0)
 		return NULL;
 
-	dca = alloc_dca_provider(&ioat3_dca_ops,
+	dca = alloc_dca_provider(&ioat_dca_ops,
 				 sizeof(*ioatdca)
 				      + (sizeof(struct ioat_dca_slot) * slots));
 	if (!dca)
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index ee0aa9f4ccfa..f66b7e640610 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -1,6 +1,6 @@
 /*
  * Intel I/OAT DMA Linux driver
- * Copyright(c) 2004 - 2009 Intel Corporation.
+ * Copyright(c) 2004 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -31,31 +31,23 @@
 #include <linux/dma-mapping.h>
 #include <linux/workqueue.h>
 #include <linux/prefetch.h>
-#include <linux/i7300_idle.h>
 #include "dma.h"
 #include "registers.h"
 #include "hw.h"
 
 #include "../dmaengine.h"
 
-int ioat_pending_level = 4;
-module_param(ioat_pending_level, int, 0644);
-MODULE_PARM_DESC(ioat_pending_level,
-		 "high-water mark for pushing ioat descriptors (default: 4)");
-
-/* internal functions */
-static void ioat1_cleanup(struct ioat_dma_chan *ioat);
-static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat);
+static void ioat_eh(struct ioatdma_chan *ioat_chan);
 
 /**
  * ioat_dma_do_interrupt - handler used for single vector interrupt mode
  * @irq: interrupt id
  * @data: interrupt data
  */
-static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
+irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
 {
 	struct ioatdma_device *instance = data;
-	struct ioat_chan_common *chan;
+	struct ioatdma_chan *ioat_chan;
 	unsigned long attnstatus;
 	int bit;
 	u8 intrctrl;
@@ -72,9 +64,9 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
 
 	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
 	for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
-		chan = ioat_chan_by_index(instance, bit);
-		if (test_bit(IOAT_RUN, &chan->state))
-			tasklet_schedule(&chan->cleanup_task);
+		ioat_chan = ioat_chan_by_index(instance, bit);
+		if (test_bit(IOAT_RUN, &ioat_chan->state))
+			tasklet_schedule(&ioat_chan->cleanup_task);
 	}
 
 	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -86,1161 +78,912 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
  * @irq: interrupt id
  * @data: interrupt data
  */
-static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
+irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
 {
-	struct ioat_chan_common *chan = data;
+	struct ioatdma_chan *ioat_chan = data;
 
-	if (test_bit(IOAT_RUN, &chan->state))
-		tasklet_schedule(&chan->cleanup_task);
+	if (test_bit(IOAT_RUN, &ioat_chan->state))
+		tasklet_schedule(&ioat_chan->cleanup_task);
 
 	return IRQ_HANDLED;
 }
 
-/* common channel initialization */
-void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *chan, int idx)
+void ioat_stop(struct ioatdma_chan *ioat_chan)
 {
-	struct dma_device *dma = &device->common;
-	struct dma_chan *c = &chan->common;
-	unsigned long data = (unsigned long) c;
-
-	chan->device = device;
-	chan->reg_base = device->reg_base + (0x80 * (idx + 1));
-	spin_lock_init(&chan->cleanup_lock);
-	chan->common.device = dma;
-	dma_cookie_init(&chan->common);
-	list_add_tail(&chan->common.device_node, &dma->channels);
-	device->idx[idx] = chan;
-	init_timer(&chan->timer);
-	chan->timer.function = device->timer_fn;
-	chan->timer.data = data;
-	tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct pci_dev *pdev = ioat_dma->pdev;
+	int chan_id = chan_num(ioat_chan);
+	struct msix_entry *msix;
+
+	/* 1/ stop irq from firing tasklets
+	 * 2/ stop the tasklet from re-arming irqs
+	 */
+	clear_bit(IOAT_RUN, &ioat_chan->state);
+
+	/* flush inflight interrupts */
+	switch (ioat_dma->irq_mode) {
+	case IOAT_MSIX:
+		msix = &ioat_dma->msix_entries[chan_id];
+		synchronize_irq(msix->vector);
+		break;
+	case IOAT_MSI:
+	case IOAT_INTX:
+		synchronize_irq(pdev->irq);
+		break;
+	default:
+		break;
+	}
+
+	/* flush inflight timers */
+	del_timer_sync(&ioat_chan->timer);
+
+	/* flush inflight tasklet runs */
+	tasklet_kill(&ioat_chan->cleanup_task);
+
+	/* final cleanup now that everything is quiesced and can't re-arm */
+	ioat_cleanup_event((unsigned long)&ioat_chan->dma_chan);
 }
 
-/**
- * ioat1_dma_enumerate_channels - find and initialize the device's channels
- * @device: the device to be enumerated
- */
-static int ioat1_enumerate_channels(struct ioatdma_device *device)
+static void __ioat_issue_pending(struct ioatdma_chan *ioat_chan)
 {
-	u8 xfercap_scale;
-	u32 xfercap;
-	int i;
-	struct ioat_dma_chan *ioat;
-	struct device *dev = &device->pdev->dev;
-	struct dma_device *dma = &device->common;
-
-	INIT_LIST_HEAD(&dma->channels);
-	dma->chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET);
-	dma->chancnt &= 0x1f; /* bits [4:0] valid */
-	if (dma->chancnt > ARRAY_SIZE(device->idx)) {
-		dev_warn(dev, "(%d) exceeds max supported channels (%zu)\n",
-			 dma->chancnt, ARRAY_SIZE(device->idx));
-		dma->chancnt = ARRAY_SIZE(device->idx);
-	}
-	xfercap_scale = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
-	xfercap_scale &= 0x1f; /* bits [4:0] valid */
-	xfercap = (xfercap_scale == 0 ? -1 : (1UL << xfercap_scale));
-	dev_dbg(dev, "%s: xfercap = %d\n", __func__, xfercap);
-
-#ifdef  CONFIG_I7300_IDLE_IOAT_CHANNEL
-	if (i7300_idle_platform_probe(NULL, NULL, 1) == 0)
-		dma->chancnt--;
-#endif
-	for (i = 0; i < dma->chancnt; i++) {
-		ioat = devm_kzalloc(dev, sizeof(*ioat), GFP_KERNEL);
-		if (!ioat)
-			break;
+	ioat_chan->dmacount += ioat_ring_pending(ioat_chan);
+	ioat_chan->issued = ioat_chan->head;
+	writew(ioat_chan->dmacount,
+	       ioat_chan->reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
+	dev_dbg(to_dev(ioat_chan),
+		"%s: head: %#x tail: %#x issued: %#x count: %#x\n",
+		__func__, ioat_chan->head, ioat_chan->tail,
+		ioat_chan->issued, ioat_chan->dmacount);
+}
+
+void ioat_issue_pending(struct dma_chan *c)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
 
-		ioat_init_channel(device, &ioat->base, i);
-		ioat->xfercap = xfercap;
-		spin_lock_init(&ioat->desc_lock);
-		INIT_LIST_HEAD(&ioat->free_desc);
-		INIT_LIST_HEAD(&ioat->used_desc);
+	if (ioat_ring_pending(ioat_chan)) {
+		spin_lock_bh(&ioat_chan->prep_lock);
+		__ioat_issue_pending(ioat_chan);
+		spin_unlock_bh(&ioat_chan->prep_lock);
 	}
-	dma->chancnt = i;
-	return i;
 }
 
 /**
- * ioat_dma_memcpy_issue_pending - push potentially unrecognized appended
- *                                 descriptors to hw
- * @chan: DMA channel handle
+ * ioat_update_pending - log pending descriptors
+ * @ioat: ioat+ channel
+ *
+ * Check if the number of unsubmitted descriptors has exceeded the
+ * watermark.  Called with prep_lock held
  */
-static inline void
-__ioat1_dma_memcpy_issue_pending(struct ioat_dma_chan *ioat)
+static void ioat_update_pending(struct ioatdma_chan *ioat_chan)
 {
-	void __iomem *reg_base = ioat->base.reg_base;
-
-	dev_dbg(to_dev(&ioat->base), "%s: pending: %d\n",
-		__func__, ioat->pending);
-	ioat->pending = 0;
-	writeb(IOAT_CHANCMD_APPEND, reg_base + IOAT1_CHANCMD_OFFSET);
+	if (ioat_ring_pending(ioat_chan) > ioat_pending_level)
+		__ioat_issue_pending(ioat_chan);
 }
 
-static void ioat1_dma_memcpy_issue_pending(struct dma_chan *chan)
+static void __ioat_start_null_desc(struct ioatdma_chan *ioat_chan)
 {
-	struct ioat_dma_chan *ioat = to_ioat_chan(chan);
+	struct ioat_ring_ent *desc;
+	struct ioat_dma_descriptor *hw;
 
-	if (ioat->pending > 0) {
-		spin_lock_bh(&ioat->desc_lock);
-		__ioat1_dma_memcpy_issue_pending(ioat);
-		spin_unlock_bh(&ioat->desc_lock);
+	if (ioat_ring_space(ioat_chan) < 1) {
+		dev_err(to_dev(ioat_chan),
+			"Unable to start null desc - ring full\n");
+		return;
 	}
+
+	dev_dbg(to_dev(ioat_chan),
+		"%s: head: %#x tail: %#x issued: %#x\n",
+		__func__, ioat_chan->head, ioat_chan->tail, ioat_chan->issued);
+	desc = ioat_get_ring_ent(ioat_chan, ioat_chan->head);
+
+	hw = desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = 1;
+	hw->ctl_f.compl_write = 1;
+	/* set size to non-zero value (channel returns error when size is 0) */
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	hw->src_addr = 0;
+	hw->dst_addr = 0;
+	async_tx_ack(&desc->txd);
+	ioat_set_chainaddr(ioat_chan, desc->txd.phys);
+	dump_desc_dbg(ioat_chan, desc);
+	/* make sure descriptors are written before we submit */
+	wmb();
+	ioat_chan->head += 1;
+	__ioat_issue_pending(ioat_chan);
 }
 
-/**
- * ioat1_reset_channel - restart a channel
- * @ioat: IOAT DMA channel handle
- */
-static void ioat1_reset_channel(struct ioat_dma_chan *ioat)
+void ioat_start_null_desc(struct ioatdma_chan *ioat_chan)
 {
-	struct ioat_chan_common *chan = &ioat->base;
-	void __iomem *reg_base = chan->reg_base;
-	u32 chansts, chanerr;
-
-	dev_warn(to_dev(chan), "reset\n");
-	chanerr = readl(reg_base + IOAT_CHANERR_OFFSET);
-	chansts = *chan->completion & IOAT_CHANSTS_STATUS;
-	if (chanerr) {
-		dev_err(to_dev(chan),
-			"chan%d, CHANSTS = 0x%08x CHANERR = 0x%04x, clearing\n",
-			chan_num(chan), chansts, chanerr);
-		writel(chanerr, reg_base + IOAT_CHANERR_OFFSET);
+	spin_lock_bh(&ioat_chan->prep_lock);
+	__ioat_start_null_desc(ioat_chan);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+}
+
+static void __ioat_restart_chan(struct ioatdma_chan *ioat_chan)
+{
+	/* set the tail to be re-issued */
+	ioat_chan->issued = ioat_chan->tail;
+	ioat_chan->dmacount = 0;
+	mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
+
+	dev_dbg(to_dev(ioat_chan),
+		"%s: head: %#x tail: %#x issued: %#x count: %#x\n",
+		__func__, ioat_chan->head, ioat_chan->tail,
+		ioat_chan->issued, ioat_chan->dmacount);
+
+	if (ioat_ring_pending(ioat_chan)) {
+		struct ioat_ring_ent *desc;
+
+		desc = ioat_get_ring_ent(ioat_chan, ioat_chan->tail);
+		ioat_set_chainaddr(ioat_chan, desc->txd.phys);
+		__ioat_issue_pending(ioat_chan);
+	} else
+		__ioat_start_null_desc(ioat_chan);
+}
+
+static int ioat_quiesce(struct ioatdma_chan *ioat_chan, unsigned long tmo)
+{
+	unsigned long end = jiffies + tmo;
+	int err = 0;
+	u32 status;
+
+	status = ioat_chansts(ioat_chan);
+	if (is_ioat_active(status) || is_ioat_idle(status))
+		ioat_suspend(ioat_chan);
+	while (is_ioat_active(status) || is_ioat_idle(status)) {
+		if (tmo && time_after(jiffies, end)) {
+			err = -ETIMEDOUT;
+			break;
+		}
+		status = ioat_chansts(ioat_chan);
+		cpu_relax();
 	}
 
-	/*
-	 * whack it upside the head with a reset
-	 * and wait for things to settle out.
-	 * force the pending count to a really big negative
-	 * to make sure no one forces an issue_pending
-	 * while we're waiting.
-	 */
+	return err;
+}
 
-	ioat->pending = INT_MIN;
-	writeb(IOAT_CHANCMD_RESET,
-	       reg_base + IOAT_CHANCMD_OFFSET(chan->device->version));
-	set_bit(IOAT_RESET_PENDING, &chan->state);
-	mod_timer(&chan->timer, jiffies + RESET_DELAY);
+static int ioat_reset_sync(struct ioatdma_chan *ioat_chan, unsigned long tmo)
+{
+	unsigned long end = jiffies + tmo;
+	int err = 0;
+
+	ioat_reset(ioat_chan);
+	while (ioat_reset_pending(ioat_chan)) {
+		if (end && time_after(jiffies, end)) {
+			err = -ETIMEDOUT;
+			break;
+		}
+		cpu_relax();
+	}
+
+	return err;
 }
 
-static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
+static dma_cookie_t ioat_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
+	__releases(&ioat_chan->prep_lock)
 {
 	struct dma_chan *c = tx->chan;
-	struct ioat_dma_chan *ioat = to_ioat_chan(c);
-	struct ioat_desc_sw *desc = tx_to_ioat_desc(tx);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioat_desc_sw *first;
-	struct ioat_desc_sw *chain_tail;
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
 	dma_cookie_t cookie;
 
-	spin_lock_bh(&ioat->desc_lock);
-	/* cookie incr and addition to used_list must be atomic */
 	cookie = dma_cookie_assign(tx);
-	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
+	dev_dbg(to_dev(ioat_chan), "%s: cookie: %d\n", __func__, cookie);
+
+	if (!test_and_set_bit(IOAT_CHAN_ACTIVE, &ioat_chan->state))
+		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
 
-	/* write address into NextDescriptor field of last desc in chain */
-	first = to_ioat_desc(desc->tx_list.next);
-	chain_tail = to_ioat_desc(ioat->used_desc.prev);
-	/* make descriptor updates globally visible before chaining */
+	/* make descriptor updates visible before advancing ioat->head,
+	 * this is purposefully not smp_wmb() since we are also
+	 * publishing the descriptor updates to a dma device
+	 */
 	wmb();
-	chain_tail->hw->next = first->txd.phys;
-	list_splice_tail_init(&desc->tx_list, &ioat->used_desc);
-	dump_desc_dbg(ioat, chain_tail);
-	dump_desc_dbg(ioat, first);
 
-	if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state))
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+	ioat_chan->head += ioat_chan->produce;
 
-	ioat->active += desc->hw->tx_cnt;
-	ioat->pending += desc->hw->tx_cnt;
-	if (ioat->pending >= ioat_pending_level)
-		__ioat1_dma_memcpy_issue_pending(ioat);
-	spin_unlock_bh(&ioat->desc_lock);
+	ioat_update_pending(ioat_chan);
+	spin_unlock_bh(&ioat_chan->prep_lock);
 
 	return cookie;
 }
 
-/**
- * ioat_dma_alloc_descriptor - allocate and return a sw and hw descriptor pair
- * @ioat: the channel supplying the memory pool for the descriptors
- * @flags: allocation flags
- */
-static struct ioat_desc_sw *
-ioat_dma_alloc_descriptor(struct ioat_dma_chan *ioat, gfp_t flags)
+static struct ioat_ring_ent *
+ioat_alloc_ring_ent(struct dma_chan *chan, gfp_t flags)
 {
-	struct ioat_dma_descriptor *desc;
-	struct ioat_desc_sw *desc_sw;
-	struct ioatdma_device *ioatdma_device;
+	struct ioat_dma_descriptor *hw;
+	struct ioat_ring_ent *desc;
+	struct ioatdma_device *ioat_dma;
 	dma_addr_t phys;
 
-	ioatdma_device = ioat->base.device;
-	desc = pci_pool_alloc(ioatdma_device->dma_pool, flags, &phys);
-	if (unlikely(!desc))
+	ioat_dma = to_ioatdma_device(chan->device);
+	hw = pci_pool_alloc(ioat_dma->dma_pool, flags, &phys);
+	if (!hw)
 		return NULL;
+	memset(hw, 0, sizeof(*hw));
 
-	desc_sw = kzalloc(sizeof(*desc_sw), flags);
-	if (unlikely(!desc_sw)) {
-		pci_pool_free(ioatdma_device->dma_pool, desc, phys);
+	desc = kmem_cache_zalloc(ioat_cache, flags);
+	if (!desc) {
+		pci_pool_free(ioat_dma->dma_pool, hw, phys);
 		return NULL;
 	}
 
-	memset(desc, 0, sizeof(*desc));
+	dma_async_tx_descriptor_init(&desc->txd, chan);
+	desc->txd.tx_submit = ioat_tx_submit_unlock;
+	desc->hw = hw;
+	desc->txd.phys = phys;
+	return desc;
+}
 
-	INIT_LIST_HEAD(&desc_sw->tx_list);
-	dma_async_tx_descriptor_init(&desc_sw->txd, &ioat->base.common);
-	desc_sw->txd.tx_submit = ioat1_tx_submit;
-	desc_sw->hw = desc;
-	desc_sw->txd.phys = phys;
-	set_desc_id(desc_sw, -1);
+void ioat_free_ring_ent(struct ioat_ring_ent *desc, struct dma_chan *chan)
+{
+	struct ioatdma_device *ioat_dma;
 
-	return desc_sw;
+	ioat_dma = to_ioatdma_device(chan->device);
+	pci_pool_free(ioat_dma->dma_pool, desc->hw, desc->txd.phys);
+	kmem_cache_free(ioat_cache, desc);
 }
 
-static int ioat_initial_desc_count = 256;
-module_param(ioat_initial_desc_count, int, 0644);
-MODULE_PARM_DESC(ioat_initial_desc_count,
-		 "ioat1: initial descriptors per channel (default: 256)");
-/**
- * ioat1_dma_alloc_chan_resources - returns the number of allocated descriptors
- * @chan: the channel to be filled out
- */
-static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
+struct ioat_ring_ent **
+ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 {
-	struct ioat_dma_chan *ioat = to_ioat_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioat_desc_sw *desc;
-	u32 chanerr;
+	struct ioat_ring_ent **ring;
+	int descs = 1 << order;
 	int i;
-	LIST_HEAD(tmp_list);
-
-	/* have we already been set up? */
-	if (!list_empty(&ioat->free_desc))
-		return ioat->desccount;
 
-	/* Setup register to interrupt and write completion status on error */
-	writew(IOAT_CHANCTRL_RUN, chan->reg_base + IOAT_CHANCTRL_OFFSET);
+	if (order > ioat_get_max_alloc_order())
+		return NULL;
 
-	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-	if (chanerr) {
-		dev_err(to_dev(chan), "CHANERR = %x, clearing\n", chanerr);
-		writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
+	/* allocate the array to hold the software ring */
+	ring = kcalloc(descs, sizeof(*ring), flags);
+	if (!ring)
+		return NULL;
+	for (i = 0; i < descs; i++) {
+		ring[i] = ioat_alloc_ring_ent(c, flags);
+		if (!ring[i]) {
+			while (i--)
+				ioat_free_ring_ent(ring[i], c);
+			kfree(ring);
+			return NULL;
+		}
+		set_desc_id(ring[i], i);
 	}
 
-	/* Allocate descriptors */
-	for (i = 0; i < ioat_initial_desc_count; i++) {
-		desc = ioat_dma_alloc_descriptor(ioat, GFP_KERNEL);
-		if (!desc) {
-			dev_err(to_dev(chan), "Only %d initial descriptors\n", i);
-			break;
-		}
-		set_desc_id(desc, i);
-		list_add_tail(&desc->node, &tmp_list);
+	/* link descs */
+	for (i = 0; i < descs-1; i++) {
+		struct ioat_ring_ent *next = ring[i+1];
+		struct ioat_dma_descriptor *hw = ring[i]->hw;
+
+		hw->next = next->txd.phys;
 	}
-	spin_lock_bh(&ioat->desc_lock);
-	ioat->desccount = i;
-	list_splice(&tmp_list, &ioat->free_desc);
-	spin_unlock_bh(&ioat->desc_lock);
-
-	/* allocate a completion writeback area */
-	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
-	chan->completion = pci_pool_alloc(chan->device->completion_pool,
-					  GFP_KERNEL, &chan->completion_dma);
-	memset(chan->completion, 0, sizeof(*chan->completion));
-	writel(((u64) chan->completion_dma) & 0x00000000FFFFFFFF,
-	       chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
-	writel(((u64) chan->completion_dma) >> 32,
-	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
-
-	set_bit(IOAT_RUN, &chan->state);
-	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
-	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
-		__func__, ioat->desccount);
-	return ioat->desccount;
+	ring[i]->hw->next = ring[0]->txd.phys;
+
+	return ring;
 }
 
-void ioat_stop(struct ioat_chan_common *chan)
+static bool reshape_ring(struct ioatdma_chan *ioat_chan, int order)
 {
-	struct ioatdma_device *device = chan->device;
-	struct pci_dev *pdev = device->pdev;
-	int chan_id = chan_num(chan);
-	struct msix_entry *msix;
+	/* reshape differs from normal ring allocation in that we want
+	 * to allocate a new software ring while only
+	 * extending/truncating the hardware ring
+	 */
+	struct dma_chan *c = &ioat_chan->dma_chan;
+	const u32 curr_size = ioat_ring_size(ioat_chan);
+	const u16 active = ioat_ring_active(ioat_chan);
+	const u32 new_size = 1 << order;
+	struct ioat_ring_ent **ring;
+	u32 i;
+
+	if (order > ioat_get_max_alloc_order())
+		return false;
 
-	/* 1/ stop irq from firing tasklets
-	 * 2/ stop the tasklet from re-arming irqs
+	/* double check that we have at least 1 free descriptor */
+	if (active == curr_size)
+		return false;
+
+	/* when shrinking, verify that we can hold the current active
+	 * set in the new ring
 	 */
-	clear_bit(IOAT_RUN, &chan->state);
+	if (active >= new_size)
+		return false;
 
-	/* flush inflight interrupts */
-	switch (device->irq_mode) {
-	case IOAT_MSIX:
-		msix = &device->msix_entries[chan_id];
-		synchronize_irq(msix->vector);
-		break;
-	case IOAT_MSI:
-	case IOAT_INTX:
-		synchronize_irq(pdev->irq);
-		break;
-	default:
-		break;
-	}
+	/* allocate the array to hold the software ring */
+	ring = kcalloc(new_size, sizeof(*ring), GFP_NOWAIT);
+	if (!ring)
+		return false;
 
-	/* flush inflight timers */
-	del_timer_sync(&chan->timer);
+	/* allocate/trim descriptors as needed */
+	if (new_size > curr_size) {
+		/* copy current descriptors to the new ring */
+		for (i = 0; i < curr_size; i++) {
+			u16 curr_idx = (ioat_chan->tail+i) & (curr_size-1);
+			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
 
-	/* flush inflight tasklet runs */
-	tasklet_kill(&chan->cleanup_task);
+			ring[new_idx] = ioat_chan->ring[curr_idx];
+			set_desc_id(ring[new_idx], new_idx);
+		}
 
-	/* final cleanup now that everything is quiesced and can't re-arm */
-	device->cleanup_fn((unsigned long) &chan->common);
-}
+		/* add new descriptors to the ring */
+		for (i = curr_size; i < new_size; i++) {
+			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
 
-/**
- * ioat1_dma_free_chan_resources - release all the descriptors
- * @chan: the channel to be cleaned
- */
-static void ioat1_dma_free_chan_resources(struct dma_chan *c)
-{
-	struct ioat_dma_chan *ioat = to_ioat_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioatdma_device *ioatdma_device = chan->device;
-	struct ioat_desc_sw *desc, *_desc;
-	int in_use_descs = 0;
-
-	/* Before freeing channel resources first check
-	 * if they have been previously allocated for this channel.
-	 */
-	if (ioat->desccount == 0)
-		return;
+			ring[new_idx] = ioat_alloc_ring_ent(c, GFP_NOWAIT);
+			if (!ring[new_idx]) {
+				while (i--) {
+					u16 new_idx = (ioat_chan->tail+i) &
+						       (new_size-1);
+
+					ioat_free_ring_ent(ring[new_idx], c);
+				}
+				kfree(ring);
+				return false;
+			}
+			set_desc_id(ring[new_idx], new_idx);
+		}
 
-	ioat_stop(chan);
+		/* hw link new descriptors */
+		for (i = curr_size-1; i < new_size; i++) {
+			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
+			struct ioat_ring_ent *next =
+				ring[(new_idx+1) & (new_size-1)];
+			struct ioat_dma_descriptor *hw = ring[new_idx]->hw;
 
-	/* Delay 100ms after reset to allow internal DMA logic to quiesce
-	 * before removing DMA descriptor resources.
-	 */
-	writeb(IOAT_CHANCMD_RESET,
-	       chan->reg_base + IOAT_CHANCMD_OFFSET(chan->device->version));
-	mdelay(100);
-
-	spin_lock_bh(&ioat->desc_lock);
-	list_for_each_entry_safe(desc, _desc, &ioat->used_desc, node) {
-		dev_dbg(to_dev(chan), "%s: freeing %d from used list\n",
-			__func__, desc_id(desc));
-		dump_desc_dbg(ioat, desc);
-		in_use_descs++;
-		list_del(&desc->node);
-		pci_pool_free(ioatdma_device->dma_pool, desc->hw,
-			      desc->txd.phys);
-		kfree(desc);
-	}
-	list_for_each_entry_safe(desc, _desc,
-				 &ioat->free_desc, node) {
-		list_del(&desc->node);
-		pci_pool_free(ioatdma_device->dma_pool, desc->hw,
-			      desc->txd.phys);
-		kfree(desc);
+			hw->next = next->txd.phys;
+		}
+	} else {
+		struct ioat_dma_descriptor *hw;
+		struct ioat_ring_ent *next;
+
+		/* copy current descriptors to the new ring, dropping the
+		 * removed descriptors
+		 */
+		for (i = 0; i < new_size; i++) {
+			u16 curr_idx = (ioat_chan->tail+i) & (curr_size-1);
+			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
+
+			ring[new_idx] = ioat_chan->ring[curr_idx];
+			set_desc_id(ring[new_idx], new_idx);
+		}
+
+		/* free deleted descriptors */
+		for (i = new_size; i < curr_size; i++) {
+			struct ioat_ring_ent *ent;
+
+			ent = ioat_get_ring_ent(ioat_chan, ioat_chan->tail+i);
+			ioat_free_ring_ent(ent, c);
+		}
+
+		/* fix up hardware ring */
+		hw = ring[(ioat_chan->tail+new_size-1) & (new_size-1)]->hw;
+		next = ring[(ioat_chan->tail+new_size) & (new_size-1)];
+		hw->next = next->txd.phys;
 	}
-	spin_unlock_bh(&ioat->desc_lock);
 
-	pci_pool_free(ioatdma_device->completion_pool,
-		      chan->completion,
-		      chan->completion_dma);
+	dev_dbg(to_dev(ioat_chan), "%s: allocated %d descriptors\n",
+		__func__, new_size);
 
-	/* one is ok since we left it on there on purpose */
-	if (in_use_descs > 1)
-		dev_err(to_dev(chan), "Freeing %d in use descriptors!\n",
-			in_use_descs - 1);
+	kfree(ioat_chan->ring);
+	ioat_chan->ring = ring;
+	ioat_chan->alloc_order = order;
 
-	chan->last_completion = 0;
-	chan->completion_dma = 0;
-	ioat->pending = 0;
-	ioat->desccount = 0;
+	return true;
 }
 
 /**
- * ioat1_dma_get_next_descriptor - return the next available descriptor
- * @ioat: IOAT DMA channel handle
- *
- * Gets the next descriptor from the chain, and must be called with the
- * channel's desc_lock held.  Allocates more descriptors if the channel
- * has run out.
+ * ioat_check_space_lock - verify space and grab ring producer lock
+ * @ioat: ioat,3 channel (ring) to operate on
+ * @num_descs: allocation length
  */
-static struct ioat_desc_sw *
-ioat1_dma_get_next_descriptor(struct ioat_dma_chan *ioat)
+int ioat_check_space_lock(struct ioatdma_chan *ioat_chan, int num_descs)
+	__acquires(&ioat_chan->prep_lock)
 {
-	struct ioat_desc_sw *new;
+	bool retry;
 
-	if (!list_empty(&ioat->free_desc)) {
-		new = to_ioat_desc(ioat->free_desc.next);
-		list_del(&new->node);
-	} else {
-		/* try to get another desc */
-		new = ioat_dma_alloc_descriptor(ioat, GFP_ATOMIC);
-		if (!new) {
-			dev_err(to_dev(&ioat->base), "alloc failed\n");
-			return NULL;
-		}
+ retry:
+	spin_lock_bh(&ioat_chan->prep_lock);
+	/* never allow the last descriptor to be consumed, we need at
+	 * least one free at all times to allow for on-the-fly ring
+	 * resizing.
+	 */
+	if (likely(ioat_ring_space(ioat_chan) > num_descs)) {
+		dev_dbg(to_dev(ioat_chan), "%s: num_descs: %d (%x:%x:%x)\n",
+			__func__, num_descs, ioat_chan->head,
+			ioat_chan->tail, ioat_chan->issued);
+		ioat_chan->produce = num_descs;
+		return 0;  /* with ioat->prep_lock held */
+	}
+	retry = test_and_set_bit(IOAT_RESHAPE_PENDING, &ioat_chan->state);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+
+	/* is another cpu already trying to expand the ring? */
+	if (retry)
+		goto retry;
+
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+	spin_lock_bh(&ioat_chan->prep_lock);
+	retry = reshape_ring(ioat_chan, ioat_chan->alloc_order + 1);
+	clear_bit(IOAT_RESHAPE_PENDING, &ioat_chan->state);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+	spin_unlock_bh(&ioat_chan->cleanup_lock);
+
+	/* if we were able to expand the ring retry the allocation */
+	if (retry)
+		goto retry;
+
+	dev_dbg_ratelimited(to_dev(ioat_chan),
+			    "%s: ring full! num_descs: %d (%x:%x:%x)\n",
+			    __func__, num_descs, ioat_chan->head,
+			    ioat_chan->tail, ioat_chan->issued);
+
+	/* progress reclaim in the allocation failure case we may be
+	 * called under bh_disabled so we need to trigger the timer
+	 * event directly
+	 */
+	if (time_is_before_jiffies(ioat_chan->timer.expires)
+	    && timer_pending(&ioat_chan->timer)) {
+		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
+		ioat_timer_event((unsigned long)ioat_chan);
 	}
-	dev_dbg(to_dev(&ioat->base), "%s: allocated: %d\n",
-		__func__, desc_id(new));
-	prefetch(new->hw);
-	return new;
+
+	return -ENOMEM;
 }
 
-static struct dma_async_tx_descriptor *
-ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
-		      dma_addr_t dma_src, size_t len, unsigned long flags)
+static bool desc_has_ext(struct ioat_ring_ent *desc)
 {
-	struct ioat_dma_chan *ioat = to_ioat_chan(c);
-	struct ioat_desc_sw *desc;
-	size_t copy;
-	LIST_HEAD(chain);
-	dma_addr_t src = dma_src;
-	dma_addr_t dest = dma_dest;
-	size_t total_len = len;
-	struct ioat_dma_descriptor *hw = NULL;
-	int tx_cnt = 0;
-
-	spin_lock_bh(&ioat->desc_lock);
-	desc = ioat1_dma_get_next_descriptor(ioat);
-	do {
-		if (!desc)
-			break;
-
-		tx_cnt++;
-		copy = min_t(size_t, len, ioat->xfercap);
+	struct ioat_dma_descriptor *hw = desc->hw;
 
-		hw = desc->hw;
-		hw->size = copy;
-		hw->ctl = 0;
-		hw->src_addr = src;
-		hw->dst_addr = dest;
+	if (hw->ctl_f.op == IOAT_OP_XOR ||
+	    hw->ctl_f.op == IOAT_OP_XOR_VAL) {
+		struct ioat_xor_descriptor *xor = desc->xor;
 
-		list_add_tail(&desc->node, &chain);
+		if (src_cnt_to_sw(xor->ctl_f.src_cnt) > 5)
+			return true;
+	} else if (hw->ctl_f.op == IOAT_OP_PQ ||
+		   hw->ctl_f.op == IOAT_OP_PQ_VAL) {
+		struct ioat_pq_descriptor *pq = desc->pq;
 
-		len -= copy;
-		dest += copy;
-		src += copy;
-		if (len) {
-			struct ioat_desc_sw *next;
-
-			async_tx_ack(&desc->txd);
-			next = ioat1_dma_get_next_descriptor(ioat);
-			hw->next = next ? next->txd.phys : 0;
-			dump_desc_dbg(ioat, desc);
-			desc = next;
-		} else
-			hw->next = 0;
-	} while (len);
-
-	if (!desc) {
-		struct ioat_chan_common *chan = &ioat->base;
-
-		dev_err(to_dev(chan),
-			"chan%d - get_next_desc failed\n", chan_num(chan));
-		list_splice(&chain, &ioat->free_desc);
-		spin_unlock_bh(&ioat->desc_lock);
-		return NULL;
+		if (src_cnt_to_sw(pq->ctl_f.src_cnt) > 3)
+			return true;
 	}
-	spin_unlock_bh(&ioat->desc_lock);
 
-	desc->txd.flags = flags;
-	desc->len = total_len;
-	list_splice(&chain, &desc->tx_list);
-	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
-	hw->ctl_f.compl_write = 1;
-	hw->tx_cnt = tx_cnt;
-	dump_desc_dbg(ioat, desc);
-
-	return &desc->txd;
+	return false;
 }
 
-static void ioat1_cleanup_event(unsigned long data)
+static void
+ioat_free_sed(struct ioatdma_device *ioat_dma, struct ioat_sed_ent *sed)
 {
-	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
-	struct ioat_chan_common *chan = &ioat->base;
-
-	ioat1_cleanup(ioat);
-	if (!test_bit(IOAT_RUN, &chan->state))
+	if (!sed)
 		return;
-	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
+
+	dma_pool_free(ioat_dma->sed_hw_pool[sed->hw_pool], sed->hw, sed->dma);
+	kmem_cache_free(ioat_sed_cache, sed);
 }
 
-dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan)
+static u64 ioat_get_current_completion(struct ioatdma_chan *ioat_chan)
 {
-	dma_addr_t phys_complete;
+	u64 phys_complete;
 	u64 completion;
 
-	completion = *chan->completion;
+	completion = *ioat_chan->completion;
 	phys_complete = ioat_chansts_to_addr(completion);
 
-	dev_dbg(to_dev(chan), "%s: phys_complete: %#llx\n", __func__,
+	dev_dbg(to_dev(ioat_chan), "%s: phys_complete: %#llx\n", __func__,
 		(unsigned long long) phys_complete);
 
-	if (is_ioat_halted(completion)) {
-		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-		dev_err(to_dev(chan), "Channel halted, chanerr = %x\n",
-			chanerr);
-
-		/* TODO do something to salvage the situation */
-	}
-
 	return phys_complete;
 }
 
-bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
-			   dma_addr_t *phys_complete)
+static bool ioat_cleanup_preamble(struct ioatdma_chan *ioat_chan,
+				   u64 *phys_complete)
 {
-	*phys_complete = ioat_get_current_completion(chan);
-	if (*phys_complete == chan->last_completion)
+	*phys_complete = ioat_get_current_completion(ioat_chan);
+	if (*phys_complete == ioat_chan->last_completion)
 		return false;
-	clear_bit(IOAT_COMPLETION_ACK, &chan->state);
-	mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+
+	clear_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
+	mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
 
 	return true;
 }
 
-static void __cleanup(struct ioat_dma_chan *ioat, dma_addr_t phys_complete)
+static void
+desc_get_errstat(struct ioatdma_chan *ioat_chan, struct ioat_ring_ent *desc)
 {
-	struct ioat_chan_common *chan = &ioat->base;
-	struct list_head *_desc, *n;
-	struct dma_async_tx_descriptor *tx;
+	struct ioat_dma_descriptor *hw = desc->hw;
 
-	dev_dbg(to_dev(chan), "%s: phys_complete: %llx\n",
-		 __func__, (unsigned long long) phys_complete);
-	list_for_each_safe(_desc, n, &ioat->used_desc) {
-		struct ioat_desc_sw *desc;
+	switch (hw->ctl_f.op) {
+	case IOAT_OP_PQ_VAL:
+	case IOAT_OP_PQ_VAL_16S:
+	{
+		struct ioat_pq_descriptor *pq = desc->pq;
 
-		prefetch(n);
-		desc = list_entry(_desc, typeof(*desc), node);
-		tx = &desc->txd;
-		/*
-		 * Incoming DMA requests may use multiple descriptors,
-		 * due to exceeding xfercap, perhaps. If so, only the
-		 * last one will have a cookie, and require unmapping.
-		 */
-		dump_desc_dbg(ioat, desc);
-		if (tx->cookie) {
-			dma_cookie_complete(tx);
-			dma_descriptor_unmap(tx);
-			ioat->active -= desc->hw->tx_cnt;
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
-		}
+		/* check if there's error written */
+		if (!pq->dwbes_f.wbes)
+			return;
 
-		if (tx->phys != phys_complete) {
-			/*
-			 * a completed entry, but not the last, so clean
-			 * up if the client is done with the descriptor
-			 */
-			if (async_tx_test_ack(tx))
-				list_move_tail(&desc->node, &ioat->free_desc);
-		} else {
-			/*
-			 * last used desc. Do not remove, so we can
-			 * append from it.
-			 */
-
-			/* if nothing else is pending, cancel the
-			 * completion timeout
-			 */
-			if (n == &ioat->used_desc) {
-				dev_dbg(to_dev(chan),
-					"%s cancel completion timeout\n",
-					__func__);
-				clear_bit(IOAT_COMPLETION_PENDING, &chan->state);
-			}
+		/* need to set a chanerr var for checking to clear later */
 
-			/* TODO check status bits? */
-			break;
-		}
-	}
+		if (pq->dwbes_f.p_val_err)
+			*desc->result |= SUM_CHECK_P_RESULT;
+
+		if (pq->dwbes_f.q_val_err)
+			*desc->result |= SUM_CHECK_Q_RESULT;
 
-	chan->last_completion = phys_complete;
+		return;
+	}
+	default:
+		return;
+	}
 }
 
 /**
- * ioat1_cleanup - cleanup up finished descriptors
- * @chan: ioat channel to be cleaned up
- *
- * To prevent lock contention we defer cleanup when the locks are
- * contended with a terminal timeout that forces cleanup and catches
- * completion notification errors.
+ * __cleanup - reclaim used descriptors
+ * @ioat: channel (ring) to clean
  */
-static void ioat1_cleanup(struct ioat_dma_chan *ioat)
+static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete)
 {
-	struct ioat_chan_common *chan = &ioat->base;
-	dma_addr_t phys_complete;
-
-	prefetch(chan->completion);
-
-	if (!spin_trylock_bh(&chan->cleanup_lock))
-		return;
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct ioat_ring_ent *desc;
+	bool seen_current = false;
+	int idx = ioat_chan->tail, i;
+	u16 active;
 
-	if (!ioat_cleanup_preamble(chan, &phys_complete)) {
-		spin_unlock_bh(&chan->cleanup_lock);
-		return;
-	}
+	dev_dbg(to_dev(ioat_chan), "%s: head: %#x tail: %#x issued: %#x\n",
+		__func__, ioat_chan->head, ioat_chan->tail, ioat_chan->issued);
 
-	if (!spin_trylock_bh(&ioat->desc_lock)) {
-		spin_unlock_bh(&chan->cleanup_lock);
+	/*
+	 * At restart of the channel, the completion address and the
+	 * channel status will be 0 due to starting a new chain. Since
+	 * it's new chain and the first descriptor "fails", there is
+	 * nothing to clean up. We do not want to reap the entire submitted
+	 * chain due to this 0 address value and then BUG.
+	 */
+	if (!phys_complete)
 		return;
-	}
 
-	__cleanup(ioat, phys_complete);
+	active = ioat_ring_active(ioat_chan);
+	for (i = 0; i < active && !seen_current; i++) {
+		struct dma_async_tx_descriptor *tx;
 
-	spin_unlock_bh(&ioat->desc_lock);
-	spin_unlock_bh(&chan->cleanup_lock);
-}
-
-static void ioat1_timer_event(unsigned long data)
-{
-	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
-	struct ioat_chan_common *chan = &ioat->base;
+		smp_read_barrier_depends();
+		prefetch(ioat_get_ring_ent(ioat_chan, idx + i + 1));
+		desc = ioat_get_ring_ent(ioat_chan, idx + i);
+		dump_desc_dbg(ioat_chan, desc);
 
-	dev_dbg(to_dev(chan), "%s: state: %lx\n", __func__, chan->state);
+		/* set err stat if we are using dwbes */
+		if (ioat_dma->cap & IOAT_CAP_DWBES)
+			desc_get_errstat(ioat_chan, desc);
 
-	spin_lock_bh(&chan->cleanup_lock);
-	if (test_and_clear_bit(IOAT_RESET_PENDING, &chan->state)) {
-		struct ioat_desc_sw *desc;
-
-		spin_lock_bh(&ioat->desc_lock);
+		tx = &desc->txd;
+		if (tx->cookie) {
+			dma_cookie_complete(tx);
+			dma_descriptor_unmap(tx);
+			if (tx->callback) {
+				tx->callback(tx->callback_param);
+				tx->callback = NULL;
+			}
+		}
 
-		/* restart active descriptors */
-		desc = to_ioat_desc(ioat->used_desc.prev);
-		ioat_set_chainaddr(ioat, desc->txd.phys);
-		ioat_start(chan);
+		if (tx->phys == phys_complete)
+			seen_current = true;
 
-		ioat->pending = 0;
-		set_bit(IOAT_COMPLETION_PENDING, &chan->state);
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-		spin_unlock_bh(&ioat->desc_lock);
-	} else if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		dma_addr_t phys_complete;
+		/* skip extended descriptors */
+		if (desc_has_ext(desc)) {
+			BUG_ON(i + 1 >= active);
+			i++;
+		}
 
-		spin_lock_bh(&ioat->desc_lock);
-		/* if we haven't made progress and we have already
-		 * acknowledged a pending completion once, then be more
-		 * forceful with a restart
-		 */
-		if (ioat_cleanup_preamble(chan, &phys_complete))
-			__cleanup(ioat, phys_complete);
-		else if (test_bit(IOAT_COMPLETION_ACK, &chan->state))
-			ioat1_reset_channel(ioat);
-		else {
-			u64 status = ioat_chansts(chan);
-
-			/* manually update the last completion address */
-			if (ioat_chansts_to_addr(status) != 0)
-				*chan->completion = status;
-
-			set_bit(IOAT_COMPLETION_ACK, &chan->state);
-			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		/* cleanup super extended descriptors */
+		if (desc->sed) {
+			ioat_free_sed(ioat_dma, desc->sed);
+			desc->sed = NULL;
 		}
-		spin_unlock_bh(&ioat->desc_lock);
 	}
-	spin_unlock_bh(&chan->cleanup_lock);
-}
-
-enum dma_status
-ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
-		   struct dma_tx_state *txstate)
-{
-	struct ioat_chan_common *chan = to_chan_common(c);
-	struct ioatdma_device *device = chan->device;
-	enum dma_status ret;
 
-	ret = dma_cookie_status(c, cookie, txstate);
-	if (ret == DMA_COMPLETE)
-		return ret;
+	/* finish all descriptor reads before incrementing tail */
+	smp_mb();
+	ioat_chan->tail = idx + i;
+	/* no active descs have written a completion? */
+	BUG_ON(active && !seen_current);
+	ioat_chan->last_completion = phys_complete;
 
-	device->cleanup_fn((unsigned long) c);
+	if (active - i == 0) {
+		dev_dbg(to_dev(ioat_chan), "%s: cancel completion timeout\n",
+			__func__);
+		mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
+	}
 
-	return dma_cookie_status(c, cookie, txstate);
+	/* 5 microsecond delay per pending descriptor */
+	writew(min((5 * (active - i)), IOAT_INTRDELAY_MASK),
+	       ioat_chan->ioat_dma->reg_base + IOAT_INTRDELAY_OFFSET);
 }
 
-static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
+static void ioat_cleanup(struct ioatdma_chan *ioat_chan)
 {
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioat_desc_sw *desc;
-	struct ioat_dma_descriptor *hw;
+	u64 phys_complete;
 
-	spin_lock_bh(&ioat->desc_lock);
+	spin_lock_bh(&ioat_chan->cleanup_lock);
 
-	desc = ioat1_dma_get_next_descriptor(ioat);
+	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
+		__cleanup(ioat_chan, phys_complete);
 
-	if (!desc) {
-		dev_err(to_dev(chan),
-			"Unable to start null desc - get next desc failed\n");
-		spin_unlock_bh(&ioat->desc_lock);
-		return;
-	}
+	if (is_ioat_halted(*ioat_chan->completion)) {
+		u32 chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
 
-	hw = desc->hw;
-	hw->ctl = 0;
-	hw->ctl_f.null = 1;
-	hw->ctl_f.int_en = 1;
-	hw->ctl_f.compl_write = 1;
-	/* set size to non-zero value (channel returns error when size is 0) */
-	hw->size = NULL_DESC_BUFFER_SIZE;
-	hw->src_addr = 0;
-	hw->dst_addr = 0;
-	async_tx_ack(&desc->txd);
-	hw->next = 0;
-	list_add_tail(&desc->node, &ioat->used_desc);
-	dump_desc_dbg(ioat, desc);
+		if (chanerr & IOAT_CHANERR_HANDLE_MASK) {
+			mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
+			ioat_eh(ioat_chan);
+		}
+	}
 
-	ioat_set_chainaddr(ioat, desc->txd.phys);
-	ioat_start(chan);
-	spin_unlock_bh(&ioat->desc_lock);
+	spin_unlock_bh(&ioat_chan->cleanup_lock);
 }
 
-/*
- * Perform a IOAT transaction to verify the HW works.
- */
-#define IOAT_TEST_SIZE 2000
+void ioat_cleanup_event(unsigned long data)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan((void *)data);
+
+	ioat_cleanup(ioat_chan);
+	if (!test_bit(IOAT_RUN, &ioat_chan->state))
+		return;
+	writew(IOAT_CHANCTRL_RUN, ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET);
+}
 
-static void ioat_dma_test_callback(void *dma_async_param)
+static void ioat_restart_channel(struct ioatdma_chan *ioat_chan)
 {
-	struct completion *cmp = dma_async_param;
+	u64 phys_complete;
+
+	ioat_quiesce(ioat_chan, 0);
+	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
+		__cleanup(ioat_chan, phys_complete);
 
-	complete(cmp);
+	__ioat_restart_chan(ioat_chan);
 }
 
-/**
- * ioat_dma_self_test - Perform a IOAT transaction to verify the HW works.
- * @device: device to be tested
- */
-int ioat_dma_self_test(struct ioatdma_device *device)
+static void ioat_eh(struct ioatdma_chan *ioat_chan)
 {
-	int i;
-	u8 *src;
-	u8 *dest;
-	struct dma_device *dma = &device->common;
-	struct device *dev = &device->pdev->dev;
-	struct dma_chan *dma_chan;
+	struct pci_dev *pdev = to_pdev(ioat_chan);
+	struct ioat_dma_descriptor *hw;
 	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
-	dma_cookie_t cookie;
-	int err = 0;
-	struct completion cmp;
-	unsigned long tmo;
-	unsigned long flags;
-
-	src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
-	if (!src)
-		return -ENOMEM;
-	dest = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
-	if (!dest) {
-		kfree(src);
-		return -ENOMEM;
-	}
+	u64 phys_complete;
+	struct ioat_ring_ent *desc;
+	u32 err_handled = 0;
+	u32 chanerr_int;
+	u32 chanerr;
 
-	/* Fill in src buffer */
-	for (i = 0; i < IOAT_TEST_SIZE; i++)
-		src[i] = (u8)i;
-
-	/* Start copy, using first DMA channel */
-	dma_chan = container_of(dma->channels.next, struct dma_chan,
-				device_node);
-	if (dma->device_alloc_chan_resources(dma_chan) < 1) {
-		dev_err(dev, "selftest cannot allocate chan resource\n");
-		err = -ENODEV;
-		goto out;
-	}
+	/* cleanup so tail points to descriptor that caused the error */
+	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
+		__cleanup(ioat_chan, phys_complete);
 
-	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, dma_src)) {
-		dev_err(dev, "mapping src buffer failed\n");
-		goto free_resources;
-	}
-	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, dma_dest)) {
-		dev_err(dev, "mapping dest buffer failed\n");
-		goto unmap_src;
-	}
-	flags = DMA_PREP_INTERRUPT;
-	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
-						   IOAT_TEST_SIZE, flags);
-	if (!tx) {
-		dev_err(dev, "Self-test prep failed, disabling\n");
-		err = -ENODEV;
-		goto unmap_dma;
-	}
+	chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+	pci_read_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, &chanerr_int);
 
-	async_tx_ack(tx);
-	init_completion(&cmp);
-	tx->callback = ioat_dma_test_callback;
-	tx->callback_param = &cmp;
-	cookie = tx->tx_submit(tx);
-	if (cookie < 0) {
-		dev_err(dev, "Self-test setup failed, disabling\n");
-		err = -ENODEV;
-		goto unmap_dma;
-	}
-	dma->device_issue_pending(dma_chan);
+	dev_dbg(to_dev(ioat_chan), "%s: error = %x:%x\n",
+		__func__, chanerr, chanerr_int);
 
-	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+	desc = ioat_get_ring_ent(ioat_chan, ioat_chan->tail);
+	hw = desc->hw;
+	dump_desc_dbg(ioat_chan, desc);
 
-	if (tmo == 0 ||
-	    dma->device_tx_status(dma_chan, cookie, NULL)
-					!= DMA_COMPLETE) {
-		dev_err(dev, "Self-test copy timed out, disabling\n");
-		err = -ENODEV;
-		goto unmap_dma;
-	}
-	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
-		dev_err(dev, "Self-test copy failed compare, disabling\n");
-		err = -ENODEV;
-		goto free_resources;
+	switch (hw->ctl_f.op) {
+	case IOAT_OP_XOR_VAL:
+		if (chanerr & IOAT_CHANERR_XOR_P_OR_CRC_ERR) {
+			*desc->result |= SUM_CHECK_P_RESULT;
+			err_handled |= IOAT_CHANERR_XOR_P_OR_CRC_ERR;
+		}
+		break;
+	case IOAT_OP_PQ_VAL:
+	case IOAT_OP_PQ_VAL_16S:
+		if (chanerr & IOAT_CHANERR_XOR_P_OR_CRC_ERR) {
+			*desc->result |= SUM_CHECK_P_RESULT;
+			err_handled |= IOAT_CHANERR_XOR_P_OR_CRC_ERR;
+		}
+		if (chanerr & IOAT_CHANERR_XOR_Q_ERR) {
+			*desc->result |= SUM_CHECK_Q_RESULT;
+			err_handled |= IOAT_CHANERR_XOR_Q_ERR;
+		}
+		break;
 	}
 
-unmap_dma:
-	dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-unmap_src:
-	dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
-free_resources:
-	dma->device_free_chan_resources(dma_chan);
-out:
-	kfree(src);
-	kfree(dest);
-	return err;
-}
-
-static char ioat_interrupt_style[32] = "msix";
-module_param_string(ioat_interrupt_style, ioat_interrupt_style,
-		    sizeof(ioat_interrupt_style), 0644);
-MODULE_PARM_DESC(ioat_interrupt_style,
-		 "set ioat interrupt style: msix (default), msi, intx");
-
-/**
- * ioat_dma_setup_interrupts - setup interrupt handler
- * @device: ioat device
- */
-int ioat_dma_setup_interrupts(struct ioatdma_device *device)
-{
-	struct ioat_chan_common *chan;
-	struct pci_dev *pdev = device->pdev;
-	struct device *dev = &pdev->dev;
-	struct msix_entry *msix;
-	int i, j, msixcnt;
-	int err = -EINVAL;
-	u8 intrctrl = 0;
-
-	if (!strcmp(ioat_interrupt_style, "msix"))
-		goto msix;
-	if (!strcmp(ioat_interrupt_style, "msi"))
-		goto msi;
-	if (!strcmp(ioat_interrupt_style, "intx"))
-		goto intx;
-	dev_err(dev, "invalid ioat_interrupt_style %s\n", ioat_interrupt_style);
-	goto err_no_irq;
-
-msix:
-	/* The number of MSI-X vectors should equal the number of channels */
-	msixcnt = device->common.chancnt;
-	for (i = 0; i < msixcnt; i++)
-		device->msix_entries[i].entry = i;
-
-	err = pci_enable_msix_exact(pdev, device->msix_entries, msixcnt);
-	if (err)
-		goto msi;
-
-	for (i = 0; i < msixcnt; i++) {
-		msix = &device->msix_entries[i];
-		chan = ioat_chan_by_index(device, i);
-		err = devm_request_irq(dev, msix->vector,
-				       ioat_dma_do_interrupt_msix, 0,
-				       "ioat-msix", chan);
-		if (err) {
-			for (j = 0; j < i; j++) {
-				msix = &device->msix_entries[j];
-				chan = ioat_chan_by_index(device, j);
-				devm_free_irq(dev, msix->vector, chan);
+	/* fault on unhandled error or spurious halt */
+	if (chanerr ^ err_handled || chanerr == 0) {
+		dev_err(to_dev(ioat_chan), "%s: fatal error (%x:%x)\n",
+			__func__, chanerr, err_handled);
+		BUG();
+	} else { /* cleanup the faulty descriptor */
+		tx = &desc->txd;
+		if (tx->cookie) {
+			dma_cookie_complete(tx);
+			dma_descriptor_unmap(tx);
+			if (tx->callback) {
+				tx->callback(tx->callback_param);
+				tx->callback = NULL;
 			}
-			goto msi;
 		}
 	}
-	intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
-	device->irq_mode = IOAT_MSIX;
-	goto done;
 
-msi:
-	err = pci_enable_msi(pdev);
-	if (err)
-		goto intx;
+	writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+	pci_write_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, chanerr_int);
 
-	err = devm_request_irq(dev, pdev->irq, ioat_dma_do_interrupt, 0,
-			       "ioat-msi", device);
-	if (err) {
-		pci_disable_msi(pdev);
-		goto intx;
-	}
-	device->irq_mode = IOAT_MSI;
-	goto done;
-
-intx:
-	err = devm_request_irq(dev, pdev->irq, ioat_dma_do_interrupt,
-			       IRQF_SHARED, "ioat-intx", device);
-	if (err)
-		goto err_no_irq;
-
-	device->irq_mode = IOAT_INTX;
-done:
-	if (device->intr_quirk)
-		device->intr_quirk(device);
-	intrctrl |= IOAT_INTRCTRL_MASTER_INT_EN;
-	writeb(intrctrl, device->reg_base + IOAT_INTRCTRL_OFFSET);
-	return 0;
-
-err_no_irq:
-	/* Disable all interrupt generation */
-	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
-	device->irq_mode = IOAT_NOIRQ;
-	dev_err(dev, "no usable interrupts\n");
-	return err;
-}
-EXPORT_SYMBOL(ioat_dma_setup_interrupts);
+	/* mark faulting descriptor as complete */
+	*ioat_chan->completion = desc->txd.phys;
 
-static void ioat_disable_interrupts(struct ioatdma_device *device)
-{
-	/* Disable all interrupt generation */
-	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
+	spin_lock_bh(&ioat_chan->prep_lock);
+	ioat_restart_channel(ioat_chan);
+	spin_unlock_bh(&ioat_chan->prep_lock);
 }
 
-int ioat_probe(struct ioatdma_device *device)
+static void check_active(struct ioatdma_chan *ioat_chan)
 {
-	int err = -ENODEV;
-	struct dma_device *dma = &device->common;
-	struct pci_dev *pdev = device->pdev;
-	struct device *dev = &pdev->dev;
-
-	/* DMA coherent memory pool for DMA descriptor allocations */
-	device->dma_pool = pci_pool_create("dma_desc_pool", pdev,
-					   sizeof(struct ioat_dma_descriptor),
-					   64, 0);
-	if (!device->dma_pool) {
-		err = -ENOMEM;
-		goto err_dma_pool;
-	}
-
-	device->completion_pool = pci_pool_create("completion_pool", pdev,
-						  sizeof(u64), SMP_CACHE_BYTES,
-						  SMP_CACHE_BYTES);
-
-	if (!device->completion_pool) {
-		err = -ENOMEM;
-		goto err_completion_pool;
+	if (ioat_ring_active(ioat_chan)) {
+		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
+		return;
 	}
 
-	device->enumerate_channels(device);
-
-	dma_cap_set(DMA_MEMCPY, dma->cap_mask);
-	dma->dev = &pdev->dev;
+	if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &ioat_chan->state))
+		mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
+	else if (ioat_chan->alloc_order > ioat_get_alloc_order()) {
+		/* if the ring is idle, empty, and oversized try to step
+		 * down the size
+		 */
+		reshape_ring(ioat_chan, ioat_chan->alloc_order - 1);
 
-	if (!dma->chancnt) {
-		dev_err(dev, "channel enumeration error\n");
-		goto err_setup_interrupts;
+		/* keep shrinking until we get back to our minimum
+		 * default size
+		 */
+		if (ioat_chan->alloc_order > ioat_get_alloc_order())
+			mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
 	}
 
-	err = ioat_dma_setup_interrupts(device);
-	if (err)
-		goto err_setup_interrupts;
+}
 
-	err = device->self_test(device);
-	if (err)
-		goto err_self_test;
+void ioat_timer_event(unsigned long data)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan((void *)data);
+	dma_addr_t phys_complete;
+	u64 status;
 
-	return 0;
+	status = ioat_chansts(ioat_chan);
 
-err_self_test:
-	ioat_disable_interrupts(device);
-err_setup_interrupts:
-	pci_pool_destroy(device->completion_pool);
-err_completion_pool:
-	pci_pool_destroy(device->dma_pool);
-err_dma_pool:
-	return err;
-}
+	/* when halted due to errors check for channel
+	 * programming errors before advancing the completion state
+	 */
+	if (is_ioat_halted(status)) {
+		u32 chanerr;
 
-int ioat_register(struct ioatdma_device *device)
-{
-	int err = dma_async_device_register(&device->common);
+		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_err(to_dev(ioat_chan), "%s: Channel halted (%x)\n",
+			__func__, chanerr);
+		if (test_bit(IOAT_RUN, &ioat_chan->state))
+			BUG_ON(is_ioat_bug(chanerr));
+		else /* we never got off the ground */
+			return;
+	}
 
-	if (err) {
-		ioat_disable_interrupts(device);
-		pci_pool_destroy(device->completion_pool);
-		pci_pool_destroy(device->dma_pool);
+	/* if we haven't made progress and we have already
+	 * acknowledged a pending completion once, then be more
+	 * forceful with a restart
+	 */
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
+		__cleanup(ioat_chan, phys_complete);
+	else if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) {
+		spin_lock_bh(&ioat_chan->prep_lock);
+		ioat_restart_channel(ioat_chan);
+		spin_unlock_bh(&ioat_chan->prep_lock);
+		spin_unlock_bh(&ioat_chan->cleanup_lock);
+		return;
+	} else {
+		set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
+		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
 	}
 
-	return err;
-}
 
-/* ioat1_intr_quirk - fix up dma ctrl register to enable / disable msi */
-static void ioat1_intr_quirk(struct ioatdma_device *device)
-{
-	struct pci_dev *pdev = device->pdev;
-	u32 dmactrl;
-
-	pci_read_config_dword(pdev, IOAT_PCI_DMACTRL_OFFSET, &dmactrl);
-	if (pdev->msi_enabled)
-		dmactrl |= IOAT_PCI_DMACTRL_MSI_EN;
-	else
-		dmactrl &= ~IOAT_PCI_DMACTRL_MSI_EN;
-	pci_write_config_dword(pdev, IOAT_PCI_DMACTRL_OFFSET, dmactrl);
+	if (ioat_ring_active(ioat_chan))
+		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
+	else {
+		spin_lock_bh(&ioat_chan->prep_lock);
+		check_active(ioat_chan);
+		spin_unlock_bh(&ioat_chan->prep_lock);
+	}
+	spin_unlock_bh(&ioat_chan->cleanup_lock);
 }
 
-static ssize_t ring_size_show(struct dma_chan *c, char *page)
+enum dma_status
+ioat_tx_status(struct dma_chan *c, dma_cookie_t cookie,
+		struct dma_tx_state *txstate)
 {
-	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	enum dma_status ret;
 
-	return sprintf(page, "%d\n", ioat->desccount);
-}
-static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size);
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
 
-static ssize_t ring_active_show(struct dma_chan *c, char *page)
-{
-	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+	ioat_cleanup(ioat_chan);
 
-	return sprintf(page, "%d\n", ioat->active);
+	return dma_cookie_status(c, cookie, txstate);
 }
-static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active);
 
-static ssize_t cap_show(struct dma_chan *c, char *page)
+static int ioat_irq_reinit(struct ioatdma_device *ioat_dma)
 {
-	struct dma_device *dma = c->device;
+	struct pci_dev *pdev = ioat_dma->pdev;
+	int irq = pdev->irq, i;
 
-	return sprintf(page, "copy%s%s%s%s%s\n",
-		       dma_has_cap(DMA_PQ, dma->cap_mask) ? " pq" : "",
-		       dma_has_cap(DMA_PQ_VAL, dma->cap_mask) ? " pq_val" : "",
-		       dma_has_cap(DMA_XOR, dma->cap_mask) ? " xor" : "",
-		       dma_has_cap(DMA_XOR_VAL, dma->cap_mask) ? " xor_val" : "",
-		       dma_has_cap(DMA_INTERRUPT, dma->cap_mask) ? " intr" : "");
+	if (!is_bwd_ioat(pdev))
+		return 0;
 
-}
-struct ioat_sysfs_entry ioat_cap_attr = __ATTR_RO(cap);
-
-static ssize_t version_show(struct dma_chan *c, char *page)
-{
-	struct dma_device *dma = c->device;
-	struct ioatdma_device *device = to_ioatdma_device(dma);
+	switch (ioat_dma->irq_mode) {
+	case IOAT_MSIX:
+		for (i = 0; i < ioat_dma->dma_dev.chancnt; i++) {
+			struct msix_entry *msix = &ioat_dma->msix_entries[i];
+			struct ioatdma_chan *ioat_chan;
 
-	return sprintf(page, "%d.%d\n",
-		       device->version >> 4, device->version & 0xf);
-}
-struct ioat_sysfs_entry ioat_version_attr = __ATTR_RO(version);
-
-static struct attribute *ioat1_attrs[] = {
-	&ring_size_attr.attr,
-	&ring_active_attr.attr,
-	&ioat_cap_attr.attr,
-	&ioat_version_attr.attr,
-	NULL,
-};
-
-static ssize_t
-ioat_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
-{
-	struct ioat_sysfs_entry *entry;
-	struct ioat_chan_common *chan;
+			ioat_chan = ioat_chan_by_index(ioat_dma, i);
+			devm_free_irq(&pdev->dev, msix->vector, ioat_chan);
+		}
 
-	entry = container_of(attr, struct ioat_sysfs_entry, attr);
-	chan = container_of(kobj, struct ioat_chan_common, kobj);
+		pci_disable_msix(pdev);
+		break;
+	case IOAT_MSI:
+		pci_disable_msi(pdev);
+		/* fall through */
+	case IOAT_INTX:
+		devm_free_irq(&pdev->dev, irq, ioat_dma);
+		break;
+	default:
+		return 0;
+	}
+	ioat_dma->irq_mode = IOAT_NOIRQ;
 
-	if (!entry->show)
-		return -EIO;
-	return entry->show(&chan->common, page);
+	return ioat_dma_setup_interrupts(ioat_dma);
 }
 
-const struct sysfs_ops ioat_sysfs_ops = {
-	.show	= ioat_attr_show,
-};
-
-static struct kobj_type ioat1_ktype = {
-	.sysfs_ops = &ioat_sysfs_ops,
-	.default_attrs = ioat1_attrs,
-};
-
-void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type)
+int ioat_reset_hw(struct ioatdma_chan *ioat_chan)
 {
-	struct dma_device *dma = &device->common;
-	struct dma_chan *c;
+	/* throw away whatever the channel was doing and get it
+	 * initialized, with ioat3 specific workarounds
+	 */
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct pci_dev *pdev = ioat_dma->pdev;
+	u32 chanerr;
+	u16 dev_id;
+	int err;
+
+	ioat_quiesce(ioat_chan, msecs_to_jiffies(100));
 
-	list_for_each_entry(c, &dma->channels, device_node) {
-		struct ioat_chan_common *chan = to_chan_common(c);
-		struct kobject *parent = &c->dev->device.kobj;
-		int err;
+	chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+	writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
 
-		err = kobject_init_and_add(&chan->kobj, type, parent, "quickdata");
+	if (ioat_dma->version < IOAT_VER_3_3) {
+		/* clear any pending errors */
+		err = pci_read_config_dword(pdev,
+				IOAT_PCI_CHANERR_INT_OFFSET, &chanerr);
 		if (err) {
-			dev_warn(to_dev(chan),
-				 "sysfs init error (%d), continuing...\n", err);
-			kobject_put(&chan->kobj);
-			set_bit(IOAT_KOBJ_INIT_FAIL, &chan->state);
+			dev_err(&pdev->dev,
+				"channel error register unreachable\n");
+			return err;
 		}
-	}
-}
+		pci_write_config_dword(pdev,
+				IOAT_PCI_CHANERR_INT_OFFSET, chanerr);
 
-void ioat_kobject_del(struct ioatdma_device *device)
-{
-	struct dma_device *dma = &device->common;
-	struct dma_chan *c;
-
-	list_for_each_entry(c, &dma->channels, device_node) {
-		struct ioat_chan_common *chan = to_chan_common(c);
-
-		if (!test_bit(IOAT_KOBJ_INIT_FAIL, &chan->state)) {
-			kobject_del(&chan->kobj);
-			kobject_put(&chan->kobj);
+		/* Clear DMAUNCERRSTS Cfg-Reg Parity Error status bit
+		 * (workaround for spurious config parity error after restart)
+		 */
+		pci_read_config_word(pdev, IOAT_PCI_DEVICE_ID_OFFSET, &dev_id);
+		if (dev_id == PCI_DEVICE_ID_INTEL_IOAT_TBG0) {
+			pci_write_config_dword(pdev,
+					       IOAT_PCI_DMAUNCERRSTS_OFFSET,
+					       0x10);
 		}
 	}
-}
 
-int ioat1_dma_probe(struct ioatdma_device *device, int dca)
-{
-	struct pci_dev *pdev = device->pdev;
-	struct dma_device *dma;
-	int err;
+	err = ioat_reset_sync(ioat_chan, msecs_to_jiffies(200));
+	if (!err)
+		err = ioat_irq_reinit(ioat_dma);
 
-	device->intr_quirk = ioat1_intr_quirk;
-	device->enumerate_channels = ioat1_enumerate_channels;
-	device->self_test = ioat_dma_self_test;
-	device->timer_fn = ioat1_timer_event;
-	device->cleanup_fn = ioat1_cleanup_event;
-	dma = &device->common;
-	dma->device_prep_dma_memcpy = ioat1_dma_prep_memcpy;
-	dma->device_issue_pending = ioat1_dma_memcpy_issue_pending;
-	dma->device_alloc_chan_resources = ioat1_dma_alloc_chan_resources;
-	dma->device_free_chan_resources = ioat1_dma_free_chan_resources;
-	dma->device_tx_status = ioat_dma_tx_status;
-
-	err = ioat_probe(device);
-	if (err)
-		return err;
-	err = ioat_register(device);
 	if (err)
-		return err;
-	ioat_kobject_add(device, &ioat1_ktype);
-
-	if (dca)
-		device->dca = ioat_dca_init(pdev, device->reg_base);
+		dev_err(&pdev->dev, "Failed to reset: %d\n", err);
 
 	return err;
 }
-
-void ioat_dma_remove(struct ioatdma_device *device)
-{
-	struct dma_device *dma = &device->common;
-
-	ioat_disable_interrupts(device);
-
-	ioat_kobject_del(device);
-
-	dma_async_device_unregister(dma);
-
-	pci_pool_destroy(device->dma_pool);
-	pci_pool_destroy(device->completion_pool);
-
-	INIT_LIST_HEAD(&dma->channels);
-}
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 30f5c7eede16..1bc084986646 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -18,26 +18,32 @@
 #define IOATDMA_H
 
 #include <linux/dmaengine.h>
-#include "hw.h"
-#include "registers.h"
 #include <linux/init.h>
 #include <linux/dmapool.h>
 #include <linux/cache.h>
 #include <linux/pci_ids.h>
-#include <net/tcp.h>
+#include <linux/circ_buf.h>
+#include <linux/interrupt.h>
+#include "registers.h"
+#include "hw.h"
 
 #define IOAT_DMA_VERSION  "4.00"
 
-#define IOAT_LOW_COMPLETION_MASK	0xffffffc0
 #define IOAT_DMA_DCA_ANY_CPU		~0
 
-#define to_ioatdma_device(dev) container_of(dev, struct ioatdma_device, common)
-#define to_ioat_desc(lh) container_of(lh, struct ioat_desc_sw, node)
-#define tx_to_ioat_desc(tx) container_of(tx, struct ioat_desc_sw, txd)
-#define to_dev(ioat_chan) (&(ioat_chan)->device->pdev->dev)
-#define to_pdev(ioat_chan) ((ioat_chan)->device->pdev)
+#define to_ioatdma_device(dev) container_of(dev, struct ioatdma_device, dma_dev)
+#define to_dev(ioat_chan) (&(ioat_chan)->ioat_dma->pdev->dev)
+#define to_pdev(ioat_chan) ((ioat_chan)->ioat_dma->pdev)
+
+#define chan_num(ch) ((int)((ch)->reg_base - (ch)->ioat_dma->reg_base) / 0x80)
 
-#define chan_num(ch) ((int)((ch)->reg_base - (ch)->device->reg_base) / 0x80)
+/* ioat hardware assumes at least two sources for raid operations */
+#define src_cnt_to_sw(x) ((x) + 2)
+#define src_cnt_to_hw(x) ((x) - 2)
+#define ndest_to_sw(x) ((x) + 1)
+#define ndest_to_hw(x) ((x) - 1)
+#define src16_cnt_to_sw(x) ((x) + 9)
+#define src16_cnt_to_hw(x) ((x) - 9)
 
 /*
  * workaround for IOAT ver.3.0 null descriptor issue
@@ -57,19 +63,15 @@ enum ioat_irq_mode {
  * @pdev: PCI-Express device
  * @reg_base: MMIO register space base address
  * @dma_pool: for allocating DMA descriptors
- * @common: embedded struct dma_device
+ * @completion_pool: DMA buffers for completion ops
+ * @sed_hw_pool: DMA super descriptor pools
+ * @dma_dev: embedded struct dma_device
  * @version: version of ioatdma device
  * @msix_entries: irq handlers
  * @idx: per channel data
  * @dca: direct cache access context
- * @intr_quirk: interrupt setup quirk (for ioat_v1 devices)
- * @enumerate_channels: hw version specific channel enumeration
- * @reset_hw: hw version specific channel (re)initialization
- * @cleanup_fn: select between the v2 and v3 cleanup routines
- * @timer_fn: select between the v2 and v3 timer watchdog routines
- * @self_test: hardware version specific self test for each supported op type
- *
- * Note: the v3 cleanup routine supports raid operations
+ * @irq_mode: interrupt mode (INTX, MSI, MSIX)
+ * @cap: read DMA capabilities register
  */
 struct ioatdma_device {
 	struct pci_dev *pdev;
@@ -78,28 +80,21 @@ struct ioatdma_device {
 	struct pci_pool *completion_pool;
 #define MAX_SED_POOLS	5
 	struct dma_pool *sed_hw_pool[MAX_SED_POOLS];
-	struct dma_device common;
+	struct dma_device dma_dev;
 	u8 version;
 	struct msix_entry msix_entries[4];
-	struct ioat_chan_common *idx[4];
+	struct ioatdma_chan *idx[4];
 	struct dca_provider *dca;
 	enum ioat_irq_mode irq_mode;
 	u32 cap;
-	void (*intr_quirk)(struct ioatdma_device *device);
-	int (*enumerate_channels)(struct ioatdma_device *device);
-	int (*reset_hw)(struct ioat_chan_common *chan);
-	void (*cleanup_fn)(unsigned long data);
-	void (*timer_fn)(unsigned long data);
-	int (*self_test)(struct ioatdma_device *device);
 };
 
-struct ioat_chan_common {
-	struct dma_chan common;
+struct ioatdma_chan {
+	struct dma_chan dma_chan;
 	void __iomem *reg_base;
 	dma_addr_t last_completion;
 	spinlock_t cleanup_lock;
 	unsigned long state;
-	#define IOAT_COMPLETION_PENDING 0
 	#define IOAT_COMPLETION_ACK 1
 	#define IOAT_RESET_PENDING 2
 	#define IOAT_KOBJ_INIT_FAIL 3
@@ -110,11 +105,32 @@ struct ioat_chan_common {
 	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
 	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
 	#define RESET_DELAY msecs_to_jiffies(100)
-	struct ioatdma_device *device;
+	struct ioatdma_device *ioat_dma;
 	dma_addr_t completion_dma;
 	u64 *completion;
 	struct tasklet_struct cleanup_task;
 	struct kobject kobj;
+
+/* ioat v2 / v3 channel attributes
+ * @xfercap_log; log2 of channel max transfer length (for fast division)
+ * @head: allocated index
+ * @issued: hardware notification point
+ * @tail: cleanup index
+ * @dmacount: identical to 'head' except for occasionally resetting to zero
+ * @alloc_order: log2 of the number of allocated descriptors
+ * @produce: number of descriptors to produce at submit time
+ * @ring: software ring buffer implementation of hardware ring
+ * @prep_lock: serializes descriptor preparation (producers)
+ */
+	size_t xfercap_log;
+	u16 head;
+	u16 issued;
+	u16 tail;
+	u16 dmacount;
+	u16 alloc_order;
+	u16 produce;
+	struct ioat_ring_ent **ring;
+	spinlock_t prep_lock;
 };
 
 struct ioat_sysfs_entry {
@@ -123,28 +139,11 @@ struct ioat_sysfs_entry {
 };
 
 /**
- * struct ioat_dma_chan - internal representation of a DMA channel
- */
-struct ioat_dma_chan {
-	struct ioat_chan_common base;
-
-	size_t xfercap;	/* XFERCAP register value expanded out */
-
-	spinlock_t desc_lock;
-	struct list_head free_desc;
-	struct list_head used_desc;
-
-	int pending;
-	u16 desccount;
-	u16 active;
-};
-
-/**
  * struct ioat_sed_ent - wrapper around super extended hardware descriptor
  * @hw: hardware SED
- * @sed_dma: dma address for the SED
- * @list: list member
+ * @dma: dma address for the SED
  * @parent: point to the dma descriptor that's the parent
+ * @hw_pool: descriptor pool index
  */
 struct ioat_sed_ent {
 	struct ioat_sed_raw_descriptor *hw;
@@ -153,39 +152,57 @@ struct ioat_sed_ent {
 	unsigned int hw_pool;
 };
 
-static inline struct ioat_chan_common *to_chan_common(struct dma_chan *c)
-{
-	return container_of(c, struct ioat_chan_common, common);
-}
-
-static inline struct ioat_dma_chan *to_ioat_chan(struct dma_chan *c)
-{
-	struct ioat_chan_common *chan = to_chan_common(c);
-
-	return container_of(chan, struct ioat_dma_chan, base);
-}
-
-/* wrapper around hardware descriptor format + additional software fields */
-
 /**
- * struct ioat_desc_sw - wrapper around hardware descriptor
+ * struct ioat_ring_ent - wrapper around hardware descriptor
  * @hw: hardware DMA descriptor (for memcpy)
- * @node: this descriptor will either be on the free list,
- *     or attached to a transaction list (tx_list)
+ * @xor: hardware xor descriptor
+ * @xor_ex: hardware xor extension descriptor
+ * @pq: hardware pq descriptor
+ * @pq_ex: hardware pq extension descriptor
+ * @pqu: hardware pq update descriptor
+ * @raw: hardware raw (un-typed) descriptor
  * @txd: the generic software descriptor for all engines
+ * @len: total transaction length for unmap
+ * @result: asynchronous result of validate operations
  * @id: identifier for debug
+ * @sed: pointer to super extended descriptor sw desc
  */
-struct ioat_desc_sw {
-	struct ioat_dma_descriptor *hw;
-	struct list_head node;
+
+struct ioat_ring_ent {
+	union {
+		struct ioat_dma_descriptor *hw;
+		struct ioat_xor_descriptor *xor;
+		struct ioat_xor_ext_descriptor *xor_ex;
+		struct ioat_pq_descriptor *pq;
+		struct ioat_pq_ext_descriptor *pq_ex;
+		struct ioat_pq_update_descriptor *pqu;
+		struct ioat_raw_descriptor *raw;
+	};
 	size_t len;
-	struct list_head tx_list;
 	struct dma_async_tx_descriptor txd;
+	enum sum_check_flags *result;
 	#ifdef DEBUG
 	int id;
 	#endif
+	struct ioat_sed_ent *sed;
 };
 
+extern const struct sysfs_ops ioat_sysfs_ops;
+extern struct ioat_sysfs_entry ioat_version_attr;
+extern struct ioat_sysfs_entry ioat_cap_attr;
+extern int ioat_pending_level;
+extern int ioat_ring_alloc_order;
+extern struct kobj_type ioat_ktype;
+extern struct kmem_cache *ioat_cache;
+extern int ioat_ring_max_alloc_order;
+extern struct kmem_cache *ioat_sed_cache;
+
+static inline struct ioatdma_chan *to_ioat_chan(struct dma_chan *c)
+{
+	return container_of(c, struct ioatdma_chan, dma_chan);
+}
+
+/* wrapper around hardware descriptor format + additional software fields */
 #ifdef DEBUG
 #define set_desc_id(desc, i) ((desc)->id = (i))
 #define desc_id(desc) ((desc)->id)
@@ -195,10 +212,10 @@ struct ioat_desc_sw {
 #endif
 
 static inline void
-__dump_desc_dbg(struct ioat_chan_common *chan, struct ioat_dma_descriptor *hw,
+__dump_desc_dbg(struct ioatdma_chan *ioat_chan, struct ioat_dma_descriptor *hw,
 		struct dma_async_tx_descriptor *tx, int id)
 {
-	struct device *dev = to_dev(chan);
+	struct device *dev = to_dev(ioat_chan);
 
 	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) cookie: %d flags: %#x"
 		" ctl: %#10.8x (op: %#x int_en: %d compl: %d)\n", id,
@@ -208,25 +225,25 @@ __dump_desc_dbg(struct ioat_chan_common *chan, struct ioat_dma_descriptor *hw,
 }
 
 #define dump_desc_dbg(c, d) \
-	({ if (d) __dump_desc_dbg(&c->base, d->hw, &d->txd, desc_id(d)); 0; })
+	({ if (d) __dump_desc_dbg(c, d->hw, &d->txd, desc_id(d)); 0; })
 
-static inline struct ioat_chan_common *
-ioat_chan_by_index(struct ioatdma_device *device, int index)
+static inline struct ioatdma_chan *
+ioat_chan_by_index(struct ioatdma_device *ioat_dma, int index)
 {
-	return device->idx[index];
+	return ioat_dma->idx[index];
 }
 
-static inline u64 ioat_chansts_32(struct ioat_chan_common *chan)
+static inline u64 ioat_chansts_32(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = chan->device->version;
+	u8 ver = ioat_chan->ioat_dma->version;
 	u64 status;
 	u32 status_lo;
 
 	/* We need to read the low address first as this causes the
 	 * chipset to latch the upper bits for the subsequent read
 	 */
-	status_lo = readl(chan->reg_base + IOAT_CHANSTS_OFFSET_LOW(ver));
-	status = readl(chan->reg_base + IOAT_CHANSTS_OFFSET_HIGH(ver));
+	status_lo = readl(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET_LOW(ver));
+	status = readl(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET_HIGH(ver));
 	status <<= 32;
 	status |= status_lo;
 
@@ -235,16 +252,16 @@ static inline u64 ioat_chansts_32(struct ioat_chan_common *chan)
 
 #if BITS_PER_LONG == 64
 
-static inline u64 ioat_chansts(struct ioat_chan_common *chan)
+static inline u64 ioat_chansts(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = chan->device->version;
+	u8 ver = ioat_chan->ioat_dma->version;
 	u64 status;
 
 	 /* With IOAT v3.3 the status register is 64bit.  */
 	if (ver >= IOAT_VER_3_3)
-		status = readq(chan->reg_base + IOAT_CHANSTS_OFFSET(ver));
+		status = readq(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET(ver));
 	else
-		status = ioat_chansts_32(chan);
+		status = ioat_chansts_32(ioat_chan);
 
 	return status;
 }
@@ -253,56 +270,41 @@ static inline u64 ioat_chansts(struct ioat_chan_common *chan)
 #define ioat_chansts ioat_chansts_32
 #endif
 
-static inline void ioat_start(struct ioat_chan_common *chan)
-{
-	u8 ver = chan->device->version;
-
-	writeb(IOAT_CHANCMD_START, chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
-}
-
 static inline u64 ioat_chansts_to_addr(u64 status)
 {
 	return status & IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
 }
 
-static inline u32 ioat_chanerr(struct ioat_chan_common *chan)
+static inline u32 ioat_chanerr(struct ioatdma_chan *ioat_chan)
 {
-	return readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+	return readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
 }
 
-static inline void ioat_suspend(struct ioat_chan_common *chan)
+static inline void ioat_suspend(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = chan->device->version;
+	u8 ver = ioat_chan->ioat_dma->version;
 
-	writeb(IOAT_CHANCMD_SUSPEND, chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
+	writeb(IOAT_CHANCMD_SUSPEND,
+	       ioat_chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
 }
 
-static inline void ioat_reset(struct ioat_chan_common *chan)
+static inline void ioat_reset(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = chan->device->version;
+	u8 ver = ioat_chan->ioat_dma->version;
 
-	writeb(IOAT_CHANCMD_RESET, chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
+	writeb(IOAT_CHANCMD_RESET,
+	       ioat_chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
 }
 
-static inline bool ioat_reset_pending(struct ioat_chan_common *chan)
+static inline bool ioat_reset_pending(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = chan->device->version;
+	u8 ver = ioat_chan->ioat_dma->version;
 	u8 cmd;
 
-	cmd = readb(chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
+	cmd = readb(ioat_chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
 	return (cmd & IOAT_CHANCMD_RESET) == IOAT_CHANCMD_RESET;
 }
 
-static inline void ioat_set_chainaddr(struct ioat_dma_chan *ioat, u64 addr)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-
-	writel(addr & 0x00000000FFFFFFFF,
-	       chan->reg_base + IOAT1_CHAINADDR_OFFSET_LOW);
-	writel(addr >> 32,
-	       chan->reg_base + IOAT1_CHAINADDR_OFFSET_HIGH);
-}
-
 static inline bool is_ioat_active(unsigned long status)
 {
 	return ((status & IOAT_CHANSTS_STATUS) == IOAT_CHANSTS_ACTIVE);
@@ -329,24 +331,111 @@ static inline bool is_ioat_bug(unsigned long err)
 	return !!err;
 }
 
-int ioat_probe(struct ioatdma_device *device);
-int ioat_register(struct ioatdma_device *device);
-int ioat1_dma_probe(struct ioatdma_device *dev, int dca);
-int ioat_dma_self_test(struct ioatdma_device *device);
-void ioat_dma_remove(struct ioatdma_device *device);
+#define IOAT_MAX_ORDER 16
+#define ioat_get_alloc_order() \
+	(min(ioat_ring_alloc_order, IOAT_MAX_ORDER))
+#define ioat_get_max_alloc_order() \
+	(min(ioat_ring_max_alloc_order, IOAT_MAX_ORDER))
+
+static inline u32 ioat_ring_size(struct ioatdma_chan *ioat_chan)
+{
+	return 1 << ioat_chan->alloc_order;
+}
+
+/* count of descriptors in flight with the engine */
+static inline u16 ioat_ring_active(struct ioatdma_chan *ioat_chan)
+{
+	return CIRC_CNT(ioat_chan->head, ioat_chan->tail,
+			ioat_ring_size(ioat_chan));
+}
+
+/* count of descriptors pending submission to hardware */
+static inline u16 ioat_ring_pending(struct ioatdma_chan *ioat_chan)
+{
+	return CIRC_CNT(ioat_chan->head, ioat_chan->issued,
+			ioat_ring_size(ioat_chan));
+}
+
+static inline u32 ioat_ring_space(struct ioatdma_chan *ioat_chan)
+{
+	return ioat_ring_size(ioat_chan) - ioat_ring_active(ioat_chan);
+}
+
+static inline u16
+ioat_xferlen_to_descs(struct ioatdma_chan *ioat_chan, size_t len)
+{
+	u16 num_descs = len >> ioat_chan->xfercap_log;
+
+	num_descs += !!(len & ((1 << ioat_chan->xfercap_log) - 1));
+	return num_descs;
+}
+
+static inline struct ioat_ring_ent *
+ioat_get_ring_ent(struct ioatdma_chan *ioat_chan, u16 idx)
+{
+	return ioat_chan->ring[idx & (ioat_ring_size(ioat_chan) - 1)];
+}
+
+static inline void
+ioat_set_chainaddr(struct ioatdma_chan *ioat_chan, u64 addr)
+{
+	writel(addr & 0x00000000FFFFFFFF,
+	       ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
+	writel(addr >> 32,
+	       ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
+}
+
+/* IOAT Prep functions */
+struct dma_async_tx_descriptor *
+ioat_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
+			   dma_addr_t dma_src, size_t len, unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_interrupt_lock(struct dma_chan *c, unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
+	       unsigned int src_cnt, size_t len, unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_xor_val(struct dma_chan *chan, dma_addr_t *src,
+		    unsigned int src_cnt, size_t len,
+		    enum sum_check_flags *result, unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
+	      unsigned int src_cnt, const unsigned char *scf, size_t len,
+	      unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
+		  unsigned int src_cnt, const unsigned char *scf, size_t len,
+		  enum sum_check_flags *pqres, unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
+		 unsigned int src_cnt, size_t len, unsigned long flags);
+struct dma_async_tx_descriptor *
+ioat_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
+		     unsigned int src_cnt, size_t len,
+		     enum sum_check_flags *result, unsigned long flags);
+
+/* IOAT Operation functions */
+irqreturn_t ioat_dma_do_interrupt(int irq, void *data);
+irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data);
+struct ioat_ring_ent **
+ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags);
+void ioat_start_null_desc(struct ioatdma_chan *ioat_chan);
+void ioat_free_ring_ent(struct ioat_ring_ent *desc, struct dma_chan *chan);
+int ioat_reset_hw(struct ioatdma_chan *ioat_chan);
+enum dma_status
+ioat_tx_status(struct dma_chan *c, dma_cookie_t cookie,
+		struct dma_tx_state *txstate);
+void ioat_cleanup_event(unsigned long data);
+void ioat_timer_event(unsigned long data);
+int ioat_check_space_lock(struct ioatdma_chan *ioat_chan, int num_descs);
+void ioat_issue_pending(struct dma_chan *chan);
+void ioat_timer_event(unsigned long data);
+
+/* IOAT Init functions */
+bool is_bwd_ioat(struct pci_dev *pdev);
 struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase);
-dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan);
-void ioat_init_channel(struct ioatdma_device *device,
-		       struct ioat_chan_common *chan, int idx);
-enum dma_status ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
-				   struct dma_tx_state *txstate);
-bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
-			   dma_addr_t *phys_complete);
-void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
-void ioat_kobject_del(struct ioatdma_device *device);
-int ioat_dma_setup_interrupts(struct ioatdma_device *device);
-void ioat_stop(struct ioat_chan_common *chan);
-extern const struct sysfs_ops ioat_sysfs_ops;
-extern struct ioat_sysfs_entry ioat_version_attr;
-extern struct ioat_sysfs_entry ioat_cap_attr;
+void ioat_kobject_add(struct ioatdma_device *ioat_dma, struct kobj_type *type);
+void ioat_kobject_del(struct ioatdma_device *ioat_dma);
+int ioat_dma_setup_interrupts(struct ioatdma_device *ioat_dma);
+void ioat_stop(struct ioatdma_chan *ioat_chan);
 #endif /* IOATDMA_H */
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
deleted file mode 100644
index 69c7dfcad023..000000000000
--- a/drivers/dma/ioat/dma_v2.c
+++ /dev/null
@@ -1,916 +0,0 @@
-/*
- * Intel I/OAT DMA Linux driver
- * Copyright(c) 2004 - 2009 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- */
-
-/*
- * This driver supports an Intel I/OAT DMA engine (versions >= 2), which
- * does asynchronous data movement and checksumming operations.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/dmaengine.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/workqueue.h>
-#include <linux/prefetch.h>
-#include <linux/i7300_idle.h>
-#include "dma.h"
-#include "dma_v2.h"
-#include "registers.h"
-#include "hw.h"
-
-#include "../dmaengine.h"
-
-int ioat_ring_alloc_order = 8;
-module_param(ioat_ring_alloc_order, int, 0644);
-MODULE_PARM_DESC(ioat_ring_alloc_order,
-		 "ioat2+: allocate 2^n descriptors per channel"
-		 " (default: 8 max: 16)");
-static int ioat_ring_max_alloc_order = IOAT_MAX_ORDER;
-module_param(ioat_ring_max_alloc_order, int, 0644);
-MODULE_PARM_DESC(ioat_ring_max_alloc_order,
-		 "ioat2+: upper limit for ring size (default: 16)");
-
-void __ioat2_issue_pending(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-
-	ioat->dmacount += ioat2_ring_pending(ioat);
-	ioat->issued = ioat->head;
-	writew(ioat->dmacount, chan->reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
-	dev_dbg(to_dev(chan),
-		"%s: head: %#x tail: %#x issued: %#x count: %#x\n",
-		__func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount);
-}
-
-void ioat2_issue_pending(struct dma_chan *c)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-
-	if (ioat2_ring_pending(ioat)) {
-		spin_lock_bh(&ioat->prep_lock);
-		__ioat2_issue_pending(ioat);
-		spin_unlock_bh(&ioat->prep_lock);
-	}
-}
-
-/**
- * ioat2_update_pending - log pending descriptors
- * @ioat: ioat2+ channel
- *
- * Check if the number of unsubmitted descriptors has exceeded the
- * watermark.  Called with prep_lock held
- */
-static void ioat2_update_pending(struct ioat2_dma_chan *ioat)
-{
-	if (ioat2_ring_pending(ioat) > ioat_pending_level)
-		__ioat2_issue_pending(ioat);
-}
-
-static void __ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_ring_ent *desc;
-	struct ioat_dma_descriptor *hw;
-
-	if (ioat2_ring_space(ioat) < 1) {
-		dev_err(to_dev(&ioat->base),
-			"Unable to start null desc - ring full\n");
-		return;
-	}
-
-	dev_dbg(to_dev(&ioat->base), "%s: head: %#x tail: %#x issued: %#x\n",
-		__func__, ioat->head, ioat->tail, ioat->issued);
-	desc = ioat2_get_ring_ent(ioat, ioat->head);
-
-	hw = desc->hw;
-	hw->ctl = 0;
-	hw->ctl_f.null = 1;
-	hw->ctl_f.int_en = 1;
-	hw->ctl_f.compl_write = 1;
-	/* set size to non-zero value (channel returns error when size is 0) */
-	hw->size = NULL_DESC_BUFFER_SIZE;
-	hw->src_addr = 0;
-	hw->dst_addr = 0;
-	async_tx_ack(&desc->txd);
-	ioat2_set_chainaddr(ioat, desc->txd.phys);
-	dump_desc_dbg(ioat, desc);
-	wmb();
-	ioat->head += 1;
-	__ioat2_issue_pending(ioat);
-}
-
-static void ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
-{
-	spin_lock_bh(&ioat->prep_lock);
-	__ioat2_start_null_desc(ioat);
-	spin_unlock_bh(&ioat->prep_lock);
-}
-
-static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	struct dma_async_tx_descriptor *tx;
-	struct ioat_ring_ent *desc;
-	bool seen_current = false;
-	u16 active;
-	int idx = ioat->tail, i;
-
-	dev_dbg(to_dev(chan), "%s: head: %#x tail: %#x issued: %#x\n",
-		__func__, ioat->head, ioat->tail, ioat->issued);
-
-	active = ioat2_ring_active(ioat);
-	for (i = 0; i < active && !seen_current; i++) {
-		smp_read_barrier_depends();
-		prefetch(ioat2_get_ring_ent(ioat, idx + i + 1));
-		desc = ioat2_get_ring_ent(ioat, idx + i);
-		tx = &desc->txd;
-		dump_desc_dbg(ioat, desc);
-		if (tx->cookie) {
-			dma_descriptor_unmap(tx);
-			dma_cookie_complete(tx);
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
-		}
-
-		if (tx->phys == phys_complete)
-			seen_current = true;
-	}
-	smp_mb(); /* finish all descriptor reads before incrementing tail */
-	ioat->tail = idx + i;
-	BUG_ON(active && !seen_current); /* no active descs have written a completion? */
-
-	chan->last_completion = phys_complete;
-	if (active - i == 0) {
-		dev_dbg(to_dev(chan), "%s: cancel completion timeout\n",
-			__func__);
-		clear_bit(IOAT_COMPLETION_PENDING, &chan->state);
-		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-	}
-}
-
-/**
- * ioat2_cleanup - clean finished descriptors (advance tail pointer)
- * @chan: ioat channel to be cleaned up
- */
-static void ioat2_cleanup(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	dma_addr_t phys_complete;
-
-	spin_lock_bh(&chan->cleanup_lock);
-	if (ioat_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-	spin_unlock_bh(&chan->cleanup_lock);
-}
-
-void ioat2_cleanup_event(unsigned long data)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
-	struct ioat_chan_common *chan = &ioat->base;
-
-	ioat2_cleanup(ioat);
-	if (!test_bit(IOAT_RUN, &chan->state))
-		return;
-	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
-}
-
-void __ioat2_restart_chan(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-
-	/* set the tail to be re-issued */
-	ioat->issued = ioat->tail;
-	ioat->dmacount = 0;
-	set_bit(IOAT_COMPLETION_PENDING, &chan->state);
-	mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-
-	dev_dbg(to_dev(chan),
-		"%s: head: %#x tail: %#x issued: %#x count: %#x\n",
-		__func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount);
-
-	if (ioat2_ring_pending(ioat)) {
-		struct ioat_ring_ent *desc;
-
-		desc = ioat2_get_ring_ent(ioat, ioat->tail);
-		ioat2_set_chainaddr(ioat, desc->txd.phys);
-		__ioat2_issue_pending(ioat);
-	} else
-		__ioat2_start_null_desc(ioat);
-}
-
-int ioat2_quiesce(struct ioat_chan_common *chan, unsigned long tmo)
-{
-	unsigned long end = jiffies + tmo;
-	int err = 0;
-	u32 status;
-
-	status = ioat_chansts(chan);
-	if (is_ioat_active(status) || is_ioat_idle(status))
-		ioat_suspend(chan);
-	while (is_ioat_active(status) || is_ioat_idle(status)) {
-		if (tmo && time_after(jiffies, end)) {
-			err = -ETIMEDOUT;
-			break;
-		}
-		status = ioat_chansts(chan);
-		cpu_relax();
-	}
-
-	return err;
-}
-
-int ioat2_reset_sync(struct ioat_chan_common *chan, unsigned long tmo)
-{
-	unsigned long end = jiffies + tmo;
-	int err = 0;
-
-	ioat_reset(chan);
-	while (ioat_reset_pending(chan)) {
-		if (end && time_after(jiffies, end)) {
-			err = -ETIMEDOUT;
-			break;
-		}
-		cpu_relax();
-	}
-
-	return err;
-}
-
-static void ioat2_restart_channel(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	dma_addr_t phys_complete;
-
-	ioat2_quiesce(chan, 0);
-	if (ioat_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-
-	__ioat2_restart_chan(ioat);
-}
-
-static void check_active(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-
-	if (ioat2_ring_active(ioat)) {
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-		return;
-	}
-
-	if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &chan->state))
-		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-	else if (ioat->alloc_order > ioat_get_alloc_order()) {
-		/* if the ring is idle, empty, and oversized try to step
-		 * down the size
-		 */
-		reshape_ring(ioat, ioat->alloc_order - 1);
-
-		/* keep shrinking until we get back to our minimum
-		 * default size
-		 */
-		if (ioat->alloc_order > ioat_get_alloc_order())
-			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-	}
-
-}
-
-void ioat2_timer_event(unsigned long data)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
-	struct ioat_chan_common *chan = &ioat->base;
-	dma_addr_t phys_complete;
-	u64 status;
-
-	status = ioat_chansts(chan);
-
-	/* when halted due to errors check for channel
-	 * programming errors before advancing the completion state
-	 */
-	if (is_ioat_halted(status)) {
-		u32 chanerr;
-
-		chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-		dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
-			__func__, chanerr);
-		if (test_bit(IOAT_RUN, &chan->state))
-			BUG_ON(is_ioat_bug(chanerr));
-		else /* we never got off the ground */
-			return;
-	}
-
-	/* if we haven't made progress and we have already
-	 * acknowledged a pending completion once, then be more
-	 * forceful with a restart
-	 */
-	spin_lock_bh(&chan->cleanup_lock);
-	if (ioat_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-	else if (test_bit(IOAT_COMPLETION_ACK, &chan->state)) {
-		spin_lock_bh(&ioat->prep_lock);
-		ioat2_restart_channel(ioat);
-		spin_unlock_bh(&ioat->prep_lock);
-		spin_unlock_bh(&chan->cleanup_lock);
-		return;
-	} else {
-		set_bit(IOAT_COMPLETION_ACK, &chan->state);
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-	}
-
-
-	if (ioat2_ring_active(ioat))
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-	else {
-		spin_lock_bh(&ioat->prep_lock);
-		check_active(ioat);
-		spin_unlock_bh(&ioat->prep_lock);
-	}
-	spin_unlock_bh(&chan->cleanup_lock);
-}
-
-static int ioat2_reset_hw(struct ioat_chan_common *chan)
-{
-	/* throw away whatever the channel was doing and get it initialized */
-	u32 chanerr;
-
-	ioat2_quiesce(chan, msecs_to_jiffies(100));
-
-	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-	writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
-
-	return ioat2_reset_sync(chan, msecs_to_jiffies(200));
-}
-
-/**
- * ioat2_enumerate_channels - find and initialize the device's channels
- * @device: the device to be enumerated
- */
-int ioat2_enumerate_channels(struct ioatdma_device *device)
-{
-	struct ioat2_dma_chan *ioat;
-	struct device *dev = &device->pdev->dev;
-	struct dma_device *dma = &device->common;
-	u8 xfercap_log;
-	int i;
-
-	INIT_LIST_HEAD(&dma->channels);
-	dma->chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET);
-	dma->chancnt &= 0x1f; /* bits [4:0] valid */
-	if (dma->chancnt > ARRAY_SIZE(device->idx)) {
-		dev_warn(dev, "(%d) exceeds max supported channels (%zu)\n",
-			 dma->chancnt, ARRAY_SIZE(device->idx));
-		dma->chancnt = ARRAY_SIZE(device->idx);
-	}
-	xfercap_log = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
-	xfercap_log &= 0x1f; /* bits [4:0] valid */
-	if (xfercap_log == 0)
-		return 0;
-	dev_dbg(dev, "%s: xfercap = %d\n", __func__, 1 << xfercap_log);
-
-	/* FIXME which i/oat version is i7300? */
-#ifdef CONFIG_I7300_IDLE_IOAT_CHANNEL
-	if (i7300_idle_platform_probe(NULL, NULL, 1) == 0)
-		dma->chancnt--;
-#endif
-	for (i = 0; i < dma->chancnt; i++) {
-		ioat = devm_kzalloc(dev, sizeof(*ioat), GFP_KERNEL);
-		if (!ioat)
-			break;
-
-		ioat_init_channel(device, &ioat->base, i);
-		ioat->xfercap_log = xfercap_log;
-		spin_lock_init(&ioat->prep_lock);
-		if (device->reset_hw(&ioat->base)) {
-			i = 0;
-			break;
-		}
-	}
-	dma->chancnt = i;
-	return i;
-}
-
-static dma_cookie_t ioat2_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
-{
-	struct dma_chan *c = tx->chan;
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	dma_cookie_t cookie;
-
-	cookie = dma_cookie_assign(tx);
-	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
-
-	if (!test_and_set_bit(IOAT_CHAN_ACTIVE, &chan->state))
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-
-	/* make descriptor updates visible before advancing ioat->head,
-	 * this is purposefully not smp_wmb() since we are also
-	 * publishing the descriptor updates to a dma device
-	 */
-	wmb();
-
-	ioat->head += ioat->produce;
-
-	ioat2_update_pending(ioat);
-	spin_unlock_bh(&ioat->prep_lock);
-
-	return cookie;
-}
-
-static struct ioat_ring_ent *ioat2_alloc_ring_ent(struct dma_chan *chan, gfp_t flags)
-{
-	struct ioat_dma_descriptor *hw;
-	struct ioat_ring_ent *desc;
-	struct ioatdma_device *dma;
-	dma_addr_t phys;
-
-	dma = to_ioatdma_device(chan->device);
-	hw = pci_pool_alloc(dma->dma_pool, flags, &phys);
-	if (!hw)
-		return NULL;
-	memset(hw, 0, sizeof(*hw));
-
-	desc = kmem_cache_zalloc(ioat2_cache, flags);
-	if (!desc) {
-		pci_pool_free(dma->dma_pool, hw, phys);
-		return NULL;
-	}
-
-	dma_async_tx_descriptor_init(&desc->txd, chan);
-	desc->txd.tx_submit = ioat2_tx_submit_unlock;
-	desc->hw = hw;
-	desc->txd.phys = phys;
-	return desc;
-}
-
-static void ioat2_free_ring_ent(struct ioat_ring_ent *desc, struct dma_chan *chan)
-{
-	struct ioatdma_device *dma;
-
-	dma = to_ioatdma_device(chan->device);
-	pci_pool_free(dma->dma_pool, desc->hw, desc->txd.phys);
-	kmem_cache_free(ioat2_cache, desc);
-}
-
-static struct ioat_ring_ent **ioat2_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
-{
-	struct ioat_ring_ent **ring;
-	int descs = 1 << order;
-	int i;
-
-	if (order > ioat_get_max_alloc_order())
-		return NULL;
-
-	/* allocate the array to hold the software ring */
-	ring = kcalloc(descs, sizeof(*ring), flags);
-	if (!ring)
-		return NULL;
-	for (i = 0; i < descs; i++) {
-		ring[i] = ioat2_alloc_ring_ent(c, flags);
-		if (!ring[i]) {
-			while (i--)
-				ioat2_free_ring_ent(ring[i], c);
-			kfree(ring);
-			return NULL;
-		}
-		set_desc_id(ring[i], i);
-	}
-
-	/* link descs */
-	for (i = 0; i < descs-1; i++) {
-		struct ioat_ring_ent *next = ring[i+1];
-		struct ioat_dma_descriptor *hw = ring[i]->hw;
-
-		hw->next = next->txd.phys;
-	}
-	ring[i]->hw->next = ring[0]->txd.phys;
-
-	return ring;
-}
-
-void ioat2_free_chan_resources(struct dma_chan *c);
-
-/* ioat2_alloc_chan_resources - allocate/initialize ioat2 descriptor ring
- * @chan: channel to be initialized
- */
-int ioat2_alloc_chan_resources(struct dma_chan *c)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioat_ring_ent **ring;
-	u64 status;
-	int order;
-	int i = 0;
-
-	/* have we already been set up? */
-	if (ioat->ring)
-		return 1 << ioat->alloc_order;
-
-	/* Setup register to interrupt and write completion status on error */
-	writew(IOAT_CHANCTRL_RUN, chan->reg_base + IOAT_CHANCTRL_OFFSET);
-
-	/* allocate a completion writeback area */
-	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
-	chan->completion = pci_pool_alloc(chan->device->completion_pool,
-					  GFP_KERNEL, &chan->completion_dma);
-	if (!chan->completion)
-		return -ENOMEM;
-
-	memset(chan->completion, 0, sizeof(*chan->completion));
-	writel(((u64) chan->completion_dma) & 0x00000000FFFFFFFF,
-	       chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
-	writel(((u64) chan->completion_dma) >> 32,
-	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
-
-	order = ioat_get_alloc_order();
-	ring = ioat2_alloc_ring(c, order, GFP_KERNEL);
-	if (!ring)
-		return -ENOMEM;
-
-	spin_lock_bh(&chan->cleanup_lock);
-	spin_lock_bh(&ioat->prep_lock);
-	ioat->ring = ring;
-	ioat->head = 0;
-	ioat->issued = 0;
-	ioat->tail = 0;
-	ioat->alloc_order = order;
-	set_bit(IOAT_RUN, &chan->state);
-	spin_unlock_bh(&ioat->prep_lock);
-	spin_unlock_bh(&chan->cleanup_lock);
-
-	ioat2_start_null_desc(ioat);
-
-	/* check that we got off the ground */
-	do {
-		udelay(1);
-		status = ioat_chansts(chan);
-	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
-
-	if (is_ioat_active(status) || is_ioat_idle(status)) {
-		return 1 << ioat->alloc_order;
-	} else {
-		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-
-		dev_WARN(to_dev(chan),
-			"failed to start channel chanerr: %#x\n", chanerr);
-		ioat2_free_chan_resources(c);
-		return -EFAULT;
-	}
-}
-
-bool reshape_ring(struct ioat2_dma_chan *ioat, int order)
-{
-	/* reshape differs from normal ring allocation in that we want
-	 * to allocate a new software ring while only
-	 * extending/truncating the hardware ring
-	 */
-	struct ioat_chan_common *chan = &ioat->base;
-	struct dma_chan *c = &chan->common;
-	const u32 curr_size = ioat2_ring_size(ioat);
-	const u16 active = ioat2_ring_active(ioat);
-	const u32 new_size = 1 << order;
-	struct ioat_ring_ent **ring;
-	u16 i;
-
-	if (order > ioat_get_max_alloc_order())
-		return false;
-
-	/* double check that we have at least 1 free descriptor */
-	if (active == curr_size)
-		return false;
-
-	/* when shrinking, verify that we can hold the current active
-	 * set in the new ring
-	 */
-	if (active >= new_size)
-		return false;
-
-	/* allocate the array to hold the software ring */
-	ring = kcalloc(new_size, sizeof(*ring), GFP_NOWAIT);
-	if (!ring)
-		return false;
-
-	/* allocate/trim descriptors as needed */
-	if (new_size > curr_size) {
-		/* copy current descriptors to the new ring */
-		for (i = 0; i < curr_size; i++) {
-			u16 curr_idx = (ioat->tail+i) & (curr_size-1);
-			u16 new_idx = (ioat->tail+i) & (new_size-1);
-
-			ring[new_idx] = ioat->ring[curr_idx];
-			set_desc_id(ring[new_idx], new_idx);
-		}
-
-		/* add new descriptors to the ring */
-		for (i = curr_size; i < new_size; i++) {
-			u16 new_idx = (ioat->tail+i) & (new_size-1);
-
-			ring[new_idx] = ioat2_alloc_ring_ent(c, GFP_NOWAIT);
-			if (!ring[new_idx]) {
-				while (i--) {
-					u16 new_idx = (ioat->tail+i) & (new_size-1);
-
-					ioat2_free_ring_ent(ring[new_idx], c);
-				}
-				kfree(ring);
-				return false;
-			}
-			set_desc_id(ring[new_idx], new_idx);
-		}
-
-		/* hw link new descriptors */
-		for (i = curr_size-1; i < new_size; i++) {
-			u16 new_idx = (ioat->tail+i) & (new_size-1);
-			struct ioat_ring_ent *next = ring[(new_idx+1) & (new_size-1)];
-			struct ioat_dma_descriptor *hw = ring[new_idx]->hw;
-
-			hw->next = next->txd.phys;
-		}
-	} else {
-		struct ioat_dma_descriptor *hw;
-		struct ioat_ring_ent *next;
-
-		/* copy current descriptors to the new ring, dropping the
-		 * removed descriptors
-		 */
-		for (i = 0; i < new_size; i++) {
-			u16 curr_idx = (ioat->tail+i) & (curr_size-1);
-			u16 new_idx = (ioat->tail+i) & (new_size-1);
-
-			ring[new_idx] = ioat->ring[curr_idx];
-			set_desc_id(ring[new_idx], new_idx);
-		}
-
-		/* free deleted descriptors */
-		for (i = new_size; i < curr_size; i++) {
-			struct ioat_ring_ent *ent;
-
-			ent = ioat2_get_ring_ent(ioat, ioat->tail+i);
-			ioat2_free_ring_ent(ent, c);
-		}
-
-		/* fix up hardware ring */
-		hw = ring[(ioat->tail+new_size-1) & (new_size-1)]->hw;
-		next = ring[(ioat->tail+new_size) & (new_size-1)];
-		hw->next = next->txd.phys;
-	}
-
-	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
-		__func__, new_size);
-
-	kfree(ioat->ring);
-	ioat->ring = ring;
-	ioat->alloc_order = order;
-
-	return true;
-}
-
-/**
- * ioat2_check_space_lock - verify space and grab ring producer lock
- * @ioat: ioat2,3 channel (ring) to operate on
- * @num_descs: allocation length
- */
-int ioat2_check_space_lock(struct ioat2_dma_chan *ioat, int num_descs)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	bool retry;
-
- retry:
-	spin_lock_bh(&ioat->prep_lock);
-	/* never allow the last descriptor to be consumed, we need at
-	 * least one free at all times to allow for on-the-fly ring
-	 * resizing.
-	 */
-	if (likely(ioat2_ring_space(ioat) > num_descs)) {
-		dev_dbg(to_dev(chan), "%s: num_descs: %d (%x:%x:%x)\n",
-			__func__, num_descs, ioat->head, ioat->tail, ioat->issued);
-		ioat->produce = num_descs;
-		return 0;  /* with ioat->prep_lock held */
-	}
-	retry = test_and_set_bit(IOAT_RESHAPE_PENDING, &chan->state);
-	spin_unlock_bh(&ioat->prep_lock);
-
-	/* is another cpu already trying to expand the ring? */
-	if (retry)
-		goto retry;
-
-	spin_lock_bh(&chan->cleanup_lock);
-	spin_lock_bh(&ioat->prep_lock);
-	retry = reshape_ring(ioat, ioat->alloc_order + 1);
-	clear_bit(IOAT_RESHAPE_PENDING, &chan->state);
-	spin_unlock_bh(&ioat->prep_lock);
-	spin_unlock_bh(&chan->cleanup_lock);
-
-	/* if we were able to expand the ring retry the allocation */
-	if (retry)
-		goto retry;
-
-	if (printk_ratelimit())
-		dev_dbg(to_dev(chan), "%s: ring full! num_descs: %d (%x:%x:%x)\n",
-			__func__, num_descs, ioat->head, ioat->tail, ioat->issued);
-
-	/* progress reclaim in the allocation failure case we may be
-	 * called under bh_disabled so we need to trigger the timer
-	 * event directly
-	 */
-	if (time_is_before_jiffies(chan->timer.expires)
-	    && timer_pending(&chan->timer)) {
-		struct ioatdma_device *device = chan->device;
-
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-		device->timer_fn((unsigned long) &chan->common);
-	}
-
-	return -ENOMEM;
-}
-
-struct dma_async_tx_descriptor *
-ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
-			   dma_addr_t dma_src, size_t len, unsigned long flags)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_dma_descriptor *hw;
-	struct ioat_ring_ent *desc;
-	dma_addr_t dst = dma_dest;
-	dma_addr_t src = dma_src;
-	size_t total_len = len;
-	int num_descs, idx, i;
-
-	num_descs = ioat2_xferlen_to_descs(ioat, len);
-	if (likely(num_descs) && ioat2_check_space_lock(ioat, num_descs) == 0)
-		idx = ioat->head;
-	else
-		return NULL;
-	i = 0;
-	do {
-		size_t copy = min_t(size_t, len, 1 << ioat->xfercap_log);
-
-		desc = ioat2_get_ring_ent(ioat, idx + i);
-		hw = desc->hw;
-
-		hw->size = copy;
-		hw->ctl = 0;
-		hw->src_addr = src;
-		hw->dst_addr = dst;
-
-		len -= copy;
-		dst += copy;
-		src += copy;
-		dump_desc_dbg(ioat, desc);
-	} while (++i < num_descs);
-
-	desc->txd.flags = flags;
-	desc->len = total_len;
-	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
-	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
-	hw->ctl_f.compl_write = 1;
-	dump_desc_dbg(ioat, desc);
-	/* we leave the channel locked to ensure in order submission */
-
-	return &desc->txd;
-}
-
-/**
- * ioat2_free_chan_resources - release all the descriptors
- * @chan: the channel to be cleaned
- */
-void ioat2_free_chan_resources(struct dma_chan *c)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioatdma_device *device = chan->device;
-	struct ioat_ring_ent *desc;
-	const u16 total_descs = 1 << ioat->alloc_order;
-	int descs;
-	int i;
-
-	/* Before freeing channel resources first check
-	 * if they have been previously allocated for this channel.
-	 */
-	if (!ioat->ring)
-		return;
-
-	ioat_stop(chan);
-	device->reset_hw(chan);
-
-	spin_lock_bh(&chan->cleanup_lock);
-	spin_lock_bh(&ioat->prep_lock);
-	descs = ioat2_ring_space(ioat);
-	dev_dbg(to_dev(chan), "freeing %d idle descriptors\n", descs);
-	for (i = 0; i < descs; i++) {
-		desc = ioat2_get_ring_ent(ioat, ioat->head + i);
-		ioat2_free_ring_ent(desc, c);
-	}
-
-	if (descs < total_descs)
-		dev_err(to_dev(chan), "Freeing %d in use descriptors!\n",
-			total_descs - descs);
-
-	for (i = 0; i < total_descs - descs; i++) {
-		desc = ioat2_get_ring_ent(ioat, ioat->tail + i);
-		dump_desc_dbg(ioat, desc);
-		ioat2_free_ring_ent(desc, c);
-	}
-
-	kfree(ioat->ring);
-	ioat->ring = NULL;
-	ioat->alloc_order = 0;
-	pci_pool_free(device->completion_pool, chan->completion,
-		      chan->completion_dma);
-	spin_unlock_bh(&ioat->prep_lock);
-	spin_unlock_bh(&chan->cleanup_lock);
-
-	chan->last_completion = 0;
-	chan->completion_dma = 0;
-	ioat->dmacount = 0;
-}
-
-static ssize_t ring_size_show(struct dma_chan *c, char *page)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-
-	return sprintf(page, "%d\n", (1 << ioat->alloc_order) & ~1);
-}
-static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size);
-
-static ssize_t ring_active_show(struct dma_chan *c, char *page)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-
-	/* ...taken outside the lock, no need to be precise */
-	return sprintf(page, "%d\n", ioat2_ring_active(ioat));
-}
-static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active);
-
-static struct attribute *ioat2_attrs[] = {
-	&ring_size_attr.attr,
-	&ring_active_attr.attr,
-	&ioat_cap_attr.attr,
-	&ioat_version_attr.attr,
-	NULL,
-};
-
-struct kobj_type ioat2_ktype = {
-	.sysfs_ops = &ioat_sysfs_ops,
-	.default_attrs = ioat2_attrs,
-};
-
-int ioat2_dma_probe(struct ioatdma_device *device, int dca)
-{
-	struct pci_dev *pdev = device->pdev;
-	struct dma_device *dma;
-	struct dma_chan *c;
-	struct ioat_chan_common *chan;
-	int err;
-
-	device->enumerate_channels = ioat2_enumerate_channels;
-	device->reset_hw = ioat2_reset_hw;
-	device->cleanup_fn = ioat2_cleanup_event;
-	device->timer_fn = ioat2_timer_event;
-	device->self_test = ioat_dma_self_test;
-	dma = &device->common;
-	dma->device_prep_dma_memcpy = ioat2_dma_prep_memcpy_lock;
-	dma->device_issue_pending = ioat2_issue_pending;
-	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
-	dma->device_free_chan_resources = ioat2_free_chan_resources;
-	dma->device_tx_status = ioat_dma_tx_status;
-
-	err = ioat_probe(device);
-	if (err)
-		return err;
-
-	list_for_each_entry(c, &dma->channels, device_node) {
-		chan = to_chan_common(c);
-		writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE | IOAT_DMA_DCA_ANY_CPU,
-		       chan->reg_base + IOAT_DCACTRL_OFFSET);
-	}
-
-	err = ioat_register(device);
-	if (err)
-		return err;
-
-	ioat_kobject_add(device, &ioat2_ktype);
-
-	if (dca)
-		device->dca = ioat2_dca_init(pdev, device->reg_base);
-
-	return err;
-}
diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h
deleted file mode 100644
index bf24ebe874b0..000000000000
--- a/drivers/dma/ioat/dma_v2.h
+++ /dev/null
@@ -1,175 +0,0 @@
-/*
- * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- */
-#ifndef IOATDMA_V2_H
-#define IOATDMA_V2_H
-
-#include <linux/dmaengine.h>
-#include <linux/circ_buf.h>
-#include "dma.h"
-#include "hw.h"
-
-
-extern int ioat_pending_level;
-extern int ioat_ring_alloc_order;
-
-/*
- * workaround for IOAT ver.3.0 null descriptor issue
- * (channel returns error when size is 0)
- */
-#define NULL_DESC_BUFFER_SIZE 1
-
-#define IOAT_MAX_ORDER 16
-#define ioat_get_alloc_order() \
-	(min(ioat_ring_alloc_order, IOAT_MAX_ORDER))
-#define ioat_get_max_alloc_order() \
-	(min(ioat_ring_max_alloc_order, IOAT_MAX_ORDER))
-
-/* struct ioat2_dma_chan - ioat v2 / v3 channel attributes
- * @base: common ioat channel parameters
- * @xfercap_log; log2 of channel max transfer length (for fast division)
- * @head: allocated index
- * @issued: hardware notification point
- * @tail: cleanup index
- * @dmacount: identical to 'head' except for occasionally resetting to zero
- * @alloc_order: log2 of the number of allocated descriptors
- * @produce: number of descriptors to produce at submit time
- * @ring: software ring buffer implementation of hardware ring
- * @prep_lock: serializes descriptor preparation (producers)
- */
-struct ioat2_dma_chan {
-	struct ioat_chan_common base;
-	size_t xfercap_log;
-	u16 head;
-	u16 issued;
-	u16 tail;
-	u16 dmacount;
-	u16 alloc_order;
-	u16 produce;
-	struct ioat_ring_ent **ring;
-	spinlock_t prep_lock;
-};
-
-static inline struct ioat2_dma_chan *to_ioat2_chan(struct dma_chan *c)
-{
-	struct ioat_chan_common *chan = to_chan_common(c);
-
-	return container_of(chan, struct ioat2_dma_chan, base);
-}
-
-static inline u32 ioat2_ring_size(struct ioat2_dma_chan *ioat)
-{
-	return 1 << ioat->alloc_order;
-}
-
-/* count of descriptors in flight with the engine */
-static inline u16 ioat2_ring_active(struct ioat2_dma_chan *ioat)
-{
-	return CIRC_CNT(ioat->head, ioat->tail, ioat2_ring_size(ioat));
-}
-
-/* count of descriptors pending submission to hardware */
-static inline u16 ioat2_ring_pending(struct ioat2_dma_chan *ioat)
-{
-	return CIRC_CNT(ioat->head, ioat->issued, ioat2_ring_size(ioat));
-}
-
-static inline u32 ioat2_ring_space(struct ioat2_dma_chan *ioat)
-{
-	return ioat2_ring_size(ioat) - ioat2_ring_active(ioat);
-}
-
-static inline u16 ioat2_xferlen_to_descs(struct ioat2_dma_chan *ioat, size_t len)
-{
-	u16 num_descs = len >> ioat->xfercap_log;
-
-	num_descs += !!(len & ((1 << ioat->xfercap_log) - 1));
-	return num_descs;
-}
-
-/**
- * struct ioat_ring_ent - wrapper around hardware descriptor
- * @hw: hardware DMA descriptor (for memcpy)
- * @fill: hardware fill descriptor
- * @xor: hardware xor descriptor
- * @xor_ex: hardware xor extension descriptor
- * @pq: hardware pq descriptor
- * @pq_ex: hardware pq extension descriptor
- * @pqu: hardware pq update descriptor
- * @raw: hardware raw (un-typed) descriptor
- * @txd: the generic software descriptor for all engines
- * @len: total transaction length for unmap
- * @result: asynchronous result of validate operations
- * @id: identifier for debug
- */
-
-struct ioat_ring_ent {
-	union {
-		struct ioat_dma_descriptor *hw;
-		struct ioat_xor_descriptor *xor;
-		struct ioat_xor_ext_descriptor *xor_ex;
-		struct ioat_pq_descriptor *pq;
-		struct ioat_pq_ext_descriptor *pq_ex;
-		struct ioat_pq_update_descriptor *pqu;
-		struct ioat_raw_descriptor *raw;
-	};
-	size_t len;
-	struct dma_async_tx_descriptor txd;
-	enum sum_check_flags *result;
-	#ifdef DEBUG
-	int id;
-	#endif
-	struct ioat_sed_ent *sed;
-};
-
-static inline struct ioat_ring_ent *
-ioat2_get_ring_ent(struct ioat2_dma_chan *ioat, u16 idx)
-{
-	return ioat->ring[idx & (ioat2_ring_size(ioat) - 1)];
-}
-
-static inline void ioat2_set_chainaddr(struct ioat2_dma_chan *ioat, u64 addr)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-
-	writel(addr & 0x00000000FFFFFFFF,
-	       chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
-	writel(addr >> 32,
-	       chan->reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
-}
-
-int ioat2_dma_probe(struct ioatdma_device *dev, int dca);
-int ioat3_dma_probe(struct ioatdma_device *dev, int dca);
-struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase);
-struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase);
-int ioat2_check_space_lock(struct ioat2_dma_chan *ioat, int num_descs);
-int ioat2_enumerate_channels(struct ioatdma_device *device);
-struct dma_async_tx_descriptor *
-ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
-			   dma_addr_t dma_src, size_t len, unsigned long flags);
-void ioat2_issue_pending(struct dma_chan *chan);
-int ioat2_alloc_chan_resources(struct dma_chan *c);
-void ioat2_free_chan_resources(struct dma_chan *c);
-void __ioat2_restart_chan(struct ioat2_dma_chan *ioat);
-bool reshape_ring(struct ioat2_dma_chan *ioat, int order);
-void __ioat2_issue_pending(struct ioat2_dma_chan *ioat);
-void ioat2_cleanup_event(unsigned long data);
-void ioat2_timer_event(unsigned long data);
-int ioat2_quiesce(struct ioat_chan_common *chan, unsigned long tmo);
-int ioat2_reset_sync(struct ioat_chan_common *chan, unsigned long tmo);
-extern struct kobj_type ioat2_ktype;
-extern struct kmem_cache *ioat2_cache;
-#endif /* IOATDMA_V2_H */
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
deleted file mode 100644
index 64790a45ef5d..000000000000
--- a/drivers/dma/ioat/dma_v3.c
+++ /dev/null
@@ -1,1717 +0,0 @@
-/*
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * BSD LICENSE
- *
- * Copyright(c) 2004-2009 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-/*
- * Support routines for v3+ hardware
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/gfp.h>
-#include <linux/dmaengine.h>
-#include <linux/dma-mapping.h>
-#include <linux/prefetch.h>
-#include "../dmaengine.h"
-#include "registers.h"
-#include "hw.h"
-#include "dma.h"
-#include "dma_v2.h"
-
-extern struct kmem_cache *ioat3_sed_cache;
-
-/* ioat hardware assumes at least two sources for raid operations */
-#define src_cnt_to_sw(x) ((x) + 2)
-#define src_cnt_to_hw(x) ((x) - 2)
-#define ndest_to_sw(x) ((x) + 1)
-#define ndest_to_hw(x) ((x) - 1)
-#define src16_cnt_to_sw(x) ((x) + 9)
-#define src16_cnt_to_hw(x) ((x) - 9)
-
-/* provide a lookup table for setting the source address in the base or
- * extended descriptor of an xor or pq descriptor
- */
-static const u8 xor_idx_to_desc = 0xe0;
-static const u8 xor_idx_to_field[] = { 1, 4, 5, 6, 7, 0, 1, 2 };
-static const u8 pq_idx_to_desc = 0xf8;
-static const u8 pq16_idx_to_desc[] = { 0, 0, 1, 1, 1, 1, 1, 1, 1,
-				       2, 2, 2, 2, 2, 2, 2 };
-static const u8 pq_idx_to_field[] = { 1, 4, 5, 0, 1, 2, 4, 5 };
-static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
-					0, 1, 2, 3, 4, 5, 6 };
-
-static void ioat3_eh(struct ioat2_dma_chan *ioat);
-
-static void xor_set_src(struct ioat_raw_descriptor *descs[2],
-			dma_addr_t addr, u32 offset, int idx)
-{
-	struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];
-
-	raw->field[xor_idx_to_field[idx]] = addr + offset;
-}
-
-static dma_addr_t pq_get_src(struct ioat_raw_descriptor *descs[2], int idx)
-{
-	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];
-
-	return raw->field[pq_idx_to_field[idx]];
-}
-
-static dma_addr_t pq16_get_src(struct ioat_raw_descriptor *desc[3], int idx)
-{
-	struct ioat_raw_descriptor *raw = desc[pq16_idx_to_desc[idx]];
-
-	return raw->field[pq16_idx_to_field[idx]];
-}
-
-static void pq_set_src(struct ioat_raw_descriptor *descs[2],
-		       dma_addr_t addr, u32 offset, u8 coef, int idx)
-{
-	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *) descs[0];
-	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];
-
-	raw->field[pq_idx_to_field[idx]] = addr + offset;
-	pq->coef[idx] = coef;
-}
-
-static bool is_jf_ioat(struct pci_dev *pdev)
-{
-	switch (pdev->device) {
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF0:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF1:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF2:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF3:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF4:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF5:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF6:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF7:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF8:
-	case PCI_DEVICE_ID_INTEL_IOAT_JSF9:
-		return true;
-	default:
-		return false;
-	}
-}
-
-static bool is_snb_ioat(struct pci_dev *pdev)
-{
-	switch (pdev->device) {
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB0:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB1:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB2:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB3:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB4:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB5:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB6:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB7:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB8:
-	case PCI_DEVICE_ID_INTEL_IOAT_SNB9:
-		return true;
-	default:
-		return false;
-	}
-}
-
-static bool is_ivb_ioat(struct pci_dev *pdev)
-{
-	switch (pdev->device) {
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB0:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB1:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB2:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB3:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB4:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB5:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB6:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB7:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB8:
-	case PCI_DEVICE_ID_INTEL_IOAT_IVB9:
-		return true;
-	default:
-		return false;
-	}
-
-}
-
-static bool is_hsw_ioat(struct pci_dev *pdev)
-{
-	switch (pdev->device) {
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW0:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW1:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW2:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW3:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW4:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW5:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW6:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW7:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW8:
-	case PCI_DEVICE_ID_INTEL_IOAT_HSW9:
-		return true;
-	default:
-		return false;
-	}
-
-}
-
-static bool is_xeon_cb32(struct pci_dev *pdev)
-{
-	return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) ||
-		is_hsw_ioat(pdev);
-}
-
-static bool is_bwd_ioat(struct pci_dev *pdev)
-{
-	switch (pdev->device) {
-	case PCI_DEVICE_ID_INTEL_IOAT_BWD0:
-	case PCI_DEVICE_ID_INTEL_IOAT_BWD1:
-	case PCI_DEVICE_ID_INTEL_IOAT_BWD2:
-	case PCI_DEVICE_ID_INTEL_IOAT_BWD3:
-	/* even though not Atom, BDX-DE has same DMA silicon */
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE0:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE1:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE2:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE3:
-		return true;
-	default:
-		return false;
-	}
-}
-
-static bool is_bwd_noraid(struct pci_dev *pdev)
-{
-	switch (pdev->device) {
-	case PCI_DEVICE_ID_INTEL_IOAT_BWD2:
-	case PCI_DEVICE_ID_INTEL_IOAT_BWD3:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE0:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE1:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE2:
-	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE3:
-		return true;
-	default:
-		return false;
-	}
-
-}
-
-static void pq16_set_src(struct ioat_raw_descriptor *desc[3],
-			dma_addr_t addr, u32 offset, u8 coef, unsigned idx)
-{
-	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *)desc[0];
-	struct ioat_pq16a_descriptor *pq16 =
-		(struct ioat_pq16a_descriptor *)desc[1];
-	struct ioat_raw_descriptor *raw = desc[pq16_idx_to_desc[idx]];
-
-	raw->field[pq16_idx_to_field[idx]] = addr + offset;
-
-	if (idx < 8)
-		pq->coef[idx] = coef;
-	else
-		pq16->coef[idx - 8] = coef;
-}
-
-static struct ioat_sed_ent *
-ioat3_alloc_sed(struct ioatdma_device *device, unsigned int hw_pool)
-{
-	struct ioat_sed_ent *sed;
-	gfp_t flags = __GFP_ZERO | GFP_ATOMIC;
-
-	sed = kmem_cache_alloc(ioat3_sed_cache, flags);
-	if (!sed)
-		return NULL;
-
-	sed->hw_pool = hw_pool;
-	sed->hw = dma_pool_alloc(device->sed_hw_pool[hw_pool],
-				 flags, &sed->dma);
-	if (!sed->hw) {
-		kmem_cache_free(ioat3_sed_cache, sed);
-		return NULL;
-	}
-
-	return sed;
-}
-
-static void ioat3_free_sed(struct ioatdma_device *device, struct ioat_sed_ent *sed)
-{
-	if (!sed)
-		return;
-
-	dma_pool_free(device->sed_hw_pool[sed->hw_pool], sed->hw, sed->dma);
-	kmem_cache_free(ioat3_sed_cache, sed);
-}
-
-static bool desc_has_ext(struct ioat_ring_ent *desc)
-{
-	struct ioat_dma_descriptor *hw = desc->hw;
-
-	if (hw->ctl_f.op == IOAT_OP_XOR ||
-	    hw->ctl_f.op == IOAT_OP_XOR_VAL) {
-		struct ioat_xor_descriptor *xor = desc->xor;
-
-		if (src_cnt_to_sw(xor->ctl_f.src_cnt) > 5)
-			return true;
-	} else if (hw->ctl_f.op == IOAT_OP_PQ ||
-		   hw->ctl_f.op == IOAT_OP_PQ_VAL) {
-		struct ioat_pq_descriptor *pq = desc->pq;
-
-		if (src_cnt_to_sw(pq->ctl_f.src_cnt) > 3)
-			return true;
-	}
-
-	return false;
-}
-
-static u64 ioat3_get_current_completion(struct ioat_chan_common *chan)
-{
-	u64 phys_complete;
-	u64 completion;
-
-	completion = *chan->completion;
-	phys_complete = ioat_chansts_to_addr(completion);
-
-	dev_dbg(to_dev(chan), "%s: phys_complete: %#llx\n", __func__,
-		(unsigned long long) phys_complete);
-
-	return phys_complete;
-}
-
-static bool ioat3_cleanup_preamble(struct ioat_chan_common *chan,
-				   u64 *phys_complete)
-{
-	*phys_complete = ioat3_get_current_completion(chan);
-	if (*phys_complete == chan->last_completion)
-		return false;
-
-	clear_bit(IOAT_COMPLETION_ACK, &chan->state);
-	mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-
-	return true;
-}
-
-static void
-desc_get_errstat(struct ioat2_dma_chan *ioat, struct ioat_ring_ent *desc)
-{
-	struct ioat_dma_descriptor *hw = desc->hw;
-
-	switch (hw->ctl_f.op) {
-	case IOAT_OP_PQ_VAL:
-	case IOAT_OP_PQ_VAL_16S:
-	{
-		struct ioat_pq_descriptor *pq = desc->pq;
-
-		/* check if there's error written */
-		if (!pq->dwbes_f.wbes)
-			return;
-
-		/* need to set a chanerr var for checking to clear later */
-
-		if (pq->dwbes_f.p_val_err)
-			*desc->result |= SUM_CHECK_P_RESULT;
-
-		if (pq->dwbes_f.q_val_err)
-			*desc->result |= SUM_CHECK_Q_RESULT;
-
-		return;
-	}
-	default:
-		return;
-	}
-}
-
-/**
- * __cleanup - reclaim used descriptors
- * @ioat: channel (ring) to clean
- *
- * The difference from the dma_v2.c __cleanup() is that this routine
- * handles extended descriptors and dma-unmapping raid operations.
- */
-static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioatdma_device *device = chan->device;
-	struct ioat_ring_ent *desc;
-	bool seen_current = false;
-	int idx = ioat->tail, i;
-	u16 active;
-
-	dev_dbg(to_dev(chan), "%s: head: %#x tail: %#x issued: %#x\n",
-		__func__, ioat->head, ioat->tail, ioat->issued);
-
-	/*
-	 * At restart of the channel, the completion address and the
-	 * channel status will be 0 due to starting a new chain. Since
-	 * it's new chain and the first descriptor "fails", there is
-	 * nothing to clean up. We do not want to reap the entire submitted
-	 * chain due to this 0 address value and then BUG.
-	 */
-	if (!phys_complete)
-		return;
-
-	active = ioat2_ring_active(ioat);
-	for (i = 0; i < active && !seen_current; i++) {
-		struct dma_async_tx_descriptor *tx;
-
-		smp_read_barrier_depends();
-		prefetch(ioat2_get_ring_ent(ioat, idx + i + 1));
-		desc = ioat2_get_ring_ent(ioat, idx + i);
-		dump_desc_dbg(ioat, desc);
-
-		/* set err stat if we are using dwbes */
-		if (device->cap & IOAT_CAP_DWBES)
-			desc_get_errstat(ioat, desc);
-
-		tx = &desc->txd;
-		if (tx->cookie) {
-			dma_cookie_complete(tx);
-			dma_descriptor_unmap(tx);
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
-		}
-
-		if (tx->phys == phys_complete)
-			seen_current = true;
-
-		/* skip extended descriptors */
-		if (desc_has_ext(desc)) {
-			BUG_ON(i + 1 >= active);
-			i++;
-		}
-
-		/* cleanup super extended descriptors */
-		if (desc->sed) {
-			ioat3_free_sed(device, desc->sed);
-			desc->sed = NULL;
-		}
-	}
-	smp_mb(); /* finish all descriptor reads before incrementing tail */
-	ioat->tail = idx + i;
-	BUG_ON(active && !seen_current); /* no active descs have written a completion? */
-	chan->last_completion = phys_complete;
-
-	if (active - i == 0) {
-		dev_dbg(to_dev(chan), "%s: cancel completion timeout\n",
-			__func__);
-		clear_bit(IOAT_COMPLETION_PENDING, &chan->state);
-		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-	}
-	/* 5 microsecond delay per pending descriptor */
-	writew(min((5 * (active - i)), IOAT_INTRDELAY_MASK),
-	       chan->device->reg_base + IOAT_INTRDELAY_OFFSET);
-}
-
-static void ioat3_cleanup(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	u64 phys_complete;
-
-	spin_lock_bh(&chan->cleanup_lock);
-
-	if (ioat3_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-
-	if (is_ioat_halted(*chan->completion)) {
-		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-
-		if (chanerr & IOAT_CHANERR_HANDLE_MASK) {
-			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-			ioat3_eh(ioat);
-		}
-	}
-
-	spin_unlock_bh(&chan->cleanup_lock);
-}
-
-static void ioat3_cleanup_event(unsigned long data)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
-	struct ioat_chan_common *chan = &ioat->base;
-
-	ioat3_cleanup(ioat);
-	if (!test_bit(IOAT_RUN, &chan->state))
-		return;
-	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
-}
-
-static void ioat3_restart_channel(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	u64 phys_complete;
-
-	ioat2_quiesce(chan, 0);
-	if (ioat3_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-
-	__ioat2_restart_chan(ioat);
-}
-
-static void ioat3_eh(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	struct pci_dev *pdev = to_pdev(chan);
-	struct ioat_dma_descriptor *hw;
-	struct dma_async_tx_descriptor *tx;
-	u64 phys_complete;
-	struct ioat_ring_ent *desc;
-	u32 err_handled = 0;
-	u32 chanerr_int;
-	u32 chanerr;
-
-	/* cleanup so tail points to descriptor that caused the error */
-	if (ioat3_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-
-	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-	pci_read_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, &chanerr_int);
-
-	dev_dbg(to_dev(chan), "%s: error = %x:%x\n",
-		__func__, chanerr, chanerr_int);
-
-	desc = ioat2_get_ring_ent(ioat, ioat->tail);
-	hw = desc->hw;
-	dump_desc_dbg(ioat, desc);
-
-	switch (hw->ctl_f.op) {
-	case IOAT_OP_XOR_VAL:
-		if (chanerr & IOAT_CHANERR_XOR_P_OR_CRC_ERR) {
-			*desc->result |= SUM_CHECK_P_RESULT;
-			err_handled |= IOAT_CHANERR_XOR_P_OR_CRC_ERR;
-		}
-		break;
-	case IOAT_OP_PQ_VAL:
-	case IOAT_OP_PQ_VAL_16S:
-		if (chanerr & IOAT_CHANERR_XOR_P_OR_CRC_ERR) {
-			*desc->result |= SUM_CHECK_P_RESULT;
-			err_handled |= IOAT_CHANERR_XOR_P_OR_CRC_ERR;
-		}
-		if (chanerr & IOAT_CHANERR_XOR_Q_ERR) {
-			*desc->result |= SUM_CHECK_Q_RESULT;
-			err_handled |= IOAT_CHANERR_XOR_Q_ERR;
-		}
-		break;
-	}
-
-	/* fault on unhandled error or spurious halt */
-	if (chanerr ^ err_handled || chanerr == 0) {
-		dev_err(to_dev(chan), "%s: fatal error (%x:%x)\n",
-			__func__, chanerr, err_handled);
-		BUG();
-	} else { /* cleanup the faulty descriptor */
-		tx = &desc->txd;
-		if (tx->cookie) {
-			dma_cookie_complete(tx);
-			dma_descriptor_unmap(tx);
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
-		}
-	}
-
-	writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
-	pci_write_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, chanerr_int);
-
-	/* mark faulting descriptor as complete */
-	*chan->completion = desc->txd.phys;
-
-	spin_lock_bh(&ioat->prep_lock);
-	ioat3_restart_channel(ioat);
-	spin_unlock_bh(&ioat->prep_lock);
-}
-
-static void check_active(struct ioat2_dma_chan *ioat)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-
-	if (ioat2_ring_active(ioat)) {
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-		return;
-	}
-
-	if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &chan->state))
-		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-	else if (ioat->alloc_order > ioat_get_alloc_order()) {
-		/* if the ring is idle, empty, and oversized try to step
-		 * down the size
-		 */
-		reshape_ring(ioat, ioat->alloc_order - 1);
-
-		/* keep shrinking until we get back to our minimum
-		 * default size
-		 */
-		if (ioat->alloc_order > ioat_get_alloc_order())
-			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
-	}
-
-}
-
-static void ioat3_timer_event(unsigned long data)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
-	struct ioat_chan_common *chan = &ioat->base;
-	dma_addr_t phys_complete;
-	u64 status;
-
-	status = ioat_chansts(chan);
-
-	/* when halted due to errors check for channel
-	 * programming errors before advancing the completion state
-	 */
-	if (is_ioat_halted(status)) {
-		u32 chanerr;
-
-		chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-		dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
-			__func__, chanerr);
-		if (test_bit(IOAT_RUN, &chan->state))
-			BUG_ON(is_ioat_bug(chanerr));
-		else /* we never got off the ground */
-			return;
-	}
-
-	/* if we haven't made progress and we have already
-	 * acknowledged a pending completion once, then be more
-	 * forceful with a restart
-	 */
-	spin_lock_bh(&chan->cleanup_lock);
-	if (ioat_cleanup_preamble(chan, &phys_complete))
-		__cleanup(ioat, phys_complete);
-	else if (test_bit(IOAT_COMPLETION_ACK, &chan->state)) {
-		spin_lock_bh(&ioat->prep_lock);
-		ioat3_restart_channel(ioat);
-		spin_unlock_bh(&ioat->prep_lock);
-		spin_unlock_bh(&chan->cleanup_lock);
-		return;
-	} else {
-		set_bit(IOAT_COMPLETION_ACK, &chan->state);
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-	}
-
-
-	if (ioat2_ring_active(ioat))
-		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-	else {
-		spin_lock_bh(&ioat->prep_lock);
-		check_active(ioat);
-		spin_unlock_bh(&ioat->prep_lock);
-	}
-	spin_unlock_bh(&chan->cleanup_lock);
-}
-
-static enum dma_status
-ioat3_tx_status(struct dma_chan *c, dma_cookie_t cookie,
-		struct dma_tx_state *txstate)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	enum dma_status ret;
-
-	ret = dma_cookie_status(c, cookie, txstate);
-	if (ret == DMA_COMPLETE)
-		return ret;
-
-	ioat3_cleanup(ioat);
-
-	return dma_cookie_status(c, cookie, txstate);
-}
-
-static struct dma_async_tx_descriptor *
-__ioat3_prep_xor_lock(struct dma_chan *c, enum sum_check_flags *result,
-		      dma_addr_t dest, dma_addr_t *src, unsigned int src_cnt,
-		      size_t len, unsigned long flags)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_ring_ent *compl_desc;
-	struct ioat_ring_ent *desc;
-	struct ioat_ring_ent *ext;
-	size_t total_len = len;
-	struct ioat_xor_descriptor *xor;
-	struct ioat_xor_ext_descriptor *xor_ex = NULL;
-	struct ioat_dma_descriptor *hw;
-	int num_descs, with_ext, idx, i;
-	u32 offset = 0;
-	u8 op = result ? IOAT_OP_XOR_VAL : IOAT_OP_XOR;
-
-	BUG_ON(src_cnt < 2);
-
-	num_descs = ioat2_xferlen_to_descs(ioat, len);
-	/* we need 2x the number of descriptors to cover greater than 5
-	 * sources
-	 */
-	if (src_cnt > 5) {
-		with_ext = 1;
-		num_descs *= 2;
-	} else
-		with_ext = 0;
-
-	/* completion writes from the raid engine may pass completion
-	 * writes from the legacy engine, so we need one extra null
-	 * (legacy) descriptor to ensure all completion writes arrive in
-	 * order.
-	 */
-	if (likely(num_descs) && ioat2_check_space_lock(ioat, num_descs+1) == 0)
-		idx = ioat->head;
-	else
-		return NULL;
-	i = 0;
-	do {
-		struct ioat_raw_descriptor *descs[2];
-		size_t xfer_size = min_t(size_t, len, 1 << ioat->xfercap_log);
-		int s;
-
-		desc = ioat2_get_ring_ent(ioat, idx + i);
-		xor = desc->xor;
-
-		/* save a branch by unconditionally retrieving the
-		 * extended descriptor xor_set_src() knows to not write
-		 * to it in the single descriptor case
-		 */
-		ext = ioat2_get_ring_ent(ioat, idx + i + 1);
-		xor_ex = ext->xor_ex;
-
-		descs[0] = (struct ioat_raw_descriptor *) xor;
-		descs[1] = (struct ioat_raw_descriptor *) xor_ex;
-		for (s = 0; s < src_cnt; s++)
-			xor_set_src(descs, src[s], offset, s);
-		xor->size = xfer_size;
-		xor->dst_addr = dest + offset;
-		xor->ctl = 0;
-		xor->ctl_f.op = op;
-		xor->ctl_f.src_cnt = src_cnt_to_hw(src_cnt);
-
-		len -= xfer_size;
-		offset += xfer_size;
-		dump_desc_dbg(ioat, desc);
-	} while ((i += 1 + with_ext) < num_descs);
-
-	/* last xor descriptor carries the unmap parameters and fence bit */
-	desc->txd.flags = flags;
-	desc->len = total_len;
-	if (result)
-		desc->result = result;
-	xor->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
-
-	/* completion descriptor carries interrupt bit */
-	compl_desc = ioat2_get_ring_ent(ioat, idx + i);
-	compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
-	hw = compl_desc->hw;
-	hw->ctl = 0;
-	hw->ctl_f.null = 1;
-	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
-	hw->ctl_f.compl_write = 1;
-	hw->size = NULL_DESC_BUFFER_SIZE;
-	dump_desc_dbg(ioat, compl_desc);
-
-	/* we leave the channel locked to ensure in order submission */
-	return &compl_desc->txd;
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
-	       unsigned int src_cnt, size_t len, unsigned long flags)
-{
-	return __ioat3_prep_xor_lock(chan, NULL, dest, src, src_cnt, len, flags);
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_xor_val(struct dma_chan *chan, dma_addr_t *src,
-		    unsigned int src_cnt, size_t len,
-		    enum sum_check_flags *result, unsigned long flags)
-{
-	/* the cleanup routine only sets bits on validate failure, it
-	 * does not clear bits on validate success... so clear it here
-	 */
-	*result = 0;
-
-	return __ioat3_prep_xor_lock(chan, result, src[0], &src[1],
-				     src_cnt - 1, len, flags);
-}
-
-static void
-dump_pq_desc_dbg(struct ioat2_dma_chan *ioat, struct ioat_ring_ent *desc, struct ioat_ring_ent *ext)
-{
-	struct device *dev = to_dev(&ioat->base);
-	struct ioat_pq_descriptor *pq = desc->pq;
-	struct ioat_pq_ext_descriptor *pq_ex = ext ? ext->pq_ex : NULL;
-	struct ioat_raw_descriptor *descs[] = { (void *) pq, (void *) pq_ex };
-	int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
-	int i;
-
-	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
-		" sz: %#10.8x ctl: %#x (op: %#x int: %d compl: %d pq: '%s%s'"
-		" src_cnt: %d)\n",
-		desc_id(desc), (unsigned long long) desc->txd.phys,
-		(unsigned long long) (pq_ex ? pq_ex->next : pq->next),
-		desc->txd.flags, pq->size, pq->ctl, pq->ctl_f.op, pq->ctl_f.int_en,
-		pq->ctl_f.compl_write,
-		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
-		pq->ctl_f.src_cnt);
-	for (i = 0; i < src_cnt; i++)
-		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
-			(unsigned long long) pq_get_src(descs, i), pq->coef[i]);
-	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
-	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
-	dev_dbg(dev, "\tNEXT: %#llx\n", pq->next);
-}
-
-static void dump_pq16_desc_dbg(struct ioat2_dma_chan *ioat,
-			       struct ioat_ring_ent *desc)
-{
-	struct device *dev = to_dev(&ioat->base);
-	struct ioat_pq_descriptor *pq = desc->pq;
-	struct ioat_raw_descriptor *descs[] = { (void *)pq,
-						(void *)pq,
-						(void *)pq };
-	int src_cnt = src16_cnt_to_sw(pq->ctl_f.src_cnt);
-	int i;
-
-	if (desc->sed) {
-		descs[1] = (void *)desc->sed->hw;
-		descs[2] = (void *)desc->sed->hw + 64;
-	}
-
-	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
-		" sz: %#x ctl: %#x (op: %#x int: %d compl: %d pq: '%s%s'"
-		" src_cnt: %d)\n",
-		desc_id(desc), (unsigned long long) desc->txd.phys,
-		(unsigned long long) pq->next,
-		desc->txd.flags, pq->size, pq->ctl,
-		pq->ctl_f.op, pq->ctl_f.int_en,
-		pq->ctl_f.compl_write,
-		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
-		pq->ctl_f.src_cnt);
-	for (i = 0; i < src_cnt; i++) {
-		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
-			(unsigned long long) pq16_get_src(descs, i),
-			pq->coef[i]);
-	}
-	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
-	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
-}
-
-static struct dma_async_tx_descriptor *
-__ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
-		     const dma_addr_t *dst, const dma_addr_t *src,
-		     unsigned int src_cnt, const unsigned char *scf,
-		     size_t len, unsigned long flags)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioatdma_device *device = chan->device;
-	struct ioat_ring_ent *compl_desc;
-	struct ioat_ring_ent *desc;
-	struct ioat_ring_ent *ext;
-	size_t total_len = len;
-	struct ioat_pq_descriptor *pq;
-	struct ioat_pq_ext_descriptor *pq_ex = NULL;
-	struct ioat_dma_descriptor *hw;
-	u32 offset = 0;
-	u8 op = result ? IOAT_OP_PQ_VAL : IOAT_OP_PQ;
-	int i, s, idx, with_ext, num_descs;
-	int cb32 = (device->version < IOAT_VER_3_3) ? 1 : 0;
-
-	dev_dbg(to_dev(chan), "%s\n", __func__);
-	/* the engine requires at least two sources (we provide
-	 * at least 1 implied source in the DMA_PREP_CONTINUE case)
-	 */
-	BUG_ON(src_cnt + dmaf_continue(flags) < 2);
-
-	num_descs = ioat2_xferlen_to_descs(ioat, len);
-	/* we need 2x the number of descriptors to cover greater than 3
-	 * sources (we need 1 extra source in the q-only continuation
-	 * case and 3 extra sources in the p+q continuation case.
-	 */
-	if (src_cnt + dmaf_p_disabled_continue(flags) > 3 ||
-	    (dmaf_continue(flags) && !dmaf_p_disabled_continue(flags))) {
-		with_ext = 1;
-		num_descs *= 2;
-	} else
-		with_ext = 0;
-
-	/* completion writes from the raid engine may pass completion
-	 * writes from the legacy engine, so we need one extra null
-	 * (legacy) descriptor to ensure all completion writes arrive in
-	 * order.
-	 */
-	if (likely(num_descs) &&
-	    ioat2_check_space_lock(ioat, num_descs + cb32) == 0)
-		idx = ioat->head;
-	else
-		return NULL;
-	i = 0;
-	do {
-		struct ioat_raw_descriptor *descs[2];
-		size_t xfer_size = min_t(size_t, len, 1 << ioat->xfercap_log);
-
-		desc = ioat2_get_ring_ent(ioat, idx + i);
-		pq = desc->pq;
-
-		/* save a branch by unconditionally retrieving the
-		 * extended descriptor pq_set_src() knows to not write
-		 * to it in the single descriptor case
-		 */
-		ext = ioat2_get_ring_ent(ioat, idx + i + with_ext);
-		pq_ex = ext->pq_ex;
-
-		descs[0] = (struct ioat_raw_descriptor *) pq;
-		descs[1] = (struct ioat_raw_descriptor *) pq_ex;
-
-		for (s = 0; s < src_cnt; s++)
-			pq_set_src(descs, src[s], offset, scf[s], s);
-
-		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
-		if (dmaf_p_disabled_continue(flags))
-			pq_set_src(descs, dst[1], offset, 1, s++);
-		else if (dmaf_continue(flags)) {
-			pq_set_src(descs, dst[0], offset, 0, s++);
-			pq_set_src(descs, dst[1], offset, 1, s++);
-			pq_set_src(descs, dst[1], offset, 0, s++);
-		}
-		pq->size = xfer_size;
-		pq->p_addr = dst[0] + offset;
-		pq->q_addr = dst[1] + offset;
-		pq->ctl = 0;
-		pq->ctl_f.op = op;
-		/* we turn on descriptor write back error status */
-		if (device->cap & IOAT_CAP_DWBES)
-			pq->ctl_f.wb_en = result ? 1 : 0;
-		pq->ctl_f.src_cnt = src_cnt_to_hw(s);
-		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
-		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);
-
-		len -= xfer_size;
-		offset += xfer_size;
-	} while ((i += 1 + with_ext) < num_descs);
-
-	/* last pq descriptor carries the unmap parameters and fence bit */
-	desc->txd.flags = flags;
-	desc->len = total_len;
-	if (result)
-		desc->result = result;
-	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
-	dump_pq_desc_dbg(ioat, desc, ext);
-
-	if (!cb32) {
-		pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
-		pq->ctl_f.compl_write = 1;
-		compl_desc = desc;
-	} else {
-		/* completion descriptor carries interrupt bit */
-		compl_desc = ioat2_get_ring_ent(ioat, idx + i);
-		compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
-		hw = compl_desc->hw;
-		hw->ctl = 0;
-		hw->ctl_f.null = 1;
-		hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
-		hw->ctl_f.compl_write = 1;
-		hw->size = NULL_DESC_BUFFER_SIZE;
-		dump_desc_dbg(ioat, compl_desc);
-	}
-
-
-	/* we leave the channel locked to ensure in order submission */
-	return &compl_desc->txd;
-}
-
-static struct dma_async_tx_descriptor *
-__ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
-		       const dma_addr_t *dst, const dma_addr_t *src,
-		       unsigned int src_cnt, const unsigned char *scf,
-		       size_t len, unsigned long flags)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_chan_common *chan = &ioat->base;
-	struct ioatdma_device *device = chan->device;
-	struct ioat_ring_ent *desc;
-	size_t total_len = len;
-	struct ioat_pq_descriptor *pq;
-	u32 offset = 0;
-	u8 op;
-	int i, s, idx, num_descs;
-
-	/* this function is only called with 9-16 sources */
-	op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;
-
-	dev_dbg(to_dev(chan), "%s\n", __func__);
-
-	num_descs = ioat2_xferlen_to_descs(ioat, len);
-
-	/*
-	 * 16 source pq is only available on cb3.3 and has no completion
-	 * write hw bug.
-	 */
-	if (num_descs && ioat2_check_space_lock(ioat, num_descs) == 0)
-		idx = ioat->head;
-	else
-		return NULL;
-
-	i = 0;
-
-	do {
-		struct ioat_raw_descriptor *descs[4];
-		size_t xfer_size = min_t(size_t, len, 1 << ioat->xfercap_log);
-
-		desc = ioat2_get_ring_ent(ioat, idx + i);
-		pq = desc->pq;
-
-		descs[0] = (struct ioat_raw_descriptor *) pq;
-
-		desc->sed = ioat3_alloc_sed(device, (src_cnt-2) >> 3);
-		if (!desc->sed) {
-			dev_err(to_dev(chan),
-				"%s: no free sed entries\n", __func__);
-			return NULL;
-		}
-
-		pq->sed_addr = desc->sed->dma;
-		desc->sed->parent = desc;
-
-		descs[1] = (struct ioat_raw_descriptor *)desc->sed->hw;
-		descs[2] = (void *)descs[1] + 64;
-
-		for (s = 0; s < src_cnt; s++)
-			pq16_set_src(descs, src[s], offset, scf[s], s);
-
-		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
-		if (dmaf_p_disabled_continue(flags))
-			pq16_set_src(descs, dst[1], offset, 1, s++);
-		else if (dmaf_continue(flags)) {
-			pq16_set_src(descs, dst[0], offset, 0, s++);
-			pq16_set_src(descs, dst[1], offset, 1, s++);
-			pq16_set_src(descs, dst[1], offset, 0, s++);
-		}
-
-		pq->size = xfer_size;
-		pq->p_addr = dst[0] + offset;
-		pq->q_addr = dst[1] + offset;
-		pq->ctl = 0;
-		pq->ctl_f.op = op;
-		pq->ctl_f.src_cnt = src16_cnt_to_hw(s);
-		/* we turn on descriptor write back error status */
-		if (device->cap & IOAT_CAP_DWBES)
-			pq->ctl_f.wb_en = result ? 1 : 0;
-		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
-		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);
-
-		len -= xfer_size;
-		offset += xfer_size;
-	} while (++i < num_descs);
-
-	/* last pq descriptor carries the unmap parameters and fence bit */
-	desc->txd.flags = flags;
-	desc->len = total_len;
-	if (result)
-		desc->result = result;
-	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
-
-	/* with cb3.3 we should be able to do completion w/o a null desc */
-	pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
-	pq->ctl_f.compl_write = 1;
-
-	dump_pq16_desc_dbg(ioat, desc);
-
-	/* we leave the channel locked to ensure in order submission */
-	return &desc->txd;
-}
-
-static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
-{
-	if (dmaf_p_disabled_continue(flags))
-		return src_cnt + 1;
-	else if (dmaf_continue(flags))
-		return src_cnt + 3;
-	else
-		return src_cnt;
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
-	      unsigned int src_cnt, const unsigned char *scf, size_t len,
-	      unsigned long flags)
-{
-	/* specify valid address for disabled result */
-	if (flags & DMA_PREP_PQ_DISABLE_P)
-		dst[0] = dst[1];
-	if (flags & DMA_PREP_PQ_DISABLE_Q)
-		dst[1] = dst[0];
-
-	/* handle the single source multiply case from the raid6
-	 * recovery path
-	 */
-	if ((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1) {
-		dma_addr_t single_source[2];
-		unsigned char single_source_coef[2];
-
-		BUG_ON(flags & DMA_PREP_PQ_DISABLE_Q);
-		single_source[0] = src[0];
-		single_source[1] = src[0];
-		single_source_coef[0] = scf[0];
-		single_source_coef[1] = 0;
-
-		return src_cnt_flags(src_cnt, flags) > 8 ?
-			__ioat3_prep_pq16_lock(chan, NULL, dst, single_source,
-					       2, single_source_coef, len,
-					       flags) :
-			__ioat3_prep_pq_lock(chan, NULL, dst, single_source, 2,
-					     single_source_coef, len, flags);
-
-	} else {
-		return src_cnt_flags(src_cnt, flags) > 8 ?
-			__ioat3_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
-					       scf, len, flags) :
-			__ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt,
-					     scf, len, flags);
-	}
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
-		  unsigned int src_cnt, const unsigned char *scf, size_t len,
-		  enum sum_check_flags *pqres, unsigned long flags)
-{
-	/* specify valid address for disabled result */
-	if (flags & DMA_PREP_PQ_DISABLE_P)
-		pq[0] = pq[1];
-	if (flags & DMA_PREP_PQ_DISABLE_Q)
-		pq[1] = pq[0];
-
-	/* the cleanup routine only sets bits on validate failure, it
-	 * does not clear bits on validate success... so clear it here
-	 */
-	*pqres = 0;
-
-	return src_cnt_flags(src_cnt, flags) > 8 ?
-		__ioat3_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
-				       flags) :
-		__ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
-				     flags);
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
-		 unsigned int src_cnt, size_t len, unsigned long flags)
-{
-	unsigned char scf[src_cnt];
-	dma_addr_t pq[2];
-
-	memset(scf, 0, src_cnt);
-	pq[0] = dst;
-	flags |= DMA_PREP_PQ_DISABLE_Q;
-	pq[1] = dst; /* specify valid address for disabled result */
-
-	return src_cnt_flags(src_cnt, flags) > 8 ?
-		__ioat3_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
-				       flags) :
-		__ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
-				     flags);
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
-		     unsigned int src_cnt, size_t len,
-		     enum sum_check_flags *result, unsigned long flags)
-{
-	unsigned char scf[src_cnt];
-	dma_addr_t pq[2];
-
-	/* the cleanup routine only sets bits on validate failure, it
-	 * does not clear bits on validate success... so clear it here
-	 */
-	*result = 0;
-
-	memset(scf, 0, src_cnt);
-	pq[0] = src[0];
-	flags |= DMA_PREP_PQ_DISABLE_Q;
-	pq[1] = pq[0]; /* specify valid address for disabled result */
-
-	return src_cnt_flags(src_cnt, flags) > 8 ?
-		__ioat3_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
-				       scf, len, flags) :
-		__ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
-				     scf, len, flags);
-}
-
-static struct dma_async_tx_descriptor *
-ioat3_prep_interrupt_lock(struct dma_chan *c, unsigned long flags)
-{
-	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
-	struct ioat_ring_ent *desc;
-	struct ioat_dma_descriptor *hw;
-
-	if (ioat2_check_space_lock(ioat, 1) == 0)
-		desc = ioat2_get_ring_ent(ioat, ioat->head);
-	else
-		return NULL;
-
-	hw = desc->hw;
-	hw->ctl = 0;
-	hw->ctl_f.null = 1;
-	hw->ctl_f.int_en = 1;
-	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
-	hw->ctl_f.compl_write = 1;
-	hw->size = NULL_DESC_BUFFER_SIZE;
-	hw->src_addr = 0;
-	hw->dst_addr = 0;
-
-	desc->txd.flags = flags;
-	desc->len = 1;
-
-	dump_desc_dbg(ioat, desc);
-
-	/* we leave the channel locked to ensure in order submission */
-	return &desc->txd;
-}
-
-static void ioat3_dma_test_callback(void *dma_async_param)
-{
-	struct completion *cmp = dma_async_param;
-
-	complete(cmp);
-}
-
-#define IOAT_NUM_SRC_TEST 6 /* must be <= 8 */
-static int ioat_xor_val_self_test(struct ioatdma_device *device)
-{
-	int i, src_idx;
-	struct page *dest;
-	struct page *xor_srcs[IOAT_NUM_SRC_TEST];
-	struct page *xor_val_srcs[IOAT_NUM_SRC_TEST + 1];
-	dma_addr_t dma_srcs[IOAT_NUM_SRC_TEST + 1];
-	dma_addr_t dest_dma;
-	struct dma_async_tx_descriptor *tx;
-	struct dma_chan *dma_chan;
-	dma_cookie_t cookie;
-	u8 cmp_byte = 0;
-	u32 cmp_word;
-	u32 xor_val_result;
-	int err = 0;
-	struct completion cmp;
-	unsigned long tmo;
-	struct device *dev = &device->pdev->dev;
-	struct dma_device *dma = &device->common;
-	u8 op = 0;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	if (!dma_has_cap(DMA_XOR, dma->cap_mask))
-		return 0;
-
-	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++) {
-		xor_srcs[src_idx] = alloc_page(GFP_KERNEL);
-		if (!xor_srcs[src_idx]) {
-			while (src_idx--)
-				__free_page(xor_srcs[src_idx]);
-			return -ENOMEM;
-		}
-	}
-
-	dest = alloc_page(GFP_KERNEL);
-	if (!dest) {
-		while (src_idx--)
-			__free_page(xor_srcs[src_idx]);
-		return -ENOMEM;
-	}
-
-	/* Fill in src buffers */
-	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++) {
-		u8 *ptr = page_address(xor_srcs[src_idx]);
-		for (i = 0; i < PAGE_SIZE; i++)
-			ptr[i] = (1 << src_idx);
-	}
-
-	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++)
-		cmp_byte ^= (u8) (1 << src_idx);
-
-	cmp_word = (cmp_byte << 24) | (cmp_byte << 16) |
-			(cmp_byte << 8) | cmp_byte;
-
-	memset(page_address(dest), 0, PAGE_SIZE);
-
-	dma_chan = container_of(dma->channels.next, struct dma_chan,
-				device_node);
-	if (dma->device_alloc_chan_resources(dma_chan) < 1) {
-		err = -ENODEV;
-		goto out;
-	}
-
-	/* test xor */
-	op = IOAT_OP_XOR;
-
-	dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, dest_dma))
-		goto dma_unmap;
-
-	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
-		dma_srcs[i] = DMA_ERROR_CODE;
-	for (i = 0; i < IOAT_NUM_SRC_TEST; i++) {
-		dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE,
-					   DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma_srcs[i]))
-			goto dma_unmap;
-	}
-	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
-				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
-				      DMA_PREP_INTERRUPT);
-
-	if (!tx) {
-		dev_err(dev, "Self-test xor prep failed\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	async_tx_ack(tx);
-	init_completion(&cmp);
-	tx->callback = ioat3_dma_test_callback;
-	tx->callback_param = &cmp;
-	cookie = tx->tx_submit(tx);
-	if (cookie < 0) {
-		dev_err(dev, "Self-test xor setup failed\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-	dma->device_issue_pending(dma_chan);
-
-	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-
-	if (tmo == 0 ||
-	    dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
-		dev_err(dev, "Self-test xor timed out\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
-		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
-
-	dma_sync_single_for_cpu(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
-	for (i = 0; i < (PAGE_SIZE / sizeof(u32)); i++) {
-		u32 *ptr = page_address(dest);
-		if (ptr[i] != cmp_word) {
-			dev_err(dev, "Self-test xor failed compare\n");
-			err = -ENODEV;
-			goto free_resources;
-		}
-	}
-	dma_sync_single_for_device(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
-
-	dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
-
-	/* skip validate if the capability is not present */
-	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
-		goto free_resources;
-
-	op = IOAT_OP_XOR_VAL;
-
-	/* validate the sources with the destintation page */
-	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
-		xor_val_srcs[i] = xor_srcs[i];
-	xor_val_srcs[i] = dest;
-
-	xor_val_result = 1;
-
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-		dma_srcs[i] = DMA_ERROR_CODE;
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
-		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
-					   DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma_srcs[i]))
-			goto dma_unmap;
-	}
-	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
-					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT);
-	if (!tx) {
-		dev_err(dev, "Self-test zero prep failed\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	async_tx_ack(tx);
-	init_completion(&cmp);
-	tx->callback = ioat3_dma_test_callback;
-	tx->callback_param = &cmp;
-	cookie = tx->tx_submit(tx);
-	if (cookie < 0) {
-		dev_err(dev, "Self-test zero setup failed\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-	dma->device_issue_pending(dma_chan);
-
-	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-
-	if (tmo == 0 ||
-	    dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
-		dev_err(dev, "Self-test validate timed out\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
-
-	if (xor_val_result != 0) {
-		dev_err(dev, "Self-test validate failed compare\n");
-		err = -ENODEV;
-		goto free_resources;
-	}
-
-	memset(page_address(dest), 0, PAGE_SIZE);
-
-	/* test for non-zero parity sum */
-	op = IOAT_OP_XOR_VAL;
-
-	xor_val_result = 0;
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-		dma_srcs[i] = DMA_ERROR_CODE;
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
-		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
-					   DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma_srcs[i]))
-			goto dma_unmap;
-	}
-	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
-					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT);
-	if (!tx) {
-		dev_err(dev, "Self-test 2nd zero prep failed\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	async_tx_ack(tx);
-	init_completion(&cmp);
-	tx->callback = ioat3_dma_test_callback;
-	tx->callback_param = &cmp;
-	cookie = tx->tx_submit(tx);
-	if (cookie < 0) {
-		dev_err(dev, "Self-test  2nd zero setup failed\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-	dma->device_issue_pending(dma_chan);
-
-	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-
-	if (tmo == 0 ||
-	    dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
-		dev_err(dev, "Self-test 2nd validate timed out\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	if (xor_val_result != SUM_CHECK_P_RESULT) {
-		dev_err(dev, "Self-test validate failed compare\n");
-		err = -ENODEV;
-		goto dma_unmap;
-	}
-
-	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
-
-	goto free_resources;
-dma_unmap:
-	if (op == IOAT_OP_XOR) {
-		if (dest_dma != DMA_ERROR_CODE)
-			dma_unmap_page(dev, dest_dma, PAGE_SIZE,
-				       DMA_FROM_DEVICE);
-		for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
-			if (dma_srcs[i] != DMA_ERROR_CODE)
-				dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
-					       DMA_TO_DEVICE);
-	} else if (op == IOAT_OP_XOR_VAL) {
-		for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
-			if (dma_srcs[i] != DMA_ERROR_CODE)
-				dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
-					       DMA_TO_DEVICE);
-	}
-free_resources:
-	dma->device_free_chan_resources(dma_chan);
-out:
-	src_idx = IOAT_NUM_SRC_TEST;
-	while (src_idx--)
-		__free_page(xor_srcs[src_idx]);
-	__free_page(dest);
-	return err;
-}
-
-static int ioat3_dma_self_test(struct ioatdma_device *device)
-{
-	int rc = ioat_dma_self_test(device);
-
-	if (rc)
-		return rc;
-
-	rc = ioat_xor_val_self_test(device);
-	if (rc)
-		return rc;
-
-	return 0;
-}
-
-static int ioat3_irq_reinit(struct ioatdma_device *device)
-{
-	struct pci_dev *pdev = device->pdev;
-	int irq = pdev->irq, i;
-
-	if (!is_bwd_ioat(pdev))
-		return 0;
-
-	switch (device->irq_mode) {
-	case IOAT_MSIX:
-		for (i = 0; i < device->common.chancnt; i++) {
-			struct msix_entry *msix = &device->msix_entries[i];
-			struct ioat_chan_common *chan;
-
-			chan = ioat_chan_by_index(device, i);
-			devm_free_irq(&pdev->dev, msix->vector, chan);
-		}
-
-		pci_disable_msix(pdev);
-		break;
-	case IOAT_MSI:
-		pci_disable_msi(pdev);
-		/* fall through */
-	case IOAT_INTX:
-		devm_free_irq(&pdev->dev, irq, device);
-		break;
-	default:
-		return 0;
-	}
-	device->irq_mode = IOAT_NOIRQ;
-
-	return ioat_dma_setup_interrupts(device);
-}
-
-static int ioat3_reset_hw(struct ioat_chan_common *chan)
-{
-	/* throw away whatever the channel was doing and get it
-	 * initialized, with ioat3 specific workarounds
-	 */
-	struct ioatdma_device *device = chan->device;
-	struct pci_dev *pdev = device->pdev;
-	u32 chanerr;
-	u16 dev_id;
-	int err;
-
-	ioat2_quiesce(chan, msecs_to_jiffies(100));
-
-	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-	writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
-
-	if (device->version < IOAT_VER_3_3) {
-		/* clear any pending errors */
-		err = pci_read_config_dword(pdev,
-				IOAT_PCI_CHANERR_INT_OFFSET, &chanerr);
-		if (err) {
-			dev_err(&pdev->dev,
-				"channel error register unreachable\n");
-			return err;
-		}
-		pci_write_config_dword(pdev,
-				IOAT_PCI_CHANERR_INT_OFFSET, chanerr);
-
-		/* Clear DMAUNCERRSTS Cfg-Reg Parity Error status bit
-		 * (workaround for spurious config parity error after restart)
-		 */
-		pci_read_config_word(pdev, IOAT_PCI_DEVICE_ID_OFFSET, &dev_id);
-		if (dev_id == PCI_DEVICE_ID_INTEL_IOAT_TBG0) {
-			pci_write_config_dword(pdev,
-					       IOAT_PCI_DMAUNCERRSTS_OFFSET,
-					       0x10);
-		}
-	}
-
-	err = ioat2_reset_sync(chan, msecs_to_jiffies(200));
-	if (!err)
-		err = ioat3_irq_reinit(device);
-
-	if (err)
-		dev_err(&pdev->dev, "Failed to reset: %d\n", err);
-
-	return err;
-}
-
-static void ioat3_intr_quirk(struct ioatdma_device *device)
-{
-	struct dma_device *dma;
-	struct dma_chan *c;
-	struct ioat_chan_common *chan;
-	u32 errmask;
-
-	dma = &device->common;
-
-	/*
-	 * if we have descriptor write back error status, we mask the
-	 * error interrupts
-	 */
-	if (device->cap & IOAT_CAP_DWBES) {
-		list_for_each_entry(c, &dma->channels, device_node) {
-			chan = to_chan_common(c);
-			errmask = readl(chan->reg_base +
-					IOAT_CHANERR_MASK_OFFSET);
-			errmask |= IOAT_CHANERR_XOR_P_OR_CRC_ERR |
-				   IOAT_CHANERR_XOR_Q_ERR;
-			writel(errmask, chan->reg_base +
-					IOAT_CHANERR_MASK_OFFSET);
-		}
-	}
-}
-
-int ioat3_dma_probe(struct ioatdma_device *device, int dca)
-{
-	struct pci_dev *pdev = device->pdev;
-	int dca_en = system_has_dca_enabled(pdev);
-	struct dma_device *dma;
-	struct dma_chan *c;
-	struct ioat_chan_common *chan;
-	bool is_raid_device = false;
-	int err;
-
-	device->enumerate_channels = ioat2_enumerate_channels;
-	device->reset_hw = ioat3_reset_hw;
-	device->self_test = ioat3_dma_self_test;
-	device->intr_quirk = ioat3_intr_quirk;
-	dma = &device->common;
-	dma->device_prep_dma_memcpy = ioat2_dma_prep_memcpy_lock;
-	dma->device_issue_pending = ioat2_issue_pending;
-	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
-	dma->device_free_chan_resources = ioat2_free_chan_resources;
-
-	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
-	dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock;
-
-	device->cap = readl(device->reg_base + IOAT_DMA_CAP_OFFSET);
-
-	if (is_xeon_cb32(pdev) || is_bwd_noraid(pdev))
-		device->cap &= ~(IOAT_CAP_XOR | IOAT_CAP_PQ | IOAT_CAP_RAID16SS);
-
-	/* dca is incompatible with raid operations */
-	if (dca_en && (device->cap & (IOAT_CAP_XOR|IOAT_CAP_PQ)))
-		device->cap &= ~(IOAT_CAP_XOR|IOAT_CAP_PQ);
-
-	if (device->cap & IOAT_CAP_XOR) {
-		is_raid_device = true;
-		dma->max_xor = 8;
-
-		dma_cap_set(DMA_XOR, dma->cap_mask);
-		dma->device_prep_dma_xor = ioat3_prep_xor;
-
-		dma_cap_set(DMA_XOR_VAL, dma->cap_mask);
-		dma->device_prep_dma_xor_val = ioat3_prep_xor_val;
-	}
-
-	if (device->cap & IOAT_CAP_PQ) {
-		is_raid_device = true;
-
-		dma->device_prep_dma_pq = ioat3_prep_pq;
-		dma->device_prep_dma_pq_val = ioat3_prep_pq_val;
-		dma_cap_set(DMA_PQ, dma->cap_mask);
-		dma_cap_set(DMA_PQ_VAL, dma->cap_mask);
-
-		if (device->cap & IOAT_CAP_RAID16SS) {
-			dma_set_maxpq(dma, 16, 0);
-		} else {
-			dma_set_maxpq(dma, 8, 0);
-		}
-
-		if (!(device->cap & IOAT_CAP_XOR)) {
-			dma->device_prep_dma_xor = ioat3_prep_pqxor;
-			dma->device_prep_dma_xor_val = ioat3_prep_pqxor_val;
-			dma_cap_set(DMA_XOR, dma->cap_mask);
-			dma_cap_set(DMA_XOR_VAL, dma->cap_mask);
-
-			if (device->cap & IOAT_CAP_RAID16SS) {
-				dma->max_xor = 16;
-			} else {
-				dma->max_xor = 8;
-			}
-		}
-	}
-
-	dma->device_tx_status = ioat3_tx_status;
-	device->cleanup_fn = ioat3_cleanup_event;
-	device->timer_fn = ioat3_timer_event;
-
-	/* starting with CB3.3 super extended descriptors are supported */
-	if (device->cap & IOAT_CAP_RAID16SS) {
-		char pool_name[14];
-		int i;
-
-		for (i = 0; i < MAX_SED_POOLS; i++) {
-			snprintf(pool_name, 14, "ioat_hw%d_sed", i);
-
-			/* allocate SED DMA pool */
-			device->sed_hw_pool[i] = dmam_pool_create(pool_name,
-					&pdev->dev,
-					SED_SIZE * (i + 1), 64, 0);
-			if (!device->sed_hw_pool[i])
-				return -ENOMEM;
-
-		}
-	}
-
-	err = ioat_probe(device);
-	if (err)
-		return err;
-
-	list_for_each_entry(c, &dma->channels, device_node) {
-		chan = to_chan_common(c);
-		writel(IOAT_DMA_DCA_ANY_CPU,
-		       chan->reg_base + IOAT_DCACTRL_OFFSET);
-	}
-
-	err = ioat_register(device);
-	if (err)
-		return err;
-
-	ioat_kobject_add(device, &ioat2_ktype);
-
-	if (dca)
-		device->dca = ioat3_dca_init(pdev, device->reg_base);
-
-	return 0;
-}
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index a3e731edce57..690e3b4f8202 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -21,11 +21,6 @@
 #define IOAT_MMIO_BAR		0
 
 /* CB device ID's */
-#define IOAT_PCI_DID_5000       0x1A38
-#define IOAT_PCI_DID_CNB        0x360B
-#define IOAT_PCI_DID_SCNB       0x65FF
-#define IOAT_PCI_DID_SNB        0x402F
-
 #define PCI_DEVICE_ID_INTEL_IOAT_IVB0	0x0e20
 #define PCI_DEVICE_ID_INTEL_IOAT_IVB1	0x0e21
 #define PCI_DEVICE_ID_INTEL_IOAT_IVB2	0x0e22
@@ -58,6 +53,17 @@
 #define PCI_DEVICE_ID_INTEL_IOAT_BDXDE2	0x6f52
 #define PCI_DEVICE_ID_INTEL_IOAT_BDXDE3	0x6f53
 
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX0	0x6f20
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX1	0x6f21
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX2	0x6f22
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX3	0x6f23
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX4	0x6f24
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX5	0x6f25
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX6	0x6f26
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX7	0x6f27
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX8	0x6f2e
+#define PCI_DEVICE_ID_INTEL_IOAT_BDX9	0x6f2f
+
 #define IOAT_VER_1_2            0x12    /* Version 1.2 */
 #define IOAT_VER_2_0            0x20    /* Version 2.0 */
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
new file mode 100644
index 000000000000..1c3c9b0abf4e
--- /dev/null
+++ b/drivers/dma/ioat/init.c
@@ -0,0 +1,1314 @@
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2004 - 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
+#include <linux/prefetch.h>
+#include <linux/dca.h>
+#include "dma.h"
+#include "registers.h"
+#include "hw.h"
+
+#include "../dmaengine.h"
+
+MODULE_VERSION(IOAT_DMA_VERSION);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel Corporation");
+
+static struct pci_device_id ioat_pci_tbl[] = {
+	/* I/OAT v3 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG7) },
+
+	/* I/OAT v3.2 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF9) },
+
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB9) },
+
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB9) },
+
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW9) },
+
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) },
+
+	/* I/OAT v3.3 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD3) },
+
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE3) },
+
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ioat_pci_tbl);
+
+static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id);
+static void ioat_remove(struct pci_dev *pdev);
+static void
+ioat_init_channel(struct ioatdma_device *ioat_dma,
+		  struct ioatdma_chan *ioat_chan, int idx);
+static void ioat_intr_quirk(struct ioatdma_device *ioat_dma);
+static int ioat_enumerate_channels(struct ioatdma_device *ioat_dma);
+static int ioat3_dma_self_test(struct ioatdma_device *ioat_dma);
+
+static int ioat_dca_enabled = 1;
+module_param(ioat_dca_enabled, int, 0644);
+MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
+int ioat_pending_level = 4;
+module_param(ioat_pending_level, int, 0644);
+MODULE_PARM_DESC(ioat_pending_level,
+		 "high-water mark for pushing ioat descriptors (default: 4)");
+int ioat_ring_alloc_order = 8;
+module_param(ioat_ring_alloc_order, int, 0644);
+MODULE_PARM_DESC(ioat_ring_alloc_order,
+		 "ioat+: allocate 2^n descriptors per channel (default: 8 max: 16)");
+int ioat_ring_max_alloc_order = IOAT_MAX_ORDER;
+module_param(ioat_ring_max_alloc_order, int, 0644);
+MODULE_PARM_DESC(ioat_ring_max_alloc_order,
+		 "ioat+: upper limit for ring size (default: 16)");
+static char ioat_interrupt_style[32] = "msix";
+module_param_string(ioat_interrupt_style, ioat_interrupt_style,
+		    sizeof(ioat_interrupt_style), 0644);
+MODULE_PARM_DESC(ioat_interrupt_style,
+		 "set ioat interrupt style: msix (default), msi, intx");
+
+struct kmem_cache *ioat_cache;
+struct kmem_cache *ioat_sed_cache;
+
+static bool is_jf_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF0:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF1:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF2:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF3:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF4:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF5:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF6:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF7:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF8:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF9:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_snb_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB0:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB1:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB2:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB3:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB4:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB5:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB6:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB7:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB8:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB9:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_ivb_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB0:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB1:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB2:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB3:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB4:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB5:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB6:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB7:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB8:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB9:
+		return true;
+	default:
+		return false;
+	}
+
+}
+
+static bool is_hsw_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW0:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW1:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW2:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW3:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW4:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW5:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW6:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW7:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW8:
+	case PCI_DEVICE_ID_INTEL_IOAT_HSW9:
+		return true;
+	default:
+		return false;
+	}
+
+}
+
+static bool is_bdx_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX0:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX1:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX2:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX3:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX4:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX5:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX6:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX7:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX8:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDX9:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_xeon_cb32(struct pci_dev *pdev)
+{
+	return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) ||
+		is_hsw_ioat(pdev) || is_bdx_ioat(pdev);
+}
+
+bool is_bwd_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_BWD0:
+	case PCI_DEVICE_ID_INTEL_IOAT_BWD1:
+	case PCI_DEVICE_ID_INTEL_IOAT_BWD2:
+	case PCI_DEVICE_ID_INTEL_IOAT_BWD3:
+	/* even though not Atom, BDX-DE has same DMA silicon */
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE0:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE1:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE2:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE3:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_bwd_noraid(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_BWD2:
+	case PCI_DEVICE_ID_INTEL_IOAT_BWD3:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE0:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE1:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE2:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE3:
+		return true;
+	default:
+		return false;
+	}
+
+}
+
+/*
+ * Perform a IOAT transaction to verify the HW works.
+ */
+#define IOAT_TEST_SIZE 2000
+
+static void ioat_dma_test_callback(void *dma_async_param)
+{
+	struct completion *cmp = dma_async_param;
+
+	complete(cmp);
+}
+
+/**
+ * ioat_dma_self_test - Perform a IOAT transaction to verify the HW works.
+ * @ioat_dma: dma device to be tested
+ */
+static int ioat_dma_self_test(struct ioatdma_device *ioat_dma)
+{
+	int i;
+	u8 *src;
+	u8 *dest;
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	struct device *dev = &ioat_dma->pdev->dev;
+	struct dma_chan *dma_chan;
+	struct dma_async_tx_descriptor *tx;
+	dma_addr_t dma_dest, dma_src;
+	dma_cookie_t cookie;
+	int err = 0;
+	struct completion cmp;
+	unsigned long tmo;
+	unsigned long flags;
+
+	src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
+	if (!src)
+		return -ENOMEM;
+	dest = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
+	if (!dest) {
+		kfree(src);
+		return -ENOMEM;
+	}
+
+	/* Fill in src buffer */
+	for (i = 0; i < IOAT_TEST_SIZE; i++)
+		src[i] = (u8)i;
+
+	/* Start copy, using first DMA channel */
+	dma_chan = container_of(dma->channels.next, struct dma_chan,
+				device_node);
+	if (dma->device_alloc_chan_resources(dma_chan) < 1) {
+		dev_err(dev, "selftest cannot allocate chan resource\n");
+		err = -ENODEV;
+		goto out;
+	}
+
+	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, dma_src)) {
+		dev_err(dev, "mapping src buffer failed\n");
+		goto free_resources;
+	}
+	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, dma_dest)) {
+		dev_err(dev, "mapping dest buffer failed\n");
+		goto unmap_src;
+	}
+	flags = DMA_PREP_INTERRUPT;
+	tx = ioat_dma->dma_dev.device_prep_dma_memcpy(dma_chan, dma_dest,
+						      dma_src, IOAT_TEST_SIZE,
+						      flags);
+	if (!tx) {
+		dev_err(dev, "Self-test prep failed, disabling\n");
+		err = -ENODEV;
+		goto unmap_dma;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test setup failed, disabling\n");
+		err = -ENODEV;
+		goto unmap_dma;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (tmo == 0 ||
+	    dma->device_tx_status(dma_chan, cookie, NULL)
+					!= DMA_COMPLETE) {
+		dev_err(dev, "Self-test copy timed out, disabling\n");
+		err = -ENODEV;
+		goto unmap_dma;
+	}
+	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
+		dev_err(dev, "Self-test copy failed compare, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+unmap_dma:
+	dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+unmap_src:
+	dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+free_resources:
+	dma->device_free_chan_resources(dma_chan);
+out:
+	kfree(src);
+	kfree(dest);
+	return err;
+}
+
+/**
+ * ioat_dma_setup_interrupts - setup interrupt handler
+ * @ioat_dma: ioat dma device
+ */
+int ioat_dma_setup_interrupts(struct ioatdma_device *ioat_dma)
+{
+	struct ioatdma_chan *ioat_chan;
+	struct pci_dev *pdev = ioat_dma->pdev;
+	struct device *dev = &pdev->dev;
+	struct msix_entry *msix;
+	int i, j, msixcnt;
+	int err = -EINVAL;
+	u8 intrctrl = 0;
+
+	if (!strcmp(ioat_interrupt_style, "msix"))
+		goto msix;
+	if (!strcmp(ioat_interrupt_style, "msi"))
+		goto msi;
+	if (!strcmp(ioat_interrupt_style, "intx"))
+		goto intx;
+	dev_err(dev, "invalid ioat_interrupt_style %s\n", ioat_interrupt_style);
+	goto err_no_irq;
+
+msix:
+	/* The number of MSI-X vectors should equal the number of channels */
+	msixcnt = ioat_dma->dma_dev.chancnt;
+	for (i = 0; i < msixcnt; i++)
+		ioat_dma->msix_entries[i].entry = i;
+
+	err = pci_enable_msix_exact(pdev, ioat_dma->msix_entries, msixcnt);
+	if (err)
+		goto msi;
+
+	for (i = 0; i < msixcnt; i++) {
+		msix = &ioat_dma->msix_entries[i];
+		ioat_chan = ioat_chan_by_index(ioat_dma, i);
+		err = devm_request_irq(dev, msix->vector,
+				       ioat_dma_do_interrupt_msix, 0,
+				       "ioat-msix", ioat_chan);
+		if (err) {
+			for (j = 0; j < i; j++) {
+				msix = &ioat_dma->msix_entries[j];
+				ioat_chan = ioat_chan_by_index(ioat_dma, j);
+				devm_free_irq(dev, msix->vector, ioat_chan);
+			}
+			goto msi;
+		}
+	}
+	intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
+	ioat_dma->irq_mode = IOAT_MSIX;
+	goto done;
+
+msi:
+	err = pci_enable_msi(pdev);
+	if (err)
+		goto intx;
+
+	err = devm_request_irq(dev, pdev->irq, ioat_dma_do_interrupt, 0,
+			       "ioat-msi", ioat_dma);
+	if (err) {
+		pci_disable_msi(pdev);
+		goto intx;
+	}
+	ioat_dma->irq_mode = IOAT_MSI;
+	goto done;
+
+intx:
+	err = devm_request_irq(dev, pdev->irq, ioat_dma_do_interrupt,
+			       IRQF_SHARED, "ioat-intx", ioat_dma);
+	if (err)
+		goto err_no_irq;
+
+	ioat_dma->irq_mode = IOAT_INTX;
+done:
+	if (is_bwd_ioat(pdev))
+		ioat_intr_quirk(ioat_dma);
+	intrctrl |= IOAT_INTRCTRL_MASTER_INT_EN;
+	writeb(intrctrl, ioat_dma->reg_base + IOAT_INTRCTRL_OFFSET);
+	return 0;
+
+err_no_irq:
+	/* Disable all interrupt generation */
+	writeb(0, ioat_dma->reg_base + IOAT_INTRCTRL_OFFSET);
+	ioat_dma->irq_mode = IOAT_NOIRQ;
+	dev_err(dev, "no usable interrupts\n");
+	return err;
+}
+
+static void ioat_disable_interrupts(struct ioatdma_device *ioat_dma)
+{
+	/* Disable all interrupt generation */
+	writeb(0, ioat_dma->reg_base + IOAT_INTRCTRL_OFFSET);
+}
+
+static int ioat_probe(struct ioatdma_device *ioat_dma)
+{
+	int err = -ENODEV;
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	struct pci_dev *pdev = ioat_dma->pdev;
+	struct device *dev = &pdev->dev;
+
+	/* DMA coherent memory pool for DMA descriptor allocations */
+	ioat_dma->dma_pool = pci_pool_create("dma_desc_pool", pdev,
+					     sizeof(struct ioat_dma_descriptor),
+					     64, 0);
+	if (!ioat_dma->dma_pool) {
+		err = -ENOMEM;
+		goto err_dma_pool;
+	}
+
+	ioat_dma->completion_pool = pci_pool_create("completion_pool", pdev,
+						    sizeof(u64),
+						    SMP_CACHE_BYTES,
+						    SMP_CACHE_BYTES);
+
+	if (!ioat_dma->completion_pool) {
+		err = -ENOMEM;
+		goto err_completion_pool;
+	}
+
+	ioat_enumerate_channels(ioat_dma);
+
+	dma_cap_set(DMA_MEMCPY, dma->cap_mask);
+	dma->dev = &pdev->dev;
+
+	if (!dma->chancnt) {
+		dev_err(dev, "channel enumeration error\n");
+		goto err_setup_interrupts;
+	}
+
+	err = ioat_dma_setup_interrupts(ioat_dma);
+	if (err)
+		goto err_setup_interrupts;
+
+	err = ioat3_dma_self_test(ioat_dma);
+	if (err)
+		goto err_self_test;
+
+	return 0;
+
+err_self_test:
+	ioat_disable_interrupts(ioat_dma);
+err_setup_interrupts:
+	pci_pool_destroy(ioat_dma->completion_pool);
+err_completion_pool:
+	pci_pool_destroy(ioat_dma->dma_pool);
+err_dma_pool:
+	return err;
+}
+
+static int ioat_register(struct ioatdma_device *ioat_dma)
+{
+	int err = dma_async_device_register(&ioat_dma->dma_dev);
+
+	if (err) {
+		ioat_disable_interrupts(ioat_dma);
+		pci_pool_destroy(ioat_dma->completion_pool);
+		pci_pool_destroy(ioat_dma->dma_pool);
+	}
+
+	return err;
+}
+
+static void ioat_dma_remove(struct ioatdma_device *ioat_dma)
+{
+	struct dma_device *dma = &ioat_dma->dma_dev;
+
+	ioat_disable_interrupts(ioat_dma);
+
+	ioat_kobject_del(ioat_dma);
+
+	dma_async_device_unregister(dma);
+
+	pci_pool_destroy(ioat_dma->dma_pool);
+	pci_pool_destroy(ioat_dma->completion_pool);
+
+	INIT_LIST_HEAD(&dma->channels);
+}
+
+/**
+ * ioat_enumerate_channels - find and initialize the device's channels
+ * @ioat_dma: the ioat dma device to be enumerated
+ */
+static int ioat_enumerate_channels(struct ioatdma_device *ioat_dma)
+{
+	struct ioatdma_chan *ioat_chan;
+	struct device *dev = &ioat_dma->pdev->dev;
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	u8 xfercap_log;
+	int i;
+
+	INIT_LIST_HEAD(&dma->channels);
+	dma->chancnt = readb(ioat_dma->reg_base + IOAT_CHANCNT_OFFSET);
+	dma->chancnt &= 0x1f; /* bits [4:0] valid */
+	if (dma->chancnt > ARRAY_SIZE(ioat_dma->idx)) {
+		dev_warn(dev, "(%d) exceeds max supported channels (%zu)\n",
+			 dma->chancnt, ARRAY_SIZE(ioat_dma->idx));
+		dma->chancnt = ARRAY_SIZE(ioat_dma->idx);
+	}
+	xfercap_log = readb(ioat_dma->reg_base + IOAT_XFERCAP_OFFSET);
+	xfercap_log &= 0x1f; /* bits [4:0] valid */
+	if (xfercap_log == 0)
+		return 0;
+	dev_dbg(dev, "%s: xfercap = %d\n", __func__, 1 << xfercap_log);
+
+	for (i = 0; i < dma->chancnt; i++) {
+		ioat_chan = devm_kzalloc(dev, sizeof(*ioat_chan), GFP_KERNEL);
+		if (!ioat_chan)
+			break;
+
+		ioat_init_channel(ioat_dma, ioat_chan, i);
+		ioat_chan->xfercap_log = xfercap_log;
+		spin_lock_init(&ioat_chan->prep_lock);
+		if (ioat_reset_hw(ioat_chan)) {
+			i = 0;
+			break;
+		}
+	}
+	dma->chancnt = i;
+	return i;
+}
+
+/**
+ * ioat_free_chan_resources - release all the descriptors
+ * @chan: the channel to be cleaned
+ */
+static void ioat_free_chan_resources(struct dma_chan *c)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct ioat_ring_ent *desc;
+	const int total_descs = 1 << ioat_chan->alloc_order;
+	int descs;
+	int i;
+
+	/* Before freeing channel resources first check
+	 * if they have been previously allocated for this channel.
+	 */
+	if (!ioat_chan->ring)
+		return;
+
+	ioat_stop(ioat_chan);
+	ioat_reset_hw(ioat_chan);
+
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+	spin_lock_bh(&ioat_chan->prep_lock);
+	descs = ioat_ring_space(ioat_chan);
+	dev_dbg(to_dev(ioat_chan), "freeing %d idle descriptors\n", descs);
+	for (i = 0; i < descs; i++) {
+		desc = ioat_get_ring_ent(ioat_chan, ioat_chan->head + i);
+		ioat_free_ring_ent(desc, c);
+	}
+
+	if (descs < total_descs)
+		dev_err(to_dev(ioat_chan), "Freeing %d in use descriptors!\n",
+			total_descs - descs);
+
+	for (i = 0; i < total_descs - descs; i++) {
+		desc = ioat_get_ring_ent(ioat_chan, ioat_chan->tail + i);
+		dump_desc_dbg(ioat_chan, desc);
+		ioat_free_ring_ent(desc, c);
+	}
+
+	kfree(ioat_chan->ring);
+	ioat_chan->ring = NULL;
+	ioat_chan->alloc_order = 0;
+	pci_pool_free(ioat_dma->completion_pool, ioat_chan->completion,
+		      ioat_chan->completion_dma);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+	spin_unlock_bh(&ioat_chan->cleanup_lock);
+
+	ioat_chan->last_completion = 0;
+	ioat_chan->completion_dma = 0;
+	ioat_chan->dmacount = 0;
+}
+
+/* ioat_alloc_chan_resources - allocate/initialize ioat descriptor ring
+ * @chan: channel to be initialized
+ */
+static int ioat_alloc_chan_resources(struct dma_chan *c)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioat_ring_ent **ring;
+	u64 status;
+	int order;
+	int i = 0;
+	u32 chanerr;
+
+	/* have we already been set up? */
+	if (ioat_chan->ring)
+		return 1 << ioat_chan->alloc_order;
+
+	/* Setup register to interrupt and write completion status on error */
+	writew(IOAT_CHANCTRL_RUN, ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET);
+
+	/* allocate a completion writeback area */
+	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
+	ioat_chan->completion =
+		pci_pool_alloc(ioat_chan->ioat_dma->completion_pool,
+			       GFP_KERNEL, &ioat_chan->completion_dma);
+	if (!ioat_chan->completion)
+		return -ENOMEM;
+
+	memset(ioat_chan->completion, 0, sizeof(*ioat_chan->completion));
+	writel(((u64)ioat_chan->completion_dma) & 0x00000000FFFFFFFF,
+	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
+	writel(((u64)ioat_chan->completion_dma) >> 32,
+	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
+
+	order = ioat_get_alloc_order();
+	ring = ioat_alloc_ring(c, order, GFP_KERNEL);
+	if (!ring)
+		return -ENOMEM;
+
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+	spin_lock_bh(&ioat_chan->prep_lock);
+	ioat_chan->ring = ring;
+	ioat_chan->head = 0;
+	ioat_chan->issued = 0;
+	ioat_chan->tail = 0;
+	ioat_chan->alloc_order = order;
+	set_bit(IOAT_RUN, &ioat_chan->state);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+	spin_unlock_bh(&ioat_chan->cleanup_lock);
+
+	ioat_start_null_desc(ioat_chan);
+
+	/* check that we got off the ground */
+	do {
+		udelay(1);
+		status = ioat_chansts(ioat_chan);
+	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
+
+	if (is_ioat_active(status) || is_ioat_idle(status))
+		return 1 << ioat_chan->alloc_order;
+
+	chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+
+	dev_WARN(to_dev(ioat_chan),
+		 "failed to start channel chanerr: %#x\n", chanerr);
+	ioat_free_chan_resources(c);
+	return -EFAULT;
+}
+
+/* common channel initialization */
+static void
+ioat_init_channel(struct ioatdma_device *ioat_dma,
+		  struct ioatdma_chan *ioat_chan, int idx)
+{
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	struct dma_chan *c = &ioat_chan->dma_chan;
+	unsigned long data = (unsigned long) c;
+
+	ioat_chan->ioat_dma = ioat_dma;
+	ioat_chan->reg_base = ioat_dma->reg_base + (0x80 * (idx + 1));
+	spin_lock_init(&ioat_chan->cleanup_lock);
+	ioat_chan->dma_chan.device = dma;
+	dma_cookie_init(&ioat_chan->dma_chan);
+	list_add_tail(&ioat_chan->dma_chan.device_node, &dma->channels);
+	ioat_dma->idx[idx] = ioat_chan;
+	init_timer(&ioat_chan->timer);
+	ioat_chan->timer.function = ioat_timer_event;
+	ioat_chan->timer.data = data;
+	tasklet_init(&ioat_chan->cleanup_task, ioat_cleanup_event, data);
+}
+
+#define IOAT_NUM_SRC_TEST 6 /* must be <= 8 */
+static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
+{
+	int i, src_idx;
+	struct page *dest;
+	struct page *xor_srcs[IOAT_NUM_SRC_TEST];
+	struct page *xor_val_srcs[IOAT_NUM_SRC_TEST + 1];
+	dma_addr_t dma_srcs[IOAT_NUM_SRC_TEST + 1];
+	dma_addr_t dest_dma;
+	struct dma_async_tx_descriptor *tx;
+	struct dma_chan *dma_chan;
+	dma_cookie_t cookie;
+	u8 cmp_byte = 0;
+	u32 cmp_word;
+	u32 xor_val_result;
+	int err = 0;
+	struct completion cmp;
+	unsigned long tmo;
+	struct device *dev = &ioat_dma->pdev->dev;
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	u8 op = 0;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	if (!dma_has_cap(DMA_XOR, dma->cap_mask))
+		return 0;
+
+	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++) {
+		xor_srcs[src_idx] = alloc_page(GFP_KERNEL);
+		if (!xor_srcs[src_idx]) {
+			while (src_idx--)
+				__free_page(xor_srcs[src_idx]);
+			return -ENOMEM;
+		}
+	}
+
+	dest = alloc_page(GFP_KERNEL);
+	if (!dest) {
+		while (src_idx--)
+			__free_page(xor_srcs[src_idx]);
+		return -ENOMEM;
+	}
+
+	/* Fill in src buffers */
+	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++) {
+		u8 *ptr = page_address(xor_srcs[src_idx]);
+
+		for (i = 0; i < PAGE_SIZE; i++)
+			ptr[i] = (1 << src_idx);
+	}
+
+	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++)
+		cmp_byte ^= (u8) (1 << src_idx);
+
+	cmp_word = (cmp_byte << 24) | (cmp_byte << 16) |
+			(cmp_byte << 8) | cmp_byte;
+
+	memset(page_address(dest), 0, PAGE_SIZE);
+
+	dma_chan = container_of(dma->channels.next, struct dma_chan,
+				device_node);
+	if (dma->device_alloc_chan_resources(dma_chan) < 1) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	/* test xor */
+	op = IOAT_OP_XOR;
+
+	dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, dest_dma))
+		goto dma_unmap;
+
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+		dma_srcs[i] = DMA_ERROR_CODE;
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++) {
+		dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma_srcs[i]))
+			goto dma_unmap;
+	}
+	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
+				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
+				      DMA_PREP_INTERRUPT);
+
+	if (!tx) {
+		dev_err(dev, "Self-test xor prep failed\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test xor setup failed\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (tmo == 0 ||
+	    dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
+		dev_err(dev, "Self-test xor timed out\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
+
+	dma_sync_single_for_cpu(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+	for (i = 0; i < (PAGE_SIZE / sizeof(u32)); i++) {
+		u32 *ptr = page_address(dest);
+
+		if (ptr[i] != cmp_word) {
+			dev_err(dev, "Self-test xor failed compare\n");
+			err = -ENODEV;
+			goto free_resources;
+		}
+	}
+	dma_sync_single_for_device(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+
+	dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+
+	/* skip validate if the capability is not present */
+	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
+		goto free_resources;
+
+	op = IOAT_OP_XOR_VAL;
+
+	/* validate the sources with the destintation page */
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+		xor_val_srcs[i] = xor_srcs[i];
+	xor_val_srcs[i] = dest;
+
+	xor_val_result = 1;
+
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_srcs[i] = DMA_ERROR_CODE;
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
+		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma_srcs[i]))
+			goto dma_unmap;
+	}
+	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
+					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
+					  &xor_val_result, DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(dev, "Self-test zero prep failed\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test zero setup failed\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (tmo == 0 ||
+	    dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
+		dev_err(dev, "Self-test validate timed out\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
+
+	if (xor_val_result != 0) {
+		dev_err(dev, "Self-test validate failed compare\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	memset(page_address(dest), 0, PAGE_SIZE);
+
+	/* test for non-zero parity sum */
+	op = IOAT_OP_XOR_VAL;
+
+	xor_val_result = 0;
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_srcs[i] = DMA_ERROR_CODE;
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
+		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma_srcs[i]))
+			goto dma_unmap;
+	}
+	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
+					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
+					  &xor_val_result, DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(dev, "Self-test 2nd zero prep failed\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test  2nd zero setup failed\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (tmo == 0 ||
+	    dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
+		dev_err(dev, "Self-test 2nd validate timed out\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	if (xor_val_result != SUM_CHECK_P_RESULT) {
+		dev_err(dev, "Self-test validate failed compare\n");
+		err = -ENODEV;
+		goto dma_unmap;
+	}
+
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
+
+	goto free_resources;
+dma_unmap:
+	if (op == IOAT_OP_XOR) {
+		if (dest_dma != DMA_ERROR_CODE)
+			dma_unmap_page(dev, dest_dma, PAGE_SIZE,
+				       DMA_FROM_DEVICE);
+		for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+			if (dma_srcs[i] != DMA_ERROR_CODE)
+				dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
+					       DMA_TO_DEVICE);
+	} else if (op == IOAT_OP_XOR_VAL) {
+		for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+			if (dma_srcs[i] != DMA_ERROR_CODE)
+				dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
+					       DMA_TO_DEVICE);
+	}
+free_resources:
+	dma->device_free_chan_resources(dma_chan);
+out:
+	src_idx = IOAT_NUM_SRC_TEST;
+	while (src_idx--)
+		__free_page(xor_srcs[src_idx]);
+	__free_page(dest);
+	return err;
+}
+
+static int ioat3_dma_self_test(struct ioatdma_device *ioat_dma)
+{
+	int rc;
+
+	rc = ioat_dma_self_test(ioat_dma);
+	if (rc)
+		return rc;
+
+	rc = ioat_xor_val_self_test(ioat_dma);
+
+	return rc;
+}
+
+static void ioat_intr_quirk(struct ioatdma_device *ioat_dma)
+{
+	struct dma_device *dma;
+	struct dma_chan *c;
+	struct ioatdma_chan *ioat_chan;
+	u32 errmask;
+
+	dma = &ioat_dma->dma_dev;
+
+	/*
+	 * if we have descriptor write back error status, we mask the
+	 * error interrupts
+	 */
+	if (ioat_dma->cap & IOAT_CAP_DWBES) {
+		list_for_each_entry(c, &dma->channels, device_node) {
+			ioat_chan = to_ioat_chan(c);
+			errmask = readl(ioat_chan->reg_base +
+					IOAT_CHANERR_MASK_OFFSET);
+			errmask |= IOAT_CHANERR_XOR_P_OR_CRC_ERR |
+				   IOAT_CHANERR_XOR_Q_ERR;
+			writel(errmask, ioat_chan->reg_base +
+					IOAT_CHANERR_MASK_OFFSET);
+		}
+	}
+}
+
+static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
+{
+	struct pci_dev *pdev = ioat_dma->pdev;
+	int dca_en = system_has_dca_enabled(pdev);
+	struct dma_device *dma;
+	struct dma_chan *c;
+	struct ioatdma_chan *ioat_chan;
+	bool is_raid_device = false;
+	int err;
+
+	dma = &ioat_dma->dma_dev;
+	dma->device_prep_dma_memcpy = ioat_dma_prep_memcpy_lock;
+	dma->device_issue_pending = ioat_issue_pending;
+	dma->device_alloc_chan_resources = ioat_alloc_chan_resources;
+	dma->device_free_chan_resources = ioat_free_chan_resources;
+
+	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
+	dma->device_prep_dma_interrupt = ioat_prep_interrupt_lock;
+
+	ioat_dma->cap = readl(ioat_dma->reg_base + IOAT_DMA_CAP_OFFSET);
+
+	if (is_xeon_cb32(pdev) || is_bwd_noraid(pdev))
+		ioat_dma->cap &=
+			~(IOAT_CAP_XOR | IOAT_CAP_PQ | IOAT_CAP_RAID16SS);
+
+	/* dca is incompatible with raid operations */
+	if (dca_en && (ioat_dma->cap & (IOAT_CAP_XOR|IOAT_CAP_PQ)))
+		ioat_dma->cap &= ~(IOAT_CAP_XOR|IOAT_CAP_PQ);
+
+	if (ioat_dma->cap & IOAT_CAP_XOR) {
+		is_raid_device = true;
+		dma->max_xor = 8;
+
+		dma_cap_set(DMA_XOR, dma->cap_mask);
+		dma->device_prep_dma_xor = ioat_prep_xor;
+
+		dma_cap_set(DMA_XOR_VAL, dma->cap_mask);
+		dma->device_prep_dma_xor_val = ioat_prep_xor_val;
+	}
+
+	if (ioat_dma->cap & IOAT_CAP_PQ) {
+		is_raid_device = true;
+
+		dma->device_prep_dma_pq = ioat_prep_pq;
+		dma->device_prep_dma_pq_val = ioat_prep_pq_val;
+		dma_cap_set(DMA_PQ, dma->cap_mask);
+		dma_cap_set(DMA_PQ_VAL, dma->cap_mask);
+
+		if (ioat_dma->cap & IOAT_CAP_RAID16SS)
+			dma_set_maxpq(dma, 16, 0);
+		else
+			dma_set_maxpq(dma, 8, 0);
+
+		if (!(ioat_dma->cap & IOAT_CAP_XOR)) {
+			dma->device_prep_dma_xor = ioat_prep_pqxor;
+			dma->device_prep_dma_xor_val = ioat_prep_pqxor_val;
+			dma_cap_set(DMA_XOR, dma->cap_mask);
+			dma_cap_set(DMA_XOR_VAL, dma->cap_mask);
+
+			if (ioat_dma->cap & IOAT_CAP_RAID16SS)
+				dma->max_xor = 16;
+			else
+				dma->max_xor = 8;
+		}
+	}
+
+	dma->device_tx_status = ioat_tx_status;
+
+	/* starting with CB3.3 super extended descriptors are supported */
+	if (ioat_dma->cap & IOAT_CAP_RAID16SS) {
+		char pool_name[14];
+		int i;
+
+		for (i = 0; i < MAX_SED_POOLS; i++) {
+			snprintf(pool_name, 14, "ioat_hw%d_sed", i);
+
+			/* allocate SED DMA pool */
+			ioat_dma->sed_hw_pool[i] = dmam_pool_create(pool_name,
+					&pdev->dev,
+					SED_SIZE * (i + 1), 64, 0);
+			if (!ioat_dma->sed_hw_pool[i])
+				return -ENOMEM;
+
+		}
+	}
+
+	if (!(ioat_dma->cap & (IOAT_CAP_XOR | IOAT_CAP_PQ)))
+		dma_cap_set(DMA_PRIVATE, dma->cap_mask);
+
+	err = ioat_probe(ioat_dma);
+	if (err)
+		return err;
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		ioat_chan = to_ioat_chan(c);
+		writel(IOAT_DMA_DCA_ANY_CPU,
+		       ioat_chan->reg_base + IOAT_DCACTRL_OFFSET);
+	}
+
+	err = ioat_register(ioat_dma);
+	if (err)
+		return err;
+
+	ioat_kobject_add(ioat_dma, &ioat_ktype);
+
+	if (dca)
+		ioat_dma->dca = ioat_dca_init(pdev, ioat_dma->reg_base);
+
+	return 0;
+}
+
+#define DRV_NAME "ioatdma"
+
+static struct pci_driver ioat_pci_driver = {
+	.name		= DRV_NAME,
+	.id_table	= ioat_pci_tbl,
+	.probe		= ioat_pci_probe,
+	.remove		= ioat_remove,
+};
+
+static struct ioatdma_device *
+alloc_ioatdma(struct pci_dev *pdev, void __iomem *iobase)
+{
+	struct device *dev = &pdev->dev;
+	struct ioatdma_device *d = devm_kzalloc(dev, sizeof(*d), GFP_KERNEL);
+
+	if (!d)
+		return NULL;
+	d->pdev = pdev;
+	d->reg_base = iobase;
+	return d;
+}
+
+static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	void __iomem * const *iomap;
+	struct device *dev = &pdev->dev;
+	struct ioatdma_device *device;
+	int err;
+
+	err = pcim_enable_device(pdev);
+	if (err)
+		return err;
+
+	err = pcim_iomap_regions(pdev, 1 << IOAT_MMIO_BAR, DRV_NAME);
+	if (err)
+		return err;
+	iomap = pcim_iomap_table(pdev);
+	if (!iomap)
+		return -ENOMEM;
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err)
+		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err)
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	device = alloc_ioatdma(pdev, iomap[IOAT_MMIO_BAR]);
+	if (!device)
+		return -ENOMEM;
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, device);
+
+	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
+	if (device->version >= IOAT_VER_3_0)
+		err = ioat3_dma_probe(device, ioat_dca_enabled);
+	else
+		return -ENODEV;
+
+	if (err) {
+		dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void ioat_remove(struct pci_dev *pdev)
+{
+	struct ioatdma_device *device = pci_get_drvdata(pdev);
+
+	if (!device)
+		return;
+
+	dev_err(&pdev->dev, "Removing dma and dca services\n");
+	if (device->dca) {
+		unregister_dca_provider(device->dca, &pdev->dev);
+		free_dca_provider(device->dca);
+		device->dca = NULL;
+	}
+	ioat_dma_remove(device);
+}
+
+static int __init ioat_init_module(void)
+{
+	int err = -ENOMEM;
+
+	pr_info("%s: Intel(R) QuickData Technology Driver %s\n",
+		DRV_NAME, IOAT_DMA_VERSION);
+
+	ioat_cache = kmem_cache_create("ioat", sizeof(struct ioat_ring_ent),
+					0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!ioat_cache)
+		return -ENOMEM;
+
+	ioat_sed_cache = KMEM_CACHE(ioat_sed_ent, 0);
+	if (!ioat_sed_cache)
+		goto err_ioat_cache;
+
+	err = pci_register_driver(&ioat_pci_driver);
+	if (err)
+		goto err_ioat3_cache;
+
+	return 0;
+
+ err_ioat3_cache:
+	kmem_cache_destroy(ioat_sed_cache);
+
+ err_ioat_cache:
+	kmem_cache_destroy(ioat_cache);
+
+	return err;
+}
+module_init(ioat_init_module);
+
+static void __exit ioat_exit_module(void)
+{
+	pci_unregister_driver(&ioat_pci_driver);
+	kmem_cache_destroy(ioat_cache);
+}
+module_exit(ioat_exit_module);
diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c
deleted file mode 100644
index 76f0dc688a19..000000000000
--- a/drivers/dma/ioat/pci.c
+++ /dev/null
@@ -1,258 +0,0 @@
-/*
- * Intel I/OAT DMA Linux driver
- * Copyright(c) 2007 - 2009 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- */
-
-/*
- * This driver supports an Intel I/OAT DMA engine, which does asynchronous
- * copy operations.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/dca.h>
-#include <linux/slab.h>
-#include "dma.h"
-#include "dma_v2.h"
-#include "registers.h"
-#include "hw.h"
-
-MODULE_VERSION(IOAT_DMA_VERSION);
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Intel Corporation");
-
-static struct pci_device_id ioat_pci_tbl[] = {
-	/* I/OAT v1 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_CNB)  },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SCNB) },
-	{ PCI_VDEVICE(UNISYS, PCI_DEVICE_ID_UNISYS_DMA_DIRECTOR) },
-
-	/* I/OAT v2 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB) },
-
-	/* I/OAT v3 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG3) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG4) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG5) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG6) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG7) },
-
-	/* I/OAT v3.2 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF3) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF4) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF5) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF6) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF7) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF8) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF9) },
-
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB3) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB4) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB5) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB6) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB7) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB8) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB9) },
-
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB3) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB4) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB5) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB6) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB7) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB8) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB9) },
-
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW3) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW4) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW5) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW6) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW7) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW8) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_HSW9) },
-
-	/* I/OAT v3.3 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD3) },
-
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE0) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE1) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE2) },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE3) },
-
-	{ 0, }
-};
-MODULE_DEVICE_TABLE(pci, ioat_pci_tbl);
-
-static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id);
-static void ioat_remove(struct pci_dev *pdev);
-
-static int ioat_dca_enabled = 1;
-module_param(ioat_dca_enabled, int, 0644);
-MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
-
-struct kmem_cache *ioat2_cache;
-struct kmem_cache *ioat3_sed_cache;
-
-#define DRV_NAME "ioatdma"
-
-static struct pci_driver ioat_pci_driver = {
-	.name		= DRV_NAME,
-	.id_table	= ioat_pci_tbl,
-	.probe		= ioat_pci_probe,
-	.remove		= ioat_remove,
-};
-
-static struct ioatdma_device *
-alloc_ioatdma(struct pci_dev *pdev, void __iomem *iobase)
-{
-	struct device *dev = &pdev->dev;
-	struct ioatdma_device *d = devm_kzalloc(dev, sizeof(*d), GFP_KERNEL);
-
-	if (!d)
-		return NULL;
-	d->pdev = pdev;
-	d->reg_base = iobase;
-	return d;
-}
-
-static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
-{
-	void __iomem * const *iomap;
-	struct device *dev = &pdev->dev;
-	struct ioatdma_device *device;
-	int err;
-
-	err = pcim_enable_device(pdev);
-	if (err)
-		return err;
-
-	err = pcim_iomap_regions(pdev, 1 << IOAT_MMIO_BAR, DRV_NAME);
-	if (err)
-		return err;
-	iomap = pcim_iomap_table(pdev);
-	if (!iomap)
-		return -ENOMEM;
-
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err)
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (err)
-		return err;
-
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (err)
-		return err;
-
-	device = alloc_ioatdma(pdev, iomap[IOAT_MMIO_BAR]);
-	if (!device)
-		return -ENOMEM;
-	pci_set_master(pdev);
-	pci_set_drvdata(pdev, device);
-
-	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
-	if (device->version == IOAT_VER_1_2)
-		err = ioat1_dma_probe(device, ioat_dca_enabled);
-	else if (device->version == IOAT_VER_2_0)
-		err = ioat2_dma_probe(device, ioat_dca_enabled);
-	else if (device->version >= IOAT_VER_3_0)
-		err = ioat3_dma_probe(device, ioat_dca_enabled);
-	else
-		return -ENODEV;
-
-	if (err) {
-		dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n");
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-static void ioat_remove(struct pci_dev *pdev)
-{
-	struct ioatdma_device *device = pci_get_drvdata(pdev);
-
-	if (!device)
-		return;
-
-	dev_err(&pdev->dev, "Removing dma and dca services\n");
-	if (device->dca) {
-		unregister_dca_provider(device->dca, &pdev->dev);
-		free_dca_provider(device->dca);
-		device->dca = NULL;
-	}
-	ioat_dma_remove(device);
-}
-
-static int __init ioat_init_module(void)
-{
-	int err = -ENOMEM;
-
-	pr_info("%s: Intel(R) QuickData Technology Driver %s\n",
-		DRV_NAME, IOAT_DMA_VERSION);
-
-	ioat2_cache = kmem_cache_create("ioat2", sizeof(struct ioat_ring_ent),
-					0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!ioat2_cache)
-		return -ENOMEM;
-
-	ioat3_sed_cache = KMEM_CACHE(ioat_sed_ent, 0);
-	if (!ioat3_sed_cache)
-		goto err_ioat2_cache;
-
-	err = pci_register_driver(&ioat_pci_driver);
-	if (err)
-		goto err_ioat3_cache;
-
-	return 0;
-
- err_ioat3_cache:
-	kmem_cache_destroy(ioat3_sed_cache);
-
- err_ioat2_cache:
-	kmem_cache_destroy(ioat2_cache);
-
-	return err;
-}
-module_init(ioat_init_module);
-
-static void __exit ioat_exit_module(void)
-{
-	pci_unregister_driver(&ioat_pci_driver);
-	kmem_cache_destroy(ioat2_cache);
-}
-module_exit(ioat_exit_module);
diff --git a/drivers/dma/ioat/prep.c b/drivers/dma/ioat/prep.c
new file mode 100644
index 000000000000..ad4fb41cd23b
--- /dev/null
+++ b/drivers/dma/ioat/prep.c
@@ -0,0 +1,715 @@
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2004 - 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/gfp.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/prefetch.h>
+#include "../dmaengine.h"
+#include "registers.h"
+#include "hw.h"
+#include "dma.h"
+
+#define MAX_SCF	1024
+
+/* provide a lookup table for setting the source address in the base or
+ * extended descriptor of an xor or pq descriptor
+ */
+static const u8 xor_idx_to_desc = 0xe0;
+static const u8 xor_idx_to_field[] = { 1, 4, 5, 6, 7, 0, 1, 2 };
+static const u8 pq_idx_to_desc = 0xf8;
+static const u8 pq16_idx_to_desc[] = { 0, 0, 1, 1, 1, 1, 1, 1, 1,
+				       2, 2, 2, 2, 2, 2, 2 };
+static const u8 pq_idx_to_field[] = { 1, 4, 5, 0, 1, 2, 4, 5 };
+static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
+					0, 1, 2, 3, 4, 5, 6 };
+
+static void xor_set_src(struct ioat_raw_descriptor *descs[2],
+			dma_addr_t addr, u32 offset, int idx)
+{
+	struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];
+
+	raw->field[xor_idx_to_field[idx]] = addr + offset;
+}
+
+static dma_addr_t pq_get_src(struct ioat_raw_descriptor *descs[2], int idx)
+{
+	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];
+
+	return raw->field[pq_idx_to_field[idx]];
+}
+
+static dma_addr_t pq16_get_src(struct ioat_raw_descriptor *desc[3], int idx)
+{
+	struct ioat_raw_descriptor *raw = desc[pq16_idx_to_desc[idx]];
+
+	return raw->field[pq16_idx_to_field[idx]];
+}
+
+static void pq_set_src(struct ioat_raw_descriptor *descs[2],
+		       dma_addr_t addr, u32 offset, u8 coef, int idx)
+{
+	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *) descs[0];
+	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];
+
+	raw->field[pq_idx_to_field[idx]] = addr + offset;
+	pq->coef[idx] = coef;
+}
+
+static void pq16_set_src(struct ioat_raw_descriptor *desc[3],
+			dma_addr_t addr, u32 offset, u8 coef, unsigned idx)
+{
+	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *)desc[0];
+	struct ioat_pq16a_descriptor *pq16 =
+		(struct ioat_pq16a_descriptor *)desc[1];
+	struct ioat_raw_descriptor *raw = desc[pq16_idx_to_desc[idx]];
+
+	raw->field[pq16_idx_to_field[idx]] = addr + offset;
+
+	if (idx < 8)
+		pq->coef[idx] = coef;
+	else
+		pq16->coef[idx - 8] = coef;
+}
+
+static struct ioat_sed_ent *
+ioat3_alloc_sed(struct ioatdma_device *ioat_dma, unsigned int hw_pool)
+{
+	struct ioat_sed_ent *sed;
+	gfp_t flags = __GFP_ZERO | GFP_ATOMIC;
+
+	sed = kmem_cache_alloc(ioat_sed_cache, flags);
+	if (!sed)
+		return NULL;
+
+	sed->hw_pool = hw_pool;
+	sed->hw = dma_pool_alloc(ioat_dma->sed_hw_pool[hw_pool],
+				 flags, &sed->dma);
+	if (!sed->hw) {
+		kmem_cache_free(ioat_sed_cache, sed);
+		return NULL;
+	}
+
+	return sed;
+}
+
+struct dma_async_tx_descriptor *
+ioat_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
+			   dma_addr_t dma_src, size_t len, unsigned long flags)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioat_dma_descriptor *hw;
+	struct ioat_ring_ent *desc;
+	dma_addr_t dst = dma_dest;
+	dma_addr_t src = dma_src;
+	size_t total_len = len;
+	int num_descs, idx, i;
+
+	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
+	if (likely(num_descs) &&
+	    ioat_check_space_lock(ioat_chan, num_descs) == 0)
+		idx = ioat_chan->head;
+	else
+		return NULL;
+	i = 0;
+	do {
+		size_t copy = min_t(size_t, len, 1 << ioat_chan->xfercap_log);
+
+		desc = ioat_get_ring_ent(ioat_chan, idx + i);
+		hw = desc->hw;
+
+		hw->size = copy;
+		hw->ctl = 0;
+		hw->src_addr = src;
+		hw->dst_addr = dst;
+
+		len -= copy;
+		dst += copy;
+		src += copy;
+		dump_desc_dbg(ioat_chan, desc);
+	} while (++i < num_descs);
+
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	hw->ctl_f.compl_write = 1;
+	dump_desc_dbg(ioat_chan, desc);
+	/* we leave the channel locked to ensure in order submission */
+
+	return &desc->txd;
+}
+
+
+static struct dma_async_tx_descriptor *
+__ioat_prep_xor_lock(struct dma_chan *c, enum sum_check_flags *result,
+		      dma_addr_t dest, dma_addr_t *src, unsigned int src_cnt,
+		      size_t len, unsigned long flags)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioat_ring_ent *compl_desc;
+	struct ioat_ring_ent *desc;
+	struct ioat_ring_ent *ext;
+	size_t total_len = len;
+	struct ioat_xor_descriptor *xor;
+	struct ioat_xor_ext_descriptor *xor_ex = NULL;
+	struct ioat_dma_descriptor *hw;
+	int num_descs, with_ext, idx, i;
+	u32 offset = 0;
+	u8 op = result ? IOAT_OP_XOR_VAL : IOAT_OP_XOR;
+
+	BUG_ON(src_cnt < 2);
+
+	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
+	/* we need 2x the number of descriptors to cover greater than 5
+	 * sources
+	 */
+	if (src_cnt > 5) {
+		with_ext = 1;
+		num_descs *= 2;
+	} else
+		with_ext = 0;
+
+	/* completion writes from the raid engine may pass completion
+	 * writes from the legacy engine, so we need one extra null
+	 * (legacy) descriptor to ensure all completion writes arrive in
+	 * order.
+	 */
+	if (likely(num_descs) &&
+	    ioat_check_space_lock(ioat_chan, num_descs+1) == 0)
+		idx = ioat_chan->head;
+	else
+		return NULL;
+	i = 0;
+	do {
+		struct ioat_raw_descriptor *descs[2];
+		size_t xfer_size = min_t(size_t,
+					 len, 1 << ioat_chan->xfercap_log);
+		int s;
+
+		desc = ioat_get_ring_ent(ioat_chan, idx + i);
+		xor = desc->xor;
+
+		/* save a branch by unconditionally retrieving the
+		 * extended descriptor xor_set_src() knows to not write
+		 * to it in the single descriptor case
+		 */
+		ext = ioat_get_ring_ent(ioat_chan, idx + i + 1);
+		xor_ex = ext->xor_ex;
+
+		descs[0] = (struct ioat_raw_descriptor *) xor;
+		descs[1] = (struct ioat_raw_descriptor *) xor_ex;
+		for (s = 0; s < src_cnt; s++)
+			xor_set_src(descs, src[s], offset, s);
+		xor->size = xfer_size;
+		xor->dst_addr = dest + offset;
+		xor->ctl = 0;
+		xor->ctl_f.op = op;
+		xor->ctl_f.src_cnt = src_cnt_to_hw(src_cnt);
+
+		len -= xfer_size;
+		offset += xfer_size;
+		dump_desc_dbg(ioat_chan, desc);
+	} while ((i += 1 + with_ext) < num_descs);
+
+	/* last xor descriptor carries the unmap parameters and fence bit */
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	if (result)
+		desc->result = result;
+	xor->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+
+	/* completion descriptor carries interrupt bit */
+	compl_desc = ioat_get_ring_ent(ioat_chan, idx + i);
+	compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
+	hw = compl_desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	hw->ctl_f.compl_write = 1;
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	dump_desc_dbg(ioat_chan, compl_desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &compl_desc->txd;
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
+	       unsigned int src_cnt, size_t len, unsigned long flags)
+{
+	return __ioat_prep_xor_lock(chan, NULL, dest, src, src_cnt, len, flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_xor_val(struct dma_chan *chan, dma_addr_t *src,
+		    unsigned int src_cnt, size_t len,
+		    enum sum_check_flags *result, unsigned long flags)
+{
+	/* the cleanup routine only sets bits on validate failure, it
+	 * does not clear bits on validate success... so clear it here
+	 */
+	*result = 0;
+
+	return __ioat_prep_xor_lock(chan, result, src[0], &src[1],
+				     src_cnt - 1, len, flags);
+}
+
+static void
+dump_pq_desc_dbg(struct ioatdma_chan *ioat_chan, struct ioat_ring_ent *desc,
+		 struct ioat_ring_ent *ext)
+{
+	struct device *dev = to_dev(ioat_chan);
+	struct ioat_pq_descriptor *pq = desc->pq;
+	struct ioat_pq_ext_descriptor *pq_ex = ext ? ext->pq_ex : NULL;
+	struct ioat_raw_descriptor *descs[] = { (void *) pq, (void *) pq_ex };
+	int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
+	int i;
+
+	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
+		" sz: %#10.8x ctl: %#x (op: %#x int: %d compl: %d pq: '%s%s'"
+		" src_cnt: %d)\n",
+		desc_id(desc), (unsigned long long) desc->txd.phys,
+		(unsigned long long) (pq_ex ? pq_ex->next : pq->next),
+		desc->txd.flags, pq->size, pq->ctl, pq->ctl_f.op,
+		pq->ctl_f.int_en, pq->ctl_f.compl_write,
+		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
+		pq->ctl_f.src_cnt);
+	for (i = 0; i < src_cnt; i++)
+		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
+			(unsigned long long) pq_get_src(descs, i), pq->coef[i]);
+	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
+	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
+	dev_dbg(dev, "\tNEXT: %#llx\n", pq->next);
+}
+
+static void dump_pq16_desc_dbg(struct ioatdma_chan *ioat_chan,
+			       struct ioat_ring_ent *desc)
+{
+	struct device *dev = to_dev(ioat_chan);
+	struct ioat_pq_descriptor *pq = desc->pq;
+	struct ioat_raw_descriptor *descs[] = { (void *)pq,
+						(void *)pq,
+						(void *)pq };
+	int src_cnt = src16_cnt_to_sw(pq->ctl_f.src_cnt);
+	int i;
+
+	if (desc->sed) {
+		descs[1] = (void *)desc->sed->hw;
+		descs[2] = (void *)desc->sed->hw + 64;
+	}
+
+	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
+		" sz: %#x ctl: %#x (op: %#x int: %d compl: %d pq: '%s%s'"
+		" src_cnt: %d)\n",
+		desc_id(desc), (unsigned long long) desc->txd.phys,
+		(unsigned long long) pq->next,
+		desc->txd.flags, pq->size, pq->ctl,
+		pq->ctl_f.op, pq->ctl_f.int_en,
+		pq->ctl_f.compl_write,
+		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
+		pq->ctl_f.src_cnt);
+	for (i = 0; i < src_cnt; i++) {
+		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
+			(unsigned long long) pq16_get_src(descs, i),
+			pq->coef[i]);
+	}
+	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
+	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
+}
+
+static struct dma_async_tx_descriptor *
+__ioat_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
+		     const dma_addr_t *dst, const dma_addr_t *src,
+		     unsigned int src_cnt, const unsigned char *scf,
+		     size_t len, unsigned long flags)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct ioat_ring_ent *compl_desc;
+	struct ioat_ring_ent *desc;
+	struct ioat_ring_ent *ext;
+	size_t total_len = len;
+	struct ioat_pq_descriptor *pq;
+	struct ioat_pq_ext_descriptor *pq_ex = NULL;
+	struct ioat_dma_descriptor *hw;
+	u32 offset = 0;
+	u8 op = result ? IOAT_OP_PQ_VAL : IOAT_OP_PQ;
+	int i, s, idx, with_ext, num_descs;
+	int cb32 = (ioat_dma->version < IOAT_VER_3_3) ? 1 : 0;
+
+	dev_dbg(to_dev(ioat_chan), "%s\n", __func__);
+	/* the engine requires at least two sources (we provide
+	 * at least 1 implied source in the DMA_PREP_CONTINUE case)
+	 */
+	BUG_ON(src_cnt + dmaf_continue(flags) < 2);
+
+	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
+	/* we need 2x the number of descriptors to cover greater than 3
+	 * sources (we need 1 extra source in the q-only continuation
+	 * case and 3 extra sources in the p+q continuation case.
+	 */
+	if (src_cnt + dmaf_p_disabled_continue(flags) > 3 ||
+	    (dmaf_continue(flags) && !dmaf_p_disabled_continue(flags))) {
+		with_ext = 1;
+		num_descs *= 2;
+	} else
+		with_ext = 0;
+
+	/* completion writes from the raid engine may pass completion
+	 * writes from the legacy engine, so we need one extra null
+	 * (legacy) descriptor to ensure all completion writes arrive in
+	 * order.
+	 */
+	if (likely(num_descs) &&
+	    ioat_check_space_lock(ioat_chan, num_descs + cb32) == 0)
+		idx = ioat_chan->head;
+	else
+		return NULL;
+	i = 0;
+	do {
+		struct ioat_raw_descriptor *descs[2];
+		size_t xfer_size = min_t(size_t, len,
+					 1 << ioat_chan->xfercap_log);
+
+		desc = ioat_get_ring_ent(ioat_chan, idx + i);
+		pq = desc->pq;
+
+		/* save a branch by unconditionally retrieving the
+		 * extended descriptor pq_set_src() knows to not write
+		 * to it in the single descriptor case
+		 */
+		ext = ioat_get_ring_ent(ioat_chan, idx + i + with_ext);
+		pq_ex = ext->pq_ex;
+
+		descs[0] = (struct ioat_raw_descriptor *) pq;
+		descs[1] = (struct ioat_raw_descriptor *) pq_ex;
+
+		for (s = 0; s < src_cnt; s++)
+			pq_set_src(descs, src[s], offset, scf[s], s);
+
+		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
+		if (dmaf_p_disabled_continue(flags))
+			pq_set_src(descs, dst[1], offset, 1, s++);
+		else if (dmaf_continue(flags)) {
+			pq_set_src(descs, dst[0], offset, 0, s++);
+			pq_set_src(descs, dst[1], offset, 1, s++);
+			pq_set_src(descs, dst[1], offset, 0, s++);
+		}
+		pq->size = xfer_size;
+		pq->p_addr = dst[0] + offset;
+		pq->q_addr = dst[1] + offset;
+		pq->ctl = 0;
+		pq->ctl_f.op = op;
+		/* we turn on descriptor write back error status */
+		if (ioat_dma->cap & IOAT_CAP_DWBES)
+			pq->ctl_f.wb_en = result ? 1 : 0;
+		pq->ctl_f.src_cnt = src_cnt_to_hw(s);
+		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
+		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);
+
+		len -= xfer_size;
+		offset += xfer_size;
+	} while ((i += 1 + with_ext) < num_descs);
+
+	/* last pq descriptor carries the unmap parameters and fence bit */
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	if (result)
+		desc->result = result;
+	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	dump_pq_desc_dbg(ioat_chan, desc, ext);
+
+	if (!cb32) {
+		pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+		pq->ctl_f.compl_write = 1;
+		compl_desc = desc;
+	} else {
+		/* completion descriptor carries interrupt bit */
+		compl_desc = ioat_get_ring_ent(ioat_chan, idx + i);
+		compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
+		hw = compl_desc->hw;
+		hw->ctl = 0;
+		hw->ctl_f.null = 1;
+		hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+		hw->ctl_f.compl_write = 1;
+		hw->size = NULL_DESC_BUFFER_SIZE;
+		dump_desc_dbg(ioat_chan, compl_desc);
+	}
+
+
+	/* we leave the channel locked to ensure in order submission */
+	return &compl_desc->txd;
+}
+
+static struct dma_async_tx_descriptor *
+__ioat_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
+		       const dma_addr_t *dst, const dma_addr_t *src,
+		       unsigned int src_cnt, const unsigned char *scf,
+		       size_t len, unsigned long flags)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct ioat_ring_ent *desc;
+	size_t total_len = len;
+	struct ioat_pq_descriptor *pq;
+	u32 offset = 0;
+	u8 op;
+	int i, s, idx, num_descs;
+
+	/* this function is only called with 9-16 sources */
+	op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;
+
+	dev_dbg(to_dev(ioat_chan), "%s\n", __func__);
+
+	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
+
+	/*
+	 * 16 source pq is only available on cb3.3 and has no completion
+	 * write hw bug.
+	 */
+	if (num_descs && ioat_check_space_lock(ioat_chan, num_descs) == 0)
+		idx = ioat_chan->head;
+	else
+		return NULL;
+
+	i = 0;
+
+	do {
+		struct ioat_raw_descriptor *descs[4];
+		size_t xfer_size = min_t(size_t, len,
+					 1 << ioat_chan->xfercap_log);
+
+		desc = ioat_get_ring_ent(ioat_chan, idx + i);
+		pq = desc->pq;
+
+		descs[0] = (struct ioat_raw_descriptor *) pq;
+
+		desc->sed = ioat3_alloc_sed(ioat_dma, (src_cnt-2) >> 3);
+		if (!desc->sed) {
+			dev_err(to_dev(ioat_chan),
+				"%s: no free sed entries\n", __func__);
+			return NULL;
+		}
+
+		pq->sed_addr = desc->sed->dma;
+		desc->sed->parent = desc;
+
+		descs[1] = (struct ioat_raw_descriptor *)desc->sed->hw;
+		descs[2] = (void *)descs[1] + 64;
+
+		for (s = 0; s < src_cnt; s++)
+			pq16_set_src(descs, src[s], offset, scf[s], s);
+
+		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
+		if (dmaf_p_disabled_continue(flags))
+			pq16_set_src(descs, dst[1], offset, 1, s++);
+		else if (dmaf_continue(flags)) {
+			pq16_set_src(descs, dst[0], offset, 0, s++);
+			pq16_set_src(descs, dst[1], offset, 1, s++);
+			pq16_set_src(descs, dst[1], offset, 0, s++);
+		}
+
+		pq->size = xfer_size;
+		pq->p_addr = dst[0] + offset;
+		pq->q_addr = dst[1] + offset;
+		pq->ctl = 0;
+		pq->ctl_f.op = op;
+		pq->ctl_f.src_cnt = src16_cnt_to_hw(s);
+		/* we turn on descriptor write back error status */
+		if (ioat_dma->cap & IOAT_CAP_DWBES)
+			pq->ctl_f.wb_en = result ? 1 : 0;
+		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
+		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);
+
+		len -= xfer_size;
+		offset += xfer_size;
+	} while (++i < num_descs);
+
+	/* last pq descriptor carries the unmap parameters and fence bit */
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	if (result)
+		desc->result = result;
+	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+
+	/* with cb3.3 we should be able to do completion w/o a null desc */
+	pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	pq->ctl_f.compl_write = 1;
+
+	dump_pq16_desc_dbg(ioat_chan, desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &desc->txd;
+}
+
+static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
+{
+	if (dmaf_p_disabled_continue(flags))
+		return src_cnt + 1;
+	else if (dmaf_continue(flags))
+		return src_cnt + 3;
+	else
+		return src_cnt;
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
+	      unsigned int src_cnt, const unsigned char *scf, size_t len,
+	      unsigned long flags)
+{
+	/* specify valid address for disabled result */
+	if (flags & DMA_PREP_PQ_DISABLE_P)
+		dst[0] = dst[1];
+	if (flags & DMA_PREP_PQ_DISABLE_Q)
+		dst[1] = dst[0];
+
+	/* handle the single source multiply case from the raid6
+	 * recovery path
+	 */
+	if ((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1) {
+		dma_addr_t single_source[2];
+		unsigned char single_source_coef[2];
+
+		BUG_ON(flags & DMA_PREP_PQ_DISABLE_Q);
+		single_source[0] = src[0];
+		single_source[1] = src[0];
+		single_source_coef[0] = scf[0];
+		single_source_coef[1] = 0;
+
+		return src_cnt_flags(src_cnt, flags) > 8 ?
+			__ioat_prep_pq16_lock(chan, NULL, dst, single_source,
+					       2, single_source_coef, len,
+					       flags) :
+			__ioat_prep_pq_lock(chan, NULL, dst, single_source, 2,
+					     single_source_coef, len, flags);
+
+	} else {
+		return src_cnt_flags(src_cnt, flags) > 8 ?
+			__ioat_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
+					       scf, len, flags) :
+			__ioat_prep_pq_lock(chan, NULL, dst, src, src_cnt,
+					     scf, len, flags);
+	}
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
+		  unsigned int src_cnt, const unsigned char *scf, size_t len,
+		  enum sum_check_flags *pqres, unsigned long flags)
+{
+	/* specify valid address for disabled result */
+	if (flags & DMA_PREP_PQ_DISABLE_P)
+		pq[0] = pq[1];
+	if (flags & DMA_PREP_PQ_DISABLE_Q)
+		pq[1] = pq[0];
+
+	/* the cleanup routine only sets bits on validate failure, it
+	 * does not clear bits on validate success... so clear it here
+	 */
+	*pqres = 0;
+
+	return src_cnt_flags(src_cnt, flags) > 8 ?
+		__ioat_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
+				       flags) :
+		__ioat_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
+				     flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
+		 unsigned int src_cnt, size_t len, unsigned long flags)
+{
+	unsigned char scf[MAX_SCF];
+	dma_addr_t pq[2];
+
+	if (src_cnt > MAX_SCF)
+		return NULL;
+
+	memset(scf, 0, src_cnt);
+	pq[0] = dst;
+	flags |= DMA_PREP_PQ_DISABLE_Q;
+	pq[1] = dst; /* specify valid address for disabled result */
+
+	return src_cnt_flags(src_cnt, flags) > 8 ?
+		__ioat_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
+				       flags) :
+		__ioat_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
+				     flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
+		     unsigned int src_cnt, size_t len,
+		     enum sum_check_flags *result, unsigned long flags)
+{
+	unsigned char scf[MAX_SCF];
+	dma_addr_t pq[2];
+
+	if (src_cnt > MAX_SCF)
+		return NULL;
+
+	/* the cleanup routine only sets bits on validate failure, it
+	 * does not clear bits on validate success... so clear it here
+	 */
+	*result = 0;
+
+	memset(scf, 0, src_cnt);
+	pq[0] = src[0];
+	flags |= DMA_PREP_PQ_DISABLE_Q;
+	pq[1] = pq[0]; /* specify valid address for disabled result */
+
+	return src_cnt_flags(src_cnt, flags) > 8 ?
+		__ioat_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
+				       scf, len, flags) :
+		__ioat_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
+				     scf, len, flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat_prep_interrupt_lock(struct dma_chan *c, unsigned long flags)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioat_ring_ent *desc;
+	struct ioat_dma_descriptor *hw;
+
+	if (ioat_check_space_lock(ioat_chan, 1) == 0)
+		desc = ioat_get_ring_ent(ioat_chan, ioat_chan->head);
+	else
+		return NULL;
+
+	hw = desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = 1;
+	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	hw->ctl_f.compl_write = 1;
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	hw->src_addr = 0;
+	hw->dst_addr = 0;
+
+	desc->txd.flags = flags;
+	desc->len = 1;
+
+	dump_desc_dbg(ioat_chan, desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &desc->txd;
+}
+
diff --git a/drivers/dma/ioat/sysfs.c b/drivers/dma/ioat/sysfs.c
new file mode 100644
index 000000000000..cb4a857ee21b
--- /dev/null
+++ b/drivers/dma/ioat/sysfs.c
@@ -0,0 +1,135 @@
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2004 - 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/dmaengine.h>
+#include <linux/pci.h>
+#include "dma.h"
+#include "registers.h"
+#include "hw.h"
+
+#include "../dmaengine.h"
+
+static ssize_t cap_show(struct dma_chan *c, char *page)
+{
+	struct dma_device *dma = c->device;
+
+	return sprintf(page, "copy%s%s%s%s%s\n",
+		       dma_has_cap(DMA_PQ, dma->cap_mask) ? " pq" : "",
+		       dma_has_cap(DMA_PQ_VAL, dma->cap_mask) ? " pq_val" : "",
+		       dma_has_cap(DMA_XOR, dma->cap_mask) ? " xor" : "",
+		       dma_has_cap(DMA_XOR_VAL, dma->cap_mask) ? " xor_val" : "",
+		       dma_has_cap(DMA_INTERRUPT, dma->cap_mask) ? " intr" : "");
+
+}
+struct ioat_sysfs_entry ioat_cap_attr = __ATTR_RO(cap);
+
+static ssize_t version_show(struct dma_chan *c, char *page)
+{
+	struct dma_device *dma = c->device;
+	struct ioatdma_device *ioat_dma = to_ioatdma_device(dma);
+
+	return sprintf(page, "%d.%d\n",
+		       ioat_dma->version >> 4, ioat_dma->version & 0xf);
+}
+struct ioat_sysfs_entry ioat_version_attr = __ATTR_RO(version);
+
+static ssize_t
+ioat_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct ioat_sysfs_entry *entry;
+	struct ioatdma_chan *ioat_chan;
+
+	entry = container_of(attr, struct ioat_sysfs_entry, attr);
+	ioat_chan = container_of(kobj, struct ioatdma_chan, kobj);
+
+	if (!entry->show)
+		return -EIO;
+	return entry->show(&ioat_chan->dma_chan, page);
+}
+
+const struct sysfs_ops ioat_sysfs_ops = {
+	.show	= ioat_attr_show,
+};
+
+void ioat_kobject_add(struct ioatdma_device *ioat_dma, struct kobj_type *type)
+{
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	struct dma_chan *c;
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+		struct kobject *parent = &c->dev->device.kobj;
+		int err;
+
+		err = kobject_init_and_add(&ioat_chan->kobj, type,
+					   parent, "quickdata");
+		if (err) {
+			dev_warn(to_dev(ioat_chan),
+				 "sysfs init error (%d), continuing...\n", err);
+			kobject_put(&ioat_chan->kobj);
+			set_bit(IOAT_KOBJ_INIT_FAIL, &ioat_chan->state);
+		}
+	}
+}
+
+void ioat_kobject_del(struct ioatdma_device *ioat_dma)
+{
+	struct dma_device *dma = &ioat_dma->dma_dev;
+	struct dma_chan *c;
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+
+		if (!test_bit(IOAT_KOBJ_INIT_FAIL, &ioat_chan->state)) {
+			kobject_del(&ioat_chan->kobj);
+			kobject_put(&ioat_chan->kobj);
+		}
+	}
+}
+
+static ssize_t ring_size_show(struct dma_chan *c, char *page)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+
+	return sprintf(page, "%d\n", (1 << ioat_chan->alloc_order) & ~1);
+}
+static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size);
+
+static ssize_t ring_active_show(struct dma_chan *c, char *page)
+{
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+
+	/* ...taken outside the lock, no need to be precise */
+	return sprintf(page, "%d\n", ioat_ring_active(ioat_chan));
+}
+static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active);
+
+static struct attribute *ioat_attrs[] = {
+	&ring_size_attr.attr,
+	&ring_active_attr.attr,
+	&ioat_cap_attr.attr,
+	&ioat_version_attr.attr,
+	NULL,
+};
+
+struct kobj_type ioat_ktype = {
+	.sysfs_ops = &ioat_sysfs_ops,
+	.default_attrs = ioat_attrs,
+};
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 998826854fdd..e4f43125e0fb 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1300,10 +1300,11 @@ static int iop_adma_probe(struct platform_device *pdev)
 	 * note: writecombine gives slightly better performance, but
 	 * requires that we explicitly flush the writes
 	 */
-	if ((adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
-					plat_data->pool_size,
-					&adev->dma_desc_pool,
-					GFP_KERNEL)) == NULL) {
+	adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
+							  plat_data->pool_size,
+							  &adev->dma_desc_pool,
+							  GFP_KERNEL);
+	if (!adev->dma_desc_pool_virt) {
 		ret = -ENOMEM;
 		goto err_free_adev;
 	}
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 2e284a4438bc..4768a829253a 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -265,10 +265,10 @@ int ipu_irq_unmap(unsigned int source)
 	return ret;
 }
 
-/* Chained IRQ handler for IPU error interrupt */
-static void ipu_irq_err(unsigned int irq, struct irq_desc *desc)
+/* Chained IRQ handler for IPU function and error interrupt */
+static void ipu_irq_handler(unsigned int __irq, struct irq_desc *desc)
 {
-	struct ipu *ipu = irq_get_handler_data(irq);
+	struct ipu *ipu = irq_desc_get_handler_data(desc);
 	u32 status;
 	int i, line;
 
@@ -286,43 +286,7 @@ static void ipu_irq_err(unsigned int irq, struct irq_desc *desc)
 		raw_spin_unlock(&bank_lock);
 		while ((line = ffs(status))) {
 			struct ipu_irq_map *map;
-
-			line--;
-			status &= ~(1UL << line);
-
-			raw_spin_lock(&bank_lock);
-			map = src2map(32 * i + line);
-			if (map)
-				irq = map->irq;
-			raw_spin_unlock(&bank_lock);
-
-			if (!map) {
-				pr_err("IPU: Interrupt on unmapped source %u bank %d\n",
-				       line, i);
-				continue;
-			}
-			generic_handle_irq(irq);
-		}
-	}
-}
-
-/* Chained IRQ handler for IPU function interrupt */
-static void ipu_irq_fn(unsigned int irq, struct irq_desc *desc)
-{
-	struct ipu *ipu = irq_desc_get_handler_data(desc);
-	u32 status;
-	int i, line;
-
-	for (i = 0; i < IPU_IRQ_NR_FN_BANKS; i++) {
-		struct ipu_irq_bank *bank = irq_bank + i;
-
-		raw_spin_lock(&bank_lock);
-		status = ipu_read_reg(ipu, bank->status);
-		/* Not clearing all interrupts, see above */
-		status &= ipu_read_reg(ipu, bank->control);
-		raw_spin_unlock(&bank_lock);
-		while ((line = ffs(status))) {
-			struct ipu_irq_map *map;
+			unsigned int irq = NO_IRQ;
 
 			line--;
 			status &= ~(1UL << line);
@@ -377,16 +341,12 @@ int __init ipu_irq_attach_irq(struct ipu *ipu, struct platform_device *dev)
 		irq_map[i].irq = irq;
 		irq_map[i].source = -EINVAL;
 		irq_set_handler(irq, handle_level_irq);
-#ifdef CONFIG_ARM
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
-#endif
+		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
-	irq_set_handler_data(ipu->irq_fn, ipu);
-	irq_set_chained_handler(ipu->irq_fn, ipu_irq_fn);
+	irq_set_chained_handler_and_data(ipu->irq_fn, ipu_irq_handler, ipu);
 
-	irq_set_handler_data(ipu->irq_err, ipu);
-	irq_set_chained_handler(ipu->irq_err, ipu_irq_err);
+	irq_set_chained_handler_and_data(ipu->irq_err, ipu_irq_handler, ipu);
 
 	ipu->irq_base = irq_base;
 
@@ -399,16 +359,12 @@ void ipu_irq_detach_irq(struct ipu *ipu, struct platform_device *dev)
 
 	irq_base = ipu->irq_base;
 
-	irq_set_chained_handler(ipu->irq_fn, NULL);
-	irq_set_handler_data(ipu->irq_fn, NULL);
+	irq_set_chained_handler_and_data(ipu->irq_fn, NULL, NULL);
 
-	irq_set_chained_handler(ipu->irq_err, NULL);
-	irq_set_handler_data(ipu->irq_err, NULL);
+	irq_set_chained_handler_and_data(ipu->irq_err, NULL, NULL);
 
 	for (irq = irq_base; irq < irq_base + CONFIG_MX3_IPU_IRQS; irq++) {
-#ifdef CONFIG_ARM
-		set_irq_flags(irq, 0);
-#endif
+		irq_set_status_flags(irq, IRQ_NOREQUEST);
 		irq_set_chip(irq, NULL);
 		irq_set_chip_data(irq, NULL);
 	}
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 647e362f01fd..1ba2fd73852d 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -24,7 +24,6 @@
 #include "virt-dma.h"
 
 #define DRIVER_NAME		"k3-dma"
-#define DMA_ALIGN		3
 #define DMA_MAX_SIZE		0x1ffc
 
 #define INT_STAT		0x00
@@ -732,7 +731,7 @@ static int k3_dma_probe(struct platform_device *op)
 	d->slave.device_pause = k3_dma_transfer_pause;
 	d->slave.device_resume = k3_dma_transfer_resume;
 	d->slave.device_terminate_all = k3_dma_terminate_all;
-	d->slave.copy_align = DMA_ALIGN;
+	d->slave.copy_align = DMAENGINE_ALIGN_8_BYTES;
 
 	/* init virtual channel */
 	d->chans = devm_kzalloc(&op->dev,
diff --git a/drivers/dma/lpc18xx-dmamux.c b/drivers/dma/lpc18xx-dmamux.c
new file mode 100644
index 000000000000..761f32687055
--- /dev/null
+++ b/drivers/dma/lpc18xx-dmamux.c
@@ -0,0 +1,183 @@
+/*
+ * DMA Router driver for LPC18xx/43xx DMA MUX
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * Based on TI DMA Crossbar driver by:
+ *   Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com
+ *   Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/regmap.h>
+#include <linux/spinlock.h>
+
+/* CREG register offset and macros for mux manipulation */
+#define LPC18XX_CREG_DMAMUX		0x11c
+#define LPC18XX_DMAMUX_VAL(v, n)	((v) << (n * 2))
+#define LPC18XX_DMAMUX_MASK(n)		(0x3 << (n * 2))
+#define LPC18XX_DMAMUX_MAX_VAL		0x3
+
+struct lpc18xx_dmamux {
+	u32 value;
+	bool busy;
+};
+
+struct lpc18xx_dmamux_data {
+	struct dma_router dmarouter;
+	struct lpc18xx_dmamux *muxes;
+	u32 dma_master_requests;
+	u32 dma_mux_requests;
+	struct regmap *reg;
+	spinlock_t lock;
+};
+
+static void lpc18xx_dmamux_free(struct device *dev, void *route_data)
+{
+	struct lpc18xx_dmamux_data *dmamux = dev_get_drvdata(dev);
+	struct lpc18xx_dmamux *mux = route_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dmamux->lock, flags);
+	mux->busy = false;
+	spin_unlock_irqrestore(&dmamux->lock, flags);
+}
+
+static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec,
+				    struct of_dma *ofdma)
+{
+	struct platform_device *pdev = of_find_device_by_node(ofdma->of_node);
+	struct lpc18xx_dmamux_data *dmamux = platform_get_drvdata(pdev);
+	unsigned long flags;
+	unsigned mux;
+
+	if (dma_spec->args_count != 3) {
+		dev_err(&pdev->dev, "invalid number of dma mux args\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	mux = dma_spec->args[0];
+	if (mux >= dmamux->dma_master_requests) {
+		dev_err(&pdev->dev, "invalid mux number: %d\n",
+			dma_spec->args[0]);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (dma_spec->args[1] > LPC18XX_DMAMUX_MAX_VAL) {
+		dev_err(&pdev->dev, "invalid dma mux value: %d\n",
+			dma_spec->args[1]);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* The of_node_put() will be done in the core for the node */
+	dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0);
+	if (!dma_spec->np) {
+		dev_err(&pdev->dev, "can't get dma master\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	spin_lock_irqsave(&dmamux->lock, flags);
+	if (dmamux->muxes[mux].busy) {
+		spin_unlock_irqrestore(&dmamux->lock, flags);
+		dev_err(&pdev->dev, "dma request %u busy with %u.%u\n",
+			mux, mux, dmamux->muxes[mux].value);
+		of_node_put(dma_spec->np);
+		return ERR_PTR(-EBUSY);
+	}
+
+	dmamux->muxes[mux].busy = true;
+	dmamux->muxes[mux].value = dma_spec->args[1];
+
+	regmap_update_bits(dmamux->reg, LPC18XX_CREG_DMAMUX,
+			   LPC18XX_DMAMUX_MASK(mux),
+			   LPC18XX_DMAMUX_VAL(dmamux->muxes[mux].value, mux));
+	spin_unlock_irqrestore(&dmamux->lock, flags);
+
+	dma_spec->args[1] = dma_spec->args[2];
+	dma_spec->args_count = 2;
+
+	dev_dbg(&pdev->dev, "mapping dmamux %u.%u to dma request %u\n", mux,
+		dmamux->muxes[mux].value, mux);
+
+	return &dmamux->muxes[mux];
+}
+
+static int lpc18xx_dmamux_probe(struct platform_device *pdev)
+{
+	struct device_node *dma_np, *np = pdev->dev.of_node;
+	struct lpc18xx_dmamux_data *dmamux;
+	int ret;
+
+	dmamux = devm_kzalloc(&pdev->dev, sizeof(*dmamux), GFP_KERNEL);
+	if (!dmamux)
+		return -ENOMEM;
+
+	dmamux->reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg");
+	if (IS_ERR(dmamux->reg)) {
+		dev_err(&pdev->dev, "syscon lookup failed\n");
+		return PTR_ERR(dmamux->reg);
+	}
+
+	ret = of_property_read_u32(np, "dma-requests",
+				   &dmamux->dma_mux_requests);
+	if (ret) {
+		dev_err(&pdev->dev, "missing dma-requests property\n");
+		return ret;
+	}
+
+	dma_np = of_parse_phandle(np, "dma-masters", 0);
+	if (!dma_np) {
+		dev_err(&pdev->dev, "can't get dma master\n");
+		return -ENODEV;
+	}
+
+	ret = of_property_read_u32(dma_np, "dma-requests",
+				   &dmamux->dma_master_requests);
+	of_node_put(dma_np);
+	if (ret) {
+		dev_err(&pdev->dev, "missing master dma-requests property\n");
+		return ret;
+	}
+
+	dmamux->muxes = devm_kcalloc(&pdev->dev, dmamux->dma_master_requests,
+				     sizeof(struct lpc18xx_dmamux),
+				     GFP_KERNEL);
+	if (!dmamux->muxes)
+		return -ENOMEM;
+
+	spin_lock_init(&dmamux->lock);
+	platform_set_drvdata(pdev, dmamux);
+	dmamux->dmarouter.dev = &pdev->dev;
+	dmamux->dmarouter.route_free = lpc18xx_dmamux_free;
+
+	return of_dma_router_register(np, lpc18xx_dmamux_reserve,
+				      &dmamux->dmarouter);
+}
+
+static const struct of_device_id lpc18xx_dmamux_match[] = {
+	{ .compatible = "nxp,lpc1850-dmamux" },
+	{},
+};
+
+static struct platform_driver lpc18xx_dmamux_driver = {
+	.probe	= lpc18xx_dmamux_probe,
+	.driver = {
+		.name = "lpc18xx-dmamux",
+		.of_match_table = lpc18xx_dmamux_match,
+	},
+};
+
+static int __init lpc18xx_dmamux_init(void)
+{
+	return platform_driver_register(&lpc18xx_dmamux_driver);
+}
+arch_initcall(lpc18xx_dmamux_init);
diff --git a/drivers/dma/mic_x100_dma.h b/drivers/dma/mic_x100_dma.h
index f663b0bdd11d..d89982034e68 100644
--- a/drivers/dma/mic_x100_dma.h
+++ b/drivers/dma/mic_x100_dma.h
@@ -39,7 +39,7 @@
  */
 #define MIC_DMA_MAX_NUM_CHAN	8
 #define MIC_DMA_NUM_CHAN	4
-#define MIC_DMA_ALIGN_SHIFT	6
+#define MIC_DMA_ALIGN_SHIFT	DMAENGINE_ALIGN_64_BYTES
 #define MIC_DMA_ALIGN_BYTES	(1 << MIC_DMA_ALIGN_SHIFT)
 #define MIC_DMA_DESC_RX_SIZE	(128 * 1024 - 4)
 
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index 462a0229a743..e39457f13d4d 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -72,7 +72,6 @@
 #define DCMD_WIDTH4	(3 << 14)	/* 4 byte width (Word) */
 #define DCMD_LENGTH	0x01fff		/* length mask (max = 8K - 1) */
 
-#define PDMA_ALIGNMENT		3
 #define PDMA_MAX_DESC_BYTES	DCMD_LENGTH
 
 struct mmp_pdma_desc_hw {
@@ -1071,7 +1070,7 @@ static int mmp_pdma_probe(struct platform_device *op)
 	pdev->device.device_issue_pending = mmp_pdma_issue_pending;
 	pdev->device.device_config = mmp_pdma_config;
 	pdev->device.device_terminate_all = mmp_pdma_terminate_all;
-	pdev->device.copy_align = PDMA_ALIGNMENT;
+	pdev->device.copy_align = DMAENGINE_ALIGN_8_BYTES;
 	pdev->device.src_addr_widths = widths;
 	pdev->device.dst_addr_widths = widths;
 	pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index e683761e0f8f..3df0422607d5 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -100,7 +100,6 @@ enum mmp_tdma_type {
 	PXA910_SQU,
 };
 
-#define TDMA_ALIGNMENT		3
 #define TDMA_MAX_XFER_BYTES    SZ_64K
 
 struct mmp_tdma_chan {
@@ -695,7 +694,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	tdev->device.device_pause = mmp_tdma_pause_chan;
 	tdev->device.device_resume = mmp_tdma_resume_chan;
 	tdev->device.device_terminate_all = mmp_tdma_terminate_all;
-	tdev->device.copy_align = TDMA_ALIGNMENT;
+	tdev->device.copy_align = DMAENGINE_ALIGN_8_BYTES;
 
 	dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
 	platform_set_drvdata(pdev, tdev);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index fbaf1ead2597..1c2de9a834a9 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -13,7 +13,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
@@ -26,6 +25,7 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/irqdomain.h>
+#include <linux/cpumask.h>
 #include <linux/platform_data/dma-mv_xor.h>
 
 #include "dmaengine.h"
@@ -162,10 +162,11 @@ static void mv_chan_set_mode(struct mv_xor_chan *chan,
 	config &= ~0x7;
 	config |= op_mode;
 
-	if (IS_ENABLED(__BIG_ENDIAN))
-		config |= XOR_DESCRIPTOR_SWAP;
-	else
-		config &= ~XOR_DESCRIPTOR_SWAP;
+#if defined(__BIG_ENDIAN)
+	config |= XOR_DESCRIPTOR_SWAP;
+#else
+	config &= ~XOR_DESCRIPTOR_SWAP;
+#endif
 
 	writel_relaxed(config, XOR_CONFIG(chan));
 	chan->current_type = type;
@@ -1125,7 +1126,8 @@ static const struct of_device_id mv_xor_dt_ids[] = {
 	{ .compatible = "marvell,armada-380-xor", .data = (void *)XOR_MODE_IN_DESC },
 	{},
 };
-MODULE_DEVICE_TABLE(of, mv_xor_dt_ids);
+
+static unsigned int mv_xor_engine_count;
 
 static int mv_xor_probe(struct platform_device *pdev)
 {
@@ -1133,6 +1135,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 	struct mv_xor_device *xordev;
 	struct mv_xor_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct resource *res;
+	unsigned int max_engines, max_channels;
 	int i, ret;
 	int op_in_desc;
 
@@ -1176,6 +1179,21 @@ static int mv_xor_probe(struct platform_device *pdev)
 	if (!IS_ERR(xordev->clk))
 		clk_prepare_enable(xordev->clk);
 
+	/*
+	 * We don't want to have more than one channel per CPU in
+	 * order for async_tx to perform well. So we limit the number
+	 * of engines and channels so that we take into account this
+	 * constraint. Note that we also want to use channels from
+	 * separate engines when possible.
+	 */
+	max_engines = num_present_cpus();
+	max_channels = min_t(unsigned int,
+			     MV_XOR_MAX_CHANNELS,
+			     DIV_ROUND_UP(num_present_cpus(), 2));
+
+	if (mv_xor_engine_count >= max_engines)
+		return 0;
+
 	if (pdev->dev.of_node) {
 		struct device_node *np;
 		int i = 0;
@@ -1189,13 +1207,13 @@ static int mv_xor_probe(struct platform_device *pdev)
 			int irq;
 			op_in_desc = (int)of_id->data;
 
+			if (i >= max_channels)
+				continue;
+
 			dma_cap_zero(cap_mask);
-			if (of_property_read_bool(np, "dmacap,memcpy"))
-				dma_cap_set(DMA_MEMCPY, cap_mask);
-			if (of_property_read_bool(np, "dmacap,xor"))
-				dma_cap_set(DMA_XOR, cap_mask);
-			if (of_property_read_bool(np, "dmacap,interrupt"))
-				dma_cap_set(DMA_INTERRUPT, cap_mask);
+			dma_cap_set(DMA_MEMCPY, cap_mask);
+			dma_cap_set(DMA_XOR, cap_mask);
+			dma_cap_set(DMA_INTERRUPT, cap_mask);
 
 			irq = irq_of_parse_and_map(np, 0);
 			if (!irq) {
@@ -1215,7 +1233,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 			i++;
 		}
 	} else if (pdata && pdata->channels) {
-		for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		for (i = 0; i < max_channels; i++) {
 			struct mv_xor_channel_data *cd;
 			struct mv_xor_chan *chan;
 			int irq;
@@ -1262,27 +1280,8 @@ err_channel_add:
 	return ret;
 }
 
-static int mv_xor_remove(struct platform_device *pdev)
-{
-	struct mv_xor_device *xordev = platform_get_drvdata(pdev);
-	int i;
-
-	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
-		if (xordev->channels[i])
-			mv_xor_channel_remove(xordev->channels[i]);
-	}
-
-	if (!IS_ERR(xordev->clk)) {
-		clk_disable_unprepare(xordev->clk);
-		clk_put(xordev->clk);
-	}
-
-	return 0;
-}
-
 static struct platform_driver mv_xor_driver = {
 	.probe		= mv_xor_probe,
-	.remove		= mv_xor_remove,
 	.driver		= {
 		.name	        = MV_XOR_NAME,
 		.of_match_table = of_match_ptr(mv_xor_dt_ids),
@@ -1294,19 +1293,10 @@ static int __init mv_xor_init(void)
 {
 	return platform_driver_register(&mv_xor_driver);
 }
-module_init(mv_xor_init);
-
-/* it's currently unsafe to unload this module */
-#if 0
-static void __exit mv_xor_exit(void)
-{
-	platform_driver_unregister(&mv_xor_driver);
-	return;
-}
-
-module_exit(mv_xor_exit);
-#endif
+device_initcall(mv_xor_init);
 
+/*
 MODULE_AUTHOR("Saeed Bishara <saeed@marvell.com>");
 MODULE_DESCRIPTION("DMA engine driver for Marvell's XOR engine");
 MODULE_LICENSE("GPL");
+*/
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index b859792dde95..113605f6fe20 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/dmaengine.h>
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index f513f77b1d85..17ee758b419f 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1198,6 +1198,9 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	unsigned lcnt0, lcnt1, ljmp0, ljmp1;
 	struct _arg_LPEND lpend;
 
+	if (*bursts == 1)
+		return _bursts(dry_run, buf, pxs, 1);
+
 	/* Max iterations possible in DMALP is 256 */
 	if (*bursts >= 256*256) {
 		lcnt1 = 256;
@@ -2328,7 +2331,7 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx)
 			desc->txd.callback = last->txd.callback;
 			desc->txd.callback_param = last->txd.callback_param;
 		}
-		last->last = false;
+		desc->last = false;
 
 		dma_cookie_assign(&desc->txd);
 
@@ -2623,6 +2626,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 		desc->rqcfg.brst_len = 1;
 
 	desc->rqcfg.brst_len = get_burst_len(desc, len);
+	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
 
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index ddcbbf5cd9e9..5cb61ce01036 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -184,19 +184,18 @@ static unsigned int pxad_drcmr(unsigned int line)
 
 static int dbg_show_requester_chan(struct seq_file *s, void *p)
 {
-	int pos = 0;
 	struct pxad_phy *phy = s->private;
 	int i;
 	u32 drcmr;
 
-	pos += seq_printf(s, "DMA channel %d requester :\n", phy->idx);
+	seq_printf(s, "DMA channel %d requester :\n", phy->idx);
 	for (i = 0; i < 70; i++) {
 		drcmr = readl_relaxed(phy->base + pxad_drcmr(i));
 		if ((drcmr & DRCMR_CHLNUM) == phy->idx)
-			pos += seq_printf(s, "\tRequester %d (MAPVLD=%d)\n", i,
-					  !!(drcmr & DRCMR_MAPVLD));
+			seq_printf(s, "\tRequester %d (MAPVLD=%d)\n", i,
+				   !!(drcmr & DRCMR_MAPVLD));
 	}
-	return pos;
+	return 0;
 }
 
 static inline int dbg_burst_from_dcmd(u32 dcmd)
@@ -906,21 +905,21 @@ static void pxad_get_config(struct pxad_chan *chan,
 	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
 
 	*dcmd = 0;
-	if (chan->cfg.direction == DMA_DEV_TO_MEM) {
+	if (dir == DMA_DEV_TO_MEM) {
 		maxburst = chan->cfg.src_maxburst;
 		width = chan->cfg.src_addr_width;
 		dev_addr = chan->cfg.src_addr;
 		*dev_src = dev_addr;
 		*dcmd |= PXA_DCMD_INCTRGADDR | PXA_DCMD_FLOWSRC;
 	}
-	if (chan->cfg.direction == DMA_MEM_TO_DEV) {
+	if (dir == DMA_MEM_TO_DEV) {
 		maxburst = chan->cfg.dst_maxburst;
 		width = chan->cfg.dst_addr_width;
 		dev_addr = chan->cfg.dst_addr;
 		*dev_dst = dev_addr;
 		*dcmd |= PXA_DCMD_INCSRCADDR | PXA_DCMD_FLOWTRG;
 	}
-	if (chan->cfg.direction == DMA_MEM_TO_MEM)
+	if (dir == DMA_MEM_TO_MEM)
 		*dcmd |= PXA_DCMD_BURST32 | PXA_DCMD_INCTRGADDR |
 			PXA_DCMD_INCSRCADDR;
 
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index 0f371524a4d9..9fda65af841e 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -39,18 +39,6 @@ config SH_DMAE_R8A73A4
 
 endif
 
-config SUDMAC
-	tristate "Renesas SUDMAC support"
-	depends on SH_DMAE_BASE
-	help
-	  Enable support for the Renesas SUDMAC controllers.
-
-config RCAR_HPB_DMAE
-	tristate "Renesas R-Car HPB DMAC support"
-	depends on SH_DMAE_BASE
-	help
-	  Enable support for the Renesas R-Car series DMA controllers.
-
 config RCAR_DMAC
 	tristate "Renesas R-Car Gen2 DMA Controller"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
@@ -59,6 +47,12 @@ config RCAR_DMAC
 	  This driver supports the general purpose DMA controller found in the
 	  Renesas R-Car second generation SoCs.
 
+config RCAR_HPB_DMAE
+	tristate "Renesas R-Car HPB DMAC support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas R-Car series DMA controllers.
+
 config RENESAS_USB_DMAC
 	tristate "Renesas USB-DMA Controller"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
@@ -67,3 +61,9 @@ config RENESAS_USB_DMAC
 	help
 	  This driver supports the USB-DMA controller found in the Renesas
 	  SoCs.
+
+config SUDMAC
+	tristate "Renesas SUDMAC support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas SUDMAC controllers.
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index b8a598066ce2..0133e4658196 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -13,7 +13,7 @@ shdma-$(CONFIG_SH_DMAE_R8A73A4) += shdma-r8a73a4.o
 shdma-objs := $(shdma-y)
 obj-$(CONFIG_SH_DMAE) += shdma.o
 
-obj-$(CONFIG_SUDMAC) += sudmac.o
-obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
 obj-$(CONFIG_RCAR_DMAC) += rcar-dmac.o
+obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
 obj-$(CONFIG_RENESAS_USB_DMAC) += usb-dmac.o
+obj-$(CONFIG_SUDMAC) += sudmac.o
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 8c5186cc9f63..7d5598d874e1 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -455,6 +455,7 @@ static int sirfsoc_dma_terminate_all(struct dma_chan *chan)
 	switch (sdma->type) {
 	case SIRFSOC_DMA_VER_A7V1:
 		writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_INT_EN_CLR);
+		writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_CH_INT);
 		writel_relaxed((1 << cid) | 1 << (cid + 16),
 			       sdma->base +
 			       SIRFSOC_DMA_CH_LOOP_CTRL_CLR_ATLAS7);
@@ -462,6 +463,8 @@ static int sirfsoc_dma_terminate_all(struct dma_chan *chan)
 		break;
 	case SIRFSOC_DMA_VER_A7V2:
 		writel_relaxed(0, sdma->base + SIRFSOC_DMA_INT_EN_ATLAS7);
+		writel_relaxed(SIRFSOC_DMA_INT_ALL_ATLAS7,
+			       sdma->base + SIRFSOC_DMA_INT_ATLAS7);
 		writel_relaxed(0, sdma->base + SIRFSOC_DMA_LOOP_CTRL_ATLAS7);
 		writel_relaxed(0, sdma->base + SIRFSOC_DMA_VALID_ATLAS7);
 		break;
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 3c10f034d4b9..750d1b313684 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -2853,7 +2853,7 @@ static void d40_ops_init(struct d40_base *base, struct dma_device *dev)
 		 * This controller can only access address at even
 		 * 32bit boundaries, i.e. 2^2
 		 */
-		dev->copy_align = 2;
+		dev->copy_align = DMAENGINE_ALIGN_4_BYTES;
 	}
 
 	if (dma_has_cap(DMA_SG, dev->cap_mask))
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
new file mode 100644
index 000000000000..a1a500d96ff2
--- /dev/null
+++ b/drivers/dma/sun4i-dma.c
@@ -0,0 +1,1288 @@
+/*
+ * Copyright (C) 2014 Emilio López
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "virt-dma.h"
+
+/** Common macros to normal and dedicated DMA registers **/
+
+#define SUN4I_DMA_CFG_LOADING			BIT(31)
+#define SUN4I_DMA_CFG_DST_DATA_WIDTH(width)	((width) << 25)
+#define SUN4I_DMA_CFG_DST_BURST_LENGTH(len)	((len) << 23)
+#define SUN4I_DMA_CFG_DST_ADDR_MODE(mode)	((mode) << 21)
+#define SUN4I_DMA_CFG_DST_DRQ_TYPE(type)	((type) << 16)
+#define SUN4I_DMA_CFG_SRC_DATA_WIDTH(width)	((width) << 9)
+#define SUN4I_DMA_CFG_SRC_BURST_LENGTH(len)	((len) << 7)
+#define SUN4I_DMA_CFG_SRC_ADDR_MODE(mode)	((mode) << 5)
+#define SUN4I_DMA_CFG_SRC_DRQ_TYPE(type)	(type)
+
+/** Normal DMA register values **/
+
+/* Normal DMA source/destination data request type values */
+#define SUN4I_NDMA_DRQ_TYPE_SDRAM		0x16
+#define SUN4I_NDMA_DRQ_TYPE_LIMIT		(0x1F + 1)
+
+/** Normal DMA register layout **/
+
+/* Dedicated DMA source/destination address mode values */
+#define SUN4I_NDMA_ADDR_MODE_LINEAR		0
+#define SUN4I_NDMA_ADDR_MODE_IO			1
+
+/* Normal DMA configuration register layout */
+#define SUN4I_NDMA_CFG_CONT_MODE		BIT(30)
+#define SUN4I_NDMA_CFG_WAIT_STATE(n)		((n) << 27)
+#define SUN4I_NDMA_CFG_DST_NON_SECURE		BIT(22)
+#define SUN4I_NDMA_CFG_BYTE_COUNT_MODE_REMAIN	BIT(15)
+#define SUN4I_NDMA_CFG_SRC_NON_SECURE		BIT(6)
+
+/** Dedicated DMA register values **/
+
+/* Dedicated DMA source/destination address mode values */
+#define SUN4I_DDMA_ADDR_MODE_LINEAR		0
+#define SUN4I_DDMA_ADDR_MODE_IO			1
+#define SUN4I_DDMA_ADDR_MODE_HORIZONTAL_PAGE	2
+#define SUN4I_DDMA_ADDR_MODE_VERTICAL_PAGE	3
+
+/* Dedicated DMA source/destination data request type values */
+#define SUN4I_DDMA_DRQ_TYPE_SDRAM		0x1
+#define SUN4I_DDMA_DRQ_TYPE_LIMIT		(0x1F + 1)
+
+/** Dedicated DMA register layout **/
+
+/* Dedicated DMA configuration register layout */
+#define SUN4I_DDMA_CFG_BUSY			BIT(30)
+#define SUN4I_DDMA_CFG_CONT_MODE		BIT(29)
+#define SUN4I_DDMA_CFG_DST_NON_SECURE		BIT(28)
+#define SUN4I_DDMA_CFG_BYTE_COUNT_MODE_REMAIN	BIT(15)
+#define SUN4I_DDMA_CFG_SRC_NON_SECURE		BIT(12)
+
+/* Dedicated DMA parameter register layout */
+#define SUN4I_DDMA_PARA_DST_DATA_BLK_SIZE(n)	(((n) - 1) << 24)
+#define SUN4I_DDMA_PARA_DST_WAIT_CYCLES(n)	(((n) - 1) << 16)
+#define SUN4I_DDMA_PARA_SRC_DATA_BLK_SIZE(n)	(((n) - 1) << 8)
+#define SUN4I_DDMA_PARA_SRC_WAIT_CYCLES(n)	(((n) - 1) << 0)
+
+/** DMA register offsets **/
+
+/* General register offsets */
+#define SUN4I_DMA_IRQ_ENABLE_REG		0x0
+#define SUN4I_DMA_IRQ_PENDING_STATUS_REG	0x4
+
+/* Normal DMA register offsets */
+#define SUN4I_NDMA_CHANNEL_REG_BASE(n)		(0x100 + (n) * 0x20)
+#define SUN4I_NDMA_CFG_REG			0x0
+#define SUN4I_NDMA_SRC_ADDR_REG			0x4
+#define SUN4I_NDMA_DST_ADDR_REG		0x8
+#define SUN4I_NDMA_BYTE_COUNT_REG		0xC
+
+/* Dedicated DMA register offsets */
+#define SUN4I_DDMA_CHANNEL_REG_BASE(n)		(0x300 + (n) * 0x20)
+#define SUN4I_DDMA_CFG_REG			0x0
+#define SUN4I_DDMA_SRC_ADDR_REG			0x4
+#define SUN4I_DDMA_DST_ADDR_REG		0x8
+#define SUN4I_DDMA_BYTE_COUNT_REG		0xC
+#define SUN4I_DDMA_PARA_REG			0x18
+
+/** DMA Driver **/
+
+/*
+ * Normal DMA has 8 channels, and Dedicated DMA has another 8, so
+ * that's 16 channels. As for endpoints, there's 29 and 21
+ * respectively. Given that the Normal DMA endpoints (other than
+ * SDRAM) can be used as tx/rx, we need 78 vchans in total
+ */
+#define SUN4I_NDMA_NR_MAX_CHANNELS	8
+#define SUN4I_DDMA_NR_MAX_CHANNELS	8
+#define SUN4I_DMA_NR_MAX_CHANNELS					\
+	(SUN4I_NDMA_NR_MAX_CHANNELS + SUN4I_DDMA_NR_MAX_CHANNELS)
+#define SUN4I_NDMA_NR_MAX_VCHANS	(29 * 2 - 1)
+#define SUN4I_DDMA_NR_MAX_VCHANS	21
+#define SUN4I_DMA_NR_MAX_VCHANS						\
+	(SUN4I_NDMA_NR_MAX_VCHANS + SUN4I_DDMA_NR_MAX_VCHANS)
+
+/* This set of SUN4I_DDMA timing parameters were found experimentally while
+ * working with the SPI driver and seem to make it behave correctly */
+#define SUN4I_DDMA_MAGIC_SPI_PARAMETERS \
+	(SUN4I_DDMA_PARA_DST_DATA_BLK_SIZE(1) |			\
+	 SUN4I_DDMA_PARA_SRC_DATA_BLK_SIZE(1) |				\
+	 SUN4I_DDMA_PARA_DST_WAIT_CYCLES(2) |				\
+	 SUN4I_DDMA_PARA_SRC_WAIT_CYCLES(2))
+
+struct sun4i_dma_pchan {
+	/* Register base of channel */
+	void __iomem			*base;
+	/* vchan currently being serviced */
+	struct sun4i_dma_vchan		*vchan;
+	/* Is this a dedicated pchan? */
+	int				is_dedicated;
+};
+
+struct sun4i_dma_vchan {
+	struct virt_dma_chan		vc;
+	struct dma_slave_config		cfg;
+	struct sun4i_dma_pchan		*pchan;
+	struct sun4i_dma_promise	*processing;
+	struct sun4i_dma_contract	*contract;
+	u8				endpoint;
+	int				is_dedicated;
+};
+
+struct sun4i_dma_promise {
+	u32				cfg;
+	u32				para;
+	dma_addr_t			src;
+	dma_addr_t			dst;
+	size_t				len;
+	struct list_head		list;
+};
+
+/* A contract is a set of promises */
+struct sun4i_dma_contract {
+	struct virt_dma_desc		vd;
+	struct list_head		demands;
+	struct list_head		completed_demands;
+	int				is_cyclic;
+};
+
+struct sun4i_dma_dev {
+	DECLARE_BITMAP(pchans_used, SUN4I_DMA_NR_MAX_CHANNELS);
+	struct dma_device		slave;
+	struct sun4i_dma_pchan		*pchans;
+	struct sun4i_dma_vchan		*vchans;
+	void __iomem			*base;
+	struct clk			*clk;
+	int				irq;
+	spinlock_t			lock;
+};
+
+static struct sun4i_dma_dev *to_sun4i_dma_dev(struct dma_device *dev)
+{
+	return container_of(dev, struct sun4i_dma_dev, slave);
+}
+
+static struct sun4i_dma_vchan *to_sun4i_dma_vchan(struct dma_chan *chan)
+{
+	return container_of(chan, struct sun4i_dma_vchan, vc.chan);
+}
+
+static struct sun4i_dma_contract *to_sun4i_dma_contract(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct sun4i_dma_contract, vd);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static int convert_burst(u32 maxburst)
+{
+	if (maxburst > 8)
+		return -EINVAL;
+
+	/* 1 -> 0, 4 -> 1, 8 -> 2 */
+	return (maxburst >> 2);
+}
+
+static int convert_buswidth(enum dma_slave_buswidth addr_width)
+{
+	if (addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES)
+		return -EINVAL;
+
+	/* 8 (1 byte) -> 0, 16 (2 bytes) -> 1, 32 (4 bytes) -> 2 */
+	return (addr_width >> 1);
+}
+
+static void sun4i_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+
+	vchan_free_chan_resources(&vchan->vc);
+}
+
+static struct sun4i_dma_pchan *find_and_use_pchan(struct sun4i_dma_dev *priv,
+						  struct sun4i_dma_vchan *vchan)
+{
+	struct sun4i_dma_pchan *pchan = NULL, *pchans = priv->pchans;
+	unsigned long flags;
+	int i, max;
+
+	/*
+	 * pchans 0-SUN4I_NDMA_NR_MAX_CHANNELS are normal, and
+	 * SUN4I_NDMA_NR_MAX_CHANNELS+ are dedicated ones
+	 */
+	if (vchan->is_dedicated) {
+		i = SUN4I_NDMA_NR_MAX_CHANNELS;
+		max = SUN4I_DMA_NR_MAX_CHANNELS;
+	} else {
+		i = 0;
+		max = SUN4I_NDMA_NR_MAX_CHANNELS;
+	}
+
+	spin_lock_irqsave(&priv->lock, flags);
+	for_each_clear_bit_from(i, &priv->pchans_used, max) {
+		pchan = &pchans[i];
+		pchan->vchan = vchan;
+		set_bit(i, priv->pchans_used);
+		break;
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return pchan;
+}
+
+static void release_pchan(struct sun4i_dma_dev *priv,
+			  struct sun4i_dma_pchan *pchan)
+{
+	unsigned long flags;
+	int nr = pchan - priv->pchans;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	pchan->vchan = NULL;
+	clear_bit(nr, priv->pchans_used);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void configure_pchan(struct sun4i_dma_pchan *pchan,
+			    struct sun4i_dma_promise *d)
+{
+	/*
+	 * Configure addresses and misc parameters depending on type
+	 * SUN4I_DDMA has an extra field with timing parameters
+	 */
+	if (pchan->is_dedicated) {
+		writel_relaxed(d->src, pchan->base + SUN4I_DDMA_SRC_ADDR_REG);
+		writel_relaxed(d->dst, pchan->base + SUN4I_DDMA_DST_ADDR_REG);
+		writel_relaxed(d->len, pchan->base + SUN4I_DDMA_BYTE_COUNT_REG);
+		writel_relaxed(d->para, pchan->base + SUN4I_DDMA_PARA_REG);
+		writel_relaxed(d->cfg, pchan->base + SUN4I_DDMA_CFG_REG);
+	} else {
+		writel_relaxed(d->src, pchan->base + SUN4I_NDMA_SRC_ADDR_REG);
+		writel_relaxed(d->dst, pchan->base + SUN4I_NDMA_DST_ADDR_REG);
+		writel_relaxed(d->len, pchan->base + SUN4I_NDMA_BYTE_COUNT_REG);
+		writel_relaxed(d->cfg, pchan->base + SUN4I_NDMA_CFG_REG);
+	}
+}
+
+static void set_pchan_interrupt(struct sun4i_dma_dev *priv,
+				struct sun4i_dma_pchan *pchan,
+				int half, int end)
+{
+	u32 reg;
+	int pchan_number = pchan - priv->pchans;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	reg = readl_relaxed(priv->base + SUN4I_DMA_IRQ_ENABLE_REG);
+
+	if (half)
+		reg |= BIT(pchan_number * 2);
+	else
+		reg &= ~BIT(pchan_number * 2);
+
+	if (end)
+		reg |= BIT(pchan_number * 2 + 1);
+	else
+		reg &= ~BIT(pchan_number * 2 + 1);
+
+	writel_relaxed(reg, priv->base + SUN4I_DMA_IRQ_ENABLE_REG);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+/**
+ * Execute pending operations on a vchan
+ *
+ * When given a vchan, this function will try to acquire a suitable
+ * pchan and, if successful, will configure it to fulfill a promise
+ * from the next pending contract.
+ *
+ * This function must be called with &vchan->vc.lock held.
+ */
+static int __execute_vchan_pending(struct sun4i_dma_dev *priv,
+				   struct sun4i_dma_vchan *vchan)
+{
+	struct sun4i_dma_promise *promise = NULL;
+	struct sun4i_dma_contract *contract = NULL;
+	struct sun4i_dma_pchan *pchan;
+	struct virt_dma_desc *vd;
+	int ret;
+
+	lockdep_assert_held(&vchan->vc.lock);
+
+	/* We need a pchan to do anything, so secure one if available */
+	pchan = find_and_use_pchan(priv, vchan);
+	if (!pchan)
+		return -EBUSY;
+
+	/*
+	 * Channel endpoints must not be repeated, so if this vchan
+	 * has already submitted some work, we can't do anything else
+	 */
+	if (vchan->processing) {
+		dev_dbg(chan2dev(&vchan->vc.chan),
+			"processing something to this endpoint already\n");
+		ret = -EBUSY;
+		goto release_pchan;
+	}
+
+	do {
+		/* Figure out which contract we're working with today */
+		vd = vchan_next_desc(&vchan->vc);
+		if (!vd) {
+			dev_dbg(chan2dev(&vchan->vc.chan),
+				"No pending contract found");
+			ret = 0;
+			goto release_pchan;
+		}
+
+		contract = to_sun4i_dma_contract(vd);
+		if (list_empty(&contract->demands)) {
+			/* The contract has been completed so mark it as such */
+			list_del(&contract->vd.node);
+			vchan_cookie_complete(&contract->vd);
+			dev_dbg(chan2dev(&vchan->vc.chan),
+				"Empty contract found and marked complete");
+		}
+	} while (list_empty(&contract->demands));
+
+	/* Now find out what we need to do */
+	promise = list_first_entry(&contract->demands,
+				   struct sun4i_dma_promise, list);
+	vchan->processing = promise;
+
+	/* ... and make it reality */
+	if (promise) {
+		vchan->contract = contract;
+		vchan->pchan = pchan;
+		set_pchan_interrupt(priv, pchan, contract->is_cyclic, 1);
+		configure_pchan(pchan, promise);
+	}
+
+	return 0;
+
+release_pchan:
+	release_pchan(priv, pchan);
+	return ret;
+}
+
+static int sanitize_config(struct dma_slave_config *sconfig,
+			   enum dma_transfer_direction direction)
+{
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		if ((sconfig->dst_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) ||
+		    !sconfig->dst_maxburst)
+			return -EINVAL;
+
+		if (sconfig->src_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+			sconfig->src_addr_width = sconfig->dst_addr_width;
+
+		if (!sconfig->src_maxburst)
+			sconfig->src_maxburst = sconfig->dst_maxburst;
+
+		break;
+
+	case DMA_DEV_TO_MEM:
+		if ((sconfig->src_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) ||
+		    !sconfig->src_maxburst)
+			return -EINVAL;
+
+		if (sconfig->dst_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+			sconfig->dst_addr_width = sconfig->src_addr_width;
+
+		if (!sconfig->dst_maxburst)
+			sconfig->dst_maxburst = sconfig->src_maxburst;
+
+		break;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+/**
+ * Generate a promise, to be used in a normal DMA contract.
+ *
+ * A NDMA promise contains all the information required to program the
+ * normal part of the DMA Engine and get data copied. A non-executed
+ * promise will live in the demands list on a contract. Once it has been
+ * completed, it will be moved to the completed demands list for later freeing.
+ * All linked promises will be freed when the corresponding contract is freed
+ */
+static struct sun4i_dma_promise *
+generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
+		      size_t len, struct dma_slave_config *sconfig,
+		      enum dma_transfer_direction direction)
+{
+	struct sun4i_dma_promise *promise;
+	int ret;
+
+	ret = sanitize_config(sconfig, direction);
+	if (ret)
+		return NULL;
+
+	promise = kzalloc(sizeof(*promise), GFP_NOWAIT);
+	if (!promise)
+		return NULL;
+
+	promise->src = src;
+	promise->dst = dest;
+	promise->len = len;
+	promise->cfg = SUN4I_DMA_CFG_LOADING |
+		SUN4I_NDMA_CFG_BYTE_COUNT_MODE_REMAIN;
+
+	dev_dbg(chan2dev(chan),
+		"src burst %d, dst burst %d, src buswidth %d, dst buswidth %d",
+		sconfig->src_maxburst, sconfig->dst_maxburst,
+		sconfig->src_addr_width, sconfig->dst_addr_width);
+
+	/* Source burst */
+	ret = convert_burst(sconfig->src_maxburst);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret);
+
+	/* Destination burst */
+	ret = convert_burst(sconfig->dst_maxburst);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret);
+
+	/* Source bus width */
+	ret = convert_buswidth(sconfig->src_addr_width);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret);
+
+	/* Destination bus width */
+	ret = convert_buswidth(sconfig->dst_addr_width);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret);
+
+	return promise;
+
+fail:
+	kfree(promise);
+	return NULL;
+}
+
+/**
+ * Generate a promise, to be used in a dedicated DMA contract.
+ *
+ * A DDMA promise contains all the information required to program the
+ * Dedicated part of the DMA Engine and get data copied. A non-executed
+ * promise will live in the demands list on a contract. Once it has been
+ * completed, it will be moved to the completed demands list for later freeing.
+ * All linked promises will be freed when the corresponding contract is freed
+ */
+static struct sun4i_dma_promise *
+generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
+		      size_t len, struct dma_slave_config *sconfig)
+{
+	struct sun4i_dma_promise *promise;
+	int ret;
+
+	promise = kzalloc(sizeof(*promise), GFP_NOWAIT);
+	if (!promise)
+		return NULL;
+
+	promise->src = src;
+	promise->dst = dest;
+	promise->len = len;
+	promise->cfg = SUN4I_DMA_CFG_LOADING |
+		SUN4I_DDMA_CFG_BYTE_COUNT_MODE_REMAIN;
+
+	/* Source burst */
+	ret = convert_burst(sconfig->src_maxburst);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret);
+
+	/* Destination burst */
+	ret = convert_burst(sconfig->dst_maxburst);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret);
+
+	/* Source bus width */
+	ret = convert_buswidth(sconfig->src_addr_width);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret);
+
+	/* Destination bus width */
+	ret = convert_buswidth(sconfig->dst_addr_width);
+	if (IS_ERR_VALUE(ret))
+		goto fail;
+	promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret);
+
+	return promise;
+
+fail:
+	kfree(promise);
+	return NULL;
+}
+
+/**
+ * Generate a contract
+ *
+ * Contracts function as DMA descriptors. As our hardware does not support
+ * linked lists, we need to implement SG via software. We use a contract
+ * to hold all the pieces of the request and process them serially one
+ * after another. Each piece is represented as a promise.
+ */
+static struct sun4i_dma_contract *generate_dma_contract(void)
+{
+	struct sun4i_dma_contract *contract;
+
+	contract = kzalloc(sizeof(*contract), GFP_NOWAIT);
+	if (!contract)
+		return NULL;
+
+	INIT_LIST_HEAD(&contract->demands);
+	INIT_LIST_HEAD(&contract->completed_demands);
+
+	return contract;
+}
+
+/**
+ * Get next promise on a cyclic transfer
+ *
+ * Cyclic contracts contain a series of promises which are executed on a
+ * loop. This function returns the next promise from a cyclic contract,
+ * so it can be programmed into the hardware.
+ */
+static struct sun4i_dma_promise *
+get_next_cyclic_promise(struct sun4i_dma_contract *contract)
+{
+	struct sun4i_dma_promise *promise;
+
+	promise = list_first_entry_or_null(&contract->demands,
+					   struct sun4i_dma_promise, list);
+	if (!promise) {
+		list_splice_init(&contract->completed_demands,
+				 &contract->demands);
+		promise = list_first_entry(&contract->demands,
+					   struct sun4i_dma_promise, list);
+	}
+
+	return promise;
+}
+
+/**
+ * Free a contract and all its associated promises
+ */
+static void sun4i_dma_free_contract(struct virt_dma_desc *vd)
+{
+	struct sun4i_dma_contract *contract = to_sun4i_dma_contract(vd);
+	struct sun4i_dma_promise *promise;
+
+	/* Free all the demands and completed demands */
+	list_for_each_entry(promise, &contract->demands, list)
+		kfree(promise);
+
+	list_for_each_entry(promise, &contract->completed_demands, list)
+		kfree(promise);
+
+	kfree(contract);
+}
+
+static struct dma_async_tx_descriptor *
+sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
+			  dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+	struct dma_slave_config *sconfig = &vchan->cfg;
+	struct sun4i_dma_promise *promise;
+	struct sun4i_dma_contract *contract;
+
+	contract = generate_dma_contract();
+	if (!contract)
+		return NULL;
+
+	/*
+	 * We can only do the copy to bus aligned addresses, so
+	 * choose the best one so we get decent performance. We also
+	 * maximize the burst size for this same reason.
+	 */
+	sconfig->src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	sconfig->dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	sconfig->src_maxburst = 8;
+	sconfig->dst_maxburst = 8;
+
+	if (vchan->is_dedicated)
+		promise = generate_ddma_promise(chan, src, dest, len, sconfig);
+	else
+		promise = generate_ndma_promise(chan, src, dest, len, sconfig,
+						DMA_MEM_TO_MEM);
+
+	if (!promise) {
+		kfree(contract);
+		return NULL;
+	}
+
+	/* Configure memcpy mode */
+	if (vchan->is_dedicated) {
+		promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM) |
+				SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM);
+	} else {
+		promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM) |
+				SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM);
+	}
+
+	/* Fill the contract with our only promise */
+	list_add_tail(&promise->list, &contract->demands);
+
+	/* And add it to the vchan */
+	return vchan_tx_prep(&vchan->vc, &contract->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *
+sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len,
+			  size_t period_len, enum dma_transfer_direction dir,
+			  unsigned long flags)
+{
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+	struct dma_slave_config *sconfig = &vchan->cfg;
+	struct sun4i_dma_promise *promise;
+	struct sun4i_dma_contract *contract;
+	dma_addr_t src, dest;
+	u32 endpoints;
+	int nr_periods, offset, plength, i;
+
+	if (!is_slave_direction(dir)) {
+		dev_err(chan2dev(chan), "Invalid DMA direction\n");
+		return NULL;
+	}
+
+	if (vchan->is_dedicated) {
+		/*
+		 * As we are using this just for audio data, we need to use
+		 * normal DMA. There is nothing stopping us from supporting
+		 * dedicated DMA here as well, so if a client comes up and
+		 * requires it, it will be simple to implement it.
+		 */
+		dev_err(chan2dev(chan),
+			"Cyclic transfers are only supported on Normal DMA\n");
+		return NULL;
+	}
+
+	contract = generate_dma_contract();
+	if (!contract)
+		return NULL;
+
+	contract->is_cyclic = 1;
+
+	/* Figure out the endpoints and the address we need */
+	if (dir == DMA_MEM_TO_DEV) {
+		src = buf;
+		dest = sconfig->dst_addr;
+		endpoints = SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM) |
+			    SUN4I_DMA_CFG_DST_DRQ_TYPE(vchan->endpoint) |
+			    SUN4I_DMA_CFG_DST_ADDR_MODE(SUN4I_NDMA_ADDR_MODE_IO);
+	} else {
+		src = sconfig->src_addr;
+		dest = buf;
+		endpoints = SUN4I_DMA_CFG_SRC_DRQ_TYPE(vchan->endpoint) |
+			    SUN4I_DMA_CFG_SRC_ADDR_MODE(SUN4I_NDMA_ADDR_MODE_IO) |
+			    SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM);
+	}
+
+	/*
+	 * We will be using half done interrupts to make two periods
+	 * out of a promise, so we need to program the DMA engine less
+	 * often
+	 */
+
+	/*
+	 * The engine can interrupt on half-transfer, so we can use
+	 * this feature to program the engine half as often as if we
+	 * didn't use it (keep in mind the hardware doesn't support
+	 * linked lists).
+	 *
+	 * Say you have a set of periods (| marks the start/end, I for
+	 * interrupt, P for programming the engine to do a new
+	 * transfer), the easy but slow way would be to do
+	 *
+	 *  |---|---|---|---| (periods / promises)
+	 *  P  I,P I,P I,P  I
+	 *
+	 * Using half transfer interrupts you can do
+	 *
+	 *  |-------|-------| (promises as configured on hw)
+	 *  |---|---|---|---| (periods)
+	 *  P   I  I,P  I   I
+	 *
+	 * Which requires half the engine programming for the same
+	 * functionality.
+	 */
+	nr_periods = DIV_ROUND_UP(len / period_len, 2);
+	for (i = 0; i < nr_periods; i++) {
+		/* Calculate the offset in the buffer and the length needed */
+		offset = i * period_len * 2;
+		plength = min((len - offset), (period_len * 2));
+		if (dir == DMA_MEM_TO_DEV)
+			src = buf + offset;
+		else
+			dest = buf + offset;
+
+		/* Make the promise */
+		promise = generate_ndma_promise(chan, src, dest,
+						plength, sconfig, dir);
+		if (!promise) {
+			/* TODO: should we free everything? */
+			return NULL;
+		}
+		promise->cfg |= endpoints;
+
+		/* Then add it to the contract */
+		list_add_tail(&promise->list, &contract->demands);
+	}
+
+	/* And add it to the vchan */
+	return vchan_tx_prep(&vchan->vc, &contract->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *
+sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+			unsigned int sg_len, enum dma_transfer_direction dir,
+			unsigned long flags, void *context)
+{
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+	struct dma_slave_config *sconfig = &vchan->cfg;
+	struct sun4i_dma_promise *promise;
+	struct sun4i_dma_contract *contract;
+	u8 ram_type, io_mode, linear_mode;
+	struct scatterlist *sg;
+	dma_addr_t srcaddr, dstaddr;
+	u32 endpoints, para;
+	int i;
+
+	if (!sgl)
+		return NULL;
+
+	if (!is_slave_direction(dir)) {
+		dev_err(chan2dev(chan), "Invalid DMA direction\n");
+		return NULL;
+	}
+
+	contract = generate_dma_contract();
+	if (!contract)
+		return NULL;
+
+	if (vchan->is_dedicated) {
+		io_mode = SUN4I_DDMA_ADDR_MODE_IO;
+		linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR;
+		ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM;
+	} else {
+		io_mode = SUN4I_NDMA_ADDR_MODE_IO;
+		linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR;
+		ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM;
+	}
+
+	if (dir == DMA_MEM_TO_DEV)
+		endpoints = SUN4I_DMA_CFG_DST_DRQ_TYPE(vchan->endpoint) |
+			    SUN4I_DMA_CFG_DST_ADDR_MODE(io_mode) |
+			    SUN4I_DMA_CFG_SRC_DRQ_TYPE(ram_type) |
+			    SUN4I_DMA_CFG_SRC_ADDR_MODE(linear_mode);
+	else
+		endpoints = SUN4I_DMA_CFG_DST_DRQ_TYPE(ram_type) |
+			    SUN4I_DMA_CFG_DST_ADDR_MODE(linear_mode) |
+			    SUN4I_DMA_CFG_SRC_DRQ_TYPE(vchan->endpoint) |
+			    SUN4I_DMA_CFG_SRC_ADDR_MODE(io_mode);
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		/* Figure out addresses */
+		if (dir == DMA_MEM_TO_DEV) {
+			srcaddr = sg_dma_address(sg);
+			dstaddr = sconfig->dst_addr;
+		} else {
+			srcaddr = sconfig->src_addr;
+			dstaddr = sg_dma_address(sg);
+		}
+
+		/*
+		 * These are the magic DMA engine timings that keep SPI going.
+		 * I haven't seen any interface on DMAEngine to configure
+		 * timings, and so far they seem to work for everything we
+		 * support, so I've kept them here. I don't know if other
+		 * devices need different timings because, as usual, we only
+		 * have the "para" bitfield meanings, but no comment on what
+		 * the values should be when doing a certain operation :|
+		 */
+		para = SUN4I_DDMA_MAGIC_SPI_PARAMETERS;
+
+		/* And make a suitable promise */
+		if (vchan->is_dedicated)
+			promise = generate_ddma_promise(chan, srcaddr, dstaddr,
+							sg_dma_len(sg),
+							sconfig);
+		else
+			promise = generate_ndma_promise(chan, srcaddr, dstaddr,
+							sg_dma_len(sg),
+							sconfig, dir);
+
+		if (!promise)
+			return NULL; /* TODO: should we free everything? */
+
+		promise->cfg |= endpoints;
+		promise->para = para;
+
+		/* Then add it to the contract */
+		list_add_tail(&promise->list, &contract->demands);
+	}
+
+	/*
+	 * Once we've got all the promises ready, add the contract
+	 * to the pending list on the vchan
+	 */
+	return vchan_tx_prep(&vchan->vc, &contract->vd, flags);
+}
+
+static int sun4i_dma_terminate_all(struct dma_chan *chan)
+{
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+	struct sun4i_dma_pchan *pchan = vchan->pchan;
+	LIST_HEAD(head);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+	vchan_get_all_descriptors(&vchan->vc, &head);
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	/*
+	 * Clearing the configuration register will halt the pchan. Interrupts
+	 * may still trigger, so don't forget to disable them.
+	 */
+	if (pchan) {
+		if (pchan->is_dedicated)
+			writel(0, pchan->base + SUN4I_DDMA_CFG_REG);
+		else
+			writel(0, pchan->base + SUN4I_NDMA_CFG_REG);
+		set_pchan_interrupt(priv, pchan, 0, 0);
+		release_pchan(priv, pchan);
+	}
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+	vchan_dma_desc_free_list(&vchan->vc, &head);
+	/* Clear these so the vchan is usable again */
+	vchan->processing = NULL;
+	vchan->pchan = NULL;
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	return 0;
+}
+
+static int sun4i_dma_config(struct dma_chan *chan,
+			    struct dma_slave_config *config)
+{
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+
+	memcpy(&vchan->cfg, config, sizeof(*config));
+
+	return 0;
+}
+
+static struct dma_chan *sun4i_dma_of_xlate(struct of_phandle_args *dma_spec,
+					   struct of_dma *ofdma)
+{
+	struct sun4i_dma_dev *priv = ofdma->of_dma_data;
+	struct sun4i_dma_vchan *vchan;
+	struct dma_chan *chan;
+	u8 is_dedicated = dma_spec->args[0];
+	u8 endpoint = dma_spec->args[1];
+
+	/* Check if type is Normal or Dedicated */
+	if (is_dedicated != 0 && is_dedicated != 1)
+		return NULL;
+
+	/* Make sure the endpoint looks sane */
+	if ((is_dedicated && endpoint >= SUN4I_DDMA_DRQ_TYPE_LIMIT) ||
+	    (!is_dedicated && endpoint >= SUN4I_NDMA_DRQ_TYPE_LIMIT))
+		return NULL;
+
+	chan = dma_get_any_slave_channel(&priv->slave);
+	if (!chan)
+		return NULL;
+
+	/* Assign the endpoint to the vchan */
+	vchan = to_sun4i_dma_vchan(chan);
+	vchan->is_dedicated = is_dedicated;
+	vchan->endpoint = endpoint;
+
+	return chan;
+}
+
+static enum dma_status sun4i_dma_tx_status(struct dma_chan *chan,
+					   dma_cookie_t cookie,
+					   struct dma_tx_state *state)
+{
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+	struct sun4i_dma_pchan *pchan = vchan->pchan;
+	struct sun4i_dma_contract *contract;
+	struct sun4i_dma_promise *promise;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	enum dma_status ret;
+	size_t bytes = 0;
+
+	ret = dma_cookie_status(chan, cookie, state);
+	if (!state || (ret == DMA_COMPLETE))
+		return ret;
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+	vd = vchan_find_desc(&vchan->vc, cookie);
+	if (!vd)
+		goto exit;
+	contract = to_sun4i_dma_contract(vd);
+
+	list_for_each_entry(promise, &contract->demands, list)
+		bytes += promise->len;
+
+	/*
+	 * The hardware is configured to return the remaining byte
+	 * quantity. If possible, replace the first listed element's
+	 * full size with the actual remaining amount
+	 */
+	promise = list_first_entry_or_null(&contract->demands,
+					   struct sun4i_dma_promise, list);
+	if (promise && pchan) {
+		bytes -= promise->len;
+		if (pchan->is_dedicated)
+			bytes += readl(pchan->base + SUN4I_DDMA_BYTE_COUNT_REG);
+		else
+			bytes += readl(pchan->base + SUN4I_NDMA_BYTE_COUNT_REG);
+	}
+
+exit:
+
+	dma_set_residue(state, bytes);
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	return ret;
+}
+
+static void sun4i_dma_issue_pending(struct dma_chan *chan)
+{
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
+	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+
+	/*
+	 * If there are pending transactions for this vchan, push one of
+	 * them into the engine to get the ball rolling.
+	 */
+	if (vchan_issue_pending(&vchan->vc))
+		__execute_vchan_pending(priv, vchan);
+
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+}
+
+static irqreturn_t sun4i_dma_interrupt(int irq, void *dev_id)
+{
+	struct sun4i_dma_dev *priv = dev_id;
+	struct sun4i_dma_pchan *pchans = priv->pchans, *pchan;
+	struct sun4i_dma_vchan *vchan;
+	struct sun4i_dma_contract *contract;
+	struct sun4i_dma_promise *promise;
+	unsigned long pendirq, irqs, disableirqs;
+	int bit, i, free_room, allow_mitigation = 1;
+
+	pendirq = readl_relaxed(priv->base + SUN4I_DMA_IRQ_PENDING_STATUS_REG);
+
+handle_pending:
+
+	disableirqs = 0;
+	free_room = 0;
+
+	for_each_set_bit(bit, &pendirq, 32) {
+		pchan = &pchans[bit >> 1];
+		vchan = pchan->vchan;
+		if (!vchan) /* a terminated channel may still interrupt */
+			continue;
+		contract = vchan->contract;
+
+		/*
+		 * Disable the IRQ and free the pchan if it's an end
+		 * interrupt (odd bit)
+		 */
+		if (bit & 1) {
+			spin_lock(&vchan->vc.lock);
+
+			/*
+			 * Move the promise into the completed list now that
+			 * we're done with it
+			 */
+			list_del(&vchan->processing->list);
+			list_add_tail(&vchan->processing->list,
+				      &contract->completed_demands);
+
+			/*
+			 * Cyclic DMA transfers are special:
+			 * - There's always something we can dispatch
+			 * - We need to run the callback
+			 * - Latency is very important, as this is used by audio
+			 * We therefore just cycle through the list and dispatch
+			 * whatever we have here, reusing the pchan. There's
+			 * no need to run the thread after this.
+			 *
+			 * For non-cyclic transfers we need to look around,
+			 * so we can program some more work, or notify the
+			 * client that their transfers have been completed.
+			 */
+			if (contract->is_cyclic) {
+				promise = get_next_cyclic_promise(contract);
+				vchan->processing = promise;
+				configure_pchan(pchan, promise);
+				vchan_cyclic_callback(&contract->vd);
+			} else {
+				vchan->processing = NULL;
+				vchan->pchan = NULL;
+
+				free_room = 1;
+				disableirqs |= BIT(bit);
+				release_pchan(priv, pchan);
+			}
+
+			spin_unlock(&vchan->vc.lock);
+		} else {
+			/* Half done interrupt */
+			if (contract->is_cyclic)
+				vchan_cyclic_callback(&contract->vd);
+			else
+				disableirqs |= BIT(bit);
+		}
+	}
+
+	/* Disable the IRQs for events we handled */
+	spin_lock(&priv->lock);
+	irqs = readl_relaxed(priv->base + SUN4I_DMA_IRQ_ENABLE_REG);
+	writel_relaxed(irqs & ~disableirqs,
+		       priv->base + SUN4I_DMA_IRQ_ENABLE_REG);
+	spin_unlock(&priv->lock);
+
+	/* Writing 1 to the pending field will clear the pending interrupt */
+	writel_relaxed(pendirq, priv->base + SUN4I_DMA_IRQ_PENDING_STATUS_REG);
+
+	/*
+	 * If a pchan was freed, we may be able to schedule something else,
+	 * so have a look around
+	 */
+	if (free_room) {
+		for (i = 0; i < SUN4I_DMA_NR_MAX_VCHANS; i++) {
+			vchan = &priv->vchans[i];
+			spin_lock(&vchan->vc.lock);
+			__execute_vchan_pending(priv, vchan);
+			spin_unlock(&vchan->vc.lock);
+		}
+	}
+
+	/*
+	 * Handle newer interrupts if some showed up, but only do it once
+	 * to avoid a too long a loop
+	 */
+	if (allow_mitigation) {
+		pendirq = readl_relaxed(priv->base +
+					SUN4I_DMA_IRQ_PENDING_STATUS_REG);
+		if (pendirq) {
+			allow_mitigation = 0;
+			goto handle_pending;
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int sun4i_dma_probe(struct platform_device *pdev)
+{
+	struct sun4i_dma_dev *priv;
+	struct resource *res;
+	int i, j, ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0) {
+		dev_err(&pdev->dev, "Cannot claim IRQ\n");
+		return priv->irq;
+	}
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "No clock specified\n");
+		return PTR_ERR(priv->clk);
+	}
+
+	platform_set_drvdata(pdev, priv);
+	spin_lock_init(&priv->lock);
+
+	dma_cap_zero(priv->slave.cap_mask);
+	dma_cap_set(DMA_PRIVATE, priv->slave.cap_mask);
+	dma_cap_set(DMA_MEMCPY, priv->slave.cap_mask);
+	dma_cap_set(DMA_CYCLIC, priv->slave.cap_mask);
+	dma_cap_set(DMA_SLAVE, priv->slave.cap_mask);
+
+	INIT_LIST_HEAD(&priv->slave.channels);
+	priv->slave.device_free_chan_resources	= sun4i_dma_free_chan_resources;
+	priv->slave.device_tx_status		= sun4i_dma_tx_status;
+	priv->slave.device_issue_pending	= sun4i_dma_issue_pending;
+	priv->slave.device_prep_slave_sg	= sun4i_dma_prep_slave_sg;
+	priv->slave.device_prep_dma_memcpy	= sun4i_dma_prep_dma_memcpy;
+	priv->slave.device_prep_dma_cyclic	= sun4i_dma_prep_dma_cyclic;
+	priv->slave.device_config		= sun4i_dma_config;
+	priv->slave.device_terminate_all	= sun4i_dma_terminate_all;
+	priv->slave.copy_align			= 2;
+	priv->slave.src_addr_widths		= BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+						  BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+						  BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	priv->slave.dst_addr_widths		= BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+						  BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+						  BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	priv->slave.directions			= BIT(DMA_DEV_TO_MEM) |
+						  BIT(DMA_MEM_TO_DEV);
+	priv->slave.residue_granularity		= DMA_RESIDUE_GRANULARITY_BURST;
+
+	priv->slave.dev = &pdev->dev;
+
+	priv->pchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_CHANNELS,
+				    sizeof(struct sun4i_dma_pchan), GFP_KERNEL);
+	priv->vchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_VCHANS,
+				    sizeof(struct sun4i_dma_vchan), GFP_KERNEL);
+	if (!priv->vchans || !priv->pchans)
+		return -ENOMEM;
+
+	/*
+	 * [0..SUN4I_NDMA_NR_MAX_CHANNELS) are normal pchans, and
+	 * [SUN4I_NDMA_NR_MAX_CHANNELS..SUN4I_DMA_NR_MAX_CHANNELS) are
+	 * dedicated ones
+	 */
+	for (i = 0; i < SUN4I_NDMA_NR_MAX_CHANNELS; i++)
+		priv->pchans[i].base = priv->base +
+			SUN4I_NDMA_CHANNEL_REG_BASE(i);
+
+	for (j = 0; i < SUN4I_DMA_NR_MAX_CHANNELS; i++, j++) {
+		priv->pchans[i].base = priv->base +
+			SUN4I_DDMA_CHANNEL_REG_BASE(j);
+		priv->pchans[i].is_dedicated = 1;
+	}
+
+	for (i = 0; i < SUN4I_DMA_NR_MAX_VCHANS; i++) {
+		struct sun4i_dma_vchan *vchan = &priv->vchans[i];
+
+		spin_lock_init(&vchan->vc.lock);
+		vchan->vc.desc_free = sun4i_dma_free_contract;
+		vchan_init(&vchan->vc, &priv->slave);
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Couldn't enable the clock\n");
+		return ret;
+	}
+
+	/*
+	 * Make sure the IRQs are all disabled and accounted for. The bootloader
+	 * likes to leave these dirty
+	 */
+	writel(0, priv->base + SUN4I_DMA_IRQ_ENABLE_REG);
+	writel(0xFFFFFFFF, priv->base + SUN4I_DMA_IRQ_PENDING_STATUS_REG);
+
+	ret = devm_request_irq(&pdev->dev, priv->irq, sun4i_dma_interrupt,
+			       0, dev_name(&pdev->dev), priv);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot request IRQ\n");
+		goto err_clk_disable;
+	}
+
+	ret = dma_async_device_register(&priv->slave);
+	if (ret) {
+		dev_warn(&pdev->dev, "Failed to register DMA engine device\n");
+		goto err_clk_disable;
+	}
+
+	ret = of_dma_controller_register(pdev->dev.of_node, sun4i_dma_of_xlate,
+					 priv);
+	if (ret) {
+		dev_err(&pdev->dev, "of_dma_controller_register failed\n");
+		goto err_dma_unregister;
+	}
+
+	dev_dbg(&pdev->dev, "Successfully probed SUN4I_DMA\n");
+
+	return 0;
+
+err_dma_unregister:
+	dma_async_device_unregister(&priv->slave);
+err_clk_disable:
+	clk_disable_unprepare(priv->clk);
+	return ret;
+}
+
+static int sun4i_dma_remove(struct platform_device *pdev)
+{
+	struct sun4i_dma_dev *priv = platform_get_drvdata(pdev);
+
+	/* Disable IRQ so no more work is scheduled */
+	disable_irq(priv->irq);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&priv->slave);
+
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static const struct of_device_id sun4i_dma_match[] = {
+	{ .compatible = "allwinner,sun4i-a10-dma" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver sun4i_dma_driver = {
+	.probe	= sun4i_dma_probe,
+	.remove	= sun4i_dma_remove,
+	.driver	= {
+		.name		= "sun4i-dma",
+		.of_match_table	= sun4i_dma_match,
+	},
+};
+
+module_platform_driver(sun4i_dma_driver);
+
+MODULE_DESCRIPTION("Allwinner A10 Dedicated DMA Controller Driver");
+MODULE_AUTHOR("Emilio López <emilio@elopez.com.ar>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index 842ff97c2cfb..73e0be6e2100 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -969,7 +969,7 @@ static int sun6i_dma_probe(struct platform_device *pdev)
 	sdc->slave.device_issue_pending		= sun6i_dma_issue_pending;
 	sdc->slave.device_prep_slave_sg		= sun6i_dma_prep_slave_sg;
 	sdc->slave.device_prep_dma_memcpy	= sun6i_dma_prep_dma_memcpy;
-	sdc->slave.copy_align			= 4;
+	sdc->slave.copy_align			= DMAENGINE_ALIGN_4_BYTES;
 	sdc->slave.device_config		= sun6i_dma_config;
 	sdc->slave.device_pause			= sun6i_dma_pause;
 	sdc->slave.device_resume		= sun6i_dma_resume;
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index eaf585e8286b..c8f79dcaaee8 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -155,7 +155,6 @@ struct tegra_dma_sg_req {
 	int				req_len;
 	bool				configured;
 	bool				last_sg;
-	bool				half_done;
 	struct list_head		node;
 	struct tegra_dma_desc		*dma_desc;
 };
@@ -188,7 +187,7 @@ struct tegra_dma_channel {
 	bool			config_init;
 	int			id;
 	int			irq;
-	unsigned long		chan_base_offset;
+	void __iomem		*chan_addr;
 	spinlock_t		lock;
 	bool			busy;
 	struct tegra_dma	*tdma;
@@ -203,8 +202,6 @@ struct tegra_dma_channel {
 	/* ISR handler and tasklet for bottom half of isr handling */
 	dma_isr_handler		isr_handler;
 	struct tasklet_struct	tasklet;
-	dma_async_tx_callback	callback;
-	void			*callback_param;
 
 	/* Channel-slave specific configuration */
 	unsigned int slave_id;
@@ -222,6 +219,13 @@ struct tegra_dma {
 	void __iomem			*base_addr;
 	const struct tegra_dma_chip_data *chip_data;
 
+	/*
+	 * Counter for managing global pausing of the DMA controller.
+	 * Only applicable for devices that don't support individual
+	 * channel pausing.
+	 */
+	u32				global_pause_count;
+
 	/* Some register need to be cache before suspend */
 	u32				reg_gen;
 
@@ -242,12 +246,12 @@ static inline u32 tdma_read(struct tegra_dma *tdma, u32 reg)
 static inline void tdc_write(struct tegra_dma_channel *tdc,
 		u32 reg, u32 val)
 {
-	writel(val, tdc->tdma->base_addr + tdc->chan_base_offset + reg);
+	writel(val, tdc->chan_addr + reg);
 }
 
 static inline u32 tdc_read(struct tegra_dma_channel *tdc, u32 reg)
 {
-	return readl(tdc->tdma->base_addr + tdc->chan_base_offset + reg);
+	return readl(tdc->chan_addr + reg);
 }
 
 static inline struct tegra_dma_channel *to_tegra_dma_chan(struct dma_chan *dc)
@@ -361,16 +365,32 @@ static void tegra_dma_global_pause(struct tegra_dma_channel *tdc,
 	struct tegra_dma *tdma = tdc->tdma;
 
 	spin_lock(&tdma->global_lock);
-	tdma_write(tdma, TEGRA_APBDMA_GENERAL, 0);
-	if (wait_for_burst_complete)
-		udelay(TEGRA_APBDMA_BURST_COMPLETE_TIME);
+
+	if (tdc->tdma->global_pause_count == 0) {
+		tdma_write(tdma, TEGRA_APBDMA_GENERAL, 0);
+		if (wait_for_burst_complete)
+			udelay(TEGRA_APBDMA_BURST_COMPLETE_TIME);
+	}
+
+	tdc->tdma->global_pause_count++;
+
+	spin_unlock(&tdma->global_lock);
 }
 
 static void tegra_dma_global_resume(struct tegra_dma_channel *tdc)
 {
 	struct tegra_dma *tdma = tdc->tdma;
 
-	tdma_write(tdma, TEGRA_APBDMA_GENERAL, TEGRA_APBDMA_GENERAL_ENABLE);
+	spin_lock(&tdma->global_lock);
+
+	if (WARN_ON(tdc->tdma->global_pause_count == 0))
+		goto out;
+
+	if (--tdc->tdma->global_pause_count == 0)
+		tdma_write(tdma, TEGRA_APBDMA_GENERAL,
+			   TEGRA_APBDMA_GENERAL_ENABLE);
+
+out:
 	spin_unlock(&tdma->global_lock);
 }
 
@@ -601,7 +621,6 @@ static void handle_once_dma_done(struct tegra_dma_channel *tdc,
 		return;
 
 	tdc_start_head_req(tdc);
-	return;
 }
 
 static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
@@ -628,7 +647,6 @@ static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
 		if (!st)
 			dma_desc->dma_status = DMA_ERROR;
 	}
-	return;
 }
 
 static void tegra_dma_tasklet(unsigned long data)
@@ -720,7 +738,6 @@ static void tegra_dma_issue_pending(struct dma_chan *dc)
 	}
 end:
 	spin_unlock_irqrestore(&tdc->lock, flags);
-	return;
 }
 
 static int tegra_dma_terminate_all(struct dma_chan *dc)
@@ -932,7 +949,6 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 	struct tegra_dma_sg_req  *sg_req = NULL;
 	u32 burst_size;
 	enum dma_slave_buswidth slave_bw;
-	int ret;
 
 	if (!tdc->config_init) {
 		dev_err(tdc2dev(tdc), "dma channel is not configured\n");
@@ -943,9 +959,8 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 		return NULL;
 	}
 
-	ret = get_transfer_param(tdc, direction, &apb_ptr, &apb_seq, &csr,
-				&burst_size, &slave_bw);
-	if (ret < 0)
+	if (get_transfer_param(tdc, direction, &apb_ptr, &apb_seq, &csr,
+				&burst_size, &slave_bw) < 0)
 		return NULL;
 
 	INIT_LIST_HEAD(&req_list);
@@ -1048,7 +1063,6 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 	dma_addr_t mem = buf_addr;
 	u32 burst_size;
 	enum dma_slave_buswidth slave_bw;
-	int ret;
 
 	if (!buf_len || !period_len) {
 		dev_err(tdc2dev(tdc), "Invalid buffer/period len\n");
@@ -1087,12 +1101,10 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 		return NULL;
 	}
 
-	ret = get_transfer_param(tdc, direction, &apb_ptr, &apb_seq, &csr,
-				&burst_size, &slave_bw);
-	if (ret < 0)
+	if (get_transfer_param(tdc, direction, &apb_ptr, &apb_seq, &csr,
+				&burst_size, &slave_bw) < 0)
 		return NULL;
 
-
 	ahb_seq = TEGRA_APBDMA_AHBSEQ_INTR_ENB;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_WRAP_NONE <<
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
@@ -1136,7 +1148,6 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 		sg_req->ch_regs.apb_seq = apb_seq;
 		sg_req->ch_regs.ahb_seq = ahb_seq;
 		sg_req->configured = false;
-		sg_req->half_done = false;
 		sg_req->last_sg = false;
 		sg_req->dma_desc = dma_desc;
 		sg_req->req_len = len;
@@ -1377,8 +1388,9 @@ static int tegra_dma_probe(struct platform_device *pdev)
 	for (i = 0; i < cdata->nr_channels; i++) {
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
 
-		tdc->chan_base_offset = TEGRA_APBDMA_CHANNEL_BASE_ADD_OFFSET +
-					i * cdata->channel_reg_size;
+		tdc->chan_addr = tdma->base_addr +
+				 TEGRA_APBDMA_CHANNEL_BASE_ADD_OFFSET +
+				 (i * cdata->channel_reg_size);
 
 		res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
 		if (!res) {
@@ -1418,6 +1430,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_PRIVATE, tdma->dma_dev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, tdma->dma_dev.cap_mask);
 
+	tdma->global_pause_count = 0;
 	tdma->dma_dev.dev = &pdev->dev;
 	tdma->dma_dev.device_alloc_chan_resources =
 					tegra_dma_alloc_chan_resources;
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 24f5ca2356bf..5cce8c9d0026 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -20,16 +20,19 @@
 #define TI_XBAR_OUTPUTS	127
 #define TI_XBAR_INPUTS	256
 
-static DEFINE_IDR(map_idr);
+#define TI_XBAR_EDMA_OFFSET	0
+#define TI_XBAR_SDMA_OFFSET	1
 
 struct ti_dma_xbar_data {
 	void __iomem *iomem;
 
 	struct dma_router dmarouter;
+	struct idr map_idr;
 
 	u16 safe_val; /* Value to rest the crossbar lines */
 	u32 xbar_requests; /* number of DMA requests connected to XBAR */
 	u32 dma_requests; /* number of DMA requests forwarded to DMA */
+	u32 dma_offset;
 };
 
 struct ti_dma_xbar_map {
@@ -51,7 +54,7 @@ static void ti_dma_xbar_free(struct device *dev, void *route_data)
 		map->xbar_in, map->xbar_out);
 
 	ti_dma_xbar_write(xbar->iomem, map->xbar_out, xbar->safe_val);
-	idr_remove(&map_idr, map->xbar_out);
+	idr_remove(&xbar->map_idr, map->xbar_out);
 	kfree(map);
 }
 
@@ -81,12 +84,11 @@ static void *ti_dma_xbar_route_allocate(struct of_phandle_args *dma_spec,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	map->xbar_out = idr_alloc(&map_idr, NULL, 0, xbar->dma_requests,
+	map->xbar_out = idr_alloc(&xbar->map_idr, NULL, 0, xbar->dma_requests,
 				  GFP_KERNEL);
 	map->xbar_in = (u16)dma_spec->args[0];
 
-	/* The DMA request is 1 based in sDMA */
-	dma_spec->args[0] = map->xbar_out + 1;
+	dma_spec->args[0] = map->xbar_out + xbar->dma_offset;
 
 	dev_dbg(&pdev->dev, "Mapping XBAR%u to DMA%d\n",
 		map->xbar_in, map->xbar_out);
@@ -96,9 +98,22 @@ static void *ti_dma_xbar_route_allocate(struct of_phandle_args *dma_spec,
 	return map;
 }
 
+static const struct of_device_id ti_dma_master_match[] = {
+	{
+		.compatible = "ti,omap4430-sdma",
+		.data = (void *)TI_XBAR_SDMA_OFFSET,
+	},
+	{
+		.compatible = "ti,edma3",
+		.data = (void *)TI_XBAR_EDMA_OFFSET,
+	},
+	{},
+};
+
 static int ti_dma_xbar_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
+	const struct of_device_id *match;
 	struct device_node *dma_node;
 	struct ti_dma_xbar_data *xbar;
 	struct resource *res;
@@ -113,12 +128,20 @@ static int ti_dma_xbar_probe(struct platform_device *pdev)
 	if (!xbar)
 		return -ENOMEM;
 
+	idr_init(&xbar->map_idr);
+
 	dma_node = of_parse_phandle(node, "dma-masters", 0);
 	if (!dma_node) {
 		dev_err(&pdev->dev, "Can't get DMA master node\n");
 		return -ENODEV;
 	}
 
+	match = of_match_node(ti_dma_master_match, dma_node);
+	if (!match) {
+		dev_err(&pdev->dev, "DMA master is not supported\n");
+		return -EINVAL;
+	}
+
 	if (of_property_read_u32(dma_node, "dma-requests",
 				 &xbar->dma_requests)) {
 		dev_info(&pdev->dev,
@@ -139,17 +162,15 @@ static int ti_dma_xbar_probe(struct platform_device *pdev)
 		xbar->safe_val = (u16)safe_val;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
 	iomem = devm_ioremap_resource(&pdev->dev, res);
-	if (!iomem)
-		return -ENOMEM;
+	if (IS_ERR(iomem))
+		return PTR_ERR(iomem);
 
 	xbar->iomem = iomem;
 
 	xbar->dmarouter.dev = &pdev->dev;
 	xbar->dmarouter.route_free = ti_dma_xbar_free;
+	xbar->dma_offset = (u32)match->data;
 
 	platform_set_drvdata(pdev, xbar);
 
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index c4c3d93fdd1b..559cd4073698 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -10,10 +10,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 /* Supports:
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 7d2c17d8d30f..6f80432a3f0a 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -29,7 +29,7 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&vc->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	list_move_tail(&vd->node, &vc->desc_submitted);
+	list_add_tail(&vd->node, &vc->desc_submitted);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
@@ -83,10 +83,8 @@ static void vchan_complete(unsigned long arg)
 		cb_data = vd->tx.callback_param;
 
 		list_del(&vd->node);
-		if (async_tx_test_ack(&vd->tx))
-			list_add(&vd->node, &vc->desc_allocated);
-		else
-			vc->desc_free(vd);
+
+		vc->desc_free(vd);
 
 		if (cb)
 			cb(cb_data);
@@ -98,13 +96,9 @@ void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
 	while (!list_empty(head)) {
 		struct virt_dma_desc *vd = list_first_entry(head,
 			struct virt_dma_desc, node);
-		if (async_tx_test_ack(&vd->tx)) {
-			list_move_tail(&vd->node, &vc->desc_allocated);
-		} else {
-			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-			list_del(&vd->node);
-			vc->desc_free(vd);
-		}
+		list_del(&vd->node);
+		dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
+		vc->desc_free(vd);
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -114,7 +108,6 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
 	dma_cookie_init(&vc->chan);
 
 	spin_lock_init(&vc->lock);
-	INIT_LIST_HEAD(&vc->desc_allocated);
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 189e75dbcb15..181b95267866 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -29,7 +29,6 @@ struct virt_dma_chan {
 	spinlock_t lock;
 
 	/* protected by vc.lock */
-	struct list_head desc_allocated;
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
@@ -56,16 +55,11 @@ static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
 	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
-	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
 	vd->tx.flags = tx_flags;
 	vd->tx.tx_submit = vchan_tx_submit;
 
-	spin_lock_irqsave(&vc->lock, flags);
-	list_add_tail(&vd->node, &vc->desc_allocated);
-	spin_unlock_irqrestore(&vc->lock, flags);
-
 	return &vd->tx;
 }
 
@@ -128,8 +122,7 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 }
 
 /**
- * vchan_get_all_descriptors - obtain all allocated, submitted and issued
- *                             descriptors
+ * vchan_get_all_descriptors - obtain all submitted and issued descriptors
  * vc: virtual channel to get descriptors from
  * head: list of descriptors found
  *
@@ -141,7 +134,6 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	struct list_head *head)
 {
-	list_splice_tail_init(&vc->desc_allocated, head);
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
@@ -149,14 +141,11 @@ static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
 {
-	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&vc->lock, flags);
 	vchan_get_all_descriptors(vc, &head);
-	list_for_each_entry(vd, &head, node)
-		async_tx_clear_ack(&vd->tx);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	vchan_dma_desc_free_list(vc, &head);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 620fd55ec766..b23e8d52d126 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -21,6 +21,7 @@
  * NOTE: PM support is currently not available.
  */
 
+#include <linux/acpi.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
@@ -111,6 +112,7 @@
 #define XGENE_DMA_MEM_RAM_SHUTDOWN		0xD070
 #define XGENE_DMA_BLK_MEM_RDY			0xD074
 #define XGENE_DMA_BLK_MEM_RDY_VAL		0xFFFFFFFF
+#define XGENE_DMA_RING_CMD_SM_OFFSET		0x8000
 
 /* X-Gene SoC EFUSE csr register and bit defination */
 #define XGENE_SOC_JTAG1_SHADOW			0x18
@@ -150,7 +152,6 @@
 #define XGENE_DMA_PQ_CHANNEL		1
 #define XGENE_DMA_MAX_BYTE_CNT		0x4000	/* 16 KB */
 #define XGENE_DMA_MAX_64B_DESC_BYTE_CNT	0x14000	/* 80 KB */
-#define XGENE_DMA_XOR_ALIGNMENT		6	/* 64 Bytes */
 #define XGENE_DMA_MAX_XOR_SRC		5
 #define XGENE_DMA_16K_BUFFER_LEN_CODE	0x0
 #define XGENE_DMA_INVALID_LEN_CODE	0x7800000000000000ULL
@@ -763,12 +764,17 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan)
 	struct xgene_dma_ring *ring = &chan->rx_ring;
 	struct xgene_dma_desc_sw *desc_sw, *_desc_sw;
 	struct xgene_dma_desc_hw *desc_hw;
+	struct list_head ld_completed;
 	u8 status;
 
+	INIT_LIST_HEAD(&ld_completed);
+
+	spin_lock_bh(&chan->lock);
+
 	/* Clean already completed and acked descriptors */
 	xgene_dma_clean_completed_descriptor(chan);
 
-	/* Run the callback for each descriptor, in order */
+	/* Move all completed descriptors to ld completed queue, in order */
 	list_for_each_entry_safe(desc_sw, _desc_sw, &chan->ld_running, node) {
 		/* Get subsequent hw descriptor from DMA rx ring */
 		desc_hw = &ring->desc_hw[ring->head];
@@ -811,15 +817,17 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan)
 		/* Mark this hw descriptor as processed */
 		desc_hw->m0 = cpu_to_le64(XGENE_DMA_DESC_EMPTY_SIGNATURE);
 
-		xgene_dma_run_tx_complete_actions(chan, desc_sw);
-
-		xgene_dma_clean_running_descriptor(chan, desc_sw);
-
 		/*
 		 * Decrement the pending transaction count
 		 * as we have processed one
 		 */
 		chan->pending--;
+
+		/*
+		 * Delete this node from ld running queue and append it to
+		 * ld completed queue for further processing
+		 */
+		list_move_tail(&desc_sw->node, &ld_completed);
 	}
 
 	/*
@@ -828,6 +836,14 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan)
 	 * ahead and free the descriptors below.
 	 */
 	xgene_chan_xfer_ld_pending(chan);
+
+	spin_unlock_bh(&chan->lock);
+
+	/* Run the callback for each descriptor, in order */
+	list_for_each_entry_safe(desc_sw, _desc_sw, &ld_completed, node) {
+		xgene_dma_run_tx_complete_actions(chan, desc_sw);
+		xgene_dma_clean_running_descriptor(chan, desc_sw);
+	}
 }
 
 static int xgene_dma_alloc_chan_resources(struct dma_chan *dchan)
@@ -876,11 +892,11 @@ static void xgene_dma_free_chan_resources(struct dma_chan *dchan)
 	if (!chan->desc_pool)
 		return;
 
-	spin_lock_bh(&chan->lock);
-
 	/* Process all running descriptor */
 	xgene_dma_cleanup_descriptors(chan);
 
+	spin_lock_bh(&chan->lock);
+
 	/* Clean all link descriptor queues */
 	xgene_dma_free_desc_list(chan, &chan->ld_pending);
 	xgene_dma_free_desc_list(chan, &chan->ld_running);
@@ -1200,15 +1216,11 @@ static void xgene_dma_tasklet_cb(unsigned long data)
 {
 	struct xgene_dma_chan *chan = (struct xgene_dma_chan *)data;
 
-	spin_lock_bh(&chan->lock);
-
 	/* Run all cleanup for descriptors which have been completed */
 	xgene_dma_cleanup_descriptors(chan);
 
 	/* Re-enable DMA channel IRQ */
 	enable_irq(chan->rx_irq);
-
-	spin_unlock_bh(&chan->lock);
 }
 
 static irqreturn_t xgene_dma_chan_ring_isr(int irq, void *id)
@@ -1740,13 +1752,13 @@ static void xgene_dma_set_caps(struct xgene_dma_chan *chan,
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
 		dma_dev->device_prep_dma_xor = xgene_dma_prep_xor;
 		dma_dev->max_xor = XGENE_DMA_MAX_XOR_SRC;
-		dma_dev->xor_align = XGENE_DMA_XOR_ALIGNMENT;
+		dma_dev->xor_align = DMAENGINE_ALIGN_64_BYTES;
 	}
 
 	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
 		dma_dev->device_prep_dma_pq = xgene_dma_prep_pq;
 		dma_dev->max_pq = XGENE_DMA_MAX_XOR_SRC;
-		dma_dev->pq_align = XGENE_DMA_XOR_ALIGNMENT;
+		dma_dev->pq_align = DMAENGINE_ALIGN_64_BYTES;
 	}
 }
 
@@ -1887,6 +1899,8 @@ static int xgene_dma_get_resources(struct platform_device *pdev,
 		return -ENOMEM;
 	}
 
+	pdma->csr_ring_cmd += XGENE_DMA_RING_CMD_SM_OFFSET;
+
 	/* Get efuse csr region */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
 	if (!res) {
@@ -1941,16 +1955,18 @@ static int xgene_dma_probe(struct platform_device *pdev)
 		return ret;
 
 	pdma->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(pdma->clk)) {
+	if (IS_ERR(pdma->clk) && !ACPI_COMPANION(&pdev->dev)) {
 		dev_err(&pdev->dev, "Failed to get clk\n");
 		return PTR_ERR(pdma->clk);
 	}
 
 	/* Enable clk before accessing registers */
-	ret = clk_prepare_enable(pdma->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to enable clk %d\n", ret);
-		return ret;
+	if (!IS_ERR(pdma->clk)) {
+		ret = clk_prepare_enable(pdma->clk);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to enable clk %d\n", ret);
+			return ret;
+		}
 	}
 
 	/* Remove DMA RAM out of shutdown */
@@ -1995,7 +2011,8 @@ err_request_irq:
 
 err_dma_mask:
 err_clk_enable:
-	clk_disable_unprepare(pdma->clk);
+	if (!IS_ERR(pdma->clk))
+		clk_disable_unprepare(pdma->clk);
 
 	return ret;
 }
@@ -2019,11 +2036,20 @@ static int xgene_dma_remove(struct platform_device *pdev)
 		xgene_dma_delete_chan_rings(chan);
 	}
 
-	clk_disable_unprepare(pdma->clk);
+	if (!IS_ERR(pdma->clk))
+		clk_disable_unprepare(pdma->clk);
 
 	return 0;
 }
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xgene_dma_acpi_match_ptr[] = {
+	{"APMC0D43", 0},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, xgene_dma_acpi_match_ptr);
+#endif
+
 static const struct of_device_id xgene_dma_of_match_ptr[] = {
 	{.compatible = "apm,xgene-storm-dma",},
 	{},
@@ -2036,6 +2062,7 @@ static struct platform_driver xgene_dma_driver = {
 	.driver = {
 		.name = "X-Gene-DMA",
 		.of_match_table = xgene_dma_of_match_ptr,
+		.acpi_match_table = ACPI_PTR(xgene_dma_acpi_match_ptr),
 	},
 };
 
diff --git a/drivers/dma/zx296702_dma.c b/drivers/dma/zx296702_dma.c
new file mode 100644
index 000000000000..39915a6b7986
--- /dev/null
+++ b/drivers/dma/zx296702_dma.c
@@ -0,0 +1,951 @@
+/*
+ * Copyright 2015 Linaro.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/sched.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/clk.h>
+#include <linux/of_dma.h>
+
+#include "virt-dma.h"
+
+#define DRIVER_NAME		"zx-dma"
+#define DMA_ALIGN		4
+#define DMA_MAX_SIZE		(0x10000 - PAGE_SIZE)
+#define LLI_BLOCK_SIZE		(4 * PAGE_SIZE)
+
+#define REG_ZX_SRC_ADDR			0x00
+#define REG_ZX_DST_ADDR			0x04
+#define REG_ZX_TX_X_COUNT		0x08
+#define REG_ZX_TX_ZY_COUNT		0x0c
+#define REG_ZX_SRC_ZY_STEP		0x10
+#define REG_ZX_DST_ZY_STEP		0x14
+#define REG_ZX_LLI_ADDR			0x1c
+#define REG_ZX_CTRL			0x20
+#define REG_ZX_TC_IRQ			0x800
+#define REG_ZX_SRC_ERR_IRQ		0x804
+#define REG_ZX_DST_ERR_IRQ		0x808
+#define REG_ZX_CFG_ERR_IRQ		0x80c
+#define REG_ZX_TC_IRQ_RAW		0x810
+#define REG_ZX_SRC_ERR_IRQ_RAW		0x814
+#define REG_ZX_DST_ERR_IRQ_RAW		0x818
+#define REG_ZX_CFG_ERR_IRQ_RAW		0x81c
+#define REG_ZX_STATUS			0x820
+#define REG_ZX_DMA_GRP_PRIO		0x824
+#define REG_ZX_DMA_ARB			0x828
+
+#define ZX_FORCE_CLOSE			BIT(31)
+#define ZX_DST_BURST_WIDTH(x)		(((x) & 0x7) << 13)
+#define ZX_MAX_BURST_LEN		16
+#define ZX_SRC_BURST_LEN(x)		(((x) & 0xf) << 9)
+#define ZX_SRC_BURST_WIDTH(x)		(((x) & 0x7) << 6)
+#define ZX_IRQ_ENABLE_ALL		(3 << 4)
+#define ZX_DST_FIFO_MODE		BIT(3)
+#define ZX_SRC_FIFO_MODE		BIT(2)
+#define ZX_SOFT_REQ			BIT(1)
+#define ZX_CH_ENABLE			BIT(0)
+
+#define ZX_DMA_BUSWIDTHS \
+	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+enum zx_dma_burst_width {
+	ZX_DMA_WIDTH_8BIT	= 0,
+	ZX_DMA_WIDTH_16BIT	= 1,
+	ZX_DMA_WIDTH_32BIT	= 2,
+	ZX_DMA_WIDTH_64BIT	= 3,
+};
+
+struct zx_desc_hw {
+	u32 saddr;
+	u32 daddr;
+	u32 src_x;
+	u32 src_zy;
+	u32 src_zy_step;
+	u32 dst_zy_step;
+	u32 reserved1;
+	u32 lli;
+	u32 ctr;
+	u32 reserved[7]; /* pack as hardware registers region size */
+} __aligned(32);
+
+struct zx_dma_desc_sw {
+	struct virt_dma_desc	vd;
+	dma_addr_t		desc_hw_lli;
+	size_t			desc_num;
+	size_t			size;
+	struct zx_desc_hw	*desc_hw;
+};
+
+struct zx_dma_phy;
+
+struct zx_dma_chan {
+	struct dma_slave_config slave_cfg;
+	int			id; /* Request phy chan id */
+	u32			ccfg;
+	u32			cyclic;
+	struct virt_dma_chan	vc;
+	struct zx_dma_phy	*phy;
+	struct list_head	node;
+	dma_addr_t		dev_addr;
+	enum dma_status		status;
+};
+
+struct zx_dma_phy {
+	u32			idx;
+	void __iomem		*base;
+	struct zx_dma_chan	*vchan;
+	struct zx_dma_desc_sw	*ds_run;
+	struct zx_dma_desc_sw	*ds_done;
+};
+
+struct zx_dma_dev {
+	struct dma_device	slave;
+	void __iomem		*base;
+	spinlock_t		lock; /* lock for ch and phy */
+	struct list_head	chan_pending;
+	struct zx_dma_phy	*phy;
+	struct zx_dma_chan	*chans;
+	struct clk		*clk;
+	struct dma_pool		*pool;
+	u32			dma_channels;
+	u32			dma_requests;
+	int 			irq;
+};
+
+#define to_zx_dma(dmadev) container_of(dmadev, struct zx_dma_dev, slave)
+
+static struct zx_dma_chan *to_zx_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct zx_dma_chan, vc.chan);
+}
+
+static void zx_dma_terminate_chan(struct zx_dma_phy *phy, struct zx_dma_dev *d)
+{
+	u32 val = 0;
+
+	val = readl_relaxed(phy->base + REG_ZX_CTRL);
+	val &= ~ZX_CH_ENABLE;
+	val |= ZX_FORCE_CLOSE;
+	writel_relaxed(val, phy->base + REG_ZX_CTRL);
+
+	val = 0x1 << phy->idx;
+	writel_relaxed(val, d->base + REG_ZX_TC_IRQ_RAW);
+	writel_relaxed(val, d->base + REG_ZX_SRC_ERR_IRQ_RAW);
+	writel_relaxed(val, d->base + REG_ZX_DST_ERR_IRQ_RAW);
+	writel_relaxed(val, d->base + REG_ZX_CFG_ERR_IRQ_RAW);
+}
+
+static void zx_dma_set_desc(struct zx_dma_phy *phy, struct zx_desc_hw *hw)
+{
+	writel_relaxed(hw->saddr, phy->base + REG_ZX_SRC_ADDR);
+	writel_relaxed(hw->daddr, phy->base + REG_ZX_DST_ADDR);
+	writel_relaxed(hw->src_x, phy->base + REG_ZX_TX_X_COUNT);
+	writel_relaxed(0, phy->base + REG_ZX_TX_ZY_COUNT);
+	writel_relaxed(0, phy->base + REG_ZX_SRC_ZY_STEP);
+	writel_relaxed(0, phy->base + REG_ZX_DST_ZY_STEP);
+	writel_relaxed(hw->lli, phy->base + REG_ZX_LLI_ADDR);
+	writel_relaxed(hw->ctr, phy->base + REG_ZX_CTRL);
+}
+
+static u32 zx_dma_get_curr_lli(struct zx_dma_phy *phy)
+{
+	return readl_relaxed(phy->base + REG_ZX_LLI_ADDR);
+}
+
+static u32 zx_dma_get_chan_stat(struct zx_dma_dev *d)
+{
+	return readl_relaxed(d->base + REG_ZX_STATUS);
+}
+
+static void zx_dma_init_state(struct zx_dma_dev *d)
+{
+	/* set same priority */
+	writel_relaxed(0x0, d->base + REG_ZX_DMA_ARB);
+	/* clear all irq */
+	writel_relaxed(0xffffffff, d->base + REG_ZX_TC_IRQ_RAW);
+	writel_relaxed(0xffffffff, d->base + REG_ZX_SRC_ERR_IRQ_RAW);
+	writel_relaxed(0xffffffff, d->base + REG_ZX_DST_ERR_IRQ_RAW);
+	writel_relaxed(0xffffffff, d->base + REG_ZX_CFG_ERR_IRQ_RAW);
+}
+
+static int zx_dma_start_txd(struct zx_dma_chan *c)
+{
+	struct zx_dma_dev *d = to_zx_dma(c->vc.chan.device);
+	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
+
+	if (!c->phy)
+		return -EAGAIN;
+
+	if (BIT(c->phy->idx) & zx_dma_get_chan_stat(d))
+		return -EAGAIN;
+
+	if (vd) {
+		struct zx_dma_desc_sw *ds =
+			container_of(vd, struct zx_dma_desc_sw, vd);
+		/*
+		 * fetch and remove request from vc->desc_issued
+		 * so vc->desc_issued only contains desc pending
+		 */
+		list_del(&ds->vd.node);
+		c->phy->ds_run = ds;
+		c->phy->ds_done = NULL;
+		/* start dma */
+		zx_dma_set_desc(c->phy, ds->desc_hw);
+		return 0;
+	}
+	c->phy->ds_done = NULL;
+	c->phy->ds_run = NULL;
+	return -EAGAIN;
+}
+
+static void zx_dma_task(struct zx_dma_dev *d)
+{
+	struct zx_dma_phy *p;
+	struct zx_dma_chan *c, *cn;
+	unsigned pch, pch_alloc = 0;
+	unsigned long flags;
+
+	/* check new dma request of running channel in vc->desc_issued */
+	list_for_each_entry_safe(c, cn, &d->slave.channels,
+				 vc.chan.device_node) {
+		spin_lock_irqsave(&c->vc.lock, flags);
+		p = c->phy;
+		if (p && p->ds_done && zx_dma_start_txd(c)) {
+			/* No current txd associated with this channel */
+			dev_dbg(d->slave.dev, "pchan %u: free\n", p->idx);
+			/* Mark this channel free */
+			c->phy = NULL;
+			p->vchan = NULL;
+		}
+		spin_unlock_irqrestore(&c->vc.lock, flags);
+	}
+
+	/* check new channel request in d->chan_pending */
+	spin_lock_irqsave(&d->lock, flags);
+	while (!list_empty(&d->chan_pending)) {
+		c = list_first_entry(&d->chan_pending,
+				     struct zx_dma_chan, node);
+		p = &d->phy[c->id];
+		if (!p->vchan) {
+			/* remove from d->chan_pending */
+			list_del_init(&c->node);
+			pch_alloc |= 1 << c->id;
+			/* Mark this channel allocated */
+			p->vchan = c;
+			c->phy = p;
+		} else {
+			dev_dbg(d->slave.dev, "pchan %u: busy!\n", c->id);
+		}
+	}
+	spin_unlock_irqrestore(&d->lock, flags);
+
+	for (pch = 0; pch < d->dma_channels; pch++) {
+		if (pch_alloc & (1 << pch)) {
+			p = &d->phy[pch];
+			c = p->vchan;
+			if (c) {
+				spin_lock_irqsave(&c->vc.lock, flags);
+				zx_dma_start_txd(c);
+				spin_unlock_irqrestore(&c->vc.lock, flags);
+			}
+		}
+	}
+}
+
+static irqreturn_t zx_dma_int_handler(int irq, void *dev_id)
+{
+	struct zx_dma_dev *d = (struct zx_dma_dev *)dev_id;
+	struct zx_dma_phy *p;
+	struct zx_dma_chan *c;
+	u32 tc = readl_relaxed(d->base + REG_ZX_TC_IRQ);
+	u32 serr = readl_relaxed(d->base + REG_ZX_SRC_ERR_IRQ);
+	u32 derr = readl_relaxed(d->base + REG_ZX_DST_ERR_IRQ);
+	u32 cfg = readl_relaxed(d->base + REG_ZX_CFG_ERR_IRQ);
+	u32 i, irq_chan = 0, task = 0;
+
+	while (tc) {
+		i = __ffs(tc);
+		tc &= ~BIT(i);
+		p = &d->phy[i];
+		c = p->vchan;
+		if (c) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&c->vc.lock, flags);
+			if (c->cyclic) {
+				vchan_cyclic_callback(&p->ds_run->vd);
+			} else {
+				vchan_cookie_complete(&p->ds_run->vd);
+				p->ds_done = p->ds_run;
+				task = 1;
+			}
+			spin_unlock_irqrestore(&c->vc.lock, flags);
+			irq_chan |= BIT(i);
+		}
+	}
+
+	if (serr || derr || cfg)
+		dev_warn(d->slave.dev, "DMA ERR src 0x%x, dst 0x%x, cfg 0x%x\n",
+			 serr, derr, cfg);
+
+	writel_relaxed(irq_chan, d->base + REG_ZX_TC_IRQ_RAW);
+	writel_relaxed(serr, d->base + REG_ZX_SRC_ERR_IRQ_RAW);
+	writel_relaxed(derr, d->base + REG_ZX_DST_ERR_IRQ_RAW);
+	writel_relaxed(cfg, d->base + REG_ZX_CFG_ERR_IRQ_RAW);
+
+	if (task)
+		zx_dma_task(d);
+	return IRQ_HANDLED;
+}
+
+static void zx_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_dev *d = to_zx_dma(chan->device);
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->lock, flags);
+	list_del_init(&c->node);
+	spin_unlock_irqrestore(&d->lock, flags);
+
+	vchan_free_chan_resources(&c->vc);
+	c->ccfg = 0;
+}
+
+static enum dma_status zx_dma_tx_status(struct dma_chan *chan,
+					dma_cookie_t cookie,
+					struct dma_tx_state *state)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_phy *p;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	enum dma_status ret;
+	size_t bytes = 0;
+
+	ret = dma_cookie_status(&c->vc.chan, cookie, state);
+	if (ret == DMA_COMPLETE || !state)
+		return ret;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	p = c->phy;
+	ret = c->status;
+
+	/*
+	 * If the cookie is on our issue queue, then the residue is
+	 * its total size.
+	 */
+	vd = vchan_find_desc(&c->vc, cookie);
+	if (vd) {
+		bytes = container_of(vd, struct zx_dma_desc_sw, vd)->size;
+	} else if ((!p) || (!p->ds_run)) {
+		bytes = 0;
+	} else {
+		struct zx_dma_desc_sw *ds = p->ds_run;
+		u32 clli = 0, index = 0;
+
+		bytes = 0;
+		clli = zx_dma_get_curr_lli(p);
+		index = (clli - ds->desc_hw_lli) / sizeof(struct zx_desc_hw);
+		for (; index < ds->desc_num; index++) {
+			bytes += ds->desc_hw[index].src_x;
+			/* end of lli */
+			if (!ds->desc_hw[index].lli)
+				break;
+		}
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+	dma_set_residue(state, bytes);
+	return ret;
+}
+
+static void zx_dma_issue_pending(struct dma_chan *chan)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_dev *d = to_zx_dma(chan->device);
+	unsigned long flags;
+	int issue = 0;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	/* add request to vc->desc_issued */
+	if (vchan_issue_pending(&c->vc)) {
+		spin_lock(&d->lock);
+		if (!c->phy && list_empty(&c->node)) {
+			/* if new channel, add chan_pending */
+			list_add_tail(&c->node, &d->chan_pending);
+			issue = 1;
+			dev_dbg(d->slave.dev, "vchan %p: issued\n", &c->vc);
+		}
+		spin_unlock(&d->lock);
+	} else {
+		dev_dbg(d->slave.dev, "vchan %p: nothing to issue\n", &c->vc);
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+
+	if (issue)
+		zx_dma_task(d);
+}
+
+static void zx_dma_fill_desc(struct zx_dma_desc_sw *ds, dma_addr_t dst,
+			     dma_addr_t src, size_t len, u32 num, u32 ccfg)
+{
+	if ((num + 1) < ds->desc_num)
+		ds->desc_hw[num].lli = ds->desc_hw_lli + (num + 1) *
+			sizeof(struct zx_desc_hw);
+	ds->desc_hw[num].saddr = src;
+	ds->desc_hw[num].daddr = dst;
+	ds->desc_hw[num].src_x = len;
+	ds->desc_hw[num].ctr = ccfg;
+}
+
+static struct zx_dma_desc_sw *zx_alloc_desc_resource(int num,
+						     struct dma_chan *chan)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_desc_sw *ds;
+	struct zx_dma_dev *d = to_zx_dma(chan->device);
+	int lli_limit = LLI_BLOCK_SIZE / sizeof(struct zx_desc_hw);
+
+	if (num > lli_limit) {
+		dev_dbg(chan->device->dev, "vch %p: sg num %d exceed max %d\n",
+			&c->vc, num, lli_limit);
+		return NULL;
+	}
+
+	ds = kzalloc(sizeof(*ds), GFP_ATOMIC);
+	if (!ds)
+		return NULL;
+
+	ds->desc_hw = dma_pool_alloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
+	if (!ds->desc_hw) {
+		dev_dbg(chan->device->dev, "vch %p: dma alloc fail\n", &c->vc);
+		kfree(ds);
+		return NULL;
+	}
+	memset(ds->desc_hw, sizeof(struct zx_desc_hw) * num, 0);
+	ds->desc_num = num;
+	return ds;
+}
+
+static enum zx_dma_burst_width zx_dma_burst_width(enum dma_slave_buswidth width)
+{
+	switch (width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+	case DMA_SLAVE_BUSWIDTH_8_BYTES:
+		return ffs(width) - 1;
+	default:
+		return ZX_DMA_WIDTH_32BIT;
+	}
+}
+
+static int zx_pre_config(struct zx_dma_chan *c, enum dma_transfer_direction dir)
+{
+	struct dma_slave_config *cfg = &c->slave_cfg;
+	enum zx_dma_burst_width src_width;
+	enum zx_dma_burst_width dst_width;
+	u32 maxburst = 0;
+
+	switch (dir) {
+	case DMA_MEM_TO_MEM:
+		c->ccfg = ZX_CH_ENABLE | ZX_SOFT_REQ
+			| ZX_SRC_BURST_LEN(ZX_MAX_BURST_LEN - 1)
+			| ZX_SRC_BURST_WIDTH(ZX_DMA_WIDTH_32BIT)
+			| ZX_DST_BURST_WIDTH(ZX_DMA_WIDTH_32BIT);
+		break;
+	case DMA_MEM_TO_DEV:
+		c->dev_addr = cfg->dst_addr;
+		/* dst len is calculated from src width, len and dst width.
+		 * We need make sure dst len not exceed MAX LEN.
+		 * Trailing single transaction that does not fill a full
+		 * burst also require identical src/dst data width.
+		 */
+		dst_width = zx_dma_burst_width(cfg->dst_addr_width);
+		maxburst = cfg->dst_maxburst;
+		maxburst = maxburst < ZX_MAX_BURST_LEN ?
+				maxburst : ZX_MAX_BURST_LEN;
+		c->ccfg = ZX_DST_FIFO_MODE | ZX_CH_ENABLE
+			| ZX_SRC_BURST_LEN(maxburst - 1)
+			| ZX_SRC_BURST_WIDTH(dst_width)
+			| ZX_DST_BURST_WIDTH(dst_width);
+		break;
+	case DMA_DEV_TO_MEM:
+		c->dev_addr = cfg->src_addr;
+		src_width = zx_dma_burst_width(cfg->src_addr_width);
+		maxburst = cfg->src_maxburst;
+		maxburst = maxburst < ZX_MAX_BURST_LEN ?
+				maxburst : ZX_MAX_BURST_LEN;
+		c->ccfg = ZX_SRC_FIFO_MODE | ZX_CH_ENABLE
+			| ZX_SRC_BURST_LEN(maxburst - 1)
+			| ZX_SRC_BURST_WIDTH(src_width)
+			| ZX_DST_BURST_WIDTH(src_width);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct dma_async_tx_descriptor *zx_dma_prep_memcpy(
+	struct dma_chan *chan,	dma_addr_t dst, dma_addr_t src,
+	size_t len, unsigned long flags)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_desc_sw *ds;
+	size_t copy = 0;
+	int num = 0;
+
+	if (!len)
+		return NULL;
+
+	if (zx_pre_config(c, DMA_MEM_TO_MEM))
+		return NULL;
+
+	num = DIV_ROUND_UP(len, DMA_MAX_SIZE);
+
+	ds = zx_alloc_desc_resource(num, chan);
+	if (!ds)
+		return NULL;
+
+	ds->size = len;
+	num = 0;
+
+	do {
+		copy = min_t(size_t, len, DMA_MAX_SIZE);
+		zx_dma_fill_desc(ds, dst, src, copy, num++, c->ccfg);
+
+		src += copy;
+		dst += copy;
+		len -= copy;
+	} while (len);
+
+	c->cyclic = 0;
+	ds->desc_hw[num - 1].lli = 0;	/* end of link */
+	ds->desc_hw[num - 1].ctr |= ZX_IRQ_ENABLE_ALL;
+	return vchan_tx_prep(&c->vc, &ds->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *zx_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sglen,
+	enum dma_transfer_direction dir, unsigned long flags, void *context)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_desc_sw *ds;
+	size_t len, avail, total = 0;
+	struct scatterlist *sg;
+	dma_addr_t addr, src = 0, dst = 0;
+	int num = sglen, i;
+
+	if (!sgl)
+		return NULL;
+
+	if (zx_pre_config(c, dir))
+		return NULL;
+
+	for_each_sg(sgl, sg, sglen, i) {
+		avail = sg_dma_len(sg);
+		if (avail > DMA_MAX_SIZE)
+			num += DIV_ROUND_UP(avail, DMA_MAX_SIZE) - 1;
+	}
+
+	ds = zx_alloc_desc_resource(num, chan);
+	if (!ds)
+		return NULL;
+
+	c->cyclic = 0;
+	num = 0;
+	for_each_sg(sgl, sg, sglen, i) {
+		addr = sg_dma_address(sg);
+		avail = sg_dma_len(sg);
+		total += avail;
+
+		do {
+			len = min_t(size_t, avail, DMA_MAX_SIZE);
+
+			if (dir == DMA_MEM_TO_DEV) {
+				src = addr;
+				dst = c->dev_addr;
+			} else if (dir == DMA_DEV_TO_MEM) {
+				src = c->dev_addr;
+				dst = addr;
+			}
+
+			zx_dma_fill_desc(ds, dst, src, len, num++, c->ccfg);
+
+			addr += len;
+			avail -= len;
+		} while (avail);
+	}
+
+	ds->desc_hw[num - 1].lli = 0;	/* end of link */
+	ds->desc_hw[num - 1].ctr |= ZX_IRQ_ENABLE_ALL;
+	ds->size = total;
+	return vchan_tx_prep(&c->vc, &ds->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *zx_dma_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction dir,
+		unsigned long flags)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_desc_sw *ds;
+	dma_addr_t src = 0, dst = 0;
+	int num_periods = buf_len / period_len;
+	int buf = 0, num = 0;
+
+	if (period_len > DMA_MAX_SIZE) {
+		dev_err(chan->device->dev, "maximum period size exceeded\n");
+		return NULL;
+	}
+
+	if (zx_pre_config(c, dir))
+		return NULL;
+
+	ds = zx_alloc_desc_resource(num_periods, chan);
+	if (!ds)
+		return NULL;
+	c->cyclic = 1;
+
+	while (buf < buf_len) {
+		if (dir == DMA_MEM_TO_DEV) {
+			src = dma_addr;
+			dst = c->dev_addr;
+		} else if (dir == DMA_DEV_TO_MEM) {
+			src = c->dev_addr;
+			dst = dma_addr;
+		}
+		zx_dma_fill_desc(ds, dst, src, period_len, num++,
+				 c->ccfg | ZX_IRQ_ENABLE_ALL);
+		dma_addr += period_len;
+		buf += period_len;
+	}
+
+	ds->desc_hw[num - 1].lli = ds->desc_hw_lli;
+	ds->size = buf_len;
+	return vchan_tx_prep(&c->vc, &ds->vd, flags);
+}
+
+static int zx_dma_config(struct dma_chan *chan,
+			 struct dma_slave_config *cfg)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+
+	if (!cfg)
+		return -EINVAL;
+
+	memcpy(&c->slave_cfg, cfg, sizeof(*cfg));
+
+	return 0;
+}
+
+static int zx_dma_terminate_all(struct dma_chan *chan)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	struct zx_dma_dev *d = to_zx_dma(chan->device);
+	struct zx_dma_phy *p = c->phy;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	dev_dbg(d->slave.dev, "vchan %p: terminate all\n", &c->vc);
+
+	/* Prevent this channel being scheduled */
+	spin_lock(&d->lock);
+	list_del_init(&c->node);
+	spin_unlock(&d->lock);
+
+	/* Clear the tx descriptor lists */
+	spin_lock_irqsave(&c->vc.lock, flags);
+	vchan_get_all_descriptors(&c->vc, &head);
+	if (p) {
+		/* vchan is assigned to a pchan - stop the channel */
+		zx_dma_terminate_chan(p, d);
+		c->phy = NULL;
+		p->vchan = NULL;
+		p->ds_run = NULL;
+		p->ds_done = NULL;
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+	vchan_dma_desc_free_list(&c->vc, &head);
+
+	return 0;
+}
+
+static int zx_dma_transfer_pause(struct dma_chan *chan)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	u32 val = 0;
+
+	val = readl_relaxed(c->phy->base + REG_ZX_CTRL);
+	val &= ~ZX_CH_ENABLE;
+	writel_relaxed(val, c->phy->base + REG_ZX_CTRL);
+
+	return 0;
+}
+
+static int zx_dma_transfer_resume(struct dma_chan *chan)
+{
+	struct zx_dma_chan *c = to_zx_chan(chan);
+	u32 val = 0;
+
+	val = readl_relaxed(c->phy->base + REG_ZX_CTRL);
+	val |= ZX_CH_ENABLE;
+	writel_relaxed(val, c->phy->base + REG_ZX_CTRL);
+
+	return 0;
+}
+
+static void zx_dma_free_desc(struct virt_dma_desc *vd)
+{
+	struct zx_dma_desc_sw *ds =
+		container_of(vd, struct zx_dma_desc_sw, vd);
+	struct zx_dma_dev *d = to_zx_dma(vd->tx.chan->device);
+
+	dma_pool_free(d->pool, ds->desc_hw, ds->desc_hw_lli);
+	kfree(ds);
+}
+
+static const struct of_device_id zx6702_dma_dt_ids[] = {
+	{ .compatible = "zte,zx296702-dma", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, zx6702_dma_dt_ids);
+
+static struct dma_chan *zx_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
+					       struct of_dma *ofdma)
+{
+	struct zx_dma_dev *d = ofdma->of_dma_data;
+	unsigned int request = dma_spec->args[0];
+	struct dma_chan *chan;
+	struct zx_dma_chan *c;
+
+	if (request > d->dma_requests)
+		return NULL;
+
+	chan = dma_get_any_slave_channel(&d->slave);
+	if (!chan) {
+		dev_err(d->slave.dev, "get channel fail in %s.\n", __func__);
+		return NULL;
+	}
+	c = to_zx_chan(chan);
+	c->id = request;
+	dev_info(d->slave.dev, "zx_dma: pchan %u: alloc vchan %p\n",
+		 c->id, &c->vc);
+	return chan;
+}
+
+static int zx_dma_probe(struct platform_device *op)
+{
+	struct zx_dma_dev *d;
+	struct resource *iores;
+	int i, ret = 0;
+
+	iores = platform_get_resource(op, IORESOURCE_MEM, 0);
+	if (!iores)
+		return -EINVAL;
+
+	d = devm_kzalloc(&op->dev, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	d->base = devm_ioremap_resource(&op->dev, iores);
+	if (IS_ERR(d->base))
+		return PTR_ERR(d->base);
+
+	of_property_read_u32((&op->dev)->of_node,
+			     "dma-channels", &d->dma_channels);
+	of_property_read_u32((&op->dev)->of_node,
+			     "dma-requests", &d->dma_requests);
+	if (!d->dma_requests || !d->dma_channels)
+		return -EINVAL;
+
+	d->clk = devm_clk_get(&op->dev, NULL);
+	if (IS_ERR(d->clk)) {
+		dev_err(&op->dev, "no dma clk\n");
+		return PTR_ERR(d->clk);
+	}
+
+	d->irq = platform_get_irq(op, 0);
+	ret = devm_request_irq(&op->dev, d->irq, zx_dma_int_handler,
+			       0, DRIVER_NAME, d);
+	if (ret)
+		return ret;
+
+	/* A DMA memory pool for LLIs, align on 32-byte boundary */
+	d->pool = dmam_pool_create(DRIVER_NAME, &op->dev,
+			LLI_BLOCK_SIZE, 32, 0);
+	if (!d->pool)
+		return -ENOMEM;
+
+	/* init phy channel */
+	d->phy = devm_kzalloc(&op->dev,
+		d->dma_channels * sizeof(struct zx_dma_phy), GFP_KERNEL);
+	if (!d->phy)
+		return -ENOMEM;
+
+	for (i = 0; i < d->dma_channels; i++) {
+		struct zx_dma_phy *p = &d->phy[i];
+
+		p->idx = i;
+		p->base = d->base + i * 0x40;
+	}
+
+	INIT_LIST_HEAD(&d->slave.channels);
+	dma_cap_set(DMA_SLAVE, d->slave.cap_mask);
+	dma_cap_set(DMA_MEMCPY, d->slave.cap_mask);
+	dma_cap_set(DMA_PRIVATE, d->slave.cap_mask);
+	d->slave.dev = &op->dev;
+	d->slave.device_free_chan_resources = zx_dma_free_chan_resources;
+	d->slave.device_tx_status = zx_dma_tx_status;
+	d->slave.device_prep_dma_memcpy = zx_dma_prep_memcpy;
+	d->slave.device_prep_slave_sg = zx_dma_prep_slave_sg;
+	d->slave.device_prep_dma_cyclic = zx_dma_prep_dma_cyclic;
+	d->slave.device_issue_pending = zx_dma_issue_pending;
+	d->slave.device_config = zx_dma_config;
+	d->slave.device_terminate_all = zx_dma_terminate_all;
+	d->slave.device_pause = zx_dma_transfer_pause;
+	d->slave.device_resume = zx_dma_transfer_resume;
+	d->slave.copy_align = DMA_ALIGN;
+	d->slave.src_addr_widths = ZX_DMA_BUSWIDTHS;
+	d->slave.dst_addr_widths = ZX_DMA_BUSWIDTHS;
+	d->slave.directions = BIT(DMA_MEM_TO_MEM) | BIT(DMA_MEM_TO_DEV)
+			| BIT(DMA_DEV_TO_MEM);
+	d->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+
+	/* init virtual channel */
+	d->chans = devm_kzalloc(&op->dev,
+		d->dma_requests * sizeof(struct zx_dma_chan), GFP_KERNEL);
+	if (!d->chans)
+		return -ENOMEM;
+
+	for (i = 0; i < d->dma_requests; i++) {
+		struct zx_dma_chan *c = &d->chans[i];
+
+		c->status = DMA_IN_PROGRESS;
+		INIT_LIST_HEAD(&c->node);
+		c->vc.desc_free = zx_dma_free_desc;
+		vchan_init(&c->vc, &d->slave);
+	}
+
+	/* Enable clock before accessing registers */
+	ret = clk_prepare_enable(d->clk);
+	if (ret < 0) {
+		dev_err(&op->dev, "clk_prepare_enable failed: %d\n", ret);
+		goto zx_dma_out;
+	}
+
+	zx_dma_init_state(d);
+
+	spin_lock_init(&d->lock);
+	INIT_LIST_HEAD(&d->chan_pending);
+	platform_set_drvdata(op, d);
+
+	ret = dma_async_device_register(&d->slave);
+	if (ret)
+		goto clk_dis;
+
+	ret = of_dma_controller_register((&op->dev)->of_node,
+					 zx_of_dma_simple_xlate, d);
+	if (ret)
+		goto of_dma_register_fail;
+
+	dev_info(&op->dev, "initialized\n");
+	return 0;
+
+of_dma_register_fail:
+	dma_async_device_unregister(&d->slave);
+clk_dis:
+	clk_disable_unprepare(d->clk);
+zx_dma_out:
+	return ret;
+}
+
+static int zx_dma_remove(struct platform_device *op)
+{
+	struct zx_dma_chan *c, *cn;
+	struct zx_dma_dev *d = platform_get_drvdata(op);
+
+	/* explictly free the irq */
+	devm_free_irq(&op->dev, d->irq, d);
+
+	dma_async_device_unregister(&d->slave);
+	of_dma_controller_free((&op->dev)->of_node);
+
+	list_for_each_entry_safe(c, cn, &d->slave.channels,
+				 vc.chan.device_node) {
+		list_del(&c->vc.chan.device_node);
+	}
+	clk_disable_unprepare(d->clk);
+	dmam_pool_destroy(d->pool);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int zx_dma_suspend_dev(struct device *dev)
+{
+	struct zx_dma_dev *d = dev_get_drvdata(dev);
+	u32 stat = 0;
+
+	stat = zx_dma_get_chan_stat(d);
+	if (stat) {
+		dev_warn(d->slave.dev,
+			 "chan %d is running fail to suspend\n", stat);
+		return -1;
+	}
+	clk_disable_unprepare(d->clk);
+	return 0;
+}
+
+static int zx_dma_resume_dev(struct device *dev)
+{
+	struct zx_dma_dev *d = dev_get_drvdata(dev);
+	int ret = 0;
+
+	ret = clk_prepare_enable(d->clk);
+	if (ret < 0) {
+		dev_err(d->slave.dev, "clk_prepare_enable failed: %d\n", ret);
+		return ret;
+	}
+	zx_dma_init_state(d);
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(zx_dma_pmops, zx_dma_suspend_dev, zx_dma_resume_dev);
+
+static struct platform_driver zx_pdma_driver = {
+	.driver		= {
+		.name	= DRIVER_NAME,
+		.pm	= &zx_dma_pmops,
+		.of_match_table = zx6702_dma_dt_ids,
+	},
+	.probe		= zx_dma_probe,
+	.remove		= zx_dma_remove,
+};
+
+module_platform_driver(zx_pdma_driver);
+
+MODULE_DESCRIPTION("ZTE ZX296702 DMA Driver");
+MODULE_AUTHOR("Jun Nie jun.nie@linaro.org");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 8677ead2a8e1..ef25000a5bc6 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -61,16 +61,6 @@ config EDAC_DECODE_MCE
 	  which occur really early upon boot, before the module infrastructure
 	  has been initialized.
 
-config EDAC_MCE_INJ
-	tristate "Simple MCE injection interface"
-	depends on EDAC_DECODE_MCE && DEBUG_FS
-	default n
-	help
-	  This is a simple debugfs interface to inject MCEs and test different
-	  aspects of the MCE handling code.
-
-	  WARNING: Do not even assume this interface is staying stable!
-
 config EDAC_MM_EDAC
 	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
 	select RAS
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 28ef2a519f65..ae3c5f3ce405 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -17,7 +17,6 @@ edac_core-y	+= edac_pci.o edac_pci_sysfs.o
 endif
 
 obj-$(CONFIG_EDAC_GHES)			+= ghes_edac.o
-obj-$(CONFIG_EDAC_MCE_INJ)		+= mce_amd_inj.o
 
 edac_mce_amd-y				:= mce_amd.o
 obj-$(CONFIG_EDAC_DECODE_MCE)		+= edac_mce_amd.o
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 58586d59bf8e..e3a945ce374b 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -763,7 +763,8 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 		c->x86, c->x86_model, c->x86_mask,
 		m->bank,
 		((m->status & MCI_STATUS_OVER)	? "Over"  : "-"),
-		((m->status & MCI_STATUS_UC)	? "UE"	  : "CE"),
+		((m->status & MCI_STATUS_UC)	? "UE"	  :
+		 (m->status & MCI_STATUS_DEFERRED) ? "-"  : "CE"),
 		((m->status & MCI_STATUS_MISCV)	? "MiscV" : "-"),
 		((m->status & MCI_STATUS_PCC)	? "PCC"	  : "-"),
 		((m->status & MCI_STATUS_ADDRV)	? "AddrV" : "-"));
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index 3515b381c131..711d8ad74f11 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -920,7 +920,7 @@ static int ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1)
 	 */
 
 	for (row = 0; row < mci->nr_csrows; row++) {
-		struct csrow_info *csi = &mci->csrows[row];
+		struct csrow_info *csi = mci->csrows[row];
 
 		/*
 		 * Get the configuration settings for this
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
index 14636e4b6a08..ba06904af2e1 100644
--- a/drivers/edac/xgene_edac.c
+++ b/drivers/edac/xgene_edac.c
@@ -1168,7 +1168,6 @@ static struct platform_driver xgene_edac_driver = {
 	.remove = xgene_edac_remove,
 	.driver = {
 		.name = "xgene-edac",
-		.owner = THIS_MODULE,
 		.of_match_table = xgene_edac_of_match,
 	},
 };
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index ad87f263056f..4b9f09cc38d8 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -20,10 +20,12 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/err.h>
+#include <linux/gpio/consumer.h>
 #include <linux/gpio.h>
 #include <linux/input.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/extcon.h>
 
@@ -46,6 +48,9 @@
 #define HPDET_DEBOUNCE 500
 #define DEFAULT_MICD_TIMEOUT 2000
 
+#define MICD_DBTIME_TWO_READINGS 2
+#define MICD_DBTIME_FOUR_READINGS 4
+
 #define MICD_LVL_1_TO_7 (ARIZONA_MICD_LVL_1 | ARIZONA_MICD_LVL_2 | \
 			 ARIZONA_MICD_LVL_3 | ARIZONA_MICD_LVL_4 | \
 			 ARIZONA_MICD_LVL_5 | ARIZONA_MICD_LVL_6 | \
@@ -94,6 +99,8 @@ struct arizona_extcon_info {
 	int hpdet_ip_version;
 
 	struct extcon_dev *edev;
+
+	struct gpio_desc *micd_pol_gpio;
 };
 
 static const struct arizona_micd_config micd_default_modes[] = {
@@ -204,6 +211,10 @@ static void arizona_extcon_set_mode(struct arizona_extcon_info *info, int mode)
 	if (arizona->pdata.micd_pol_gpio > 0)
 		gpio_set_value_cansleep(arizona->pdata.micd_pol_gpio,
 					info->micd_modes[mode].gpio);
+	else
+		gpiod_set_value_cansleep(info->micd_pol_gpio,
+					 info->micd_modes[mode].gpio);
+
 	regmap_update_bits(arizona->regmap, ARIZONA_MIC_DETECT_1,
 			   ARIZONA_MICD_BIAS_SRC_MASK,
 			   info->micd_modes[mode].bias <<
@@ -757,10 +768,11 @@ static void arizona_micd_timeout_work(struct work_struct *work)
 	mutex_lock(&info->lock);
 
 	dev_dbg(info->arizona->dev, "MICD timed out, reporting HP\n");
-	arizona_identify_headphone(info);
 
 	info->detecting = false;
 
+	arizona_identify_headphone(info);
+
 	arizona_stop_mic(info);
 
 	mutex_unlock(&info->lock);
@@ -820,12 +832,18 @@ static void arizona_micd_detect(struct work_struct *work)
 	/* Due to jack detect this should never happen */
 	if (!(val & ARIZONA_MICD_STS)) {
 		dev_warn(arizona->dev, "Detected open circuit\n");
+		info->mic = false;
+		arizona_stop_mic(info);
 		info->detecting = false;
+		arizona_identify_headphone(info);
 		goto handled;
 	}
 
 	/* If we got a high impedence we should have a headset, report it. */
 	if (info->detecting && (val & ARIZONA_MICD_LVL_8)) {
+		info->mic = true;
+		info->detecting = false;
+
 		arizona_identify_headphone(info);
 
 		ret = extcon_set_cable_state_(info->edev,
@@ -841,8 +859,6 @@ static void arizona_micd_detect(struct work_struct *work)
 				ret);
 		}
 
-		info->mic = true;
-		info->detecting = false;
 		goto handled;
 	}
 
@@ -855,10 +871,11 @@ static void arizona_micd_detect(struct work_struct *work)
 	if (info->detecting && (val & MICD_LVL_1_TO_7)) {
 		if (info->jack_flips >= info->micd_num_modes * 10) {
 			dev_dbg(arizona->dev, "Detected HP/line\n");
-			arizona_identify_headphone(info);
 
 			info->detecting = false;
 
+			arizona_identify_headphone(info);
+
 			arizona_stop_mic(info);
 		} else {
 			info->micd_mode++;
@@ -1110,12 +1127,12 @@ static void arizona_micd_set_level(struct arizona *arizona, int index,
 	regmap_update_bits(arizona->regmap, reg, mask, level);
 }
 
-static int arizona_extcon_of_get_pdata(struct arizona *arizona)
+static int arizona_extcon_device_get_pdata(struct arizona *arizona)
 {
 	struct arizona_pdata *pdata = &arizona->pdata;
 	unsigned int val = ARIZONA_ACCDET_MODE_HPL;
 
-	of_property_read_u32(arizona->dev->of_node, "wlf,hpdet-channel", &val);
+	device_property_read_u32(arizona->dev, "wlf,hpdet-channel", &val);
 	switch (val) {
 	case ARIZONA_ACCDET_MODE_HPL:
 	case ARIZONA_ACCDET_MODE_HPR:
@@ -1127,6 +1144,24 @@ static int arizona_extcon_of_get_pdata(struct arizona *arizona)
 		pdata->hpdet_channel = ARIZONA_ACCDET_MODE_HPL;
 	}
 
+	device_property_read_u32(arizona->dev, "wlf,micd-detect-debounce",
+				 &pdata->micd_detect_debounce);
+
+	device_property_read_u32(arizona->dev, "wlf,micd-bias-start-time",
+				 &pdata->micd_bias_start_time);
+
+	device_property_read_u32(arizona->dev, "wlf,micd-rate",
+				 &pdata->micd_rate);
+
+	device_property_read_u32(arizona->dev, "wlf,micd-dbtime",
+				 &pdata->micd_dbtime);
+
+	device_property_read_u32(arizona->dev, "wlf,micd-timeout",
+				 &pdata->micd_timeout);
+
+	pdata->micd_force_micbias = device_property_read_bool(arizona->dev,
+						"wlf,micd-force-micbias");
+
 	return 0;
 }
 
@@ -1147,10 +1182,8 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 	if (!info)
 		return -ENOMEM;
 
-	if (IS_ENABLED(CONFIG_OF)) {
-		if (!dev_get_platdata(arizona->dev))
-			arizona_extcon_of_get_pdata(arizona);
-	}
+	if (!dev_get_platdata(arizona->dev))
+		arizona_extcon_device_get_pdata(arizona);
 
 	info->micvdd = devm_regulator_get(&pdev->dev, "MICVDD");
 	if (IS_ERR(info->micvdd)) {
@@ -1241,6 +1274,27 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 				arizona->pdata.micd_pol_gpio, ret);
 			goto err_register;
 		}
+	} else {
+		if (info->micd_modes[0].gpio)
+			mode = GPIOD_OUT_HIGH;
+		else
+			mode = GPIOD_OUT_LOW;
+
+		/* We can't use devm here because we need to do the get
+		 * against the MFD device, as that is where the of_node
+		 * will reside, but if we devm against that the GPIO
+		 * will not be freed if the extcon driver is unloaded.
+		 */
+		info->micd_pol_gpio = gpiod_get_optional(arizona->dev,
+							 "wlf,micd-pol",
+							 GPIOD_OUT_LOW);
+		if (IS_ERR(info->micd_pol_gpio)) {
+			ret = PTR_ERR(info->micd_pol_gpio);
+			dev_err(arizona->dev,
+				"Failed to get microphone polarity GPIO: %d\n",
+				ret);
+			goto err_register;
+		}
 	}
 
 	if (arizona->pdata.hpdet_id_gpio > 0) {
@@ -1251,7 +1305,7 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to request GPIO%d: %d\n",
 				arizona->pdata.hpdet_id_gpio, ret);
-			goto err_register;
+			goto err_gpio;
 		}
 	}
 
@@ -1267,11 +1321,19 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 				   arizona->pdata.micd_rate
 				   << ARIZONA_MICD_RATE_SHIFT);
 
-	if (arizona->pdata.micd_dbtime)
+	switch (arizona->pdata.micd_dbtime) {
+	case MICD_DBTIME_FOUR_READINGS:
 		regmap_update_bits(arizona->regmap, ARIZONA_MIC_DETECT_1,
 				   ARIZONA_MICD_DBTIME_MASK,
-				   arizona->pdata.micd_dbtime
-				   << ARIZONA_MICD_DBTIME_SHIFT);
+				   ARIZONA_MICD_DBTIME);
+		break;
+	case MICD_DBTIME_TWO_READINGS:
+		regmap_update_bits(arizona->regmap, ARIZONA_MIC_DETECT_1,
+				   ARIZONA_MICD_DBTIME_MASK, 0);
+		break;
+	default:
+		break;
+	}
 
 	BUILD_BUG_ON(ARRAY_SIZE(arizona_micd_levels) != 0x40);
 
@@ -1295,7 +1357,7 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 				dev_err(arizona->dev,
 					"MICD ranges must be sorted\n");
 				ret = -EINVAL;
-				goto err_input;
+				goto err_gpio;
 			}
 		}
 	}
@@ -1314,7 +1376,7 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 			dev_err(arizona->dev, "Unsupported MICD level %d\n",
 				info->micd_ranges[i].max);
 			ret = -EINVAL;
-			goto err_input;
+			goto err_gpio;
 		}
 
 		dev_dbg(arizona->dev, "%d ohms for MICD threshold %d\n",
@@ -1387,7 +1449,7 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 	if (ret != 0) {
 		dev_err(&pdev->dev, "Failed to get JACKDET rise IRQ: %d\n",
 			ret);
-		goto err_input;
+		goto err_gpio;
 	}
 
 	ret = arizona_set_irq_wake(arizona, jack_irq_rise, 1);
@@ -1458,7 +1520,8 @@ err_rise_wake:
 	arizona_set_irq_wake(arizona, jack_irq_rise, 0);
 err_rise:
 	arizona_free_irq(arizona, jack_irq_rise, info);
-err_input:
+err_gpio:
+	gpiod_put(info->micd_pol_gpio);
 err_register:
 	pm_runtime_disable(&pdev->dev);
 	return ret;
@@ -1470,6 +1533,8 @@ static int arizona_extcon_remove(struct platform_device *pdev)
 	struct arizona *arizona = info->arizona;
 	int jack_irq_rise, jack_irq_fall;
 
+	gpiod_put(info->micd_pol_gpio);
+
 	pm_runtime_disable(&pdev->dev);
 
 	regmap_update_bits(arizona->regmap,
diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index 355459a54e8b..57c24fa52edb 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -65,22 +65,6 @@ static irqreturn_t gpio_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static ssize_t extcon_gpio_print_state(struct extcon_dev *edev, char *buf)
-{
-	struct device *dev = edev->dev.parent;
-	struct gpio_extcon_data *extcon_data = dev_get_drvdata(dev);
-	const char *state;
-
-	if (extcon_get_state(edev))
-		state = extcon_data->state_on;
-	else
-		state = extcon_data->state_off;
-
-	if (state)
-		return sprintf(buf, "%s\n", state);
-	return -EINVAL;
-}
-
 static int gpio_extcon_probe(struct platform_device *pdev)
 {
 	struct gpio_extcon_platform_data *pdata = dev_get_platdata(&pdev->dev);
@@ -110,8 +94,6 @@ static int gpio_extcon_probe(struct platform_device *pdev)
 	extcon_data->state_on = pdata->state_on;
 	extcon_data->state_off = pdata->state_off;
 	extcon_data->check_on_resume = pdata->check_on_resume;
-	if (pdata->state_on && pdata->state_off)
-		extcon_data->edev->print_state = extcon_gpio_print_state;
 
 	ret = devm_gpio_request_one(&pdev->dev, extcon_data->gpio, GPIOF_DIR_IN,
 				    pdev->name);
diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index f4f3b3d53928..35b9e118b2fb 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -24,6 +24,7 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/max77693.h>
+#include <linux/mfd/max77693-common.h>
 #include <linux/mfd/max77693-private.h>
 #include <linux/extcon.h>
 #include <linux/regmap.h>
@@ -42,7 +43,7 @@ static struct max77693_reg_data default_init_data[] = {
 	{
 		/* STATUS2 - [3]ChgDetRun */
 		.addr = MAX77693_MUIC_REG_STATUS2,
-		.data = STATUS2_CHGDETRUN_MASK,
+		.data = MAX77693_STATUS2_CHGDETRUN_MASK,
 	}, {
 		/* INTMASK1 - Unmask [3]ADC1KM,[0]ADCM */
 		.addr = MAX77693_MUIC_REG_INTMASK1,
@@ -235,7 +236,7 @@ static int max77693_muic_set_debounce_time(struct max77693_muic_info *info,
 		 */
 		ret = regmap_write(info->max77693->regmap_muic,
 				  MAX77693_MUIC_REG_CTRL3,
-				  time << CONTROL3_ADCDBSET_SHIFT);
+				  time << MAX77693_CONTROL3_ADCDBSET_SHIFT);
 		if (ret) {
 			dev_err(info->dev, "failed to set ADC debounce time\n");
 			return ret;
@@ -268,7 +269,7 @@ static int max77693_muic_set_path(struct max77693_muic_info *info,
 	if (attached)
 		ctrl1 = val;
 	else
-		ctrl1 = CONTROL1_SW_OPEN;
+		ctrl1 = MAX77693_CONTROL1_SW_OPEN;
 
 	ret = regmap_update_bits(info->max77693->regmap_muic,
 			MAX77693_MUIC_REG_CTRL1, COMP_SW_MASK, ctrl1);
@@ -278,13 +279,14 @@ static int max77693_muic_set_path(struct max77693_muic_info *info,
 	}
 
 	if (attached)
-		ctrl2 |= CONTROL2_CPEN_MASK;	/* LowPwr=0, CPEn=1 */
+		ctrl2 |= MAX77693_CONTROL2_CPEN_MASK;	/* LowPwr=0, CPEn=1 */
 	else
-		ctrl2 |= CONTROL2_LOWPWR_MASK;	/* LowPwr=1, CPEn=0 */
+		ctrl2 |= MAX77693_CONTROL2_LOWPWR_MASK;	/* LowPwr=1, CPEn=0 */
 
 	ret = regmap_update_bits(info->max77693->regmap_muic,
 			MAX77693_MUIC_REG_CTRL2,
-			CONTROL2_LOWPWR_MASK | CONTROL2_CPEN_MASK, ctrl2);
+			MAX77693_CONTROL2_LOWPWR_MASK | MAX77693_CONTROL2_CPEN_MASK,
+			ctrl2);
 	if (ret < 0) {
 		dev_err(info->dev, "failed to update MUIC register\n");
 		return ret;
@@ -326,8 +328,8 @@ static int max77693_muic_get_cable_type(struct max77693_muic_info *info,
 		 * Read ADC value to check cable type and decide cable state
 		 * according to cable type
 		 */
-		adc = info->status[0] & STATUS1_ADC_MASK;
-		adc >>= STATUS1_ADC_SHIFT;
+		adc = info->status[0] & MAX77693_STATUS1_ADC_MASK;
+		adc >>= MAX77693_STATUS1_ADC_SHIFT;
 
 		/*
 		 * Check current cable state/cable type and store cable type
@@ -350,8 +352,8 @@ static int max77693_muic_get_cable_type(struct max77693_muic_info *info,
 		 * Read ADC value to check cable type and decide cable state
 		 * according to cable type
 		 */
-		adc = info->status[0] & STATUS1_ADC_MASK;
-		adc >>= STATUS1_ADC_SHIFT;
+		adc = info->status[0] & MAX77693_STATUS1_ADC_MASK;
+		adc >>= MAX77693_STATUS1_ADC_SHIFT;
 
 		/*
 		 * Check current cable state/cable type and store cable type
@@ -366,13 +368,13 @@ static int max77693_muic_get_cable_type(struct max77693_muic_info *info,
 		} else {
 			*attached = true;
 
-			adclow = info->status[0] & STATUS1_ADCLOW_MASK;
-			adclow >>= STATUS1_ADCLOW_SHIFT;
-			adc1k = info->status[0] & STATUS1_ADC1K_MASK;
-			adc1k >>= STATUS1_ADC1K_SHIFT;
+			adclow = info->status[0] & MAX77693_STATUS1_ADCLOW_MASK;
+			adclow >>= MAX77693_STATUS1_ADCLOW_SHIFT;
+			adc1k = info->status[0] & MAX77693_STATUS1_ADC1K_MASK;
+			adc1k >>= MAX77693_STATUS1_ADC1K_SHIFT;
 
-			vbvolt = info->status[1] & STATUS2_VBVOLT_MASK;
-			vbvolt >>= STATUS2_VBVOLT_SHIFT;
+			vbvolt = info->status[1] & MAX77693_STATUS2_VBVOLT_MASK;
+			vbvolt >>= MAX77693_STATUS2_VBVOLT_SHIFT;
 
 			/**
 			 * [0x1|VBVolt|ADCLow|ADC1K]
@@ -397,8 +399,8 @@ static int max77693_muic_get_cable_type(struct max77693_muic_info *info,
 		 * Read charger type to check cable type and decide cable state
 		 * according to type of charger cable.
 		 */
-		chg_type = info->status[1] & STATUS2_CHGTYP_MASK;
-		chg_type >>= STATUS2_CHGTYP_SHIFT;
+		chg_type = info->status[1] & MAX77693_STATUS2_CHGTYP_MASK;
+		chg_type >>= MAX77693_STATUS2_CHGTYP_SHIFT;
 
 		if (chg_type == MAX77693_CHARGER_TYPE_NONE) {
 			*attached = false;
@@ -422,10 +424,10 @@ static int max77693_muic_get_cable_type(struct max77693_muic_info *info,
 		 * Read ADC value to check cable type and decide cable state
 		 * according to cable type
 		 */
-		adc = info->status[0] & STATUS1_ADC_MASK;
-		adc >>= STATUS1_ADC_SHIFT;
-		chg_type = info->status[1] & STATUS2_CHGTYP_MASK;
-		chg_type >>= STATUS2_CHGTYP_SHIFT;
+		adc = info->status[0] & MAX77693_STATUS1_ADC_MASK;
+		adc >>= MAX77693_STATUS1_ADC_SHIFT;
+		chg_type = info->status[1] & MAX77693_STATUS2_CHGTYP_MASK;
+		chg_type >>= MAX77693_STATUS2_CHGTYP_SHIFT;
 
 		if (adc == MAX77693_MUIC_ADC_OPEN
 				&& chg_type == MAX77693_CHARGER_TYPE_NONE)
@@ -437,8 +439,8 @@ static int max77693_muic_get_cable_type(struct max77693_muic_info *info,
 		 * Read vbvolt field, if vbvolt is 1,
 		 * this cable is used for charging.
 		 */
-		vbvolt = info->status[1] & STATUS2_VBVOLT_MASK;
-		vbvolt >>= STATUS2_VBVOLT_SHIFT;
+		vbvolt = info->status[1] & MAX77693_STATUS2_VBVOLT_MASK;
+		vbvolt >>= MAX77693_STATUS2_VBVOLT_SHIFT;
 
 		cable_type = vbvolt;
 		break;
@@ -520,7 +522,8 @@ static int max77693_muic_dock_handler(struct max77693_muic_info *info,
 	}
 
 	/* Dock-Car/Desk/Audio, PATH:AUDIO */
-	ret = max77693_muic_set_path(info, CONTROL1_SW_AUDIO, attached);
+	ret = max77693_muic_set_path(info, MAX77693_CONTROL1_SW_AUDIO,
+					attached);
 	if (ret < 0)
 		return ret;
 	extcon_set_cable_state_(info->edev, dock_id, attached);
@@ -585,14 +588,16 @@ static int max77693_muic_adc_ground_handler(struct max77693_muic_info *info)
 	case MAX77693_MUIC_GND_USB_HOST:
 	case MAX77693_MUIC_GND_USB_HOST_VB:
 		/* USB_HOST, PATH: AP_USB */
-		ret = max77693_muic_set_path(info, CONTROL1_SW_USB, attached);
+		ret = max77693_muic_set_path(info, MAX77693_CONTROL1_SW_USB,
+						attached);
 		if (ret < 0)
 			return ret;
 		extcon_set_cable_state_(info->edev, EXTCON_USB_HOST, attached);
 		break;
 	case MAX77693_MUIC_GND_AV_CABLE_LOAD:
 		/* Audio Video Cable with load, PATH:AUDIO */
-		ret = max77693_muic_set_path(info, CONTROL1_SW_AUDIO, attached);
+		ret = max77693_muic_set_path(info, MAX77693_CONTROL1_SW_AUDIO,
+						attached);
 		if (ret < 0)
 			return ret;
 		extcon_set_cable_state_(info->edev, EXTCON_USB, attached);
@@ -615,7 +620,7 @@ static int max77693_muic_jig_handler(struct max77693_muic_info *info,
 		int cable_type, bool attached)
 {
 	int ret = 0;
-	u8 path = CONTROL1_SW_OPEN;
+	u8 path = MAX77693_CONTROL1_SW_OPEN;
 
 	dev_info(info->dev,
 		"external connector is %s (adc:0x%02x)\n",
@@ -625,12 +630,12 @@ static int max77693_muic_jig_handler(struct max77693_muic_info *info,
 	case MAX77693_MUIC_ADC_FACTORY_MODE_USB_OFF:	/* ADC_JIG_USB_OFF */
 	case MAX77693_MUIC_ADC_FACTORY_MODE_USB_ON:	/* ADC_JIG_USB_ON */
 		/* PATH:AP_USB */
-		path = CONTROL1_SW_USB;
+		path = MAX77693_CONTROL1_SW_USB;
 		break;
 	case MAX77693_MUIC_ADC_FACTORY_MODE_UART_OFF:	/* ADC_JIG_UART_OFF */
 	case MAX77693_MUIC_ADC_FACTORY_MODE_UART_ON:	/* ADC_JIG_UART_ON */
 		/* PATH:AP_UART */
-		path = CONTROL1_SW_UART;
+		path = MAX77693_CONTROL1_SW_UART;
 		break;
 	default:
 		dev_err(info->dev, "failed to detect %s jig cable\n",
@@ -1077,7 +1082,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 		dev_dbg(&pdev->dev, "allocate register map\n");
 	} else {
 		info->max77693->regmap_muic = devm_regmap_init_i2c(
-						info->max77693->muic,
+						info->max77693->i2c_muic,
 						&max77693_muic_regmap_config);
 		if (IS_ERR(info->max77693->regmap_muic)) {
 			ret = PTR_ERR(info->max77693->regmap_muic);
@@ -1164,28 +1169,9 @@ static int max77693_muic_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < num_init_data; i++) {
-		enum max77693_irq_source irq_src
-				= MAX77693_IRQ_GROUP_NR;
-
 		regmap_write(info->max77693->regmap_muic,
 				init_data[i].addr,
 				init_data[i].data);
-
-		switch (init_data[i].addr) {
-		case MAX77693_MUIC_REG_INTMASK1:
-			irq_src = MUIC_INT1;
-			break;
-		case MAX77693_MUIC_REG_INTMASK2:
-			irq_src = MUIC_INT2;
-			break;
-		case MAX77693_MUIC_REG_INTMASK3:
-			irq_src = MUIC_INT3;
-			break;
-		}
-
-		if (irq_src < MAX77693_IRQ_GROUP_NR)
-			info->max77693->irq_masks_cur[irq_src]
-				= init_data[i].data;
 	}
 
 	if (pdata && pdata->muic_data) {
@@ -1199,12 +1185,12 @@ static int max77693_muic_probe(struct platform_device *pdev)
 		if (muic_pdata->path_uart)
 			info->path_uart = muic_pdata->path_uart;
 		else
-			info->path_uart = CONTROL1_SW_UART;
+			info->path_uart = MAX77693_CONTROL1_SW_UART;
 
 		if (muic_pdata->path_usb)
 			info->path_usb = muic_pdata->path_usb;
 		else
-			info->path_usb = CONTROL1_SW_USB;
+			info->path_usb = MAX77693_CONTROL1_SW_USB;
 
 		/*
 		 * Default delay time for detecting cable state
@@ -1216,8 +1202,8 @@ static int max77693_muic_probe(struct platform_device *pdev)
 		else
 			delay_jiffies = msecs_to_jiffies(DELAY_MS_DEFAULT);
 	} else {
-		info->path_usb = CONTROL1_SW_USB;
-		info->path_uart = CONTROL1_SW_UART;
+		info->path_usb = MAX77693_CONTROL1_SW_USB;
+		info->path_uart = MAX77693_CONTROL1_SW_UART;
 		delay_jiffies = msecs_to_jiffies(DELAY_MS_DEFAULT);
 	}
 
diff --git a/drivers/extcon/extcon-max77843.c b/drivers/extcon/extcon-max77843.c
index fac2f1417a79..fdd928542c19 100644
--- a/drivers/extcon/extcon-max77843.c
+++ b/drivers/extcon/extcon-max77843.c
@@ -15,6 +15,7 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/mfd/max77693-common.h>
 #include <linux/mfd/max77843-private.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -32,7 +33,7 @@ enum max77843_muic_status {
 
 struct max77843_muic_info {
 	struct device *dev;
-	struct max77843 *max77843;
+	struct max77693_dev *max77843;
 	struct extcon_dev *edev;
 
 	struct mutex mutex;
@@ -198,18 +199,18 @@ static const struct regmap_irq_chip max77843_muic_irq_chip = {
 static int max77843_muic_set_path(struct max77843_muic_info *info,
 		u8 val, bool attached)
 {
-	struct max77843 *max77843 = info->max77843;
+	struct max77693_dev *max77843 = info->max77843;
 	int ret = 0;
 	unsigned int ctrl1, ctrl2;
 
 	if (attached)
 		ctrl1 = val;
 	else
-		ctrl1 = CONTROL1_SW_OPEN;
+		ctrl1 = MAX77843_MUIC_CONTROL1_SW_OPEN;
 
 	ret = regmap_update_bits(max77843->regmap_muic,
 			MAX77843_MUIC_REG_CONTROL1,
-			CONTROL1_COM_SW, ctrl1);
+			MAX77843_MUIC_CONTROL1_COM_SW, ctrl1);
 	if (ret < 0) {
 		dev_err(info->dev, "Cannot switch MUIC port\n");
 		return ret;
@@ -243,7 +244,7 @@ static int max77843_muic_get_cable_type(struct max77843_muic_info *info,
 
 	adc = info->status[MAX77843_MUIC_STATUS1] &
 			MAX77843_MUIC_STATUS1_ADC_MASK;
-	adc >>= STATUS1_ADC_SHIFT;
+	adc >>= MAX77843_MUIC_STATUS1_ADC_SHIFT;
 
 	switch (group) {
 	case MAX77843_CABLE_GROUP_ADC:
@@ -309,7 +310,7 @@ static int max77843_muic_get_cable_type(struct max77843_muic_info *info,
 			/* Get VBVolt register bit */
 			gnd_type |= (info->status[MAX77843_MUIC_STATUS2] &
 					MAX77843_MUIC_STATUS2_VBVOLT_MASK);
-			gnd_type >>= STATUS2_VBVOLT_SHIFT;
+			gnd_type >>= MAX77843_MUIC_STATUS2_VBVOLT_SHIFT;
 
 			/* Offset of GND cable */
 			gnd_type |= MAX77843_MUIC_GND_USB_HOST;
@@ -338,7 +339,9 @@ static int max77843_muic_adc_gnd_handler(struct max77843_muic_info *info)
 	switch (gnd_cable_type) {
 	case MAX77843_MUIC_GND_USB_HOST:
 	case MAX77843_MUIC_GND_USB_HOST_VB:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_USB, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_USB,
+					     attached);
 		if (ret < 0)
 			return ret;
 
@@ -346,7 +349,9 @@ static int max77843_muic_adc_gnd_handler(struct max77843_muic_info *info)
 		break;
 	case MAX77843_MUIC_GND_MHL_VB:
 	case MAX77843_MUIC_GND_MHL:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_OPEN, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_OPEN,
+					     attached);
 		if (ret < 0)
 			return ret;
 
@@ -365,7 +370,7 @@ static int max77843_muic_jig_handler(struct max77843_muic_info *info,
 		int cable_type, bool attached)
 {
 	int ret;
-	u8 path = CONTROL1_SW_OPEN;
+	u8 path = MAX77843_MUIC_CONTROL1_SW_OPEN;
 
 	dev_dbg(info->dev, "external connector is %s (adc:0x%02x)\n",
 			attached ? "attached" : "detached", cable_type);
@@ -373,10 +378,10 @@ static int max77843_muic_jig_handler(struct max77843_muic_info *info,
 	switch (cable_type) {
 	case MAX77843_MUIC_ADC_FACTORY_MODE_USB_OFF:
 	case MAX77843_MUIC_ADC_FACTORY_MODE_USB_ON:
-		path = CONTROL1_SW_USB;
+		path = MAX77843_MUIC_CONTROL1_SW_USB;
 		break;
 	case MAX77843_MUIC_ADC_FACTORY_MODE_UART_OFF:
-		path = CONTROL1_SW_UART;
+		path = MAX77843_MUIC_CONTROL1_SW_UART;
 		break;
 	default:
 		return -EINVAL;
@@ -474,14 +479,18 @@ static int max77843_muic_chg_handler(struct max77843_muic_info *info)
 
 	switch (chg_type) {
 	case MAX77843_MUIC_CHG_USB:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_USB, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_USB,
+					     attached);
 		if (ret < 0)
 			return ret;
 
 		extcon_set_cable_state_(info->edev, EXTCON_USB, attached);
 		break;
 	case MAX77843_MUIC_CHG_DOWNSTREAM:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_OPEN, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_OPEN,
+					     attached);
 		if (ret < 0)
 			return ret;
 
@@ -489,14 +498,18 @@ static int max77843_muic_chg_handler(struct max77843_muic_info *info)
 					attached);
 		break;
 	case MAX77843_MUIC_CHG_DEDICATED:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_OPEN, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_OPEN,
+					     attached);
 		if (ret < 0)
 			return ret;
 
 		extcon_set_cable_state_(info->edev, EXTCON_TA, attached);
 		break;
 	case MAX77843_MUIC_CHG_SPECIAL_500MA:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_OPEN, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_OPEN,
+					     attached);
 		if (ret < 0)
 			return ret;
 
@@ -504,7 +517,9 @@ static int max77843_muic_chg_handler(struct max77843_muic_info *info)
 					attached);
 		break;
 	case MAX77843_MUIC_CHG_SPECIAL_1A:
-		ret = max77843_muic_set_path(info, CONTROL1_SW_OPEN, attached);
+		ret = max77843_muic_set_path(info,
+					     MAX77843_MUIC_CONTROL1_SW_OPEN,
+					     attached);
 		if (ret < 0)
 			return ret;
 
@@ -528,7 +543,8 @@ static int max77843_muic_chg_handler(struct max77843_muic_info *info)
 			"failed to detect %s accessory (chg_type:0x%x)\n",
 			attached ? "attached" : "detached", chg_type);
 
-		max77843_muic_set_path(info, CONTROL1_SW_OPEN, attached);
+		max77843_muic_set_path(info, MAX77843_MUIC_CONTROL1_SW_OPEN,
+				       attached);
 		return -EINVAL;
 	}
 
@@ -539,7 +555,7 @@ static void max77843_muic_irq_work(struct work_struct *work)
 {
 	struct max77843_muic_info *info = container_of(work,
 			struct max77843_muic_info, irq_work);
-	struct max77843 *max77843 = info->max77843;
+	struct max77693_dev *max77843 = info->max77843;
 	int ret = 0;
 
 	mutex_lock(&info->mutex);
@@ -615,7 +631,7 @@ static void max77843_muic_detect_cable_wq(struct work_struct *work)
 {
 	struct max77843_muic_info *info = container_of(to_delayed_work(work),
 			struct max77843_muic_info, wq_detcable);
-	struct max77843 *max77843 = info->max77843;
+	struct max77693_dev *max77843 = info->max77843;
 	int chg_type, adc, ret;
 	bool attached;
 
@@ -656,7 +672,7 @@ err_cable_wq:
 static int max77843_muic_set_debounce_time(struct max77843_muic_info *info,
 		enum max77843_muic_adc_debounce_time time)
 {
-	struct max77843 *max77843 = info->max77843;
+	struct max77693_dev *max77843 = info->max77843;
 	int ret;
 
 	switch (time) {
@@ -667,7 +683,7 @@ static int max77843_muic_set_debounce_time(struct max77843_muic_info *info,
 		ret = regmap_update_bits(max77843->regmap_muic,
 				MAX77843_MUIC_REG_CONTROL4,
 				MAX77843_MUIC_CONTROL4_ADCDBSET_MASK,
-				time << CONTROL4_ADCDBSET_SHIFT);
+				time << MAX77843_MUIC_CONTROL4_ADCDBSET_SHIFT);
 		if (ret < 0) {
 			dev_err(info->dev, "Cannot write MUIC regmap\n");
 			return ret;
@@ -681,7 +697,7 @@ static int max77843_muic_set_debounce_time(struct max77843_muic_info *info,
 	return 0;
 }
 
-static int max77843_init_muic_regmap(struct max77843 *max77843)
+static int max77843_init_muic_regmap(struct max77693_dev *max77843)
 {
 	int ret;
 
@@ -720,7 +736,7 @@ err_muic_i2c:
 
 static int max77843_muic_probe(struct platform_device *pdev)
 {
-	struct max77843 *max77843 = dev_get_drvdata(pdev->dev.parent);
+	struct max77693_dev *max77843 = dev_get_drvdata(pdev->dev.parent);
 	struct max77843_muic_info *info;
 	unsigned int id;
 	int i, ret;
@@ -768,7 +784,7 @@ static int max77843_muic_probe(struct platform_device *pdev)
 	max77843_muic_set_debounce_time(info, MAX77843_DEBOUNCE_TIME_25MS);
 
 	/* Set initial path for UART */
-	max77843_muic_set_path(info, CONTROL1_SW_UART, true);
+	max77843_muic_set_path(info, MAX77843_MUIC_CONTROL1_SW_UART, true);
 
 	/* Check revision number of MUIC device */
 	ret = regmap_read(max77843->regmap_muic, MAX77843_MUIC_REG_ID, &id);
@@ -781,6 +797,15 @@ static int max77843_muic_probe(struct platform_device *pdev)
 	/* Support virtual irq domain for max77843 MUIC device */
 	INIT_WORK(&info->irq_work, max77843_muic_irq_work);
 
+	/* Clear IRQ bits before request IRQs */
+	ret = regmap_bulk_read(max77843->regmap_muic,
+			MAX77843_MUIC_REG_INT1, info->status,
+			MAX77843_MUIC_IRQ_NUM);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to Clear IRQ bits\n");
+		goto err_muic_irq;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(max77843_muic_irqs); i++) {
 		struct max77843_muic_irq *muic_irq = &max77843_muic_irqs[i];
 		unsigned int virq = 0;
@@ -821,7 +846,7 @@ err_muic_irq:
 static int max77843_muic_remove(struct platform_device *pdev)
 {
 	struct max77843_muic_info *info = platform_get_drvdata(pdev);
-	struct max77843 *max77843 = info->max77843;
+	struct max77693_dev *max77843 = info->max77843;
 
 	cancel_work_sync(&info->irq_work);
 	regmap_del_irq_chip(max77843->irq, max77843->irq_data_muic);
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index 080d5cc27055..93c30a885740 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -28,6 +28,11 @@
 #include <linux/mfd/palmas.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/workqueue.h>
+
+#define USB_GPIO_DEBOUNCE_MS	20	/* ms */
 
 static const unsigned int palmas_extcon_cable[] = {
 	EXTCON_USB,
@@ -35,8 +40,6 @@ static const unsigned int palmas_extcon_cable[] = {
 	EXTCON_NONE,
 };
 
-static const int mutually_exclusive[] = {0x3, 0x0};
-
 static void palmas_usb_wakeup(struct palmas *palmas, int enable)
 {
 	if (enable)
@@ -120,19 +123,54 @@ static irqreturn_t palmas_id_irq_handler(int irq, void *_palmas_usb)
 	return IRQ_HANDLED;
 }
 
+static void palmas_gpio_id_detect(struct work_struct *work)
+{
+	int id;
+	struct palmas_usb *palmas_usb = container_of(to_delayed_work(work),
+						     struct palmas_usb,
+						     wq_detectid);
+	struct extcon_dev *edev = palmas_usb->edev;
+
+	if (!palmas_usb->id_gpiod)
+		return;
+
+	id = gpiod_get_value_cansleep(palmas_usb->id_gpiod);
+
+	if (id) {
+		extcon_set_cable_state_(edev, EXTCON_USB_HOST, false);
+		dev_info(palmas_usb->dev, "USB-HOST cable is detached\n");
+	} else {
+		extcon_set_cable_state_(edev, EXTCON_USB_HOST, true);
+		dev_info(palmas_usb->dev, "USB-HOST cable is attached\n");
+	}
+}
+
+static irqreturn_t palmas_gpio_id_irq_handler(int irq, void *_palmas_usb)
+{
+	struct palmas_usb *palmas_usb = _palmas_usb;
+
+	queue_delayed_work(system_power_efficient_wq, &palmas_usb->wq_detectid,
+			   palmas_usb->sw_debounce_jiffies);
+
+	return IRQ_HANDLED;
+}
+
 static void palmas_enable_irq(struct palmas_usb *palmas_usb)
 {
 	palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
 		PALMAS_USB_VBUS_CTRL_SET,
 		PALMAS_USB_VBUS_CTRL_SET_VBUS_ACT_COMP);
 
-	palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
-		PALMAS_USB_ID_CTRL_SET, PALMAS_USB_ID_CTRL_SET_ID_ACT_COMP);
+	if (palmas_usb->enable_id_detection) {
+		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
+			     PALMAS_USB_ID_CTRL_SET,
+			     PALMAS_USB_ID_CTRL_SET_ID_ACT_COMP);
 
-	palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
-		PALMAS_USB_ID_INT_EN_HI_SET,
-		PALMAS_USB_ID_INT_EN_HI_SET_ID_GND |
-		PALMAS_USB_ID_INT_EN_HI_SET_ID_FLOAT);
+		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
+			     PALMAS_USB_ID_INT_EN_HI_SET,
+			     PALMAS_USB_ID_INT_EN_HI_SET_ID_GND |
+			     PALMAS_USB_ID_INT_EN_HI_SET_ID_FLOAT);
+	}
 
 	if (palmas_usb->enable_vbus_detection)
 		palmas_vbus_irq_handler(palmas_usb->vbus_irq, palmas_usb);
@@ -171,20 +209,37 @@ static int palmas_usb_probe(struct platform_device *pdev)
 			palmas_usb->wakeup = pdata->wakeup;
 	}
 
+	palmas_usb->id_gpiod = devm_gpiod_get_optional(&pdev->dev, "id",
+							GPIOD_IN);
+	if (IS_ERR(palmas_usb->id_gpiod)) {
+		dev_err(&pdev->dev, "failed to get id gpio\n");
+		return PTR_ERR(palmas_usb->id_gpiod);
+	}
+
+	if (palmas_usb->enable_id_detection && palmas_usb->id_gpiod) {
+		palmas_usb->enable_id_detection = false;
+		palmas_usb->enable_gpio_id_detection = true;
+	}
+
+	if (palmas_usb->enable_gpio_id_detection) {
+		u32 debounce;
+
+		if (of_property_read_u32(node, "debounce-delay-ms", &debounce))
+			debounce = USB_GPIO_DEBOUNCE_MS;
+
+		status = gpiod_set_debounce(palmas_usb->id_gpiod,
+					    debounce * 1000);
+		if (status < 0)
+			palmas_usb->sw_debounce_jiffies = msecs_to_jiffies(debounce);
+	}
+
+	INIT_DELAYED_WORK(&palmas_usb->wq_detectid, palmas_gpio_id_detect);
+
 	palmas->usb = palmas_usb;
 	palmas_usb->palmas = palmas;
 
 	palmas_usb->dev	 = &pdev->dev;
 
-	palmas_usb->id_otg_irq = regmap_irq_get_virq(palmas->irq_data,
-						PALMAS_ID_OTG_IRQ);
-	palmas_usb->id_irq = regmap_irq_get_virq(palmas->irq_data,
-						PALMAS_ID_IRQ);
-	palmas_usb->vbus_otg_irq = regmap_irq_get_virq(palmas->irq_data,
-						PALMAS_VBUS_OTG_IRQ);
-	palmas_usb->vbus_irq = regmap_irq_get_virq(palmas->irq_data,
-						PALMAS_VBUS_IRQ);
-
 	palmas_usb_wakeup(palmas, palmas_usb->wakeup);
 
 	platform_set_drvdata(pdev, palmas_usb);
@@ -195,16 +250,18 @@ static int palmas_usb_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "failed to allocate extcon device\n");
 		return -ENOMEM;
 	}
-	palmas_usb->edev->mutually_exclusive = mutually_exclusive;
 
 	status = devm_extcon_dev_register(&pdev->dev, palmas_usb->edev);
 	if (status) {
 		dev_err(&pdev->dev, "failed to register extcon device\n");
-		kfree(palmas_usb->edev->name);
 		return status;
 	}
 
 	if (palmas_usb->enable_id_detection) {
+		palmas_usb->id_otg_irq = regmap_irq_get_virq(palmas->irq_data,
+							     PALMAS_ID_OTG_IRQ);
+		palmas_usb->id_irq = regmap_irq_get_virq(palmas->irq_data,
+							 PALMAS_ID_IRQ);
 		status = devm_request_threaded_irq(palmas_usb->dev,
 				palmas_usb->id_irq,
 				NULL, palmas_id_irq_handler,
@@ -214,12 +271,35 @@ static int palmas_usb_probe(struct platform_device *pdev)
 		if (status < 0) {
 			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->id_irq, status);
-			kfree(palmas_usb->edev->name);
+			return status;
+		}
+	} else if (palmas_usb->enable_gpio_id_detection) {
+		palmas_usb->gpio_id_irq = gpiod_to_irq(palmas_usb->id_gpiod);
+		if (palmas_usb->gpio_id_irq < 0) {
+			dev_err(&pdev->dev, "failed to get id irq\n");
+			return palmas_usb->gpio_id_irq;
+		}
+		status = devm_request_threaded_irq(&pdev->dev,
+						   palmas_usb->gpio_id_irq,
+						   NULL,
+						   palmas_gpio_id_irq_handler,
+						   IRQF_TRIGGER_RISING |
+						   IRQF_TRIGGER_FALLING |
+						   IRQF_ONESHOT,
+						   "palmas_usb_id",
+						   palmas_usb);
+		if (status < 0) {
+			dev_err(&pdev->dev,
+				"failed to request handler for id irq\n");
 			return status;
 		}
 	}
 
 	if (palmas_usb->enable_vbus_detection) {
+		palmas_usb->vbus_otg_irq = regmap_irq_get_virq(palmas->irq_data,
+						       PALMAS_VBUS_OTG_IRQ);
+		palmas_usb->vbus_irq = regmap_irq_get_virq(palmas->irq_data,
+							   PALMAS_VBUS_IRQ);
 		status = devm_request_threaded_irq(palmas_usb->dev,
 				palmas_usb->vbus_irq, NULL,
 				palmas_vbus_irq_handler,
@@ -229,12 +309,13 @@ static int palmas_usb_probe(struct platform_device *pdev)
 		if (status < 0) {
 			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->vbus_irq, status);
-			kfree(palmas_usb->edev->name);
 			return status;
 		}
 	}
 
 	palmas_enable_irq(palmas_usb);
+	/* perform initial detection */
+	palmas_gpio_id_detect(&palmas_usb->wq_detectid.work);
 	device_set_wakeup_capable(&pdev->dev, true);
 	return 0;
 }
@@ -243,7 +324,7 @@ static int palmas_usb_remove(struct platform_device *pdev)
 {
 	struct palmas_usb *palmas_usb = platform_get_drvdata(pdev);
 
-	kfree(palmas_usb->edev->name);
+	cancel_delayed_work_sync(&palmas_usb->wq_detectid);
 
 	return 0;
 }
@@ -258,6 +339,8 @@ static int palmas_usb_suspend(struct device *dev)
 			enable_irq_wake(palmas_usb->vbus_irq);
 		if (palmas_usb->enable_id_detection)
 			enable_irq_wake(palmas_usb->id_irq);
+		if (palmas_usb->enable_gpio_id_detection)
+			enable_irq_wake(palmas_usb->gpio_id_irq);
 	}
 	return 0;
 }
@@ -271,6 +354,8 @@ static int palmas_usb_resume(struct device *dev)
 			disable_irq_wake(palmas_usb->vbus_irq);
 		if (palmas_usb->enable_id_detection)
 			disable_irq_wake(palmas_usb->id_irq);
+		if (palmas_usb->enable_gpio_id_detection)
+			disable_irq_wake(palmas_usb->gpio_id_irq);
 	}
 	return 0;
 };
diff --git a/drivers/extcon/extcon-rt8973a.c b/drivers/extcon/extcon-rt8973a.c
index 92c939221a41..11592e980bc1 100644
--- a/drivers/extcon/extcon-rt8973a.c
+++ b/drivers/extcon/extcon-rt8973a.c
@@ -693,7 +693,6 @@ MODULE_DEVICE_TABLE(i2c, rt8973a_i2c_id);
 static struct i2c_driver rt8973a_muic_i2c_driver = {
 	.driver		= {
 		.name	= "rt8973a",
-		.owner	= THIS_MODULE,
 		.pm	= &rt8973a_muic_pm_ops,
 		.of_match_table = rt8973a_dt_match,
 	},
diff --git a/drivers/extcon/extcon-sm5502.c b/drivers/extcon/extcon-sm5502.c
index 817dece23b4c..0ffefefa2e26 100644
--- a/drivers/extcon/extcon-sm5502.c
+++ b/drivers/extcon/extcon-sm5502.c
@@ -685,7 +685,6 @@ MODULE_DEVICE_TABLE(i2c, sm5502_i2c_id);
 static struct i2c_driver sm5502_muic_i2c_driver = {
 	.driver		= {
 		.name	= "sm5502",
-		.owner	= THIS_MODULE,
 		.pm	= &sm5502_muic_pm_ops,
 		.of_match_table = sm5502_dt_match,
 	},
diff --git a/drivers/extcon/extcon-usb-gpio.c b/drivers/extcon/extcon-usb-gpio.c
index a2a44536a608..2b2fecffb1ad 100644
--- a/drivers/extcon/extcon-usb-gpio.c
+++ b/drivers/extcon/extcon-usb-gpio.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/extcon.h>
+#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 76157ab9faf3..a07addde297b 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -124,25 +124,35 @@ static int find_cable_index_by_id(struct extcon_dev *edev, const unsigned int id
 	return -EINVAL;
 }
 
-static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
+static int find_cable_id_by_name(struct extcon_dev *edev, const char *name)
 {
-	unsigned int id = EXTCON_NONE;
+	int id = -EINVAL;
 	int i = 0;
 
-	if (edev->max_supported == 0)
-		return -EINVAL;
-
-	/* Find the the number of extcon cable */
+	/* Find the id of extcon cable */
 	while (extcon_name[i]) {
 		if (!strncmp(extcon_name[i], name, CABLE_NAME_MAX)) {
 			id = i;
 			break;
 		}
+		i++;
 	}
 
-	if (id == EXTCON_NONE)
+	return id;
+}
+
+static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
+{
+	int id;
+
+	if (edev->max_supported == 0)
 		return -EINVAL;
 
+	/* Find the the number of extcon cable */
+	id = find_cable_id_by_name(edev, name);
+	if (id < 0)
+		return id;
+
 	return find_cable_index_by_id(edev, id);
 }
 
@@ -162,14 +172,6 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr,
 	int i, count = 0;
 	struct extcon_dev *edev = dev_get_drvdata(dev);
 
-	if (edev->print_state) {
-		int ret = edev->print_state(edev, buf);
-
-		if (ret >= 0)
-			return ret;
-		/* Use default if failed */
-	}
-
 	if (edev->max_supported == 0)
 		return sprintf(buf, "%u\n", edev->state);
 
@@ -228,9 +230,11 @@ static ssize_t cable_state_show(struct device *dev,
 	struct extcon_cable *cable = container_of(attr, struct extcon_cable,
 						  attr_state);
 
+	int i = cable->cable_index;
+
 	return sprintf(buf, "%d\n",
 		       extcon_get_cable_state_(cable->edev,
-					       cable->cable_index));
+					       cable->edev->supported_cable[i]));
 }
 
 /**
@@ -260,23 +264,31 @@ int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state)
 	unsigned long flags;
 	bool attached;
 
+	if (!edev)
+		return -EINVAL;
+
 	spin_lock_irqsave(&edev->lock, flags);
 
 	if (edev->state != ((edev->state & ~mask) | (state & mask))) {
+		u32 old_state;
+
 		if (check_mutually_exclusive(edev, (edev->state & ~mask) |
 						   (state & mask))) {
 			spin_unlock_irqrestore(&edev->lock, flags);
 			return -EPERM;
 		}
 
-		for (index = 0; index < edev->max_supported; index++) {
-			if (is_extcon_changed(edev->state, state, index, &attached))
-				raw_notifier_call_chain(&edev->nh[index], attached, edev);
-		}
-
+		old_state = edev->state;
 		edev->state &= ~mask;
 		edev->state |= state & mask;
 
+		for (index = 0; index < edev->max_supported; index++) {
+			if (is_extcon_changed(old_state, edev->state, index,
+					      &attached))
+				raw_notifier_call_chain(&edev->nh[index],
+							attached, edev);
+		}
+
 		/* This could be in interrupt handler */
 		prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
 		if (prop_buf) {
@@ -328,6 +340,9 @@ EXPORT_SYMBOL_GPL(extcon_update_state);
  */
 int extcon_set_state(struct extcon_dev *edev, u32 state)
 {
+	if (!edev)
+		return -EINVAL;
+
 	return extcon_update_state(edev, 0xffffffff, state);
 }
 EXPORT_SYMBOL_GPL(extcon_set_state);
@@ -341,6 +356,9 @@ int extcon_get_cable_state_(struct extcon_dev *edev, const unsigned int id)
 {
 	int index;
 
+	if (!edev)
+		return -EINVAL;
+
 	index = find_cable_index_by_id(edev, id);
 	if (index < 0)
 		return index;
@@ -361,8 +379,13 @@ EXPORT_SYMBOL_GPL(extcon_get_cable_state_);
  */
 int extcon_get_cable_state(struct extcon_dev *edev, const char *cable_name)
 {
-	return extcon_get_cable_state_(edev, find_cable_index_by_name
-						(edev, cable_name));
+	int id;
+
+	id = find_cable_id_by_name(edev, cable_name);
+	if (id < 0)
+		return id;
+
+	return extcon_get_cable_state_(edev, id);
 }
 EXPORT_SYMBOL_GPL(extcon_get_cable_state);
 
@@ -380,6 +403,9 @@ int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id,
 	u32 state;
 	int index;
 
+	if (!edev)
+		return -EINVAL;
+
 	index = find_cable_index_by_id(edev, id);
 	if (index < 0)
 		return index;
@@ -404,8 +430,13 @@ EXPORT_SYMBOL_GPL(extcon_set_cable_state_);
 int extcon_set_cable_state(struct extcon_dev *edev,
 			const char *cable_name, bool cable_state)
 {
-	return extcon_set_cable_state_(edev, find_cable_index_by_name
-					(edev, cable_name), cable_state);
+	int id;
+
+	id = find_cable_id_by_name(edev, cable_name);
+	if (id < 0)
+		return id;
+
+	return extcon_set_cable_state_(edev, id, cable_state);
 }
 EXPORT_SYMBOL_GPL(extcon_set_cable_state);
 
@@ -417,6 +448,9 @@ struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name)
 {
 	struct extcon_dev *sd;
 
+	if (!extcon_name)
+		return ERR_PTR(-EINVAL);
+
 	mutex_lock(&extcon_dev_list_lock);
 	list_for_each_entry(sd, &extcon_dev_list, entry) {
 		if (!strcmp(sd->name, extcon_name))
@@ -545,6 +579,9 @@ int extcon_register_notifier(struct extcon_dev *edev, unsigned int id,
 	unsigned long flags;
 	int ret, idx;
 
+	if (!edev || !nb)
+		return -EINVAL;
+
 	idx = find_cable_index_by_id(edev, id);
 
 	spin_lock_irqsave(&edev->lock, flags);
@@ -567,6 +604,9 @@ int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id,
 	unsigned long flags;
 	int ret, idx;
 
+	if (!edev || !nb)
+		return -EINVAL;
+
 	idx = find_cable_index_by_id(edev, id);
 
 	spin_lock_irqsave(&edev->lock, flags);
@@ -627,6 +667,9 @@ struct extcon_dev *extcon_dev_allocate(const unsigned int *supported_cable)
 {
 	struct extcon_dev *edev;
 
+	if (!supported_cable)
+		return ERR_PTR(-EINVAL);
+
 	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
 	if (!edev)
 		return ERR_PTR(-ENOMEM);
@@ -727,7 +770,7 @@ int extcon_dev_register(struct extcon_dev *edev)
 			return ret;
 	}
 
-	if (!edev->supported_cable)
+	if (!edev || !edev->supported_cable)
 		return -EINVAL;
 
 	for (; edev->supported_cable[index] != EXTCON_NONE; index++);
@@ -933,6 +976,9 @@ void extcon_dev_unregister(struct extcon_dev *edev)
 {
 	int index;
 
+	if (!edev)
+		return;
+
 	mutex_lock(&extcon_dev_list_lock);
 	list_del(&edev->entry);
 	mutex_unlock(&extcon_dev_list_lock);
@@ -1039,6 +1085,9 @@ struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index)
 	struct device_node *node;
 	struct extcon_dev *edev;
 
+	if (!dev)
+		return ERR_PTR(-EINVAL);
+
 	if (!dev->of_node) {
 		dev_err(dev, "device does not have a device node entry\n");
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 99c69a3205c4..d8de6a8dd4de 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -5,6 +5,9 @@
 
 menu "Firmware Drivers"
 
+config ARM_PSCI_FW
+	bool
+
 config EDD
 	tristate "BIOS Enhanced Disk Drive calls determine boot disk"
 	depends on X86
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 4a4b897f9314..000830fc6707 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -1,6 +1,7 @@
 #
 # Makefile for the linux kernel.
 #
+obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
 obj-$(CONFIG_DMI)		+= dmi_scan.o
 obj-$(CONFIG_DMI_SYSFS)		+= dmi-sysfs.o
 obj-$(CONFIG_EDD)		+= edd.o
diff --git a/drivers/firmware/broadcom/bcm47xx_nvram.c b/drivers/firmware/broadcom/bcm47xx_nvram.c
index 87add3fdce52..e41594510b97 100644
--- a/drivers/firmware/broadcom/bcm47xx_nvram.c
+++ b/drivers/firmware/broadcom/bcm47xx_nvram.c
@@ -245,4 +245,4 @@ char *bcm47xx_nvram_get_contents(size_t *nvram_size)
 }
 EXPORT_SYMBOL(bcm47xx_nvram_get_contents);
 
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 4fd9961d552e..d42537425438 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -305,10 +305,17 @@ const char *cper_mem_err_unpack(struct trace_seq *p,
 	return ret;
 }
 
-static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
+	int len)
 {
 	struct cper_mem_err_compact cmem;
 
+	/* Don't trust UEFI 2.1/2.2 structure with bad validation bits */
+	if (len == sizeof(struct cper_sec_mem_err_old) &&
+	    (mem->validation_bits & ~(CPER_MEM_VALID_RANK_NUMBER - 1))) {
+		pr_err(FW_WARN "valid bits set for fields beyond structure\n");
+		return;
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
 	if (mem->validation_bits & CPER_MEM_VALID_PA)
@@ -405,8 +412,10 @@ static void cper_estatus_print_section(
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
 		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
 		printk("%s""section_type: memory error\n", newpfx);
-		if (gdata->error_data_length >= sizeof(*mem_err))
-			cper_print_mem(newpfx, mem_err);
+		if (gdata->error_data_length >=
+		    sizeof(struct cper_sec_mem_err_old))
+			cper_print_mem(newpfx, mem_err,
+				       gdata->error_data_length);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9fa8084a7c8d..d6144e3b97c5 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -58,6 +58,11 @@ bool efi_runtime_disabled(void)
 
 static int __init parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
new file mode 100644
index 000000000000..42700f09a8c5
--- /dev/null
+++ b/drivers/firmware/psci.c
@@ -0,0 +1,382 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 ARM Limited
+ */
+
+#define pr_fmt(fmt) "psci: " fmt
+
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <linux/of.h>
+#include <linux/pm.h>
+#include <linux/printk.h>
+#include <linux/psci.h>
+#include <linux/reboot.h>
+
+#include <uapi/linux/psci.h>
+
+#include <asm/cputype.h>
+#include <asm/system_misc.h>
+#include <asm/smp_plat.h>
+
+/*
+ * While a 64-bit OS can make calls with SMC32 calling conventions, for some
+ * calls it is necessary to use SMC64 to pass or return 64-bit values. For such
+ * calls PSCI_0_2_FN_NATIVE(x) will choose the appropriate (native-width)
+ * function ID.
+ */
+#ifdef CONFIG_64BIT
+#define PSCI_0_2_FN_NATIVE(name)	PSCI_0_2_FN64_##name
+#else
+#define PSCI_0_2_FN_NATIVE(name)	PSCI_0_2_FN_##name
+#endif
+
+/*
+ * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF
+ * calls to its resident CPU, so we must avoid issuing those. We never migrate
+ * a Trusted OS even if it claims to be capable of migration -- doing so will
+ * require cooperation with a Trusted OS driver.
+ */
+static int resident_cpu = -1;
+
+bool psci_tos_resident_on(int cpu)
+{
+	return cpu == resident_cpu;
+}
+
+struct psci_operations psci_ops;
+
+typedef unsigned long (psci_fn)(unsigned long, unsigned long,
+				unsigned long, unsigned long);
+asmlinkage psci_fn __invoke_psci_fn_hvc;
+asmlinkage psci_fn __invoke_psci_fn_smc;
+static psci_fn *invoke_psci_fn;
+
+enum psci_function {
+	PSCI_FN_CPU_SUSPEND,
+	PSCI_FN_CPU_ON,
+	PSCI_FN_CPU_OFF,
+	PSCI_FN_MIGRATE,
+	PSCI_FN_MAX,
+};
+
+static u32 psci_function_id[PSCI_FN_MAX];
+
+static int psci_to_linux_errno(int errno)
+{
+	switch (errno) {
+	case PSCI_RET_SUCCESS:
+		return 0;
+	case PSCI_RET_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case PSCI_RET_INVALID_PARAMS:
+		return -EINVAL;
+	case PSCI_RET_DENIED:
+		return -EPERM;
+	};
+
+	return -EINVAL;
+}
+
+static u32 psci_get_version(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
+}
+
+static int psci_cpu_suspend(u32 state, unsigned long entry_point)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
+	err = invoke_psci_fn(fn, state, entry_point, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_off(u32 state)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_OFF];
+	err = invoke_psci_fn(fn, state, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_ON];
+	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_migrate(unsigned long cpuid)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_MIGRATE];
+	err = invoke_psci_fn(fn, cpuid, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_affinity_info(unsigned long target_affinity,
+		unsigned long lowest_affinity_level)
+{
+	return invoke_psci_fn(PSCI_0_2_FN_NATIVE(AFFINITY_INFO),
+			      target_affinity, lowest_affinity_level, 0);
+}
+
+static int psci_migrate_info_type(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0);
+}
+
+static unsigned long psci_migrate_info_up_cpu(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN_NATIVE(MIGRATE_INFO_UP_CPU),
+			      0, 0, 0);
+}
+
+static int get_set_conduit_method(struct device_node *np)
+{
+	const char *method;
+
+	pr_info("probing for conduit method from DT.\n");
+
+	if (of_property_read_string(np, "method", &method)) {
+		pr_warn("missing \"method\" property\n");
+		return -ENXIO;
+	}
+
+	if (!strcmp("hvc", method)) {
+		invoke_psci_fn = __invoke_psci_fn_hvc;
+	} else if (!strcmp("smc", method)) {
+		invoke_psci_fn = __invoke_psci_fn_smc;
+	} else {
+		pr_warn("invalid \"method\" property: %s\n", method);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+}
+
+static void psci_sys_poweroff(void)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
+}
+
+/*
+ * Detect the presence of a resident Trusted OS which may cause CPU_OFF to
+ * return DENIED (which would be fatal).
+ */
+static void __init psci_init_migrate(void)
+{
+	unsigned long cpuid;
+	int type, cpu = -1;
+
+	type = psci_ops.migrate_info_type();
+
+	if (type == PSCI_0_2_TOS_MP) {
+		pr_info("Trusted OS migration not required\n");
+		return;
+	}
+
+	if (type == PSCI_RET_NOT_SUPPORTED) {
+		pr_info("MIGRATE_INFO_TYPE not supported.\n");
+		return;
+	}
+
+	if (type != PSCI_0_2_TOS_UP_MIGRATE &&
+	    type != PSCI_0_2_TOS_UP_NO_MIGRATE) {
+		pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type);
+		return;
+	}
+
+	cpuid = psci_migrate_info_up_cpu();
+	if (cpuid & ~MPIDR_HWID_BITMASK) {
+		pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n",
+			cpuid);
+		return;
+	}
+
+	cpu = get_logical_index(cpuid);
+	resident_cpu = cpu >= 0 ? cpu : -1;
+
+	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
+}
+
+static void __init psci_0_2_set_functions(void)
+{
+	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_NATIVE(CPU_SUSPEND);
+	psci_ops.cpu_suspend = psci_cpu_suspend;
+
+	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
+	psci_ops.cpu_off = psci_cpu_off;
+
+	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_NATIVE(CPU_ON);
+	psci_ops.cpu_on = psci_cpu_on;
+
+	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_NATIVE(MIGRATE);
+	psci_ops.migrate = psci_migrate;
+
+	psci_ops.affinity_info = psci_affinity_info;
+
+	psci_ops.migrate_info_type = psci_migrate_info_type;
+
+	arm_pm_restart = psci_sys_reset;
+
+	pm_power_off = psci_sys_poweroff;
+}
+
+/*
+ * Probe function for PSCI firmware versions >= 0.2
+ */
+static int __init psci_probe(void)
+{
+	u32 ver = psci_get_version();
+
+	pr_info("PSCIv%d.%d detected in firmware.\n",
+			PSCI_VERSION_MAJOR(ver),
+			PSCI_VERSION_MINOR(ver));
+
+	if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) {
+		pr_err("Conflicting PSCI version detected.\n");
+		return -EINVAL;
+	}
+
+	psci_0_2_set_functions();
+
+	psci_init_migrate();
+
+	return 0;
+}
+
+typedef int (*psci_initcall_t)(const struct device_node *);
+
+/*
+ * PSCI init function for PSCI versions >=0.2
+ *
+ * Probe based on PSCI PSCI_VERSION function
+ */
+static int __init psci_0_2_init(struct device_node *np)
+{
+	int err;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+	/*
+	 * Starting with v0.2, the PSCI specification introduced a call
+	 * (PSCI_VERSION) that allows probing the firmware version, so
+	 * that PSCI function IDs and version specific initialization
+	 * can be carried out according to the specific version reported
+	 * by firmware
+	 */
+	err = psci_probe();
+
+out_put_node:
+	of_node_put(np);
+	return err;
+}
+
+/*
+ * PSCI < v0.2 get PSCI Function IDs via DT.
+ */
+static int __init psci_0_1_init(struct device_node *np)
+{
+	u32 id;
+	int err;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	pr_info("Using PSCI v0.1 Function IDs from DT\n");
+
+	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
+		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
+		psci_ops.cpu_suspend = psci_cpu_suspend;
+	}
+
+	if (!of_property_read_u32(np, "cpu_off", &id)) {
+		psci_function_id[PSCI_FN_CPU_OFF] = id;
+		psci_ops.cpu_off = psci_cpu_off;
+	}
+
+	if (!of_property_read_u32(np, "cpu_on", &id)) {
+		psci_function_id[PSCI_FN_CPU_ON] = id;
+		psci_ops.cpu_on = psci_cpu_on;
+	}
+
+	if (!of_property_read_u32(np, "migrate", &id)) {
+		psci_function_id[PSCI_FN_MIGRATE] = id;
+		psci_ops.migrate = psci_migrate;
+	}
+
+out_put_node:
+	of_node_put(np);
+	return err;
+}
+
+static const struct of_device_id const psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci",	.data = psci_0_1_init},
+	{ .compatible = "arm,psci-0.2",	.data = psci_0_2_init},
+	{},
+};
+
+int __init psci_dt_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *matched_np;
+	psci_initcall_t init_fn;
+
+	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
+
+	if (!np)
+		return -ENODEV;
+
+	init_fn = (psci_initcall_t)matched_np->data;
+	return init_fn(np);
+}
+
+#ifdef CONFIG_ACPI
+/*
+ * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's
+ * explicitly clarified in SBBR
+ */
+int __init psci_acpi_init(void)
+{
+	if (!acpi_psci_present()) {
+		pr_info("is not implemented in ACPI.\n");
+		return -EOPNOTSUPP;
+	}
+
+	pr_info("probing for conduit method from ACPI.\n");
+
+	if (acpi_psci_use_hvc())
+		invoke_psci_fn = __invoke_psci_fn_hvc;
+	else
+		invoke_psci_fn = __invoke_psci_fn_smc;
+
+	return psci_probe();
+}
+#endif
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 1bd6f9c34331..29e6850665eb 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -24,7 +24,6 @@
 #include <linux/err.h>
 #include <linux/qcom_scm.h>
 
-#include <asm/outercache.h>
 #include <asm/cacheflush.h>
 
 #include "qcom_scm.h"
@@ -219,8 +218,7 @@ static int __qcom_scm_call(const struct qcom_scm_command *cmd)
 	 * Flush the command buffer so that the secure world sees
 	 * the correct data.
 	 */
-	__cpuc_flush_dcache_area((void *)cmd, cmd->len);
-	outer_flush_range(cmd_addr, cmd_addr + cmd->len);
+	secure_flush_area(cmd, cmd->len);
 
 	ret = smc(cmd_addr);
 	if (ret < 0)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 8f1fe739c985..b4fc9e4d24c6 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -113,7 +113,6 @@ config GPIO_74XX_MMIO
 config GPIO_ALTERA
 	tristate "Altera GPIO"
 	depends on OF_GPIO
-	select GPIO_GENERIC
 	select GPIOLIB_IRQCHIP
 	help
 	  Say Y or M here to build support for the Altera PIO device.
@@ -131,6 +130,7 @@ config GPIO_BRCMSTB
 	default y if ARCH_BRCMSTB
 	depends on OF_GPIO && (ARCH_BRCMSTB || COMPILE_TEST)
 	select GPIO_GENERIC
+	select GPIOLIB_IRQCHIP
 	help
 	  Say yes here to enable GPIO support for Broadcom STB (BCM7XXX) SoCs.
 
@@ -172,6 +172,7 @@ config GPIO_ETRAXFS
 	depends on CRIS || COMPILE_TEST
 	depends on OF
 	select GPIO_GENERIC
+	select GPIOLIB_IRQCHIP
 	help
 	  Say yes here to support the GPIO controller on Axis ETRAX FS SoCs.
 
@@ -308,7 +309,6 @@ config GPIO_MVEBU
 	def_bool y
 	depends on PLAT_ORION
 	depends on OF
-	select GPIO_GENERIC
 	select GENERIC_IRQ_CHIP
 
 config GPIO_MXC
@@ -1005,6 +1005,12 @@ config GPIO_MC33880
 	  SPI driver for Freescale MC33880 high-side/low-side switch.
 	  This provides GPIO interface supporting inputs and outputs.
 
+config GPIO_ZX
+	bool "ZTE ZX GPIO support"
+	select GPIOLIB_IRQCHIP
+	help
+	  Say yes here to support the GPIO device on ZTE ZX SoCs.
+
 endmenu
 
 menu "USB GPIO expanders"
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index f82cd678ce08..f79a7c482a99 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_GPIO_ADP5588)	+= gpio-adp5588.o
 obj-$(CONFIG_GPIO_ALTERA)  	+= gpio-altera.o
 obj-$(CONFIG_GPIO_AMD8111)	+= gpio-amd8111.o
 obj-$(CONFIG_GPIO_ARIZONA)	+= gpio-arizona.o
+obj-$(CONFIG_ATH79)		+= gpio-ath79.o
 obj-$(CONFIG_GPIO_BCM_KONA)	+= gpio-bcm-kona.o
 obj-$(CONFIG_GPIO_BRCMSTB)	+= gpio-brcmstb.o
 obj-$(CONFIG_GPIO_BT8XX)	+= gpio-bt8xx.o
@@ -116,3 +117,4 @@ obj-$(CONFIG_GPIO_XLP)		+= gpio-xlp.o
 obj-$(CONFIG_GPIO_XTENSA)	+= gpio-xtensa.o
 obj-$(CONFIG_GPIO_ZEVIO)	+= gpio-zevio.o
 obj-$(CONFIG_GPIO_ZYNQ)		+= gpio-zynq.o
+obj-$(CONFIG_GPIO_ZX)		+= gpio-zx.o
diff --git a/drivers/gpio/devres.c b/drivers/gpio/devres.c
index 07ba82317ece..903fcf4d04a0 100644
--- a/drivers/gpio/devres.c
+++ b/drivers/gpio/devres.c
@@ -59,13 +59,13 @@ static int devm_gpiod_match_array(struct device *dev, void *res, void *data)
  * automatically disposed on driver detach. See gpiod_get() for detailed
  * information about behavior and return values.
  */
-struct gpio_desc *__must_check __devm_gpiod_get(struct device *dev,
+struct gpio_desc *__must_check devm_gpiod_get(struct device *dev,
 					      const char *con_id,
 					      enum gpiod_flags flags)
 {
 	return devm_gpiod_get_index(dev, con_id, 0, flags);
 }
-EXPORT_SYMBOL(__devm_gpiod_get);
+EXPORT_SYMBOL(devm_gpiod_get);
 
 /**
  * devm_gpiod_get_optional - Resource-managed gpiod_get_optional()
@@ -77,13 +77,13 @@ EXPORT_SYMBOL(__devm_gpiod_get);
  * are automatically disposed on driver detach. See gpiod_get_optional() for
  * detailed information about behavior and return values.
  */
-struct gpio_desc *__must_check __devm_gpiod_get_optional(struct device *dev,
+struct gpio_desc *__must_check devm_gpiod_get_optional(struct device *dev,
 						       const char *con_id,
 						       enum gpiod_flags flags)
 {
 	return devm_gpiod_get_index_optional(dev, con_id, 0, flags);
 }
-EXPORT_SYMBOL(__devm_gpiod_get_optional);
+EXPORT_SYMBOL(devm_gpiod_get_optional);
 
 /**
  * devm_gpiod_get_index - Resource-managed gpiod_get_index()
@@ -96,7 +96,7 @@ EXPORT_SYMBOL(__devm_gpiod_get_optional);
  * automatically disposed on driver detach. See gpiod_get_index() for detailed
  * information about behavior and return values.
  */
-struct gpio_desc *__must_check __devm_gpiod_get_index(struct device *dev,
+struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev,
 						    const char *con_id,
 						    unsigned int idx,
 						    enum gpiod_flags flags)
@@ -120,7 +120,7 @@ struct gpio_desc *__must_check __devm_gpiod_get_index(struct device *dev,
 
 	return desc;
 }
-EXPORT_SYMBOL(__devm_gpiod_get_index);
+EXPORT_SYMBOL(devm_gpiod_get_index);
 
 /**
  * devm_get_gpiod_from_child - get a GPIO descriptor from a device's child node
@@ -182,10 +182,10 @@ EXPORT_SYMBOL(devm_get_gpiod_from_child);
  * gpiod_get_index_optional() for detailed information about behavior and
  * return values.
  */
-struct gpio_desc *__must_check __devm_gpiod_get_index_optional(struct device *dev,
+struct gpio_desc *__must_check devm_gpiod_get_index_optional(struct device *dev,
 							     const char *con_id,
 							     unsigned int index,
-							 enum gpiod_flags flags)
+							     enum gpiod_flags flags)
 {
 	struct gpio_desc *desc;
 
@@ -197,7 +197,7 @@ struct gpio_desc *__must_check __devm_gpiod_get_index_optional(struct device *de
 
 	return desc;
 }
-EXPORT_SYMBOL(__devm_gpiod_get_index_optional);
+EXPORT_SYMBOL(devm_gpiod_get_index_optional);
 
 /**
  * devm_gpiod_get_array - Resource-managed gpiod_get_array()
diff --git a/drivers/gpio/gpio-74xx-mmio.c b/drivers/gpio/gpio-74xx-mmio.c
index 0763655cca6c..6ed7c0fb3378 100644
--- a/drivers/gpio/gpio-74xx-mmio.c
+++ b/drivers/gpio/gpio-74xx-mmio.c
@@ -129,7 +129,7 @@ static int mmio_74xx_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(dat))
 		return PTR_ERR(dat);
 
-	priv->flags = (unsigned)of_id->data;
+	priv->flags = (uintptr_t) of_id->data;
 
 	err = bgpio_init(&priv->bgc, &pdev->dev,
 			 DIV_ROUND_UP(MMIO_74XX_BIT_CNT(priv->flags), 8),
diff --git a/drivers/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c
index d3fe6a6776da..984186ee58a0 100644
--- a/drivers/gpio/gpio-adp5588.c
+++ b/drivers/gpio/gpio-adp5588.c
@@ -305,15 +305,7 @@ static int adp5588_irq_setup(struct adp5588_gpio *dev)
 		irq_set_chip_and_handler(irq, &adp5588_irq_chip,
 					 handle_level_irq);
 		irq_set_nested_thread(irq, 1);
-#ifdef CONFIG_ARM
-		/*
-		 * ARM needs us to explicitly flag the IRQ as VALID,
-		 * once we do so, it will also set the noprobe.
-		 */
-		set_irq_flags(irq, IRQF_VALID);
-#else
-		irq_set_noprobe(irq);
-#endif
+		irq_modify_status(irq, IRQ_NOREQUEST, IRQ_NOPROBE);
 	}
 
 	ret = request_threaded_irq(client->irq,
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 0f3d336d6303..9b7e0b3db387 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -338,9 +338,9 @@ static int altera_gpio_remove(struct platform_device *pdev)
 {
 	struct altera_gpio_chip *altera_gc = platform_get_drvdata(pdev);
 
-	gpiochip_remove(&altera_gc->mmchip.gc);
+	of_mm_gpiochip_remove(&altera_gc->mmchip);
 
-	return -EIO;
+	return 0;
 }
 
 static const struct of_device_id altera_gpio_of_match[] = {
diff --git a/arch/mips/ath79/gpio.c b/drivers/gpio/gpio-ath79.c
index f59ccb26520a..03b995304ad6 100644
--- a/arch/mips/ath79/gpio.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -24,8 +24,6 @@
 #include <linux/of_device.h>
 
 #include <asm/mach-ath79/ar71xx_regs.h>
-#include <asm/mach-ath79/ath79.h>
-#include "common.h"
 
 static void __iomem *ath79_gpio_base;
 static u32 ath79_gpio_count;
@@ -139,47 +137,6 @@ static struct gpio_chip ath79_gpio_chip = {
 	.base			= 0,
 };
 
-static void __iomem *ath79_gpio_get_function_reg(void)
-{
-	u32 reg = 0;
-
-	if (soc_is_ar71xx() ||
-	    soc_is_ar724x() ||
-	    soc_is_ar913x() ||
-	    soc_is_ar933x())
-		reg = AR71XX_GPIO_REG_FUNC;
-	else if (soc_is_ar934x())
-		reg = AR934X_GPIO_REG_FUNC;
-	else
-		BUG();
-
-	return ath79_gpio_base + reg;
-}
-
-void ath79_gpio_function_setup(u32 set, u32 clear)
-{
-	void __iomem *reg = ath79_gpio_get_function_reg();
-	unsigned long flags;
-
-	spin_lock_irqsave(&ath79_gpio_lock, flags);
-
-	__raw_writel((__raw_readl(reg) & ~clear) | set, reg);
-	/* flush write */
-	__raw_readl(reg);
-
-	spin_unlock_irqrestore(&ath79_gpio_lock, flags);
-}
-
-void ath79_gpio_function_enable(u32 mask)
-{
-	ath79_gpio_function_setup(mask, 0);
-}
-
-void ath79_gpio_function_disable(u32 mask)
-{
-	ath79_gpio_function_setup(0, mask);
-}
-
 static const struct of_device_id ath79_gpio_of_match[] = {
 	{ .compatible = "qca,ar7100-gpio" },
 	{ .compatible = "qca,ar9340-gpio" },
@@ -245,35 +202,3 @@ static struct platform_driver ath79_gpio_driver = {
 };
 
 module_platform_driver(ath79_gpio_driver);
-
-int gpio_get_value(unsigned gpio)
-{
-	if (gpio < ath79_gpio_count)
-		return __ath79_gpio_get_value(gpio);
-
-	return __gpio_get_value(gpio);
-}
-EXPORT_SYMBOL(gpio_get_value);
-
-void gpio_set_value(unsigned gpio, int value)
-{
-	if (gpio < ath79_gpio_count)
-		__ath79_gpio_set_value(gpio, value);
-	else
-		__gpio_set_value(gpio, value);
-}
-EXPORT_SYMBOL(gpio_set_value);
-
-int gpio_to_irq(unsigned gpio)
-{
-	/* FIXME */
-	return -EINVAL;
-}
-EXPORT_SYMBOL(gpio_to_irq);
-
-int irq_to_gpio(unsigned irq)
-{
-	/* FIXME */
-	return -EINVAL;
-}
-EXPORT_SYMBOL(irq_to_gpio);
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 40343fa92c7b..31b90ac15204 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -438,7 +438,7 @@ static void bcm_kona_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 	void __iomem *reg_base;
 	int bit, bank_id;
 	unsigned long sta;
-	struct bcm_kona_gpio_bank *bank = irq_get_handler_data(irq);
+	struct bcm_kona_gpio_bank *bank = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
 	chained_irq_enter(chip, desc);
@@ -525,11 +525,7 @@ static int bcm_kona_gpio_irq_map(struct irq_domain *d, unsigned int irq,
 		return ret;
 	irq_set_lockdep_class(irq, &gpio_lock_class);
 	irq_set_chip_and_handler(irq, &bcm_gpio_irq_chip, handle_simple_irq);
-#ifdef CONFIG_ARM
-	set_irq_flags(irq, IRQF_VALID);
-#else
 	irq_set_noprobe(irq);
-#endif
 
 	return 0;
 }
@@ -644,17 +640,6 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev)
 		dev_err(dev, "Couldn't add GPIO chip -- %d\n", ret);
 		goto err_irq_domain;
 	}
-	for (i = 0; i < chip->ngpio; i++) {
-		int irq = bcm_kona_gpio_to_irq(chip, i);
-		irq_set_lockdep_class(irq, &gpio_lock_class);
-		irq_set_chip_and_handler(irq, &bcm_gpio_irq_chip,
-					 handle_simple_irq);
-#ifdef CONFIG_ARM
-		set_irq_flags(irq, IRQF_VALID);
-#else
-		irq_set_noprobe(irq);
-#endif
-	}
 	for (i = 0; i < kona_gpio->num_bank; i++) {
 		bank = &kona_gpio->banks[i];
 		irq_set_chained_handler_and_data(bank->irq,
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
index 7a3cb1fa0a76..9ea86d2ac054 100644
--- a/drivers/gpio/gpio-brcmstb.c
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -17,6 +17,10 @@
 #include <linux/of_irq.h>
 #include <linux/module.h>
 #include <linux/basic_mmio_gpio.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/interrupt.h>
+#include <linux/reboot.h>
 
 #define GIO_BANK_SIZE           0x20
 #define GIO_ODEN(bank)          (((bank) * GIO_BANK_SIZE) + 0x00)
@@ -34,14 +38,18 @@ struct brcmstb_gpio_bank {
 	struct bgpio_chip bgc;
 	struct brcmstb_gpio_priv *parent_priv;
 	u32 width;
+	struct irq_chip irq_chip;
 };
 
 struct brcmstb_gpio_priv {
 	struct list_head bank_list;
 	void __iomem *reg_base;
-	int num_banks;
 	struct platform_device *pdev;
+	int parent_irq;
 	int gpio_base;
+	bool can_wake;
+	int parent_wake_irq;
+	struct notifier_block reboot_notifier;
 };
 
 #define MAX_GPIO_PER_BANK           32
@@ -63,6 +71,203 @@ brcmstb_gpio_gc_to_priv(struct gpio_chip *gc)
 	return bank->parent_priv;
 }
 
+static void brcmstb_gpio_set_imask(struct brcmstb_gpio_bank *bank,
+		unsigned int offset, bool enable)
+{
+	struct bgpio_chip *bgc = &bank->bgc;
+	struct brcmstb_gpio_priv *priv = bank->parent_priv;
+	u32 mask = bgc->pin2mask(bgc, offset);
+	u32 imask;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bgc->lock, flags);
+	imask = bgc->read_reg(priv->reg_base + GIO_MASK(bank->id));
+	if (enable)
+		imask |= mask;
+	else
+		imask &= ~mask;
+	bgc->write_reg(priv->reg_base + GIO_MASK(bank->id), imask);
+	spin_unlock_irqrestore(&bgc->lock, flags);
+}
+
+/* -------------------- IRQ chip functions -------------------- */
+
+static void brcmstb_gpio_irq_mask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+
+	brcmstb_gpio_set_imask(bank, d->hwirq, false);
+}
+
+static void brcmstb_gpio_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+
+	brcmstb_gpio_set_imask(bank, d->hwirq, true);
+}
+
+static int brcmstb_gpio_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+	struct brcmstb_gpio_priv *priv = bank->parent_priv;
+	u32 mask = BIT(d->hwirq);
+	u32 edge_insensitive, iedge_insensitive;
+	u32 edge_config, iedge_config;
+	u32 level, ilevel;
+	unsigned long flags;
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_LOW:
+		level = 0;
+		edge_config = 0;
+		edge_insensitive = 0;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		level = mask;
+		edge_config = 0;
+		edge_insensitive = 0;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		level = 0;
+		edge_config = 0;
+		edge_insensitive = 0;
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		level = 0;
+		edge_config = mask;
+		edge_insensitive = 0;
+		break;
+	case IRQ_TYPE_EDGE_BOTH:
+		level = 0;
+		edge_config = 0;  /* don't care, but want known value */
+		edge_insensitive = mask;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&bank->bgc.lock, flags);
+
+	iedge_config = bank->bgc.read_reg(priv->reg_base +
+			GIO_EC(bank->id)) & ~mask;
+	iedge_insensitive = bank->bgc.read_reg(priv->reg_base +
+			GIO_EI(bank->id)) & ~mask;
+	ilevel = bank->bgc.read_reg(priv->reg_base +
+			GIO_LEVEL(bank->id)) & ~mask;
+
+	bank->bgc.write_reg(priv->reg_base + GIO_EC(bank->id),
+			iedge_config | edge_config);
+	bank->bgc.write_reg(priv->reg_base + GIO_EI(bank->id),
+			iedge_insensitive | edge_insensitive);
+	bank->bgc.write_reg(priv->reg_base + GIO_LEVEL(bank->id),
+			ilevel | level);
+
+	spin_unlock_irqrestore(&bank->bgc.lock, flags);
+	return 0;
+}
+
+static int brcmstb_gpio_priv_set_wake(struct brcmstb_gpio_priv *priv,
+		unsigned int enable)
+{
+	int ret = 0;
+
+	/*
+	 * Only enable wake IRQ once for however many hwirqs can wake
+	 * since they all use the same wake IRQ.  Mask will be set
+	 * up appropriately thanks to IRQCHIP_MASK_ON_SUSPEND flag.
+	 */
+	if (enable)
+		ret = enable_irq_wake(priv->parent_wake_irq);
+	else
+		ret = disable_irq_wake(priv->parent_wake_irq);
+	if (ret)
+		dev_err(&priv->pdev->dev, "failed to %s wake-up interrupt\n",
+				enable ? "enable" : "disable");
+	return ret;
+}
+
+static int brcmstb_gpio_irq_set_wake(struct irq_data *d, unsigned int enable)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct brcmstb_gpio_priv *priv = brcmstb_gpio_gc_to_priv(gc);
+
+	return brcmstb_gpio_priv_set_wake(priv, enable);
+}
+
+static irqreturn_t brcmstb_gpio_wake_irq_handler(int irq, void *data)
+{
+	struct brcmstb_gpio_priv *priv = data;
+
+	if (!priv || irq != priv->parent_wake_irq)
+		return IRQ_NONE;
+	pm_wakeup_event(&priv->pdev->dev, 0);
+	return IRQ_HANDLED;
+}
+
+static void brcmstb_gpio_irq_bank_handler(struct brcmstb_gpio_bank *bank)
+{
+	struct brcmstb_gpio_priv *priv = bank->parent_priv;
+	struct irq_domain *irq_domain = bank->bgc.gc.irqdomain;
+	void __iomem *reg_base = priv->reg_base;
+	unsigned long status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bank->bgc.lock, flags);
+	while ((status = bank->bgc.read_reg(reg_base + GIO_STAT(bank->id)) &
+			 bank->bgc.read_reg(reg_base + GIO_MASK(bank->id)))) {
+		int bit;
+
+		for_each_set_bit(bit, &status, 32) {
+			u32 stat = bank->bgc.read_reg(reg_base +
+						      GIO_STAT(bank->id));
+			if (bit >= bank->width)
+				dev_warn(&priv->pdev->dev,
+					 "IRQ for invalid GPIO (bank=%d, offset=%d)\n",
+					 bank->id, bit);
+			bank->bgc.write_reg(reg_base + GIO_STAT(bank->id),
+					    stat | BIT(bit));
+			generic_handle_irq(irq_find_mapping(irq_domain, bit));
+		}
+	}
+	spin_unlock_irqrestore(&bank->bgc.lock, flags);
+}
+
+/* Each UPG GIO block has one IRQ for all banks */
+static void brcmstb_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
+	struct brcmstb_gpio_priv *priv = brcmstb_gpio_gc_to_priv(gc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct list_head *pos;
+
+	/* Interrupts weren't properly cleared during probe */
+	BUG_ON(!priv || !chip);
+
+	chained_irq_enter(chip, desc);
+	list_for_each(pos, &priv->bank_list) {
+		struct brcmstb_gpio_bank *bank =
+			list_entry(pos, struct brcmstb_gpio_bank, node);
+		brcmstb_gpio_irq_bank_handler(bank);
+	}
+	chained_irq_exit(chip, desc);
+}
+
+static int brcmstb_gpio_reboot(struct notifier_block *nb,
+		unsigned long action, void *data)
+{
+	struct brcmstb_gpio_priv *priv =
+		container_of(nb, struct brcmstb_gpio_priv, reboot_notifier);
+
+	/* Enable GPIO for S5 cold boot */
+	if (action == SYS_POWER_OFF)
+		brcmstb_gpio_priv_set_wake(priv, 1);
+
+	return NOTIFY_DONE;
+}
+
 /* Make sure that the number of banks matches up between properties */
 static int brcmstb_gpio_sanity_check_banks(struct device *dev,
 		struct device_node *np, struct resource *res)
@@ -87,11 +292,26 @@ static int brcmstb_gpio_remove(struct platform_device *pdev)
 	struct brcmstb_gpio_bank *bank;
 	int ret = 0;
 
+	if (!priv) {
+		dev_err(&pdev->dev, "called %s without drvdata!\n", __func__);
+		return -EFAULT;
+	}
+
+	/*
+	 * You can lose return values below, but we report all errors, and it's
+	 * more important to actually perform all of the steps.
+	 */
 	list_for_each(pos, &priv->bank_list) {
 		bank = list_entry(pos, struct brcmstb_gpio_bank, node);
 		ret = bgpio_remove(&bank->bgc);
 		if (ret)
-			dev_err(&pdev->dev, "gpiochip_remove fail in cleanup");
+			dev_err(&pdev->dev, "gpiochip_remove fail in cleanup\n");
+	}
+	if (priv->reboot_notifier.notifier_call) {
+		ret = unregister_reboot_notifier(&priv->reboot_notifier);
+		if (ret)
+			dev_err(&pdev->dev,
+				"failed to unregister reboot notifier\n");
 	}
 	return ret;
 }
@@ -112,7 +332,7 @@ static int brcmstb_gpio_of_xlate(struct gpio_chip *gc,
 		return -EINVAL;
 
 	offset = gpiospec->args[0] - (gc->base - priv->gpio_base);
-	if (offset >= gc->ngpio)
+	if (offset >= gc->ngpio || offset < 0)
 		return -EINVAL;
 
 	if (unlikely(offset >= bank->width)) {
@@ -127,6 +347,65 @@ static int brcmstb_gpio_of_xlate(struct gpio_chip *gc,
 	return offset;
 }
 
+/* Before calling, must have bank->parent_irq set and gpiochip registered */
+static int brcmstb_gpio_irq_setup(struct platform_device *pdev,
+		struct brcmstb_gpio_bank *bank)
+{
+	struct brcmstb_gpio_priv *priv = bank->parent_priv;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+
+	bank->irq_chip.name = dev_name(dev);
+	bank->irq_chip.irq_mask = brcmstb_gpio_irq_mask;
+	bank->irq_chip.irq_unmask = brcmstb_gpio_irq_unmask;
+	bank->irq_chip.irq_set_type = brcmstb_gpio_irq_set_type;
+
+	/* Ensures that all non-wakeup IRQs are disabled at suspend */
+	bank->irq_chip.flags = IRQCHIP_MASK_ON_SUSPEND;
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP) && !priv->can_wake &&
+			of_property_read_bool(np, "wakeup-source")) {
+		priv->parent_wake_irq = platform_get_irq(pdev, 1);
+		if (priv->parent_wake_irq < 0) {
+			dev_warn(dev,
+				"Couldn't get wake IRQ - GPIOs will not be able to wake from sleep");
+		} else {
+			int err;
+
+			/*
+			 * Set wakeup capability before requesting wakeup
+			 * interrupt, so we can process boot-time "wakeups"
+			 * (e.g., from S5 cold boot)
+			 */
+			device_set_wakeup_capable(dev, true);
+			device_wakeup_enable(dev);
+			err = devm_request_irq(dev, priv->parent_wake_irq,
+					brcmstb_gpio_wake_irq_handler, 0,
+					"brcmstb-gpio-wake", priv);
+
+			if (err < 0) {
+				dev_err(dev, "Couldn't request wake IRQ");
+				return err;
+			}
+
+			priv->reboot_notifier.notifier_call =
+				brcmstb_gpio_reboot;
+			register_reboot_notifier(&priv->reboot_notifier);
+			priv->can_wake = true;
+		}
+	}
+
+	if (priv->can_wake)
+		bank->irq_chip.irq_set_wake = brcmstb_gpio_irq_set_wake;
+
+	gpiochip_irqchip_add(&bank->bgc.gc, &bank->irq_chip, 0,
+			handle_simple_irq, IRQ_TYPE_NONE);
+	gpiochip_set_chained_irqchip(&bank->bgc.gc, &bank->irq_chip,
+			priv->parent_irq, brcmstb_gpio_irq_handler);
+
+	return 0;
+}
+
 static int brcmstb_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -137,12 +416,15 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 	struct property *prop;
 	const __be32 *p;
 	u32 bank_width;
+	int num_banks = 0;
 	int err;
 	static int gpio_base;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+	INIT_LIST_HEAD(&priv->bank_list);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg_base = devm_ioremap_resource(dev, res);
@@ -153,7 +435,16 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 	priv->reg_base = reg_base;
 	priv->pdev = pdev;
 
-	INIT_LIST_HEAD(&priv->bank_list);
+	if (of_property_read_bool(np, "interrupt-controller")) {
+		priv->parent_irq = platform_get_irq(pdev, 0);
+		if (priv->parent_irq <= 0) {
+			dev_err(dev, "Couldn't get IRQ");
+			return -ENOENT;
+		}
+	} else {
+		priv->parent_irq = -ENOENT;
+	}
+
 	if (brcmstb_gpio_sanity_check_banks(dev, np, res))
 		return -EINVAL;
 
@@ -170,7 +461,7 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 		}
 
 		bank->parent_priv = priv;
-		bank->id = priv->num_banks;
+		bank->id = num_banks;
 		if (bank_width <= 0 || bank_width > MAX_GPIO_PER_BANK) {
 			dev_err(dev, "Invalid bank width %d\n", bank_width);
 			goto fail;
@@ -202,6 +493,12 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 		/* not all ngpio lines are valid, will use bank width later */
 		gc->ngpio = MAX_GPIO_PER_BANK;
 
+		/*
+		 * Mask all interrupts by default, since wakeup interrupts may
+		 * be retained from S5 cold boot
+		 */
+		bank->bgc.write_reg(reg_base + GIO_MASK(bank->id), 0);
+
 		err = gpiochip_add(gc);
 		if (err) {
 			dev_err(dev, "Could not add gpiochip for bank %d\n",
@@ -209,19 +506,24 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 			goto fail;
 		}
 		gpio_base += gc->ngpio;
+
+		if (priv->parent_irq > 0) {
+			err = brcmstb_gpio_irq_setup(pdev, bank);
+			if (err)
+				goto fail;
+		}
+
 		dev_dbg(dev, "bank=%d, base=%d, ngpio=%d, width=%d\n", bank->id,
 			gc->base, gc->ngpio, bank->width);
 
 		/* Everything looks good, so add bank to list */
 		list_add(&bank->node, &priv->bank_list);
 
-		priv->num_banks++;
+		num_banks++;
 	}
 
 	dev_info(dev, "Registered %d banks (GPIO(s): %d-%d)\n",
-			priv->num_banks, priv->gpio_base, gpio_base - 1);
-
-	platform_set_drvdata(pdev, priv);
+			num_banks, priv->gpio_base, gpio_base - 1);
 
 	return 0;
 
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index c5e05c82d67c..94b0ab709721 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -65,11 +65,11 @@ static struct davinci_gpio_regs __iomem *gpio2regs(unsigned gpio)
 	return ptr;
 }
 
-static inline struct davinci_gpio_regs __iomem *irq2regs(int irq)
+static inline struct davinci_gpio_regs __iomem *irq2regs(struct irq_data *d)
 {
 	struct davinci_gpio_regs __iomem *g;
 
-	g = (__force struct davinci_gpio_regs __iomem *)irq_get_chip_data(irq);
+	g = (__force struct davinci_gpio_regs __iomem *)irq_data_get_irq_chip_data(d);
 
 	return g;
 }
@@ -287,7 +287,7 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 
 static void gpio_irq_disable(struct irq_data *d)
 {
-	struct davinci_gpio_regs __iomem *g = irq2regs(d->irq);
+	struct davinci_gpio_regs __iomem *g = irq2regs(d);
 	u32 mask = (u32) irq_data_get_irq_handler_data(d);
 
 	writel_relaxed(mask, &g->clr_falling);
@@ -296,7 +296,7 @@ static void gpio_irq_disable(struct irq_data *d)
 
 static void gpio_irq_enable(struct irq_data *d)
 {
-	struct davinci_gpio_regs __iomem *g = irq2regs(d->irq);
+	struct davinci_gpio_regs __iomem *g = irq2regs(d);
 	u32 mask = (u32) irq_data_get_irq_handler_data(d);
 	unsigned status = irqd_get_trigger_type(d);
 
@@ -327,8 +327,9 @@ static struct irq_chip gpio_irqchip = {
 };
 
 static void
-gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+gpio_irq_handler(unsigned __irq, struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
 	struct davinci_gpio_regs __iomem *g;
 	u32 mask = 0xffff;
 	struct davinci_gpio_controller *d;
@@ -396,7 +397,7 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
 	struct davinci_gpio_regs __iomem *g;
 	u32 mask;
 
-	d = (struct davinci_gpio_controller *)data->handler_data;
+	d = (struct davinci_gpio_controller *)irq_data_get_irq_handler_data(data);
 	g = (struct davinci_gpio_regs __iomem *)d->regs;
 	mask = __gpio_mask(data->irq - d->gpio_irq);
 
@@ -422,7 +423,6 @@ davinci_gpio_irq_map(struct irq_domain *d, unsigned int irq,
 	irq_set_irq_type(irq, IRQ_TYPE_NONE);
 	irq_set_chip_data(irq, (__force void *)g);
 	irq_set_handler_data(irq, (void *)__gpio_mask(hw));
-	set_irq_flags(irq, IRQF_VALID);
 
 	return 0;
 }
@@ -545,7 +545,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 		chips[0].chip.to_irq = gpio_to_irq_unbanked;
 		chips[0].gpio_irq = bank_irq;
 		chips[0].gpio_unbanked = pdata->gpio_unbanked;
-		binten = BIT(0);
+		binten = GENMASK(pdata->gpio_unbanked / 16, 0);
 
 		/* AINTC handles mask/unmask; GPIO handles triggering */
 		irq = bank_irq;
@@ -578,15 +578,13 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 		writel_relaxed(~0, &g->clr_falling);
 		writel_relaxed(~0, &g->clr_rising);
 
-		/* set up all irqs in this bank */
-		irq_set_chained_handler(bank_irq, gpio_irq_handler);
-
 		/*
 		 * Each chip handles 32 gpios, and each irq bank consists of 16
 		 * gpio irqs. Pass the irq bank's corresponding controller to
 		 * the chained irq handler.
 		 */
-		irq_set_handler_data(bank_irq, &chips[gpio / 32]);
+		irq_set_chained_handler_and_data(bank_irq, gpio_irq_handler,
+						 &chips[gpio / 32]);
 
 		binten |= BIT(bank);
 	}
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 55fa9853a7f2..c5be4b9b8baf 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -149,7 +149,7 @@ static u32 dwapb_do_irq(struct dwapb_gpio *gpio)
 
 static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
 {
-	struct dwapb_gpio *gpio = irq_get_handler_data(irq);
+	struct dwapb_gpio *gpio = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
 	dwapb_do_irq(gpio);
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index fbf287307c4c..6bca1e125e12 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/pinctrl/consumer.h>
-#include <linux/platform_data/gpio-em.h>
 
 struct em_gio_priv {
 	void __iomem *base0;
@@ -262,7 +261,6 @@ static int em_gio_irq_domain_map(struct irq_domain *h, unsigned int irq,
 
 	irq_set_chip_data(irq, h->host_data);
 	irq_set_chip_and_handler(irq, &p->irq_chip, handle_level_irq);
-	set_irq_flags(irq, IRQF_VALID); /* kill me now */
 	return 0;
 }
 
@@ -273,13 +271,12 @@ static const struct irq_domain_ops em_gio_irq_domain_ops = {
 
 static int em_gio_probe(struct platform_device *pdev)
 {
-	struct gpio_em_config pdata_dt;
-	struct gpio_em_config *pdata = dev_get_platdata(&pdev->dev);
 	struct em_gio_priv *p;
 	struct resource *io[2], *irq[2];
 	struct gpio_chip *gpio_chip;
 	struct irq_chip *irq_chip;
 	const char *name = dev_name(&pdev->dev);
+	unsigned int ngpios;
 	int ret;
 
 	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
@@ -319,18 +316,10 @@ static int em_gio_probe(struct platform_device *pdev)
 		goto err0;
 	}
 
-	if (!pdata) {
-		memset(&pdata_dt, 0, sizeof(pdata_dt));
-		pdata = &pdata_dt;
-
-		if (of_property_read_u32(pdev->dev.of_node, "ngpios",
-					 &pdata->number_of_pins)) {
-			dev_err(&pdev->dev, "Missing ngpios OF property\n");
-			ret = -EINVAL;
-			goto err0;
-		}
-
-		pdata->gpio_base = -1;
+	if (of_property_read_u32(pdev->dev.of_node, "ngpios", &ngpios)) {
+		dev_err(&pdev->dev, "Missing ngpios OF property\n");
+		ret = -EINVAL;
+		goto err0;
 	}
 
 	gpio_chip = &p->gpio_chip;
@@ -345,8 +334,8 @@ static int em_gio_probe(struct platform_device *pdev)
 	gpio_chip->label = name;
 	gpio_chip->dev = &pdev->dev;
 	gpio_chip->owner = THIS_MODULE;
-	gpio_chip->base = pdata->gpio_base;
-	gpio_chip->ngpio = pdata->number_of_pins;
+	gpio_chip->base = -1;
+	gpio_chip->ngpio = ngpios;
 
 	irq_chip = &p->irq_chip;
 	irq_chip->name = name;
@@ -357,9 +346,7 @@ static int em_gio_probe(struct platform_device *pdev)
 	irq_chip->irq_release_resources = em_gio_irq_relres;
 	irq_chip->flags	= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND;
 
-	p->irq_domain = irq_domain_add_simple(pdev->dev.of_node,
-					      pdata->number_of_pins,
-					      pdata->irq_base,
+	p->irq_domain = irq_domain_add_simple(pdev->dev.of_node, ngpios, 0,
 					      &em_gio_irq_domain_ops, p);
 	if (!p->irq_domain) {
 		ret = -ENXIO;
@@ -387,12 +374,6 @@ static int em_gio_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
-	if (pdata->pctl_name) {
-		ret = gpiochip_add_pin_range(gpio_chip, pdata->pctl_name, 0,
-					     gpio_chip->base, gpio_chip->ngpio);
-		if (ret < 0)
-			dev_warn(&pdev->dev, "failed to add pin range\n");
-	}
 	return 0;
 
 err1:
diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c
index 45684f36ddb1..9d90366ea259 100644
--- a/drivers/gpio/gpio-ep93xx.c
+++ b/drivers/gpio/gpio-ep93xx.c
@@ -100,13 +100,15 @@ static void ep93xx_gpio_ab_irq_handler(unsigned int irq, struct irq_desc *desc)
 	}
 }
 
-static void ep93xx_gpio_f_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ep93xx_gpio_f_irq_handler(unsigned int __irq,
+				      struct irq_desc *desc)
 {
 	/*
 	 * map discontiguous hw irq range to continuous sw irq range:
 	 *
 	 *  IRQ_EP93XX_GPIO{0..7}MUX -> gpio_to_irq(EP93XX_GPIO_LINE_F({0..7})
 	 */
+	unsigned int irq = irq_desc_get_irq(desc);
 	int port_f_idx = ((irq + 1) & 7) ^ 4; /* {19..22,47..50} -> {0..7} */
 	int gpio_irq = gpio_to_irq(EP93XX_GPIO_LINE_F(0)) + port_f_idx;
 
@@ -208,7 +210,7 @@ static int ep93xx_gpio_irq_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	__irq_set_handler_locked(d->irq, handler);
+	irq_set_handler_locked(d, handler);
 
 	gpio_int_enabled[port] |= port_mask;
 
@@ -234,7 +236,7 @@ static void ep93xx_gpio_init_irq(void)
 	     gpio_irq <= gpio_to_irq(EP93XX_GPIO_LINE_MAX_IRQ); ++gpio_irq) {
 		irq_set_chip_and_handler(gpio_irq, &ep93xx_gpio_irq_chip,
 					 handle_level_irq);
-		set_irq_flags(gpio_irq, IRQF_VALID);
+		irq_clear_status_flags(gpio_irq, IRQ_NOREQUEST);
 	}
 
 	irq_set_chained_handler(IRQ_EP93XX_GPIO_AB,
diff --git a/drivers/gpio/gpio-etraxfs.c b/drivers/gpio/gpio-etraxfs.c
index 28071f4a5672..2ffcd9fdd1f2 100644
--- a/drivers/gpio/gpio-etraxfs.c
+++ b/drivers/gpio/gpio-etraxfs.c
@@ -1,8 +1,10 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/of_gpio.h>
 #include <linux/io.h>
+#include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/basic_mmio_gpio.h>
 
@@ -13,6 +15,7 @@
 #define ETRAX_FS_rw_intr_mask	16
 #define ETRAX_FS_rw_ack_intr	20
 #define ETRAX_FS_r_intr		24
+#define ETRAX_FS_r_masked_intr	28
 #define ETRAX_FS_rw_pb_dout	32
 #define ETRAX_FS_r_pb_din	36
 #define ETRAX_FS_rw_pb_oe	40
@@ -26,6 +29,48 @@
 #define ETRAX_FS_r_pe_din	84
 #define ETRAX_FS_rw_pe_oe	88
 
+#define ARTPEC3_r_pa_din	0
+#define ARTPEC3_rw_pa_dout	4
+#define ARTPEC3_rw_pa_oe	8
+#define ARTPEC3_r_pb_din	44
+#define ARTPEC3_rw_pb_dout	48
+#define ARTPEC3_rw_pb_oe	52
+#define ARTPEC3_r_pc_din	88
+#define ARTPEC3_rw_pc_dout	92
+#define ARTPEC3_rw_pc_oe	96
+#define ARTPEC3_r_pd_din	116
+#define ARTPEC3_rw_intr_cfg	120
+#define ARTPEC3_rw_intr_pins	124
+#define ARTPEC3_rw_intr_mask	128
+#define ARTPEC3_rw_ack_intr	132
+#define ARTPEC3_r_masked_intr	140
+
+#define GIO_CFG_OFF		0
+#define GIO_CFG_HI		1
+#define GIO_CFG_LO		2
+#define GIO_CFG_SET		3
+#define GIO_CFG_POSEDGE		5
+#define GIO_CFG_NEGEDGE		6
+#define GIO_CFG_ANYEDGE		7
+
+struct etraxfs_gpio_info;
+
+struct etraxfs_gpio_block {
+	spinlock_t lock;
+	u32 mask;
+	u32 cfg;
+	u32 pins;
+	unsigned int group[8];
+
+	void __iomem *regs;
+	const struct etraxfs_gpio_info *info;
+};
+
+struct etraxfs_gpio_chip {
+	struct bgpio_chip bgc;
+	struct etraxfs_gpio_block *block;
+};
+
 struct etraxfs_gpio_port {
 	const char *label;
 	unsigned int oe;
@@ -37,6 +82,12 @@ struct etraxfs_gpio_port {
 struct etraxfs_gpio_info {
 	unsigned int num_ports;
 	const struct etraxfs_gpio_port *ports;
+
+	unsigned int rw_ack_intr;
+	unsigned int rw_intr_mask;
+	unsigned int rw_intr_cfg;
+	unsigned int rw_intr_pins;
+	unsigned int r_masked_intr;
 };
 
 static const struct etraxfs_gpio_port etraxfs_gpio_etraxfs_ports[] = {
@@ -80,8 +131,56 @@ static const struct etraxfs_gpio_port etraxfs_gpio_etraxfs_ports[] = {
 static const struct etraxfs_gpio_info etraxfs_gpio_etraxfs = {
 	.num_ports = ARRAY_SIZE(etraxfs_gpio_etraxfs_ports),
 	.ports = etraxfs_gpio_etraxfs_ports,
+	.rw_ack_intr	= ETRAX_FS_rw_ack_intr,
+	.rw_intr_mask	= ETRAX_FS_rw_intr_mask,
+	.rw_intr_cfg	= ETRAX_FS_rw_intr_cfg,
+	.r_masked_intr	= ETRAX_FS_r_masked_intr,
+};
+
+static const struct etraxfs_gpio_port etraxfs_gpio_artpec3_ports[] = {
+	{
+		.label	= "A",
+		.ngpio	= 32,
+		.oe	= ARTPEC3_rw_pa_oe,
+		.dout	= ARTPEC3_rw_pa_dout,
+		.din	= ARTPEC3_r_pa_din,
+	},
+	{
+		.label	= "B",
+		.ngpio	= 32,
+		.oe	= ARTPEC3_rw_pb_oe,
+		.dout	= ARTPEC3_rw_pb_dout,
+		.din	= ARTPEC3_r_pb_din,
+	},
+	{
+		.label	= "C",
+		.ngpio	= 16,
+		.oe	= ARTPEC3_rw_pc_oe,
+		.dout	= ARTPEC3_rw_pc_dout,
+		.din	= ARTPEC3_r_pc_din,
+	},
+	{
+		.label	= "D",
+		.ngpio	= 32,
+		.din	= ARTPEC3_r_pd_din,
+	},
+};
+
+static const struct etraxfs_gpio_info etraxfs_gpio_artpec3 = {
+	.num_ports = ARRAY_SIZE(etraxfs_gpio_artpec3_ports),
+	.ports = etraxfs_gpio_artpec3_ports,
+	.rw_ack_intr	= ARTPEC3_rw_ack_intr,
+	.rw_intr_mask	= ARTPEC3_rw_intr_mask,
+	.rw_intr_cfg	= ARTPEC3_rw_intr_cfg,
+	.r_masked_intr	= ARTPEC3_r_masked_intr,
+	.rw_intr_pins	= ARTPEC3_rw_intr_pins,
 };
 
+static unsigned int etraxfs_gpio_chip_to_port(struct gpio_chip *gc)
+{
+	return gc->label[0] - 'A';
+}
+
 static int etraxfs_gpio_of_xlate(struct gpio_chip *gc,
 			       const struct of_phandle_args *gpiospec,
 			       u32 *flags)
@@ -90,7 +189,7 @@ static int etraxfs_gpio_of_xlate(struct gpio_chip *gc,
 	 * Port numbers are A to E, and the properties are integers, so we
 	 * specify them as 0xA - 0xE.
 	 */
-	if (gc->label[0] - 'A' + 0xA != gpiospec->args[2])
+	if (etraxfs_gpio_chip_to_port(gc) + 0xA != gpiospec->args[2])
 		return -EINVAL;
 
 	return of_gpio_simple_xlate(gc, gpiospec, flags);
@@ -101,24 +200,174 @@ static const struct of_device_id etraxfs_gpio_of_table[] = {
 		.compatible = "axis,etraxfs-gio",
 		.data = &etraxfs_gpio_etraxfs,
 	},
+	{
+		.compatible = "axis,artpec3-gio",
+		.data = &etraxfs_gpio_artpec3,
+	},
 	{},
 };
 
+static unsigned int etraxfs_gpio_to_group_irq(unsigned int gpio)
+{
+	return gpio % 8;
+}
+
+static unsigned int etraxfs_gpio_to_group_pin(struct etraxfs_gpio_chip *chip,
+					      unsigned int gpio)
+{
+	return 4 * etraxfs_gpio_chip_to_port(&chip->bgc.gc) + gpio / 8;
+}
+
+static void etraxfs_gpio_irq_ack(struct irq_data *d)
+{
+	struct etraxfs_gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct etraxfs_gpio_block *block = chip->block;
+	unsigned int grpirq = etraxfs_gpio_to_group_irq(d->hwirq);
+
+	writel(BIT(grpirq), block->regs + block->info->rw_ack_intr);
+}
+
+static void etraxfs_gpio_irq_mask(struct irq_data *d)
+{
+	struct etraxfs_gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct etraxfs_gpio_block *block = chip->block;
+	unsigned int grpirq = etraxfs_gpio_to_group_irq(d->hwirq);
+
+	spin_lock(&block->lock);
+	block->mask &= ~BIT(grpirq);
+	writel(block->mask, block->regs + block->info->rw_intr_mask);
+	spin_unlock(&block->lock);
+}
+
+static void etraxfs_gpio_irq_unmask(struct irq_data *d)
+{
+	struct etraxfs_gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct etraxfs_gpio_block *block = chip->block;
+	unsigned int grpirq = etraxfs_gpio_to_group_irq(d->hwirq);
+
+	spin_lock(&block->lock);
+	block->mask |= BIT(grpirq);
+	writel(block->mask, block->regs + block->info->rw_intr_mask);
+	spin_unlock(&block->lock);
+}
+
+static int etraxfs_gpio_irq_set_type(struct irq_data *d, u32 type)
+{
+	struct etraxfs_gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct etraxfs_gpio_block *block = chip->block;
+	unsigned int grpirq = etraxfs_gpio_to_group_irq(d->hwirq);
+	u32 cfg;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+		cfg = GIO_CFG_POSEDGE;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		cfg = GIO_CFG_NEGEDGE;
+		break;
+	case IRQ_TYPE_EDGE_BOTH:
+		cfg = GIO_CFG_ANYEDGE;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		cfg = GIO_CFG_LO;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		cfg = GIO_CFG_HI;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock(&block->lock);
+	block->cfg &= ~(0x7 << (grpirq * 3));
+	block->cfg |= (cfg << (grpirq * 3));
+	writel(block->cfg, block->regs + block->info->rw_intr_cfg);
+	spin_unlock(&block->lock);
+
+	return 0;
+}
+
+static int etraxfs_gpio_irq_request_resources(struct irq_data *d)
+{
+	struct etraxfs_gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct etraxfs_gpio_block *block = chip->block;
+	unsigned int grpirq = etraxfs_gpio_to_group_irq(d->hwirq);
+	int ret = -EBUSY;
+
+	spin_lock(&block->lock);
+	if (block->group[grpirq])
+		goto out;
+
+	ret = gpiochip_lock_as_irq(&chip->bgc.gc, d->hwirq);
+	if (ret)
+		goto out;
+
+	block->group[grpirq] = d->irq;
+	if (block->info->rw_intr_pins) {
+		unsigned int pin = etraxfs_gpio_to_group_pin(chip, d->hwirq);
+
+		block->pins &= ~(0xf << (grpirq * 4));
+		block->pins |= (pin << (grpirq * 4));
+
+		writel(block->pins, block->regs + block->info->rw_intr_pins);
+	}
+
+out:
+	spin_unlock(&block->lock);
+	return ret;
+}
+
+static void etraxfs_gpio_irq_release_resources(struct irq_data *d)
+{
+	struct etraxfs_gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct etraxfs_gpio_block *block = chip->block;
+	unsigned int grpirq = etraxfs_gpio_to_group_irq(d->hwirq);
+
+	spin_lock(&block->lock);
+	block->group[grpirq] = 0;
+	gpiochip_unlock_as_irq(&chip->bgc.gc, d->hwirq);
+	spin_unlock(&block->lock);
+}
+
+static struct irq_chip etraxfs_gpio_irq_chip = {
+	.name		= "gpio-etraxfs",
+	.irq_ack	= etraxfs_gpio_irq_ack,
+	.irq_mask	= etraxfs_gpio_irq_mask,
+	.irq_unmask	= etraxfs_gpio_irq_unmask,
+	.irq_set_type	= etraxfs_gpio_irq_set_type,
+	.irq_request_resources = etraxfs_gpio_irq_request_resources,
+	.irq_release_resources = etraxfs_gpio_irq_release_resources,
+};
+
+static irqreturn_t etraxfs_gpio_interrupt(int irq, void *dev_id)
+{
+	struct etraxfs_gpio_block *block = dev_id;
+	unsigned long intr = readl(block->regs + block->info->r_masked_intr);
+	int bit;
+
+	for_each_set_bit(bit, &intr, 8)
+		generic_handle_irq(block->group[bit]);
+
+	return IRQ_RETVAL(intr & 0xff);
+}
+
 static int etraxfs_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	const struct etraxfs_gpio_info *info;
 	const struct of_device_id *match;
-	struct bgpio_chip *chips;
-	struct resource *res;
+	struct etraxfs_gpio_block *block;
+	struct etraxfs_gpio_chip *chips;
+	struct resource *res, *irq;
+	bool allportsirq = false;
 	void __iomem *regs;
 	int ret;
 	int i;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(dev, res);
-	if (!regs)
-		return -ENOMEM;
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	match = of_match_node(etraxfs_gpio_of_table, dev->of_node);
 	if (!match)
@@ -130,19 +379,57 @@ static int etraxfs_gpio_probe(struct platform_device *pdev)
 	if (!chips)
 		return -ENOMEM;
 
+	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!irq)
+		return -EINVAL;
+
+	block = devm_kzalloc(dev, sizeof(*block), GFP_KERNEL);
+	if (!block)
+		return -ENOMEM;
+
+	spin_lock_init(&block->lock);
+
+	block->regs = regs;
+	block->info = info;
+
+	writel(0, block->regs + info->rw_intr_mask);
+	writel(0, block->regs + info->rw_intr_cfg);
+	if (info->rw_intr_pins) {
+		allportsirq = true;
+		writel(0, block->regs + info->rw_intr_pins);
+	}
+
+	ret = devm_request_irq(dev, irq->start, etraxfs_gpio_interrupt,
+			       IRQF_SHARED, dev_name(dev), block);
+	if (ret) {
+		dev_err(dev, "Unable to request irq %d\n", ret);
+		return ret;
+	}
+
 	for (i = 0; i < info->num_ports; i++) {
-		struct bgpio_chip *bgc = &chips[i];
+		struct etraxfs_gpio_chip *chip = &chips[i];
+		struct bgpio_chip *bgc = &chip->bgc;
 		const struct etraxfs_gpio_port *port = &info->ports[i];
+		unsigned long flags = BGPIOF_READ_OUTPUT_REG_SET;
+		void __iomem *dat = regs + port->din;
+		void __iomem *set = regs + port->dout;
+		void __iomem *dirout = regs + port->oe;
+
+		chip->block = block;
+
+		if (dirout == set) {
+			dirout = set = NULL;
+			flags = BGPIOF_NO_OUTPUT;
+		}
 
 		ret = bgpio_init(bgc, dev, 4,
-				 regs + port->din,	/* dat */
-				 regs + port->dout,	/* set */
-				 NULL,			/* clr */
-				 regs + port->oe,	/* dirout */
-				 NULL,			/* dirin */
-				 BGPIOF_UNREADABLE_REG_SET);
-		if (ret)
-			return ret;
+				 dat, set, NULL, dirout, NULL,
+				 flags);
+		if (ret) {
+			dev_err(dev, "Unable to init port %s\n",
+				port->label);
+			continue;
+		}
 
 		bgc->gc.ngpio = port->ngpio;
 		bgc->gc.label = port->label;
@@ -152,9 +439,21 @@ static int etraxfs_gpio_probe(struct platform_device *pdev)
 		bgc->gc.of_xlate = etraxfs_gpio_of_xlate;
 
 		ret = gpiochip_add(&bgc->gc);
-		if (ret)
+		if (ret) {
 			dev_err(dev, "Unable to register port %s\n",
 				bgc->gc.label);
+			continue;
+		}
+
+		if (i > 0 && !allportsirq)
+			continue;
+
+		ret = gpiochip_irqchip_add(&bgc->gc, &etraxfs_gpio_irq_chip, 0,
+					   handle_level_irq, IRQ_TYPE_NONE);
+		if (ret) {
+			dev_err(dev, "Unable to add irqchip to port %s\n",
+				bgc->gc.label);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c
index 9bda3727fac1..a3f07537fe62 100644
--- a/drivers/gpio/gpio-generic.c
+++ b/drivers/gpio/gpio-generic.c
@@ -153,6 +153,10 @@ static int bgpio_get(struct gpio_chip *gc, unsigned int gpio)
 	return !!(bgc->read_reg(bgc->reg_dat) & bgc->pin2mask(bgc, gpio));
 }
 
+static void bgpio_set_none(struct gpio_chip *gc, unsigned int gpio, int val)
+{
+}
+
 static void bgpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct bgpio_chip *bgc = to_bgpio_chip(gc);
@@ -279,6 +283,12 @@ static int bgpio_simple_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	return 0;
 }
 
+static int bgpio_dir_out_err(struct gpio_chip *gc, unsigned int gpio,
+				int val)
+{
+	return -EINVAL;
+}
+
 static int bgpio_simple_dir_out(struct gpio_chip *gc, unsigned int gpio,
 				int val)
 {
@@ -302,6 +312,14 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	return 0;
 }
 
+static int bgpio_get_dir(struct gpio_chip *gc, unsigned int gpio)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+
+	return (bgc->read_reg(bgc->reg_dir) & bgc->pin2mask(bgc, gpio)) ?
+	       GPIOF_DIR_OUT : GPIOF_DIR_IN;
+}
+
 static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct bgpio_chip *bgc = to_bgpio_chip(gc);
@@ -351,6 +369,14 @@ static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val)
 	return 0;
 }
 
+static int bgpio_get_dir_inv(struct gpio_chip *gc, unsigned int gpio)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+
+	return (bgc->read_reg(bgc->reg_dir) & bgc->pin2mask(bgc, gpio)) ?
+	       GPIOF_DIR_IN : GPIOF_DIR_OUT;
+}
+
 static int bgpio_setup_accessors(struct device *dev,
 				 struct bgpio_chip *bgc,
 				 bool bit_be,
@@ -444,6 +470,9 @@ static int bgpio_setup_io(struct bgpio_chip *bgc,
 		bgc->reg_set = set;
 		bgc->gc.set = bgpio_set_set;
 		bgc->gc.set_multiple = bgpio_set_multiple_set;
+	} else if (flags & BGPIOF_NO_OUTPUT) {
+		bgc->gc.set = bgpio_set_none;
+		bgc->gc.set_multiple = NULL;
 	} else {
 		bgc->gc.set = bgpio_set;
 		bgc->gc.set_multiple = bgpio_set_multiple;
@@ -460,7 +489,8 @@ static int bgpio_setup_io(struct bgpio_chip *bgc,
 
 static int bgpio_setup_direction(struct bgpio_chip *bgc,
 				 void __iomem *dirout,
-				 void __iomem *dirin)
+				 void __iomem *dirin,
+				 unsigned long flags)
 {
 	if (dirout && dirin) {
 		return -EINVAL;
@@ -468,12 +498,17 @@ static int bgpio_setup_direction(struct bgpio_chip *bgc,
 		bgc->reg_dir = dirout;
 		bgc->gc.direction_output = bgpio_dir_out;
 		bgc->gc.direction_input = bgpio_dir_in;
+		bgc->gc.get_direction = bgpio_get_dir;
 	} else if (dirin) {
 		bgc->reg_dir = dirin;
 		bgc->gc.direction_output = bgpio_dir_out_inv;
 		bgc->gc.direction_input = bgpio_dir_in_inv;
+		bgc->gc.get_direction = bgpio_get_dir_inv;
 	} else {
-		bgc->gc.direction_output = bgpio_simple_dir_out;
+		if (flags & BGPIOF_NO_OUTPUT)
+			bgc->gc.direction_output = bgpio_dir_out_err;
+		else
+			bgc->gc.direction_output = bgpio_simple_dir_out;
 		bgc->gc.direction_input = bgpio_simple_dir_in;
 	}
 
@@ -525,7 +560,7 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev,
 	if (ret)
 		return ret;
 
-	ret = bgpio_setup_direction(bgc, dirout, dirin);
+	ret = bgpio_setup_direction(bgc, dirout, dirin, flags);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpio/gpio-grgpio.c b/drivers/gpio/gpio-grgpio.c
index 0a8f7617e72e..801423fe8143 100644
--- a/drivers/gpio/gpio-grgpio.c
+++ b/drivers/gpio/gpio-grgpio.c
@@ -104,17 +104,12 @@ static void grgpio_set_imask(struct grgpio_priv *priv, unsigned int offset,
 {
 	struct bgpio_chip *bgc = &priv->bgc;
 	unsigned long mask = bgc->pin2mask(bgc, offset);
-	unsigned long flags;
-
-	spin_lock_irqsave(&bgc->lock, flags);
 
 	if (val)
 		priv->imask |= mask;
 	else
 		priv->imask &= ~mask;
 	bgc->write_reg(priv->regs + GRGPIO_IMASK, priv->imask);
-
-	spin_unlock_irqrestore(&bgc->lock, flags);
 }
 
 static int grgpio_to_irq(struct gpio_chip *gc, unsigned offset)
@@ -180,16 +175,26 @@ static void grgpio_irq_mask(struct irq_data *d)
 {
 	struct grgpio_priv *priv = irq_data_get_irq_chip_data(d);
 	int offset = d->hwirq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->bgc.lock, flags);
 
 	grgpio_set_imask(priv, offset, 0);
+
+	spin_unlock_irqrestore(&priv->bgc.lock, flags);
 }
 
 static void grgpio_irq_unmask(struct irq_data *d)
 {
 	struct grgpio_priv *priv = irq_data_get_irq_chip_data(d);
 	int offset = d->hwirq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->bgc.lock, flags);
 
 	grgpio_set_imask(priv, offset, 1);
+
+	spin_unlock_irqrestore(&priv->bgc.lock, flags);
 }
 
 static struct irq_chip grgpio_irq_chip = {
@@ -281,12 +286,7 @@ static int grgpio_irq_map(struct irq_domain *d, unsigned int irq,
 	irq_set_chip_data(irq, priv);
 	irq_set_chip_and_handler(irq, &grgpio_irq_chip,
 				 handle_simple_irq);
-	irq_clear_status_flags(irq, IRQ_NOREQUEST);
-#ifdef CONFIG_ARM
-	set_irq_flags(irq, IRQF_VALID);
-#else
 	irq_set_noprobe(irq);
-#endif
 
 	return ret;
 }
@@ -301,9 +301,6 @@ static void grgpio_irq_unmap(struct irq_domain *d, unsigned int irq)
 	int ngpio = priv->bgc.gc.ngpio;
 	int i;
 
-#ifdef CONFIG_ARM
-	set_irq_flags(irq, 0);
-#endif
 	irq_set_chip_and_handler(irq, NULL, NULL);
 	irq_set_chip_data(irq, NULL);
 
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index aed4ca9338bc..8c5252c6c327 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -603,6 +603,7 @@ static int max732x_setup_gpio(struct max732x_chip *chip,
 	gc->base = gpio_start;
 	gc->ngpio = port;
 	gc->label = chip->client->name;
+	gc->dev = &chip->client->dev;
 	gc->owner = THIS_MODULE;
 
 	return port;
@@ -684,9 +685,14 @@ static int max732x_probe(struct i2c_client *client,
 
 	mutex_init(&chip->lock);
 
-	max732x_readb(chip, is_group_a(chip, 0), &chip->reg_out[0]);
-	if (nr_port > 8)
-		max732x_readb(chip, is_group_a(chip, 8), &chip->reg_out[1]);
+	ret = max732x_readb(chip, is_group_a(chip, 0), &chip->reg_out[0]);
+	if (ret)
+		goto out_failed;
+	if (nr_port > 8) {
+		ret = max732x_readb(chip, is_group_a(chip, 8), &chip->reg_out[1]);
+		if (ret)
+			goto out_failed;
+	}
 
 	ret = gpiochip_add(&chip->gpio_chip);
 	if (ret)
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 2fc7ff852d16..73db7ecd7ffd 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -507,11 +507,7 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp)
 		irq_set_chip_data(irq, mcp);
 		irq_set_chip(irq, &mcp23s08_irq_chip);
 		irq_set_nested_thread(irq, true);
-#ifdef CONFIG_ARM
-		set_irq_flags(irq, IRQF_VALID);
-#else
 		irq_set_noprobe(irq);
-#endif
 	}
 	return 0;
 }
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 20aa66f34f6e..8ef7a12de983 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -32,7 +32,7 @@
 
 struct mpc8xxx_gpio_chip {
 	struct of_mm_gpio_chip mm_gc;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 
 	/*
 	 * shadowed data register to be able to clear/set output pins in
@@ -95,7 +95,7 @@ static void mpc8xxx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
 	unsigned long flags;
 
-	spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+	raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 
 	if (val)
 		mpc8xxx_gc->data |= mpc8xxx_gpio2mask(gpio);
@@ -104,7 +104,7 @@ static void mpc8xxx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 
 	out_be32(mm->regs + GPIO_DAT, mpc8xxx_gc->data);
 
-	spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+	raw_spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 }
 
 static void mpc8xxx_gpio_set_multiple(struct gpio_chip *gc,
@@ -115,7 +115,7 @@ static void mpc8xxx_gpio_set_multiple(struct gpio_chip *gc,
 	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+	raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 
 	for (i = 0; i < gc->ngpio; i++) {
 		if (*mask == 0)
@@ -130,7 +130,7 @@ static void mpc8xxx_gpio_set_multiple(struct gpio_chip *gc,
 
 	out_be32(mm->regs + GPIO_DAT, mpc8xxx_gc->data);
 
-	spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+	raw_spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 }
 
 static int mpc8xxx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -139,11 +139,11 @@ static int mpc8xxx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
 	unsigned long flags;
 
-	spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+	raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 
 	clrbits32(mm->regs + GPIO_DIR, mpc8xxx_gpio2mask(gpio));
 
-	spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+	raw_spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 
 	return 0;
 }
@@ -156,11 +156,11 @@ static int mpc8xxx_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val
 
 	mpc8xxx_gpio_set(gc, gpio, val);
 
-	spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+	raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 
 	setbits32(mm->regs + GPIO_DIR, mpc8xxx_gpio2mask(gpio));
 
-	spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+	raw_spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 
 	return 0;
 }
@@ -174,6 +174,15 @@ static int mpc5121_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val
 	return mpc8xxx_gpio_dir_out(gc, gpio, val);